From 9da5d7e90ff4070ae0f5ab0dea5e190b5270154c Mon Sep 17 00:00:00 2001 From: Michael Jerris Date: Tue, 19 Dec 2006 19:54:26 +0000 Subject: [PATCH] add pcre to in tree libs git-svn-id: http://svn.freeswitch.org/svn/freeswitch/trunk@3732 d0543943-73ff-0310-b7d9-9358b9ac24b2 --- libs/pcre/AUTHORS | 23 + libs/pcre/COPYING | 68 + libs/pcre/ChangeLog | 2279 ++ libs/pcre/INSTALL | 185 + libs/pcre/LICENCE | 68 + libs/pcre/Makefile.in | 606 + libs/pcre/NEWS | 266 + libs/pcre/NON-UNIX-USE | 269 + libs/pcre/README | 528 + libs/pcre/RunGrepTest.in | 208 + libs/pcre/RunTest.in | 258 + libs/pcre/config.guess | 1495 ++ libs/pcre/config.h.in | 143 + libs/pcre/config.sub | 1627 ++ libs/pcre/configure | 21093 ++++++++++++++++ libs/pcre/configure.ac | 302 + libs/pcre/dftables.c | 172 + libs/pcre/doc/Tech.Notes | 348 + libs/pcre/doc/html/index.html | 128 + libs/pcre/doc/html/pcre.html | 252 + libs/pcre/doc/html/pcre_compile.html | 80 + libs/pcre/doc/html/pcre_compile2.html | 85 + libs/pcre/doc/html/pcre_config.html | 62 + .../doc/html/pcre_copy_named_substring.html | 53 + libs/pcre/doc/html/pcre_copy_substring.html | 51 + libs/pcre/doc/html/pcre_dfa_exec.html | 93 + libs/pcre/doc/html/pcre_exec.html | 84 + libs/pcre/doc/html/pcre_free_substring.html | 40 + .../doc/html/pcre_free_substring_list.html | 40 + libs/pcre/doc/html/pcre_fullinfo.html | 71 + .../doc/html/pcre_get_named_substring.html | 54 + libs/pcre/doc/html/pcre_get_stringnumber.html | 46 + .../html/pcre_get_stringtable_entries.html | 52 + libs/pcre/doc/html/pcre_get_substring.html | 52 + .../doc/html/pcre_get_substring_list.html | 51 + libs/pcre/doc/html/pcre_info.html | 39 + libs/pcre/doc/html/pcre_maketables.html | 42 + libs/pcre/doc/html/pcre_refcount.html | 45 + libs/pcre/doc/html/pcre_study.html | 56 + libs/pcre/doc/html/pcre_version.html | 39 + libs/pcre/doc/html/pcreapi.html | 1770 ++ libs/pcre/doc/html/pcrebuild.html | 225 + libs/pcre/doc/html/pcrecallout.html | 186 + libs/pcre/doc/html/pcrecompat.html | 156 + libs/pcre/doc/html/pcrecpp.html | 337 + libs/pcre/doc/html/pcregrep.html | 424 + libs/pcre/doc/html/pcrematching.html | 192 + libs/pcre/doc/html/pcrepartial.html | 225 + libs/pcre/doc/html/pcrepattern.html | 1661 ++ libs/pcre/doc/html/pcreperform.html | 97 + libs/pcre/doc/html/pcreposix.html | 244 + libs/pcre/doc/html/pcreprecompile.html | 140 + libs/pcre/doc/html/pcresample.html | 81 + libs/pcre/doc/html/pcrestack.html | 127 + libs/pcre/doc/html/pcretest.html | 616 + libs/pcre/doc/pcre.3 | 244 + libs/pcre/doc/pcre.txt | 5153 ++++ libs/pcre/doc/pcre_compile.3 | 69 + libs/pcre/doc/pcre_compile2.3 | 74 + libs/pcre/doc/pcre_config.3 | 50 + libs/pcre/doc/pcre_copy_named_substring.3 | 44 + libs/pcre/doc/pcre_copy_substring.3 | 41 + libs/pcre/doc/pcre_dfa_exec.3 | 85 + libs/pcre/doc/pcre_exec.3 | 73 + libs/pcre/doc/pcre_free_substring.3 | 28 + libs/pcre/doc/pcre_free_substring_list.3 | 28 + libs/pcre/doc/pcre_fullinfo.3 | 59 + libs/pcre/doc/pcre_get_named_substring.3 | 45 + libs/pcre/doc/pcre_get_stringnumber.3 | 35 + libs/pcre/doc/pcre_get_stringtable_entries.3 | 41 + libs/pcre/doc/pcre_get_substring.3 | 42 + libs/pcre/doc/pcre_get_substring_list.3 | 40 + libs/pcre/doc/pcre_info.3 | 27 + libs/pcre/doc/pcre_maketables.3 | 30 + libs/pcre/doc/pcre_refcount.3 | 33 + libs/pcre/doc/pcre_study.3 | 43 + libs/pcre/doc/pcre_version.3 | 27 + libs/pcre/doc/pcreapi.3 | 1789 ++ libs/pcre/doc/pcrebuild.3 | 213 + libs/pcre/doc/pcrecallout.3 | 161 + libs/pcre/doc/pcrecompat.3 | 126 + libs/pcre/doc/pcrecpp.3 | 312 + libs/pcre/doc/pcregrep.1 | 376 + libs/pcre/doc/pcregrep.txt | 399 + libs/pcre/doc/pcrematching.3 | 157 + libs/pcre/doc/pcrepartial.3 | 203 + libs/pcre/doc/pcrepattern.3 | 1645 ++ libs/pcre/doc/pcreperform.3 | 76 + libs/pcre/doc/pcreposix.3 | 226 + libs/pcre/doc/pcreprecompile.3 | 131 + libs/pcre/doc/pcresample.3 | 66 + libs/pcre/doc/pcrestack.3 | 115 + libs/pcre/doc/pcretest.1 | 631 + libs/pcre/doc/pcretest.txt | 569 + libs/pcre/doc/perltest.txt | 33 + libs/pcre/install-sh | 251 + libs/pcre/libpcre.def | 20 + libs/pcre/libpcre.pc.in | 12 + libs/pcre/libpcreposix.def | 25 + libs/pcre/ltmain.sh | 6971 +++++ libs/pcre/makevp.bat | 25 + libs/pcre/mkinstalldirs | 40 + libs/pcre/pcre-config.in | 66 + libs/pcre/pcre.def | 29 + libs/pcre/pcre.h | 290 + libs/pcre/pcre_compile.c | 5281 ++++ libs/pcre/pcre_config.c | 116 + libs/pcre/pcre_dfa_exec.c | 2088 ++ libs/pcre/pcre_exec.c | 3933 +++ libs/pcre/pcre_fullinfo.c | 149 + libs/pcre/pcre_get.c | 462 + libs/pcre/pcre_globals.c | 69 + libs/pcre/pcre_info.c | 89 + libs/pcre/pcre_internal.h | 950 + libs/pcre/pcre_maketables.c | 140 + libs/pcre/pcre_ord2utf8.c | 78 + libs/pcre/pcre_printint.src | 460 + libs/pcre/pcre_refcount.c | 77 + libs/pcre/pcre_scanner.cc | 173 + libs/pcre/pcre_scanner.h | 163 + libs/pcre/pcre_scanner_unittest.cc | 126 + libs/pcre/pcre_stringpiece.cc | 39 + libs/pcre/pcre_stringpiece.h.in | 172 + libs/pcre/pcre_stringpiece_unittest.cc | 145 + libs/pcre/pcre_study.c | 525 + libs/pcre/pcre_tables.c | 193 + libs/pcre/pcre_try_flipped.c | 132 + libs/pcre/pcre_ucp_searchfuncs.c | 175 + libs/pcre/pcre_valid_utf8.c | 130 + libs/pcre/pcre_version.c | 64 + libs/pcre/pcre_xclass.c | 144 + libs/pcre/pcrecpp.cc | 823 + libs/pcre/pcrecpp.h | 667 + libs/pcre/pcrecpp_unittest.cc | 1116 + libs/pcre/pcrecpparg.h.in | 171 + libs/pcre/pcredemo.c | 324 + libs/pcre/pcregrep.c | 1758 ++ libs/pcre/pcreposix.c | 315 + libs/pcre/pcreposix.h | 147 + libs/pcre/pcretest.c | 2186 ++ libs/pcre/perltest | 191 + libs/pcre/testdata/grepinput | 609 + libs/pcre/testdata/grepinputx | 48 + libs/pcre/testdata/greplist | 7 + libs/pcre/testdata/grepoutput | 417 + libs/pcre/testdata/testinput1 | 3886 +++ libs/pcre/testdata/testinput2 | 1646 ++ libs/pcre/testdata/testinput3 | 91 + libs/pcre/testdata/testinput4 | 523 + libs/pcre/testdata/testinput5 | 274 + libs/pcre/testdata/testinput6 | 750 + libs/pcre/testdata/testinput7 | 4117 +++ libs/pcre/testdata/testinput8 | 540 + libs/pcre/testdata/testinput9 | 816 + libs/pcre/testdata/testoutput1 | 6356 +++++ libs/pcre/testdata/testoutput2 | 6554 +++++ libs/pcre/testdata/testoutput3 | 163 + libs/pcre/testdata/testoutput4 | 917 + libs/pcre/testdata/testoutput5 | 1123 + libs/pcre/testdata/testoutput6 | 1413 ++ libs/pcre/testdata/testoutput7 | 6731 +++++ libs/pcre/testdata/testoutput8 | 1031 + libs/pcre/testdata/testoutput9 | 1627 ++ libs/pcre/ucp.h | 126 + libs/pcre/ucpinternal.h | 87 + libs/pcre/ucptable.c | 2968 +++ 166 files changed, 125793 insertions(+) create mode 100644 libs/pcre/AUTHORS create mode 100644 libs/pcre/COPYING create mode 100644 libs/pcre/ChangeLog create mode 100644 libs/pcre/INSTALL create mode 100644 libs/pcre/LICENCE create mode 100644 libs/pcre/Makefile.in create mode 100644 libs/pcre/NEWS create mode 100644 libs/pcre/NON-UNIX-USE create mode 100644 libs/pcre/README create mode 100644 libs/pcre/RunGrepTest.in create mode 100755 libs/pcre/RunTest.in create mode 100755 libs/pcre/config.guess create mode 100644 libs/pcre/config.h.in create mode 100755 libs/pcre/config.sub create mode 100755 libs/pcre/configure create mode 100644 libs/pcre/configure.ac create mode 100644 libs/pcre/dftables.c create mode 100644 libs/pcre/doc/Tech.Notes create mode 100644 libs/pcre/doc/html/index.html create mode 100644 libs/pcre/doc/html/pcre.html create mode 100644 libs/pcre/doc/html/pcre_compile.html create mode 100644 libs/pcre/doc/html/pcre_compile2.html create mode 100644 libs/pcre/doc/html/pcre_config.html create mode 100644 libs/pcre/doc/html/pcre_copy_named_substring.html create mode 100644 libs/pcre/doc/html/pcre_copy_substring.html create mode 100644 libs/pcre/doc/html/pcre_dfa_exec.html create mode 100644 libs/pcre/doc/html/pcre_exec.html create mode 100644 libs/pcre/doc/html/pcre_free_substring.html create mode 100644 libs/pcre/doc/html/pcre_free_substring_list.html create mode 100644 libs/pcre/doc/html/pcre_fullinfo.html create mode 100644 libs/pcre/doc/html/pcre_get_named_substring.html create mode 100644 libs/pcre/doc/html/pcre_get_stringnumber.html create mode 100644 libs/pcre/doc/html/pcre_get_stringtable_entries.html create mode 100644 libs/pcre/doc/html/pcre_get_substring.html create mode 100644 libs/pcre/doc/html/pcre_get_substring_list.html create mode 100644 libs/pcre/doc/html/pcre_info.html create mode 100644 libs/pcre/doc/html/pcre_maketables.html create mode 100644 libs/pcre/doc/html/pcre_refcount.html create mode 100644 libs/pcre/doc/html/pcre_study.html create mode 100644 libs/pcre/doc/html/pcre_version.html create mode 100644 libs/pcre/doc/html/pcreapi.html create mode 100644 libs/pcre/doc/html/pcrebuild.html create mode 100644 libs/pcre/doc/html/pcrecallout.html create mode 100644 libs/pcre/doc/html/pcrecompat.html create mode 100644 libs/pcre/doc/html/pcrecpp.html create mode 100644 libs/pcre/doc/html/pcregrep.html create mode 100644 libs/pcre/doc/html/pcrematching.html create mode 100644 libs/pcre/doc/html/pcrepartial.html create mode 100644 libs/pcre/doc/html/pcrepattern.html create mode 100644 libs/pcre/doc/html/pcreperform.html create mode 100644 libs/pcre/doc/html/pcreposix.html create mode 100644 libs/pcre/doc/html/pcreprecompile.html create mode 100644 libs/pcre/doc/html/pcresample.html create mode 100644 libs/pcre/doc/html/pcrestack.html create mode 100644 libs/pcre/doc/html/pcretest.html create mode 100644 libs/pcre/doc/pcre.3 create mode 100644 libs/pcre/doc/pcre.txt create mode 100644 libs/pcre/doc/pcre_compile.3 create mode 100644 libs/pcre/doc/pcre_compile2.3 create mode 100644 libs/pcre/doc/pcre_config.3 create mode 100644 libs/pcre/doc/pcre_copy_named_substring.3 create mode 100644 libs/pcre/doc/pcre_copy_substring.3 create mode 100644 libs/pcre/doc/pcre_dfa_exec.3 create mode 100644 libs/pcre/doc/pcre_exec.3 create mode 100644 libs/pcre/doc/pcre_free_substring.3 create mode 100644 libs/pcre/doc/pcre_free_substring_list.3 create mode 100644 libs/pcre/doc/pcre_fullinfo.3 create mode 100644 libs/pcre/doc/pcre_get_named_substring.3 create mode 100644 libs/pcre/doc/pcre_get_stringnumber.3 create mode 100644 libs/pcre/doc/pcre_get_stringtable_entries.3 create mode 100644 libs/pcre/doc/pcre_get_substring.3 create mode 100644 libs/pcre/doc/pcre_get_substring_list.3 create mode 100644 libs/pcre/doc/pcre_info.3 create mode 100644 libs/pcre/doc/pcre_maketables.3 create mode 100644 libs/pcre/doc/pcre_refcount.3 create mode 100644 libs/pcre/doc/pcre_study.3 create mode 100644 libs/pcre/doc/pcre_version.3 create mode 100644 libs/pcre/doc/pcreapi.3 create mode 100644 libs/pcre/doc/pcrebuild.3 create mode 100644 libs/pcre/doc/pcrecallout.3 create mode 100644 libs/pcre/doc/pcrecompat.3 create mode 100644 libs/pcre/doc/pcrecpp.3 create mode 100644 libs/pcre/doc/pcregrep.1 create mode 100644 libs/pcre/doc/pcregrep.txt create mode 100644 libs/pcre/doc/pcrematching.3 create mode 100644 libs/pcre/doc/pcrepartial.3 create mode 100644 libs/pcre/doc/pcrepattern.3 create mode 100644 libs/pcre/doc/pcreperform.3 create mode 100644 libs/pcre/doc/pcreposix.3 create mode 100644 libs/pcre/doc/pcreprecompile.3 create mode 100644 libs/pcre/doc/pcresample.3 create mode 100644 libs/pcre/doc/pcrestack.3 create mode 100644 libs/pcre/doc/pcretest.1 create mode 100644 libs/pcre/doc/pcretest.txt create mode 100644 libs/pcre/doc/perltest.txt create mode 100755 libs/pcre/install-sh create mode 100644 libs/pcre/libpcre.def create mode 100644 libs/pcre/libpcre.pc.in create mode 100644 libs/pcre/libpcreposix.def create mode 100644 libs/pcre/ltmain.sh create mode 100644 libs/pcre/makevp.bat create mode 100755 libs/pcre/mkinstalldirs create mode 100644 libs/pcre/pcre-config.in create mode 100644 libs/pcre/pcre.def create mode 100644 libs/pcre/pcre.h create mode 100644 libs/pcre/pcre_compile.c create mode 100644 libs/pcre/pcre_config.c create mode 100644 libs/pcre/pcre_dfa_exec.c create mode 100644 libs/pcre/pcre_exec.c create mode 100644 libs/pcre/pcre_fullinfo.c create mode 100644 libs/pcre/pcre_get.c create mode 100644 libs/pcre/pcre_globals.c create mode 100644 libs/pcre/pcre_info.c create mode 100644 libs/pcre/pcre_internal.h create mode 100644 libs/pcre/pcre_maketables.c create mode 100644 libs/pcre/pcre_ord2utf8.c create mode 100644 libs/pcre/pcre_printint.src create mode 100644 libs/pcre/pcre_refcount.c create mode 100644 libs/pcre/pcre_scanner.cc create mode 100644 libs/pcre/pcre_scanner.h create mode 100644 libs/pcre/pcre_scanner_unittest.cc create mode 100644 libs/pcre/pcre_stringpiece.cc create mode 100644 libs/pcre/pcre_stringpiece.h.in create mode 100644 libs/pcre/pcre_stringpiece_unittest.cc create mode 100644 libs/pcre/pcre_study.c create mode 100644 libs/pcre/pcre_tables.c create mode 100644 libs/pcre/pcre_try_flipped.c create mode 100644 libs/pcre/pcre_ucp_searchfuncs.c create mode 100644 libs/pcre/pcre_valid_utf8.c create mode 100644 libs/pcre/pcre_version.c create mode 100644 libs/pcre/pcre_xclass.c create mode 100644 libs/pcre/pcrecpp.cc create mode 100644 libs/pcre/pcrecpp.h create mode 100644 libs/pcre/pcrecpp_unittest.cc create mode 100644 libs/pcre/pcrecpparg.h.in create mode 100644 libs/pcre/pcredemo.c create mode 100644 libs/pcre/pcregrep.c create mode 100644 libs/pcre/pcreposix.c create mode 100644 libs/pcre/pcreposix.h create mode 100644 libs/pcre/pcretest.c create mode 100755 libs/pcre/perltest create mode 100644 libs/pcre/testdata/grepinput create mode 100644 libs/pcre/testdata/grepinputx create mode 100644 libs/pcre/testdata/greplist create mode 100644 libs/pcre/testdata/grepoutput create mode 100644 libs/pcre/testdata/testinput1 create mode 100644 libs/pcre/testdata/testinput2 create mode 100644 libs/pcre/testdata/testinput3 create mode 100644 libs/pcre/testdata/testinput4 create mode 100644 libs/pcre/testdata/testinput5 create mode 100644 libs/pcre/testdata/testinput6 create mode 100644 libs/pcre/testdata/testinput7 create mode 100644 libs/pcre/testdata/testinput8 create mode 100644 libs/pcre/testdata/testinput9 create mode 100644 libs/pcre/testdata/testoutput1 create mode 100644 libs/pcre/testdata/testoutput2 create mode 100644 libs/pcre/testdata/testoutput3 create mode 100644 libs/pcre/testdata/testoutput4 create mode 100644 libs/pcre/testdata/testoutput5 create mode 100644 libs/pcre/testdata/testoutput6 create mode 100644 libs/pcre/testdata/testoutput7 create mode 100644 libs/pcre/testdata/testoutput8 create mode 100644 libs/pcre/testdata/testoutput9 create mode 100644 libs/pcre/ucp.h create mode 100644 libs/pcre/ucpinternal.h create mode 100644 libs/pcre/ucptable.c diff --git a/libs/pcre/AUTHORS b/libs/pcre/AUTHORS new file mode 100644 index 0000000000..adb4fc4019 --- /dev/null +++ b/libs/pcre/AUTHORS @@ -0,0 +1,23 @@ +THE MAIN PCRE LIBRARY +--------------------- + +Written by: Philip Hazel +Email local part: ph10 +Email domain: cam.ac.uk + +University of Cambridge Computing Service, +Cambridge, England. Phone: +44 1223 334714. + +Copyright (c) 1997-2006 University of Cambridge +All rights reserved + + +THE C++ WRAPPER LIBRARY +----------------------- + +Written by: Google Inc. + +Copyright (c) 2006 Google Inc +All rights reserved + +#### diff --git a/libs/pcre/COPYING b/libs/pcre/COPYING new file mode 100644 index 0000000000..daea2e48a3 --- /dev/null +++ b/libs/pcre/COPYING @@ -0,0 +1,68 @@ +PCRE LICENCE +------------ + +PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + +Release 6 of PCRE is distributed under the terms of the "BSD" licence, as +specified below. The documentation for PCRE, supplied in the "doc" +directory, is distributed under the same terms as the software itself. + +The basic library functions are written in C and are freestanding. Also +included in the distribution is a set of C++ wrapper functions. + + +THE BASIC LIBRARY FUNCTIONS +--------------------------- + +Written by: Philip Hazel +Email local part: ph10 +Email domain: cam.ac.uk + +University of Cambridge Computing Service, +Cambridge, England. Phone: +44 1223 334714. + +Copyright (c) 1997-2006 University of Cambridge +All rights reserved. + + +THE C++ WRAPPER FUNCTIONS +------------------------- + +Contributed by: Google Inc. + +Copyright (c) 2006, Google Inc. +All rights reserved. + + +THE "BSD" LICENCE +----------------- + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the name of Google + Inc. nor the names of their contributors may be used to endorse or + promote products derived from this software without specific prior + written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. + +End diff --git a/libs/pcre/ChangeLog b/libs/pcre/ChangeLog new file mode 100644 index 0000000000..2a14134848 --- /dev/null +++ b/libs/pcre/ChangeLog @@ -0,0 +1,2279 @@ +ChangeLog for PCRE +------------------ + +Version 6.7 04-Jul-06 +--------------------- + + 1. In order to handle tests when input lines are enormously long, pcretest has + been re-factored so that it automatically extends its buffers when + necessary. The code is crude, but this _is_ just a test program. The + default size has been increased from 32K to 50K. + + 2. The code in pcre_study() was using the value of the re argument before + testing it for NULL. (Of course, in any sensible call of the function, it + won't be NULL.) + + 3. The memmove() emulation function in pcre_internal.h, which is used on + systems that lack both memmove() and bcopy() - that is, hardly ever - + was missing a "static" storage class specifier. + + 4. When UTF-8 mode was not set, PCRE looped when compiling certain patterns + containing an extended class (one that cannot be represented by a bitmap + because it contains high-valued characters or Unicode property items, e.g. + [\pZ]). Almost always one would set UTF-8 mode when processing such a + pattern, but PCRE should not loop if you do not (it no longer does). + [Detail: two cases were found: (a) a repeated subpattern containing an + extended class; (b) a recursive reference to a subpattern that followed a + previous extended class. It wasn't skipping over the extended class + correctly when UTF-8 mode was not set.] + + 5. A negated single-character class was not being recognized as fixed-length + in lookbehind assertions such as (?<=[^f]), leading to an incorrect + compile error "lookbehind assertion is not fixed length". + + 6. The RunPerlTest auxiliary script was showing an unexpected difference + between PCRE and Perl for UTF-8 tests. It turns out that it is hard to + write a Perl script that can interpret lines of an input file either as + byte characters or as UTF-8, which is what "perltest" was being required to + do for the non-UTF-8 and UTF-8 tests, respectively. Essentially what you + can't do is switch easily at run time between having the "use utf8;" pragma + or not. In the end, I fudged it by using the RunPerlTest script to insert + "use utf8;" explicitly for the UTF-8 tests. + + 7. In multiline (/m) mode, PCRE was matching ^ after a terminating newline at + the end of the subject string, contrary to the documentation and to what + Perl does. This was true of both matching functions. Now it matches only at + the start of the subject and immediately after *internal* newlines. + + 8. A call of pcre_fullinfo() from pcretest to get the option bits was passing + a pointer to an int instead of a pointer to an unsigned long int. This + caused problems on 64-bit systems. + + 9. Applied a patch from the folks at Google to pcrecpp.cc, to fix "another + instance of the 'standard' template library not being so standard". + +10. There was no check on the number of named subpatterns nor the maximum + length of a subpattern name. The product of these values is used to compute + the size of the memory block for a compiled pattern. By supplying a very + long subpattern name and a large number of named subpatterns, the size + computation could be caused to overflow. This is now prevented by limiting + the length of names to 32 characters, and the number of named subpatterns + to 10,000. + +11. Subpatterns that are repeated with specific counts have to be replicated in + the compiled pattern. The size of memory for this was computed from the + length of the subpattern and the repeat count. The latter is limited to + 65535, but there was no limit on the former, meaning that integer overflow + could in principle occur. The compiled length of a repeated subpattern is + now limited to 30,000 bytes in order to prevent this. + +12. Added the optional facility to have named substrings with the same name. + +13. Added the ability to use a named substring as a condition, using the + Python syntax: (?(name)yes|no). This overloads (?(R)... and names that + are numbers (not recommended). Forward references are permitted. + +14. Added forward references in named backreferences (if you see what I mean). + +15. In UTF-8 mode, with the PCRE_DOTALL option set, a quantified dot in the + pattern could run off the end of the subject. For example, the pattern + "(?s)(.{1,5})"8 did this with the subject "ab". + +16. If PCRE_DOTALL or PCRE_MULTILINE were set, pcre_dfa_exec() behaved as if + PCRE_CASELESS was set when matching characters that were quantified with ? + or *. + +17. A character class other than a single negated character that had a minimum + but no maximum quantifier - for example [ab]{6,} - was not handled + correctly by pce_dfa_exec(). It would match only one character. + +18. A valid (though odd) pattern that looked like a POSIX character + class but used an invalid character after [ (for example [[,abc,]]) caused + pcre_compile() to give the error "Failed: internal error: code overflow" or + in some cases to crash with a glibc free() error. This could even happen if + the pattern terminated after [[ but there just happened to be a sequence of + letters, a binary zero, and a closing ] in the memory that followed. + +19. Perl's treatment of octal escapes in the range \400 to \777 has changed + over the years. Originally (before any Unicode support), just the bottom 8 + bits were taken. Thus, for example, \500 really meant \100. Nowadays the + output from "man perlunicode" includes this: + + The regular expression compiler produces polymorphic opcodes. That + is, the pattern adapts to the data and automatically switches to + the Unicode character scheme when presented with Unicode data--or + instead uses a traditional byte scheme when presented with byte + data. + + Sadly, a wide octal escape does not cause a switch, and in a string with + no other multibyte characters, these octal escapes are treated as before. + Thus, in Perl, the pattern /\500/ actually matches \100 but the pattern + /\500|\x{1ff}/ matches \500 or \777 because the whole thing is treated as a + Unicode string. + + I have not perpetrated such confusion in PCRE. Up till now, it took just + the bottom 8 bits, as in old Perl. I have now made octal escapes with + values greater than \377 illegal in non-UTF-8 mode. In UTF-8 mode they + translate to the appropriate multibyte character. + +29. Applied some refactoring to reduce the number of warnings from Microsoft + and Borland compilers. This has included removing the fudge introduced + seven years ago for the OS/2 compiler (see 2.02/2 below) because it caused + a warning about an unused variable. + +21. PCRE has not included VT (character 0x0b) in the set of whitespace + characters since release 4.0, because Perl (from release 5.004) does not. + [Or at least, is documented not to: some releases seem to be in conflict + with the documentation.] However, when a pattern was studied with + pcre_study() and all its branches started with \s, PCRE still included VT + as a possible starting character. Of course, this did no harm; it just + caused an unnecessary match attempt. + +22. Removed a now-redundant internal flag bit that recorded the fact that case + dependency changed within the pattern. This was once needed for "required + byte" processing, but is no longer used. This recovers a now-scarce options + bit. Also moved the least significant internal flag bit to the most- + significant bit of the word, which was not previously used (hangover from + the days when it was an int rather than a uint) to free up another bit for + the future. + +23. Added support for CRLF line endings as well as CR and LF. As well as the + default being selectable at build time, it can now be changed at runtime + via the PCRE_NEWLINE_xxx flags. There are now options for pcregrep to + specify that it is scanning data with non-default line endings. + +24. Changed the definition of CXXLINK to make it agree with the definition of + LINK in the Makefile, by replacing LDFLAGS to CXXFLAGS. + +25. Applied Ian Taylor's patches to avoid using another stack frame for tail + recursions. This makes a big different to stack usage for some patterns. + +26. If a subpattern containing a named recursion or subroutine reference such + as (?P>B) was quantified, for example (xxx(?P>B)){3}, the calculation of + the space required for the compiled pattern went wrong and gave too small a + value. Depending on the environment, this could lead to "Failed: internal + error: code overflow at offset 49" or "glibc detected double free or + corruption" errors. + +27. Applied patches from Google (a) to support the new newline modes and (b) to + advance over multibyte UTF-8 characters in GlobalReplace. + +28. Change free() to pcre_free() in pcredemo.c. Apparently this makes a + difference for some implementation of PCRE in some Windows version. + +29. Added some extra testing facilities to pcretest: + + \q in a data line sets the "match limit" value + \Q in a data line sets the "match recursion limt" value + -S sets the stack size, where is in megabytes + + The -S option isn't available for Windows. + + +Version 6.6 06-Feb-06 +--------------------- + + 1. Change 16(a) for 6.5 broke things, because PCRE_DATA_SCOPE was not defined + in pcreposix.h. I have copied the definition from pcre.h. + + 2. Change 25 for 6.5 broke compilation in a build directory out-of-tree + because pcre.h is no longer a built file. + + 3. Added Jeff Friedl's additional debugging patches to pcregrep. These are + not normally included in the compiled code. + + +Version 6.5 01-Feb-06 +--------------------- + + 1. When using the partial match feature with pcre_dfa_exec(), it was not + anchoring the second and subsequent partial matches at the new starting + point. This could lead to incorrect results. For example, with the pattern + /1234/, partially matching against "123" and then "a4" gave a match. + + 2. Changes to pcregrep: + + (a) All non-match returns from pcre_exec() were being treated as failures + to match the line. Now, unless the error is PCRE_ERROR_NOMATCH, an + error message is output. Some extra information is given for the + PCRE_ERROR_MATCHLIMIT and PCRE_ERROR_RECURSIONLIMIT errors, which are + probably the only errors that are likely to be caused by users (by + specifying a regex that has nested indefinite repeats, for instance). + If there are more than 20 of these errors, pcregrep is abandoned. + + (b) A binary zero was treated as data while matching, but terminated the + output line if it was written out. This has been fixed: binary zeroes + are now no different to any other data bytes. + + (c) Whichever of the LC_ALL or LC_CTYPE environment variables is set is + used to set a locale for matching. The --locale=xxxx long option has + been added (no short equivalent) to specify a locale explicitly on the + pcregrep command, overriding the environment variables. + + (d) When -B was used with -n, some line numbers in the output were one less + than they should have been. + + (e) Added the -o (--only-matching) option. + + (f) If -A or -C was used with -c (count only), some lines of context were + accidentally printed for the final match. + + (g) Added the -H (--with-filename) option. + + (h) The combination of options -rh failed to suppress file names for files + that were found from directory arguments. + + (i) Added the -D (--devices) and -d (--directories) options. + + (j) Added the -F (--fixed-strings) option. + + (k) Allow "-" to be used as a file name for -f as well as for a data file. + + (l) Added the --colo(u)r option. + + (m) Added Jeffrey Friedl's -S testing option, but within #ifdefs so that it + is not present by default. + + 3. A nasty bug was discovered in the handling of recursive patterns, that is, + items such as (?R) or (?1), when the recursion could match a number of + alternatives. If it matched one of the alternatives, but subsequently, + outside the recursion, there was a failure, the code tried to back up into + the recursion. However, because of the way PCRE is implemented, this is not + possible, and the result was an incorrect result from the match. + + In order to prevent this happening, the specification of recursion has + been changed so that all such subpatterns are automatically treated as + atomic groups. Thus, for example, (?R) is treated as if it were (?>(?R)). + + 4. I had overlooked the fact that, in some locales, there are characters for + which isalpha() is true but neither isupper() nor islower() are true. In + the fr_FR locale, for instance, the \xAA and \xBA characters (ordmasculine + and ordfeminine) are like this. This affected the treatment of \w and \W + when they appeared in character classes, but not when they appeared outside + a character class. The bit map for "word" characters is now created + separately from the results of isalnum() instead of just taking it from the + upper, lower, and digit maps. (Plus the underscore character, of course.) + + 5. The above bug also affected the handling of POSIX character classes such as + [[:alpha:]] and [[:alnum:]]. These do not have their own bit maps in PCRE's + permanent tables. Instead, the bit maps for such a class were previously + created as the appropriate unions of the upper, lower, and digit bitmaps. + Now they are created by subtraction from the [[:word:]] class, which has + its own bitmap. + + 6. The [[:blank:]] character class matches horizontal, but not vertical space. + It is created by subtracting the vertical space characters (\x09, \x0a, + \x0b, \x0c) from the [[:space:]] bitmap. Previously, however, the + subtraction was done in the overall bitmap for a character class, meaning + that a class such as [\x0c[:blank:]] was incorrect because \x0c would not + be recognized. This bug has been fixed. + + 7. Patches from the folks at Google: + + (a) pcrecpp.cc: "to handle a corner case that may or may not happen in + real life, but is still worth protecting against". + + (b) pcrecpp.cc: "corrects a bug when negative radixes are used with + regular expressions". + + (c) pcre_scanner.cc: avoid use of std::count() because not all systems + have it. + + (d) Split off pcrecpparg.h from pcrecpp.h and had the former built by + "configure" and the latter not, in order to fix a problem somebody had + with compiling the Arg class on HP-UX. + + (e) Improve the error-handling of the C++ wrapper a little bit. + + (f) New tests for checking recursion limiting. + + 8. The pcre_memmove() function, which is used only if the environment does not + have a standard memmove() function (and is therefore rarely compiled), + contained two bugs: (a) use of int instead of size_t, and (b) it was not + returning a result (though PCRE never actually uses the result). + + 9. In the POSIX regexec() interface, if nmatch is specified as a ridiculously + large number - greater than INT_MAX/(3*sizeof(int)) - REG_ESPACE is + returned instead of calling malloc() with an overflowing number that would + most likely cause subsequent chaos. + +10. The debugging option of pcretest was not showing the NO_AUTO_CAPTURE flag. + +11. The POSIX flag REG_NOSUB is now supported. When a pattern that was compiled + with this option is matched, the nmatch and pmatch options of regexec() are + ignored. + +12. Added REG_UTF8 to the POSIX interface. This is not defined by POSIX, but is + provided in case anyone wants to the the POSIX interface with UTF-8 + strings. + +13. Added CXXLDFLAGS to the Makefile parameters to provide settings only on the + C++ linking (needed for some HP-UX environments). + +14. Avoid compiler warnings in get_ucpname() when compiled without UCP support + (unused parameter) and in the pcre_printint() function (omitted "default" + switch label when the default is to do nothing). + +15. Added some code to make it possible, when PCRE is compiled as a C++ + library, to replace subject pointers for pcre_exec() with a smart pointer + class, thus making it possible to process discontinuous strings. + +16. The two macros PCRE_EXPORT and PCRE_DATA_SCOPE are confusing, and perform + much the same function. They were added by different people who were trying + to make PCRE easy to compile on non-Unix systems. It has been suggested + that PCRE_EXPORT be abolished now that there is more automatic apparatus + for compiling on Windows systems. I have therefore replaced it with + PCRE_DATA_SCOPE. This is set automatically for Windows; if not set it + defaults to "extern" for C or "extern C" for C++, which works fine on + Unix-like systems. It is now possible to override the value of PCRE_DATA_ + SCOPE with something explicit in config.h. In addition: + + (a) pcreposix.h still had just "extern" instead of either of these macros; + I have replaced it with PCRE_DATA_SCOPE. + + (b) Functions such as _pcre_xclass(), which are internal to the library, + but external in the C sense, all had PCRE_EXPORT in their definitions. + This is apparently wrong for the Windows case, so I have removed it. + (It makes no difference on Unix-like systems.) + +17. Added a new limit, MATCH_LIMIT_RECURSION, which limits the depth of nesting + of recursive calls to match(). This is different to MATCH_LIMIT because + that limits the total number of calls to match(), not all of which increase + the depth of recursion. Limiting the recursion depth limits the amount of + stack (or heap if NO_RECURSE is set) that is used. The default can be set + when PCRE is compiled, and changed at run time. A patch from Google adds + this functionality to the C++ interface. + +18. Changes to the handling of Unicode character properties: + + (a) Updated the table to Unicode 4.1.0. + + (b) Recognize characters that are not in the table as "Cn" (undefined). + + (c) I revised the way the table is implemented to a much improved format + which includes recognition of ranges. It now supports the ranges that + are defined in UnicodeData.txt, and it also amalgamates other + characters into ranges. This has reduced the number of entries in the + table from around 16,000 to around 3,000, thus reducing its size + considerably. I realized I did not need to use a tree structure after + all - a binary chop search is just as efficient. Having reduced the + number of entries, I extended their size from 6 bytes to 8 bytes to + allow for more data. + + (d) Added support for Unicode script names via properties such as \p{Han}. + +19. In UTF-8 mode, a backslash followed by a non-Ascii character was not + matching that character. + +20. When matching a repeated Unicode property with a minimum greater than zero, + (for example \pL{2,}), PCRE could look past the end of the subject if it + reached it while seeking the minimum number of characters. This could + happen only if some of the characters were more than one byte long, because + there is a check for at least the minimum number of bytes. + +21. Refactored the implementation of \p and \P so as to be more general, to + allow for more different types of property in future. This has changed the + compiled form incompatibly. Anybody with saved compiled patterns that use + \p or \P will have to recompile them. + +22. Added "Any" and "L&" to the supported property types. + +23. Recognize \x{...} as a code point specifier, even when not in UTF-8 mode, + but give a compile time error if the value is greater than 0xff. + +24. The man pages for pcrepartial, pcreprecompile, and pcre_compile2 were + accidentally not being installed or uninstalled. + +25. The pcre.h file was built from pcre.h.in, but the only changes that were + made were to insert the current release number. This seemed silly, because + it made things harder for people building PCRE on systems that don't run + "configure". I have turned pcre.h into a distributed file, no longer built + by "configure", with the version identification directly included. There is + no longer a pcre.h.in file. + + However, this change necessitated a change to the pcre-config script as + well. It is built from pcre-config.in, and one of the substitutions was the + release number. I have updated configure.ac so that ./configure now finds + the release number by grepping pcre.h. + +26. Added the ability to run the tests under valgrind. + + +Version 6.4 05-Sep-05 +--------------------- + + 1. Change 6.0/10/(l) to pcregrep introduced a bug that caused separator lines + "--" to be printed when multiple files were scanned, even when none of the + -A, -B, or -C options were used. This is not compatible with Gnu grep, so I + consider it to be a bug, and have restored the previous behaviour. + + 2. A couple of code tidies to get rid of compiler warnings. + + 3. The pcretest program used to cheat by referring to symbols in the library + whose names begin with _pcre_. These are internal symbols that are not + really supposed to be visible externally, and in some environments it is + possible to suppress them. The cheating is now confined to including + certain files from the library's source, which is a bit cleaner. + + 4. Renamed pcre.in as pcre.h.in to go with pcrecpp.h.in; it also makes the + file's purpose clearer. + + 5. Reorganized pcre_ucp_findchar(). + + +Version 6.3 15-Aug-05 +--------------------- + + 1. The file libpcre.pc.in did not have general read permission in the tarball. + + 2. There were some problems when building without C++ support: + + (a) If C++ support was not built, "make install" and "make test" still + tried to test it. + + (b) There were problems when the value of CXX was explicitly set. Some + changes have been made to try to fix these, and ... + + (c) --disable-cpp can now be used to explicitly disable C++ support. + + (d) The use of @CPP_OBJ@ directly caused a blank line preceded by a + backslash in a target when C++ was disabled. This confuses some + versions of "make", apparently. Using an intermediate variable solves + this. (Same for CPP_LOBJ.) + + 3. $(LINK_FOR_BUILD) now includes $(CFLAGS_FOR_BUILD) and $(LINK) + (non-Windows) now includes $(CFLAGS) because these flags are sometimes + necessary on certain architectures. + + 4. Added a setting of -export-symbols-regex to the link command to remove + those symbols that are exported in the C sense, but actually are local + within the library, and not documented. Their names all begin with + "_pcre_". This is not a perfect job, because (a) we have to except some + symbols that pcretest ("illegally") uses, and (b) the facility isn't always + available (and never for static libraries). I have made a note to try to + find a way round (a) in the future. + + +Version 6.2 01-Aug-05 +--------------------- + + 1. There was no test for integer overflow of quantifier values. A construction + such as {1111111111111111} would give undefined results. What is worse, if + a minimum quantifier for a parenthesized subpattern overflowed and became + negative, the calculation of the memory size went wrong. This could have + led to memory overwriting. + + 2. Building PCRE using VPATH was broken. Hopefully it is now fixed. + + 3. Added "b" to the 2nd argument of fopen() in dftables.c, for non-Unix-like + operating environments where this matters. + + 4. Applied Giuseppe Maxia's patch to add additional features for controlling + PCRE options from within the C++ wrapper. + + 5. Named capturing subpatterns were not being correctly counted when a pattern + was compiled. This caused two problems: (a) If there were more than 100 + such subpatterns, the calculation of the memory needed for the whole + compiled pattern went wrong, leading to an overflow error. (b) Numerical + back references of the form \12, where the number was greater than 9, were + not recognized as back references, even though there were sufficient + previous subpatterns. + + 6. Two minor patches to pcrecpp.cc in order to allow it to compile on older + versions of gcc, e.g. 2.95.4. + + +Version 6.1 21-Jun-05 +--------------------- + + 1. There was one reference to the variable "posix" in pcretest.c that was not + surrounded by "#if !defined NOPOSIX". + + 2. Make it possible to compile pcretest without DFA support, UTF8 support, or + the cross-check on the old pcre_info() function, for the benefit of the + cut-down version of PCRE that is currently imported into Exim. + + 3. A (silly) pattern starting with (?i)(?-i) caused an internal space + allocation error. I've done the easy fix, which wastes 2 bytes for sensible + patterns that start (?i) but I don't think that matters. The use of (?i) is + just an example; this all applies to the other options as well. + + 4. Since libtool seems to echo the compile commands it is issuing, the output + from "make" can be reduced a bit by putting "@" in front of each libtool + compile command. + + 5. Patch from the folks at Google for configure.in to be a bit more thorough + in checking for a suitable C++ installation before trying to compile the + C++ stuff. This should fix a reported problem when a compiler was present, + but no suitable headers. + + 6. The man pages all had just "PCRE" as their title. I have changed them to + be the relevant file name. I have also arranged that these names are + retained in the file doc/pcre.txt, which is a concatenation in text format + of all the man pages except the little individual ones for each function. + + 7. The NON-UNIX-USE file had not been updated for the different set of source + files that come with release 6. I also added a few comments about the C++ + wrapper. + + +Version 6.0 07-Jun-05 +--------------------- + + 1. Some minor internal re-organization to help with my DFA experiments. + + 2. Some missing #ifdef SUPPORT_UCP conditionals in pcretest and printint that + didn't matter for the library itself when fully configured, but did matter + when compiling without UCP support, or within Exim, where the ucp files are + not imported. + + 3. Refactoring of the library code to split up the various functions into + different source modules. The addition of the new DFA matching code (see + below) to a single monolithic source would have made it really too + unwieldy, quite apart from causing all the code to be include in a + statically linked application, when only some functions are used. This is + relevant even without the DFA addition now that patterns can be compiled in + one application and matched in another. + + The downside of splitting up is that there have to be some external + functions and data tables that are used internally in different modules of + the library but which are not part of the API. These have all had their + names changed to start with "_pcre_" so that they are unlikely to clash + with other external names. + + 4. Added an alternate matching function, pcre_dfa_exec(), which matches using + a different (DFA) algorithm. Although it is slower than the original + function, it does have some advantages for certain types of matching + problem. + + 5. Upgrades to pcretest in order to test the features of pcre_dfa_exec(), + including restarting after a partial match. + + 6. A patch for pcregrep that defines INVALID_FILE_ATTRIBUTES if it is not + defined when compiling for Windows was sent to me. I have put it into the + code, though I have no means of testing or verifying it. + + 7. Added the pcre_refcount() auxiliary function. + + 8. Added the PCRE_FIRSTLINE option. This constrains an unanchored pattern to + match before or at the first newline in the subject string. In pcretest, + the /f option on a pattern can be used to set this. + + 9. A repeated \w when used in UTF-8 mode with characters greater than 256 + would behave wrongly. This has been present in PCRE since release 4.0. + +10. A number of changes to the pcregrep command: + + (a) Refactored how -x works; insert ^(...)$ instead of setting + PCRE_ANCHORED and checking the length, in preparation for adding + something similar for -w. + + (b) Added the -w (match as a word) option. + + (c) Refactored the way lines are read and buffered so as to have more + than one at a time available. + + (d) Implemented a pcregrep test script. + + (e) Added the -M (multiline match) option. This allows patterns to match + over several lines of the subject. The buffering ensures that at least + 8K, or the rest of the document (whichever is the shorter) is available + for matching (and similarly the previous 8K for lookbehind assertions). + + (f) Changed the --help output so that it now says + + -w, --word-regex(p) + + instead of two lines, one with "regex" and the other with "regexp" + because that confused at least one person since the short forms are the + same. (This required a bit of code, as the output is generated + automatically from a table. It wasn't just a text change.) + + (g) -- can be used to terminate pcregrep options if the next thing isn't an + option but starts with a hyphen. Could be a pattern or a path name + starting with a hyphen, for instance. + + (h) "-" can be given as a file name to represent stdin. + + (i) When file names are being printed, "(standard input)" is used for + the standard input, for compatibility with GNU grep. Previously + "" was used. + + (j) The option --label=xxx can be used to supply a name to be used for + stdin when file names are being printed. There is no short form. + + (k) Re-factored the options decoding logic because we are going to add + two more options that take data. Such options can now be given in four + different ways, e.g. "-fname", "-f name", "--file=name", "--file name". + + (l) Added the -A, -B, and -C options for requesting that lines of context + around matches be printed. + + (m) Added the -L option to print the names of files that do not contain + any matching lines, that is, the complement of -l. + + (n) The return code is 2 if any file cannot be opened, but pcregrep does + continue to scan other files. + + (o) The -s option was incorrectly implemented. For compatibility with other + greps, it now suppresses the error message for a non-existent or non- + accessible file (but not the return code). There is a new option called + -q that suppresses the output of matching lines, which was what -s was + previously doing. + + (p) Added --include and --exclude options to specify files for inclusion + and exclusion when recursing. + +11. The Makefile was not using the Autoconf-supported LDFLAGS macro properly. + Hopefully, it now does. + +12. Missing cast in pcre_study(). + +13. Added an "uninstall" target to the makefile. + +14. Replaced "extern" in the function prototypes in Makefile.in with + "PCRE_DATA_SCOPE", which defaults to 'extern' or 'extern "C"' in the Unix + world, but is set differently for Windows. + +15. Added a second compiling function called pcre_compile2(). The only + difference is that it has an extra argument, which is a pointer to an + integer error code. When there is a compile-time failure, this is set + non-zero, in addition to the error test pointer being set to point to an + error message. The new argument may be NULL if no error number is required + (but then you may as well call pcre_compile(), which is now just a + wrapper). This facility is provided because some applications need a + numeric error indication, but it has also enabled me to tidy up the way + compile-time errors are handled in the POSIX wrapper. + +16. Added VPATH=.libs to the makefile; this should help when building with one + prefix path and installing with another. (Or so I'm told by someone who + knows more about this stuff than I do.) + +17. Added a new option, REG_DOTALL, to the POSIX function regcomp(). This + passes PCRE_DOTALL to the pcre_compile() function, making the "." character + match everything, including newlines. This is not POSIX-compatible, but + somebody wanted the feature. From pcretest it can be activated by using + both the P and the s flags. + +18. AC_PROG_LIBTOOL appeared twice in Makefile.in. Removed one. + +19. libpcre.pc was being incorrectly installed as executable. + +20. A couple of places in pcretest check for end-of-line by looking for '\n'; + it now also looks for '\r' so that it will work unmodified on Windows. + +21. Added Google's contributed C++ wrapper to the distribution. + +22. Added some untidy missing memory free() calls in pcretest, to keep + Electric Fence happy when testing. + + + +Version 5.0 13-Sep-04 +--------------------- + + 1. Internal change: literal characters are no longer packed up into items + containing multiple characters in a single byte-string. Each character + is now matched using a separate opcode. However, there may be more than one + byte in the character in UTF-8 mode. + + 2. The pcre_callout_block structure has two new fields: pattern_position and + next_item_length. These contain the offset in the pattern to the next match + item, and its length, respectively. + + 3. The PCRE_AUTO_CALLOUT option for pcre_compile() requests the automatic + insertion of callouts before each pattern item. Added the /C option to + pcretest to make use of this. + + 4. On the advice of a Windows user, the lines + + #if defined(_WIN32) || defined(WIN32) + _setmode( _fileno( stdout ), 0x8000 ); + #endif /* defined(_WIN32) || defined(WIN32) */ + + have been added to the source of pcretest. This apparently does useful + magic in relation to line terminators. + + 5. Changed "r" and "w" in the calls to fopen() in pcretest to "rb" and "wb" + for the benefit of those environments where the "b" makes a difference. + + 6. The icc compiler has the same options as gcc, but "configure" doesn't seem + to know about it. I have put a hack into configure.in that adds in code + to set GCC=yes if CC=icc. This seems to end up at a point in the + generated configure script that is early enough to affect the setting of + compiler options, which is what is needed, but I have no means of testing + whether it really works. (The user who reported this had patched the + generated configure script, which of course I cannot do.) + + LATER: After change 22 below (new libtool files), the configure script + seems to know about icc (and also ecc). Therefore, I have commented out + this hack in configure.in. + + 7. Added support for pkg-config (2 patches were sent in). + + 8. Negated POSIX character classes that used a combination of internal tables + were completely broken. These were [[:^alpha:]], [[:^alnum:]], and + [[:^ascii]]. Typically, they would match almost any characters. The other + POSIX classes were not broken in this way. + + 9. Matching the pattern "\b.*?" against "ab cd", starting at offset 1, failed + to find the match, as PCRE was deluded into thinking that the match had to + start at the start point or following a newline. The same bug applied to + patterns with negative forward assertions or any backward assertions + preceding ".*" at the start, unless the pattern required a fixed first + character. This was a failing pattern: "(?!.bcd).*". The bug is now fixed. + +10. In UTF-8 mode, when moving forwards in the subject after a failed match + starting at the last subject character, bytes beyond the end of the subject + string were read. + +11. Renamed the variable "class" as "classbits" to make life easier for C++ + users. (Previously there was a macro definition, but it apparently wasn't + enough.) + +12. Added the new field "tables" to the extra data so that tables can be passed + in at exec time, or the internal tables can be re-selected. This allows + a compiled regex to be saved and re-used at a later time by a different + program that might have everything at different addresses. + +13. Modified the pcre-config script so that, when run on Solaris, it shows a + -R library as well as a -L library. + +14. The debugging options of pcretest (-d on the command line or D on a + pattern) showed incorrect output for anything following an extended class + that contained multibyte characters and which was followed by a quantifier. + +15. Added optional support for general category Unicode character properties + via the \p, \P, and \X escapes. Unicode property support implies UTF-8 + support. It adds about 90K to the size of the library. The meanings of the + inbuilt class escapes such as \d and \s have NOT been changed. + +16. Updated pcredemo.c to include calls to free() to release the memory for the + compiled pattern. + +17. The generated file chartables.c was being created in the source directory + instead of in the building directory. This caused the build to fail if the + source directory was different from the building directory, and was + read-only. + +18. Added some sample Win commands from Mark Tetrode into the NON-UNIX-USE + file. No doubt somebody will tell me if they don't make sense... Also added + Dan Mooney's comments about building on OpenVMS. + +19. Added support for partial matching via the PCRE_PARTIAL option for + pcre_exec() and the \P data escape in pcretest. + +20. Extended pcretest with 3 new pattern features: + + (i) A pattern option of the form ">rest-of-line" causes pcretest to + write the compiled pattern to the file whose name is "rest-of-line". + This is a straight binary dump of the data, with the saved pointer to + the character tables forced to be NULL. The study data, if any, is + written too. After writing, pcretest reads a new pattern. + + (ii) If, instead of a pattern, ": new target + : new target + : use native compiler + : use native linker + : handle Windows platform correctly + : ditto + : ditto + copy DLL to top builddir before testing + + As part of these changes, -no-undefined was removed again. This was reported + to give trouble on HP-UX 11.0, so getting rid of it seems like a good idea + in any case. + +3. Some tidies to get rid of compiler warnings: + + . In the match_data structure, match_limit was an unsigned long int, whereas + match_call_count was an int. I've made them both unsigned long ints. + + . In pcretest the fact that a const uschar * doesn't automatically cast to + a void * provoked a warning. + + . Turning on some more compiler warnings threw up some "shadow" variables + and a few more missing casts. + +4. If PCRE was complied with UTF-8 support, but called without the PCRE_UTF8 + option, a class that contained a single character with a value between 128 + and 255 (e.g. /[\xFF]/) caused PCRE to crash. + +5. If PCRE was compiled with UTF-8 support, but called without the PCRE_UTF8 + option, a class that contained several characters, but with at least one + whose value was between 128 and 255 caused PCRE to crash. + + +Version 4.1 12-Mar-03 +--------------------- + +1. Compiling with gcc -pedantic found a couple of places where casts were +needed, and a string in dftables.c that was longer than standard compilers are +required to support. + +2. Compiling with Sun's compiler found a few more places where the code could +be tidied up in order to avoid warnings. + +3. The variables for cross-compiling were called HOST_CC and HOST_CFLAGS; the +first of these names is deprecated in the latest Autoconf in favour of the name +CC_FOR_BUILD, because "host" is typically used to mean the system on which the +compiled code will be run. I can't find a reference for HOST_CFLAGS, but by +analogy I have changed it to CFLAGS_FOR_BUILD. + +4. Added -no-undefined to the linking command in the Makefile, because this is +apparently helpful for Windows. To make it work, also added "-L. -lpcre" to the +linking step for the pcreposix library. + +5. PCRE was failing to diagnose the case of two named groups with the same +name. + +6. A problem with one of PCRE's optimizations was discovered. PCRE remembers a +literal character that is needed in the subject for a match, and scans along to +ensure that it is present before embarking on the full matching process. This +saves time in cases of nested unlimited repeats that are never going to match. +Problem: the scan can take a lot of time if the subject is very long (e.g. +megabytes), thus penalizing straightforward matches. It is now done only if the +amount of subject to be scanned is less than 1000 bytes. + +7. A lesser problem with the same optimization is that it was recording the +first character of an anchored pattern as "needed", thus provoking a search +right along the subject, even when the first match of the pattern was going to +fail. The "needed" character is now not set for anchored patterns, unless it +follows something in the pattern that is of non-fixed length. Thus, it still +fulfils its original purpose of finding quick non-matches in cases of nested +unlimited repeats, but isn't used for simple anchored patterns such as /^abc/. + + +Version 4.0 17-Feb-03 +--------------------- + +1. If a comment in an extended regex that started immediately after a meta-item +extended to the end of string, PCRE compiled incorrect data. This could lead to +all kinds of weird effects. Example: /#/ was bad; /()#/ was bad; /a#/ was not. + +2. Moved to autoconf 2.53 and libtool 1.4.2. + +3. Perl 5.8 no longer needs "use utf8" for doing UTF-8 things. Consequently, +the special perltest8 script is no longer needed - all the tests can be run +from a single perltest script. + +4. From 5.004, Perl has not included the VT character (0x0b) in the set defined +by \s. It has now been removed in PCRE. This means it isn't recognized as +whitespace in /x regexes too, which is the same as Perl. Note that the POSIX +class [:space:] *does* include VT, thereby creating a mess. + +5. Added the class [:blank:] (a GNU extension from Perl 5.8) to match only +space and tab. + +6. Perl 5.005 was a long time ago. It's time to amalgamate the tests that use +its new features into the main test script, reducing the number of scripts. + +7. Perl 5.8 has changed the meaning of patterns like /a(?i)b/. Earlier versions +were backward compatible, and made the (?i) apply to the whole pattern, as if +/i were given. Now it behaves more logically, and applies the option setting +only to what follows. PCRE has been changed to follow suit. However, if it +finds options settings right at the start of the pattern, it extracts them into +the global options, as before. Thus, they show up in the info data. + +8. Added support for the \Q...\E escape sequence. Characters in between are +treated as literals. This is slightly different from Perl in that $ and @ are +also handled as literals inside the quotes. In Perl, they will cause variable +interpolation. Note the following examples: + + Pattern PCRE matches Perl matches + + \Qabc$xyz\E abc$xyz abc followed by the contents of $xyz + \Qabc\$xyz\E abc\$xyz abc\$xyz + \Qabc\E\$\Qxyz\E abc$xyz abc$xyz + +For compatibility with Perl, \Q...\E sequences are recognized inside character +classes as well as outside them. + +9. Re-organized 3 code statements in pcretest to avoid "overflow in +floating-point constant arithmetic" warnings from a Microsoft compiler. Added a +(size_t) cast to one statement in pcretest and one in pcreposix to avoid +signed/unsigned warnings. + +10. SunOS4 doesn't have strtoul(). This was used only for unpicking the -o +option for pcretest, so I've replaced it by a simple function that does just +that job. + +11. pcregrep was ending with code 0 instead of 2 for the commands "pcregrep" or +"pcregrep -". + +12. Added "possessive quantifiers" ?+, *+, ++, and {,}+ which come from Sun's +Java package. This provides some syntactic sugar for simple cases of what my +documentation calls "once-only subpatterns". A pattern such as x*+ is the same +as (?>x*). In other words, if what is inside (?>...) is just a single repeated +item, you can use this simplified notation. Note that only makes sense with +greedy quantifiers. Consequently, the use of the possessive quantifier forces +greediness, whatever the setting of the PCRE_UNGREEDY option. + +13. A change of greediness default within a pattern was not taking effect at +the current level for patterns like /(b+(?U)a+)/. It did apply to parenthesized +subpatterns that followed. Patterns like /b+(?U)a+/ worked because the option +was abstracted outside. + +14. PCRE now supports the \G assertion. It is true when the current matching +position is at the start point of the match. This differs from \A when the +starting offset is non-zero. Used with the /g option of pcretest (or similar +code), it works in the same way as it does for Perl's /g option. If all +alternatives of a regex begin with \G, the expression is anchored to the start +match position, and the "anchored" flag is set in the compiled expression. + +15. Some bugs concerning the handling of certain option changes within patterns +have been fixed. These applied to options other than (?ims). For example, +"a(?x: b c )d" did not match "XabcdY" but did match "Xa b c dY". It should have +been the other way round. Some of this was related to change 7 above. + +16. PCRE now gives errors for /[.x.]/ and /[=x=]/ as unsupported POSIX +features, as Perl does. Previously, PCRE gave the warnings only for /[[.x.]]/ +and /[[=x=]]/. PCRE now also gives an error for /[:name:]/ because it supports +POSIX classes only within a class (e.g. /[[:alpha:]]/). + +17. Added support for Perl's \C escape. This matches one byte, even in UTF8 +mode. Unlike ".", it always matches newline, whatever the setting of +PCRE_DOTALL. However, PCRE does not permit \C to appear in lookbehind +assertions. Perl allows it, but it doesn't (in general) work because it can't +calculate the length of the lookbehind. At least, that's the case for Perl +5.8.0 - I've been told they are going to document that it doesn't work in +future. + +18. Added an error diagnosis for escapes that PCRE does not support: these are +\L, \l, \N, \P, \p, \U, \u, and \X. + +19. Although correctly diagnosing a missing ']' in a character class, PCRE was +reading past the end of the pattern in cases such as /[abcd/. + +20. PCRE was getting more memory than necessary for patterns with classes that +contained both POSIX named classes and other characters, e.g. /[[:space:]abc/. + +21. Added some code, conditional on #ifdef VPCOMPAT, to make life easier for +compiling PCRE for use with Virtual Pascal. + +22. Small fix to the Makefile to make it work properly if the build is done +outside the source tree. + +23. Added a new extension: a condition to go with recursion. If a conditional +subpattern starts with (?(R) the "true" branch is used if recursion has +happened, whereas the "false" branch is used only at the top level. + +24. When there was a very long string of literal characters (over 255 bytes +without UTF support, over 250 bytes with UTF support), the computation of how +much memory was required could be incorrect, leading to segfaults or other +strange effects. + +25. PCRE was incorrectly assuming anchoring (either to start of subject or to +start of line for a non-DOTALL pattern) when a pattern started with (.*) and +there was a subsequent back reference to those brackets. This meant that, for +example, /(.*)\d+\1/ failed to match "abc123bc". Unfortunately, it isn't +possible to check for precisely this case. All we can do is abandon the +optimization if .* occurs inside capturing brackets when there are any back +references whatsoever. (See below for a better fix that came later.) + +26. The handling of the optimization for finding the first character of a +non-anchored pattern, and for finding a character that is required later in the +match were failing in some cases. This didn't break the matching; it just +failed to optimize when it could. The way this is done has been re-implemented. + +27. Fixed typo in error message for invalid (?R item (it said "(?p"). + +28. Added a new feature that provides some of the functionality that Perl +provides with (?{...}). The facility is termed a "callout". The way it is done +in PCRE is for the caller to provide an optional function, by setting +pcre_callout to its entry point. Like pcre_malloc and pcre_free, this is a +global variable. By default it is unset, which disables all calling out. To get +the function called, the regex must include (?C) at appropriate points. This +is, in fact, equivalent to (?C0), and any number <= 255 may be given with (?C). +This provides a means of identifying different callout points. When PCRE +reaches such a point in the regex, if pcre_callout has been set, the external +function is called. It is provided with data in a structure called +pcre_callout_block, which is defined in pcre.h. If the function returns 0, +matching continues; if it returns a non-zero value, the match at the current +point fails. However, backtracking will occur if possible. [This was changed +later and other features added - see item 49 below.] + +29. pcretest is upgraded to test the callout functionality. It provides a +callout function that displays information. By default, it shows the start of +the match and the current position in the text. There are some new data escapes +to vary what happens: + + \C+ in addition, show current contents of captured substrings + \C- do not supply a callout function + \C!n return 1 when callout number n is reached + \C!n!m return 1 when callout number n is reached for the mth time + +30. If pcregrep was called with the -l option and just a single file name, it +output "" if a match was found, instead of the file name. + +31. Improve the efficiency of the POSIX API to PCRE. If the number of capturing +slots is less than POSIX_MALLOC_THRESHOLD, use a block on the stack to pass to +pcre_exec(). This saves a malloc/free per call. The default value of +POSIX_MALLOC_THRESHOLD is 10; it can be changed by --with-posix-malloc-threshold +when configuring. + +32. The default maximum size of a compiled pattern is 64K. There have been a +few cases of people hitting this limit. The code now uses macros to handle the +storing of links as offsets within the compiled pattern. It defaults to 2-byte +links, but this can be changed to 3 or 4 bytes by --with-link-size when +configuring. Tests 2 and 5 work only with 2-byte links because they output +debugging information about compiled patterns. + +33. Internal code re-arrangements: + +(a) Moved the debugging function for printing out a compiled regex into + its own source file (printint.c) and used #include to pull it into + pcretest.c and, when DEBUG is defined, into pcre.c, instead of having two + separate copies. + +(b) Defined the list of op-code names for debugging as a macro in + internal.h so that it is next to the definition of the opcodes. + +(c) Defined a table of op-code lengths for simpler skipping along compiled + code. This is again a macro in internal.h so that it is next to the + definition of the opcodes. + +34. Added support for recursive calls to individual subpatterns, along the +lines of Robin Houston's patch (but implemented somewhat differently). + +35. Further mods to the Makefile to help Win32. Also, added code to pcregrep to +allow it to read and process whole directories in Win32. This code was +contributed by Lionel Fourquaux; it has not been tested by me. + +36. Added support for named subpatterns. The Python syntax (?P...) is +used to name a group. Names consist of alphanumerics and underscores, and must +be unique. Back references use the syntax (?P=name) and recursive calls use +(?P>name) which is a PCRE extension to the Python extension. Groups still have +numbers. The function pcre_fullinfo() can be used after compilation to extract +a name/number map. There are three relevant calls: + + PCRE_INFO_NAMEENTRYSIZE yields the size of each entry in the map + PCRE_INFO_NAMECOUNT yields the number of entries + PCRE_INFO_NAMETABLE yields a pointer to the map. + +The map is a vector of fixed-size entries. The size of each entry depends on +the length of the longest name used. The first two bytes of each entry are the +group number, most significant byte first. There follows the corresponding +name, zero terminated. The names are in alphabetical order. + +37. Make the maximum literal string in the compiled code 250 for the non-UTF-8 +case instead of 255. Making it the same both with and without UTF-8 support +means that the same test output works with both. + +38. There was a case of malloc(0) in the POSIX testing code in pcretest. Avoid +calling malloc() with a zero argument. + +39. Change 25 above had to resort to a heavy-handed test for the .* anchoring +optimization. I've improved things by keeping a bitmap of backreferences with +numbers 1-31 so that if .* occurs inside capturing brackets that are not in +fact referenced, the optimization can be applied. It is unlikely that a +relevant occurrence of .* (i.e. one which might indicate anchoring or forcing +the match to follow \n) will appear inside brackets with a number greater than +31, but if it does, any back reference > 31 suppresses the optimization. + +40. Added a new compile-time option PCRE_NO_AUTO_CAPTURE. This has the effect +of disabling numbered capturing parentheses. Any opening parenthesis that is +not followed by ? behaves as if it were followed by ?: but named parentheses +can still be used for capturing (and they will acquire numbers in the usual +way). + +41. Redesigned the return codes from the match() function into yes/no/error so +that errors can be passed back from deep inside the nested calls. A malloc +failure while inside a recursive subpattern call now causes the +PCRE_ERROR_NOMEMORY return instead of quietly going wrong. + +42. It is now possible to set a limit on the number of times the match() +function is called in a call to pcre_exec(). This facility makes it possible to +limit the amount of recursion and backtracking, though not in a directly +obvious way, because the match() function is used in a number of different +circumstances. The count starts from zero for each position in the subject +string (for non-anchored patterns). The default limit is, for compatibility, a +large number, namely 10 000 000. You can change this in two ways: + +(a) When configuring PCRE before making, you can use --with-match-limit=n + to set a default value for the compiled library. + +(b) For each call to pcre_exec(), you can pass a pcre_extra block in which + a different value is set. See 45 below. + +If the limit is exceeded, pcre_exec() returns PCRE_ERROR_MATCHLIMIT. + +43. Added a new function pcre_config(int, void *) to enable run-time extraction +of things that can be changed at compile time. The first argument specifies +what is wanted and the second points to where the information is to be placed. +The current list of available information is: + + PCRE_CONFIG_UTF8 + +The output is an integer that is set to one if UTF-8 support is available; +otherwise it is set to zero. + + PCRE_CONFIG_NEWLINE + +The output is an integer that it set to the value of the code that is used for +newline. It is either LF (10) or CR (13). + + PCRE_CONFIG_LINK_SIZE + +The output is an integer that contains the number of bytes used for internal +linkage in compiled expressions. The value is 2, 3, or 4. See item 32 above. + + PCRE_CONFIG_POSIX_MALLOC_THRESHOLD + +The output is an integer that contains the threshold above which the POSIX +interface uses malloc() for output vectors. See item 31 above. + + PCRE_CONFIG_MATCH_LIMIT + +The output is an unsigned integer that contains the default limit of the number +of match() calls in a pcre_exec() execution. See 42 above. + +44. pcretest has been upgraded by the addition of the -C option. This causes it +to extract all the available output from the new pcre_config() function, and to +output it. The program then exits immediately. + +45. A need has arisen to pass over additional data with calls to pcre_exec() in +order to support additional features. One way would have been to define +pcre_exec2() (for example) with extra arguments, but this would not have been +extensible, and would also have required all calls to the original function to +be mapped to the new one. Instead, I have chosen to extend the mechanism that +is used for passing in "extra" data from pcre_study(). + +The pcre_extra structure is now exposed and defined in pcre.h. It currently +contains the following fields: + + flags a bitmap indicating which of the following fields are set + study_data opaque data from pcre_study() + match_limit a way of specifying a limit on match() calls for a specific + call to pcre_exec() + callout_data data for callouts (see 49 below) + +The flag bits are also defined in pcre.h, and are + + PCRE_EXTRA_STUDY_DATA + PCRE_EXTRA_MATCH_LIMIT + PCRE_EXTRA_CALLOUT_DATA + +The pcre_study() function now returns one of these new pcre_extra blocks, with +the actual study data pointed to by the study_data field, and the +PCRE_EXTRA_STUDY_DATA flag set. This can be passed directly to pcre_exec() as +before. That is, this change is entirely upwards-compatible and requires no +change to existing code. + +If you want to pass in additional data to pcre_exec(), you can either place it +in a pcre_extra block provided by pcre_study(), or create your own pcre_extra +block. + +46. pcretest has been extended to test the PCRE_EXTRA_MATCH_LIMIT feature. If a +data string contains the escape sequence \M, pcretest calls pcre_exec() several +times with different match limits, until it finds the minimum value needed for +pcre_exec() to complete. The value is then output. This can be instructive; for +most simple matches the number is quite small, but for pathological cases it +gets very large very quickly. + +47. There's a new option for pcre_fullinfo() called PCRE_INFO_STUDYSIZE. It +returns the size of the data block pointed to by the study_data field in a +pcre_extra block, that is, the value that was passed as the argument to +pcre_malloc() when PCRE was getting memory in which to place the information +created by pcre_study(). The fourth argument should point to a size_t variable. +pcretest has been extended so that this information is shown after a successful +pcre_study() call when information about the compiled regex is being displayed. + +48. Cosmetic change to Makefile: there's no need to have / after $(DESTDIR) +because what follows is always an absolute path. (Later: it turns out that this +is more than cosmetic for MinGW, because it doesn't like empty path +components.) + +49. Some changes have been made to the callout feature (see 28 above): + +(i) A callout function now has three choices for what it returns: + + 0 => success, carry on matching + > 0 => failure at this point, but backtrack if possible + < 0 => serious error, return this value from pcre_exec() + + Negative values should normally be chosen from the set of PCRE_ERROR_xxx + values. In particular, returning PCRE_ERROR_NOMATCH forces a standard + "match failed" error. The error number PCRE_ERROR_CALLOUT is reserved for + use by callout functions. It will never be used by PCRE itself. + +(ii) The pcre_extra structure (see 45 above) has a void * field called + callout_data, with corresponding flag bit PCRE_EXTRA_CALLOUT_DATA. The + pcre_callout_block structure has a field of the same name. The contents of + the field passed in the pcre_extra structure are passed to the callout + function in the corresponding field in the callout block. This makes it + easier to use the same callout-containing regex from multiple threads. For + testing, the pcretest program has a new data escape + + \C*n pass the number n (may be negative) as callout_data + + If the callout function in pcretest receives a non-zero value as + callout_data, it returns that value. + +50. Makefile wasn't handling CFLAGS properly when compiling dftables. Also, +there were some redundant $(CFLAGS) in commands that are now specified as +$(LINK), which already includes $(CFLAGS). + +51. Extensions to UTF-8 support are listed below. These all apply when (a) PCRE +has been compiled with UTF-8 support *and* pcre_compile() has been compiled +with the PCRE_UTF8 flag. Patterns that are compiled without that flag assume +one-byte characters throughout. Note that case-insensitive matching applies +only to characters whose values are less than 256. PCRE doesn't support the +notion of cases for higher-valued characters. + +(i) A character class whose characters are all within 0-255 is handled as + a bit map, and the map is inverted for negative classes. Previously, a + character > 255 always failed to match such a class; however it should + match if the class was a negative one (e.g. [^ab]). This has been fixed. + +(ii) A negated character class with a single character < 255 is coded as + "not this character" (OP_NOT). This wasn't working properly when the test + character was multibyte, either singly or repeated. + +(iii) Repeats of multibyte characters are now handled correctly in UTF-8 + mode, for example: \x{100}{2,3}. + +(iv) The character escapes \b, \B, \d, \D, \s, \S, \w, and \W (either + singly or repeated) now correctly test multibyte characters. However, + PCRE doesn't recognize any characters with values greater than 255 as + digits, spaces, or word characters. Such characters always match \D, \S, + and \W, and never match \d, \s, or \w. + +(v) Classes may now contain characters and character ranges with values + greater than 255. For example: [ab\x{100}-\x{400}]. + +(vi) pcregrep now has a --utf-8 option (synonym -u) which makes it call + PCRE in UTF-8 mode. + +52. The info request value PCRE_INFO_FIRSTCHAR has been renamed +PCRE_INFO_FIRSTBYTE because it is a byte value. However, the old name is +retained for backwards compatibility. (Note that LASTLITERAL is also a byte +value.) + +53. The single man page has become too large. I have therefore split it up into +a number of separate man pages. These also give rise to individual HTML pages; +these are now put in a separate directory, and there is an index.html page that +lists them all. Some hyperlinking between the pages has been installed. + +54. Added convenience functions for handling named capturing parentheses. + +55. Unknown escapes inside character classes (e.g. [\M]) and escapes that +aren't interpreted therein (e.g. [\C]) are literals in Perl. This is now also +true in PCRE, except when the PCRE_EXTENDED option is set, in which case they +are faulted. + +56. Introduced HOST_CC and HOST_CFLAGS which can be set in the environment when +calling configure. These values are used when compiling the dftables.c program +which is run to generate the source of the default character tables. They +default to the values of CC and CFLAGS. If you are cross-compiling PCRE, +you will need to set these values. + +57. Updated the building process for Windows DLL, as provided by Fred Cox. + + +Version 3.9 02-Jan-02 +--------------------- + +1. A bit of extraneous text had somehow crept into the pcregrep documentation. + +2. If --disable-static was given, the building process failed when trying to +build pcretest and pcregrep. (For some reason it was using libtool to compile +them, which is not right, as they aren't part of the library.) + + +Version 3.8 18-Dec-01 +--------------------- + +1. The experimental UTF-8 code was completely screwed up. It was packing the +bytes in the wrong order. How dumb can you get? + + +Version 3.7 29-Oct-01 +--------------------- + +1. In updating pcretest to check change 1 of version 3.6, I screwed up. +This caused pcretest, when used on the test data, to segfault. Unfortunately, +this didn't happen under Solaris 8, where I normally test things. + +2. The Makefile had to be changed to make it work on BSD systems, where 'make' +doesn't seem to recognize that ./xxx and xxx are the same file. (This entry +isn't in ChangeLog distributed with 3.7 because I forgot when I hastily made +this fix an hour or so after the initial 3.7 release.) + + +Version 3.6 23-Oct-01 +--------------------- + +1. Crashed with /(sens|respons)e and \1ibility/ and "sense and sensibility" if +offsets passed as NULL with zero offset count. + +2. The config.guess and config.sub files had not been updated when I moved to +the latest autoconf. + + +Version 3.5 15-Aug-01 +--------------------- + +1. Added some missing #if !defined NOPOSIX conditionals in pcretest.c that +had been forgotten. + +2. By using declared but undefined structures, we can avoid using "void" +definitions in pcre.h while keeping the internal definitions of the structures +private. + +3. The distribution is now built using autoconf 2.50 and libtool 1.4. From a +user point of view, this means that both static and shared libraries are built +by default, but this can be individually controlled. More of the work of +handling this static/shared cases is now inside libtool instead of PCRE's make +file. + +4. The pcretest utility is now installed along with pcregrep because it is +useful for users (to test regexs) and by doing this, it automatically gets +relinked by libtool. The documentation has been turned into a man page, so +there are now .1, .txt, and .html versions in /doc. + +5. Upgrades to pcregrep: + (i) Added long-form option names like gnu grep. + (ii) Added --help to list all options with an explanatory phrase. + (iii) Added -r, --recursive to recurse into sub-directories. + (iv) Added -f, --file to read patterns from a file. + +6. pcre_exec() was referring to its "code" argument before testing that +argument for NULL (and giving an error if it was NULL). + +7. Upgraded Makefile.in to allow for compiling in a different directory from +the source directory. + +8. Tiny buglet in pcretest: when pcre_fullinfo() was called to retrieve the +options bits, the pointer it was passed was to an int instead of to an unsigned +long int. This mattered only on 64-bit systems. + +9. Fixed typo (3.4/1) in pcre.h again. Sigh. I had changed pcre.h (which is +generated) instead of pcre.in, which it its source. Also made the same change +in several of the .c files. + +10. A new release of gcc defines printf() as a macro, which broke pcretest +because it had an ifdef in the middle of a string argument for printf(). Fixed +by using separate calls to printf(). + +11. Added --enable-newline-is-cr and --enable-newline-is-lf to the configure +script, to force use of CR or LF instead of \n in the source. On non-Unix +systems, the value can be set in config.h. + +12. The limit of 200 on non-capturing parentheses is a _nesting_ limit, not an +absolute limit. Changed the text of the error message to make this clear, and +likewise updated the man page. + +13. The limit of 99 on the number of capturing subpatterns has been removed. +The new limit is 65535, which I hope will not be a "real" limit. + + +Version 3.4 22-Aug-00 +--------------------- + +1. Fixed typo in pcre.h: unsigned const char * changed to const unsigned char *. + +2. Diagnose condition (?(0) as an error instead of crashing on matching. + + +Version 3.3 01-Aug-00 +--------------------- + +1. If an octal character was given, but the value was greater than \377, it +was not getting masked to the least significant bits, as documented. This could +lead to crashes in some systems. + +2. Perl 5.6 (if not earlier versions) accepts classes like [a-\d] and treats +the hyphen as a literal. PCRE used to give an error; it now behaves like Perl. + +3. Added the functions pcre_free_substring() and pcre_free_substring_list(). +These just pass their arguments on to (pcre_free)(), but they are provided +because some uses of PCRE bind it to non-C systems that can call its functions, +but cannot call free() or pcre_free() directly. + +4. Add "make test" as a synonym for "make check". Corrected some comments in +the Makefile. + +5. Add $(DESTDIR)/ in front of all the paths in the "install" target in the +Makefile. + +6. Changed the name of pgrep to pcregrep, because Solaris has introduced a +command called pgrep for grepping around the active processes. + +7. Added the beginnings of support for UTF-8 character strings. + +8. Arranged for the Makefile to pass over the settings of CC, CFLAGS, and +RANLIB to ./ltconfig so that they are used by libtool. I think these are all +the relevant ones. (AR is not passed because ./ltconfig does its own figuring +out for the ar command.) + + +Version 3.2 12-May-00 +--------------------- + +This is purely a bug fixing release. + +1. If the pattern /((Z)+|A)*/ was matched agained ZABCDEFG it matched Z instead +of ZA. This was just one example of several cases that could provoke this bug, +which was introduced by change 9 of version 2.00. The code for breaking +infinite loops after an iteration that matches an empty string was't working +correctly. + +2. The pcretest program was not imitating Perl correctly for the pattern /a*/g +when matched against abbab (for example). After matching an empty string, it +wasn't forcing anchoring when setting PCRE_NOTEMPTY for the next attempt; this +caused it to match further down the string than it should. + +3. The code contained an inclusion of sys/types.h. It isn't clear why this +was there because it doesn't seem to be needed, and it causes trouble on some +systems, as it is not a Standard C header. It has been removed. + +4. Made 4 silly changes to the source to avoid stupid compiler warnings that +were reported on the Macintosh. The changes were from + + while ((c = *(++ptr)) != 0 && c != '\n'); +to + while ((c = *(++ptr)) != 0 && c != '\n') ; + +Totally extraordinary, but if that's what it takes... + +5. PCRE is being used in one environment where neither memmove() nor bcopy() is +available. Added HAVE_BCOPY and an autoconf test for it; if neither +HAVE_MEMMOVE nor HAVE_BCOPY is set, use a built-in emulation function which +assumes the way PCRE uses memmove() (always moving upwards). + +6. PCRE is being used in one environment where strchr() is not available. There +was only one use in pcre.c, and writing it out to avoid strchr() probably gives +faster code anyway. + + +Version 3.1 09-Feb-00 +--------------------- + +The only change in this release is the fixing of some bugs in Makefile.in for +the "install" target: + +(1) It was failing to install pcreposix.h. + +(2) It was overwriting the pcre.3 man page with the pcreposix.3 man page. + + +Version 3.0 01-Feb-00 +--------------------- + +1. Add support for the /+ modifier to perltest (to output $` like it does in +pcretest). + +2. Add support for the /g modifier to perltest. + +3. Fix pcretest so that it behaves even more like Perl for /g when the pattern +matches null strings. + +4. Fix perltest so that it doesn't do unwanted things when fed an empty +pattern. Perl treats empty patterns specially - it reuses the most recent +pattern, which is not what we want. Replace // by /(?#)/ in order to avoid this +effect. + +5. The POSIX interface was broken in that it was just handing over the POSIX +captured string vector to pcre_exec(), but (since release 2.00) PCRE has +required a bigger vector, with some working space on the end. This means that +the POSIX wrapper now has to get and free some memory, and copy the results. + +6. Added some simple autoconf support, placing the test data and the +documentation in separate directories, re-organizing some of the +information files, and making it build pcre-config (a GNU standard). Also added +libtool support for building PCRE as a shared library, which is now the +default. + +7. Got rid of the leading zero in the definition of PCRE_MINOR because 08 and +09 are not valid octal constants. Single digits will be used for minor values +less than 10. + +8. Defined REG_EXTENDED and REG_NOSUB as zero in the POSIX header, so that +existing programs that set these in the POSIX interface can use PCRE without +modification. + +9. Added a new function, pcre_fullinfo() with an extensible interface. It can +return all that pcre_info() returns, plus additional data. The pcre_info() +function is retained for compatibility, but is considered to be obsolete. + +10. Added experimental recursion feature (?R) to handle one common case that +Perl 5.6 will be able to do with (?p{...}). + +11. Added support for POSIX character classes like [:alpha:], which Perl is +adopting. + + +Version 2.08 31-Aug-99 +---------------------- + +1. When startoffset was not zero and the pattern began with ".*", PCRE was not +trying to match at the startoffset position, but instead was moving forward to +the next newline as if a previous match had failed. + +2. pcretest was not making use of PCRE_NOTEMPTY when repeating for /g and /G, +and could get into a loop if a null string was matched other than at the start +of the subject. + +3. Added definitions of PCRE_MAJOR and PCRE_MINOR to pcre.h so the version can +be distinguished at compile time, and for completeness also added PCRE_DATE. + +5. Added Paul Sokolovsky's minor changes to make it easy to compile a Win32 DLL +in GnuWin32 environments. + + +Version 2.07 29-Jul-99 +---------------------- + +1. The documentation is now supplied in plain text form and HTML as well as in +the form of man page sources. + +2. C++ compilers don't like assigning (void *) values to other pointer types. +In particular this affects malloc(). Although there is no problem in Standard +C, I've put in casts to keep C++ compilers happy. + +3. Typo on pcretest.c; a cast of (unsigned char *) in the POSIX regexec() call +should be (const char *). + +4. If NOPOSIX is defined, pcretest.c compiles without POSIX support. This may +be useful for non-Unix systems who don't want to bother with the POSIX stuff. +However, I haven't made this a standard facility. The documentation doesn't +mention it, and the Makefile doesn't support it. + +5. The Makefile now contains an "install" target, with editable destinations at +the top of the file. The pcretest program is not installed. + +6. pgrep -V now gives the PCRE version number and date. + +7. Fixed bug: a zero repetition after a literal string (e.g. /abcde{0}/) was +causing the entire string to be ignored, instead of just the last character. + +8. If a pattern like /"([^\\"]+|\\.)*"/ is applied in the normal way to a +non-matching string, it can take a very, very long time, even for strings of +quite modest length, because of the nested recursion. PCRE now does better in +some of these cases. It does this by remembering the last required literal +character in the pattern, and pre-searching the subject to ensure it is present +before running the real match. In other words, it applies a heuristic to detect +some types of certain failure quickly, and in the above example, if presented +with a string that has no trailing " it gives "no match" very quickly. + +9. A new runtime option PCRE_NOTEMPTY causes null string matches to be ignored; +other alternatives are tried instead. + + +Version 2.06 09-Jun-99 +---------------------- + +1. Change pcretest's output for amount of store used to show just the code +space, because the remainder (the data block) varies in size between 32-bit and +64-bit systems. + +2. Added an extra argument to pcre_exec() to supply an offset in the subject to +start matching at. This allows lookbehinds to work when searching for multiple +occurrences in a string. + +3. Added additional options to pcretest for testing multiple occurrences: + + /+ outputs the rest of the string that follows a match + /g loops for multiple occurrences, using the new startoffset argument + /G loops for multiple occurrences by passing an incremented pointer + +4. PCRE wasn't doing the "first character" optimization for patterns starting +with \b or \B, though it was doing it for other lookbehind assertions. That is, +it wasn't noticing that a match for a pattern such as /\bxyz/ has to start with +the letter 'x'. On long subject strings, this gives a significant speed-up. + + +Version 2.05 21-Apr-99 +---------------------- + +1. Changed the type of magic_number from int to long int so that it works +properly on 16-bit systems. + +2. Fixed a bug which caused patterns starting with .* not to work correctly +when the subject string contained newline characters. PCRE was assuming +anchoring for such patterns in all cases, which is not correct because .* will +not pass a newline unless PCRE_DOTALL is set. It now assumes anchoring only if +DOTALL is set at top level; otherwise it knows that patterns starting with .* +must be retried after every newline in the subject. + + +Version 2.04 18-Feb-99 +---------------------- + +1. For parenthesized subpatterns with repeats whose minimum was zero, the +computation of the store needed to hold the pattern was incorrect (too large). +If such patterns were nested a few deep, this could multiply and become a real +problem. + +2. Added /M option to pcretest to show the memory requirement of a specific +pattern. Made -m a synonym of -s (which does this globally) for compatibility. + +3. Subpatterns of the form (regex){n,m} (i.e. limited maximum) were being +compiled in such a way that the backtracking after subsequent failure was +pessimal. Something like (a){0,3} was compiled as (a)?(a)?(a)? instead of +((a)((a)(a)?)?)? with disastrous performance if the maximum was of any size. + + +Version 2.03 02-Feb-99 +---------------------- + +1. Fixed typo and small mistake in man page. + +2. Added 4th condition (GPL supersedes if conflict) and created separate +LICENCE file containing the conditions. + +3. Updated pcretest so that patterns such as /abc\/def/ work like they do in +Perl, that is the internal \ allows the delimiter to be included in the +pattern. Locked out the use of \ as a delimiter. If \ immediately follows +the final delimiter, add \ to the end of the pattern (to test the error). + +4. Added the convenience functions for extracting substrings after a successful +match. Updated pcretest to make it able to test these functions. + + +Version 2.02 14-Jan-99 +---------------------- + +1. Initialized the working variables associated with each extraction so that +their saving and restoring doesn't refer to uninitialized store. + +2. Put dummy code into study.c in order to trick the optimizer of the IBM C +compiler for OS/2 into generating correct code. Apparently IBM isn't going to +fix the problem. + +3. Pcretest: the timing code wasn't using LOOPREPEAT for timing execution +calls, and wasn't printing the correct value for compiling calls. Increased the +default value of LOOPREPEAT, and the number of significant figures in the +times. + +4. Changed "/bin/rm" in the Makefile to "-rm" so it works on Windows NT. + +5. Renamed "deftables" as "dftables" to get it down to 8 characters, to avoid +a building problem on Windows NT with a FAT file system. + + +Version 2.01 21-Oct-98 +---------------------- + +1. Changed the API for pcre_compile() to allow for the provision of a pointer +to character tables built by pcre_maketables() in the current locale. If NULL +is passed, the default tables are used. + + +Version 2.00 24-Sep-98 +---------------------- + +1. Since the (>?) facility is in Perl 5.005, don't require PCRE_EXTRA to enable +it any more. + +2. Allow quantification of (?>) groups, and make it work correctly. + +3. The first character computation wasn't working for (?>) groups. + +4. Correct the implementation of \Z (it is permitted to match on the \n at the +end of the subject) and add 5.005's \z, which really does match only at the +very end of the subject. + +5. Remove the \X "cut" facility; Perl doesn't have it, and (?> is neater. + +6. Remove the ability to specify CASELESS, MULTILINE, DOTALL, and +DOLLAR_END_ONLY at runtime, to make it possible to implement the Perl 5.005 +localized options. All options to pcre_study() were also removed. + +7. Add other new features from 5.005: + + $(?<= positive lookbehind + $(?a*))*/ (a PCRE_EXTRA facility). + + +Version 1.00 18-Nov-97 +---------------------- + +1. Added compile-time macros to support systems such as SunOS4 which don't have +memmove() or strerror() but have other things that can be used instead. + +2. Arranged that "make clean" removes the executables. + + +Version 0.99 27-Oct-97 +---------------------- + +1. Fixed bug in code for optimizing classes with only one character. It was +initializing a 32-byte map regardless, which could cause it to run off the end +of the memory it had got. + +2. Added, conditional on PCRE_EXTRA, the proposed (?>REGEX) construction. + + +Version 0.98 22-Oct-97 +---------------------- + +1. Fixed bug in code for handling temporary memory usage when there are more +back references than supplied space in the ovector. This could cause segfaults. + + +Version 0.97 21-Oct-97 +---------------------- + +1. Added the \X "cut" facility, conditional on PCRE_EXTRA. + +2. Optimized negated single characters not to use a bit map. + +3. Brought error texts together as macro definitions; clarified some of them; +fixed one that was wrong - it said "range out of order" when it meant "invalid +escape sequence". + +4. Changed some char * arguments to const char *. + +5. Added PCRE_NOTBOL and PCRE_NOTEOL (from POSIX). + +6. Added the POSIX-style API wrapper in pcreposix.a and testing facilities in +pcretest. + + +Version 0.96 16-Oct-97 +---------------------- + +1. Added a simple "pgrep" utility to the distribution. + +2. Fixed an incompatibility with Perl: "{" is now treated as a normal character +unless it appears in one of the precise forms "{ddd}", "{ddd,}", or "{ddd,ddd}" +where "ddd" means "one or more decimal digits". + +3. Fixed serious bug. If a pattern had a back reference, but the call to +pcre_exec() didn't supply a large enough ovector to record the related +identifying subpattern, the match always failed. PCRE now remembers the number +of the largest back reference, and gets some temporary memory in which to save +the offsets during matching if necessary, in order to ensure that +backreferences always work. + +4. Increased the compatibility with Perl in a number of ways: + + (a) . no longer matches \n by default; an option PCRE_DOTALL is provided + to request this handling. The option can be set at compile or exec time. + + (b) $ matches before a terminating newline by default; an option + PCRE_DOLLAR_ENDONLY is provided to override this (but not in multiline + mode). The option can be set at compile or exec time. + + (c) The handling of \ followed by a digit other than 0 is now supposed to be + the same as Perl's. If the decimal number it represents is less than 10 + or there aren't that many previous left capturing parentheses, an octal + escape is read. Inside a character class, it's always an octal escape, + even if it is a single digit. + + (d) An escaped but undefined alphabetic character is taken as a literal, + unless PCRE_EXTRA is set. Currently this just reserves the remaining + escapes. + + (e) {0} is now permitted. (The previous item is removed from the compiled + pattern). + +5. Changed all the names of code files so that the basic parts are no longer +than 10 characters, and abolished the teeny "globals.c" file. + +6. Changed the handling of character classes; they are now done with a 32-byte +bit map always. + +7. Added the -d and /D options to pcretest to make it possible to look at the +internals of compilation without having to recompile pcre. + + +Version 0.95 23-Sep-97 +---------------------- + +1. Fixed bug in pre-pass concerning escaped "normal" characters such as \x5c or +\x20 at the start of a run of normal characters. These were being treated as +real characters, instead of the source characters being re-checked. + + +Version 0.94 18-Sep-97 +---------------------- + +1. The functions are now thread-safe, with the caveat that the global variables +containing pointers to malloc() and free() or alternative functions are the +same for all threads. + +2. Get pcre_study() to generate a bitmap of initial characters for non- +anchored patterns when this is possible, and use it if passed to pcre_exec(). + + +Version 0.93 15-Sep-97 +---------------------- + +1. /(b)|(:+)/ was computing an incorrect first character. + +2. Add pcre_study() to the API and the passing of pcre_extra to pcre_exec(), +but not actually doing anything yet. + +3. Treat "-" characters in classes that cannot be part of ranges as literals, +as Perl does (e.g. [-az] or [az-]). + +4. Set the anchored flag if a branch starts with .* or .*? because that tests +all possible positions. + +5. Split up into different modules to avoid including unneeded functions in a +compiled binary. However, compile and exec are still in one module. The "study" +function is split off. + +6. The character tables are now in a separate module whose source is generated +by an auxiliary program - but can then be edited by hand if required. There are +now no calls to isalnum(), isspace(), isdigit(), isxdigit(), tolower() or +toupper() in the code. + +7. Turn the malloc/free funtions variables into pcre_malloc and pcre_free and +make them global. Abolish the function for setting them, as the caller can now +set them directly. + + +Version 0.92 11-Sep-97 +---------------------- + +1. A repeat with a fixed maximum and a minimum of 1 for an ordinary character +(e.g. /a{1,3}/) was broken (I mis-optimized it). + +2. Caseless matching was not working in character classes if the characters in +the pattern were in upper case. + +3. Make ranges like [W-c] work in the same way as Perl for caseless matching. + +4. Make PCRE_ANCHORED public and accept as a compile option. + +5. Add an options word to pcre_exec() and accept PCRE_ANCHORED and +PCRE_CASELESS at run time. Add escapes \A and \I to pcretest to cause it to +pass them. + +6. Give an error if bad option bits passed at compile or run time. + +7. Add PCRE_MULTILINE at compile and exec time, and (?m) as well. Add \M to +pcretest to cause it to pass that flag. + +8. Add pcre_info(), to get the number of identifying subpatterns, the stored +options, and the first character, if set. + +9. Recognize C+ or C{n,m} where n >= 1 as providing a fixed starting character. + + +Version 0.91 10-Sep-97 +---------------------- + +1. PCRE was failing to diagnose unlimited repeats of subpatterns that could +match the empty string as in /(a*)*/. It was looping and ultimately crashing. + +2. PCRE was looping on encountering an indefinitely repeated back reference to +a subpattern that had matched an empty string, e.g. /(a|)\1*/. It now does what +Perl does - treats the match as successful. + +**** diff --git a/libs/pcre/INSTALL b/libs/pcre/INSTALL new file mode 100644 index 0000000000..08802812de --- /dev/null +++ b/libs/pcre/INSTALL @@ -0,0 +1,185 @@ +Basic Installation +================== + + These are generic installation instructions that apply to systems that +can run the `configure' shell script - Unix systems and any that imitate +it. They are not specific to PCRE. There are PCRE-specific instructions +for non-Unix systems in the file NON-UNIX-USE. + + The `configure' shell script attempts to guess correct values for +various system-dependent variables used during compilation. It uses +those values to create a `Makefile' in each directory of the package. +It may also create one or more `.h' files containing system-dependent +definitions. Finally, it creates a shell script `config.status' that +you can run in the future to recreate the current configuration, a file +`config.cache' that saves the results of its tests to speed up +reconfiguring, and a file `config.log' containing compiler output +(useful mainly for debugging `configure'). + + If you need to do unusual things to compile the package, please try +to figure out how `configure' could check whether to do them, and mail +diffs or instructions to the address given in the `README' so they can +be considered for the next release. If at some point `config.cache' +contains results you don't want to keep, you may remove or edit it. + + The file `configure.in' is used to create `configure' by a program +called `autoconf'. You only need `configure.in' if you want to change +it or regenerate `configure' using a newer version of `autoconf'. + +The simplest way to compile this package is: + + 1. `cd' to the directory containing the package's source code and type + `./configure' to configure the package for your system. If you're + using `csh' on an old version of System V, you might need to type + `sh ./configure' instead to prevent `csh' from trying to execute + `configure' itself. + + Running `configure' takes awhile. While running, it prints some + messages telling which features it is checking for. + + 2. Type `make' to compile the package. + + 3. Optionally, type `make check' to run any self-tests that come with + the package. + + 4. Type `make install' to install the programs and any data files and + documentation. + + 5. You can remove the program binaries and object files from the + source code directory by typing `make clean'. To also remove the + files that `configure' created (so you can compile the package for + a different kind of computer), type `make distclean'. There is + also a `make maintainer-clean' target, but that is intended mainly + for the package's developers. If you use it, you may have to get + all sorts of other programs in order to regenerate files that came + with the distribution. + +Compilers and Options +===================== + + Some systems require unusual options for compilation or linking that +the `configure' script does not know about. You can give `configure' +initial values for variables by setting them in the environment. Using +a Bourne-compatible shell, you can do that on the command line like +this: + CC=c89 CFLAGS=-O2 LIBS=-lposix ./configure + +Or on systems that have the `env' program, you can do it like this: + env CPPFLAGS=-I/usr/local/include LDFLAGS=-s ./configure + +Compiling For Multiple Architectures +==================================== + + You can compile the package for more than one kind of computer at the +same time, by placing the object files for each architecture in their +own directory. To do this, you must use a version of `make' that +supports the `VPATH' variable, such as GNU `make'. `cd' to the +directory where you want the object files and executables to go and run +the `configure' script. `configure' automatically checks for the +source code in the directory that `configure' is in and in `..'. + + If you have to use a `make' that does not supports the `VPATH' +variable, you have to compile the package for one architecture at a time +in the source code directory. After you have installed the package for +one architecture, use `make distclean' before reconfiguring for another +architecture. + +Installation Names +================== + + By default, `make install' will install the package's files in +`/usr/local/bin', `/usr/local/man', etc. You can specify an +installation prefix other than `/usr/local' by giving `configure' the +option `--prefix=PATH'. + + You can specify separate installation prefixes for +architecture-specific files and architecture-independent files. If you +give `configure' the option `--exec-prefix=PATH', the package will use +PATH as the prefix for installing programs and libraries. +Documentation and other data files will still use the regular prefix. + + In addition, if you use an unusual directory layout you can give +options like `--bindir=PATH' to specify different values for particular +kinds of files. Run `configure --help' for a list of the directories +you can set and what kinds of files go in them. + + If the package supports it, you can cause programs to be installed +with an extra prefix or suffix on their names by giving `configure' the +option `--program-prefix=PREFIX' or `--program-suffix=SUFFIX'. + +Optional Features +================= + + Some packages pay attention to `--enable-FEATURE' options to +`configure', where FEATURE indicates an optional part of the package. +They may also pay attention to `--with-PACKAGE' options, where PACKAGE +is something like `gnu-as' or `x' (for the X Window System). The +`README' should mention any `--enable-' and `--with-' options that the +package recognizes. + + For packages that use the X Window System, `configure' can usually +find the X include and library files automatically, but if it doesn't, +you can use the `configure' options `--x-includes=DIR' and +`--x-libraries=DIR' to specify their locations. + +Specifying the System Type +========================== + + There may be some features `configure' can not figure out +automatically, but needs to determine by the type of host the package +will run on. Usually `configure' can figure that out, but if it prints +a message saying it can not guess the host type, give it the +`--host=TYPE' option. TYPE can either be a short name for the system +type, such as `sun4', or a canonical name with three fields: + CPU-COMPANY-SYSTEM + +See the file `config.sub' for the possible values of each field. If +`config.sub' isn't included in this package, then this package doesn't +need to know the host type. + + If you are building compiler tools for cross-compiling, you can also +use the `--target=TYPE' option to select the type of system they will +produce code for and the `--build=TYPE' option to select the type of +system on which you are compiling the package. + +Sharing Defaults +================ + + If you want to set default values for `configure' scripts to share, +you can create a site shell script called `config.site' that gives +default values for variables like `CC', `cache_file', and `prefix'. +`configure' looks for `PREFIX/share/config.site' if it exists, then +`PREFIX/etc/config.site' if it exists. Or, you can set the +`CONFIG_SITE' environment variable to the location of the site script. +A warning: not all `configure' scripts look for a site script. + +Operation Controls +================== + + `configure' recognizes the following options to control how it +operates. + +`--cache-file=FILE' + Use and save the results of the tests in FILE instead of + `./config.cache'. Set FILE to `/dev/null' to disable caching, for + debugging `configure'. + +`--help' + Print a summary of the options to `configure', and exit. + +`--quiet' +`--silent' +`-q' + Do not print messages saying which checks are being made. To + suppress all normal output, redirect it to `/dev/null' (any error + messages will still be shown). + +`--srcdir=DIR' + Look for the package's source code in directory DIR. Usually + `configure' can determine that directory automatically. + +`--version' + Print the version of Autoconf used to generate the `configure' + script, and exit. + +`configure' also accepts some other, not widely useful, options. diff --git a/libs/pcre/LICENCE b/libs/pcre/LICENCE new file mode 100644 index 0000000000..daea2e48a3 --- /dev/null +++ b/libs/pcre/LICENCE @@ -0,0 +1,68 @@ +PCRE LICENCE +------------ + +PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + +Release 6 of PCRE is distributed under the terms of the "BSD" licence, as +specified below. The documentation for PCRE, supplied in the "doc" +directory, is distributed under the same terms as the software itself. + +The basic library functions are written in C and are freestanding. Also +included in the distribution is a set of C++ wrapper functions. + + +THE BASIC LIBRARY FUNCTIONS +--------------------------- + +Written by: Philip Hazel +Email local part: ph10 +Email domain: cam.ac.uk + +University of Cambridge Computing Service, +Cambridge, England. Phone: +44 1223 334714. + +Copyright (c) 1997-2006 University of Cambridge +All rights reserved. + + +THE C++ WRAPPER FUNCTIONS +------------------------- + +Contributed by: Google Inc. + +Copyright (c) 2006, Google Inc. +All rights reserved. + + +THE "BSD" LICENCE +----------------- + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the name of Google + Inc. nor the names of their contributors may be used to endorse or + promote products derived from this software without specific prior + written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. + +End diff --git a/libs/pcre/Makefile.in b/libs/pcre/Makefile.in new file mode 100644 index 0000000000..556360803e --- /dev/null +++ b/libs/pcre/Makefile.in @@ -0,0 +1,606 @@ + +# Makefile.in for PCRE (Perl-Compatible Regular Expression) library. + + +############################################################################# + +# PCRE is developed on a Unix system. I do not use Windows or Macs, and know +# nothing about building software on them. Although the code of PCRE should +# be very portable, the building system in this Makefile is designed for Unix +# systems. However, there are features that have been supplied to me by various +# people that should make it work on MinGW and Cygwin systems. + +# This setting enables Unix-style directory scanning in pcregrep, triggered +# by the -f option. Maybe one day someone will add code for other systems. + +PCREGREP_OSTYPE=-DIS_UNIX + +############################################################################# + + +# Libtool places .o files in the .libs directory; this can mean that "make" +# thinks is it not up-to-date when in fact it is. This setting helps when +# GNU "make" is being used. It presumably does no harm in other cases. + +VPATH=.libs + + +#---------------------------------------------------------------------------# +# The following lines are modified by "configure" to insert data that it is # +# given in its arguments, or which it finds out for itself. # +#---------------------------------------------------------------------------# + +SHELL = @SHELL@ +prefix = @prefix@ +exec_prefix = @exec_prefix@ +top_srcdir = @top_srcdir@ + +mkinstalldirs = $(SHELL) $(top_srcdir)/mkinstalldirs + +# NB: top_builddir is not referred to directly below, but it is used in the +# setting of $(LIBTOOL), so don't remove it! + +top_builddir = . + +# BINDIR is the directory in which the pcregrep, pcretest, and pcre-config +# commands are installed. +# INCDIR is the directory in which the public header files pcre.h and +# pcreposix.h are installed. +# LIBDIR is the directory in which the libraries are installed. +# MANDIR is the directory in which the man pages are installed. + +BINDIR = @bindir@ +LIBDIR = @libdir@ +INCDIR = @includedir@ +MANDIR = @mandir@ + +# EXEEXT is set by configure to the extention of an executable file +# OBJEXT is set by configure to the extention of an object file +# The BUILD_* equivalents are the same but for the host we're building on + +EXEEXT = @EXEEXT@ +OBJEXT = @OBJEXT@ +# Note that these are just here to have a convenient place to look at the +# outcome. +BUILD_EXEEXT = @BUILD_EXEEXT@ +BUILD_OBJEXT = @BUILD_OBJEXT@ + +# POSIX_OBJ and POSIX_LOBJ are either set empty, or to the names of the +# POSIX object files. + +POSIX_OBJ = @POSIX_OBJ@ +POSIX_LOBJ = @POSIX_LOBJ@ + +# The compiler, C flags, preprocessor flags, etc + +CC = @CC@ +CXX = @CXX@ +CFLAGS = @CFLAGS@ +CXXFLAGS = @CXXFLAGS@ +LDFLAGS = @LDFLAGS@ +CXXLDFLAGS = @CXXLDFLAGS@ + +CC_FOR_BUILD = @CC_FOR_BUILD@ +CFLAGS_FOR_BUILD = @CFLAGS_FOR_BUILD@ +CXX_FOR_BUILD = @CXX_FOR_BUILD@ +CXXFLAGS_FOR_BUILD = @CXXFLAGS_FOR_BUILD@ +LDFLAGS_FOR_BUILD = $(LDFLAGS) + +UCP = @UCP@ +UTF8 = @UTF8@ +NEWLINE = @NEWLINE@ +POSIX_MALLOC_THRESHOLD = @POSIX_MALLOC_THRESHOLD@ +LINK_SIZE = @LINK_SIZE@ +MATCH_LIMIT = @MATCH_LIMIT@ @MATCH_LIMIT_RECURSION@ +NO_RECURSE = @NO_RECURSE@ +EBCDIC = @EBCDIC@ + +INSTALL = @INSTALL@ +INSTALL_DATA = @INSTALL_DATA@ + +# LIBTOOL enables the building of shared and static libraries. It is set up +# to do one or the other or both by ./configure. + +LIBTOOL = @LIBTOOL@ +LTCOMPILE = $(LIBTOOL) --mode=compile $(CC) -c $(CFLAGS) -I. -I$(top_srcdir) $(NEWLINE) $(LINK_SIZE) $(MATCH_LIMIT) $(NO_RECURSE) $(EBCDIC) +LTCXXCOMPILE = $(LIBTOOL) --mode=compile $(CXX) -c $(CXXFLAGS) -I. -I$(top_srcdir) $(NEWLINE) $(LINK_SIZE) $(MATCH_LIMIT) $(NO_RECURSE) $(EBCDIC) +@ON_WINDOWS@LINK = $(CC) $(LDFLAGS) -I. -I$(top_srcdir) -L.libs +@NOT_ON_WINDOWS@LINK = $(LIBTOOL) --mode=link $(CC) $(CFLAGS) $(LDFLAGS) -I. -I$(top_srcdir) +LINKLIB = $(LIBTOOL) --mode=link $(CC) -export-symbols-regex '^[^_]' $(LDFLAGS) -I. -I$(top_srcdir) +LINK_FOR_BUILD = $(LIBTOOL) --mode=link $(CC_FOR_BUILD) $(CFLAGS_FOR_BUILD) $(LDFLAGS_FOR_BUILD) -I. -I$(top_srcdir) +@ON_WINDOWS@CXXLINK = $(CXX) $(LDFLAGS) -I. -I$(top_srcdir) -L.libs +@NOT_ON_WINDOWS@CXXLINK = $(LIBTOOL) --mode=link $(CXX) $(CXXFLAGS) $(CXXLDFLAGS) -I. -I$(top_srcdir) +CXXLINKLIB = $(LIBTOOL) --mode=link $(CXX) $(LDFLAGS) -I. -I$(top_srcdir) + +# These are the version numbers for the shared libraries + +PCRELIBVERSION = @PCRE_LIB_VERSION@ +PCREPOSIXLIBVERSION = @PCRE_POSIXLIB_VERSION@ +PCRECPPLIBVERSION = @PCRE_CPPLIB_VERSION@ + +############################################################################## + + +OBJ = pcre_chartables.@OBJEXT@ \ + pcre_compile.@OBJEXT@ \ + pcre_config.@OBJEXT@ \ + pcre_dfa_exec.@OBJEXT@ \ + pcre_exec.@OBJEXT@ \ + pcre_fullinfo.@OBJEXT@ \ + pcre_get.@OBJEXT@ \ + pcre_globals.@OBJEXT@ \ + pcre_info.@OBJEXT@ \ + pcre_maketables.@OBJEXT@ \ + pcre_ord2utf8.@OBJEXT@ \ + pcre_refcount.@OBJEXT@ \ + pcre_study.@OBJEXT@ \ + pcre_tables.@OBJEXT@ \ + pcre_try_flipped.@OBJEXT@ \ + pcre_ucp_searchfuncs.@OBJEXT@ \ + pcre_valid_utf8.@OBJEXT@ \ + pcre_version.@OBJEXT@ \ + pcre_xclass.@OBJEXT@ \ + $(POSIX_OBJ) + +LOBJ = pcre_chartables.lo \ + pcre_compile.lo \ + pcre_config.lo \ + pcre_dfa_exec.lo \ + pcre_exec.lo \ + pcre_fullinfo.lo \ + pcre_get.lo \ + pcre_globals.lo \ + pcre_info.lo \ + pcre_maketables.lo \ + pcre_ord2utf8.lo \ + pcre_refcount.lo \ + pcre_study.lo \ + pcre_tables.lo \ + pcre_try_flipped.lo \ + pcre_ucp_searchfuncs.lo \ + pcre_valid_utf8.lo \ + pcre_version.lo \ + pcre_xclass.lo \ + $(POSIX_LOBJ) + +CPPOBJ = pcrecpp.@OBJEXT@ \ + pcre_scanner.@OBJEXT@ \ + pcre_stringpiece.@OBJEXT@ + +CPPLOBJ = pcrecpp.lo \ + pcre_scanner.lo \ + pcre_stringpiece.lo + +CPP_TARGETS = libpcrecpp.la \ + pcrecpp_unittest@EXEEXT@ \ + pcre_scanner_unittest@EXEEXT@ \ + pcre_stringpiece_unittest@EXEEXT@ + +all: libpcre.la @POSIX_LIB@ pcretest@EXEEXT@ pcregrep@EXEEXT@ \ + @MAYBE_CPP_TARGETS@ @ON_WINDOWS@ winshared + +pcregrep@EXEEXT@: libpcre.la pcregrep.@OBJEXT@ @ON_WINDOWS@ winshared + $(LINK) -o pcregrep@EXEEXT@ pcregrep.@OBJEXT@ libpcre.la + +pcretest@EXEEXT@: libpcre.la @POSIX_LIB@ pcretest.@OBJEXT@ \ + @ON_WINDOWS@ winshared + $(LINK) $(PURIFY) $(EFENCE) -o pcretest@EXEEXT@ \ + pcretest.@OBJEXT@ \ + libpcre.la @POSIX_LIB@ + +pcrecpp_unittest@EXEEXT@: libpcrecpp.la pcrecpp_unittest.@OBJEXT@ \ + @ON_WINDOWS@ winshared + $(CXXLINK) $(PURIFY) $(EFENCE) -o pcrecpp_unittest@EXEEXT@ \ + pcrecpp_unittest.@OBJEXT@ \ + libpcrecpp.la @POSIX_LIB@ + +pcre_scanner_unittest@EXEEXT@: libpcrecpp.la pcre_scanner_unittest.@OBJEXT@ \ + @ON_WINDOWS@ winshared + $(CXXLINK) $(PURIFY) $(EFENCE) \ + -o pcre_scanner_unittest@EXEEXT@ \ + pcre_scanner_unittest.@OBJEXT@ \ + libpcrecpp.la @POSIX_LIB@ + +pcre_stringpiece_unittest@EXEEXT@: libpcrecpp.la \ + pcre_stringpiece_unittest.@OBJEXT@ @ON_WINDOWS@ winshared + $(CXXLINK) $(PURIFY) $(EFENCE) \ + -o pcre_stringpiece_unittest@EXEEXT@ \ + pcre_stringpiece_unittest.@OBJEXT@ \ + libpcrecpp.la @POSIX_LIB@ + +libpcre.la: $(OBJ) + -rm -f libpcre.la + $(LINKLIB) -rpath $(LIBDIR) -version-info \ + '$(PCRELIBVERSION)' -o libpcre.la $(LOBJ) + +libpcreposix.la: libpcre.la pcreposix.@OBJEXT@ + -rm -f libpcreposix.la + $(LINKLIB) -rpath $(LIBDIR) libpcre.la -version-info \ + '$(PCREPOSIXLIBVERSION)' -o libpcreposix.la pcreposix.lo + +libpcrecpp.la: libpcre.la $(CPPOBJ) + -rm -f libpcrecpp.la + $(CXXLINKLIB) -rpath $(LIBDIR) libpcre.la -version-info \ + '$(PCRECPPLIBVERSION)' -o libpcrecpp.la $(CPPLOBJ) + +# Note that files generated by ./configure and by dftables are in the current +# directory, not the source directory. + +pcre_chartables.@OBJEXT@: pcre_chartables.c + @$(LTCOMPILE) pcre_chartables.c + +pcre_compile.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ + $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_compile.c \ + $(top_srcdir)/pcre_printint.src + @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_compile.c + +pcre_config.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ + $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_config.c + @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_config.c + +pcre_dfa_exec.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ + $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_dfa_exec.c + @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_dfa_exec.c + +pcre_exec.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ + $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_exec.c + @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_exec.c + +pcre_fullinfo.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ + $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_fullinfo.c + @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_fullinfo.c + +pcre_get.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ + $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_get.c + @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_get.c + +pcre_globals.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ + $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_globals.c + @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_globals.c + +pcre_info.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ + $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_info.c + @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_info.c + +pcre_maketables.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ + $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_maketables.c + @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_maketables.c + +pcre_ord2utf8.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ + $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_ord2utf8.c + @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_ord2utf8.c + +pcre_refcount.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ + $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_refcount.c + @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_refcount.c + +pcre_study.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ + $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_study.c + @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_study.c + +pcre_tables.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ + $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_tables.c + @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_tables.c + +pcre_try_flipped.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ + $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_try_flipped.c + @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_try_flipped.c + +pcre_ucp_searchfuncs.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ + $(top_srcdir)/pcre_internal.h \ + $(top_srcdir)/pcre_ucp_searchfuncs.c \ + $(top_srcdir)/ucptable.c + @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_ucp_searchfuncs.c + +pcre_valid_utf8.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ + $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_valid_utf8.c + @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_valid_utf8.c + +pcre_version.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ + $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_version.c + @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_version.c + +pcre_xclass.@OBJEXT@: Makefile config.h $(top_srcdir)/pcre.h \ + $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre_xclass.c + @$(LTCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_xclass.c + +pcreposix.@OBJEXT@: $(top_srcdir)/pcreposix.c $(top_srcdir)/pcreposix.h \ + $(top_srcdir)/pcre_internal.h $(top_srcdir)/pcre.h config.h Makefile + @$(LTCOMPILE) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcreposix.c + +pcrecpp.@OBJEXT@: $(top_srcdir)/pcrecpp.cc $(top_srcdir)/pcrecpp.h \ + pcrecpparg.h pcre_stringpiece.h $(top_srcdir)/pcre.h config.h Makefile + @$(LTCXXCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcrecpp.cc + +pcre_scanner.@OBJEXT@: $(top_srcdir)/pcre_scanner.cc \ + $(top_srcdir)/pcre_scanner.h \ + $(top_srcdir)/pcrecpp.h pcrecpparg.h pcre_stringpiece.h \ + $(top_srcdir)/pcre.h config.h Makefile + @$(LTCXXCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_scanner.cc + +pcre_stringpiece.@OBJEXT@: $(top_srcdir)/pcre_stringpiece.cc \ + pcre_stringpiece.h \ + config.h Makefile + @$(LTCXXCOMPILE) $(UTF8) $(UCP) $(POSIX_MALLOC_THRESHOLD) \ + $(top_srcdir)/pcre_stringpiece.cc + +pcretest.@OBJEXT@: $(top_srcdir)/pcretest.c $(top_srcdir)/pcre_internal.h \ + $(top_srcdir)/pcre_printint.src $(top_srcdir)/pcre.h config.h Makefile + $(CC) -c $(CFLAGS) -I. -I$(top_srcdir) $(UTF8) $(UCP) \ + $(LINK_SIZE) $(top_srcdir)/pcretest.c + +pcrecpp_unittest.@OBJEXT@: $(top_srcdir)/pcrecpp_unittest.cc \ + $(top_srcdir)/pcrecpp.h \ + pcrecpparg.h pcre_stringpiece.h $(top_srcdir)/pcre.h config.h Makefile + $(CXX) -c $(CXXFLAGS) -I. -I$(top_srcdir) $(UTF8) $(UCP) \ + $(LINK_SIZE) $(top_srcdir)/pcrecpp_unittest.cc + +pcre_stringpiece_unittest.@OBJEXT@: $(top_srcdir)/pcre_stringpiece_unittest.cc \ + pcre_stringpiece.h pcrecpparg.h config.h Makefile + $(CXX) -c $(CXXFLAGS) -I. -I$(top_srcdir) $(UTF8) $(UCP) \ + $(LINK_SIZE) $(top_srcdir)/pcre_stringpiece_unittest.cc + +pcre_scanner_unittest.@OBJEXT@: $(top_srcdir)/pcre_scanner_unittest.cc \ + $(top_srcdir)/pcre_scanner.h \ + $(top_srcdir)/pcrecpp.h pcre_stringpiece.h \ + $(top_srcdir)/pcre.h pcrecpparg.h config.h Makefile + $(CXX) -c $(CXXFLAGS) -I. -I$(top_srcdir) $(UTF8) $(UCP) \ + $(LINK_SIZE) $(top_srcdir)/pcre_scanner_unittest.cc + +pcregrep.@OBJEXT@: $(top_srcdir)/pcregrep.c $(top_srcdir)/pcre.h Makefile config.h + $(CC) -c $(CFLAGS) -I. -I$(top_srcdir) $(UTF8) $(UCP) \ + $(PCREGREP_OSTYPE) $(top_srcdir)/pcregrep.c + +# Some Windows-specific targets for MinGW. Do not use for Cygwin. + +winshared : .libs/@WIN_PREFIX@pcre.dll .libs/@WIN_PREFIX@pcreposix.dll \ + .libs/@WIN_PREFIX@pcrecpp.dll + +.libs/@WIN_PREFIX@pcre.dll : libpcre.la + $(CC) $(CFLAGS) -shared -o $@ \ + -Wl,--whole-archive .libs/libpcre.a \ + -Wl,--out-implib,.libs/libpcre.dll.a \ + -Wl,--output-def,.libs/@WIN_PREFIX@pcre.dll-def \ + -Wl,--export-all-symbols \ + -Wl,--no-whole-archive + sed -e "s#dlname=''#dlname='../bin/@WIN_PREFIX@pcre.dll'#" \ + -e "s#library_names=''#library_names='libpcre.dll.a'#" \ + < .libs/libpcre.lai > .libs/libpcre.lai.tmp && \ + mv -f .libs/libpcre.lai.tmp .libs/libpcre.lai + sed -e "s#dlname=''#dlname='../bin/@WIN_PREFIX@pcre.dll'#" \ + -e "s#library_names=''#library_names='libpcre.dll.a'#" \ + < libpcre.la > libpcre.la.tmp && \ + mv -f libpcre.la.tmp libpcre.la + + +.libs/@WIN_PREFIX@pcreposix.dll: libpcreposix.la libpcre.la + $(CC) $(CFLAGS) -shared -o $@ \ + -Wl,--whole-archive .libs/libpcreposix.a \ + -Wl,--out-implib,.libs/@WIN_PREFIX@pcreposix.dll.a \ + -Wl,--output-def,.libs/@WIN_PREFIX@libpcreposix.dll-def \ + -Wl,--export-all-symbols \ + -Wl,--no-whole-archive .libs/libpcre.a + sed -e "s#dlname=''#dlname='../bin/@WIN_PREFIX@pcreposix.dll'#" \ + -e "s#library_names=''#library_names='libpcreposix.dll.a'#"\ + < .libs/libpcreposix.lai > .libs/libpcreposix.lai.tmp && \ + mv -f .libs/libpcreposix.lai.tmp .libs/libpcreposix.lai + sed -e "s#dlname=''#dlname='../bin/@WIN_PREFIX@pcreposix.dll'#" \ + -e "s#library_names=''#library_names='libpcreposix.dll.a'#"\ + < libpcreposix.la > libpcreposix.la.tmp && \ + mv -f libpcreposix.la.tmp libpcreposix.la + +.libs/@WIN_PREFIX@pcrecpp.dll: libpcrecpp.la libpcre.la + $(CXX) $(CXXFLAGS) -shared -o $@ \ + -Wl,--whole-archive .libs/libpcrecpp.a \ + -Wl,--out-implib,.libs/@WIN_PREFIX@pcrecpp.dll.a \ + -Wl,--output-def,.libs/@WIN_PREFIX@libpcrecpp.dll-def \ + -Wl,--export-all-symbols \ + -Wl,--no-whole-archive .libs/libpcre.a + sed -e "s#dlname=''#dlname='../bin/@WIN_PREFIX@pcrecpp.dll'#" \ + -e "s#library_names=''#library_names='libpcrecpp.dll.a'#"\ + < .libs/libpcrecpp.lai > .libs/libpcrecpp.lai.tmp && \ + mv -f .libs/libpcrecpp.lai.tmp .libs/libpcrecpp.lai + sed -e "s#dlname=''#dlname='../bin/@WIN_PREFIX@pcrecpp.dll'#" \ + -e "s#library_names=''#library_names='libpcrecpp.dll.a'#"\ + < libpcrecpp.la > libpcrecpp.la.tmp && \ + mv -f libpcrecpp.la.tmp libpcrecpp.la + + +wininstall : winshared + $(mkinstalldirs) $(DESTDIR)$(LIBDIR) + $(mkinstalldirs) $(DESTDIR)$(BINDIR) + $(INSTALL) .libs/@WIN_PREFIX@pcre.dll $(DESTDIR)$(BINDIR)/@WIN_PREFIX@pcre.dll + $(INSTALL) .libs/@WIN_PREFIX@pcreposix.dll $(DESTDIR)$(BINDIR)/@WIN_PREFIX@pcreposix.dll + $(INSTALL) .libs/@WIN_PREFIX@libpcreposix.dll.a $(DESTDIR)$(LIBDIR)/@WIN_PREFIX@libpcreposix.dll.a + $(INSTALL) .libs/@WIN_PREFIX@libpcre.dll.a $(DESTDIR)$(LIBDIR)/@WIN_PREFIX@libpcre.dll.a +@HAVE_CPP@ $(INSTALL) .libs/@WIN_PREFIX@pcrecpp.dll $(DESTDIR)$(BINDIR)/@WIN_PREFIX@pcrecpp.dll +@HAVE_CPP@ $(INSTALL) .libs/@WIN_PREFIX@libpcrecpp.dll.a $(DESTDIR)$(LIBDIR)/@WIN_PREFIX@libpcrecpp.dll.a + -strip -g $(DESTDIR)$(BINDIR)/@WIN_PREFIX@pcre.dll + -strip -g $(DESTDIR)$(BINDIR)/@WIN_PREFIX@pcreposix.dll +@HAVE_CPP@ -strip -g $(DESTDIR)$(BINDIR)/@WIN_PREFIX@pcrecpp.dll + -strip $(DESTDIR)$(BINDIR)/pcregrep@EXEEXT@ + -strip $(DESTDIR)$(BINDIR)/pcretest@EXEEXT@ + +# An auxiliary program makes the default character table source. This is put +# in the current directory, NOT the $top_srcdir directory. + +pcre_chartables.c: dftables@BUILD_EXEEXT@ + ./dftables@BUILD_EXEEXT@ pcre_chartables.c + +dftables.@BUILD_OBJEXT@: $(top_srcdir)/dftables.c \ + $(top_srcdir)/pcre_maketables.c $(top_srcdir)/pcre_internal.h \ + $(top_srcdir)/pcre.h config.h Makefile + $(CC_FOR_BUILD) -c $(CFLAGS_FOR_BUILD) -I. $(top_srcdir)/dftables.c + +dftables@BUILD_EXEEXT@: dftables.@BUILD_OBJEXT@ + $(LINK_FOR_BUILD) -o dftables@BUILD_EXEEXT@ dftables.@OBJEXT@ + +install: all @ON_WINDOWS@ wininstall +@NOT_ON_WINDOWS@ $(mkinstalldirs) $(DESTDIR)$(LIBDIR) +@NOT_ON_WINDOWS@ echo "$(LIBTOOL) --mode=install $(INSTALL) libpcre.la $(DESTDIR)$(LIBDIR)/libpcre.la" +@NOT_ON_WINDOWS@ $(LIBTOOL) --mode=install $(INSTALL) libpcre.la $(DESTDIR)$(LIBDIR)/libpcre.la +@NOT_ON_WINDOWS@ echo "$(LIBTOOL) --mode=install $(INSTALL) libpcreposix.la $(DESTDIR)$(LIBDIR)/libpcreposix.la" +@NOT_ON_WINDOWS@ $(LIBTOOL) --mode=install $(INSTALL) libpcreposix.la $(DESTDIR)$(LIBDIR)/libpcreposix.la +@NOT_ON_WINDOWS@@HAVE_CPP@ echo "$(LIBTOOL) --mode=install $(INSTALL) libpcrecpp.la $(DESTDIR)$(LIBDIR)/libpcrecpp.la" +@NOT_ON_WINDOWS@@HAVE_CPP@ $(LIBTOOL) --mode=install $(INSTALL) libpcrecpp.la $(DESTDIR)$(LIBDIR)/libpcrecpp.la +@NOT_ON_WINDOWS@ $(LIBTOOL) --finish $(DESTDIR)$(LIBDIR) + $(mkinstalldirs) $(DESTDIR)$(INCDIR) + $(INSTALL_DATA) $(top_srcdir)/pcre.h $(DESTDIR)$(INCDIR)/pcre.h + $(INSTALL_DATA) $(top_srcdir)/pcreposix.h $(DESTDIR)$(INCDIR)/pcreposix.h +@HAVE_CPP@ $(INSTALL_DATA) $(top_srcdir)/pcrecpp.h $(DESTDIR)$(INCDIR)/pcrecpp.h +@HAVE_CPP@ $(INSTALL_DATA) pcrecpparg.h $(DESTDIR)$(INCDIR)/pcrecpparg.h +@HAVE_CPP@ $(INSTALL_DATA) pcre_stringpiece.h $(DESTDIR)$(INCDIR)/pcre_stringpiece.h +@HAVE_CPP@ $(INSTALL_DATA) $(top_srcdir)/pcre_scanner.h $(DESTDIR)$(INCDIR)/pcre_scanner.h + $(mkinstalldirs) $(DESTDIR)$(MANDIR)/man3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre.3 $(DESTDIR)$(MANDIR)/man3/pcre.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcreapi.3 $(DESTDIR)$(MANDIR)/man3/pcreapi.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcrebuild.3 $(DESTDIR)$(MANDIR)/man3/pcrebuild.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcrecallout.3 $(DESTDIR)$(MANDIR)/man3/pcrecallout.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcrecompat.3 $(DESTDIR)$(MANDIR)/man3/pcrecompat.3 +@HAVE_CPP@ $(INSTALL_DATA) $(top_srcdir)/doc/pcrecpp.3 $(DESTDIR)$(MANDIR)/man3/pcrecpp.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcrematching.3 $(DESTDIR)$(MANDIR)/man3/pcrematching.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcrepartial.3 $(DESTDIR)$(MANDIR)/man3/pcrepartial.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcrepattern.3 $(DESTDIR)$(MANDIR)/man3/pcrepattern.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcreperform.3 $(DESTDIR)$(MANDIR)/man3/pcreperform.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcreposix.3 $(DESTDIR)$(MANDIR)/man3/pcreposix.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcreprecompile.3 $(DESTDIR)$(MANDIR)/man3/pcreprecompile.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcresample.3 $(DESTDIR)$(MANDIR)/man3/pcresample.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcrestack.3 $(DESTDIR)$(MANDIR)/man3/pcrestack.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_compile.3 $(DESTDIR)$(MANDIR)/man3/pcre_compile.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_compile2.3 $(DESTDIR)$(MANDIR)/man3/pcre_compile2.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_config.3 $(DESTDIR)$(MANDIR)/man3/pcre_config.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_copy_named_substring.3 $(DESTDIR)$(MANDIR)/man3/pcre_copy_named_substring.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_copy_substring.3 $(DESTDIR)$(MANDIR)/man3/pcre_copy_substring.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_dfa_exec.3 $(DESTDIR)$(MANDIR)/man3/pcre_dfa_exec.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_exec.3 $(DESTDIR)$(MANDIR)/man3/pcre_exec.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_free_substring.3 $(DESTDIR)$(MANDIR)/man3/pcre_free_substring.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_free_substring_list.3 $(DESTDIR)$(MANDIR)/man3/pcre_free_substring_list.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_fullinfo.3 $(DESTDIR)$(MANDIR)/man3/pcre_fullinfo.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_get_named_substring.3 $(DESTDIR)$(MANDIR)/man3/pcre_get_named_substring.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_get_stringnumber.3 $(DESTDIR)$(MANDIR)/man3/pcre_get_stringnumber.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_get_stringtable_entries.3 $(DESTDIR)$(MANDIR)/man3/pcre_get_stringtable_entries.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_get_substring.3 $(DESTDIR)$(MANDIR)/man3/pcre_get_substring.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_get_substring_list.3 $(DESTDIR)$(MANDIR)/man3/pcre_get_substring_list.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_info.3 $(DESTDIR)$(MANDIR)/man3/pcre_info.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_maketables.3 $(DESTDIR)$(MANDIR)/man3/pcre_maketables.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_refcount.3 $(DESTDIR)$(MANDIR)/man3/pcre_refcount.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_study.3 $(DESTDIR)$(MANDIR)/man3/pcre_study.3 + $(INSTALL_DATA) $(top_srcdir)/doc/pcre_version.3 $(DESTDIR)$(MANDIR)/man3/pcre_version.3 + $(mkinstalldirs) $(DESTDIR)$(MANDIR)/man1 + $(INSTALL_DATA) $(top_srcdir)/doc/pcregrep.1 $(DESTDIR)$(MANDIR)/man1/pcregrep.1 + $(INSTALL_DATA) $(top_srcdir)/doc/pcretest.1 $(DESTDIR)$(MANDIR)/man1/pcretest.1 + $(mkinstalldirs) $(DESTDIR)$(BINDIR) + $(LIBTOOL) --mode=install $(INSTALL) pcregrep@EXEEXT@ $(DESTDIR)$(BINDIR)/pcregrep@EXEEXT@ + $(LIBTOOL) --mode=install $(INSTALL) pcretest@EXEEXT@ $(DESTDIR)$(BINDIR)/pcretest@EXEEXT@ + $(INSTALL) pcre-config $(DESTDIR)$(BINDIR)/pcre-config + $(mkinstalldirs) $(DESTDIR)$(LIBDIR)/pkgconfig + $(INSTALL_DATA) libpcre.pc $(DESTDIR)$(LIBDIR)/pkgconfig/libpcre.pc + +# The uninstall target removes all the files that were installed. + +uninstall:; -rm -rf \ + $(DESTDIR)$(LIBDIR)/libpcre.* \ + $(DESTDIR)$(LIBDIR)/libpcreposix.* \ + $(DESTDIR)$(LIBDIR)/libpcrecpp.* \ + $(DESTDIR)$(INCDIR)/pcre.h \ + $(DESTDIR)$(INCDIR)/pcreposix.h \ + $(DESTDIR)$(INCDIR)/pcrecpp.h \ + $(DESTDIR)$(INCDIR)/pcrecpparg.h \ + $(DESTDIR)$(INCDIR)/pcre_scanner.h \ + $(DESTDIR)$(INCDIR)/pcre_stringpiece.h \ + $(DESTDIR)$(MANDIR)/man3/pcre.3 \ + $(DESTDIR)$(MANDIR)/man3/pcreapi.3 \ + $(DESTDIR)$(MANDIR)/man3/pcrebuild.3 \ + $(DESTDIR)$(MANDIR)/man3/pcrecallout.3 \ + $(DESTDIR)$(MANDIR)/man3/pcrecompat.3 \ + $(DESTDIR)$(MANDIR)/man3/pcrecpp.3 \ + $(DESTDIR)$(MANDIR)/man3/pcrematching.3 \ + $(DESTDIR)$(MANDIR)/man3/pcrepartial.3 \ + $(DESTDIR)$(MANDIR)/man3/pcrepattern.3 \ + $(DESTDIR)$(MANDIR)/man3/pcreperform.3 \ + $(DESTDIR)$(MANDIR)/man3/pcreposix.3 \ + $(DESTDIR)$(MANDIR)/man3/pcreprecompile.3 \ + $(DESTDIR)$(MANDIR)/man3/pcresample.3 \ + $(DESTDIR)$(MANDIR)/man3/pcrestack.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_compile.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_compile2.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_config.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_copy_named_substring.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_copy_substring.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_dfa_exec.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_exec.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_free_substring.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_free_substring_list.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_fullinfo.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_get_named_substring.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_get_stringnumber.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_get_stringtable_entries.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_get_substring.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_get_substring_list.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_info.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_maketables.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_refcount.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_study.3 \ + $(DESTDIR)$(MANDIR)/man3/pcre_version.3 \ + $(DESTDIR)$(MANDIR)/man1/pcregrep.1 \ + $(DESTDIR)$(MANDIR)/man1/pcretest.1 \ + $(DESTDIR)$(BINDIR)/pcregrep@EXEEXT@ \ + $(DESTDIR)$(BINDIR)/pcretest@EXEEXT@ \ + $(DESTDIR)$(BINDIR)/pcre-config \ + $(DESTDIR)$(LIBDIR)/pkgconfig/libpcre.pc + +# We deliberately omit dftables and pcre_chartables.c from 'make clean'; once +# made pcre_chartables.c shouldn't change, and if people have edited the tables +# by hand, you don't want to throw them away. + +clean:; -rm -rf *.@OBJEXT@ *.lo *.a *.la .libs pcretest@EXEEXT@ pcre_stringpiece_unittest@EXEEXT@ pcrecpp_unittest@EXEEXT@ pcre_scanner_unittest@EXEEXT@ pcregrep@EXEEXT@ testtry + +# But "make distclean" should get back to a virgin distribution + +distclean: clean + -rm -f pcre_chartables.c libtool pcre-config libpcre.pc \ + pcre_stringpiece.h pcrecpparg.h \ + dftables@EXEEXT@ RunGrepTest RunTest \ + Makefile config.h config.status config.log config.cache + +check: runtest + +@WIN_PREFIX@pcre.dll : winshared + cp .libs/@WIN_PREFIX@pcre.dll . + +test: runtest + +runtest: all @ON_WINDOWS@ @WIN_PREFIX@pcre.dll + @./RunTest + @./RunGrepTest +@HAVE_CPP@ @echo "" +@HAVE_CPP@ @echo "Testing C++ wrapper" +@HAVE_CPP@ @echo ""; echo "Test 1++: stringpiece" +@HAVE_CPP@ @./pcre_stringpiece_unittest@EXEEXT@ +@HAVE_CPP@ @echo ""; echo "Test 2++: RE class" +@HAVE_CPP@ @./pcrecpp_unittest@EXEEXT@ +@HAVE_CPP@ @echo ""; echo "Test 3++: Scanner class" +@HAVE_CPP@ @./pcre_scanner_unittest@EXEEXT@ + +# End diff --git a/libs/pcre/NEWS b/libs/pcre/NEWS new file mode 100644 index 0000000000..4f17b198a0 --- /dev/null +++ b/libs/pcre/NEWS @@ -0,0 +1,266 @@ +News about PCRE releases +------------------------ + +Release 6.7 04-Jul-06 +--------------------- + +The main additions to this release are the ability to use the same name for +multiple sets of parentheses, and support for CRLF line endings in both the +library and pcregrep (and in pcretest for testing). + +Thanks to Ian Taylor, the stack usage for many kinds of pattern has been +significantly reduced for certain subject strings. + + +Release 6.5 01-Feb-06 +--------------------- + +Important changes in this release: + +1. A number of new features have been added to pcregrep. + +2. The Unicode property tables have been updated to Unicode 4.1.0, and the + supported properties have been extended with script names such as "Arabic", + and the derived properties "Any" and "L&". This has necessitated a change to + the interal format of compiled patterns. Any saved compiled patterns that + use \p or \P must be recompiled. + +3. The specification of recursion in patterns has been changed so that all + recursive subpatterns are automatically treated as atomic groups. Thus, for + example, (?R) is treated as if it were (?>(?R)). This is necessary because + otherwise there are situations where recursion does not work. + +See the ChangeLog for a complete list of changes, which include a number of bug +fixes and tidies. + + +Release 6.0 07-Jun-05 +--------------------- + +The release number has been increased to 6.0 because of the addition of several +major new pieces of functionality. + +A new function, pcre_dfa_exec(), which implements pattern matching using a DFA +algorithm, has been added. This has a number of advantages for certain cases, +though it does run more slowly, and lacks the ability to capture substrings. On +the other hand, it does find all matches, not just the first, and it works +better for partial matching. The pcrematching man page discusses the +differences. + +The pcretest program has been enhanced so that it can make use of the new +pcre_dfa_exec() matching function and the extra features it provides. + +The distribution now includes a C++ wrapper library. This is built +automatically if a C++ compiler is found. The pcrecpp man page discusses this +interface. + +The code itself has been re-organized into many more files, one for each +function, so it no longer requires everything to be linked in when static +linkage is used. As a consequence, some internal functions have had to have +their names exposed. These functions all have names starting with _pcre_. They +are undocumented, and are not intended for use by outside callers. + +The pcregrep program has been enhanced with new functionality such as +multiline-matching and options for output more matching context. See the +ChangeLog for a complete list of changes to the library and the utility +programs. + + +Release 5.0 13-Sep-04 +--------------------- + +The licence under which PCRE is released has been changed to the more +conventional "BSD" licence. + +In the code, some bugs have been fixed, and there are also some major changes +in this release (which is why I've increased the number to 5.0). Some changes +are internal rearrangements, and some provide a number of new facilities. The +new features are: + +1. There's an "automatic callout" feature that inserts callouts before every + item in the regex, and there's a new callout field that gives the position + in the pattern - useful for debugging and tracing. + +2. The extra_data structure can now be used to pass in a set of character + tables at exec time. This is useful if compiled regex are saved and re-used + at a later time when the tables may not be at the same address. If the + default internal tables are used, the pointer saved with the compiled + pattern is now set to NULL, which means that you don't need to do anything + special unless you are using custom tables. + +3. It is possible, with some restrictions on the content of the regex, to + request "partial" matching. A special return code is given if all of the + subject string matched part of the regex. This could be useful for testing + an input field as it is being typed. + +4. There is now some optional support for Unicode character properties, which + means that the patterns items such as \p{Lu} and \X can now be used. Only + the general category properties are supported. If PCRE is compiled with this + support, an additional 90K data structure is include, which increases the + size of the library dramatically. + +5. There is support for saving compiled patterns and re-using them later. + +6. There is support for running regular expressions that were compiled on a + different host with the opposite endianness. + +7. The pcretest program has been extended to accommodate the new features. + +The main internal rearrangement is that sequences of literal characters are no +longer handled as strings. Instead, each character is handled on its own. This +makes some UTF-8 handling easier, and makes the support of partial matching +possible. Compiled patterns containing long literal strings will be larger as a +result of this change; I hope that performance will not be much affected. + + +Release 4.5 01-Dec-03 +--------------------- + +Again mainly a bug-fix and tidying release, with only a couple of new features: + +1. It's possible now to compile PCRE so that it does not use recursive +function calls when matching. Instead it gets memory from the heap. This slows +things down, but may be necessary on systems with limited stacks. + +2. UTF-8 string checking has been tightened to reject overlong sequences and to +check that a starting offset points to the start of a character. Failure of the +latter returns a new error code: PCRE_ERROR_BADUTF8_OFFSET. + +3. PCRE can now be compiled for systems that use EBCDIC code. + + +Release 4.4 21-Aug-03 +--------------------- + +This is mainly a bug-fix and tidying release. The only new feature is that PCRE +checks UTF-8 strings for validity by default. There is an option to suppress +this, just in case anybody wants that teeny extra bit of performance. + + +Releases 4.1 - 4.3 +------------------ + +Sorry, I forgot about updating the NEWS file for these releases. Please take a +look at ChangeLog. + + +Release 4.0 17-Feb-03 +--------------------- + +There have been a lot of changes for the 4.0 release, adding additional +functionality and mending bugs. Below is a list of the highlights of the new +functionality. For full details of these features, please consult the +documentation. For a complete list of changes, see the ChangeLog file. + +1. Support for Perl's \Q...\E escapes. + +2. "Possessive quantifiers" ?+, *+, ++, and {,}+ which come from Sun's Java +package. They provide some syntactic sugar for simple cases of "atomic +grouping". + +3. Support for the \G assertion. It is true when the current matching position +is at the start point of the match. + +4. A new feature that provides some of the functionality that Perl provides +with (?{...}). The facility is termed a "callout". The way it is done in PCRE +is for the caller to provide an optional function, by setting pcre_callout to +its entry point. To get the function called, the regex must include (?C) at +appropriate points. + +5. Support for recursive calls to individual subpatterns. This makes it really +easy to get totally confused. + +6. Support for named subpatterns. The Python syntax (?P...) is used to +name a group. + +7. Several extensions to UTF-8 support; it is now fairly complete. There is an +option for pcregrep to make it operate in UTF-8 mode. + +8. The single man page has been split into a number of separate man pages. +These also give rise to individual HTML pages which are put in a separate +directory. There is an index.html page that lists them all. Some hyperlinking +between the pages has been installed. + + +Release 3.5 15-Aug-01 +--------------------- + +1. The configuring system has been upgraded to use later versions of autoconf +and libtool. By default it builds both a shared and a static library if the OS +supports it. You can use --disable-shared or --disable-static on the configure +command if you want only one of them. + +2. The pcretest utility is now installed along with pcregrep because it is +useful for users (to test regexs) and by doing this, it automatically gets +relinked by libtool. The documentation has been turned into a man page, so +there are now .1, .txt, and .html versions in /doc. + +3. Upgrades to pcregrep: + (i) Added long-form option names like gnu grep. + (ii) Added --help to list all options with an explanatory phrase. + (iii) Added -r, --recursive to recurse into sub-directories. + (iv) Added -f, --file to read patterns from a file. + +4. Added --enable-newline-is-cr and --enable-newline-is-lf to the configure +script, to force use of CR or LF instead of \n in the source. On non-Unix +systems, the value can be set in config.h. + +5. The limit of 200 on non-capturing parentheses is a _nesting_ limit, not an +absolute limit. Changed the text of the error message to make this clear, and +likewise updated the man page. + +6. The limit of 99 on the number of capturing subpatterns has been removed. +The new limit is 65535, which I hope will not be a "real" limit. + + +Release 3.3 01-Aug-00 +--------------------- + +There is some support for UTF-8 character strings. This is incomplete and +experimental. The documentation describes what is and what is not implemented. +Otherwise, this is just a bug-fixing release. + + +Release 3.0 01-Feb-00 +--------------------- + +1. A "configure" script is now used to configure PCRE for Unix systems. It +builds a Makefile, a config.h file, and the pcre-config script. + +2. PCRE is built as a shared library by default. + +3. There is support for POSIX classes such as [:alpha:]. + +5. There is an experimental recursion feature. + +---------------------------------------------------------------------------- + IMPORTANT FOR THOSE UPGRADING FROM VERSIONS BEFORE 2.00 + +Please note that there has been a change in the API such that a larger +ovector is required at matching time, to provide some additional workspace. +The new man page has details. This change was necessary in order to support +some of the new functionality in Perl 5.005. + + IMPORTANT FOR THOSE UPGRADING FROM VERSION 2.00 + +Another (I hope this is the last!) change has been made to the API for the +pcre_compile() function. An additional argument has been added to make it +possible to pass over a pointer to character tables built in the current +locale by pcre_maketables(). To use the default tables, this new arguement +should be passed as NULL. + + IMPORTANT FOR THOSE UPGRADING FROM VERSION 2.05 + +Yet another (and again I hope this really is the last) change has been made +to the API for the pcre_exec() function. An additional argument has been +added to make it possible to start the match other than at the start of the +subject string. This is important if there are lookbehinds. The new man +page has the details, but you just want to convert existing programs, all +you need to do is to stick in a new fifth argument to pcre_exec(), with a +value of zero. For example, change + + pcre_exec(pattern, extra, subject, length, options, ovec, ovecsize) +to + pcre_exec(pattern, extra, subject, length, 0, options, ovec, ovecsize) + +**** diff --git a/libs/pcre/NON-UNIX-USE b/libs/pcre/NON-UNIX-USE new file mode 100644 index 0000000000..459bdf2b4f --- /dev/null +++ b/libs/pcre/NON-UNIX-USE @@ -0,0 +1,269 @@ +Compiling PCRE on non-Unix systems +---------------------------------- + +See below for comments on Cygwin or MinGW and OpenVMS usage. I (Philip Hazel) +have no knowledge of Windows or VMS sytems and how their libraries work. The +items in the PCRE Makefile that relate to anything other than Unix-like systems +have been contributed by PCRE users. There are some other comments and files in +the Contrib directory on the ftp site that you may find useful. See + + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib + +If you want to compile PCRE for a non-Unix system (or perhaps, more strictly, +for a system that does not support "configure" and "make" files), note that +the basic PCRE library consists entirely of code written in Standard C, and so +should compile successfully on any system that has a Standard C compiler and +library. The C++ wrapper functions are a separate issue (see below). + + +GENERIC INSTRUCTIONS FOR THE C LIBRARY + +The following are generic comments about building PCRE. The interspersed +indented commands are suggestions from Mark Tetrode as to which commands you +might use on a Windows system to build a static library. + +(1) Copy or rename the file config.in as config.h, and change the macros that +define HAVE_STRERROR and HAVE_MEMMOVE to define them as 1 rather than 0. +Unfortunately, because of the way Unix autoconf works, the default setting has +to be 0. You may also want to make changes to other macros in config.h. In +particular, if you want to force a specific value for newline, you can define +the NEWLINE macro. The default is to use '\n', thereby using whatever value +your compiler gives to '\n'. + + rem Mark Tetrode's commands + copy config.in config.h + rem Use write, because notepad cannot handle UNIX files. Change values. + write config.h + +(2) Compile dftables.c as a stand-alone program, and then run it with +the single argument "pcre_chartables.c". This generates a set of standard +character tables and writes them to that file. + + rem Mark Tetrode's commands + rem Compile & run + cl -DSUPPORT_UTF8 -DSUPPORT_UCP dftables.c + dftables.exe pcre_chartables.c + +(3) Compile the following source files: + + pcre_chartables.c + pcre_compile.c + pcre_config.c + pcre_dfa_exec.c + pcre_exec.c + pcre_fullinfo.c + pcre_get.c + pcre_globals.c + pcre_info.c + pcre_maketables.c + pcre_ord2utf8.c + pcre_refcount.c + pcre_study.c + pcre_tables.c + pcre_try_flipped.c + pcre_ucp_searchfuncs.c + pcre_valid_utf8.c + pcre_version.c + pcre_xclass.c + +and link them all together into an object library in whichever form your system +keeps such libraries. This is the pcre C library. If your system has static and +shared libraries, you may have to do this once for each type. + + rem These comments are out-of-date, referring to a previous release which + rem had fewer source files. Replace with the file names from above. + rem Mark Tetrode's commands, for a static library + rem Compile & lib + cl -DSUPPORT_UTF8 -DSUPPORT_UCP -DPOSIX_MALLOC_THRESHOLD=10 /c maketables.c get.c study.c pcre.c + lib /OUT:pcre.lib maketables.obj get.obj study.obj pcre.obj + +(4) Similarly, compile pcreposix.c and link it (on its own) as the pcreposix +library. + + rem Mark Tetrode's commands, for a static library + rem Compile & lib + cl -DSUPPORT_UTF8 -DSUPPORT_UCP -DPOSIX_MALLOC_THRESHOLD=10 /c pcreposix.c + lib /OUT:pcreposix.lib pcreposix.obj + +(5) Compile the test program pcretest.c. This needs the functions in the +pcre and pcreposix libraries when linking. + + rem Mark Tetrode's commands + rem compile & link + cl /F0x400000 pcretest.c pcre.lib pcreposix.lib + +(6) Run pcretest on the testinput files in the testdata directory, and check +that the output matches the corresponding testoutput files. You must use the +-i option when checking testinput2. Note that the supplied files are in Unix +format, with just LF characters as line terminators. You may need to edit them +to change this if your system uses a different convention. + + rem Mark Tetrode's commands + pcretest testdata\testinput1 testdata\myoutput1 + windiff testdata\testoutput1 testdata\myoutput1 + pcretest -i testdata\testinput2 testdata\myoutput2 + windiff testdata\testoutput2 testdata\myoutput2 + pcretest testdata\testinput3 testdata\myoutput3 + windiff testdata\testoutput3 testdata\myoutput3 + pcretest testdata\testinput4 testdata\myoutput4 + windiff testdata\testoutput4 testdata\myoutput4 + pcretest testdata\testinput5 testdata\myoutput5 + windiff testdata\testoutput5 testdata\myoutput5 + pcretest testdata\testinput6 testdata\myoutput6 + windiff testdata\testoutput6 testdata\myoutput6 + +Note that there are now three more tests (7, 8, 9) that did not exist when Mark +wrote those comments. The test the new pcre_dfa_exec() function. + +(7) If you want to use the pcregrep command, compile and link pcregrep.c; it +uses only the basic PCRE library. + + +THE C++ WRAPPER FUNCTIONS + +The PCRE distribution now contains some C++ wrapper functions and tests, +contributed by Google Inc. On a system that can use "configure" and "make", +the functions are automatically built into a library called pcrecpp. It should +be straightforward to compile the .cc files manually on other systems. The +files called xxx_unittest.cc are test programs for each of the corresponding +xxx.cc files. + + +FURTHER REMARKS + +If you have a system without "configure" but where you can use a Makefile, edit +Makefile.in to create Makefile, substituting suitable values for the variables +at the head of the file. + +Some help in building a Win32 DLL of PCRE in GnuWin32 environments was +contributed by Paul Sokolovsky. These environments are Mingw32 +(http://www.xraylith.wisc.edu/~khan/software/gnu-win32/) and CygWin +(http://sourceware.cygnus.com/cygwin/). Paul comments: + + For CygWin, set CFLAGS=-mno-cygwin, and do 'make dll'. You'll get + pcre.dll (containing pcreposix also), libpcre.dll.a, and dynamically + linked pgrep and pcretest. If you have /bin/sh, run RunTest (three + main test go ok, locale not supported). + +Changes to do MinGW with autoconf 2.50 were supplied by Fred Cox +, who comments as follows: + + If you are using the PCRE DLL, the normal Unix style configure && make && + make check && make install should just work[*]. If you want to statically + link against the .a file, you must define PCRE_STATIC before including + pcre.h, otherwise the pcre_malloc and pcre_free exported functions will be + declared __declspec(dllimport), with hilarious results. See the configure.in + and pcretest.c for how it is done for the static test. + + Also, there will only be a libpcre.la, not a libpcreposix.la, as you + would expect from the Unix version. The single DLL includes the pcreposix + interface. + +[*] But note that the supplied test files are in Unix format, with just LF +characters as line terminators. You will have to edit them to change to CR LF +terminators. + +A script for building PCRE using Borland's C++ compiler for use with VPASCAL +was contributed by Alexander Tokarev. It is called makevp.bat. + +These are some further comments about Win32 builds from Mark Evans. They +were contributed before Fred Cox's changes were made, so it is possible that +they may no longer be relevant. + +"The documentation for Win32 builds is a bit shy. Under MSVC6 I +followed their instructions to the letter, but there were still +some things missing. + +(1) Must #define STATIC for entire project if linking statically. + (I see no reason to use DLLs for code this compact.) This of + course is a project setting in MSVC under Preprocessor. + +(2) Missing some #ifdefs relating to the function pointers + pcre_malloc and pcre_free. See my solution below. (The stubs + may not be mandatory but they made me feel better.)" + +========================= +#ifdef _WIN32 +#include + +void* malloc_stub(size_t N) +{ return malloc(N); } +void free_stub(void* p) +{ free(p); } +void *(*pcre_malloc)(size_t) = &malloc_stub; +void (*pcre_free)(void *) = &free_stub; + +#else + +void *(*pcre_malloc)(size_t) = malloc; +void (*pcre_free)(void *) = free; + +#endif +========================= + + +BUILDING PCRE ON OPENVMS + +Dan Mooney sent the following comments about building PCRE on OpenVMS. They +relate to an older version of PCRE that used fewer source files, so the exact +commands will need changing. See the current list of source files above. + +"It was quite easy to compile and link the library. I don't have a formal +make file but the attached file [reproduced below] contains the OpenVMS DCL +commands I used to build the library. I had to add #define +POSIX_MALLOC_THRESHOLD 10 to pcre.h since it was not defined anywhere. + +The library was built on: +O/S: HP OpenVMS v7.3-1 +Compiler: Compaq C v6.5-001-48BCD +Linker: vA13-01 + +The test results did not match 100% due to the issues you mention in your +documentation regarding isprint(), iscntrl(), isgraph() and ispunct(). I +modified some of the character tables temporarily and was able to get the +results to match. Tests using the fr locale did not match since I don't have +that locale loaded. The study size was always reported to be 3 less than the +value in the standard test output files." + +========================= +$! This DCL procedure builds PCRE on OpenVMS +$! +$! I followed the instructions in the non-unix-use file in the distribution. +$! +$ COMPILE == "CC/LIST/NOMEMBER_ALIGNMENT/PREFIX_LIBRARY_ENTRIES=ALL_ENTRIES +$ COMPILE DFTABLES.C +$ LINK/EXE=DFTABLES.EXE DFTABLES.OBJ +$ RUN DFTABLES.EXE/OUTPUT=CHARTABLES.C +$ COMPILE MAKETABLES.C +$ COMPILE GET.C +$ COMPILE STUDY.C +$! I had to set POSIX_MALLOC_THRESHOLD to 10 in PCRE.H since the symbol +$! did not seem to be defined anywhere. +$! I edited pcre.h and added #DEFINE SUPPORT_UTF8 to enable UTF8 support. +$ COMPILE PCRE.C +$ LIB/CREATE PCRE MAKETABLES.OBJ, GET.OBJ, STUDY.OBJ, PCRE.OBJ +$! I had to set POSIX_MALLOC_THRESHOLD to 10 in PCRE.H since the symbol +$! did not seem to be defined anywhere. +$ COMPILE PCREPOSIX.C +$ LIB/CREATE PCREPOSIX PCREPOSIX.OBJ +$ COMPILE PCRETEST.C +$ LINK/EXE=PCRETEST.EXE PCRETEST.OBJ, PCRE/LIB, PCREPOSIX/LIB +$! C programs that want access to command line arguments must be +$! defined as a symbol +$ PCRETEST :== "$ SYS$ROADSUSERS:[DMOONEY.REGEXP]PCRETEST.EXE" +$! Arguments must be enclosed in quotes. +$ PCRETEST "-C" +$! Test results: +$! +$! The test results did not match 100%. The functions isprint(), iscntrl(), +$! isgraph() and ispunct() on OpenVMS must not produce the same results +$! as the system that built the test output files provided with the +$! distribution. +$! +$! The study size did not match and was always 3 less on OpenVMS. +$! +$! Locale could not be set to fr +$! +========================= + +**** diff --git a/libs/pcre/README b/libs/pcre/README new file mode 100644 index 0000000000..24d0b97497 --- /dev/null +++ b/libs/pcre/README @@ -0,0 +1,528 @@ +README file for PCRE (Perl-compatible regular expression library) +----------------------------------------------------------------- + +The latest release of PCRE is always available from + + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-xxx.tar.gz + +Please read the NEWS file if you are upgrading from a previous release. + + +The PCRE APIs +------------- + +PCRE is written in C, and it has its own API. The distribution now includes a +set of C++ wrapper functions, courtesy of Google Inc. (see the pcrecpp man page +for details). + +Also included are a set of C wrapper functions that are based on the POSIX +API. These end up in the library called libpcreposix. Note that this just +provides a POSIX calling interface to PCRE: the regular expressions themselves +still follow Perl syntax and semantics. The header file for the POSIX-style +functions is called pcreposix.h. The official POSIX name is regex.h, but I +didn't want to risk possible problems with existing files of that name by +distributing it that way. To use it with an existing program that uses the +POSIX API, it will have to be renamed or pointed at by a link. + +If you are using the POSIX interface to PCRE and there is already a POSIX regex +library installed on your system, you must take care when linking programs to +ensure that they link with PCRE's libpcreposix library. Otherwise they may pick +up the "real" POSIX functions of the same name. + + +Documentation for PCRE +---------------------- + +If you install PCRE in the normal way, you will end up with an installed set of +man pages whose names all start with "pcre". The one that is just called "pcre" +lists all the others. In addition to these man pages, the PCRE documentation is +supplied in two other forms; however, as there is no standard place to install +them, they are left in the doc directory of the unpacked source distribution. +These forms are: + + 1. Files called doc/pcre.txt, doc/pcregrep.txt, and doc/pcretest.txt. The + first of these is a concatenation of the text forms of all the section 3 + man pages except those that summarize individual functions. The other two + are the text forms of the section 1 man pages for the pcregrep and + pcretest commands. Text forms are provided for ease of scanning with text + editors or similar tools. + + 2. A subdirectory called doc/html contains all the documentation in HTML + form, hyperlinked in various ways, and rooted in a file called + doc/index.html. + + +Contributions by users of PCRE +------------------------------ + +You can find contributions from PCRE users in the directory + + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/Contrib + +where there is also a README file giving brief descriptions of what they are. +Several of them provide support for compiling PCRE on various flavours of +Windows systems (I myself do not use Windows). Some are complete in themselves; +others are pointers to URLs containing relevant files. + + +Building PCRE on a Unix-like system +----------------------------------- + +If you are using HP's ANSI C++ compiler (aCC), please see the special note +in the section entitled "Using HP's ANSI C++ compiler (aCC)" below. + +To build PCRE on a Unix-like system, first run the "configure" command from the +PCRE distribution directory, with your current directory set to the directory +where you want the files to be created. This command is a standard GNU +"autoconf" configuration script, for which generic instructions are supplied in +INSTALL. + +Most commonly, people build PCRE within its own distribution directory, and in +this case, on many systems, just running "./configure" is sufficient, but the +usual methods of changing standard defaults are available. For example: + +CFLAGS='-O2 -Wall' ./configure --prefix=/opt/local + +specifies that the C compiler should be run with the flags '-O2 -Wall' instead +of the default, and that "make install" should install PCRE under /opt/local +instead of the default /usr/local. + +If you want to build in a different directory, just run "configure" with that +directory as current. For example, suppose you have unpacked the PCRE source +into /source/pcre/pcre-xxx, but you want to build it in /build/pcre/pcre-xxx: + +cd /build/pcre/pcre-xxx +/source/pcre/pcre-xxx/configure + +PCRE is written in C and is normally compiled as a C library. However, it is +possible to build it as a C++ library, though the provided building apparatus +does not have any features to support this. + +There are some optional features that can be included or omitted from the PCRE +library. You can read more about them in the pcrebuild man page. + +. If you want to suppress the building of the C++ wrapper library, you can add + --disable-cpp to the "configure" command. Otherwise, when "configure" is run, + will try to find a C++ compiler and C++ header files, and if it succeeds, it + will try to build the C++ wrapper. + +. If you want to make use of the support for UTF-8 character strings in PCRE, + you must add --enable-utf8 to the "configure" command. Without it, the code + for handling UTF-8 is not included in the library. (Even when included, it + still has to be enabled by an option at run time.) + +. If, in addition to support for UTF-8 character strings, you want to include + support for the \P, \p, and \X sequences that recognize Unicode character + properties, you must add --enable-unicode-properties to the "configure" + command. This adds about 30K to the size of the library (in the form of a + property table); only the basic two-letter properties such as Lu are + supported. + +. You can build PCRE to recognize either CR or LF or the sequence CRLF as + indicating the end of a line. Whatever you specify at build time is the + default; the caller of PCRE can change the selection at run time. The default + newline indicator is a single LF character (the Unix standard). You can + specify the default newline indicator by adding --newline-is-cr or + --newline-is-lf or --newline-is-crlf to the "configure" command, + respectively. + +. When called via the POSIX interface, PCRE uses malloc() to get additional + storage for processing capturing parentheses if there are more than 10 of + them. You can increase this threshold by setting, for example, + + --with-posix-malloc-threshold=20 + + on the "configure" command. + +. PCRE has a counter that can be set to limit the amount of resources it uses. + If the limit is exceeded during a match, the match fails. The default is ten + million. You can change the default by setting, for example, + + --with-match-limit=500000 + + on the "configure" command. This is just the default; individual calls to + pcre_exec() can supply their own value. There is discussion on the pcreapi + man page. + +. There is a separate counter that limits the depth of recursive function calls + during a matching process. This also has a default of ten million, which is + essentially "unlimited". You can change the default by setting, for example, + + --with-match-limit-recursion=500000 + + Recursive function calls use up the runtime stack; running out of stack can + cause programs to crash in strange ways. There is a discussion about stack + sizes in the pcrestack man page. + +. The default maximum compiled pattern size is around 64K. You can increase + this by adding --with-link-size=3 to the "configure" command. You can + increase it even more by setting --with-link-size=4, but this is unlikely + ever to be necessary. If you build PCRE with an increased link size, test 2 + (and 5 if you are using UTF-8) will fail. Part of the output of these tests + is a representation of the compiled pattern, and this changes with the link + size. + +. You can build PCRE so that its internal match() function that is called from + pcre_exec() does not call itself recursively. Instead, it uses blocks of data + from the heap via special functions pcre_stack_malloc() and pcre_stack_free() + to save data that would otherwise be saved on the stack. To build PCRE like + this, use + + --disable-stack-for-recursion + + on the "configure" command. PCRE runs more slowly in this mode, but it may be + necessary in environments with limited stack sizes. This applies only to the + pcre_exec() function; it does not apply to pcre_dfa_exec(), which does not + use deeply nested recursion. + +The "configure" script builds eight files for the basic C library: + +. Makefile is the makefile that builds the library +. config.h contains build-time configuration options for the library +. pcre-config is a script that shows the settings of "configure" options +. libpcre.pc is data for the pkg-config command +. libtool is a script that builds shared and/or static libraries +. RunTest is a script for running tests on the library +. RunGrepTest is a script for running tests on the pcregrep command + +In addition, if a C++ compiler is found, the following are also built: + +. pcrecpp.h is the header file for programs that call PCRE via the C++ wrapper +. pcre_stringpiece.h is the header for the C++ "stringpiece" functions + +The "configure" script also creates config.status, which is an executable +script that can be run to recreate the configuration, and config.log, which +contains compiler output from tests that "configure" runs. + +Once "configure" has run, you can run "make". It builds two libraries, called +libpcre and libpcreposix, a test program called pcretest, and the pcregrep +command. If a C++ compiler was found on your system, it also builds the C++ +wrapper library, which is called libpcrecpp, and some test programs called +pcrecpp_unittest, pcre_scanner_unittest, and pcre_stringpiece_unittest. + +The command "make test" runs all the appropriate tests. Details of the PCRE +tests are given in a separate section of this document, below. + +You can use "make install" to copy the libraries, the public header files +pcre.h, pcreposix.h, pcrecpp.h, and pcre_stringpiece.h (the last two only if +the C++ wrapper was built), and the man pages to appropriate live directories +on your system, in the normal way. + +If you want to remove PCRE from your system, you can run "make uninstall". +This removes all the files that "make install" installed. However, it does not +remove any directories, because these are often shared with other programs. + + +Retrieving configuration information on Unix-like systems +--------------------------------------------------------- + +Running "make install" also installs the command pcre-config, which can be used +to recall information about the PCRE configuration and installation. For +example: + + pcre-config --version + +prints the version number, and + + pcre-config --libs + +outputs information about where the library is installed. This command can be +included in makefiles for programs that use PCRE, saving the programmer from +having to remember too many details. + +The pkg-config command is another system for saving and retrieving information +about installed libraries. Instead of separate commands for each library, a +single command is used. For example: + + pkg-config --cflags pcre + +The data is held in *.pc files that are installed in a directory called +pkgconfig. + + +Shared libraries on Unix-like systems +------------------------------------- + +The default distribution builds PCRE as shared libraries and static libraries, +as long as the operating system supports shared libraries. Shared library +support relies on the "libtool" script which is built as part of the +"configure" process. + +The libtool script is used to compile and link both shared and static +libraries. They are placed in a subdirectory called .libs when they are newly +built. The programs pcretest and pcregrep are built to use these uninstalled +libraries (by means of wrapper scripts in the case of shared libraries). When +you use "make install" to install shared libraries, pcregrep and pcretest are +automatically re-built to use the newly installed shared libraries before being +installed themselves. However, the versions left in the source directory still +use the uninstalled libraries. + +To build PCRE using static libraries only you must use --disable-shared when +configuring it. For example: + +./configure --prefix=/usr/gnu --disable-shared + +Then run "make" in the usual way. Similarly, you can use --disable-static to +build only shared libraries. + + +Cross-compiling on a Unix-like system +------------------------------------- + +You can specify CC and CFLAGS in the normal way to the "configure" command, in +order to cross-compile PCRE for some other host. However, during the building +process, the dftables.c source file is compiled *and run* on the local host, in +order to generate the default character tables (the chartables.c file). It +therefore needs to be compiled with the local compiler, not the cross compiler. +You can do this by specifying CC_FOR_BUILD (and if necessary CFLAGS_FOR_BUILD; +there are also CXX_FOR_BUILD and CXXFLAGS_FOR_BUILD for the C++ wrapper) +when calling the "configure" command. If they are not specified, they default +to the values of CC and CFLAGS. + + +Using HP's ANSI C++ compiler (aCC) +---------------------------------- + +Unless C++ support is disabled by specifiying the "--disable-cpp" option of the +"configure" script, you *must* include the "-AA" option in the CXXFLAGS +environment variable in order for the C++ components to compile correctly. + +Also, note that the aCC compiler on PA-RISC platforms may have a defect whereby +needed libraries fail to get included when specifying the "-AA" compiler +option. If you experience unresolved symbols when linking the C++ programs, +use the workaround of specifying the following environment variable prior to +running the "configure" script: + + CXXLDFLAGS="-lstd_v2 -lCsup_v2" + + +Building on non-Unix systems +---------------------------- + +For a non-Unix system, read the comments in the file NON-UNIX-USE, though if +the system supports the use of "configure" and "make" you may be able to build +PCRE in the same way as for Unix systems. + +PCRE has been compiled on Windows systems and on Macintoshes, but I don't know +the details because I don't use those systems. It should be straightforward to +build PCRE on any system that has a Standard C compiler, because it uses only +Standard C functions. + + +Testing PCRE +------------ + +To test PCRE on a Unix system, run the RunTest script that is created by the +configuring process. There is also a script called RunGrepTest that tests the +options of the pcregrep command. If the C++ wrapper library is build, three +test programs called pcrecpp_unittest, pcre_scanner_unittest, and +pcre_stringpiece_unittest are provided. + +Both the scripts and all the program tests are run if you obey "make runtest", +"make check", or "make test". For other systems, see the instructions in +NON-UNIX-USE. + +The RunTest script runs the pcretest test program (which is documented in its +own man page) on each of the testinput files (in the testdata directory) in +turn, and compares the output with the contents of the corresponding testoutput +file. A file called testtry is used to hold the main output from pcretest +(testsavedregex is also used as a working file). To run pcretest on just one of +the test files, give its number as an argument to RunTest, for example: + + RunTest 2 + +The first file can also be fed directly into the perltest script to check that +Perl gives the same results. The only difference you should see is in the first +few lines, where the Perl version is given instead of the PCRE version. + +The second set of tests check pcre_fullinfo(), pcre_info(), pcre_study(), +pcre_copy_substring(), pcre_get_substring(), pcre_get_substring_list(), error +detection, and run-time flags that are specific to PCRE, as well as the POSIX +wrapper API. It also uses the debugging flag to check some of the internals of +pcre_compile(). + +If you build PCRE with a locale setting that is not the standard C locale, the +character tables may be different (see next paragraph). In some cases, this may +cause failures in the second set of tests. For example, in a locale where the +isprint() function yields TRUE for characters in the range 128-255, the use of +[:isascii:] inside a character class defines a different set of characters, and +this shows up in this test as a difference in the compiled code, which is being +listed for checking. Where the comparison test output contains [\x00-\x7f] the +test will contain [\x00-\xff], and similarly in some other cases. This is not a +bug in PCRE. + +The third set of tests checks pcre_maketables(), the facility for building a +set of character tables for a specific locale and using them instead of the +default tables. The tests make use of the "fr_FR" (French) locale. Before +running the test, the script checks for the presence of this locale by running +the "locale" command. If that command fails, or if it doesn't include "fr_FR" +in the list of available locales, the third test cannot be run, and a comment +is output to say why. If running this test produces instances of the error + + ** Failed to set locale "fr_FR" + +in the comparison output, it means that locale is not available on your system, +despite being listed by "locale". This does not mean that PCRE is broken. + +The fourth test checks the UTF-8 support. It is not run automatically unless +PCRE is built with UTF-8 support. To do this you must set --enable-utf8 when +running "configure". This file can be also fed directly to the perltest script, +provided you are running Perl 5.8 or higher. (For Perl 5.6, a small patch, +commented in the script, can be be used.) + +The fifth test checks error handling with UTF-8 encoding, and internal UTF-8 +features of PCRE that are not relevant to Perl. + +The sixth and test checks the support for Unicode character properties. It it +not run automatically unless PCRE is built with Unicode property support. To to +this you must set --enable-unicode-properties when running "configure". + +The seventh, eighth, and ninth tests check the pcre_dfa_exec() alternative +matching function, in non-UTF-8 mode, UTF-8 mode, and UTF-8 mode with Unicode +property support, respectively. The eighth and ninth tests are not run +automatically unless PCRE is build with the relevant support. + + +Character tables +---------------- + +PCRE uses four tables for manipulating and identifying characters whose values +are less than 256. The final argument of the pcre_compile() function is a +pointer to a block of memory containing the concatenated tables. A call to +pcre_maketables() can be used to generate a set of tables in the current +locale. If the final argument for pcre_compile() is passed as NULL, a set of +default tables that is built into the binary is used. + +The source file called chartables.c contains the default set of tables. This is +not supplied in the distribution, but is built by the program dftables +(compiled from dftables.c), which uses the ANSI C character handling functions +such as isalnum(), isalpha(), isupper(), islower(), etc. to build the table +sources. This means that the default C locale which is set for your system will +control the contents of these default tables. You can change the default tables +by editing chartables.c and then re-building PCRE. If you do this, you should +probably also edit Makefile to ensure that the file doesn't ever get +re-generated. + +The first two 256-byte tables provide lower casing and case flipping functions, +respectively. The next table consists of three 32-byte bit maps which identify +digits, "word" characters, and white space, respectively. These are used when +building 32-byte bit maps that represent character classes. + +The final 256-byte table has bits indicating various character types, as +follows: + + 1 white space character + 2 letter + 4 decimal digit + 8 hexadecimal digit + 16 alphanumeric or '_' + 128 regular expression metacharacter or binary zero + +You should not alter the set of characters that contain the 128 bit, as that +will cause PCRE to malfunction. + + +Manifest +-------- + +The distribution should contain the following files: + +(A) The actual source files of the PCRE library functions and their + headers: + + dftables.c auxiliary program for building chartables.c + + pcreposix.c ) + pcre_compile.c ) + pcre_config.c ) + pcre_dfa_exec.c ) + pcre_exec.c ) + pcre_fullinfo.c ) + pcre_get.c ) sources for the functions in the library, + pcre_globals.c ) and some internal functions that they use + pcre_info.c ) + pcre_maketables.c ) + pcre_ord2utf8.c ) + pcre_refcount.c ) + pcre_study.c ) + pcre_tables.c ) + pcre_try_flipped.c ) + pcre_ucp_searchfuncs.c) + pcre_valid_utf8.c ) + pcre_version.c ) + pcre_xclass.c ) + ucptable.c ) + + pcre_printint.src ) debugging function that is #included in pcretest, and + ) can also be #included in pcre_compile() + + pcre.h the public PCRE header file + pcreposix.h header for the external POSIX wrapper API + pcre_internal.h header for internal use + ucp.h ) headers concerned with + ucpinternal.h ) Unicode property handling + config.in template for config.h, which is built by configure + + pcrecpp.h the header file for the C++ wrapper + pcrecpparg.h.in "source" for another C++ header file + pcrecpp.cc ) + pcre_scanner.cc ) source for the C++ wrapper library + + pcre_stringpiece.h.in "source" for pcre_stringpiece.h, the header for the + C++ stringpiece functions + pcre_stringpiece.cc source for the C++ stringpiece functions + +(B) Auxiliary files: + + AUTHORS information about the author of PCRE + ChangeLog log of changes to the code + INSTALL generic installation instructions + LICENCE conditions for the use of PCRE + COPYING the same, using GNU's standard name + Makefile.in template for Unix Makefile, which is built by configure + NEWS important changes in this release + NON-UNIX-USE notes on building PCRE on non-Unix systems + README this file + RunTest.in template for a Unix shell script for running tests + RunGrepTest.in template for a Unix shell script for pcregrep tests + config.guess ) files used by libtool, + config.sub ) used only when building a shared library + config.h.in "source" for the config.h header file + configure a configuring shell script (built by autoconf) + configure.ac the autoconf input used to build configure + doc/Tech.Notes notes on the encoding + doc/*.3 man page sources for the PCRE functions + doc/*.1 man page sources for pcregrep and pcretest + doc/html/* HTML documentation + doc/pcre.txt plain text version of the man pages + doc/pcretest.txt plain text documentation of test program + doc/perltest.txt plain text documentation of Perl test program + install-sh a shell script for installing files + libpcre.pc.in "source" for libpcre.pc for pkg-config + ltmain.sh file used to build a libtool script + mkinstalldirs script for making install directories + pcretest.c comprehensive test program + pcredemo.c simple demonstration of coding calls to PCRE + perltest Perl test program + pcregrep.c source of a grep utility that uses PCRE + pcre-config.in source of script which retains PCRE information + pcrecpp_unittest.c ) + pcre_scanner_unittest.c ) test programs for the C++ wrapper + pcre_stringpiece_unittest.c ) + testdata/testinput* test data for main library tests + testdata/testoutput* expected test results + testdata/grep* input and output for pcregrep tests + +(C) Auxiliary files for Win32 DLL + + libpcre.def + libpcreposix.def + +(D) Auxiliary file for VPASCAL + + makevp.bat + +Philip Hazel +Email local part: ph10 +Email domain: cam.ac.uk +June 2006 diff --git a/libs/pcre/RunGrepTest.in b/libs/pcre/RunGrepTest.in new file mode 100644 index 0000000000..86ada8dbf4 --- /dev/null +++ b/libs/pcre/RunGrepTest.in @@ -0,0 +1,208 @@ +#! /bin/sh + +# This file is generated by configure from RunGrepTest.in. Make any changes +# to that file. + +echo "Testing pcregrep" +./pcregrep -V + +# Run pcregrep tests. The assumption is that the PCRE tests check the library +# itself. What we are checking here is the file handling and options that are +# supported by pcregrep. + +cf=diff +valgrind= +if [ ! -d testdata ] ; then + ln -s @top_srcdir@/testdata testdata +fi +testdata=./testdata + +while [ $# -gt 0 ] ; do + case $1 in + valgrind) valgrind="valgrind -q --leak-check=no";; + *) echo "Unknown argument $1"; exit 1;; + esac + shift +done + +echo "---------------------------- Test 1 ------------------------------" >testtry +$valgrind ./pcregrep PATTERN $testdata/grepinput >>testtry + +echo "---------------------------- Test 2 ------------------------------" >>testtry +$valgrind ./pcregrep '^PATTERN' $testdata/grepinput >>testtry + +echo "---------------------------- Test 3 ------------------------------" >>testtry +$valgrind ./pcregrep -in PATTERN $testdata/grepinput >>testtry + +echo "---------------------------- Test 4 ------------------------------" >>testtry +$valgrind ./pcregrep -ic PATTERN $testdata/grepinput >>testtry + +echo "---------------------------- Test 5 ------------------------------" >>testtry +$valgrind ./pcregrep -in PATTERN $testdata/grepinput $testdata/grepinputx >>testtry + +echo "---------------------------- Test 6 ------------------------------" >>testtry +$valgrind ./pcregrep -inh PATTERN $testdata/grepinput $testdata/grepinputx >>testtry + +echo "---------------------------- Test 7 ------------------------------" >>testtry +$valgrind ./pcregrep -il PATTERN $testdata/grepinput $testdata/grepinputx >>testtry + +echo "---------------------------- Test 8 ------------------------------" >>testtry +$valgrind ./pcregrep -l PATTERN $testdata/grepinput $testdata/grepinputx >>testtry + +echo "---------------------------- Test 9 ------------------------------" >>testtry +$valgrind ./pcregrep -q PATTERN $testdata/grepinput $testdata/grepinputx >>testtry +echo "RC=$?" >>testtry + +echo "---------------------------- Test 10 -----------------------------" >>testtry +$valgrind ./pcregrep -q NEVER-PATTERN $testdata/grepinput $testdata/grepinputx >>testtry +echo "RC=$?" >>testtry + +echo "---------------------------- Test 11 -----------------------------" >>testtry +$valgrind ./pcregrep -vn pattern $testdata/grepinputx >>testtry + +echo "---------------------------- Test 12 -----------------------------" >>testtry +$valgrind ./pcregrep -ix pattern $testdata/grepinputx >>testtry + +echo "---------------------------- Test 13 -----------------------------" >>testtry +$valgrind ./pcregrep -f$testdata/greplist $testdata/grepinputx >>testtry + +echo "---------------------------- Test 14 -----------------------------" >>testtry +$valgrind ./pcregrep -w pat $testdata/grepinput $testdata/grepinputx >>testtry + +echo "---------------------------- Test 15 -----------------------------" >>testtry +$valgrind ./pcregrep 'abc^*' $testdata/grepinput 2>>testtry >>testtry + +echo "---------------------------- Test 16 -----------------------------" >>testtry +$valgrind ./pcregrep abc $testdata/grepinput $testdata/nonexistfile 2>>testtry >>testtry + +echo "---------------------------- Test 17 -----------------------------" >>testtry +$valgrind ./pcregrep -M 'the\noutput' $testdata/grepinput >>testtry + +echo "---------------------------- Test 18 -----------------------------" >>testtry +$valgrind ./pcregrep -Mn '(the\noutput|dog\.\n--)' $testdata/grepinput >>testtry + +echo "---------------------------- Test 19 -----------------------------" >>testtry +$valgrind ./pcregrep -Mix 'Pattern' $testdata/grepinputx >>testtry + +echo "---------------------------- Test 20 -----------------------------" >>testtry +$valgrind ./pcregrep -Mixn 'complete pair\nof lines' $testdata/grepinputx >>testtry + +echo "---------------------------- Test 21 -----------------------------" >>testtry +$valgrind ./pcregrep -nA3 'four' $testdata/grepinputx >>testtry + +echo "---------------------------- Test 22 -----------------------------" >>testtry +$valgrind ./pcregrep -nB3 'four' $testdata/grepinputx >>testtry + +echo "---------------------------- Test 23 -----------------------------" >>testtry +$valgrind ./pcregrep -C3 'four' $testdata/grepinputx >>testtry + +echo "---------------------------- Test 24 -----------------------------" >>testtry +$valgrind ./pcregrep -A9 'four' $testdata/grepinputx >>testtry + +echo "---------------------------- Test 25 -----------------------------" >>testtry +$valgrind ./pcregrep -nB9 'four' $testdata/grepinputx >>testtry + +echo "---------------------------- Test 26 -----------------------------" >>testtry +$valgrind ./pcregrep -A9 -B9 'four' $testdata/grepinputx >>testtry + +echo "---------------------------- Test 27 -----------------------------" >>testtry +$valgrind ./pcregrep -A10 'four' $testdata/grepinputx >>testtry + +echo "---------------------------- Test 28 -----------------------------" >>testtry +$valgrind ./pcregrep -nB10 'four' $testdata/grepinputx >>testtry + +echo "---------------------------- Test 29 -----------------------------" >>testtry +$valgrind ./pcregrep -C12 -B10 'four' $testdata/grepinputx >>testtry + +echo "---------------------------- Test 30 -----------------------------" >>testtry +$valgrind ./pcregrep -inB3 'pattern' $testdata/grepinput $testdata/grepinputx >>testtry + +echo "---------------------------- Test 31 -----------------------------" >>testtry +$valgrind ./pcregrep -inA3 'pattern' $testdata/grepinput $testdata/grepinputx >>testtry + +echo "---------------------------- Test 32 -----------------------------" >>testtry +$valgrind ./pcregrep -L 'fox' $testdata/grepinput $testdata/grepinputx >>testtry + +echo "---------------------------- Test 33 -----------------------------" >>testtry +$valgrind ./pcregrep 'fox' $testdata/grepnonexist >>testtry 2>&1 +echo "RC=$?" >>testtry + +echo "---------------------------- Test 34 -----------------------------" >>testtry +$valgrind ./pcregrep -s 'fox' $testdata/grepnonexist >>testtry 2>&1 +echo "RC=$?" >>testtry + +echo "---------------------------- Test 35 -----------------------------" >>testtry +$valgrind ./pcregrep -L -r --include=grepinputx 'fox' $testdata >>testtry +echo "RC=$?" >>testtry + +echo "---------------------------- Test 36 -----------------------------" >>testtry +$valgrind ./pcregrep -L -r --include=grepinput --exclude 'grepinput$' 'fox' $testdata >>testtry +echo "RC=$?" >>testtry + +echo "---------------------------- Test 37 -----------------------------" >>testtry +$valgrind ./pcregrep '^(a+)*\d' $testdata/grepinput >>testtry 2>teststderr +echo "RC=$?" >>testtry +echo "======== STDERR ========" >>testtry +cat teststderr >>testtry + +echo "---------------------------- Test 38 ------------------------------" >>testtry +$valgrind ./pcregrep '>\x00<' $testdata/grepinput >>testtry + +echo "---------------------------- Test 39 ------------------------------" >>testtry +$valgrind ./pcregrep -A1 'before the binary zero' $testdata/grepinput >>testtry + +echo "---------------------------- Test 40 ------------------------------" >>testtry +$valgrind ./pcregrep -B1 'after the binary zero' $testdata/grepinput >>testtry + +echo "---------------------------- Test 41 ------------------------------" >>testtry +$valgrind ./pcregrep -B1 -o '\w+ the binary zero' $testdata/grepinput >>testtry + +echo "---------------------------- Test 41 ------------------------------" >>testtry +$valgrind ./pcregrep -B1 -onH '\w+ the binary zero' $testdata/grepinput >>testtry + +echo "---------------------------- Test 42 ------------------------------" >>testtry +$valgrind ./pcregrep -on 'before|zero|after' $testdata/grepinput >>testtry + +echo "---------------------------- Test 43 ------------------------------" >>testtry +$valgrind ./pcregrep -on -e before -e zero -e after $testdata/grepinput >>testtry + +echo "---------------------------- Test 44 ------------------------------" >>testtry +$valgrind ./pcregrep -on -f $testdata/greplist -e binary $testdata/grepinput >>testtry + +echo "---------------------------- Test 45 ------------------------------" >>testtry +$valgrind ./pcregrep -e abc -e '(unclosed' $testdata/grepinput 2>>testtry >>testtry + +echo "---------------------------- Test 46 ------------------------------" >>testtry +$valgrind ./pcregrep -Fx "AB.VE +elephant" $testdata/grepinput >>testtry + +echo "---------------------------- Test 47 ------------------------------" >>testtry +$valgrind ./pcregrep -F "AB.VE +elephant" $testdata/grepinput >>testtry + +echo "---------------------------- Test 48 ------------------------------" >>testtry +$valgrind ./pcregrep -F -e DATA -e "AB.VE +elephant" $testdata/grepinput >>testtry + +echo "---------------------------- Test 49 ------------------------------" >>testtry +$valgrind ./pcregrep "^(abc|def|ghi|jkl)" $testdata/grepinputx >>testtry + +echo "---------------------------- Test 50 ------------------------------" >>testtry +$valgrind ./pcregrep -N CR "^(abc|def|ghi|jkl)" $testdata/grepinputx >>testtry + +echo "---------------------------- Test 51 ------------------------------" >>testtry +$valgrind ./pcregrep --newline=crlf "^(abc|def|ghi|jkl)" $testdata/grepinputx >>testtry + +echo "---------------------------- Test 52 ------------------------------" >>testtry +$valgrind ./pcregrep --newline=cr -F "def jkl" $testdata/grepinputx >>testtry + +echo "---------------------------- Test 53 ------------------------------" >>testtry +$valgrind ./pcregrep --newline=crlf -F "xxx +jkl" $testdata/grepinputx >>testtry + +# Now compare the results. + +$cf testtry $testdata/grepoutput +if [ $? != 0 ] ; then exit 1; else exit 0; fi + +# End diff --git a/libs/pcre/RunTest.in b/libs/pcre/RunTest.in new file mode 100755 index 0000000000..f6518ed57e --- /dev/null +++ b/libs/pcre/RunTest.in @@ -0,0 +1,258 @@ +#! /bin/sh + +# This file is generated by configure from RunTest.in. Make any changes +# to that file. + +# Run PCRE tests + +cf=diff +valgrind= +if [ ! -d testdata ] ; then + ln -s @top_srcdir@/testdata testdata +fi +testdata=./testdata + + +# Select which tests to run; if no selection, run all + +do1=no +do2=no +do3=no +do4=no +do5=no +do6=no +do7=no +do8=no +do9=no + +while [ $# -gt 0 ] ; do + case $1 in + 1) do1=yes;; + 2) do2=yes;; + 3) do3=yes;; + 4) do4=yes;; + 5) do5=yes;; + 6) do6=yes;; + 7) do7=yes;; + 8) do8=yes;; + 9) do9=yes;; + valgrind) valgrind="valgrind -q";; + *) echo "Unknown test number $1"; exit 1;; + esac + shift +done + +if [ "@LINK_SIZE@" != "" -a "@LINK_SIZE@" != "-DLINK_SIZE=2" ] ; then + if [ $do2 = yes ] ; then + echo "Can't run test 2 with an internal link size other than 2" + exit 1 + fi + if [ $do5 = yes ] ; then + echo "Can't run test 5 with an internal link size other than 2" + exit 1 + fi + if [ $do6 = yes ] ; then + echo "Can't run test 6 with an internal link size other than 2" + exit 1 + fi +fi + +if [ "@UTF8@" = "" ] ; then + if [ $do4 = yes ] ; then + echo "Can't run test 4 because UTF-8 support is not configured" + exit 1 + fi + if [ $do5 = yes ] ; then + echo "Can't run test 5 because UTF-8 support is not configured" + exit 1 + fi + if [ $do6 = yes ] ; then + echo "Can't run test 6 because UTF-8 support is not configured" + exit 1 + fi + if [ $do8 = yes ] ; then + echo "Can't run test 8 because UTF-8 support is not configured" + exit 1 + fi + if [ $do9 = yes ] ; then + echo "Can't run test 9 because UTF-8 support is not configured" + exit 1 + fi +fi + +if [ "@UCP@" = "" ] ; then + if [ $do6 = yes ] ; then + echo "Can't run test 6 because Unicode property support is not configured" + exit 1 + fi + if [ $do9 = yes ] ; then + echo "Can't run test 9 because Unicode property support is not configured" + exit 1 + fi +fi + +if [ $do1 = no -a $do2 = no -a $do3 = no -a $do4 = no -a \ + $do5 = no -a $do6 = no -a $do7 = no -a $do8 = no -a \ + $do9 = no ] ; then + do1=yes + do2=yes + do3=yes + if [ "@UTF8@" != "" ] ; then do4=yes; fi + if [ "@UTF8@" != "" ] ; then do5=yes; fi + if [ "@UTF8@" != "" -a "@UCP@" != "" ] ; then do6=yes; fi + do7=yes + if [ "@UTF8@" != "" ] ; then do8=yes; fi + if [ "@UTF8@" != "" -a "@UCP@" != "" ] ; then do9=yes; fi +fi + +# Show which release + +./pcretest /dev/null + +# Primary test, Perl-compatible + +if [ $do1 = yes ] ; then + echo "Test 1: main functionality (Perl compatible)" + $valgrind ./pcretest -q $testdata/testinput1 testtry + if [ $? = 0 ] ; then + $cf testtry $testdata/testoutput1 + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo "OK" + echo " " +fi + +# PCRE tests that are not Perl-compatible - API & error tests, mostly + +if [ $do2 = yes ] ; then + if [ "@LINK_SIZE@" = "" -o "@LINK_SIZE@" = "-DLINK_SIZE=2" ] ; then + echo "Test 2: API and error handling (not Perl compatible)" + $valgrind ./pcretest -q -i $testdata/testinput2 testtry + if [ $? = 0 ] ; then + $cf testtry $testdata/testoutput2 + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo "OK" + echo " " + else + echo Test 2 skipped for link size other than 2 \(@LINK_SIZE@\) + echo " " + fi +fi + +# Locale-specific tests, provided the "fr_FR" locale is available + +if [ $do3 = yes ] ; then + locale -a | grep '^fr_FR$' >/dev/null + if [ $? -eq 0 ] ; then + echo "Test 3: locale-specific features (using 'fr_FR' locale)" + $valgrind ./pcretest -q $testdata/testinput3 testtry + if [ $? = 0 ] ; then + $cf testtry $testdata/testoutput3 + if [ $? != 0 ] ; then + echo " " + echo "Locale test did not run entirely successfully." + echo "This usually means that there is a problem with the locale" + echo "settings rather than a bug in PCRE." + else + echo "OK" + fi + echo " " + else exit 1 + fi + else + echo "Cannot test locale-specific features - 'fr_FR' locale not found," + echo "or the \"locale\" command is not available to check for it." + echo " " + fi +fi + +# Additional tests for UTF8 support + +if [ $do4 = yes ] ; then + echo "Test 4: UTF-8 support (Perl compatible)" + $valgrind ./pcretest -q $testdata/testinput4 testtry + if [ $? = 0 ] ; then + $cf testtry $testdata/testoutput4 + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo "OK" + echo " " +fi + +if [ $do5 = yes ] ; then + if [ "@LINK_SIZE@" = "" -o "@LINK_SIZE@" = "-DLINK_SIZE=2" ] ; then + echo "Test 5: API and internals for UTF-8 support (not Perl compatible)" + $valgrind ./pcretest -q $testdata/testinput5 testtry + if [ $? = 0 ] ; then + $cf testtry $testdata/testoutput5 + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo "OK" + echo " " + else + echo Test 5 skipped for link size other than 2 \(@LINK_SIZE@\) + echo " " + fi +fi + +if [ $do6 = yes ] ; then + if [ "@LINK_SIZE@" = "" -o "@LINK_SIZE@" = "-DLINK_SIZE=2" ] ; then + echo "Test 6: Unicode property support" + $valgrind ./pcretest -q $testdata/testinput6 testtry + if [ $? = 0 ] ; then + $cf testtry $testdata/testoutput6 + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo "OK" + echo " " + else + echo Test 6 skipped for link size other than 2 \(@LINK_SIZE@\) + echo " " + fi +fi + +# Tests for DFA matching support + +if [ $do7 = yes ] ; then + echo "Test 7: DFA matching" + $valgrind ./pcretest -q -dfa $testdata/testinput7 testtry + if [ $? = 0 ] ; then + $cf testtry $testdata/testoutput7 + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo "OK" + echo " " +fi + +if [ $do8 = yes ] ; then + echo "Test 8: DFA matching with UTF-8" + $valgrind ./pcretest -q -dfa $testdata/testinput8 testtry + if [ $? = 0 ] ; then + $cf testtry $testdata/testoutput8 + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo "OK" + echo " " +fi + +if [ $do9 = yes ] ; then + echo "Test 9: DFA matching with Unicode properties" + $valgrind ./pcretest -q -dfa $testdata/testinput9 testtry + if [ $? = 0 ] ; then + $cf testtry $testdata/testoutput9 + if [ $? != 0 ] ; then exit 1; fi + else exit 1 + fi + echo "OK" + echo " " +fi + +# End diff --git a/libs/pcre/config.guess b/libs/pcre/config.guess new file mode 100755 index 0000000000..01edd7ba35 --- /dev/null +++ b/libs/pcre/config.guess @@ -0,0 +1,1495 @@ +#! /bin/sh +# Attempt to guess a canonical system name. +# Copyright (C) 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, +# 2000, 2001, 2002, 2003, 2004, 2005 Free Software Foundation, Inc. + +timestamp='2005-12-23' + +# This file is free software; you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, but +# WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +# General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 51 Franklin Street - Fifth Floor, Boston, MA +# 02110-1301, USA. +# +# As a special exception to the GNU General Public License, if you +# distribute this file as part of a program that contains a +# configuration script generated by Autoconf, you may include it under +# the same distribution terms that you use for the rest of that program. + + +# Originally written by Per Bothner . +# Please send patches to . Submit a context +# diff and a properly formatted ChangeLog entry. +# +# This script attempts to guess a canonical system name similar to +# config.sub. If it succeeds, it prints the system name on stdout, and +# exits with 0. Otherwise, it exits with 1. +# +# The plan is that this can be called by configure scripts if you +# don't specify an explicit build system type. + +me=`echo "$0" | sed -e 's,.*/,,'` + +usage="\ +Usage: $0 [OPTION] + +Output the configuration name of the system \`$me' is run on. + +Operation modes: + -h, --help print this help, then exit + -t, --time-stamp print date of last modification, then exit + -v, --version print version number, then exit + +Report bugs and patches to ." + +version="\ +GNU config.guess ($timestamp) + +Originally written by Per Bothner. +Copyright (C) 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005 +Free Software Foundation, Inc. + +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE." + +help=" +Try \`$me --help' for more information." + +# Parse command line +while test $# -gt 0 ; do + case $1 in + --time-stamp | --time* | -t ) + echo "$timestamp" ; exit ;; + --version | -v ) + echo "$version" ; exit ;; + --help | --h* | -h ) + echo "$usage"; exit ;; + -- ) # Stop option processing + shift; break ;; + - ) # Use stdin as input. + break ;; + -* ) + echo "$me: invalid option $1$help" >&2 + exit 1 ;; + * ) + break ;; + esac +done + +if test $# != 0; then + echo "$me: too many arguments$help" >&2 + exit 1 +fi + +trap 'exit 1' 1 2 15 + +# CC_FOR_BUILD -- compiler used by this script. Note that the use of a +# compiler to aid in system detection is discouraged as it requires +# temporary files to be created and, as you can see below, it is a +# headache to deal with in a portable fashion. + +# Historically, `CC_FOR_BUILD' used to be named `HOST_CC'. We still +# use `HOST_CC' if defined, but it is deprecated. + +# Portable tmp directory creation inspired by the Autoconf team. + +set_cc_for_build=' +trap "exitcode=\$?; (rm -f \$tmpfiles 2>/dev/null; rmdir \$tmp 2>/dev/null) && exit \$exitcode" 0 ; +trap "rm -f \$tmpfiles 2>/dev/null; rmdir \$tmp 2>/dev/null; exit 1" 1 2 13 15 ; +: ${TMPDIR=/tmp} ; + { tmp=`(umask 077 && mktemp -d -q "$TMPDIR/cgXXXXXX") 2>/dev/null` && test -n "$tmp" && test -d "$tmp" ; } || + { test -n "$RANDOM" && tmp=$TMPDIR/cg$$-$RANDOM && (umask 077 && mkdir $tmp) ; } || + { tmp=$TMPDIR/cg-$$ && (umask 077 && mkdir $tmp) && echo "Warning: creating insecure temp directory" >&2 ; } || + { echo "$me: cannot create a temporary directory in $TMPDIR" >&2 ; exit 1 ; } ; +dummy=$tmp/dummy ; +tmpfiles="$dummy.c $dummy.o $dummy.rel $dummy" ; +case $CC_FOR_BUILD,$HOST_CC,$CC in + ,,) echo "int x;" > $dummy.c ; + for c in cc gcc c89 c99 ; do + if ($c -c -o $dummy.o $dummy.c) >/dev/null 2>&1 ; then + CC_FOR_BUILD="$c"; break ; + fi ; + done ; + if test x"$CC_FOR_BUILD" = x ; then + CC_FOR_BUILD=no_compiler_found ; + fi + ;; + ,,*) CC_FOR_BUILD=$CC ;; + ,*,*) CC_FOR_BUILD=$HOST_CC ;; +esac ; set_cc_for_build= ;' + +# This is needed to find uname on a Pyramid OSx when run in the BSD universe. +# (ghazi@noc.rutgers.edu 1994-08-24) +if (test -f /.attbin/uname) >/dev/null 2>&1 ; then + PATH=$PATH:/.attbin ; export PATH +fi + +UNAME_MACHINE=`(uname -m) 2>/dev/null` || UNAME_MACHINE=unknown +UNAME_RELEASE=`(uname -r) 2>/dev/null` || UNAME_RELEASE=unknown +UNAME_SYSTEM=`(uname -s) 2>/dev/null` || UNAME_SYSTEM=unknown +UNAME_VERSION=`(uname -v) 2>/dev/null` || UNAME_VERSION=unknown + +if [ "${UNAME_SYSTEM}" = "Linux" ] ; then + eval $set_cc_for_build + cat << EOF > $dummy.c + #include + #ifdef __UCLIBC__ + # ifdef __UCLIBC_CONFIG_VERSION__ + LIBC=uclibc __UCLIBC_CONFIG_VERSION__ + # else + LIBC=uclibc + # endif + #else + LIBC=gnu + #endif +EOF + eval `$CC_FOR_BUILD -E $dummy.c 2>/dev/null | grep LIBC= | sed -e 's: ::g'` +fi + +# Note: order is significant - the case branches are not exclusive. + +case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in + *:NetBSD:*:*) + # NetBSD (nbsd) targets should (where applicable) match one or + # more of the tupples: *-*-netbsdelf*, *-*-netbsdaout*, + # *-*-netbsdecoff* and *-*-netbsd*. For targets that recently + # switched to ELF, *-*-netbsd* would select the old + # object file format. This provides both forward + # compatibility and a consistent mechanism for selecting the + # object file format. + # + # Note: NetBSD doesn't particularly care about the vendor + # portion of the name. We always set it to "unknown". + sysctl="sysctl -n hw.machine_arch" + UNAME_MACHINE_ARCH=`(/sbin/$sysctl 2>/dev/null || \ + /usr/sbin/$sysctl 2>/dev/null || echo unknown)` + case "${UNAME_MACHINE_ARCH}" in + armeb) machine=armeb-unknown ;; + arm*) machine=arm-unknown ;; + sh3el) machine=shl-unknown ;; + sh3eb) machine=sh-unknown ;; + *) machine=${UNAME_MACHINE_ARCH}-unknown ;; + esac + # The Operating System including object format, if it has switched + # to ELF recently, or will in the future. + case "${UNAME_MACHINE_ARCH}" in + arm*|i386|m68k|ns32k|sh3*|sparc|vax) + eval $set_cc_for_build + if echo __ELF__ | $CC_FOR_BUILD -E - 2>/dev/null \ + | grep __ELF__ >/dev/null + then + # Once all utilities can be ECOFF (netbsdecoff) or a.out (netbsdaout). + # Return netbsd for either. FIX? + os=netbsd + else + os=netbsdelf + fi + ;; + *) + os=netbsd + ;; + esac + # The OS release + # Debian GNU/NetBSD machines have a different userland, and + # thus, need a distinct triplet. However, they do not need + # kernel version information, so it can be replaced with a + # suitable tag, in the style of linux-gnu. + case "${UNAME_VERSION}" in + Debian*) + release='-gnu' + ;; + *) + release=`echo ${UNAME_RELEASE}|sed -e 's/[-_].*/\./'` + ;; + esac + # Since CPU_TYPE-MANUFACTURER-KERNEL-OPERATING_SYSTEM: + # contains redundant information, the shorter form: + # CPU_TYPE-MANUFACTURER-OPERATING_SYSTEM is used. + echo "${machine}-${os}${release}" + exit ;; + *:OpenBSD:*:*) + UNAME_MACHINE_ARCH=`arch | sed 's/OpenBSD.//'` + echo ${UNAME_MACHINE_ARCH}-unknown-openbsd${UNAME_RELEASE} + exit ;; + *:ekkoBSD:*:*) + echo ${UNAME_MACHINE}-unknown-ekkobsd${UNAME_RELEASE} + exit ;; + macppc:MirBSD:*:*) + echo powerppc-unknown-mirbsd${UNAME_RELEASE} + exit ;; + *:MirBSD:*:*) + echo ${UNAME_MACHINE}-unknown-mirbsd${UNAME_RELEASE} + exit ;; + alpha:OSF1:*:*) + case $UNAME_RELEASE in + *4.0) + UNAME_RELEASE=`/usr/sbin/sizer -v | awk '{print $3}'` + ;; + *5.*) + UNAME_RELEASE=`/usr/sbin/sizer -v | awk '{print $4}'` + ;; + esac + # According to Compaq, /usr/sbin/psrinfo has been available on + # OSF/1 and Tru64 systems produced since 1995. I hope that + # covers most systems running today. This code pipes the CPU + # types through head -n 1, so we only detect the type of CPU 0. + ALPHA_CPU_TYPE=`/usr/sbin/psrinfo -v | sed -n -e 's/^ The alpha \(.*\) processor.*$/\1/p' | head -n 1` + case "$ALPHA_CPU_TYPE" in + "EV4 (21064)") + UNAME_MACHINE="alpha" ;; + "EV4.5 (21064)") + UNAME_MACHINE="alpha" ;; + "LCA4 (21066/21068)") + UNAME_MACHINE="alpha" ;; + "EV5 (21164)") + UNAME_MACHINE="alphaev5" ;; + "EV5.6 (21164A)") + UNAME_MACHINE="alphaev56" ;; + "EV5.6 (21164PC)") + UNAME_MACHINE="alphapca56" ;; + "EV5.7 (21164PC)") + UNAME_MACHINE="alphapca57" ;; + "EV6 (21264)") + UNAME_MACHINE="alphaev6" ;; + "EV6.7 (21264A)") + UNAME_MACHINE="alphaev67" ;; + "EV6.8CB (21264C)") + UNAME_MACHINE="alphaev68" ;; + "EV6.8AL (21264B)") + UNAME_MACHINE="alphaev68" ;; + "EV6.8CX (21264D)") + UNAME_MACHINE="alphaev68" ;; + "EV6.9A (21264/EV69A)") + UNAME_MACHINE="alphaev69" ;; + "EV7 (21364)") + UNAME_MACHINE="alphaev7" ;; + "EV7.9 (21364A)") + UNAME_MACHINE="alphaev79" ;; + esac + # A Pn.n version is a patched version. + # A Vn.n version is a released version. + # A Tn.n version is a released field test version. + # A Xn.n version is an unreleased experimental baselevel. + # 1.2 uses "1.2" for uname -r. + echo ${UNAME_MACHINE}-dec-osf`echo ${UNAME_RELEASE} | sed -e 's/^[PVTX]//' | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz'` + exit ;; + Alpha\ *:Windows_NT*:*) + # How do we know it's Interix rather than the generic POSIX subsystem? + # Should we change UNAME_MACHINE based on the output of uname instead + # of the specific Alpha model? + echo alpha-pc-interix + exit ;; + 21064:Windows_NT:50:3) + echo alpha-dec-winnt3.5 + exit ;; + Amiga*:UNIX_System_V:4.0:*) + echo m68k-unknown-sysv4 + exit ;; + *:[Aa]miga[Oo][Ss]:*:*) + echo ${UNAME_MACHINE}-unknown-amigaos + exit ;; + *:[Mm]orph[Oo][Ss]:*:*) + echo ${UNAME_MACHINE}-unknown-morphos + exit ;; + *:OS/390:*:*) + echo i370-ibm-openedition + exit ;; + *:z/VM:*:*) + echo s390-ibm-zvmoe + exit ;; + *:OS400:*:*) + echo powerpc-ibm-os400 + exit ;; + arm:RISC*:1.[012]*:*|arm:riscix:1.[012]*:*) + echo arm-acorn-riscix${UNAME_RELEASE} + exit ;; + arm:riscos:*:*|arm:RISCOS:*:*) + echo arm-unknown-riscos + exit ;; + SR2?01:HI-UX/MPP:*:* | SR8000:HI-UX/MPP:*:*) + echo hppa1.1-hitachi-hiuxmpp + exit ;; + Pyramid*:OSx*:*:* | MIS*:OSx*:*:* | MIS*:SMP_DC-OSx*:*:*) + # akee@wpdis03.wpafb.af.mil (Earle F. Ake) contributed MIS and NILE. + if test "`(/bin/universe) 2>/dev/null`" = att ; then + echo pyramid-pyramid-sysv3 + else + echo pyramid-pyramid-bsd + fi + exit ;; + NILE*:*:*:dcosx) + echo pyramid-pyramid-svr4 + exit ;; + DRS?6000:unix:4.0:6*) + echo sparc-icl-nx6 + exit ;; + DRS?6000:UNIX_SV:4.2*:7* | DRS?6000:isis:4.2*:7*) + case `/usr/bin/uname -p` in + sparc) echo sparc-icl-nx7; exit ;; + esac ;; + sun4H:SunOS:5.*:*) + echo sparc-hal-solaris2`echo ${UNAME_RELEASE}|sed -e 's/[^.]*//'` + exit ;; + sun4*:SunOS:5.*:* | tadpole*:SunOS:5.*:*) + echo sparc-sun-solaris2`echo ${UNAME_RELEASE}|sed -e 's/[^.]*//'` + exit ;; + i86pc:SunOS:5.*:*) + echo i386-pc-solaris2`echo ${UNAME_RELEASE}|sed -e 's/[^.]*//'` + exit ;; + sun4*:SunOS:6*:*) + # According to config.sub, this is the proper way to canonicalize + # SunOS6. Hard to guess exactly what SunOS6 will be like, but + # it's likely to be more like Solaris than SunOS4. + echo sparc-sun-solaris3`echo ${UNAME_RELEASE}|sed -e 's/[^.]*//'` + exit ;; + sun4*:SunOS:*:*) + case "`/usr/bin/arch -k`" in + Series*|S4*) + UNAME_RELEASE=`uname -v` + ;; + esac + # Japanese Language versions have a version number like `4.1.3-JL'. + echo sparc-sun-sunos`echo ${UNAME_RELEASE}|sed -e 's/-/_/'` + exit ;; + sun3*:SunOS:*:*) + echo m68k-sun-sunos${UNAME_RELEASE} + exit ;; + sun*:*:4.2BSD:*) + UNAME_RELEASE=`(sed 1q /etc/motd | awk '{print substr($5,1,3)}') 2>/dev/null` + test "x${UNAME_RELEASE}" = "x" && UNAME_RELEASE=3 + case "`/bin/arch`" in + sun3) + echo m68k-sun-sunos${UNAME_RELEASE} + ;; + sun4) + echo sparc-sun-sunos${UNAME_RELEASE} + ;; + esac + exit ;; + aushp:SunOS:*:*) + echo sparc-auspex-sunos${UNAME_RELEASE} + exit ;; + # The situation for MiNT is a little confusing. The machine name + # can be virtually everything (everything which is not + # "atarist" or "atariste" at least should have a processor + # > m68000). The system name ranges from "MiNT" over "FreeMiNT" + # to the lowercase version "mint" (or "freemint"). Finally + # the system name "TOS" denotes a system which is actually not + # MiNT. But MiNT is downward compatible to TOS, so this should + # be no problem. + atarist[e]:*MiNT:*:* | atarist[e]:*mint:*:* | atarist[e]:*TOS:*:*) + echo m68k-atari-mint${UNAME_RELEASE} + exit ;; + atari*:*MiNT:*:* | atari*:*mint:*:* | atarist[e]:*TOS:*:*) + echo m68k-atari-mint${UNAME_RELEASE} + exit ;; + *falcon*:*MiNT:*:* | *falcon*:*mint:*:* | *falcon*:*TOS:*:*) + echo m68k-atari-mint${UNAME_RELEASE} + exit ;; + milan*:*MiNT:*:* | milan*:*mint:*:* | *milan*:*TOS:*:*) + echo m68k-milan-mint${UNAME_RELEASE} + exit ;; + hades*:*MiNT:*:* | hades*:*mint:*:* | *hades*:*TOS:*:*) + echo m68k-hades-mint${UNAME_RELEASE} + exit ;; + *:*MiNT:*:* | *:*mint:*:* | *:*TOS:*:*) + echo m68k-unknown-mint${UNAME_RELEASE} + exit ;; + m68k:machten:*:*) + echo m68k-apple-machten${UNAME_RELEASE} + exit ;; + powerpc:machten:*:*) + echo powerpc-apple-machten${UNAME_RELEASE} + exit ;; + RISC*:Mach:*:*) + echo mips-dec-mach_bsd4.3 + exit ;; + RISC*:ULTRIX:*:*) + echo mips-dec-ultrix${UNAME_RELEASE} + exit ;; + VAX*:ULTRIX*:*:*) + echo vax-dec-ultrix${UNAME_RELEASE} + exit ;; + 2020:CLIX:*:* | 2430:CLIX:*:*) + echo clipper-intergraph-clix${UNAME_RELEASE} + exit ;; + mips:*:*:UMIPS | mips:*:*:RISCos) + eval $set_cc_for_build + sed 's/^ //' << EOF >$dummy.c +#ifdef __cplusplus +#include /* for printf() prototype */ + int main (int argc, char *argv[]) { +#else + int main (argc, argv) int argc; char *argv[]; { +#endif + #if defined (host_mips) && defined (MIPSEB) + #if defined (SYSTYPE_SYSV) + printf ("mips-mips-riscos%ssysv\n", argv[1]); exit (0); + #endif + #if defined (SYSTYPE_SVR4) + printf ("mips-mips-riscos%ssvr4\n", argv[1]); exit (0); + #endif + #if defined (SYSTYPE_BSD43) || defined(SYSTYPE_BSD) + printf ("mips-mips-riscos%sbsd\n", argv[1]); exit (0); + #endif + #endif + exit (-1); + } +EOF + $CC_FOR_BUILD -o $dummy $dummy.c && + dummyarg=`echo "${UNAME_RELEASE}" | sed -n 's/\([0-9]*\).*/\1/p'` && + SYSTEM_NAME=`$dummy $dummyarg` && + { echo "$SYSTEM_NAME"; exit; } + echo mips-mips-riscos${UNAME_RELEASE} + exit ;; + Motorola:PowerMAX_OS:*:*) + echo powerpc-motorola-powermax + exit ;; + Motorola:*:4.3:PL8-*) + echo powerpc-harris-powermax + exit ;; + Night_Hawk:*:*:PowerMAX_OS | Synergy:PowerMAX_OS:*:*) + echo powerpc-harris-powermax + exit ;; + Night_Hawk:Power_UNIX:*:*) + echo powerpc-harris-powerunix + exit ;; + m88k:CX/UX:7*:*) + echo m88k-harris-cxux7 + exit ;; + m88k:*:4*:R4*) + echo m88k-motorola-sysv4 + exit ;; + m88k:*:3*:R3*) + echo m88k-motorola-sysv3 + exit ;; + AViiON:dgux:*:*) + # DG/UX returns AViiON for all architectures + UNAME_PROCESSOR=`/usr/bin/uname -p` + if [ $UNAME_PROCESSOR = mc88100 ] || [ $UNAME_PROCESSOR = mc88110 ] + then + if [ ${TARGET_BINARY_INTERFACE}x = m88kdguxelfx ] || \ + [ ${TARGET_BINARY_INTERFACE}x = x ] + then + echo m88k-dg-dgux${UNAME_RELEASE} + else + echo m88k-dg-dguxbcs${UNAME_RELEASE} + fi + else + echo i586-dg-dgux${UNAME_RELEASE} + fi + exit ;; + M88*:DolphinOS:*:*) # DolphinOS (SVR3) + echo m88k-dolphin-sysv3 + exit ;; + M88*:*:R3*:*) + # Delta 88k system running SVR3 + echo m88k-motorola-sysv3 + exit ;; + XD88*:*:*:*) # Tektronix XD88 system running UTekV (SVR3) + echo m88k-tektronix-sysv3 + exit ;; + Tek43[0-9][0-9]:UTek:*:*) # Tektronix 4300 system running UTek (BSD) + echo m68k-tektronix-bsd + exit ;; + *:IRIX*:*:*) + echo mips-sgi-irix`echo ${UNAME_RELEASE}|sed -e 's/-/_/g'` + exit ;; + ????????:AIX?:[12].1:2) # AIX 2.2.1 or AIX 2.1.1 is RT/PC AIX. + echo romp-ibm-aix # uname -m gives an 8 hex-code CPU id + exit ;; # Note that: echo "'`uname -s`'" gives 'AIX ' + i*86:AIX:*:*) + echo i386-ibm-aix + exit ;; + ia64:AIX:*:*) + if [ -x /usr/bin/oslevel ] ; then + IBM_REV=`/usr/bin/oslevel` + else + IBM_REV=${UNAME_VERSION}.${UNAME_RELEASE} + fi + echo ${UNAME_MACHINE}-ibm-aix${IBM_REV} + exit ;; + *:AIX:2:3) + if grep bos325 /usr/include/stdio.h >/dev/null 2>&1; then + eval $set_cc_for_build + sed 's/^ //' << EOF >$dummy.c + #include + + main() + { + if (!__power_pc()) + exit(1); + puts("powerpc-ibm-aix3.2.5"); + exit(0); + } +EOF + if $CC_FOR_BUILD -o $dummy $dummy.c && SYSTEM_NAME=`$dummy` + then + echo "$SYSTEM_NAME" + else + echo rs6000-ibm-aix3.2.5 + fi + elif grep bos324 /usr/include/stdio.h >/dev/null 2>&1; then + echo rs6000-ibm-aix3.2.4 + else + echo rs6000-ibm-aix3.2 + fi + exit ;; + *:AIX:*:[45]) + IBM_CPU_ID=`/usr/sbin/lsdev -C -c processor -S available | sed 1q | awk '{ print $1 }'` + if /usr/sbin/lsattr -El ${IBM_CPU_ID} | grep ' POWER' >/dev/null 2>&1; then + IBM_ARCH=rs6000 + else + IBM_ARCH=powerpc + fi + if [ -x /usr/bin/oslevel ] ; then + IBM_REV=`/usr/bin/oslevel` + else + IBM_REV=${UNAME_VERSION}.${UNAME_RELEASE} + fi + echo ${IBM_ARCH}-ibm-aix${IBM_REV} + exit ;; + *:AIX:*:*) + echo rs6000-ibm-aix + exit ;; + ibmrt:4.4BSD:*|romp-ibm:BSD:*) + echo romp-ibm-bsd4.4 + exit ;; + ibmrt:*BSD:*|romp-ibm:BSD:*) # covers RT/PC BSD and + echo romp-ibm-bsd${UNAME_RELEASE} # 4.3 with uname added to + exit ;; # report: romp-ibm BSD 4.3 + *:BOSX:*:*) + echo rs6000-bull-bosx + exit ;; + DPX/2?00:B.O.S.:*:*) + echo m68k-bull-sysv3 + exit ;; + 9000/[34]??:4.3bsd:1.*:*) + echo m68k-hp-bsd + exit ;; + hp300:4.4BSD:*:* | 9000/[34]??:4.3bsd:2.*:*) + echo m68k-hp-bsd4.4 + exit ;; + 9000/[34678]??:HP-UX:*:*) + HPUX_REV=`echo ${UNAME_RELEASE}|sed -e 's/[^.]*.[0B]*//'` + case "${UNAME_MACHINE}" in + 9000/31? ) HP_ARCH=m68000 ;; + 9000/[34]?? ) HP_ARCH=m68k ;; + 9000/[678][0-9][0-9]) + if [ -x /usr/bin/getconf ]; then + sc_cpu_version=`/usr/bin/getconf SC_CPU_VERSION 2>/dev/null` + sc_kernel_bits=`/usr/bin/getconf SC_KERNEL_BITS 2>/dev/null` + case "${sc_cpu_version}" in + 523) HP_ARCH="hppa1.0" ;; # CPU_PA_RISC1_0 + 528) HP_ARCH="hppa1.1" ;; # CPU_PA_RISC1_1 + 532) # CPU_PA_RISC2_0 + case "${sc_kernel_bits}" in + 32) HP_ARCH="hppa2.0n" ;; + 64) HP_ARCH="hppa2.0w" ;; + '') HP_ARCH="hppa2.0" ;; # HP-UX 10.20 + esac ;; + esac + fi + if [ "${HP_ARCH}" = "" ]; then + eval $set_cc_for_build + sed 's/^ //' << EOF >$dummy.c + + #define _HPUX_SOURCE + #include + #include + + int main () + { + #if defined(_SC_KERNEL_BITS) + long bits = sysconf(_SC_KERNEL_BITS); + #endif + long cpu = sysconf (_SC_CPU_VERSION); + + switch (cpu) + { + case CPU_PA_RISC1_0: puts ("hppa1.0"); break; + case CPU_PA_RISC1_1: puts ("hppa1.1"); break; + case CPU_PA_RISC2_0: + #if defined(_SC_KERNEL_BITS) + switch (bits) + { + case 64: puts ("hppa2.0w"); break; + case 32: puts ("hppa2.0n"); break; + default: puts ("hppa2.0"); break; + } break; + #else /* !defined(_SC_KERNEL_BITS) */ + puts ("hppa2.0"); break; + #endif + default: puts ("hppa1.0"); break; + } + exit (0); + } +EOF + (CCOPTS= $CC_FOR_BUILD -o $dummy $dummy.c 2>/dev/null) && HP_ARCH=`$dummy` + test -z "$HP_ARCH" && HP_ARCH=hppa + fi ;; + esac + if [ ${HP_ARCH} = "hppa2.0w" ] + then + eval $set_cc_for_build + + # hppa2.0w-hp-hpux* has a 64-bit kernel and a compiler generating + # 32-bit code. hppa64-hp-hpux* has the same kernel and a compiler + # generating 64-bit code. GNU and HP use different nomenclature: + # + # $ CC_FOR_BUILD=cc ./config.guess + # => hppa2.0w-hp-hpux11.23 + # $ CC_FOR_BUILD="cc +DA2.0w" ./config.guess + # => hppa64-hp-hpux11.23 + + if echo __LP64__ | (CCOPTS= $CC_FOR_BUILD -E - 2>/dev/null) | + grep __LP64__ >/dev/null + then + HP_ARCH="hppa2.0w" + else + HP_ARCH="hppa64" + fi + fi + echo ${HP_ARCH}-hp-hpux${HPUX_REV} + exit ;; + ia64:HP-UX:*:*) + HPUX_REV=`echo ${UNAME_RELEASE}|sed -e 's/[^.]*.[0B]*//'` + echo ia64-hp-hpux${HPUX_REV} + exit ;; + 3050*:HI-UX:*:*) + eval $set_cc_for_build + sed 's/^ //' << EOF >$dummy.c + #include + int + main () + { + long cpu = sysconf (_SC_CPU_VERSION); + /* The order matters, because CPU_IS_HP_MC68K erroneously returns + true for CPU_PA_RISC1_0. CPU_IS_PA_RISC returns correct + results, however. */ + if (CPU_IS_PA_RISC (cpu)) + { + switch (cpu) + { + case CPU_PA_RISC1_0: puts ("hppa1.0-hitachi-hiuxwe2"); break; + case CPU_PA_RISC1_1: puts ("hppa1.1-hitachi-hiuxwe2"); break; + case CPU_PA_RISC2_0: puts ("hppa2.0-hitachi-hiuxwe2"); break; + default: puts ("hppa-hitachi-hiuxwe2"); break; + } + } + else if (CPU_IS_HP_MC68K (cpu)) + puts ("m68k-hitachi-hiuxwe2"); + else puts ("unknown-hitachi-hiuxwe2"); + exit (0); + } +EOF + $CC_FOR_BUILD -o $dummy $dummy.c && SYSTEM_NAME=`$dummy` && + { echo "$SYSTEM_NAME"; exit; } + echo unknown-hitachi-hiuxwe2 + exit ;; + 9000/7??:4.3bsd:*:* | 9000/8?[79]:4.3bsd:*:* ) + echo hppa1.1-hp-bsd + exit ;; + 9000/8??:4.3bsd:*:*) + echo hppa1.0-hp-bsd + exit ;; + *9??*:MPE/iX:*:* | *3000*:MPE/iX:*:*) + echo hppa1.0-hp-mpeix + exit ;; + hp7??:OSF1:*:* | hp8?[79]:OSF1:*:* ) + echo hppa1.1-hp-osf + exit ;; + hp8??:OSF1:*:*) + echo hppa1.0-hp-osf + exit ;; + i*86:OSF1:*:*) + if [ -x /usr/sbin/sysversion ] ; then + echo ${UNAME_MACHINE}-unknown-osf1mk + else + echo ${UNAME_MACHINE}-unknown-osf1 + fi + exit ;; + parisc*:Lites*:*:*) + echo hppa1.1-hp-lites + exit ;; + C1*:ConvexOS:*:* | convex:ConvexOS:C1*:*) + echo c1-convex-bsd + exit ;; + C2*:ConvexOS:*:* | convex:ConvexOS:C2*:*) + if getsysinfo -f scalar_acc + then echo c32-convex-bsd + else echo c2-convex-bsd + fi + exit ;; + C34*:ConvexOS:*:* | convex:ConvexOS:C34*:*) + echo c34-convex-bsd + exit ;; + C38*:ConvexOS:*:* | convex:ConvexOS:C38*:*) + echo c38-convex-bsd + exit ;; + C4*:ConvexOS:*:* | convex:ConvexOS:C4*:*) + echo c4-convex-bsd + exit ;; + CRAY*Y-MP:*:*:*) + echo ymp-cray-unicos${UNAME_RELEASE} | sed -e 's/\.[^.]*$/.X/' + exit ;; + CRAY*[A-Z]90:*:*:*) + echo ${UNAME_MACHINE}-cray-unicos${UNAME_RELEASE} \ + | sed -e 's/CRAY.*\([A-Z]90\)/\1/' \ + -e y/ABCDEFGHIJKLMNOPQRSTUVWXYZ/abcdefghijklmnopqrstuvwxyz/ \ + -e 's/\.[^.]*$/.X/' + exit ;; + CRAY*TS:*:*:*) + echo t90-cray-unicos${UNAME_RELEASE} | sed -e 's/\.[^.]*$/.X/' + exit ;; + CRAY*T3E:*:*:*) + echo alphaev5-cray-unicosmk${UNAME_RELEASE} | sed -e 's/\.[^.]*$/.X/' + exit ;; + CRAY*SV1:*:*:*) + echo sv1-cray-unicos${UNAME_RELEASE} | sed -e 's/\.[^.]*$/.X/' + exit ;; + *:UNICOS/mp:*:*) + echo craynv-cray-unicosmp${UNAME_RELEASE} | sed -e 's/\.[^.]*$/.X/' + exit ;; + F30[01]:UNIX_System_V:*:* | F700:UNIX_System_V:*:*) + FUJITSU_PROC=`uname -m | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz'` + FUJITSU_SYS=`uname -p | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz' | sed -e 's/\///'` + FUJITSU_REL=`echo ${UNAME_RELEASE} | sed -e 's/ /_/'` + echo "${FUJITSU_PROC}-fujitsu-${FUJITSU_SYS}${FUJITSU_REL}" + exit ;; + 5000:UNIX_System_V:4.*:*) + FUJITSU_SYS=`uname -p | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz' | sed -e 's/\///'` + FUJITSU_REL=`echo ${UNAME_RELEASE} | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz' | sed -e 's/ /_/'` + echo "sparc-fujitsu-${FUJITSU_SYS}${FUJITSU_REL}" + exit ;; + i*86:BSD/386:*:* | i*86:BSD/OS:*:* | *:Ascend\ Embedded/OS:*:*) + echo ${UNAME_MACHINE}-pc-bsdi${UNAME_RELEASE} + exit ;; + sparc*:BSD/OS:*:*) + echo sparc-unknown-bsdi${UNAME_RELEASE} + exit ;; + *:BSD/OS:*:*) + echo ${UNAME_MACHINE}-unknown-bsdi${UNAME_RELEASE} + exit ;; + *:FreeBSD:*:*) + case ${UNAME_MACHINE} in + pc98) + echo i386-unknown-freebsd`echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'` ;; + *) + echo ${UNAME_MACHINE}-unknown-freebsd`echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'` ;; + esac + exit ;; + i*:CYGWIN*:*) + echo ${UNAME_MACHINE}-pc-cygwin + exit ;; + i*:MINGW*:*) + echo ${UNAME_MACHINE}-pc-mingw32 + exit ;; + i*:windows32*:*) + # uname -m includes "-pc" on this system. + echo ${UNAME_MACHINE}-mingw32 + exit ;; + i*:PW*:*) + echo ${UNAME_MACHINE}-pc-pw32 + exit ;; + x86:Interix*:[345]*) + echo i586-pc-interix${UNAME_RELEASE}|sed -e 's/\..*//' + exit ;; + [345]86:Windows_95:* | [345]86:Windows_98:* | [345]86:Windows_NT:*) + echo i${UNAME_MACHINE}-pc-mks + exit ;; + i*:Windows_NT*:* | Pentium*:Windows_NT*:*) + # How do we know it's Interix rather than the generic POSIX subsystem? + # It also conflicts with pre-2.0 versions of AT&T UWIN. Should we + # UNAME_MACHINE based on the output of uname instead of i386? + echo i586-pc-interix + exit ;; + i*:UWIN*:*) + echo ${UNAME_MACHINE}-pc-uwin + exit ;; + amd64:CYGWIN*:*:* | x86_64:CYGWIN*:*:*) + echo x86_64-unknown-cygwin + exit ;; + p*:CYGWIN*:*) + echo powerpcle-unknown-cygwin + exit ;; + prep*:SunOS:5.*:*) + echo powerpcle-unknown-solaris2`echo ${UNAME_RELEASE}|sed -e 's/[^.]*//'` + exit ;; + *:GNU:*:*) + # the GNU system + echo `echo ${UNAME_MACHINE}|sed -e 's,[-/].*$,,'`-unknown-gnu`echo ${UNAME_RELEASE}|sed -e 's,/.*$,,'` + exit ;; + *:GNU/*:*:*) + # other systems with GNU libc and userland + echo ${UNAME_MACHINE}-unknown-`echo ${UNAME_SYSTEM} | sed 's,^[^/]*/,,' | tr '[A-Z]' '[a-z]'``echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'`-gnu + exit ;; + i*86:Minix:*:*) + echo ${UNAME_MACHINE}-pc-minix + exit ;; + arm*:Linux:*:*) + echo ${UNAME_MACHINE}-unknown-linux-${LIBC} + exit ;; + cris:Linux:*:*) + echo cris-axis-linux-${LIBC} + exit ;; + crisv32:Linux:*:*) + echo crisv32-axis-linux-${LIBC} + exit ;; + frv:Linux:*:*) + echo frv-unknown-linux-${LIBC} + exit ;; + ia64:Linux:*:*) + echo ${UNAME_MACHINE}-unknown-linux-${LIBC} + exit ;; + m32r*:Linux:*:*) + echo ${UNAME_MACHINE}-unknown-linux-${LIBC} + exit ;; + m68*:Linux:*:*) + echo ${UNAME_MACHINE}-unknown-linux-${LIBC} + exit ;; + mips:Linux:*:*) + eval $set_cc_for_build + sed 's/^ //' << EOF >$dummy.c + #undef CPU + #undef mips + #undef mipsel + #if defined(__MIPSEL__) || defined(__MIPSEL) || defined(_MIPSEL) || defined(MIPSEL) + CPU=mipsel + #else + #if defined(__MIPSEB__) || defined(__MIPSEB) || defined(_MIPSEB) || defined(MIPSEB) + CPU=mips + #else + CPU= + #endif + #endif +EOF + eval "`$CC_FOR_BUILD -E $dummy.c 2>/dev/null | sed -n '/^CPU/{s: ::g;p;}'`" + test x"${CPU}" != x && { echo "${CPU}-unknown-linux-${LIBC}"; exit; } + ;; + mips64:Linux:*:*) + eval $set_cc_for_build + sed 's/^ //' << EOF >$dummy.c + #undef CPU + #undef mips64 + #undef mips64el + #if defined(__MIPSEL__) || defined(__MIPSEL) || defined(_MIPSEL) || defined(MIPSEL) + CPU=mips64el + #else + #if defined(__MIPSEB__) || defined(__MIPSEB) || defined(_MIPSEB) || defined(MIPSEB) + CPU=mips64 + #else + CPU= + #endif + #endif +EOF + eval "`$CC_FOR_BUILD -E $dummy.c 2>/dev/null | sed -n '/^CPU/{s: ::g;p;}'`" + test x"${CPU}" != x && { echo "${CPU}-unknown-linux-${LIBC}"; exit; } + ;; + or32:Linux:*:*) + echo or32-unknown-linux-${LIBC} + exit ;; + ppc:Linux:*:*) + echo powerpc-unknown-linux-${LIBC} + exit ;; + ppc64:Linux:*:*) + echo powerpc64-unknown-linux-${LIBC} + exit ;; + alpha:Linux:*:*) + case `sed -n '/^cpu model/s/^.*: \(.*\)/\1/p' < /proc/cpuinfo` in + EV5) UNAME_MACHINE=alphaev5 ;; + EV56) UNAME_MACHINE=alphaev56 ;; + PCA56) UNAME_MACHINE=alphapca56 ;; + PCA57) UNAME_MACHINE=alphapca56 ;; + EV6) UNAME_MACHINE=alphaev6 ;; + EV67) UNAME_MACHINE=alphaev67 ;; + EV68*) UNAME_MACHINE=alphaev68 ;; + esac + objdump --private-headers /bin/sh | grep ld.so.1 >/dev/null + if test "$?" = 0 ; then LIBC="gnulibc1" ; fi + echo ${UNAME_MACHINE}-unknown-linux-${LIBC} + exit ;; + parisc:Linux:*:* | hppa:Linux:*:*) + # Look for CPU level + case `grep '^cpu[^a-z]*:' /proc/cpuinfo 2>/dev/null | cut -d' ' -f2` in + PA7*) echo hppa1.1-unknown-linux-${LIBC} ;; + PA8*) echo hppa2.0-unknown-linux-${LIBC} ;; + *) echo hppa-unknown-linux-${LIBC} ;; + esac + exit ;; + parisc64:Linux:*:* | hppa64:Linux:*:*) + echo hppa64-unknown-linux-${LIBC} + exit ;; + s390:Linux:*:* | s390x:Linux:*:*) + echo ${UNAME_MACHINE}-ibm-linux + exit ;; + sh64*:Linux:*:*) + echo ${UNAME_MACHINE}-unknown-linux-${LIBC} + exit ;; + sh*:Linux:*:*) + echo ${UNAME_MACHINE}-unknown-linux-${LIBC} + exit ;; + sparc:Linux:*:* | sparc64:Linux:*:*) + echo ${UNAME_MACHINE}-unknown-linux-${LIBC} + exit ;; + vax:Linux:*:*) + echo ${UNAME_MACHINE}-dec-linux-${LIBC} + exit ;; + x86_64:Linux:*:*) + echo x86_64-unknown-linux-${LIBC} + exit ;; + i*86:Linux:*:*) + # The BFD linker knows what the default object file format is, so + # first see if it will tell us. cd to the root directory to prevent + # problems with other programs or directories called `ld' in the path. + # Set LC_ALL=C to ensure ld outputs messages in English. + ld_supported_targets=`cd /; LC_ALL=C ld --help 2>&1 \ + | sed -ne '/supported targets:/!d + s/[ ][ ]*/ /g + s/.*supported targets: *// + s/ .*// + p'` + case "$ld_supported_targets" in + elf32-i386) + TENTATIVE="${UNAME_MACHINE}-pc-linux-${LIBC}" + ;; + a.out-i386-linux) + echo "${UNAME_MACHINE}-pc-linux-${LIBC}aout" + exit ;; + coff-i386) + echo "${UNAME_MACHINE}-pc-linux-${LIBC}coff" + exit ;; + "") + # Either a pre-BFD a.out linker (linux-gnuoldld) or + # one that does not give us useful --help. + echo "${UNAME_MACHINE}-pc-linux-${LIBC}oldld" + exit ;; + esac + # This should get integrated into the C code below, but now we hack + if [ "$LIBC" != "gnu" ] ; then echo "$TENTATIVE" && exit 0 ; fi + # Determine whether the default compiler is a.out or elf + eval $set_cc_for_build + sed 's/^ //' << EOF >$dummy.c + #include + #ifdef __ELF__ + # ifdef __GLIBC__ + # if __GLIBC__ >= 2 + LIBC=gnu + # else + LIBC=gnulibc1 + # endif + # else + LIBC=gnulibc1 + # endif + #else + #if defined(__INTEL_COMPILER) || defined(__PGI) + LIBC=gnu + #else + LIBC=gnuaout + #endif + #endif + #ifdef __dietlibc__ + LIBC=dietlibc + #endif +EOF + eval "`$CC_FOR_BUILD -E $dummy.c 2>/dev/null | sed -n '/^LIBC/{s: ::g;p;}'`" + test x"${LIBC}" != x && { + echo "${UNAME_MACHINE}-pc-linux-${LIBC}" + exit + } + test x"${TENTATIVE}" != x && { echo "${TENTATIVE}"; exit; } + ;; + i*86:DYNIX/ptx:4*:*) + # ptx 4.0 does uname -s correctly, with DYNIX/ptx in there. + # earlier versions are messed up and put the nodename in both + # sysname and nodename. + echo i386-sequent-sysv4 + exit ;; + i*86:UNIX_SV:4.2MP:2.*) + # Unixware is an offshoot of SVR4, but it has its own version + # number series starting with 2... + # I am not positive that other SVR4 systems won't match this, + # I just have to hope. -- rms. + # Use sysv4.2uw... so that sysv4* matches it. + echo ${UNAME_MACHINE}-pc-sysv4.2uw${UNAME_VERSION} + exit ;; + i*86:OS/2:*:*) + # If we were able to find `uname', then EMX Unix compatibility + # is probably installed. + echo ${UNAME_MACHINE}-pc-os2-emx + exit ;; + i*86:XTS-300:*:STOP) + echo ${UNAME_MACHINE}-unknown-stop + exit ;; + i*86:atheos:*:*) + echo ${UNAME_MACHINE}-unknown-atheos + exit ;; + i*86:syllable:*:*) + echo ${UNAME_MACHINE}-pc-syllable + exit ;; + i*86:LynxOS:2.*:* | i*86:LynxOS:3.[01]*:* | i*86:LynxOS:4.0*:*) + echo i386-unknown-lynxos${UNAME_RELEASE} + exit ;; + i*86:*DOS:*:*) + echo ${UNAME_MACHINE}-pc-msdosdjgpp + exit ;; + i*86:*:4.*:* | i*86:SYSTEM_V:4.*:*) + UNAME_REL=`echo ${UNAME_RELEASE} | sed 's/\/MP$//'` + if grep Novell /usr/include/link.h >/dev/null 2>/dev/null; then + echo ${UNAME_MACHINE}-univel-sysv${UNAME_REL} + else + echo ${UNAME_MACHINE}-pc-sysv${UNAME_REL} + fi + exit ;; + i*86:*:5:[678]*) + # UnixWare 7.x, OpenUNIX and OpenServer 6. + case `/bin/uname -X | grep "^Machine"` in + *486*) UNAME_MACHINE=i486 ;; + *Pentium) UNAME_MACHINE=i586 ;; + *Pent*|*Celeron) UNAME_MACHINE=i686 ;; + esac + echo ${UNAME_MACHINE}-unknown-sysv${UNAME_RELEASE}${UNAME_SYSTEM}${UNAME_VERSION} + exit ;; + i*86:*:3.2:*) + if test -f /usr/options/cb.name; then + UNAME_REL=`sed -n 's/.*Version //p' /dev/null >/dev/null ; then + UNAME_REL=`(/bin/uname -X|grep Release|sed -e 's/.*= //')` + (/bin/uname -X|grep i80486 >/dev/null) && UNAME_MACHINE=i486 + (/bin/uname -X|grep '^Machine.*Pentium' >/dev/null) \ + && UNAME_MACHINE=i586 + (/bin/uname -X|grep '^Machine.*Pent *II' >/dev/null) \ + && UNAME_MACHINE=i686 + (/bin/uname -X|grep '^Machine.*Pentium Pro' >/dev/null) \ + && UNAME_MACHINE=i686 + echo ${UNAME_MACHINE}-pc-sco$UNAME_REL + else + echo ${UNAME_MACHINE}-pc-sysv32 + fi + exit ;; + pc:*:*:*) + # Left here for compatibility: + # uname -m prints for DJGPP always 'pc', but it prints nothing about + # the processor, so we play safe by assuming i386. + echo i386-pc-msdosdjgpp + exit ;; + Intel:Mach:3*:*) + echo i386-pc-mach3 + exit ;; + paragon:*:*:*) + echo i860-intel-osf1 + exit ;; + i860:*:4.*:*) # i860-SVR4 + if grep Stardent /usr/include/sys/uadmin.h >/dev/null 2>&1 ; then + echo i860-stardent-sysv${UNAME_RELEASE} # Stardent Vistra i860-SVR4 + else # Add other i860-SVR4 vendors below as they are discovered. + echo i860-unknown-sysv${UNAME_RELEASE} # Unknown i860-SVR4 + fi + exit ;; + mini*:CTIX:SYS*5:*) + # "miniframe" + echo m68010-convergent-sysv + exit ;; + mc68k:UNIX:SYSTEM5:3.51m) + echo m68k-convergent-sysv + exit ;; + M680?0:D-NIX:5.3:*) + echo m68k-diab-dnix + exit ;; + M68*:*:R3V[5678]*:*) + test -r /sysV68 && { echo 'm68k-motorola-sysv'; exit; } ;; + 3[345]??:*:4.0:3.0 | 3[34]??A:*:4.0:3.0 | 3[34]??,*:*:4.0:3.0 | 3[34]??/*:*:4.0:3.0 | 4400:*:4.0:3.0 | 4850:*:4.0:3.0 | SKA40:*:4.0:3.0 | SDS2:*:4.0:3.0 | SHG2:*:4.0:3.0 | S7501*:*:4.0:3.0) + OS_REL='' + test -r /etc/.relid \ + && OS_REL=.`sed -n 's/[^ ]* [^ ]* \([0-9][0-9]\).*/\1/p' < /etc/.relid` + /bin/uname -p 2>/dev/null | grep 86 >/dev/null \ + && { echo i486-ncr-sysv4.3${OS_REL}; exit; } + /bin/uname -p 2>/dev/null | /bin/grep entium >/dev/null \ + && { echo i586-ncr-sysv4.3${OS_REL}; exit; } ;; + 3[34]??:*:4.0:* | 3[34]??,*:*:4.0:*) + /bin/uname -p 2>/dev/null | grep 86 >/dev/null \ + && { echo i486-ncr-sysv4; exit; } ;; + m68*:LynxOS:2.*:* | m68*:LynxOS:3.0*:*) + echo m68k-unknown-lynxos${UNAME_RELEASE} + exit ;; + mc68030:UNIX_System_V:4.*:*) + echo m68k-atari-sysv4 + exit ;; + TSUNAMI:LynxOS:2.*:*) + echo sparc-unknown-lynxos${UNAME_RELEASE} + exit ;; + rs6000:LynxOS:2.*:*) + echo rs6000-unknown-lynxos${UNAME_RELEASE} + exit ;; + PowerPC:LynxOS:2.*:* | PowerPC:LynxOS:3.[01]*:* | PowerPC:LynxOS:4.0*:*) + echo powerpc-unknown-lynxos${UNAME_RELEASE} + exit ;; + SM[BE]S:UNIX_SV:*:*) + echo mips-dde-sysv${UNAME_RELEASE} + exit ;; + RM*:ReliantUNIX-*:*:*) + echo mips-sni-sysv4 + exit ;; + RM*:SINIX-*:*:*) + echo mips-sni-sysv4 + exit ;; + *:SINIX-*:*:*) + if uname -p 2>/dev/null >/dev/null ; then + UNAME_MACHINE=`(uname -p) 2>/dev/null` + echo ${UNAME_MACHINE}-sni-sysv4 + else + echo ns32k-sni-sysv + fi + exit ;; + PENTIUM:*:4.0*:*) # Unisys `ClearPath HMP IX 4000' SVR4/MP effort + # says + echo i586-unisys-sysv4 + exit ;; + *:UNIX_System_V:4*:FTX*) + # From Gerald Hewes . + # How about differentiating between stratus architectures? -djm + echo hppa1.1-stratus-sysv4 + exit ;; + *:*:*:FTX*) + # From seanf@swdc.stratus.com. + echo i860-stratus-sysv4 + exit ;; + i*86:VOS:*:*) + # From Paul.Green@stratus.com. + echo ${UNAME_MACHINE}-stratus-vos + exit ;; + *:VOS:*:*) + # From Paul.Green@stratus.com. + echo hppa1.1-stratus-vos + exit ;; + mc68*:A/UX:*:*) + echo m68k-apple-aux${UNAME_RELEASE} + exit ;; + news*:NEWS-OS:6*:*) + echo mips-sony-newsos6 + exit ;; + R[34]000:*System_V*:*:* | R4000:UNIX_SYSV:*:* | R*000:UNIX_SV:*:*) + if [ -d /usr/nec ]; then + echo mips-nec-sysv${UNAME_RELEASE} + else + echo mips-unknown-sysv${UNAME_RELEASE} + fi + exit ;; + BeBox:BeOS:*:*) # BeOS running on hardware made by Be, PPC only. + echo powerpc-be-beos + exit ;; + BeMac:BeOS:*:*) # BeOS running on Mac or Mac clone, PPC only. + echo powerpc-apple-beos + exit ;; + BePC:BeOS:*:*) # BeOS running on Intel PC compatible. + echo i586-pc-beos + exit ;; + SX-4:SUPER-UX:*:*) + echo sx4-nec-superux${UNAME_RELEASE} + exit ;; + SX-5:SUPER-UX:*:*) + echo sx5-nec-superux${UNAME_RELEASE} + exit ;; + SX-6:SUPER-UX:*:*) + echo sx6-nec-superux${UNAME_RELEASE} + exit ;; + Power*:Rhapsody:*:*) + echo powerpc-apple-rhapsody${UNAME_RELEASE} + exit ;; + *:Rhapsody:*:*) + echo ${UNAME_MACHINE}-apple-rhapsody${UNAME_RELEASE} + exit ;; + *:Darwin:*:*) + UNAME_PROCESSOR=`uname -p` || UNAME_PROCESSOR=unknown + case $UNAME_PROCESSOR in + unknown) UNAME_PROCESSOR=powerpc ;; + esac + echo ${UNAME_PROCESSOR}-apple-darwin${UNAME_RELEASE} + exit ;; + *:procnto*:*:* | *:QNX:[0123456789]*:*) + UNAME_PROCESSOR=`uname -p` + if test "$UNAME_PROCESSOR" = "x86"; then + UNAME_PROCESSOR=i386 + UNAME_MACHINE=pc + fi + echo ${UNAME_PROCESSOR}-${UNAME_MACHINE}-nto-qnx${UNAME_RELEASE} + exit ;; + *:QNX:*:4*) + echo i386-pc-qnx + exit ;; + NSE-?:NONSTOP_KERNEL:*:*) + echo nse-tandem-nsk${UNAME_RELEASE} + exit ;; + NSR-?:NONSTOP_KERNEL:*:*) + echo nsr-tandem-nsk${UNAME_RELEASE} + exit ;; + *:NonStop-UX:*:*) + echo mips-compaq-nonstopux + exit ;; + BS2000:POSIX*:*:*) + echo bs2000-siemens-sysv + exit ;; + DS/*:UNIX_System_V:*:*) + echo ${UNAME_MACHINE}-${UNAME_SYSTEM}-${UNAME_RELEASE} + exit ;; + *:Plan9:*:*) + # "uname -m" is not consistent, so use $cputype instead. 386 + # is converted to i386 for consistency with other x86 + # operating systems. + if test "$cputype" = "386"; then + UNAME_MACHINE=i386 + else + UNAME_MACHINE="$cputype" + fi + echo ${UNAME_MACHINE}-unknown-plan9 + exit ;; + *:TOPS-10:*:*) + echo pdp10-unknown-tops10 + exit ;; + *:TENEX:*:*) + echo pdp10-unknown-tenex + exit ;; + KS10:TOPS-20:*:* | KL10:TOPS-20:*:* | TYPE4:TOPS-20:*:*) + echo pdp10-dec-tops20 + exit ;; + XKL-1:TOPS-20:*:* | TYPE5:TOPS-20:*:*) + echo pdp10-xkl-tops20 + exit ;; + *:TOPS-20:*:*) + echo pdp10-unknown-tops20 + exit ;; + *:ITS:*:*) + echo pdp10-unknown-its + exit ;; + SEI:*:*:SEIUX) + echo mips-sei-seiux${UNAME_RELEASE} + exit ;; + *:DragonFly:*:*) + echo ${UNAME_MACHINE}-unknown-dragonfly`echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'` + exit ;; + *:*VMS:*:*) + UNAME_MACHINE=`(uname -p) 2>/dev/null` + case "${UNAME_MACHINE}" in + A*) echo alpha-dec-vms ; exit ;; + I*) echo ia64-dec-vms ; exit ;; + V*) echo vax-dec-vms ; exit ;; + esac ;; + *:XENIX:*:SysV) + echo i386-pc-xenix + exit ;; + i*86:skyos:*:*) + echo ${UNAME_MACHINE}-pc-skyos`echo ${UNAME_RELEASE}` | sed -e 's/ .*$//' + exit ;; + i*86:rdos:*:*) + echo ${UNAME_MACHINE}-pc-rdos + exit ;; +esac + +#echo '(No uname command or uname output not recognized.)' 1>&2 +#echo "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" 1>&2 + +eval $set_cc_for_build +cat >$dummy.c < +# include +#endif +main () +{ +#if defined (sony) +#if defined (MIPSEB) + /* BFD wants "bsd" instead of "newsos". Perhaps BFD should be changed, + I don't know.... */ + printf ("mips-sony-bsd\n"); exit (0); +#else +#include + printf ("m68k-sony-newsos%s\n", +#ifdef NEWSOS4 + "4" +#else + "" +#endif + ); exit (0); +#endif +#endif + +#if defined (__arm) && defined (__acorn) && defined (__unix) + printf ("arm-acorn-riscix\n"); exit (0); +#endif + +#if defined (hp300) && !defined (hpux) + printf ("m68k-hp-bsd\n"); exit (0); +#endif + +#if defined (NeXT) +#if !defined (__ARCHITECTURE__) +#define __ARCHITECTURE__ "m68k" +#endif + int version; + version=`(hostinfo | sed -n 's/.*NeXT Mach \([0-9]*\).*/\1/p') 2>/dev/null`; + if (version < 4) + printf ("%s-next-nextstep%d\n", __ARCHITECTURE__, version); + else + printf ("%s-next-openstep%d\n", __ARCHITECTURE__, version); + exit (0); +#endif + +#if defined (MULTIMAX) || defined (n16) +#if defined (UMAXV) + printf ("ns32k-encore-sysv\n"); exit (0); +#else +#if defined (CMU) + printf ("ns32k-encore-mach\n"); exit (0); +#else + printf ("ns32k-encore-bsd\n"); exit (0); +#endif +#endif +#endif + +#if defined (__386BSD__) + printf ("i386-pc-bsd\n"); exit (0); +#endif + +#if defined (sequent) +#if defined (i386) + printf ("i386-sequent-dynix\n"); exit (0); +#endif +#if defined (ns32000) + printf ("ns32k-sequent-dynix\n"); exit (0); +#endif +#endif + +#if defined (_SEQUENT_) + struct utsname un; + + uname(&un); + + if (strncmp(un.version, "V2", 2) == 0) { + printf ("i386-sequent-ptx2\n"); exit (0); + } + if (strncmp(un.version, "V1", 2) == 0) { /* XXX is V1 correct? */ + printf ("i386-sequent-ptx1\n"); exit (0); + } + printf ("i386-sequent-ptx\n"); exit (0); + +#endif + +#if defined (vax) +# if !defined (ultrix) +# include +# if defined (BSD) +# if BSD == 43 + printf ("vax-dec-bsd4.3\n"); exit (0); +# else +# if BSD == 199006 + printf ("vax-dec-bsd4.3reno\n"); exit (0); +# else + printf ("vax-dec-bsd\n"); exit (0); +# endif +# endif +# else + printf ("vax-dec-bsd\n"); exit (0); +# endif +# else + printf ("vax-dec-ultrix\n"); exit (0); +# endif +#endif + +#if defined (alliant) && defined (i860) + printf ("i860-alliant-bsd\n"); exit (0); +#endif + + exit (1); +} +EOF + +$CC_FOR_BUILD -o $dummy $dummy.c 2>/dev/null && SYSTEM_NAME=`$dummy` && + { echo "$SYSTEM_NAME"; exit; } + +# Apollos put the system type in the environment. + +test -d /usr/apollo && { echo ${ISP}-apollo-${SYSTYPE}; exit; } + +# Convex versions that predate uname can use getsysinfo(1) + +if [ -x /usr/convex/getsysinfo ] +then + case `getsysinfo -f cpu_type` in + c1*) + echo c1-convex-bsd + exit ;; + c2*) + if getsysinfo -f scalar_acc + then echo c32-convex-bsd + else echo c2-convex-bsd + fi + exit ;; + c34*) + echo c34-convex-bsd + exit ;; + c38*) + echo c38-convex-bsd + exit ;; + c4*) + echo c4-convex-bsd + exit ;; + esac +fi + +cat >&2 < in order to provide the needed +information to handle your system. + +config.guess timestamp = $timestamp + +uname -m = `(uname -m) 2>/dev/null || echo unknown` +uname -r = `(uname -r) 2>/dev/null || echo unknown` +uname -s = `(uname -s) 2>/dev/null || echo unknown` +uname -v = `(uname -v) 2>/dev/null || echo unknown` + +/usr/bin/uname -p = `(/usr/bin/uname -p) 2>/dev/null` +/bin/uname -X = `(/bin/uname -X) 2>/dev/null` + +hostinfo = `(hostinfo) 2>/dev/null` +/bin/universe = `(/bin/universe) 2>/dev/null` +/usr/bin/arch -k = `(/usr/bin/arch -k) 2>/dev/null` +/bin/arch = `(/bin/arch) 2>/dev/null` +/usr/bin/oslevel = `(/usr/bin/oslevel) 2>/dev/null` +/usr/convex/getsysinfo = `(/usr/convex/getsysinfo) 2>/dev/null` + +UNAME_MACHINE = ${UNAME_MACHINE} +UNAME_RELEASE = ${UNAME_RELEASE} +UNAME_SYSTEM = ${UNAME_SYSTEM} +UNAME_VERSION = ${UNAME_VERSION} +EOF + +exit 1 + +# Local variables: +# eval: (add-hook 'write-file-hooks 'time-stamp) +# time-stamp-start: "timestamp='" +# time-stamp-format: "%:y-%02m-%02d" +# time-stamp-end: "'" +# End: diff --git a/libs/pcre/config.h.in b/libs/pcre/config.h.in new file mode 100644 index 0000000000..efc5371545 --- /dev/null +++ b/libs/pcre/config.h.in @@ -0,0 +1,143 @@ + +/* On Unix-like systems config.in is converted by "configure" into config.h. +Some other environments also support the use of "configure". PCRE is written in +Standard C, but there are a few non-standard things it can cope with, allowing +it to run on SunOS4 and other "close to standard" systems. + +On a non-Unix-like system you should just copy this file into config.h, and set +up the macros the way you need them. You should normally change the definitions +of HAVE_STRERROR and HAVE_MEMMOVE to 1. Unfortunately, because of the way +autoconf works, these cannot be made the defaults. If your system has bcopy() +and not memmove(), change the definition of HAVE_BCOPY instead of HAVE_MEMMOVE. +If your system has neither bcopy() nor memmove(), leave them both as 0; an +emulation function will be used. */ + +/* If you are compiling for a system that uses EBCDIC instead of ASCII +character codes, define this macro as 1. On systems that can use "configure", +this can be done via --enable-ebcdic. */ + +#ifndef EBCDIC +#define EBCDIC 0 +#endif + +/* If you are compiling for a system other than a Unix-like system or Win32, +and it needs some magic to be inserted before the definition of a function that +is exported by the library, define this macro to contain the relevant magic. If +you do not define this macro, it defaults to "extern" for a C compiler and +"extern C" for a C++ compiler on non-Win32 systems. This macro apears at the +start of every exported function that is part of the external API. It does not +appear on functions that are "external" in the C sense, but which are internal +to the library. */ + +/* #define PCRE_DATA_SCOPE */ + +/* Define the following macro to empty if the "const" keyword does not work. */ + +#undef const + +/* Define the following macro to "unsigned" if does not define +size_t. */ + +#undef size_t + +/* The following two definitions are mainly for the benefit of SunOS4, which +does not have the strerror() or memmove() functions that should be present in +all Standard C libraries. The macros HAVE_STRERROR and HAVE_MEMMOVE should +normally be defined with the value 1 for other systems, but unfortunately we +cannot make this the default because "configure" files generated by autoconf +will only change 0 to 1; they won't change 1 to 0 if the functions are not +found. */ + +#define HAVE_STRERROR 0 +#define HAVE_MEMMOVE 0 + +/* There are some non-Unix-like systems that don't even have bcopy(). If this +macro is false, an emulation is used. If HAVE_MEMMOVE is set to 1, the value of +HAVE_BCOPY is not relevant. */ + +#define HAVE_BCOPY 0 + +/* The value of NEWLINE determines the newline character. The default is to +leave it up to the compiler, but some sites want to force a particular value. +On Unix-like systems, "configure" can be used to override this default. */ + +#ifndef NEWLINE +#define NEWLINE '\n' +#endif + +/* The value of LINK_SIZE determines the number of bytes used to store links as +offsets within the compiled regex. The default is 2, which allows for compiled +patterns up to 64K long. This covers the vast majority of cases. However, PCRE +can also be compiled to use 3 or 4 bytes instead. This allows for longer +patterns in extreme cases. On systems that support it, "configure" can be used +to override this default. */ + +#ifndef LINK_SIZE +#define LINK_SIZE 2 +#endif + +/* When calling PCRE via the POSIX interface, additional working storage is +required for holding the pointers to capturing substrings because PCRE requires +three integers per substring, whereas the POSIX interface provides only two. If +the number of expected substrings is small, the wrapper function uses space on +the stack, because this is faster than using malloc() for each call. The +threshold above which the stack is no longer used is defined by POSIX_MALLOC_ +THRESHOLD. On systems that support it, "configure" can be used to override this +default. */ + +#ifndef POSIX_MALLOC_THRESHOLD +#define POSIX_MALLOC_THRESHOLD 10 +#endif + +/* PCRE uses recursive function calls to handle backtracking while matching. +This can sometimes be a problem on systems that have stacks of limited size. +Define NO_RECURSE to get a version that doesn't use recursion in the match() +function; instead it creates its own stack by steam using pcre_recurse_malloc() +to obtain memory from the heap. For more detail, see the comments and other +stuff just above the match() function. On systems that support it, "configure" +can be used to set this in the Makefile (use --disable-stack-for-recursion). */ + +/* #define NO_RECURSE */ + +/* The value of MATCH_LIMIT determines the default number of times the internal +match() function can be called during a single execution of pcre_exec(). There +is a runtime interface for setting a different limit. The limit exists in order +to catch runaway regular expressions that take for ever to determine that they +do not match. The default is set very large so that it does not accidentally +catch legitimate cases. On systems that support it, "configure" can be used to +override this default default. */ + +#ifndef MATCH_LIMIT +#define MATCH_LIMIT 10000000 +#endif + +/* The above limit applies to all calls of match(), whether or not they +increase the recursion depth. In some environments it is desirable to limit the +depth of recursive calls of match() more strictly, in order to restrict the +maximum amount of stack (or heap, if NO_RECURSE is defined) that is used. The +value of MATCH_LIMIT_RECURSION applies only to recursive calls of match(). To +have any useful effect, it must be less than the value of MATCH_LIMIT. There is +a runtime method for setting a different limit. On systems that support it, +"configure" can be used to override this default default. */ + +#ifndef MATCH_LIMIT_RECURSION +#define MATCH_LIMIT_RECURSION MATCH_LIMIT +#endif + +/* These three limits are parameterized just in case anybody ever wants to +change them. Care must be taken if they are increased, because they guard +against integer overflow caused by enormously large patterns. */ + +#ifndef MAX_NAME_SIZE +#define MAX_NAME_SIZE 32 +#endif + +#ifndef MAX_NAME_COUNT +#define MAX_NAME_COUNT 10000 +#endif + +#ifndef MAX_DUPLENGTH +#define MAX_DUPLENGTH 30000 +#endif + +/* End */ diff --git a/libs/pcre/config.sub b/libs/pcre/config.sub new file mode 100755 index 0000000000..14332b7bf6 --- /dev/null +++ b/libs/pcre/config.sub @@ -0,0 +1,1627 @@ +#! /bin/sh +# Configuration validation subroutine script. +# Copyright (C) 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, +# 2000, 2001, 2002, 2003, 2004, 2005 Free Software Foundation, Inc. + +timestamp='2005-12-23' + +# This file is (in principle) common to ALL GNU software. +# The presence of a machine in this file suggests that SOME GNU software +# can handle that machine. It does not imply ALL GNU software can. +# +# This file is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 51 Franklin Street - Fifth Floor, Boston, MA +# 02110-1301, USA. +# +# As a special exception to the GNU General Public License, if you +# distribute this file as part of a program that contains a +# configuration script generated by Autoconf, you may include it under +# the same distribution terms that you use for the rest of that program. + + +# Please send patches to . Submit a context +# diff and a properly formatted ChangeLog entry. +# +# Configuration subroutine to validate and canonicalize a configuration type. +# Supply the specified configuration type as an argument. +# If it is invalid, we print an error message on stderr and exit with code 1. +# Otherwise, we print the canonical config type on stdout and succeed. + +# This file is supposed to be the same for all GNU packages +# and recognize all the CPU types, system types and aliases +# that are meaningful with *any* GNU software. +# Each package is responsible for reporting which valid configurations +# it does not support. The user should be able to distinguish +# a failure to support a valid configuration from a meaningless +# configuration. + +# The goal of this file is to map all the various variations of a given +# machine specification into a single specification in the form: +# CPU_TYPE-MANUFACTURER-OPERATING_SYSTEM +# or in some cases, the newer four-part form: +# CPU_TYPE-MANUFACTURER-KERNEL-OPERATING_SYSTEM +# It is wrong to echo any other type of specification. + +me=`echo "$0" | sed -e 's,.*/,,'` + +usage="\ +Usage: $0 [OPTION] CPU-MFR-OPSYS + $0 [OPTION] ALIAS + +Canonicalize a configuration name. + +Operation modes: + -h, --help print this help, then exit + -t, --time-stamp print date of last modification, then exit + -v, --version print version number, then exit + +Report bugs and patches to ." + +version="\ +GNU config.sub ($timestamp) + +Copyright (C) 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005 +Free Software Foundation, Inc. + +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE." + +help=" +Try \`$me --help' for more information." + +# Parse command line +while test $# -gt 0 ; do + case $1 in + --time-stamp | --time* | -t ) + echo "$timestamp" ; exit ;; + --version | -v ) + echo "$version" ; exit ;; + --help | --h* | -h ) + echo "$usage"; exit ;; + -- ) # Stop option processing + shift; break ;; + - ) # Use stdin as input. + break ;; + -* ) + echo "$me: invalid option $1$help" + exit 1 ;; + + *local*) + # First pass through any local machine types. + echo $1 + exit ;; + + * ) + break ;; + esac +done + +case $# in + 0) echo "$me: missing argument$help" >&2 + exit 1;; + 1) ;; + *) echo "$me: too many arguments$help" >&2 + exit 1;; +esac + +# Separate what the user gave into CPU-COMPANY and OS or KERNEL-OS (if any). +# Here we must recognize all the valid KERNEL-OS combinations. +maybe_os=`echo $1 | sed 's/^\(.*\)-\([^-]*-[^-]*\)$/\2/'` +case $maybe_os in + nto-qnx* | linux-gnu* | linux-dietlibc | linux-newlib* | linux-uclibc* | \ + uclinux-uclibc* | uclinux-gnu* | kfreebsd*-gnu* | knetbsd*-gnu* | netbsd*-gnu* | \ + storm-chaos* | os2-emx* | rtmk-nova*) + os=-$maybe_os + basic_machine=`echo $1 | sed 's/^\(.*\)-\([^-]*-[^-]*\)$/\1/'` + ;; + *) + basic_machine=`echo $1 | sed 's/-[^-]*$//'` + if [ $basic_machine != $1 ] + then os=`echo $1 | sed 's/.*-/-/'` + else os=; fi + ;; +esac + +### Let's recognize common machines as not being operating systems so +### that things like config.sub decstation-3100 work. We also +### recognize some manufacturers as not being operating systems, so we +### can provide default operating systems below. +case $os in + -sun*os*) + # Prevent following clause from handling this invalid input. + ;; + -dec* | -mips* | -sequent* | -encore* | -pc532* | -sgi* | -sony* | \ + -att* | -7300* | -3300* | -delta* | -motorola* | -sun[234]* | \ + -unicom* | -ibm* | -next | -hp | -isi* | -apollo | -altos* | \ + -convergent* | -ncr* | -news | -32* | -3600* | -3100* | -hitachi* |\ + -c[123]* | -convex* | -sun | -crds | -omron* | -dg | -ultra | -tti* | \ + -harris | -dolphin | -highlevel | -gould | -cbm | -ns | -masscomp | \ + -apple | -axis | -knuth | -cray) + os= + basic_machine=$1 + ;; + -sim | -cisco | -oki | -wec | -winbond) + os= + basic_machine=$1 + ;; + -scout) + ;; + -wrs) + os=-vxworks + basic_machine=$1 + ;; + -chorusos*) + os=-chorusos + basic_machine=$1 + ;; + -chorusrdb) + os=-chorusrdb + basic_machine=$1 + ;; + -hiux*) + os=-hiuxwe2 + ;; + -sco6) + os=-sco5v6 + basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` + ;; + -sco5) + os=-sco3.2v5 + basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` + ;; + -sco4) + os=-sco3.2v4 + basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` + ;; + -sco3.2.[4-9]*) + os=`echo $os | sed -e 's/sco3.2./sco3.2v/'` + basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` + ;; + -sco3.2v[4-9]*) + # Don't forget version if it is 3.2v4 or newer. + basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` + ;; + -sco5v6*) + # Don't forget version if it is 3.2v4 or newer. + basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` + ;; + -sco*) + os=-sco3.2v2 + basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` + ;; + -udk*) + basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` + ;; + -isc) + os=-isc2.2 + basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` + ;; + -clix*) + basic_machine=clipper-intergraph + ;; + -isc*) + basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` + ;; + -lynx*) + os=-lynxos + ;; + -ptx*) + basic_machine=`echo $1 | sed -e 's/86-.*/86-sequent/'` + ;; + -windowsnt*) + os=`echo $os | sed -e 's/windowsnt/winnt/'` + ;; + -psos*) + os=-psos + ;; + -mint | -mint[0-9]*) + basic_machine=m68k-atari + os=-mint + ;; +esac + +# Decode aliases for certain CPU-COMPANY combinations. +case $basic_machine in + # Recognize the basic CPU types without company name. + # Some are omitted here because they have special meanings below. + 1750a | 580 \ + | a29k \ + | alpha | alphaev[4-8] | alphaev56 | alphaev6[78] | alphapca5[67] \ + | alpha64 | alpha64ev[4-8] | alpha64ev56 | alpha64ev6[78] | alpha64pca5[67] \ + | am33_2.0 \ + | arc | arm | arm[bl]e | arme[lb] | armv[2345] | armv[345][lb] | avr \ + | bfin \ + | c4x | clipper \ + | d10v | d30v | dlx | dsp16xx | dvp \ + | fr30 | frv \ + | h8300 | h8500 | hppa | hppa1.[01] | hppa2.0 | hppa2.0[nw] | hppa64 \ + | i370 | i860 | i960 | ia64 \ + | ip2k | iq2000 \ + | m32r | m32rle | m68000 | m68k | m88k | maxq | mb | microblaze | mcore \ + | mips | mipsbe | mipseb | mipsel | mipsle \ + | mips16 \ + | mips64 | mips64el \ + | mips64vr | mips64vrel \ + | mips64orion | mips64orionel \ + | mips64vr4100 | mips64vr4100el \ + | mips64vr4300 | mips64vr4300el \ + | mips64vr5000 | mips64vr5000el \ + | mips64vr5900 | mips64vr5900el \ + | mipsisa32 | mipsisa32el \ + | mipsisa32r2 | mipsisa32r2el \ + | mipsisa64 | mipsisa64el \ + | mipsisa64r2 | mipsisa64r2el \ + | mipsisa64sb1 | mipsisa64sb1el \ + | mipsisa64sr71k | mipsisa64sr71kel \ + | mipstx39 | mipstx39el \ + | mn10200 | mn10300 \ + | mt \ + | msp430 \ + | ns16k | ns32k \ + | or32 \ + | pdp10 | pdp11 | pj | pjl \ + | powerpc | powerpc64 | powerpc64le | powerpcle | ppcbe \ + | pyramid \ + | sh | sh[1234] | sh[24]a | sh[24]a*eb | sh[23]e | sh[34]eb | shbe | shle | sh[1234]le | sh3ele \ + | sh64 | sh64le \ + | sparc | sparc64 | sparc64b | sparc86x | sparclet | sparclite \ + | sparcv8 | sparcv9 | sparcv9b \ + | strongarm \ + | tahoe | thumb | tic4x | tic80 | tron \ + | v850 | v850e \ + | we32k \ + | x86 | xscale | xscalee[bl] | xstormy16 | xtensa \ + | z8k) + basic_machine=$basic_machine-unknown + ;; + m32c) + basic_machine=$basic_machine-unknown + ;; + m6811 | m68hc11 | m6812 | m68hc12) + # Motorola 68HC11/12. + basic_machine=$basic_machine-unknown + os=-none + ;; + m88110 | m680[12346]0 | m683?2 | m68360 | m5200 | v70 | w65 | z8k) + ;; + ms1) + basic_machine=mt-unknown + ;; + nios2 | nios2-* | nios2 | nios2-*) + basic_machine=nios2-altera + os=-none + ;; + + # We use `pc' rather than `unknown' + # because (1) that's what they normally are, and + # (2) the word "unknown" tends to confuse beginning users. + i*86 | x86_64) + basic_machine=$basic_machine-pc + ;; + # Object if more than one company name word. + *-*-*) + echo Invalid configuration \`$1\': machine \`$basic_machine\' not recognized 1>&2 + exit 1 + ;; + # Recognize the basic CPU types with company name. + 580-* \ + | a29k-* \ + | alpha-* | alphaev[4-8]-* | alphaev56-* | alphaev6[78]-* \ + | alpha64-* | alpha64ev[4-8]-* | alpha64ev56-* | alpha64ev6[78]-* \ + | alphapca5[67]-* | alpha64pca5[67]-* | arc-* \ + | arm-* | armbe-* | armle-* | armeb-* | armv*-* \ + | avr-* \ + | bfin-* | bs2000-* \ + | c[123]* | c30-* | [cjt]90-* | c4x-* | c54x-* | c55x-* | c6x-* \ + | clipper-* | craynv-* | cydra-* \ + | d10v-* | d30v-* | dlx-* \ + | elxsi-* \ + | f30[01]-* | f700-* | fr30-* | frv-* | fx80-* \ + | h8300-* | h8500-* \ + | hppa-* | hppa1.[01]-* | hppa2.0-* | hppa2.0[nw]-* | hppa64-* \ + | i*86-* | i860-* | i960-* | ia64-* \ + | ip2k-* | iq2000-* \ + | m32r-* | m32rle-* \ + | m68000-* | m680[012346]0-* | m68360-* | m683?2-* | m68k-* \ + | m88110-* | m88k-* | maxq-* | mcore-* \ + | mips-* | mipsbe-* | mipseb-* | mipsel-* | mipsle-* \ + | mips16-* \ + | mips64-* | mips64el-* \ + | mips64vr-* | mips64vrel-* \ + | mips64orion-* | mips64orionel-* \ + | mips64vr4100-* | mips64vr4100el-* \ + | mips64vr4300-* | mips64vr4300el-* \ + | mips64vr5000-* | mips64vr5000el-* \ + | mips64vr5900-* | mips64vr5900el-* \ + | mipsisa32-* | mipsisa32el-* \ + | mipsisa32r2-* | mipsisa32r2el-* \ + | mipsisa64-* | mipsisa64el-* \ + | mipsisa64r2-* | mipsisa64r2el-* \ + | mipsisa64sb1-* | mipsisa64sb1el-* \ + | mipsisa64sr71k-* | mipsisa64sr71kel-* \ + | mipstx39-* | mipstx39el-* \ + | mmix-* \ + | mt-* \ + | msp430-* \ + | none-* | np1-* | ns16k-* | ns32k-* \ + | orion-* \ + | pdp10-* | pdp11-* | pj-* | pjl-* | pn-* | power-* \ + | powerpc-* | powerpc64-* | powerpc64le-* | powerpcle-* | ppcbe-* \ + | pyramid-* \ + | romp-* | rs6000-* \ + | sh-* | sh[1234]-* | sh[24]a-* | sh[23]e-* | sh[34]eb-* | shbe-* \ + | shle-* | sh[1234]le-* | sh3ele-* | sh64-* | sh64le-* \ + | sparc-* | sparc64-* | sparc64b-* | sparc86x-* | sparclet-* \ + | sparclite-* \ + | sparcv8-* | sparcv9-* | sparcv9b-* | strongarm-* | sv1-* | sx?-* \ + | tahoe-* | thumb-* \ + | tic30-* | tic4x-* | tic54x-* | tic55x-* | tic6x-* | tic80-* \ + | tron-* \ + | v850-* | v850e-* | vax-* \ + | we32k-* \ + | x86-* | x86_64-* | xps100-* | xscale-* | xscalee[bl]-* \ + | xstormy16-* | xtensa-* \ + | ymp-* \ + | z8k-*) + ;; + m32c-*) + ;; + # Recognize the various machine names and aliases which stand + # for a CPU type and a company and sometimes even an OS. + 386bsd) + basic_machine=i386-unknown + os=-bsd + ;; + 3b1 | 7300 | 7300-att | att-7300 | pc7300 | safari | unixpc) + basic_machine=m68000-att + ;; + 3b*) + basic_machine=we32k-att + ;; + a29khif) + basic_machine=a29k-amd + os=-udi + ;; + abacus) + basic_machine=abacus-unknown + ;; + adobe68k) + basic_machine=m68010-adobe + os=-scout + ;; + alliant | fx80) + basic_machine=fx80-alliant + ;; + altos | altos3068) + basic_machine=m68k-altos + ;; + am29k) + basic_machine=a29k-none + os=-bsd + ;; + amd64) + basic_machine=x86_64-pc + ;; + amd64-*) + basic_machine=x86_64-`echo $basic_machine | sed 's/^[^-]*-//'` + ;; + amdahl) + basic_machine=580-amdahl + os=-sysv + ;; + amiga | amiga-*) + basic_machine=m68k-unknown + ;; + amigaos | amigados) + basic_machine=m68k-unknown + os=-amigaos + ;; + amigaunix | amix) + basic_machine=m68k-unknown + os=-sysv4 + ;; + apollo68) + basic_machine=m68k-apollo + os=-sysv + ;; + apollo68bsd) + basic_machine=m68k-apollo + os=-bsd + ;; + aux) + basic_machine=m68k-apple + os=-aux + ;; + balance) + basic_machine=ns32k-sequent + os=-dynix + ;; + c90) + basic_machine=c90-cray + os=-unicos + ;; + convex-c1) + basic_machine=c1-convex + os=-bsd + ;; + convex-c2) + basic_machine=c2-convex + os=-bsd + ;; + convex-c32) + basic_machine=c32-convex + os=-bsd + ;; + convex-c34) + basic_machine=c34-convex + os=-bsd + ;; + convex-c38) + basic_machine=c38-convex + os=-bsd + ;; + cray | j90) + basic_machine=j90-cray + os=-unicos + ;; + craynv) + basic_machine=craynv-cray + os=-unicosmp + ;; + cr16c) + basic_machine=cr16c-unknown + os=-elf + ;; + crds | unos) + basic_machine=m68k-crds + ;; + crisv32 | crisv32-* | etraxfs*) + basic_machine=crisv32-axis + ;; + cris | cris-* | etrax*) + basic_machine=cris-axis + ;; + crx) + basic_machine=crx-unknown + os=-elf + ;; + da30 | da30-*) + basic_machine=m68k-da30 + ;; + decstation | decstation-3100 | pmax | pmax-* | pmin | dec3100 | decstatn) + basic_machine=mips-dec + ;; + decsystem10* | dec10*) + basic_machine=pdp10-dec + os=-tops10 + ;; + decsystem20* | dec20*) + basic_machine=pdp10-dec + os=-tops20 + ;; + delta | 3300 | motorola-3300 | motorola-delta \ + | 3300-motorola | delta-motorola) + basic_machine=m68k-motorola + ;; + delta88) + basic_machine=m88k-motorola + os=-sysv3 + ;; + djgpp) + basic_machine=i586-pc + os=-msdosdjgpp + ;; + dpx20 | dpx20-*) + basic_machine=rs6000-bull + os=-bosx + ;; + dpx2* | dpx2*-bull) + basic_machine=m68k-bull + os=-sysv3 + ;; + ebmon29k) + basic_machine=a29k-amd + os=-ebmon + ;; + elxsi) + basic_machine=elxsi-elxsi + os=-bsd + ;; + encore | umax | mmax) + basic_machine=ns32k-encore + ;; + es1800 | OSE68k | ose68k | ose | OSE) + basic_machine=m68k-ericsson + os=-ose + ;; + fx2800) + basic_machine=i860-alliant + ;; + genix) + basic_machine=ns32k-ns + ;; + gmicro) + basic_machine=tron-gmicro + os=-sysv + ;; + go32) + basic_machine=i386-pc + os=-go32 + ;; + h3050r* | hiux*) + basic_machine=hppa1.1-hitachi + os=-hiuxwe2 + ;; + h8300hms) + basic_machine=h8300-hitachi + os=-hms + ;; + h8300xray) + basic_machine=h8300-hitachi + os=-xray + ;; + h8500hms) + basic_machine=h8500-hitachi + os=-hms + ;; + harris) + basic_machine=m88k-harris + os=-sysv3 + ;; + hp300-*) + basic_machine=m68k-hp + ;; + hp300bsd) + basic_machine=m68k-hp + os=-bsd + ;; + hp300hpux) + basic_machine=m68k-hp + os=-hpux + ;; + hp3k9[0-9][0-9] | hp9[0-9][0-9]) + basic_machine=hppa1.0-hp + ;; + hp9k2[0-9][0-9] | hp9k31[0-9]) + basic_machine=m68000-hp + ;; + hp9k3[2-9][0-9]) + basic_machine=m68k-hp + ;; + hp9k6[0-9][0-9] | hp6[0-9][0-9]) + basic_machine=hppa1.0-hp + ;; + hp9k7[0-79][0-9] | hp7[0-79][0-9]) + basic_machine=hppa1.1-hp + ;; + hp9k78[0-9] | hp78[0-9]) + # FIXME: really hppa2.0-hp + basic_machine=hppa1.1-hp + ;; + hp9k8[67]1 | hp8[67]1 | hp9k80[24] | hp80[24] | hp9k8[78]9 | hp8[78]9 | hp9k893 | hp893) + # FIXME: really hppa2.0-hp + basic_machine=hppa1.1-hp + ;; + hp9k8[0-9][13679] | hp8[0-9][13679]) + basic_machine=hppa1.1-hp + ;; + hp9k8[0-9][0-9] | hp8[0-9][0-9]) + basic_machine=hppa1.0-hp + ;; + hppa-next) + os=-nextstep3 + ;; + hppaosf) + basic_machine=hppa1.1-hp + os=-osf + ;; + hppro) + basic_machine=hppa1.1-hp + os=-proelf + ;; + i370-ibm* | ibm*) + basic_machine=i370-ibm + ;; +# I'm not sure what "Sysv32" means. Should this be sysv3.2? + i*86v32) + basic_machine=`echo $1 | sed -e 's/86.*/86-pc/'` + os=-sysv32 + ;; + i*86v4*) + basic_machine=`echo $1 | sed -e 's/86.*/86-pc/'` + os=-sysv4 + ;; + i*86v) + basic_machine=`echo $1 | sed -e 's/86.*/86-pc/'` + os=-sysv + ;; + i*86sol2) + basic_machine=`echo $1 | sed -e 's/86.*/86-pc/'` + os=-solaris2 + ;; + i386mach) + basic_machine=i386-mach + os=-mach + ;; + i386-vsta | vsta) + basic_machine=i386-unknown + os=-vsta + ;; + iris | iris4d) + basic_machine=mips-sgi + case $os in + -irix*) + ;; + *) + os=-irix4 + ;; + esac + ;; + isi68 | isi) + basic_machine=m68k-isi + os=-sysv + ;; + m88k-omron*) + basic_machine=m88k-omron + ;; + magnum | m3230) + basic_machine=mips-mips + os=-sysv + ;; + merlin) + basic_machine=ns32k-utek + os=-sysv + ;; + mingw32) + basic_machine=i386-pc + os=-mingw32 + ;; + miniframe) + basic_machine=m68000-convergent + ;; + *mint | -mint[0-9]* | *MiNT | *MiNT[0-9]*) + basic_machine=m68k-atari + os=-mint + ;; + mipsEE* | ee | ps2) + basic_machine=mips64r5900el-scei + case $os in + -linux*) + ;; + *) + os=-elf + ;; + esac + ;; + iop) + basic_machine=mipsel-scei + os=-irx + ;; + dvp) + basic_machine=dvp-scei + os=-elf + ;; + mips3*-*) + basic_machine=`echo $basic_machine | sed -e 's/mips3/mips64/'` + ;; + mips3*) + basic_machine=`echo $basic_machine | sed -e 's/mips3/mips64/'`-unknown + ;; + monitor) + basic_machine=m68k-rom68k + os=-coff + ;; + morphos) + basic_machine=powerpc-unknown + os=-morphos + ;; + msdos) + basic_machine=i386-pc + os=-msdos + ;; + ms1-*) + basic_machine=`echo $basic_machine | sed -e 's/ms1-/mt-/'` + ;; + mvs) + basic_machine=i370-ibm + os=-mvs + ;; + ncr3000) + basic_machine=i486-ncr + os=-sysv4 + ;; + netbsd386) + basic_machine=i386-unknown + os=-netbsd + ;; + netwinder) + basic_machine=armv4l-rebel + os=-linux + ;; + news | news700 | news800 | news900) + basic_machine=m68k-sony + os=-newsos + ;; + news1000) + basic_machine=m68030-sony + os=-newsos + ;; + news-3600 | risc-news) + basic_machine=mips-sony + os=-newsos + ;; + necv70) + basic_machine=v70-nec + os=-sysv + ;; + next | m*-next ) + basic_machine=m68k-next + case $os in + -nextstep* ) + ;; + -ns2*) + os=-nextstep2 + ;; + *) + os=-nextstep3 + ;; + esac + ;; + nh3000) + basic_machine=m68k-harris + os=-cxux + ;; + nh[45]000) + basic_machine=m88k-harris + os=-cxux + ;; + nindy960) + basic_machine=i960-intel + os=-nindy + ;; + mon960) + basic_machine=i960-intel + os=-mon960 + ;; + nonstopux) + basic_machine=mips-compaq + os=-nonstopux + ;; + np1) + basic_machine=np1-gould + ;; + nsr-tandem) + basic_machine=nsr-tandem + ;; + op50n-* | op60c-*) + basic_machine=hppa1.1-oki + os=-proelf + ;; + openrisc | openrisc-*) + basic_machine=or32-unknown + ;; + os400) + basic_machine=powerpc-ibm + os=-os400 + ;; + OSE68000 | ose68000) + basic_machine=m68000-ericsson + os=-ose + ;; + os68k) + basic_machine=m68k-none + os=-os68k + ;; + pa-hitachi) + basic_machine=hppa1.1-hitachi + os=-hiuxwe2 + ;; + paragon) + basic_machine=i860-intel + os=-osf + ;; + pbd) + basic_machine=sparc-tti + ;; + pbb) + basic_machine=m68k-tti + ;; + pc532 | pc532-*) + basic_machine=ns32k-pc532 + ;; + pc98) + basic_machine=i386-pc + ;; + pc98-*) + basic_machine=i386-`echo $basic_machine | sed 's/^[^-]*-//'` + ;; + pentium | p5 | k5 | k6 | nexgen | viac3) + basic_machine=i586-pc + ;; + pentiumpro | p6 | 6x86 | athlon | athlon_*) + basic_machine=i686-pc + ;; + pentiumii | pentium2 | pentiumiii | pentium3) + basic_machine=i686-pc + ;; + pentium4) + basic_machine=i786-pc + ;; + pentium-* | p5-* | k5-* | k6-* | nexgen-* | viac3-*) + basic_machine=i586-`echo $basic_machine | sed 's/^[^-]*-//'` + ;; + pentiumpro-* | p6-* | 6x86-* | athlon-*) + basic_machine=i686-`echo $basic_machine | sed 's/^[^-]*-//'` + ;; + pentiumii-* | pentium2-* | pentiumiii-* | pentium3-*) + basic_machine=i686-`echo $basic_machine | sed 's/^[^-]*-//'` + ;; + pentium4-*) + basic_machine=i786-`echo $basic_machine | sed 's/^[^-]*-//'` + ;; + pn) + basic_machine=pn-gould + ;; + power) basic_machine=power-ibm + ;; + ppc) basic_machine=powerpc-unknown + ;; + ppc-*) basic_machine=powerpc-`echo $basic_machine | sed 's/^[^-]*-//'` + ;; + ppcle | powerpclittle | ppc-le | powerpc-little) + basic_machine=powerpcle-unknown + ;; + ppcle-* | powerpclittle-*) + basic_machine=powerpcle-`echo $basic_machine | sed 's/^[^-]*-//'` + ;; + ppc64) basic_machine=powerpc64-unknown + ;; + ppc64-*) basic_machine=powerpc64-`echo $basic_machine | sed 's/^[^-]*-//'` + ;; + ppc64le | powerpc64little | ppc64-le | powerpc64-little) + basic_machine=powerpc64le-unknown + ;; + ppc64le-* | powerpc64little-*) + basic_machine=powerpc64le-`echo $basic_machine | sed 's/^[^-]*-//'` + ;; + ps2) + basic_machine=i386-ibm + ;; + pw32) + basic_machine=i586-unknown + os=-pw32 + ;; + rdos) + basic_machine=i386-pc + os=-rdos + ;; + rom68k) + basic_machine=m68k-rom68k + os=-coff + ;; + rm[46]00) + basic_machine=mips-siemens + ;; + rtpc | rtpc-*) + basic_machine=romp-ibm + ;; + s390 | s390-*) + basic_machine=s390-ibm + ;; + s390x | s390x-*) + basic_machine=s390x-ibm + ;; + sa29200) + basic_machine=a29k-amd + os=-udi + ;; + sb1) + basic_machine=mipsisa64sb1-unknown + ;; + sb1el) + basic_machine=mipsisa64sb1el-unknown + ;; + sei) + basic_machine=mips-sei + os=-seiux + ;; + sequent) + basic_machine=i386-sequent + ;; + sh) + basic_machine=sh-hitachi + os=-hms + ;; + sh64) + basic_machine=sh64-unknown + ;; + sparclite-wrs | simso-wrs) + basic_machine=sparclite-wrs + os=-vxworks + ;; + sps7) + basic_machine=m68k-bull + os=-sysv2 + ;; + spur) + basic_machine=spur-unknown + ;; + st2000) + basic_machine=m68k-tandem + ;; + stratus) + basic_machine=i860-stratus + os=-sysv4 + ;; + sun2) + basic_machine=m68000-sun + ;; + sun2os3) + basic_machine=m68000-sun + os=-sunos3 + ;; + sun2os4) + basic_machine=m68000-sun + os=-sunos4 + ;; + sun3os3) + basic_machine=m68k-sun + os=-sunos3 + ;; + sun3os4) + basic_machine=m68k-sun + os=-sunos4 + ;; + sun4os3) + basic_machine=sparc-sun + os=-sunos3 + ;; + sun4os4) + basic_machine=sparc-sun + os=-sunos4 + ;; + sun4sol2) + basic_machine=sparc-sun + os=-solaris2 + ;; + sun3 | sun3-*) + basic_machine=m68k-sun + ;; + sun4) + basic_machine=sparc-sun + ;; + sun386 | sun386i | roadrunner) + basic_machine=i386-sun + ;; + sv1) + basic_machine=sv1-cray + os=-unicos + ;; + symmetry) + basic_machine=i386-sequent + os=-dynix + ;; + t3e) + basic_machine=alphaev5-cray + os=-unicos + ;; + t90) + basic_machine=t90-cray + os=-unicos + ;; + tic54x | c54x*) + basic_machine=tic54x-unknown + os=-coff + ;; + tic55x | c55x*) + basic_machine=tic55x-unknown + os=-coff + ;; + tic6x | c6x*) + basic_machine=tic6x-unknown + os=-coff + ;; + tx39) + basic_machine=mipstx39-unknown + ;; + tx39el) + basic_machine=mipstx39el-unknown + ;; + toad1) + basic_machine=pdp10-xkl + os=-tops20 + ;; + tower | tower-32) + basic_machine=m68k-ncr + ;; + tpf) + basic_machine=s390x-ibm + os=-tpf + ;; + udi29k) + basic_machine=a29k-amd + os=-udi + ;; + ultra3) + basic_machine=a29k-nyu + os=-sym1 + ;; + v810 | necv810) + basic_machine=v810-nec + os=-none + ;; + vaxv) + basic_machine=vax-dec + os=-sysv + ;; + vms) + basic_machine=vax-dec + os=-vms + ;; + vpp*|vx|vx-*) + basic_machine=f301-fujitsu + ;; + vxworks960) + basic_machine=i960-wrs + os=-vxworks + ;; + vxworks68) + basic_machine=m68k-wrs + os=-vxworks + ;; + vxworks29k) + basic_machine=a29k-wrs + os=-vxworks + ;; + w65*) + basic_machine=w65-wdc + os=-none + ;; + w89k-*) + basic_machine=hppa1.1-winbond + os=-proelf + ;; + xbox) + basic_machine=i686-pc + os=-mingw32 + ;; + xps | xps100) + basic_machine=xps100-honeywell + ;; + ymp) + basic_machine=ymp-cray + os=-unicos + ;; + z8k-*-coff) + basic_machine=z8k-unknown + os=-sim + ;; + none) + basic_machine=none-none + os=-none + ;; + +# Here we handle the default manufacturer of certain CPU types. It is in +# some cases the only manufacturer, in others, it is the most popular. + w89k) + basic_machine=hppa1.1-winbond + ;; + op50n) + basic_machine=hppa1.1-oki + ;; + op60c) + basic_machine=hppa1.1-oki + ;; + romp) + basic_machine=romp-ibm + ;; + mmix) + basic_machine=mmix-knuth + ;; + rs6000) + basic_machine=rs6000-ibm + ;; + vax) + basic_machine=vax-dec + ;; + pdp10) + # there are many clones, so DEC is not a safe bet + basic_machine=pdp10-unknown + ;; + pdp11) + basic_machine=pdp11-dec + ;; + we32k) + basic_machine=we32k-att + ;; + sh[1234] | sh[24]a | sh[34]eb | sh[1234]le | sh[23]ele) + basic_machine=sh-unknown + ;; + sparc | sparcv8 | sparcv9 | sparcv9b) + basic_machine=sparc-sun + ;; + cydra) + basic_machine=cydra-cydrome + ;; + orion) + basic_machine=orion-highlevel + ;; + orion105) + basic_machine=clipper-highlevel + ;; + mac | mpw | mac-mpw) + basic_machine=m68k-apple + ;; + pmac | pmac-mpw) + basic_machine=powerpc-apple + ;; + *-unknown) + # Make sure to match an already-canonicalized machine name. + ;; + *) + echo Invalid configuration \`$1\': machine \`$basic_machine\' not recognized 1>&2 + exit 1 + ;; +esac + +# Here we canonicalize certain aliases for manufacturers. +case $basic_machine in + *-digital*) + basic_machine=`echo $basic_machine | sed 's/digital.*/dec/'` + ;; + *-commodore*) + basic_machine=`echo $basic_machine | sed 's/commodore.*/cbm/'` + ;; + *) + ;; +esac + +# Decode manufacturer-specific aliases for certain operating systems. + +if [ x"$os" != x"" ] +then +case $os in + # First match some system type aliases + # that might get confused with valid system types. + # -solaris* is a basic system type, with this one exception. + -solaris1 | -solaris1.*) + os=`echo $os | sed -e 's|solaris1|sunos4|'` + ;; + -solaris) + os=-solaris2 + ;; + -svr4*) + os=-sysv4 + ;; + -unixware*) + os=-sysv4.2uw + ;; + -gnu/linux*) + os=`echo $os | sed -e 's|gnu/linux|linux-gnu|'` + ;; + # First accept the basic system types. + # The portable systems comes first. + # Each alternative MUST END IN A *, to match a version number. + # -sysv* is not here because it comes later, after sysvr4. + -gnu* | -bsd* | -mach* | -minix* | -genix* | -ultrix* | -irix* \ + | -*vms* | -sco* | -esix* | -isc* | -aix* | -sunos | -sunos[34]*\ + | -hpux* | -unos* | -osf* | -luna* | -dgux* | -solaris* | -sym* \ + | -amigaos* | -amigados* | -msdos* | -newsos* | -unicos* | -aof* \ + | -aos* \ + | -nindy* | -vxsim* | -vxworks* | -ebmon* | -hms* | -mvs* \ + | -clix* | -riscos* | -uniplus* | -iris* | -rtu* | -xenix* \ + | -hiux* | -386bsd* | -knetbsd* | -mirbsd* | -netbsd* | -openbsd* \ + | -ekkobsd* | -kfreebsd* | -freebsd* | -riscix* | -lynxos* \ + | -bosx* | -nextstep* | -cxux* | -aout* | -elf* | -oabi* \ + | -ptx* | -coff* | -ecoff* | -winnt* | -domain* | -vsta* \ + | -udi* | -eabi* | -lites* | -ieee* | -go32* | -aux* \ + | -chorusos* | -chorusrdb* \ + | -cygwin* | -pe* | -psos* | -moss* | -proelf* | -rtems* \ + | -mingw32* | -linux-gnu* | -linux-newlib* | -linux-uclibc* \ + | -uxpv* | -beos* | -mpeix* | -udk* \ + | -interix* | -uwin* | -mks* | -rhapsody* | -darwin* | -opened* \ + | -openstep* | -oskit* | -conix* | -pw32* | -nonstopux* \ + | -storm-chaos* | -tops10* | -tenex* | -tops20* | -its* \ + | -os2* | -vos* | -palmos* | -uclinux* | -nucleus* \ + | -morphos* | -superux* | -rtmk* | -rtmk-nova* | -windiss* \ + | -powermax* | -dnix* | -nx6 | -nx7 | -sei* | -dragonfly* \ + | -skyos* | -haiku* | -rdos* | -irx*) + # Remember, each alternative MUST END IN *, to match a version number. + ;; + -qnx*) + case $basic_machine in + x86-* | i*86-*) + ;; + *) + os=-nto$os + ;; + esac + ;; + -nto-qnx*) + ;; + -nto*) + os=`echo $os | sed -e 's|nto|nto-qnx|'` + ;; + -sim | -es1800* | -hms* | -xray | -os68k* | -none* | -v88r* \ + | -windows* | -osx | -abug | -netware* | -os9* | -beos* | -haiku* \ + | -macos* | -mpw* | -magic* | -mmixware* | -mon960* | -lnews*) + ;; + -mac*) + os=`echo $os | sed -e 's|mac|macos|'` + ;; + -linux-dietlibc) + os=-linux-dietlibc + ;; + -linux*) + os=`echo $os | sed -e 's|linux|linux-gnu|'` + ;; + -sunos5*) + os=`echo $os | sed -e 's|sunos5|solaris2|'` + ;; + -sunos6*) + os=`echo $os | sed -e 's|sunos6|solaris3|'` + ;; + -opened*) + os=-openedition + ;; + -os400*) + os=-os400 + ;; + -wince*) + os=-wince + ;; + -osfrose*) + os=-osfrose + ;; + -osf*) + os=-osf + ;; + -utek*) + os=-bsd + ;; + -dynix*) + os=-bsd + ;; + -acis*) + os=-aos + ;; + -atheos*) + os=-atheos + ;; + -syllable*) + os=-syllable + ;; + -386bsd) + os=-bsd + ;; + -ctix* | -uts*) + os=-sysv + ;; + -nova*) + os=-rtmk-nova + ;; + -ns2 ) + os=-nextstep2 + ;; + -nsk*) + os=-nsk + ;; + # Preserve the version number of sinix5. + -sinix5.*) + os=`echo $os | sed -e 's|sinix|sysv|'` + ;; + -sinix*) + os=-sysv4 + ;; + -tpf*) + os=-tpf + ;; + -triton*) + os=-sysv3 + ;; + -oss*) + os=-sysv3 + ;; + -svr4) + os=-sysv4 + ;; + -svr3) + os=-sysv3 + ;; + -sysvr4) + os=-sysv4 + ;; + # This must come after -sysvr4. + -sysv*) + ;; + -ose*) + os=-ose + ;; + -es1800*) + os=-ose + ;; + -xenix) + os=-xenix + ;; + -*mint | -mint[0-9]* | -*MiNT | -MiNT[0-9]*) + os=-mint + ;; + -aros*) + os=-aros + ;; + -kaos*) + os=-kaos + ;; + -zvmoe) + os=-zvmoe + ;; + -none) + ;; + *) + # Get rid of the `-' at the beginning of $os. + os=`echo $os | sed 's/[^-]*-//'` + echo Invalid configuration \`$1\': system \`$os\' not recognized 1>&2 + exit 1 + ;; +esac +else + +# Here we handle the default operating systems that come with various machines. +# The value should be what the vendor currently ships out the door with their +# machine or put another way, the most popular os provided with the machine. + +# Note that if you're going to try to match "-MANUFACTURER" here (say, +# "-sun"), then you have to tell the case statement up towards the top +# that MANUFACTURER isn't an operating system. Otherwise, code above +# will signal an error saying that MANUFACTURER isn't an operating +# system, and we'll never get to this point. + +case $basic_machine in + *-acorn) + os=-riscix1.2 + ;; + arm*-rebel) + os=-linux + ;; + arm*-semi) + os=-aout + ;; + c4x-* | tic4x-*) + os=-coff + ;; + # This must come before the *-dec entry. + pdp10-*) + os=-tops20 + ;; + pdp11-*) + os=-none + ;; + *-dec | vax-*) + os=-ultrix4.2 + ;; + m68*-apollo) + os=-domain + ;; + i386-sun) + os=-sunos4.0.2 + ;; + m68000-sun) + os=-sunos3 + # This also exists in the configure program, but was not the + # default. + # os=-sunos4 + ;; + m68*-cisco) + os=-aout + ;; + mips*-cisco) + os=-elf + ;; + mips*-*) + os=-elf + ;; + or32-*) + os=-coff + ;; + *-tti) # must be before sparc entry or we get the wrong os. + os=-sysv3 + ;; + sparc-* | *-sun) + os=-sunos4.1.1 + ;; + *-be) + os=-beos + ;; + *-haiku) + os=-haiku + ;; + *-ibm) + os=-aix + ;; + *-knuth) + os=-mmixware + ;; + *-wec) + os=-proelf + ;; + *-winbond) + os=-proelf + ;; + *-oki) + os=-proelf + ;; + *-hp) + os=-hpux + ;; + *-hitachi) + os=-hiux + ;; + i860-* | *-att | *-ncr | *-altos | *-motorola | *-convergent) + os=-sysv + ;; + *-cbm) + os=-amigaos + ;; + *-dg) + os=-dgux + ;; + *-dolphin) + os=-sysv3 + ;; + m68k-ccur) + os=-rtu + ;; + m88k-omron*) + os=-luna + ;; + *-next ) + os=-nextstep + ;; + *-sequent) + os=-ptx + ;; + *-crds) + os=-unos + ;; + *-ns) + os=-genix + ;; + i370-*) + os=-mvs + ;; + *-next) + os=-nextstep3 + ;; + *-gould) + os=-sysv + ;; + *-highlevel) + os=-bsd + ;; + *-encore) + os=-bsd + ;; + *-sgi) + os=-irix + ;; + *-siemens) + os=-sysv4 + ;; + *-masscomp) + os=-rtu + ;; + f30[01]-fujitsu | f700-fujitsu) + os=-uxpv + ;; + *-rom68k) + os=-coff + ;; + *-*bug) + os=-coff + ;; + *-apple) + os=-macos + ;; + *-atari*) + os=-mint + ;; + *) + os=-none + ;; +esac +fi + +# Here we handle the case where we know the os, and the CPU type, but not the +# manufacturer. We pick the logical manufacturer. +vendor=unknown +case $basic_machine in + *-unknown) + case $os in + -riscix*) + vendor=acorn + ;; + -sunos*) + vendor=sun + ;; + -aix*) + vendor=ibm + ;; + -beos*) + vendor=be + ;; + -hpux*) + vendor=hp + ;; + -mpeix*) + vendor=hp + ;; + -hiux*) + vendor=hitachi + ;; + -unos*) + vendor=crds + ;; + -dgux*) + vendor=dg + ;; + -luna*) + vendor=omron + ;; + -genix*) + vendor=ns + ;; + -mvs* | -opened*) + vendor=ibm + ;; + -os400*) + vendor=ibm + ;; + -ptx*) + vendor=sequent + ;; + -tpf*) + vendor=ibm + ;; + -vxsim* | -vxworks* | -windiss*) + vendor=wrs + ;; + -aux*) + vendor=apple + ;; + -hms*) + vendor=hitachi + ;; + -mpw* | -macos*) + vendor=apple + ;; + -*mint | -mint[0-9]* | -*MiNT | -MiNT[0-9]*) + vendor=atari + ;; + -vos*) + vendor=stratus + ;; + esac + basic_machine=`echo $basic_machine | sed "s/unknown/$vendor/"` + ;; +esac + +echo $basic_machine$os +exit + +# Local variables: +# eval: (add-hook 'write-file-hooks 'time-stamp) +# time-stamp-start: "timestamp='" +# time-stamp-format: "%:y-%02m-%02d" +# time-stamp-end: "'" +# End: diff --git a/libs/pcre/configure b/libs/pcre/configure new file mode 100755 index 0000000000..cd0a4ca8da --- /dev/null +++ b/libs/pcre/configure @@ -0,0 +1,21093 @@ +#! /bin/sh +# Guess values for system-dependent variables and create Makefiles. +# Generated by GNU Autoconf 2.59. +# +# Copyright (C) 2003 Free Software Foundation, Inc. +# This configure script is free software; the Free Software Foundation +# gives unlimited permission to copy, distribute and modify it. +## --------------------- ## +## M4sh Initialization. ## +## --------------------- ## + +# Be Bourne compatible +if test -n "${ZSH_VERSION+set}" && (emulate sh) >/dev/null 2>&1; then + emulate sh + NULLCMD=: + # Zsh 3.x and 4.x performs word splitting on ${1+"$@"}, which + # is contrary to our usage. Disable this feature. + alias -g '${1+"$@"}'='"$@"' +elif test -n "${BASH_VERSION+set}" && (set -o posix) >/dev/null 2>&1; then + set -o posix +fi +DUALCASE=1; export DUALCASE # for MKS sh + +# Support unset when possible. +if ( (MAIL=60; unset MAIL) || exit) >/dev/null 2>&1; then + as_unset=unset +else + as_unset=false +fi + + +# Work around bugs in pre-3.0 UWIN ksh. +$as_unset ENV MAIL MAILPATH +PS1='$ ' +PS2='> ' +PS4='+ ' + +# NLS nuisances. +for as_var in \ + LANG LANGUAGE LC_ADDRESS LC_ALL LC_COLLATE LC_CTYPE LC_IDENTIFICATION \ + LC_MEASUREMENT LC_MESSAGES LC_MONETARY LC_NAME LC_NUMERIC LC_PAPER \ + LC_TELEPHONE LC_TIME +do + if (set +x; test -z "`(eval $as_var=C; export $as_var) 2>&1`"); then + eval $as_var=C; export $as_var + else + $as_unset $as_var + fi +done + +# Required to use basename. +if expr a : '\(a\)' >/dev/null 2>&1; then + as_expr=expr +else + as_expr=false +fi + +if (basename /) >/dev/null 2>&1 && test "X`basename / 2>&1`" = "X/"; then + as_basename=basename +else + as_basename=false +fi + + +# Name of the executable. +as_me=`$as_basename "$0" || +$as_expr X/"$0" : '.*/\([^/][^/]*\)/*$' \| \ + X"$0" : 'X\(//\)$' \| \ + X"$0" : 'X\(/\)$' \| \ + . : '\(.\)' 2>/dev/null || +echo X/"$0" | + sed '/^.*\/\([^/][^/]*\)\/*$/{ s//\1/; q; } + /^X\/\(\/\/\)$/{ s//\1/; q; } + /^X\/\(\/\).*/{ s//\1/; q; } + s/.*/./; q'` + + +# PATH needs CR, and LINENO needs CR and PATH. +# Avoid depending upon Character Ranges. +as_cr_letters='abcdefghijklmnopqrstuvwxyz' +as_cr_LETTERS='ABCDEFGHIJKLMNOPQRSTUVWXYZ' +as_cr_Letters=$as_cr_letters$as_cr_LETTERS +as_cr_digits='0123456789' +as_cr_alnum=$as_cr_Letters$as_cr_digits + +# The user is always right. +if test "${PATH_SEPARATOR+set}" != set; then + echo "#! /bin/sh" >conf$$.sh + echo "exit 0" >>conf$$.sh + chmod +x conf$$.sh + if (PATH="/nonexistent;."; conf$$.sh) >/dev/null 2>&1; then + PATH_SEPARATOR=';' + else + PATH_SEPARATOR=: + fi + rm -f conf$$.sh +fi + + + as_lineno_1=$LINENO + as_lineno_2=$LINENO + as_lineno_3=`(expr $as_lineno_1 + 1) 2>/dev/null` + test "x$as_lineno_1" != "x$as_lineno_2" && + test "x$as_lineno_3" = "x$as_lineno_2" || { + # Find who we are. Look in the path if we contain no path at all + # relative or not. + case $0 in + *[\\/]* ) as_myself=$0 ;; + *) as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + test -r "$as_dir/$0" && as_myself=$as_dir/$0 && break +done + + ;; + esac + # We did not find ourselves, most probably we were run as `sh COMMAND' + # in which case we are not to be found in the path. + if test "x$as_myself" = x; then + as_myself=$0 + fi + if test ! -f "$as_myself"; then + { echo "$as_me: error: cannot find myself; rerun with an absolute path" >&2 + { (exit 1); exit 1; }; } + fi + case $CONFIG_SHELL in + '') + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in /bin$PATH_SEPARATOR/usr/bin$PATH_SEPARATOR$PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for as_base in sh bash ksh sh5; do + case $as_dir in + /*) + if ("$as_dir/$as_base" -c ' + as_lineno_1=$LINENO + as_lineno_2=$LINENO + as_lineno_3=`(expr $as_lineno_1 + 1) 2>/dev/null` + test "x$as_lineno_1" != "x$as_lineno_2" && + test "x$as_lineno_3" = "x$as_lineno_2" ') 2>/dev/null; then + $as_unset BASH_ENV || test "${BASH_ENV+set}" != set || { BASH_ENV=; export BASH_ENV; } + $as_unset ENV || test "${ENV+set}" != set || { ENV=; export ENV; } + CONFIG_SHELL=$as_dir/$as_base + export CONFIG_SHELL + exec "$CONFIG_SHELL" "$0" ${1+"$@"} + fi;; + esac + done +done +;; + esac + + # Create $as_me.lineno as a copy of $as_myself, but with $LINENO + # uniformly replaced by the line number. The first 'sed' inserts a + # line-number line before each line; the second 'sed' does the real + # work. The second script uses 'N' to pair each line-number line + # with the numbered line, and appends trailing '-' during + # substitution so that $LINENO is not a special case at line end. + # (Raja R Harinath suggested sed '=', and Paul Eggert wrote the + # second 'sed' script. Blame Lee E. McMahon for sed's syntax. :-) + sed '=' <$as_myself | + sed ' + N + s,$,-, + : loop + s,^\(['$as_cr_digits']*\)\(.*\)[$]LINENO\([^'$as_cr_alnum'_]\),\1\2\1\3, + t loop + s,-$,, + s,^['$as_cr_digits']*\n,, + ' >$as_me.lineno && + chmod +x $as_me.lineno || + { echo "$as_me: error: cannot create $as_me.lineno; rerun with a POSIX shell" >&2 + { (exit 1); exit 1; }; } + + # Don't try to exec as it changes $[0], causing all sort of problems + # (the dirname of $[0] is not the place where we might find the + # original and so on. Autoconf is especially sensible to this). + . ./$as_me.lineno + # Exit status is that of the last command. + exit +} + + +case `echo "testing\c"; echo 1,2,3`,`echo -n testing; echo 1,2,3` in + *c*,-n*) ECHO_N= ECHO_C=' +' ECHO_T=' ' ;; + *c*,* ) ECHO_N=-n ECHO_C= ECHO_T= ;; + *) ECHO_N= ECHO_C='\c' ECHO_T= ;; +esac + +if expr a : '\(a\)' >/dev/null 2>&1; then + as_expr=expr +else + as_expr=false +fi + +rm -f conf$$ conf$$.exe conf$$.file +echo >conf$$.file +if ln -s conf$$.file conf$$ 2>/dev/null; then + # We could just check for DJGPP; but this test a) works b) is more generic + # and c) will remain valid once DJGPP supports symlinks (DJGPP 2.04). + if test -f conf$$.exe; then + # Don't use ln at all; we don't have any links + as_ln_s='cp -p' + else + as_ln_s='ln -s' + fi +elif ln conf$$.file conf$$ 2>/dev/null; then + as_ln_s=ln +else + as_ln_s='cp -p' +fi +rm -f conf$$ conf$$.exe conf$$.file + +if mkdir -p . 2>/dev/null; then + as_mkdir_p=: +else + test -d ./-p && rmdir ./-p + as_mkdir_p=false +fi + +as_executable_p="test -f" + +# Sed expression to map a string onto a valid CPP name. +as_tr_cpp="eval sed 'y%*$as_cr_letters%P$as_cr_LETTERS%;s%[^_$as_cr_alnum]%_%g'" + +# Sed expression to map a string onto a valid variable name. +as_tr_sh="eval sed 'y%*+%pp%;s%[^_$as_cr_alnum]%_%g'" + + +# IFS +# We need space, tab and new line, in precisely that order. +as_nl=' +' +IFS=" $as_nl" + +# CDPATH. +$as_unset CDPATH + + + +# Check that we are running under the correct shell. +SHELL=${CONFIG_SHELL-/bin/sh} + +case X$ECHO in +X*--fallback-echo) + # Remove one level of quotation (which was required for Make). + ECHO=`echo "$ECHO" | sed 's,\\\\\$\\$0,'$0','` + ;; +esac + +echo=${ECHO-echo} +if test "X$1" = X--no-reexec; then + # Discard the --no-reexec flag, and continue. + shift +elif test "X$1" = X--fallback-echo; then + # Avoid inline document here, it may be left over + : +elif test "X`($echo '\t') 2>/dev/null`" = 'X\t' ; then + # Yippee, $echo works! + : +else + # Restart under the correct shell. + exec $SHELL "$0" --no-reexec ${1+"$@"} +fi + +if test "X$1" = X--fallback-echo; then + # used as fallback echo + shift + cat </dev/null 2>&1 && unset CDPATH + +if test -z "$ECHO"; then +if test "X${echo_test_string+set}" != Xset; then +# find a string as large as possible, as long as the shell can cope with it + for cmd in 'sed 50q "$0"' 'sed 20q "$0"' 'sed 10q "$0"' 'sed 2q "$0"' 'echo test'; do + # expected sizes: less than 2Kb, 1Kb, 512 bytes, 16 bytes, ... + if (echo_test_string=`eval $cmd`) 2>/dev/null && + echo_test_string=`eval $cmd` && + (test "X$echo_test_string" = "X$echo_test_string") 2>/dev/null + then + break + fi + done +fi + +if test "X`($echo '\t') 2>/dev/null`" = 'X\t' && + echo_testing_string=`($echo "$echo_test_string") 2>/dev/null` && + test "X$echo_testing_string" = "X$echo_test_string"; then + : +else + # The Solaris, AIX, and Digital Unix default echo programs unquote + # backslashes. This makes it impossible to quote backslashes using + # echo "$something" | sed 's/\\/\\\\/g' + # + # So, first we look for a working echo in the user's PATH. + + lt_save_ifs="$IFS"; IFS=$PATH_SEPARATOR + for dir in $PATH /usr/ucb; do + IFS="$lt_save_ifs" + if (test -f $dir/echo || test -f $dir/echo$ac_exeext) && + test "X`($dir/echo '\t') 2>/dev/null`" = 'X\t' && + echo_testing_string=`($dir/echo "$echo_test_string") 2>/dev/null` && + test "X$echo_testing_string" = "X$echo_test_string"; then + echo="$dir/echo" + break + fi + done + IFS="$lt_save_ifs" + + if test "X$echo" = Xecho; then + # We didn't find a better echo, so look for alternatives. + if test "X`(print -r '\t') 2>/dev/null`" = 'X\t' && + echo_testing_string=`(print -r "$echo_test_string") 2>/dev/null` && + test "X$echo_testing_string" = "X$echo_test_string"; then + # This shell has a builtin print -r that does the trick. + echo='print -r' + elif (test -f /bin/ksh || test -f /bin/ksh$ac_exeext) && + test "X$CONFIG_SHELL" != X/bin/ksh; then + # If we have ksh, try running configure again with it. + ORIGINAL_CONFIG_SHELL=${CONFIG_SHELL-/bin/sh} + export ORIGINAL_CONFIG_SHELL + CONFIG_SHELL=/bin/ksh + export CONFIG_SHELL + exec $CONFIG_SHELL "$0" --no-reexec ${1+"$@"} + else + # Try using printf. + echo='printf %s\n' + if test "X`($echo '\t') 2>/dev/null`" = 'X\t' && + echo_testing_string=`($echo "$echo_test_string") 2>/dev/null` && + test "X$echo_testing_string" = "X$echo_test_string"; then + # Cool, printf works + : + elif echo_testing_string=`($ORIGINAL_CONFIG_SHELL "$0" --fallback-echo '\t') 2>/dev/null` && + test "X$echo_testing_string" = 'X\t' && + echo_testing_string=`($ORIGINAL_CONFIG_SHELL "$0" --fallback-echo "$echo_test_string") 2>/dev/null` && + test "X$echo_testing_string" = "X$echo_test_string"; then + CONFIG_SHELL=$ORIGINAL_CONFIG_SHELL + export CONFIG_SHELL + SHELL="$CONFIG_SHELL" + export SHELL + echo="$CONFIG_SHELL $0 --fallback-echo" + elif echo_testing_string=`($CONFIG_SHELL "$0" --fallback-echo '\t') 2>/dev/null` && + test "X$echo_testing_string" = 'X\t' && + echo_testing_string=`($CONFIG_SHELL "$0" --fallback-echo "$echo_test_string") 2>/dev/null` && + test "X$echo_testing_string" = "X$echo_test_string"; then + echo="$CONFIG_SHELL $0 --fallback-echo" + else + # maybe with a smaller string... + prev=: + + for cmd in 'echo test' 'sed 2q "$0"' 'sed 10q "$0"' 'sed 20q "$0"' 'sed 50q "$0"'; do + if (test "X$echo_test_string" = "X`eval $cmd`") 2>/dev/null + then + break + fi + prev="$cmd" + done + + if test "$prev" != 'sed 50q "$0"'; then + echo_test_string=`eval $prev` + export echo_test_string + exec ${ORIGINAL_CONFIG_SHELL-${CONFIG_SHELL-/bin/sh}} "$0" ${1+"$@"} + else + # Oops. We lost completely, so just stick with echo. + echo=echo + fi + fi + fi + fi +fi +fi + +# Copy echo and quote the copy suitably for passing to libtool from +# the Makefile, instead of quoting the original, which is used later. +ECHO=$echo +if test "X$ECHO" = "X$CONFIG_SHELL $0 --fallback-echo"; then + ECHO="$CONFIG_SHELL \\\$\$0 --fallback-echo" +fi + + + + +tagnames=${tagnames+${tagnames},}CXX + +tagnames=${tagnames+${tagnames},}F77 + +# Name of the host. +# hostname on some systems (SVR3.2, Linux) returns a bogus exit status, +# so uname gets run too. +ac_hostname=`(hostname || uname -n) 2>/dev/null | sed 1q` + +exec 6>&1 + +# +# Initializations. +# +ac_default_prefix=/usr/local +ac_config_libobj_dir=. +cross_compiling=no +subdirs= +MFLAGS= +MAKEFLAGS= +SHELL=${CONFIG_SHELL-/bin/sh} + +# Maximum number of lines to put in a shell here document. +# This variable seems obsolete. It should probably be removed, and +# only ac_max_sed_lines should be used. +: ${ac_max_here_lines=38} + +# Identity of this package. +PACKAGE_NAME= +PACKAGE_TARNAME= +PACKAGE_VERSION= +PACKAGE_STRING= +PACKAGE_BUGREPORT= + +ac_unique_file="dftables.c" +ac_unique_file="pcre.h" +# Factoring default headers for most tests. +ac_includes_default="\ +#include +#if HAVE_SYS_TYPES_H +# include +#endif +#if HAVE_SYS_STAT_H +# include +#endif +#if STDC_HEADERS +# include +# include +#else +# if HAVE_STDLIB_H +# include +# endif +#endif +#if HAVE_STRING_H +# if !STDC_HEADERS && HAVE_MEMORY_H +# include +# endif +# include +#endif +#if HAVE_STRINGS_H +# include +#endif +#if HAVE_INTTYPES_H +# include +#else +# if HAVE_STDINT_H +# include +# endif +#endif +#if HAVE_UNISTD_H +# include +#endif" + +ac_subst_vars='SHELL PATH_SEPARATOR PACKAGE_NAME PACKAGE_TARNAME PACKAGE_VERSION PACKAGE_STRING PACKAGE_BUGREPORT exec_prefix prefix program_transform_name bindir sbindir libexecdir datadir sysconfdir sharedstatedir localstatedir libdir includedir oldincludedir infodir mandir build_alias host_alias target_alias DEFS ECHO_C ECHO_N ECHO_T LIBS CC CFLAGS LDFLAGS CPPFLAGS ac_ct_CC EXEEXT OBJEXT CXX CXXFLAGS ac_ct_CXX INSTALL_PROGRAM INSTALL_SCRIPT INSTALL_DATA build build_cpu build_vendor build_os host host_cpu host_vendor host_os EGREP LN_S ECHO AR ac_ct_AR RANLIB ac_ct_RANLIB STRIP ac_ct_STRIP DLLTOOL ac_ct_DLLTOOL AS ac_ct_AS OBJDUMP ac_ct_OBJDUMP CPP CXXCPP F77 FFLAGS ac_ct_F77 LIBTOOL pcre_have_bits_type_traits pcre_have_type_traits MAYBE_CPP_TARGETS HAVE_CPP pcre_have_long_long pcre_have_ulong_long BUILD_EXEEXT BUILD_OBJEXT CC_FOR_BUILD CXX_FOR_BUILD CFLAGS_FOR_BUILD CXXFLAGS_FOR_BUILD CXXLDFLAGS EBCDIC HAVE_MEMMOVE HAVE_STRERROR LINK_SIZE MATCH_LIMIT MATCH_LIMIT_RECURSION NEWLINE NO_RECURSE PCRE_LIB_VERSION PCRE_POSIXLIB_VERSION PCRE_CPPLIB_VERSION PCRE_VERSION POSIX_MALLOC_THRESHOLD UCP UTF8 WIN_PREFIX ON_WINDOWS NOT_ON_WINDOWS POSIX_OBJ POSIX_LOBJ POSIX_LIB LIBOBJS LTLIBOBJS' +ac_subst_files='' + +# Initialize some variables set by options. +ac_init_help= +ac_init_version=false +# The variables have the same names as the options, with +# dashes changed to underlines. +cache_file=/dev/null +exec_prefix=NONE +no_create= +no_recursion= +prefix=NONE +program_prefix=NONE +program_suffix=NONE +program_transform_name=s,x,x, +silent= +site= +srcdir= +verbose= +x_includes=NONE +x_libraries=NONE + +# Installation directory options. +# These are left unexpanded so users can "make install exec_prefix=/foo" +# and all the variables that are supposed to be based on exec_prefix +# by default will actually change. +# Use braces instead of parens because sh, perl, etc. also accept them. +bindir='${exec_prefix}/bin' +sbindir='${exec_prefix}/sbin' +libexecdir='${exec_prefix}/libexec' +datadir='${prefix}/share' +sysconfdir='${prefix}/etc' +sharedstatedir='${prefix}/com' +localstatedir='${prefix}/var' +libdir='${exec_prefix}/lib' +includedir='${prefix}/include' +oldincludedir='/usr/include' +infodir='${prefix}/info' +mandir='${prefix}/man' + +ac_prev= +for ac_option +do + # If the previous option needs an argument, assign it. + if test -n "$ac_prev"; then + eval "$ac_prev=\$ac_option" + ac_prev= + continue + fi + + ac_optarg=`expr "x$ac_option" : 'x[^=]*=\(.*\)'` + + # Accept the important Cygnus configure options, so we can diagnose typos. + + case $ac_option in + + -bindir | --bindir | --bindi | --bind | --bin | --bi) + ac_prev=bindir ;; + -bindir=* | --bindir=* | --bindi=* | --bind=* | --bin=* | --bi=*) + bindir=$ac_optarg ;; + + -build | --build | --buil | --bui | --bu) + ac_prev=build_alias ;; + -build=* | --build=* | --buil=* | --bui=* | --bu=*) + build_alias=$ac_optarg ;; + + -cache-file | --cache-file | --cache-fil | --cache-fi \ + | --cache-f | --cache- | --cache | --cach | --cac | --ca | --c) + ac_prev=cache_file ;; + -cache-file=* | --cache-file=* | --cache-fil=* | --cache-fi=* \ + | --cache-f=* | --cache-=* | --cache=* | --cach=* | --cac=* | --ca=* | --c=*) + cache_file=$ac_optarg ;; + + --config-cache | -C) + cache_file=config.cache ;; + + -datadir | --datadir | --datadi | --datad | --data | --dat | --da) + ac_prev=datadir ;; + -datadir=* | --datadir=* | --datadi=* | --datad=* | --data=* | --dat=* \ + | --da=*) + datadir=$ac_optarg ;; + + -disable-* | --disable-*) + ac_feature=`expr "x$ac_option" : 'x-*disable-\(.*\)'` + # Reject names that are not valid shell variable names. + expr "x$ac_feature" : ".*[^-_$as_cr_alnum]" >/dev/null && + { echo "$as_me: error: invalid feature name: $ac_feature" >&2 + { (exit 1); exit 1; }; } + ac_feature=`echo $ac_feature | sed 's/-/_/g'` + eval "enable_$ac_feature=no" ;; + + -enable-* | --enable-*) + ac_feature=`expr "x$ac_option" : 'x-*enable-\([^=]*\)'` + # Reject names that are not valid shell variable names. + expr "x$ac_feature" : ".*[^-_$as_cr_alnum]" >/dev/null && + { echo "$as_me: error: invalid feature name: $ac_feature" >&2 + { (exit 1); exit 1; }; } + ac_feature=`echo $ac_feature | sed 's/-/_/g'` + case $ac_option in + *=*) ac_optarg=`echo "$ac_optarg" | sed "s/'/'\\\\\\\\''/g"`;; + *) ac_optarg=yes ;; + esac + eval "enable_$ac_feature='$ac_optarg'" ;; + + -exec-prefix | --exec_prefix | --exec-prefix | --exec-prefi \ + | --exec-pref | --exec-pre | --exec-pr | --exec-p | --exec- \ + | --exec | --exe | --ex) + ac_prev=exec_prefix ;; + -exec-prefix=* | --exec_prefix=* | --exec-prefix=* | --exec-prefi=* \ + | --exec-pref=* | --exec-pre=* | --exec-pr=* | --exec-p=* | --exec-=* \ + | --exec=* | --exe=* | --ex=*) + exec_prefix=$ac_optarg ;; + + -gas | --gas | --ga | --g) + # Obsolete; use --with-gas. + with_gas=yes ;; + + -help | --help | --hel | --he | -h) + ac_init_help=long ;; + -help=r* | --help=r* | --hel=r* | --he=r* | -hr*) + ac_init_help=recursive ;; + -help=s* | --help=s* | --hel=s* | --he=s* | -hs*) + ac_init_help=short ;; + + -host | --host | --hos | --ho) + ac_prev=host_alias ;; + -host=* | --host=* | --hos=* | --ho=*) + host_alias=$ac_optarg ;; + + -includedir | --includedir | --includedi | --included | --include \ + | --includ | --inclu | --incl | --inc) + ac_prev=includedir ;; + -includedir=* | --includedir=* | --includedi=* | --included=* | --include=* \ + | --includ=* | --inclu=* | --incl=* | --inc=*) + includedir=$ac_optarg ;; + + -infodir | --infodir | --infodi | --infod | --info | --inf) + ac_prev=infodir ;; + -infodir=* | --infodir=* | --infodi=* | --infod=* | --info=* | --inf=*) + infodir=$ac_optarg ;; + + -libdir | --libdir | --libdi | --libd) + ac_prev=libdir ;; + -libdir=* | --libdir=* | --libdi=* | --libd=*) + libdir=$ac_optarg ;; + + -libexecdir | --libexecdir | --libexecdi | --libexecd | --libexec \ + | --libexe | --libex | --libe) + ac_prev=libexecdir ;; + -libexecdir=* | --libexecdir=* | --libexecdi=* | --libexecd=* | --libexec=* \ + | --libexe=* | --libex=* | --libe=*) + libexecdir=$ac_optarg ;; + + -localstatedir | --localstatedir | --localstatedi | --localstated \ + | --localstate | --localstat | --localsta | --localst \ + | --locals | --local | --loca | --loc | --lo) + ac_prev=localstatedir ;; + -localstatedir=* | --localstatedir=* | --localstatedi=* | --localstated=* \ + | --localstate=* | --localstat=* | --localsta=* | --localst=* \ + | --locals=* | --local=* | --loca=* | --loc=* | --lo=*) + localstatedir=$ac_optarg ;; + + -mandir | --mandir | --mandi | --mand | --man | --ma | --m) + ac_prev=mandir ;; + -mandir=* | --mandir=* | --mandi=* | --mand=* | --man=* | --ma=* | --m=*) + mandir=$ac_optarg ;; + + -nfp | --nfp | --nf) + # Obsolete; use --without-fp. + with_fp=no ;; + + -no-create | --no-create | --no-creat | --no-crea | --no-cre \ + | --no-cr | --no-c | -n) + no_create=yes ;; + + -no-recursion | --no-recursion | --no-recursio | --no-recursi \ + | --no-recurs | --no-recur | --no-recu | --no-rec | --no-re | --no-r) + no_recursion=yes ;; + + -oldincludedir | --oldincludedir | --oldincludedi | --oldincluded \ + | --oldinclude | --oldinclud | --oldinclu | --oldincl | --oldinc \ + | --oldin | --oldi | --old | --ol | --o) + ac_prev=oldincludedir ;; + -oldincludedir=* | --oldincludedir=* | --oldincludedi=* | --oldincluded=* \ + | --oldinclude=* | --oldinclud=* | --oldinclu=* | --oldincl=* | --oldinc=* \ + | --oldin=* | --oldi=* | --old=* | --ol=* | --o=*) + oldincludedir=$ac_optarg ;; + + -prefix | --prefix | --prefi | --pref | --pre | --pr | --p) + ac_prev=prefix ;; + -prefix=* | --prefix=* | --prefi=* | --pref=* | --pre=* | --pr=* | --p=*) + prefix=$ac_optarg ;; + + -program-prefix | --program-prefix | --program-prefi | --program-pref \ + | --program-pre | --program-pr | --program-p) + ac_prev=program_prefix ;; + -program-prefix=* | --program-prefix=* | --program-prefi=* \ + | --program-pref=* | --program-pre=* | --program-pr=* | --program-p=*) + program_prefix=$ac_optarg ;; + + -program-suffix | --program-suffix | --program-suffi | --program-suff \ + | --program-suf | --program-su | --program-s) + ac_prev=program_suffix ;; + -program-suffix=* | --program-suffix=* | --program-suffi=* \ + | --program-suff=* | --program-suf=* | --program-su=* | --program-s=*) + program_suffix=$ac_optarg ;; + + -program-transform-name | --program-transform-name \ + | --program-transform-nam | --program-transform-na \ + | --program-transform-n | --program-transform- \ + | --program-transform | --program-transfor \ + | --program-transfo | --program-transf \ + | --program-trans | --program-tran \ + | --progr-tra | --program-tr | --program-t) + ac_prev=program_transform_name ;; + -program-transform-name=* | --program-transform-name=* \ + | --program-transform-nam=* | --program-transform-na=* \ + | --program-transform-n=* | --program-transform-=* \ + | --program-transform=* | --program-transfor=* \ + | --program-transfo=* | --program-transf=* \ + | --program-trans=* | --program-tran=* \ + | --progr-tra=* | --program-tr=* | --program-t=*) + program_transform_name=$ac_optarg ;; + + -q | -quiet | --quiet | --quie | --qui | --qu | --q \ + | -silent | --silent | --silen | --sile | --sil) + silent=yes ;; + + -sbindir | --sbindir | --sbindi | --sbind | --sbin | --sbi | --sb) + ac_prev=sbindir ;; + -sbindir=* | --sbindir=* | --sbindi=* | --sbind=* | --sbin=* \ + | --sbi=* | --sb=*) + sbindir=$ac_optarg ;; + + -sharedstatedir | --sharedstatedir | --sharedstatedi \ + | --sharedstated | --sharedstate | --sharedstat | --sharedsta \ + | --sharedst | --shareds | --shared | --share | --shar \ + | --sha | --sh) + ac_prev=sharedstatedir ;; + -sharedstatedir=* | --sharedstatedir=* | --sharedstatedi=* \ + | --sharedstated=* | --sharedstate=* | --sharedstat=* | --sharedsta=* \ + | --sharedst=* | --shareds=* | --shared=* | --share=* | --shar=* \ + | --sha=* | --sh=*) + sharedstatedir=$ac_optarg ;; + + -site | --site | --sit) + ac_prev=site ;; + -site=* | --site=* | --sit=*) + site=$ac_optarg ;; + + -srcdir | --srcdir | --srcdi | --srcd | --src | --sr) + ac_prev=srcdir ;; + -srcdir=* | --srcdir=* | --srcdi=* | --srcd=* | --src=* | --sr=*) + srcdir=$ac_optarg ;; + + -sysconfdir | --sysconfdir | --sysconfdi | --sysconfd | --sysconf \ + | --syscon | --sysco | --sysc | --sys | --sy) + ac_prev=sysconfdir ;; + -sysconfdir=* | --sysconfdir=* | --sysconfdi=* | --sysconfd=* | --sysconf=* \ + | --syscon=* | --sysco=* | --sysc=* | --sys=* | --sy=*) + sysconfdir=$ac_optarg ;; + + -target | --target | --targe | --targ | --tar | --ta | --t) + ac_prev=target_alias ;; + -target=* | --target=* | --targe=* | --targ=* | --tar=* | --ta=* | --t=*) + target_alias=$ac_optarg ;; + + -v | -verbose | --verbose | --verbos | --verbo | --verb) + verbose=yes ;; + + -version | --version | --versio | --versi | --vers | -V) + ac_init_version=: ;; + + -with-* | --with-*) + ac_package=`expr "x$ac_option" : 'x-*with-\([^=]*\)'` + # Reject names that are not valid shell variable names. + expr "x$ac_package" : ".*[^-_$as_cr_alnum]" >/dev/null && + { echo "$as_me: error: invalid package name: $ac_package" >&2 + { (exit 1); exit 1; }; } + ac_package=`echo $ac_package| sed 's/-/_/g'` + case $ac_option in + *=*) ac_optarg=`echo "$ac_optarg" | sed "s/'/'\\\\\\\\''/g"`;; + *) ac_optarg=yes ;; + esac + eval "with_$ac_package='$ac_optarg'" ;; + + -without-* | --without-*) + ac_package=`expr "x$ac_option" : 'x-*without-\(.*\)'` + # Reject names that are not valid shell variable names. + expr "x$ac_package" : ".*[^-_$as_cr_alnum]" >/dev/null && + { echo "$as_me: error: invalid package name: $ac_package" >&2 + { (exit 1); exit 1; }; } + ac_package=`echo $ac_package | sed 's/-/_/g'` + eval "with_$ac_package=no" ;; + + --x) + # Obsolete; use --with-x. + with_x=yes ;; + + -x-includes | --x-includes | --x-include | --x-includ | --x-inclu \ + | --x-incl | --x-inc | --x-in | --x-i) + ac_prev=x_includes ;; + -x-includes=* | --x-includes=* | --x-include=* | --x-includ=* | --x-inclu=* \ + | --x-incl=* | --x-inc=* | --x-in=* | --x-i=*) + x_includes=$ac_optarg ;; + + -x-libraries | --x-libraries | --x-librarie | --x-librari \ + | --x-librar | --x-libra | --x-libr | --x-lib | --x-li | --x-l) + ac_prev=x_libraries ;; + -x-libraries=* | --x-libraries=* | --x-librarie=* | --x-librari=* \ + | --x-librar=* | --x-libra=* | --x-libr=* | --x-lib=* | --x-li=* | --x-l=*) + x_libraries=$ac_optarg ;; + + -*) { echo "$as_me: error: unrecognized option: $ac_option +Try \`$0 --help' for more information." >&2 + { (exit 1); exit 1; }; } + ;; + + *=*) + ac_envvar=`expr "x$ac_option" : 'x\([^=]*\)='` + # Reject names that are not valid shell variable names. + expr "x$ac_envvar" : ".*[^_$as_cr_alnum]" >/dev/null && + { echo "$as_me: error: invalid variable name: $ac_envvar" >&2 + { (exit 1); exit 1; }; } + ac_optarg=`echo "$ac_optarg" | sed "s/'/'\\\\\\\\''/g"` + eval "$ac_envvar='$ac_optarg'" + export $ac_envvar ;; + + *) + # FIXME: should be removed in autoconf 3.0. + echo "$as_me: WARNING: you should use --build, --host, --target" >&2 + expr "x$ac_option" : ".*[^-._$as_cr_alnum]" >/dev/null && + echo "$as_me: WARNING: invalid host type: $ac_option" >&2 + : ${build_alias=$ac_option} ${host_alias=$ac_option} ${target_alias=$ac_option} + ;; + + esac +done + +if test -n "$ac_prev"; then + ac_option=--`echo $ac_prev | sed 's/_/-/g'` + { echo "$as_me: error: missing argument to $ac_option" >&2 + { (exit 1); exit 1; }; } +fi + +# Be sure to have absolute paths. +for ac_var in exec_prefix prefix +do + eval ac_val=$`echo $ac_var` + case $ac_val in + [\\/$]* | ?:[\\/]* | NONE | '' ) ;; + *) { echo "$as_me: error: expected an absolute directory name for --$ac_var: $ac_val" >&2 + { (exit 1); exit 1; }; };; + esac +done + +# Be sure to have absolute paths. +for ac_var in bindir sbindir libexecdir datadir sysconfdir sharedstatedir \ + localstatedir libdir includedir oldincludedir infodir mandir +do + eval ac_val=$`echo $ac_var` + case $ac_val in + [\\/$]* | ?:[\\/]* ) ;; + *) { echo "$as_me: error: expected an absolute directory name for --$ac_var: $ac_val" >&2 + { (exit 1); exit 1; }; };; + esac +done + +# There might be people who depend on the old broken behavior: `$host' +# used to hold the argument of --host etc. +# FIXME: To remove some day. +build=$build_alias +host=$host_alias +target=$target_alias + +# FIXME: To remove some day. +if test "x$host_alias" != x; then + if test "x$build_alias" = x; then + cross_compiling=maybe + echo "$as_me: WARNING: If you wanted to set the --build type, don't use --host. + If a cross compiler is detected then cross compile mode will be used." >&2 + elif test "x$build_alias" != "x$host_alias"; then + cross_compiling=yes + fi +fi + +ac_tool_prefix= +test -n "$host_alias" && ac_tool_prefix=$host_alias- + +test "$silent" = yes && exec 6>/dev/null + + +# Find the source files, if location was not specified. +if test -z "$srcdir"; then + ac_srcdir_defaulted=yes + # Try the directory containing this script, then its parent. + ac_confdir=`(dirname "$0") 2>/dev/null || +$as_expr X"$0" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ + X"$0" : 'X\(//\)[^/]' \| \ + X"$0" : 'X\(//\)$' \| \ + X"$0" : 'X\(/\)' \| \ + . : '\(.\)' 2>/dev/null || +echo X"$0" | + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ s//\1/; q; } + /^X\(\/\/\)[^/].*/{ s//\1/; q; } + /^X\(\/\/\)$/{ s//\1/; q; } + /^X\(\/\).*/{ s//\1/; q; } + s/.*/./; q'` + srcdir=$ac_confdir + if test ! -r "$srcdir/$ac_unique_file"; then + srcdir=.. + fi +else + ac_srcdir_defaulted=no +fi +if test ! -r "$srcdir/$ac_unique_file"; then + if test "$ac_srcdir_defaulted" = yes; then + { echo "$as_me: error: cannot find sources ($ac_unique_file) in $ac_confdir or .." >&2 + { (exit 1); exit 1; }; } + else + { echo "$as_me: error: cannot find sources ($ac_unique_file) in $srcdir" >&2 + { (exit 1); exit 1; }; } + fi +fi +(cd $srcdir && test -r "./$ac_unique_file") 2>/dev/null || + { echo "$as_me: error: sources are in $srcdir, but \`cd $srcdir' does not work" >&2 + { (exit 1); exit 1; }; } +srcdir=`echo "$srcdir" | sed 's%\([^\\/]\)[\\/]*$%\1%'` +ac_env_build_alias_set=${build_alias+set} +ac_env_build_alias_value=$build_alias +ac_cv_env_build_alias_set=${build_alias+set} +ac_cv_env_build_alias_value=$build_alias +ac_env_host_alias_set=${host_alias+set} +ac_env_host_alias_value=$host_alias +ac_cv_env_host_alias_set=${host_alias+set} +ac_cv_env_host_alias_value=$host_alias +ac_env_target_alias_set=${target_alias+set} +ac_env_target_alias_value=$target_alias +ac_cv_env_target_alias_set=${target_alias+set} +ac_cv_env_target_alias_value=$target_alias +ac_env_CC_set=${CC+set} +ac_env_CC_value=$CC +ac_cv_env_CC_set=${CC+set} +ac_cv_env_CC_value=$CC +ac_env_CFLAGS_set=${CFLAGS+set} +ac_env_CFLAGS_value=$CFLAGS +ac_cv_env_CFLAGS_set=${CFLAGS+set} +ac_cv_env_CFLAGS_value=$CFLAGS +ac_env_LDFLAGS_set=${LDFLAGS+set} +ac_env_LDFLAGS_value=$LDFLAGS +ac_cv_env_LDFLAGS_set=${LDFLAGS+set} +ac_cv_env_LDFLAGS_value=$LDFLAGS +ac_env_CPPFLAGS_set=${CPPFLAGS+set} +ac_env_CPPFLAGS_value=$CPPFLAGS +ac_cv_env_CPPFLAGS_set=${CPPFLAGS+set} +ac_cv_env_CPPFLAGS_value=$CPPFLAGS +ac_env_CXX_set=${CXX+set} +ac_env_CXX_value=$CXX +ac_cv_env_CXX_set=${CXX+set} +ac_cv_env_CXX_value=$CXX +ac_env_CXXFLAGS_set=${CXXFLAGS+set} +ac_env_CXXFLAGS_value=$CXXFLAGS +ac_cv_env_CXXFLAGS_set=${CXXFLAGS+set} +ac_cv_env_CXXFLAGS_value=$CXXFLAGS +ac_env_CPP_set=${CPP+set} +ac_env_CPP_value=$CPP +ac_cv_env_CPP_set=${CPP+set} +ac_cv_env_CPP_value=$CPP +ac_env_CXXCPP_set=${CXXCPP+set} +ac_env_CXXCPP_value=$CXXCPP +ac_cv_env_CXXCPP_set=${CXXCPP+set} +ac_cv_env_CXXCPP_value=$CXXCPP +ac_env_F77_set=${F77+set} +ac_env_F77_value=$F77 +ac_cv_env_F77_set=${F77+set} +ac_cv_env_F77_value=$F77 +ac_env_FFLAGS_set=${FFLAGS+set} +ac_env_FFLAGS_value=$FFLAGS +ac_cv_env_FFLAGS_set=${FFLAGS+set} +ac_cv_env_FFLAGS_value=$FFLAGS + +# +# Report the --help message. +# +if test "$ac_init_help" = "long"; then + # Omit some internal or obsolete options to make the list less imposing. + # This message is too long to be a string in the A/UX 3.1 sh. + cat <<_ACEOF +\`configure' configures this package to adapt to many kinds of systems. + +Usage: $0 [OPTION]... [VAR=VALUE]... + +To assign environment variables (e.g., CC, CFLAGS...), specify them as +VAR=VALUE. See below for descriptions of some of the useful variables. + +Defaults for the options are specified in brackets. + +Configuration: + -h, --help display this help and exit + --help=short display options specific to this package + --help=recursive display the short help of all the included packages + -V, --version display version information and exit + -q, --quiet, --silent do not print \`checking...' messages + --cache-file=FILE cache test results in FILE [disabled] + -C, --config-cache alias for \`--cache-file=config.cache' + -n, --no-create do not create output files + --srcdir=DIR find the sources in DIR [configure dir or \`..'] + +_ACEOF + + cat <<_ACEOF +Installation directories: + --prefix=PREFIX install architecture-independent files in PREFIX + [$ac_default_prefix] + --exec-prefix=EPREFIX install architecture-dependent files in EPREFIX + [PREFIX] + +By default, \`make install' will install all the files in +\`$ac_default_prefix/bin', \`$ac_default_prefix/lib' etc. You can specify +an installation prefix other than \`$ac_default_prefix' using \`--prefix', +for instance \`--prefix=\$HOME'. + +For better control, use the options below. + +Fine tuning of the installation directories: + --bindir=DIR user executables [EPREFIX/bin] + --sbindir=DIR system admin executables [EPREFIX/sbin] + --libexecdir=DIR program executables [EPREFIX/libexec] + --datadir=DIR read-only architecture-independent data [PREFIX/share] + --sysconfdir=DIR read-only single-machine data [PREFIX/etc] + --sharedstatedir=DIR modifiable architecture-independent data [PREFIX/com] + --localstatedir=DIR modifiable single-machine data [PREFIX/var] + --libdir=DIR object code libraries [EPREFIX/lib] + --includedir=DIR C header files [PREFIX/include] + --oldincludedir=DIR C header files for non-gcc [/usr/include] + --infodir=DIR info documentation [PREFIX/info] + --mandir=DIR man documentation [PREFIX/man] +_ACEOF + + cat <<\_ACEOF + +System types: + --build=BUILD configure for building on BUILD [guessed] + --host=HOST cross-compile to build programs to run on HOST [BUILD] +_ACEOF +fi + +if test -n "$ac_init_help"; then + + cat <<\_ACEOF + +Optional Features: + --disable-FEATURE do not include FEATURE (same as --enable-FEATURE=no) + --enable-FEATURE[=ARG] include FEATURE [ARG=yes] + --disable-cpp disable C++ support + --enable-shared[=PKGS] + build shared libraries [default=yes] + --enable-static[=PKGS] + build static libraries [default=yes] + --enable-fast-install[=PKGS] + optimize for fast installation [default=yes] + --disable-libtool-lock avoid locking (might break parallel builds) + --enable-utf8 enable UTF8 support + --enable-unicode-properties enable Unicode properties support + --enable-newline-is-cr use CR as the newline character + --enable-newline-is-lf use LF as the newline character + --enable-newline-is-crlf use CRLF as the newline sequence + --enable-ebcdic assume EBCDIC coding rather than ASCII + --disable-stack-for-recursion disable use of stack recursion when matching + +Optional Packages: + --with-PACKAGE[=ARG] use PACKAGE [ARG=yes] + --without-PACKAGE do not use PACKAGE (same as --with-PACKAGE=no) + --with-gnu-ld assume the C compiler uses GNU ld [default=no] + --with-pic try to use only PIC/non-PIC objects [default=use + both] + --with-tags[=TAGS] + include additional configurations [automatic] + --with-posix-malloc-threshold=10 threshold for POSIX malloc usage + --with-link-size=2 internal link size (2, 3, or 4 allowed) + --with-match-limit=10000000 default limit on internal looping + --with-match-limit-recursion=10000000 default limit on internal recursion + +Some influential environment variables: + CC C compiler command + CFLAGS C compiler flags + LDFLAGS linker flags, e.g. -L if you have libraries in a + nonstandard directory + CPPFLAGS C/C++ preprocessor flags, e.g. -I if you have + headers in a nonstandard directory + CXX C++ compiler command + CXXFLAGS C++ compiler flags + CPP C preprocessor + CXXCPP C++ preprocessor + F77 Fortran 77 compiler command + FFLAGS Fortran 77 compiler flags + +Use these variables to override the choices made by `configure' or to help +it to find libraries and programs with nonstandard names/locations. + +_ACEOF +fi + +if test "$ac_init_help" = "recursive"; then + # If there are subdirs, report their specific --help. + ac_popdir=`pwd` + for ac_dir in : $ac_subdirs_all; do test "x$ac_dir" = x: && continue + test -d $ac_dir || continue + ac_builddir=. + +if test "$ac_dir" != .; then + ac_dir_suffix=/`echo "$ac_dir" | sed 's,^\.[\\/],,'` + # A "../" for each directory in $ac_dir_suffix. + ac_top_builddir=`echo "$ac_dir_suffix" | sed 's,/[^\\/]*,../,g'` +else + ac_dir_suffix= ac_top_builddir= +fi + +case $srcdir in + .) # No --srcdir option. We are building in place. + ac_srcdir=. + if test -z "$ac_top_builddir"; then + ac_top_srcdir=. + else + ac_top_srcdir=`echo $ac_top_builddir | sed 's,/$,,'` + fi ;; + [\\/]* | ?:[\\/]* ) # Absolute path. + ac_srcdir=$srcdir$ac_dir_suffix; + ac_top_srcdir=$srcdir ;; + *) # Relative path. + ac_srcdir=$ac_top_builddir$srcdir$ac_dir_suffix + ac_top_srcdir=$ac_top_builddir$srcdir ;; +esac + +# Do not use `cd foo && pwd` to compute absolute paths, because +# the directories may not exist. +case `pwd` in +.) ac_abs_builddir="$ac_dir";; +*) + case "$ac_dir" in + .) ac_abs_builddir=`pwd`;; + [\\/]* | ?:[\\/]* ) ac_abs_builddir="$ac_dir";; + *) ac_abs_builddir=`pwd`/"$ac_dir";; + esac;; +esac +case $ac_abs_builddir in +.) ac_abs_top_builddir=${ac_top_builddir}.;; +*) + case ${ac_top_builddir}. in + .) ac_abs_top_builddir=$ac_abs_builddir;; + [\\/]* | ?:[\\/]* ) ac_abs_top_builddir=${ac_top_builddir}.;; + *) ac_abs_top_builddir=$ac_abs_builddir/${ac_top_builddir}.;; + esac;; +esac +case $ac_abs_builddir in +.) ac_abs_srcdir=$ac_srcdir;; +*) + case $ac_srcdir in + .) ac_abs_srcdir=$ac_abs_builddir;; + [\\/]* | ?:[\\/]* ) ac_abs_srcdir=$ac_srcdir;; + *) ac_abs_srcdir=$ac_abs_builddir/$ac_srcdir;; + esac;; +esac +case $ac_abs_builddir in +.) ac_abs_top_srcdir=$ac_top_srcdir;; +*) + case $ac_top_srcdir in + .) ac_abs_top_srcdir=$ac_abs_builddir;; + [\\/]* | ?:[\\/]* ) ac_abs_top_srcdir=$ac_top_srcdir;; + *) ac_abs_top_srcdir=$ac_abs_builddir/$ac_top_srcdir;; + esac;; +esac + + cd $ac_dir + # Check for guested configure; otherwise get Cygnus style configure. + if test -f $ac_srcdir/configure.gnu; then + echo + $SHELL $ac_srcdir/configure.gnu --help=recursive + elif test -f $ac_srcdir/configure; then + echo + $SHELL $ac_srcdir/configure --help=recursive + elif test -f $ac_srcdir/configure.ac || + test -f $ac_srcdir/configure.in; then + echo + $ac_configure --help + else + echo "$as_me: WARNING: no configuration information is in $ac_dir" >&2 + fi + cd $ac_popdir + done +fi + +test -n "$ac_init_help" && exit 0 +if $ac_init_version; then + cat <<\_ACEOF + +Copyright (C) 2003 Free Software Foundation, Inc. +This configure script is free software; the Free Software Foundation +gives unlimited permission to copy, distribute and modify it. +_ACEOF + exit 0 +fi +exec 5>config.log +cat >&5 <<_ACEOF +This file contains any messages produced by compilers while +running configure, to aid debugging if configure makes a mistake. + +It was created by $as_me, which was +generated by GNU Autoconf 2.59. Invocation command line was + + $ $0 $@ + +_ACEOF +{ +cat <<_ASUNAME +## --------- ## +## Platform. ## +## --------- ## + +hostname = `(hostname || uname -n) 2>/dev/null | sed 1q` +uname -m = `(uname -m) 2>/dev/null || echo unknown` +uname -r = `(uname -r) 2>/dev/null || echo unknown` +uname -s = `(uname -s) 2>/dev/null || echo unknown` +uname -v = `(uname -v) 2>/dev/null || echo unknown` + +/usr/bin/uname -p = `(/usr/bin/uname -p) 2>/dev/null || echo unknown` +/bin/uname -X = `(/bin/uname -X) 2>/dev/null || echo unknown` + +/bin/arch = `(/bin/arch) 2>/dev/null || echo unknown` +/usr/bin/arch -k = `(/usr/bin/arch -k) 2>/dev/null || echo unknown` +/usr/convex/getsysinfo = `(/usr/convex/getsysinfo) 2>/dev/null || echo unknown` +hostinfo = `(hostinfo) 2>/dev/null || echo unknown` +/bin/machine = `(/bin/machine) 2>/dev/null || echo unknown` +/usr/bin/oslevel = `(/usr/bin/oslevel) 2>/dev/null || echo unknown` +/bin/universe = `(/bin/universe) 2>/dev/null || echo unknown` + +_ASUNAME + +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + echo "PATH: $as_dir" +done + +} >&5 + +cat >&5 <<_ACEOF + + +## ----------- ## +## Core tests. ## +## ----------- ## + +_ACEOF + + +# Keep a trace of the command line. +# Strip out --no-create and --no-recursion so they do not pile up. +# Strip out --silent because we don't want to record it for future runs. +# Also quote any args containing shell meta-characters. +# Make two passes to allow for proper duplicate-argument suppression. +ac_configure_args= +ac_configure_args0= +ac_configure_args1= +ac_sep= +ac_must_keep_next=false +for ac_pass in 1 2 +do + for ac_arg + do + case $ac_arg in + -no-create | --no-c* | -n | -no-recursion | --no-r*) continue ;; + -q | -quiet | --quiet | --quie | --qui | --qu | --q \ + | -silent | --silent | --silen | --sile | --sil) + continue ;; + *" "*|*" "*|*[\[\]\~\#\$\^\&\*\(\)\{\}\\\|\;\<\>\?\"\']*) + ac_arg=`echo "$ac_arg" | sed "s/'/'\\\\\\\\''/g"` ;; + esac + case $ac_pass in + 1) ac_configure_args0="$ac_configure_args0 '$ac_arg'" ;; + 2) + ac_configure_args1="$ac_configure_args1 '$ac_arg'" + if test $ac_must_keep_next = true; then + ac_must_keep_next=false # Got value, back to normal. + else + case $ac_arg in + *=* | --config-cache | -C | -disable-* | --disable-* \ + | -enable-* | --enable-* | -gas | --g* | -nfp | --nf* \ + | -q | -quiet | --q* | -silent | --sil* | -v | -verb* \ + | -with-* | --with-* | -without-* | --without-* | --x) + case "$ac_configure_args0 " in + "$ac_configure_args1"*" '$ac_arg' "* ) continue ;; + esac + ;; + -* ) ac_must_keep_next=true ;; + esac + fi + ac_configure_args="$ac_configure_args$ac_sep'$ac_arg'" + # Get rid of the leading space. + ac_sep=" " + ;; + esac + done +done +$as_unset ac_configure_args0 || test "${ac_configure_args0+set}" != set || { ac_configure_args0=; export ac_configure_args0; } +$as_unset ac_configure_args1 || test "${ac_configure_args1+set}" != set || { ac_configure_args1=; export ac_configure_args1; } + +# When interrupted or exit'd, cleanup temporary files, and complete +# config.log. We remove comments because anyway the quotes in there +# would cause problems or look ugly. +# WARNING: Be sure not to use single quotes in there, as some shells, +# such as our DU 5.0 friend, will then `close' the trap. +trap 'exit_status=$? + # Save into config.log some information that might help in debugging. + { + echo + + cat <<\_ASBOX +## ---------------- ## +## Cache variables. ## +## ---------------- ## +_ASBOX + echo + # The following way of writing the cache mishandles newlines in values, +{ + (set) 2>&1 | + case `(ac_space='"'"' '"'"'; set | grep ac_space) 2>&1` in + *ac_space=\ *) + sed -n \ + "s/'"'"'/'"'"'\\\\'"'"''"'"'/g; + s/^\\([_$as_cr_alnum]*_cv_[_$as_cr_alnum]*\\)=\\(.*\\)/\\1='"'"'\\2'"'"'/p" + ;; + *) + sed -n \ + "s/^\\([_$as_cr_alnum]*_cv_[_$as_cr_alnum]*\\)=\\(.*\\)/\\1=\\2/p" + ;; + esac; +} + echo + + cat <<\_ASBOX +## ----------------- ## +## Output variables. ## +## ----------------- ## +_ASBOX + echo + for ac_var in $ac_subst_vars + do + eval ac_val=$`echo $ac_var` + echo "$ac_var='"'"'$ac_val'"'"'" + done | sort + echo + + if test -n "$ac_subst_files"; then + cat <<\_ASBOX +## ------------- ## +## Output files. ## +## ------------- ## +_ASBOX + echo + for ac_var in $ac_subst_files + do + eval ac_val=$`echo $ac_var` + echo "$ac_var='"'"'$ac_val'"'"'" + done | sort + echo + fi + + if test -s confdefs.h; then + cat <<\_ASBOX +## ----------- ## +## confdefs.h. ## +## ----------- ## +_ASBOX + echo + sed "/^$/d" confdefs.h | sort + echo + fi + test "$ac_signal" != 0 && + echo "$as_me: caught signal $ac_signal" + echo "$as_me: exit $exit_status" + } >&5 + rm -f core *.core && + rm -rf conftest* confdefs* conf$$* $ac_clean_files && + exit $exit_status + ' 0 +for ac_signal in 1 2 13 15; do + trap 'ac_signal='$ac_signal'; { (exit 1); exit 1; }' $ac_signal +done +ac_signal=0 + +# confdefs.h avoids OS command line length limits that DEFS can exceed. +rm -rf conftest* confdefs.h +# AIX cpp loses on an empty file, so make sure it contains at least a newline. +echo >confdefs.h + +# Predefined preprocessor variables. + +cat >>confdefs.h <<_ACEOF +#define PACKAGE_NAME "$PACKAGE_NAME" +_ACEOF + + +cat >>confdefs.h <<_ACEOF +#define PACKAGE_TARNAME "$PACKAGE_TARNAME" +_ACEOF + + +cat >>confdefs.h <<_ACEOF +#define PACKAGE_VERSION "$PACKAGE_VERSION" +_ACEOF + + +cat >>confdefs.h <<_ACEOF +#define PACKAGE_STRING "$PACKAGE_STRING" +_ACEOF + + +cat >>confdefs.h <<_ACEOF +#define PACKAGE_BUGREPORT "$PACKAGE_BUGREPORT" +_ACEOF + + +# Let the site file select an alternate cache file if it wants to. +# Prefer explicitly selected file to automatically selected ones. +if test -z "$CONFIG_SITE"; then + if test "x$prefix" != xNONE; then + CONFIG_SITE="$prefix/share/config.site $prefix/etc/config.site" + else + CONFIG_SITE="$ac_default_prefix/share/config.site $ac_default_prefix/etc/config.site" + fi +fi +for ac_site_file in $CONFIG_SITE; do + if test -r "$ac_site_file"; then + { echo "$as_me:$LINENO: loading site script $ac_site_file" >&5 +echo "$as_me: loading site script $ac_site_file" >&6;} + sed 's/^/| /' "$ac_site_file" >&5 + . "$ac_site_file" + fi +done + +if test -r "$cache_file"; then + # Some versions of bash will fail to source /dev/null (special + # files actually), so we avoid doing that. + if test -f "$cache_file"; then + { echo "$as_me:$LINENO: loading cache $cache_file" >&5 +echo "$as_me: loading cache $cache_file" >&6;} + case $cache_file in + [\\/]* | ?:[\\/]* ) . $cache_file;; + *) . ./$cache_file;; + esac + fi +else + { echo "$as_me:$LINENO: creating cache $cache_file" >&5 +echo "$as_me: creating cache $cache_file" >&6;} + >$cache_file +fi + +# Check that the precious variables saved in the cache have kept the same +# value. +ac_cache_corrupted=false +for ac_var in `(set) 2>&1 | + sed -n 's/^ac_env_\([a-zA-Z_0-9]*\)_set=.*/\1/p'`; do + eval ac_old_set=\$ac_cv_env_${ac_var}_set + eval ac_new_set=\$ac_env_${ac_var}_set + eval ac_old_val="\$ac_cv_env_${ac_var}_value" + eval ac_new_val="\$ac_env_${ac_var}_value" + case $ac_old_set,$ac_new_set in + set,) + { echo "$as_me:$LINENO: error: \`$ac_var' was set to \`$ac_old_val' in the previous run" >&5 +echo "$as_me: error: \`$ac_var' was set to \`$ac_old_val' in the previous run" >&2;} + ac_cache_corrupted=: ;; + ,set) + { echo "$as_me:$LINENO: error: \`$ac_var' was not set in the previous run" >&5 +echo "$as_me: error: \`$ac_var' was not set in the previous run" >&2;} + ac_cache_corrupted=: ;; + ,);; + *) + if test "x$ac_old_val" != "x$ac_new_val"; then + { echo "$as_me:$LINENO: error: \`$ac_var' has changed since the previous run:" >&5 +echo "$as_me: error: \`$ac_var' has changed since the previous run:" >&2;} + { echo "$as_me:$LINENO: former value: $ac_old_val" >&5 +echo "$as_me: former value: $ac_old_val" >&2;} + { echo "$as_me:$LINENO: current value: $ac_new_val" >&5 +echo "$as_me: current value: $ac_new_val" >&2;} + ac_cache_corrupted=: + fi;; + esac + # Pass precious variables to config.status. + if test "$ac_new_set" = set; then + case $ac_new_val in + *" "*|*" "*|*[\[\]\~\#\$\^\&\*\(\)\{\}\\\|\;\<\>\?\"\']*) + ac_arg=$ac_var=`echo "$ac_new_val" | sed "s/'/'\\\\\\\\''/g"` ;; + *) ac_arg=$ac_var=$ac_new_val ;; + esac + case " $ac_configure_args " in + *" '$ac_arg' "*) ;; # Avoid dups. Use of quotes ensures accuracy. + *) ac_configure_args="$ac_configure_args '$ac_arg'" ;; + esac + fi +done +if $ac_cache_corrupted; then + { echo "$as_me:$LINENO: error: changes in the environment can compromise the build" >&5 +echo "$as_me: error: changes in the environment can compromise the build" >&2;} + { { echo "$as_me:$LINENO: error: run \`make distclean' and/or \`rm $cache_file' and start over" >&5 +echo "$as_me: error: run \`make distclean' and/or \`rm $cache_file' and start over" >&2;} + { (exit 1); exit 1; }; } +fi + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + + + + + + + + + + + + + + + + + + + + + + + + + ac_config_headers="$ac_config_headers config.h" + + + +POSIX_MALLOC_THRESHOLD=-DPOSIX_MALLOC_THRESHOLD=10 + + +PCRE_LIB_VERSION=0:1:0 +PCRE_POSIXLIB_VERSION=0:0:0 +PCRE_CPPLIB_VERSION=0:0:0 + + +PCRE_MAJOR=`grep '#define PCRE_MAJOR' ${srcdir}/pcre.h | cut -c 29-` +PCRE_MINOR=`grep '#define PCRE_MINOR' ${srcdir}/pcre.h | cut -c 29-` +PCRE_PRERELEASE=`grep '#define PCRE_PRERELEASE' ${srcdir}/pcre.h | cut -c 29-` +PCRE_VERSION=${PCRE_MAJOR}.${PCRE_MINOR}${PCRE_PRERELEASE} + + +# Check whether --enable-cpp or --disable-cpp was given. +if test "${enable_cpp+set}" = set; then + enableval="$enable_cpp" + want_cpp="$enableval" +else + want_cpp=yes +fi; + + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu +if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}gcc", so it can be a program name with args. +set dummy ${ac_tool_prefix}gcc; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_CC+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$CC"; then + ac_cv_prog_CC="$CC" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_CC="${ac_tool_prefix}gcc" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + +fi +fi +CC=$ac_cv_prog_CC +if test -n "$CC"; then + echo "$as_me:$LINENO: result: $CC" >&5 +echo "${ECHO_T}$CC" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + +fi +if test -z "$ac_cv_prog_CC"; then + ac_ct_CC=$CC + # Extract the first word of "gcc", so it can be a program name with args. +set dummy gcc; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_ac_ct_CC+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$ac_ct_CC"; then + ac_cv_prog_ac_ct_CC="$ac_ct_CC" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_CC="gcc" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + +fi +fi +ac_ct_CC=$ac_cv_prog_ac_ct_CC +if test -n "$ac_ct_CC"; then + echo "$as_me:$LINENO: result: $ac_ct_CC" >&5 +echo "${ECHO_T}$ac_ct_CC" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + + CC=$ac_ct_CC +else + CC="$ac_cv_prog_CC" +fi + +if test -z "$CC"; then + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}cc", so it can be a program name with args. +set dummy ${ac_tool_prefix}cc; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_CC+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$CC"; then + ac_cv_prog_CC="$CC" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_CC="${ac_tool_prefix}cc" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + +fi +fi +CC=$ac_cv_prog_CC +if test -n "$CC"; then + echo "$as_me:$LINENO: result: $CC" >&5 +echo "${ECHO_T}$CC" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + +fi +if test -z "$ac_cv_prog_CC"; then + ac_ct_CC=$CC + # Extract the first word of "cc", so it can be a program name with args. +set dummy cc; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_ac_ct_CC+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$ac_ct_CC"; then + ac_cv_prog_ac_ct_CC="$ac_ct_CC" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_CC="cc" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + +fi +fi +ac_ct_CC=$ac_cv_prog_ac_ct_CC +if test -n "$ac_ct_CC"; then + echo "$as_me:$LINENO: result: $ac_ct_CC" >&5 +echo "${ECHO_T}$ac_ct_CC" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + + CC=$ac_ct_CC +else + CC="$ac_cv_prog_CC" +fi + +fi +if test -z "$CC"; then + # Extract the first word of "cc", so it can be a program name with args. +set dummy cc; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_CC+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$CC"; then + ac_cv_prog_CC="$CC" # Let the user override the test. +else + ac_prog_rejected=no +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + if test "$as_dir/$ac_word$ac_exec_ext" = "/usr/ucb/cc"; then + ac_prog_rejected=yes + continue + fi + ac_cv_prog_CC="cc" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + +if test $ac_prog_rejected = yes; then + # We found a bogon in the path, so make sure we never use it. + set dummy $ac_cv_prog_CC + shift + if test $# != 0; then + # We chose a different compiler from the bogus one. + # However, it has the same basename, so the bogon will be chosen + # first if we set CC to just the basename; use the full file name. + shift + ac_cv_prog_CC="$as_dir/$ac_word${1+' '}$@" + fi +fi +fi +fi +CC=$ac_cv_prog_CC +if test -n "$CC"; then + echo "$as_me:$LINENO: result: $CC" >&5 +echo "${ECHO_T}$CC" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + +fi +if test -z "$CC"; then + if test -n "$ac_tool_prefix"; then + for ac_prog in cl + do + # Extract the first word of "$ac_tool_prefix$ac_prog", so it can be a program name with args. +set dummy $ac_tool_prefix$ac_prog; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_CC+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$CC"; then + ac_cv_prog_CC="$CC" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_CC="$ac_tool_prefix$ac_prog" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + +fi +fi +CC=$ac_cv_prog_CC +if test -n "$CC"; then + echo "$as_me:$LINENO: result: $CC" >&5 +echo "${ECHO_T}$CC" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + + test -n "$CC" && break + done +fi +if test -z "$CC"; then + ac_ct_CC=$CC + for ac_prog in cl +do + # Extract the first word of "$ac_prog", so it can be a program name with args. +set dummy $ac_prog; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_ac_ct_CC+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$ac_ct_CC"; then + ac_cv_prog_ac_ct_CC="$ac_ct_CC" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_CC="$ac_prog" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + +fi +fi +ac_ct_CC=$ac_cv_prog_ac_ct_CC +if test -n "$ac_ct_CC"; then + echo "$as_me:$LINENO: result: $ac_ct_CC" >&5 +echo "${ECHO_T}$ac_ct_CC" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + + test -n "$ac_ct_CC" && break +done + + CC=$ac_ct_CC +fi + +fi + + +test -z "$CC" && { { echo "$as_me:$LINENO: error: no acceptable C compiler found in \$PATH +See \`config.log' for more details." >&5 +echo "$as_me: error: no acceptable C compiler found in \$PATH +See \`config.log' for more details." >&2;} + { (exit 1); exit 1; }; } + +# Provide some information about the compiler. +echo "$as_me:$LINENO:" \ + "checking for C compiler version" >&5 +ac_compiler=`set X $ac_compile; echo $2` +{ (eval echo "$as_me:$LINENO: \"$ac_compiler --version &5\"") >&5 + (eval $ac_compiler --version &5) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } +{ (eval echo "$as_me:$LINENO: \"$ac_compiler -v &5\"") >&5 + (eval $ac_compiler -v &5) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } +{ (eval echo "$as_me:$LINENO: \"$ac_compiler -V &5\"") >&5 + (eval $ac_compiler -V &5) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } + +cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +ac_clean_files_save=$ac_clean_files +ac_clean_files="$ac_clean_files a.out a.exe b.out" +# Try to create an executable without -o first, disregard a.out. +# It will help us diagnose broken compilers, and finding out an intuition +# of exeext. +echo "$as_me:$LINENO: checking for C compiler default output file name" >&5 +echo $ECHO_N "checking for C compiler default output file name... $ECHO_C" >&6 +ac_link_default=`echo "$ac_link" | sed 's/ -o *conftest[^ ]*//'` +if { (eval echo "$as_me:$LINENO: \"$ac_link_default\"") >&5 + (eval $ac_link_default) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; then + # Find the output, starting from the most likely. This scheme is +# not robust to junk in `.', hence go to wildcards (a.*) only as a last +# resort. + +# Be careful to initialize this variable, since it used to be cached. +# Otherwise an old cache value of `no' led to `EXEEXT = no' in a Makefile. +ac_cv_exeext= +# b.out is created by i960 compilers. +for ac_file in a_out.exe a.exe conftest.exe a.out conftest a.* conftest.* b.out +do + test -f "$ac_file" || continue + case $ac_file in + *.$ac_ext | *.xcoff | *.tds | *.d | *.pdb | *.xSYM | *.bb | *.bbg | *.o | *.obj ) + ;; + conftest.$ac_ext ) + # This is the source file. + ;; + [ab].out ) + # We found the default executable, but exeext='' is most + # certainly right. + break;; + *.* ) + ac_cv_exeext=`expr "$ac_file" : '[^.]*\(\..*\)'` + # FIXME: I believe we export ac_cv_exeext for Libtool, + # but it would be cool to find out if it's true. Does anybody + # maintain Libtool? --akim. + export ac_cv_exeext + break;; + * ) + break;; + esac +done +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +{ { echo "$as_me:$LINENO: error: C compiler cannot create executables +See \`config.log' for more details." >&5 +echo "$as_me: error: C compiler cannot create executables +See \`config.log' for more details." >&2;} + { (exit 77); exit 77; }; } +fi + +ac_exeext=$ac_cv_exeext +echo "$as_me:$LINENO: result: $ac_file" >&5 +echo "${ECHO_T}$ac_file" >&6 + +# Check the compiler produces executables we can run. If not, either +# the compiler is broken, or we cross compile. +echo "$as_me:$LINENO: checking whether the C compiler works" >&5 +echo $ECHO_N "checking whether the C compiler works... $ECHO_C" >&6 +# FIXME: These cross compiler hacks should be removed for Autoconf 3.0 +# If not cross compiling, check that we can run a simple program. +if test "$cross_compiling" != yes; then + if { ac_try='./$ac_file' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + cross_compiling=no + else + if test "$cross_compiling" = maybe; then + cross_compiling=yes + else + { { echo "$as_me:$LINENO: error: cannot run C compiled programs. +If you meant to cross compile, use \`--host'. +See \`config.log' for more details." >&5 +echo "$as_me: error: cannot run C compiled programs. +If you meant to cross compile, use \`--host'. +See \`config.log' for more details." >&2;} + { (exit 1); exit 1; }; } + fi + fi +fi +echo "$as_me:$LINENO: result: yes" >&5 +echo "${ECHO_T}yes" >&6 + +rm -f a.out a.exe conftest$ac_cv_exeext b.out +ac_clean_files=$ac_clean_files_save +# Check the compiler produces executables we can run. If not, either +# the compiler is broken, or we cross compile. +echo "$as_me:$LINENO: checking whether we are cross compiling" >&5 +echo $ECHO_N "checking whether we are cross compiling... $ECHO_C" >&6 +echo "$as_me:$LINENO: result: $cross_compiling" >&5 +echo "${ECHO_T}$cross_compiling" >&6 + +echo "$as_me:$LINENO: checking for suffix of executables" >&5 +echo $ECHO_N "checking for suffix of executables... $ECHO_C" >&6 +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; then + # If both `conftest.exe' and `conftest' are `present' (well, observable) +# catch `conftest.exe'. For instance with Cygwin, `ls conftest' will +# work properly (i.e., refer to `conftest.exe'), while it won't with +# `rm'. +for ac_file in conftest.exe conftest conftest.*; do + test -f "$ac_file" || continue + case $ac_file in + *.$ac_ext | *.xcoff | *.tds | *.d | *.pdb | *.xSYM | *.bb | *.bbg | *.o | *.obj ) ;; + *.* ) ac_cv_exeext=`expr "$ac_file" : '[^.]*\(\..*\)'` + export ac_cv_exeext + break;; + * ) break;; + esac +done +else + { { echo "$as_me:$LINENO: error: cannot compute suffix of executables: cannot compile and link +See \`config.log' for more details." >&5 +echo "$as_me: error: cannot compute suffix of executables: cannot compile and link +See \`config.log' for more details." >&2;} + { (exit 1); exit 1; }; } +fi + +rm -f conftest$ac_cv_exeext +echo "$as_me:$LINENO: result: $ac_cv_exeext" >&5 +echo "${ECHO_T}$ac_cv_exeext" >&6 + +rm -f conftest.$ac_ext +EXEEXT=$ac_cv_exeext +ac_exeext=$EXEEXT +echo "$as_me:$LINENO: checking for suffix of object files" >&5 +echo $ECHO_N "checking for suffix of object files... $ECHO_C" >&6 +if test "${ac_cv_objext+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +rm -f conftest.o conftest.obj +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; then + for ac_file in `(ls conftest.o conftest.obj; ls conftest.*) 2>/dev/null`; do + case $ac_file in + *.$ac_ext | *.xcoff | *.tds | *.d | *.pdb | *.xSYM | *.bb | *.bbg ) ;; + *) ac_cv_objext=`expr "$ac_file" : '.*\.\(.*\)'` + break;; + esac +done +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +{ { echo "$as_me:$LINENO: error: cannot compute suffix of object files: cannot compile +See \`config.log' for more details." >&5 +echo "$as_me: error: cannot compute suffix of object files: cannot compile +See \`config.log' for more details." >&2;} + { (exit 1); exit 1; }; } +fi + +rm -f conftest.$ac_cv_objext conftest.$ac_ext +fi +echo "$as_me:$LINENO: result: $ac_cv_objext" >&5 +echo "${ECHO_T}$ac_cv_objext" >&6 +OBJEXT=$ac_cv_objext +ac_objext=$OBJEXT +echo "$as_me:$LINENO: checking whether we are using the GNU C compiler" >&5 +echo $ECHO_N "checking whether we are using the GNU C compiler... $ECHO_C" >&6 +if test "${ac_cv_c_compiler_gnu+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +int +main () +{ +#ifndef __GNUC__ + choke me +#endif + + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_compiler_gnu=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_compiler_gnu=no +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext +ac_cv_c_compiler_gnu=$ac_compiler_gnu + +fi +echo "$as_me:$LINENO: result: $ac_cv_c_compiler_gnu" >&5 +echo "${ECHO_T}$ac_cv_c_compiler_gnu" >&6 +GCC=`test $ac_compiler_gnu = yes && echo yes` +ac_test_CFLAGS=${CFLAGS+set} +ac_save_CFLAGS=$CFLAGS +CFLAGS="-g" +echo "$as_me:$LINENO: checking whether $CC accepts -g" >&5 +echo $ECHO_N "checking whether $CC accepts -g... $ECHO_C" >&6 +if test "${ac_cv_prog_cc_g+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_cv_prog_cc_g=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_cv_prog_cc_g=no +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext +fi +echo "$as_me:$LINENO: result: $ac_cv_prog_cc_g" >&5 +echo "${ECHO_T}$ac_cv_prog_cc_g" >&6 +if test "$ac_test_CFLAGS" = set; then + CFLAGS=$ac_save_CFLAGS +elif test $ac_cv_prog_cc_g = yes; then + if test "$GCC" = yes; then + CFLAGS="-g -O2" + else + CFLAGS="-g" + fi +else + if test "$GCC" = yes; then + CFLAGS="-O2" + else + CFLAGS= + fi +fi +echo "$as_me:$LINENO: checking for $CC option to accept ANSI C" >&5 +echo $ECHO_N "checking for $CC option to accept ANSI C... $ECHO_C" >&6 +if test "${ac_cv_prog_cc_stdc+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + ac_cv_prog_cc_stdc=no +ac_save_CC=$CC +cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#include +#include +#include +#include +/* Most of the following tests are stolen from RCS 5.7's src/conf.sh. */ +struct buf { int x; }; +FILE * (*rcsopen) (struct buf *, struct stat *, int); +static char *e (p, i) + char **p; + int i; +{ + return p[i]; +} +static char *f (char * (*g) (char **, int), char **p, ...) +{ + char *s; + va_list v; + va_start (v,p); + s = g (p, va_arg (v,int)); + va_end (v); + return s; +} + +/* OSF 4.0 Compaq cc is some sort of almost-ANSI by default. It has + function prototypes and stuff, but not '\xHH' hex character constants. + These don't provoke an error unfortunately, instead are silently treated + as 'x'. The following induces an error, until -std1 is added to get + proper ANSI mode. Curiously '\x00'!='x' always comes out true, for an + array size at least. It's necessary to write '\x00'==0 to get something + that's true only with -std1. */ +int osf4_cc_array ['\x00' == 0 ? 1 : -1]; + +int test (int i, double x); +struct s1 {int (*f) (int a);}; +struct s2 {int (*f) (double a);}; +int pairnames (int, char **, FILE *(*)(struct buf *, struct stat *, int), int, int); +int argc; +char **argv; +int +main () +{ +return f (e, argv, 0) != argv[0] || f (e, argv, 1) != argv[1]; + ; + return 0; +} +_ACEOF +# Don't try gcc -ansi; that turns off useful extensions and +# breaks some systems' header files. +# AIX -qlanglvl=ansi +# Ultrix and OSF/1 -std1 +# HP-UX 10.20 and later -Ae +# HP-UX older versions -Aa -D_HPUX_SOURCE +# SVR4 -Xc -D__EXTENSIONS__ +for ac_arg in "" -qlanglvl=ansi -std1 -Ae "-Aa -D_HPUX_SOURCE" "-Xc -D__EXTENSIONS__" +do + CC="$ac_save_CC $ac_arg" + rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_cv_prog_cc_stdc=$ac_arg +break +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +fi +rm -f conftest.err conftest.$ac_objext +done +rm -f conftest.$ac_ext conftest.$ac_objext +CC=$ac_save_CC + +fi + +case "x$ac_cv_prog_cc_stdc" in + x|xno) + echo "$as_me:$LINENO: result: none needed" >&5 +echo "${ECHO_T}none needed" >&6 ;; + *) + echo "$as_me:$LINENO: result: $ac_cv_prog_cc_stdc" >&5 +echo "${ECHO_T}$ac_cv_prog_cc_stdc" >&6 + CC="$CC $ac_cv_prog_cc_stdc" ;; +esac + +# Some people use a C++ compiler to compile C. Since we use `exit', +# in C++ we need to declare it. In case someone uses the same compiler +# for both compiling C and C++ we need to have the C++ compiler decide +# the declaration of exit, since it's the most demanding environment. +cat >conftest.$ac_ext <<_ACEOF +#ifndef __cplusplus + choke me +#endif +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + for ac_declaration in \ + '' \ + 'extern "C" void std::exit (int) throw (); using std::exit;' \ + 'extern "C" void std::exit (int); using std::exit;' \ + 'extern "C" void exit (int) throw ();' \ + 'extern "C" void exit (int);' \ + 'void exit (int);' +do + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +$ac_declaration +#include +int +main () +{ +exit (42); + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + : +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +continue +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +$ac_declaration +int +main () +{ +exit (42); + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + break +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext +done +rm -f conftest* +if test -n "$ac_declaration"; then + echo '#ifdef __cplusplus' >>confdefs.h + echo $ac_declaration >>confdefs.h + echo '#endif' >>confdefs.h +fi + +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + + + +ac_ext=cc +ac_cpp='$CXXCPP $CPPFLAGS' +ac_compile='$CXX -c $CXXFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CXX -o conftest$ac_exeext $CXXFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_cxx_compiler_gnu +if test -n "$ac_tool_prefix"; then + for ac_prog in $CCC g++ c++ gpp aCC CC cxx cc++ cl FCC KCC RCC xlC_r xlC + do + # Extract the first word of "$ac_tool_prefix$ac_prog", so it can be a program name with args. +set dummy $ac_tool_prefix$ac_prog; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_CXX+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$CXX"; then + ac_cv_prog_CXX="$CXX" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_CXX="$ac_tool_prefix$ac_prog" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + +fi +fi +CXX=$ac_cv_prog_CXX +if test -n "$CXX"; then + echo "$as_me:$LINENO: result: $CXX" >&5 +echo "${ECHO_T}$CXX" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + + test -n "$CXX" && break + done +fi +if test -z "$CXX"; then + ac_ct_CXX=$CXX + for ac_prog in $CCC g++ c++ gpp aCC CC cxx cc++ cl FCC KCC RCC xlC_r xlC +do + # Extract the first word of "$ac_prog", so it can be a program name with args. +set dummy $ac_prog; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_ac_ct_CXX+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$ac_ct_CXX"; then + ac_cv_prog_ac_ct_CXX="$ac_ct_CXX" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_CXX="$ac_prog" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + +fi +fi +ac_ct_CXX=$ac_cv_prog_ac_ct_CXX +if test -n "$ac_ct_CXX"; then + echo "$as_me:$LINENO: result: $ac_ct_CXX" >&5 +echo "${ECHO_T}$ac_ct_CXX" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + + test -n "$ac_ct_CXX" && break +done +test -n "$ac_ct_CXX" || ac_ct_CXX="g++" + + CXX=$ac_ct_CXX +fi + + +# Provide some information about the compiler. +echo "$as_me:$LINENO:" \ + "checking for C++ compiler version" >&5 +ac_compiler=`set X $ac_compile; echo $2` +{ (eval echo "$as_me:$LINENO: \"$ac_compiler --version &5\"") >&5 + (eval $ac_compiler --version &5) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } +{ (eval echo "$as_me:$LINENO: \"$ac_compiler -v &5\"") >&5 + (eval $ac_compiler -v &5) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } +{ (eval echo "$as_me:$LINENO: \"$ac_compiler -V &5\"") >&5 + (eval $ac_compiler -V &5) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } + +echo "$as_me:$LINENO: checking whether we are using the GNU C++ compiler" >&5 +echo $ECHO_N "checking whether we are using the GNU C++ compiler... $ECHO_C" >&6 +if test "${ac_cv_cxx_compiler_gnu+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +int +main () +{ +#ifndef __GNUC__ + choke me +#endif + + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_cxx_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_compiler_gnu=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_compiler_gnu=no +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext +ac_cv_cxx_compiler_gnu=$ac_compiler_gnu + +fi +echo "$as_me:$LINENO: result: $ac_cv_cxx_compiler_gnu" >&5 +echo "${ECHO_T}$ac_cv_cxx_compiler_gnu" >&6 +GXX=`test $ac_compiler_gnu = yes && echo yes` +ac_test_CXXFLAGS=${CXXFLAGS+set} +ac_save_CXXFLAGS=$CXXFLAGS +CXXFLAGS="-g" +echo "$as_me:$LINENO: checking whether $CXX accepts -g" >&5 +echo $ECHO_N "checking whether $CXX accepts -g... $ECHO_C" >&6 +if test "${ac_cv_prog_cxx_g+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_cxx_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_cv_prog_cxx_g=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_cv_prog_cxx_g=no +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext +fi +echo "$as_me:$LINENO: result: $ac_cv_prog_cxx_g" >&5 +echo "${ECHO_T}$ac_cv_prog_cxx_g" >&6 +if test "$ac_test_CXXFLAGS" = set; then + CXXFLAGS=$ac_save_CXXFLAGS +elif test $ac_cv_prog_cxx_g = yes; then + if test "$GXX" = yes; then + CXXFLAGS="-g -O2" + else + CXXFLAGS="-g" + fi +else + if test "$GXX" = yes; then + CXXFLAGS="-O2" + else + CXXFLAGS= + fi +fi +for ac_declaration in \ + '' \ + 'extern "C" void std::exit (int) throw (); using std::exit;' \ + 'extern "C" void std::exit (int); using std::exit;' \ + 'extern "C" void exit (int) throw ();' \ + 'extern "C" void exit (int);' \ + 'void exit (int);' +do + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +$ac_declaration +#include +int +main () +{ +exit (42); + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_cxx_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + : +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +continue +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +$ac_declaration +int +main () +{ +exit (42); + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_cxx_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + break +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext +done +rm -f conftest* +if test -n "$ac_declaration"; then + echo '#ifdef __cplusplus' >>confdefs.h + echo $ac_declaration >>confdefs.h + echo '#endif' >>confdefs.h +fi + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + + + +ac_aux_dir= +for ac_dir in $srcdir $srcdir/.. $srcdir/../..; do + if test -f $ac_dir/install-sh; then + ac_aux_dir=$ac_dir + ac_install_sh="$ac_aux_dir/install-sh -c" + break + elif test -f $ac_dir/install.sh; then + ac_aux_dir=$ac_dir + ac_install_sh="$ac_aux_dir/install.sh -c" + break + elif test -f $ac_dir/shtool; then + ac_aux_dir=$ac_dir + ac_install_sh="$ac_aux_dir/shtool install -c" + break + fi +done +if test -z "$ac_aux_dir"; then + { { echo "$as_me:$LINENO: error: cannot find install-sh or install.sh in $srcdir $srcdir/.. $srcdir/../.." >&5 +echo "$as_me: error: cannot find install-sh or install.sh in $srcdir $srcdir/.. $srcdir/../.." >&2;} + { (exit 1); exit 1; }; } +fi +ac_config_guess="$SHELL $ac_aux_dir/config.guess" +ac_config_sub="$SHELL $ac_aux_dir/config.sub" +ac_configure="$SHELL $ac_aux_dir/configure" # This should be Cygnus configure. + +# Find a good install program. We prefer a C program (faster), +# so one script is as good as another. But avoid the broken or +# incompatible versions: +# SysV /etc/install, /usr/sbin/install +# SunOS /usr/etc/install +# IRIX /sbin/install +# AIX /bin/install +# AmigaOS /C/install, which installs bootblocks on floppy discs +# AIX 4 /usr/bin/installbsd, which doesn't work without a -g flag +# AFS /usr/afsws/bin/install, which mishandles nonexistent args +# SVR4 /usr/ucb/install, which tries to use the nonexistent group "staff" +# OS/2's system install, which has a completely different semantic +# ./install, which can be erroneously created by make from ./install.sh. +echo "$as_me:$LINENO: checking for a BSD-compatible install" >&5 +echo $ECHO_N "checking for a BSD-compatible install... $ECHO_C" >&6 +if test -z "$INSTALL"; then +if test "${ac_cv_path_install+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + # Account for people who put trailing slashes in PATH elements. +case $as_dir/ in + ./ | .// | /cC/* | \ + /etc/* | /usr/sbin/* | /usr/etc/* | /sbin/* | /usr/afsws/bin/* | \ + ?:\\/os2\\/install\\/* | ?:\\/OS2\\/INSTALL\\/* | \ + /usr/ucb/* ) ;; + *) + # OSF1 and SCO ODT 3.0 have their own names for install. + # Don't use installbsd from OSF since it installs stuff as root + # by default. + for ac_prog in ginstall scoinst install; do + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_prog$ac_exec_ext"; then + if test $ac_prog = install && + grep dspmsg "$as_dir/$ac_prog$ac_exec_ext" >/dev/null 2>&1; then + # AIX install. It has an incompatible calling convention. + : + elif test $ac_prog = install && + grep pwplus "$as_dir/$ac_prog$ac_exec_ext" >/dev/null 2>&1; then + # program-specific install script used by HP pwplus--don't use. + : + else + ac_cv_path_install="$as_dir/$ac_prog$ac_exec_ext -c" + break 3 + fi + fi + done + done + ;; +esac +done + + +fi + if test "${ac_cv_path_install+set}" = set; then + INSTALL=$ac_cv_path_install + else + # As a last resort, use the slow shell script. We don't cache a + # path for INSTALL within a source directory, because that will + # break other packages using the cache if that directory is + # removed, or if the path is relative. + INSTALL=$ac_install_sh + fi +fi +echo "$as_me:$LINENO: result: $INSTALL" >&5 +echo "${ECHO_T}$INSTALL" >&6 + +# Use test -z because SunOS4 sh mishandles braces in ${var-val}. +# It thinks the first close brace ends the variable substitution. +test -z "$INSTALL_PROGRAM" && INSTALL_PROGRAM='${INSTALL}' + +test -z "$INSTALL_SCRIPT" && INSTALL_SCRIPT='${INSTALL}' + +test -z "$INSTALL_DATA" && INSTALL_DATA='${INSTALL} -m 644' + + + +# Check whether --enable-shared or --disable-shared was given. +if test "${enable_shared+set}" = set; then + enableval="$enable_shared" + p=${PACKAGE-default} + case $enableval in + yes) enable_shared=yes ;; + no) enable_shared=no ;; + *) + enable_shared=no + # Look at the argument we got. We use all the common list separators. + lt_save_ifs="$IFS"; IFS="${IFS}$PATH_SEPARATOR," + for pkg in $enableval; do + IFS="$lt_save_ifs" + if test "X$pkg" = "X$p"; then + enable_shared=yes + fi + done + IFS="$lt_save_ifs" + ;; + esac +else + enable_shared=yes +fi; + +# Check whether --enable-static or --disable-static was given. +if test "${enable_static+set}" = set; then + enableval="$enable_static" + p=${PACKAGE-default} + case $enableval in + yes) enable_static=yes ;; + no) enable_static=no ;; + *) + enable_static=no + # Look at the argument we got. We use all the common list separators. + lt_save_ifs="$IFS"; IFS="${IFS}$PATH_SEPARATOR," + for pkg in $enableval; do + IFS="$lt_save_ifs" + if test "X$pkg" = "X$p"; then + enable_static=yes + fi + done + IFS="$lt_save_ifs" + ;; + esac +else + enable_static=yes +fi; + +# Check whether --enable-fast-install or --disable-fast-install was given. +if test "${enable_fast_install+set}" = set; then + enableval="$enable_fast_install" + p=${PACKAGE-default} + case $enableval in + yes) enable_fast_install=yes ;; + no) enable_fast_install=no ;; + *) + enable_fast_install=no + # Look at the argument we got. We use all the common list separators. + lt_save_ifs="$IFS"; IFS="${IFS}$PATH_SEPARATOR," + for pkg in $enableval; do + IFS="$lt_save_ifs" + if test "X$pkg" = "X$p"; then + enable_fast_install=yes + fi + done + IFS="$lt_save_ifs" + ;; + esac +else + enable_fast_install=yes +fi; + +# Make sure we can run config.sub. +$ac_config_sub sun4 >/dev/null 2>&1 || + { { echo "$as_me:$LINENO: error: cannot run $ac_config_sub" >&5 +echo "$as_me: error: cannot run $ac_config_sub" >&2;} + { (exit 1); exit 1; }; } + +echo "$as_me:$LINENO: checking build system type" >&5 +echo $ECHO_N "checking build system type... $ECHO_C" >&6 +if test "${ac_cv_build+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + ac_cv_build_alias=$build_alias +test -z "$ac_cv_build_alias" && + ac_cv_build_alias=`$ac_config_guess` +test -z "$ac_cv_build_alias" && + { { echo "$as_me:$LINENO: error: cannot guess build type; you must specify one" >&5 +echo "$as_me: error: cannot guess build type; you must specify one" >&2;} + { (exit 1); exit 1; }; } +ac_cv_build=`$ac_config_sub $ac_cv_build_alias` || + { { echo "$as_me:$LINENO: error: $ac_config_sub $ac_cv_build_alias failed" >&5 +echo "$as_me: error: $ac_config_sub $ac_cv_build_alias failed" >&2;} + { (exit 1); exit 1; }; } + +fi +echo "$as_me:$LINENO: result: $ac_cv_build" >&5 +echo "${ECHO_T}$ac_cv_build" >&6 +build=$ac_cv_build +build_cpu=`echo $ac_cv_build | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\1/'` +build_vendor=`echo $ac_cv_build | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\2/'` +build_os=`echo $ac_cv_build | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\3/'` + + +echo "$as_me:$LINENO: checking host system type" >&5 +echo $ECHO_N "checking host system type... $ECHO_C" >&6 +if test "${ac_cv_host+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + ac_cv_host_alias=$host_alias +test -z "$ac_cv_host_alias" && + ac_cv_host_alias=$ac_cv_build_alias +ac_cv_host=`$ac_config_sub $ac_cv_host_alias` || + { { echo "$as_me:$LINENO: error: $ac_config_sub $ac_cv_host_alias failed" >&5 +echo "$as_me: error: $ac_config_sub $ac_cv_host_alias failed" >&2;} + { (exit 1); exit 1; }; } + +fi +echo "$as_me:$LINENO: result: $ac_cv_host" >&5 +echo "${ECHO_T}$ac_cv_host" >&6 +host=$ac_cv_host +host_cpu=`echo $ac_cv_host | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\1/'` +host_vendor=`echo $ac_cv_host | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\2/'` +host_os=`echo $ac_cv_host | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\3/'` + + +echo "$as_me:$LINENO: checking for a sed that does not truncate output" >&5 +echo $ECHO_N "checking for a sed that does not truncate output... $ECHO_C" >&6 +if test "${lt_cv_path_SED+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + # Loop through the user's path and test for sed and gsed. +# Then use that list of sed's as ones to test for truncation. +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for lt_ac_prog in sed gsed; do + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$lt_ac_prog$ac_exec_ext"; then + lt_ac_sed_list="$lt_ac_sed_list $as_dir/$lt_ac_prog$ac_exec_ext" + fi + done + done +done +lt_ac_max=0 +lt_ac_count=0 +# Add /usr/xpg4/bin/sed as it is typically found on Solaris +# along with /bin/sed that truncates output. +for lt_ac_sed in $lt_ac_sed_list /usr/xpg4/bin/sed; do + test ! -f $lt_ac_sed && continue + cat /dev/null > conftest.in + lt_ac_count=0 + echo $ECHO_N "0123456789$ECHO_C" >conftest.in + # Check for GNU sed and select it if it is found. + if "$lt_ac_sed" --version 2>&1 < /dev/null | grep 'GNU' > /dev/null; then + lt_cv_path_SED=$lt_ac_sed + break + fi + while true; do + cat conftest.in conftest.in >conftest.tmp + mv conftest.tmp conftest.in + cp conftest.in conftest.nl + echo >>conftest.nl + $lt_ac_sed -e 's/a$//' < conftest.nl >conftest.out || break + cmp -s conftest.out conftest.nl || break + # 10000 chars as input seems more than enough + test $lt_ac_count -gt 10 && break + lt_ac_count=`expr $lt_ac_count + 1` + if test $lt_ac_count -gt $lt_ac_max; then + lt_ac_max=$lt_ac_count + lt_cv_path_SED=$lt_ac_sed + fi + done +done + +fi + +SED=$lt_cv_path_SED +echo "$as_me:$LINENO: result: $SED" >&5 +echo "${ECHO_T}$SED" >&6 + +echo "$as_me:$LINENO: checking for egrep" >&5 +echo $ECHO_N "checking for egrep... $ECHO_C" >&6 +if test "${ac_cv_prog_egrep+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if echo a | (grep -E '(a|b)') >/dev/null 2>&1 + then ac_cv_prog_egrep='grep -E' + else ac_cv_prog_egrep='egrep' + fi +fi +echo "$as_me:$LINENO: result: $ac_cv_prog_egrep" >&5 +echo "${ECHO_T}$ac_cv_prog_egrep" >&6 + EGREP=$ac_cv_prog_egrep + + + +# Check whether --with-gnu-ld or --without-gnu-ld was given. +if test "${with_gnu_ld+set}" = set; then + withval="$with_gnu_ld" + test "$withval" = no || with_gnu_ld=yes +else + with_gnu_ld=no +fi; +ac_prog=ld +if test "$GCC" = yes; then + # Check if gcc -print-prog-name=ld gives a path. + echo "$as_me:$LINENO: checking for ld used by $CC" >&5 +echo $ECHO_N "checking for ld used by $CC... $ECHO_C" >&6 + case $host in + *-*-mingw*) + # gcc leaves a trailing carriage return which upsets mingw + ac_prog=`($CC -print-prog-name=ld) 2>&5 | tr -d '\015'` ;; + *) + ac_prog=`($CC -print-prog-name=ld) 2>&5` ;; + esac + case $ac_prog in + # Accept absolute paths. + [\\/]* | ?:[\\/]*) + re_direlt='/[^/][^/]*/\.\./' + # Canonicalize the pathname of ld + ac_prog=`echo $ac_prog| $SED 's%\\\\%/%g'` + while echo $ac_prog | grep "$re_direlt" > /dev/null 2>&1; do + ac_prog=`echo $ac_prog| $SED "s%$re_direlt%/%"` + done + test -z "$LD" && LD="$ac_prog" + ;; + "") + # If it fails, then pretend we aren't using GCC. + ac_prog=ld + ;; + *) + # If it is relative, then search for the first ld in PATH. + with_gnu_ld=unknown + ;; + esac +elif test "$with_gnu_ld" = yes; then + echo "$as_me:$LINENO: checking for GNU ld" >&5 +echo $ECHO_N "checking for GNU ld... $ECHO_C" >&6 +else + echo "$as_me:$LINENO: checking for non-GNU ld" >&5 +echo $ECHO_N "checking for non-GNU ld... $ECHO_C" >&6 +fi +if test "${lt_cv_path_LD+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -z "$LD"; then + lt_save_ifs="$IFS"; IFS=$PATH_SEPARATOR + for ac_dir in $PATH; do + IFS="$lt_save_ifs" + test -z "$ac_dir" && ac_dir=. + if test -f "$ac_dir/$ac_prog" || test -f "$ac_dir/$ac_prog$ac_exeext"; then + lt_cv_path_LD="$ac_dir/$ac_prog" + # Check to see if the program is GNU ld. I'd rather use --version, + # but apparently some variants of GNU ld only accept -v. + # Break only if it was the GNU/non-GNU ld that we prefer. + case `"$lt_cv_path_LD" -v 2>&1 &5 +echo "${ECHO_T}$LD" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi +test -z "$LD" && { { echo "$as_me:$LINENO: error: no acceptable ld found in \$PATH" >&5 +echo "$as_me: error: no acceptable ld found in \$PATH" >&2;} + { (exit 1); exit 1; }; } +echo "$as_me:$LINENO: checking if the linker ($LD) is GNU ld" >&5 +echo $ECHO_N "checking if the linker ($LD) is GNU ld... $ECHO_C" >&6 +if test "${lt_cv_prog_gnu_ld+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + # I'd rather use --version here, but apparently some GNU lds only accept -v. +case `$LD -v 2>&1 &5 +echo "${ECHO_T}$lt_cv_prog_gnu_ld" >&6 +with_gnu_ld=$lt_cv_prog_gnu_ld + + +echo "$as_me:$LINENO: checking for $LD option to reload object files" >&5 +echo $ECHO_N "checking for $LD option to reload object files... $ECHO_C" >&6 +if test "${lt_cv_ld_reload_flag+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + lt_cv_ld_reload_flag='-r' +fi +echo "$as_me:$LINENO: result: $lt_cv_ld_reload_flag" >&5 +echo "${ECHO_T}$lt_cv_ld_reload_flag" >&6 +reload_flag=$lt_cv_ld_reload_flag +case $reload_flag in +"" | " "*) ;; +*) reload_flag=" $reload_flag" ;; +esac +reload_cmds='$LD$reload_flag -o $output$reload_objs' +case $host_os in + darwin*) + if test "$GCC" = yes; then + reload_cmds='$LTCC $LTCFLAGS -nostdlib ${wl}-r -o $output$reload_objs' + else + reload_cmds='$LD$reload_flag -o $output$reload_objs' + fi + ;; +esac + +echo "$as_me:$LINENO: checking for BSD-compatible nm" >&5 +echo $ECHO_N "checking for BSD-compatible nm... $ECHO_C" >&6 +if test "${lt_cv_path_NM+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$NM"; then + # Let the user override the test. + lt_cv_path_NM="$NM" +else + lt_nm_to_check="${ac_tool_prefix}nm" + if test -n "$ac_tool_prefix" && test "$build" = "$host"; then + lt_nm_to_check="$lt_nm_to_check nm" + fi + for lt_tmp_nm in $lt_nm_to_check; do + lt_save_ifs="$IFS"; IFS=$PATH_SEPARATOR + for ac_dir in $PATH /usr/ccs/bin/elf /usr/ccs/bin /usr/ucb /bin; do + IFS="$lt_save_ifs" + test -z "$ac_dir" && ac_dir=. + tmp_nm="$ac_dir/$lt_tmp_nm" + if test -f "$tmp_nm" || test -f "$tmp_nm$ac_exeext" ; then + # Check to see if the nm accepts a BSD-compat flag. + # Adding the `sed 1q' prevents false positives on HP-UX, which says: + # nm: unknown option "B" ignored + # Tru64's nm complains that /dev/null is an invalid object file + case `"$tmp_nm" -B /dev/null 2>&1 | sed '1q'` in + */dev/null* | *'Invalid file or object type'*) + lt_cv_path_NM="$tmp_nm -B" + break + ;; + *) + case `"$tmp_nm" -p /dev/null 2>&1 | sed '1q'` in + */dev/null*) + lt_cv_path_NM="$tmp_nm -p" + break + ;; + *) + lt_cv_path_NM=${lt_cv_path_NM="$tmp_nm"} # keep the first match, but + continue # so that we can try to find one that supports BSD flags + ;; + esac + ;; + esac + fi + done + IFS="$lt_save_ifs" + done + test -z "$lt_cv_path_NM" && lt_cv_path_NM=nm +fi +fi +echo "$as_me:$LINENO: result: $lt_cv_path_NM" >&5 +echo "${ECHO_T}$lt_cv_path_NM" >&6 +NM="$lt_cv_path_NM" + +echo "$as_me:$LINENO: checking whether ln -s works" >&5 +echo $ECHO_N "checking whether ln -s works... $ECHO_C" >&6 +LN_S=$as_ln_s +if test "$LN_S" = "ln -s"; then + echo "$as_me:$LINENO: result: yes" >&5 +echo "${ECHO_T}yes" >&6 +else + echo "$as_me:$LINENO: result: no, using $LN_S" >&5 +echo "${ECHO_T}no, using $LN_S" >&6 +fi + +echo "$as_me:$LINENO: checking how to recognise dependent libraries" >&5 +echo $ECHO_N "checking how to recognise dependent libraries... $ECHO_C" >&6 +if test "${lt_cv_deplibs_check_method+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + lt_cv_file_magic_cmd='$MAGIC_CMD' +lt_cv_file_magic_test_file= +lt_cv_deplibs_check_method='unknown' +# Need to set the preceding variable on all platforms that support +# interlibrary dependencies. +# 'none' -- dependencies not supported. +# `unknown' -- same as none, but documents that we really don't know. +# 'pass_all' -- all dependencies passed with no checks. +# 'test_compile' -- check by making test program. +# 'file_magic [[regex]]' -- check by looking for files in library path +# which responds to the $file_magic_cmd with a given extended regex. +# If you have `file' or equivalent on your system and you're not sure +# whether `pass_all' will *always* work, you probably want this one. + +case $host_os in +aix4* | aix5*) + lt_cv_deplibs_check_method=pass_all + ;; + +beos*) + lt_cv_deplibs_check_method=pass_all + ;; + +bsdi[45]*) + lt_cv_deplibs_check_method='file_magic ELF [0-9][0-9]*-bit [ML]SB (shared object|dynamic lib)' + lt_cv_file_magic_cmd='/usr/bin/file -L' + lt_cv_file_magic_test_file=/shlib/libc.so + ;; + +cygwin*) + # func_win32_libid is a shell function defined in ltmain.sh + lt_cv_deplibs_check_method='file_magic ^x86 archive import|^x86 DLL' + lt_cv_file_magic_cmd='func_win32_libid' + ;; + +mingw* | pw32*) + # Base MSYS/MinGW do not provide the 'file' command needed by + # func_win32_libid shell function, so use a weaker test based on 'objdump'. + lt_cv_deplibs_check_method='file_magic file format pei*-i386(.*architecture: i386)?' + lt_cv_file_magic_cmd='$OBJDUMP -f' + ;; + +darwin* | rhapsody*) + lt_cv_deplibs_check_method=pass_all + ;; + +freebsd* | kfreebsd*-gnu | dragonfly*) + if echo __ELF__ | $CC -E - | grep __ELF__ > /dev/null; then + case $host_cpu in + i*86 ) + # Not sure whether the presence of OpenBSD here was a mistake. + # Let's accept both of them until this is cleared up. + lt_cv_deplibs_check_method='file_magic (FreeBSD|OpenBSD|DragonFly)/i[3-9]86 (compact )?demand paged shared library' + lt_cv_file_magic_cmd=/usr/bin/file + lt_cv_file_magic_test_file=`echo /usr/lib/libc.so.*` + ;; + esac + else + lt_cv_deplibs_check_method=pass_all + fi + ;; + +gnu*) + lt_cv_deplibs_check_method=pass_all + ;; + +hpux10.20* | hpux11*) + lt_cv_file_magic_cmd=/usr/bin/file + case $host_cpu in + ia64*) + lt_cv_deplibs_check_method='file_magic (s[0-9][0-9][0-9]|ELF-[0-9][0-9]) shared object file - IA64' + lt_cv_file_magic_test_file=/usr/lib/hpux32/libc.so + ;; + hppa*64*) + lt_cv_deplibs_check_method='file_magic (s[0-9][0-9][0-9]|ELF-[0-9][0-9]) shared object file - PA-RISC [0-9].[0-9]' + lt_cv_file_magic_test_file=/usr/lib/pa20_64/libc.sl + ;; + *) + lt_cv_deplibs_check_method='file_magic (s[0-9][0-9][0-9]|PA-RISC[0-9].[0-9]) shared library' + lt_cv_file_magic_test_file=/usr/lib/libc.sl + ;; + esac + ;; + +interix3*) + # PIC code is broken on Interix 3.x, that's why |\.a not |_pic\.a here + lt_cv_deplibs_check_method='match_pattern /lib[^/]+(\.so|\.a)$' + ;; + +irix5* | irix6* | nonstopux*) + case $LD in + *-32|*"-32 ") libmagic=32-bit;; + *-n32|*"-n32 ") libmagic=N32;; + *-64|*"-64 ") libmagic=64-bit;; + *) libmagic=never-match;; + esac + lt_cv_deplibs_check_method=pass_all + ;; + +# This must be Linux ELF. +linux*) + lt_cv_deplibs_check_method=pass_all + ;; + +netbsd*) + if echo __ELF__ | $CC -E - | grep __ELF__ > /dev/null; then + lt_cv_deplibs_check_method='match_pattern /lib[^/]+(\.so\.[0-9]+\.[0-9]+|_pic\.a)$' + else + lt_cv_deplibs_check_method='match_pattern /lib[^/]+(\.so|_pic\.a)$' + fi + ;; + +newos6*) + lt_cv_deplibs_check_method='file_magic ELF [0-9][0-9]*-bit [ML]SB (executable|dynamic lib)' + lt_cv_file_magic_cmd=/usr/bin/file + lt_cv_file_magic_test_file=/usr/lib/libnls.so + ;; + +nto-qnx*) + lt_cv_deplibs_check_method=unknown + ;; + +openbsd*) + if test -z "`echo __ELF__ | $CC -E - | grep __ELF__`" || test "$host_os-$host_cpu" = "openbsd2.8-powerpc"; then + lt_cv_deplibs_check_method='match_pattern /lib[^/]+(\.so\.[0-9]+\.[0-9]+|\.so|_pic\.a)$' + else + lt_cv_deplibs_check_method='match_pattern /lib[^/]+(\.so\.[0-9]+\.[0-9]+|_pic\.a)$' + fi + ;; + +osf3* | osf4* | osf5*) + lt_cv_deplibs_check_method=pass_all + ;; + +solaris*) + lt_cv_deplibs_check_method=pass_all + ;; + +sysv4 | sysv4.3*) + case $host_vendor in + motorola) + lt_cv_deplibs_check_method='file_magic ELF [0-9][0-9]*-bit [ML]SB (shared object|dynamic lib) M[0-9][0-9]* Version [0-9]' + lt_cv_file_magic_test_file=`echo /usr/lib/libc.so*` + ;; + ncr) + lt_cv_deplibs_check_method=pass_all + ;; + sequent) + lt_cv_file_magic_cmd='/bin/file' + lt_cv_deplibs_check_method='file_magic ELF [0-9][0-9]*-bit [LM]SB (shared object|dynamic lib )' + ;; + sni) + lt_cv_file_magic_cmd='/bin/file' + lt_cv_deplibs_check_method="file_magic ELF [0-9][0-9]*-bit [LM]SB dynamic lib" + lt_cv_file_magic_test_file=/lib/libc.so + ;; + siemens) + lt_cv_deplibs_check_method=pass_all + ;; + pc) + lt_cv_deplibs_check_method=pass_all + ;; + esac + ;; + +sysv5* | sco3.2v5* | sco5v6* | unixware* | OpenUNIX* | sysv4*uw2*) + lt_cv_deplibs_check_method=pass_all + ;; +esac + +fi +echo "$as_me:$LINENO: result: $lt_cv_deplibs_check_method" >&5 +echo "${ECHO_T}$lt_cv_deplibs_check_method" >&6 +file_magic_cmd=$lt_cv_file_magic_cmd +deplibs_check_method=$lt_cv_deplibs_check_method +test -z "$deplibs_check_method" && deplibs_check_method=unknown + + + + +# If no C compiler was specified, use CC. +LTCC=${LTCC-"$CC"} + +# If no C compiler flags were specified, use CFLAGS. +LTCFLAGS=${LTCFLAGS-"$CFLAGS"} + +# Allow CC to be a program name with arguments. +compiler=$CC + + +# Check whether --enable-libtool-lock or --disable-libtool-lock was given. +if test "${enable_libtool_lock+set}" = set; then + enableval="$enable_libtool_lock" + +fi; +test "x$enable_libtool_lock" != xno && enable_libtool_lock=yes + +# Some flags need to be propagated to the compiler or linker for good +# libtool support. +case $host in +ia64-*-hpux*) + # Find out which ABI we are using. + echo 'int i;' > conftest.$ac_ext + if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; then + case `/usr/bin/file conftest.$ac_objext` in + *ELF-32*) + HPUX_IA64_MODE="32" + ;; + *ELF-64*) + HPUX_IA64_MODE="64" + ;; + esac + fi + rm -rf conftest* + ;; +*-*-irix6*) + # Find out which ABI we are using. + echo '#line 3550 "configure"' > conftest.$ac_ext + if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; then + if test "$lt_cv_prog_gnu_ld" = yes; then + case `/usr/bin/file conftest.$ac_objext` in + *32-bit*) + LD="${LD-ld} -melf32bsmip" + ;; + *N32*) + LD="${LD-ld} -melf32bmipn32" + ;; + *64-bit*) + LD="${LD-ld} -melf64bmip" + ;; + esac + else + case `/usr/bin/file conftest.$ac_objext` in + *32-bit*) + LD="${LD-ld} -32" + ;; + *N32*) + LD="${LD-ld} -n32" + ;; + *64-bit*) + LD="${LD-ld} -64" + ;; + esac + fi + fi + rm -rf conftest* + ;; + +x86_64-*linux*|ppc*-*linux*|powerpc*-*linux*|s390*-*linux*|sparc*-*linux*) + # Find out which ABI we are using. + echo 'int i;' > conftest.$ac_ext + if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; then + case `/usr/bin/file conftest.o` in + *32-bit*) + case $host in + x86_64-*linux*) + LD="${LD-ld} -m elf_i386" + ;; + ppc64-*linux*|powerpc64-*linux*) + LD="${LD-ld} -m elf32ppclinux" + ;; + s390x-*linux*) + LD="${LD-ld} -m elf_s390" + ;; + sparc64-*linux*) + LD="${LD-ld} -m elf32_sparc" + ;; + esac + ;; + *64-bit*) + case $host in + x86_64-*linux*) + LD="${LD-ld} -m elf_x86_64" + ;; + ppc*-*linux*|powerpc*-*linux*) + LD="${LD-ld} -m elf64ppc" + ;; + s390*-*linux*) + LD="${LD-ld} -m elf64_s390" + ;; + sparc*-*linux*) + LD="${LD-ld} -m elf64_sparc" + ;; + esac + ;; + esac + fi + rm -rf conftest* + ;; + +*-*-sco3.2v5*) + # On SCO OpenServer 5, we need -belf to get full-featured binaries. + SAVE_CFLAGS="$CFLAGS" + CFLAGS="$CFLAGS -belf" + echo "$as_me:$LINENO: checking whether the C compiler needs -belf" >&5 +echo $ECHO_N "checking whether the C compiler needs -belf... $ECHO_C" >&6 +if test "${lt_cv_cc_needs_belf+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext conftest$ac_exeext +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest$ac_exeext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + lt_cv_cc_needs_belf=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +lt_cv_cc_needs_belf=no +fi +rm -f conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext + ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + +fi +echo "$as_me:$LINENO: result: $lt_cv_cc_needs_belf" >&5 +echo "${ECHO_T}$lt_cv_cc_needs_belf" >&6 + if test x"$lt_cv_cc_needs_belf" != x"yes"; then + # this is probably gcc 2.8.0, egcs 1.0 or newer; no need for -belf + CFLAGS="$SAVE_CFLAGS" + fi + ;; +sparc*-*solaris*) + # Find out which ABI we are using. + echo 'int i;' > conftest.$ac_ext + if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; then + case `/usr/bin/file conftest.o` in + *64-bit*) + case $lt_cv_prog_gnu_ld in + yes*) LD="${LD-ld} -m elf64_sparc" ;; + *) LD="${LD-ld} -64" ;; + esac + ;; + esac + fi + rm -rf conftest* + ;; + +*-*-cygwin* | *-*-mingw* | *-*-pw32*) + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}dlltool", so it can be a program name with args. +set dummy ${ac_tool_prefix}dlltool; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_DLLTOOL+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$DLLTOOL"; then + ac_cv_prog_DLLTOOL="$DLLTOOL" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_DLLTOOL="${ac_tool_prefix}dlltool" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + +fi +fi +DLLTOOL=$ac_cv_prog_DLLTOOL +if test -n "$DLLTOOL"; then + echo "$as_me:$LINENO: result: $DLLTOOL" >&5 +echo "${ECHO_T}$DLLTOOL" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + +fi +if test -z "$ac_cv_prog_DLLTOOL"; then + ac_ct_DLLTOOL=$DLLTOOL + # Extract the first word of "dlltool", so it can be a program name with args. +set dummy dlltool; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_ac_ct_DLLTOOL+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$ac_ct_DLLTOOL"; then + ac_cv_prog_ac_ct_DLLTOOL="$ac_ct_DLLTOOL" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_DLLTOOL="dlltool" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + + test -z "$ac_cv_prog_ac_ct_DLLTOOL" && ac_cv_prog_ac_ct_DLLTOOL="false" +fi +fi +ac_ct_DLLTOOL=$ac_cv_prog_ac_ct_DLLTOOL +if test -n "$ac_ct_DLLTOOL"; then + echo "$as_me:$LINENO: result: $ac_ct_DLLTOOL" >&5 +echo "${ECHO_T}$ac_ct_DLLTOOL" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + + DLLTOOL=$ac_ct_DLLTOOL +else + DLLTOOL="$ac_cv_prog_DLLTOOL" +fi + + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}as", so it can be a program name with args. +set dummy ${ac_tool_prefix}as; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_AS+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$AS"; then + ac_cv_prog_AS="$AS" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_AS="${ac_tool_prefix}as" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + +fi +fi +AS=$ac_cv_prog_AS +if test -n "$AS"; then + echo "$as_me:$LINENO: result: $AS" >&5 +echo "${ECHO_T}$AS" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + +fi +if test -z "$ac_cv_prog_AS"; then + ac_ct_AS=$AS + # Extract the first word of "as", so it can be a program name with args. +set dummy as; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_ac_ct_AS+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$ac_ct_AS"; then + ac_cv_prog_ac_ct_AS="$ac_ct_AS" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_AS="as" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + + test -z "$ac_cv_prog_ac_ct_AS" && ac_cv_prog_ac_ct_AS="false" +fi +fi +ac_ct_AS=$ac_cv_prog_ac_ct_AS +if test -n "$ac_ct_AS"; then + echo "$as_me:$LINENO: result: $ac_ct_AS" >&5 +echo "${ECHO_T}$ac_ct_AS" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + + AS=$ac_ct_AS +else + AS="$ac_cv_prog_AS" +fi + + if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}objdump", so it can be a program name with args. +set dummy ${ac_tool_prefix}objdump; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_OBJDUMP+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$OBJDUMP"; then + ac_cv_prog_OBJDUMP="$OBJDUMP" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_OBJDUMP="${ac_tool_prefix}objdump" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + +fi +fi +OBJDUMP=$ac_cv_prog_OBJDUMP +if test -n "$OBJDUMP"; then + echo "$as_me:$LINENO: result: $OBJDUMP" >&5 +echo "${ECHO_T}$OBJDUMP" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + +fi +if test -z "$ac_cv_prog_OBJDUMP"; then + ac_ct_OBJDUMP=$OBJDUMP + # Extract the first word of "objdump", so it can be a program name with args. +set dummy objdump; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_ac_ct_OBJDUMP+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$ac_ct_OBJDUMP"; then + ac_cv_prog_ac_ct_OBJDUMP="$ac_ct_OBJDUMP" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_OBJDUMP="objdump" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + + test -z "$ac_cv_prog_ac_ct_OBJDUMP" && ac_cv_prog_ac_ct_OBJDUMP="false" +fi +fi +ac_ct_OBJDUMP=$ac_cv_prog_ac_ct_OBJDUMP +if test -n "$ac_ct_OBJDUMP"; then + echo "$as_me:$LINENO: result: $ac_ct_OBJDUMP" >&5 +echo "${ECHO_T}$ac_ct_OBJDUMP" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + + OBJDUMP=$ac_ct_OBJDUMP +else + OBJDUMP="$ac_cv_prog_OBJDUMP" +fi + + ;; + +esac + +need_locks="$enable_libtool_lock" + + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu +echo "$as_me:$LINENO: checking how to run the C preprocessor" >&5 +echo $ECHO_N "checking how to run the C preprocessor... $ECHO_C" >&6 +# On Suns, sometimes $CPP names a directory. +if test -n "$CPP" && test -d "$CPP"; then + CPP= +fi +if test -z "$CPP"; then + if test "${ac_cv_prog_CPP+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + # Double quotes because CPP needs to be expanded + for CPP in "$CC -E" "$CC -E -traditional-cpp" "/lib/cpp" + do + ac_preproc_ok=false +for ac_c_preproc_warn_flag in '' yes +do + # Use a header file that comes with gcc, so configuring glibc + # with a fresh cross-compiler works. + # Prefer to if __STDC__ is defined, since + # exists even on freestanding compilers. + # On the NeXT, cc -E runs the code through the compiler's parser, + # not just through cpp. "Syntax error" is here to catch this case. + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#ifdef __STDC__ +# include +#else +# include +#endif + Syntax error +_ACEOF +if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 + (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } >/dev/null; then + if test -s conftest.err; then + ac_cpp_err=$ac_c_preproc_warn_flag + ac_cpp_err=$ac_cpp_err$ac_c_werror_flag + else + ac_cpp_err= + fi +else + ac_cpp_err=yes +fi +if test -z "$ac_cpp_err"; then + : +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + # Broken: fails on valid input. +continue +fi +rm -f conftest.err conftest.$ac_ext + + # OK, works on sane cases. Now check whether non-existent headers + # can be detected and how. + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#include +_ACEOF +if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 + (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } >/dev/null; then + if test -s conftest.err; then + ac_cpp_err=$ac_c_preproc_warn_flag + ac_cpp_err=$ac_cpp_err$ac_c_werror_flag + else + ac_cpp_err= + fi +else + ac_cpp_err=yes +fi +if test -z "$ac_cpp_err"; then + # Broken: success on invalid input. +continue +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + # Passes both tests. +ac_preproc_ok=: +break +fi +rm -f conftest.err conftest.$ac_ext + +done +# Because of `break', _AC_PREPROC_IFELSE's cleaning code was skipped. +rm -f conftest.err conftest.$ac_ext +if $ac_preproc_ok; then + break +fi + + done + ac_cv_prog_CPP=$CPP + +fi + CPP=$ac_cv_prog_CPP +else + ac_cv_prog_CPP=$CPP +fi +echo "$as_me:$LINENO: result: $CPP" >&5 +echo "${ECHO_T}$CPP" >&6 +ac_preproc_ok=false +for ac_c_preproc_warn_flag in '' yes +do + # Use a header file that comes with gcc, so configuring glibc + # with a fresh cross-compiler works. + # Prefer to if __STDC__ is defined, since + # exists even on freestanding compilers. + # On the NeXT, cc -E runs the code through the compiler's parser, + # not just through cpp. "Syntax error" is here to catch this case. + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#ifdef __STDC__ +# include +#else +# include +#endif + Syntax error +_ACEOF +if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 + (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } >/dev/null; then + if test -s conftest.err; then + ac_cpp_err=$ac_c_preproc_warn_flag + ac_cpp_err=$ac_cpp_err$ac_c_werror_flag + else + ac_cpp_err= + fi +else + ac_cpp_err=yes +fi +if test -z "$ac_cpp_err"; then + : +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + # Broken: fails on valid input. +continue +fi +rm -f conftest.err conftest.$ac_ext + + # OK, works on sane cases. Now check whether non-existent headers + # can be detected and how. + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#include +_ACEOF +if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 + (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } >/dev/null; then + if test -s conftest.err; then + ac_cpp_err=$ac_c_preproc_warn_flag + ac_cpp_err=$ac_cpp_err$ac_c_werror_flag + else + ac_cpp_err= + fi +else + ac_cpp_err=yes +fi +if test -z "$ac_cpp_err"; then + # Broken: success on invalid input. +continue +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + # Passes both tests. +ac_preproc_ok=: +break +fi +rm -f conftest.err conftest.$ac_ext + +done +# Because of `break', _AC_PREPROC_IFELSE's cleaning code was skipped. +rm -f conftest.err conftest.$ac_ext +if $ac_preproc_ok; then + : +else + { { echo "$as_me:$LINENO: error: C preprocessor \"$CPP\" fails sanity check +See \`config.log' for more details." >&5 +echo "$as_me: error: C preprocessor \"$CPP\" fails sanity check +See \`config.log' for more details." >&2;} + { (exit 1); exit 1; }; } +fi + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + + +echo "$as_me:$LINENO: checking for ANSI C header files" >&5 +echo $ECHO_N "checking for ANSI C header files... $ECHO_C" >&6 +if test "${ac_cv_header_stdc+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#include +#include +#include +#include + +int +main () +{ + + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_cv_header_stdc=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_cv_header_stdc=no +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext + +if test $ac_cv_header_stdc = yes; then + # SunOS 4.x string.h does not declare mem*, contrary to ANSI. + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#include + +_ACEOF +if (eval "$ac_cpp conftest.$ac_ext") 2>&5 | + $EGREP "memchr" >/dev/null 2>&1; then + : +else + ac_cv_header_stdc=no +fi +rm -f conftest* + +fi + +if test $ac_cv_header_stdc = yes; then + # ISC 2.0.2 stdlib.h does not declare free, contrary to ANSI. + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#include + +_ACEOF +if (eval "$ac_cpp conftest.$ac_ext") 2>&5 | + $EGREP "free" >/dev/null 2>&1; then + : +else + ac_cv_header_stdc=no +fi +rm -f conftest* + +fi + +if test $ac_cv_header_stdc = yes; then + # /bin/cc in Irix-4.0.5 gets non-ANSI ctype macros unless using -ansi. + if test "$cross_compiling" = yes; then + : +else + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#include +#if ((' ' & 0x0FF) == 0x020) +# define ISLOWER(c) ('a' <= (c) && (c) <= 'z') +# define TOUPPER(c) (ISLOWER(c) ? 'A' + ((c) - 'a') : (c)) +#else +# define ISLOWER(c) \ + (('a' <= (c) && (c) <= 'i') \ + || ('j' <= (c) && (c) <= 'r') \ + || ('s' <= (c) && (c) <= 'z')) +# define TOUPPER(c) (ISLOWER(c) ? ((c) | 0x40) : (c)) +#endif + +#define XOR(e, f) (((e) && !(f)) || (!(e) && (f))) +int +main () +{ + int i; + for (i = 0; i < 256; i++) + if (XOR (islower (i), ISLOWER (i)) + || toupper (i) != TOUPPER (i)) + exit(2); + exit (0); +} +_ACEOF +rm -f conftest$ac_exeext +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && { ac_try='./conftest$ac_exeext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + : +else + echo "$as_me: program exited with status $ac_status" >&5 +echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +( exit $ac_status ) +ac_cv_header_stdc=no +fi +rm -f core *.core gmon.out bb.out conftest$ac_exeext conftest.$ac_objext conftest.$ac_ext +fi +fi +fi +echo "$as_me:$LINENO: result: $ac_cv_header_stdc" >&5 +echo "${ECHO_T}$ac_cv_header_stdc" >&6 +if test $ac_cv_header_stdc = yes; then + +cat >>confdefs.h <<\_ACEOF +#define STDC_HEADERS 1 +_ACEOF + +fi + +# On IRIX 5.3, sys/types and inttypes.h are conflicting. + + + + + + + + + +for ac_header in sys/types.h sys/stat.h stdlib.h string.h memory.h strings.h \ + inttypes.h stdint.h unistd.h +do +as_ac_Header=`echo "ac_cv_header_$ac_header" | $as_tr_sh` +echo "$as_me:$LINENO: checking for $ac_header" >&5 +echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6 +if eval "test \"\${$as_ac_Header+set}\" = set"; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +$ac_includes_default + +#include <$ac_header> +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + eval "$as_ac_Header=yes" +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +eval "$as_ac_Header=no" +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext +fi +echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_Header'}'`" >&5 +echo "${ECHO_T}`eval echo '${'$as_ac_Header'}'`" >&6 +if test `eval echo '${'$as_ac_Header'}'` = yes; then + cat >>confdefs.h <<_ACEOF +#define `echo "HAVE_$ac_header" | $as_tr_cpp` 1 +_ACEOF + +fi + +done + + + +for ac_header in dlfcn.h +do +as_ac_Header=`echo "ac_cv_header_$ac_header" | $as_tr_sh` +if eval "test \"\${$as_ac_Header+set}\" = set"; then + echo "$as_me:$LINENO: checking for $ac_header" >&5 +echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6 +if eval "test \"\${$as_ac_Header+set}\" = set"; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +fi +echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_Header'}'`" >&5 +echo "${ECHO_T}`eval echo '${'$as_ac_Header'}'`" >&6 +else + # Is the header compilable? +echo "$as_me:$LINENO: checking $ac_header usability" >&5 +echo $ECHO_N "checking $ac_header usability... $ECHO_C" >&6 +cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +$ac_includes_default +#include <$ac_header> +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_header_compiler=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_header_compiler=no +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext +echo "$as_me:$LINENO: result: $ac_header_compiler" >&5 +echo "${ECHO_T}$ac_header_compiler" >&6 + +# Is the header present? +echo "$as_me:$LINENO: checking $ac_header presence" >&5 +echo $ECHO_N "checking $ac_header presence... $ECHO_C" >&6 +cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#include <$ac_header> +_ACEOF +if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 + (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } >/dev/null; then + if test -s conftest.err; then + ac_cpp_err=$ac_c_preproc_warn_flag + ac_cpp_err=$ac_cpp_err$ac_c_werror_flag + else + ac_cpp_err= + fi +else + ac_cpp_err=yes +fi +if test -z "$ac_cpp_err"; then + ac_header_preproc=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + ac_header_preproc=no +fi +rm -f conftest.err conftest.$ac_ext +echo "$as_me:$LINENO: result: $ac_header_preproc" >&5 +echo "${ECHO_T}$ac_header_preproc" >&6 + +# So? What about this header? +case $ac_header_compiler:$ac_header_preproc:$ac_c_preproc_warn_flag in + yes:no: ) + { echo "$as_me:$LINENO: WARNING: $ac_header: accepted by the compiler, rejected by the preprocessor!" >&5 +echo "$as_me: WARNING: $ac_header: accepted by the compiler, rejected by the preprocessor!" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: proceeding with the compiler's result" >&5 +echo "$as_me: WARNING: $ac_header: proceeding with the compiler's result" >&2;} + ac_header_preproc=yes + ;; + no:yes:* ) + { echo "$as_me:$LINENO: WARNING: $ac_header: present but cannot be compiled" >&5 +echo "$as_me: WARNING: $ac_header: present but cannot be compiled" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: check for missing prerequisite headers?" >&5 +echo "$as_me: WARNING: $ac_header: check for missing prerequisite headers?" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: see the Autoconf documentation" >&5 +echo "$as_me: WARNING: $ac_header: see the Autoconf documentation" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: section \"Present But Cannot Be Compiled\"" >&5 +echo "$as_me: WARNING: $ac_header: section \"Present But Cannot Be Compiled\"" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: proceeding with the preprocessor's result" >&5 +echo "$as_me: WARNING: $ac_header: proceeding with the preprocessor's result" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: in the future, the compiler will take precedence" >&5 +echo "$as_me: WARNING: $ac_header: in the future, the compiler will take precedence" >&2;} + ( + cat <<\_ASBOX +## ------------------------------------------ ## +## Report this to the AC_PACKAGE_NAME lists. ## +## ------------------------------------------ ## +_ASBOX + ) | + sed "s/^/$as_me: WARNING: /" >&2 + ;; +esac +echo "$as_me:$LINENO: checking for $ac_header" >&5 +echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6 +if eval "test \"\${$as_ac_Header+set}\" = set"; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + eval "$as_ac_Header=\$ac_header_preproc" +fi +echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_Header'}'`" >&5 +echo "${ECHO_T}`eval echo '${'$as_ac_Header'}'`" >&6 + +fi +if test `eval echo '${'$as_ac_Header'}'` = yes; then + cat >>confdefs.h <<_ACEOF +#define `echo "HAVE_$ac_header" | $as_tr_cpp` 1 +_ACEOF + +fi + +done + + + +if test -n "$CXX" && ( test "X$CXX" != "Xno" && + ( (test "X$CXX" = "Xg++" && `g++ -v >/dev/null 2>&1` ) || + (test "X$CXX" != "Xg++"))) ; then + ac_ext=cc +ac_cpp='$CXXCPP $CPPFLAGS' +ac_compile='$CXX -c $CXXFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CXX -o conftest$ac_exeext $CXXFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_cxx_compiler_gnu +echo "$as_me:$LINENO: checking how to run the C++ preprocessor" >&5 +echo $ECHO_N "checking how to run the C++ preprocessor... $ECHO_C" >&6 +if test -z "$CXXCPP"; then + if test "${ac_cv_prog_CXXCPP+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + # Double quotes because CXXCPP needs to be expanded + for CXXCPP in "$CXX -E" "/lib/cpp" + do + ac_preproc_ok=false +for ac_cxx_preproc_warn_flag in '' yes +do + # Use a header file that comes with gcc, so configuring glibc + # with a fresh cross-compiler works. + # Prefer to if __STDC__ is defined, since + # exists even on freestanding compilers. + # On the NeXT, cc -E runs the code through the compiler's parser, + # not just through cpp. "Syntax error" is here to catch this case. + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#ifdef __STDC__ +# include +#else +# include +#endif + Syntax error +_ACEOF +if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 + (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } >/dev/null; then + if test -s conftest.err; then + ac_cpp_err=$ac_cxx_preproc_warn_flag + ac_cpp_err=$ac_cpp_err$ac_cxx_werror_flag + else + ac_cpp_err= + fi +else + ac_cpp_err=yes +fi +if test -z "$ac_cpp_err"; then + : +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + # Broken: fails on valid input. +continue +fi +rm -f conftest.err conftest.$ac_ext + + # OK, works on sane cases. Now check whether non-existent headers + # can be detected and how. + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#include +_ACEOF +if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 + (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } >/dev/null; then + if test -s conftest.err; then + ac_cpp_err=$ac_cxx_preproc_warn_flag + ac_cpp_err=$ac_cpp_err$ac_cxx_werror_flag + else + ac_cpp_err= + fi +else + ac_cpp_err=yes +fi +if test -z "$ac_cpp_err"; then + # Broken: success on invalid input. +continue +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + # Passes both tests. +ac_preproc_ok=: +break +fi +rm -f conftest.err conftest.$ac_ext + +done +# Because of `break', _AC_PREPROC_IFELSE's cleaning code was skipped. +rm -f conftest.err conftest.$ac_ext +if $ac_preproc_ok; then + break +fi + + done + ac_cv_prog_CXXCPP=$CXXCPP + +fi + CXXCPP=$ac_cv_prog_CXXCPP +else + ac_cv_prog_CXXCPP=$CXXCPP +fi +echo "$as_me:$LINENO: result: $CXXCPP" >&5 +echo "${ECHO_T}$CXXCPP" >&6 +ac_preproc_ok=false +for ac_cxx_preproc_warn_flag in '' yes +do + # Use a header file that comes with gcc, so configuring glibc + # with a fresh cross-compiler works. + # Prefer to if __STDC__ is defined, since + # exists even on freestanding compilers. + # On the NeXT, cc -E runs the code through the compiler's parser, + # not just through cpp. "Syntax error" is here to catch this case. + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#ifdef __STDC__ +# include +#else +# include +#endif + Syntax error +_ACEOF +if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 + (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } >/dev/null; then + if test -s conftest.err; then + ac_cpp_err=$ac_cxx_preproc_warn_flag + ac_cpp_err=$ac_cpp_err$ac_cxx_werror_flag + else + ac_cpp_err= + fi +else + ac_cpp_err=yes +fi +if test -z "$ac_cpp_err"; then + : +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + # Broken: fails on valid input. +continue +fi +rm -f conftest.err conftest.$ac_ext + + # OK, works on sane cases. Now check whether non-existent headers + # can be detected and how. + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#include +_ACEOF +if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 + (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } >/dev/null; then + if test -s conftest.err; then + ac_cpp_err=$ac_cxx_preproc_warn_flag + ac_cpp_err=$ac_cpp_err$ac_cxx_werror_flag + else + ac_cpp_err= + fi +else + ac_cpp_err=yes +fi +if test -z "$ac_cpp_err"; then + # Broken: success on invalid input. +continue +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + # Passes both tests. +ac_preproc_ok=: +break +fi +rm -f conftest.err conftest.$ac_ext + +done +# Because of `break', _AC_PREPROC_IFELSE's cleaning code was skipped. +rm -f conftest.err conftest.$ac_ext +if $ac_preproc_ok; then + : +else + { { echo "$as_me:$LINENO: error: C++ preprocessor \"$CXXCPP\" fails sanity check +See \`config.log' for more details." >&5 +echo "$as_me: error: C++ preprocessor \"$CXXCPP\" fails sanity check +See \`config.log' for more details." >&2;} + { (exit 1); exit 1; }; } +fi + +ac_ext=cc +ac_cpp='$CXXCPP $CPPFLAGS' +ac_compile='$CXX -c $CXXFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CXX -o conftest$ac_exeext $CXXFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_cxx_compiler_gnu + +fi + + +ac_ext=f +ac_compile='$F77 -c $FFLAGS conftest.$ac_ext >&5' +ac_link='$F77 -o conftest$ac_exeext $FFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_f77_compiler_gnu +if test -n "$ac_tool_prefix"; then + for ac_prog in g77 f77 xlf frt pgf77 fort77 fl32 af77 f90 xlf90 pgf90 epcf90 f95 fort xlf95 ifc efc pgf95 lf95 gfortran + do + # Extract the first word of "$ac_tool_prefix$ac_prog", so it can be a program name with args. +set dummy $ac_tool_prefix$ac_prog; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_F77+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$F77"; then + ac_cv_prog_F77="$F77" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_F77="$ac_tool_prefix$ac_prog" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + +fi +fi +F77=$ac_cv_prog_F77 +if test -n "$F77"; then + echo "$as_me:$LINENO: result: $F77" >&5 +echo "${ECHO_T}$F77" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + + test -n "$F77" && break + done +fi +if test -z "$F77"; then + ac_ct_F77=$F77 + for ac_prog in g77 f77 xlf frt pgf77 fort77 fl32 af77 f90 xlf90 pgf90 epcf90 f95 fort xlf95 ifc efc pgf95 lf95 gfortran +do + # Extract the first word of "$ac_prog", so it can be a program name with args. +set dummy $ac_prog; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_ac_ct_F77+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$ac_ct_F77"; then + ac_cv_prog_ac_ct_F77="$ac_ct_F77" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_F77="$ac_prog" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + +fi +fi +ac_ct_F77=$ac_cv_prog_ac_ct_F77 +if test -n "$ac_ct_F77"; then + echo "$as_me:$LINENO: result: $ac_ct_F77" >&5 +echo "${ECHO_T}$ac_ct_F77" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + + test -n "$ac_ct_F77" && break +done + + F77=$ac_ct_F77 +fi + + +# Provide some information about the compiler. +echo "$as_me:4927:" \ + "checking for Fortran 77 compiler version" >&5 +ac_compiler=`set X $ac_compile; echo $2` +{ (eval echo "$as_me:$LINENO: \"$ac_compiler --version &5\"") >&5 + (eval $ac_compiler --version &5) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } +{ (eval echo "$as_me:$LINENO: \"$ac_compiler -v &5\"") >&5 + (eval $ac_compiler -v &5) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } +{ (eval echo "$as_me:$LINENO: \"$ac_compiler -V &5\"") >&5 + (eval $ac_compiler -V &5) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } +rm -f a.out + +# If we don't use `.F' as extension, the preprocessor is not run on the +# input file. (Note that this only needs to work for GNU compilers.) +ac_save_ext=$ac_ext +ac_ext=F +echo "$as_me:$LINENO: checking whether we are using the GNU Fortran 77 compiler" >&5 +echo $ECHO_N "checking whether we are using the GNU Fortran 77 compiler... $ECHO_C" >&6 +if test "${ac_cv_f77_compiler_gnu+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + cat >conftest.$ac_ext <<_ACEOF + program main +#ifndef __GNUC__ + choke me +#endif + + end +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_f77_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_compiler_gnu=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_compiler_gnu=no +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext +ac_cv_f77_compiler_gnu=$ac_compiler_gnu + +fi +echo "$as_me:$LINENO: result: $ac_cv_f77_compiler_gnu" >&5 +echo "${ECHO_T}$ac_cv_f77_compiler_gnu" >&6 +ac_ext=$ac_save_ext +ac_test_FFLAGS=${FFLAGS+set} +ac_save_FFLAGS=$FFLAGS +FFLAGS= +echo "$as_me:$LINENO: checking whether $F77 accepts -g" >&5 +echo $ECHO_N "checking whether $F77 accepts -g... $ECHO_C" >&6 +if test "${ac_cv_prog_f77_g+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + FFLAGS=-g +cat >conftest.$ac_ext <<_ACEOF + program main + + end +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_f77_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_cv_prog_f77_g=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_cv_prog_f77_g=no +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext + +fi +echo "$as_me:$LINENO: result: $ac_cv_prog_f77_g" >&5 +echo "${ECHO_T}$ac_cv_prog_f77_g" >&6 +if test "$ac_test_FFLAGS" = set; then + FFLAGS=$ac_save_FFLAGS +elif test $ac_cv_prog_f77_g = yes; then + if test "x$ac_cv_f77_compiler_gnu" = xyes; then + FFLAGS="-g -O2" + else + FFLAGS="-g" + fi +else + if test "x$ac_cv_f77_compiler_gnu" = xyes; then + FFLAGS="-O2" + else + FFLAGS= + fi +fi + +G77=`test $ac_compiler_gnu = yes && echo yes` +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + + + +# Autoconf 2.13's AC_OBJEXT and AC_EXEEXT macros only works for C compilers! + +# find the maximum length of command line arguments +echo "$as_me:$LINENO: checking the maximum length of command line arguments" >&5 +echo $ECHO_N "checking the maximum length of command line arguments... $ECHO_C" >&6 +if test "${lt_cv_sys_max_cmd_len+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + i=0 + teststring="ABCD" + + case $build_os in + msdosdjgpp*) + # On DJGPP, this test can blow up pretty badly due to problems in libc + # (any single argument exceeding 2000 bytes causes a buffer overrun + # during glob expansion). Even if it were fixed, the result of this + # check would be larger than it should be. + lt_cv_sys_max_cmd_len=12288; # 12K is about right + ;; + + gnu*) + # Under GNU Hurd, this test is not required because there is + # no limit to the length of command line arguments. + # Libtool will interpret -1 as no limit whatsoever + lt_cv_sys_max_cmd_len=-1; + ;; + + cygwin* | mingw*) + # On Win9x/ME, this test blows up -- it succeeds, but takes + # about 5 minutes as the teststring grows exponentially. + # Worse, since 9x/ME are not pre-emptively multitasking, + # you end up with a "frozen" computer, even though with patience + # the test eventually succeeds (with a max line length of 256k). + # Instead, let's just punt: use the minimum linelength reported by + # all of the supported platforms: 8192 (on NT/2K/XP). + lt_cv_sys_max_cmd_len=8192; + ;; + + amigaos*) + # On AmigaOS with pdksh, this test takes hours, literally. + # So we just punt and use a minimum line length of 8192. + lt_cv_sys_max_cmd_len=8192; + ;; + + netbsd* | freebsd* | openbsd* | darwin* | dragonfly*) + # This has been around since 386BSD, at least. Likely further. + if test -x /sbin/sysctl; then + lt_cv_sys_max_cmd_len=`/sbin/sysctl -n kern.argmax` + elif test -x /usr/sbin/sysctl; then + lt_cv_sys_max_cmd_len=`/usr/sbin/sysctl -n kern.argmax` + else + lt_cv_sys_max_cmd_len=65536 # usable default for all BSDs + fi + # And add a safety zone + lt_cv_sys_max_cmd_len=`expr $lt_cv_sys_max_cmd_len \/ 4` + lt_cv_sys_max_cmd_len=`expr $lt_cv_sys_max_cmd_len \* 3` + ;; + + interix*) + # We know the value 262144 and hardcode it with a safety zone (like BSD) + lt_cv_sys_max_cmd_len=196608 + ;; + + osf*) + # Dr. Hans Ekkehard Plesser reports seeing a kernel panic running configure + # due to this test when exec_disable_arg_limit is 1 on Tru64. It is not + # nice to cause kernel panics so lets avoid the loop below. + # First set a reasonable default. + lt_cv_sys_max_cmd_len=16384 + # + if test -x /sbin/sysconfig; then + case `/sbin/sysconfig -q proc exec_disable_arg_limit` in + *1*) lt_cv_sys_max_cmd_len=-1 ;; + esac + fi + ;; + sco3.2v5*) + lt_cv_sys_max_cmd_len=102400 + ;; + sysv5* | sco5v6* | sysv4.2uw2*) + kargmax=`grep ARG_MAX /etc/conf/cf.d/stune 2>/dev/null` + if test -n "$kargmax"; then + lt_cv_sys_max_cmd_len=`echo $kargmax | sed 's/.*[ ]//'` + else + lt_cv_sys_max_cmd_len=32768 + fi + ;; + *) + # If test is not a shell built-in, we'll probably end up computing a + # maximum length that is only half of the actual maximum length, but + # we can't tell. + SHELL=${SHELL-${CONFIG_SHELL-/bin/sh}} + while (test "X"`$SHELL $0 --fallback-echo "X$teststring" 2>/dev/null` \ + = "XX$teststring") >/dev/null 2>&1 && + new_result=`expr "X$teststring" : ".*" 2>&1` && + lt_cv_sys_max_cmd_len=$new_result && + test $i != 17 # 1/2 MB should be enough + do + i=`expr $i + 1` + teststring=$teststring$teststring + done + teststring= + # Add a significant safety factor because C++ compilers can tack on massive + # amounts of additional arguments before passing them to the linker. + # It appears as though 1/2 is a usable value. + lt_cv_sys_max_cmd_len=`expr $lt_cv_sys_max_cmd_len \/ 2` + ;; + esac + +fi + +if test -n $lt_cv_sys_max_cmd_len ; then + echo "$as_me:$LINENO: result: $lt_cv_sys_max_cmd_len" >&5 +echo "${ECHO_T}$lt_cv_sys_max_cmd_len" >&6 +else + echo "$as_me:$LINENO: result: none" >&5 +echo "${ECHO_T}none" >&6 +fi + + + + +# Check for command to grab the raw symbol name followed by C symbol from nm. +echo "$as_me:$LINENO: checking command to parse $NM output from $compiler object" >&5 +echo $ECHO_N "checking command to parse $NM output from $compiler object... $ECHO_C" >&6 +if test "${lt_cv_sys_global_symbol_pipe+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + +# These are sane defaults that work on at least a few old systems. +# [They come from Ultrix. What could be older than Ultrix?!! ;)] + +# Character class describing NM global symbol codes. +symcode='[BCDEGRST]' + +# Regexp to match symbols that can be accessed directly from C. +sympat='\([_A-Za-z][_A-Za-z0-9]*\)' + +# Transform an extracted symbol line into a proper C declaration +lt_cv_sys_global_symbol_to_cdecl="sed -n -e 's/^. .* \(.*\)$/extern int \1;/p'" + +# Transform an extracted symbol line into symbol name and symbol address +lt_cv_sys_global_symbol_to_c_name_address="sed -n -e 's/^: \([^ ]*\) $/ {\\\"\1\\\", (lt_ptr) 0},/p' -e 's/^$symcode \([^ ]*\) \([^ ]*\)$/ {\"\2\", (lt_ptr) \&\2},/p'" + +# Define system-specific variables. +case $host_os in +aix*) + symcode='[BCDT]' + ;; +cygwin* | mingw* | pw32*) + symcode='[ABCDGISTW]' + ;; +hpux*) # Its linker distinguishes data from code symbols + if test "$host_cpu" = ia64; then + symcode='[ABCDEGRST]' + fi + lt_cv_sys_global_symbol_to_cdecl="sed -n -e 's/^T .* \(.*\)$/extern int \1();/p' -e 's/^$symcode* .* \(.*\)$/extern char \1;/p'" + lt_cv_sys_global_symbol_to_c_name_address="sed -n -e 's/^: \([^ ]*\) $/ {\\\"\1\\\", (lt_ptr) 0},/p' -e 's/^$symcode* \([^ ]*\) \([^ ]*\)$/ {\"\2\", (lt_ptr) \&\2},/p'" + ;; +linux*) + if test "$host_cpu" = ia64; then + symcode='[ABCDGIRSTW]' + lt_cv_sys_global_symbol_to_cdecl="sed -n -e 's/^T .* \(.*\)$/extern int \1();/p' -e 's/^$symcode* .* \(.*\)$/extern char \1;/p'" + lt_cv_sys_global_symbol_to_c_name_address="sed -n -e 's/^: \([^ ]*\) $/ {\\\"\1\\\", (lt_ptr) 0},/p' -e 's/^$symcode* \([^ ]*\) \([^ ]*\)$/ {\"\2\", (lt_ptr) \&\2},/p'" + fi + ;; +irix* | nonstopux*) + symcode='[BCDEGRST]' + ;; +osf*) + symcode='[BCDEGQRST]' + ;; +solaris*) + symcode='[BDRT]' + ;; +sco3.2v5*) + symcode='[DT]' + ;; +sysv4.2uw2*) + symcode='[DT]' + ;; +sysv5* | sco5v6* | unixware* | OpenUNIX*) + symcode='[ABDT]' + ;; +sysv4) + symcode='[DFNSTU]' + ;; +esac + +# Handle CRLF in mingw tool chain +opt_cr= +case $build_os in +mingw*) + opt_cr=`echo 'x\{0,1\}' | tr x '\015'` # option cr in regexp + ;; +esac + +# If we're using GNU nm, then use its standard symbol codes. +case `$NM -V 2>&1` in +*GNU* | *'with BFD'*) + symcode='[ABCDGIRSTW]' ;; +esac + +# Try without a prefix undercore, then with it. +for ac_symprfx in "" "_"; do + + # Transform symcode, sympat, and symprfx into a raw symbol and a C symbol. + symxfrm="\\1 $ac_symprfx\\2 \\2" + + # Write the raw and C identifiers. + lt_cv_sys_global_symbol_pipe="sed -n -e 's/^.*[ ]\($symcode$symcode*\)[ ][ ]*$ac_symprfx$sympat$opt_cr$/$symxfrm/p'" + + # Check to see that the pipe works correctly. + pipe_works=no + + rm -f conftest* + cat > conftest.$ac_ext <&5 + (eval $ac_compile) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; then + # Now try to grab the symbols. + nlist=conftest.nm + if { (eval echo "$as_me:$LINENO: \"$NM conftest.$ac_objext \| $lt_cv_sys_global_symbol_pipe \> $nlist\"") >&5 + (eval $NM conftest.$ac_objext \| $lt_cv_sys_global_symbol_pipe \> $nlist) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && test -s "$nlist"; then + # Try sorting and uniquifying the output. + if sort "$nlist" | uniq > "$nlist"T; then + mv -f "$nlist"T "$nlist" + else + rm -f "$nlist"T + fi + + # Make sure that we snagged all the symbols we need. + if grep ' nm_test_var$' "$nlist" >/dev/null; then + if grep ' nm_test_func$' "$nlist" >/dev/null; then + cat < conftest.$ac_ext +#ifdef __cplusplus +extern "C" { +#endif + +EOF + # Now generate the symbol file. + eval "$lt_cv_sys_global_symbol_to_cdecl"' < "$nlist" | grep -v main >> conftest.$ac_ext' + + cat <> conftest.$ac_ext +#if defined (__STDC__) && __STDC__ +# define lt_ptr_t void * +#else +# define lt_ptr_t char * +# define const +#endif + +/* The mapping between symbol names and symbols. */ +const struct { + const char *name; + lt_ptr_t address; +} +lt_preloaded_symbols[] = +{ +EOF + $SED "s/^$symcode$symcode* \(.*\) \(.*\)$/ {\"\2\", (lt_ptr_t) \&\2},/" < "$nlist" | grep -v main >> conftest.$ac_ext + cat <<\EOF >> conftest.$ac_ext + {0, (lt_ptr_t) 0} +}; + +#ifdef __cplusplus +} +#endif +EOF + # Now try linking the two files. + mv conftest.$ac_objext conftstm.$ac_objext + lt_save_LIBS="$LIBS" + lt_save_CFLAGS="$CFLAGS" + LIBS="conftstm.$ac_objext" + CFLAGS="$CFLAGS$lt_prog_compiler_no_builtin_flag" + if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && test -s conftest${ac_exeext}; then + pipe_works=yes + fi + LIBS="$lt_save_LIBS" + CFLAGS="$lt_save_CFLAGS" + else + echo "cannot find nm_test_func in $nlist" >&5 + fi + else + echo "cannot find nm_test_var in $nlist" >&5 + fi + else + echo "cannot run $lt_cv_sys_global_symbol_pipe" >&5 + fi + else + echo "$progname: failed program was:" >&5 + cat conftest.$ac_ext >&5 + fi + rm -f conftest* conftst* + + # Do not use the global_symbol_pipe unless it works. + if test "$pipe_works" = yes; then + break + else + lt_cv_sys_global_symbol_pipe= + fi +done + +fi + +if test -z "$lt_cv_sys_global_symbol_pipe"; then + lt_cv_sys_global_symbol_to_cdecl= +fi +if test -z "$lt_cv_sys_global_symbol_pipe$lt_cv_sys_global_symbol_to_cdecl"; then + echo "$as_me:$LINENO: result: failed" >&5 +echo "${ECHO_T}failed" >&6 +else + echo "$as_me:$LINENO: result: ok" >&5 +echo "${ECHO_T}ok" >&6 +fi + +echo "$as_me:$LINENO: checking for objdir" >&5 +echo $ECHO_N "checking for objdir... $ECHO_C" >&6 +if test "${lt_cv_objdir+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + rm -f .libs 2>/dev/null +mkdir .libs 2>/dev/null +if test -d .libs; then + lt_cv_objdir=.libs +else + # MS-DOS does not allow filenames that begin with a dot. + lt_cv_objdir=_libs +fi +rmdir .libs 2>/dev/null +fi +echo "$as_me:$LINENO: result: $lt_cv_objdir" >&5 +echo "${ECHO_T}$lt_cv_objdir" >&6 +objdir=$lt_cv_objdir + + + + + +case $host_os in +aix3*) + # AIX sometimes has problems with the GCC collect2 program. For some + # reason, if we set the COLLECT_NAMES environment variable, the problems + # vanish in a puff of smoke. + if test "X${COLLECT_NAMES+set}" != Xset; then + COLLECT_NAMES= + export COLLECT_NAMES + fi + ;; +esac + +# Sed substitution that helps us do robust quoting. It backslashifies +# metacharacters that are still active within double-quoted strings. +Xsed='sed -e 1s/^X//' +sed_quote_subst='s/\([\\"\\`$\\\\]\)/\\\1/g' + +# Same as above, but do not quote variable references. +double_quote_subst='s/\([\\"\\`\\\\]\)/\\\1/g' + +# Sed substitution to delay expansion of an escaped shell variable in a +# double_quote_subst'ed string. +delay_variable_subst='s/\\\\\\\\\\\$/\\\\\\$/g' + +# Sed substitution to avoid accidental globbing in evaled expressions +no_glob_subst='s/\*/\\\*/g' + +# Constants: +rm="rm -f" + +# Global variables: +default_ofile=libtool +can_build_shared=yes + +# All known linkers require a `.a' archive for static linking (except MSVC, +# which needs '.lib'). +libext=a +ltmain="$ac_aux_dir/ltmain.sh" +ofile="$default_ofile" +with_gnu_ld="$lt_cv_prog_gnu_ld" + +if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}ar", so it can be a program name with args. +set dummy ${ac_tool_prefix}ar; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_AR+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$AR"; then + ac_cv_prog_AR="$AR" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_AR="${ac_tool_prefix}ar" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + +fi +fi +AR=$ac_cv_prog_AR +if test -n "$AR"; then + echo "$as_me:$LINENO: result: $AR" >&5 +echo "${ECHO_T}$AR" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + +fi +if test -z "$ac_cv_prog_AR"; then + ac_ct_AR=$AR + # Extract the first word of "ar", so it can be a program name with args. +set dummy ar; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_ac_ct_AR+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$ac_ct_AR"; then + ac_cv_prog_ac_ct_AR="$ac_ct_AR" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_AR="ar" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + + test -z "$ac_cv_prog_ac_ct_AR" && ac_cv_prog_ac_ct_AR="false" +fi +fi +ac_ct_AR=$ac_cv_prog_ac_ct_AR +if test -n "$ac_ct_AR"; then + echo "$as_me:$LINENO: result: $ac_ct_AR" >&5 +echo "${ECHO_T}$ac_ct_AR" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + + AR=$ac_ct_AR +else + AR="$ac_cv_prog_AR" +fi + +if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}ranlib", so it can be a program name with args. +set dummy ${ac_tool_prefix}ranlib; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_RANLIB+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$RANLIB"; then + ac_cv_prog_RANLIB="$RANLIB" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_RANLIB="${ac_tool_prefix}ranlib" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + +fi +fi +RANLIB=$ac_cv_prog_RANLIB +if test -n "$RANLIB"; then + echo "$as_me:$LINENO: result: $RANLIB" >&5 +echo "${ECHO_T}$RANLIB" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + +fi +if test -z "$ac_cv_prog_RANLIB"; then + ac_ct_RANLIB=$RANLIB + # Extract the first word of "ranlib", so it can be a program name with args. +set dummy ranlib; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_ac_ct_RANLIB+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$ac_ct_RANLIB"; then + ac_cv_prog_ac_ct_RANLIB="$ac_ct_RANLIB" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_RANLIB="ranlib" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + + test -z "$ac_cv_prog_ac_ct_RANLIB" && ac_cv_prog_ac_ct_RANLIB=":" +fi +fi +ac_ct_RANLIB=$ac_cv_prog_ac_ct_RANLIB +if test -n "$ac_ct_RANLIB"; then + echo "$as_me:$LINENO: result: $ac_ct_RANLIB" >&5 +echo "${ECHO_T}$ac_ct_RANLIB" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + + RANLIB=$ac_ct_RANLIB +else + RANLIB="$ac_cv_prog_RANLIB" +fi + +if test -n "$ac_tool_prefix"; then + # Extract the first word of "${ac_tool_prefix}strip", so it can be a program name with args. +set dummy ${ac_tool_prefix}strip; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_STRIP+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$STRIP"; then + ac_cv_prog_STRIP="$STRIP" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_STRIP="${ac_tool_prefix}strip" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + +fi +fi +STRIP=$ac_cv_prog_STRIP +if test -n "$STRIP"; then + echo "$as_me:$LINENO: result: $STRIP" >&5 +echo "${ECHO_T}$STRIP" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + +fi +if test -z "$ac_cv_prog_STRIP"; then + ac_ct_STRIP=$STRIP + # Extract the first word of "strip", so it can be a program name with args. +set dummy strip; ac_word=$2 +echo "$as_me:$LINENO: checking for $ac_word" >&5 +echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 +if test "${ac_cv_prog_ac_ct_STRIP+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -n "$ac_ct_STRIP"; then + ac_cv_prog_ac_ct_STRIP="$ac_ct_STRIP" # Let the user override the test. +else +as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for ac_exec_ext in '' $ac_executable_extensions; do + if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then + ac_cv_prog_ac_ct_STRIP="strip" + echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 + break 2 + fi +done +done + + test -z "$ac_cv_prog_ac_ct_STRIP" && ac_cv_prog_ac_ct_STRIP=":" +fi +fi +ac_ct_STRIP=$ac_cv_prog_ac_ct_STRIP +if test -n "$ac_ct_STRIP"; then + echo "$as_me:$LINENO: result: $ac_ct_STRIP" >&5 +echo "${ECHO_T}$ac_ct_STRIP" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + + STRIP=$ac_ct_STRIP +else + STRIP="$ac_cv_prog_STRIP" +fi + + +old_CC="$CC" +old_CFLAGS="$CFLAGS" + +# Set sane defaults for various variables +test -z "$AR" && AR=ar +test -z "$AR_FLAGS" && AR_FLAGS=cru +test -z "$AS" && AS=as +test -z "$CC" && CC=cc +test -z "$LTCC" && LTCC=$CC +test -z "$LTCFLAGS" && LTCFLAGS=$CFLAGS +test -z "$DLLTOOL" && DLLTOOL=dlltool +test -z "$LD" && LD=ld +test -z "$LN_S" && LN_S="ln -s" +test -z "$MAGIC_CMD" && MAGIC_CMD=file +test -z "$NM" && NM=nm +test -z "$SED" && SED=sed +test -z "$OBJDUMP" && OBJDUMP=objdump +test -z "$RANLIB" && RANLIB=: +test -z "$STRIP" && STRIP=: +test -z "$ac_objext" && ac_objext=o + +# Determine commands to create old-style static archives. +old_archive_cmds='$AR $AR_FLAGS $oldlib$oldobjs$old_deplibs' +old_postinstall_cmds='chmod 644 $oldlib' +old_postuninstall_cmds= + +if test -n "$RANLIB"; then + case $host_os in + openbsd*) + old_postinstall_cmds="$old_postinstall_cmds~\$RANLIB -t \$oldlib" + ;; + *) + old_postinstall_cmds="$old_postinstall_cmds~\$RANLIB \$oldlib" + ;; + esac + old_archive_cmds="$old_archive_cmds~\$RANLIB \$oldlib" +fi + +for cc_temp in $compiler""; do + case $cc_temp in + compile | *[\\/]compile | ccache | *[\\/]ccache ) ;; + distcc | *[\\/]distcc | purify | *[\\/]purify ) ;; + \-*) ;; + *) break;; + esac +done +cc_basename=`$echo "X$cc_temp" | $Xsed -e 's%.*/%%' -e "s%^$host_alias-%%"` + + +# Only perform the check for file, if the check method requires it +case $deplibs_check_method in +file_magic*) + if test "$file_magic_cmd" = '$MAGIC_CMD'; then + echo "$as_me:$LINENO: checking for ${ac_tool_prefix}file" >&5 +echo $ECHO_N "checking for ${ac_tool_prefix}file... $ECHO_C" >&6 +if test "${lt_cv_path_MAGIC_CMD+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + case $MAGIC_CMD in +[\\/*] | ?:[\\/]*) + lt_cv_path_MAGIC_CMD="$MAGIC_CMD" # Let the user override the test with a path. + ;; +*) + lt_save_MAGIC_CMD="$MAGIC_CMD" + lt_save_ifs="$IFS"; IFS=$PATH_SEPARATOR + ac_dummy="/usr/bin$PATH_SEPARATOR$PATH" + for ac_dir in $ac_dummy; do + IFS="$lt_save_ifs" + test -z "$ac_dir" && ac_dir=. + if test -f $ac_dir/${ac_tool_prefix}file; then + lt_cv_path_MAGIC_CMD="$ac_dir/${ac_tool_prefix}file" + if test -n "$file_magic_test_file"; then + case $deplibs_check_method in + "file_magic "*) + file_magic_regex=`expr "$deplibs_check_method" : "file_magic \(.*\)"` + MAGIC_CMD="$lt_cv_path_MAGIC_CMD" + if eval $file_magic_cmd \$file_magic_test_file 2> /dev/null | + $EGREP "$file_magic_regex" > /dev/null; then + : + else + cat <&2 + +*** Warning: the command libtool uses to detect shared libraries, +*** $file_magic_cmd, produces output that libtool cannot recognize. +*** The result is that libtool may fail to recognize shared libraries +*** as such. This will affect the creation of libtool libraries that +*** depend on shared libraries, but programs linked with such libtool +*** libraries will work regardless of this problem. Nevertheless, you +*** may want to report the problem to your system manager and/or to +*** bug-libtool@gnu.org + +EOF + fi ;; + esac + fi + break + fi + done + IFS="$lt_save_ifs" + MAGIC_CMD="$lt_save_MAGIC_CMD" + ;; +esac +fi + +MAGIC_CMD="$lt_cv_path_MAGIC_CMD" +if test -n "$MAGIC_CMD"; then + echo "$as_me:$LINENO: result: $MAGIC_CMD" >&5 +echo "${ECHO_T}$MAGIC_CMD" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + +if test -z "$lt_cv_path_MAGIC_CMD"; then + if test -n "$ac_tool_prefix"; then + echo "$as_me:$LINENO: checking for file" >&5 +echo $ECHO_N "checking for file... $ECHO_C" >&6 +if test "${lt_cv_path_MAGIC_CMD+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + case $MAGIC_CMD in +[\\/*] | ?:[\\/]*) + lt_cv_path_MAGIC_CMD="$MAGIC_CMD" # Let the user override the test with a path. + ;; +*) + lt_save_MAGIC_CMD="$MAGIC_CMD" + lt_save_ifs="$IFS"; IFS=$PATH_SEPARATOR + ac_dummy="/usr/bin$PATH_SEPARATOR$PATH" + for ac_dir in $ac_dummy; do + IFS="$lt_save_ifs" + test -z "$ac_dir" && ac_dir=. + if test -f $ac_dir/file; then + lt_cv_path_MAGIC_CMD="$ac_dir/file" + if test -n "$file_magic_test_file"; then + case $deplibs_check_method in + "file_magic "*) + file_magic_regex=`expr "$deplibs_check_method" : "file_magic \(.*\)"` + MAGIC_CMD="$lt_cv_path_MAGIC_CMD" + if eval $file_magic_cmd \$file_magic_test_file 2> /dev/null | + $EGREP "$file_magic_regex" > /dev/null; then + : + else + cat <&2 + +*** Warning: the command libtool uses to detect shared libraries, +*** $file_magic_cmd, produces output that libtool cannot recognize. +*** The result is that libtool may fail to recognize shared libraries +*** as such. This will affect the creation of libtool libraries that +*** depend on shared libraries, but programs linked with such libtool +*** libraries will work regardless of this problem. Nevertheless, you +*** may want to report the problem to your system manager and/or to +*** bug-libtool@gnu.org + +EOF + fi ;; + esac + fi + break + fi + done + IFS="$lt_save_ifs" + MAGIC_CMD="$lt_save_MAGIC_CMD" + ;; +esac +fi + +MAGIC_CMD="$lt_cv_path_MAGIC_CMD" +if test -n "$MAGIC_CMD"; then + echo "$as_me:$LINENO: result: $MAGIC_CMD" >&5 +echo "${ECHO_T}$MAGIC_CMD" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + + else + MAGIC_CMD=: + fi +fi + + fi + ;; +esac + +enable_dlopen=no +enable_win32_dll=yes + +# Check whether --enable-libtool-lock or --disable-libtool-lock was given. +if test "${enable_libtool_lock+set}" = set; then + enableval="$enable_libtool_lock" + +fi; +test "x$enable_libtool_lock" != xno && enable_libtool_lock=yes + + +# Check whether --with-pic or --without-pic was given. +if test "${with_pic+set}" = set; then + withval="$with_pic" + pic_mode="$withval" +else + pic_mode=default +fi; +test -z "$pic_mode" && pic_mode=default + +# Check if we have a version mismatch between libtool.m4 and ltmain.sh. +# +# Note: This should be in AC_LIBTOOL_SETUP, _after_ $ltmain have been defined. +# We also should do it _before_ AC_LIBTOOL_LANG_C_CONFIG that actually +# calls AC_LIBTOOL_CONFIG and creates libtool. +# +echo "$as_me:$LINENO: checking for correct ltmain.sh version" >&5 +echo $ECHO_N "checking for correct ltmain.sh version... $ECHO_C" >&6 +if test "x$ltmain" = "x" ; then + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 + { { echo "$as_me:$LINENO: error: + +*** [Gentoo] sanity check failed! *** +*** \$ltmain is not defined, please check the patch for consistency! *** +" >&5 +echo "$as_me: error: + +*** [Gentoo] sanity check failed! *** +*** \$ltmain is not defined, please check the patch for consistency! *** +" >&2;} + { (exit 1); exit 1; }; } +fi +gentoo_lt_version="1.5.22" +gentoo_ltmain_version=`sed -n '/^[ ]*VERSION=/{s/^[ ]*VERSION=//;p;q;}' "$ltmain"` +if test "x$gentoo_lt_version" != "x$gentoo_ltmain_version" ; then + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 + { { echo "$as_me:$LINENO: error: + +*** [Gentoo] sanity check failed! *** +*** libtool.m4 and ltmain.sh have a version mismatch! *** +*** (libtool.m4 = $gentoo_lt_version, ltmain.sh = $gentoo_ltmain_version) *** + +Please run: + + libtoolize --copy --force + +if appropriate, please contact the maintainer of this +package (or your distribution) for help. +" >&5 +echo "$as_me: error: + +*** [Gentoo] sanity check failed! *** +*** libtool.m4 and ltmain.sh have a version mismatch! *** +*** (libtool.m4 = $gentoo_lt_version, ltmain.sh = $gentoo_ltmain_version) *** + +Please run: + + libtoolize --copy --force + +if appropriate, please contact the maintainer of this +package (or your distribution) for help. +" >&2;} + { (exit 1); exit 1; }; } +else + echo "$as_me:$LINENO: result: yes" >&5 +echo "${ECHO_T}yes" >&6 +fi + + +# Use C for the default configuration in the libtool script +tagname= +lt_save_CC="$CC" +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + + +# Source file extension for C test sources. +ac_ext=c + +# Object file extension for compiled C test sources. +objext=o +objext=$objext + +# Code to be used in simple compile tests +lt_simple_compile_test_code="int some_variable = 0;\n" + +# Code to be used in simple link tests +lt_simple_link_test_code='int main(){return(0);}\n' + + +# If no C compiler was specified, use CC. +LTCC=${LTCC-"$CC"} + +# If no C compiler flags were specified, use CFLAGS. +LTCFLAGS=${LTCFLAGS-"$CFLAGS"} + +# Allow CC to be a program name with arguments. +compiler=$CC + + +# save warnings/boilerplate of simple test code +ac_outfile=conftest.$ac_objext +printf "$lt_simple_compile_test_code" >conftest.$ac_ext +eval "$ac_compile" 2>&1 >/dev/null | $SED '/^$/d; /^ *+/d' >conftest.err +_lt_compiler_boilerplate=`cat conftest.err` +$rm conftest* + +ac_outfile=conftest.$ac_objext +printf "$lt_simple_link_test_code" >conftest.$ac_ext +eval "$ac_link" 2>&1 >/dev/null | $SED '/^$/d; /^ *+/d' >conftest.err +_lt_linker_boilerplate=`cat conftest.err` +$rm conftest* + + + +lt_prog_compiler_no_builtin_flag= + +if test "$GCC" = yes; then + lt_prog_compiler_no_builtin_flag=' -fno-builtin' + + +echo "$as_me:$LINENO: checking if $compiler supports -fno-rtti -fno-exceptions" >&5 +echo $ECHO_N "checking if $compiler supports -fno-rtti -fno-exceptions... $ECHO_C" >&6 +if test "${lt_cv_prog_compiler_rtti_exceptions+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + lt_cv_prog_compiler_rtti_exceptions=no + ac_outfile=conftest.$ac_objext + printf "$lt_simple_compile_test_code" > conftest.$ac_ext + lt_compiler_flag="-fno-rtti -fno-exceptions" + # Insert the option either (1) after the last *FLAGS variable, or + # (2) before a word containing "conftest.", or (3) at the end. + # Note that $ac_compile itself does not contain backslashes and begins + # with a dollar sign (not a hyphen), so the echo should work correctly. + # The option is referenced via a variable to avoid confusing sed. + lt_compile=`echo "$ac_compile" | $SED \ + -e 's:.*FLAGS}\{0,1\} :&$lt_compiler_flag :; t' \ + -e 's: [^ ]*conftest\.: $lt_compiler_flag&:; t' \ + -e 's:$: $lt_compiler_flag:'` + (eval echo "\"\$as_me:6051: $lt_compile\"" >&5) + (eval "$lt_compile" 2>conftest.err) + ac_status=$? + cat conftest.err >&5 + echo "$as_me:6055: \$? = $ac_status" >&5 + if (exit $ac_status) && test -s "$ac_outfile"; then + # The compiler can only warn and ignore the option if not recognized + # So say no if there are warnings other than the usual output. + $echo "X$_lt_compiler_boilerplate" | $Xsed -e '/^$/d' >conftest.exp + $SED '/^$/d; /^ *+/d' conftest.err >conftest.er2 + if test ! -s conftest.er2 || diff conftest.exp conftest.er2 >/dev/null; then + lt_cv_prog_compiler_rtti_exceptions=yes + fi + fi + $rm conftest* + +fi +echo "$as_me:$LINENO: result: $lt_cv_prog_compiler_rtti_exceptions" >&5 +echo "${ECHO_T}$lt_cv_prog_compiler_rtti_exceptions" >&6 + +if test x"$lt_cv_prog_compiler_rtti_exceptions" = xyes; then + lt_prog_compiler_no_builtin_flag="$lt_prog_compiler_no_builtin_flag -fno-rtti -fno-exceptions" +else + : +fi + +fi + +lt_prog_compiler_wl= +lt_prog_compiler_pic= +lt_prog_compiler_static= + +echo "$as_me:$LINENO: checking for $compiler option to produce PIC" >&5 +echo $ECHO_N "checking for $compiler option to produce PIC... $ECHO_C" >&6 + + if test "$GCC" = yes; then + lt_prog_compiler_wl='-Wl,' + lt_prog_compiler_static='-static' + + case $host_os in + aix*) + # All AIX code is PIC. + if test "$host_cpu" = ia64; then + # AIX 5 now supports IA64 processor + lt_prog_compiler_static='-Bstatic' + fi + ;; + + amigaos*) + # FIXME: we need at least 68020 code to build shared libraries, but + # adding the `-m68020' flag to GCC prevents building anything better, + # like `-m68040'. + lt_prog_compiler_pic='-m68020 -resident32 -malways-restore-a4' + ;; + + beos* | cygwin* | irix5* | irix6* | nonstopux* | osf3* | osf4* | osf5*) + # PIC is the default for these OSes. + ;; + + mingw* | pw32* | os2*) + # This hack is so that the source file can tell whether it is being + # built for inclusion in a dll (and should export symbols for example). + lt_prog_compiler_pic='-DDLL_EXPORT' + ;; + + darwin* | rhapsody*) + # PIC is the default on this platform + # Common symbols not allowed in MH_DYLIB files + lt_prog_compiler_pic='-fno-common' + ;; + + interix3*) + # Interix 3.x gcc -fpic/-fPIC options generate broken code. + # Instead, we relocate shared libraries at runtime. + ;; + + msdosdjgpp*) + # Just because we use GCC doesn't mean we suddenly get shared libraries + # on systems that don't support them. + lt_prog_compiler_can_build_shared=no + enable_shared=no + ;; + + sysv4*MP*) + if test -d /usr/nec; then + lt_prog_compiler_pic=-Kconform_pic + fi + ;; + + hpux*) + # PIC is the default for IA64 HP-UX and 64-bit HP-UX, but + # not for PA HP-UX. + case $host_cpu in + hppa*64*|ia64*) + # +Z the default + ;; + *) + lt_prog_compiler_pic='-fPIC' + ;; + esac + ;; + + *) + lt_prog_compiler_pic='-fPIC' + ;; + esac + else + # PORTME Check for flag to pass linker flags through the system compiler. + case $host_os in + aix*) + lt_prog_compiler_wl='-Wl,' + if test "$host_cpu" = ia64; then + # AIX 5 now supports IA64 processor + lt_prog_compiler_static='-Bstatic' + else + lt_prog_compiler_static='-bnso -bI:/lib/syscalls.exp' + fi + ;; + darwin*) + # PIC is the default on this platform + # Common symbols not allowed in MH_DYLIB files + case $cc_basename in + xlc*) + lt_prog_compiler_pic='-qnocommon' + lt_prog_compiler_wl='-Wl,' + ;; + esac + ;; + + mingw* | pw32* | os2*) + # This hack is so that the source file can tell whether it is being + # built for inclusion in a dll (and should export symbols for example). + lt_prog_compiler_pic='-DDLL_EXPORT' + ;; + + hpux9* | hpux10* | hpux11*) + lt_prog_compiler_wl='-Wl,' + # PIC is the default for IA64 HP-UX and 64-bit HP-UX, but + # not for PA HP-UX. + case $host_cpu in + hppa*64*|ia64*) + # +Z the default + ;; + *) + lt_prog_compiler_pic='+Z' + ;; + esac + # Is there a better lt_prog_compiler_static that works with the bundled CC? + lt_prog_compiler_static='${wl}-a ${wl}archive' + ;; + + irix5* | irix6* | nonstopux*) + lt_prog_compiler_wl='-Wl,' + # PIC (with -KPIC) is the default. + lt_prog_compiler_static='-non_shared' + ;; + + newsos6) + lt_prog_compiler_pic='-KPIC' + lt_prog_compiler_static='-Bstatic' + ;; + + linux*) + case $cc_basename in + icc* | ecc*) + lt_prog_compiler_wl='-Wl,' + lt_prog_compiler_pic='-KPIC' + lt_prog_compiler_static='-static' + ;; + pgcc* | pgf77* | pgf90* | pgf95*) + # Portland Group compilers (*not* the Pentium gcc compiler, + # which looks to be a dead project) + lt_prog_compiler_wl='-Wl,' + lt_prog_compiler_pic='-fpic' + lt_prog_compiler_static='-Bstatic' + ;; + ccc*) + lt_prog_compiler_wl='-Wl,' + # All Alpha code is PIC. + lt_prog_compiler_static='-non_shared' + ;; + esac + ;; + + osf3* | osf4* | osf5*) + lt_prog_compiler_wl='-Wl,' + # All OSF/1 code is PIC. + lt_prog_compiler_static='-non_shared' + ;; + + solaris*) + lt_prog_compiler_pic='-KPIC' + lt_prog_compiler_static='-Bstatic' + case $cc_basename in + f77* | f90* | f95*) + lt_prog_compiler_wl='-Qoption ld ';; + *) + lt_prog_compiler_wl='-Wl,';; + esac + ;; + + sunos4*) + lt_prog_compiler_wl='-Qoption ld ' + lt_prog_compiler_pic='-PIC' + lt_prog_compiler_static='-Bstatic' + ;; + + sysv4 | sysv4.2uw2* | sysv4.3*) + lt_prog_compiler_wl='-Wl,' + lt_prog_compiler_pic='-KPIC' + lt_prog_compiler_static='-Bstatic' + ;; + + sysv4*MP*) + if test -d /usr/nec ;then + lt_prog_compiler_pic='-Kconform_pic' + lt_prog_compiler_static='-Bstatic' + fi + ;; + + sysv5* | unixware* | sco3.2v5* | sco5v6* | OpenUNIX*) + lt_prog_compiler_wl='-Wl,' + lt_prog_compiler_pic='-KPIC' + lt_prog_compiler_static='-Bstatic' + ;; + + unicos*) + lt_prog_compiler_wl='-Wl,' + lt_prog_compiler_can_build_shared=no + ;; + + uts4*) + lt_prog_compiler_pic='-pic' + lt_prog_compiler_static='-Bstatic' + ;; + + *) + lt_prog_compiler_can_build_shared=no + ;; + esac + fi + +echo "$as_me:$LINENO: result: $lt_prog_compiler_pic" >&5 +echo "${ECHO_T}$lt_prog_compiler_pic" >&6 + +# +# Check to make sure the PIC flag actually works. +# +if test -n "$lt_prog_compiler_pic"; then + +echo "$as_me:$LINENO: checking if $compiler PIC flag $lt_prog_compiler_pic works" >&5 +echo $ECHO_N "checking if $compiler PIC flag $lt_prog_compiler_pic works... $ECHO_C" >&6 +if test "${lt_prog_compiler_pic_works+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + lt_prog_compiler_pic_works=no + ac_outfile=conftest.$ac_objext + printf "$lt_simple_compile_test_code" > conftest.$ac_ext + lt_compiler_flag="$lt_prog_compiler_pic -DPIC" + # Insert the option either (1) after the last *FLAGS variable, or + # (2) before a word containing "conftest.", or (3) at the end. + # Note that $ac_compile itself does not contain backslashes and begins + # with a dollar sign (not a hyphen), so the echo should work correctly. + # The option is referenced via a variable to avoid confusing sed. + lt_compile=`echo "$ac_compile" | $SED \ + -e 's:.*FLAGS}\{0,1\} :&$lt_compiler_flag :; t' \ + -e 's: [^ ]*conftest\.: $lt_compiler_flag&:; t' \ + -e 's:$: $lt_compiler_flag:'` + (eval echo "\"\$as_me:6319: $lt_compile\"" >&5) + (eval "$lt_compile" 2>conftest.err) + ac_status=$? + cat conftest.err >&5 + echo "$as_me:6323: \$? = $ac_status" >&5 + if (exit $ac_status) && test -s "$ac_outfile"; then + # The compiler can only warn and ignore the option if not recognized + # So say no if there are warnings other than the usual output. + $echo "X$_lt_compiler_boilerplate" | $Xsed -e '/^$/d' >conftest.exp + $SED '/^$/d; /^ *+/d' conftest.err >conftest.er2 + if test ! -s conftest.er2 || diff conftest.exp conftest.er2 >/dev/null; then + lt_prog_compiler_pic_works=yes + fi + fi + $rm conftest* + +fi +echo "$as_me:$LINENO: result: $lt_prog_compiler_pic_works" >&5 +echo "${ECHO_T}$lt_prog_compiler_pic_works" >&6 + +if test x"$lt_prog_compiler_pic_works" = xyes; then + case $lt_prog_compiler_pic in + "" | " "*) ;; + *) lt_prog_compiler_pic=" $lt_prog_compiler_pic" ;; + esac +else + lt_prog_compiler_pic= + lt_prog_compiler_can_build_shared=no +fi + +fi +case $host_os in + # For platforms which do not support PIC, -DPIC is meaningless: + *djgpp*) + lt_prog_compiler_pic= + ;; + *) + lt_prog_compiler_pic="$lt_prog_compiler_pic -DPIC" + ;; +esac + +# +# Check to make sure the static flag actually works. +# +wl=$lt_prog_compiler_wl eval lt_tmp_static_flag=\"$lt_prog_compiler_static\" +echo "$as_me:$LINENO: checking if $compiler static flag $lt_tmp_static_flag works" >&5 +echo $ECHO_N "checking if $compiler static flag $lt_tmp_static_flag works... $ECHO_C" >&6 +if test "${lt_prog_compiler_static_works+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + lt_prog_compiler_static_works=no + save_LDFLAGS="$LDFLAGS" + LDFLAGS="$LDFLAGS $lt_tmp_static_flag" + printf "$lt_simple_link_test_code" > conftest.$ac_ext + if (eval $ac_link 2>conftest.err) && test -s conftest$ac_exeext; then + # The linker can only warn and ignore the option if not recognized + # So say no if there are warnings + if test -s conftest.err; then + # Append any errors to the config.log. + cat conftest.err 1>&5 + $echo "X$_lt_linker_boilerplate" | $Xsed -e '/^$/d' > conftest.exp + $SED '/^$/d; /^ *+/d' conftest.err >conftest.er2 + if diff conftest.exp conftest.er2 >/dev/null; then + lt_prog_compiler_static_works=yes + fi + else + lt_prog_compiler_static_works=yes + fi + fi + $rm conftest* + LDFLAGS="$save_LDFLAGS" + +fi +echo "$as_me:$LINENO: result: $lt_prog_compiler_static_works" >&5 +echo "${ECHO_T}$lt_prog_compiler_static_works" >&6 + +if test x"$lt_prog_compiler_static_works" = xyes; then + : +else + lt_prog_compiler_static= +fi + + +echo "$as_me:$LINENO: checking if $compiler supports -c -o file.$ac_objext" >&5 +echo $ECHO_N "checking if $compiler supports -c -o file.$ac_objext... $ECHO_C" >&6 +if test "${lt_cv_prog_compiler_c_o+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + lt_cv_prog_compiler_c_o=no + $rm -r conftest 2>/dev/null + mkdir conftest + cd conftest + mkdir out + printf "$lt_simple_compile_test_code" > conftest.$ac_ext + + lt_compiler_flag="-o out/conftest2.$ac_objext" + # Insert the option either (1) after the last *FLAGS variable, or + # (2) before a word containing "conftest.", or (3) at the end. + # Note that $ac_compile itself does not contain backslashes and begins + # with a dollar sign (not a hyphen), so the echo should work correctly. + lt_compile=`echo "$ac_compile" | $SED \ + -e 's:.*FLAGS}\{0,1\} :&$lt_compiler_flag :; t' \ + -e 's: [^ ]*conftest\.: $lt_compiler_flag&:; t' \ + -e 's:$: $lt_compiler_flag:'` + (eval echo "\"\$as_me:6423: $lt_compile\"" >&5) + (eval "$lt_compile" 2>out/conftest.err) + ac_status=$? + cat out/conftest.err >&5 + echo "$as_me:6427: \$? = $ac_status" >&5 + if (exit $ac_status) && test -s out/conftest2.$ac_objext + then + # The compiler can only warn and ignore the option if not recognized + # So say no if there are warnings + $echo "X$_lt_compiler_boilerplate" | $Xsed -e '/^$/d' > out/conftest.exp + $SED '/^$/d; /^ *+/d' out/conftest.err >out/conftest.er2 + if test ! -s out/conftest.er2 || diff out/conftest.exp out/conftest.er2 >/dev/null; then + lt_cv_prog_compiler_c_o=yes + fi + fi + chmod u+w . 2>&5 + $rm conftest* + # SGI C++ compiler will create directory out/ii_files/ for + # template instantiation + test -d out/ii_files && $rm out/ii_files/* && rmdir out/ii_files + $rm out/* && rmdir out + cd .. + rmdir conftest + $rm conftest* + +fi +echo "$as_me:$LINENO: result: $lt_cv_prog_compiler_c_o" >&5 +echo "${ECHO_T}$lt_cv_prog_compiler_c_o" >&6 + + +hard_links="nottested" +if test "$lt_cv_prog_compiler_c_o" = no && test "$need_locks" != no; then + # do not overwrite the value of need_locks provided by the user + echo "$as_me:$LINENO: checking if we can lock with hard links" >&5 +echo $ECHO_N "checking if we can lock with hard links... $ECHO_C" >&6 + hard_links=yes + $rm conftest* + ln conftest.a conftest.b 2>/dev/null && hard_links=no + touch conftest.a + ln conftest.a conftest.b 2>&5 || hard_links=no + ln conftest.a conftest.b 2>/dev/null && hard_links=no + echo "$as_me:$LINENO: result: $hard_links" >&5 +echo "${ECHO_T}$hard_links" >&6 + if test "$hard_links" = no; then + { echo "$as_me:$LINENO: WARNING: \`$CC' does not support \`-c -o', so \`make -j' may be unsafe" >&5 +echo "$as_me: WARNING: \`$CC' does not support \`-c -o', so \`make -j' may be unsafe" >&2;} + need_locks=warn + fi +else + need_locks=no +fi + +echo "$as_me:$LINENO: checking whether the $compiler linker ($LD) supports shared libraries" >&5 +echo $ECHO_N "checking whether the $compiler linker ($LD) supports shared libraries... $ECHO_C" >&6 + + runpath_var= + allow_undefined_flag= + enable_shared_with_static_runtimes=no + archive_cmds= + archive_expsym_cmds= + old_archive_From_new_cmds= + old_archive_from_expsyms_cmds= + export_dynamic_flag_spec= + whole_archive_flag_spec= + thread_safe_flag_spec= + hardcode_libdir_flag_spec= + hardcode_libdir_flag_spec_ld= + hardcode_libdir_separator= + hardcode_direct=no + hardcode_minus_L=no + hardcode_shlibpath_var=unsupported + link_all_deplibs=unknown + hardcode_automatic=no + module_cmds= + module_expsym_cmds= + always_export_symbols=no + export_symbols_cmds='$NM $libobjs $convenience | $global_symbol_pipe | $SED '\''s/.* //'\'' | sort | uniq > $export_symbols' + # include_expsyms should be a list of space-separated symbols to be *always* + # included in the symbol list + include_expsyms= + # exclude_expsyms can be an extended regexp of symbols to exclude + # it will be wrapped by ` (' and `)$', so one must not match beginning or + # end of line. Example: `a|bc|.*d.*' will exclude the symbols `a' and `bc', + # as well as any symbol that contains `d'. + exclude_expsyms="_GLOBAL_OFFSET_TABLE_" + # Although _GLOBAL_OFFSET_TABLE_ is a valid symbol C name, most a.out + # platforms (ab)use it in PIC code, but their linkers get confused if + # the symbol is explicitly referenced. Since portable code cannot + # rely on this symbol name, it's probably fine to never include it in + # preloaded symbol tables. + extract_expsyms_cmds= + # Just being paranoid about ensuring that cc_basename is set. + for cc_temp in $compiler""; do + case $cc_temp in + compile | *[\\/]compile | ccache | *[\\/]ccache ) ;; + distcc | *[\\/]distcc | purify | *[\\/]purify ) ;; + \-*) ;; + *) break;; + esac +done +cc_basename=`$echo "X$cc_temp" | $Xsed -e 's%.*/%%' -e "s%^$host_alias-%%"` + + case $host_os in + cygwin* | mingw* | pw32*) + # FIXME: the MSVC++ port hasn't been tested in a loooong time + # When not using gcc, we currently assume that we are using + # Microsoft Visual C++. + if test "$GCC" != yes; then + with_gnu_ld=no + fi + ;; + interix*) + # we just hope/assume this is gcc and not c89 (= MSVC++) + with_gnu_ld=yes + ;; + openbsd*) + with_gnu_ld=no + ;; + esac + + ld_shlibs=yes + if test "$with_gnu_ld" = yes; then + # If archive_cmds runs LD, not CC, wlarc should be empty + wlarc='${wl}' + + # Set some defaults for GNU ld with shared library support. These + # are reset later if shared libraries are not supported. Putting them + # here allows them to be overridden if necessary. + runpath_var=LD_RUN_PATH + hardcode_libdir_flag_spec='${wl}--rpath ${wl}$libdir' + export_dynamic_flag_spec='${wl}--export-dynamic' + # ancient GNU ld didn't support --whole-archive et. al. + if $LD --help 2>&1 | grep 'no-whole-archive' > /dev/null; then + whole_archive_flag_spec="$wlarc"'--whole-archive$convenience '"$wlarc"'--no-whole-archive' + else + whole_archive_flag_spec= + fi + supports_anon_versioning=no + case `$LD -v 2>/dev/null` in + *\ [01].* | *\ 2.[0-9].* | *\ 2.10.*) ;; # catch versions < 2.11 + *\ 2.11.93.0.2\ *) supports_anon_versioning=yes ;; # RH7.3 ... + *\ 2.11.92.0.12\ *) supports_anon_versioning=yes ;; # Mandrake 8.2 ... + *\ 2.11.*) ;; # other 2.11 versions + *) supports_anon_versioning=yes ;; + esac + + # See if GNU ld supports shared libraries. + case $host_os in + aix3* | aix4* | aix5*) + # On AIX/PPC, the GNU linker is very broken + if test "$host_cpu" != ia64; then + ld_shlibs=no + cat <&2 + +*** Warning: the GNU linker, at least up to release 2.9.1, is reported +*** to be unable to reliably create shared libraries on AIX. +*** Therefore, libtool is disabling shared libraries support. If you +*** really care for shared libraries, you may want to modify your PATH +*** so that a non-GNU linker is found, and then restart. + +EOF + fi + ;; + + amigaos*) + archive_cmds='$rm $output_objdir/a2ixlibrary.data~$echo "#define NAME $libname" > $output_objdir/a2ixlibrary.data~$echo "#define LIBRARY_ID 1" >> $output_objdir/a2ixlibrary.data~$echo "#define VERSION $major" >> $output_objdir/a2ixlibrary.data~$echo "#define REVISION $revision" >> $output_objdir/a2ixlibrary.data~$AR $AR_FLAGS $lib $libobjs~$RANLIB $lib~(cd $output_objdir && a2ixlibrary -32)' + hardcode_libdir_flag_spec='-L$libdir' + hardcode_minus_L=yes + + # Samuel A. Falvo II reports + # that the semantics of dynamic libraries on AmigaOS, at least up + # to version 4, is to share data among multiple programs linked + # with the same dynamic library. Since this doesn't match the + # behavior of shared libraries on other platforms, we can't use + # them. + ld_shlibs=no + ;; + + beos*) + if $LD --help 2>&1 | grep ': supported targets:.* elf' > /dev/null; then + allow_undefined_flag=unsupported + # Joseph Beckenbach says some releases of gcc + # support --undefined. This deserves some investigation. FIXME + archive_cmds='$CC -nostart $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + else + ld_shlibs=no + fi + ;; + + cygwin* | mingw* | pw32*) + # _LT_AC_TAGVAR(hardcode_libdir_flag_spec, ) is actually meaningless, + # as there is no search path for DLLs. + hardcode_libdir_flag_spec='-L$libdir' + allow_undefined_flag=unsupported + always_export_symbols=no + enable_shared_with_static_runtimes=yes + export_symbols_cmds='$NM $libobjs $convenience | $global_symbol_pipe | $SED -e '\''/^[BCDGRS] /s/.* \([^ ]*\)/\1 DATA/'\'' | $SED -e '\''/^[AITW] /s/.* //'\'' | sort | uniq > $export_symbols' + + if $LD --help 2>&1 | grep 'auto-import' > /dev/null; then + archive_cmds='$CC -shared $libobjs $deplibs $compiler_flags -o $output_objdir/$soname ${wl}--enable-auto-image-base -Xlinker --out-implib -Xlinker $lib' + # If the export-symbols file already is a .def file (1st line + # is EXPORTS), use it as is; otherwise, prepend... + archive_expsym_cmds='if test "x`$SED 1q $export_symbols`" = xEXPORTS; then + cp $export_symbols $output_objdir/$soname.def; + else + echo EXPORTS > $output_objdir/$soname.def; + cat $export_symbols >> $output_objdir/$soname.def; + fi~ + $CC -shared $output_objdir/$soname.def $libobjs $deplibs $compiler_flags -o $output_objdir/$soname ${wl}--enable-auto-image-base -Xlinker --out-implib -Xlinker $lib' + else + ld_shlibs=no + fi + ;; + + interix3*) + hardcode_direct=no + hardcode_shlibpath_var=no + hardcode_libdir_flag_spec='${wl}-rpath,$libdir' + export_dynamic_flag_spec='${wl}-E' + # Hack: On Interix 3.x, we cannot compile PIC because of a broken gcc. + # Instead, shared libraries are loaded at an image base (0x10000000 by + # default) and relocated if they conflict, which is a slow very memory + # consuming and fragmenting process. To avoid this, we pick a random, + # 256 KiB-aligned image base between 0x50000000 and 0x6FFC0000 at link + # time. Moving up from 0x10000000 also allows more sbrk(2) space. + archive_cmds='$CC -shared $pic_flag $libobjs $deplibs $compiler_flags ${wl}-h,$soname ${wl}--image-base,`expr ${RANDOM-$$} % 4096 / 2 \* 262144 + 1342177280` -o $lib' + archive_expsym_cmds='sed "s,^,_," $export_symbols >$output_objdir/$soname.expsym~$CC -shared $pic_flag $libobjs $deplibs $compiler_flags ${wl}-h,$soname ${wl}--retain-symbols-file,$output_objdir/$soname.expsym ${wl}--image-base,`expr ${RANDOM-$$} % 4096 / 2 \* 262144 + 1342177280` -o $lib' + ;; + + linux*) + if $LD --help 2>&1 | grep ': supported targets:.* elf' > /dev/null; then + tmp_addflag= + case $cc_basename,$host_cpu in + pgcc*) # Portland Group C compiler + whole_archive_flag_spec='${wl}--whole-archive`for conv in $convenience\"\"; do test -n \"$conv\" && new_convenience=\"$new_convenience,$conv\"; done; $echo \"$new_convenience\"` ${wl}--no-whole-archive' + tmp_addflag=' $pic_flag' + ;; + pgf77* | pgf90* | pgf95*) # Portland Group f77 and f90 compilers + whole_archive_flag_spec='${wl}--whole-archive`for conv in $convenience\"\"; do test -n \"$conv\" && new_convenience=\"$new_convenience,$conv\"; done; $echo \"$new_convenience\"` ${wl}--no-whole-archive' + tmp_addflag=' $pic_flag -Mnomain' ;; + ecc*,ia64* | icc*,ia64*) # Intel C compiler on ia64 + tmp_addflag=' -i_dynamic' ;; + efc*,ia64* | ifort*,ia64*) # Intel Fortran compiler on ia64 + tmp_addflag=' -i_dynamic -nofor_main' ;; + ifc* | ifort*) # Intel Fortran compiler + tmp_addflag=' -nofor_main' ;; + esac + archive_cmds='$CC -shared'"$tmp_addflag"' $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + + if test $supports_anon_versioning = yes; then + archive_expsym_cmds='$echo "{ global:" > $output_objdir/$libname.ver~ + cat $export_symbols | sed -e "s/\(.*\)/\1;/" >> $output_objdir/$libname.ver~ + $echo "local: *; };" >> $output_objdir/$libname.ver~ + $CC -shared'"$tmp_addflag"' $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-version-script ${wl}$output_objdir/$libname.ver -o $lib' + fi + else + ld_shlibs=no + fi + ;; + + netbsd*) + if echo __ELF__ | $CC -E - | grep __ELF__ >/dev/null; then + archive_cmds='$LD -Bshareable $libobjs $deplibs $linker_flags -o $lib' + wlarc= + else + archive_cmds='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + archive_expsym_cmds='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-retain-symbols-file $wl$export_symbols -o $lib' + fi + ;; + + solaris*) + if $LD -v 2>&1 | grep 'BFD 2\.8' > /dev/null; then + ld_shlibs=no + cat <&2 + +*** Warning: The releases 2.8.* of the GNU linker cannot reliably +*** create shared libraries on Solaris systems. Therefore, libtool +*** is disabling shared libraries support. We urge you to upgrade GNU +*** binutils to release 2.9.1 or newer. Another option is to modify +*** your PATH or compiler configuration so that the native linker is +*** used, and then restart. + +EOF + elif $LD --help 2>&1 | grep ': supported targets:.* elf' > /dev/null; then + archive_cmds='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + archive_expsym_cmds='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-retain-symbols-file $wl$export_symbols -o $lib' + else + ld_shlibs=no + fi + ;; + + sysv5* | sco3.2v5* | sco5v6* | unixware* | OpenUNIX*) + case `$LD -v 2>&1` in + *\ [01].* | *\ 2.[0-9].* | *\ 2.1[0-5].*) + ld_shlibs=no + cat <<_LT_EOF 1>&2 + +*** Warning: Releases of the GNU linker prior to 2.16.91.0.3 can not +*** reliably create shared libraries on SCO systems. Therefore, libtool +*** is disabling shared libraries support. We urge you to upgrade GNU +*** binutils to release 2.16.91.0.3 or newer. Another option is to modify +*** your PATH or compiler configuration so that the native linker is +*** used, and then restart. + +_LT_EOF + ;; + *) + if $LD --help 2>&1 | grep ': supported targets:.* elf' > /dev/null; then + hardcode_libdir_flag_spec='`test -z "$SCOABSPATH" && echo ${wl}-rpath,$libdir`' + archive_cmds='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname,\${SCOABSPATH:+${install_libdir}/}$soname -o $lib' + archive_expsym_cmds='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname,\${SCOABSPATH:+${install_libdir}/}$soname,-retain-symbols-file,$export_symbols -o $lib' + else + ld_shlibs=no + fi + ;; + esac + ;; + + sunos4*) + archive_cmds='$LD -assert pure-text -Bshareable -o $lib $libobjs $deplibs $linker_flags' + wlarc= + hardcode_direct=yes + hardcode_shlibpath_var=no + ;; + + *) + if $LD --help 2>&1 | grep ': supported targets:.* elf' > /dev/null; then + archive_cmds='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + archive_expsym_cmds='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-retain-symbols-file $wl$export_symbols -o $lib' + else + ld_shlibs=no + fi + ;; + esac + + if test "$ld_shlibs" = no; then + runpath_var= + hardcode_libdir_flag_spec= + export_dynamic_flag_spec= + whole_archive_flag_spec= + fi + else + # PORTME fill in a description of your system's linker (not GNU ld) + case $host_os in + aix3*) + allow_undefined_flag=unsupported + always_export_symbols=yes + archive_expsym_cmds='$LD -o $output_objdir/$soname $libobjs $deplibs $linker_flags -bE:$export_symbols -T512 -H512 -bM:SRE~$AR $AR_FLAGS $lib $output_objdir/$soname' + # Note: this linker hardcodes the directories in LIBPATH if there + # are no directories specified by -L. + hardcode_minus_L=yes + if test "$GCC" = yes && test -z "$lt_prog_compiler_static"; then + # Neither direct hardcoding nor static linking is supported with a + # broken collect2. + hardcode_direct=unsupported + fi + ;; + + aix4* | aix5*) + if test "$host_cpu" = ia64; then + # On IA64, the linker does run time linking by default, so we don't + # have to do anything special. + aix_use_runtimelinking=no + exp_sym_flag='-Bexport' + no_entry_flag="" + else + # If we're using GNU nm, then we don't want the "-C" option. + # -C means demangle to AIX nm, but means don't demangle with GNU nm + if $NM -V 2>&1 | grep 'GNU' > /dev/null; then + export_symbols_cmds='$NM -Bpg $libobjs $convenience | awk '\''{ if (((\$2 == "T") || (\$2 == "D") || (\$2 == "B")) && (substr(\$3,1,1) != ".")) { print \$3 } }'\'' | sort -u > $export_symbols' + else + export_symbols_cmds='$NM -BCpg $libobjs $convenience | awk '\''{ if (((\$2 == "T") || (\$2 == "D") || (\$2 == "B")) && (substr(\$3,1,1) != ".")) { print \$3 } }'\'' | sort -u > $export_symbols' + fi + aix_use_runtimelinking=no + + # Test if we are trying to use run time linking or normal + # AIX style linking. If -brtl is somewhere in LDFLAGS, we + # need to do runtime linking. + case $host_os in aix4.[23]|aix4.[23].*|aix5*) + for ld_flag in $LDFLAGS; do + if (test $ld_flag = "-brtl" || test $ld_flag = "-Wl,-brtl"); then + aix_use_runtimelinking=yes + break + fi + done + ;; + esac + + exp_sym_flag='-bexport' + no_entry_flag='-bnoentry' + fi + + # When large executables or shared objects are built, AIX ld can + # have problems creating the table of contents. If linking a library + # or program results in "error TOC overflow" add -mminimal-toc to + # CXXFLAGS/CFLAGS for g++/gcc. In the cases where that is not + # enough to fix the problem, add -Wl,-bbigtoc to LDFLAGS. + + archive_cmds='' + hardcode_direct=yes + hardcode_libdir_separator=':' + link_all_deplibs=yes + + if test "$GCC" = yes; then + case $host_os in aix4.[012]|aix4.[012].*) + # We only want to do this on AIX 4.2 and lower, the check + # below for broken collect2 doesn't work under 4.3+ + collect2name=`${CC} -print-prog-name=collect2` + if test -f "$collect2name" && \ + strings "$collect2name" | grep resolve_lib_name >/dev/null + then + # We have reworked collect2 + hardcode_direct=yes + else + # We have old collect2 + hardcode_direct=unsupported + # It fails to find uninstalled libraries when the uninstalled + # path is not listed in the libpath. Setting hardcode_minus_L + # to unsupported forces relinking + hardcode_minus_L=yes + hardcode_libdir_flag_spec='-L$libdir' + hardcode_libdir_separator= + fi + ;; + esac + shared_flag='-shared' + if test "$aix_use_runtimelinking" = yes; then + shared_flag="$shared_flag "'${wl}-G' + fi + else + # not using gcc + if test "$host_cpu" = ia64; then + # VisualAge C++, Version 5.5 for AIX 5L for IA-64, Beta 3 Release + # chokes on -Wl,-G. The following line is correct: + shared_flag='-G' + else + if test "$aix_use_runtimelinking" = yes; then + shared_flag='${wl}-G' + else + shared_flag='${wl}-bM:SRE' + fi + fi + fi + + # It seems that -bexpall does not export symbols beginning with + # underscore (_), so it is better to generate a list of symbols to export. + always_export_symbols=yes + if test "$aix_use_runtimelinking" = yes; then + # Warning - without using the other runtime loading flags (-brtl), + # -berok will link without error, but may produce a broken library. + allow_undefined_flag='-berok' + # Determine the default libpath from the value encoded in an empty executable. + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext conftest$ac_exeext +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest$ac_exeext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + +aix_libpath=`dump -H conftest$ac_exeext 2>/dev/null | $SED -n -e '/Import File Strings/,/^$/ { /^0/ { s/^0 *\(.*\)$/\1/; p; } +}'` +# Check for a 64-bit object if we didn't find anything. +if test -z "$aix_libpath"; then aix_libpath=`dump -HX64 conftest$ac_exeext 2>/dev/null | $SED -n -e '/Import File Strings/,/^$/ { /^0/ { s/^0 *\(.*\)$/\1/; p; } +}'`; fi +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +fi +rm -f conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +if test -z "$aix_libpath"; then aix_libpath="/usr/lib:/lib"; fi + + hardcode_libdir_flag_spec='${wl}-blibpath:$libdir:'"$aix_libpath" + archive_expsym_cmds="\$CC"' -o $output_objdir/$soname $libobjs $deplibs '"\${wl}$no_entry_flag"' $compiler_flags `if test "x${allow_undefined_flag}" != "x"; then echo "${wl}${allow_undefined_flag}"; else :; fi` '"\${wl}$exp_sym_flag:\$export_symbols $shared_flag" + else + if test "$host_cpu" = ia64; then + hardcode_libdir_flag_spec='${wl}-R $libdir:/usr/lib:/lib' + allow_undefined_flag="-z nodefs" + archive_expsym_cmds="\$CC $shared_flag"' -o $output_objdir/$soname $libobjs $deplibs '"\${wl}$no_entry_flag"' $compiler_flags ${wl}${allow_undefined_flag} '"\${wl}$exp_sym_flag:\$export_symbols" + else + # Determine the default libpath from the value encoded in an empty executable. + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext conftest$ac_exeext +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest$ac_exeext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + +aix_libpath=`dump -H conftest$ac_exeext 2>/dev/null | $SED -n -e '/Import File Strings/,/^$/ { /^0/ { s/^0 *\(.*\)$/\1/; p; } +}'` +# Check for a 64-bit object if we didn't find anything. +if test -z "$aix_libpath"; then aix_libpath=`dump -HX64 conftest$ac_exeext 2>/dev/null | $SED -n -e '/Import File Strings/,/^$/ { /^0/ { s/^0 *\(.*\)$/\1/; p; } +}'`; fi +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +fi +rm -f conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +if test -z "$aix_libpath"; then aix_libpath="/usr/lib:/lib"; fi + + hardcode_libdir_flag_spec='${wl}-blibpath:$libdir:'"$aix_libpath" + # Warning - without using the other run time loading flags, + # -berok will link without error, but may produce a broken library. + no_undefined_flag=' ${wl}-bernotok' + allow_undefined_flag=' ${wl}-berok' + # Exported symbols can be pulled into shared objects from archives + whole_archive_flag_spec='$convenience' + archive_cmds_need_lc=yes + # This is similar to how AIX traditionally builds its shared libraries. + archive_expsym_cmds="\$CC $shared_flag"' -o $output_objdir/$soname $libobjs $deplibs ${wl}-bnoentry $compiler_flags ${wl}-bE:$export_symbols${allow_undefined_flag}~$AR $AR_FLAGS $output_objdir/$libname$release.a $output_objdir/$soname' + fi + fi + ;; + + amigaos*) + archive_cmds='$rm $output_objdir/a2ixlibrary.data~$echo "#define NAME $libname" > $output_objdir/a2ixlibrary.data~$echo "#define LIBRARY_ID 1" >> $output_objdir/a2ixlibrary.data~$echo "#define VERSION $major" >> $output_objdir/a2ixlibrary.data~$echo "#define REVISION $revision" >> $output_objdir/a2ixlibrary.data~$AR $AR_FLAGS $lib $libobjs~$RANLIB $lib~(cd $output_objdir && a2ixlibrary -32)' + hardcode_libdir_flag_spec='-L$libdir' + hardcode_minus_L=yes + # see comment about different semantics on the GNU ld section + ld_shlibs=no + ;; + + bsdi[45]*) + export_dynamic_flag_spec=-rdynamic + ;; + + cygwin* | mingw* | pw32*) + # When not using gcc, we currently assume that we are using + # Microsoft Visual C++. + # hardcode_libdir_flag_spec is actually meaningless, as there is + # no search path for DLLs. + hardcode_libdir_flag_spec=' ' + allow_undefined_flag=unsupported + # Tell ltmain to make .lib files, not .a files. + libext=lib + # Tell ltmain to make .dll files, not .so files. + shrext_cmds=".dll" + # FIXME: Setting linknames here is a bad hack. + archive_cmds='$CC -o $lib $libobjs $compiler_flags `echo "$deplibs" | $SED -e '\''s/ -lc$//'\''` -link -dll~linknames=' + # The linker will automatically build a .lib file if we build a DLL. + old_archive_From_new_cmds='true' + # FIXME: Should let the user specify the lib program. + old_archive_cmds='lib /OUT:$oldlib$oldobjs$old_deplibs' + fix_srcfile_path='`cygpath -w "$srcfile"`' + enable_shared_with_static_runtimes=yes + ;; + + darwin* | rhapsody*) + case $host_os in + rhapsody* | darwin1.[012]) + allow_undefined_flag='${wl}-undefined ${wl}suppress' + ;; + *) # Darwin 1.3 on + if test -z ${MACOSX_DEPLOYMENT_TARGET} ; then + allow_undefined_flag='${wl}-flat_namespace ${wl}-undefined ${wl}suppress' + else + case ${MACOSX_DEPLOYMENT_TARGET} in + 10.[012]) + allow_undefined_flag='${wl}-flat_namespace ${wl}-undefined ${wl}suppress' + ;; + 10.*) + allow_undefined_flag='${wl}-undefined ${wl}dynamic_lookup' + ;; + esac + fi + ;; + esac + archive_cmds_need_lc=no + hardcode_direct=no + hardcode_automatic=yes + hardcode_shlibpath_var=unsupported + whole_archive_flag_spec='' + link_all_deplibs=yes + if test "$GCC" = yes ; then + output_verbose_link_cmd='echo' + archive_cmds='$CC -dynamiclib $allow_undefined_flag -o $lib $libobjs $deplibs $compiler_flags -install_name $rpath/$soname $verstring' + module_cmds='$CC $allow_undefined_flag -o $lib -bundle $libobjs $deplibs$compiler_flags' + # Don't fix this by using the ld -exported_symbols_list flag, it doesn't exist in older darwin lds + archive_expsym_cmds='sed -e "s,#.*,," -e "s,^[ ]*,," -e "s,^\(..*\),_&," < $export_symbols > $output_objdir/${libname}-symbols.expsym~$CC -dynamiclib $allow_undefined_flag -o $lib $libobjs $deplibs $compiler_flags -install_name $rpath/$soname $verstring~nmedit -s $output_objdir/${libname}-symbols.expsym ${lib}' + module_expsym_cmds='sed -e "s,#.*,," -e "s,^[ ]*,," -e "s,^\(..*\),_&," < $export_symbols > $output_objdir/${libname}-symbols.expsym~$CC $allow_undefined_flag -o $lib -bundle $libobjs $deplibs$compiler_flags~nmedit -s $output_objdir/${libname}-symbols.expsym ${lib}' + else + case $cc_basename in + xlc*) + output_verbose_link_cmd='echo' + archive_cmds='$CC -qmkshrobj $allow_undefined_flag -o $lib $libobjs $deplibs $compiler_flags ${wl}-install_name ${wl}`echo $rpath/$soname` $verstring' + module_cmds='$CC $allow_undefined_flag -o $lib -bundle $libobjs $deplibs$compiler_flags' + # Don't fix this by using the ld -exported_symbols_list flag, it doesn't exist in older darwin lds + archive_expsym_cmds='sed -e "s,#.*,," -e "s,^[ ]*,," -e "s,^\(..*\),_&," < $export_symbols > $output_objdir/${libname}-symbols.expsym~$CC -qmkshrobj $allow_undefined_flag -o $lib $libobjs $deplibs $compiler_flags ${wl}-install_name ${wl}$rpath/$soname $verstring~nmedit -s $output_objdir/${libname}-symbols.expsym ${lib}' + module_expsym_cmds='sed -e "s,#.*,," -e "s,^[ ]*,," -e "s,^\(..*\),_&," < $export_symbols > $output_objdir/${libname}-symbols.expsym~$CC $allow_undefined_flag -o $lib -bundle $libobjs $deplibs$compiler_flags~nmedit -s $output_objdir/${libname}-symbols.expsym ${lib}' + ;; + *) + ld_shlibs=no + ;; + esac + fi + ;; + + dgux*) + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_libdir_flag_spec='-L$libdir' + hardcode_shlibpath_var=no + ;; + + freebsd1*) + ld_shlibs=no + ;; + + # FreeBSD 2.2.[012] allows us to include c++rt0.o to get C++ constructor + # support. Future versions do this automatically, but an explicit c++rt0.o + # does not break anything, and helps significantly (at the cost of a little + # extra space). + freebsd2.2*) + archive_cmds='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags /usr/lib/c++rt0.o' + hardcode_libdir_flag_spec='-R$libdir' + hardcode_direct=yes + hardcode_shlibpath_var=no + ;; + + # Unfortunately, older versions of FreeBSD 2 do not have this feature. + freebsd2*) + archive_cmds='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags' + hardcode_direct=yes + hardcode_minus_L=yes + hardcode_shlibpath_var=no + ;; + + # FreeBSD 3 and greater uses gcc -shared to do shared libraries. + freebsd* | kfreebsd*-gnu | dragonfly*) + archive_cmds='$CC -shared -o $lib $libobjs $deplibs $compiler_flags' + hardcode_libdir_flag_spec='-R$libdir' + hardcode_direct=yes + hardcode_shlibpath_var=no + ;; + + hpux9*) + if test "$GCC" = yes; then + archive_cmds='$rm $output_objdir/$soname~$CC -shared -fPIC ${wl}+b ${wl}$install_libdir -o $output_objdir/$soname $libobjs $deplibs $compiler_flags~test $output_objdir/$soname = $lib || mv $output_objdir/$soname $lib' + else + archive_cmds='$rm $output_objdir/$soname~$LD -b +b $install_libdir -o $output_objdir/$soname $libobjs $deplibs $linker_flags~test $output_objdir/$soname = $lib || mv $output_objdir/$soname $lib' + fi + hardcode_libdir_flag_spec='${wl}+b ${wl}$libdir' + hardcode_libdir_separator=: + hardcode_direct=yes + + # hardcode_minus_L: Not really in the search PATH, + # but as the default location of the library. + hardcode_minus_L=yes + export_dynamic_flag_spec='${wl}-E' + ;; + + hpux10*) + if test "$GCC" = yes -a "$with_gnu_ld" = no; then + archive_cmds='$CC -shared -fPIC ${wl}+h ${wl}$soname ${wl}+b ${wl}$install_libdir -o $lib $libobjs $deplibs $compiler_flags' + else + archive_cmds='$LD -b +h $soname +b $install_libdir -o $lib $libobjs $deplibs $linker_flags' + fi + if test "$with_gnu_ld" = no; then + hardcode_libdir_flag_spec='${wl}+b ${wl}$libdir' + hardcode_libdir_separator=: + + hardcode_direct=yes + export_dynamic_flag_spec='${wl}-E' + + # hardcode_minus_L: Not really in the search PATH, + # but as the default location of the library. + hardcode_minus_L=yes + fi + ;; + + hpux11*) + if test "$GCC" = yes -a "$with_gnu_ld" = no; then + case $host_cpu in + hppa*64*) + archive_cmds='$CC -shared ${wl}+h ${wl}$soname -o $lib $libobjs $deplibs $compiler_flags' + ;; + ia64*) + archive_cmds='$CC -shared ${wl}+h ${wl}$soname ${wl}+nodefaultrpath -o $lib $libobjs $deplibs $compiler_flags' + ;; + *) + archive_cmds='$CC -shared -fPIC ${wl}+h ${wl}$soname ${wl}+b ${wl}$install_libdir -o $lib $libobjs $deplibs $compiler_flags' + ;; + esac + else + case $host_cpu in + hppa*64*) + archive_cmds='$CC -b ${wl}+h ${wl}$soname -o $lib $libobjs $deplibs $compiler_flags' + ;; + ia64*) + archive_cmds='$CC -b ${wl}+h ${wl}$soname ${wl}+nodefaultrpath -o $lib $libobjs $deplibs $compiler_flags' + ;; + *) + archive_cmds='$CC -b ${wl}+h ${wl}$soname ${wl}+b ${wl}$install_libdir -o $lib $libobjs $deplibs $compiler_flags' + ;; + esac + fi + if test "$with_gnu_ld" = no; then + hardcode_libdir_flag_spec='${wl}+b ${wl}$libdir' + hardcode_libdir_separator=: + + case $host_cpu in + hppa*64*|ia64*) + hardcode_libdir_flag_spec_ld='+b $libdir' + hardcode_direct=no + hardcode_shlibpath_var=no + ;; + *) + hardcode_direct=yes + export_dynamic_flag_spec='${wl}-E' + + # hardcode_minus_L: Not really in the search PATH, + # but as the default location of the library. + hardcode_minus_L=yes + ;; + esac + fi + ;; + + irix5* | irix6* | nonstopux*) + if test "$GCC" = yes; then + archive_cmds='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname ${wl}$soname `test -n "$verstring" && echo ${wl}-set_version ${wl}$verstring` ${wl}-update_registry ${wl}${output_objdir}/so_locations -o $lib' + else + archive_cmds='$LD -shared $libobjs $deplibs $linker_flags -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${output_objdir}/so_locations -o $lib' + hardcode_libdir_flag_spec_ld='-rpath $libdir' + fi + hardcode_libdir_flag_spec='${wl}-rpath ${wl}$libdir' + hardcode_libdir_separator=: + link_all_deplibs=yes + ;; + + netbsd*) + if echo __ELF__ | $CC -E - | grep __ELF__ >/dev/null; then + archive_cmds='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags' # a.out + else + archive_cmds='$LD -shared -o $lib $libobjs $deplibs $linker_flags' # ELF + fi + hardcode_libdir_flag_spec='-R$libdir' + hardcode_direct=yes + hardcode_shlibpath_var=no + ;; + + newsos6) + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_direct=yes + hardcode_libdir_flag_spec='${wl}-rpath ${wl}$libdir' + hardcode_libdir_separator=: + hardcode_shlibpath_var=no + ;; + + openbsd*) + hardcode_direct=yes + hardcode_shlibpath_var=no + if test -z "`echo __ELF__ | $CC -E - | grep __ELF__`" || test "$host_os-$host_cpu" = "openbsd2.8-powerpc"; then + archive_cmds='$CC -shared $pic_flag -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds='$CC -shared $pic_flag -o $lib $libobjs $deplibs $compiler_flags ${wl}-retain-symbols-file,$export_symbols' + hardcode_libdir_flag_spec='${wl}-rpath,$libdir' + export_dynamic_flag_spec='${wl}-E' + else + case $host_os in + openbsd[01].* | openbsd2.[0-7] | openbsd2.[0-7].*) + archive_cmds='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags' + hardcode_libdir_flag_spec='-R$libdir' + ;; + *) + archive_cmds='$CC -shared $pic_flag -o $lib $libobjs $deplibs $compiler_flags' + hardcode_libdir_flag_spec='${wl}-rpath,$libdir' + ;; + esac + fi + ;; + + os2*) + hardcode_libdir_flag_spec='-L$libdir' + hardcode_minus_L=yes + allow_undefined_flag=unsupported + archive_cmds='$echo "LIBRARY $libname INITINSTANCE" > $output_objdir/$libname.def~$echo "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~$echo DATA >> $output_objdir/$libname.def~$echo " SINGLE NONSHARED" >> $output_objdir/$libname.def~$echo EXPORTS >> $output_objdir/$libname.def~emxexp $libobjs >> $output_objdir/$libname.def~$CC -Zdll -Zcrtdll -o $lib $libobjs $deplibs $compiler_flags $output_objdir/$libname.def' + old_archive_From_new_cmds='emximp -o $output_objdir/$libname.a $output_objdir/$libname.def' + ;; + + osf3*) + if test "$GCC" = yes; then + allow_undefined_flag=' ${wl}-expect_unresolved ${wl}\*' + archive_cmds='$CC -shared${allow_undefined_flag} $libobjs $deplibs $compiler_flags ${wl}-soname ${wl}$soname `test -n "$verstring" && echo ${wl}-set_version ${wl}$verstring` ${wl}-update_registry ${wl}${output_objdir}/so_locations -o $lib' + else + allow_undefined_flag=' -expect_unresolved \*' + archive_cmds='$LD -shared${allow_undefined_flag} $libobjs $deplibs $linker_flags -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${output_objdir}/so_locations -o $lib' + fi + hardcode_libdir_flag_spec='${wl}-rpath ${wl}$libdir' + hardcode_libdir_separator=: + ;; + + osf4* | osf5*) # as osf3* with the addition of -msym flag + if test "$GCC" = yes; then + allow_undefined_flag=' ${wl}-expect_unresolved ${wl}\*' + archive_cmds='$CC -shared${allow_undefined_flag} $libobjs $deplibs $compiler_flags ${wl}-msym ${wl}-soname ${wl}$soname `test -n "$verstring" && echo ${wl}-set_version ${wl}$verstring` ${wl}-update_registry ${wl}${output_objdir}/so_locations -o $lib' + hardcode_libdir_flag_spec='${wl}-rpath ${wl}$libdir' + else + allow_undefined_flag=' -expect_unresolved \*' + archive_cmds='$LD -shared${allow_undefined_flag} $libobjs $deplibs $linker_flags -msym -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${output_objdir}/so_locations -o $lib' + archive_expsym_cmds='for i in `cat $export_symbols`; do printf "%s %s\\n" -exported_symbol "\$i" >> $lib.exp; done; echo "-hidden">> $lib.exp~ + $LD -shared${allow_undefined_flag} -input $lib.exp $linker_flags $libobjs $deplibs -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${output_objdir}/so_locations -o $lib~$rm $lib.exp' + + # Both c and cxx compiler support -rpath directly + hardcode_libdir_flag_spec='-rpath $libdir' + fi + hardcode_libdir_separator=: + ;; + + solaris*) + no_undefined_flag=' -z text' + if test "$GCC" = yes; then + wlarc='${wl}' + archive_cmds='$CC -shared ${wl}-h ${wl}$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds='$echo "{ global:" > $lib.exp~cat $export_symbols | $SED -e "s/\(.*\)/\1;/" >> $lib.exp~$echo "local: *; };" >> $lib.exp~ + $CC -shared ${wl}-M ${wl}$lib.exp ${wl}-h ${wl}$soname -o $lib $libobjs $deplibs $compiler_flags~$rm $lib.exp' + else + wlarc='' + archive_cmds='$LD -G${allow_undefined_flag} -h $soname -o $lib $libobjs $deplibs $linker_flags' + archive_expsym_cmds='$echo "{ global:" > $lib.exp~cat $export_symbols | $SED -e "s/\(.*\)/\1;/" >> $lib.exp~$echo "local: *; };" >> $lib.exp~ + $LD -G${allow_undefined_flag} -M $lib.exp -h $soname -o $lib $libobjs $deplibs $linker_flags~$rm $lib.exp' + fi + hardcode_libdir_flag_spec='-R$libdir' + hardcode_shlibpath_var=no + case $host_os in + solaris2.[0-5] | solaris2.[0-5].*) ;; + *) + # The compiler driver will combine linker options so we + # cannot just pass the convience library names through + # without $wl, iff we do not link with $LD. + # Luckily, gcc supports the same syntax we need for Sun Studio. + # Supported since Solaris 2.6 (maybe 2.5.1?) + case $wlarc in + '') + whole_archive_flag_spec='-z allextract$convenience -z defaultextract' ;; + *) + whole_archive_flag_spec='${wl}-z ${wl}allextract`for conv in $convenience\"\"; do test -n \"$conv\" && new_convenience=\"$new_convenience,$conv\"; done; $echo \"$new_convenience\"` ${wl}-z ${wl}defaultextract' ;; + esac ;; + esac + link_all_deplibs=yes + ;; + + sunos4*) + if test "x$host_vendor" = xsequent; then + # Use $CC to link under sequent, because it throws in some extra .o + # files that make .init and .fini sections work. + archive_cmds='$CC -G ${wl}-h $soname -o $lib $libobjs $deplibs $compiler_flags' + else + archive_cmds='$LD -assert pure-text -Bstatic -o $lib $libobjs $deplibs $linker_flags' + fi + hardcode_libdir_flag_spec='-L$libdir' + hardcode_direct=yes + hardcode_minus_L=yes + hardcode_shlibpath_var=no + ;; + + sysv4) + case $host_vendor in + sni) + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_direct=yes # is this really true??? + ;; + siemens) + ## LD is ld it makes a PLAMLIB + ## CC just makes a GrossModule. + archive_cmds='$LD -G -o $lib $libobjs $deplibs $linker_flags' + reload_cmds='$CC -r -o $output$reload_objs' + hardcode_direct=no + ;; + motorola) + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_direct=no #Motorola manual says yes, but my tests say they lie + ;; + esac + runpath_var='LD_RUN_PATH' + hardcode_shlibpath_var=no + ;; + + sysv4.3*) + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_shlibpath_var=no + export_dynamic_flag_spec='-Bexport' + ;; + + sysv4*MP*) + if test -d /usr/nec; then + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_shlibpath_var=no + runpath_var=LD_RUN_PATH + hardcode_runpath_var=yes + ld_shlibs=yes + fi + ;; + + sysv4*uw2* | sysv5OpenUNIX* | sysv5UnixWare7.[01].[10]* | unixware7*) + no_undefined_flag='${wl}-z,text' + archive_cmds_need_lc=no + hardcode_shlibpath_var=no + runpath_var='LD_RUN_PATH' + + if test "$GCC" = yes; then + archive_cmds='$CC -shared ${wl}-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds='$CC -shared ${wl}-Bexport:$export_symbols ${wl}-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + else + archive_cmds='$CC -G ${wl}-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds='$CC -G ${wl}-Bexport:$export_symbols ${wl}-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + fi + ;; + + sysv5* | sco3.2v5* | sco5v6*) + # Note: We can NOT use -z defs as we might desire, because we do not + # link with -lc, and that would cause any symbols used from libc to + # always be unresolved, which means just about no library would + # ever link correctly. If we're not using GNU ld we use -z text + # though, which does catch some bad symbols but isn't as heavy-handed + # as -z defs. + no_undefined_flag='${wl}-z,text' + allow_undefined_flag='${wl}-z,nodefs' + archive_cmds_need_lc=no + hardcode_shlibpath_var=no + hardcode_libdir_flag_spec='`test -z "$SCOABSPATH" && echo ${wl}-R,$libdir`' + hardcode_libdir_separator=':' + link_all_deplibs=yes + export_dynamic_flag_spec='${wl}-Bexport' + runpath_var='LD_RUN_PATH' + + if test "$GCC" = yes; then + archive_cmds='$CC -shared ${wl}-h,\${SCOABSPATH:+${install_libdir}/}$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds='$CC -shared ${wl}-Bexport:$export_symbols ${wl}-h,\${SCOABSPATH:+${install_libdir}/}$soname -o $lib $libobjs $deplibs $compiler_flags' + else + archive_cmds='$CC -G ${wl}-h,\${SCOABSPATH:+${install_libdir}/}$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds='$CC -G ${wl}-Bexport:$export_symbols ${wl}-h,\${SCOABSPATH:+${install_libdir}/}$soname -o $lib $libobjs $deplibs $compiler_flags' + fi + ;; + + uts4*) + archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_libdir_flag_spec='-L$libdir' + hardcode_shlibpath_var=no + ;; + + *) + ld_shlibs=no + ;; + esac + fi + +echo "$as_me:$LINENO: result: $ld_shlibs" >&5 +echo "${ECHO_T}$ld_shlibs" >&6 +test "$ld_shlibs" = no && can_build_shared=no + +# +# Do we need to explicitly link libc? +# +case "x$archive_cmds_need_lc" in +x|xyes) + # Assume -lc should be added + archive_cmds_need_lc=yes + + if test "$enable_shared" = yes && test "$GCC" = yes; then + case $archive_cmds in + *'~'*) + # FIXME: we may have to deal with multi-command sequences. + ;; + '$CC '*) + # Test whether the compiler implicitly links with -lc since on some + # systems, -lgcc has to come before -lc. If gcc already passes -lc + # to ld, don't add -lc before -lgcc. + echo "$as_me:$LINENO: checking whether -lc should be explicitly linked in" >&5 +echo $ECHO_N "checking whether -lc should be explicitly linked in... $ECHO_C" >&6 + $rm conftest* + printf "$lt_simple_compile_test_code" > conftest.$ac_ext + + if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } 2>conftest.err; then + soname=conftest + lib=conftest + libobjs=conftest.$ac_objext + deplibs= + wl=$lt_prog_compiler_wl + pic_flag=$lt_prog_compiler_pic + compiler_flags=-v + linker_flags=-v + verstring= + output_objdir=. + libname=conftest + lt_save_allow_undefined_flag=$allow_undefined_flag + allow_undefined_flag= + if { (eval echo "$as_me:$LINENO: \"$archive_cmds 2\>\&1 \| grep \" -lc \" \>/dev/null 2\>\&1\"") >&5 + (eval $archive_cmds 2\>\&1 \| grep \" -lc \" \>/dev/null 2\>\&1) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } + then + archive_cmds_need_lc=no + else + archive_cmds_need_lc=yes + fi + allow_undefined_flag=$lt_save_allow_undefined_flag + else + cat conftest.err 1>&5 + fi + $rm conftest* + echo "$as_me:$LINENO: result: $archive_cmds_need_lc" >&5 +echo "${ECHO_T}$archive_cmds_need_lc" >&6 + ;; + esac + fi + ;; +esac + +echo "$as_me:$LINENO: checking dynamic linker characteristics" >&5 +echo $ECHO_N "checking dynamic linker characteristics... $ECHO_C" >&6 +library_names_spec= +libname_spec='lib$name' +soname_spec= +shrext_cmds=".so" +postinstall_cmds= +postuninstall_cmds= +finish_cmds= +finish_eval= +shlibpath_var= +shlibpath_overrides_runpath=unknown +version_type=none +dynamic_linker="$host_os ld.so" +sys_lib_dlsearch_path_spec="/lib /usr/lib" +if test "$GCC" = yes; then + sys_lib_search_path_spec=`$CC -print-search-dirs | grep "^libraries:" | $SED -e "s/^libraries://" -e "s,=/,/,g"` + if echo "$sys_lib_search_path_spec" | grep ';' >/dev/null ; then + # if the path contains ";" then we assume it to be the separator + # otherwise default to the standard path separator (i.e. ":") - it is + # assumed that no part of a normal pathname contains ";" but that should + # okay in the real world where ";" in dirpaths is itself problematic. + sys_lib_search_path_spec=`echo "$sys_lib_search_path_spec" | $SED -e 's/;/ /g'` + else + sys_lib_search_path_spec=`echo "$sys_lib_search_path_spec" | $SED -e "s/$PATH_SEPARATOR/ /g"` + fi +else + sys_lib_search_path_spec="/lib /usr/lib /usr/local/lib" +fi +need_lib_prefix=unknown +hardcode_into_libs=no + +# when you set need_version to no, make sure it does not cause -set_version +# flags to be left without arguments +need_version=unknown + +case $host_os in +aix3*) + version_type=linux + library_names_spec='${libname}${release}${shared_ext}$versuffix $libname.a' + shlibpath_var=LIBPATH + + # AIX 3 has no versioning support, so we append a major version to the name. + soname_spec='${libname}${release}${shared_ext}$major' + ;; + +aix4* | aix5*) + version_type=linux + need_lib_prefix=no + need_version=no + hardcode_into_libs=yes + if test "$host_cpu" = ia64; then + # AIX 5 supports IA64 + library_names_spec='${libname}${release}${shared_ext}$major ${libname}${release}${shared_ext}$versuffix $libname${shared_ext}' + shlibpath_var=LD_LIBRARY_PATH + else + # With GCC up to 2.95.x, collect2 would create an import file + # for dependence libraries. The import file would start with + # the line `#! .'. This would cause the generated library to + # depend on `.', always an invalid library. This was fixed in + # development snapshots of GCC prior to 3.0. + case $host_os in + aix4 | aix4.[01] | aix4.[01].*) + if { echo '#if __GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 97)' + echo ' yes ' + echo '#endif'; } | ${CC} -E - | grep yes > /dev/null; then + : + else + can_build_shared=no + fi + ;; + esac + # AIX (on Power*) has no versioning support, so currently we can not hardcode correct + # soname into executable. Probably we can add versioning support to + # collect2, so additional links can be useful in future. + if test "$aix_use_runtimelinking" = yes; then + # If using run time linking (on AIX 4.2 or later) use lib.so + # instead of lib.a to let people know that these are not + # typical AIX shared libraries. + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + else + # We preserve .a as extension for shared libraries through AIX4.2 + # and later when we are not doing run time linking. + library_names_spec='${libname}${release}.a $libname.a' + soname_spec='${libname}${release}${shared_ext}$major' + fi + shlibpath_var=LIBPATH + fi + ;; + +amigaos*) + library_names_spec='$libname.ixlibrary $libname.a' + # Create ${libname}_ixlibrary.a entries in /sys/libs. + finish_eval='for lib in `ls $libdir/*.ixlibrary 2>/dev/null`; do libname=`$echo "X$lib" | $Xsed -e '\''s%^.*/\([^/]*\)\.ixlibrary$%\1%'\''`; test $rm /sys/libs/${libname}_ixlibrary.a; $show "cd /sys/libs && $LN_S $lib ${libname}_ixlibrary.a"; cd /sys/libs && $LN_S $lib ${libname}_ixlibrary.a || exit 1; done' + ;; + +beos*) + library_names_spec='${libname}${shared_ext}' + dynamic_linker="$host_os ld.so" + shlibpath_var=LIBRARY_PATH + ;; + +bsdi[45]*) + version_type=linux + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + finish_cmds='PATH="\$PATH:/sbin" ldconfig $libdir' + shlibpath_var=LD_LIBRARY_PATH + sys_lib_search_path_spec="/shlib /usr/lib /usr/X11/lib /usr/contrib/lib /lib /usr/local/lib" + sys_lib_dlsearch_path_spec="/shlib /usr/lib /usr/local/lib" + # the default ld.so.conf also contains /usr/contrib/lib and + # /usr/X11R6/lib (/usr/X11 is a link to /usr/X11R6), but let us allow + # libtool to hard-code these into programs + ;; + +cygwin* | mingw* | pw32*) + version_type=windows + shrext_cmds=".dll" + need_version=no + need_lib_prefix=no + + case $GCC,$host_os in + yes,cygwin* | yes,mingw* | yes,pw32*) + library_names_spec='$libname.dll.a' + # DLL is installed to $(libdir)/../bin by postinstall_cmds + postinstall_cmds='base_file=`basename \${file}`~ + dlpath=`$SHELL 2>&1 -c '\''. $dir/'\''\${base_file}'\''i;echo \$dlname'\''`~ + dldir=$destdir/`dirname \$dlpath`~ + test -d \$dldir || mkdir -p \$dldir~ + $install_prog $dir/$dlname \$dldir/$dlname~ + chmod a+x \$dldir/$dlname' + postuninstall_cmds='dldll=`$SHELL 2>&1 -c '\''. $file; echo \$dlname'\''`~ + dlpath=$dir/\$dldll~ + $rm \$dlpath' + shlibpath_overrides_runpath=yes + + case $host_os in + cygwin*) + # Cygwin DLLs use 'cyg' prefix rather than 'lib' + soname_spec='`echo ${libname} | sed -e 's/^lib/cyg/'``echo ${release} | $SED -e 's/[.]/-/g'`${versuffix}${shared_ext}' + sys_lib_search_path_spec="/usr/lib /lib/w32api /lib /usr/local/lib" + ;; + mingw*) + # MinGW DLLs use traditional 'lib' prefix + soname_spec='${libname}`echo ${release} | $SED -e 's/[.]/-/g'`${versuffix}${shared_ext}' + sys_lib_search_path_spec=`$CC -print-search-dirs | grep "^libraries:" | $SED -e "s/^libraries://" -e "s,=/,/,g"` + if echo "$sys_lib_search_path_spec" | grep ';[c-zC-Z]:/' >/dev/null; then + # It is most probably a Windows format PATH printed by + # mingw gcc, but we are running on Cygwin. Gcc prints its search + # path with ; separators, and with drive letters. We can handle the + # drive letters (cygwin fileutils understands them), so leave them, + # especially as we might pass files found there to a mingw objdump, + # which wouldn't understand a cygwinified path. Ahh. + sys_lib_search_path_spec=`echo "$sys_lib_search_path_spec" | $SED -e 's/;/ /g'` + else + sys_lib_search_path_spec=`echo "$sys_lib_search_path_spec" | $SED -e "s/$PATH_SEPARATOR/ /g"` + fi + ;; + pw32*) + # pw32 DLLs use 'pw' prefix rather than 'lib' + library_names_spec='`echo ${libname} | sed -e 's/^lib/pw/'``echo ${release} | $SED -e 's/[.]/-/g'`${versuffix}${shared_ext}' + ;; + esac + ;; + + linux*) + if $LD --help 2>&1 | egrep ': supported targets:.* elf' > /dev/null; then + archive_cmds='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + supports_anon_versioning=no + case `$LD -v 2>/dev/null` in + *\ 01.* | *\ 2.[0-9].* | *\ 2.10.*) ;; # catch versions < 2.11 + *\ 2.11.93.0.2\ *) supports_anon_versioning=yes ;; # RH7.3 ... + *\ 2.11.92.0.12\ *) supports_anon_versioning=yes ;; # Mandrake 8.2 ... + *\ 2.11.*) ;; # other 2.11 versions + *) supports_anon_versioning=yes ;; + esac + if test $supports_anon_versioning = yes; then + archive_expsym_cmds='$echo "{ global:" > $output_objdir/$libname.ver~ +cat $export_symbols | sed -e "s/\(.*\)/\1;/" >> $output_objdir/$libname.ver~ +$echo "local: *; };" >> $output_objdir/$libname.ver~ + $CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-version-script ${wl}$output_objdir/$libname.ver -o $lib' + else + $archive_expsym_cmds="$archive_cmds" + fi + else + ld_shlibs=no + fi + ;; + + *) + library_names_spec='${libname}`echo ${release} | $SED -e 's/[.]/-/g'`${versuffix}${shared_ext} $libname.lib' + ;; + esac + dynamic_linker='Win32 ld.exe' + # FIXME: first we should search . and the directory the executable is in + shlibpath_var=PATH + ;; + +darwin* | rhapsody*) + dynamic_linker="$host_os dyld" + version_type=darwin + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${versuffix}$shared_ext ${libname}${release}${major}$shared_ext ${libname}$shared_ext' + soname_spec='${libname}${release}${major}$shared_ext' + shlibpath_overrides_runpath=yes + shlibpath_var=DYLD_LIBRARY_PATH + shrext_cmds='`test .$module = .yes && echo .so || echo .dylib`' + # Apple's gcc prints 'gcc -print-search-dirs' doesn't operate the same. + if test "$GCC" = yes; then + sys_lib_search_path_spec=`$CC -print-search-dirs | tr "\n" "$PATH_SEPARATOR" | sed -e 's/libraries:/@libraries:/' | tr "@" "\n" | grep "^libraries:" | sed -e "s/^libraries://" -e "s,=/,/,g" -e "s,$PATH_SEPARATOR, ,g" -e "s,.*,& /lib /usr/lib /usr/local/lib,g"` + else + sys_lib_search_path_spec='/lib /usr/lib /usr/local/lib' + fi + sys_lib_dlsearch_path_spec='/usr/local/lib /lib /usr/lib' + ;; + +dgux*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname$shared_ext' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + ;; + +freebsd1*) + dynamic_linker=no + ;; + +kfreebsd*-gnu) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + dynamic_linker='GNU ld.so' + ;; + +freebsd* | dragonfly*) + # DragonFly does not have aout. When/if they implement a new + # versioning mechanism, adjust this. + if test -x /usr/bin/objformat; then + objformat=`/usr/bin/objformat` + else + case $host_os in + freebsd[123]*) objformat=aout ;; + *) objformat=elf ;; + esac + fi + # Handle Gentoo/FreeBSD as it was Linux + case $host_vendor in + gentoo) + version_type=linux ;; + *) + version_type=freebsd-$objformat ;; + esac + + case $version_type in + freebsd-elf*) + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext} $libname${shared_ext}' + need_version=no + need_lib_prefix=no + ;; + freebsd-*) + library_names_spec='${libname}${release}${shared_ext}$versuffix $libname${shared_ext}$versuffix' + need_version=yes + ;; + linux) + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + need_lib_prefix=no + need_version=no + ;; + esac + shlibpath_var=LD_LIBRARY_PATH + case $host_os in + freebsd2*) + shlibpath_overrides_runpath=yes + ;; + freebsd3.[01]* | freebsdelf3.[01]*) + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + ;; + freebsd3.[2-9]* | freebsdelf3.[2-9]* | \ + freebsd4.[0-5] | freebsdelf4.[0-5] | freebsd4.1.1 | freebsdelf4.1.1) + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + ;; + freebsd*) # from 4.6 on + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + ;; + esac + ;; + +gnu*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}${major} ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + hardcode_into_libs=yes + ;; + +hpux9* | hpux10* | hpux11*) + # Give a soname corresponding to the major version so that dld.sl refuses to + # link against other versions. + version_type=sunos + need_lib_prefix=no + need_version=no + case $host_cpu in + ia64*) + shrext_cmds='.so' + hardcode_into_libs=yes + dynamic_linker="$host_os dld.so" + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes # Unless +noenvvar is specified. + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + if test "X$HPUX_IA64_MODE" = X32; then + sys_lib_search_path_spec="/usr/lib/hpux32 /usr/local/lib/hpux32 /usr/local/lib" + else + sys_lib_search_path_spec="/usr/lib/hpux64 /usr/local/lib/hpux64" + fi + sys_lib_dlsearch_path_spec=$sys_lib_search_path_spec + ;; + hppa*64*) + shrext_cmds='.sl' + hardcode_into_libs=yes + dynamic_linker="$host_os dld.sl" + shlibpath_var=LD_LIBRARY_PATH # How should we handle SHLIB_PATH + shlibpath_overrides_runpath=yes # Unless +noenvvar is specified. + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + sys_lib_search_path_spec="/usr/lib/pa20_64 /usr/ccs/lib/pa20_64" + sys_lib_dlsearch_path_spec=$sys_lib_search_path_spec + ;; + *) + shrext_cmds='.sl' + dynamic_linker="$host_os dld.sl" + shlibpath_var=SHLIB_PATH + shlibpath_overrides_runpath=no # +s is required to enable SHLIB_PATH + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + ;; + esac + # HP-UX runs *really* slowly unless shared libraries are mode 555. + postinstall_cmds='chmod 555 $lib' + ;; + +interix3*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + dynamic_linker='Interix 3.x ld.so.1 (PE, like ELF)' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + ;; + +irix5* | irix6* | nonstopux*) + case $host_os in + nonstopux*) version_type=nonstopux ;; + *) + if test "$lt_cv_prog_gnu_ld" = yes; then + version_type=linux + else + version_type=irix + fi ;; + esac + need_lib_prefix=no + need_version=no + soname_spec='${libname}${release}${shared_ext}$major' + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${release}${shared_ext} $libname${shared_ext}' + case $host_os in + irix5* | nonstopux*) + libsuff= shlibsuff= + ;; + *) + case $LD in # libtool.m4 will add one of these switches to LD + *-32|*"-32 "|*-melf32bsmip|*"-melf32bsmip ") + libsuff= shlibsuff= libmagic=32-bit;; + *-n32|*"-n32 "|*-melf32bmipn32|*"-melf32bmipn32 ") + libsuff=32 shlibsuff=N32 libmagic=N32;; + *-64|*"-64 "|*-melf64bmip|*"-melf64bmip ") + libsuff=64 shlibsuff=64 libmagic=64-bit;; + *) libsuff= shlibsuff= libmagic=never-match;; + esac + ;; + esac + shlibpath_var=LD_LIBRARY${shlibsuff}_PATH + shlibpath_overrides_runpath=no + sys_lib_search_path_spec="/usr/lib${libsuff} /lib${libsuff} /usr/local/lib${libsuff}" + sys_lib_dlsearch_path_spec="/usr/lib${libsuff} /lib${libsuff}" + hardcode_into_libs=yes + ;; + +# No shared lib support for Linux oldld, aout, or coff. +linux*oldld* | linux*aout* | linux*coff*) + dynamic_linker=no + ;; + +# This must be Linux ELF. +linux*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + finish_cmds='PATH="\$PATH:/sbin" ldconfig -n $libdir' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + # This implies no fast_install, which is unacceptable. + # Some rework will be needed to allow for fast_install + # before this can be enabled. + hardcode_into_libs=yes + + # Append ld.so.conf contents to the search path + if test -f /etc/ld.so.conf; then + lt_ld_extra=`awk '/^include / { system(sprintf("cd /etc; cat %s", \$2)); skip = 1; } { if (!skip) print \$0; skip = 0; }' < /etc/ld.so.conf | $SED -e 's/#.*//;s/[:, ]/ /g;s/=[^=]*$//;s/=[^= ]* / /g;/^$/d' | tr '\n' ' '` + sys_lib_dlsearch_path_spec="/lib /usr/lib $lt_ld_extra" + fi + + # We used to test for /lib/ld.so.1 and disable shared libraries on + # powerpc, because MkLinux only supported shared libraries with the + # GNU dynamic linker. Since this was broken with cross compilers, + # most powerpc-linux boxes support dynamic linking these days and + # people can always --disable-shared, the test was removed, and we + # assume the GNU/Linux dynamic linker is in use. + dynamic_linker='GNU/Linux ld.so' + ;; + +knetbsd*-gnu) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + dynamic_linker='GNU ld.so' + ;; + +netbsd*) + version_type=sunos + need_lib_prefix=no + need_version=no + if echo __ELF__ | $CC -E - | grep __ELF__ >/dev/null; then + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${shared_ext}$versuffix' + finish_cmds='PATH="\$PATH:/sbin" ldconfig -m $libdir' + dynamic_linker='NetBSD (a.out) ld.so' + else + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + dynamic_linker='NetBSD ld.elf_so' + fi + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + ;; + +newsos6) + version_type=linux + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + ;; + +nto-qnx*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + ;; + +openbsd*) + version_type=sunos + sys_lib_dlsearch_path_spec="/usr/lib" + need_lib_prefix=no + # Some older versions of OpenBSD (3.3 at least) *do* need versioned libs. + case $host_os in + openbsd3.3 | openbsd3.3.*) need_version=yes ;; + *) need_version=no ;; + esac + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${shared_ext}$versuffix' + finish_cmds='PATH="\$PATH:/sbin" ldconfig -m $libdir' + shlibpath_var=LD_LIBRARY_PATH + if test -z "`echo __ELF__ | $CC -E - | grep __ELF__`" || test "$host_os-$host_cpu" = "openbsd2.8-powerpc"; then + case $host_os in + openbsd2.[89] | openbsd2.[89].*) + shlibpath_overrides_runpath=no + ;; + *) + shlibpath_overrides_runpath=yes + ;; + esac + else + shlibpath_overrides_runpath=yes + fi + ;; + +os2*) + libname_spec='$name' + shrext_cmds=".dll" + need_lib_prefix=no + library_names_spec='$libname${shared_ext} $libname.a' + dynamic_linker='OS/2 ld.exe' + shlibpath_var=LIBPATH + ;; + +osf3* | osf4* | osf5*) + version_type=osf + need_lib_prefix=no + need_version=no + soname_spec='${libname}${release}${shared_ext}$major' + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + shlibpath_var=LD_LIBRARY_PATH + sys_lib_search_path_spec="/usr/shlib /usr/ccs/lib /usr/lib/cmplrs/cc /usr/lib /usr/local/lib /var/shlib" + sys_lib_dlsearch_path_spec="$sys_lib_search_path_spec" + ;; + +solaris*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + # ldd complains unless libraries are executable + postinstall_cmds='chmod +x $lib' + ;; + +sunos4*) + version_type=sunos + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${shared_ext}$versuffix' + finish_cmds='PATH="\$PATH:/usr/etc" ldconfig $libdir' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + if test "$with_gnu_ld" = yes; then + need_lib_prefix=no + fi + need_version=yes + ;; + +sysv4 | sysv4.3*) + version_type=linux + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + case $host_vendor in + sni) + shlibpath_overrides_runpath=no + need_lib_prefix=no + export_dynamic_flag_spec='${wl}-Blargedynsym' + runpath_var=LD_RUN_PATH + ;; + siemens) + need_lib_prefix=no + ;; + motorola) + need_lib_prefix=no + need_version=no + shlibpath_overrides_runpath=no + sys_lib_search_path_spec='/lib /usr/lib /usr/ccs/lib' + ;; + esac + ;; + +sysv4*MP*) + if test -d /usr/nec ;then + version_type=linux + library_names_spec='$libname${shared_ext}.$versuffix $libname${shared_ext}.$major $libname${shared_ext}' + soname_spec='$libname${shared_ext}.$major' + shlibpath_var=LD_LIBRARY_PATH + fi + ;; + +sysv5* | sco3.2v5* | sco5v6* | unixware* | OpenUNIX* | sysv4*uw2*) + version_type=freebsd-elf + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext} $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + hardcode_into_libs=yes + if test "$with_gnu_ld" = yes; then + sys_lib_search_path_spec='/usr/local/lib /usr/gnu/lib /usr/ccs/lib /usr/lib /lib' + shlibpath_overrides_runpath=no + else + sys_lib_search_path_spec='/usr/ccs/lib /usr/lib' + shlibpath_overrides_runpath=yes + case $host_os in + sco3.2v5*) + sys_lib_search_path_spec="$sys_lib_search_path_spec /lib" + ;; + esac + fi + sys_lib_dlsearch_path_spec='/usr/lib' + ;; + +uts4*) + version_type=linux + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + ;; + +*) + dynamic_linker=no + ;; +esac +echo "$as_me:$LINENO: result: $dynamic_linker" >&5 +echo "${ECHO_T}$dynamic_linker" >&6 +test "$dynamic_linker" = no && can_build_shared=no + +variables_saved_for_relink="PATH $shlibpath_var $runpath_var" +if test "$GCC" = yes; then + variables_saved_for_relink="$variables_saved_for_relink GCC_EXEC_PREFIX COMPILER_PATH LIBRARY_PATH" +fi + +echo "$as_me:$LINENO: checking how to hardcode library paths into programs" >&5 +echo $ECHO_N "checking how to hardcode library paths into programs... $ECHO_C" >&6 +hardcode_action= +if test -n "$hardcode_libdir_flag_spec" || \ + test -n "$runpath_var" || \ + test "X$hardcode_automatic" = "Xyes" ; then + + # We can hardcode non-existant directories. + if test "$hardcode_direct" != no && + # If the only mechanism to avoid hardcoding is shlibpath_var, we + # have to relink, otherwise we might link with an installed library + # when we should be linking with a yet-to-be-installed one + ## test "$_LT_AC_TAGVAR(hardcode_shlibpath_var, )" != no && + test "$hardcode_minus_L" != no; then + # Linking always hardcodes the temporary library directory. + hardcode_action=relink + else + # We can link without hardcoding, and we can hardcode nonexisting dirs. + hardcode_action=immediate + fi +else + # We cannot hardcode anything, or else we can only hardcode existing + # directories. + hardcode_action=unsupported +fi +echo "$as_me:$LINENO: result: $hardcode_action" >&5 +echo "${ECHO_T}$hardcode_action" >&6 + +if test "$hardcode_action" = relink; then + # Fast installation is not supported + enable_fast_install=no +elif test "$shlibpath_overrides_runpath" = yes || + test "$enable_shared" = no; then + # Fast installation is not necessary + enable_fast_install=needless +fi + +striplib= +old_striplib= +echo "$as_me:$LINENO: checking whether stripping libraries is possible" >&5 +echo $ECHO_N "checking whether stripping libraries is possible... $ECHO_C" >&6 +if test -n "$STRIP" && $STRIP -V 2>&1 | grep "GNU strip" >/dev/null; then + test -z "$old_striplib" && old_striplib="$STRIP --strip-debug" + test -z "$striplib" && striplib="$STRIP --strip-unneeded" + echo "$as_me:$LINENO: result: yes" >&5 +echo "${ECHO_T}yes" >&6 +else +# FIXME - insert some real tests, host_os isn't really good enough + case $host_os in + darwin*) + if test -n "$STRIP" ; then + striplib="$STRIP -x" + echo "$as_me:$LINENO: result: yes" >&5 +echo "${ECHO_T}yes" >&6 + else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi + ;; + *) + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 + ;; + esac +fi + +if test "x$enable_dlopen" != xyes; then + enable_dlopen=unknown + enable_dlopen_self=unknown + enable_dlopen_self_static=unknown +else + lt_cv_dlopen=no + lt_cv_dlopen_libs= + + case $host_os in + beos*) + lt_cv_dlopen="load_add_on" + lt_cv_dlopen_libs= + lt_cv_dlopen_self=yes + ;; + + mingw* | pw32*) + lt_cv_dlopen="LoadLibrary" + lt_cv_dlopen_libs= + ;; + + cygwin*) + lt_cv_dlopen="dlopen" + lt_cv_dlopen_libs= + ;; + + darwin*) + # if libdl is installed we need to link against it + echo "$as_me:$LINENO: checking for dlopen in -ldl" >&5 +echo $ECHO_N "checking for dlopen in -ldl... $ECHO_C" >&6 +if test "${ac_cv_lib_dl_dlopen+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-ldl $LIBS" +cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +/* Override any gcc2 internal prototype to avoid an error. */ +#ifdef __cplusplus +extern "C" +#endif +/* We use char because int might match the return type of a gcc2 + builtin and then its argument prototype would still apply. */ +char dlopen (); +int +main () +{ +dlopen (); + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext conftest$ac_exeext +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest$ac_exeext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_cv_lib_dl_dlopen=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_cv_lib_dl_dlopen=no +fi +rm -f conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +echo "$as_me:$LINENO: result: $ac_cv_lib_dl_dlopen" >&5 +echo "${ECHO_T}$ac_cv_lib_dl_dlopen" >&6 +if test $ac_cv_lib_dl_dlopen = yes; then + lt_cv_dlopen="dlopen" lt_cv_dlopen_libs="-ldl" +else + + lt_cv_dlopen="dyld" + lt_cv_dlopen_libs= + lt_cv_dlopen_self=yes + +fi + + ;; + + *) + echo "$as_me:$LINENO: checking for shl_load" >&5 +echo $ECHO_N "checking for shl_load... $ECHO_C" >&6 +if test "${ac_cv_func_shl_load+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +/* Define shl_load to an innocuous variant, in case declares shl_load. + For example, HP-UX 11i declares gettimeofday. */ +#define shl_load innocuous_shl_load + +/* System header to define __stub macros and hopefully few prototypes, + which can conflict with char shl_load (); below. + Prefer to if __STDC__ is defined, since + exists even on freestanding compilers. */ + +#ifdef __STDC__ +# include +#else +# include +#endif + +#undef shl_load + +/* Override any gcc2 internal prototype to avoid an error. */ +#ifdef __cplusplus +extern "C" +{ +#endif +/* We use char because int might match the return type of a gcc2 + builtin and then its argument prototype would still apply. */ +char shl_load (); +/* The GNU C library defines this for functions which it implements + to always fail with ENOSYS. Some functions are actually named + something starting with __ and the normal name is an alias. */ +#if defined (__stub_shl_load) || defined (__stub___shl_load) +choke me +#else +char (*f) () = shl_load; +#endif +#ifdef __cplusplus +} +#endif + +int +main () +{ +return f != shl_load; + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext conftest$ac_exeext +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest$ac_exeext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_cv_func_shl_load=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_cv_func_shl_load=no +fi +rm -f conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +fi +echo "$as_me:$LINENO: result: $ac_cv_func_shl_load" >&5 +echo "${ECHO_T}$ac_cv_func_shl_load" >&6 +if test $ac_cv_func_shl_load = yes; then + lt_cv_dlopen="shl_load" +else + echo "$as_me:$LINENO: checking for shl_load in -ldld" >&5 +echo $ECHO_N "checking for shl_load in -ldld... $ECHO_C" >&6 +if test "${ac_cv_lib_dld_shl_load+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-ldld $LIBS" +cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +/* Override any gcc2 internal prototype to avoid an error. */ +#ifdef __cplusplus +extern "C" +#endif +/* We use char because int might match the return type of a gcc2 + builtin and then its argument prototype would still apply. */ +char shl_load (); +int +main () +{ +shl_load (); + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext conftest$ac_exeext +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest$ac_exeext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_cv_lib_dld_shl_load=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_cv_lib_dld_shl_load=no +fi +rm -f conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +echo "$as_me:$LINENO: result: $ac_cv_lib_dld_shl_load" >&5 +echo "${ECHO_T}$ac_cv_lib_dld_shl_load" >&6 +if test $ac_cv_lib_dld_shl_load = yes; then + lt_cv_dlopen="shl_load" lt_cv_dlopen_libs="-dld" +else + echo "$as_me:$LINENO: checking for dlopen" >&5 +echo $ECHO_N "checking for dlopen... $ECHO_C" >&6 +if test "${ac_cv_func_dlopen+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +/* Define dlopen to an innocuous variant, in case declares dlopen. + For example, HP-UX 11i declares gettimeofday. */ +#define dlopen innocuous_dlopen + +/* System header to define __stub macros and hopefully few prototypes, + which can conflict with char dlopen (); below. + Prefer to if __STDC__ is defined, since + exists even on freestanding compilers. */ + +#ifdef __STDC__ +# include +#else +# include +#endif + +#undef dlopen + +/* Override any gcc2 internal prototype to avoid an error. */ +#ifdef __cplusplus +extern "C" +{ +#endif +/* We use char because int might match the return type of a gcc2 + builtin and then its argument prototype would still apply. */ +char dlopen (); +/* The GNU C library defines this for functions which it implements + to always fail with ENOSYS. Some functions are actually named + something starting with __ and the normal name is an alias. */ +#if defined (__stub_dlopen) || defined (__stub___dlopen) +choke me +#else +char (*f) () = dlopen; +#endif +#ifdef __cplusplus +} +#endif + +int +main () +{ +return f != dlopen; + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext conftest$ac_exeext +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest$ac_exeext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_cv_func_dlopen=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_cv_func_dlopen=no +fi +rm -f conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +fi +echo "$as_me:$LINENO: result: $ac_cv_func_dlopen" >&5 +echo "${ECHO_T}$ac_cv_func_dlopen" >&6 +if test $ac_cv_func_dlopen = yes; then + lt_cv_dlopen="dlopen" +else + echo "$as_me:$LINENO: checking for dlopen in -ldl" >&5 +echo $ECHO_N "checking for dlopen in -ldl... $ECHO_C" >&6 +if test "${ac_cv_lib_dl_dlopen+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-ldl $LIBS" +cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +/* Override any gcc2 internal prototype to avoid an error. */ +#ifdef __cplusplus +extern "C" +#endif +/* We use char because int might match the return type of a gcc2 + builtin and then its argument prototype would still apply. */ +char dlopen (); +int +main () +{ +dlopen (); + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext conftest$ac_exeext +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest$ac_exeext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_cv_lib_dl_dlopen=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_cv_lib_dl_dlopen=no +fi +rm -f conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +echo "$as_me:$LINENO: result: $ac_cv_lib_dl_dlopen" >&5 +echo "${ECHO_T}$ac_cv_lib_dl_dlopen" >&6 +if test $ac_cv_lib_dl_dlopen = yes; then + lt_cv_dlopen="dlopen" lt_cv_dlopen_libs="-ldl" +else + echo "$as_me:$LINENO: checking for dlopen in -lsvld" >&5 +echo $ECHO_N "checking for dlopen in -lsvld... $ECHO_C" >&6 +if test "${ac_cv_lib_svld_dlopen+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-lsvld $LIBS" +cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +/* Override any gcc2 internal prototype to avoid an error. */ +#ifdef __cplusplus +extern "C" +#endif +/* We use char because int might match the return type of a gcc2 + builtin and then its argument prototype would still apply. */ +char dlopen (); +int +main () +{ +dlopen (); + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext conftest$ac_exeext +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest$ac_exeext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_cv_lib_svld_dlopen=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_cv_lib_svld_dlopen=no +fi +rm -f conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +echo "$as_me:$LINENO: result: $ac_cv_lib_svld_dlopen" >&5 +echo "${ECHO_T}$ac_cv_lib_svld_dlopen" >&6 +if test $ac_cv_lib_svld_dlopen = yes; then + lt_cv_dlopen="dlopen" lt_cv_dlopen_libs="-lsvld" +else + echo "$as_me:$LINENO: checking for dld_link in -ldld" >&5 +echo $ECHO_N "checking for dld_link in -ldld... $ECHO_C" >&6 +if test "${ac_cv_lib_dld_dld_link+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-ldld $LIBS" +cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +/* Override any gcc2 internal prototype to avoid an error. */ +#ifdef __cplusplus +extern "C" +#endif +/* We use char because int might match the return type of a gcc2 + builtin and then its argument prototype would still apply. */ +char dld_link (); +int +main () +{ +dld_link (); + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext conftest$ac_exeext +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest$ac_exeext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_cv_lib_dld_dld_link=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_cv_lib_dld_dld_link=no +fi +rm -f conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +echo "$as_me:$LINENO: result: $ac_cv_lib_dld_dld_link" >&5 +echo "${ECHO_T}$ac_cv_lib_dld_dld_link" >&6 +if test $ac_cv_lib_dld_dld_link = yes; then + lt_cv_dlopen="dld_link" lt_cv_dlopen_libs="-dld" +fi + + +fi + + +fi + + +fi + + +fi + + +fi + + ;; + esac + + if test "x$lt_cv_dlopen" != xno; then + enable_dlopen=yes + else + enable_dlopen=no + fi + + case $lt_cv_dlopen in + dlopen) + save_CPPFLAGS="$CPPFLAGS" + test "x$ac_cv_header_dlfcn_h" = xyes && CPPFLAGS="$CPPFLAGS -DHAVE_DLFCN_H" + + save_LDFLAGS="$LDFLAGS" + wl=$lt_prog_compiler_wl eval LDFLAGS=\"\$LDFLAGS $export_dynamic_flag_spec\" + + save_LIBS="$LIBS" + LIBS="$lt_cv_dlopen_libs $LIBS" + + echo "$as_me:$LINENO: checking whether a program can dlopen itself" >&5 +echo $ECHO_N "checking whether a program can dlopen itself... $ECHO_C" >&6 +if test "${lt_cv_dlopen_self+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test "$cross_compiling" = yes; then : + lt_cv_dlopen_self=cross +else + lt_dlunknown=0; lt_dlno_uscore=1; lt_dlneed_uscore=2 + lt_status=$lt_dlunknown + cat > conftest.$ac_ext < +#endif + +#include + +#ifdef RTLD_GLOBAL +# define LT_DLGLOBAL RTLD_GLOBAL +#else +# ifdef DL_GLOBAL +# define LT_DLGLOBAL DL_GLOBAL +# else +# define LT_DLGLOBAL 0 +# endif +#endif + +/* We may have to define LT_DLLAZY_OR_NOW in the command line if we + find out it does not work in some platform. */ +#ifndef LT_DLLAZY_OR_NOW +# ifdef RTLD_LAZY +# define LT_DLLAZY_OR_NOW RTLD_LAZY +# else +# ifdef DL_LAZY +# define LT_DLLAZY_OR_NOW DL_LAZY +# else +# ifdef RTLD_NOW +# define LT_DLLAZY_OR_NOW RTLD_NOW +# else +# ifdef DL_NOW +# define LT_DLLAZY_OR_NOW DL_NOW +# else +# define LT_DLLAZY_OR_NOW 0 +# endif +# endif +# endif +# endif +#endif + +#ifdef __cplusplus +extern "C" void exit (int); +#endif + +void fnord() { int i=42;} +int main () +{ + void *self = dlopen (0, LT_DLGLOBAL|LT_DLLAZY_OR_NOW); + int status = $lt_dlunknown; + + if (self) + { + if (dlsym (self,"fnord")) status = $lt_dlno_uscore; + else if (dlsym( self,"_fnord")) status = $lt_dlneed_uscore; + /* dlclose (self); */ + } + else + puts (dlerror ()); + + exit (status); +} +EOF + if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && test -s conftest${ac_exeext} 2>/dev/null; then + (./conftest; exit; ) >&5 2>/dev/null + lt_status=$? + case x$lt_status in + x$lt_dlno_uscore) lt_cv_dlopen_self=yes ;; + x$lt_dlneed_uscore) lt_cv_dlopen_self=yes ;; + x$lt_dlunknown|x*) lt_cv_dlopen_self=no ;; + esac + else : + # compilation failed + lt_cv_dlopen_self=no + fi +fi +rm -fr conftest* + + +fi +echo "$as_me:$LINENO: result: $lt_cv_dlopen_self" >&5 +echo "${ECHO_T}$lt_cv_dlopen_self" >&6 + + if test "x$lt_cv_dlopen_self" = xyes; then + wl=$lt_prog_compiler_wl eval LDFLAGS=\"\$LDFLAGS $lt_prog_compiler_static\" + echo "$as_me:$LINENO: checking whether a statically linked program can dlopen itself" >&5 +echo $ECHO_N "checking whether a statically linked program can dlopen itself... $ECHO_C" >&6 +if test "${lt_cv_dlopen_self_static+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test "$cross_compiling" = yes; then : + lt_cv_dlopen_self_static=cross +else + lt_dlunknown=0; lt_dlno_uscore=1; lt_dlneed_uscore=2 + lt_status=$lt_dlunknown + cat > conftest.$ac_ext < +#endif + +#include + +#ifdef RTLD_GLOBAL +# define LT_DLGLOBAL RTLD_GLOBAL +#else +# ifdef DL_GLOBAL +# define LT_DLGLOBAL DL_GLOBAL +# else +# define LT_DLGLOBAL 0 +# endif +#endif + +/* We may have to define LT_DLLAZY_OR_NOW in the command line if we + find out it does not work in some platform. */ +#ifndef LT_DLLAZY_OR_NOW +# ifdef RTLD_LAZY +# define LT_DLLAZY_OR_NOW RTLD_LAZY +# else +# ifdef DL_LAZY +# define LT_DLLAZY_OR_NOW DL_LAZY +# else +# ifdef RTLD_NOW +# define LT_DLLAZY_OR_NOW RTLD_NOW +# else +# ifdef DL_NOW +# define LT_DLLAZY_OR_NOW DL_NOW +# else +# define LT_DLLAZY_OR_NOW 0 +# endif +# endif +# endif +# endif +#endif + +#ifdef __cplusplus +extern "C" void exit (int); +#endif + +void fnord() { int i=42;} +int main () +{ + void *self = dlopen (0, LT_DLGLOBAL|LT_DLLAZY_OR_NOW); + int status = $lt_dlunknown; + + if (self) + { + if (dlsym (self,"fnord")) status = $lt_dlno_uscore; + else if (dlsym( self,"_fnord")) status = $lt_dlneed_uscore; + /* dlclose (self); */ + } + else + puts (dlerror ()); + + exit (status); +} +EOF + if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && test -s conftest${ac_exeext} 2>/dev/null; then + (./conftest; exit; ) >&5 2>/dev/null + lt_status=$? + case x$lt_status in + x$lt_dlno_uscore) lt_cv_dlopen_self_static=yes ;; + x$lt_dlneed_uscore) lt_cv_dlopen_self_static=yes ;; + x$lt_dlunknown|x*) lt_cv_dlopen_self_static=no ;; + esac + else : + # compilation failed + lt_cv_dlopen_self_static=no + fi +fi +rm -fr conftest* + + +fi +echo "$as_me:$LINENO: result: $lt_cv_dlopen_self_static" >&5 +echo "${ECHO_T}$lt_cv_dlopen_self_static" >&6 + fi + + CPPFLAGS="$save_CPPFLAGS" + LDFLAGS="$save_LDFLAGS" + LIBS="$save_LIBS" + ;; + esac + + case $lt_cv_dlopen_self in + yes|no) enable_dlopen_self=$lt_cv_dlopen_self ;; + *) enable_dlopen_self=unknown ;; + esac + + case $lt_cv_dlopen_self_static in + yes|no) enable_dlopen_self_static=$lt_cv_dlopen_self_static ;; + *) enable_dlopen_self_static=unknown ;; + esac +fi + + +# Report which library types will actually be built +echo "$as_me:$LINENO: checking if libtool supports shared libraries" >&5 +echo $ECHO_N "checking if libtool supports shared libraries... $ECHO_C" >&6 +echo "$as_me:$LINENO: result: $can_build_shared" >&5 +echo "${ECHO_T}$can_build_shared" >&6 + +echo "$as_me:$LINENO: checking whether to build shared libraries" >&5 +echo $ECHO_N "checking whether to build shared libraries... $ECHO_C" >&6 +test "$can_build_shared" = "no" && enable_shared=no + +# On AIX, shared libraries and static libraries use the same namespace, and +# are all built from PIC. +case $host_os in +aix3*) + test "$enable_shared" = yes && enable_static=no + if test -n "$RANLIB"; then + archive_cmds="$archive_cmds~\$RANLIB \$lib" + postinstall_cmds='$RANLIB $lib' + fi + ;; + +aix4* | aix5*) + if test "$host_cpu" != ia64 && test "$aix_use_runtimelinking" = no ; then + test "$enable_shared" = yes && enable_static=no + fi + ;; +esac +echo "$as_me:$LINENO: result: $enable_shared" >&5 +echo "${ECHO_T}$enable_shared" >&6 + +echo "$as_me:$LINENO: checking whether to build static libraries" >&5 +echo $ECHO_N "checking whether to build static libraries... $ECHO_C" >&6 +# Make sure either enable_shared or enable_static is yes. +test "$enable_shared" = yes || enable_static=yes +echo "$as_me:$LINENO: result: $enable_static" >&5 +echo "${ECHO_T}$enable_static" >&6 + +# The else clause should only fire when bootstrapping the +# libtool distribution, otherwise you forgot to ship ltmain.sh +# with your package, and you will get complaints that there are +# no rules to generate ltmain.sh. +if test -f "$ltmain"; then + # See if we are running on zsh, and set the options which allow our commands through + # without removal of \ escapes. + if test -n "${ZSH_VERSION+set}" ; then + setopt NO_GLOB_SUBST + fi + # Now quote all the things that may contain metacharacters while being + # careful not to overquote the AC_SUBSTed values. We take copies of the + # variables and quote the copies for generation of the libtool script. + for var in echo old_CC old_CFLAGS AR AR_FLAGS EGREP RANLIB LN_S LTCC LTCFLAGS NM \ + SED SHELL STRIP \ + libname_spec library_names_spec soname_spec extract_expsyms_cmds \ + old_striplib striplib file_magic_cmd finish_cmds finish_eval \ + deplibs_check_method reload_flag reload_cmds need_locks \ + lt_cv_sys_global_symbol_pipe lt_cv_sys_global_symbol_to_cdecl \ + lt_cv_sys_global_symbol_to_c_name_address \ + sys_lib_search_path_spec sys_lib_dlsearch_path_spec \ + old_postinstall_cmds old_postuninstall_cmds \ + compiler \ + CC \ + LD \ + lt_prog_compiler_wl \ + lt_prog_compiler_pic \ + lt_prog_compiler_static \ + lt_prog_compiler_no_builtin_flag \ + export_dynamic_flag_spec \ + thread_safe_flag_spec \ + whole_archive_flag_spec \ + enable_shared_with_static_runtimes \ + old_archive_cmds \ + old_archive_from_new_cmds \ + predep_objects \ + postdep_objects \ + predeps \ + postdeps \ + compiler_lib_search_path \ + archive_cmds \ + archive_expsym_cmds \ + postinstall_cmds \ + postuninstall_cmds \ + old_archive_from_expsyms_cmds \ + allow_undefined_flag \ + no_undefined_flag \ + export_symbols_cmds \ + hardcode_libdir_flag_spec \ + hardcode_libdir_flag_spec_ld \ + hardcode_libdir_separator \ + hardcode_automatic \ + module_cmds \ + module_expsym_cmds \ + lt_cv_prog_compiler_c_o \ + exclude_expsyms \ + include_expsyms; do + + case $var in + old_archive_cmds | \ + old_archive_from_new_cmds | \ + archive_cmds | \ + archive_expsym_cmds | \ + module_cmds | \ + module_expsym_cmds | \ + old_archive_from_expsyms_cmds | \ + export_symbols_cmds | \ + extract_expsyms_cmds | reload_cmds | finish_cmds | \ + postinstall_cmds | postuninstall_cmds | \ + old_postinstall_cmds | old_postuninstall_cmds | \ + sys_lib_search_path_spec | sys_lib_dlsearch_path_spec) + # Double-quote double-evaled strings. + eval "lt_$var=\\\"\`\$echo \"X\$$var\" | \$Xsed -e \"\$double_quote_subst\" -e \"\$sed_quote_subst\" -e \"\$delay_variable_subst\"\`\\\"" + ;; + *) + eval "lt_$var=\\\"\`\$echo \"X\$$var\" | \$Xsed -e \"\$sed_quote_subst\"\`\\\"" + ;; + esac + done + + case $lt_echo in + *'\$0 --fallback-echo"') + lt_echo=`$echo "X$lt_echo" | $Xsed -e 's/\\\\\\\$0 --fallback-echo"$/$0 --fallback-echo"/'` + ;; + esac + +cfgfile="${ofile}T" + trap "$rm \"$cfgfile\"; exit 1" 1 2 15 + $rm -f "$cfgfile" + { echo "$as_me:$LINENO: creating $ofile" >&5 +echo "$as_me: creating $ofile" >&6;} + + cat <<__EOF__ >> "$cfgfile" +#! $SHELL + +# `$echo "$cfgfile" | sed 's%^.*/%%'` - Provide generalized library-building support services. +# Generated automatically by $PROGRAM (GNU $PACKAGE $VERSION$TIMESTAMP) +# NOTE: Changes made to this file will be lost: look at ltmain.sh. +# +# Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001 +# Free Software Foundation, Inc. +# +# This file is part of GNU Libtool: +# Originally by Gordon Matzigkeit , 1996 +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, but +# WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +# General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. +# +# As a special exception to the GNU General Public License, if you +# distribute this file as part of a program that contains a +# configuration script generated by Autoconf, you may include it under +# the same distribution terms that you use for the rest of that program. + +# A sed program that does not truncate output. +SED=$lt_SED + +# Sed that helps us avoid accidentally triggering echo(1) options like -n. +Xsed="$SED -e 1s/^X//" + +# The HP-UX ksh and POSIX shell print the target directory to stdout +# if CDPATH is set. +(unset CDPATH) >/dev/null 2>&1 && unset CDPATH + +# The names of the tagged configurations supported by this script. +available_tags= + +# ### BEGIN LIBTOOL CONFIG + +# Libtool was configured on host `(hostname || uname -n) 2>/dev/null | sed 1q`: + +# Shell to use when invoking shell scripts. +SHELL=$lt_SHELL + +# Whether or not to build shared libraries. +build_libtool_libs=$enable_shared + +# Whether or not to build static libraries. +build_old_libs=$enable_static + +# Whether or not to add -lc for building shared libraries. +build_libtool_need_lc=$archive_cmds_need_lc + +# Whether or not to disallow shared libs when runtime libs are static +allow_libtool_libs_with_static_runtimes=$enable_shared_with_static_runtimes + +# Whether or not to optimize for fast installation. +fast_install=$enable_fast_install + +# The host system. +host_alias=$host_alias +host=$host +host_os=$host_os + +# The build system. +build_alias=$build_alias +build=$build +build_os=$build_os + +# An echo program that does not interpret backslashes. +echo=$lt_echo + +# The archiver. +AR=$lt_AR +AR_FLAGS=$lt_AR_FLAGS + +# A C compiler. +LTCC=$lt_LTCC + +# LTCC compiler flags. +LTCFLAGS=$lt_LTCFLAGS + +# A language-specific compiler. +CC=$lt_compiler + +# Is the compiler the GNU C compiler? +with_gcc=$GCC + +# An ERE matcher. +EGREP=$lt_EGREP + +# The linker used to build libraries. +LD=$lt_LD + +# Whether we need hard or soft links. +LN_S=$lt_LN_S + +# A BSD-compatible nm program. +NM=$lt_NM + +# A symbol stripping program +STRIP=$lt_STRIP + +# Used to examine libraries when file_magic_cmd begins "file" +MAGIC_CMD=$MAGIC_CMD + +# Used on cygwin: DLL creation program. +DLLTOOL="$DLLTOOL" + +# Used on cygwin: object dumper. +OBJDUMP="$OBJDUMP" + +# Used on cygwin: assembler. +AS="$AS" + +# The name of the directory that contains temporary libtool files. +objdir=$objdir + +# How to create reloadable object files. +reload_flag=$lt_reload_flag +reload_cmds=$lt_reload_cmds + +# How to pass a linker flag through the compiler. +wl=$lt_lt_prog_compiler_wl + +# Object file suffix (normally "o"). +objext="$ac_objext" + +# Old archive suffix (normally "a"). +libext="$libext" + +# Shared library suffix (normally ".so"). +shrext_cmds='$shrext_cmds' + +# Executable file suffix (normally ""). +exeext="$exeext" + +# Additional compiler flags for building library objects. +pic_flag=$lt_lt_prog_compiler_pic +pic_mode=$pic_mode + +# What is the maximum length of a command? +max_cmd_len=$lt_cv_sys_max_cmd_len + +# Does compiler simultaneously support -c and -o options? +compiler_c_o=$lt_lt_cv_prog_compiler_c_o + +# Must we lock files when doing compilation? +need_locks=$lt_need_locks + +# Do we need the lib prefix for modules? +need_lib_prefix=$need_lib_prefix + +# Do we need a version for libraries? +need_version=$need_version + +# Whether dlopen is supported. +dlopen_support=$enable_dlopen + +# Whether dlopen of programs is supported. +dlopen_self=$enable_dlopen_self + +# Whether dlopen of statically linked programs is supported. +dlopen_self_static=$enable_dlopen_self_static + +# Compiler flag to prevent dynamic linking. +link_static_flag=$lt_lt_prog_compiler_static + +# Compiler flag to turn off builtin functions. +no_builtin_flag=$lt_lt_prog_compiler_no_builtin_flag + +# Compiler flag to allow reflexive dlopens. +export_dynamic_flag_spec=$lt_export_dynamic_flag_spec + +# Compiler flag to generate shared objects directly from archives. +whole_archive_flag_spec=$lt_whole_archive_flag_spec + +# Compiler flag to generate thread-safe objects. +thread_safe_flag_spec=$lt_thread_safe_flag_spec + +# Library versioning type. +version_type=$version_type + +# Format of library name prefix. +libname_spec=$lt_libname_spec + +# List of archive names. First name is the real one, the rest are links. +# The last name is the one that the linker finds with -lNAME. +library_names_spec=$lt_library_names_spec + +# The coded name of the library, if different from the real name. +soname_spec=$lt_soname_spec + +# Commands used to build and install an old-style archive. +RANLIB=$lt_RANLIB +old_archive_cmds=$lt_old_archive_cmds +old_postinstall_cmds=$lt_old_postinstall_cmds +old_postuninstall_cmds=$lt_old_postuninstall_cmds + +# Create an old-style archive from a shared archive. +old_archive_from_new_cmds=$lt_old_archive_from_new_cmds + +# Create a temporary old-style archive to link instead of a shared archive. +old_archive_from_expsyms_cmds=$lt_old_archive_from_expsyms_cmds + +# Commands used to build and install a shared archive. +archive_cmds=$lt_archive_cmds +archive_expsym_cmds=$lt_archive_expsym_cmds +postinstall_cmds=$lt_postinstall_cmds +postuninstall_cmds=$lt_postuninstall_cmds + +# Commands used to build a loadable module (assumed same as above if empty) +module_cmds=$lt_module_cmds +module_expsym_cmds=$lt_module_expsym_cmds + +# Commands to strip libraries. +old_striplib=$lt_old_striplib +striplib=$lt_striplib + +# Dependencies to place before the objects being linked to create a +# shared library. +predep_objects=$lt_predep_objects + +# Dependencies to place after the objects being linked to create a +# shared library. +postdep_objects=$lt_postdep_objects + +# Dependencies to place before the objects being linked to create a +# shared library. +predeps=$lt_predeps + +# Dependencies to place after the objects being linked to create a +# shared library. +postdeps=$lt_postdeps + +# The library search path used internally by the compiler when linking +# a shared library. +compiler_lib_search_path=$lt_compiler_lib_search_path + +# Method to check whether dependent libraries are shared objects. +deplibs_check_method=$lt_deplibs_check_method + +# Command to use when deplibs_check_method == file_magic. +file_magic_cmd=$lt_file_magic_cmd + +# Flag that allows shared libraries with undefined symbols to be built. +allow_undefined_flag=$lt_allow_undefined_flag + +# Flag that forces no undefined symbols. +no_undefined_flag=$lt_no_undefined_flag + +# Commands used to finish a libtool library installation in a directory. +finish_cmds=$lt_finish_cmds + +# Same as above, but a single script fragment to be evaled but not shown. +finish_eval=$lt_finish_eval + +# Take the output of nm and produce a listing of raw symbols and C names. +global_symbol_pipe=$lt_lt_cv_sys_global_symbol_pipe + +# Transform the output of nm in a proper C declaration +global_symbol_to_cdecl=$lt_lt_cv_sys_global_symbol_to_cdecl + +# Transform the output of nm in a C name address pair +global_symbol_to_c_name_address=$lt_lt_cv_sys_global_symbol_to_c_name_address + +# This is the shared library runtime path variable. +runpath_var=$runpath_var + +# This is the shared library path variable. +shlibpath_var=$shlibpath_var + +# Is shlibpath searched before the hard-coded library search path? +shlibpath_overrides_runpath=$shlibpath_overrides_runpath + +# How to hardcode a shared library path into an executable. +hardcode_action=$hardcode_action + +# Whether we should hardcode library paths into libraries. +hardcode_into_libs=$hardcode_into_libs + +# Flag to hardcode \$libdir into a binary during linking. +# This must work even if \$libdir does not exist. +hardcode_libdir_flag_spec=$lt_hardcode_libdir_flag_spec + +# If ld is used when linking, flag to hardcode \$libdir into +# a binary during linking. This must work even if \$libdir does +# not exist. +hardcode_libdir_flag_spec_ld=$lt_hardcode_libdir_flag_spec_ld + +# Whether we need a single -rpath flag with a separated argument. +hardcode_libdir_separator=$lt_hardcode_libdir_separator + +# Set to yes if using DIR/libNAME${shared_ext} during linking hardcodes DIR into the +# resulting binary. +hardcode_direct=$hardcode_direct + +# Set to yes if using the -LDIR flag during linking hardcodes DIR into the +# resulting binary. +hardcode_minus_L=$hardcode_minus_L + +# Set to yes if using SHLIBPATH_VAR=DIR during linking hardcodes DIR into +# the resulting binary. +hardcode_shlibpath_var=$hardcode_shlibpath_var + +# Set to yes if building a shared library automatically hardcodes DIR into the library +# and all subsequent libraries and executables linked against it. +hardcode_automatic=$hardcode_automatic + +# Variables whose values should be saved in libtool wrapper scripts and +# restored at relink time. +variables_saved_for_relink="$variables_saved_for_relink" + +# Whether libtool must link a program against all its dependency libraries. +link_all_deplibs=$link_all_deplibs + +# Compile-time system search path for libraries +sys_lib_search_path_spec=$lt_sys_lib_search_path_spec + +# Run-time system search path for libraries +sys_lib_dlsearch_path_spec=$lt_sys_lib_dlsearch_path_spec + +# Fix the shell variable \$srcfile for the compiler. +fix_srcfile_path="$fix_srcfile_path" + +# Set to yes if exported symbols are required. +always_export_symbols=$always_export_symbols + +# The commands to list exported symbols. +export_symbols_cmds=$lt_export_symbols_cmds + +# The commands to extract the exported symbol list from a shared archive. +extract_expsyms_cmds=$lt_extract_expsyms_cmds + +# Symbols that should not be listed in the preloaded symbols. +exclude_expsyms=$lt_exclude_expsyms + +# Symbols that must always be exported. +include_expsyms=$lt_include_expsyms + +# ### END LIBTOOL CONFIG + +__EOF__ + + + case $host_os in + aix3*) + cat <<\EOF >> "$cfgfile" + +# AIX sometimes has problems with the GCC collect2 program. For some +# reason, if we set the COLLECT_NAMES environment variable, the problems +# vanish in a puff of smoke. +if test "X${COLLECT_NAMES+set}" != Xset; then + COLLECT_NAMES= + export COLLECT_NAMES +fi +EOF + ;; + esac + + # We use sed instead of cat because bash on DJGPP gets confused if + # if finds mixed CR/LF and LF-only lines. Since sed operates in + # text mode, it properly converts lines to CR/LF. This bash problem + # is reportedly fixed, but why not run on old versions too? + sed '$q' "$ltmain" >> "$cfgfile" || (rm -f "$cfgfile"; exit 1) + + mv -f "$cfgfile" "$ofile" || \ + (rm -f "$ofile" && cp "$cfgfile" "$ofile" && rm -f "$cfgfile") + chmod +x "$ofile" + +else + # If there is no Makefile yet, we rely on a make rule to execute + # `config.status --recheck' to rerun these tests and create the + # libtool script then. + ltmain_in=`echo $ltmain | sed -e 's/\.sh$/.in/'` + if test -f "$ltmain_in"; then + test -f Makefile && make "$ltmain" + fi +fi + + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + +CC="$lt_save_CC" + + +# Check whether --with-tags or --without-tags was given. +if test "${with_tags+set}" = set; then + withval="$with_tags" + tagnames="$withval" +fi; + +if test -f "$ltmain" && test -n "$tagnames"; then + if test ! -f "${ofile}"; then + { echo "$as_me:$LINENO: WARNING: output file \`$ofile' does not exist" >&5 +echo "$as_me: WARNING: output file \`$ofile' does not exist" >&2;} + fi + + if test -z "$LTCC"; then + eval "`$SHELL ${ofile} --config | grep '^LTCC='`" + if test -z "$LTCC"; then + { echo "$as_me:$LINENO: WARNING: output file \`$ofile' does not look like a libtool script" >&5 +echo "$as_me: WARNING: output file \`$ofile' does not look like a libtool script" >&2;} + else + { echo "$as_me:$LINENO: WARNING: using \`LTCC=$LTCC', extracted from \`$ofile'" >&5 +echo "$as_me: WARNING: using \`LTCC=$LTCC', extracted from \`$ofile'" >&2;} + fi + fi + if test -z "$LTCFLAGS"; then + eval "`$SHELL ${ofile} --config | grep '^LTCFLAGS='`" + fi + + # Extract list of available tagged configurations in $ofile. + # Note that this assumes the entire list is on one line. + available_tags=`grep "^available_tags=" "${ofile}" | $SED -e 's/available_tags=\(.*$\)/\1/' -e 's/\"//g'` + + lt_save_ifs="$IFS"; IFS="${IFS}$PATH_SEPARATOR," + for tagname in $tagnames; do + IFS="$lt_save_ifs" + # Check whether tagname contains only valid characters + case `$echo "X$tagname" | $Xsed -e 's:[-_ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz1234567890,/]::g'` in + "") ;; + *) { { echo "$as_me:$LINENO: error: invalid tag name: $tagname" >&5 +echo "$as_me: error: invalid tag name: $tagname" >&2;} + { (exit 1); exit 1; }; } + ;; + esac + + if grep "^# ### BEGIN LIBTOOL TAG CONFIG: $tagname$" < "${ofile}" > /dev/null + then + { { echo "$as_me:$LINENO: error: tag name \"$tagname\" already exists" >&5 +echo "$as_me: error: tag name \"$tagname\" already exists" >&2;} + { (exit 1); exit 1; }; } + fi + + # Update the list of available tags. + if test -n "$tagname"; then + echo appending configuration tag \"$tagname\" to $ofile + + case $tagname in + CXX) + if test -n "$CXX" && ( test "X$CXX" != "Xno" && + ( (test "X$CXX" = "Xg++" && `g++ -v >/dev/null 2>&1` ) || + (test "X$CXX" != "Xg++"))) ; then + ac_ext=cc +ac_cpp='$CXXCPP $CPPFLAGS' +ac_compile='$CXX -c $CXXFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CXX -o conftest$ac_exeext $CXXFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_cxx_compiler_gnu + + + + +archive_cmds_need_lc_CXX=no +allow_undefined_flag_CXX= +always_export_symbols_CXX=no +archive_expsym_cmds_CXX= +export_dynamic_flag_spec_CXX= +hardcode_direct_CXX=no +hardcode_libdir_flag_spec_CXX= +hardcode_libdir_flag_spec_ld_CXX= +hardcode_libdir_separator_CXX= +hardcode_minus_L_CXX=no +hardcode_shlibpath_var_CXX=unsupported +hardcode_automatic_CXX=no +module_cmds_CXX= +module_expsym_cmds_CXX= +link_all_deplibs_CXX=unknown +old_archive_cmds_CXX=$old_archive_cmds +no_undefined_flag_CXX= +whole_archive_flag_spec_CXX= +enable_shared_with_static_runtimes_CXX=no + +# Dependencies to place before and after the object being linked: +predep_objects_CXX= +postdep_objects_CXX= +predeps_CXX= +postdeps_CXX= +compiler_lib_search_path_CXX= + +# Source file extension for C++ test sources. +ac_ext=cpp + +# Object file extension for compiled C++ test sources. +objext=o +objext_CXX=$objext + +# Code to be used in simple compile tests +lt_simple_compile_test_code="int some_variable = 0;\n" + +# Code to be used in simple link tests +lt_simple_link_test_code='int main(int, char *[]) { return(0); }\n' + +# ltmain only uses $CC for tagged configurations so make sure $CC is set. + +# If no C compiler was specified, use CC. +LTCC=${LTCC-"$CC"} + +# If no C compiler flags were specified, use CFLAGS. +LTCFLAGS=${LTCFLAGS-"$CFLAGS"} + +# Allow CC to be a program name with arguments. +compiler=$CC + + +# save warnings/boilerplate of simple test code +ac_outfile=conftest.$ac_objext +printf "$lt_simple_compile_test_code" >conftest.$ac_ext +eval "$ac_compile" 2>&1 >/dev/null | $SED '/^$/d; /^ *+/d' >conftest.err +_lt_compiler_boilerplate=`cat conftest.err` +$rm conftest* + +ac_outfile=conftest.$ac_objext +printf "$lt_simple_link_test_code" >conftest.$ac_ext +eval "$ac_link" 2>&1 >/dev/null | $SED '/^$/d; /^ *+/d' >conftest.err +_lt_linker_boilerplate=`cat conftest.err` +$rm conftest* + + +# Allow CC to be a program name with arguments. +lt_save_CC=$CC +lt_save_LD=$LD +lt_save_GCC=$GCC +GCC=$GXX +lt_save_with_gnu_ld=$with_gnu_ld +lt_save_path_LD=$lt_cv_path_LD +if test -n "${lt_cv_prog_gnu_ldcxx+set}"; then + lt_cv_prog_gnu_ld=$lt_cv_prog_gnu_ldcxx +else + $as_unset lt_cv_prog_gnu_ld +fi +if test -n "${lt_cv_path_LDCXX+set}"; then + lt_cv_path_LD=$lt_cv_path_LDCXX +else + $as_unset lt_cv_path_LD +fi +test -z "${LDCXX+set}" || LD=$LDCXX +CC=${CXX-"c++"} +compiler=$CC +compiler_CXX=$CC +for cc_temp in $compiler""; do + case $cc_temp in + compile | *[\\/]compile | ccache | *[\\/]ccache ) ;; + distcc | *[\\/]distcc | purify | *[\\/]purify ) ;; + \-*) ;; + *) break;; + esac +done +cc_basename=`$echo "X$cc_temp" | $Xsed -e 's%.*/%%' -e "s%^$host_alias-%%"` + + +# We don't want -fno-exception wen compiling C++ code, so set the +# no_builtin_flag separately +if test "$GXX" = yes; then + lt_prog_compiler_no_builtin_flag_CXX=' -fno-builtin' +else + lt_prog_compiler_no_builtin_flag_CXX= +fi + +if test "$GXX" = yes; then + # Set up default GNU C++ configuration + + +# Check whether --with-gnu-ld or --without-gnu-ld was given. +if test "${with_gnu_ld+set}" = set; then + withval="$with_gnu_ld" + test "$withval" = no || with_gnu_ld=yes +else + with_gnu_ld=no +fi; +ac_prog=ld +if test "$GCC" = yes; then + # Check if gcc -print-prog-name=ld gives a path. + echo "$as_me:$LINENO: checking for ld used by $CC" >&5 +echo $ECHO_N "checking for ld used by $CC... $ECHO_C" >&6 + case $host in + *-*-mingw*) + # gcc leaves a trailing carriage return which upsets mingw + ac_prog=`($CC -print-prog-name=ld) 2>&5 | tr -d '\015'` ;; + *) + ac_prog=`($CC -print-prog-name=ld) 2>&5` ;; + esac + case $ac_prog in + # Accept absolute paths. + [\\/]* | ?:[\\/]*) + re_direlt='/[^/][^/]*/\.\./' + # Canonicalize the pathname of ld + ac_prog=`echo $ac_prog| $SED 's%\\\\%/%g'` + while echo $ac_prog | grep "$re_direlt" > /dev/null 2>&1; do + ac_prog=`echo $ac_prog| $SED "s%$re_direlt%/%"` + done + test -z "$LD" && LD="$ac_prog" + ;; + "") + # If it fails, then pretend we aren't using GCC. + ac_prog=ld + ;; + *) + # If it is relative, then search for the first ld in PATH. + with_gnu_ld=unknown + ;; + esac +elif test "$with_gnu_ld" = yes; then + echo "$as_me:$LINENO: checking for GNU ld" >&5 +echo $ECHO_N "checking for GNU ld... $ECHO_C" >&6 +else + echo "$as_me:$LINENO: checking for non-GNU ld" >&5 +echo $ECHO_N "checking for non-GNU ld... $ECHO_C" >&6 +fi +if test "${lt_cv_path_LD+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + if test -z "$LD"; then + lt_save_ifs="$IFS"; IFS=$PATH_SEPARATOR + for ac_dir in $PATH; do + IFS="$lt_save_ifs" + test -z "$ac_dir" && ac_dir=. + if test -f "$ac_dir/$ac_prog" || test -f "$ac_dir/$ac_prog$ac_exeext"; then + lt_cv_path_LD="$ac_dir/$ac_prog" + # Check to see if the program is GNU ld. I'd rather use --version, + # but apparently some variants of GNU ld only accept -v. + # Break only if it was the GNU/non-GNU ld that we prefer. + case `"$lt_cv_path_LD" -v 2>&1 &5 +echo "${ECHO_T}$LD" >&6 +else + echo "$as_me:$LINENO: result: no" >&5 +echo "${ECHO_T}no" >&6 +fi +test -z "$LD" && { { echo "$as_me:$LINENO: error: no acceptable ld found in \$PATH" >&5 +echo "$as_me: error: no acceptable ld found in \$PATH" >&2;} + { (exit 1); exit 1; }; } +echo "$as_me:$LINENO: checking if the linker ($LD) is GNU ld" >&5 +echo $ECHO_N "checking if the linker ($LD) is GNU ld... $ECHO_C" >&6 +if test "${lt_cv_prog_gnu_ld+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + # I'd rather use --version here, but apparently some GNU lds only accept -v. +case `$LD -v 2>&1 &5 +echo "${ECHO_T}$lt_cv_prog_gnu_ld" >&6 +with_gnu_ld=$lt_cv_prog_gnu_ld + + + + # Check if GNU C++ uses GNU ld as the underlying linker, since the + # archiving commands below assume that GNU ld is being used. + if test "$with_gnu_ld" = yes; then + archive_cmds_CXX='$CC -shared -nostdlib $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags ${wl}-soname $wl$soname -o $lib' + archive_expsym_cmds_CXX='$CC -shared -nostdlib $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags ${wl}-soname $wl$soname ${wl}-retain-symbols-file $wl$export_symbols -o $lib' + + hardcode_libdir_flag_spec_CXX='${wl}--rpath ${wl}$libdir' + export_dynamic_flag_spec_CXX='${wl}--export-dynamic' + + # If archive_cmds runs LD, not CC, wlarc should be empty + # XXX I think wlarc can be eliminated in ltcf-cxx, but I need to + # investigate it a little bit more. (MM) + wlarc='${wl}' + + # ancient GNU ld didn't support --whole-archive et. al. + if eval "`$CC -print-prog-name=ld` --help 2>&1" | \ + grep 'no-whole-archive' > /dev/null; then + whole_archive_flag_spec_CXX="$wlarc"'--whole-archive$convenience '"$wlarc"'--no-whole-archive' + else + whole_archive_flag_spec_CXX= + fi + else + with_gnu_ld=no + wlarc= + + # A generic and very simple default shared library creation + # command for GNU C++ for the case where it uses the native + # linker, instead of GNU ld. If possible, this setting should + # overridden to take advantage of the native linker features on + # the platform it is being used on. + archive_cmds_CXX='$CC -shared -nostdlib $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags -o $lib' + fi + + # Commands to make compiler produce verbose output that lists + # what "hidden" libraries, object files and flags are used when + # linking a shared library. + output_verbose_link_cmd='$CC -shared $CFLAGS -v conftest.$objext 2>&1 | grep "\-L"' + +else + GXX=no + with_gnu_ld=no + wlarc= +fi + +# PORTME: fill in a description of your system's C++ link characteristics +echo "$as_me:$LINENO: checking whether the $compiler linker ($LD) supports shared libraries" >&5 +echo $ECHO_N "checking whether the $compiler linker ($LD) supports shared libraries... $ECHO_C" >&6 +ld_shlibs_CXX=yes +case $host_os in + aix3*) + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + aix4* | aix5*) + if test "$host_cpu" = ia64; then + # On IA64, the linker does run time linking by default, so we don't + # have to do anything special. + aix_use_runtimelinking=no + exp_sym_flag='-Bexport' + no_entry_flag="" + else + aix_use_runtimelinking=no + + # Test if we are trying to use run time linking or normal + # AIX style linking. If -brtl is somewhere in LDFLAGS, we + # need to do runtime linking. + case $host_os in aix4.[23]|aix4.[23].*|aix5*) + for ld_flag in $LDFLAGS; do + case $ld_flag in + *-brtl*) + aix_use_runtimelinking=yes + break + ;; + esac + done + ;; + esac + + exp_sym_flag='-bexport' + no_entry_flag='-bnoentry' + fi + + # When large executables or shared objects are built, AIX ld can + # have problems creating the table of contents. If linking a library + # or program results in "error TOC overflow" add -mminimal-toc to + # CXXFLAGS/CFLAGS for g++/gcc. In the cases where that is not + # enough to fix the problem, add -Wl,-bbigtoc to LDFLAGS. + + archive_cmds_CXX='' + hardcode_direct_CXX=yes + hardcode_libdir_separator_CXX=':' + link_all_deplibs_CXX=yes + + if test "$GXX" = yes; then + case $host_os in aix4.[012]|aix4.[012].*) + # We only want to do this on AIX 4.2 and lower, the check + # below for broken collect2 doesn't work under 4.3+ + collect2name=`${CC} -print-prog-name=collect2` + if test -f "$collect2name" && \ + strings "$collect2name" | grep resolve_lib_name >/dev/null + then + # We have reworked collect2 + hardcode_direct_CXX=yes + else + # We have old collect2 + hardcode_direct_CXX=unsupported + # It fails to find uninstalled libraries when the uninstalled + # path is not listed in the libpath. Setting hardcode_minus_L + # to unsupported forces relinking + hardcode_minus_L_CXX=yes + hardcode_libdir_flag_spec_CXX='-L$libdir' + hardcode_libdir_separator_CXX= + fi + ;; + esac + shared_flag='-shared' + if test "$aix_use_runtimelinking" = yes; then + shared_flag="$shared_flag "'${wl}-G' + fi + else + # not using gcc + if test "$host_cpu" = ia64; then + # VisualAge C++, Version 5.5 for AIX 5L for IA-64, Beta 3 Release + # chokes on -Wl,-G. The following line is correct: + shared_flag='-G' + else + if test "$aix_use_runtimelinking" = yes; then + shared_flag='${wl}-G' + else + shared_flag='${wl}-bM:SRE' + fi + fi + fi + + # It seems that -bexpall does not export symbols beginning with + # underscore (_), so it is better to generate a list of symbols to export. + always_export_symbols_CXX=yes + if test "$aix_use_runtimelinking" = yes; then + # Warning - without using the other runtime loading flags (-brtl), + # -berok will link without error, but may produce a broken library. + allow_undefined_flag_CXX='-berok' + # Determine the default libpath from the value encoded in an empty executable. + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext conftest$ac_exeext +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_cxx_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest$ac_exeext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + +aix_libpath=`dump -H conftest$ac_exeext 2>/dev/null | $SED -n -e '/Import File Strings/,/^$/ { /^0/ { s/^0 *\(.*\)$/\1/; p; } +}'` +# Check for a 64-bit object if we didn't find anything. +if test -z "$aix_libpath"; then aix_libpath=`dump -HX64 conftest$ac_exeext 2>/dev/null | $SED -n -e '/Import File Strings/,/^$/ { /^0/ { s/^0 *\(.*\)$/\1/; p; } +}'`; fi +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +fi +rm -f conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +if test -z "$aix_libpath"; then aix_libpath="/usr/lib:/lib"; fi + + hardcode_libdir_flag_spec_CXX='${wl}-blibpath:$libdir:'"$aix_libpath" + + archive_expsym_cmds_CXX="\$CC"' -o $output_objdir/$soname $libobjs $deplibs '"\${wl}$no_entry_flag"' $compiler_flags `if test "x${allow_undefined_flag}" != "x"; then echo "${wl}${allow_undefined_flag}"; else :; fi` '"\${wl}$exp_sym_flag:\$export_symbols $shared_flag" + else + if test "$host_cpu" = ia64; then + hardcode_libdir_flag_spec_CXX='${wl}-R $libdir:/usr/lib:/lib' + allow_undefined_flag_CXX="-z nodefs" + archive_expsym_cmds_CXX="\$CC $shared_flag"' -o $output_objdir/$soname $libobjs $deplibs '"\${wl}$no_entry_flag"' $compiler_flags ${wl}${allow_undefined_flag} '"\${wl}$exp_sym_flag:\$export_symbols" + else + # Determine the default libpath from the value encoded in an empty executable. + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext conftest$ac_exeext +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_cxx_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest$ac_exeext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + +aix_libpath=`dump -H conftest$ac_exeext 2>/dev/null | $SED -n -e '/Import File Strings/,/^$/ { /^0/ { s/^0 *\(.*\)$/\1/; p; } +}'` +# Check for a 64-bit object if we didn't find anything. +if test -z "$aix_libpath"; then aix_libpath=`dump -HX64 conftest$ac_exeext 2>/dev/null | $SED -n -e '/Import File Strings/,/^$/ { /^0/ { s/^0 *\(.*\)$/\1/; p; } +}'`; fi +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +fi +rm -f conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +if test -z "$aix_libpath"; then aix_libpath="/usr/lib:/lib"; fi + + hardcode_libdir_flag_spec_CXX='${wl}-blibpath:$libdir:'"$aix_libpath" + # Warning - without using the other run time loading flags, + # -berok will link without error, but may produce a broken library. + no_undefined_flag_CXX=' ${wl}-bernotok' + allow_undefined_flag_CXX=' ${wl}-berok' + # Exported symbols can be pulled into shared objects from archives + whole_archive_flag_spec_CXX='$convenience' + archive_cmds_need_lc_CXX=yes + # This is similar to how AIX traditionally builds its shared libraries. + archive_expsym_cmds_CXX="\$CC $shared_flag"' -o $output_objdir/$soname $libobjs $deplibs ${wl}-bnoentry $compiler_flags ${wl}-bE:$export_symbols${allow_undefined_flag}~$AR $AR_FLAGS $output_objdir/$libname$release.a $output_objdir/$soname' + fi + fi + ;; + + beos*) + if $LD --help 2>&1 | grep ': supported targets:.* elf' > /dev/null; then + allow_undefined_flag_CXX=unsupported + # Joseph Beckenbach says some releases of gcc + # support --undefined. This deserves some investigation. FIXME + archive_cmds_CXX='$CC -nostart $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + else + ld_shlibs_CXX=no + fi + ;; + + chorus*) + case $cc_basename in + *) + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + esac + ;; + + cygwin* | mingw* | pw32*) + # _LT_AC_TAGVAR(hardcode_libdir_flag_spec, CXX) is actually meaningless, + # as there is no search path for DLLs. + hardcode_libdir_flag_spec_CXX='-L$libdir' + allow_undefined_flag_CXX=unsupported + always_export_symbols_CXX=no + enable_shared_with_static_runtimes_CXX=yes + + if $LD --help 2>&1 | grep 'auto-import' > /dev/null; then + archive_cmds_CXX='$CC -shared -nostdlib $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags -o $output_objdir/$soname ${wl}--enable-auto-image-base -Xlinker --out-implib -Xlinker $lib' + # If the export-symbols file already is a .def file (1st line + # is EXPORTS), use it as is; otherwise, prepend... + archive_expsym_cmds_CXX='if test "x`$SED 1q $export_symbols`" = xEXPORTS; then + cp $export_symbols $output_objdir/$soname.def; + else + echo EXPORTS > $output_objdir/$soname.def; + cat $export_symbols >> $output_objdir/$soname.def; + fi~ + $CC -shared -nostdlib $output_objdir/$soname.def $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags -o $output_objdir/$soname ${wl}--enable-auto-image-base -Xlinker --out-implib -Xlinker $lib' + else + ld_shlibs_CXX=no + fi + ;; + darwin* | rhapsody*) + case $host_os in + rhapsody* | darwin1.[012]) + allow_undefined_flag_CXX='${wl}-undefined ${wl}suppress' + ;; + *) # Darwin 1.3 on + if test -z ${MACOSX_DEPLOYMENT_TARGET} ; then + allow_undefined_flag_CXX='${wl}-flat_namespace ${wl}-undefined ${wl}suppress' + else + case ${MACOSX_DEPLOYMENT_TARGET} in + 10.[012]) + allow_undefined_flag_CXX='${wl}-flat_namespace ${wl}-undefined ${wl}suppress' + ;; + 10.*) + allow_undefined_flag_CXX='${wl}-undefined ${wl}dynamic_lookup' + ;; + esac + fi + ;; + esac + archive_cmds_need_lc_CXX=no + hardcode_direct_CXX=no + hardcode_automatic_CXX=yes + hardcode_shlibpath_var_CXX=unsupported + whole_archive_flag_spec_CXX='' + link_all_deplibs_CXX=yes + + if test "$GXX" = yes ; then + lt_int_apple_cc_single_mod=no + output_verbose_link_cmd='echo' + if $CC -dumpspecs 2>&1 | $EGREP 'single_module' >/dev/null ; then + lt_int_apple_cc_single_mod=yes + fi + if test "X$lt_int_apple_cc_single_mod" = Xyes ; then + archive_cmds_CXX='$CC -dynamiclib -single_module $allow_undefined_flag -o $lib $libobjs $deplibs $compiler_flags -install_name $rpath/$soname $verstring' + else + archive_cmds_CXX='$CC -r -keep_private_externs -nostdlib -o ${lib}-master.o $libobjs~$CC -dynamiclib $allow_undefined_flag -o $lib ${lib}-master.o $deplibs $compiler_flags -install_name $rpath/$soname $verstring' + fi + module_cmds_CXX='$CC $allow_undefined_flag -o $lib -bundle $libobjs $deplibs$compiler_flags' + # Don't fix this by using the ld -exported_symbols_list flag, it doesn't exist in older darwin lds + if test "X$lt_int_apple_cc_single_mod" = Xyes ; then + archive_expsym_cmds_CXX='sed -e "s,#.*,," -e "s,^[ ]*,," -e "s,^\(..*\),_&," < $export_symbols > $output_objdir/${libname}-symbols.expsym~$CC -dynamiclib -single_module $allow_undefined_flag -o $lib $libobjs $deplibs $compiler_flags -install_name $rpath/$soname $verstring~nmedit -s $output_objdir/${libname}-symbols.expsym ${lib}' + else + archive_expsym_cmds_CXX='sed -e "s,#.*,," -e "s,^[ ]*,," -e "s,^\(..*\),_&," < $export_symbols > $output_objdir/${libname}-symbols.expsym~$CC -r -keep_private_externs -nostdlib -o ${lib}-master.o $libobjs~$CC -dynamiclib $allow_undefined_flag -o $lib ${lib}-master.o $deplibs $compiler_flags -install_name $rpath/$soname $verstring~nmedit -s $output_objdir/${libname}-symbols.expsym ${lib}' + fi + module_expsym_cmds_CXX='sed -e "s,#.*,," -e "s,^[ ]*,," -e "s,^\(..*\),_&," < $export_symbols > $output_objdir/${libname}-symbols.expsym~$CC $allow_undefined_flag -o $lib -bundle $libobjs $deplibs$compiler_flags~nmedit -s $output_objdir/${libname}-symbols.expsym ${lib}' + else + case $cc_basename in + xlc*) + output_verbose_link_cmd='echo' + archive_cmds_CXX='$CC -qmkshrobj ${wl}-single_module $allow_undefined_flag -o $lib $libobjs $deplibs $compiler_flags ${wl}-install_name ${wl}`echo $rpath/$soname` $verstring' + module_cmds_CXX='$CC $allow_undefined_flag -o $lib -bundle $libobjs $deplibs$compiler_flags' + # Don't fix this by using the ld -exported_symbols_list flag, it doesn't exist in older darwin lds + archive_expsym_cmds_CXX='sed -e "s,#.*,," -e "s,^[ ]*,," -e "s,^\(..*\),_&," < $export_symbols > $output_objdir/${libname}-symbols.expsym~$CC -qmkshrobj ${wl}-single_module $allow_undefined_flag -o $lib $libobjs $deplibs $compiler_flags ${wl}-install_name ${wl}$rpath/$soname $verstring~nmedit -s $output_objdir/${libname}-symbols.expsym ${lib}' + module_expsym_cmds_CXX='sed -e "s,#.*,," -e "s,^[ ]*,," -e "s,^\(..*\),_&," < $export_symbols > $output_objdir/${libname}-symbols.expsym~$CC $allow_undefined_flag -o $lib -bundle $libobjs $deplibs$compiler_flags~nmedit -s $output_objdir/${libname}-symbols.expsym ${lib}' + ;; + *) + ld_shlibs_CXX=no + ;; + esac + fi + ;; + + dgux*) + case $cc_basename in + ec++*) + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + ghcx*) + # Green Hills C++ Compiler + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + *) + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + esac + ;; + freebsd[12]*) + # C++ shared libraries reported to be fairly broken before switch to ELF + ld_shlibs_CXX=no + ;; + freebsd-elf*) + archive_cmds_need_lc_CXX=no + ;; + freebsd* | kfreebsd*-gnu | dragonfly*) + # FreeBSD 3 and later use GNU C++ and GNU ld with standard ELF + # conventions + ld_shlibs_CXX=yes + ;; + gnu*) + ;; + hpux9*) + hardcode_libdir_flag_spec_CXX='${wl}+b ${wl}$libdir' + hardcode_libdir_separator_CXX=: + export_dynamic_flag_spec_CXX='${wl}-E' + hardcode_direct_CXX=yes + hardcode_minus_L_CXX=yes # Not in the search PATH, + # but as the default + # location of the library. + + case $cc_basename in + CC*) + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + aCC*) + archive_cmds_CXX='$rm $output_objdir/$soname~$CC -b ${wl}+b ${wl}$install_libdir -o $output_objdir/$soname $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags~test $output_objdir/$soname = $lib || mv $output_objdir/$soname $lib' + # Commands to make compiler produce verbose output that lists + # what "hidden" libraries, object files and flags are used when + # linking a shared library. + # + # There doesn't appear to be a way to prevent this compiler from + # explicitly linking system object files so we need to strip them + # from the output so that they don't get included in the library + # dependencies. + output_verbose_link_cmd='templist=`($CC -b $CFLAGS -v conftest.$objext 2>&1) | grep "[-]L"`; list=""; for z in $templist; do case $z in conftest.$objext) list="$list $z";; *.$objext);; *) list="$list $z";;esac; done; echo $list' + ;; + *) + if test "$GXX" = yes; then + archive_cmds_CXX='$rm $output_objdir/$soname~$CC -shared -nostdlib -fPIC ${wl}+b ${wl}$install_libdir -o $output_objdir/$soname $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags~test $output_objdir/$soname = $lib || mv $output_objdir/$soname $lib' + else + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + fi + ;; + esac + ;; + hpux10*|hpux11*) + if test $with_gnu_ld = no; then + hardcode_libdir_flag_spec_CXX='${wl}+b ${wl}$libdir' + hardcode_libdir_separator_CXX=: + + case $host_cpu in + hppa*64*|ia64*) + hardcode_libdir_flag_spec_ld_CXX='+b $libdir' + ;; + *) + export_dynamic_flag_spec_CXX='${wl}-E' + ;; + esac + fi + case $host_cpu in + hppa*64*|ia64*) + hardcode_direct_CXX=no + hardcode_shlibpath_var_CXX=no + ;; + *) + hardcode_direct_CXX=yes + hardcode_minus_L_CXX=yes # Not in the search PATH, + # but as the default + # location of the library. + ;; + esac + + case $cc_basename in + CC*) + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + aCC*) + case $host_cpu in + hppa*64*) + archive_cmds_CXX='$CC -b ${wl}+h ${wl}$soname -o $lib $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags' + ;; + ia64*) + archive_cmds_CXX='$CC -b ${wl}+h ${wl}$soname ${wl}+nodefaultrpath -o $lib $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags' + ;; + *) + archive_cmds_CXX='$CC -b ${wl}+h ${wl}$soname ${wl}+b ${wl}$install_libdir -o $lib $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags' + ;; + esac + # Commands to make compiler produce verbose output that lists + # what "hidden" libraries, object files and flags are used when + # linking a shared library. + # + # There doesn't appear to be a way to prevent this compiler from + # explicitly linking system object files so we need to strip them + # from the output so that they don't get included in the library + # dependencies. + output_verbose_link_cmd='templist=`($CC -b $CFLAGS -v conftest.$objext 2>&1) | grep "\-L"`; list=""; for z in $templist; do case $z in conftest.$objext) list="$list $z";; *.$objext);; *) list="$list $z";;esac; done; echo $list' + ;; + *) + if test "$GXX" = yes; then + if test $with_gnu_ld = no; then + case $host_cpu in + hppa*64*) + archive_cmds_CXX='$CC -shared -nostdlib -fPIC ${wl}+h ${wl}$soname -o $lib $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags' + ;; + ia64*) + archive_cmds_CXX='$CC -shared -nostdlib -fPIC ${wl}+h ${wl}$soname ${wl}+nodefaultrpath -o $lib $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags' + ;; + *) + archive_cmds_CXX='$CC -shared -nostdlib -fPIC ${wl}+h ${wl}$soname ${wl}+b ${wl}$install_libdir -o $lib $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags' + ;; + esac + fi + else + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + fi + ;; + esac + ;; + interix3*) + hardcode_direct_CXX=no + hardcode_shlibpath_var_CXX=no + hardcode_libdir_flag_spec_CXX='${wl}-rpath,$libdir' + export_dynamic_flag_spec_CXX='${wl}-E' + # Hack: On Interix 3.x, we cannot compile PIC because of a broken gcc. + # Instead, shared libraries are loaded at an image base (0x10000000 by + # default) and relocated if they conflict, which is a slow very memory + # consuming and fragmenting process. To avoid this, we pick a random, + # 256 KiB-aligned image base between 0x50000000 and 0x6FFC0000 at link + # time. Moving up from 0x10000000 also allows more sbrk(2) space. + archive_cmds_CXX='$CC -shared $pic_flag $libobjs $deplibs $compiler_flags ${wl}-h,$soname ${wl}--image-base,`expr ${RANDOM-$$} % 4096 / 2 \* 262144 + 1342177280` -o $lib' + archive_expsym_cmds_CXX='sed "s,^,_," $export_symbols >$output_objdir/$soname.expsym~$CC -shared $pic_flag $libobjs $deplibs $compiler_flags ${wl}-h,$soname ${wl}--retain-symbols-file,$output_objdir/$soname.expsym ${wl}--image-base,`expr ${RANDOM-$$} % 4096 / 2 \* 262144 + 1342177280` -o $lib' + ;; + irix5* | irix6*) + case $cc_basename in + CC*) + # SGI C++ + archive_cmds_CXX='$CC -shared -all -multigot $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${output_objdir}/so_locations -o $lib' + + # Archives containing C++ object files must be created using + # "CC -ar", where "CC" is the IRIX C++ compiler. This is + # necessary to make sure instantiated templates are included + # in the archive. + old_archive_cmds_CXX='$CC -ar -WR,-u -o $oldlib $oldobjs' + ;; + *) + if test "$GXX" = yes; then + if test "$with_gnu_ld" = no; then + archive_cmds_CXX='$CC -shared -nostdlib $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags ${wl}-soname ${wl}$soname `test -n "$verstring" && echo ${wl}-set_version ${wl}$verstring` ${wl}-update_registry ${wl}${output_objdir}/so_locations -o $lib' + else + archive_cmds_CXX='$CC -shared -nostdlib $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags ${wl}-soname ${wl}$soname `test -n "$verstring" && echo ${wl}-set_version ${wl}$verstring` -o $lib' + fi + fi + link_all_deplibs_CXX=yes + ;; + esac + hardcode_libdir_flag_spec_CXX='${wl}-rpath ${wl}$libdir' + hardcode_libdir_separator_CXX=: + ;; + linux*) + case $cc_basename in + KCC*) + # Kuck and Associates, Inc. (KAI) C++ Compiler + + # KCC will only create a shared library if the output file + # ends with ".so" (or ".sl" for HP-UX), so rename the library + # to its proper name (with version) after linking. + archive_cmds_CXX='tempext=`echo $shared_ext | $SED -e '\''s/\([^()0-9A-Za-z{}]\)/\\\\\1/g'\''`; templib=`echo $lib | $SED -e "s/\${tempext}\..*/.so/"`; $CC $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags --soname $soname -o \$templib; mv \$templib $lib' + archive_expsym_cmds_CXX='tempext=`echo $shared_ext | $SED -e '\''s/\([^()0-9A-Za-z{}]\)/\\\\\1/g'\''`; templib=`echo $lib | $SED -e "s/\${tempext}\..*/.so/"`; $CC $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags --soname $soname -o \$templib ${wl}-retain-symbols-file,$export_symbols; mv \$templib $lib' + # Commands to make compiler produce verbose output that lists + # what "hidden" libraries, object files and flags are used when + # linking a shared library. + # + # There doesn't appear to be a way to prevent this compiler from + # explicitly linking system object files so we need to strip them + # from the output so that they don't get included in the library + # dependencies. + output_verbose_link_cmd='templist=`$CC $CFLAGS -v conftest.$objext -o libconftest$shared_ext 2>&1 | grep "ld"`; rm -f libconftest$shared_ext; list=""; for z in $templist; do case $z in conftest.$objext) list="$list $z";; *.$objext);; *) list="$list $z";;esac; done; echo $list' + + hardcode_libdir_flag_spec_CXX='${wl}--rpath,$libdir' + export_dynamic_flag_spec_CXX='${wl}--export-dynamic' + + # Archives containing C++ object files must be created using + # "CC -Bstatic", where "CC" is the KAI C++ compiler. + old_archive_cmds_CXX='$CC -Bstatic -o $oldlib $oldobjs' + ;; + icpc*) + # Intel C++ + with_gnu_ld=yes + # version 8.0 and above of icpc choke on multiply defined symbols + # if we add $predep_objects and $postdep_objects, however 7.1 and + # earlier do not add the objects themselves. + case `$CC -V 2>&1` in + *"Version 7."*) + archive_cmds_CXX='$CC -shared $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags ${wl}-soname $wl$soname -o $lib' + archive_expsym_cmds_CXX='$CC -shared $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags ${wl}-soname $wl$soname ${wl}-retain-symbols-file $wl$export_symbols -o $lib' + ;; + *) # Version 8.0 or newer + tmp_idyn= + case $host_cpu in + ia64*) tmp_idyn=' -i_dynamic';; + esac + archive_cmds_CXX='$CC -shared'"$tmp_idyn"' $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + archive_expsym_cmds_CXX='$CC -shared'"$tmp_idyn"' $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-retain-symbols-file $wl$export_symbols -o $lib' + ;; + esac + archive_cmds_need_lc_CXX=no + hardcode_libdir_flag_spec_CXX='${wl}-rpath,$libdir' + export_dynamic_flag_spec_CXX='${wl}--export-dynamic' + whole_archive_flag_spec_CXX='${wl}--whole-archive$convenience ${wl}--no-whole-archive' + ;; + pgCC*) + # Portland Group C++ compiler + archive_cmds_CXX='$CC -shared $pic_flag $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags ${wl}-soname ${wl}$soname -o $lib' + archive_expsym_cmds_CXX='$CC -shared $pic_flag $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags ${wl}-soname ${wl}$soname ${wl}-retain-symbols-file ${wl}$export_symbols -o $lib' + + hardcode_libdir_flag_spec_CXX='${wl}--rpath ${wl}$libdir' + export_dynamic_flag_spec_CXX='${wl}--export-dynamic' + whole_archive_flag_spec_CXX='${wl}--whole-archive`for conv in $convenience\"\"; do test -n \"$conv\" && new_convenience=\"$new_convenience,$conv\"; done; $echo \"$new_convenience\"` ${wl}--no-whole-archive' + ;; + cxx*) + # Compaq C++ + archive_cmds_CXX='$CC -shared $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags ${wl}-soname $wl$soname -o $lib' + archive_expsym_cmds_CXX='$CC -shared $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags ${wl}-soname $wl$soname -o $lib ${wl}-retain-symbols-file $wl$export_symbols' + + runpath_var=LD_RUN_PATH + hardcode_libdir_flag_spec_CXX='-rpath $libdir' + hardcode_libdir_separator_CXX=: + + # Commands to make compiler produce verbose output that lists + # what "hidden" libraries, object files and flags are used when + # linking a shared library. + # + # There doesn't appear to be a way to prevent this compiler from + # explicitly linking system object files so we need to strip them + # from the output so that they don't get included in the library + # dependencies. + output_verbose_link_cmd='templist=`$CC -shared $CFLAGS -v conftest.$objext 2>&1 | grep "ld"`; templist=`echo $templist | $SED "s/\(^.*ld.*\)\( .*ld .*$\)/\1/"`; list=""; for z in $templist; do case $z in conftest.$objext) list="$list $z";; *.$objext);; *) list="$list $z";;esac; done; echo $list' + ;; + esac + ;; + lynxos*) + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + m88k*) + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + mvs*) + case $cc_basename in + cxx*) + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + *) + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + esac + ;; + netbsd*) + if echo __ELF__ | $CC -E - | grep __ELF__ >/dev/null; then + archive_cmds_CXX='$LD -Bshareable -o $lib $predep_objects $libobjs $deplibs $postdep_objects $linker_flags' + wlarc= + hardcode_libdir_flag_spec_CXX='-R$libdir' + hardcode_direct_CXX=yes + hardcode_shlibpath_var_CXX=no + fi + # Workaround some broken pre-1.5 toolchains + output_verbose_link_cmd='$CC -shared $CFLAGS -v conftest.$objext 2>&1 | grep conftest.$objext | $SED -e "s:-lgcc -lc -lgcc::"' + ;; + openbsd2*) + # C++ shared libraries are fairly broken + ld_shlibs_CXX=no + ;; + openbsd*) + hardcode_direct_CXX=yes + hardcode_shlibpath_var_CXX=no + archive_cmds_CXX='$CC -shared $pic_flag $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags -o $lib' + hardcode_libdir_flag_spec_CXX='${wl}-rpath,$libdir' + if test -z "`echo __ELF__ | $CC -E - | grep __ELF__`" || test "$host_os-$host_cpu" = "openbsd2.8-powerpc"; then + archive_expsym_cmds_CXX='$CC -shared $pic_flag $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags ${wl}-retain-symbols-file,$export_symbols -o $lib' + export_dynamic_flag_spec_CXX='${wl}-E' + whole_archive_flag_spec_CXX="$wlarc"'--whole-archive$convenience '"$wlarc"'--no-whole-archive' + fi + output_verbose_link_cmd='echo' + ;; + osf3*) + case $cc_basename in + KCC*) + # Kuck and Associates, Inc. (KAI) C++ Compiler + + # KCC will only create a shared library if the output file + # ends with ".so" (or ".sl" for HP-UX), so rename the library + # to its proper name (with version) after linking. + archive_cmds_CXX='tempext=`echo $shared_ext | $SED -e '\''s/\([^()0-9A-Za-z{}]\)/\\\\\1/g'\''`; templib=`echo $lib | $SED -e "s/\${tempext}\..*/.so/"`; $CC $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags --soname $soname -o \$templib; mv \$templib $lib' + + hardcode_libdir_flag_spec_CXX='${wl}-rpath,$libdir' + hardcode_libdir_separator_CXX=: + + # Archives containing C++ object files must be created using + # "CC -Bstatic", where "CC" is the KAI C++ compiler. + old_archive_cmds_CXX='$CC -Bstatic -o $oldlib $oldobjs' + + ;; + RCC*) + # Rational C++ 2.4.1 + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + cxx*) + allow_undefined_flag_CXX=' ${wl}-expect_unresolved ${wl}\*' + archive_cmds_CXX='$CC -shared${allow_undefined_flag} $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags ${wl}-soname $soname `test -n "$verstring" && echo ${wl}-set_version $verstring` -update_registry ${output_objdir}/so_locations -o $lib' + + hardcode_libdir_flag_spec_CXX='${wl}-rpath ${wl}$libdir' + hardcode_libdir_separator_CXX=: + + # Commands to make compiler produce verbose output that lists + # what "hidden" libraries, object files and flags are used when + # linking a shared library. + # + # There doesn't appear to be a way to prevent this compiler from + # explicitly linking system object files so we need to strip them + # from the output so that they don't get included in the library + # dependencies. + output_verbose_link_cmd='templist=`$CC -shared $CFLAGS -v conftest.$objext 2>&1 | grep "ld" | grep -v "ld:"`; templist=`echo $templist | $SED "s/\(^.*ld.*\)\( .*ld.*$\)/\1/"`; list=""; for z in $templist; do case $z in conftest.$objext) list="$list $z";; *.$objext);; *) list="$list $z";;esac; done; echo $list' + ;; + *) + if test "$GXX" = yes && test "$with_gnu_ld" = no; then + allow_undefined_flag_CXX=' ${wl}-expect_unresolved ${wl}\*' + archive_cmds_CXX='$CC -shared -nostdlib ${allow_undefined_flag} $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags ${wl}-soname ${wl}$soname `test -n "$verstring" && echo ${wl}-set_version ${wl}$verstring` ${wl}-update_registry ${wl}${output_objdir}/so_locations -o $lib' + + hardcode_libdir_flag_spec_CXX='${wl}-rpath ${wl}$libdir' + hardcode_libdir_separator_CXX=: + + # Commands to make compiler produce verbose output that lists + # what "hidden" libraries, object files and flags are used when + # linking a shared library. + output_verbose_link_cmd='$CC -shared $CFLAGS -v conftest.$objext 2>&1 | grep "\-L"' + + else + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + fi + ;; + esac + ;; + osf4* | osf5*) + case $cc_basename in + KCC*) + # Kuck and Associates, Inc. (KAI) C++ Compiler + + # KCC will only create a shared library if the output file + # ends with ".so" (or ".sl" for HP-UX), so rename the library + # to its proper name (with version) after linking. + archive_cmds_CXX='tempext=`echo $shared_ext | $SED -e '\''s/\([^()0-9A-Za-z{}]\)/\\\\\1/g'\''`; templib=`echo $lib | $SED -e "s/\${tempext}\..*/.so/"`; $CC $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags --soname $soname -o \$templib; mv \$templib $lib' + + hardcode_libdir_flag_spec_CXX='${wl}-rpath,$libdir' + hardcode_libdir_separator_CXX=: + + # Archives containing C++ object files must be created using + # the KAI C++ compiler. + old_archive_cmds_CXX='$CC -o $oldlib $oldobjs' + ;; + RCC*) + # Rational C++ 2.4.1 + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + cxx*) + allow_undefined_flag_CXX=' -expect_unresolved \*' + archive_cmds_CXX='$CC -shared${allow_undefined_flag} $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags -msym -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${output_objdir}/so_locations -o $lib' + archive_expsym_cmds_CXX='for i in `cat $export_symbols`; do printf "%s %s\\n" -exported_symbol "\$i" >> $lib.exp; done~ + echo "-hidden">> $lib.exp~ + $CC -shared$allow_undefined_flag $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags -msym -soname $soname -Wl,-input -Wl,$lib.exp `test -n "$verstring" && echo -set_version $verstring` -update_registry ${output_objdir}/so_locations -o $lib~ + $rm $lib.exp' + + hardcode_libdir_flag_spec_CXX='-rpath $libdir' + hardcode_libdir_separator_CXX=: + + # Commands to make compiler produce verbose output that lists + # what "hidden" libraries, object files and flags are used when + # linking a shared library. + # + # There doesn't appear to be a way to prevent this compiler from + # explicitly linking system object files so we need to strip them + # from the output so that they don't get included in the library + # dependencies. + output_verbose_link_cmd='templist=`$CC -shared $CFLAGS -v conftest.$objext 2>&1 | grep "ld" | grep -v "ld:"`; templist=`echo $templist | $SED "s/\(^.*ld.*\)\( .*ld.*$\)/\1/"`; list=""; for z in $templist; do case $z in conftest.$objext) list="$list $z";; *.$objext);; *) list="$list $z";;esac; done; echo $list' + ;; + *) + if test "$GXX" = yes && test "$with_gnu_ld" = no; then + allow_undefined_flag_CXX=' ${wl}-expect_unresolved ${wl}\*' + archive_cmds_CXX='$CC -shared -nostdlib ${allow_undefined_flag} $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags ${wl}-msym ${wl}-soname ${wl}$soname `test -n "$verstring" && echo ${wl}-set_version ${wl}$verstring` ${wl}-update_registry ${wl}${output_objdir}/so_locations -o $lib' + + hardcode_libdir_flag_spec_CXX='${wl}-rpath ${wl}$libdir' + hardcode_libdir_separator_CXX=: + + # Commands to make compiler produce verbose output that lists + # what "hidden" libraries, object files and flags are used when + # linking a shared library. + output_verbose_link_cmd='$CC -shared $CFLAGS -v conftest.$objext 2>&1 | grep "\-L"' + + else + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + fi + ;; + esac + ;; + psos*) + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + sunos4*) + case $cc_basename in + CC*) + # Sun C++ 4.x + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + lcc*) + # Lucid + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + *) + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + esac + ;; + solaris*) + case $cc_basename in + CC*) + # Sun C++ 4.2, 5.x and Centerline C++ + archive_cmds_need_lc_CXX=yes + no_undefined_flag_CXX=' -zdefs' + archive_cmds_CXX='$CC -G${allow_undefined_flag} -h$soname -o $lib $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags' + archive_expsym_cmds_CXX='$echo "{ global:" > $lib.exp~cat $export_symbols | $SED -e "s/\(.*\)/\1;/" >> $lib.exp~$echo "local: *; };" >> $lib.exp~ + $CC -G${allow_undefined_flag} ${wl}-M ${wl}$lib.exp -h$soname -o $lib $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags~$rm $lib.exp' + + hardcode_libdir_flag_spec_CXX='-R$libdir' + hardcode_shlibpath_var_CXX=no + case $host_os in + solaris2.[0-5] | solaris2.[0-5].*) ;; + *) + # The C++ compiler is used as linker so we must use $wl + # flag to pass the commands to the underlying system + # linker. We must also pass each convience library through + # to the system linker between allextract/defaultextract. + # The C++ compiler will combine linker options so we + # cannot just pass the convience library names through + # without $wl. + # Supported since Solaris 2.6 (maybe 2.5.1?) + whole_archive_flag_spec_CXX='${wl}-z ${wl}allextract`for conv in $convenience\"\"; do test -n \"$conv\" && new_convenience=\"$new_convenience,$conv\"; done; $echo \"$new_convenience\"` ${wl}-z ${wl}defaultextract' + ;; + esac + link_all_deplibs_CXX=yes + + output_verbose_link_cmd='echo' + + # Archives containing C++ object files must be created using + # "CC -xar", where "CC" is the Sun C++ compiler. This is + # necessary to make sure instantiated templates are included + # in the archive. + old_archive_cmds_CXX='$CC -xar -o $oldlib $oldobjs' + ;; + gcx*) + # Green Hills C++ Compiler + archive_cmds_CXX='$CC -shared $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags ${wl}-h $wl$soname -o $lib' + + # The C++ compiler must be used to create the archive. + old_archive_cmds_CXX='$CC $LDFLAGS -archive -o $oldlib $oldobjs' + ;; + *) + # GNU C++ compiler with Solaris linker + if test "$GXX" = yes && test "$with_gnu_ld" = no; then + no_undefined_flag_CXX=' ${wl}-z ${wl}defs' + if $CC --version | grep -v '^2\.7' > /dev/null; then + archive_cmds_CXX='$CC -shared -nostdlib $LDFLAGS $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags ${wl}-h $wl$soname -o $lib' + archive_expsym_cmds_CXX='$echo "{ global:" > $lib.exp~cat $export_symbols | $SED -e "s/\(.*\)/\1;/" >> $lib.exp~$echo "local: *; };" >> $lib.exp~ + $CC -shared -nostdlib ${wl}-M $wl$lib.exp -o $lib $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags~$rm $lib.exp' + + # Commands to make compiler produce verbose output that lists + # what "hidden" libraries, object files and flags are used when + # linking a shared library. + output_verbose_link_cmd="$CC -shared $CFLAGS -v conftest.$objext 2>&1 | grep \"\-L\"" + else + # g++ 2.7 appears to require `-G' NOT `-shared' on this + # platform. + archive_cmds_CXX='$CC -G -nostdlib $LDFLAGS $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags ${wl}-h $wl$soname -o $lib' + archive_expsym_cmds_CXX='$echo "{ global:" > $lib.exp~cat $export_symbols | $SED -e "s/\(.*\)/\1;/" >> $lib.exp~$echo "local: *; };" >> $lib.exp~ + $CC -G -nostdlib ${wl}-M $wl$lib.exp -o $lib $predep_objects $libobjs $deplibs $postdep_objects $compiler_flags~$rm $lib.exp' + + # Commands to make compiler produce verbose output that lists + # what "hidden" libraries, object files and flags are used when + # linking a shared library. + output_verbose_link_cmd="$CC -G $CFLAGS -v conftest.$objext 2>&1 | grep \"\-L\"" + fi + + hardcode_libdir_flag_spec_CXX='${wl}-R $wl$libdir' + fi + ;; + esac + ;; + sysv4*uw2* | sysv5OpenUNIX* | sysv5UnixWare7.[01].[10]* | unixware7* | sco3.2v5.0.[024]*) + no_undefined_flag_CXX='${wl}-z,text' + archive_cmds_need_lc_CXX=no + hardcode_shlibpath_var_CXX=no + runpath_var='LD_RUN_PATH' + + case $cc_basename in + CC*) + archive_cmds_CXX='$CC -G ${wl}-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds_CXX='$CC -G ${wl}-Bexport:$export_symbols ${wl}-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + ;; + *) + archive_cmds_CXX='$CC -shared ${wl}-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds_CXX='$CC -shared ${wl}-Bexport:$export_symbols ${wl}-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + ;; + esac + ;; + sysv5* | sco3.2v5* | sco5v6*) + # Note: We can NOT use -z defs as we might desire, because we do not + # link with -lc, and that would cause any symbols used from libc to + # always be unresolved, which means just about no library would + # ever link correctly. If we're not using GNU ld we use -z text + # though, which does catch some bad symbols but isn't as heavy-handed + # as -z defs. + # For security reasons, it is highly recommended that you always + # use absolute paths for naming shared libraries, and exclude the + # DT_RUNPATH tag from executables and libraries. But doing so + # requires that you compile everything twice, which is a pain. + # So that behaviour is only enabled if SCOABSPATH is set to a + # non-empty value in the environment. Most likely only useful for + # creating official distributions of packages. + # This is a hack until libtool officially supports absolute path + # names for shared libraries. + no_undefined_flag_CXX='${wl}-z,text' + allow_undefined_flag_CXX='${wl}-z,nodefs' + archive_cmds_need_lc_CXX=no + hardcode_shlibpath_var_CXX=no + hardcode_libdir_flag_spec_CXX='`test -z "$SCOABSPATH" && echo ${wl}-R,$libdir`' + hardcode_libdir_separator_CXX=':' + link_all_deplibs_CXX=yes + export_dynamic_flag_spec_CXX='${wl}-Bexport' + runpath_var='LD_RUN_PATH' + + case $cc_basename in + CC*) + archive_cmds_CXX='$CC -G ${wl}-h,\${SCOABSPATH:+${install_libdir}/}$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds_CXX='$CC -G ${wl}-Bexport:$export_symbols ${wl}-h,\${SCOABSPATH:+${install_libdir}/}$soname -o $lib $libobjs $deplibs $compiler_flags' + ;; + *) + archive_cmds_CXX='$CC -shared ${wl}-h,\${SCOABSPATH:+${install_libdir}/}$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds_CXX='$CC -shared ${wl}-Bexport:$export_symbols ${wl}-h,\${SCOABSPATH:+${install_libdir}/}$soname -o $lib $libobjs $deplibs $compiler_flags' + ;; + esac + ;; + tandem*) + case $cc_basename in + NCC*) + # NonStop-UX NCC 3.20 + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + *) + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + esac + ;; + vxworks*) + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; + *) + # FIXME: insert proper C++ library support + ld_shlibs_CXX=no + ;; +esac +echo "$as_me:$LINENO: result: $ld_shlibs_CXX" >&5 +echo "${ECHO_T}$ld_shlibs_CXX" >&6 +test "$ld_shlibs_CXX" = no && can_build_shared=no + +GCC_CXX="$GXX" +LD_CXX="$LD" + + +cat > conftest.$ac_ext <&5 + (eval $ac_compile) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; then + # Parse the compiler output and extract the necessary + # objects, libraries and library flags. + + # Sentinel used to keep track of whether or not we are before + # the conftest object file. + pre_test_object_deps_done=no + + # The `*' in the case matches for architectures that use `case' in + # $output_verbose_cmd can trigger glob expansion during the loop + # eval without this substitution. + output_verbose_link_cmd=`$echo "X$output_verbose_link_cmd" | $Xsed -e "$no_glob_subst"` + + for p in `eval $output_verbose_link_cmd`; do + case $p in + + -L* | -R* | -l*) + # Some compilers place space between "-{L,R}" and the path. + # Remove the space. + if test $p = "-L" \ + || test $p = "-R"; then + prev=$p + continue + else + prev= + fi + + if test "$pre_test_object_deps_done" = no; then + case $p in + -L* | -R*) + # Internal compiler library paths should come after those + # provided the user. The postdeps already come after the + # user supplied libs so there is no need to process them. + if test -z "$compiler_lib_search_path_CXX"; then + compiler_lib_search_path_CXX="${prev}${p}" + else + compiler_lib_search_path_CXX="${compiler_lib_search_path_CXX} ${prev}${p}" + fi + ;; + # The "-l" case would never come before the object being + # linked, so don't bother handling this case. + esac + else + if test -z "$postdeps_CXX"; then + postdeps_CXX="${prev}${p}" + else + postdeps_CXX="${postdeps_CXX} ${prev}${p}" + fi + fi + ;; + + *.$objext) + # This assumes that the test object file only shows up + # once in the compiler output. + if test "$p" = "conftest.$objext"; then + pre_test_object_deps_done=yes + continue + fi + + if test "$pre_test_object_deps_done" = no; then + if test -z "$predep_objects_CXX"; then + predep_objects_CXX="$p" + else + predep_objects_CXX="$predep_objects_CXX $p" + fi + else + if test -z "$postdep_objects_CXX"; then + postdep_objects_CXX="$p" + else + postdep_objects_CXX="$postdep_objects_CXX $p" + fi + fi + ;; + + *) ;; # Ignore the rest. + + esac + done + + # Clean up. + rm -f a.out a.exe +else + echo "libtool.m4: error: problem compiling CXX test program" +fi + +$rm -f confest.$objext + +# PORTME: override above test on systems where it is broken +case $host_os in +interix3*) + # Interix 3.5 installs completely hosed .la files for C++, so rather than + # hack all around it, let's just trust "g++" to DTRT. + predep_objects_CXX= + postdep_objects_CXX= + postdeps_CXX= + ;; + +solaris*) + case $cc_basename in + CC*) + # Adding this requires a known-good setup of shared libraries for + # Sun compiler versions before 5.6, else PIC objects from an old + # archive will be linked into the output, leading to subtle bugs. + postdeps_CXX='-lCstd -lCrun' + ;; + esac + ;; +esac + + +case " $postdeps_CXX " in +*" -lc "*) archive_cmds_need_lc_CXX=no ;; +esac + +lt_prog_compiler_wl_CXX= +lt_prog_compiler_pic_CXX= +lt_prog_compiler_static_CXX= + +echo "$as_me:$LINENO: checking for $compiler option to produce PIC" >&5 +echo $ECHO_N "checking for $compiler option to produce PIC... $ECHO_C" >&6 + + # C++ specific cases for pic, static, wl, etc. + if test "$GXX" = yes; then + lt_prog_compiler_wl_CXX='-Wl,' + lt_prog_compiler_static_CXX='-static' + + case $host_os in + aix*) + # All AIX code is PIC. + if test "$host_cpu" = ia64; then + # AIX 5 now supports IA64 processor + lt_prog_compiler_static_CXX='-Bstatic' + fi + ;; + amigaos*) + # FIXME: we need at least 68020 code to build shared libraries, but + # adding the `-m68020' flag to GCC prevents building anything better, + # like `-m68040'. + lt_prog_compiler_pic_CXX='-m68020 -resident32 -malways-restore-a4' + ;; + beos* | cygwin* | irix5* | irix6* | nonstopux* | osf3* | osf4* | osf5*) + # PIC is the default for these OSes. + ;; + mingw* | os2* | pw32*) + # This hack is so that the source file can tell whether it is being + # built for inclusion in a dll (and should export symbols for example). + lt_prog_compiler_pic_CXX='-DDLL_EXPORT' + ;; + darwin* | rhapsody*) + # PIC is the default on this platform + # Common symbols not allowed in MH_DYLIB files + lt_prog_compiler_pic_CXX='-fno-common' + ;; + *djgpp*) + # DJGPP does not support shared libraries at all + lt_prog_compiler_pic_CXX= + ;; + interix3*) + # Interix 3.x gcc -fpic/-fPIC options generate broken code. + # Instead, we relocate shared libraries at runtime. + ;; + sysv4*MP*) + if test -d /usr/nec; then + lt_prog_compiler_pic_CXX=-Kconform_pic + fi + ;; + hpux*) + # PIC is the default for IA64 HP-UX and 64-bit HP-UX, but + # not for PA HP-UX. + case $host_cpu in + hppa*64*|ia64*) + ;; + *) + lt_prog_compiler_pic_CXX='-fPIC' + ;; + esac + ;; + *) + lt_prog_compiler_pic_CXX='-fPIC' + ;; + esac + else + case $host_os in + aix4* | aix5*) + # All AIX code is PIC. + if test "$host_cpu" = ia64; then + # AIX 5 now supports IA64 processor + lt_prog_compiler_static_CXX='-Bstatic' + else + lt_prog_compiler_static_CXX='-bnso -bI:/lib/syscalls.exp' + fi + ;; + chorus*) + case $cc_basename in + cxch68*) + # Green Hills C++ Compiler + # _LT_AC_TAGVAR(lt_prog_compiler_static, CXX)="--no_auto_instantiation -u __main -u __premain -u _abort -r $COOL_DIR/lib/libOrb.a $MVME_DIR/lib/CC/libC.a $MVME_DIR/lib/classix/libcx.s.a" + ;; + esac + ;; + darwin*) + # PIC is the default on this platform + # Common symbols not allowed in MH_DYLIB files + case $cc_basename in + xlc*) + lt_prog_compiler_pic_CXX='-qnocommon' + lt_prog_compiler_wl_CXX='-Wl,' + ;; + esac + ;; + dgux*) + case $cc_basename in + ec++*) + lt_prog_compiler_pic_CXX='-KPIC' + ;; + ghcx*) + # Green Hills C++ Compiler + lt_prog_compiler_pic_CXX='-pic' + ;; + *) + ;; + esac + ;; + freebsd* | kfreebsd*-gnu | dragonfly*) + # FreeBSD uses GNU C++ + ;; + hpux9* | hpux10* | hpux11*) + case $cc_basename in + CC*) + lt_prog_compiler_wl_CXX='-Wl,' + lt_prog_compiler_static_CXX='${wl}-a ${wl}archive' + if test "$host_cpu" != ia64; then + lt_prog_compiler_pic_CXX='+Z' + fi + ;; + aCC*) + lt_prog_compiler_wl_CXX='-Wl,' + lt_prog_compiler_static_CXX='${wl}-a ${wl}archive' + case $host_cpu in + hppa*64*|ia64*) + # +Z the default + ;; + *) + lt_prog_compiler_pic_CXX='+Z' + ;; + esac + ;; + *) + ;; + esac + ;; + interix*) + # This is c89, which is MS Visual C++ (no shared libs) + # Anyone wants to do a port? + ;; + irix5* | irix6* | nonstopux*) + case $cc_basename in + CC*) + lt_prog_compiler_wl_CXX='-Wl,' + lt_prog_compiler_static_CXX='-non_shared' + # CC pic flag -KPIC is the default. + ;; + *) + ;; + esac + ;; + linux*) + case $cc_basename in + KCC*) + # KAI C++ Compiler + lt_prog_compiler_wl_CXX='--backend -Wl,' + lt_prog_compiler_pic_CXX='-fPIC' + ;; + icpc* | ecpc*) + # Intel C++ + lt_prog_compiler_wl_CXX='-Wl,' + lt_prog_compiler_pic_CXX='-KPIC' + lt_prog_compiler_static_CXX='-static' + ;; + pgCC*) + # Portland Group C++ compiler. + lt_prog_compiler_wl_CXX='-Wl,' + lt_prog_compiler_pic_CXX='-fpic' + lt_prog_compiler_static_CXX='-Bstatic' + ;; + cxx*) + # Compaq C++ + # Make sure the PIC flag is empty. It appears that all Alpha + # Linux and Compaq Tru64 Unix objects are PIC. + lt_prog_compiler_pic_CXX= + lt_prog_compiler_static_CXX='-non_shared' + ;; + *) + ;; + esac + ;; + lynxos*) + ;; + m88k*) + ;; + mvs*) + case $cc_basename in + cxx*) + lt_prog_compiler_pic_CXX='-W c,exportall' + ;; + *) + ;; + esac + ;; + netbsd*) + ;; + osf3* | osf4* | osf5*) + case $cc_basename in + KCC*) + lt_prog_compiler_wl_CXX='--backend -Wl,' + ;; + RCC*) + # Rational C++ 2.4.1 + lt_prog_compiler_pic_CXX='-pic' + ;; + cxx*) + # Digital/Compaq C++ + lt_prog_compiler_wl_CXX='-Wl,' + # Make sure the PIC flag is empty. It appears that all Alpha + # Linux and Compaq Tru64 Unix objects are PIC. + lt_prog_compiler_pic_CXX= + lt_prog_compiler_static_CXX='-non_shared' + ;; + *) + ;; + esac + ;; + psos*) + ;; + solaris*) + case $cc_basename in + CC*) + # Sun C++ 4.2, 5.x and Centerline C++ + lt_prog_compiler_pic_CXX='-KPIC' + lt_prog_compiler_static_CXX='-Bstatic' + lt_prog_compiler_wl_CXX='-Qoption ld ' + ;; + gcx*) + # Green Hills C++ Compiler + lt_prog_compiler_pic_CXX='-PIC' + ;; + *) + ;; + esac + ;; + sunos4*) + case $cc_basename in + CC*) + # Sun C++ 4.x + lt_prog_compiler_pic_CXX='-pic' + lt_prog_compiler_static_CXX='-Bstatic' + ;; + lcc*) + # Lucid + lt_prog_compiler_pic_CXX='-pic' + ;; + *) + ;; + esac + ;; + tandem*) + case $cc_basename in + NCC*) + # NonStop-UX NCC 3.20 + lt_prog_compiler_pic_CXX='-KPIC' + ;; + *) + ;; + esac + ;; + sysv5* | unixware* | sco3.2v5* | sco5v6* | OpenUNIX*) + case $cc_basename in + CC*) + lt_prog_compiler_wl_CXX='-Wl,' + lt_prog_compiler_pic_CXX='-KPIC' + lt_prog_compiler_static_CXX='-Bstatic' + ;; + esac + ;; + vxworks*) + ;; + *) + lt_prog_compiler_can_build_shared_CXX=no + ;; + esac + fi + +echo "$as_me:$LINENO: result: $lt_prog_compiler_pic_CXX" >&5 +echo "${ECHO_T}$lt_prog_compiler_pic_CXX" >&6 + +# +# Check to make sure the PIC flag actually works. +# +if test -n "$lt_prog_compiler_pic_CXX"; then + +echo "$as_me:$LINENO: checking if $compiler PIC flag $lt_prog_compiler_pic_CXX works" >&5 +echo $ECHO_N "checking if $compiler PIC flag $lt_prog_compiler_pic_CXX works... $ECHO_C" >&6 +if test "${lt_prog_compiler_pic_works_CXX+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + lt_prog_compiler_pic_works_CXX=no + ac_outfile=conftest.$ac_objext + printf "$lt_simple_compile_test_code" > conftest.$ac_ext + lt_compiler_flag="$lt_prog_compiler_pic_CXX -DPIC" + # Insert the option either (1) after the last *FLAGS variable, or + # (2) before a word containing "conftest.", or (3) at the end. + # Note that $ac_compile itself does not contain backslashes and begins + # with a dollar sign (not a hyphen), so the echo should work correctly. + # The option is referenced via a variable to avoid confusing sed. + lt_compile=`echo "$ac_compile" | $SED \ + -e 's:.*FLAGS}\{0,1\} :&$lt_compiler_flag :; t' \ + -e 's: [^ ]*conftest\.: $lt_compiler_flag&:; t' \ + -e 's:$: $lt_compiler_flag:'` + (eval echo "\"\$as_me:11245: $lt_compile\"" >&5) + (eval "$lt_compile" 2>conftest.err) + ac_status=$? + cat conftest.err >&5 + echo "$as_me:11249: \$? = $ac_status" >&5 + if (exit $ac_status) && test -s "$ac_outfile"; then + # The compiler can only warn and ignore the option if not recognized + # So say no if there are warnings other than the usual output. + $echo "X$_lt_compiler_boilerplate" | $Xsed -e '/^$/d' >conftest.exp + $SED '/^$/d; /^ *+/d' conftest.err >conftest.er2 + if test ! -s conftest.er2 || diff conftest.exp conftest.er2 >/dev/null; then + lt_prog_compiler_pic_works_CXX=yes + fi + fi + $rm conftest* + +fi +echo "$as_me:$LINENO: result: $lt_prog_compiler_pic_works_CXX" >&5 +echo "${ECHO_T}$lt_prog_compiler_pic_works_CXX" >&6 + +if test x"$lt_prog_compiler_pic_works_CXX" = xyes; then + case $lt_prog_compiler_pic_CXX in + "" | " "*) ;; + *) lt_prog_compiler_pic_CXX=" $lt_prog_compiler_pic_CXX" ;; + esac +else + lt_prog_compiler_pic_CXX= + lt_prog_compiler_can_build_shared_CXX=no +fi + +fi +case $host_os in + # For platforms which do not support PIC, -DPIC is meaningless: + *djgpp*) + lt_prog_compiler_pic_CXX= + ;; + *) + lt_prog_compiler_pic_CXX="$lt_prog_compiler_pic_CXX -DPIC" + ;; +esac + +# +# Check to make sure the static flag actually works. +# +wl=$lt_prog_compiler_wl_CXX eval lt_tmp_static_flag=\"$lt_prog_compiler_static_CXX\" +echo "$as_me:$LINENO: checking if $compiler static flag $lt_tmp_static_flag works" >&5 +echo $ECHO_N "checking if $compiler static flag $lt_tmp_static_flag works... $ECHO_C" >&6 +if test "${lt_prog_compiler_static_works_CXX+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + lt_prog_compiler_static_works_CXX=no + save_LDFLAGS="$LDFLAGS" + LDFLAGS="$LDFLAGS $lt_tmp_static_flag" + printf "$lt_simple_link_test_code" > conftest.$ac_ext + if (eval $ac_link 2>conftest.err) && test -s conftest$ac_exeext; then + # The linker can only warn and ignore the option if not recognized + # So say no if there are warnings + if test -s conftest.err; then + # Append any errors to the config.log. + cat conftest.err 1>&5 + $echo "X$_lt_linker_boilerplate" | $Xsed -e '/^$/d' > conftest.exp + $SED '/^$/d; /^ *+/d' conftest.err >conftest.er2 + if diff conftest.exp conftest.er2 >/dev/null; then + lt_prog_compiler_static_works_CXX=yes + fi + else + lt_prog_compiler_static_works_CXX=yes + fi + fi + $rm conftest* + LDFLAGS="$save_LDFLAGS" + +fi +echo "$as_me:$LINENO: result: $lt_prog_compiler_static_works_CXX" >&5 +echo "${ECHO_T}$lt_prog_compiler_static_works_CXX" >&6 + +if test x"$lt_prog_compiler_static_works_CXX" = xyes; then + : +else + lt_prog_compiler_static_CXX= +fi + + +echo "$as_me:$LINENO: checking if $compiler supports -c -o file.$ac_objext" >&5 +echo $ECHO_N "checking if $compiler supports -c -o file.$ac_objext... $ECHO_C" >&6 +if test "${lt_cv_prog_compiler_c_o_CXX+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + lt_cv_prog_compiler_c_o_CXX=no + $rm -r conftest 2>/dev/null + mkdir conftest + cd conftest + mkdir out + printf "$lt_simple_compile_test_code" > conftest.$ac_ext + + lt_compiler_flag="-o out/conftest2.$ac_objext" + # Insert the option either (1) after the last *FLAGS variable, or + # (2) before a word containing "conftest.", or (3) at the end. + # Note that $ac_compile itself does not contain backslashes and begins + # with a dollar sign (not a hyphen), so the echo should work correctly. + lt_compile=`echo "$ac_compile" | $SED \ + -e 's:.*FLAGS}\{0,1\} :&$lt_compiler_flag :; t' \ + -e 's: [^ ]*conftest\.: $lt_compiler_flag&:; t' \ + -e 's:$: $lt_compiler_flag:'` + (eval echo "\"\$as_me:11349: $lt_compile\"" >&5) + (eval "$lt_compile" 2>out/conftest.err) + ac_status=$? + cat out/conftest.err >&5 + echo "$as_me:11353: \$? = $ac_status" >&5 + if (exit $ac_status) && test -s out/conftest2.$ac_objext + then + # The compiler can only warn and ignore the option if not recognized + # So say no if there are warnings + $echo "X$_lt_compiler_boilerplate" | $Xsed -e '/^$/d' > out/conftest.exp + $SED '/^$/d; /^ *+/d' out/conftest.err >out/conftest.er2 + if test ! -s out/conftest.er2 || diff out/conftest.exp out/conftest.er2 >/dev/null; then + lt_cv_prog_compiler_c_o_CXX=yes + fi + fi + chmod u+w . 2>&5 + $rm conftest* + # SGI C++ compiler will create directory out/ii_files/ for + # template instantiation + test -d out/ii_files && $rm out/ii_files/* && rmdir out/ii_files + $rm out/* && rmdir out + cd .. + rmdir conftest + $rm conftest* + +fi +echo "$as_me:$LINENO: result: $lt_cv_prog_compiler_c_o_CXX" >&5 +echo "${ECHO_T}$lt_cv_prog_compiler_c_o_CXX" >&6 + + +hard_links="nottested" +if test "$lt_cv_prog_compiler_c_o_CXX" = no && test "$need_locks" != no; then + # do not overwrite the value of need_locks provided by the user + echo "$as_me:$LINENO: checking if we can lock with hard links" >&5 +echo $ECHO_N "checking if we can lock with hard links... $ECHO_C" >&6 + hard_links=yes + $rm conftest* + ln conftest.a conftest.b 2>/dev/null && hard_links=no + touch conftest.a + ln conftest.a conftest.b 2>&5 || hard_links=no + ln conftest.a conftest.b 2>/dev/null && hard_links=no + echo "$as_me:$LINENO: result: $hard_links" >&5 +echo "${ECHO_T}$hard_links" >&6 + if test "$hard_links" = no; then + { echo "$as_me:$LINENO: WARNING: \`$CC' does not support \`-c -o', so \`make -j' may be unsafe" >&5 +echo "$as_me: WARNING: \`$CC' does not support \`-c -o', so \`make -j' may be unsafe" >&2;} + need_locks=warn + fi +else + need_locks=no +fi + +echo "$as_me:$LINENO: checking whether the $compiler linker ($LD) supports shared libraries" >&5 +echo $ECHO_N "checking whether the $compiler linker ($LD) supports shared libraries... $ECHO_C" >&6 + + export_symbols_cmds_CXX='$NM $libobjs $convenience | $global_symbol_pipe | $SED '\''s/.* //'\'' | sort | uniq > $export_symbols' + case $host_os in + aix4* | aix5*) + # If we're using GNU nm, then we don't want the "-C" option. + # -C means demangle to AIX nm, but means don't demangle with GNU nm + if $NM -V 2>&1 | grep 'GNU' > /dev/null; then + export_symbols_cmds_CXX='$NM -Bpg $libobjs $convenience | awk '\''{ if (((\$2 == "T") || (\$2 == "D") || (\$2 == "B")) && (substr(\$3,1,1) != ".")) { print \$3 } }'\'' | sort -u > $export_symbols' + else + export_symbols_cmds_CXX='$NM -BCpg $libobjs $convenience | awk '\''{ if (((\$2 == "T") || (\$2 == "D") || (\$2 == "B")) && (substr(\$3,1,1) != ".")) { print \$3 } }'\'' | sort -u > $export_symbols' + fi + ;; + pw32*) + export_symbols_cmds_CXX="$ltdll_cmds" + ;; + cygwin* | mingw*) + export_symbols_cmds_CXX='$NM $libobjs $convenience | $global_symbol_pipe | $SED -e '\''/^[BCDGRS] /s/.* \([^ ]*\)/\1 DATA/;/^.* __nm__/s/^.* __nm__\([^ ]*\) [^ ]*/\1 DATA/;/^I /d;/^[AITW] /s/.* //'\'' | sort | uniq > $export_symbols' + ;; + *) + export_symbols_cmds_CXX='$NM $libobjs $convenience | $global_symbol_pipe | $SED '\''s/.* //'\'' | sort | uniq > $export_symbols' + ;; + esac + +echo "$as_me:$LINENO: result: $ld_shlibs_CXX" >&5 +echo "${ECHO_T}$ld_shlibs_CXX" >&6 +test "$ld_shlibs_CXX" = no && can_build_shared=no + +# +# Do we need to explicitly link libc? +# +case "x$archive_cmds_need_lc_CXX" in +x|xyes) + # Assume -lc should be added + archive_cmds_need_lc_CXX=yes + + if test "$enable_shared" = yes && test "$GCC" = yes; then + case $archive_cmds_CXX in + *'~'*) + # FIXME: we may have to deal with multi-command sequences. + ;; + '$CC '*) + # Test whether the compiler implicitly links with -lc since on some + # systems, -lgcc has to come before -lc. If gcc already passes -lc + # to ld, don't add -lc before -lgcc. + echo "$as_me:$LINENO: checking whether -lc should be explicitly linked in" >&5 +echo $ECHO_N "checking whether -lc should be explicitly linked in... $ECHO_C" >&6 + $rm conftest* + printf "$lt_simple_compile_test_code" > conftest.$ac_ext + + if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } 2>conftest.err; then + soname=conftest + lib=conftest + libobjs=conftest.$ac_objext + deplibs= + wl=$lt_prog_compiler_wl_CXX + pic_flag=$lt_prog_compiler_pic_CXX + compiler_flags=-v + linker_flags=-v + verstring= + output_objdir=. + libname=conftest + lt_save_allow_undefined_flag=$allow_undefined_flag_CXX + allow_undefined_flag_CXX= + if { (eval echo "$as_me:$LINENO: \"$archive_cmds_CXX 2\>\&1 \| grep \" -lc \" \>/dev/null 2\>\&1\"") >&5 + (eval $archive_cmds_CXX 2\>\&1 \| grep \" -lc \" \>/dev/null 2\>\&1) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } + then + archive_cmds_need_lc_CXX=no + else + archive_cmds_need_lc_CXX=yes + fi + allow_undefined_flag_CXX=$lt_save_allow_undefined_flag + else + cat conftest.err 1>&5 + fi + $rm conftest* + echo "$as_me:$LINENO: result: $archive_cmds_need_lc_CXX" >&5 +echo "${ECHO_T}$archive_cmds_need_lc_CXX" >&6 + ;; + esac + fi + ;; +esac + +echo "$as_me:$LINENO: checking dynamic linker characteristics" >&5 +echo $ECHO_N "checking dynamic linker characteristics... $ECHO_C" >&6 +library_names_spec= +libname_spec='lib$name' +soname_spec= +shrext_cmds=".so" +postinstall_cmds= +postuninstall_cmds= +finish_cmds= +finish_eval= +shlibpath_var= +shlibpath_overrides_runpath=unknown +version_type=none +dynamic_linker="$host_os ld.so" +sys_lib_dlsearch_path_spec="/lib /usr/lib" +if test "$GCC" = yes; then + sys_lib_search_path_spec=`$CC -print-search-dirs | grep "^libraries:" | $SED -e "s/^libraries://" -e "s,=/,/,g"` + if echo "$sys_lib_search_path_spec" | grep ';' >/dev/null ; then + # if the path contains ";" then we assume it to be the separator + # otherwise default to the standard path separator (i.e. ":") - it is + # assumed that no part of a normal pathname contains ";" but that should + # okay in the real world where ";" in dirpaths is itself problematic. + sys_lib_search_path_spec=`echo "$sys_lib_search_path_spec" | $SED -e 's/;/ /g'` + else + sys_lib_search_path_spec=`echo "$sys_lib_search_path_spec" | $SED -e "s/$PATH_SEPARATOR/ /g"` + fi +else + sys_lib_search_path_spec="/lib /usr/lib /usr/local/lib" +fi +need_lib_prefix=unknown +hardcode_into_libs=no + +# when you set need_version to no, make sure it does not cause -set_version +# flags to be left without arguments +need_version=unknown + +case $host_os in +aix3*) + version_type=linux + library_names_spec='${libname}${release}${shared_ext}$versuffix $libname.a' + shlibpath_var=LIBPATH + + # AIX 3 has no versioning support, so we append a major version to the name. + soname_spec='${libname}${release}${shared_ext}$major' + ;; + +aix4* | aix5*) + version_type=linux + need_lib_prefix=no + need_version=no + hardcode_into_libs=yes + if test "$host_cpu" = ia64; then + # AIX 5 supports IA64 + library_names_spec='${libname}${release}${shared_ext}$major ${libname}${release}${shared_ext}$versuffix $libname${shared_ext}' + shlibpath_var=LD_LIBRARY_PATH + else + # With GCC up to 2.95.x, collect2 would create an import file + # for dependence libraries. The import file would start with + # the line `#! .'. This would cause the generated library to + # depend on `.', always an invalid library. This was fixed in + # development snapshots of GCC prior to 3.0. + case $host_os in + aix4 | aix4.[01] | aix4.[01].*) + if { echo '#if __GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 97)' + echo ' yes ' + echo '#endif'; } | ${CC} -E - | grep yes > /dev/null; then + : + else + can_build_shared=no + fi + ;; + esac + # AIX (on Power*) has no versioning support, so currently we can not hardcode correct + # soname into executable. Probably we can add versioning support to + # collect2, so additional links can be useful in future. + if test "$aix_use_runtimelinking" = yes; then + # If using run time linking (on AIX 4.2 or later) use lib.so + # instead of lib.a to let people know that these are not + # typical AIX shared libraries. + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + else + # We preserve .a as extension for shared libraries through AIX4.2 + # and later when we are not doing run time linking. + library_names_spec='${libname}${release}.a $libname.a' + soname_spec='${libname}${release}${shared_ext}$major' + fi + shlibpath_var=LIBPATH + fi + ;; + +amigaos*) + library_names_spec='$libname.ixlibrary $libname.a' + # Create ${libname}_ixlibrary.a entries in /sys/libs. + finish_eval='for lib in `ls $libdir/*.ixlibrary 2>/dev/null`; do libname=`$echo "X$lib" | $Xsed -e '\''s%^.*/\([^/]*\)\.ixlibrary$%\1%'\''`; test $rm /sys/libs/${libname}_ixlibrary.a; $show "cd /sys/libs && $LN_S $lib ${libname}_ixlibrary.a"; cd /sys/libs && $LN_S $lib ${libname}_ixlibrary.a || exit 1; done' + ;; + +beos*) + library_names_spec='${libname}${shared_ext}' + dynamic_linker="$host_os ld.so" + shlibpath_var=LIBRARY_PATH + ;; + +bsdi[45]*) + version_type=linux + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + finish_cmds='PATH="\$PATH:/sbin" ldconfig $libdir' + shlibpath_var=LD_LIBRARY_PATH + sys_lib_search_path_spec="/shlib /usr/lib /usr/X11/lib /usr/contrib/lib /lib /usr/local/lib" + sys_lib_dlsearch_path_spec="/shlib /usr/lib /usr/local/lib" + # the default ld.so.conf also contains /usr/contrib/lib and + # /usr/X11R6/lib (/usr/X11 is a link to /usr/X11R6), but let us allow + # libtool to hard-code these into programs + ;; + +cygwin* | mingw* | pw32*) + version_type=windows + shrext_cmds=".dll" + need_version=no + need_lib_prefix=no + + case $GCC,$host_os in + yes,cygwin* | yes,mingw* | yes,pw32*) + library_names_spec='$libname.dll.a' + # DLL is installed to $(libdir)/../bin by postinstall_cmds + postinstall_cmds='base_file=`basename \${file}`~ + dlpath=`$SHELL 2>&1 -c '\''. $dir/'\''\${base_file}'\''i;echo \$dlname'\''`~ + dldir=$destdir/`dirname \$dlpath`~ + test -d \$dldir || mkdir -p \$dldir~ + $install_prog $dir/$dlname \$dldir/$dlname~ + chmod a+x \$dldir/$dlname' + postuninstall_cmds='dldll=`$SHELL 2>&1 -c '\''. $file; echo \$dlname'\''`~ + dlpath=$dir/\$dldll~ + $rm \$dlpath' + shlibpath_overrides_runpath=yes + + case $host_os in + cygwin*) + # Cygwin DLLs use 'cyg' prefix rather than 'lib' + soname_spec='`echo ${libname} | sed -e 's/^lib/cyg/'``echo ${release} | $SED -e 's/[.]/-/g'`${versuffix}${shared_ext}' + sys_lib_search_path_spec="/usr/lib /lib/w32api /lib /usr/local/lib" + ;; + mingw*) + # MinGW DLLs use traditional 'lib' prefix + soname_spec='${libname}`echo ${release} | $SED -e 's/[.]/-/g'`${versuffix}${shared_ext}' + sys_lib_search_path_spec=`$CC -print-search-dirs | grep "^libraries:" | $SED -e "s/^libraries://" -e "s,=/,/,g"` + if echo "$sys_lib_search_path_spec" | grep ';[c-zC-Z]:/' >/dev/null; then + # It is most probably a Windows format PATH printed by + # mingw gcc, but we are running on Cygwin. Gcc prints its search + # path with ; separators, and with drive letters. We can handle the + # drive letters (cygwin fileutils understands them), so leave them, + # especially as we might pass files found there to a mingw objdump, + # which wouldn't understand a cygwinified path. Ahh. + sys_lib_search_path_spec=`echo "$sys_lib_search_path_spec" | $SED -e 's/;/ /g'` + else + sys_lib_search_path_spec=`echo "$sys_lib_search_path_spec" | $SED -e "s/$PATH_SEPARATOR/ /g"` + fi + ;; + pw32*) + # pw32 DLLs use 'pw' prefix rather than 'lib' + library_names_spec='`echo ${libname} | sed -e 's/^lib/pw/'``echo ${release} | $SED -e 's/[.]/-/g'`${versuffix}${shared_ext}' + ;; + esac + ;; + + linux*) + if $LD --help 2>&1 | egrep ': supported targets:.* elf' > /dev/null; then + archive_cmds='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + supports_anon_versioning=no + case `$LD -v 2>/dev/null` in + *\ 01.* | *\ 2.[0-9].* | *\ 2.10.*) ;; # catch versions < 2.11 + *\ 2.11.93.0.2\ *) supports_anon_versioning=yes ;; # RH7.3 ... + *\ 2.11.92.0.12\ *) supports_anon_versioning=yes ;; # Mandrake 8.2 ... + *\ 2.11.*) ;; # other 2.11 versions + *) supports_anon_versioning=yes ;; + esac + if test $supports_anon_versioning = yes; then + archive_expsym_cmds='$echo "{ global:" > $output_objdir/$libname.ver~ +cat $export_symbols | sed -e "s/\(.*\)/\1;/" >> $output_objdir/$libname.ver~ +$echo "local: *; };" >> $output_objdir/$libname.ver~ + $CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-version-script ${wl}$output_objdir/$libname.ver -o $lib' + else + $archive_expsym_cmds="$archive_cmds" + fi + else + ld_shlibs=no + fi + ;; + + *) + library_names_spec='${libname}`echo ${release} | $SED -e 's/[.]/-/g'`${versuffix}${shared_ext} $libname.lib' + ;; + esac + dynamic_linker='Win32 ld.exe' + # FIXME: first we should search . and the directory the executable is in + shlibpath_var=PATH + ;; + +darwin* | rhapsody*) + dynamic_linker="$host_os dyld" + version_type=darwin + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${versuffix}$shared_ext ${libname}${release}${major}$shared_ext ${libname}$shared_ext' + soname_spec='${libname}${release}${major}$shared_ext' + shlibpath_overrides_runpath=yes + shlibpath_var=DYLD_LIBRARY_PATH + shrext_cmds='`test .$module = .yes && echo .so || echo .dylib`' + # Apple's gcc prints 'gcc -print-search-dirs' doesn't operate the same. + if test "$GCC" = yes; then + sys_lib_search_path_spec=`$CC -print-search-dirs | tr "\n" "$PATH_SEPARATOR" | sed -e 's/libraries:/@libraries:/' | tr "@" "\n" | grep "^libraries:" | sed -e "s/^libraries://" -e "s,=/,/,g" -e "s,$PATH_SEPARATOR, ,g" -e "s,.*,& /lib /usr/lib /usr/local/lib,g"` + else + sys_lib_search_path_spec='/lib /usr/lib /usr/local/lib' + fi + sys_lib_dlsearch_path_spec='/usr/local/lib /lib /usr/lib' + ;; + +dgux*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname$shared_ext' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + ;; + +freebsd1*) + dynamic_linker=no + ;; + +kfreebsd*-gnu) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + dynamic_linker='GNU ld.so' + ;; + +freebsd* | dragonfly*) + # DragonFly does not have aout. When/if they implement a new + # versioning mechanism, adjust this. + if test -x /usr/bin/objformat; then + objformat=`/usr/bin/objformat` + else + case $host_os in + freebsd[123]*) objformat=aout ;; + *) objformat=elf ;; + esac + fi + # Handle Gentoo/FreeBSD as it was Linux + case $host_vendor in + gentoo) + version_type=linux ;; + *) + version_type=freebsd-$objformat ;; + esac + + case $version_type in + freebsd-elf*) + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext} $libname${shared_ext}' + need_version=no + need_lib_prefix=no + ;; + freebsd-*) + library_names_spec='${libname}${release}${shared_ext}$versuffix $libname${shared_ext}$versuffix' + need_version=yes + ;; + linux) + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + need_lib_prefix=no + need_version=no + ;; + esac + shlibpath_var=LD_LIBRARY_PATH + case $host_os in + freebsd2*) + shlibpath_overrides_runpath=yes + ;; + freebsd3.[01]* | freebsdelf3.[01]*) + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + ;; + freebsd3.[2-9]* | freebsdelf3.[2-9]* | \ + freebsd4.[0-5] | freebsdelf4.[0-5] | freebsd4.1.1 | freebsdelf4.1.1) + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + ;; + freebsd*) # from 4.6 on + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + ;; + esac + ;; + +gnu*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}${major} ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + hardcode_into_libs=yes + ;; + +hpux9* | hpux10* | hpux11*) + # Give a soname corresponding to the major version so that dld.sl refuses to + # link against other versions. + version_type=sunos + need_lib_prefix=no + need_version=no + case $host_cpu in + ia64*) + shrext_cmds='.so' + hardcode_into_libs=yes + dynamic_linker="$host_os dld.so" + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes # Unless +noenvvar is specified. + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + if test "X$HPUX_IA64_MODE" = X32; then + sys_lib_search_path_spec="/usr/lib/hpux32 /usr/local/lib/hpux32 /usr/local/lib" + else + sys_lib_search_path_spec="/usr/lib/hpux64 /usr/local/lib/hpux64" + fi + sys_lib_dlsearch_path_spec=$sys_lib_search_path_spec + ;; + hppa*64*) + shrext_cmds='.sl' + hardcode_into_libs=yes + dynamic_linker="$host_os dld.sl" + shlibpath_var=LD_LIBRARY_PATH # How should we handle SHLIB_PATH + shlibpath_overrides_runpath=yes # Unless +noenvvar is specified. + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + sys_lib_search_path_spec="/usr/lib/pa20_64 /usr/ccs/lib/pa20_64" + sys_lib_dlsearch_path_spec=$sys_lib_search_path_spec + ;; + *) + shrext_cmds='.sl' + dynamic_linker="$host_os dld.sl" + shlibpath_var=SHLIB_PATH + shlibpath_overrides_runpath=no # +s is required to enable SHLIB_PATH + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + ;; + esac + # HP-UX runs *really* slowly unless shared libraries are mode 555. + postinstall_cmds='chmod 555 $lib' + ;; + +interix3*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + dynamic_linker='Interix 3.x ld.so.1 (PE, like ELF)' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + ;; + +irix5* | irix6* | nonstopux*) + case $host_os in + nonstopux*) version_type=nonstopux ;; + *) + if test "$lt_cv_prog_gnu_ld" = yes; then + version_type=linux + else + version_type=irix + fi ;; + esac + need_lib_prefix=no + need_version=no + soname_spec='${libname}${release}${shared_ext}$major' + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${release}${shared_ext} $libname${shared_ext}' + case $host_os in + irix5* | nonstopux*) + libsuff= shlibsuff= + ;; + *) + case $LD in # libtool.m4 will add one of these switches to LD + *-32|*"-32 "|*-melf32bsmip|*"-melf32bsmip ") + libsuff= shlibsuff= libmagic=32-bit;; + *-n32|*"-n32 "|*-melf32bmipn32|*"-melf32bmipn32 ") + libsuff=32 shlibsuff=N32 libmagic=N32;; + *-64|*"-64 "|*-melf64bmip|*"-melf64bmip ") + libsuff=64 shlibsuff=64 libmagic=64-bit;; + *) libsuff= shlibsuff= libmagic=never-match;; + esac + ;; + esac + shlibpath_var=LD_LIBRARY${shlibsuff}_PATH + shlibpath_overrides_runpath=no + sys_lib_search_path_spec="/usr/lib${libsuff} /lib${libsuff} /usr/local/lib${libsuff}" + sys_lib_dlsearch_path_spec="/usr/lib${libsuff} /lib${libsuff}" + hardcode_into_libs=yes + ;; + +# No shared lib support for Linux oldld, aout, or coff. +linux*oldld* | linux*aout* | linux*coff*) + dynamic_linker=no + ;; + +# This must be Linux ELF. +linux*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + finish_cmds='PATH="\$PATH:/sbin" ldconfig -n $libdir' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + # This implies no fast_install, which is unacceptable. + # Some rework will be needed to allow for fast_install + # before this can be enabled. + hardcode_into_libs=yes + + # Append ld.so.conf contents to the search path + if test -f /etc/ld.so.conf; then + lt_ld_extra=`awk '/^include / { system(sprintf("cd /etc; cat %s", \$2)); skip = 1; } { if (!skip) print \$0; skip = 0; }' < /etc/ld.so.conf | $SED -e 's/#.*//;s/[:, ]/ /g;s/=[^=]*$//;s/=[^= ]* / /g;/^$/d' | tr '\n' ' '` + sys_lib_dlsearch_path_spec="/lib /usr/lib $lt_ld_extra" + fi + + # We used to test for /lib/ld.so.1 and disable shared libraries on + # powerpc, because MkLinux only supported shared libraries with the + # GNU dynamic linker. Since this was broken with cross compilers, + # most powerpc-linux boxes support dynamic linking these days and + # people can always --disable-shared, the test was removed, and we + # assume the GNU/Linux dynamic linker is in use. + dynamic_linker='GNU/Linux ld.so' + ;; + +knetbsd*-gnu) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + dynamic_linker='GNU ld.so' + ;; + +netbsd*) + version_type=sunos + need_lib_prefix=no + need_version=no + if echo __ELF__ | $CC -E - | grep __ELF__ >/dev/null; then + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${shared_ext}$versuffix' + finish_cmds='PATH="\$PATH:/sbin" ldconfig -m $libdir' + dynamic_linker='NetBSD (a.out) ld.so' + else + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + dynamic_linker='NetBSD ld.elf_so' + fi + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + ;; + +newsos6) + version_type=linux + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + ;; + +nto-qnx*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + ;; + +openbsd*) + version_type=sunos + sys_lib_dlsearch_path_spec="/usr/lib" + need_lib_prefix=no + # Some older versions of OpenBSD (3.3 at least) *do* need versioned libs. + case $host_os in + openbsd3.3 | openbsd3.3.*) need_version=yes ;; + *) need_version=no ;; + esac + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${shared_ext}$versuffix' + finish_cmds='PATH="\$PATH:/sbin" ldconfig -m $libdir' + shlibpath_var=LD_LIBRARY_PATH + if test -z "`echo __ELF__ | $CC -E - | grep __ELF__`" || test "$host_os-$host_cpu" = "openbsd2.8-powerpc"; then + case $host_os in + openbsd2.[89] | openbsd2.[89].*) + shlibpath_overrides_runpath=no + ;; + *) + shlibpath_overrides_runpath=yes + ;; + esac + else + shlibpath_overrides_runpath=yes + fi + ;; + +os2*) + libname_spec='$name' + shrext_cmds=".dll" + need_lib_prefix=no + library_names_spec='$libname${shared_ext} $libname.a' + dynamic_linker='OS/2 ld.exe' + shlibpath_var=LIBPATH + ;; + +osf3* | osf4* | osf5*) + version_type=osf + need_lib_prefix=no + need_version=no + soname_spec='${libname}${release}${shared_ext}$major' + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + shlibpath_var=LD_LIBRARY_PATH + sys_lib_search_path_spec="/usr/shlib /usr/ccs/lib /usr/lib/cmplrs/cc /usr/lib /usr/local/lib /var/shlib" + sys_lib_dlsearch_path_spec="$sys_lib_search_path_spec" + ;; + +solaris*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + # ldd complains unless libraries are executable + postinstall_cmds='chmod +x $lib' + ;; + +sunos4*) + version_type=sunos + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${shared_ext}$versuffix' + finish_cmds='PATH="\$PATH:/usr/etc" ldconfig $libdir' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + if test "$with_gnu_ld" = yes; then + need_lib_prefix=no + fi + need_version=yes + ;; + +sysv4 | sysv4.3*) + version_type=linux + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + case $host_vendor in + sni) + shlibpath_overrides_runpath=no + need_lib_prefix=no + export_dynamic_flag_spec='${wl}-Blargedynsym' + runpath_var=LD_RUN_PATH + ;; + siemens) + need_lib_prefix=no + ;; + motorola) + need_lib_prefix=no + need_version=no + shlibpath_overrides_runpath=no + sys_lib_search_path_spec='/lib /usr/lib /usr/ccs/lib' + ;; + esac + ;; + +sysv4*MP*) + if test -d /usr/nec ;then + version_type=linux + library_names_spec='$libname${shared_ext}.$versuffix $libname${shared_ext}.$major $libname${shared_ext}' + soname_spec='$libname${shared_ext}.$major' + shlibpath_var=LD_LIBRARY_PATH + fi + ;; + +sysv5* | sco3.2v5* | sco5v6* | unixware* | OpenUNIX* | sysv4*uw2*) + version_type=freebsd-elf + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext} $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + hardcode_into_libs=yes + if test "$with_gnu_ld" = yes; then + sys_lib_search_path_spec='/usr/local/lib /usr/gnu/lib /usr/ccs/lib /usr/lib /lib' + shlibpath_overrides_runpath=no + else + sys_lib_search_path_spec='/usr/ccs/lib /usr/lib' + shlibpath_overrides_runpath=yes + case $host_os in + sco3.2v5*) + sys_lib_search_path_spec="$sys_lib_search_path_spec /lib" + ;; + esac + fi + sys_lib_dlsearch_path_spec='/usr/lib' + ;; + +uts4*) + version_type=linux + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + ;; + +*) + dynamic_linker=no + ;; +esac +echo "$as_me:$LINENO: result: $dynamic_linker" >&5 +echo "${ECHO_T}$dynamic_linker" >&6 +test "$dynamic_linker" = no && can_build_shared=no + +variables_saved_for_relink="PATH $shlibpath_var $runpath_var" +if test "$GCC" = yes; then + variables_saved_for_relink="$variables_saved_for_relink GCC_EXEC_PREFIX COMPILER_PATH LIBRARY_PATH" +fi + +echo "$as_me:$LINENO: checking how to hardcode library paths into programs" >&5 +echo $ECHO_N "checking how to hardcode library paths into programs... $ECHO_C" >&6 +hardcode_action_CXX= +if test -n "$hardcode_libdir_flag_spec_CXX" || \ + test -n "$runpath_var_CXX" || \ + test "X$hardcode_automatic_CXX" = "Xyes" ; then + + # We can hardcode non-existant directories. + if test "$hardcode_direct_CXX" != no && + # If the only mechanism to avoid hardcoding is shlibpath_var, we + # have to relink, otherwise we might link with an installed library + # when we should be linking with a yet-to-be-installed one + ## test "$_LT_AC_TAGVAR(hardcode_shlibpath_var, CXX)" != no && + test "$hardcode_minus_L_CXX" != no; then + # Linking always hardcodes the temporary library directory. + hardcode_action_CXX=relink + else + # We can link without hardcoding, and we can hardcode nonexisting dirs. + hardcode_action_CXX=immediate + fi +else + # We cannot hardcode anything, or else we can only hardcode existing + # directories. + hardcode_action_CXX=unsupported +fi +echo "$as_me:$LINENO: result: $hardcode_action_CXX" >&5 +echo "${ECHO_T}$hardcode_action_CXX" >&6 + +if test "$hardcode_action_CXX" = relink; then + # Fast installation is not supported + enable_fast_install=no +elif test "$shlibpath_overrides_runpath" = yes || + test "$enable_shared" = no; then + # Fast installation is not necessary + enable_fast_install=needless +fi + + +# The else clause should only fire when bootstrapping the +# libtool distribution, otherwise you forgot to ship ltmain.sh +# with your package, and you will get complaints that there are +# no rules to generate ltmain.sh. +if test -f "$ltmain"; then + # See if we are running on zsh, and set the options which allow our commands through + # without removal of \ escapes. + if test -n "${ZSH_VERSION+set}" ; then + setopt NO_GLOB_SUBST + fi + # Now quote all the things that may contain metacharacters while being + # careful not to overquote the AC_SUBSTed values. We take copies of the + # variables and quote the copies for generation of the libtool script. + for var in echo old_CC old_CFLAGS AR AR_FLAGS EGREP RANLIB LN_S LTCC LTCFLAGS NM \ + SED SHELL STRIP \ + libname_spec library_names_spec soname_spec extract_expsyms_cmds \ + old_striplib striplib file_magic_cmd finish_cmds finish_eval \ + deplibs_check_method reload_flag reload_cmds need_locks \ + lt_cv_sys_global_symbol_pipe lt_cv_sys_global_symbol_to_cdecl \ + lt_cv_sys_global_symbol_to_c_name_address \ + sys_lib_search_path_spec sys_lib_dlsearch_path_spec \ + old_postinstall_cmds old_postuninstall_cmds \ + compiler_CXX \ + CC_CXX \ + LD_CXX \ + lt_prog_compiler_wl_CXX \ + lt_prog_compiler_pic_CXX \ + lt_prog_compiler_static_CXX \ + lt_prog_compiler_no_builtin_flag_CXX \ + export_dynamic_flag_spec_CXX \ + thread_safe_flag_spec_CXX \ + whole_archive_flag_spec_CXX \ + enable_shared_with_static_runtimes_CXX \ + old_archive_cmds_CXX \ + old_archive_from_new_cmds_CXX \ + predep_objects_CXX \ + postdep_objects_CXX \ + predeps_CXX \ + postdeps_CXX \ + compiler_lib_search_path_CXX \ + archive_cmds_CXX \ + archive_expsym_cmds_CXX \ + postinstall_cmds_CXX \ + postuninstall_cmds_CXX \ + old_archive_from_expsyms_cmds_CXX \ + allow_undefined_flag_CXX \ + no_undefined_flag_CXX \ + export_symbols_cmds_CXX \ + hardcode_libdir_flag_spec_CXX \ + hardcode_libdir_flag_spec_ld_CXX \ + hardcode_libdir_separator_CXX \ + hardcode_automatic_CXX \ + module_cmds_CXX \ + module_expsym_cmds_CXX \ + lt_cv_prog_compiler_c_o_CXX \ + exclude_expsyms_CXX \ + include_expsyms_CXX; do + + case $var in + old_archive_cmds_CXX | \ + old_archive_from_new_cmds_CXX | \ + archive_cmds_CXX | \ + archive_expsym_cmds_CXX | \ + module_cmds_CXX | \ + module_expsym_cmds_CXX | \ + old_archive_from_expsyms_cmds_CXX | \ + export_symbols_cmds_CXX | \ + extract_expsyms_cmds | reload_cmds | finish_cmds | \ + postinstall_cmds | postuninstall_cmds | \ + old_postinstall_cmds | old_postuninstall_cmds | \ + sys_lib_search_path_spec | sys_lib_dlsearch_path_spec) + # Double-quote double-evaled strings. + eval "lt_$var=\\\"\`\$echo \"X\$$var\" | \$Xsed -e \"\$double_quote_subst\" -e \"\$sed_quote_subst\" -e \"\$delay_variable_subst\"\`\\\"" + ;; + *) + eval "lt_$var=\\\"\`\$echo \"X\$$var\" | \$Xsed -e \"\$sed_quote_subst\"\`\\\"" + ;; + esac + done + + case $lt_echo in + *'\$0 --fallback-echo"') + lt_echo=`$echo "X$lt_echo" | $Xsed -e 's/\\\\\\\$0 --fallback-echo"$/$0 --fallback-echo"/'` + ;; + esac + +cfgfile="$ofile" + + cat <<__EOF__ >> "$cfgfile" +# ### BEGIN LIBTOOL TAG CONFIG: $tagname + +# Libtool was configured on host `(hostname || uname -n) 2>/dev/null | sed 1q`: + +# Shell to use when invoking shell scripts. +SHELL=$lt_SHELL + +# Whether or not to build shared libraries. +build_libtool_libs=$enable_shared + +# Whether or not to build static libraries. +build_old_libs=$enable_static + +# Whether or not to add -lc for building shared libraries. +build_libtool_need_lc=$archive_cmds_need_lc_CXX + +# Whether or not to disallow shared libs when runtime libs are static +allow_libtool_libs_with_static_runtimes=$enable_shared_with_static_runtimes_CXX + +# Whether or not to optimize for fast installation. +fast_install=$enable_fast_install + +# The host system. +host_alias=$host_alias +host=$host +host_os=$host_os + +# The build system. +build_alias=$build_alias +build=$build +build_os=$build_os + +# An echo program that does not interpret backslashes. +echo=$lt_echo + +# The archiver. +AR=$lt_AR +AR_FLAGS=$lt_AR_FLAGS + +# A C compiler. +LTCC=$lt_LTCC + +# LTCC compiler flags. +LTCFLAGS=$lt_LTCFLAGS + +# A language-specific compiler. +CC=$lt_compiler_CXX + +# Is the compiler the GNU C compiler? +with_gcc=$GCC_CXX + +# An ERE matcher. +EGREP=$lt_EGREP + +# The linker used to build libraries. +LD=$lt_LD_CXX + +# Whether we need hard or soft links. +LN_S=$lt_LN_S + +# A BSD-compatible nm program. +NM=$lt_NM + +# A symbol stripping program +STRIP=$lt_STRIP + +# Used to examine libraries when file_magic_cmd begins "file" +MAGIC_CMD=$MAGIC_CMD + +# Used on cygwin: DLL creation program. +DLLTOOL="$DLLTOOL" + +# Used on cygwin: object dumper. +OBJDUMP="$OBJDUMP" + +# Used on cygwin: assembler. +AS="$AS" + +# The name of the directory that contains temporary libtool files. +objdir=$objdir + +# How to create reloadable object files. +reload_flag=$lt_reload_flag +reload_cmds=$lt_reload_cmds + +# How to pass a linker flag through the compiler. +wl=$lt_lt_prog_compiler_wl_CXX + +# Object file suffix (normally "o"). +objext="$ac_objext" + +# Old archive suffix (normally "a"). +libext="$libext" + +# Shared library suffix (normally ".so"). +shrext_cmds='$shrext_cmds' + +# Executable file suffix (normally ""). +exeext="$exeext" + +# Additional compiler flags for building library objects. +pic_flag=$lt_lt_prog_compiler_pic_CXX +pic_mode=$pic_mode + +# What is the maximum length of a command? +max_cmd_len=$lt_cv_sys_max_cmd_len + +# Does compiler simultaneously support -c and -o options? +compiler_c_o=$lt_lt_cv_prog_compiler_c_o_CXX + +# Must we lock files when doing compilation? +need_locks=$lt_need_locks + +# Do we need the lib prefix for modules? +need_lib_prefix=$need_lib_prefix + +# Do we need a version for libraries? +need_version=$need_version + +# Whether dlopen is supported. +dlopen_support=$enable_dlopen + +# Whether dlopen of programs is supported. +dlopen_self=$enable_dlopen_self + +# Whether dlopen of statically linked programs is supported. +dlopen_self_static=$enable_dlopen_self_static + +# Compiler flag to prevent dynamic linking. +link_static_flag=$lt_lt_prog_compiler_static_CXX + +# Compiler flag to turn off builtin functions. +no_builtin_flag=$lt_lt_prog_compiler_no_builtin_flag_CXX + +# Compiler flag to allow reflexive dlopens. +export_dynamic_flag_spec=$lt_export_dynamic_flag_spec_CXX + +# Compiler flag to generate shared objects directly from archives. +whole_archive_flag_spec=$lt_whole_archive_flag_spec_CXX + +# Compiler flag to generate thread-safe objects. +thread_safe_flag_spec=$lt_thread_safe_flag_spec_CXX + +# Library versioning type. +version_type=$version_type + +# Format of library name prefix. +libname_spec=$lt_libname_spec + +# List of archive names. First name is the real one, the rest are links. +# The last name is the one that the linker finds with -lNAME. +library_names_spec=$lt_library_names_spec + +# The coded name of the library, if different from the real name. +soname_spec=$lt_soname_spec + +# Commands used to build and install an old-style archive. +RANLIB=$lt_RANLIB +old_archive_cmds=$lt_old_archive_cmds_CXX +old_postinstall_cmds=$lt_old_postinstall_cmds +old_postuninstall_cmds=$lt_old_postuninstall_cmds + +# Create an old-style archive from a shared archive. +old_archive_from_new_cmds=$lt_old_archive_from_new_cmds_CXX + +# Create a temporary old-style archive to link instead of a shared archive. +old_archive_from_expsyms_cmds=$lt_old_archive_from_expsyms_cmds_CXX + +# Commands used to build and install a shared archive. +archive_cmds=$lt_archive_cmds_CXX +archive_expsym_cmds=$lt_archive_expsym_cmds_CXX +postinstall_cmds=$lt_postinstall_cmds +postuninstall_cmds=$lt_postuninstall_cmds + +# Commands used to build a loadable module (assumed same as above if empty) +module_cmds=$lt_module_cmds_CXX +module_expsym_cmds=$lt_module_expsym_cmds_CXX + +# Commands to strip libraries. +old_striplib=$lt_old_striplib +striplib=$lt_striplib + +# Dependencies to place before the objects being linked to create a +# shared library. +predep_objects=$lt_predep_objects_CXX + +# Dependencies to place after the objects being linked to create a +# shared library. +postdep_objects=$lt_postdep_objects_CXX + +# Dependencies to place before the objects being linked to create a +# shared library. +predeps=$lt_predeps_CXX + +# Dependencies to place after the objects being linked to create a +# shared library. +postdeps=$lt_postdeps_CXX + +# The library search path used internally by the compiler when linking +# a shared library. +compiler_lib_search_path=$lt_compiler_lib_search_path_CXX + +# Method to check whether dependent libraries are shared objects. +deplibs_check_method=$lt_deplibs_check_method + +# Command to use when deplibs_check_method == file_magic. +file_magic_cmd=$lt_file_magic_cmd + +# Flag that allows shared libraries with undefined symbols to be built. +allow_undefined_flag=$lt_allow_undefined_flag_CXX + +# Flag that forces no undefined symbols. +no_undefined_flag=$lt_no_undefined_flag_CXX + +# Commands used to finish a libtool library installation in a directory. +finish_cmds=$lt_finish_cmds + +# Same as above, but a single script fragment to be evaled but not shown. +finish_eval=$lt_finish_eval + +# Take the output of nm and produce a listing of raw symbols and C names. +global_symbol_pipe=$lt_lt_cv_sys_global_symbol_pipe + +# Transform the output of nm in a proper C declaration +global_symbol_to_cdecl=$lt_lt_cv_sys_global_symbol_to_cdecl + +# Transform the output of nm in a C name address pair +global_symbol_to_c_name_address=$lt_lt_cv_sys_global_symbol_to_c_name_address + +# This is the shared library runtime path variable. +runpath_var=$runpath_var + +# This is the shared library path variable. +shlibpath_var=$shlibpath_var + +# Is shlibpath searched before the hard-coded library search path? +shlibpath_overrides_runpath=$shlibpath_overrides_runpath + +# How to hardcode a shared library path into an executable. +hardcode_action=$hardcode_action_CXX + +# Whether we should hardcode library paths into libraries. +hardcode_into_libs=$hardcode_into_libs + +# Flag to hardcode \$libdir into a binary during linking. +# This must work even if \$libdir does not exist. +hardcode_libdir_flag_spec=$lt_hardcode_libdir_flag_spec_CXX + +# If ld is used when linking, flag to hardcode \$libdir into +# a binary during linking. This must work even if \$libdir does +# not exist. +hardcode_libdir_flag_spec_ld=$lt_hardcode_libdir_flag_spec_ld_CXX + +# Whether we need a single -rpath flag with a separated argument. +hardcode_libdir_separator=$lt_hardcode_libdir_separator_CXX + +# Set to yes if using DIR/libNAME${shared_ext} during linking hardcodes DIR into the +# resulting binary. +hardcode_direct=$hardcode_direct_CXX + +# Set to yes if using the -LDIR flag during linking hardcodes DIR into the +# resulting binary. +hardcode_minus_L=$hardcode_minus_L_CXX + +# Set to yes if using SHLIBPATH_VAR=DIR during linking hardcodes DIR into +# the resulting binary. +hardcode_shlibpath_var=$hardcode_shlibpath_var_CXX + +# Set to yes if building a shared library automatically hardcodes DIR into the library +# and all subsequent libraries and executables linked against it. +hardcode_automatic=$hardcode_automatic_CXX + +# Variables whose values should be saved in libtool wrapper scripts and +# restored at relink time. +variables_saved_for_relink="$variables_saved_for_relink" + +# Whether libtool must link a program against all its dependency libraries. +link_all_deplibs=$link_all_deplibs_CXX + +# Compile-time system search path for libraries +sys_lib_search_path_spec=$lt_sys_lib_search_path_spec + +# Run-time system search path for libraries +sys_lib_dlsearch_path_spec=$lt_sys_lib_dlsearch_path_spec + +# Fix the shell variable \$srcfile for the compiler. +fix_srcfile_path="$fix_srcfile_path_CXX" + +# Set to yes if exported symbols are required. +always_export_symbols=$always_export_symbols_CXX + +# The commands to list exported symbols. +export_symbols_cmds=$lt_export_symbols_cmds_CXX + +# The commands to extract the exported symbol list from a shared archive. +extract_expsyms_cmds=$lt_extract_expsyms_cmds + +# Symbols that should not be listed in the preloaded symbols. +exclude_expsyms=$lt_exclude_expsyms_CXX + +# Symbols that must always be exported. +include_expsyms=$lt_include_expsyms_CXX + +# ### END LIBTOOL TAG CONFIG: $tagname + +__EOF__ + + +else + # If there is no Makefile yet, we rely on a make rule to execute + # `config.status --recheck' to rerun these tests and create the + # libtool script then. + ltmain_in=`echo $ltmain | sed -e 's/\.sh$/.in/'` + if test -f "$ltmain_in"; then + test -f Makefile && make "$ltmain" + fi +fi + + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + +CC=$lt_save_CC +LDCXX=$LD +LD=$lt_save_LD +GCC=$lt_save_GCC +with_gnu_ldcxx=$with_gnu_ld +with_gnu_ld=$lt_save_with_gnu_ld +lt_cv_path_LDCXX=$lt_cv_path_LD +lt_cv_path_LD=$lt_save_path_LD +lt_cv_prog_gnu_ldcxx=$lt_cv_prog_gnu_ld +lt_cv_prog_gnu_ld=$lt_save_with_gnu_ld + + else + tagname="" + fi + ;; + + F77) + if test -n "$F77" && test "X$F77" != "Xno"; then + +ac_ext=f +ac_compile='$F77 -c $FFLAGS conftest.$ac_ext >&5' +ac_link='$F77 -o conftest$ac_exeext $FFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_f77_compiler_gnu + + +archive_cmds_need_lc_F77=no +allow_undefined_flag_F77= +always_export_symbols_F77=no +archive_expsym_cmds_F77= +export_dynamic_flag_spec_F77= +hardcode_direct_F77=no +hardcode_libdir_flag_spec_F77= +hardcode_libdir_flag_spec_ld_F77= +hardcode_libdir_separator_F77= +hardcode_minus_L_F77=no +hardcode_automatic_F77=no +module_cmds_F77= +module_expsym_cmds_F77= +link_all_deplibs_F77=unknown +old_archive_cmds_F77=$old_archive_cmds +no_undefined_flag_F77= +whole_archive_flag_spec_F77= +enable_shared_with_static_runtimes_F77=no + +# Source file extension for f77 test sources. +ac_ext=f + +# Object file extension for compiled f77 test sources. +objext=o +objext_F77=$objext + +# Code to be used in simple compile tests +lt_simple_compile_test_code=" subroutine t\n return\n end\n" + +# Code to be used in simple link tests +lt_simple_link_test_code=" program t\n end\n" + +# ltmain only uses $CC for tagged configurations so make sure $CC is set. + +# If no C compiler was specified, use CC. +LTCC=${LTCC-"$CC"} + +# If no C compiler flags were specified, use CFLAGS. +LTCFLAGS=${LTCFLAGS-"$CFLAGS"} + +# Allow CC to be a program name with arguments. +compiler=$CC + + +# save warnings/boilerplate of simple test code +ac_outfile=conftest.$ac_objext +printf "$lt_simple_compile_test_code" >conftest.$ac_ext +eval "$ac_compile" 2>&1 >/dev/null | $SED '/^$/d; /^ *+/d' >conftest.err +_lt_compiler_boilerplate=`cat conftest.err` +$rm conftest* + +ac_outfile=conftest.$ac_objext +printf "$lt_simple_link_test_code" >conftest.$ac_ext +eval "$ac_link" 2>&1 >/dev/null | $SED '/^$/d; /^ *+/d' >conftest.err +_lt_linker_boilerplate=`cat conftest.err` +$rm conftest* + + +# Allow CC to be a program name with arguments. +lt_save_CC="$CC" +CC=${F77-"f77"} +compiler=$CC +compiler_F77=$CC +for cc_temp in $compiler""; do + case $cc_temp in + compile | *[\\/]compile | ccache | *[\\/]ccache ) ;; + distcc | *[\\/]distcc | purify | *[\\/]purify ) ;; + \-*) ;; + *) break;; + esac +done +cc_basename=`$echo "X$cc_temp" | $Xsed -e 's%.*/%%' -e "s%^$host_alias-%%"` + + +echo "$as_me:$LINENO: checking if libtool supports shared libraries" >&5 +echo $ECHO_N "checking if libtool supports shared libraries... $ECHO_C" >&6 +echo "$as_me:$LINENO: result: $can_build_shared" >&5 +echo "${ECHO_T}$can_build_shared" >&6 + +echo "$as_me:$LINENO: checking whether to build shared libraries" >&5 +echo $ECHO_N "checking whether to build shared libraries... $ECHO_C" >&6 +test "$can_build_shared" = "no" && enable_shared=no + +# On AIX, shared libraries and static libraries use the same namespace, and +# are all built from PIC. +case $host_os in +aix3*) + test "$enable_shared" = yes && enable_static=no + if test -n "$RANLIB"; then + archive_cmds="$archive_cmds~\$RANLIB \$lib" + postinstall_cmds='$RANLIB $lib' + fi + ;; +aix4* | aix5*) + if test "$host_cpu" != ia64 && test "$aix_use_runtimelinking" = no ; then + test "$enable_shared" = yes && enable_static=no + fi + ;; +esac +echo "$as_me:$LINENO: result: $enable_shared" >&5 +echo "${ECHO_T}$enable_shared" >&6 + +echo "$as_me:$LINENO: checking whether to build static libraries" >&5 +echo $ECHO_N "checking whether to build static libraries... $ECHO_C" >&6 +# Make sure either enable_shared or enable_static is yes. +test "$enable_shared" = yes || enable_static=yes +echo "$as_me:$LINENO: result: $enable_static" >&5 +echo "${ECHO_T}$enable_static" >&6 + +GCC_F77="$G77" +LD_F77="$LD" + +lt_prog_compiler_wl_F77= +lt_prog_compiler_pic_F77= +lt_prog_compiler_static_F77= + +echo "$as_me:$LINENO: checking for $compiler option to produce PIC" >&5 +echo $ECHO_N "checking for $compiler option to produce PIC... $ECHO_C" >&6 + + if test "$GCC" = yes; then + lt_prog_compiler_wl_F77='-Wl,' + lt_prog_compiler_static_F77='-static' + + case $host_os in + aix*) + # All AIX code is PIC. + if test "$host_cpu" = ia64; then + # AIX 5 now supports IA64 processor + lt_prog_compiler_static_F77='-Bstatic' + fi + ;; + + amigaos*) + # FIXME: we need at least 68020 code to build shared libraries, but + # adding the `-m68020' flag to GCC prevents building anything better, + # like `-m68040'. + lt_prog_compiler_pic_F77='-m68020 -resident32 -malways-restore-a4' + ;; + + beos* | cygwin* | irix5* | irix6* | nonstopux* | osf3* | osf4* | osf5*) + # PIC is the default for these OSes. + ;; + + mingw* | pw32* | os2*) + # This hack is so that the source file can tell whether it is being + # built for inclusion in a dll (and should export symbols for example). + lt_prog_compiler_pic_F77='-DDLL_EXPORT' + ;; + + darwin* | rhapsody*) + # PIC is the default on this platform + # Common symbols not allowed in MH_DYLIB files + lt_prog_compiler_pic_F77='-fno-common' + ;; + + interix3*) + # Interix 3.x gcc -fpic/-fPIC options generate broken code. + # Instead, we relocate shared libraries at runtime. + ;; + + msdosdjgpp*) + # Just because we use GCC doesn't mean we suddenly get shared libraries + # on systems that don't support them. + lt_prog_compiler_can_build_shared_F77=no + enable_shared=no + ;; + + sysv4*MP*) + if test -d /usr/nec; then + lt_prog_compiler_pic_F77=-Kconform_pic + fi + ;; + + hpux*) + # PIC is the default for IA64 HP-UX and 64-bit HP-UX, but + # not for PA HP-UX. + case $host_cpu in + hppa*64*|ia64*) + # +Z the default + ;; + *) + lt_prog_compiler_pic_F77='-fPIC' + ;; + esac + ;; + + *) + lt_prog_compiler_pic_F77='-fPIC' + ;; + esac + else + # PORTME Check for flag to pass linker flags through the system compiler. + case $host_os in + aix*) + lt_prog_compiler_wl_F77='-Wl,' + if test "$host_cpu" = ia64; then + # AIX 5 now supports IA64 processor + lt_prog_compiler_static_F77='-Bstatic' + else + lt_prog_compiler_static_F77='-bnso -bI:/lib/syscalls.exp' + fi + ;; + darwin*) + # PIC is the default on this platform + # Common symbols not allowed in MH_DYLIB files + case $cc_basename in + xlc*) + lt_prog_compiler_pic_F77='-qnocommon' + lt_prog_compiler_wl_F77='-Wl,' + ;; + esac + ;; + + mingw* | pw32* | os2*) + # This hack is so that the source file can tell whether it is being + # built for inclusion in a dll (and should export symbols for example). + lt_prog_compiler_pic_F77='-DDLL_EXPORT' + ;; + + hpux9* | hpux10* | hpux11*) + lt_prog_compiler_wl_F77='-Wl,' + # PIC is the default for IA64 HP-UX and 64-bit HP-UX, but + # not for PA HP-UX. + case $host_cpu in + hppa*64*|ia64*) + # +Z the default + ;; + *) + lt_prog_compiler_pic_F77='+Z' + ;; + esac + # Is there a better lt_prog_compiler_static that works with the bundled CC? + lt_prog_compiler_static_F77='${wl}-a ${wl}archive' + ;; + + irix5* | irix6* | nonstopux*) + lt_prog_compiler_wl_F77='-Wl,' + # PIC (with -KPIC) is the default. + lt_prog_compiler_static_F77='-non_shared' + ;; + + newsos6) + lt_prog_compiler_pic_F77='-KPIC' + lt_prog_compiler_static_F77='-Bstatic' + ;; + + linux*) + case $cc_basename in + icc* | ecc*) + lt_prog_compiler_wl_F77='-Wl,' + lt_prog_compiler_pic_F77='-KPIC' + lt_prog_compiler_static_F77='-static' + ;; + pgcc* | pgf77* | pgf90* | pgf95*) + # Portland Group compilers (*not* the Pentium gcc compiler, + # which looks to be a dead project) + lt_prog_compiler_wl_F77='-Wl,' + lt_prog_compiler_pic_F77='-fpic' + lt_prog_compiler_static_F77='-Bstatic' + ;; + ccc*) + lt_prog_compiler_wl_F77='-Wl,' + # All Alpha code is PIC. + lt_prog_compiler_static_F77='-non_shared' + ;; + esac + ;; + + osf3* | osf4* | osf5*) + lt_prog_compiler_wl_F77='-Wl,' + # All OSF/1 code is PIC. + lt_prog_compiler_static_F77='-non_shared' + ;; + + solaris*) + lt_prog_compiler_pic_F77='-KPIC' + lt_prog_compiler_static_F77='-Bstatic' + case $cc_basename in + f77* | f90* | f95*) + lt_prog_compiler_wl_F77='-Qoption ld ';; + *) + lt_prog_compiler_wl_F77='-Wl,';; + esac + ;; + + sunos4*) + lt_prog_compiler_wl_F77='-Qoption ld ' + lt_prog_compiler_pic_F77='-PIC' + lt_prog_compiler_static_F77='-Bstatic' + ;; + + sysv4 | sysv4.2uw2* | sysv4.3*) + lt_prog_compiler_wl_F77='-Wl,' + lt_prog_compiler_pic_F77='-KPIC' + lt_prog_compiler_static_F77='-Bstatic' + ;; + + sysv4*MP*) + if test -d /usr/nec ;then + lt_prog_compiler_pic_F77='-Kconform_pic' + lt_prog_compiler_static_F77='-Bstatic' + fi + ;; + + sysv5* | unixware* | sco3.2v5* | sco5v6* | OpenUNIX*) + lt_prog_compiler_wl_F77='-Wl,' + lt_prog_compiler_pic_F77='-KPIC' + lt_prog_compiler_static_F77='-Bstatic' + ;; + + unicos*) + lt_prog_compiler_wl_F77='-Wl,' + lt_prog_compiler_can_build_shared_F77=no + ;; + + uts4*) + lt_prog_compiler_pic_F77='-pic' + lt_prog_compiler_static_F77='-Bstatic' + ;; + + *) + lt_prog_compiler_can_build_shared_F77=no + ;; + esac + fi + +echo "$as_me:$LINENO: result: $lt_prog_compiler_pic_F77" >&5 +echo "${ECHO_T}$lt_prog_compiler_pic_F77" >&6 + +# +# Check to make sure the PIC flag actually works. +# +if test -n "$lt_prog_compiler_pic_F77"; then + +echo "$as_me:$LINENO: checking if $compiler PIC flag $lt_prog_compiler_pic_F77 works" >&5 +echo $ECHO_N "checking if $compiler PIC flag $lt_prog_compiler_pic_F77 works... $ECHO_C" >&6 +if test "${lt_prog_compiler_pic_works_F77+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + lt_prog_compiler_pic_works_F77=no + ac_outfile=conftest.$ac_objext + printf "$lt_simple_compile_test_code" > conftest.$ac_ext + lt_compiler_flag="$lt_prog_compiler_pic_F77" + # Insert the option either (1) after the last *FLAGS variable, or + # (2) before a word containing "conftest.", or (3) at the end. + # Note that $ac_compile itself does not contain backslashes and begins + # with a dollar sign (not a hyphen), so the echo should work correctly. + # The option is referenced via a variable to avoid confusing sed. + lt_compile=`echo "$ac_compile" | $SED \ + -e 's:.*FLAGS}\{0,1\} :&$lt_compiler_flag :; t' \ + -e 's: [^ ]*conftest\.: $lt_compiler_flag&:; t' \ + -e 's:$: $lt_compiler_flag:'` + (eval echo "\"\$as_me:12956: $lt_compile\"" >&5) + (eval "$lt_compile" 2>conftest.err) + ac_status=$? + cat conftest.err >&5 + echo "$as_me:12960: \$? = $ac_status" >&5 + if (exit $ac_status) && test -s "$ac_outfile"; then + # The compiler can only warn and ignore the option if not recognized + # So say no if there are warnings other than the usual output. + $echo "X$_lt_compiler_boilerplate" | $Xsed -e '/^$/d' >conftest.exp + $SED '/^$/d; /^ *+/d' conftest.err >conftest.er2 + if test ! -s conftest.er2 || diff conftest.exp conftest.er2 >/dev/null; then + lt_prog_compiler_pic_works_F77=yes + fi + fi + $rm conftest* + +fi +echo "$as_me:$LINENO: result: $lt_prog_compiler_pic_works_F77" >&5 +echo "${ECHO_T}$lt_prog_compiler_pic_works_F77" >&6 + +if test x"$lt_prog_compiler_pic_works_F77" = xyes; then + case $lt_prog_compiler_pic_F77 in + "" | " "*) ;; + *) lt_prog_compiler_pic_F77=" $lt_prog_compiler_pic_F77" ;; + esac +else + lt_prog_compiler_pic_F77= + lt_prog_compiler_can_build_shared_F77=no +fi + +fi +case $host_os in + # For platforms which do not support PIC, -DPIC is meaningless: + *djgpp*) + lt_prog_compiler_pic_F77= + ;; + *) + lt_prog_compiler_pic_F77="$lt_prog_compiler_pic_F77" + ;; +esac + +# +# Check to make sure the static flag actually works. +# +wl=$lt_prog_compiler_wl_F77 eval lt_tmp_static_flag=\"$lt_prog_compiler_static_F77\" +echo "$as_me:$LINENO: checking if $compiler static flag $lt_tmp_static_flag works" >&5 +echo $ECHO_N "checking if $compiler static flag $lt_tmp_static_flag works... $ECHO_C" >&6 +if test "${lt_prog_compiler_static_works_F77+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + lt_prog_compiler_static_works_F77=no + save_LDFLAGS="$LDFLAGS" + LDFLAGS="$LDFLAGS $lt_tmp_static_flag" + printf "$lt_simple_link_test_code" > conftest.$ac_ext + if (eval $ac_link 2>conftest.err) && test -s conftest$ac_exeext; then + # The linker can only warn and ignore the option if not recognized + # So say no if there are warnings + if test -s conftest.err; then + # Append any errors to the config.log. + cat conftest.err 1>&5 + $echo "X$_lt_linker_boilerplate" | $Xsed -e '/^$/d' > conftest.exp + $SED '/^$/d; /^ *+/d' conftest.err >conftest.er2 + if diff conftest.exp conftest.er2 >/dev/null; then + lt_prog_compiler_static_works_F77=yes + fi + else + lt_prog_compiler_static_works_F77=yes + fi + fi + $rm conftest* + LDFLAGS="$save_LDFLAGS" + +fi +echo "$as_me:$LINENO: result: $lt_prog_compiler_static_works_F77" >&5 +echo "${ECHO_T}$lt_prog_compiler_static_works_F77" >&6 + +if test x"$lt_prog_compiler_static_works_F77" = xyes; then + : +else + lt_prog_compiler_static_F77= +fi + + +echo "$as_me:$LINENO: checking if $compiler supports -c -o file.$ac_objext" >&5 +echo $ECHO_N "checking if $compiler supports -c -o file.$ac_objext... $ECHO_C" >&6 +if test "${lt_cv_prog_compiler_c_o_F77+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + lt_cv_prog_compiler_c_o_F77=no + $rm -r conftest 2>/dev/null + mkdir conftest + cd conftest + mkdir out + printf "$lt_simple_compile_test_code" > conftest.$ac_ext + + lt_compiler_flag="-o out/conftest2.$ac_objext" + # Insert the option either (1) after the last *FLAGS variable, or + # (2) before a word containing "conftest.", or (3) at the end. + # Note that $ac_compile itself does not contain backslashes and begins + # with a dollar sign (not a hyphen), so the echo should work correctly. + lt_compile=`echo "$ac_compile" | $SED \ + -e 's:.*FLAGS}\{0,1\} :&$lt_compiler_flag :; t' \ + -e 's: [^ ]*conftest\.: $lt_compiler_flag&:; t' \ + -e 's:$: $lt_compiler_flag:'` + (eval echo "\"\$as_me:13060: $lt_compile\"" >&5) + (eval "$lt_compile" 2>out/conftest.err) + ac_status=$? + cat out/conftest.err >&5 + echo "$as_me:13064: \$? = $ac_status" >&5 + if (exit $ac_status) && test -s out/conftest2.$ac_objext + then + # The compiler can only warn and ignore the option if not recognized + # So say no if there are warnings + $echo "X$_lt_compiler_boilerplate" | $Xsed -e '/^$/d' > out/conftest.exp + $SED '/^$/d; /^ *+/d' out/conftest.err >out/conftest.er2 + if test ! -s out/conftest.er2 || diff out/conftest.exp out/conftest.er2 >/dev/null; then + lt_cv_prog_compiler_c_o_F77=yes + fi + fi + chmod u+w . 2>&5 + $rm conftest* + # SGI C++ compiler will create directory out/ii_files/ for + # template instantiation + test -d out/ii_files && $rm out/ii_files/* && rmdir out/ii_files + $rm out/* && rmdir out + cd .. + rmdir conftest + $rm conftest* + +fi +echo "$as_me:$LINENO: result: $lt_cv_prog_compiler_c_o_F77" >&5 +echo "${ECHO_T}$lt_cv_prog_compiler_c_o_F77" >&6 + + +hard_links="nottested" +if test "$lt_cv_prog_compiler_c_o_F77" = no && test "$need_locks" != no; then + # do not overwrite the value of need_locks provided by the user + echo "$as_me:$LINENO: checking if we can lock with hard links" >&5 +echo $ECHO_N "checking if we can lock with hard links... $ECHO_C" >&6 + hard_links=yes + $rm conftest* + ln conftest.a conftest.b 2>/dev/null && hard_links=no + touch conftest.a + ln conftest.a conftest.b 2>&5 || hard_links=no + ln conftest.a conftest.b 2>/dev/null && hard_links=no + echo "$as_me:$LINENO: result: $hard_links" >&5 +echo "${ECHO_T}$hard_links" >&6 + if test "$hard_links" = no; then + { echo "$as_me:$LINENO: WARNING: \`$CC' does not support \`-c -o', so \`make -j' may be unsafe" >&5 +echo "$as_me: WARNING: \`$CC' does not support \`-c -o', so \`make -j' may be unsafe" >&2;} + need_locks=warn + fi +else + need_locks=no +fi + +echo "$as_me:$LINENO: checking whether the $compiler linker ($LD) supports shared libraries" >&5 +echo $ECHO_N "checking whether the $compiler linker ($LD) supports shared libraries... $ECHO_C" >&6 + + runpath_var= + allow_undefined_flag_F77= + enable_shared_with_static_runtimes_F77=no + archive_cmds_F77= + archive_expsym_cmds_F77= + old_archive_From_new_cmds_F77= + old_archive_from_expsyms_cmds_F77= + export_dynamic_flag_spec_F77= + whole_archive_flag_spec_F77= + thread_safe_flag_spec_F77= + hardcode_libdir_flag_spec_F77= + hardcode_libdir_flag_spec_ld_F77= + hardcode_libdir_separator_F77= + hardcode_direct_F77=no + hardcode_minus_L_F77=no + hardcode_shlibpath_var_F77=unsupported + link_all_deplibs_F77=unknown + hardcode_automatic_F77=no + module_cmds_F77= + module_expsym_cmds_F77= + always_export_symbols_F77=no + export_symbols_cmds_F77='$NM $libobjs $convenience | $global_symbol_pipe | $SED '\''s/.* //'\'' | sort | uniq > $export_symbols' + # include_expsyms should be a list of space-separated symbols to be *always* + # included in the symbol list + include_expsyms_F77= + # exclude_expsyms can be an extended regexp of symbols to exclude + # it will be wrapped by ` (' and `)$', so one must not match beginning or + # end of line. Example: `a|bc|.*d.*' will exclude the symbols `a' and `bc', + # as well as any symbol that contains `d'. + exclude_expsyms_F77="_GLOBAL_OFFSET_TABLE_" + # Although _GLOBAL_OFFSET_TABLE_ is a valid symbol C name, most a.out + # platforms (ab)use it in PIC code, but their linkers get confused if + # the symbol is explicitly referenced. Since portable code cannot + # rely on this symbol name, it's probably fine to never include it in + # preloaded symbol tables. + extract_expsyms_cmds= + # Just being paranoid about ensuring that cc_basename is set. + for cc_temp in $compiler""; do + case $cc_temp in + compile | *[\\/]compile | ccache | *[\\/]ccache ) ;; + distcc | *[\\/]distcc | purify | *[\\/]purify ) ;; + \-*) ;; + *) break;; + esac +done +cc_basename=`$echo "X$cc_temp" | $Xsed -e 's%.*/%%' -e "s%^$host_alias-%%"` + + case $host_os in + cygwin* | mingw* | pw32*) + # FIXME: the MSVC++ port hasn't been tested in a loooong time + # When not using gcc, we currently assume that we are using + # Microsoft Visual C++. + if test "$GCC" != yes; then + with_gnu_ld=no + fi + ;; + interix*) + # we just hope/assume this is gcc and not c89 (= MSVC++) + with_gnu_ld=yes + ;; + openbsd*) + with_gnu_ld=no + ;; + esac + + ld_shlibs_F77=yes + if test "$with_gnu_ld" = yes; then + # If archive_cmds runs LD, not CC, wlarc should be empty + wlarc='${wl}' + + # Set some defaults for GNU ld with shared library support. These + # are reset later if shared libraries are not supported. Putting them + # here allows them to be overridden if necessary. + runpath_var=LD_RUN_PATH + hardcode_libdir_flag_spec_F77='${wl}--rpath ${wl}$libdir' + export_dynamic_flag_spec_F77='${wl}--export-dynamic' + # ancient GNU ld didn't support --whole-archive et. al. + if $LD --help 2>&1 | grep 'no-whole-archive' > /dev/null; then + whole_archive_flag_spec_F77="$wlarc"'--whole-archive$convenience '"$wlarc"'--no-whole-archive' + else + whole_archive_flag_spec_F77= + fi + supports_anon_versioning=no + case `$LD -v 2>/dev/null` in + *\ [01].* | *\ 2.[0-9].* | *\ 2.10.*) ;; # catch versions < 2.11 + *\ 2.11.93.0.2\ *) supports_anon_versioning=yes ;; # RH7.3 ... + *\ 2.11.92.0.12\ *) supports_anon_versioning=yes ;; # Mandrake 8.2 ... + *\ 2.11.*) ;; # other 2.11 versions + *) supports_anon_versioning=yes ;; + esac + + # See if GNU ld supports shared libraries. + case $host_os in + aix3* | aix4* | aix5*) + # On AIX/PPC, the GNU linker is very broken + if test "$host_cpu" != ia64; then + ld_shlibs_F77=no + cat <&2 + +*** Warning: the GNU linker, at least up to release 2.9.1, is reported +*** to be unable to reliably create shared libraries on AIX. +*** Therefore, libtool is disabling shared libraries support. If you +*** really care for shared libraries, you may want to modify your PATH +*** so that a non-GNU linker is found, and then restart. + +EOF + fi + ;; + + amigaos*) + archive_cmds_F77='$rm $output_objdir/a2ixlibrary.data~$echo "#define NAME $libname" > $output_objdir/a2ixlibrary.data~$echo "#define LIBRARY_ID 1" >> $output_objdir/a2ixlibrary.data~$echo "#define VERSION $major" >> $output_objdir/a2ixlibrary.data~$echo "#define REVISION $revision" >> $output_objdir/a2ixlibrary.data~$AR $AR_FLAGS $lib $libobjs~$RANLIB $lib~(cd $output_objdir && a2ixlibrary -32)' + hardcode_libdir_flag_spec_F77='-L$libdir' + hardcode_minus_L_F77=yes + + # Samuel A. Falvo II reports + # that the semantics of dynamic libraries on AmigaOS, at least up + # to version 4, is to share data among multiple programs linked + # with the same dynamic library. Since this doesn't match the + # behavior of shared libraries on other platforms, we can't use + # them. + ld_shlibs_F77=no + ;; + + beos*) + if $LD --help 2>&1 | grep ': supported targets:.* elf' > /dev/null; then + allow_undefined_flag_F77=unsupported + # Joseph Beckenbach says some releases of gcc + # support --undefined. This deserves some investigation. FIXME + archive_cmds_F77='$CC -nostart $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + else + ld_shlibs_F77=no + fi + ;; + + cygwin* | mingw* | pw32*) + # _LT_AC_TAGVAR(hardcode_libdir_flag_spec, F77) is actually meaningless, + # as there is no search path for DLLs. + hardcode_libdir_flag_spec_F77='-L$libdir' + allow_undefined_flag_F77=unsupported + always_export_symbols_F77=no + enable_shared_with_static_runtimes_F77=yes + export_symbols_cmds_F77='$NM $libobjs $convenience | $global_symbol_pipe | $SED -e '\''/^[BCDGRS] /s/.* \([^ ]*\)/\1 DATA/'\'' | $SED -e '\''/^[AITW] /s/.* //'\'' | sort | uniq > $export_symbols' + + if $LD --help 2>&1 | grep 'auto-import' > /dev/null; then + archive_cmds_F77='$CC -shared $libobjs $deplibs $compiler_flags -o $output_objdir/$soname ${wl}--enable-auto-image-base -Xlinker --out-implib -Xlinker $lib' + # If the export-symbols file already is a .def file (1st line + # is EXPORTS), use it as is; otherwise, prepend... + archive_expsym_cmds_F77='if test "x`$SED 1q $export_symbols`" = xEXPORTS; then + cp $export_symbols $output_objdir/$soname.def; + else + echo EXPORTS > $output_objdir/$soname.def; + cat $export_symbols >> $output_objdir/$soname.def; + fi~ + $CC -shared $output_objdir/$soname.def $libobjs $deplibs $compiler_flags -o $output_objdir/$soname ${wl}--enable-auto-image-base -Xlinker --out-implib -Xlinker $lib' + else + ld_shlibs_F77=no + fi + ;; + + interix3*) + hardcode_direct_F77=no + hardcode_shlibpath_var_F77=no + hardcode_libdir_flag_spec_F77='${wl}-rpath,$libdir' + export_dynamic_flag_spec_F77='${wl}-E' + # Hack: On Interix 3.x, we cannot compile PIC because of a broken gcc. + # Instead, shared libraries are loaded at an image base (0x10000000 by + # default) and relocated if they conflict, which is a slow very memory + # consuming and fragmenting process. To avoid this, we pick a random, + # 256 KiB-aligned image base between 0x50000000 and 0x6FFC0000 at link + # time. Moving up from 0x10000000 also allows more sbrk(2) space. + archive_cmds_F77='$CC -shared $pic_flag $libobjs $deplibs $compiler_flags ${wl}-h,$soname ${wl}--image-base,`expr ${RANDOM-$$} % 4096 / 2 \* 262144 + 1342177280` -o $lib' + archive_expsym_cmds_F77='sed "s,^,_," $export_symbols >$output_objdir/$soname.expsym~$CC -shared $pic_flag $libobjs $deplibs $compiler_flags ${wl}-h,$soname ${wl}--retain-symbols-file,$output_objdir/$soname.expsym ${wl}--image-base,`expr ${RANDOM-$$} % 4096 / 2 \* 262144 + 1342177280` -o $lib' + ;; + + linux*) + if $LD --help 2>&1 | grep ': supported targets:.* elf' > /dev/null; then + tmp_addflag= + case $cc_basename,$host_cpu in + pgcc*) # Portland Group C compiler + whole_archive_flag_spec_F77='${wl}--whole-archive`for conv in $convenience\"\"; do test -n \"$conv\" && new_convenience=\"$new_convenience,$conv\"; done; $echo \"$new_convenience\"` ${wl}--no-whole-archive' + tmp_addflag=' $pic_flag' + ;; + pgf77* | pgf90* | pgf95*) # Portland Group f77 and f90 compilers + whole_archive_flag_spec_F77='${wl}--whole-archive`for conv in $convenience\"\"; do test -n \"$conv\" && new_convenience=\"$new_convenience,$conv\"; done; $echo \"$new_convenience\"` ${wl}--no-whole-archive' + tmp_addflag=' $pic_flag -Mnomain' ;; + ecc*,ia64* | icc*,ia64*) # Intel C compiler on ia64 + tmp_addflag=' -i_dynamic' ;; + efc*,ia64* | ifort*,ia64*) # Intel Fortran compiler on ia64 + tmp_addflag=' -i_dynamic -nofor_main' ;; + ifc* | ifort*) # Intel Fortran compiler + tmp_addflag=' -nofor_main' ;; + esac + archive_cmds_F77='$CC -shared'"$tmp_addflag"' $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + + if test $supports_anon_versioning = yes; then + archive_expsym_cmds_F77='$echo "{ global:" > $output_objdir/$libname.ver~ + cat $export_symbols | sed -e "s/\(.*\)/\1;/" >> $output_objdir/$libname.ver~ + $echo "local: *; };" >> $output_objdir/$libname.ver~ + $CC -shared'"$tmp_addflag"' $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-version-script ${wl}$output_objdir/$libname.ver -o $lib' + fi + else + ld_shlibs_F77=no + fi + ;; + + netbsd*) + if echo __ELF__ | $CC -E - | grep __ELF__ >/dev/null; then + archive_cmds_F77='$LD -Bshareable $libobjs $deplibs $linker_flags -o $lib' + wlarc= + else + archive_cmds_F77='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + archive_expsym_cmds_F77='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-retain-symbols-file $wl$export_symbols -o $lib' + fi + ;; + + solaris*) + if $LD -v 2>&1 | grep 'BFD 2\.8' > /dev/null; then + ld_shlibs_F77=no + cat <&2 + +*** Warning: The releases 2.8.* of the GNU linker cannot reliably +*** create shared libraries on Solaris systems. Therefore, libtool +*** is disabling shared libraries support. We urge you to upgrade GNU +*** binutils to release 2.9.1 or newer. Another option is to modify +*** your PATH or compiler configuration so that the native linker is +*** used, and then restart. + +EOF + elif $LD --help 2>&1 | grep ': supported targets:.* elf' > /dev/null; then + archive_cmds_F77='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + archive_expsym_cmds_F77='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-retain-symbols-file $wl$export_symbols -o $lib' + else + ld_shlibs_F77=no + fi + ;; + + sysv5* | sco3.2v5* | sco5v6* | unixware* | OpenUNIX*) + case `$LD -v 2>&1` in + *\ [01].* | *\ 2.[0-9].* | *\ 2.1[0-5].*) + ld_shlibs_F77=no + cat <<_LT_EOF 1>&2 + +*** Warning: Releases of the GNU linker prior to 2.16.91.0.3 can not +*** reliably create shared libraries on SCO systems. Therefore, libtool +*** is disabling shared libraries support. We urge you to upgrade GNU +*** binutils to release 2.16.91.0.3 or newer. Another option is to modify +*** your PATH or compiler configuration so that the native linker is +*** used, and then restart. + +_LT_EOF + ;; + *) + if $LD --help 2>&1 | grep ': supported targets:.* elf' > /dev/null; then + hardcode_libdir_flag_spec_F77='`test -z "$SCOABSPATH" && echo ${wl}-rpath,$libdir`' + archive_cmds_F77='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname,\${SCOABSPATH:+${install_libdir}/}$soname -o $lib' + archive_expsym_cmds_F77='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname,\${SCOABSPATH:+${install_libdir}/}$soname,-retain-symbols-file,$export_symbols -o $lib' + else + ld_shlibs_F77=no + fi + ;; + esac + ;; + + sunos4*) + archive_cmds_F77='$LD -assert pure-text -Bshareable -o $lib $libobjs $deplibs $linker_flags' + wlarc= + hardcode_direct_F77=yes + hardcode_shlibpath_var_F77=no + ;; + + *) + if $LD --help 2>&1 | grep ': supported targets:.* elf' > /dev/null; then + archive_cmds_F77='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + archive_expsym_cmds_F77='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-retain-symbols-file $wl$export_symbols -o $lib' + else + ld_shlibs_F77=no + fi + ;; + esac + + if test "$ld_shlibs_F77" = no; then + runpath_var= + hardcode_libdir_flag_spec_F77= + export_dynamic_flag_spec_F77= + whole_archive_flag_spec_F77= + fi + else + # PORTME fill in a description of your system's linker (not GNU ld) + case $host_os in + aix3*) + allow_undefined_flag_F77=unsupported + always_export_symbols_F77=yes + archive_expsym_cmds_F77='$LD -o $output_objdir/$soname $libobjs $deplibs $linker_flags -bE:$export_symbols -T512 -H512 -bM:SRE~$AR $AR_FLAGS $lib $output_objdir/$soname' + # Note: this linker hardcodes the directories in LIBPATH if there + # are no directories specified by -L. + hardcode_minus_L_F77=yes + if test "$GCC" = yes && test -z "$lt_prog_compiler_static"; then + # Neither direct hardcoding nor static linking is supported with a + # broken collect2. + hardcode_direct_F77=unsupported + fi + ;; + + aix4* | aix5*) + if test "$host_cpu" = ia64; then + # On IA64, the linker does run time linking by default, so we don't + # have to do anything special. + aix_use_runtimelinking=no + exp_sym_flag='-Bexport' + no_entry_flag="" + else + # If we're using GNU nm, then we don't want the "-C" option. + # -C means demangle to AIX nm, but means don't demangle with GNU nm + if $NM -V 2>&1 | grep 'GNU' > /dev/null; then + export_symbols_cmds_F77='$NM -Bpg $libobjs $convenience | awk '\''{ if (((\$2 == "T") || (\$2 == "D") || (\$2 == "B")) && (substr(\$3,1,1) != ".")) { print \$3 } }'\'' | sort -u > $export_symbols' + else + export_symbols_cmds_F77='$NM -BCpg $libobjs $convenience | awk '\''{ if (((\$2 == "T") || (\$2 == "D") || (\$2 == "B")) && (substr(\$3,1,1) != ".")) { print \$3 } }'\'' | sort -u > $export_symbols' + fi + aix_use_runtimelinking=no + + # Test if we are trying to use run time linking or normal + # AIX style linking. If -brtl is somewhere in LDFLAGS, we + # need to do runtime linking. + case $host_os in aix4.[23]|aix4.[23].*|aix5*) + for ld_flag in $LDFLAGS; do + if (test $ld_flag = "-brtl" || test $ld_flag = "-Wl,-brtl"); then + aix_use_runtimelinking=yes + break + fi + done + ;; + esac + + exp_sym_flag='-bexport' + no_entry_flag='-bnoentry' + fi + + # When large executables or shared objects are built, AIX ld can + # have problems creating the table of contents. If linking a library + # or program results in "error TOC overflow" add -mminimal-toc to + # CXXFLAGS/CFLAGS for g++/gcc. In the cases where that is not + # enough to fix the problem, add -Wl,-bbigtoc to LDFLAGS. + + archive_cmds_F77='' + hardcode_direct_F77=yes + hardcode_libdir_separator_F77=':' + link_all_deplibs_F77=yes + + if test "$GCC" = yes; then + case $host_os in aix4.[012]|aix4.[012].*) + # We only want to do this on AIX 4.2 and lower, the check + # below for broken collect2 doesn't work under 4.3+ + collect2name=`${CC} -print-prog-name=collect2` + if test -f "$collect2name" && \ + strings "$collect2name" | grep resolve_lib_name >/dev/null + then + # We have reworked collect2 + hardcode_direct_F77=yes + else + # We have old collect2 + hardcode_direct_F77=unsupported + # It fails to find uninstalled libraries when the uninstalled + # path is not listed in the libpath. Setting hardcode_minus_L + # to unsupported forces relinking + hardcode_minus_L_F77=yes + hardcode_libdir_flag_spec_F77='-L$libdir' + hardcode_libdir_separator_F77= + fi + ;; + esac + shared_flag='-shared' + if test "$aix_use_runtimelinking" = yes; then + shared_flag="$shared_flag "'${wl}-G' + fi + else + # not using gcc + if test "$host_cpu" = ia64; then + # VisualAge C++, Version 5.5 for AIX 5L for IA-64, Beta 3 Release + # chokes on -Wl,-G. The following line is correct: + shared_flag='-G' + else + if test "$aix_use_runtimelinking" = yes; then + shared_flag='${wl}-G' + else + shared_flag='${wl}-bM:SRE' + fi + fi + fi + + # It seems that -bexpall does not export symbols beginning with + # underscore (_), so it is better to generate a list of symbols to export. + always_export_symbols_F77=yes + if test "$aix_use_runtimelinking" = yes; then + # Warning - without using the other runtime loading flags (-brtl), + # -berok will link without error, but may produce a broken library. + allow_undefined_flag_F77='-berok' + # Determine the default libpath from the value encoded in an empty executable. + cat >conftest.$ac_ext <<_ACEOF + program main + + end +_ACEOF +rm -f conftest.$ac_objext conftest$ac_exeext +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_f77_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest$ac_exeext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + +aix_libpath=`dump -H conftest$ac_exeext 2>/dev/null | $SED -n -e '/Import File Strings/,/^$/ { /^0/ { s/^0 *\(.*\)$/\1/; p; } +}'` +# Check for a 64-bit object if we didn't find anything. +if test -z "$aix_libpath"; then aix_libpath=`dump -HX64 conftest$ac_exeext 2>/dev/null | $SED -n -e '/Import File Strings/,/^$/ { /^0/ { s/^0 *\(.*\)$/\1/; p; } +}'`; fi +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +fi +rm -f conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +if test -z "$aix_libpath"; then aix_libpath="/usr/lib:/lib"; fi + + hardcode_libdir_flag_spec_F77='${wl}-blibpath:$libdir:'"$aix_libpath" + archive_expsym_cmds_F77="\$CC"' -o $output_objdir/$soname $libobjs $deplibs '"\${wl}$no_entry_flag"' $compiler_flags `if test "x${allow_undefined_flag}" != "x"; then echo "${wl}${allow_undefined_flag}"; else :; fi` '"\${wl}$exp_sym_flag:\$export_symbols $shared_flag" + else + if test "$host_cpu" = ia64; then + hardcode_libdir_flag_spec_F77='${wl}-R $libdir:/usr/lib:/lib' + allow_undefined_flag_F77="-z nodefs" + archive_expsym_cmds_F77="\$CC $shared_flag"' -o $output_objdir/$soname $libobjs $deplibs '"\${wl}$no_entry_flag"' $compiler_flags ${wl}${allow_undefined_flag} '"\${wl}$exp_sym_flag:\$export_symbols" + else + # Determine the default libpath from the value encoded in an empty executable. + cat >conftest.$ac_ext <<_ACEOF + program main + + end +_ACEOF +rm -f conftest.$ac_objext conftest$ac_exeext +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_f77_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest$ac_exeext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + +aix_libpath=`dump -H conftest$ac_exeext 2>/dev/null | $SED -n -e '/Import File Strings/,/^$/ { /^0/ { s/^0 *\(.*\)$/\1/; p; } +}'` +# Check for a 64-bit object if we didn't find anything. +if test -z "$aix_libpath"; then aix_libpath=`dump -HX64 conftest$ac_exeext 2>/dev/null | $SED -n -e '/Import File Strings/,/^$/ { /^0/ { s/^0 *\(.*\)$/\1/; p; } +}'`; fi +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +fi +rm -f conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +if test -z "$aix_libpath"; then aix_libpath="/usr/lib:/lib"; fi + + hardcode_libdir_flag_spec_F77='${wl}-blibpath:$libdir:'"$aix_libpath" + # Warning - without using the other run time loading flags, + # -berok will link without error, but may produce a broken library. + no_undefined_flag_F77=' ${wl}-bernotok' + allow_undefined_flag_F77=' ${wl}-berok' + # Exported symbols can be pulled into shared objects from archives + whole_archive_flag_spec_F77='$convenience' + archive_cmds_need_lc_F77=yes + # This is similar to how AIX traditionally builds its shared libraries. + archive_expsym_cmds_F77="\$CC $shared_flag"' -o $output_objdir/$soname $libobjs $deplibs ${wl}-bnoentry $compiler_flags ${wl}-bE:$export_symbols${allow_undefined_flag}~$AR $AR_FLAGS $output_objdir/$libname$release.a $output_objdir/$soname' + fi + fi + ;; + + amigaos*) + archive_cmds_F77='$rm $output_objdir/a2ixlibrary.data~$echo "#define NAME $libname" > $output_objdir/a2ixlibrary.data~$echo "#define LIBRARY_ID 1" >> $output_objdir/a2ixlibrary.data~$echo "#define VERSION $major" >> $output_objdir/a2ixlibrary.data~$echo "#define REVISION $revision" >> $output_objdir/a2ixlibrary.data~$AR $AR_FLAGS $lib $libobjs~$RANLIB $lib~(cd $output_objdir && a2ixlibrary -32)' + hardcode_libdir_flag_spec_F77='-L$libdir' + hardcode_minus_L_F77=yes + # see comment about different semantics on the GNU ld section + ld_shlibs_F77=no + ;; + + bsdi[45]*) + export_dynamic_flag_spec_F77=-rdynamic + ;; + + cygwin* | mingw* | pw32*) + # When not using gcc, we currently assume that we are using + # Microsoft Visual C++. + # hardcode_libdir_flag_spec is actually meaningless, as there is + # no search path for DLLs. + hardcode_libdir_flag_spec_F77=' ' + allow_undefined_flag_F77=unsupported + # Tell ltmain to make .lib files, not .a files. + libext=lib + # Tell ltmain to make .dll files, not .so files. + shrext_cmds=".dll" + # FIXME: Setting linknames here is a bad hack. + archive_cmds_F77='$CC -o $lib $libobjs $compiler_flags `echo "$deplibs" | $SED -e '\''s/ -lc$//'\''` -link -dll~linknames=' + # The linker will automatically build a .lib file if we build a DLL. + old_archive_From_new_cmds_F77='true' + # FIXME: Should let the user specify the lib program. + old_archive_cmds_F77='lib /OUT:$oldlib$oldobjs$old_deplibs' + fix_srcfile_path_F77='`cygpath -w "$srcfile"`' + enable_shared_with_static_runtimes_F77=yes + ;; + + darwin* | rhapsody*) + case $host_os in + rhapsody* | darwin1.[012]) + allow_undefined_flag_F77='${wl}-undefined ${wl}suppress' + ;; + *) # Darwin 1.3 on + if test -z ${MACOSX_DEPLOYMENT_TARGET} ; then + allow_undefined_flag_F77='${wl}-flat_namespace ${wl}-undefined ${wl}suppress' + else + case ${MACOSX_DEPLOYMENT_TARGET} in + 10.[012]) + allow_undefined_flag_F77='${wl}-flat_namespace ${wl}-undefined ${wl}suppress' + ;; + 10.*) + allow_undefined_flag_F77='${wl}-undefined ${wl}dynamic_lookup' + ;; + esac + fi + ;; + esac + archive_cmds_need_lc_F77=no + hardcode_direct_F77=no + hardcode_automatic_F77=yes + hardcode_shlibpath_var_F77=unsupported + whole_archive_flag_spec_F77='' + link_all_deplibs_F77=yes + if test "$GCC" = yes ; then + output_verbose_link_cmd='echo' + archive_cmds_F77='$CC -dynamiclib $allow_undefined_flag -o $lib $libobjs $deplibs $compiler_flags -install_name $rpath/$soname $verstring' + module_cmds_F77='$CC $allow_undefined_flag -o $lib -bundle $libobjs $deplibs$compiler_flags' + # Don't fix this by using the ld -exported_symbols_list flag, it doesn't exist in older darwin lds + archive_expsym_cmds_F77='sed -e "s,#.*,," -e "s,^[ ]*,," -e "s,^\(..*\),_&," < $export_symbols > $output_objdir/${libname}-symbols.expsym~$CC -dynamiclib $allow_undefined_flag -o $lib $libobjs $deplibs $compiler_flags -install_name $rpath/$soname $verstring~nmedit -s $output_objdir/${libname}-symbols.expsym ${lib}' + module_expsym_cmds_F77='sed -e "s,#.*,," -e "s,^[ ]*,," -e "s,^\(..*\),_&," < $export_symbols > $output_objdir/${libname}-symbols.expsym~$CC $allow_undefined_flag -o $lib -bundle $libobjs $deplibs$compiler_flags~nmedit -s $output_objdir/${libname}-symbols.expsym ${lib}' + else + case $cc_basename in + xlc*) + output_verbose_link_cmd='echo' + archive_cmds_F77='$CC -qmkshrobj $allow_undefined_flag -o $lib $libobjs $deplibs $compiler_flags ${wl}-install_name ${wl}`echo $rpath/$soname` $verstring' + module_cmds_F77='$CC $allow_undefined_flag -o $lib -bundle $libobjs $deplibs$compiler_flags' + # Don't fix this by using the ld -exported_symbols_list flag, it doesn't exist in older darwin lds + archive_expsym_cmds_F77='sed -e "s,#.*,," -e "s,^[ ]*,," -e "s,^\(..*\),_&," < $export_symbols > $output_objdir/${libname}-symbols.expsym~$CC -qmkshrobj $allow_undefined_flag -o $lib $libobjs $deplibs $compiler_flags ${wl}-install_name ${wl}$rpath/$soname $verstring~nmedit -s $output_objdir/${libname}-symbols.expsym ${lib}' + module_expsym_cmds_F77='sed -e "s,#.*,," -e "s,^[ ]*,," -e "s,^\(..*\),_&," < $export_symbols > $output_objdir/${libname}-symbols.expsym~$CC $allow_undefined_flag -o $lib -bundle $libobjs $deplibs$compiler_flags~nmedit -s $output_objdir/${libname}-symbols.expsym ${lib}' + ;; + *) + ld_shlibs_F77=no + ;; + esac + fi + ;; + + dgux*) + archive_cmds_F77='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_libdir_flag_spec_F77='-L$libdir' + hardcode_shlibpath_var_F77=no + ;; + + freebsd1*) + ld_shlibs_F77=no + ;; + + # FreeBSD 2.2.[012] allows us to include c++rt0.o to get C++ constructor + # support. Future versions do this automatically, but an explicit c++rt0.o + # does not break anything, and helps significantly (at the cost of a little + # extra space). + freebsd2.2*) + archive_cmds_F77='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags /usr/lib/c++rt0.o' + hardcode_libdir_flag_spec_F77='-R$libdir' + hardcode_direct_F77=yes + hardcode_shlibpath_var_F77=no + ;; + + # Unfortunately, older versions of FreeBSD 2 do not have this feature. + freebsd2*) + archive_cmds_F77='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags' + hardcode_direct_F77=yes + hardcode_minus_L_F77=yes + hardcode_shlibpath_var_F77=no + ;; + + # FreeBSD 3 and greater uses gcc -shared to do shared libraries. + freebsd* | kfreebsd*-gnu | dragonfly*) + archive_cmds_F77='$CC -shared -o $lib $libobjs $deplibs $compiler_flags' + hardcode_libdir_flag_spec_F77='-R$libdir' + hardcode_direct_F77=yes + hardcode_shlibpath_var_F77=no + ;; + + hpux9*) + if test "$GCC" = yes; then + archive_cmds_F77='$rm $output_objdir/$soname~$CC -shared -fPIC ${wl}+b ${wl}$install_libdir -o $output_objdir/$soname $libobjs $deplibs $compiler_flags~test $output_objdir/$soname = $lib || mv $output_objdir/$soname $lib' + else + archive_cmds_F77='$rm $output_objdir/$soname~$LD -b +b $install_libdir -o $output_objdir/$soname $libobjs $deplibs $linker_flags~test $output_objdir/$soname = $lib || mv $output_objdir/$soname $lib' + fi + hardcode_libdir_flag_spec_F77='${wl}+b ${wl}$libdir' + hardcode_libdir_separator_F77=: + hardcode_direct_F77=yes + + # hardcode_minus_L: Not really in the search PATH, + # but as the default location of the library. + hardcode_minus_L_F77=yes + export_dynamic_flag_spec_F77='${wl}-E' + ;; + + hpux10*) + if test "$GCC" = yes -a "$with_gnu_ld" = no; then + archive_cmds_F77='$CC -shared -fPIC ${wl}+h ${wl}$soname ${wl}+b ${wl}$install_libdir -o $lib $libobjs $deplibs $compiler_flags' + else + archive_cmds_F77='$LD -b +h $soname +b $install_libdir -o $lib $libobjs $deplibs $linker_flags' + fi + if test "$with_gnu_ld" = no; then + hardcode_libdir_flag_spec_F77='${wl}+b ${wl}$libdir' + hardcode_libdir_separator_F77=: + + hardcode_direct_F77=yes + export_dynamic_flag_spec_F77='${wl}-E' + + # hardcode_minus_L: Not really in the search PATH, + # but as the default location of the library. + hardcode_minus_L_F77=yes + fi + ;; + + hpux11*) + if test "$GCC" = yes -a "$with_gnu_ld" = no; then + case $host_cpu in + hppa*64*) + archive_cmds_F77='$CC -shared ${wl}+h ${wl}$soname -o $lib $libobjs $deplibs $compiler_flags' + ;; + ia64*) + archive_cmds_F77='$CC -shared ${wl}+h ${wl}$soname ${wl}+nodefaultrpath -o $lib $libobjs $deplibs $compiler_flags' + ;; + *) + archive_cmds_F77='$CC -shared -fPIC ${wl}+h ${wl}$soname ${wl}+b ${wl}$install_libdir -o $lib $libobjs $deplibs $compiler_flags' + ;; + esac + else + case $host_cpu in + hppa*64*) + archive_cmds_F77='$CC -b ${wl}+h ${wl}$soname -o $lib $libobjs $deplibs $compiler_flags' + ;; + ia64*) + archive_cmds_F77='$CC -b ${wl}+h ${wl}$soname ${wl}+nodefaultrpath -o $lib $libobjs $deplibs $compiler_flags' + ;; + *) + archive_cmds_F77='$CC -b ${wl}+h ${wl}$soname ${wl}+b ${wl}$install_libdir -o $lib $libobjs $deplibs $compiler_flags' + ;; + esac + fi + if test "$with_gnu_ld" = no; then + hardcode_libdir_flag_spec_F77='${wl}+b ${wl}$libdir' + hardcode_libdir_separator_F77=: + + case $host_cpu in + hppa*64*|ia64*) + hardcode_libdir_flag_spec_ld_F77='+b $libdir' + hardcode_direct_F77=no + hardcode_shlibpath_var_F77=no + ;; + *) + hardcode_direct_F77=yes + export_dynamic_flag_spec_F77='${wl}-E' + + # hardcode_minus_L: Not really in the search PATH, + # but as the default location of the library. + hardcode_minus_L_F77=yes + ;; + esac + fi + ;; + + irix5* | irix6* | nonstopux*) + if test "$GCC" = yes; then + archive_cmds_F77='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname ${wl}$soname `test -n "$verstring" && echo ${wl}-set_version ${wl}$verstring` ${wl}-update_registry ${wl}${output_objdir}/so_locations -o $lib' + else + archive_cmds_F77='$LD -shared $libobjs $deplibs $linker_flags -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${output_objdir}/so_locations -o $lib' + hardcode_libdir_flag_spec_ld_F77='-rpath $libdir' + fi + hardcode_libdir_flag_spec_F77='${wl}-rpath ${wl}$libdir' + hardcode_libdir_separator_F77=: + link_all_deplibs_F77=yes + ;; + + netbsd*) + if echo __ELF__ | $CC -E - | grep __ELF__ >/dev/null; then + archive_cmds_F77='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags' # a.out + else + archive_cmds_F77='$LD -shared -o $lib $libobjs $deplibs $linker_flags' # ELF + fi + hardcode_libdir_flag_spec_F77='-R$libdir' + hardcode_direct_F77=yes + hardcode_shlibpath_var_F77=no + ;; + + newsos6) + archive_cmds_F77='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_direct_F77=yes + hardcode_libdir_flag_spec_F77='${wl}-rpath ${wl}$libdir' + hardcode_libdir_separator_F77=: + hardcode_shlibpath_var_F77=no + ;; + + openbsd*) + hardcode_direct_F77=yes + hardcode_shlibpath_var_F77=no + if test -z "`echo __ELF__ | $CC -E - | grep __ELF__`" || test "$host_os-$host_cpu" = "openbsd2.8-powerpc"; then + archive_cmds_F77='$CC -shared $pic_flag -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds_F77='$CC -shared $pic_flag -o $lib $libobjs $deplibs $compiler_flags ${wl}-retain-symbols-file,$export_symbols' + hardcode_libdir_flag_spec_F77='${wl}-rpath,$libdir' + export_dynamic_flag_spec_F77='${wl}-E' + else + case $host_os in + openbsd[01].* | openbsd2.[0-7] | openbsd2.[0-7].*) + archive_cmds_F77='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags' + hardcode_libdir_flag_spec_F77='-R$libdir' + ;; + *) + archive_cmds_F77='$CC -shared $pic_flag -o $lib $libobjs $deplibs $compiler_flags' + hardcode_libdir_flag_spec_F77='${wl}-rpath,$libdir' + ;; + esac + fi + ;; + + os2*) + hardcode_libdir_flag_spec_F77='-L$libdir' + hardcode_minus_L_F77=yes + allow_undefined_flag_F77=unsupported + archive_cmds_F77='$echo "LIBRARY $libname INITINSTANCE" > $output_objdir/$libname.def~$echo "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~$echo DATA >> $output_objdir/$libname.def~$echo " SINGLE NONSHARED" >> $output_objdir/$libname.def~$echo EXPORTS >> $output_objdir/$libname.def~emxexp $libobjs >> $output_objdir/$libname.def~$CC -Zdll -Zcrtdll -o $lib $libobjs $deplibs $compiler_flags $output_objdir/$libname.def' + old_archive_From_new_cmds_F77='emximp -o $output_objdir/$libname.a $output_objdir/$libname.def' + ;; + + osf3*) + if test "$GCC" = yes; then + allow_undefined_flag_F77=' ${wl}-expect_unresolved ${wl}\*' + archive_cmds_F77='$CC -shared${allow_undefined_flag} $libobjs $deplibs $compiler_flags ${wl}-soname ${wl}$soname `test -n "$verstring" && echo ${wl}-set_version ${wl}$verstring` ${wl}-update_registry ${wl}${output_objdir}/so_locations -o $lib' + else + allow_undefined_flag_F77=' -expect_unresolved \*' + archive_cmds_F77='$LD -shared${allow_undefined_flag} $libobjs $deplibs $linker_flags -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${output_objdir}/so_locations -o $lib' + fi + hardcode_libdir_flag_spec_F77='${wl}-rpath ${wl}$libdir' + hardcode_libdir_separator_F77=: + ;; + + osf4* | osf5*) # as osf3* with the addition of -msym flag + if test "$GCC" = yes; then + allow_undefined_flag_F77=' ${wl}-expect_unresolved ${wl}\*' + archive_cmds_F77='$CC -shared${allow_undefined_flag} $libobjs $deplibs $compiler_flags ${wl}-msym ${wl}-soname ${wl}$soname `test -n "$verstring" && echo ${wl}-set_version ${wl}$verstring` ${wl}-update_registry ${wl}${output_objdir}/so_locations -o $lib' + hardcode_libdir_flag_spec_F77='${wl}-rpath ${wl}$libdir' + else + allow_undefined_flag_F77=' -expect_unresolved \*' + archive_cmds_F77='$LD -shared${allow_undefined_flag} $libobjs $deplibs $linker_flags -msym -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${output_objdir}/so_locations -o $lib' + archive_expsym_cmds_F77='for i in `cat $export_symbols`; do printf "%s %s\\n" -exported_symbol "\$i" >> $lib.exp; done; echo "-hidden">> $lib.exp~ + $LD -shared${allow_undefined_flag} -input $lib.exp $linker_flags $libobjs $deplibs -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${output_objdir}/so_locations -o $lib~$rm $lib.exp' + + # Both c and cxx compiler support -rpath directly + hardcode_libdir_flag_spec_F77='-rpath $libdir' + fi + hardcode_libdir_separator_F77=: + ;; + + solaris*) + no_undefined_flag_F77=' -z text' + if test "$GCC" = yes; then + wlarc='${wl}' + archive_cmds_F77='$CC -shared ${wl}-h ${wl}$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds_F77='$echo "{ global:" > $lib.exp~cat $export_symbols | $SED -e "s/\(.*\)/\1;/" >> $lib.exp~$echo "local: *; };" >> $lib.exp~ + $CC -shared ${wl}-M ${wl}$lib.exp ${wl}-h ${wl}$soname -o $lib $libobjs $deplibs $compiler_flags~$rm $lib.exp' + else + wlarc='' + archive_cmds_F77='$LD -G${allow_undefined_flag} -h $soname -o $lib $libobjs $deplibs $linker_flags' + archive_expsym_cmds_F77='$echo "{ global:" > $lib.exp~cat $export_symbols | $SED -e "s/\(.*\)/\1;/" >> $lib.exp~$echo "local: *; };" >> $lib.exp~ + $LD -G${allow_undefined_flag} -M $lib.exp -h $soname -o $lib $libobjs $deplibs $linker_flags~$rm $lib.exp' + fi + hardcode_libdir_flag_spec_F77='-R$libdir' + hardcode_shlibpath_var_F77=no + case $host_os in + solaris2.[0-5] | solaris2.[0-5].*) ;; + *) + # The compiler driver will combine linker options so we + # cannot just pass the convience library names through + # without $wl, iff we do not link with $LD. + # Luckily, gcc supports the same syntax we need for Sun Studio. + # Supported since Solaris 2.6 (maybe 2.5.1?) + case $wlarc in + '') + whole_archive_flag_spec_F77='-z allextract$convenience -z defaultextract' ;; + *) + whole_archive_flag_spec_F77='${wl}-z ${wl}allextract`for conv in $convenience\"\"; do test -n \"$conv\" && new_convenience=\"$new_convenience,$conv\"; done; $echo \"$new_convenience\"` ${wl}-z ${wl}defaultextract' ;; + esac ;; + esac + link_all_deplibs_F77=yes + ;; + + sunos4*) + if test "x$host_vendor" = xsequent; then + # Use $CC to link under sequent, because it throws in some extra .o + # files that make .init and .fini sections work. + archive_cmds_F77='$CC -G ${wl}-h $soname -o $lib $libobjs $deplibs $compiler_flags' + else + archive_cmds_F77='$LD -assert pure-text -Bstatic -o $lib $libobjs $deplibs $linker_flags' + fi + hardcode_libdir_flag_spec_F77='-L$libdir' + hardcode_direct_F77=yes + hardcode_minus_L_F77=yes + hardcode_shlibpath_var_F77=no + ;; + + sysv4) + case $host_vendor in + sni) + archive_cmds_F77='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_direct_F77=yes # is this really true??? + ;; + siemens) + ## LD is ld it makes a PLAMLIB + ## CC just makes a GrossModule. + archive_cmds_F77='$LD -G -o $lib $libobjs $deplibs $linker_flags' + reload_cmds_F77='$CC -r -o $output$reload_objs' + hardcode_direct_F77=no + ;; + motorola) + archive_cmds_F77='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_direct_F77=no #Motorola manual says yes, but my tests say they lie + ;; + esac + runpath_var='LD_RUN_PATH' + hardcode_shlibpath_var_F77=no + ;; + + sysv4.3*) + archive_cmds_F77='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_shlibpath_var_F77=no + export_dynamic_flag_spec_F77='-Bexport' + ;; + + sysv4*MP*) + if test -d /usr/nec; then + archive_cmds_F77='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_shlibpath_var_F77=no + runpath_var=LD_RUN_PATH + hardcode_runpath_var=yes + ld_shlibs_F77=yes + fi + ;; + + sysv4*uw2* | sysv5OpenUNIX* | sysv5UnixWare7.[01].[10]* | unixware7*) + no_undefined_flag_F77='${wl}-z,text' + archive_cmds_need_lc_F77=no + hardcode_shlibpath_var_F77=no + runpath_var='LD_RUN_PATH' + + if test "$GCC" = yes; then + archive_cmds_F77='$CC -shared ${wl}-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds_F77='$CC -shared ${wl}-Bexport:$export_symbols ${wl}-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + else + archive_cmds_F77='$CC -G ${wl}-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds_F77='$CC -G ${wl}-Bexport:$export_symbols ${wl}-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + fi + ;; + + sysv5* | sco3.2v5* | sco5v6*) + # Note: We can NOT use -z defs as we might desire, because we do not + # link with -lc, and that would cause any symbols used from libc to + # always be unresolved, which means just about no library would + # ever link correctly. If we're not using GNU ld we use -z text + # though, which does catch some bad symbols but isn't as heavy-handed + # as -z defs. + no_undefined_flag_F77='${wl}-z,text' + allow_undefined_flag_F77='${wl}-z,nodefs' + archive_cmds_need_lc_F77=no + hardcode_shlibpath_var_F77=no + hardcode_libdir_flag_spec_F77='`test -z "$SCOABSPATH" && echo ${wl}-R,$libdir`' + hardcode_libdir_separator_F77=':' + link_all_deplibs_F77=yes + export_dynamic_flag_spec_F77='${wl}-Bexport' + runpath_var='LD_RUN_PATH' + + if test "$GCC" = yes; then + archive_cmds_F77='$CC -shared ${wl}-h,\${SCOABSPATH:+${install_libdir}/}$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds_F77='$CC -shared ${wl}-Bexport:$export_symbols ${wl}-h,\${SCOABSPATH:+${install_libdir}/}$soname -o $lib $libobjs $deplibs $compiler_flags' + else + archive_cmds_F77='$CC -G ${wl}-h,\${SCOABSPATH:+${install_libdir}/}$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds_F77='$CC -G ${wl}-Bexport:$export_symbols ${wl}-h,\${SCOABSPATH:+${install_libdir}/}$soname -o $lib $libobjs $deplibs $compiler_flags' + fi + ;; + + uts4*) + archive_cmds_F77='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_libdir_flag_spec_F77='-L$libdir' + hardcode_shlibpath_var_F77=no + ;; + + *) + ld_shlibs_F77=no + ;; + esac + fi + +echo "$as_me:$LINENO: result: $ld_shlibs_F77" >&5 +echo "${ECHO_T}$ld_shlibs_F77" >&6 +test "$ld_shlibs_F77" = no && can_build_shared=no + +# +# Do we need to explicitly link libc? +# +case "x$archive_cmds_need_lc_F77" in +x|xyes) + # Assume -lc should be added + archive_cmds_need_lc_F77=yes + + if test "$enable_shared" = yes && test "$GCC" = yes; then + case $archive_cmds_F77 in + *'~'*) + # FIXME: we may have to deal with multi-command sequences. + ;; + '$CC '*) + # Test whether the compiler implicitly links with -lc since on some + # systems, -lgcc has to come before -lc. If gcc already passes -lc + # to ld, don't add -lc before -lgcc. + echo "$as_me:$LINENO: checking whether -lc should be explicitly linked in" >&5 +echo $ECHO_N "checking whether -lc should be explicitly linked in... $ECHO_C" >&6 + $rm conftest* + printf "$lt_simple_compile_test_code" > conftest.$ac_ext + + if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } 2>conftest.err; then + soname=conftest + lib=conftest + libobjs=conftest.$ac_objext + deplibs= + wl=$lt_prog_compiler_wl_F77 + pic_flag=$lt_prog_compiler_pic_F77 + compiler_flags=-v + linker_flags=-v + verstring= + output_objdir=. + libname=conftest + lt_save_allow_undefined_flag=$allow_undefined_flag_F77 + allow_undefined_flag_F77= + if { (eval echo "$as_me:$LINENO: \"$archive_cmds_F77 2\>\&1 \| grep \" -lc \" \>/dev/null 2\>\&1\"") >&5 + (eval $archive_cmds_F77 2\>\&1 \| grep \" -lc \" \>/dev/null 2\>\&1) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } + then + archive_cmds_need_lc_F77=no + else + archive_cmds_need_lc_F77=yes + fi + allow_undefined_flag_F77=$lt_save_allow_undefined_flag + else + cat conftest.err 1>&5 + fi + $rm conftest* + echo "$as_me:$LINENO: result: $archive_cmds_need_lc_F77" >&5 +echo "${ECHO_T}$archive_cmds_need_lc_F77" >&6 + ;; + esac + fi + ;; +esac + +echo "$as_me:$LINENO: checking dynamic linker characteristics" >&5 +echo $ECHO_N "checking dynamic linker characteristics... $ECHO_C" >&6 +library_names_spec= +libname_spec='lib$name' +soname_spec= +shrext_cmds=".so" +postinstall_cmds= +postuninstall_cmds= +finish_cmds= +finish_eval= +shlibpath_var= +shlibpath_overrides_runpath=unknown +version_type=none +dynamic_linker="$host_os ld.so" +sys_lib_dlsearch_path_spec="/lib /usr/lib" +if test "$GCC" = yes; then + sys_lib_search_path_spec=`$CC -print-search-dirs | grep "^libraries:" | $SED -e "s/^libraries://" -e "s,=/,/,g"` + if echo "$sys_lib_search_path_spec" | grep ';' >/dev/null ; then + # if the path contains ";" then we assume it to be the separator + # otherwise default to the standard path separator (i.e. ":") - it is + # assumed that no part of a normal pathname contains ";" but that should + # okay in the real world where ";" in dirpaths is itself problematic. + sys_lib_search_path_spec=`echo "$sys_lib_search_path_spec" | $SED -e 's/;/ /g'` + else + sys_lib_search_path_spec=`echo "$sys_lib_search_path_spec" | $SED -e "s/$PATH_SEPARATOR/ /g"` + fi +else + sys_lib_search_path_spec="/lib /usr/lib /usr/local/lib" +fi +need_lib_prefix=unknown +hardcode_into_libs=no + +# when you set need_version to no, make sure it does not cause -set_version +# flags to be left without arguments +need_version=unknown + +case $host_os in +aix3*) + version_type=linux + library_names_spec='${libname}${release}${shared_ext}$versuffix $libname.a' + shlibpath_var=LIBPATH + + # AIX 3 has no versioning support, so we append a major version to the name. + soname_spec='${libname}${release}${shared_ext}$major' + ;; + +aix4* | aix5*) + version_type=linux + need_lib_prefix=no + need_version=no + hardcode_into_libs=yes + if test "$host_cpu" = ia64; then + # AIX 5 supports IA64 + library_names_spec='${libname}${release}${shared_ext}$major ${libname}${release}${shared_ext}$versuffix $libname${shared_ext}' + shlibpath_var=LD_LIBRARY_PATH + else + # With GCC up to 2.95.x, collect2 would create an import file + # for dependence libraries. The import file would start with + # the line `#! .'. This would cause the generated library to + # depend on `.', always an invalid library. This was fixed in + # development snapshots of GCC prior to 3.0. + case $host_os in + aix4 | aix4.[01] | aix4.[01].*) + if { echo '#if __GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 97)' + echo ' yes ' + echo '#endif'; } | ${CC} -E - | grep yes > /dev/null; then + : + else + can_build_shared=no + fi + ;; + esac + # AIX (on Power*) has no versioning support, so currently we can not hardcode correct + # soname into executable. Probably we can add versioning support to + # collect2, so additional links can be useful in future. + if test "$aix_use_runtimelinking" = yes; then + # If using run time linking (on AIX 4.2 or later) use lib.so + # instead of lib.a to let people know that these are not + # typical AIX shared libraries. + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + else + # We preserve .a as extension for shared libraries through AIX4.2 + # and later when we are not doing run time linking. + library_names_spec='${libname}${release}.a $libname.a' + soname_spec='${libname}${release}${shared_ext}$major' + fi + shlibpath_var=LIBPATH + fi + ;; + +amigaos*) + library_names_spec='$libname.ixlibrary $libname.a' + # Create ${libname}_ixlibrary.a entries in /sys/libs. + finish_eval='for lib in `ls $libdir/*.ixlibrary 2>/dev/null`; do libname=`$echo "X$lib" | $Xsed -e '\''s%^.*/\([^/]*\)\.ixlibrary$%\1%'\''`; test $rm /sys/libs/${libname}_ixlibrary.a; $show "cd /sys/libs && $LN_S $lib ${libname}_ixlibrary.a"; cd /sys/libs && $LN_S $lib ${libname}_ixlibrary.a || exit 1; done' + ;; + +beos*) + library_names_spec='${libname}${shared_ext}' + dynamic_linker="$host_os ld.so" + shlibpath_var=LIBRARY_PATH + ;; + +bsdi[45]*) + version_type=linux + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + finish_cmds='PATH="\$PATH:/sbin" ldconfig $libdir' + shlibpath_var=LD_LIBRARY_PATH + sys_lib_search_path_spec="/shlib /usr/lib /usr/X11/lib /usr/contrib/lib /lib /usr/local/lib" + sys_lib_dlsearch_path_spec="/shlib /usr/lib /usr/local/lib" + # the default ld.so.conf also contains /usr/contrib/lib and + # /usr/X11R6/lib (/usr/X11 is a link to /usr/X11R6), but let us allow + # libtool to hard-code these into programs + ;; + +cygwin* | mingw* | pw32*) + version_type=windows + shrext_cmds=".dll" + need_version=no + need_lib_prefix=no + + case $GCC,$host_os in + yes,cygwin* | yes,mingw* | yes,pw32*) + library_names_spec='$libname.dll.a' + # DLL is installed to $(libdir)/../bin by postinstall_cmds + postinstall_cmds='base_file=`basename \${file}`~ + dlpath=`$SHELL 2>&1 -c '\''. $dir/'\''\${base_file}'\''i;echo \$dlname'\''`~ + dldir=$destdir/`dirname \$dlpath`~ + test -d \$dldir || mkdir -p \$dldir~ + $install_prog $dir/$dlname \$dldir/$dlname~ + chmod a+x \$dldir/$dlname' + postuninstall_cmds='dldll=`$SHELL 2>&1 -c '\''. $file; echo \$dlname'\''`~ + dlpath=$dir/\$dldll~ + $rm \$dlpath' + shlibpath_overrides_runpath=yes + + case $host_os in + cygwin*) + # Cygwin DLLs use 'cyg' prefix rather than 'lib' + soname_spec='`echo ${libname} | sed -e 's/^lib/cyg/'``echo ${release} | $SED -e 's/[.]/-/g'`${versuffix}${shared_ext}' + sys_lib_search_path_spec="/usr/lib /lib/w32api /lib /usr/local/lib" + ;; + mingw*) + # MinGW DLLs use traditional 'lib' prefix + soname_spec='${libname}`echo ${release} | $SED -e 's/[.]/-/g'`${versuffix}${shared_ext}' + sys_lib_search_path_spec=`$CC -print-search-dirs | grep "^libraries:" | $SED -e "s/^libraries://" -e "s,=/,/,g"` + if echo "$sys_lib_search_path_spec" | grep ';[c-zC-Z]:/' >/dev/null; then + # It is most probably a Windows format PATH printed by + # mingw gcc, but we are running on Cygwin. Gcc prints its search + # path with ; separators, and with drive letters. We can handle the + # drive letters (cygwin fileutils understands them), so leave them, + # especially as we might pass files found there to a mingw objdump, + # which wouldn't understand a cygwinified path. Ahh. + sys_lib_search_path_spec=`echo "$sys_lib_search_path_spec" | $SED -e 's/;/ /g'` + else + sys_lib_search_path_spec=`echo "$sys_lib_search_path_spec" | $SED -e "s/$PATH_SEPARATOR/ /g"` + fi + ;; + pw32*) + # pw32 DLLs use 'pw' prefix rather than 'lib' + library_names_spec='`echo ${libname} | sed -e 's/^lib/pw/'``echo ${release} | $SED -e 's/[.]/-/g'`${versuffix}${shared_ext}' + ;; + esac + ;; + + linux*) + if $LD --help 2>&1 | egrep ': supported targets:.* elf' > /dev/null; then + archive_cmds='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + supports_anon_versioning=no + case `$LD -v 2>/dev/null` in + *\ 01.* | *\ 2.[0-9].* | *\ 2.10.*) ;; # catch versions < 2.11 + *\ 2.11.93.0.2\ *) supports_anon_versioning=yes ;; # RH7.3 ... + *\ 2.11.92.0.12\ *) supports_anon_versioning=yes ;; # Mandrake 8.2 ... + *\ 2.11.*) ;; # other 2.11 versions + *) supports_anon_versioning=yes ;; + esac + if test $supports_anon_versioning = yes; then + archive_expsym_cmds='$echo "{ global:" > $output_objdir/$libname.ver~ +cat $export_symbols | sed -e "s/\(.*\)/\1;/" >> $output_objdir/$libname.ver~ +$echo "local: *; };" >> $output_objdir/$libname.ver~ + $CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-version-script ${wl}$output_objdir/$libname.ver -o $lib' + else + $archive_expsym_cmds="$archive_cmds" + fi + else + ld_shlibs=no + fi + ;; + + *) + library_names_spec='${libname}`echo ${release} | $SED -e 's/[.]/-/g'`${versuffix}${shared_ext} $libname.lib' + ;; + esac + dynamic_linker='Win32 ld.exe' + # FIXME: first we should search . and the directory the executable is in + shlibpath_var=PATH + ;; + +darwin* | rhapsody*) + dynamic_linker="$host_os dyld" + version_type=darwin + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${versuffix}$shared_ext ${libname}${release}${major}$shared_ext ${libname}$shared_ext' + soname_spec='${libname}${release}${major}$shared_ext' + shlibpath_overrides_runpath=yes + shlibpath_var=DYLD_LIBRARY_PATH + shrext_cmds='`test .$module = .yes && echo .so || echo .dylib`' + # Apple's gcc prints 'gcc -print-search-dirs' doesn't operate the same. + if test "$GCC" = yes; then + sys_lib_search_path_spec=`$CC -print-search-dirs | tr "\n" "$PATH_SEPARATOR" | sed -e 's/libraries:/@libraries:/' | tr "@" "\n" | grep "^libraries:" | sed -e "s/^libraries://" -e "s,=/,/,g" -e "s,$PATH_SEPARATOR, ,g" -e "s,.*,& /lib /usr/lib /usr/local/lib,g"` + else + sys_lib_search_path_spec='/lib /usr/lib /usr/local/lib' + fi + sys_lib_dlsearch_path_spec='/usr/local/lib /lib /usr/lib' + ;; + +dgux*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname$shared_ext' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + ;; + +freebsd1*) + dynamic_linker=no + ;; + +kfreebsd*-gnu) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + dynamic_linker='GNU ld.so' + ;; + +freebsd* | dragonfly*) + # DragonFly does not have aout. When/if they implement a new + # versioning mechanism, adjust this. + if test -x /usr/bin/objformat; then + objformat=`/usr/bin/objformat` + else + case $host_os in + freebsd[123]*) objformat=aout ;; + *) objformat=elf ;; + esac + fi + # Handle Gentoo/FreeBSD as it was Linux + case $host_vendor in + gentoo) + version_type=linux ;; + *) + version_type=freebsd-$objformat ;; + esac + + case $version_type in + freebsd-elf*) + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext} $libname${shared_ext}' + need_version=no + need_lib_prefix=no + ;; + freebsd-*) + library_names_spec='${libname}${release}${shared_ext}$versuffix $libname${shared_ext}$versuffix' + need_version=yes + ;; + linux) + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + need_lib_prefix=no + need_version=no + ;; + esac + shlibpath_var=LD_LIBRARY_PATH + case $host_os in + freebsd2*) + shlibpath_overrides_runpath=yes + ;; + freebsd3.[01]* | freebsdelf3.[01]*) + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + ;; + freebsd3.[2-9]* | freebsdelf3.[2-9]* | \ + freebsd4.[0-5] | freebsdelf4.[0-5] | freebsd4.1.1 | freebsdelf4.1.1) + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + ;; + freebsd*) # from 4.6 on + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + ;; + esac + ;; + +gnu*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}${major} ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + hardcode_into_libs=yes + ;; + +hpux9* | hpux10* | hpux11*) + # Give a soname corresponding to the major version so that dld.sl refuses to + # link against other versions. + version_type=sunos + need_lib_prefix=no + need_version=no + case $host_cpu in + ia64*) + shrext_cmds='.so' + hardcode_into_libs=yes + dynamic_linker="$host_os dld.so" + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes # Unless +noenvvar is specified. + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + if test "X$HPUX_IA64_MODE" = X32; then + sys_lib_search_path_spec="/usr/lib/hpux32 /usr/local/lib/hpux32 /usr/local/lib" + else + sys_lib_search_path_spec="/usr/lib/hpux64 /usr/local/lib/hpux64" + fi + sys_lib_dlsearch_path_spec=$sys_lib_search_path_spec + ;; + hppa*64*) + shrext_cmds='.sl' + hardcode_into_libs=yes + dynamic_linker="$host_os dld.sl" + shlibpath_var=LD_LIBRARY_PATH # How should we handle SHLIB_PATH + shlibpath_overrides_runpath=yes # Unless +noenvvar is specified. + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + sys_lib_search_path_spec="/usr/lib/pa20_64 /usr/ccs/lib/pa20_64" + sys_lib_dlsearch_path_spec=$sys_lib_search_path_spec + ;; + *) + shrext_cmds='.sl' + dynamic_linker="$host_os dld.sl" + shlibpath_var=SHLIB_PATH + shlibpath_overrides_runpath=no # +s is required to enable SHLIB_PATH + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + ;; + esac + # HP-UX runs *really* slowly unless shared libraries are mode 555. + postinstall_cmds='chmod 555 $lib' + ;; + +interix3*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + dynamic_linker='Interix 3.x ld.so.1 (PE, like ELF)' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + ;; + +irix5* | irix6* | nonstopux*) + case $host_os in + nonstopux*) version_type=nonstopux ;; + *) + if test "$lt_cv_prog_gnu_ld" = yes; then + version_type=linux + else + version_type=irix + fi ;; + esac + need_lib_prefix=no + need_version=no + soname_spec='${libname}${release}${shared_ext}$major' + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${release}${shared_ext} $libname${shared_ext}' + case $host_os in + irix5* | nonstopux*) + libsuff= shlibsuff= + ;; + *) + case $LD in # libtool.m4 will add one of these switches to LD + *-32|*"-32 "|*-melf32bsmip|*"-melf32bsmip ") + libsuff= shlibsuff= libmagic=32-bit;; + *-n32|*"-n32 "|*-melf32bmipn32|*"-melf32bmipn32 ") + libsuff=32 shlibsuff=N32 libmagic=N32;; + *-64|*"-64 "|*-melf64bmip|*"-melf64bmip ") + libsuff=64 shlibsuff=64 libmagic=64-bit;; + *) libsuff= shlibsuff= libmagic=never-match;; + esac + ;; + esac + shlibpath_var=LD_LIBRARY${shlibsuff}_PATH + shlibpath_overrides_runpath=no + sys_lib_search_path_spec="/usr/lib${libsuff} /lib${libsuff} /usr/local/lib${libsuff}" + sys_lib_dlsearch_path_spec="/usr/lib${libsuff} /lib${libsuff}" + hardcode_into_libs=yes + ;; + +# No shared lib support for Linux oldld, aout, or coff. +linux*oldld* | linux*aout* | linux*coff*) + dynamic_linker=no + ;; + +# This must be Linux ELF. +linux*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + finish_cmds='PATH="\$PATH:/sbin" ldconfig -n $libdir' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + # This implies no fast_install, which is unacceptable. + # Some rework will be needed to allow for fast_install + # before this can be enabled. + hardcode_into_libs=yes + + # Append ld.so.conf contents to the search path + if test -f /etc/ld.so.conf; then + lt_ld_extra=`awk '/^include / { system(sprintf("cd /etc; cat %s", \$2)); skip = 1; } { if (!skip) print \$0; skip = 0; }' < /etc/ld.so.conf | $SED -e 's/#.*//;s/[:, ]/ /g;s/=[^=]*$//;s/=[^= ]* / /g;/^$/d' | tr '\n' ' '` + sys_lib_dlsearch_path_spec="/lib /usr/lib $lt_ld_extra" + fi + + # We used to test for /lib/ld.so.1 and disable shared libraries on + # powerpc, because MkLinux only supported shared libraries with the + # GNU dynamic linker. Since this was broken with cross compilers, + # most powerpc-linux boxes support dynamic linking these days and + # people can always --disable-shared, the test was removed, and we + # assume the GNU/Linux dynamic linker is in use. + dynamic_linker='GNU/Linux ld.so' + ;; + +knetbsd*-gnu) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + dynamic_linker='GNU ld.so' + ;; + +netbsd*) + version_type=sunos + need_lib_prefix=no + need_version=no + if echo __ELF__ | $CC -E - | grep __ELF__ >/dev/null; then + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${shared_ext}$versuffix' + finish_cmds='PATH="\$PATH:/sbin" ldconfig -m $libdir' + dynamic_linker='NetBSD (a.out) ld.so' + else + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + dynamic_linker='NetBSD ld.elf_so' + fi + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + ;; + +newsos6) + version_type=linux + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + ;; + +nto-qnx*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + ;; + +openbsd*) + version_type=sunos + sys_lib_dlsearch_path_spec="/usr/lib" + need_lib_prefix=no + # Some older versions of OpenBSD (3.3 at least) *do* need versioned libs. + case $host_os in + openbsd3.3 | openbsd3.3.*) need_version=yes ;; + *) need_version=no ;; + esac + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${shared_ext}$versuffix' + finish_cmds='PATH="\$PATH:/sbin" ldconfig -m $libdir' + shlibpath_var=LD_LIBRARY_PATH + if test -z "`echo __ELF__ | $CC -E - | grep __ELF__`" || test "$host_os-$host_cpu" = "openbsd2.8-powerpc"; then + case $host_os in + openbsd2.[89] | openbsd2.[89].*) + shlibpath_overrides_runpath=no + ;; + *) + shlibpath_overrides_runpath=yes + ;; + esac + else + shlibpath_overrides_runpath=yes + fi + ;; + +os2*) + libname_spec='$name' + shrext_cmds=".dll" + need_lib_prefix=no + library_names_spec='$libname${shared_ext} $libname.a' + dynamic_linker='OS/2 ld.exe' + shlibpath_var=LIBPATH + ;; + +osf3* | osf4* | osf5*) + version_type=osf + need_lib_prefix=no + need_version=no + soname_spec='${libname}${release}${shared_ext}$major' + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + shlibpath_var=LD_LIBRARY_PATH + sys_lib_search_path_spec="/usr/shlib /usr/ccs/lib /usr/lib/cmplrs/cc /usr/lib /usr/local/lib /var/shlib" + sys_lib_dlsearch_path_spec="$sys_lib_search_path_spec" + ;; + +solaris*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + # ldd complains unless libraries are executable + postinstall_cmds='chmod +x $lib' + ;; + +sunos4*) + version_type=sunos + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${shared_ext}$versuffix' + finish_cmds='PATH="\$PATH:/usr/etc" ldconfig $libdir' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + if test "$with_gnu_ld" = yes; then + need_lib_prefix=no + fi + need_version=yes + ;; + +sysv4 | sysv4.3*) + version_type=linux + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + case $host_vendor in + sni) + shlibpath_overrides_runpath=no + need_lib_prefix=no + export_dynamic_flag_spec='${wl}-Blargedynsym' + runpath_var=LD_RUN_PATH + ;; + siemens) + need_lib_prefix=no + ;; + motorola) + need_lib_prefix=no + need_version=no + shlibpath_overrides_runpath=no + sys_lib_search_path_spec='/lib /usr/lib /usr/ccs/lib' + ;; + esac + ;; + +sysv4*MP*) + if test -d /usr/nec ;then + version_type=linux + library_names_spec='$libname${shared_ext}.$versuffix $libname${shared_ext}.$major $libname${shared_ext}' + soname_spec='$libname${shared_ext}.$major' + shlibpath_var=LD_LIBRARY_PATH + fi + ;; + +sysv5* | sco3.2v5* | sco5v6* | unixware* | OpenUNIX* | sysv4*uw2*) + version_type=freebsd-elf + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext} $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + hardcode_into_libs=yes + if test "$with_gnu_ld" = yes; then + sys_lib_search_path_spec='/usr/local/lib /usr/gnu/lib /usr/ccs/lib /usr/lib /lib' + shlibpath_overrides_runpath=no + else + sys_lib_search_path_spec='/usr/ccs/lib /usr/lib' + shlibpath_overrides_runpath=yes + case $host_os in + sco3.2v5*) + sys_lib_search_path_spec="$sys_lib_search_path_spec /lib" + ;; + esac + fi + sys_lib_dlsearch_path_spec='/usr/lib' + ;; + +uts4*) + version_type=linux + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + ;; + +*) + dynamic_linker=no + ;; +esac +echo "$as_me:$LINENO: result: $dynamic_linker" >&5 +echo "${ECHO_T}$dynamic_linker" >&6 +test "$dynamic_linker" = no && can_build_shared=no + +variables_saved_for_relink="PATH $shlibpath_var $runpath_var" +if test "$GCC" = yes; then + variables_saved_for_relink="$variables_saved_for_relink GCC_EXEC_PREFIX COMPILER_PATH LIBRARY_PATH" +fi + +echo "$as_me:$LINENO: checking how to hardcode library paths into programs" >&5 +echo $ECHO_N "checking how to hardcode library paths into programs... $ECHO_C" >&6 +hardcode_action_F77= +if test -n "$hardcode_libdir_flag_spec_F77" || \ + test -n "$runpath_var_F77" || \ + test "X$hardcode_automatic_F77" = "Xyes" ; then + + # We can hardcode non-existant directories. + if test "$hardcode_direct_F77" != no && + # If the only mechanism to avoid hardcoding is shlibpath_var, we + # have to relink, otherwise we might link with an installed library + # when we should be linking with a yet-to-be-installed one + ## test "$_LT_AC_TAGVAR(hardcode_shlibpath_var, F77)" != no && + test "$hardcode_minus_L_F77" != no; then + # Linking always hardcodes the temporary library directory. + hardcode_action_F77=relink + else + # We can link without hardcoding, and we can hardcode nonexisting dirs. + hardcode_action_F77=immediate + fi +else + # We cannot hardcode anything, or else we can only hardcode existing + # directories. + hardcode_action_F77=unsupported +fi +echo "$as_me:$LINENO: result: $hardcode_action_F77" >&5 +echo "${ECHO_T}$hardcode_action_F77" >&6 + +if test "$hardcode_action_F77" = relink; then + # Fast installation is not supported + enable_fast_install=no +elif test "$shlibpath_overrides_runpath" = yes || + test "$enable_shared" = no; then + # Fast installation is not necessary + enable_fast_install=needless +fi + + +# The else clause should only fire when bootstrapping the +# libtool distribution, otherwise you forgot to ship ltmain.sh +# with your package, and you will get complaints that there are +# no rules to generate ltmain.sh. +if test -f "$ltmain"; then + # See if we are running on zsh, and set the options which allow our commands through + # without removal of \ escapes. + if test -n "${ZSH_VERSION+set}" ; then + setopt NO_GLOB_SUBST + fi + # Now quote all the things that may contain metacharacters while being + # careful not to overquote the AC_SUBSTed values. We take copies of the + # variables and quote the copies for generation of the libtool script. + for var in echo old_CC old_CFLAGS AR AR_FLAGS EGREP RANLIB LN_S LTCC LTCFLAGS NM \ + SED SHELL STRIP \ + libname_spec library_names_spec soname_spec extract_expsyms_cmds \ + old_striplib striplib file_magic_cmd finish_cmds finish_eval \ + deplibs_check_method reload_flag reload_cmds need_locks \ + lt_cv_sys_global_symbol_pipe lt_cv_sys_global_symbol_to_cdecl \ + lt_cv_sys_global_symbol_to_c_name_address \ + sys_lib_search_path_spec sys_lib_dlsearch_path_spec \ + old_postinstall_cmds old_postuninstall_cmds \ + compiler_F77 \ + CC_F77 \ + LD_F77 \ + lt_prog_compiler_wl_F77 \ + lt_prog_compiler_pic_F77 \ + lt_prog_compiler_static_F77 \ + lt_prog_compiler_no_builtin_flag_F77 \ + export_dynamic_flag_spec_F77 \ + thread_safe_flag_spec_F77 \ + whole_archive_flag_spec_F77 \ + enable_shared_with_static_runtimes_F77 \ + old_archive_cmds_F77 \ + old_archive_from_new_cmds_F77 \ + predep_objects_F77 \ + postdep_objects_F77 \ + predeps_F77 \ + postdeps_F77 \ + compiler_lib_search_path_F77 \ + archive_cmds_F77 \ + archive_expsym_cmds_F77 \ + postinstall_cmds_F77 \ + postuninstall_cmds_F77 \ + old_archive_from_expsyms_cmds_F77 \ + allow_undefined_flag_F77 \ + no_undefined_flag_F77 \ + export_symbols_cmds_F77 \ + hardcode_libdir_flag_spec_F77 \ + hardcode_libdir_flag_spec_ld_F77 \ + hardcode_libdir_separator_F77 \ + hardcode_automatic_F77 \ + module_cmds_F77 \ + module_expsym_cmds_F77 \ + lt_cv_prog_compiler_c_o_F77 \ + exclude_expsyms_F77 \ + include_expsyms_F77; do + + case $var in + old_archive_cmds_F77 | \ + old_archive_from_new_cmds_F77 | \ + archive_cmds_F77 | \ + archive_expsym_cmds_F77 | \ + module_cmds_F77 | \ + module_expsym_cmds_F77 | \ + old_archive_from_expsyms_cmds_F77 | \ + export_symbols_cmds_F77 | \ + extract_expsyms_cmds | reload_cmds | finish_cmds | \ + postinstall_cmds | postuninstall_cmds | \ + old_postinstall_cmds | old_postuninstall_cmds | \ + sys_lib_search_path_spec | sys_lib_dlsearch_path_spec) + # Double-quote double-evaled strings. + eval "lt_$var=\\\"\`\$echo \"X\$$var\" | \$Xsed -e \"\$double_quote_subst\" -e \"\$sed_quote_subst\" -e \"\$delay_variable_subst\"\`\\\"" + ;; + *) + eval "lt_$var=\\\"\`\$echo \"X\$$var\" | \$Xsed -e \"\$sed_quote_subst\"\`\\\"" + ;; + esac + done + + case $lt_echo in + *'\$0 --fallback-echo"') + lt_echo=`$echo "X$lt_echo" | $Xsed -e 's/\\\\\\\$0 --fallback-echo"$/$0 --fallback-echo"/'` + ;; + esac + +cfgfile="$ofile" + + cat <<__EOF__ >> "$cfgfile" +# ### BEGIN LIBTOOL TAG CONFIG: $tagname + +# Libtool was configured on host `(hostname || uname -n) 2>/dev/null | sed 1q`: + +# Shell to use when invoking shell scripts. +SHELL=$lt_SHELL + +# Whether or not to build shared libraries. +build_libtool_libs=$enable_shared + +# Whether or not to build static libraries. +build_old_libs=$enable_static + +# Whether or not to add -lc for building shared libraries. +build_libtool_need_lc=$archive_cmds_need_lc_F77 + +# Whether or not to disallow shared libs when runtime libs are static +allow_libtool_libs_with_static_runtimes=$enable_shared_with_static_runtimes_F77 + +# Whether or not to optimize for fast installation. +fast_install=$enable_fast_install + +# The host system. +host_alias=$host_alias +host=$host +host_os=$host_os + +# The build system. +build_alias=$build_alias +build=$build +build_os=$build_os + +# An echo program that does not interpret backslashes. +echo=$lt_echo + +# The archiver. +AR=$lt_AR +AR_FLAGS=$lt_AR_FLAGS + +# A C compiler. +LTCC=$lt_LTCC + +# LTCC compiler flags. +LTCFLAGS=$lt_LTCFLAGS + +# A language-specific compiler. +CC=$lt_compiler_F77 + +# Is the compiler the GNU C compiler? +with_gcc=$GCC_F77 + +# An ERE matcher. +EGREP=$lt_EGREP + +# The linker used to build libraries. +LD=$lt_LD_F77 + +# Whether we need hard or soft links. +LN_S=$lt_LN_S + +# A BSD-compatible nm program. +NM=$lt_NM + +# A symbol stripping program +STRIP=$lt_STRIP + +# Used to examine libraries when file_magic_cmd begins "file" +MAGIC_CMD=$MAGIC_CMD + +# Used on cygwin: DLL creation program. +DLLTOOL="$DLLTOOL" + +# Used on cygwin: object dumper. +OBJDUMP="$OBJDUMP" + +# Used on cygwin: assembler. +AS="$AS" + +# The name of the directory that contains temporary libtool files. +objdir=$objdir + +# How to create reloadable object files. +reload_flag=$lt_reload_flag +reload_cmds=$lt_reload_cmds + +# How to pass a linker flag through the compiler. +wl=$lt_lt_prog_compiler_wl_F77 + +# Object file suffix (normally "o"). +objext="$ac_objext" + +# Old archive suffix (normally "a"). +libext="$libext" + +# Shared library suffix (normally ".so"). +shrext_cmds='$shrext_cmds' + +# Executable file suffix (normally ""). +exeext="$exeext" + +# Additional compiler flags for building library objects. +pic_flag=$lt_lt_prog_compiler_pic_F77 +pic_mode=$pic_mode + +# What is the maximum length of a command? +max_cmd_len=$lt_cv_sys_max_cmd_len + +# Does compiler simultaneously support -c and -o options? +compiler_c_o=$lt_lt_cv_prog_compiler_c_o_F77 + +# Must we lock files when doing compilation? +need_locks=$lt_need_locks + +# Do we need the lib prefix for modules? +need_lib_prefix=$need_lib_prefix + +# Do we need a version for libraries? +need_version=$need_version + +# Whether dlopen is supported. +dlopen_support=$enable_dlopen + +# Whether dlopen of programs is supported. +dlopen_self=$enable_dlopen_self + +# Whether dlopen of statically linked programs is supported. +dlopen_self_static=$enable_dlopen_self_static + +# Compiler flag to prevent dynamic linking. +link_static_flag=$lt_lt_prog_compiler_static_F77 + +# Compiler flag to turn off builtin functions. +no_builtin_flag=$lt_lt_prog_compiler_no_builtin_flag_F77 + +# Compiler flag to allow reflexive dlopens. +export_dynamic_flag_spec=$lt_export_dynamic_flag_spec_F77 + +# Compiler flag to generate shared objects directly from archives. +whole_archive_flag_spec=$lt_whole_archive_flag_spec_F77 + +# Compiler flag to generate thread-safe objects. +thread_safe_flag_spec=$lt_thread_safe_flag_spec_F77 + +# Library versioning type. +version_type=$version_type + +# Format of library name prefix. +libname_spec=$lt_libname_spec + +# List of archive names. First name is the real one, the rest are links. +# The last name is the one that the linker finds with -lNAME. +library_names_spec=$lt_library_names_spec + +# The coded name of the library, if different from the real name. +soname_spec=$lt_soname_spec + +# Commands used to build and install an old-style archive. +RANLIB=$lt_RANLIB +old_archive_cmds=$lt_old_archive_cmds_F77 +old_postinstall_cmds=$lt_old_postinstall_cmds +old_postuninstall_cmds=$lt_old_postuninstall_cmds + +# Create an old-style archive from a shared archive. +old_archive_from_new_cmds=$lt_old_archive_from_new_cmds_F77 + +# Create a temporary old-style archive to link instead of a shared archive. +old_archive_from_expsyms_cmds=$lt_old_archive_from_expsyms_cmds_F77 + +# Commands used to build and install a shared archive. +archive_cmds=$lt_archive_cmds_F77 +archive_expsym_cmds=$lt_archive_expsym_cmds_F77 +postinstall_cmds=$lt_postinstall_cmds +postuninstall_cmds=$lt_postuninstall_cmds + +# Commands used to build a loadable module (assumed same as above if empty) +module_cmds=$lt_module_cmds_F77 +module_expsym_cmds=$lt_module_expsym_cmds_F77 + +# Commands to strip libraries. +old_striplib=$lt_old_striplib +striplib=$lt_striplib + +# Dependencies to place before the objects being linked to create a +# shared library. +predep_objects=$lt_predep_objects_F77 + +# Dependencies to place after the objects being linked to create a +# shared library. +postdep_objects=$lt_postdep_objects_F77 + +# Dependencies to place before the objects being linked to create a +# shared library. +predeps=$lt_predeps_F77 + +# Dependencies to place after the objects being linked to create a +# shared library. +postdeps=$lt_postdeps_F77 + +# The library search path used internally by the compiler when linking +# a shared library. +compiler_lib_search_path=$lt_compiler_lib_search_path_F77 + +# Method to check whether dependent libraries are shared objects. +deplibs_check_method=$lt_deplibs_check_method + +# Command to use when deplibs_check_method == file_magic. +file_magic_cmd=$lt_file_magic_cmd + +# Flag that allows shared libraries with undefined symbols to be built. +allow_undefined_flag=$lt_allow_undefined_flag_F77 + +# Flag that forces no undefined symbols. +no_undefined_flag=$lt_no_undefined_flag_F77 + +# Commands used to finish a libtool library installation in a directory. +finish_cmds=$lt_finish_cmds + +# Same as above, but a single script fragment to be evaled but not shown. +finish_eval=$lt_finish_eval + +# Take the output of nm and produce a listing of raw symbols and C names. +global_symbol_pipe=$lt_lt_cv_sys_global_symbol_pipe + +# Transform the output of nm in a proper C declaration +global_symbol_to_cdecl=$lt_lt_cv_sys_global_symbol_to_cdecl + +# Transform the output of nm in a C name address pair +global_symbol_to_c_name_address=$lt_lt_cv_sys_global_symbol_to_c_name_address + +# This is the shared library runtime path variable. +runpath_var=$runpath_var + +# This is the shared library path variable. +shlibpath_var=$shlibpath_var + +# Is shlibpath searched before the hard-coded library search path? +shlibpath_overrides_runpath=$shlibpath_overrides_runpath + +# How to hardcode a shared library path into an executable. +hardcode_action=$hardcode_action_F77 + +# Whether we should hardcode library paths into libraries. +hardcode_into_libs=$hardcode_into_libs + +# Flag to hardcode \$libdir into a binary during linking. +# This must work even if \$libdir does not exist. +hardcode_libdir_flag_spec=$lt_hardcode_libdir_flag_spec_F77 + +# If ld is used when linking, flag to hardcode \$libdir into +# a binary during linking. This must work even if \$libdir does +# not exist. +hardcode_libdir_flag_spec_ld=$lt_hardcode_libdir_flag_spec_ld_F77 + +# Whether we need a single -rpath flag with a separated argument. +hardcode_libdir_separator=$lt_hardcode_libdir_separator_F77 + +# Set to yes if using DIR/libNAME${shared_ext} during linking hardcodes DIR into the +# resulting binary. +hardcode_direct=$hardcode_direct_F77 + +# Set to yes if using the -LDIR flag during linking hardcodes DIR into the +# resulting binary. +hardcode_minus_L=$hardcode_minus_L_F77 + +# Set to yes if using SHLIBPATH_VAR=DIR during linking hardcodes DIR into +# the resulting binary. +hardcode_shlibpath_var=$hardcode_shlibpath_var_F77 + +# Set to yes if building a shared library automatically hardcodes DIR into the library +# and all subsequent libraries and executables linked against it. +hardcode_automatic=$hardcode_automatic_F77 + +# Variables whose values should be saved in libtool wrapper scripts and +# restored at relink time. +variables_saved_for_relink="$variables_saved_for_relink" + +# Whether libtool must link a program against all its dependency libraries. +link_all_deplibs=$link_all_deplibs_F77 + +# Compile-time system search path for libraries +sys_lib_search_path_spec=$lt_sys_lib_search_path_spec + +# Run-time system search path for libraries +sys_lib_dlsearch_path_spec=$lt_sys_lib_dlsearch_path_spec + +# Fix the shell variable \$srcfile for the compiler. +fix_srcfile_path="$fix_srcfile_path_F77" + +# Set to yes if exported symbols are required. +always_export_symbols=$always_export_symbols_F77 + +# The commands to list exported symbols. +export_symbols_cmds=$lt_export_symbols_cmds_F77 + +# The commands to extract the exported symbol list from a shared archive. +extract_expsyms_cmds=$lt_extract_expsyms_cmds + +# Symbols that should not be listed in the preloaded symbols. +exclude_expsyms=$lt_exclude_expsyms_F77 + +# Symbols that must always be exported. +include_expsyms=$lt_include_expsyms_F77 + +# ### END LIBTOOL TAG CONFIG: $tagname + +__EOF__ + + +else + # If there is no Makefile yet, we rely on a make rule to execute + # `config.status --recheck' to rerun these tests and create the + # libtool script then. + ltmain_in=`echo $ltmain | sed -e 's/\.sh$/.in/'` + if test -f "$ltmain_in"; then + test -f Makefile && make "$ltmain" + fi +fi + + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + +CC="$lt_save_CC" + + else + tagname="" + fi + ;; + + GCJ) + if test -n "$GCJ" && test "X$GCJ" != "Xno"; then + + + +# Source file extension for Java test sources. +ac_ext=java + +# Object file extension for compiled Java test sources. +objext=o +objext_GCJ=$objext + +# Code to be used in simple compile tests +lt_simple_compile_test_code="class foo {}\n" + +# Code to be used in simple link tests +lt_simple_link_test_code='public class conftest { public static void main(String[] argv) {}; }\n' + +# ltmain only uses $CC for tagged configurations so make sure $CC is set. + +# If no C compiler was specified, use CC. +LTCC=${LTCC-"$CC"} + +# If no C compiler flags were specified, use CFLAGS. +LTCFLAGS=${LTCFLAGS-"$CFLAGS"} + +# Allow CC to be a program name with arguments. +compiler=$CC + + +# save warnings/boilerplate of simple test code +ac_outfile=conftest.$ac_objext +printf "$lt_simple_compile_test_code" >conftest.$ac_ext +eval "$ac_compile" 2>&1 >/dev/null | $SED '/^$/d; /^ *+/d' >conftest.err +_lt_compiler_boilerplate=`cat conftest.err` +$rm conftest* + +ac_outfile=conftest.$ac_objext +printf "$lt_simple_link_test_code" >conftest.$ac_ext +eval "$ac_link" 2>&1 >/dev/null | $SED '/^$/d; /^ *+/d' >conftest.err +_lt_linker_boilerplate=`cat conftest.err` +$rm conftest* + + +# Allow CC to be a program name with arguments. +lt_save_CC="$CC" +CC=${GCJ-"gcj"} +compiler=$CC +compiler_GCJ=$CC +for cc_temp in $compiler""; do + case $cc_temp in + compile | *[\\/]compile | ccache | *[\\/]ccache ) ;; + distcc | *[\\/]distcc | purify | *[\\/]purify ) ;; + \-*) ;; + *) break;; + esac +done +cc_basename=`$echo "X$cc_temp" | $Xsed -e 's%.*/%%' -e "s%^$host_alias-%%"` + + +# GCJ did not exist at the time GCC didn't implicitly link libc in. +archive_cmds_need_lc_GCJ=no + +old_archive_cmds_GCJ=$old_archive_cmds + + +lt_prog_compiler_no_builtin_flag_GCJ= + +if test "$GCC" = yes; then + lt_prog_compiler_no_builtin_flag_GCJ=' -fno-builtin' + + +echo "$as_me:$LINENO: checking if $compiler supports -fno-rtti -fno-exceptions" >&5 +echo $ECHO_N "checking if $compiler supports -fno-rtti -fno-exceptions... $ECHO_C" >&6 +if test "${lt_cv_prog_compiler_rtti_exceptions+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + lt_cv_prog_compiler_rtti_exceptions=no + ac_outfile=conftest.$ac_objext + printf "$lt_simple_compile_test_code" > conftest.$ac_ext + lt_compiler_flag="-fno-rtti -fno-exceptions" + # Insert the option either (1) after the last *FLAGS variable, or + # (2) before a word containing "conftest.", or (3) at the end. + # Note that $ac_compile itself does not contain backslashes and begins + # with a dollar sign (not a hyphen), so the echo should work correctly. + # The option is referenced via a variable to avoid confusing sed. + lt_compile=`echo "$ac_compile" | $SED \ + -e 's:.*FLAGS}\{0,1\} :&$lt_compiler_flag :; t' \ + -e 's: [^ ]*conftest\.: $lt_compiler_flag&:; t' \ + -e 's:$: $lt_compiler_flag:'` + (eval echo "\"\$as_me:15300: $lt_compile\"" >&5) + (eval "$lt_compile" 2>conftest.err) + ac_status=$? + cat conftest.err >&5 + echo "$as_me:15304: \$? = $ac_status" >&5 + if (exit $ac_status) && test -s "$ac_outfile"; then + # The compiler can only warn and ignore the option if not recognized + # So say no if there are warnings other than the usual output. + $echo "X$_lt_compiler_boilerplate" | $Xsed -e '/^$/d' >conftest.exp + $SED '/^$/d; /^ *+/d' conftest.err >conftest.er2 + if test ! -s conftest.er2 || diff conftest.exp conftest.er2 >/dev/null; then + lt_cv_prog_compiler_rtti_exceptions=yes + fi + fi + $rm conftest* + +fi +echo "$as_me:$LINENO: result: $lt_cv_prog_compiler_rtti_exceptions" >&5 +echo "${ECHO_T}$lt_cv_prog_compiler_rtti_exceptions" >&6 + +if test x"$lt_cv_prog_compiler_rtti_exceptions" = xyes; then + lt_prog_compiler_no_builtin_flag_GCJ="$lt_prog_compiler_no_builtin_flag_GCJ -fno-rtti -fno-exceptions" +else + : +fi + +fi + +lt_prog_compiler_wl_GCJ= +lt_prog_compiler_pic_GCJ= +lt_prog_compiler_static_GCJ= + +echo "$as_me:$LINENO: checking for $compiler option to produce PIC" >&5 +echo $ECHO_N "checking for $compiler option to produce PIC... $ECHO_C" >&6 + + if test "$GCC" = yes; then + lt_prog_compiler_wl_GCJ='-Wl,' + lt_prog_compiler_static_GCJ='-static' + + case $host_os in + aix*) + # All AIX code is PIC. + if test "$host_cpu" = ia64; then + # AIX 5 now supports IA64 processor + lt_prog_compiler_static_GCJ='-Bstatic' + fi + ;; + + amigaos*) + # FIXME: we need at least 68020 code to build shared libraries, but + # adding the `-m68020' flag to GCC prevents building anything better, + # like `-m68040'. + lt_prog_compiler_pic_GCJ='-m68020 -resident32 -malways-restore-a4' + ;; + + beos* | cygwin* | irix5* | irix6* | nonstopux* | osf3* | osf4* | osf5*) + # PIC is the default for these OSes. + ;; + + mingw* | pw32* | os2*) + # This hack is so that the source file can tell whether it is being + # built for inclusion in a dll (and should export symbols for example). + lt_prog_compiler_pic_GCJ='-DDLL_EXPORT' + ;; + + darwin* | rhapsody*) + # PIC is the default on this platform + # Common symbols not allowed in MH_DYLIB files + lt_prog_compiler_pic_GCJ='-fno-common' + ;; + + interix3*) + # Interix 3.x gcc -fpic/-fPIC options generate broken code. + # Instead, we relocate shared libraries at runtime. + ;; + + msdosdjgpp*) + # Just because we use GCC doesn't mean we suddenly get shared libraries + # on systems that don't support them. + lt_prog_compiler_can_build_shared_GCJ=no + enable_shared=no + ;; + + sysv4*MP*) + if test -d /usr/nec; then + lt_prog_compiler_pic_GCJ=-Kconform_pic + fi + ;; + + hpux*) + # PIC is the default for IA64 HP-UX and 64-bit HP-UX, but + # not for PA HP-UX. + case $host_cpu in + hppa*64*|ia64*) + # +Z the default + ;; + *) + lt_prog_compiler_pic_GCJ='-fPIC' + ;; + esac + ;; + + *) + lt_prog_compiler_pic_GCJ='-fPIC' + ;; + esac + else + # PORTME Check for flag to pass linker flags through the system compiler. + case $host_os in + aix*) + lt_prog_compiler_wl_GCJ='-Wl,' + if test "$host_cpu" = ia64; then + # AIX 5 now supports IA64 processor + lt_prog_compiler_static_GCJ='-Bstatic' + else + lt_prog_compiler_static_GCJ='-bnso -bI:/lib/syscalls.exp' + fi + ;; + darwin*) + # PIC is the default on this platform + # Common symbols not allowed in MH_DYLIB files + case $cc_basename in + xlc*) + lt_prog_compiler_pic_GCJ='-qnocommon' + lt_prog_compiler_wl_GCJ='-Wl,' + ;; + esac + ;; + + mingw* | pw32* | os2*) + # This hack is so that the source file can tell whether it is being + # built for inclusion in a dll (and should export symbols for example). + lt_prog_compiler_pic_GCJ='-DDLL_EXPORT' + ;; + + hpux9* | hpux10* | hpux11*) + lt_prog_compiler_wl_GCJ='-Wl,' + # PIC is the default for IA64 HP-UX and 64-bit HP-UX, but + # not for PA HP-UX. + case $host_cpu in + hppa*64*|ia64*) + # +Z the default + ;; + *) + lt_prog_compiler_pic_GCJ='+Z' + ;; + esac + # Is there a better lt_prog_compiler_static that works with the bundled CC? + lt_prog_compiler_static_GCJ='${wl}-a ${wl}archive' + ;; + + irix5* | irix6* | nonstopux*) + lt_prog_compiler_wl_GCJ='-Wl,' + # PIC (with -KPIC) is the default. + lt_prog_compiler_static_GCJ='-non_shared' + ;; + + newsos6) + lt_prog_compiler_pic_GCJ='-KPIC' + lt_prog_compiler_static_GCJ='-Bstatic' + ;; + + linux*) + case $cc_basename in + icc* | ecc*) + lt_prog_compiler_wl_GCJ='-Wl,' + lt_prog_compiler_pic_GCJ='-KPIC' + lt_prog_compiler_static_GCJ='-static' + ;; + pgcc* | pgf77* | pgf90* | pgf95*) + # Portland Group compilers (*not* the Pentium gcc compiler, + # which looks to be a dead project) + lt_prog_compiler_wl_GCJ='-Wl,' + lt_prog_compiler_pic_GCJ='-fpic' + lt_prog_compiler_static_GCJ='-Bstatic' + ;; + ccc*) + lt_prog_compiler_wl_GCJ='-Wl,' + # All Alpha code is PIC. + lt_prog_compiler_static_GCJ='-non_shared' + ;; + esac + ;; + + osf3* | osf4* | osf5*) + lt_prog_compiler_wl_GCJ='-Wl,' + # All OSF/1 code is PIC. + lt_prog_compiler_static_GCJ='-non_shared' + ;; + + solaris*) + lt_prog_compiler_pic_GCJ='-KPIC' + lt_prog_compiler_static_GCJ='-Bstatic' + case $cc_basename in + f77* | f90* | f95*) + lt_prog_compiler_wl_GCJ='-Qoption ld ';; + *) + lt_prog_compiler_wl_GCJ='-Wl,';; + esac + ;; + + sunos4*) + lt_prog_compiler_wl_GCJ='-Qoption ld ' + lt_prog_compiler_pic_GCJ='-PIC' + lt_prog_compiler_static_GCJ='-Bstatic' + ;; + + sysv4 | sysv4.2uw2* | sysv4.3*) + lt_prog_compiler_wl_GCJ='-Wl,' + lt_prog_compiler_pic_GCJ='-KPIC' + lt_prog_compiler_static_GCJ='-Bstatic' + ;; + + sysv4*MP*) + if test -d /usr/nec ;then + lt_prog_compiler_pic_GCJ='-Kconform_pic' + lt_prog_compiler_static_GCJ='-Bstatic' + fi + ;; + + sysv5* | unixware* | sco3.2v5* | sco5v6* | OpenUNIX*) + lt_prog_compiler_wl_GCJ='-Wl,' + lt_prog_compiler_pic_GCJ='-KPIC' + lt_prog_compiler_static_GCJ='-Bstatic' + ;; + + unicos*) + lt_prog_compiler_wl_GCJ='-Wl,' + lt_prog_compiler_can_build_shared_GCJ=no + ;; + + uts4*) + lt_prog_compiler_pic_GCJ='-pic' + lt_prog_compiler_static_GCJ='-Bstatic' + ;; + + *) + lt_prog_compiler_can_build_shared_GCJ=no + ;; + esac + fi + +echo "$as_me:$LINENO: result: $lt_prog_compiler_pic_GCJ" >&5 +echo "${ECHO_T}$lt_prog_compiler_pic_GCJ" >&6 + +# +# Check to make sure the PIC flag actually works. +# +if test -n "$lt_prog_compiler_pic_GCJ"; then + +echo "$as_me:$LINENO: checking if $compiler PIC flag $lt_prog_compiler_pic_GCJ works" >&5 +echo $ECHO_N "checking if $compiler PIC flag $lt_prog_compiler_pic_GCJ works... $ECHO_C" >&6 +if test "${lt_prog_compiler_pic_works_GCJ+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + lt_prog_compiler_pic_works_GCJ=no + ac_outfile=conftest.$ac_objext + printf "$lt_simple_compile_test_code" > conftest.$ac_ext + lt_compiler_flag="$lt_prog_compiler_pic_GCJ" + # Insert the option either (1) after the last *FLAGS variable, or + # (2) before a word containing "conftest.", or (3) at the end. + # Note that $ac_compile itself does not contain backslashes and begins + # with a dollar sign (not a hyphen), so the echo should work correctly. + # The option is referenced via a variable to avoid confusing sed. + lt_compile=`echo "$ac_compile" | $SED \ + -e 's:.*FLAGS}\{0,1\} :&$lt_compiler_flag :; t' \ + -e 's: [^ ]*conftest\.: $lt_compiler_flag&:; t' \ + -e 's:$: $lt_compiler_flag:'` + (eval echo "\"\$as_me:15568: $lt_compile\"" >&5) + (eval "$lt_compile" 2>conftest.err) + ac_status=$? + cat conftest.err >&5 + echo "$as_me:15572: \$? = $ac_status" >&5 + if (exit $ac_status) && test -s "$ac_outfile"; then + # The compiler can only warn and ignore the option if not recognized + # So say no if there are warnings other than the usual output. + $echo "X$_lt_compiler_boilerplate" | $Xsed -e '/^$/d' >conftest.exp + $SED '/^$/d; /^ *+/d' conftest.err >conftest.er2 + if test ! -s conftest.er2 || diff conftest.exp conftest.er2 >/dev/null; then + lt_prog_compiler_pic_works_GCJ=yes + fi + fi + $rm conftest* + +fi +echo "$as_me:$LINENO: result: $lt_prog_compiler_pic_works_GCJ" >&5 +echo "${ECHO_T}$lt_prog_compiler_pic_works_GCJ" >&6 + +if test x"$lt_prog_compiler_pic_works_GCJ" = xyes; then + case $lt_prog_compiler_pic_GCJ in + "" | " "*) ;; + *) lt_prog_compiler_pic_GCJ=" $lt_prog_compiler_pic_GCJ" ;; + esac +else + lt_prog_compiler_pic_GCJ= + lt_prog_compiler_can_build_shared_GCJ=no +fi + +fi +case $host_os in + # For platforms which do not support PIC, -DPIC is meaningless: + *djgpp*) + lt_prog_compiler_pic_GCJ= + ;; + *) + lt_prog_compiler_pic_GCJ="$lt_prog_compiler_pic_GCJ" + ;; +esac + +# +# Check to make sure the static flag actually works. +# +wl=$lt_prog_compiler_wl_GCJ eval lt_tmp_static_flag=\"$lt_prog_compiler_static_GCJ\" +echo "$as_me:$LINENO: checking if $compiler static flag $lt_tmp_static_flag works" >&5 +echo $ECHO_N "checking if $compiler static flag $lt_tmp_static_flag works... $ECHO_C" >&6 +if test "${lt_prog_compiler_static_works_GCJ+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + lt_prog_compiler_static_works_GCJ=no + save_LDFLAGS="$LDFLAGS" + LDFLAGS="$LDFLAGS $lt_tmp_static_flag" + printf "$lt_simple_link_test_code" > conftest.$ac_ext + if (eval $ac_link 2>conftest.err) && test -s conftest$ac_exeext; then + # The linker can only warn and ignore the option if not recognized + # So say no if there are warnings + if test -s conftest.err; then + # Append any errors to the config.log. + cat conftest.err 1>&5 + $echo "X$_lt_linker_boilerplate" | $Xsed -e '/^$/d' > conftest.exp + $SED '/^$/d; /^ *+/d' conftest.err >conftest.er2 + if diff conftest.exp conftest.er2 >/dev/null; then + lt_prog_compiler_static_works_GCJ=yes + fi + else + lt_prog_compiler_static_works_GCJ=yes + fi + fi + $rm conftest* + LDFLAGS="$save_LDFLAGS" + +fi +echo "$as_me:$LINENO: result: $lt_prog_compiler_static_works_GCJ" >&5 +echo "${ECHO_T}$lt_prog_compiler_static_works_GCJ" >&6 + +if test x"$lt_prog_compiler_static_works_GCJ" = xyes; then + : +else + lt_prog_compiler_static_GCJ= +fi + + +echo "$as_me:$LINENO: checking if $compiler supports -c -o file.$ac_objext" >&5 +echo $ECHO_N "checking if $compiler supports -c -o file.$ac_objext... $ECHO_C" >&6 +if test "${lt_cv_prog_compiler_c_o_GCJ+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + lt_cv_prog_compiler_c_o_GCJ=no + $rm -r conftest 2>/dev/null + mkdir conftest + cd conftest + mkdir out + printf "$lt_simple_compile_test_code" > conftest.$ac_ext + + lt_compiler_flag="-o out/conftest2.$ac_objext" + # Insert the option either (1) after the last *FLAGS variable, or + # (2) before a word containing "conftest.", or (3) at the end. + # Note that $ac_compile itself does not contain backslashes and begins + # with a dollar sign (not a hyphen), so the echo should work correctly. + lt_compile=`echo "$ac_compile" | $SED \ + -e 's:.*FLAGS}\{0,1\} :&$lt_compiler_flag :; t' \ + -e 's: [^ ]*conftest\.: $lt_compiler_flag&:; t' \ + -e 's:$: $lt_compiler_flag:'` + (eval echo "\"\$as_me:15672: $lt_compile\"" >&5) + (eval "$lt_compile" 2>out/conftest.err) + ac_status=$? + cat out/conftest.err >&5 + echo "$as_me:15676: \$? = $ac_status" >&5 + if (exit $ac_status) && test -s out/conftest2.$ac_objext + then + # The compiler can only warn and ignore the option if not recognized + # So say no if there are warnings + $echo "X$_lt_compiler_boilerplate" | $Xsed -e '/^$/d' > out/conftest.exp + $SED '/^$/d; /^ *+/d' out/conftest.err >out/conftest.er2 + if test ! -s out/conftest.er2 || diff out/conftest.exp out/conftest.er2 >/dev/null; then + lt_cv_prog_compiler_c_o_GCJ=yes + fi + fi + chmod u+w . 2>&5 + $rm conftest* + # SGI C++ compiler will create directory out/ii_files/ for + # template instantiation + test -d out/ii_files && $rm out/ii_files/* && rmdir out/ii_files + $rm out/* && rmdir out + cd .. + rmdir conftest + $rm conftest* + +fi +echo "$as_me:$LINENO: result: $lt_cv_prog_compiler_c_o_GCJ" >&5 +echo "${ECHO_T}$lt_cv_prog_compiler_c_o_GCJ" >&6 + + +hard_links="nottested" +if test "$lt_cv_prog_compiler_c_o_GCJ" = no && test "$need_locks" != no; then + # do not overwrite the value of need_locks provided by the user + echo "$as_me:$LINENO: checking if we can lock with hard links" >&5 +echo $ECHO_N "checking if we can lock with hard links... $ECHO_C" >&6 + hard_links=yes + $rm conftest* + ln conftest.a conftest.b 2>/dev/null && hard_links=no + touch conftest.a + ln conftest.a conftest.b 2>&5 || hard_links=no + ln conftest.a conftest.b 2>/dev/null && hard_links=no + echo "$as_me:$LINENO: result: $hard_links" >&5 +echo "${ECHO_T}$hard_links" >&6 + if test "$hard_links" = no; then + { echo "$as_me:$LINENO: WARNING: \`$CC' does not support \`-c -o', so \`make -j' may be unsafe" >&5 +echo "$as_me: WARNING: \`$CC' does not support \`-c -o', so \`make -j' may be unsafe" >&2;} + need_locks=warn + fi +else + need_locks=no +fi + +echo "$as_me:$LINENO: checking whether the $compiler linker ($LD) supports shared libraries" >&5 +echo $ECHO_N "checking whether the $compiler linker ($LD) supports shared libraries... $ECHO_C" >&6 + + runpath_var= + allow_undefined_flag_GCJ= + enable_shared_with_static_runtimes_GCJ=no + archive_cmds_GCJ= + archive_expsym_cmds_GCJ= + old_archive_From_new_cmds_GCJ= + old_archive_from_expsyms_cmds_GCJ= + export_dynamic_flag_spec_GCJ= + whole_archive_flag_spec_GCJ= + thread_safe_flag_spec_GCJ= + hardcode_libdir_flag_spec_GCJ= + hardcode_libdir_flag_spec_ld_GCJ= + hardcode_libdir_separator_GCJ= + hardcode_direct_GCJ=no + hardcode_minus_L_GCJ=no + hardcode_shlibpath_var_GCJ=unsupported + link_all_deplibs_GCJ=unknown + hardcode_automatic_GCJ=no + module_cmds_GCJ= + module_expsym_cmds_GCJ= + always_export_symbols_GCJ=no + export_symbols_cmds_GCJ='$NM $libobjs $convenience | $global_symbol_pipe | $SED '\''s/.* //'\'' | sort | uniq > $export_symbols' + # include_expsyms should be a list of space-separated symbols to be *always* + # included in the symbol list + include_expsyms_GCJ= + # exclude_expsyms can be an extended regexp of symbols to exclude + # it will be wrapped by ` (' and `)$', so one must not match beginning or + # end of line. Example: `a|bc|.*d.*' will exclude the symbols `a' and `bc', + # as well as any symbol that contains `d'. + exclude_expsyms_GCJ="_GLOBAL_OFFSET_TABLE_" + # Although _GLOBAL_OFFSET_TABLE_ is a valid symbol C name, most a.out + # platforms (ab)use it in PIC code, but their linkers get confused if + # the symbol is explicitly referenced. Since portable code cannot + # rely on this symbol name, it's probably fine to never include it in + # preloaded symbol tables. + extract_expsyms_cmds= + # Just being paranoid about ensuring that cc_basename is set. + for cc_temp in $compiler""; do + case $cc_temp in + compile | *[\\/]compile | ccache | *[\\/]ccache ) ;; + distcc | *[\\/]distcc | purify | *[\\/]purify ) ;; + \-*) ;; + *) break;; + esac +done +cc_basename=`$echo "X$cc_temp" | $Xsed -e 's%.*/%%' -e "s%^$host_alias-%%"` + + case $host_os in + cygwin* | mingw* | pw32*) + # FIXME: the MSVC++ port hasn't been tested in a loooong time + # When not using gcc, we currently assume that we are using + # Microsoft Visual C++. + if test "$GCC" != yes; then + with_gnu_ld=no + fi + ;; + interix*) + # we just hope/assume this is gcc and not c89 (= MSVC++) + with_gnu_ld=yes + ;; + openbsd*) + with_gnu_ld=no + ;; + esac + + ld_shlibs_GCJ=yes + if test "$with_gnu_ld" = yes; then + # If archive_cmds runs LD, not CC, wlarc should be empty + wlarc='${wl}' + + # Set some defaults for GNU ld with shared library support. These + # are reset later if shared libraries are not supported. Putting them + # here allows them to be overridden if necessary. + runpath_var=LD_RUN_PATH + hardcode_libdir_flag_spec_GCJ='${wl}--rpath ${wl}$libdir' + export_dynamic_flag_spec_GCJ='${wl}--export-dynamic' + # ancient GNU ld didn't support --whole-archive et. al. + if $LD --help 2>&1 | grep 'no-whole-archive' > /dev/null; then + whole_archive_flag_spec_GCJ="$wlarc"'--whole-archive$convenience '"$wlarc"'--no-whole-archive' + else + whole_archive_flag_spec_GCJ= + fi + supports_anon_versioning=no + case `$LD -v 2>/dev/null` in + *\ [01].* | *\ 2.[0-9].* | *\ 2.10.*) ;; # catch versions < 2.11 + *\ 2.11.93.0.2\ *) supports_anon_versioning=yes ;; # RH7.3 ... + *\ 2.11.92.0.12\ *) supports_anon_versioning=yes ;; # Mandrake 8.2 ... + *\ 2.11.*) ;; # other 2.11 versions + *) supports_anon_versioning=yes ;; + esac + + # See if GNU ld supports shared libraries. + case $host_os in + aix3* | aix4* | aix5*) + # On AIX/PPC, the GNU linker is very broken + if test "$host_cpu" != ia64; then + ld_shlibs_GCJ=no + cat <&2 + +*** Warning: the GNU linker, at least up to release 2.9.1, is reported +*** to be unable to reliably create shared libraries on AIX. +*** Therefore, libtool is disabling shared libraries support. If you +*** really care for shared libraries, you may want to modify your PATH +*** so that a non-GNU linker is found, and then restart. + +EOF + fi + ;; + + amigaos*) + archive_cmds_GCJ='$rm $output_objdir/a2ixlibrary.data~$echo "#define NAME $libname" > $output_objdir/a2ixlibrary.data~$echo "#define LIBRARY_ID 1" >> $output_objdir/a2ixlibrary.data~$echo "#define VERSION $major" >> $output_objdir/a2ixlibrary.data~$echo "#define REVISION $revision" >> $output_objdir/a2ixlibrary.data~$AR $AR_FLAGS $lib $libobjs~$RANLIB $lib~(cd $output_objdir && a2ixlibrary -32)' + hardcode_libdir_flag_spec_GCJ='-L$libdir' + hardcode_minus_L_GCJ=yes + + # Samuel A. Falvo II reports + # that the semantics of dynamic libraries on AmigaOS, at least up + # to version 4, is to share data among multiple programs linked + # with the same dynamic library. Since this doesn't match the + # behavior of shared libraries on other platforms, we can't use + # them. + ld_shlibs_GCJ=no + ;; + + beos*) + if $LD --help 2>&1 | grep ': supported targets:.* elf' > /dev/null; then + allow_undefined_flag_GCJ=unsupported + # Joseph Beckenbach says some releases of gcc + # support --undefined. This deserves some investigation. FIXME + archive_cmds_GCJ='$CC -nostart $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + else + ld_shlibs_GCJ=no + fi + ;; + + cygwin* | mingw* | pw32*) + # _LT_AC_TAGVAR(hardcode_libdir_flag_spec, GCJ) is actually meaningless, + # as there is no search path for DLLs. + hardcode_libdir_flag_spec_GCJ='-L$libdir' + allow_undefined_flag_GCJ=unsupported + always_export_symbols_GCJ=no + enable_shared_with_static_runtimes_GCJ=yes + export_symbols_cmds_GCJ='$NM $libobjs $convenience | $global_symbol_pipe | $SED -e '\''/^[BCDGRS] /s/.* \([^ ]*\)/\1 DATA/'\'' | $SED -e '\''/^[AITW] /s/.* //'\'' | sort | uniq > $export_symbols' + + if $LD --help 2>&1 | grep 'auto-import' > /dev/null; then + archive_cmds_GCJ='$CC -shared $libobjs $deplibs $compiler_flags -o $output_objdir/$soname ${wl}--enable-auto-image-base -Xlinker --out-implib -Xlinker $lib' + # If the export-symbols file already is a .def file (1st line + # is EXPORTS), use it as is; otherwise, prepend... + archive_expsym_cmds_GCJ='if test "x`$SED 1q $export_symbols`" = xEXPORTS; then + cp $export_symbols $output_objdir/$soname.def; + else + echo EXPORTS > $output_objdir/$soname.def; + cat $export_symbols >> $output_objdir/$soname.def; + fi~ + $CC -shared $output_objdir/$soname.def $libobjs $deplibs $compiler_flags -o $output_objdir/$soname ${wl}--enable-auto-image-base -Xlinker --out-implib -Xlinker $lib' + else + ld_shlibs_GCJ=no + fi + ;; + + interix3*) + hardcode_direct_GCJ=no + hardcode_shlibpath_var_GCJ=no + hardcode_libdir_flag_spec_GCJ='${wl}-rpath,$libdir' + export_dynamic_flag_spec_GCJ='${wl}-E' + # Hack: On Interix 3.x, we cannot compile PIC because of a broken gcc. + # Instead, shared libraries are loaded at an image base (0x10000000 by + # default) and relocated if they conflict, which is a slow very memory + # consuming and fragmenting process. To avoid this, we pick a random, + # 256 KiB-aligned image base between 0x50000000 and 0x6FFC0000 at link + # time. Moving up from 0x10000000 also allows more sbrk(2) space. + archive_cmds_GCJ='$CC -shared $pic_flag $libobjs $deplibs $compiler_flags ${wl}-h,$soname ${wl}--image-base,`expr ${RANDOM-$$} % 4096 / 2 \* 262144 + 1342177280` -o $lib' + archive_expsym_cmds_GCJ='sed "s,^,_," $export_symbols >$output_objdir/$soname.expsym~$CC -shared $pic_flag $libobjs $deplibs $compiler_flags ${wl}-h,$soname ${wl}--retain-symbols-file,$output_objdir/$soname.expsym ${wl}--image-base,`expr ${RANDOM-$$} % 4096 / 2 \* 262144 + 1342177280` -o $lib' + ;; + + linux*) + if $LD --help 2>&1 | grep ': supported targets:.* elf' > /dev/null; then + tmp_addflag= + case $cc_basename,$host_cpu in + pgcc*) # Portland Group C compiler + whole_archive_flag_spec_GCJ='${wl}--whole-archive`for conv in $convenience\"\"; do test -n \"$conv\" && new_convenience=\"$new_convenience,$conv\"; done; $echo \"$new_convenience\"` ${wl}--no-whole-archive' + tmp_addflag=' $pic_flag' + ;; + pgf77* | pgf90* | pgf95*) # Portland Group f77 and f90 compilers + whole_archive_flag_spec_GCJ='${wl}--whole-archive`for conv in $convenience\"\"; do test -n \"$conv\" && new_convenience=\"$new_convenience,$conv\"; done; $echo \"$new_convenience\"` ${wl}--no-whole-archive' + tmp_addflag=' $pic_flag -Mnomain' ;; + ecc*,ia64* | icc*,ia64*) # Intel C compiler on ia64 + tmp_addflag=' -i_dynamic' ;; + efc*,ia64* | ifort*,ia64*) # Intel Fortran compiler on ia64 + tmp_addflag=' -i_dynamic -nofor_main' ;; + ifc* | ifort*) # Intel Fortran compiler + tmp_addflag=' -nofor_main' ;; + esac + archive_cmds_GCJ='$CC -shared'"$tmp_addflag"' $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + + if test $supports_anon_versioning = yes; then + archive_expsym_cmds_GCJ='$echo "{ global:" > $output_objdir/$libname.ver~ + cat $export_symbols | sed -e "s/\(.*\)/\1;/" >> $output_objdir/$libname.ver~ + $echo "local: *; };" >> $output_objdir/$libname.ver~ + $CC -shared'"$tmp_addflag"' $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-version-script ${wl}$output_objdir/$libname.ver -o $lib' + fi + else + ld_shlibs_GCJ=no + fi + ;; + + netbsd*) + if echo __ELF__ | $CC -E - | grep __ELF__ >/dev/null; then + archive_cmds_GCJ='$LD -Bshareable $libobjs $deplibs $linker_flags -o $lib' + wlarc= + else + archive_cmds_GCJ='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + archive_expsym_cmds_GCJ='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-retain-symbols-file $wl$export_symbols -o $lib' + fi + ;; + + solaris*) + if $LD -v 2>&1 | grep 'BFD 2\.8' > /dev/null; then + ld_shlibs_GCJ=no + cat <&2 + +*** Warning: The releases 2.8.* of the GNU linker cannot reliably +*** create shared libraries on Solaris systems. Therefore, libtool +*** is disabling shared libraries support. We urge you to upgrade GNU +*** binutils to release 2.9.1 or newer. Another option is to modify +*** your PATH or compiler configuration so that the native linker is +*** used, and then restart. + +EOF + elif $LD --help 2>&1 | grep ': supported targets:.* elf' > /dev/null; then + archive_cmds_GCJ='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + archive_expsym_cmds_GCJ='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-retain-symbols-file $wl$export_symbols -o $lib' + else + ld_shlibs_GCJ=no + fi + ;; + + sysv5* | sco3.2v5* | sco5v6* | unixware* | OpenUNIX*) + case `$LD -v 2>&1` in + *\ [01].* | *\ 2.[0-9].* | *\ 2.1[0-5].*) + ld_shlibs_GCJ=no + cat <<_LT_EOF 1>&2 + +*** Warning: Releases of the GNU linker prior to 2.16.91.0.3 can not +*** reliably create shared libraries on SCO systems. Therefore, libtool +*** is disabling shared libraries support. We urge you to upgrade GNU +*** binutils to release 2.16.91.0.3 or newer. Another option is to modify +*** your PATH or compiler configuration so that the native linker is +*** used, and then restart. + +_LT_EOF + ;; + *) + if $LD --help 2>&1 | grep ': supported targets:.* elf' > /dev/null; then + hardcode_libdir_flag_spec_GCJ='`test -z "$SCOABSPATH" && echo ${wl}-rpath,$libdir`' + archive_cmds_GCJ='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname,\${SCOABSPATH:+${install_libdir}/}$soname -o $lib' + archive_expsym_cmds_GCJ='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname,\${SCOABSPATH:+${install_libdir}/}$soname,-retain-symbols-file,$export_symbols -o $lib' + else + ld_shlibs_GCJ=no + fi + ;; + esac + ;; + + sunos4*) + archive_cmds_GCJ='$LD -assert pure-text -Bshareable -o $lib $libobjs $deplibs $linker_flags' + wlarc= + hardcode_direct_GCJ=yes + hardcode_shlibpath_var_GCJ=no + ;; + + *) + if $LD --help 2>&1 | grep ': supported targets:.* elf' > /dev/null; then + archive_cmds_GCJ='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + archive_expsym_cmds_GCJ='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-retain-symbols-file $wl$export_symbols -o $lib' + else + ld_shlibs_GCJ=no + fi + ;; + esac + + if test "$ld_shlibs_GCJ" = no; then + runpath_var= + hardcode_libdir_flag_spec_GCJ= + export_dynamic_flag_spec_GCJ= + whole_archive_flag_spec_GCJ= + fi + else + # PORTME fill in a description of your system's linker (not GNU ld) + case $host_os in + aix3*) + allow_undefined_flag_GCJ=unsupported + always_export_symbols_GCJ=yes + archive_expsym_cmds_GCJ='$LD -o $output_objdir/$soname $libobjs $deplibs $linker_flags -bE:$export_symbols -T512 -H512 -bM:SRE~$AR $AR_FLAGS $lib $output_objdir/$soname' + # Note: this linker hardcodes the directories in LIBPATH if there + # are no directories specified by -L. + hardcode_minus_L_GCJ=yes + if test "$GCC" = yes && test -z "$lt_prog_compiler_static"; then + # Neither direct hardcoding nor static linking is supported with a + # broken collect2. + hardcode_direct_GCJ=unsupported + fi + ;; + + aix4* | aix5*) + if test "$host_cpu" = ia64; then + # On IA64, the linker does run time linking by default, so we don't + # have to do anything special. + aix_use_runtimelinking=no + exp_sym_flag='-Bexport' + no_entry_flag="" + else + # If we're using GNU nm, then we don't want the "-C" option. + # -C means demangle to AIX nm, but means don't demangle with GNU nm + if $NM -V 2>&1 | grep 'GNU' > /dev/null; then + export_symbols_cmds_GCJ='$NM -Bpg $libobjs $convenience | awk '\''{ if (((\$2 == "T") || (\$2 == "D") || (\$2 == "B")) && (substr(\$3,1,1) != ".")) { print \$3 } }'\'' | sort -u > $export_symbols' + else + export_symbols_cmds_GCJ='$NM -BCpg $libobjs $convenience | awk '\''{ if (((\$2 == "T") || (\$2 == "D") || (\$2 == "B")) && (substr(\$3,1,1) != ".")) { print \$3 } }'\'' | sort -u > $export_symbols' + fi + aix_use_runtimelinking=no + + # Test if we are trying to use run time linking or normal + # AIX style linking. If -brtl is somewhere in LDFLAGS, we + # need to do runtime linking. + case $host_os in aix4.[23]|aix4.[23].*|aix5*) + for ld_flag in $LDFLAGS; do + if (test $ld_flag = "-brtl" || test $ld_flag = "-Wl,-brtl"); then + aix_use_runtimelinking=yes + break + fi + done + ;; + esac + + exp_sym_flag='-bexport' + no_entry_flag='-bnoentry' + fi + + # When large executables or shared objects are built, AIX ld can + # have problems creating the table of contents. If linking a library + # or program results in "error TOC overflow" add -mminimal-toc to + # CXXFLAGS/CFLAGS for g++/gcc. In the cases where that is not + # enough to fix the problem, add -Wl,-bbigtoc to LDFLAGS. + + archive_cmds_GCJ='' + hardcode_direct_GCJ=yes + hardcode_libdir_separator_GCJ=':' + link_all_deplibs_GCJ=yes + + if test "$GCC" = yes; then + case $host_os in aix4.[012]|aix4.[012].*) + # We only want to do this on AIX 4.2 and lower, the check + # below for broken collect2 doesn't work under 4.3+ + collect2name=`${CC} -print-prog-name=collect2` + if test -f "$collect2name" && \ + strings "$collect2name" | grep resolve_lib_name >/dev/null + then + # We have reworked collect2 + hardcode_direct_GCJ=yes + else + # We have old collect2 + hardcode_direct_GCJ=unsupported + # It fails to find uninstalled libraries when the uninstalled + # path is not listed in the libpath. Setting hardcode_minus_L + # to unsupported forces relinking + hardcode_minus_L_GCJ=yes + hardcode_libdir_flag_spec_GCJ='-L$libdir' + hardcode_libdir_separator_GCJ= + fi + ;; + esac + shared_flag='-shared' + if test "$aix_use_runtimelinking" = yes; then + shared_flag="$shared_flag "'${wl}-G' + fi + else + # not using gcc + if test "$host_cpu" = ia64; then + # VisualAge C++, Version 5.5 for AIX 5L for IA-64, Beta 3 Release + # chokes on -Wl,-G. The following line is correct: + shared_flag='-G' + else + if test "$aix_use_runtimelinking" = yes; then + shared_flag='${wl}-G' + else + shared_flag='${wl}-bM:SRE' + fi + fi + fi + + # It seems that -bexpall does not export symbols beginning with + # underscore (_), so it is better to generate a list of symbols to export. + always_export_symbols_GCJ=yes + if test "$aix_use_runtimelinking" = yes; then + # Warning - without using the other runtime loading flags (-brtl), + # -berok will link without error, but may produce a broken library. + allow_undefined_flag_GCJ='-berok' + # Determine the default libpath from the value encoded in an empty executable. + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext conftest$ac_exeext +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest$ac_exeext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + +aix_libpath=`dump -H conftest$ac_exeext 2>/dev/null | $SED -n -e '/Import File Strings/,/^$/ { /^0/ { s/^0 *\(.*\)$/\1/; p; } +}'` +# Check for a 64-bit object if we didn't find anything. +if test -z "$aix_libpath"; then aix_libpath=`dump -HX64 conftest$ac_exeext 2>/dev/null | $SED -n -e '/Import File Strings/,/^$/ { /^0/ { s/^0 *\(.*\)$/\1/; p; } +}'`; fi +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +fi +rm -f conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +if test -z "$aix_libpath"; then aix_libpath="/usr/lib:/lib"; fi + + hardcode_libdir_flag_spec_GCJ='${wl}-blibpath:$libdir:'"$aix_libpath" + archive_expsym_cmds_GCJ="\$CC"' -o $output_objdir/$soname $libobjs $deplibs '"\${wl}$no_entry_flag"' $compiler_flags `if test "x${allow_undefined_flag}" != "x"; then echo "${wl}${allow_undefined_flag}"; else :; fi` '"\${wl}$exp_sym_flag:\$export_symbols $shared_flag" + else + if test "$host_cpu" = ia64; then + hardcode_libdir_flag_spec_GCJ='${wl}-R $libdir:/usr/lib:/lib' + allow_undefined_flag_GCJ="-z nodefs" + archive_expsym_cmds_GCJ="\$CC $shared_flag"' -o $output_objdir/$soname $libobjs $deplibs '"\${wl}$no_entry_flag"' $compiler_flags ${wl}${allow_undefined_flag} '"\${wl}$exp_sym_flag:\$export_symbols" + else + # Determine the default libpath from the value encoded in an empty executable. + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +int +main () +{ + + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext conftest$ac_exeext +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest$ac_exeext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + +aix_libpath=`dump -H conftest$ac_exeext 2>/dev/null | $SED -n -e '/Import File Strings/,/^$/ { /^0/ { s/^0 *\(.*\)$/\1/; p; } +}'` +# Check for a 64-bit object if we didn't find anything. +if test -z "$aix_libpath"; then aix_libpath=`dump -HX64 conftest$ac_exeext 2>/dev/null | $SED -n -e '/Import File Strings/,/^$/ { /^0/ { s/^0 *\(.*\)$/\1/; p; } +}'`; fi +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +fi +rm -f conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +if test -z "$aix_libpath"; then aix_libpath="/usr/lib:/lib"; fi + + hardcode_libdir_flag_spec_GCJ='${wl}-blibpath:$libdir:'"$aix_libpath" + # Warning - without using the other run time loading flags, + # -berok will link without error, but may produce a broken library. + no_undefined_flag_GCJ=' ${wl}-bernotok' + allow_undefined_flag_GCJ=' ${wl}-berok' + # Exported symbols can be pulled into shared objects from archives + whole_archive_flag_spec_GCJ='$convenience' + archive_cmds_need_lc_GCJ=yes + # This is similar to how AIX traditionally builds its shared libraries. + archive_expsym_cmds_GCJ="\$CC $shared_flag"' -o $output_objdir/$soname $libobjs $deplibs ${wl}-bnoentry $compiler_flags ${wl}-bE:$export_symbols${allow_undefined_flag}~$AR $AR_FLAGS $output_objdir/$libname$release.a $output_objdir/$soname' + fi + fi + ;; + + amigaos*) + archive_cmds_GCJ='$rm $output_objdir/a2ixlibrary.data~$echo "#define NAME $libname" > $output_objdir/a2ixlibrary.data~$echo "#define LIBRARY_ID 1" >> $output_objdir/a2ixlibrary.data~$echo "#define VERSION $major" >> $output_objdir/a2ixlibrary.data~$echo "#define REVISION $revision" >> $output_objdir/a2ixlibrary.data~$AR $AR_FLAGS $lib $libobjs~$RANLIB $lib~(cd $output_objdir && a2ixlibrary -32)' + hardcode_libdir_flag_spec_GCJ='-L$libdir' + hardcode_minus_L_GCJ=yes + # see comment about different semantics on the GNU ld section + ld_shlibs_GCJ=no + ;; + + bsdi[45]*) + export_dynamic_flag_spec_GCJ=-rdynamic + ;; + + cygwin* | mingw* | pw32*) + # When not using gcc, we currently assume that we are using + # Microsoft Visual C++. + # hardcode_libdir_flag_spec is actually meaningless, as there is + # no search path for DLLs. + hardcode_libdir_flag_spec_GCJ=' ' + allow_undefined_flag_GCJ=unsupported + # Tell ltmain to make .lib files, not .a files. + libext=lib + # Tell ltmain to make .dll files, not .so files. + shrext_cmds=".dll" + # FIXME: Setting linknames here is a bad hack. + archive_cmds_GCJ='$CC -o $lib $libobjs $compiler_flags `echo "$deplibs" | $SED -e '\''s/ -lc$//'\''` -link -dll~linknames=' + # The linker will automatically build a .lib file if we build a DLL. + old_archive_From_new_cmds_GCJ='true' + # FIXME: Should let the user specify the lib program. + old_archive_cmds_GCJ='lib /OUT:$oldlib$oldobjs$old_deplibs' + fix_srcfile_path_GCJ='`cygpath -w "$srcfile"`' + enable_shared_with_static_runtimes_GCJ=yes + ;; + + darwin* | rhapsody*) + case $host_os in + rhapsody* | darwin1.[012]) + allow_undefined_flag_GCJ='${wl}-undefined ${wl}suppress' + ;; + *) # Darwin 1.3 on + if test -z ${MACOSX_DEPLOYMENT_TARGET} ; then + allow_undefined_flag_GCJ='${wl}-flat_namespace ${wl}-undefined ${wl}suppress' + else + case ${MACOSX_DEPLOYMENT_TARGET} in + 10.[012]) + allow_undefined_flag_GCJ='${wl}-flat_namespace ${wl}-undefined ${wl}suppress' + ;; + 10.*) + allow_undefined_flag_GCJ='${wl}-undefined ${wl}dynamic_lookup' + ;; + esac + fi + ;; + esac + archive_cmds_need_lc_GCJ=no + hardcode_direct_GCJ=no + hardcode_automatic_GCJ=yes + hardcode_shlibpath_var_GCJ=unsupported + whole_archive_flag_spec_GCJ='' + link_all_deplibs_GCJ=yes + if test "$GCC" = yes ; then + output_verbose_link_cmd='echo' + archive_cmds_GCJ='$CC -dynamiclib $allow_undefined_flag -o $lib $libobjs $deplibs $compiler_flags -install_name $rpath/$soname $verstring' + module_cmds_GCJ='$CC $allow_undefined_flag -o $lib -bundle $libobjs $deplibs$compiler_flags' + # Don't fix this by using the ld -exported_symbols_list flag, it doesn't exist in older darwin lds + archive_expsym_cmds_GCJ='sed -e "s,#.*,," -e "s,^[ ]*,," -e "s,^\(..*\),_&," < $export_symbols > $output_objdir/${libname}-symbols.expsym~$CC -dynamiclib $allow_undefined_flag -o $lib $libobjs $deplibs $compiler_flags -install_name $rpath/$soname $verstring~nmedit -s $output_objdir/${libname}-symbols.expsym ${lib}' + module_expsym_cmds_GCJ='sed -e "s,#.*,," -e "s,^[ ]*,," -e "s,^\(..*\),_&," < $export_symbols > $output_objdir/${libname}-symbols.expsym~$CC $allow_undefined_flag -o $lib -bundle $libobjs $deplibs$compiler_flags~nmedit -s $output_objdir/${libname}-symbols.expsym ${lib}' + else + case $cc_basename in + xlc*) + output_verbose_link_cmd='echo' + archive_cmds_GCJ='$CC -qmkshrobj $allow_undefined_flag -o $lib $libobjs $deplibs $compiler_flags ${wl}-install_name ${wl}`echo $rpath/$soname` $verstring' + module_cmds_GCJ='$CC $allow_undefined_flag -o $lib -bundle $libobjs $deplibs$compiler_flags' + # Don't fix this by using the ld -exported_symbols_list flag, it doesn't exist in older darwin lds + archive_expsym_cmds_GCJ='sed -e "s,#.*,," -e "s,^[ ]*,," -e "s,^\(..*\),_&," < $export_symbols > $output_objdir/${libname}-symbols.expsym~$CC -qmkshrobj $allow_undefined_flag -o $lib $libobjs $deplibs $compiler_flags ${wl}-install_name ${wl}$rpath/$soname $verstring~nmedit -s $output_objdir/${libname}-symbols.expsym ${lib}' + module_expsym_cmds_GCJ='sed -e "s,#.*,," -e "s,^[ ]*,," -e "s,^\(..*\),_&," < $export_symbols > $output_objdir/${libname}-symbols.expsym~$CC $allow_undefined_flag -o $lib -bundle $libobjs $deplibs$compiler_flags~nmedit -s $output_objdir/${libname}-symbols.expsym ${lib}' + ;; + *) + ld_shlibs_GCJ=no + ;; + esac + fi + ;; + + dgux*) + archive_cmds_GCJ='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_libdir_flag_spec_GCJ='-L$libdir' + hardcode_shlibpath_var_GCJ=no + ;; + + freebsd1*) + ld_shlibs_GCJ=no + ;; + + # FreeBSD 2.2.[012] allows us to include c++rt0.o to get C++ constructor + # support. Future versions do this automatically, but an explicit c++rt0.o + # does not break anything, and helps significantly (at the cost of a little + # extra space). + freebsd2.2*) + archive_cmds_GCJ='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags /usr/lib/c++rt0.o' + hardcode_libdir_flag_spec_GCJ='-R$libdir' + hardcode_direct_GCJ=yes + hardcode_shlibpath_var_GCJ=no + ;; + + # Unfortunately, older versions of FreeBSD 2 do not have this feature. + freebsd2*) + archive_cmds_GCJ='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags' + hardcode_direct_GCJ=yes + hardcode_minus_L_GCJ=yes + hardcode_shlibpath_var_GCJ=no + ;; + + # FreeBSD 3 and greater uses gcc -shared to do shared libraries. + freebsd* | kfreebsd*-gnu | dragonfly*) + archive_cmds_GCJ='$CC -shared -o $lib $libobjs $deplibs $compiler_flags' + hardcode_libdir_flag_spec_GCJ='-R$libdir' + hardcode_direct_GCJ=yes + hardcode_shlibpath_var_GCJ=no + ;; + + hpux9*) + if test "$GCC" = yes; then + archive_cmds_GCJ='$rm $output_objdir/$soname~$CC -shared -fPIC ${wl}+b ${wl}$install_libdir -o $output_objdir/$soname $libobjs $deplibs $compiler_flags~test $output_objdir/$soname = $lib || mv $output_objdir/$soname $lib' + else + archive_cmds_GCJ='$rm $output_objdir/$soname~$LD -b +b $install_libdir -o $output_objdir/$soname $libobjs $deplibs $linker_flags~test $output_objdir/$soname = $lib || mv $output_objdir/$soname $lib' + fi + hardcode_libdir_flag_spec_GCJ='${wl}+b ${wl}$libdir' + hardcode_libdir_separator_GCJ=: + hardcode_direct_GCJ=yes + + # hardcode_minus_L: Not really in the search PATH, + # but as the default location of the library. + hardcode_minus_L_GCJ=yes + export_dynamic_flag_spec_GCJ='${wl}-E' + ;; + + hpux10*) + if test "$GCC" = yes -a "$with_gnu_ld" = no; then + archive_cmds_GCJ='$CC -shared -fPIC ${wl}+h ${wl}$soname ${wl}+b ${wl}$install_libdir -o $lib $libobjs $deplibs $compiler_flags' + else + archive_cmds_GCJ='$LD -b +h $soname +b $install_libdir -o $lib $libobjs $deplibs $linker_flags' + fi + if test "$with_gnu_ld" = no; then + hardcode_libdir_flag_spec_GCJ='${wl}+b ${wl}$libdir' + hardcode_libdir_separator_GCJ=: + + hardcode_direct_GCJ=yes + export_dynamic_flag_spec_GCJ='${wl}-E' + + # hardcode_minus_L: Not really in the search PATH, + # but as the default location of the library. + hardcode_minus_L_GCJ=yes + fi + ;; + + hpux11*) + if test "$GCC" = yes -a "$with_gnu_ld" = no; then + case $host_cpu in + hppa*64*) + archive_cmds_GCJ='$CC -shared ${wl}+h ${wl}$soname -o $lib $libobjs $deplibs $compiler_flags' + ;; + ia64*) + archive_cmds_GCJ='$CC -shared ${wl}+h ${wl}$soname ${wl}+nodefaultrpath -o $lib $libobjs $deplibs $compiler_flags' + ;; + *) + archive_cmds_GCJ='$CC -shared -fPIC ${wl}+h ${wl}$soname ${wl}+b ${wl}$install_libdir -o $lib $libobjs $deplibs $compiler_flags' + ;; + esac + else + case $host_cpu in + hppa*64*) + archive_cmds_GCJ='$CC -b ${wl}+h ${wl}$soname -o $lib $libobjs $deplibs $compiler_flags' + ;; + ia64*) + archive_cmds_GCJ='$CC -b ${wl}+h ${wl}$soname ${wl}+nodefaultrpath -o $lib $libobjs $deplibs $compiler_flags' + ;; + *) + archive_cmds_GCJ='$CC -b ${wl}+h ${wl}$soname ${wl}+b ${wl}$install_libdir -o $lib $libobjs $deplibs $compiler_flags' + ;; + esac + fi + if test "$with_gnu_ld" = no; then + hardcode_libdir_flag_spec_GCJ='${wl}+b ${wl}$libdir' + hardcode_libdir_separator_GCJ=: + + case $host_cpu in + hppa*64*|ia64*) + hardcode_libdir_flag_spec_ld_GCJ='+b $libdir' + hardcode_direct_GCJ=no + hardcode_shlibpath_var_GCJ=no + ;; + *) + hardcode_direct_GCJ=yes + export_dynamic_flag_spec_GCJ='${wl}-E' + + # hardcode_minus_L: Not really in the search PATH, + # but as the default location of the library. + hardcode_minus_L_GCJ=yes + ;; + esac + fi + ;; + + irix5* | irix6* | nonstopux*) + if test "$GCC" = yes; then + archive_cmds_GCJ='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname ${wl}$soname `test -n "$verstring" && echo ${wl}-set_version ${wl}$verstring` ${wl}-update_registry ${wl}${output_objdir}/so_locations -o $lib' + else + archive_cmds_GCJ='$LD -shared $libobjs $deplibs $linker_flags -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${output_objdir}/so_locations -o $lib' + hardcode_libdir_flag_spec_ld_GCJ='-rpath $libdir' + fi + hardcode_libdir_flag_spec_GCJ='${wl}-rpath ${wl}$libdir' + hardcode_libdir_separator_GCJ=: + link_all_deplibs_GCJ=yes + ;; + + netbsd*) + if echo __ELF__ | $CC -E - | grep __ELF__ >/dev/null; then + archive_cmds_GCJ='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags' # a.out + else + archive_cmds_GCJ='$LD -shared -o $lib $libobjs $deplibs $linker_flags' # ELF + fi + hardcode_libdir_flag_spec_GCJ='-R$libdir' + hardcode_direct_GCJ=yes + hardcode_shlibpath_var_GCJ=no + ;; + + newsos6) + archive_cmds_GCJ='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_direct_GCJ=yes + hardcode_libdir_flag_spec_GCJ='${wl}-rpath ${wl}$libdir' + hardcode_libdir_separator_GCJ=: + hardcode_shlibpath_var_GCJ=no + ;; + + openbsd*) + hardcode_direct_GCJ=yes + hardcode_shlibpath_var_GCJ=no + if test -z "`echo __ELF__ | $CC -E - | grep __ELF__`" || test "$host_os-$host_cpu" = "openbsd2.8-powerpc"; then + archive_cmds_GCJ='$CC -shared $pic_flag -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds_GCJ='$CC -shared $pic_flag -o $lib $libobjs $deplibs $compiler_flags ${wl}-retain-symbols-file,$export_symbols' + hardcode_libdir_flag_spec_GCJ='${wl}-rpath,$libdir' + export_dynamic_flag_spec_GCJ='${wl}-E' + else + case $host_os in + openbsd[01].* | openbsd2.[0-7] | openbsd2.[0-7].*) + archive_cmds_GCJ='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags' + hardcode_libdir_flag_spec_GCJ='-R$libdir' + ;; + *) + archive_cmds_GCJ='$CC -shared $pic_flag -o $lib $libobjs $deplibs $compiler_flags' + hardcode_libdir_flag_spec_GCJ='${wl}-rpath,$libdir' + ;; + esac + fi + ;; + + os2*) + hardcode_libdir_flag_spec_GCJ='-L$libdir' + hardcode_minus_L_GCJ=yes + allow_undefined_flag_GCJ=unsupported + archive_cmds_GCJ='$echo "LIBRARY $libname INITINSTANCE" > $output_objdir/$libname.def~$echo "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~$echo DATA >> $output_objdir/$libname.def~$echo " SINGLE NONSHARED" >> $output_objdir/$libname.def~$echo EXPORTS >> $output_objdir/$libname.def~emxexp $libobjs >> $output_objdir/$libname.def~$CC -Zdll -Zcrtdll -o $lib $libobjs $deplibs $compiler_flags $output_objdir/$libname.def' + old_archive_From_new_cmds_GCJ='emximp -o $output_objdir/$libname.a $output_objdir/$libname.def' + ;; + + osf3*) + if test "$GCC" = yes; then + allow_undefined_flag_GCJ=' ${wl}-expect_unresolved ${wl}\*' + archive_cmds_GCJ='$CC -shared${allow_undefined_flag} $libobjs $deplibs $compiler_flags ${wl}-soname ${wl}$soname `test -n "$verstring" && echo ${wl}-set_version ${wl}$verstring` ${wl}-update_registry ${wl}${output_objdir}/so_locations -o $lib' + else + allow_undefined_flag_GCJ=' -expect_unresolved \*' + archive_cmds_GCJ='$LD -shared${allow_undefined_flag} $libobjs $deplibs $linker_flags -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${output_objdir}/so_locations -o $lib' + fi + hardcode_libdir_flag_spec_GCJ='${wl}-rpath ${wl}$libdir' + hardcode_libdir_separator_GCJ=: + ;; + + osf4* | osf5*) # as osf3* with the addition of -msym flag + if test "$GCC" = yes; then + allow_undefined_flag_GCJ=' ${wl}-expect_unresolved ${wl}\*' + archive_cmds_GCJ='$CC -shared${allow_undefined_flag} $libobjs $deplibs $compiler_flags ${wl}-msym ${wl}-soname ${wl}$soname `test -n "$verstring" && echo ${wl}-set_version ${wl}$verstring` ${wl}-update_registry ${wl}${output_objdir}/so_locations -o $lib' + hardcode_libdir_flag_spec_GCJ='${wl}-rpath ${wl}$libdir' + else + allow_undefined_flag_GCJ=' -expect_unresolved \*' + archive_cmds_GCJ='$LD -shared${allow_undefined_flag} $libobjs $deplibs $linker_flags -msym -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${output_objdir}/so_locations -o $lib' + archive_expsym_cmds_GCJ='for i in `cat $export_symbols`; do printf "%s %s\\n" -exported_symbol "\$i" >> $lib.exp; done; echo "-hidden">> $lib.exp~ + $LD -shared${allow_undefined_flag} -input $lib.exp $linker_flags $libobjs $deplibs -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${output_objdir}/so_locations -o $lib~$rm $lib.exp' + + # Both c and cxx compiler support -rpath directly + hardcode_libdir_flag_spec_GCJ='-rpath $libdir' + fi + hardcode_libdir_separator_GCJ=: + ;; + + solaris*) + no_undefined_flag_GCJ=' -z text' + if test "$GCC" = yes; then + wlarc='${wl}' + archive_cmds_GCJ='$CC -shared ${wl}-h ${wl}$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds_GCJ='$echo "{ global:" > $lib.exp~cat $export_symbols | $SED -e "s/\(.*\)/\1;/" >> $lib.exp~$echo "local: *; };" >> $lib.exp~ + $CC -shared ${wl}-M ${wl}$lib.exp ${wl}-h ${wl}$soname -o $lib $libobjs $deplibs $compiler_flags~$rm $lib.exp' + else + wlarc='' + archive_cmds_GCJ='$LD -G${allow_undefined_flag} -h $soname -o $lib $libobjs $deplibs $linker_flags' + archive_expsym_cmds_GCJ='$echo "{ global:" > $lib.exp~cat $export_symbols | $SED -e "s/\(.*\)/\1;/" >> $lib.exp~$echo "local: *; };" >> $lib.exp~ + $LD -G${allow_undefined_flag} -M $lib.exp -h $soname -o $lib $libobjs $deplibs $linker_flags~$rm $lib.exp' + fi + hardcode_libdir_flag_spec_GCJ='-R$libdir' + hardcode_shlibpath_var_GCJ=no + case $host_os in + solaris2.[0-5] | solaris2.[0-5].*) ;; + *) + # The compiler driver will combine linker options so we + # cannot just pass the convience library names through + # without $wl, iff we do not link with $LD. + # Luckily, gcc supports the same syntax we need for Sun Studio. + # Supported since Solaris 2.6 (maybe 2.5.1?) + case $wlarc in + '') + whole_archive_flag_spec_GCJ='-z allextract$convenience -z defaultextract' ;; + *) + whole_archive_flag_spec_GCJ='${wl}-z ${wl}allextract`for conv in $convenience\"\"; do test -n \"$conv\" && new_convenience=\"$new_convenience,$conv\"; done; $echo \"$new_convenience\"` ${wl}-z ${wl}defaultextract' ;; + esac ;; + esac + link_all_deplibs_GCJ=yes + ;; + + sunos4*) + if test "x$host_vendor" = xsequent; then + # Use $CC to link under sequent, because it throws in some extra .o + # files that make .init and .fini sections work. + archive_cmds_GCJ='$CC -G ${wl}-h $soname -o $lib $libobjs $deplibs $compiler_flags' + else + archive_cmds_GCJ='$LD -assert pure-text -Bstatic -o $lib $libobjs $deplibs $linker_flags' + fi + hardcode_libdir_flag_spec_GCJ='-L$libdir' + hardcode_direct_GCJ=yes + hardcode_minus_L_GCJ=yes + hardcode_shlibpath_var_GCJ=no + ;; + + sysv4) + case $host_vendor in + sni) + archive_cmds_GCJ='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_direct_GCJ=yes # is this really true??? + ;; + siemens) + ## LD is ld it makes a PLAMLIB + ## CC just makes a GrossModule. + archive_cmds_GCJ='$LD -G -o $lib $libobjs $deplibs $linker_flags' + reload_cmds_GCJ='$CC -r -o $output$reload_objs' + hardcode_direct_GCJ=no + ;; + motorola) + archive_cmds_GCJ='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_direct_GCJ=no #Motorola manual says yes, but my tests say they lie + ;; + esac + runpath_var='LD_RUN_PATH' + hardcode_shlibpath_var_GCJ=no + ;; + + sysv4.3*) + archive_cmds_GCJ='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_shlibpath_var_GCJ=no + export_dynamic_flag_spec_GCJ='-Bexport' + ;; + + sysv4*MP*) + if test -d /usr/nec; then + archive_cmds_GCJ='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_shlibpath_var_GCJ=no + runpath_var=LD_RUN_PATH + hardcode_runpath_var=yes + ld_shlibs_GCJ=yes + fi + ;; + + sysv4*uw2* | sysv5OpenUNIX* | sysv5UnixWare7.[01].[10]* | unixware7*) + no_undefined_flag_GCJ='${wl}-z,text' + archive_cmds_need_lc_GCJ=no + hardcode_shlibpath_var_GCJ=no + runpath_var='LD_RUN_PATH' + + if test "$GCC" = yes; then + archive_cmds_GCJ='$CC -shared ${wl}-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds_GCJ='$CC -shared ${wl}-Bexport:$export_symbols ${wl}-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + else + archive_cmds_GCJ='$CC -G ${wl}-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds_GCJ='$CC -G ${wl}-Bexport:$export_symbols ${wl}-h,$soname -o $lib $libobjs $deplibs $compiler_flags' + fi + ;; + + sysv5* | sco3.2v5* | sco5v6*) + # Note: We can NOT use -z defs as we might desire, because we do not + # link with -lc, and that would cause any symbols used from libc to + # always be unresolved, which means just about no library would + # ever link correctly. If we're not using GNU ld we use -z text + # though, which does catch some bad symbols but isn't as heavy-handed + # as -z defs. + no_undefined_flag_GCJ='${wl}-z,text' + allow_undefined_flag_GCJ='${wl}-z,nodefs' + archive_cmds_need_lc_GCJ=no + hardcode_shlibpath_var_GCJ=no + hardcode_libdir_flag_spec_GCJ='`test -z "$SCOABSPATH" && echo ${wl}-R,$libdir`' + hardcode_libdir_separator_GCJ=':' + link_all_deplibs_GCJ=yes + export_dynamic_flag_spec_GCJ='${wl}-Bexport' + runpath_var='LD_RUN_PATH' + + if test "$GCC" = yes; then + archive_cmds_GCJ='$CC -shared ${wl}-h,\${SCOABSPATH:+${install_libdir}/}$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds_GCJ='$CC -shared ${wl}-Bexport:$export_symbols ${wl}-h,\${SCOABSPATH:+${install_libdir}/}$soname -o $lib $libobjs $deplibs $compiler_flags' + else + archive_cmds_GCJ='$CC -G ${wl}-h,\${SCOABSPATH:+${install_libdir}/}$soname -o $lib $libobjs $deplibs $compiler_flags' + archive_expsym_cmds_GCJ='$CC -G ${wl}-Bexport:$export_symbols ${wl}-h,\${SCOABSPATH:+${install_libdir}/}$soname -o $lib $libobjs $deplibs $compiler_flags' + fi + ;; + + uts4*) + archive_cmds_GCJ='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' + hardcode_libdir_flag_spec_GCJ='-L$libdir' + hardcode_shlibpath_var_GCJ=no + ;; + + *) + ld_shlibs_GCJ=no + ;; + esac + fi + +echo "$as_me:$LINENO: result: $ld_shlibs_GCJ" >&5 +echo "${ECHO_T}$ld_shlibs_GCJ" >&6 +test "$ld_shlibs_GCJ" = no && can_build_shared=no + +# +# Do we need to explicitly link libc? +# +case "x$archive_cmds_need_lc_GCJ" in +x|xyes) + # Assume -lc should be added + archive_cmds_need_lc_GCJ=yes + + if test "$enable_shared" = yes && test "$GCC" = yes; then + case $archive_cmds_GCJ in + *'~'*) + # FIXME: we may have to deal with multi-command sequences. + ;; + '$CC '*) + # Test whether the compiler implicitly links with -lc since on some + # systems, -lgcc has to come before -lc. If gcc already passes -lc + # to ld, don't add -lc before -lgcc. + echo "$as_me:$LINENO: checking whether -lc should be explicitly linked in" >&5 +echo $ECHO_N "checking whether -lc should be explicitly linked in... $ECHO_C" >&6 + $rm conftest* + printf "$lt_simple_compile_test_code" > conftest.$ac_ext + + if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } 2>conftest.err; then + soname=conftest + lib=conftest + libobjs=conftest.$ac_objext + deplibs= + wl=$lt_prog_compiler_wl_GCJ + pic_flag=$lt_prog_compiler_pic_GCJ + compiler_flags=-v + linker_flags=-v + verstring= + output_objdir=. + libname=conftest + lt_save_allow_undefined_flag=$allow_undefined_flag_GCJ + allow_undefined_flag_GCJ= + if { (eval echo "$as_me:$LINENO: \"$archive_cmds_GCJ 2\>\&1 \| grep \" -lc \" \>/dev/null 2\>\&1\"") >&5 + (eval $archive_cmds_GCJ 2\>\&1 \| grep \" -lc \" \>/dev/null 2\>\&1) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } + then + archive_cmds_need_lc_GCJ=no + else + archive_cmds_need_lc_GCJ=yes + fi + allow_undefined_flag_GCJ=$lt_save_allow_undefined_flag + else + cat conftest.err 1>&5 + fi + $rm conftest* + echo "$as_me:$LINENO: result: $archive_cmds_need_lc_GCJ" >&5 +echo "${ECHO_T}$archive_cmds_need_lc_GCJ" >&6 + ;; + esac + fi + ;; +esac + +echo "$as_me:$LINENO: checking dynamic linker characteristics" >&5 +echo $ECHO_N "checking dynamic linker characteristics... $ECHO_C" >&6 +library_names_spec= +libname_spec='lib$name' +soname_spec= +shrext_cmds=".so" +postinstall_cmds= +postuninstall_cmds= +finish_cmds= +finish_eval= +shlibpath_var= +shlibpath_overrides_runpath=unknown +version_type=none +dynamic_linker="$host_os ld.so" +sys_lib_dlsearch_path_spec="/lib /usr/lib" +if test "$GCC" = yes; then + sys_lib_search_path_spec=`$CC -print-search-dirs | grep "^libraries:" | $SED -e "s/^libraries://" -e "s,=/,/,g"` + if echo "$sys_lib_search_path_spec" | grep ';' >/dev/null ; then + # if the path contains ";" then we assume it to be the separator + # otherwise default to the standard path separator (i.e. ":") - it is + # assumed that no part of a normal pathname contains ";" but that should + # okay in the real world where ";" in dirpaths is itself problematic. + sys_lib_search_path_spec=`echo "$sys_lib_search_path_spec" | $SED -e 's/;/ /g'` + else + sys_lib_search_path_spec=`echo "$sys_lib_search_path_spec" | $SED -e "s/$PATH_SEPARATOR/ /g"` + fi +else + sys_lib_search_path_spec="/lib /usr/lib /usr/local/lib" +fi +need_lib_prefix=unknown +hardcode_into_libs=no + +# when you set need_version to no, make sure it does not cause -set_version +# flags to be left without arguments +need_version=unknown + +case $host_os in +aix3*) + version_type=linux + library_names_spec='${libname}${release}${shared_ext}$versuffix $libname.a' + shlibpath_var=LIBPATH + + # AIX 3 has no versioning support, so we append a major version to the name. + soname_spec='${libname}${release}${shared_ext}$major' + ;; + +aix4* | aix5*) + version_type=linux + need_lib_prefix=no + need_version=no + hardcode_into_libs=yes + if test "$host_cpu" = ia64; then + # AIX 5 supports IA64 + library_names_spec='${libname}${release}${shared_ext}$major ${libname}${release}${shared_ext}$versuffix $libname${shared_ext}' + shlibpath_var=LD_LIBRARY_PATH + else + # With GCC up to 2.95.x, collect2 would create an import file + # for dependence libraries. The import file would start with + # the line `#! .'. This would cause the generated library to + # depend on `.', always an invalid library. This was fixed in + # development snapshots of GCC prior to 3.0. + case $host_os in + aix4 | aix4.[01] | aix4.[01].*) + if { echo '#if __GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 97)' + echo ' yes ' + echo '#endif'; } | ${CC} -E - | grep yes > /dev/null; then + : + else + can_build_shared=no + fi + ;; + esac + # AIX (on Power*) has no versioning support, so currently we can not hardcode correct + # soname into executable. Probably we can add versioning support to + # collect2, so additional links can be useful in future. + if test "$aix_use_runtimelinking" = yes; then + # If using run time linking (on AIX 4.2 or later) use lib.so + # instead of lib.a to let people know that these are not + # typical AIX shared libraries. + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + else + # We preserve .a as extension for shared libraries through AIX4.2 + # and later when we are not doing run time linking. + library_names_spec='${libname}${release}.a $libname.a' + soname_spec='${libname}${release}${shared_ext}$major' + fi + shlibpath_var=LIBPATH + fi + ;; + +amigaos*) + library_names_spec='$libname.ixlibrary $libname.a' + # Create ${libname}_ixlibrary.a entries in /sys/libs. + finish_eval='for lib in `ls $libdir/*.ixlibrary 2>/dev/null`; do libname=`$echo "X$lib" | $Xsed -e '\''s%^.*/\([^/]*\)\.ixlibrary$%\1%'\''`; test $rm /sys/libs/${libname}_ixlibrary.a; $show "cd /sys/libs && $LN_S $lib ${libname}_ixlibrary.a"; cd /sys/libs && $LN_S $lib ${libname}_ixlibrary.a || exit 1; done' + ;; + +beos*) + library_names_spec='${libname}${shared_ext}' + dynamic_linker="$host_os ld.so" + shlibpath_var=LIBRARY_PATH + ;; + +bsdi[45]*) + version_type=linux + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + finish_cmds='PATH="\$PATH:/sbin" ldconfig $libdir' + shlibpath_var=LD_LIBRARY_PATH + sys_lib_search_path_spec="/shlib /usr/lib /usr/X11/lib /usr/contrib/lib /lib /usr/local/lib" + sys_lib_dlsearch_path_spec="/shlib /usr/lib /usr/local/lib" + # the default ld.so.conf also contains /usr/contrib/lib and + # /usr/X11R6/lib (/usr/X11 is a link to /usr/X11R6), but let us allow + # libtool to hard-code these into programs + ;; + +cygwin* | mingw* | pw32*) + version_type=windows + shrext_cmds=".dll" + need_version=no + need_lib_prefix=no + + case $GCC,$host_os in + yes,cygwin* | yes,mingw* | yes,pw32*) + library_names_spec='$libname.dll.a' + # DLL is installed to $(libdir)/../bin by postinstall_cmds + postinstall_cmds='base_file=`basename \${file}`~ + dlpath=`$SHELL 2>&1 -c '\''. $dir/'\''\${base_file}'\''i;echo \$dlname'\''`~ + dldir=$destdir/`dirname \$dlpath`~ + test -d \$dldir || mkdir -p \$dldir~ + $install_prog $dir/$dlname \$dldir/$dlname~ + chmod a+x \$dldir/$dlname' + postuninstall_cmds='dldll=`$SHELL 2>&1 -c '\''. $file; echo \$dlname'\''`~ + dlpath=$dir/\$dldll~ + $rm \$dlpath' + shlibpath_overrides_runpath=yes + + case $host_os in + cygwin*) + # Cygwin DLLs use 'cyg' prefix rather than 'lib' + soname_spec='`echo ${libname} | sed -e 's/^lib/cyg/'``echo ${release} | $SED -e 's/[.]/-/g'`${versuffix}${shared_ext}' + sys_lib_search_path_spec="/usr/lib /lib/w32api /lib /usr/local/lib" + ;; + mingw*) + # MinGW DLLs use traditional 'lib' prefix + soname_spec='${libname}`echo ${release} | $SED -e 's/[.]/-/g'`${versuffix}${shared_ext}' + sys_lib_search_path_spec=`$CC -print-search-dirs | grep "^libraries:" | $SED -e "s/^libraries://" -e "s,=/,/,g"` + if echo "$sys_lib_search_path_spec" | grep ';[c-zC-Z]:/' >/dev/null; then + # It is most probably a Windows format PATH printed by + # mingw gcc, but we are running on Cygwin. Gcc prints its search + # path with ; separators, and with drive letters. We can handle the + # drive letters (cygwin fileutils understands them), so leave them, + # especially as we might pass files found there to a mingw objdump, + # which wouldn't understand a cygwinified path. Ahh. + sys_lib_search_path_spec=`echo "$sys_lib_search_path_spec" | $SED -e 's/;/ /g'` + else + sys_lib_search_path_spec=`echo "$sys_lib_search_path_spec" | $SED -e "s/$PATH_SEPARATOR/ /g"` + fi + ;; + pw32*) + # pw32 DLLs use 'pw' prefix rather than 'lib' + library_names_spec='`echo ${libname} | sed -e 's/^lib/pw/'``echo ${release} | $SED -e 's/[.]/-/g'`${versuffix}${shared_ext}' + ;; + esac + ;; + + linux*) + if $LD --help 2>&1 | egrep ': supported targets:.* elf' > /dev/null; then + archive_cmds='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' + supports_anon_versioning=no + case `$LD -v 2>/dev/null` in + *\ 01.* | *\ 2.[0-9].* | *\ 2.10.*) ;; # catch versions < 2.11 + *\ 2.11.93.0.2\ *) supports_anon_versioning=yes ;; # RH7.3 ... + *\ 2.11.92.0.12\ *) supports_anon_versioning=yes ;; # Mandrake 8.2 ... + *\ 2.11.*) ;; # other 2.11 versions + *) supports_anon_versioning=yes ;; + esac + if test $supports_anon_versioning = yes; then + archive_expsym_cmds='$echo "{ global:" > $output_objdir/$libname.ver~ +cat $export_symbols | sed -e "s/\(.*\)/\1;/" >> $output_objdir/$libname.ver~ +$echo "local: *; };" >> $output_objdir/$libname.ver~ + $CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-version-script ${wl}$output_objdir/$libname.ver -o $lib' + else + $archive_expsym_cmds="$archive_cmds" + fi + else + ld_shlibs=no + fi + ;; + + *) + library_names_spec='${libname}`echo ${release} | $SED -e 's/[.]/-/g'`${versuffix}${shared_ext} $libname.lib' + ;; + esac + dynamic_linker='Win32 ld.exe' + # FIXME: first we should search . and the directory the executable is in + shlibpath_var=PATH + ;; + +darwin* | rhapsody*) + dynamic_linker="$host_os dyld" + version_type=darwin + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${versuffix}$shared_ext ${libname}${release}${major}$shared_ext ${libname}$shared_ext' + soname_spec='${libname}${release}${major}$shared_ext' + shlibpath_overrides_runpath=yes + shlibpath_var=DYLD_LIBRARY_PATH + shrext_cmds='`test .$module = .yes && echo .so || echo .dylib`' + # Apple's gcc prints 'gcc -print-search-dirs' doesn't operate the same. + if test "$GCC" = yes; then + sys_lib_search_path_spec=`$CC -print-search-dirs | tr "\n" "$PATH_SEPARATOR" | sed -e 's/libraries:/@libraries:/' | tr "@" "\n" | grep "^libraries:" | sed -e "s/^libraries://" -e "s,=/,/,g" -e "s,$PATH_SEPARATOR, ,g" -e "s,.*,& /lib /usr/lib /usr/local/lib,g"` + else + sys_lib_search_path_spec='/lib /usr/lib /usr/local/lib' + fi + sys_lib_dlsearch_path_spec='/usr/local/lib /lib /usr/lib' + ;; + +dgux*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname$shared_ext' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + ;; + +freebsd1*) + dynamic_linker=no + ;; + +kfreebsd*-gnu) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + dynamic_linker='GNU ld.so' + ;; + +freebsd* | dragonfly*) + # DragonFly does not have aout. When/if they implement a new + # versioning mechanism, adjust this. + if test -x /usr/bin/objformat; then + objformat=`/usr/bin/objformat` + else + case $host_os in + freebsd[123]*) objformat=aout ;; + *) objformat=elf ;; + esac + fi + # Handle Gentoo/FreeBSD as it was Linux + case $host_vendor in + gentoo) + version_type=linux ;; + *) + version_type=freebsd-$objformat ;; + esac + + case $version_type in + freebsd-elf*) + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext} $libname${shared_ext}' + need_version=no + need_lib_prefix=no + ;; + freebsd-*) + library_names_spec='${libname}${release}${shared_ext}$versuffix $libname${shared_ext}$versuffix' + need_version=yes + ;; + linux) + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + need_lib_prefix=no + need_version=no + ;; + esac + shlibpath_var=LD_LIBRARY_PATH + case $host_os in + freebsd2*) + shlibpath_overrides_runpath=yes + ;; + freebsd3.[01]* | freebsdelf3.[01]*) + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + ;; + freebsd3.[2-9]* | freebsdelf3.[2-9]* | \ + freebsd4.[0-5] | freebsdelf4.[0-5] | freebsd4.1.1 | freebsdelf4.1.1) + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + ;; + freebsd*) # from 4.6 on + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + ;; + esac + ;; + +gnu*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}${major} ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + hardcode_into_libs=yes + ;; + +hpux9* | hpux10* | hpux11*) + # Give a soname corresponding to the major version so that dld.sl refuses to + # link against other versions. + version_type=sunos + need_lib_prefix=no + need_version=no + case $host_cpu in + ia64*) + shrext_cmds='.so' + hardcode_into_libs=yes + dynamic_linker="$host_os dld.so" + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes # Unless +noenvvar is specified. + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + if test "X$HPUX_IA64_MODE" = X32; then + sys_lib_search_path_spec="/usr/lib/hpux32 /usr/local/lib/hpux32 /usr/local/lib" + else + sys_lib_search_path_spec="/usr/lib/hpux64 /usr/local/lib/hpux64" + fi + sys_lib_dlsearch_path_spec=$sys_lib_search_path_spec + ;; + hppa*64*) + shrext_cmds='.sl' + hardcode_into_libs=yes + dynamic_linker="$host_os dld.sl" + shlibpath_var=LD_LIBRARY_PATH # How should we handle SHLIB_PATH + shlibpath_overrides_runpath=yes # Unless +noenvvar is specified. + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + sys_lib_search_path_spec="/usr/lib/pa20_64 /usr/ccs/lib/pa20_64" + sys_lib_dlsearch_path_spec=$sys_lib_search_path_spec + ;; + *) + shrext_cmds='.sl' + dynamic_linker="$host_os dld.sl" + shlibpath_var=SHLIB_PATH + shlibpath_overrides_runpath=no # +s is required to enable SHLIB_PATH + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + ;; + esac + # HP-UX runs *really* slowly unless shared libraries are mode 555. + postinstall_cmds='chmod 555 $lib' + ;; + +interix3*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + dynamic_linker='Interix 3.x ld.so.1 (PE, like ELF)' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + ;; + +irix5* | irix6* | nonstopux*) + case $host_os in + nonstopux*) version_type=nonstopux ;; + *) + if test "$lt_cv_prog_gnu_ld" = yes; then + version_type=linux + else + version_type=irix + fi ;; + esac + need_lib_prefix=no + need_version=no + soname_spec='${libname}${release}${shared_ext}$major' + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${release}${shared_ext} $libname${shared_ext}' + case $host_os in + irix5* | nonstopux*) + libsuff= shlibsuff= + ;; + *) + case $LD in # libtool.m4 will add one of these switches to LD + *-32|*"-32 "|*-melf32bsmip|*"-melf32bsmip ") + libsuff= shlibsuff= libmagic=32-bit;; + *-n32|*"-n32 "|*-melf32bmipn32|*"-melf32bmipn32 ") + libsuff=32 shlibsuff=N32 libmagic=N32;; + *-64|*"-64 "|*-melf64bmip|*"-melf64bmip ") + libsuff=64 shlibsuff=64 libmagic=64-bit;; + *) libsuff= shlibsuff= libmagic=never-match;; + esac + ;; + esac + shlibpath_var=LD_LIBRARY${shlibsuff}_PATH + shlibpath_overrides_runpath=no + sys_lib_search_path_spec="/usr/lib${libsuff} /lib${libsuff} /usr/local/lib${libsuff}" + sys_lib_dlsearch_path_spec="/usr/lib${libsuff} /lib${libsuff}" + hardcode_into_libs=yes + ;; + +# No shared lib support for Linux oldld, aout, or coff. +linux*oldld* | linux*aout* | linux*coff*) + dynamic_linker=no + ;; + +# This must be Linux ELF. +linux*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + finish_cmds='PATH="\$PATH:/sbin" ldconfig -n $libdir' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + # This implies no fast_install, which is unacceptable. + # Some rework will be needed to allow for fast_install + # before this can be enabled. + hardcode_into_libs=yes + + # Append ld.so.conf contents to the search path + if test -f /etc/ld.so.conf; then + lt_ld_extra=`awk '/^include / { system(sprintf("cd /etc; cat %s", \$2)); skip = 1; } { if (!skip) print \$0; skip = 0; }' < /etc/ld.so.conf | $SED -e 's/#.*//;s/[:, ]/ /g;s/=[^=]*$//;s/=[^= ]* / /g;/^$/d' | tr '\n' ' '` + sys_lib_dlsearch_path_spec="/lib /usr/lib $lt_ld_extra" + fi + + # We used to test for /lib/ld.so.1 and disable shared libraries on + # powerpc, because MkLinux only supported shared libraries with the + # GNU dynamic linker. Since this was broken with cross compilers, + # most powerpc-linux boxes support dynamic linking these days and + # people can always --disable-shared, the test was removed, and we + # assume the GNU/Linux dynamic linker is in use. + dynamic_linker='GNU/Linux ld.so' + ;; + +knetbsd*-gnu) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=no + hardcode_into_libs=yes + dynamic_linker='GNU ld.so' + ;; + +netbsd*) + version_type=sunos + need_lib_prefix=no + need_version=no + if echo __ELF__ | $CC -E - | grep __ELF__ >/dev/null; then + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${shared_ext}$versuffix' + finish_cmds='PATH="\$PATH:/sbin" ldconfig -m $libdir' + dynamic_linker='NetBSD (a.out) ld.so' + else + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major ${libname}${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + dynamic_linker='NetBSD ld.elf_so' + fi + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + ;; + +newsos6) + version_type=linux + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + ;; + +nto-qnx*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + ;; + +openbsd*) + version_type=sunos + sys_lib_dlsearch_path_spec="/usr/lib" + need_lib_prefix=no + # Some older versions of OpenBSD (3.3 at least) *do* need versioned libs. + case $host_os in + openbsd3.3 | openbsd3.3.*) need_version=yes ;; + *) need_version=no ;; + esac + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${shared_ext}$versuffix' + finish_cmds='PATH="\$PATH:/sbin" ldconfig -m $libdir' + shlibpath_var=LD_LIBRARY_PATH + if test -z "`echo __ELF__ | $CC -E - | grep __ELF__`" || test "$host_os-$host_cpu" = "openbsd2.8-powerpc"; then + case $host_os in + openbsd2.[89] | openbsd2.[89].*) + shlibpath_overrides_runpath=no + ;; + *) + shlibpath_overrides_runpath=yes + ;; + esac + else + shlibpath_overrides_runpath=yes + fi + ;; + +os2*) + libname_spec='$name' + shrext_cmds=".dll" + need_lib_prefix=no + library_names_spec='$libname${shared_ext} $libname.a' + dynamic_linker='OS/2 ld.exe' + shlibpath_var=LIBPATH + ;; + +osf3* | osf4* | osf5*) + version_type=osf + need_lib_prefix=no + need_version=no + soname_spec='${libname}${release}${shared_ext}$major' + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + shlibpath_var=LD_LIBRARY_PATH + sys_lib_search_path_spec="/usr/shlib /usr/ccs/lib /usr/lib/cmplrs/cc /usr/lib /usr/local/lib /var/shlib" + sys_lib_dlsearch_path_spec="$sys_lib_search_path_spec" + ;; + +solaris*) + version_type=linux + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + hardcode_into_libs=yes + # ldd complains unless libraries are executable + postinstall_cmds='chmod +x $lib' + ;; + +sunos4*) + version_type=sunos + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${shared_ext}$versuffix' + finish_cmds='PATH="\$PATH:/usr/etc" ldconfig $libdir' + shlibpath_var=LD_LIBRARY_PATH + shlibpath_overrides_runpath=yes + if test "$with_gnu_ld" = yes; then + need_lib_prefix=no + fi + need_version=yes + ;; + +sysv4 | sysv4.3*) + version_type=linux + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + case $host_vendor in + sni) + shlibpath_overrides_runpath=no + need_lib_prefix=no + export_dynamic_flag_spec='${wl}-Blargedynsym' + runpath_var=LD_RUN_PATH + ;; + siemens) + need_lib_prefix=no + ;; + motorola) + need_lib_prefix=no + need_version=no + shlibpath_overrides_runpath=no + sys_lib_search_path_spec='/lib /usr/lib /usr/ccs/lib' + ;; + esac + ;; + +sysv4*MP*) + if test -d /usr/nec ;then + version_type=linux + library_names_spec='$libname${shared_ext}.$versuffix $libname${shared_ext}.$major $libname${shared_ext}' + soname_spec='$libname${shared_ext}.$major' + shlibpath_var=LD_LIBRARY_PATH + fi + ;; + +sysv5* | sco3.2v5* | sco5v6* | unixware* | OpenUNIX* | sysv4*uw2*) + version_type=freebsd-elf + need_lib_prefix=no + need_version=no + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext} $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + hardcode_into_libs=yes + if test "$with_gnu_ld" = yes; then + sys_lib_search_path_spec='/usr/local/lib /usr/gnu/lib /usr/ccs/lib /usr/lib /lib' + shlibpath_overrides_runpath=no + else + sys_lib_search_path_spec='/usr/ccs/lib /usr/lib' + shlibpath_overrides_runpath=yes + case $host_os in + sco3.2v5*) + sys_lib_search_path_spec="$sys_lib_search_path_spec /lib" + ;; + esac + fi + sys_lib_dlsearch_path_spec='/usr/lib' + ;; + +uts4*) + version_type=linux + library_names_spec='${libname}${release}${shared_ext}$versuffix ${libname}${release}${shared_ext}$major $libname${shared_ext}' + soname_spec='${libname}${release}${shared_ext}$major' + shlibpath_var=LD_LIBRARY_PATH + ;; + +*) + dynamic_linker=no + ;; +esac +echo "$as_me:$LINENO: result: $dynamic_linker" >&5 +echo "${ECHO_T}$dynamic_linker" >&6 +test "$dynamic_linker" = no && can_build_shared=no + +variables_saved_for_relink="PATH $shlibpath_var $runpath_var" +if test "$GCC" = yes; then + variables_saved_for_relink="$variables_saved_for_relink GCC_EXEC_PREFIX COMPILER_PATH LIBRARY_PATH" +fi + +echo "$as_me:$LINENO: checking how to hardcode library paths into programs" >&5 +echo $ECHO_N "checking how to hardcode library paths into programs... $ECHO_C" >&6 +hardcode_action_GCJ= +if test -n "$hardcode_libdir_flag_spec_GCJ" || \ + test -n "$runpath_var_GCJ" || \ + test "X$hardcode_automatic_GCJ" = "Xyes" ; then + + # We can hardcode non-existant directories. + if test "$hardcode_direct_GCJ" != no && + # If the only mechanism to avoid hardcoding is shlibpath_var, we + # have to relink, otherwise we might link with an installed library + # when we should be linking with a yet-to-be-installed one + ## test "$_LT_AC_TAGVAR(hardcode_shlibpath_var, GCJ)" != no && + test "$hardcode_minus_L_GCJ" != no; then + # Linking always hardcodes the temporary library directory. + hardcode_action_GCJ=relink + else + # We can link without hardcoding, and we can hardcode nonexisting dirs. + hardcode_action_GCJ=immediate + fi +else + # We cannot hardcode anything, or else we can only hardcode existing + # directories. + hardcode_action_GCJ=unsupported +fi +echo "$as_me:$LINENO: result: $hardcode_action_GCJ" >&5 +echo "${ECHO_T}$hardcode_action_GCJ" >&6 + +if test "$hardcode_action_GCJ" = relink; then + # Fast installation is not supported + enable_fast_install=no +elif test "$shlibpath_overrides_runpath" = yes || + test "$enable_shared" = no; then + # Fast installation is not necessary + enable_fast_install=needless +fi + + +# The else clause should only fire when bootstrapping the +# libtool distribution, otherwise you forgot to ship ltmain.sh +# with your package, and you will get complaints that there are +# no rules to generate ltmain.sh. +if test -f "$ltmain"; then + # See if we are running on zsh, and set the options which allow our commands through + # without removal of \ escapes. + if test -n "${ZSH_VERSION+set}" ; then + setopt NO_GLOB_SUBST + fi + # Now quote all the things that may contain metacharacters while being + # careful not to overquote the AC_SUBSTed values. We take copies of the + # variables and quote the copies for generation of the libtool script. + for var in echo old_CC old_CFLAGS AR AR_FLAGS EGREP RANLIB LN_S LTCC LTCFLAGS NM \ + SED SHELL STRIP \ + libname_spec library_names_spec soname_spec extract_expsyms_cmds \ + old_striplib striplib file_magic_cmd finish_cmds finish_eval \ + deplibs_check_method reload_flag reload_cmds need_locks \ + lt_cv_sys_global_symbol_pipe lt_cv_sys_global_symbol_to_cdecl \ + lt_cv_sys_global_symbol_to_c_name_address \ + sys_lib_search_path_spec sys_lib_dlsearch_path_spec \ + old_postinstall_cmds old_postuninstall_cmds \ + compiler_GCJ \ + CC_GCJ \ + LD_GCJ \ + lt_prog_compiler_wl_GCJ \ + lt_prog_compiler_pic_GCJ \ + lt_prog_compiler_static_GCJ \ + lt_prog_compiler_no_builtin_flag_GCJ \ + export_dynamic_flag_spec_GCJ \ + thread_safe_flag_spec_GCJ \ + whole_archive_flag_spec_GCJ \ + enable_shared_with_static_runtimes_GCJ \ + old_archive_cmds_GCJ \ + old_archive_from_new_cmds_GCJ \ + predep_objects_GCJ \ + postdep_objects_GCJ \ + predeps_GCJ \ + postdeps_GCJ \ + compiler_lib_search_path_GCJ \ + archive_cmds_GCJ \ + archive_expsym_cmds_GCJ \ + postinstall_cmds_GCJ \ + postuninstall_cmds_GCJ \ + old_archive_from_expsyms_cmds_GCJ \ + allow_undefined_flag_GCJ \ + no_undefined_flag_GCJ \ + export_symbols_cmds_GCJ \ + hardcode_libdir_flag_spec_GCJ \ + hardcode_libdir_flag_spec_ld_GCJ \ + hardcode_libdir_separator_GCJ \ + hardcode_automatic_GCJ \ + module_cmds_GCJ \ + module_expsym_cmds_GCJ \ + lt_cv_prog_compiler_c_o_GCJ \ + exclude_expsyms_GCJ \ + include_expsyms_GCJ; do + + case $var in + old_archive_cmds_GCJ | \ + old_archive_from_new_cmds_GCJ | \ + archive_cmds_GCJ | \ + archive_expsym_cmds_GCJ | \ + module_cmds_GCJ | \ + module_expsym_cmds_GCJ | \ + old_archive_from_expsyms_cmds_GCJ | \ + export_symbols_cmds_GCJ | \ + extract_expsyms_cmds | reload_cmds | finish_cmds | \ + postinstall_cmds | postuninstall_cmds | \ + old_postinstall_cmds | old_postuninstall_cmds | \ + sys_lib_search_path_spec | sys_lib_dlsearch_path_spec) + # Double-quote double-evaled strings. + eval "lt_$var=\\\"\`\$echo \"X\$$var\" | \$Xsed -e \"\$double_quote_subst\" -e \"\$sed_quote_subst\" -e \"\$delay_variable_subst\"\`\\\"" + ;; + *) + eval "lt_$var=\\\"\`\$echo \"X\$$var\" | \$Xsed -e \"\$sed_quote_subst\"\`\\\"" + ;; + esac + done + + case $lt_echo in + *'\$0 --fallback-echo"') + lt_echo=`$echo "X$lt_echo" | $Xsed -e 's/\\\\\\\$0 --fallback-echo"$/$0 --fallback-echo"/'` + ;; + esac + +cfgfile="$ofile" + + cat <<__EOF__ >> "$cfgfile" +# ### BEGIN LIBTOOL TAG CONFIG: $tagname + +# Libtool was configured on host `(hostname || uname -n) 2>/dev/null | sed 1q`: + +# Shell to use when invoking shell scripts. +SHELL=$lt_SHELL + +# Whether or not to build shared libraries. +build_libtool_libs=$enable_shared + +# Whether or not to build static libraries. +build_old_libs=$enable_static + +# Whether or not to add -lc for building shared libraries. +build_libtool_need_lc=$archive_cmds_need_lc_GCJ + +# Whether or not to disallow shared libs when runtime libs are static +allow_libtool_libs_with_static_runtimes=$enable_shared_with_static_runtimes_GCJ + +# Whether or not to optimize for fast installation. +fast_install=$enable_fast_install + +# The host system. +host_alias=$host_alias +host=$host +host_os=$host_os + +# The build system. +build_alias=$build_alias +build=$build +build_os=$build_os + +# An echo program that does not interpret backslashes. +echo=$lt_echo + +# The archiver. +AR=$lt_AR +AR_FLAGS=$lt_AR_FLAGS + +# A C compiler. +LTCC=$lt_LTCC + +# LTCC compiler flags. +LTCFLAGS=$lt_LTCFLAGS + +# A language-specific compiler. +CC=$lt_compiler_GCJ + +# Is the compiler the GNU C compiler? +with_gcc=$GCC_GCJ + +# An ERE matcher. +EGREP=$lt_EGREP + +# The linker used to build libraries. +LD=$lt_LD_GCJ + +# Whether we need hard or soft links. +LN_S=$lt_LN_S + +# A BSD-compatible nm program. +NM=$lt_NM + +# A symbol stripping program +STRIP=$lt_STRIP + +# Used to examine libraries when file_magic_cmd begins "file" +MAGIC_CMD=$MAGIC_CMD + +# Used on cygwin: DLL creation program. +DLLTOOL="$DLLTOOL" + +# Used on cygwin: object dumper. +OBJDUMP="$OBJDUMP" + +# Used on cygwin: assembler. +AS="$AS" + +# The name of the directory that contains temporary libtool files. +objdir=$objdir + +# How to create reloadable object files. +reload_flag=$lt_reload_flag +reload_cmds=$lt_reload_cmds + +# How to pass a linker flag through the compiler. +wl=$lt_lt_prog_compiler_wl_GCJ + +# Object file suffix (normally "o"). +objext="$ac_objext" + +# Old archive suffix (normally "a"). +libext="$libext" + +# Shared library suffix (normally ".so"). +shrext_cmds='$shrext_cmds' + +# Executable file suffix (normally ""). +exeext="$exeext" + +# Additional compiler flags for building library objects. +pic_flag=$lt_lt_prog_compiler_pic_GCJ +pic_mode=$pic_mode + +# What is the maximum length of a command? +max_cmd_len=$lt_cv_sys_max_cmd_len + +# Does compiler simultaneously support -c and -o options? +compiler_c_o=$lt_lt_cv_prog_compiler_c_o_GCJ + +# Must we lock files when doing compilation? +need_locks=$lt_need_locks + +# Do we need the lib prefix for modules? +need_lib_prefix=$need_lib_prefix + +# Do we need a version for libraries? +need_version=$need_version + +# Whether dlopen is supported. +dlopen_support=$enable_dlopen + +# Whether dlopen of programs is supported. +dlopen_self=$enable_dlopen_self + +# Whether dlopen of statically linked programs is supported. +dlopen_self_static=$enable_dlopen_self_static + +# Compiler flag to prevent dynamic linking. +link_static_flag=$lt_lt_prog_compiler_static_GCJ + +# Compiler flag to turn off builtin functions. +no_builtin_flag=$lt_lt_prog_compiler_no_builtin_flag_GCJ + +# Compiler flag to allow reflexive dlopens. +export_dynamic_flag_spec=$lt_export_dynamic_flag_spec_GCJ + +# Compiler flag to generate shared objects directly from archives. +whole_archive_flag_spec=$lt_whole_archive_flag_spec_GCJ + +# Compiler flag to generate thread-safe objects. +thread_safe_flag_spec=$lt_thread_safe_flag_spec_GCJ + +# Library versioning type. +version_type=$version_type + +# Format of library name prefix. +libname_spec=$lt_libname_spec + +# List of archive names. First name is the real one, the rest are links. +# The last name is the one that the linker finds with -lNAME. +library_names_spec=$lt_library_names_spec + +# The coded name of the library, if different from the real name. +soname_spec=$lt_soname_spec + +# Commands used to build and install an old-style archive. +RANLIB=$lt_RANLIB +old_archive_cmds=$lt_old_archive_cmds_GCJ +old_postinstall_cmds=$lt_old_postinstall_cmds +old_postuninstall_cmds=$lt_old_postuninstall_cmds + +# Create an old-style archive from a shared archive. +old_archive_from_new_cmds=$lt_old_archive_from_new_cmds_GCJ + +# Create a temporary old-style archive to link instead of a shared archive. +old_archive_from_expsyms_cmds=$lt_old_archive_from_expsyms_cmds_GCJ + +# Commands used to build and install a shared archive. +archive_cmds=$lt_archive_cmds_GCJ +archive_expsym_cmds=$lt_archive_expsym_cmds_GCJ +postinstall_cmds=$lt_postinstall_cmds +postuninstall_cmds=$lt_postuninstall_cmds + +# Commands used to build a loadable module (assumed same as above if empty) +module_cmds=$lt_module_cmds_GCJ +module_expsym_cmds=$lt_module_expsym_cmds_GCJ + +# Commands to strip libraries. +old_striplib=$lt_old_striplib +striplib=$lt_striplib + +# Dependencies to place before the objects being linked to create a +# shared library. +predep_objects=$lt_predep_objects_GCJ + +# Dependencies to place after the objects being linked to create a +# shared library. +postdep_objects=$lt_postdep_objects_GCJ + +# Dependencies to place before the objects being linked to create a +# shared library. +predeps=$lt_predeps_GCJ + +# Dependencies to place after the objects being linked to create a +# shared library. +postdeps=$lt_postdeps_GCJ + +# The library search path used internally by the compiler when linking +# a shared library. +compiler_lib_search_path=$lt_compiler_lib_search_path_GCJ + +# Method to check whether dependent libraries are shared objects. +deplibs_check_method=$lt_deplibs_check_method + +# Command to use when deplibs_check_method == file_magic. +file_magic_cmd=$lt_file_magic_cmd + +# Flag that allows shared libraries with undefined symbols to be built. +allow_undefined_flag=$lt_allow_undefined_flag_GCJ + +# Flag that forces no undefined symbols. +no_undefined_flag=$lt_no_undefined_flag_GCJ + +# Commands used to finish a libtool library installation in a directory. +finish_cmds=$lt_finish_cmds + +# Same as above, but a single script fragment to be evaled but not shown. +finish_eval=$lt_finish_eval + +# Take the output of nm and produce a listing of raw symbols and C names. +global_symbol_pipe=$lt_lt_cv_sys_global_symbol_pipe + +# Transform the output of nm in a proper C declaration +global_symbol_to_cdecl=$lt_lt_cv_sys_global_symbol_to_cdecl + +# Transform the output of nm in a C name address pair +global_symbol_to_c_name_address=$lt_lt_cv_sys_global_symbol_to_c_name_address + +# This is the shared library runtime path variable. +runpath_var=$runpath_var + +# This is the shared library path variable. +shlibpath_var=$shlibpath_var + +# Is shlibpath searched before the hard-coded library search path? +shlibpath_overrides_runpath=$shlibpath_overrides_runpath + +# How to hardcode a shared library path into an executable. +hardcode_action=$hardcode_action_GCJ + +# Whether we should hardcode library paths into libraries. +hardcode_into_libs=$hardcode_into_libs + +# Flag to hardcode \$libdir into a binary during linking. +# This must work even if \$libdir does not exist. +hardcode_libdir_flag_spec=$lt_hardcode_libdir_flag_spec_GCJ + +# If ld is used when linking, flag to hardcode \$libdir into +# a binary during linking. This must work even if \$libdir does +# not exist. +hardcode_libdir_flag_spec_ld=$lt_hardcode_libdir_flag_spec_ld_GCJ + +# Whether we need a single -rpath flag with a separated argument. +hardcode_libdir_separator=$lt_hardcode_libdir_separator_GCJ + +# Set to yes if using DIR/libNAME${shared_ext} during linking hardcodes DIR into the +# resulting binary. +hardcode_direct=$hardcode_direct_GCJ + +# Set to yes if using the -LDIR flag during linking hardcodes DIR into the +# resulting binary. +hardcode_minus_L=$hardcode_minus_L_GCJ + +# Set to yes if using SHLIBPATH_VAR=DIR during linking hardcodes DIR into +# the resulting binary. +hardcode_shlibpath_var=$hardcode_shlibpath_var_GCJ + +# Set to yes if building a shared library automatically hardcodes DIR into the library +# and all subsequent libraries and executables linked against it. +hardcode_automatic=$hardcode_automatic_GCJ + +# Variables whose values should be saved in libtool wrapper scripts and +# restored at relink time. +variables_saved_for_relink="$variables_saved_for_relink" + +# Whether libtool must link a program against all its dependency libraries. +link_all_deplibs=$link_all_deplibs_GCJ + +# Compile-time system search path for libraries +sys_lib_search_path_spec=$lt_sys_lib_search_path_spec + +# Run-time system search path for libraries +sys_lib_dlsearch_path_spec=$lt_sys_lib_dlsearch_path_spec + +# Fix the shell variable \$srcfile for the compiler. +fix_srcfile_path="$fix_srcfile_path_GCJ" + +# Set to yes if exported symbols are required. +always_export_symbols=$always_export_symbols_GCJ + +# The commands to list exported symbols. +export_symbols_cmds=$lt_export_symbols_cmds_GCJ + +# The commands to extract the exported symbol list from a shared archive. +extract_expsyms_cmds=$lt_extract_expsyms_cmds + +# Symbols that should not be listed in the preloaded symbols. +exclude_expsyms=$lt_exclude_expsyms_GCJ + +# Symbols that must always be exported. +include_expsyms=$lt_include_expsyms_GCJ + +# ### END LIBTOOL TAG CONFIG: $tagname + +__EOF__ + + +else + # If there is no Makefile yet, we rely on a make rule to execute + # `config.status --recheck' to rerun these tests and create the + # libtool script then. + ltmain_in=`echo $ltmain | sed -e 's/\.sh$/.in/'` + if test -f "$ltmain_in"; then + test -f Makefile && make "$ltmain" + fi +fi + + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + +CC="$lt_save_CC" + + else + tagname="" + fi + ;; + + RC) + + + +# Source file extension for RC test sources. +ac_ext=rc + +# Object file extension for compiled RC test sources. +objext=o +objext_RC=$objext + +# Code to be used in simple compile tests +lt_simple_compile_test_code='sample MENU { MENUITEM "&Soup", 100, CHECKED }\n' + +# Code to be used in simple link tests +lt_simple_link_test_code="$lt_simple_compile_test_code" + +# ltmain only uses $CC for tagged configurations so make sure $CC is set. + +# If no C compiler was specified, use CC. +LTCC=${LTCC-"$CC"} + +# If no C compiler flags were specified, use CFLAGS. +LTCFLAGS=${LTCFLAGS-"$CFLAGS"} + +# Allow CC to be a program name with arguments. +compiler=$CC + + +# save warnings/boilerplate of simple test code +ac_outfile=conftest.$ac_objext +printf "$lt_simple_compile_test_code" >conftest.$ac_ext +eval "$ac_compile" 2>&1 >/dev/null | $SED '/^$/d; /^ *+/d' >conftest.err +_lt_compiler_boilerplate=`cat conftest.err` +$rm conftest* + +ac_outfile=conftest.$ac_objext +printf "$lt_simple_link_test_code" >conftest.$ac_ext +eval "$ac_link" 2>&1 >/dev/null | $SED '/^$/d; /^ *+/d' >conftest.err +_lt_linker_boilerplate=`cat conftest.err` +$rm conftest* + + +# Allow CC to be a program name with arguments. +lt_save_CC="$CC" +CC=${RC-"windres"} +compiler=$CC +compiler_RC=$CC +for cc_temp in $compiler""; do + case $cc_temp in + compile | *[\\/]compile | ccache | *[\\/]ccache ) ;; + distcc | *[\\/]distcc | purify | *[\\/]purify ) ;; + \-*) ;; + *) break;; + esac +done +cc_basename=`$echo "X$cc_temp" | $Xsed -e 's%.*/%%' -e "s%^$host_alias-%%"` + +lt_cv_prog_compiler_c_o_RC=yes + +# The else clause should only fire when bootstrapping the +# libtool distribution, otherwise you forgot to ship ltmain.sh +# with your package, and you will get complaints that there are +# no rules to generate ltmain.sh. +if test -f "$ltmain"; then + # See if we are running on zsh, and set the options which allow our commands through + # without removal of \ escapes. + if test -n "${ZSH_VERSION+set}" ; then + setopt NO_GLOB_SUBST + fi + # Now quote all the things that may contain metacharacters while being + # careful not to overquote the AC_SUBSTed values. We take copies of the + # variables and quote the copies for generation of the libtool script. + for var in echo old_CC old_CFLAGS AR AR_FLAGS EGREP RANLIB LN_S LTCC LTCFLAGS NM \ + SED SHELL STRIP \ + libname_spec library_names_spec soname_spec extract_expsyms_cmds \ + old_striplib striplib file_magic_cmd finish_cmds finish_eval \ + deplibs_check_method reload_flag reload_cmds need_locks \ + lt_cv_sys_global_symbol_pipe lt_cv_sys_global_symbol_to_cdecl \ + lt_cv_sys_global_symbol_to_c_name_address \ + sys_lib_search_path_spec sys_lib_dlsearch_path_spec \ + old_postinstall_cmds old_postuninstall_cmds \ + compiler_RC \ + CC_RC \ + LD_RC \ + lt_prog_compiler_wl_RC \ + lt_prog_compiler_pic_RC \ + lt_prog_compiler_static_RC \ + lt_prog_compiler_no_builtin_flag_RC \ + export_dynamic_flag_spec_RC \ + thread_safe_flag_spec_RC \ + whole_archive_flag_spec_RC \ + enable_shared_with_static_runtimes_RC \ + old_archive_cmds_RC \ + old_archive_from_new_cmds_RC \ + predep_objects_RC \ + postdep_objects_RC \ + predeps_RC \ + postdeps_RC \ + compiler_lib_search_path_RC \ + archive_cmds_RC \ + archive_expsym_cmds_RC \ + postinstall_cmds_RC \ + postuninstall_cmds_RC \ + old_archive_from_expsyms_cmds_RC \ + allow_undefined_flag_RC \ + no_undefined_flag_RC \ + export_symbols_cmds_RC \ + hardcode_libdir_flag_spec_RC \ + hardcode_libdir_flag_spec_ld_RC \ + hardcode_libdir_separator_RC \ + hardcode_automatic_RC \ + module_cmds_RC \ + module_expsym_cmds_RC \ + lt_cv_prog_compiler_c_o_RC \ + exclude_expsyms_RC \ + include_expsyms_RC; do + + case $var in + old_archive_cmds_RC | \ + old_archive_from_new_cmds_RC | \ + archive_cmds_RC | \ + archive_expsym_cmds_RC | \ + module_cmds_RC | \ + module_expsym_cmds_RC | \ + old_archive_from_expsyms_cmds_RC | \ + export_symbols_cmds_RC | \ + extract_expsyms_cmds | reload_cmds | finish_cmds | \ + postinstall_cmds | postuninstall_cmds | \ + old_postinstall_cmds | old_postuninstall_cmds | \ + sys_lib_search_path_spec | sys_lib_dlsearch_path_spec) + # Double-quote double-evaled strings. + eval "lt_$var=\\\"\`\$echo \"X\$$var\" | \$Xsed -e \"\$double_quote_subst\" -e \"\$sed_quote_subst\" -e \"\$delay_variable_subst\"\`\\\"" + ;; + *) + eval "lt_$var=\\\"\`\$echo \"X\$$var\" | \$Xsed -e \"\$sed_quote_subst\"\`\\\"" + ;; + esac + done + + case $lt_echo in + *'\$0 --fallback-echo"') + lt_echo=`$echo "X$lt_echo" | $Xsed -e 's/\\\\\\\$0 --fallback-echo"$/$0 --fallback-echo"/'` + ;; + esac + +cfgfile="$ofile" + + cat <<__EOF__ >> "$cfgfile" +# ### BEGIN LIBTOOL TAG CONFIG: $tagname + +# Libtool was configured on host `(hostname || uname -n) 2>/dev/null | sed 1q`: + +# Shell to use when invoking shell scripts. +SHELL=$lt_SHELL + +# Whether or not to build shared libraries. +build_libtool_libs=$enable_shared + +# Whether or not to build static libraries. +build_old_libs=$enable_static + +# Whether or not to add -lc for building shared libraries. +build_libtool_need_lc=$archive_cmds_need_lc_RC + +# Whether or not to disallow shared libs when runtime libs are static +allow_libtool_libs_with_static_runtimes=$enable_shared_with_static_runtimes_RC + +# Whether or not to optimize for fast installation. +fast_install=$enable_fast_install + +# The host system. +host_alias=$host_alias +host=$host +host_os=$host_os + +# The build system. +build_alias=$build_alias +build=$build +build_os=$build_os + +# An echo program that does not interpret backslashes. +echo=$lt_echo + +# The archiver. +AR=$lt_AR +AR_FLAGS=$lt_AR_FLAGS + +# A C compiler. +LTCC=$lt_LTCC + +# LTCC compiler flags. +LTCFLAGS=$lt_LTCFLAGS + +# A language-specific compiler. +CC=$lt_compiler_RC + +# Is the compiler the GNU C compiler? +with_gcc=$GCC_RC + +# An ERE matcher. +EGREP=$lt_EGREP + +# The linker used to build libraries. +LD=$lt_LD_RC + +# Whether we need hard or soft links. +LN_S=$lt_LN_S + +# A BSD-compatible nm program. +NM=$lt_NM + +# A symbol stripping program +STRIP=$lt_STRIP + +# Used to examine libraries when file_magic_cmd begins "file" +MAGIC_CMD=$MAGIC_CMD + +# Used on cygwin: DLL creation program. +DLLTOOL="$DLLTOOL" + +# Used on cygwin: object dumper. +OBJDUMP="$OBJDUMP" + +# Used on cygwin: assembler. +AS="$AS" + +# The name of the directory that contains temporary libtool files. +objdir=$objdir + +# How to create reloadable object files. +reload_flag=$lt_reload_flag +reload_cmds=$lt_reload_cmds + +# How to pass a linker flag through the compiler. +wl=$lt_lt_prog_compiler_wl_RC + +# Object file suffix (normally "o"). +objext="$ac_objext" + +# Old archive suffix (normally "a"). +libext="$libext" + +# Shared library suffix (normally ".so"). +shrext_cmds='$shrext_cmds' + +# Executable file suffix (normally ""). +exeext="$exeext" + +# Additional compiler flags for building library objects. +pic_flag=$lt_lt_prog_compiler_pic_RC +pic_mode=$pic_mode + +# What is the maximum length of a command? +max_cmd_len=$lt_cv_sys_max_cmd_len + +# Does compiler simultaneously support -c and -o options? +compiler_c_o=$lt_lt_cv_prog_compiler_c_o_RC + +# Must we lock files when doing compilation? +need_locks=$lt_need_locks + +# Do we need the lib prefix for modules? +need_lib_prefix=$need_lib_prefix + +# Do we need a version for libraries? +need_version=$need_version + +# Whether dlopen is supported. +dlopen_support=$enable_dlopen + +# Whether dlopen of programs is supported. +dlopen_self=$enable_dlopen_self + +# Whether dlopen of statically linked programs is supported. +dlopen_self_static=$enable_dlopen_self_static + +# Compiler flag to prevent dynamic linking. +link_static_flag=$lt_lt_prog_compiler_static_RC + +# Compiler flag to turn off builtin functions. +no_builtin_flag=$lt_lt_prog_compiler_no_builtin_flag_RC + +# Compiler flag to allow reflexive dlopens. +export_dynamic_flag_spec=$lt_export_dynamic_flag_spec_RC + +# Compiler flag to generate shared objects directly from archives. +whole_archive_flag_spec=$lt_whole_archive_flag_spec_RC + +# Compiler flag to generate thread-safe objects. +thread_safe_flag_spec=$lt_thread_safe_flag_spec_RC + +# Library versioning type. +version_type=$version_type + +# Format of library name prefix. +libname_spec=$lt_libname_spec + +# List of archive names. First name is the real one, the rest are links. +# The last name is the one that the linker finds with -lNAME. +library_names_spec=$lt_library_names_spec + +# The coded name of the library, if different from the real name. +soname_spec=$lt_soname_spec + +# Commands used to build and install an old-style archive. +RANLIB=$lt_RANLIB +old_archive_cmds=$lt_old_archive_cmds_RC +old_postinstall_cmds=$lt_old_postinstall_cmds +old_postuninstall_cmds=$lt_old_postuninstall_cmds + +# Create an old-style archive from a shared archive. +old_archive_from_new_cmds=$lt_old_archive_from_new_cmds_RC + +# Create a temporary old-style archive to link instead of a shared archive. +old_archive_from_expsyms_cmds=$lt_old_archive_from_expsyms_cmds_RC + +# Commands used to build and install a shared archive. +archive_cmds=$lt_archive_cmds_RC +archive_expsym_cmds=$lt_archive_expsym_cmds_RC +postinstall_cmds=$lt_postinstall_cmds +postuninstall_cmds=$lt_postuninstall_cmds + +# Commands used to build a loadable module (assumed same as above if empty) +module_cmds=$lt_module_cmds_RC +module_expsym_cmds=$lt_module_expsym_cmds_RC + +# Commands to strip libraries. +old_striplib=$lt_old_striplib +striplib=$lt_striplib + +# Dependencies to place before the objects being linked to create a +# shared library. +predep_objects=$lt_predep_objects_RC + +# Dependencies to place after the objects being linked to create a +# shared library. +postdep_objects=$lt_postdep_objects_RC + +# Dependencies to place before the objects being linked to create a +# shared library. +predeps=$lt_predeps_RC + +# Dependencies to place after the objects being linked to create a +# shared library. +postdeps=$lt_postdeps_RC + +# The library search path used internally by the compiler when linking +# a shared library. +compiler_lib_search_path=$lt_compiler_lib_search_path_RC + +# Method to check whether dependent libraries are shared objects. +deplibs_check_method=$lt_deplibs_check_method + +# Command to use when deplibs_check_method == file_magic. +file_magic_cmd=$lt_file_magic_cmd + +# Flag that allows shared libraries with undefined symbols to be built. +allow_undefined_flag=$lt_allow_undefined_flag_RC + +# Flag that forces no undefined symbols. +no_undefined_flag=$lt_no_undefined_flag_RC + +# Commands used to finish a libtool library installation in a directory. +finish_cmds=$lt_finish_cmds + +# Same as above, but a single script fragment to be evaled but not shown. +finish_eval=$lt_finish_eval + +# Take the output of nm and produce a listing of raw symbols and C names. +global_symbol_pipe=$lt_lt_cv_sys_global_symbol_pipe + +# Transform the output of nm in a proper C declaration +global_symbol_to_cdecl=$lt_lt_cv_sys_global_symbol_to_cdecl + +# Transform the output of nm in a C name address pair +global_symbol_to_c_name_address=$lt_lt_cv_sys_global_symbol_to_c_name_address + +# This is the shared library runtime path variable. +runpath_var=$runpath_var + +# This is the shared library path variable. +shlibpath_var=$shlibpath_var + +# Is shlibpath searched before the hard-coded library search path? +shlibpath_overrides_runpath=$shlibpath_overrides_runpath + +# How to hardcode a shared library path into an executable. +hardcode_action=$hardcode_action_RC + +# Whether we should hardcode library paths into libraries. +hardcode_into_libs=$hardcode_into_libs + +# Flag to hardcode \$libdir into a binary during linking. +# This must work even if \$libdir does not exist. +hardcode_libdir_flag_spec=$lt_hardcode_libdir_flag_spec_RC + +# If ld is used when linking, flag to hardcode \$libdir into +# a binary during linking. This must work even if \$libdir does +# not exist. +hardcode_libdir_flag_spec_ld=$lt_hardcode_libdir_flag_spec_ld_RC + +# Whether we need a single -rpath flag with a separated argument. +hardcode_libdir_separator=$lt_hardcode_libdir_separator_RC + +# Set to yes if using DIR/libNAME${shared_ext} during linking hardcodes DIR into the +# resulting binary. +hardcode_direct=$hardcode_direct_RC + +# Set to yes if using the -LDIR flag during linking hardcodes DIR into the +# resulting binary. +hardcode_minus_L=$hardcode_minus_L_RC + +# Set to yes if using SHLIBPATH_VAR=DIR during linking hardcodes DIR into +# the resulting binary. +hardcode_shlibpath_var=$hardcode_shlibpath_var_RC + +# Set to yes if building a shared library automatically hardcodes DIR into the library +# and all subsequent libraries and executables linked against it. +hardcode_automatic=$hardcode_automatic_RC + +# Variables whose values should be saved in libtool wrapper scripts and +# restored at relink time. +variables_saved_for_relink="$variables_saved_for_relink" + +# Whether libtool must link a program against all its dependency libraries. +link_all_deplibs=$link_all_deplibs_RC + +# Compile-time system search path for libraries +sys_lib_search_path_spec=$lt_sys_lib_search_path_spec + +# Run-time system search path for libraries +sys_lib_dlsearch_path_spec=$lt_sys_lib_dlsearch_path_spec + +# Fix the shell variable \$srcfile for the compiler. +fix_srcfile_path="$fix_srcfile_path_RC" + +# Set to yes if exported symbols are required. +always_export_symbols=$always_export_symbols_RC + +# The commands to list exported symbols. +export_symbols_cmds=$lt_export_symbols_cmds_RC + +# The commands to extract the exported symbol list from a shared archive. +extract_expsyms_cmds=$lt_extract_expsyms_cmds + +# Symbols that should not be listed in the preloaded symbols. +exclude_expsyms=$lt_exclude_expsyms_RC + +# Symbols that must always be exported. +include_expsyms=$lt_include_expsyms_RC + +# ### END LIBTOOL TAG CONFIG: $tagname + +__EOF__ + + +else + # If there is no Makefile yet, we rely on a make rule to execute + # `config.status --recheck' to rerun these tests and create the + # libtool script then. + ltmain_in=`echo $ltmain | sed -e 's/\.sh$/.in/'` + if test -f "$ltmain_in"; then + test -f Makefile && make "$ltmain" + fi +fi + + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + +CC="$lt_save_CC" + + ;; + + *) + { { echo "$as_me:$LINENO: error: Unsupported tag name: $tagname" >&5 +echo "$as_me: error: Unsupported tag name: $tagname" >&2;} + { (exit 1); exit 1; }; } + ;; + esac + + # Append the new tag name to the list of available tags. + if test -n "$tagname" ; then + available_tags="$available_tags $tagname" + fi + fi + done + IFS="$lt_save_ifs" + + # Now substitute the updated list of available tags. + if eval "sed -e 's/^available_tags=.*\$/available_tags=\"$available_tags\"/' \"$ofile\" > \"${ofile}T\""; then + mv "${ofile}T" "$ofile" + chmod +x "$ofile" + else + rm -f "${ofile}T" + { { echo "$as_me:$LINENO: error: unable to update list of available tagged configurations." >&5 +echo "$as_me: error: unable to update list of available tagged configurations." >&2;} + { (exit 1); exit 1; }; } + fi +fi + + + +# This can be used to rebuild libtool when needed +LIBTOOL_DEPS="$ac_aux_dir/ltmain.sh" + +# Always use our own libtool. +LIBTOOL='$(SHELL) $(top_builddir)/libtool' + +# Prevent multiple expansion + + + + + + + + + + + + + + + + + + + + + + +CC_FOR_BUILD=${CC_FOR_BUILD:-'$(CC)'} +CXX_FOR_BUILD=${CXX_FOR_BUILD:-'$(CXX)'} +CFLAGS_FOR_BUILD=${CFLAGS_FOR_BUILD:-'$(CFLAGS)'} +CPPFLAGS_FOR_BUILD=${CFLAGS_FOR_BUILD:-'$(CPPFLAGS)'} +CXXFLAGS_FOR_BUILD=${CXXFLAGS_FOR_BUILD:-'$(CXXFLAGS)'} +BUILD_EXEEXT=${BUILD_EXEEXT:-'$(EXEEXT)'} +BUILD_OBJEXT=${BUILD_OBJEXT:-'$(OBJEXT)'} + + +echo "$as_me:$LINENO: checking for ANSI C header files" >&5 +echo $ECHO_N "checking for ANSI C header files... $ECHO_C" >&6 +if test "${ac_cv_header_stdc+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#include +#include +#include +#include + +int +main () +{ + + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_cv_header_stdc=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_cv_header_stdc=no +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext + +if test $ac_cv_header_stdc = yes; then + # SunOS 4.x string.h does not declare mem*, contrary to ANSI. + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#include + +_ACEOF +if (eval "$ac_cpp conftest.$ac_ext") 2>&5 | + $EGREP "memchr" >/dev/null 2>&1; then + : +else + ac_cv_header_stdc=no +fi +rm -f conftest* + +fi + +if test $ac_cv_header_stdc = yes; then + # ISC 2.0.2 stdlib.h does not declare free, contrary to ANSI. + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#include + +_ACEOF +if (eval "$ac_cpp conftest.$ac_ext") 2>&5 | + $EGREP "free" >/dev/null 2>&1; then + : +else + ac_cv_header_stdc=no +fi +rm -f conftest* + +fi + +if test $ac_cv_header_stdc = yes; then + # /bin/cc in Irix-4.0.5 gets non-ANSI ctype macros unless using -ansi. + if test "$cross_compiling" = yes; then + : +else + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#include +#if ((' ' & 0x0FF) == 0x020) +# define ISLOWER(c) ('a' <= (c) && (c) <= 'z') +# define TOUPPER(c) (ISLOWER(c) ? 'A' + ((c) - 'a') : (c)) +#else +# define ISLOWER(c) \ + (('a' <= (c) && (c) <= 'i') \ + || ('j' <= (c) && (c) <= 'r') \ + || ('s' <= (c) && (c) <= 'z')) +# define TOUPPER(c) (ISLOWER(c) ? ((c) | 0x40) : (c)) +#endif + +#define XOR(e, f) (((e) && !(f)) || (!(e) && (f))) +int +main () +{ + int i; + for (i = 0; i < 256; i++) + if (XOR (islower (i), ISLOWER (i)) + || toupper (i) != TOUPPER (i)) + exit(2); + exit (0); +} +_ACEOF +rm -f conftest$ac_exeext +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && { ac_try='./conftest$ac_exeext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + : +else + echo "$as_me: program exited with status $ac_status" >&5 +echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +( exit $ac_status ) +ac_cv_header_stdc=no +fi +rm -f core *.core gmon.out bb.out conftest$ac_exeext conftest.$ac_objext conftest.$ac_ext +fi +fi +fi +echo "$as_me:$LINENO: result: $ac_cv_header_stdc" >&5 +echo "${ECHO_T}$ac_cv_header_stdc" >&6 +if test $ac_cv_header_stdc = yes; then + +cat >>confdefs.h <<\_ACEOF +#define STDC_HEADERS 1 +_ACEOF + +fi + + +for ac_header in limits.h +do +as_ac_Header=`echo "ac_cv_header_$ac_header" | $as_tr_sh` +if eval "test \"\${$as_ac_Header+set}\" = set"; then + echo "$as_me:$LINENO: checking for $ac_header" >&5 +echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6 +if eval "test \"\${$as_ac_Header+set}\" = set"; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +fi +echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_Header'}'`" >&5 +echo "${ECHO_T}`eval echo '${'$as_ac_Header'}'`" >&6 +else + # Is the header compilable? +echo "$as_me:$LINENO: checking $ac_header usability" >&5 +echo $ECHO_N "checking $ac_header usability... $ECHO_C" >&6 +cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +$ac_includes_default +#include <$ac_header> +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_header_compiler=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_header_compiler=no +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext +echo "$as_me:$LINENO: result: $ac_header_compiler" >&5 +echo "${ECHO_T}$ac_header_compiler" >&6 + +# Is the header present? +echo "$as_me:$LINENO: checking $ac_header presence" >&5 +echo $ECHO_N "checking $ac_header presence... $ECHO_C" >&6 +cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#include <$ac_header> +_ACEOF +if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 + (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } >/dev/null; then + if test -s conftest.err; then + ac_cpp_err=$ac_c_preproc_warn_flag + ac_cpp_err=$ac_cpp_err$ac_c_werror_flag + else + ac_cpp_err= + fi +else + ac_cpp_err=yes +fi +if test -z "$ac_cpp_err"; then + ac_header_preproc=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + ac_header_preproc=no +fi +rm -f conftest.err conftest.$ac_ext +echo "$as_me:$LINENO: result: $ac_header_preproc" >&5 +echo "${ECHO_T}$ac_header_preproc" >&6 + +# So? What about this header? +case $ac_header_compiler:$ac_header_preproc:$ac_c_preproc_warn_flag in + yes:no: ) + { echo "$as_me:$LINENO: WARNING: $ac_header: accepted by the compiler, rejected by the preprocessor!" >&5 +echo "$as_me: WARNING: $ac_header: accepted by the compiler, rejected by the preprocessor!" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: proceeding with the compiler's result" >&5 +echo "$as_me: WARNING: $ac_header: proceeding with the compiler's result" >&2;} + ac_header_preproc=yes + ;; + no:yes:* ) + { echo "$as_me:$LINENO: WARNING: $ac_header: present but cannot be compiled" >&5 +echo "$as_me: WARNING: $ac_header: present but cannot be compiled" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: check for missing prerequisite headers?" >&5 +echo "$as_me: WARNING: $ac_header: check for missing prerequisite headers?" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: see the Autoconf documentation" >&5 +echo "$as_me: WARNING: $ac_header: see the Autoconf documentation" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: section \"Present But Cannot Be Compiled\"" >&5 +echo "$as_me: WARNING: $ac_header: section \"Present But Cannot Be Compiled\"" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: proceeding with the preprocessor's result" >&5 +echo "$as_me: WARNING: $ac_header: proceeding with the preprocessor's result" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: in the future, the compiler will take precedence" >&5 +echo "$as_me: WARNING: $ac_header: in the future, the compiler will take precedence" >&2;} + ( + cat <<\_ASBOX +## ------------------------------------------ ## +## Report this to the AC_PACKAGE_NAME lists. ## +## ------------------------------------------ ## +_ASBOX + ) | + sed "s/^/$as_me: WARNING: /" >&2 + ;; +esac +echo "$as_me:$LINENO: checking for $ac_header" >&5 +echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6 +if eval "test \"\${$as_ac_Header+set}\" = set"; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + eval "$as_ac_Header=\$ac_header_preproc" +fi +echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_Header'}'`" >&5 +echo "${ECHO_T}`eval echo '${'$as_ac_Header'}'`" >&6 + +fi +if test `eval echo '${'$as_ac_Header'}'` = yes; then + cat >>confdefs.h <<_ACEOF +#define `echo "HAVE_$ac_header" | $as_tr_cpp` 1 +_ACEOF + +fi + +done + + + +if test "x$want_cpp" = "xyes" -a -n "$CXX" +then + + +ac_ext=cc +ac_cpp='$CXXCPP $CPPFLAGS' +ac_compile='$CXX -c $CXXFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CXX -o conftest$ac_exeext $CXXFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_cxx_compiler_gnu + + + + +for ac_header in string +do +as_ac_Header=`echo "ac_cv_header_$ac_header" | $as_tr_sh` +if eval "test \"\${$as_ac_Header+set}\" = set"; then + echo "$as_me:$LINENO: checking for $ac_header" >&5 +echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6 +if eval "test \"\${$as_ac_Header+set}\" = set"; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +fi +echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_Header'}'`" >&5 +echo "${ECHO_T}`eval echo '${'$as_ac_Header'}'`" >&6 +else + # Is the header compilable? +echo "$as_me:$LINENO: checking $ac_header usability" >&5 +echo $ECHO_N "checking $ac_header usability... $ECHO_C" >&6 +cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +$ac_includes_default +#include <$ac_header> +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_cxx_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_header_compiler=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_header_compiler=no +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext +echo "$as_me:$LINENO: result: $ac_header_compiler" >&5 +echo "${ECHO_T}$ac_header_compiler" >&6 + +# Is the header present? +echo "$as_me:$LINENO: checking $ac_header presence" >&5 +echo $ECHO_N "checking $ac_header presence... $ECHO_C" >&6 +cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#include <$ac_header> +_ACEOF +if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 + (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } >/dev/null; then + if test -s conftest.err; then + ac_cpp_err=$ac_cxx_preproc_warn_flag + ac_cpp_err=$ac_cpp_err$ac_cxx_werror_flag + else + ac_cpp_err= + fi +else + ac_cpp_err=yes +fi +if test -z "$ac_cpp_err"; then + ac_header_preproc=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + ac_header_preproc=no +fi +rm -f conftest.err conftest.$ac_ext +echo "$as_me:$LINENO: result: $ac_header_preproc" >&5 +echo "${ECHO_T}$ac_header_preproc" >&6 + +# So? What about this header? +case $ac_header_compiler:$ac_header_preproc:$ac_cxx_preproc_warn_flag in + yes:no: ) + { echo "$as_me:$LINENO: WARNING: $ac_header: accepted by the compiler, rejected by the preprocessor!" >&5 +echo "$as_me: WARNING: $ac_header: accepted by the compiler, rejected by the preprocessor!" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: proceeding with the compiler's result" >&5 +echo "$as_me: WARNING: $ac_header: proceeding with the compiler's result" >&2;} + ac_header_preproc=yes + ;; + no:yes:* ) + { echo "$as_me:$LINENO: WARNING: $ac_header: present but cannot be compiled" >&5 +echo "$as_me: WARNING: $ac_header: present but cannot be compiled" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: check for missing prerequisite headers?" >&5 +echo "$as_me: WARNING: $ac_header: check for missing prerequisite headers?" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: see the Autoconf documentation" >&5 +echo "$as_me: WARNING: $ac_header: see the Autoconf documentation" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: section \"Present But Cannot Be Compiled\"" >&5 +echo "$as_me: WARNING: $ac_header: section \"Present But Cannot Be Compiled\"" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: proceeding with the preprocessor's result" >&5 +echo "$as_me: WARNING: $ac_header: proceeding with the preprocessor's result" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: in the future, the compiler will take precedence" >&5 +echo "$as_me: WARNING: $ac_header: in the future, the compiler will take precedence" >&2;} + ( + cat <<\_ASBOX +## ------------------------------------------ ## +## Report this to the AC_PACKAGE_NAME lists. ## +## ------------------------------------------ ## +_ASBOX + ) | + sed "s/^/$as_me: WARNING: /" >&2 + ;; +esac +echo "$as_me:$LINENO: checking for $ac_header" >&5 +echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6 +if eval "test \"\${$as_ac_Header+set}\" = set"; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + eval "$as_ac_Header=\$ac_header_preproc" +fi +echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_Header'}'`" >&5 +echo "${ECHO_T}`eval echo '${'$as_ac_Header'}'`" >&6 + +fi +if test `eval echo '${'$as_ac_Header'}'` = yes; then + cat >>confdefs.h <<_ACEOF +#define `echo "HAVE_$ac_header" | $as_tr_cpp` 1 +_ACEOF + pcre_have_cpp_headers="1" +else + pcre_have_cpp_headers="0" +fi + +done + + +for ac_header in bits/type_traits.h +do +as_ac_Header=`echo "ac_cv_header_$ac_header" | $as_tr_sh` +if eval "test \"\${$as_ac_Header+set}\" = set"; then + echo "$as_me:$LINENO: checking for $ac_header" >&5 +echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6 +if eval "test \"\${$as_ac_Header+set}\" = set"; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +fi +echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_Header'}'`" >&5 +echo "${ECHO_T}`eval echo '${'$as_ac_Header'}'`" >&6 +else + # Is the header compilable? +echo "$as_me:$LINENO: checking $ac_header usability" >&5 +echo $ECHO_N "checking $ac_header usability... $ECHO_C" >&6 +cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +$ac_includes_default +#include <$ac_header> +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_cxx_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_header_compiler=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_header_compiler=no +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext +echo "$as_me:$LINENO: result: $ac_header_compiler" >&5 +echo "${ECHO_T}$ac_header_compiler" >&6 + +# Is the header present? +echo "$as_me:$LINENO: checking $ac_header presence" >&5 +echo $ECHO_N "checking $ac_header presence... $ECHO_C" >&6 +cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#include <$ac_header> +_ACEOF +if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 + (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } >/dev/null; then + if test -s conftest.err; then + ac_cpp_err=$ac_cxx_preproc_warn_flag + ac_cpp_err=$ac_cpp_err$ac_cxx_werror_flag + else + ac_cpp_err= + fi +else + ac_cpp_err=yes +fi +if test -z "$ac_cpp_err"; then + ac_header_preproc=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + ac_header_preproc=no +fi +rm -f conftest.err conftest.$ac_ext +echo "$as_me:$LINENO: result: $ac_header_preproc" >&5 +echo "${ECHO_T}$ac_header_preproc" >&6 + +# So? What about this header? +case $ac_header_compiler:$ac_header_preproc:$ac_cxx_preproc_warn_flag in + yes:no: ) + { echo "$as_me:$LINENO: WARNING: $ac_header: accepted by the compiler, rejected by the preprocessor!" >&5 +echo "$as_me: WARNING: $ac_header: accepted by the compiler, rejected by the preprocessor!" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: proceeding with the compiler's result" >&5 +echo "$as_me: WARNING: $ac_header: proceeding with the compiler's result" >&2;} + ac_header_preproc=yes + ;; + no:yes:* ) + { echo "$as_me:$LINENO: WARNING: $ac_header: present but cannot be compiled" >&5 +echo "$as_me: WARNING: $ac_header: present but cannot be compiled" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: check for missing prerequisite headers?" >&5 +echo "$as_me: WARNING: $ac_header: check for missing prerequisite headers?" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: see the Autoconf documentation" >&5 +echo "$as_me: WARNING: $ac_header: see the Autoconf documentation" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: section \"Present But Cannot Be Compiled\"" >&5 +echo "$as_me: WARNING: $ac_header: section \"Present But Cannot Be Compiled\"" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: proceeding with the preprocessor's result" >&5 +echo "$as_me: WARNING: $ac_header: proceeding with the preprocessor's result" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: in the future, the compiler will take precedence" >&5 +echo "$as_me: WARNING: $ac_header: in the future, the compiler will take precedence" >&2;} + ( + cat <<\_ASBOX +## ------------------------------------------ ## +## Report this to the AC_PACKAGE_NAME lists. ## +## ------------------------------------------ ## +_ASBOX + ) | + sed "s/^/$as_me: WARNING: /" >&2 + ;; +esac +echo "$as_me:$LINENO: checking for $ac_header" >&5 +echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6 +if eval "test \"\${$as_ac_Header+set}\" = set"; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + eval "$as_ac_Header=\$ac_header_preproc" +fi +echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_Header'}'`" >&5 +echo "${ECHO_T}`eval echo '${'$as_ac_Header'}'`" >&6 + +fi +if test `eval echo '${'$as_ac_Header'}'` = yes; then + cat >>confdefs.h <<_ACEOF +#define `echo "HAVE_$ac_header" | $as_tr_cpp` 1 +_ACEOF + pcre_have_bits_type_traits="1" +else + pcre_have_bits_type_traits="0" +fi + +done + + +for ac_header in type_traits.h +do +as_ac_Header=`echo "ac_cv_header_$ac_header" | $as_tr_sh` +if eval "test \"\${$as_ac_Header+set}\" = set"; then + echo "$as_me:$LINENO: checking for $ac_header" >&5 +echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6 +if eval "test \"\${$as_ac_Header+set}\" = set"; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +fi +echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_Header'}'`" >&5 +echo "${ECHO_T}`eval echo '${'$as_ac_Header'}'`" >&6 +else + # Is the header compilable? +echo "$as_me:$LINENO: checking $ac_header usability" >&5 +echo $ECHO_N "checking $ac_header usability... $ECHO_C" >&6 +cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +$ac_includes_default +#include <$ac_header> +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_cxx_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_header_compiler=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_header_compiler=no +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext +echo "$as_me:$LINENO: result: $ac_header_compiler" >&5 +echo "${ECHO_T}$ac_header_compiler" >&6 + +# Is the header present? +echo "$as_me:$LINENO: checking $ac_header presence" >&5 +echo $ECHO_N "checking $ac_header presence... $ECHO_C" >&6 +cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +#include <$ac_header> +_ACEOF +if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 + (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } >/dev/null; then + if test -s conftest.err; then + ac_cpp_err=$ac_cxx_preproc_warn_flag + ac_cpp_err=$ac_cpp_err$ac_cxx_werror_flag + else + ac_cpp_err= + fi +else + ac_cpp_err=yes +fi +if test -z "$ac_cpp_err"; then + ac_header_preproc=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + ac_header_preproc=no +fi +rm -f conftest.err conftest.$ac_ext +echo "$as_me:$LINENO: result: $ac_header_preproc" >&5 +echo "${ECHO_T}$ac_header_preproc" >&6 + +# So? What about this header? +case $ac_header_compiler:$ac_header_preproc:$ac_cxx_preproc_warn_flag in + yes:no: ) + { echo "$as_me:$LINENO: WARNING: $ac_header: accepted by the compiler, rejected by the preprocessor!" >&5 +echo "$as_me: WARNING: $ac_header: accepted by the compiler, rejected by the preprocessor!" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: proceeding with the compiler's result" >&5 +echo "$as_me: WARNING: $ac_header: proceeding with the compiler's result" >&2;} + ac_header_preproc=yes + ;; + no:yes:* ) + { echo "$as_me:$LINENO: WARNING: $ac_header: present but cannot be compiled" >&5 +echo "$as_me: WARNING: $ac_header: present but cannot be compiled" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: check for missing prerequisite headers?" >&5 +echo "$as_me: WARNING: $ac_header: check for missing prerequisite headers?" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: see the Autoconf documentation" >&5 +echo "$as_me: WARNING: $ac_header: see the Autoconf documentation" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: section \"Present But Cannot Be Compiled\"" >&5 +echo "$as_me: WARNING: $ac_header: section \"Present But Cannot Be Compiled\"" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: proceeding with the preprocessor's result" >&5 +echo "$as_me: WARNING: $ac_header: proceeding with the preprocessor's result" >&2;} + { echo "$as_me:$LINENO: WARNING: $ac_header: in the future, the compiler will take precedence" >&5 +echo "$as_me: WARNING: $ac_header: in the future, the compiler will take precedence" >&2;} + ( + cat <<\_ASBOX +## ------------------------------------------ ## +## Report this to the AC_PACKAGE_NAME lists. ## +## ------------------------------------------ ## +_ASBOX + ) | + sed "s/^/$as_me: WARNING: /" >&2 + ;; +esac +echo "$as_me:$LINENO: checking for $ac_header" >&5 +echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6 +if eval "test \"\${$as_ac_Header+set}\" = set"; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + eval "$as_ac_Header=\$ac_header_preproc" +fi +echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_Header'}'`" >&5 +echo "${ECHO_T}`eval echo '${'$as_ac_Header'}'`" >&6 + +fi +if test `eval echo '${'$as_ac_Header'}'` = yes; then + cat >>confdefs.h <<_ACEOF +#define `echo "HAVE_$ac_header" | $as_tr_cpp` 1 +_ACEOF + pcre_have_type_traits="1" +else + pcre_have_type_traits="0" +fi + +done + + + +ac_ext=c +ac_cpp='$CPP $CPPFLAGS' +ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' +ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' +ac_compiler_gnu=$ac_cv_c_compiler_gnu + +fi + +if test "x$want_cpp" = "xyes" -a -n "$CXX" -a "$pcre_have_cpp_headers" = 1; then + MAYBE_CPP_TARGETS='$(CPP_TARGETS)' + HAVE_CPP= +else + MAYBE_CPP_TARGETS= + HAVE_CPP="#" +fi + + + + +echo "$as_me:$LINENO: checking for an ANSI C-conforming const" >&5 +echo $ECHO_N "checking for an ANSI C-conforming const... $ECHO_C" >&6 +if test "${ac_cv_c_const+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ + +int +main () +{ +/* FIXME: Include the comments suggested by Paul. */ +#ifndef __cplusplus + /* Ultrix mips cc rejects this. */ + typedef int charset[2]; + const charset x; + /* SunOS 4.1.1 cc rejects this. */ + char const *const *ccp; + char **p; + /* NEC SVR4.0.2 mips cc rejects this. */ + struct point {int x, y;}; + static struct point const zero = {0,0}; + /* AIX XL C 1.02.0.0 rejects this. + It does not let you subtract one const X* pointer from another in + an arm of an if-expression whose if-part is not a constant + expression */ + const char *g = "string"; + ccp = &g + (g ? g-g : 0); + /* HPUX 7.0 cc rejects these. */ + ++ccp; + p = (char**) ccp; + ccp = (char const *const *) p; + { /* SCO 3.2v4 cc rejects this. */ + char *t; + char const *s = 0 ? (char *) 0 : (char const *) 0; + + *t++ = 0; + } + { /* Someone thinks the Sun supposedly-ANSI compiler will reject this. */ + int x[] = {25, 17}; + const int *foo = &x[0]; + ++foo; + } + { /* Sun SC1.0 ANSI compiler rejects this -- but not the above. */ + typedef const int *iptr; + iptr p = 0; + ++p; + } + { /* AIX XL C 1.02.0.0 rejects this saying + "k.c", line 2.27: 1506-025 (S) Operand must be a modifiable lvalue. */ + struct s { int j; const int *ap[3]; }; + struct s *b; b->j = 5; + } + { /* ULTRIX-32 V3.1 (Rev 9) vcc rejects this */ + const int foo = 10; + } +#endif + + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_cv_c_const=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_cv_c_const=no +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext +fi +echo "$as_me:$LINENO: result: $ac_cv_c_const" >&5 +echo "${ECHO_T}$ac_cv_c_const" >&6 +if test $ac_cv_c_const = no; then + +cat >>confdefs.h <<\_ACEOF +#define const +_ACEOF + +fi + +echo "$as_me:$LINENO: checking for size_t" >&5 +echo $ECHO_N "checking for size_t... $ECHO_C" >&6 +if test "${ac_cv_type_size_t+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +$ac_includes_default +int +main () +{ +if ((size_t *) 0) + return 0; +if (sizeof (size_t)) + return 0; + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_cv_type_size_t=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_cv_type_size_t=no +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext +fi +echo "$as_me:$LINENO: result: $ac_cv_type_size_t" >&5 +echo "${ECHO_T}$ac_cv_type_size_t" >&6 +if test $ac_cv_type_size_t = yes; then + : +else + +cat >>confdefs.h <<_ACEOF +#define size_t unsigned +_ACEOF + +fi + + +echo "$as_me:$LINENO: checking for long long" >&5 +echo $ECHO_N "checking for long long... $ECHO_C" >&6 +if test "${ac_cv_type_long_long+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +$ac_includes_default +int +main () +{ +if ((long long *) 0) + return 0; +if (sizeof (long long)) + return 0; + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_cv_type_long_long=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_cv_type_long_long=no +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext +fi +echo "$as_me:$LINENO: result: $ac_cv_type_long_long" >&5 +echo "${ECHO_T}$ac_cv_type_long_long" >&6 +if test $ac_cv_type_long_long = yes; then + +cat >>confdefs.h <<_ACEOF +#define HAVE_LONG_LONG 1 +_ACEOF + +pcre_have_long_long="1" +else + pcre_have_long_long="0" +fi + +echo "$as_me:$LINENO: checking for unsigned long long" >&5 +echo $ECHO_N "checking for unsigned long long... $ECHO_C" >&6 +if test "${ac_cv_type_unsigned_long_long+set}" = set; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +$ac_includes_default +int +main () +{ +if ((unsigned long long *) 0) + return 0; +if (sizeof (unsigned long long)) + return 0; + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext +if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 + (eval $ac_compile) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest.$ac_objext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + ac_cv_type_unsigned_long_long=yes +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +ac_cv_type_unsigned_long_long=no +fi +rm -f conftest.err conftest.$ac_objext conftest.$ac_ext +fi +echo "$as_me:$LINENO: result: $ac_cv_type_unsigned_long_long" >&5 +echo "${ECHO_T}$ac_cv_type_unsigned_long_long" >&6 +if test $ac_cv_type_unsigned_long_long = yes; then + +cat >>confdefs.h <<_ACEOF +#define HAVE_UNSIGNED_LONG_LONG 1 +_ACEOF + +pcre_have_ulong_long="1" +else + pcre_have_ulong_long="0" +fi + + + + + + + + + + +for ac_func in bcopy memmove strerror strtoq strtoll +do +as_ac_var=`echo "ac_cv_func_$ac_func" | $as_tr_sh` +echo "$as_me:$LINENO: checking for $ac_func" >&5 +echo $ECHO_N "checking for $ac_func... $ECHO_C" >&6 +if eval "test \"\${$as_ac_var+set}\" = set"; then + echo $ECHO_N "(cached) $ECHO_C" >&6 +else + cat >conftest.$ac_ext <<_ACEOF +/* confdefs.h. */ +_ACEOF +cat confdefs.h >>conftest.$ac_ext +cat >>conftest.$ac_ext <<_ACEOF +/* end confdefs.h. */ +/* Define $ac_func to an innocuous variant, in case declares $ac_func. + For example, HP-UX 11i declares gettimeofday. */ +#define $ac_func innocuous_$ac_func + +/* System header to define __stub macros and hopefully few prototypes, + which can conflict with char $ac_func (); below. + Prefer to if __STDC__ is defined, since + exists even on freestanding compilers. */ + +#ifdef __STDC__ +# include +#else +# include +#endif + +#undef $ac_func + +/* Override any gcc2 internal prototype to avoid an error. */ +#ifdef __cplusplus +extern "C" +{ +#endif +/* We use char because int might match the return type of a gcc2 + builtin and then its argument prototype would still apply. */ +char $ac_func (); +/* The GNU C library defines this for functions which it implements + to always fail with ENOSYS. Some functions are actually named + something starting with __ and the normal name is an alias. */ +#if defined (__stub_$ac_func) || defined (__stub___$ac_func) +choke me +#else +char (*f) () = $ac_func; +#endif +#ifdef __cplusplus +} +#endif + +int +main () +{ +return f != $ac_func; + ; + return 0; +} +_ACEOF +rm -f conftest.$ac_objext conftest$ac_exeext +if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 + (eval $ac_link) 2>conftest.er1 + ac_status=$? + grep -v '^ *+' conftest.er1 >conftest.err + rm -f conftest.er1 + cat conftest.err >&5 + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); } && + { ac_try='test -z "$ac_c_werror_flag" + || test ! -s conftest.err' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; } && + { ac_try='test -s conftest$ac_exeext' + { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 + (eval $ac_try) 2>&5 + ac_status=$? + echo "$as_me:$LINENO: \$? = $ac_status" >&5 + (exit $ac_status); }; }; then + eval "$as_ac_var=yes" +else + echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + +eval "$as_ac_var=no" +fi +rm -f conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +fi +echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_var'}'`" >&5 +echo "${ECHO_T}`eval echo '${'$as_ac_var'}'`" >&6 +if test `eval echo '${'$as_ac_var'}'` = yes; then + cat >>confdefs.h <<_ACEOF +#define `echo "HAVE_$ac_func" | $as_tr_cpp` 1 +_ACEOF + +fi +done + + + +# Check whether --enable-utf8 or --disable-utf8 was given. +if test "${enable_utf8+set}" = set; then + enableval="$enable_utf8" + if test "$enableval" = "yes"; then + UTF8=-DSUPPORT_UTF8 +fi + +fi; + + +# Check whether --enable-unicode-properties or --disable-unicode-properties was given. +if test "${enable_unicode_properties+set}" = set; then + enableval="$enable_unicode_properties" + if test "$enableval" = "yes"; then + UCP=-DSUPPORT_UCP +fi + +fi; + + +# Check whether --enable-newline-is-cr or --disable-newline-is-cr was given. +if test "${enable_newline_is_cr+set}" = set; then + enableval="$enable_newline_is_cr" + if test "$enableval" = "yes"; then + NEWLINE=-DNEWLINE=13 +fi + +fi; + + +# Check whether --enable-newline-is-lf or --disable-newline-is-lf was given. +if test "${enable_newline_is_lf+set}" = set; then + enableval="$enable_newline_is_lf" + if test "$enableval" = "yes"; then + NEWLINE=-DNEWLINE=10 +fi + +fi; + + +# Check whether --enable-newline-is-crlf or --disable-newline-is-crlf was given. +if test "${enable_newline_is_crlf+set}" = set; then + enableval="$enable_newline_is_crlf" + if test "$enableval" = "yes"; then + NEWLINE=-DNEWLINE=3338 +fi + +fi; + + +# Check whether --enable-ebcdic or --disable-ebcdic was given. +if test "${enable_ebcdic+set}" = set; then + enableval="$enable_ebcdic" + if test "$enableval" == "yes"; then + EBCDIC=-DEBCDIC=1 +fi + +fi; + + +# Check whether --enable-stack-for-recursion or --disable-stack-for-recursion was given. +if test "${enable_stack_for_recursion+set}" = set; then + enableval="$enable_stack_for_recursion" + if test "$enableval" = "no"; then + NO_RECURSE=-DNO_RECURSE +fi + +fi; + + + + +# Check whether --with-posix-malloc-threshold or --without-posix-malloc-threshold was given. +if test "${with_posix_malloc_threshold+set}" = set; then + withval="$with_posix_malloc_threshold" + POSIX_MALLOC_THRESHOLD=-DPOSIX_MALLOC_THRESHOLD=$withval + +fi; + + + +# Check whether --with-link-size or --without-link-size was given. +if test "${with_link_size+set}" = set; then + withval="$with_link_size" + LINK_SIZE=-DLINK_SIZE=$withval + +fi; + + + +# Check whether --with-match-limit or --without-match-limit was given. +if test "${with_match_limit+set}" = set; then + withval="$with_match_limit" + MATCH_LIMIT=-DMATCH_LIMIT=$withval + +fi; + + + +# Check whether --with-match-limit-recursion or --without-match-limit-recursion was given. +if test "${with_match_limit_recursion+set}" = set; then + withval="$with_match_limit_recursion" + MATCH_LIMIT_RECURSION=-DMATCH_LIMIT_RECURSION=$withval + +fi; + + +if test "$UCP" != "" ; then + UTF8=-DSUPPORT_UTF8 +fi + + + + + + + + + + + + + + + + + + + + + + + + + + +case $host_os in +mingw* ) + POSIX_OBJ=pcreposix.o + POSIX_LOBJ=pcreposix.lo + POSIX_LIB= + ON_WINDOWS= + NOT_ON_WINDOWS="#" + WIN_PREFIX= + ;; +* ) + ON_WINDOWS="#" + NOT_ON_WINDOWS= + POSIX_OBJ= + POSIX_LOBJ= + POSIX_LIB=libpcreposix.la + WIN_PREFIX= + ;; +esac + + + + + + + +if test "x$enable_shared" = "xno" ; then + +cat >>confdefs.h <<\_ACEOF +#define PCRE_STATIC 1 +_ACEOF + +fi + + ac_config_files="$ac_config_files Makefile pcre-config:pcre-config.in libpcre.pc:libpcre.pc.in pcrecpparg.h:pcrecpparg.h.in pcre_stringpiece.h:pcre_stringpiece.h.in RunGrepTest:RunGrepTest.in RunTest:RunTest.in" + ac_config_commands="$ac_config_commands default" +cat >confcache <<\_ACEOF +# This file is a shell script that caches the results of configure +# tests run on this system so they can be shared between configure +# scripts and configure runs, see configure's option --config-cache. +# It is not useful on other systems. If it contains results you don't +# want to keep, you may remove or edit it. +# +# config.status only pays attention to the cache file if you give it +# the --recheck option to rerun configure. +# +# `ac_cv_env_foo' variables (set or unset) will be overridden when +# loading this file, other *unset* `ac_cv_foo' will be assigned the +# following values. + +_ACEOF + +# The following way of writing the cache mishandles newlines in values, +# but we know of no workaround that is simple, portable, and efficient. +# So, don't put newlines in cache variables' values. +# Ultrix sh set writes to stderr and can't be redirected directly, +# and sets the high bit in the cache file unless we assign to the vars. +{ + (set) 2>&1 | + case `(ac_space=' '; set | grep ac_space) 2>&1` in + *ac_space=\ *) + # `set' does not quote correctly, so add quotes (double-quote + # substitution turns \\\\ into \\, and sed turns \\ into \). + sed -n \ + "s/'/'\\\\''/g; + s/^\\([_$as_cr_alnum]*_cv_[_$as_cr_alnum]*\\)=\\(.*\\)/\\1='\\2'/p" + ;; + *) + # `set' quotes correctly as required by POSIX, so do not add quotes. + sed -n \ + "s/^\\([_$as_cr_alnum]*_cv_[_$as_cr_alnum]*\\)=\\(.*\\)/\\1=\\2/p" + ;; + esac; +} | + sed ' + t clear + : clear + s/^\([^=]*\)=\(.*[{}].*\)$/test "${\1+set}" = set || &/ + t end + /^ac_cv_env/!s/^\([^=]*\)=\(.*\)$/\1=${\1=\2}/ + : end' >>confcache +if diff $cache_file confcache >/dev/null 2>&1; then :; else + if test -w $cache_file; then + test "x$cache_file" != "x/dev/null" && echo "updating cache $cache_file" + cat confcache >$cache_file + else + echo "not updating unwritable cache $cache_file" + fi +fi +rm -f confcache + +test "x$prefix" = xNONE && prefix=$ac_default_prefix +# Let make expand exec_prefix. +test "x$exec_prefix" = xNONE && exec_prefix='${prefix}' + +# VPATH may cause trouble with some makes, so we remove $(srcdir), +# ${srcdir} and @srcdir@ from VPATH if srcdir is ".", strip leading and +# trailing colons and then remove the whole line if VPATH becomes empty +# (actually we leave an empty line to preserve line numbers). +if test "x$srcdir" = x.; then + ac_vpsub='/^[ ]*VPATH[ ]*=/{ +s/:*\$(srcdir):*/:/; +s/:*\${srcdir}:*/:/; +s/:*@srcdir@:*/:/; +s/^\([^=]*=[ ]*\):*/\1/; +s/:*$//; +s/^[^=]*=[ ]*$//; +}' +fi + +DEFS=-DHAVE_CONFIG_H + +ac_libobjs= +ac_ltlibobjs= +for ac_i in : $LIBOBJS; do test "x$ac_i" = x: && continue + # 1. Remove the extension, and $U if already installed. + ac_i=`echo "$ac_i" | + sed 's/\$U\././;s/\.o$//;s/\.obj$//'` + # 2. Add them. + ac_libobjs="$ac_libobjs $ac_i\$U.$ac_objext" + ac_ltlibobjs="$ac_ltlibobjs $ac_i"'$U.lo' +done +LIBOBJS=$ac_libobjs + +LTLIBOBJS=$ac_ltlibobjs + + + +: ${CONFIG_STATUS=./config.status} +ac_clean_files_save=$ac_clean_files +ac_clean_files="$ac_clean_files $CONFIG_STATUS" +{ echo "$as_me:$LINENO: creating $CONFIG_STATUS" >&5 +echo "$as_me: creating $CONFIG_STATUS" >&6;} +cat >$CONFIG_STATUS <<_ACEOF +#! $SHELL +# Generated by $as_me. +# Run this file to recreate the current configuration. +# Compiler output produced by configure, useful for debugging +# configure, is in config.log if it exists. + +debug=false +ac_cs_recheck=false +ac_cs_silent=false +SHELL=\${CONFIG_SHELL-$SHELL} +_ACEOF + +cat >>$CONFIG_STATUS <<\_ACEOF +## --------------------- ## +## M4sh Initialization. ## +## --------------------- ## + +# Be Bourne compatible +if test -n "${ZSH_VERSION+set}" && (emulate sh) >/dev/null 2>&1; then + emulate sh + NULLCMD=: + # Zsh 3.x and 4.x performs word splitting on ${1+"$@"}, which + # is contrary to our usage. Disable this feature. + alias -g '${1+"$@"}'='"$@"' +elif test -n "${BASH_VERSION+set}" && (set -o posix) >/dev/null 2>&1; then + set -o posix +fi +DUALCASE=1; export DUALCASE # for MKS sh + +# Support unset when possible. +if ( (MAIL=60; unset MAIL) || exit) >/dev/null 2>&1; then + as_unset=unset +else + as_unset=false +fi + + +# Work around bugs in pre-3.0 UWIN ksh. +$as_unset ENV MAIL MAILPATH +PS1='$ ' +PS2='> ' +PS4='+ ' + +# NLS nuisances. +for as_var in \ + LANG LANGUAGE LC_ADDRESS LC_ALL LC_COLLATE LC_CTYPE LC_IDENTIFICATION \ + LC_MEASUREMENT LC_MESSAGES LC_MONETARY LC_NAME LC_NUMERIC LC_PAPER \ + LC_TELEPHONE LC_TIME +do + if (set +x; test -z "`(eval $as_var=C; export $as_var) 2>&1`"); then + eval $as_var=C; export $as_var + else + $as_unset $as_var + fi +done + +# Required to use basename. +if expr a : '\(a\)' >/dev/null 2>&1; then + as_expr=expr +else + as_expr=false +fi + +if (basename /) >/dev/null 2>&1 && test "X`basename / 2>&1`" = "X/"; then + as_basename=basename +else + as_basename=false +fi + + +# Name of the executable. +as_me=`$as_basename "$0" || +$as_expr X/"$0" : '.*/\([^/][^/]*\)/*$' \| \ + X"$0" : 'X\(//\)$' \| \ + X"$0" : 'X\(/\)$' \| \ + . : '\(.\)' 2>/dev/null || +echo X/"$0" | + sed '/^.*\/\([^/][^/]*\)\/*$/{ s//\1/; q; } + /^X\/\(\/\/\)$/{ s//\1/; q; } + /^X\/\(\/\).*/{ s//\1/; q; } + s/.*/./; q'` + + +# PATH needs CR, and LINENO needs CR and PATH. +# Avoid depending upon Character Ranges. +as_cr_letters='abcdefghijklmnopqrstuvwxyz' +as_cr_LETTERS='ABCDEFGHIJKLMNOPQRSTUVWXYZ' +as_cr_Letters=$as_cr_letters$as_cr_LETTERS +as_cr_digits='0123456789' +as_cr_alnum=$as_cr_Letters$as_cr_digits + +# The user is always right. +if test "${PATH_SEPARATOR+set}" != set; then + echo "#! /bin/sh" >conf$$.sh + echo "exit 0" >>conf$$.sh + chmod +x conf$$.sh + if (PATH="/nonexistent;."; conf$$.sh) >/dev/null 2>&1; then + PATH_SEPARATOR=';' + else + PATH_SEPARATOR=: + fi + rm -f conf$$.sh +fi + + + as_lineno_1=$LINENO + as_lineno_2=$LINENO + as_lineno_3=`(expr $as_lineno_1 + 1) 2>/dev/null` + test "x$as_lineno_1" != "x$as_lineno_2" && + test "x$as_lineno_3" = "x$as_lineno_2" || { + # Find who we are. Look in the path if we contain no path at all + # relative or not. + case $0 in + *[\\/]* ) as_myself=$0 ;; + *) as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in $PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + test -r "$as_dir/$0" && as_myself=$as_dir/$0 && break +done + + ;; + esac + # We did not find ourselves, most probably we were run as `sh COMMAND' + # in which case we are not to be found in the path. + if test "x$as_myself" = x; then + as_myself=$0 + fi + if test ! -f "$as_myself"; then + { { echo "$as_me:$LINENO: error: cannot find myself; rerun with an absolute path" >&5 +echo "$as_me: error: cannot find myself; rerun with an absolute path" >&2;} + { (exit 1); exit 1; }; } + fi + case $CONFIG_SHELL in + '') + as_save_IFS=$IFS; IFS=$PATH_SEPARATOR +for as_dir in /bin$PATH_SEPARATOR/usr/bin$PATH_SEPARATOR$PATH +do + IFS=$as_save_IFS + test -z "$as_dir" && as_dir=. + for as_base in sh bash ksh sh5; do + case $as_dir in + /*) + if ("$as_dir/$as_base" -c ' + as_lineno_1=$LINENO + as_lineno_2=$LINENO + as_lineno_3=`(expr $as_lineno_1 + 1) 2>/dev/null` + test "x$as_lineno_1" != "x$as_lineno_2" && + test "x$as_lineno_3" = "x$as_lineno_2" ') 2>/dev/null; then + $as_unset BASH_ENV || test "${BASH_ENV+set}" != set || { BASH_ENV=; export BASH_ENV; } + $as_unset ENV || test "${ENV+set}" != set || { ENV=; export ENV; } + CONFIG_SHELL=$as_dir/$as_base + export CONFIG_SHELL + exec "$CONFIG_SHELL" "$0" ${1+"$@"} + fi;; + esac + done +done +;; + esac + + # Create $as_me.lineno as a copy of $as_myself, but with $LINENO + # uniformly replaced by the line number. The first 'sed' inserts a + # line-number line before each line; the second 'sed' does the real + # work. The second script uses 'N' to pair each line-number line + # with the numbered line, and appends trailing '-' during + # substitution so that $LINENO is not a special case at line end. + # (Raja R Harinath suggested sed '=', and Paul Eggert wrote the + # second 'sed' script. Blame Lee E. McMahon for sed's syntax. :-) + sed '=' <$as_myself | + sed ' + N + s,$,-, + : loop + s,^\(['$as_cr_digits']*\)\(.*\)[$]LINENO\([^'$as_cr_alnum'_]\),\1\2\1\3, + t loop + s,-$,, + s,^['$as_cr_digits']*\n,, + ' >$as_me.lineno && + chmod +x $as_me.lineno || + { { echo "$as_me:$LINENO: error: cannot create $as_me.lineno; rerun with a POSIX shell" >&5 +echo "$as_me: error: cannot create $as_me.lineno; rerun with a POSIX shell" >&2;} + { (exit 1); exit 1; }; } + + # Don't try to exec as it changes $[0], causing all sort of problems + # (the dirname of $[0] is not the place where we might find the + # original and so on. Autoconf is especially sensible to this). + . ./$as_me.lineno + # Exit status is that of the last command. + exit +} + + +case `echo "testing\c"; echo 1,2,3`,`echo -n testing; echo 1,2,3` in + *c*,-n*) ECHO_N= ECHO_C=' +' ECHO_T=' ' ;; + *c*,* ) ECHO_N=-n ECHO_C= ECHO_T= ;; + *) ECHO_N= ECHO_C='\c' ECHO_T= ;; +esac + +if expr a : '\(a\)' >/dev/null 2>&1; then + as_expr=expr +else + as_expr=false +fi + +rm -f conf$$ conf$$.exe conf$$.file +echo >conf$$.file +if ln -s conf$$.file conf$$ 2>/dev/null; then + # We could just check for DJGPP; but this test a) works b) is more generic + # and c) will remain valid once DJGPP supports symlinks (DJGPP 2.04). + if test -f conf$$.exe; then + # Don't use ln at all; we don't have any links + as_ln_s='cp -p' + else + as_ln_s='ln -s' + fi +elif ln conf$$.file conf$$ 2>/dev/null; then + as_ln_s=ln +else + as_ln_s='cp -p' +fi +rm -f conf$$ conf$$.exe conf$$.file + +if mkdir -p . 2>/dev/null; then + as_mkdir_p=: +else + test -d ./-p && rmdir ./-p + as_mkdir_p=false +fi + +as_executable_p="test -f" + +# Sed expression to map a string onto a valid CPP name. +as_tr_cpp="eval sed 'y%*$as_cr_letters%P$as_cr_LETTERS%;s%[^_$as_cr_alnum]%_%g'" + +# Sed expression to map a string onto a valid variable name. +as_tr_sh="eval sed 'y%*+%pp%;s%[^_$as_cr_alnum]%_%g'" + + +# IFS +# We need space, tab and new line, in precisely that order. +as_nl=' +' +IFS=" $as_nl" + +# CDPATH. +$as_unset CDPATH + +exec 6>&1 + +# Open the log real soon, to keep \$[0] and so on meaningful, and to +# report actual input values of CONFIG_FILES etc. instead of their +# values after options handling. Logging --version etc. is OK. +exec 5>>config.log +{ + echo + sed 'h;s/./-/g;s/^.../## /;s/...$/ ##/;p;x;p;x' <<_ASBOX +## Running $as_me. ## +_ASBOX +} >&5 +cat >&5 <<_CSEOF + +This file was extended by $as_me, which was +generated by GNU Autoconf 2.59. Invocation command line was + + CONFIG_FILES = $CONFIG_FILES + CONFIG_HEADERS = $CONFIG_HEADERS + CONFIG_LINKS = $CONFIG_LINKS + CONFIG_COMMANDS = $CONFIG_COMMANDS + $ $0 $@ + +_CSEOF +echo "on `(hostname || uname -n) 2>/dev/null | sed 1q`" >&5 +echo >&5 +_ACEOF + +# Files that config.status was made for. +if test -n "$ac_config_files"; then + echo "config_files=\"$ac_config_files\"" >>$CONFIG_STATUS +fi + +if test -n "$ac_config_headers"; then + echo "config_headers=\"$ac_config_headers\"" >>$CONFIG_STATUS +fi + +if test -n "$ac_config_links"; then + echo "config_links=\"$ac_config_links\"" >>$CONFIG_STATUS +fi + +if test -n "$ac_config_commands"; then + echo "config_commands=\"$ac_config_commands\"" >>$CONFIG_STATUS +fi + +cat >>$CONFIG_STATUS <<\_ACEOF + +ac_cs_usage="\ +\`$as_me' instantiates files from templates according to the +current configuration. + +Usage: $0 [OPTIONS] [FILE]... + + -h, --help print this help, then exit + -V, --version print version number, then exit + -q, --quiet do not print progress messages + -d, --debug don't remove temporary files + --recheck update $as_me by reconfiguring in the same conditions + --file=FILE[:TEMPLATE] + instantiate the configuration file FILE + --header=FILE[:TEMPLATE] + instantiate the configuration header FILE + +Configuration files: +$config_files + +Configuration headers: +$config_headers + +Configuration commands: +$config_commands + +Report bugs to ." +_ACEOF + +cat >>$CONFIG_STATUS <<_ACEOF +ac_cs_version="\\ +config.status +configured by $0, generated by GNU Autoconf 2.59, + with options \\"`echo "$ac_configure_args" | sed 's/[\\""\`\$]/\\\\&/g'`\\" + +Copyright (C) 2003 Free Software Foundation, Inc. +This config.status script is free software; the Free Software Foundation +gives unlimited permission to copy, distribute and modify it." +srcdir=$srcdir +INSTALL="$INSTALL" +_ACEOF + +cat >>$CONFIG_STATUS <<\_ACEOF +# If no file are specified by the user, then we need to provide default +# value. By we need to know if files were specified by the user. +ac_need_defaults=: +while test $# != 0 +do + case $1 in + --*=*) + ac_option=`expr "x$1" : 'x\([^=]*\)='` + ac_optarg=`expr "x$1" : 'x[^=]*=\(.*\)'` + ac_shift=: + ;; + -*) + ac_option=$1 + ac_optarg=$2 + ac_shift=shift + ;; + *) # This is not an option, so the user has probably given explicit + # arguments. + ac_option=$1 + ac_need_defaults=false;; + esac + + case $ac_option in + # Handling of the options. +_ACEOF +cat >>$CONFIG_STATUS <<\_ACEOF + -recheck | --recheck | --rechec | --reche | --rech | --rec | --re | --r) + ac_cs_recheck=: ;; + --version | --vers* | -V ) + echo "$ac_cs_version"; exit 0 ;; + --he | --h) + # Conflict between --help and --header + { { echo "$as_me:$LINENO: error: ambiguous option: $1 +Try \`$0 --help' for more information." >&5 +echo "$as_me: error: ambiguous option: $1 +Try \`$0 --help' for more information." >&2;} + { (exit 1); exit 1; }; };; + --help | --hel | -h ) + echo "$ac_cs_usage"; exit 0 ;; + --debug | --d* | -d ) + debug=: ;; + --file | --fil | --fi | --f ) + $ac_shift + CONFIG_FILES="$CONFIG_FILES $ac_optarg" + ac_need_defaults=false;; + --header | --heade | --head | --hea ) + $ac_shift + CONFIG_HEADERS="$CONFIG_HEADERS $ac_optarg" + ac_need_defaults=false;; + -q | -quiet | --quiet | --quie | --qui | --qu | --q \ + | -silent | --silent | --silen | --sile | --sil | --si | --s) + ac_cs_silent=: ;; + + # This is an error. + -*) { { echo "$as_me:$LINENO: error: unrecognized option: $1 +Try \`$0 --help' for more information." >&5 +echo "$as_me: error: unrecognized option: $1 +Try \`$0 --help' for more information." >&2;} + { (exit 1); exit 1; }; } ;; + + *) ac_config_targets="$ac_config_targets $1" ;; + + esac + shift +done + +ac_configure_extra_args= + +if $ac_cs_silent; then + exec 6>/dev/null + ac_configure_extra_args="$ac_configure_extra_args --silent" +fi + +_ACEOF +cat >>$CONFIG_STATUS <<_ACEOF +if \$ac_cs_recheck; then + echo "running $SHELL $0 " $ac_configure_args \$ac_configure_extra_args " --no-create --no-recursion" >&6 + exec $SHELL $0 $ac_configure_args \$ac_configure_extra_args --no-create --no-recursion +fi + +_ACEOF + + + + + +cat >>$CONFIG_STATUS <<\_ACEOF +for ac_config_target in $ac_config_targets +do + case "$ac_config_target" in + # Handling of arguments. + "Makefile" ) CONFIG_FILES="$CONFIG_FILES Makefile" ;; + "pcre-config" ) CONFIG_FILES="$CONFIG_FILES pcre-config:pcre-config.in" ;; + "libpcre.pc" ) CONFIG_FILES="$CONFIG_FILES libpcre.pc:libpcre.pc.in" ;; + "pcrecpparg.h" ) CONFIG_FILES="$CONFIG_FILES pcrecpparg.h:pcrecpparg.h.in" ;; + "pcre_stringpiece.h" ) CONFIG_FILES="$CONFIG_FILES pcre_stringpiece.h:pcre_stringpiece.h.in" ;; + "RunGrepTest" ) CONFIG_FILES="$CONFIG_FILES RunGrepTest:RunGrepTest.in" ;; + "RunTest" ) CONFIG_FILES="$CONFIG_FILES RunTest:RunTest.in" ;; + "default" ) CONFIG_COMMANDS="$CONFIG_COMMANDS default" ;; + "config.h" ) CONFIG_HEADERS="$CONFIG_HEADERS config.h" ;; + *) { { echo "$as_me:$LINENO: error: invalid argument: $ac_config_target" >&5 +echo "$as_me: error: invalid argument: $ac_config_target" >&2;} + { (exit 1); exit 1; }; };; + esac +done + +# If the user did not use the arguments to specify the items to instantiate, +# then the envvar interface is used. Set only those that are not. +# We use the long form for the default assignment because of an extremely +# bizarre bug on SunOS 4.1.3. +if $ac_need_defaults; then + test "${CONFIG_FILES+set}" = set || CONFIG_FILES=$config_files + test "${CONFIG_HEADERS+set}" = set || CONFIG_HEADERS=$config_headers + test "${CONFIG_COMMANDS+set}" = set || CONFIG_COMMANDS=$config_commands +fi + +# Have a temporary directory for convenience. Make it in the build tree +# simply because there is no reason to put it here, and in addition, +# creating and moving files from /tmp can sometimes cause problems. +# Create a temporary directory, and hook for its removal unless debugging. +$debug || +{ + trap 'exit_status=$?; rm -rf $tmp && exit $exit_status' 0 + trap '{ (exit 1); exit 1; }' 1 2 13 15 +} + +# Create a (secure) tmp directory for tmp files. + +{ + tmp=`(umask 077 && mktemp -d -q "./confstatXXXXXX") 2>/dev/null` && + test -n "$tmp" && test -d "$tmp" +} || +{ + tmp=./confstat$$-$RANDOM + (umask 077 && mkdir $tmp) +} || +{ + echo "$me: cannot create a temporary directory in ." >&2 + { (exit 1); exit 1; } +} + +_ACEOF + +cat >>$CONFIG_STATUS <<_ACEOF + +# +# CONFIG_FILES section. +# + +# No need to generate the scripts if there are no CONFIG_FILES. +# This happens for instance when ./config.status config.h +if test -n "\$CONFIG_FILES"; then + # Protect against being on the right side of a sed subst in config.status. + sed 's/,@/@@/; s/@,/@@/; s/,;t t\$/@;t t/; /@;t t\$/s/[\\\\&,]/\\\\&/g; + s/@@/,@/; s/@@/@,/; s/@;t t\$/,;t t/' >\$tmp/subs.sed <<\\CEOF +s,@SHELL@,$SHELL,;t t +s,@PATH_SEPARATOR@,$PATH_SEPARATOR,;t t +s,@PACKAGE_NAME@,$PACKAGE_NAME,;t t +s,@PACKAGE_TARNAME@,$PACKAGE_TARNAME,;t t +s,@PACKAGE_VERSION@,$PACKAGE_VERSION,;t t +s,@PACKAGE_STRING@,$PACKAGE_STRING,;t t +s,@PACKAGE_BUGREPORT@,$PACKAGE_BUGREPORT,;t t +s,@exec_prefix@,$exec_prefix,;t t +s,@prefix@,$prefix,;t t +s,@program_transform_name@,$program_transform_name,;t t +s,@bindir@,$bindir,;t t +s,@sbindir@,$sbindir,;t t +s,@libexecdir@,$libexecdir,;t t +s,@datadir@,$datadir,;t t +s,@sysconfdir@,$sysconfdir,;t t +s,@sharedstatedir@,$sharedstatedir,;t t +s,@localstatedir@,$localstatedir,;t t +s,@libdir@,$libdir,;t t +s,@includedir@,$includedir,;t t +s,@oldincludedir@,$oldincludedir,;t t +s,@infodir@,$infodir,;t t +s,@mandir@,$mandir,;t t +s,@build_alias@,$build_alias,;t t +s,@host_alias@,$host_alias,;t t +s,@target_alias@,$target_alias,;t t +s,@DEFS@,$DEFS,;t t +s,@ECHO_C@,$ECHO_C,;t t +s,@ECHO_N@,$ECHO_N,;t t +s,@ECHO_T@,$ECHO_T,;t t +s,@LIBS@,$LIBS,;t t +s,@CC@,$CC,;t t +s,@CFLAGS@,$CFLAGS,;t t +s,@LDFLAGS@,$LDFLAGS,;t t +s,@CPPFLAGS@,$CPPFLAGS,;t t +s,@ac_ct_CC@,$ac_ct_CC,;t t +s,@EXEEXT@,$EXEEXT,;t t +s,@OBJEXT@,$OBJEXT,;t t +s,@CXX@,$CXX,;t t +s,@CXXFLAGS@,$CXXFLAGS,;t t +s,@ac_ct_CXX@,$ac_ct_CXX,;t t +s,@INSTALL_PROGRAM@,$INSTALL_PROGRAM,;t t +s,@INSTALL_SCRIPT@,$INSTALL_SCRIPT,;t t +s,@INSTALL_DATA@,$INSTALL_DATA,;t t +s,@build@,$build,;t t +s,@build_cpu@,$build_cpu,;t t +s,@build_vendor@,$build_vendor,;t t +s,@build_os@,$build_os,;t t +s,@host@,$host,;t t +s,@host_cpu@,$host_cpu,;t t +s,@host_vendor@,$host_vendor,;t t +s,@host_os@,$host_os,;t t +s,@EGREP@,$EGREP,;t t +s,@LN_S@,$LN_S,;t t +s,@ECHO@,$ECHO,;t t +s,@AR@,$AR,;t t +s,@ac_ct_AR@,$ac_ct_AR,;t t +s,@RANLIB@,$RANLIB,;t t +s,@ac_ct_RANLIB@,$ac_ct_RANLIB,;t t +s,@STRIP@,$STRIP,;t t +s,@ac_ct_STRIP@,$ac_ct_STRIP,;t t +s,@DLLTOOL@,$DLLTOOL,;t t +s,@ac_ct_DLLTOOL@,$ac_ct_DLLTOOL,;t t +s,@AS@,$AS,;t t +s,@ac_ct_AS@,$ac_ct_AS,;t t +s,@OBJDUMP@,$OBJDUMP,;t t +s,@ac_ct_OBJDUMP@,$ac_ct_OBJDUMP,;t t +s,@CPP@,$CPP,;t t +s,@CXXCPP@,$CXXCPP,;t t +s,@F77@,$F77,;t t +s,@FFLAGS@,$FFLAGS,;t t +s,@ac_ct_F77@,$ac_ct_F77,;t t +s,@LIBTOOL@,$LIBTOOL,;t t +s,@pcre_have_bits_type_traits@,$pcre_have_bits_type_traits,;t t +s,@pcre_have_type_traits@,$pcre_have_type_traits,;t t +s,@MAYBE_CPP_TARGETS@,$MAYBE_CPP_TARGETS,;t t +s,@HAVE_CPP@,$HAVE_CPP,;t t +s,@pcre_have_long_long@,$pcre_have_long_long,;t t +s,@pcre_have_ulong_long@,$pcre_have_ulong_long,;t t +s,@BUILD_EXEEXT@,$BUILD_EXEEXT,;t t +s,@BUILD_OBJEXT@,$BUILD_OBJEXT,;t t +s,@CC_FOR_BUILD@,$CC_FOR_BUILD,;t t +s,@CXX_FOR_BUILD@,$CXX_FOR_BUILD,;t t +s,@CFLAGS_FOR_BUILD@,$CFLAGS_FOR_BUILD,;t t +s,@CXXFLAGS_FOR_BUILD@,$CXXFLAGS_FOR_BUILD,;t t +s,@CXXLDFLAGS@,$CXXLDFLAGS,;t t +s,@EBCDIC@,$EBCDIC,;t t +s,@HAVE_MEMMOVE@,$HAVE_MEMMOVE,;t t +s,@HAVE_STRERROR@,$HAVE_STRERROR,;t t +s,@LINK_SIZE@,$LINK_SIZE,;t t +s,@MATCH_LIMIT@,$MATCH_LIMIT,;t t +s,@MATCH_LIMIT_RECURSION@,$MATCH_LIMIT_RECURSION,;t t +s,@NEWLINE@,$NEWLINE,;t t +s,@NO_RECURSE@,$NO_RECURSE,;t t +s,@PCRE_LIB_VERSION@,$PCRE_LIB_VERSION,;t t +s,@PCRE_POSIXLIB_VERSION@,$PCRE_POSIXLIB_VERSION,;t t +s,@PCRE_CPPLIB_VERSION@,$PCRE_CPPLIB_VERSION,;t t +s,@PCRE_VERSION@,$PCRE_VERSION,;t t +s,@POSIX_MALLOC_THRESHOLD@,$POSIX_MALLOC_THRESHOLD,;t t +s,@UCP@,$UCP,;t t +s,@UTF8@,$UTF8,;t t +s,@WIN_PREFIX@,$WIN_PREFIX,;t t +s,@ON_WINDOWS@,$ON_WINDOWS,;t t +s,@NOT_ON_WINDOWS@,$NOT_ON_WINDOWS,;t t +s,@POSIX_OBJ@,$POSIX_OBJ,;t t +s,@POSIX_LOBJ@,$POSIX_LOBJ,;t t +s,@POSIX_LIB@,$POSIX_LIB,;t t +s,@LIBOBJS@,$LIBOBJS,;t t +s,@LTLIBOBJS@,$LTLIBOBJS,;t t +CEOF + +_ACEOF + + cat >>$CONFIG_STATUS <<\_ACEOF + # Split the substitutions into bite-sized pieces for seds with + # small command number limits, like on Digital OSF/1 and HP-UX. + ac_max_sed_lines=48 + ac_sed_frag=1 # Number of current file. + ac_beg=1 # First line for current file. + ac_end=$ac_max_sed_lines # Line after last line for current file. + ac_more_lines=: + ac_sed_cmds= + while $ac_more_lines; do + if test $ac_beg -gt 1; then + sed "1,${ac_beg}d; ${ac_end}q" $tmp/subs.sed >$tmp/subs.frag + else + sed "${ac_end}q" $tmp/subs.sed >$tmp/subs.frag + fi + if test ! -s $tmp/subs.frag; then + ac_more_lines=false + else + # The purpose of the label and of the branching condition is to + # speed up the sed processing (if there are no `@' at all, there + # is no need to browse any of the substitutions). + # These are the two extra sed commands mentioned above. + (echo ':t + /@[a-zA-Z_][a-zA-Z_0-9]*@/!b' && cat $tmp/subs.frag) >$tmp/subs-$ac_sed_frag.sed + if test -z "$ac_sed_cmds"; then + ac_sed_cmds="sed -f $tmp/subs-$ac_sed_frag.sed" + else + ac_sed_cmds="$ac_sed_cmds | sed -f $tmp/subs-$ac_sed_frag.sed" + fi + ac_sed_frag=`expr $ac_sed_frag + 1` + ac_beg=$ac_end + ac_end=`expr $ac_end + $ac_max_sed_lines` + fi + done + if test -z "$ac_sed_cmds"; then + ac_sed_cmds=cat + fi +fi # test -n "$CONFIG_FILES" + +_ACEOF +cat >>$CONFIG_STATUS <<\_ACEOF +for ac_file in : $CONFIG_FILES; do test "x$ac_file" = x: && continue + # Support "outfile[:infile[:infile...]]", defaulting infile="outfile.in". + case $ac_file in + - | *:- | *:-:* ) # input from stdin + cat >$tmp/stdin + ac_file_in=`echo "$ac_file" | sed 's,[^:]*:,,'` + ac_file=`echo "$ac_file" | sed 's,:.*,,'` ;; + *:* ) ac_file_in=`echo "$ac_file" | sed 's,[^:]*:,,'` + ac_file=`echo "$ac_file" | sed 's,:.*,,'` ;; + * ) ac_file_in=$ac_file.in ;; + esac + + # Compute @srcdir@, @top_srcdir@, and @INSTALL@ for subdirectories. + ac_dir=`(dirname "$ac_file") 2>/dev/null || +$as_expr X"$ac_file" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ + X"$ac_file" : 'X\(//\)[^/]' \| \ + X"$ac_file" : 'X\(//\)$' \| \ + X"$ac_file" : 'X\(/\)' \| \ + . : '\(.\)' 2>/dev/null || +echo X"$ac_file" | + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ s//\1/; q; } + /^X\(\/\/\)[^/].*/{ s//\1/; q; } + /^X\(\/\/\)$/{ s//\1/; q; } + /^X\(\/\).*/{ s//\1/; q; } + s/.*/./; q'` + { if $as_mkdir_p; then + mkdir -p "$ac_dir" + else + as_dir="$ac_dir" + as_dirs= + while test ! -d "$as_dir"; do + as_dirs="$as_dir $as_dirs" + as_dir=`(dirname "$as_dir") 2>/dev/null || +$as_expr X"$as_dir" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ + X"$as_dir" : 'X\(//\)[^/]' \| \ + X"$as_dir" : 'X\(//\)$' \| \ + X"$as_dir" : 'X\(/\)' \| \ + . : '\(.\)' 2>/dev/null || +echo X"$as_dir" | + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ s//\1/; q; } + /^X\(\/\/\)[^/].*/{ s//\1/; q; } + /^X\(\/\/\)$/{ s//\1/; q; } + /^X\(\/\).*/{ s//\1/; q; } + s/.*/./; q'` + done + test ! -n "$as_dirs" || mkdir $as_dirs + fi || { { echo "$as_me:$LINENO: error: cannot create directory \"$ac_dir\"" >&5 +echo "$as_me: error: cannot create directory \"$ac_dir\"" >&2;} + { (exit 1); exit 1; }; }; } + + ac_builddir=. + +if test "$ac_dir" != .; then + ac_dir_suffix=/`echo "$ac_dir" | sed 's,^\.[\\/],,'` + # A "../" for each directory in $ac_dir_suffix. + ac_top_builddir=`echo "$ac_dir_suffix" | sed 's,/[^\\/]*,../,g'` +else + ac_dir_suffix= ac_top_builddir= +fi + +case $srcdir in + .) # No --srcdir option. We are building in place. + ac_srcdir=. + if test -z "$ac_top_builddir"; then + ac_top_srcdir=. + else + ac_top_srcdir=`echo $ac_top_builddir | sed 's,/$,,'` + fi ;; + [\\/]* | ?:[\\/]* ) # Absolute path. + ac_srcdir=$srcdir$ac_dir_suffix; + ac_top_srcdir=$srcdir ;; + *) # Relative path. + ac_srcdir=$ac_top_builddir$srcdir$ac_dir_suffix + ac_top_srcdir=$ac_top_builddir$srcdir ;; +esac + +# Do not use `cd foo && pwd` to compute absolute paths, because +# the directories may not exist. +case `pwd` in +.) ac_abs_builddir="$ac_dir";; +*) + case "$ac_dir" in + .) ac_abs_builddir=`pwd`;; + [\\/]* | ?:[\\/]* ) ac_abs_builddir="$ac_dir";; + *) ac_abs_builddir=`pwd`/"$ac_dir";; + esac;; +esac +case $ac_abs_builddir in +.) ac_abs_top_builddir=${ac_top_builddir}.;; +*) + case ${ac_top_builddir}. in + .) ac_abs_top_builddir=$ac_abs_builddir;; + [\\/]* | ?:[\\/]* ) ac_abs_top_builddir=${ac_top_builddir}.;; + *) ac_abs_top_builddir=$ac_abs_builddir/${ac_top_builddir}.;; + esac;; +esac +case $ac_abs_builddir in +.) ac_abs_srcdir=$ac_srcdir;; +*) + case $ac_srcdir in + .) ac_abs_srcdir=$ac_abs_builddir;; + [\\/]* | ?:[\\/]* ) ac_abs_srcdir=$ac_srcdir;; + *) ac_abs_srcdir=$ac_abs_builddir/$ac_srcdir;; + esac;; +esac +case $ac_abs_builddir in +.) ac_abs_top_srcdir=$ac_top_srcdir;; +*) + case $ac_top_srcdir in + .) ac_abs_top_srcdir=$ac_abs_builddir;; + [\\/]* | ?:[\\/]* ) ac_abs_top_srcdir=$ac_top_srcdir;; + *) ac_abs_top_srcdir=$ac_abs_builddir/$ac_top_srcdir;; + esac;; +esac + + + case $INSTALL in + [\\/$]* | ?:[\\/]* ) ac_INSTALL=$INSTALL ;; + *) ac_INSTALL=$ac_top_builddir$INSTALL ;; + esac + + if test x"$ac_file" != x-; then + { echo "$as_me:$LINENO: creating $ac_file" >&5 +echo "$as_me: creating $ac_file" >&6;} + rm -f "$ac_file" + fi + # Let's still pretend it is `configure' which instantiates (i.e., don't + # use $as_me), people would be surprised to read: + # /* config.h. Generated by config.status. */ + if test x"$ac_file" = x-; then + configure_input= + else + configure_input="$ac_file. " + fi + configure_input=$configure_input"Generated from `echo $ac_file_in | + sed 's,.*/,,'` by configure." + + # First look for the input files in the build tree, otherwise in the + # src tree. + ac_file_inputs=`IFS=: + for f in $ac_file_in; do + case $f in + -) echo $tmp/stdin ;; + [\\/$]*) + # Absolute (can't be DOS-style, as IFS=:) + test -f "$f" || { { echo "$as_me:$LINENO: error: cannot find input file: $f" >&5 +echo "$as_me: error: cannot find input file: $f" >&2;} + { (exit 1); exit 1; }; } + echo "$f";; + *) # Relative + if test -f "$f"; then + # Build tree + echo "$f" + elif test -f "$srcdir/$f"; then + # Source tree + echo "$srcdir/$f" + else + # /dev/null tree + { { echo "$as_me:$LINENO: error: cannot find input file: $f" >&5 +echo "$as_me: error: cannot find input file: $f" >&2;} + { (exit 1); exit 1; }; } + fi;; + esac + done` || { (exit 1); exit 1; } +_ACEOF +cat >>$CONFIG_STATUS <<_ACEOF + sed "$ac_vpsub +$extrasub +_ACEOF +cat >>$CONFIG_STATUS <<\_ACEOF +:t +/@[a-zA-Z_][a-zA-Z_0-9]*@/!b +s,@configure_input@,$configure_input,;t t +s,@srcdir@,$ac_srcdir,;t t +s,@abs_srcdir@,$ac_abs_srcdir,;t t +s,@top_srcdir@,$ac_top_srcdir,;t t +s,@abs_top_srcdir@,$ac_abs_top_srcdir,;t t +s,@builddir@,$ac_builddir,;t t +s,@abs_builddir@,$ac_abs_builddir,;t t +s,@top_builddir@,$ac_top_builddir,;t t +s,@abs_top_builddir@,$ac_abs_top_builddir,;t t +s,@INSTALL@,$ac_INSTALL,;t t +" $ac_file_inputs | (eval "$ac_sed_cmds") >$tmp/out + rm -f $tmp/stdin + if test x"$ac_file" != x-; then + mv $tmp/out $ac_file + else + cat $tmp/out + rm -f $tmp/out + fi + +done +_ACEOF +cat >>$CONFIG_STATUS <<\_ACEOF + +# +# CONFIG_HEADER section. +# + +# These sed commands are passed to sed as "A NAME B NAME C VALUE D", where +# NAME is the cpp macro being defined and VALUE is the value it is being given. +# +# ac_d sets the value in "#define NAME VALUE" lines. +ac_dA='s,^\([ ]*\)#\([ ]*define[ ][ ]*\)' +ac_dB='[ ].*$,\1#\2' +ac_dC=' ' +ac_dD=',;t' +# ac_u turns "#undef NAME" without trailing blanks into "#define NAME VALUE". +ac_uA='s,^\([ ]*\)#\([ ]*\)undef\([ ][ ]*\)' +ac_uB='$,\1#\2define\3' +ac_uC=' ' +ac_uD=',;t' + +for ac_file in : $CONFIG_HEADERS; do test "x$ac_file" = x: && continue + # Support "outfile[:infile[:infile...]]", defaulting infile="outfile.in". + case $ac_file in + - | *:- | *:-:* ) # input from stdin + cat >$tmp/stdin + ac_file_in=`echo "$ac_file" | sed 's,[^:]*:,,'` + ac_file=`echo "$ac_file" | sed 's,:.*,,'` ;; + *:* ) ac_file_in=`echo "$ac_file" | sed 's,[^:]*:,,'` + ac_file=`echo "$ac_file" | sed 's,:.*,,'` ;; + * ) ac_file_in=$ac_file.in ;; + esac + + test x"$ac_file" != x- && { echo "$as_me:$LINENO: creating $ac_file" >&5 +echo "$as_me: creating $ac_file" >&6;} + + # First look for the input files in the build tree, otherwise in the + # src tree. + ac_file_inputs=`IFS=: + for f in $ac_file_in; do + case $f in + -) echo $tmp/stdin ;; + [\\/$]*) + # Absolute (can't be DOS-style, as IFS=:) + test -f "$f" || { { echo "$as_me:$LINENO: error: cannot find input file: $f" >&5 +echo "$as_me: error: cannot find input file: $f" >&2;} + { (exit 1); exit 1; }; } + # Do quote $f, to prevent DOS paths from being IFS'd. + echo "$f";; + *) # Relative + if test -f "$f"; then + # Build tree + echo "$f" + elif test -f "$srcdir/$f"; then + # Source tree + echo "$srcdir/$f" + else + # /dev/null tree + { { echo "$as_me:$LINENO: error: cannot find input file: $f" >&5 +echo "$as_me: error: cannot find input file: $f" >&2;} + { (exit 1); exit 1; }; } + fi;; + esac + done` || { (exit 1); exit 1; } + # Remove the trailing spaces. + sed 's/[ ]*$//' $ac_file_inputs >$tmp/in + +_ACEOF + +# Transform confdefs.h into two sed scripts, `conftest.defines' and +# `conftest.undefs', that substitutes the proper values into +# config.h.in to produce config.h. The first handles `#define' +# templates, and the second `#undef' templates. +# And first: Protect against being on the right side of a sed subst in +# config.status. Protect against being in an unquoted here document +# in config.status. +rm -f conftest.defines conftest.undefs +# Using a here document instead of a string reduces the quoting nightmare. +# Putting comments in sed scripts is not portable. +# +# `end' is used to avoid that the second main sed command (meant for +# 0-ary CPP macros) applies to n-ary macro definitions. +# See the Autoconf documentation for `clear'. +cat >confdef2sed.sed <<\_ACEOF +s/[\\&,]/\\&/g +s,[\\$`],\\&,g +t clear +: clear +s,^[ ]*#[ ]*define[ ][ ]*\([^ (][^ (]*\)\(([^)]*)\)[ ]*\(.*\)$,${ac_dA}\1${ac_dB}\1\2${ac_dC}\3${ac_dD},gp +t end +s,^[ ]*#[ ]*define[ ][ ]*\([^ ][^ ]*\)[ ]*\(.*\)$,${ac_dA}\1${ac_dB}\1${ac_dC}\2${ac_dD},gp +: end +_ACEOF +# If some macros were called several times there might be several times +# the same #defines, which is useless. Nevertheless, we may not want to +# sort them, since we want the *last* AC-DEFINE to be honored. +uniq confdefs.h | sed -n -f confdef2sed.sed >conftest.defines +sed 's/ac_d/ac_u/g' conftest.defines >conftest.undefs +rm -f confdef2sed.sed + +# This sed command replaces #undef with comments. This is necessary, for +# example, in the case of _POSIX_SOURCE, which is predefined and required +# on some systems where configure will not decide to define it. +cat >>conftest.undefs <<\_ACEOF +s,^[ ]*#[ ]*undef[ ][ ]*[a-zA-Z_][a-zA-Z_0-9]*,/* & */, +_ACEOF + +# Break up conftest.defines because some shells have a limit on the size +# of here documents, and old seds have small limits too (100 cmds). +echo ' # Handle all the #define templates only if necessary.' >>$CONFIG_STATUS +echo ' if grep "^[ ]*#[ ]*define" $tmp/in >/dev/null; then' >>$CONFIG_STATUS +echo ' # If there are no defines, we may have an empty if/fi' >>$CONFIG_STATUS +echo ' :' >>$CONFIG_STATUS +rm -f conftest.tail +while grep . conftest.defines >/dev/null +do + # Write a limited-size here document to $tmp/defines.sed. + echo ' cat >$tmp/defines.sed <>$CONFIG_STATUS + # Speed up: don't consider the non `#define' lines. + echo '/^[ ]*#[ ]*define/!b' >>$CONFIG_STATUS + # Work around the forget-to-reset-the-flag bug. + echo 't clr' >>$CONFIG_STATUS + echo ': clr' >>$CONFIG_STATUS + sed ${ac_max_here_lines}q conftest.defines >>$CONFIG_STATUS + echo 'CEOF + sed -f $tmp/defines.sed $tmp/in >$tmp/out + rm -f $tmp/in + mv $tmp/out $tmp/in +' >>$CONFIG_STATUS + sed 1,${ac_max_here_lines}d conftest.defines >conftest.tail + rm -f conftest.defines + mv conftest.tail conftest.defines +done +rm -f conftest.defines +echo ' fi # grep' >>$CONFIG_STATUS +echo >>$CONFIG_STATUS + +# Break up conftest.undefs because some shells have a limit on the size +# of here documents, and old seds have small limits too (100 cmds). +echo ' # Handle all the #undef templates' >>$CONFIG_STATUS +rm -f conftest.tail +while grep . conftest.undefs >/dev/null +do + # Write a limited-size here document to $tmp/undefs.sed. + echo ' cat >$tmp/undefs.sed <>$CONFIG_STATUS + # Speed up: don't consider the non `#undef' + echo '/^[ ]*#[ ]*undef/!b' >>$CONFIG_STATUS + # Work around the forget-to-reset-the-flag bug. + echo 't clr' >>$CONFIG_STATUS + echo ': clr' >>$CONFIG_STATUS + sed ${ac_max_here_lines}q conftest.undefs >>$CONFIG_STATUS + echo 'CEOF + sed -f $tmp/undefs.sed $tmp/in >$tmp/out + rm -f $tmp/in + mv $tmp/out $tmp/in +' >>$CONFIG_STATUS + sed 1,${ac_max_here_lines}d conftest.undefs >conftest.tail + rm -f conftest.undefs + mv conftest.tail conftest.undefs +done +rm -f conftest.undefs + +cat >>$CONFIG_STATUS <<\_ACEOF + # Let's still pretend it is `configure' which instantiates (i.e., don't + # use $as_me), people would be surprised to read: + # /* config.h. Generated by config.status. */ + if test x"$ac_file" = x-; then + echo "/* Generated by configure. */" >$tmp/config.h + else + echo "/* $ac_file. Generated by configure. */" >$tmp/config.h + fi + cat $tmp/in >>$tmp/config.h + rm -f $tmp/in + if test x"$ac_file" != x-; then + if diff $ac_file $tmp/config.h >/dev/null 2>&1; then + { echo "$as_me:$LINENO: $ac_file is unchanged" >&5 +echo "$as_me: $ac_file is unchanged" >&6;} + else + ac_dir=`(dirname "$ac_file") 2>/dev/null || +$as_expr X"$ac_file" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ + X"$ac_file" : 'X\(//\)[^/]' \| \ + X"$ac_file" : 'X\(//\)$' \| \ + X"$ac_file" : 'X\(/\)' \| \ + . : '\(.\)' 2>/dev/null || +echo X"$ac_file" | + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ s//\1/; q; } + /^X\(\/\/\)[^/].*/{ s//\1/; q; } + /^X\(\/\/\)$/{ s//\1/; q; } + /^X\(\/\).*/{ s//\1/; q; } + s/.*/./; q'` + { if $as_mkdir_p; then + mkdir -p "$ac_dir" + else + as_dir="$ac_dir" + as_dirs= + while test ! -d "$as_dir"; do + as_dirs="$as_dir $as_dirs" + as_dir=`(dirname "$as_dir") 2>/dev/null || +$as_expr X"$as_dir" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ + X"$as_dir" : 'X\(//\)[^/]' \| \ + X"$as_dir" : 'X\(//\)$' \| \ + X"$as_dir" : 'X\(/\)' \| \ + . : '\(.\)' 2>/dev/null || +echo X"$as_dir" | + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ s//\1/; q; } + /^X\(\/\/\)[^/].*/{ s//\1/; q; } + /^X\(\/\/\)$/{ s//\1/; q; } + /^X\(\/\).*/{ s//\1/; q; } + s/.*/./; q'` + done + test ! -n "$as_dirs" || mkdir $as_dirs + fi || { { echo "$as_me:$LINENO: error: cannot create directory \"$ac_dir\"" >&5 +echo "$as_me: error: cannot create directory \"$ac_dir\"" >&2;} + { (exit 1); exit 1; }; }; } + + rm -f $ac_file + mv $tmp/config.h $ac_file + fi + else + cat $tmp/config.h + rm -f $tmp/config.h + fi +done +_ACEOF +cat >>$CONFIG_STATUS <<\_ACEOF + +# +# CONFIG_COMMANDS section. +# +for ac_file in : $CONFIG_COMMANDS; do test "x$ac_file" = x: && continue + ac_dest=`echo "$ac_file" | sed 's,:.*,,'` + ac_source=`echo "$ac_file" | sed 's,[^:]*:,,'` + ac_dir=`(dirname "$ac_dest") 2>/dev/null || +$as_expr X"$ac_dest" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ + X"$ac_dest" : 'X\(//\)[^/]' \| \ + X"$ac_dest" : 'X\(//\)$' \| \ + X"$ac_dest" : 'X\(/\)' \| \ + . : '\(.\)' 2>/dev/null || +echo X"$ac_dest" | + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ s//\1/; q; } + /^X\(\/\/\)[^/].*/{ s//\1/; q; } + /^X\(\/\/\)$/{ s//\1/; q; } + /^X\(\/\).*/{ s//\1/; q; } + s/.*/./; q'` + { if $as_mkdir_p; then + mkdir -p "$ac_dir" + else + as_dir="$ac_dir" + as_dirs= + while test ! -d "$as_dir"; do + as_dirs="$as_dir $as_dirs" + as_dir=`(dirname "$as_dir") 2>/dev/null || +$as_expr X"$as_dir" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ + X"$as_dir" : 'X\(//\)[^/]' \| \ + X"$as_dir" : 'X\(//\)$' \| \ + X"$as_dir" : 'X\(/\)' \| \ + . : '\(.\)' 2>/dev/null || +echo X"$as_dir" | + sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ s//\1/; q; } + /^X\(\/\/\)[^/].*/{ s//\1/; q; } + /^X\(\/\/\)$/{ s//\1/; q; } + /^X\(\/\).*/{ s//\1/; q; } + s/.*/./; q'` + done + test ! -n "$as_dirs" || mkdir $as_dirs + fi || { { echo "$as_me:$LINENO: error: cannot create directory \"$ac_dir\"" >&5 +echo "$as_me: error: cannot create directory \"$ac_dir\"" >&2;} + { (exit 1); exit 1; }; }; } + + ac_builddir=. + +if test "$ac_dir" != .; then + ac_dir_suffix=/`echo "$ac_dir" | sed 's,^\.[\\/],,'` + # A "../" for each directory in $ac_dir_suffix. + ac_top_builddir=`echo "$ac_dir_suffix" | sed 's,/[^\\/]*,../,g'` +else + ac_dir_suffix= ac_top_builddir= +fi + +case $srcdir in + .) # No --srcdir option. We are building in place. + ac_srcdir=. + if test -z "$ac_top_builddir"; then + ac_top_srcdir=. + else + ac_top_srcdir=`echo $ac_top_builddir | sed 's,/$,,'` + fi ;; + [\\/]* | ?:[\\/]* ) # Absolute path. + ac_srcdir=$srcdir$ac_dir_suffix; + ac_top_srcdir=$srcdir ;; + *) # Relative path. + ac_srcdir=$ac_top_builddir$srcdir$ac_dir_suffix + ac_top_srcdir=$ac_top_builddir$srcdir ;; +esac + +# Do not use `cd foo && pwd` to compute absolute paths, because +# the directories may not exist. +case `pwd` in +.) ac_abs_builddir="$ac_dir";; +*) + case "$ac_dir" in + .) ac_abs_builddir=`pwd`;; + [\\/]* | ?:[\\/]* ) ac_abs_builddir="$ac_dir";; + *) ac_abs_builddir=`pwd`/"$ac_dir";; + esac;; +esac +case $ac_abs_builddir in +.) ac_abs_top_builddir=${ac_top_builddir}.;; +*) + case ${ac_top_builddir}. in + .) ac_abs_top_builddir=$ac_abs_builddir;; + [\\/]* | ?:[\\/]* ) ac_abs_top_builddir=${ac_top_builddir}.;; + *) ac_abs_top_builddir=$ac_abs_builddir/${ac_top_builddir}.;; + esac;; +esac +case $ac_abs_builddir in +.) ac_abs_srcdir=$ac_srcdir;; +*) + case $ac_srcdir in + .) ac_abs_srcdir=$ac_abs_builddir;; + [\\/]* | ?:[\\/]* ) ac_abs_srcdir=$ac_srcdir;; + *) ac_abs_srcdir=$ac_abs_builddir/$ac_srcdir;; + esac;; +esac +case $ac_abs_builddir in +.) ac_abs_top_srcdir=$ac_top_srcdir;; +*) + case $ac_top_srcdir in + .) ac_abs_top_srcdir=$ac_abs_builddir;; + [\\/]* | ?:[\\/]* ) ac_abs_top_srcdir=$ac_top_srcdir;; + *) ac_abs_top_srcdir=$ac_abs_builddir/$ac_top_srcdir;; + esac;; +esac + + + { echo "$as_me:$LINENO: executing $ac_dest commands" >&5 +echo "$as_me: executing $ac_dest commands" >&6;} + case $ac_dest in + default ) chmod a+x RunTest RunGrepTest pcre-config ;; + esac +done +_ACEOF + +cat >>$CONFIG_STATUS <<\_ACEOF + +{ (exit 0); exit 0; } +_ACEOF +chmod +x $CONFIG_STATUS +ac_clean_files=$ac_clean_files_save + + +# configure is writing to config.log, and then calls config.status. +# config.status does its own redirection, appending to config.log. +# Unfortunately, on DOS this fails, as config.log is still kept open +# by configure, so config.status won't be able to write to it; its +# output is simply discarded. So we exec the FD to /dev/null, +# effectively closing config.log, so it can be properly (re)opened and +# appended to by config.status. When coming back to configure, we +# need to make the FD available again. +if test "$no_create" != yes; then + ac_cs_success=: + ac_config_status_args= + test "$silent" = yes && + ac_config_status_args="$ac_config_status_args --quiet" + exec 5>/dev/null + $SHELL $CONFIG_STATUS $ac_config_status_args || ac_cs_success=false + exec 5>>config.log + # Use ||, not &&, to avoid exiting from the if with $? = 1, which + # would make configure fail if this is the last instruction. + $ac_cs_success || { (exit 1); exit 1; } +fi + diff --git a/libs/pcre/configure.ac b/libs/pcre/configure.ac new file mode 100644 index 0000000000..6a318c17ff --- /dev/null +++ b/libs/pcre/configure.ac @@ -0,0 +1,302 @@ +dnl Process this file with autoconf to produce a configure script. + +dnl This configure.in file has been hacked around quite a lot as a result of +dnl patches that various people have sent to me (PH). Sometimes the information +dnl I get is contradictory. I've tried to put in comments that explain things, +dnl but in some cases the information is second-hand and I have no way of +dnl verifying it. I am not an autoconf or libtool expert! + +dnl This is required at the start; the name is the name of a file +dnl it should be seeing, to verify it is in the same directory. + +AC_INIT(dftables.c) +AC_CONFIG_SRCDIR([pcre.h]) + +dnl A safety precaution + +AC_PREREQ(2.57) + +dnl Arrange to build config.h from config.h.in. +dnl Manual says this macro should come right after AC_INIT. +AC_CONFIG_HEADER(config.h) + +dnl Default values for miscellaneous macros + +POSIX_MALLOC_THRESHOLD=-DPOSIX_MALLOC_THRESHOLD=10 + +dnl Provide versioning information for libtool shared libraries that +dnl are built by default on Unix systems. + +PCRE_LIB_VERSION=0:1:0 +PCRE_POSIXLIB_VERSION=0:0:0 +PCRE_CPPLIB_VERSION=0:0:0 + +dnl Find the PCRE version from the pcre.h file. The PCRE_VERSION variable is +dnl substituted in pcre-config.in. + +PCRE_MAJOR=`grep '#define PCRE_MAJOR' ${srcdir}/pcre.h | cut -c 29-` +PCRE_MINOR=`grep '#define PCRE_MINOR' ${srcdir}/pcre.h | cut -c 29-` +PCRE_PRERELEASE=`grep '#define PCRE_PRERELEASE' ${srcdir}/pcre.h | cut -c 29-` +PCRE_VERSION=${PCRE_MAJOR}.${PCRE_MINOR}${PCRE_PRERELEASE} + +dnl Handle --disable-cpp + +AC_ARG_ENABLE(cpp, +[ --disable-cpp disable C++ support], +want_cpp="$enableval", want_cpp=yes) + +dnl Checks for programs. + +AC_PROG_CC + +dnl Test for C++ for the C++ wrapper libpcrecpp. It seems, however, that +dnl AC_PROC_CXX will set $CXX to "g++" when no C++ compiler is installed, even +dnl though that is completely bogus. (This may happen only on certain systems +dnl with certain versions of autoconf, of course.) An attempt to include this +dnl test inside a check for want_cpp was criticized by a libtool expert, who +dnl tells me that it isn't allowed. + +AC_PROG_CXX + +dnl The icc compiler has the same options as gcc, so let the rest of the +dnl configure script think it has gcc when setting up dnl options etc. +dnl This is a nasty hack which no longer seems necessary with the update +dnl to the latest libtool files, so I have commented it out. +dnl +dnl if test "$CC" = "icc" ; then GCC=yes ; fi + +AC_PROG_INSTALL +AC_LIBTOOL_WIN32_DLL +AC_PROG_LIBTOOL + +dnl We need to find a compiler for compiling a program to run on the local host +dnl while building. It needs to be different from CC when cross-compiling. +dnl There is a macro called AC_PROG_CC_FOR_BUILD in the GNU archive for +dnl figuring this out automatically. Unfortunately, it does not work with the +dnl latest versions of autoconf. So for the moment, we just default to the +dnl same values as the "main" compiler. People who are cross-compiling will +dnl just have to adjust the Makefile by hand or set these values when they +dnl run "configure". + +CC_FOR_BUILD=${CC_FOR_BUILD:-'$(CC)'} +CXX_FOR_BUILD=${CXX_FOR_BUILD:-'$(CXX)'} +CFLAGS_FOR_BUILD=${CFLAGS_FOR_BUILD:-'$(CFLAGS)'} +CPPFLAGS_FOR_BUILD=${CFLAGS_FOR_BUILD:-'$(CPPFLAGS)'} +CXXFLAGS_FOR_BUILD=${CXXFLAGS_FOR_BUILD:-'$(CXXFLAGS)'} +BUILD_EXEEXT=${BUILD_EXEEXT:-'$(EXEEXT)'} +BUILD_OBJEXT=${BUILD_OBJEXT:-'$(OBJEXT)'} + +dnl Checks for header files. + +AC_HEADER_STDC +AC_CHECK_HEADERS(limits.h) + +dnl The files below are C++ header files. One person told me (PH) that +dnl AC_LANG_CPLUSPLUS unsets CXX if it was explicitly set to something which +dnl doesn't work. However, this doesn't always seem to be the case. + +if test "x$want_cpp" = "xyes" -a -n "$CXX" +then +AC_LANG_SAVE +AC_LANG_CPLUSPLUS + +dnl We could be more clever here, given we're doing AC_SUBST with this +dnl (eg set a var to be the name of the include file we want). But we're not +dnl so it's easy to change back to 'regular' autoconf vars if we needed to. +AC_CHECK_HEADERS(string, [pcre_have_cpp_headers="1"], + [pcre_have_cpp_headers="0"]) +AC_CHECK_HEADERS(bits/type_traits.h, [pcre_have_bits_type_traits="1"], + [pcre_have_bits_type_traits="0"]) +AC_CHECK_HEADERS(type_traits.h, [pcre_have_type_traits="1"], + [pcre_have_type_traits="0"]) +dnl Using AC_SUBST eliminates the need to include config.h in a public .h file +AC_SUBST(pcre_have_bits_type_traits) +AC_SUBST(pcre_have_type_traits) +AC_LANG_RESTORE +fi + +dnl From the above, we now have enough info to know if C++ is fully installed +if test "x$want_cpp" = "xyes" -a -n "$CXX" -a "$pcre_have_cpp_headers" = 1; then + MAYBE_CPP_TARGETS='$(CPP_TARGETS)' + HAVE_CPP= +else + MAYBE_CPP_TARGETS= + HAVE_CPP="#" +fi +AC_SUBST(MAYBE_CPP_TARGETS) +AC_SUBST(HAVE_CPP) + +dnl Checks for typedefs, structures, and compiler characteristics. + +AC_C_CONST +AC_TYPE_SIZE_T + +AC_CHECK_TYPES([long long], [pcre_have_long_long="1"], [pcre_have_long_long="0"]) +AC_CHECK_TYPES([unsigned long long], [pcre_have_ulong_long="1"], [pcre_have_ulong_long="0"]) +AC_SUBST(pcre_have_long_long) +AC_SUBST(pcre_have_ulong_long) + +dnl Checks for library functions. + +AC_CHECK_FUNCS(bcopy memmove strerror strtoq strtoll) + +dnl Handle --enable-utf8 + +AC_ARG_ENABLE(utf8, +[ --enable-utf8 enable UTF8 support], +if test "$enableval" = "yes"; then + UTF8=-DSUPPORT_UTF8 +fi +) + +dnl Handle --enable-unicode-properties + +AC_ARG_ENABLE(unicode-properties, +[ --enable-unicode-properties enable Unicode properties support], +if test "$enableval" = "yes"; then + UCP=-DSUPPORT_UCP +fi +) + +dnl Handle --enable-newline-is-cr + +AC_ARG_ENABLE(newline-is-cr, +[ --enable-newline-is-cr use CR as the newline character], +if test "$enableval" = "yes"; then + NEWLINE=-DNEWLINE=13 +fi +) + +dnl Handle --enable-newline-is-lf + +AC_ARG_ENABLE(newline-is-lf, +[ --enable-newline-is-lf use LF as the newline character], +if test "$enableval" = "yes"; then + NEWLINE=-DNEWLINE=10 +fi +) + +dnl Handle --enable-newline-is-crlf + +AC_ARG_ENABLE(newline-is-crlf, +[ --enable-newline-is-crlf use CRLF as the newline sequence], +if test "$enableval" = "yes"; then + NEWLINE=-DNEWLINE=3338 +fi +) + +dnl Handle --enable-ebcdic + +AC_ARG_ENABLE(ebcdic, +[ --enable-ebcdic assume EBCDIC coding rather than ASCII], +if test "$enableval" == "yes"; then + EBCDIC=-DEBCDIC=1 +fi +) + +dnl Handle --disable-stack-for-recursion + +AC_ARG_ENABLE(stack-for-recursion, +[ --disable-stack-for-recursion disable use of stack recursion when matching], +if test "$enableval" = "no"; then + NO_RECURSE=-DNO_RECURSE +fi +) + +dnl There doesn't seem to be a straightforward way of having parameters +dnl that set values, other than fudging the --with thing. So that's what +dnl I've done. + +dnl Handle --with-posix-malloc-threshold=n + +AC_ARG_WITH(posix-malloc-threshold, +[ --with-posix-malloc-threshold=10 threshold for POSIX malloc usage], + POSIX_MALLOC_THRESHOLD=-DPOSIX_MALLOC_THRESHOLD=$withval +) + +dnl Handle --with-link-size=n + +AC_ARG_WITH(link-size, +[ --with-link-size=2 internal link size (2, 3, or 4 allowed)], + LINK_SIZE=-DLINK_SIZE=$withval +) + +dnl Handle --with-match-limit=n + +AC_ARG_WITH(match-limit, +[ --with-match-limit=10000000 default limit on internal looping], + MATCH_LIMIT=-DMATCH_LIMIT=$withval +) + +dnl Handle --with-match-limit_recursion=n + +AC_ARG_WITH(match-limit-recursion, +[ --with-match-limit-recursion=10000000 default limit on internal recursion], + MATCH_LIMIT_RECURSION=-DMATCH_LIMIT_RECURSION=$withval +) + +dnl Unicode character property support implies UTF-8 support + +if test "$UCP" != "" ; then + UTF8=-DSUPPORT_UTF8 +fi + +dnl "Export" these variables + +AC_SUBST(BUILD_EXEEXT) +AC_SUBST(BUILD_OBJEXT) +AC_SUBST(CC_FOR_BUILD) +AC_SUBST(CXX_FOR_BUILD) +AC_SUBST(CFLAGS_FOR_BUILD) +AC_SUBST(CXXFLAGS_FOR_BUILD) +AC_SUBST(CXXLDFLAGS) +AC_SUBST(EBCDIC) +AC_SUBST(HAVE_MEMMOVE) +AC_SUBST(HAVE_STRERROR) +AC_SUBST(LINK_SIZE) +AC_SUBST(MATCH_LIMIT) +AC_SUBST(MATCH_LIMIT_RECURSION) +AC_SUBST(NEWLINE) +AC_SUBST(NO_RECURSE) +AC_SUBST(PCRE_LIB_VERSION) +AC_SUBST(PCRE_POSIXLIB_VERSION) +AC_SUBST(PCRE_CPPLIB_VERSION) +AC_SUBST(PCRE_VERSION) +AC_SUBST(POSIX_MALLOC_THRESHOLD) +AC_SUBST(UCP) +AC_SUBST(UTF8) + +dnl Stuff to make MinGW work better. Special treatment is no longer +dnl needed for Cygwin. + +case $host_os in +mingw* ) + POSIX_OBJ=pcreposix.o + POSIX_LOBJ=pcreposix.lo + POSIX_LIB= + ON_WINDOWS= + NOT_ON_WINDOWS="#" + WIN_PREFIX= + ;; +* ) + ON_WINDOWS="#" + NOT_ON_WINDOWS= + POSIX_OBJ= + POSIX_LOBJ= + POSIX_LIB=libpcreposix.la + WIN_PREFIX= + ;; +esac +AC_SUBST(WIN_PREFIX) +AC_SUBST(ON_WINDOWS) +AC_SUBST(NOT_ON_WINDOWS) +AC_SUBST(POSIX_OBJ) +AC_SUBST(POSIX_LOBJ) +AC_SUBST(POSIX_LIB) + +if test "x$enable_shared" = "xno" ; then + AC_DEFINE([PCRE_STATIC],[1],[to link statically]) +fi + +dnl This must be last; it determines what files are written as well as config.h +AC_OUTPUT(Makefile pcre-config:pcre-config.in libpcre.pc:libpcre.pc.in pcrecpparg.h:pcrecpparg.h.in pcre_stringpiece.h:pcre_stringpiece.h.in RunGrepTest:RunGrepTest.in RunTest:RunTest.in,[chmod a+x RunTest RunGrepTest pcre-config]) diff --git a/libs/pcre/dftables.c b/libs/pcre/dftables.c new file mode 100644 index 0000000000..5ba207aeb3 --- /dev/null +++ b/libs/pcre/dftables.c @@ -0,0 +1,172 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This is a freestanding support program to generate a file containing default +character tables for PCRE. The tables are built according to the default C +locale. Now that pcre_maketables is a function visible to the outside world, we +make use of its code from here in order to be consistent. */ + +#include +#include +#include + +#include "pcre_internal.h" + +#define DFTABLES /* pcre_maketables.c notices this */ +#include "pcre_maketables.c" + + +int main(int argc, char **argv) +{ +int i; +FILE *f; +const unsigned char *tables = pcre_maketables(); +const unsigned char *base_of_tables = tables; + +if (argc != 2) + { + fprintf(stderr, "dftables: one filename argument is required\n"); + return 1; + } + +f = fopen(argv[1], "wb"); +if (f == NULL) + { + fprintf(stderr, "dftables: failed to open %s for writing\n", argv[1]); + return 1; + } + +/* There are two fprintf() calls here, because gcc in pedantic mode complains +about the very long string otherwise. */ + +fprintf(f, + "/*************************************************\n" + "* Perl-Compatible Regular Expressions *\n" + "*************************************************/\n\n" + "/* This file is automatically written by the dftables auxiliary \n" + "program. If you edit it by hand, you might like to edit the Makefile to \n" + "prevent its ever being regenerated.\n\n"); +fprintf(f, + "This file contains the default tables for characters with codes less than\n" + "128 (ASCII characters). These tables are used when no external tables are\n" + "passed to PCRE. */\n\n" + "const unsigned char _pcre_default_tables[] = {\n\n" + "/* This table is a lower casing table. */\n\n"); + +fprintf(f, " "); +for (i = 0; i < 256; i++) + { + if ((i & 7) == 0 && i != 0) fprintf(f, "\n "); + fprintf(f, "%3d", *tables++); + if (i != 255) fprintf(f, ","); + } +fprintf(f, ",\n\n"); + +fprintf(f, "/* This table is a case flipping table. */\n\n"); + +fprintf(f, " "); +for (i = 0; i < 256; i++) + { + if ((i & 7) == 0 && i != 0) fprintf(f, "\n "); + fprintf(f, "%3d", *tables++); + if (i != 255) fprintf(f, ","); + } +fprintf(f, ",\n\n"); + +fprintf(f, + "/* This table contains bit maps for various character classes.\n" + "Each map is 32 bytes long and the bits run from the least\n" + "significant end of each byte. The classes that have their own\n" + "maps are: space, xdigit, digit, upper, lower, word, graph\n" + "print, punct, and cntrl. Other classes are built from combinations. */\n\n"); + +fprintf(f, " "); +for (i = 0; i < cbit_length; i++) + { + if ((i & 7) == 0 && i != 0) + { + if ((i & 31) == 0) fprintf(f, "\n"); + fprintf(f, "\n "); + } + fprintf(f, "0x%02x", *tables++); + if (i != cbit_length - 1) fprintf(f, ","); + } +fprintf(f, ",\n\n"); + +fprintf(f, + "/* This table identifies various classes of character by individual bits:\n" + " 0x%02x white space character\n" + " 0x%02x letter\n" + " 0x%02x decimal digit\n" + " 0x%02x hexadecimal digit\n" + " 0x%02x alphanumeric or '_'\n" + " 0x%02x regular expression metacharacter or binary zero\n*/\n\n", + ctype_space, ctype_letter, ctype_digit, ctype_xdigit, ctype_word, + ctype_meta); + +fprintf(f, " "); +for (i = 0; i < 256; i++) + { + if ((i & 7) == 0 && i != 0) + { + fprintf(f, " /* "); + if (isprint(i-8)) fprintf(f, " %c -", i-8); + else fprintf(f, "%3d-", i-8); + if (isprint(i-1)) fprintf(f, " %c ", i-1); + else fprintf(f, "%3d", i-1); + fprintf(f, " */\n "); + } + fprintf(f, "0x%02x", *tables++); + if (i != 255) fprintf(f, ","); + } + +fprintf(f, "};/* "); +if (isprint(i-8)) fprintf(f, " %c -", i-8); + else fprintf(f, "%3d-", i-8); +if (isprint(i-1)) fprintf(f, " %c ", i-1); + else fprintf(f, "%3d", i-1); +fprintf(f, " */\n\n/* End of chartables.c */\n"); + +fclose(f); +free((void *)base_of_tables); +return 0; +} + +/* End of dftables.c */ diff --git a/libs/pcre/doc/Tech.Notes b/libs/pcre/doc/Tech.Notes new file mode 100644 index 0000000000..21dbe1f9b5 --- /dev/null +++ b/libs/pcre/doc/Tech.Notes @@ -0,0 +1,348 @@ +Technical Notes about PCRE +-------------------------- + +These are very rough technical notes that record potentially useful information +about PCRE internals. + +Historical note 1 +----------------- + +Many years ago I implemented some regular expression functions to an algorithm +suggested by Martin Richards. These were not Unix-like in form, and were quite +restricted in what they could do by comparison with Perl. The interesting part +about the algorithm was that the amount of space required to hold the compiled +form of an expression was known in advance. The code to apply an expression did +not operate by backtracking, as the original Henry Spencer code and current +Perl code does, but instead checked all possibilities simultaneously by keeping +a list of current states and checking all of them as it advanced through the +subject string. In the terminology of Jeffrey Friedl's book, it was a "DFA +algorithm". When the pattern was all used up, all remaining states were +possible matches, and the one matching the longest subset of the subject string +was chosen. This did not necessarily maximize the individual wild portions of +the pattern, as is expected in Unix and Perl-style regular expressions. + +Historical note 2 +----------------- + +By contrast, the code originally written by Henry Spencer (which was +subsequently heavily modified for Perl) compiles the expression twice: once in +a dummy mode in order to find out how much store will be needed, and then for +real. (The Perl version probably doesn't do this any more; I'm talking about +the original library.) The execution function operates by backtracking and +maximizing (or, optionally, minimizing in Perl) the amount of the subject that +matches individual wild portions of the pattern. This is an "NFA algorithm" in +Friedl's terminology. + +OK, here's the real stuff +------------------------- + +For the set of functions that form the "basic" PCRE library (which are +unrelated to those mentioned above), I tried at first to invent an algorithm +that used an amount of store bounded by a multiple of the number of characters +in the pattern, to save on compiling time. However, because of the greater +complexity in Perl regular expressions, I couldn't do this. In any case, a +first pass through the pattern is needed, for a number of reasons. PCRE works +by running a very degenerate first pass to calculate a maximum store size, and +then a second pass to do the real compile - which may use a bit less than the +predicted amount of store. The idea is that this is going to turn out faster +because the first pass is degenerate and the second pass can just store stuff +straight into the vector, which it knows is big enough. It does make the +compiling functions bigger, of course, but they have become quite big anyway to +handle all the Perl stuff. + +Traditional matching function +----------------------------- + +The "traditional", and original, matching function is called pcre_exec(), and +it implements an NFA algorithm, similar to the original Henry Spencer algorithm +and the way that Perl works. Not surprising, since it is intended to be as +compatible with Perl as possible. This is the function most users of PCRE will +use most of the time. + +Supplementary matching function +------------------------------- + +From PCRE 6.0, there is also a supplementary matching function called +pcre_dfa_exec(). This implements a DFA matching algorithm that searches +simultaneously for all possible matches that start at one point in the subject +string. (Going back to my roots: see Historical Note 1 above.) This function +intreprets the same compiled pattern data as pcre_exec(); however, not all the +facilities are available, and those that are do not always work in quite the +same way. See the user documentation for details. + +Format of compiled patterns +--------------------------- + +The compiled form of a pattern is a vector of bytes, containing items of +variable length. The first byte in an item is an opcode, and the length of the +item is either implicit in the opcode or contained in the data bytes that +follow it. + +In many cases below "two-byte" data values are specified. This is in fact just +a default. PCRE can be compiled to use 3-byte or 4-byte values (impairing the +performance). This is necessary only when patterns whose compiled length is +greater than 64K are going to be processed. In this description, we assume the +"normal" compilation options. + +A list of all the opcodes follows: + +Opcodes with no following data +------------------------------ + +These items are all just one byte long + + OP_END end of pattern + OP_ANY match any character + OP_ANYBYTE match any single byte, even in UTF-8 mode + OP_SOD match start of data: \A + OP_SOM, start of match (subject + offset): \G + OP_CIRC ^ (start of data, or after \n in multiline) + OP_NOT_WORD_BOUNDARY \W + OP_WORD_BOUNDARY \w + OP_NOT_DIGIT \D + OP_DIGIT \d + OP_NOT_WHITESPACE \S + OP_WHITESPACE \s + OP_NOT_WORDCHAR \W + OP_WORDCHAR \w + OP_EODN match end of data or \n at end: \Z + OP_EOD match end of data: \z + OP_DOLL $ (end of data, or before \n in multiline) + OP_EXTUNI match an extended Unicode character + + +Repeating single characters +--------------------------- + +The common repeats (*, +, ?) when applied to a single character use the +following opcodes: + + OP_STAR + OP_MINSTAR + OP_PLUS + OP_MINPLUS + OP_QUERY + OP_MINQUERY + +In ASCII mode, these are two-byte items; in UTF-8 mode, the length is variable. +Those with "MIN" in their name are the minimizing versions. Each is followed by +the character that is to be repeated. Other repeats make use of + + OP_UPTO + OP_MINUPTO + OP_EXACT + +which are followed by a two-byte count (most significant first) and the +repeated character. OP_UPTO matches from 0 to the given number. A repeat with a +non-zero minimum and a fixed maximum is coded as an OP_EXACT followed by an +OP_UPTO (or OP_MINUPTO). + + +Repeating character types +------------------------- + +Repeats of things like \d are done exactly as for single characters, except +that instead of a character, the opcode for the type is stored in the data +byte. The opcodes are: + + OP_TYPESTAR + OP_TYPEMINSTAR + OP_TYPEPLUS + OP_TYPEMINPLUS + OP_TYPEQUERY + OP_TYPEMINQUERY + OP_TYPEUPTO + OP_TYPEMINUPTO + OP_TYPEEXACT + + +Match by Unicode property +------------------------- + +OP_PROP and OP_NOTPROP are used for positive and negative matches of a +character by testing its Unicode property (the \p and \P escape sequences). +Each is followed by two bytes that encode the desired property as a type and a +value. + +Repeats of these items use the OP_TYPESTAR etc. set of opcodes, followed by +three bytes: OP_PROP or OP_NOTPROP and then the desired property type and +value. + + +Matching literal characters +--------------------------- + +The OP_CHAR opcode is followed by a single character that is to be matched +casefully. For caseless matching, OP_CHARNC is used. In UTF-8 mode, the +character may be more than one byte long. (Earlier versions of PCRE used +multi-character strings, but this was changed to allow some new features to be +added.) + + +Character classes +----------------- + +If there is only one character, OP_CHAR or OP_CHARNC is used for a positive +class, and OP_NOT for a negative one (that is, for something like [^a]). +However, in UTF-8 mode, the use of OP_NOT applies only to characters with +values < 128, because OP_NOT is confined to single bytes. + +Another set of repeating opcodes (OP_NOTSTAR etc.) are used for a repeated, +negated, single-character class. The normal ones (OP_STAR etc.) are used for a +repeated positive single-character class. + +When there's more than one character in a class and all the characters are less +than 256, OP_CLASS is used for a positive class, and OP_NCLASS for a negative +one. In either case, the opcode is followed by a 32-byte bit map containing a 1 +bit for every character that is acceptable. The bits are counted from the least +significant end of each byte. + +The reason for having both OP_CLASS and OP_NCLASS is so that, in UTF-8 mode, +subject characters with values greater than 256 can be handled correctly. For +OP_CLASS they don't match, whereas for OP_NCLASS they do. + +For classes containing characters with values > 255, OP_XCLASS is used. It +optionally uses a bit map (if any characters lie within it), followed by a list +of pairs and single characters. There is a flag character than indicates +whether it's a positive or a negative class. + + +Back references +--------------- + +OP_REF is followed by two bytes containing the reference number. + + +Repeating character classes and back references +----------------------------------------------- + +Single-character classes are handled specially (see above). This applies to +OP_CLASS and OP_REF. In both cases, the repeat information follows the base +item. The matching code looks at the following opcode to see if it is one of + + OP_CRSTAR + OP_CRMINSTAR + OP_CRPLUS + OP_CRMINPLUS + OP_CRQUERY + OP_CRMINQUERY + OP_CRRANGE + OP_CRMINRANGE + +All but the last two are just single-byte items. The others are followed by +four bytes of data, comprising the minimum and maximum repeat counts. + + +Brackets and alternation +------------------------ + +A pair of non-capturing (round) brackets is wrapped round each expression at +compile time, so alternation always happens in the context of brackets. + +Non-capturing brackets use the opcode OP_BRA, while capturing brackets use +OP_BRA+1, OP_BRA+2, etc. [Note for North Americans: "bracket" to some English +speakers, including myself, can be round, square, curly, or pointy. Hence this +usage.] + +Originally PCRE was limited to 99 capturing brackets (so as not to use up all +the opcodes). From release 3.5, there is no limit. What happens is that the +first ones, up to EXTRACT_BASIC_MAX are handled with separate opcodes, as +above. If there are more, the opcode is set to EXTRACT_BASIC_MAX+1, and the +first operation in the bracket is OP_BRANUMBER, followed by a 2-byte bracket +number. This opcode is ignored while matching, but is fished out when handling +the bracket itself. (They could have all been done like this, but I was making +minimal changes.) + +A bracket opcode is followed by LINK_SIZE bytes which give the offset to the +next alternative OP_ALT or, if there aren't any branches, to the matching +OP_KET opcode. Each OP_ALT is followed by LINK_SIZE bytes giving the offset to +the next one, or to the OP_KET opcode. + +OP_KET is used for subpatterns that do not repeat indefinitely, while +OP_KETRMIN and OP_KETRMAX are used for indefinite repetitions, minimally or +maximally respectively. All three are followed by LINK_SIZE bytes giving (as a +positive number) the offset back to the matching OP_BRA opcode. + +If a subpattern is quantified such that it is permitted to match zero times, it +is preceded by one of OP_BRAZERO or OP_BRAMINZERO. These are single-byte +opcodes which tell the matcher that skipping this subpattern entirely is a +valid branch. + +A subpattern with an indefinite maximum repetition is replicated in the +compiled data its minimum number of times (or once with OP_BRAZERO if the +minimum is zero), with the final copy terminating with OP_KETRMIN or OP_KETRMAX +as appropriate. + +A subpattern with a bounded maximum repetition is replicated in a nested +fashion up to the maximum number of times, with OP_BRAZERO or OP_BRAMINZERO +before each replication after the minimum, so that, for example, (abc){2,5} is +compiled as (abc)(abc)((abc)((abc)(abc)?)?)?. + + +Assertions +---------- + +Forward assertions are just like other subpatterns, but starting with one of +the opcodes OP_ASSERT or OP_ASSERT_NOT. Backward assertions use the opcodes +OP_ASSERTBACK and OP_ASSERTBACK_NOT, and the first opcode inside the assertion +is OP_REVERSE, followed by a two byte count of the number of characters to move +back the pointer in the subject string. When operating in UTF-8 mode, the count +is a character count rather than a byte count. A separate count is present in +each alternative of a lookbehind assertion, allowing them to have different +fixed lengths. + + +Once-only subpatterns +--------------------- + +These are also just like other subpatterns, but they start with the opcode +OP_ONCE. + + +Conditional subpatterns +----------------------- + +These are like other subpatterns, but they start with the opcode OP_COND. If +the condition is a back reference, this is stored at the start of the +subpattern using the opcode OP_CREF followed by two bytes containing the +reference number. If the condition is "in recursion" (coded as "(?(R)"), the +same scheme is used, with a "reference number" of 0xffff. Otherwise, a +conditional subpattern always starts with one of the assertions. + + +Recursion +--------- + +Recursion either matches the current regex, or some subexpression. The opcode +OP_RECURSE is followed by an value which is the offset to the starting bracket +from the start of the whole pattern. From release 6.5, OP_RECURSE is +automatically wrapped inside OP_ONCE brackets (because otherwise some patterns +broke it). OP_RECURSE is also used for "subroutine" calls, even though they +are not strictly a recursion. + + +Callout +------- + +OP_CALLOUT is followed by one byte of data that holds a callout number in the +range 0 to 254 for manual callouts, or 255 for an automatic callout. In both +cases there follows a two-byte value giving the offset in the pattern to the +start of the following item, and another two-byte item giving the length of the +next item. + + +Changing options +---------------- + +If any of the /i, /m, or /s options are changed within a pattern, an OP_OPT +opcode is compiled, followed by one byte containing the new settings of these +flags. If there are several alternatives, there is an occurrence of OP_OPT at +the start of all those following the first options change, to set appropriate +options for the start of the alternative. Immediately after the end of the +group there is another such item to reset the flags to their previous values. A +change of flag right at the very start of the pattern can be handled entirely +at compile time, and so does not cause anything to be put into the compiled +data. + +Philip Hazel +June 2006 diff --git a/libs/pcre/doc/html/index.html b/libs/pcre/doc/html/index.html new file mode 100644 index 0000000000..68932e85ce --- /dev/null +++ b/libs/pcre/doc/html/index.html @@ -0,0 +1,128 @@ + + +PCRE specification + + +

Perl-compatible Regular Expressions (PCRE)

+

+The HTML documentation for PCRE comprises the following pages: +

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
pcre  Introductory page
pcreapi  PCRE's native API
pcrebuild  Options for building PCRE
pcrecallout  The callout facility
pcrecompat  Compability with Perl
pcrecpp  The C++ wrapper for the PCRE library
pcregrep  The pcregrep command
pcrematching  Discussion of the two matching algorithms
pcrepartial  Using PCRE for partial matching
pcrepattern  Specification of the regular expressions supported by PCRE
pcreperform  Some comments on performance
pcreposix  The POSIX API to the PCRE library
pcreprecompile  How to save and re-use compiled patterns
pcresample  Description of the sample program
pcrestack  Discussion of PCRE's stack usage
pcretest  The pcretest command for testing PCRE
+ +

+There are also individual pages that summarize the interface for each function +in the library: +

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
pcre_compile  Compile a regular expression
pcre_compile2  Compile a regular expression (alternate interface)
pcre_config  Show build-time configuration options
pcre_copy_named_substring  Extract named substring into given buffer
pcre_copy_substring  Extract numbered substring into given buffer
pcre_dfa_exec  Match a compiled pattern to a subject string + (DFA algorithm; not Perl compatible)
pcre_exec  Match a compiled pattern to a subject string + (Perl compatible)
pcre_free_substring  Free extracted substring
pcre_free_substring_list  Free list of extracted substrings
pcre_fullinfo  Extract information about a pattern
pcre_get_named_substring  Extract named substring into new memory
pcre_get_stringnumber  Convert captured string name to number
pcre_get_substring  Extract numbered substring into new memory
pcre_get_substring_list  Extract all substrings into new memory
pcre_info  Obsolete information extraction function
pcre_maketables  Build character tables in current locale
pcre_refcount  Maintain reference count in compiled pattern
pcre_study  Study a compiled pattern
pcre_version  Return PCRE version and release date
+ + diff --git a/libs/pcre/doc/html/pcre.html b/libs/pcre/doc/html/pcre.html new file mode 100644 index 0000000000..eb2102dd4c --- /dev/null +++ b/libs/pcre/doc/html/pcre.html @@ -0,0 +1,252 @@ + + +pcre specification + + +

pcre man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+

+
INTRODUCTION
+

+The PCRE library is a set of functions that implement regular expression +pattern matching using the same syntax and semantics as Perl, with just a few +differences. The current implementation of PCRE (release 6.x) corresponds +approximately with Perl 5.8, including support for UTF-8 encoded strings and +Unicode general category properties. However, this support has to be explicitly +enabled; it is not the default. +

+

+In addition to the Perl-compatible matching function, PCRE also contains an +alternative matching function that matches the same compiled patterns in a +different way. In certain circumstances, the alternative function has some +advantages. For a discussion of the two matching algorithms, see the +pcrematching +page. +

+

+PCRE is written in C and released as a C library. A number of people have +written wrappers and interfaces of various kinds. In particular, Google Inc. +have provided a comprehensive C++ wrapper. This is now included as part of the +PCRE distribution. The +pcrecpp +page has details of this interface. Other people's contributions can be found +in the Contrib directory at the primary FTP site, which is: +ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre +

+

+Details of exactly which Perl regular expression features are and are not +supported by PCRE are given in separate documents. See the +pcrepattern +and +pcrecompat +pages. +

+

+Some features of PCRE can be included, excluded, or changed when the library is +built. The +pcre_config() +function makes it possible for a client to discover which features are +available. The features themselves are described in the +pcrebuild +page. Documentation about building PCRE for various operating systems can be +found in the README file in the source distribution. +

+

+The library contains a number of undocumented internal functions and data +tables that are used by more than one of the exported external functions, but +which are not intended for use by external callers. Their names all begin with +"_pcre_", which hopefully will not provoke any name clashes. In some +environments, it is possible to control which external symbols are exported +when a shared library is built, and in these cases the undocumented symbols are +not exported. +

+
USER DOCUMENTATION
+

+The user documentation for PCRE comprises a number of different sections. In +the "man" format, each of these is a separate "man page". In the HTML format, +each is a separate page, linked from the index page. In the plain text format, +all the sections are concatenated, for ease of searching. The sections are as +follows: +

+  pcre              this document
+  pcreapi           details of PCRE's native C API
+  pcrebuild         options for building PCRE
+  pcrecallout       details of the callout feature
+  pcrecompat        discussion of Perl compatibility
+  pcrecpp           details of the C++ wrapper
+  pcregrep          description of the pcregrep command
+  pcrematching      discussion of the two matching algorithms
+  pcrepartial       details of the partial matching facility
+  pcrepattern       syntax and semantics of supported regular expressions
+  pcreperform       discussion of performance issues
+  pcreposix         the POSIX-compatible C API
+  pcreprecompile    details of saving and re-using precompiled patterns
+  pcresample        discussion of the sample program
+  pcrestack         discussion of stack usage
+  pcretest          description of the pcretest testing command
+
+In addition, in the "man" and HTML formats, there is a short page for each +C library function, listing its arguments and results. +

+
LIMITATIONS
+

+There are some size limitations in PCRE but it is hoped that they will never in +practice be relevant. +

+

+The maximum length of a compiled pattern is 65539 (sic) bytes if PCRE is +compiled with the default internal linkage size of 2. If you want to process +regular expressions that are truly enormous, you can compile PCRE with an +internal linkage size of 3 or 4 (see the README file in the source +distribution and the +pcrebuild +documentation for details). In these cases the limit is substantially larger. +However, the speed of execution will be slower. +

+

+All values in repeating quantifiers must be less than 65536. The maximum +compiled length of subpattern with an explicit repeat count is 30000 bytes. The +maximum number of capturing subpatterns is 65535. +

+

+There is no limit to the number of non-capturing subpatterns, but the maximum +depth of nesting of all kinds of parenthesized subpattern, including capturing +subpatterns, assertions, and other types of subpattern, is 200. +

+

+The maximum length of name for a named subpattern is 32, and the maximum number +of named subpatterns is 10000. +

+

+The maximum length of a subject string is the largest positive number that an +integer variable can hold. However, when using the traditional matching +function, PCRE uses recursion to handle subpatterns and indefinite repetition. +This means that the available stack space may limit the size of a subject +string that can be processed by certain patterns. For a discussion of stack +issues, see the +pcrestack +documentation. +

+
UTF-8 AND UNICODE PROPERTY SUPPORT
+

+From release 3.3, PCRE has had some support for character strings encoded in +the UTF-8 format. For release 4.0 this was greatly extended to cover most +common requirements, and in release 5.0 additional support for Unicode general +category properties was added. +

+

+In order process UTF-8 strings, you must build PCRE to include UTF-8 support in +the code, and, in addition, you must call +pcre_compile() +with the PCRE_UTF8 option flag. When you do this, both the pattern and any +subject strings that are matched against it are treated as UTF-8 strings +instead of just strings of bytes. +

+

+If you compile PCRE with UTF-8 support, but do not use it at run time, the +library will be a bit bigger, but the additional run time overhead is limited +to testing the PCRE_UTF8 flag in several places, so should not be very large. +

+

+If PCRE is built with Unicode character property support (which implies UTF-8 +support), the escape sequences \p{..}, \P{..}, and \X are supported. +The available properties that can be tested are limited to the general +category properties such as Lu for an upper case letter or Nd for a decimal +number, the Unicode script names such as Arabic or Han, and the derived +properties Any and L&. A full list is given in the +pcrepattern +documentation. Only the short names for properties are supported. For example, +\p{L} matches a letter. Its Perl synonym, \p{Letter}, is not supported. +Furthermore, in Perl, many properties may optionally be prefixed by "Is", for +compatibility with Perl 5.6. PCRE does not support this. +

+

+The following comments apply when PCRE is running in UTF-8 mode: +

+

+1. When you set the PCRE_UTF8 flag, the strings passed as patterns and subjects +are checked for validity on entry to the relevant functions. If an invalid +UTF-8 string is passed, an error return is given. In some situations, you may +already know that your strings are valid, and therefore want to skip these +checks in order to improve performance. If you set the PCRE_NO_UTF8_CHECK flag +at compile time or at run time, PCRE assumes that the pattern or subject it +is given (respectively) contains only valid UTF-8 codes. In this case, it does +not diagnose an invalid UTF-8 string. If you pass an invalid UTF-8 string to +PCRE when PCRE_NO_UTF8_CHECK is set, the results are undefined. Your program +may crash. +

+

+2. An unbraced hexadecimal escape sequence (such as \xb3) matches a two-byte +UTF-8 character if the value is greater than 127. +

+

+3. Octal numbers up to \777 are recognized, and match two-byte UTF-8 +characters for values greater than \177. +

+

+4. Repeat quantifiers apply to complete UTF-8 characters, not to individual +bytes, for example: \x{100}{3}. +

+

+5. The dot metacharacter matches one UTF-8 character instead of a single byte. +

+

+6. The escape sequence \C can be used to match a single byte in UTF-8 mode, +but its use can lead to some strange effects. This facility is not available in +the alternative matching function, pcre_dfa_exec(). +

+

+7. The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly +test characters of any code value, but the characters that PCRE recognizes as +digits, spaces, or word characters remain the same set as before, all with +values less than 256. This remains true even when PCRE includes Unicode +property support, because to do otherwise would slow down PCRE in many common +cases. If you really want to test for a wider sense of, say, "digit", you +must use Unicode property tests such as \p{Nd}. +

+

+8. Similarly, characters that match the POSIX named character classes are all +low-valued characters. +

+

+9. Case-insensitive matching applies only to characters whose values are less +than 128, unless PCRE is built with Unicode property support. Even when Unicode +property support is available, PCRE still uses its own character tables when +checking the case of low-valued characters, so as not to degrade performance. +The Unicode property information is used only for characters with higher +values. Even when Unicode property support is available, PCRE supports +case-insensitive matching only when there is a one-to-one mapping between a +letter's cases. There are a small number of many-to-one mappings in Unicode; +these are not supported by PCRE. +

+
AUTHOR
+

+Philip Hazel +
+University Computing Service, +
+Cambridge CB2 3QG, England. +

+

+Putting an actual email address here seems to have been a spam magnet, so I've +taken it away. If you want to email me, use my initial and surname, separated +by a dot, at the domain ucs.cam.ac.uk. +Last updated: 05 June 2006 +
+Copyright © 1997-2006 University of Cambridge. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_compile.html b/libs/pcre/doc/html/pcre_compile.html new file mode 100644 index 0000000000..e46558b8db --- /dev/null +++ b/libs/pcre/doc/html/pcre_compile.html @@ -0,0 +1,80 @@ + + +pcre_compile specification + + +

pcre_compile man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+pcre *pcre_compile(const char *pattern, int options, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +

+
+DESCRIPTION +
+

+This function compiles a regular expression into an internal form. Its +arguments are: +

+  pattern       A zero-terminated string containing the
+                  regular expression to be compiled
+  options       Zero or more option bits
+  errptr        Where to put an error message
+  erroffset     Offset in pattern where error was found
+  tableptr      Pointer to character tables, or NULL to
+                  use the built-in default
+
+The option bits are: +
+  PCRE_ANCHORED         Force pattern anchoring
+  PCRE_AUTO_CALLOUT     Compile automatic callouts
+  PCRE_CASELESS         Do caseless matching
+  PCRE_DOLLAR_ENDONLY   $ not to match newline at end
+  PCRE_DOTALL           . matches anything including NL
+  PCRE_DUPNAMES         Allow duplicate names for subpatterns
+  PCRE_EXTENDED         Ignore whitespace and # comments
+  PCRE_EXTRA            PCRE extra features
+                          (not much use currently)
+  PCRE_FIRSTLINE        Force matching to be before newline
+  PCRE_MULTILINE        ^ and $ match newlines within data
+  PCRE_NEWLINE_CR       Set CR as the newline sequence
+  PCRE_NEWLINE_CRLF     Set CRLF as the newline sequence
+  PCRE_NEWLINE_LF       Set LF as the newline sequence
+  PCRE_NO_AUTO_CAPTURE  Disable numbered capturing paren-
+                          theses (named ones available)
+  PCRE_UNGREEDY         Invert greediness of quantifiers
+  PCRE_UTF8             Run in UTF-8 mode
+  PCRE_NO_UTF8_CHECK    Do not check the pattern for UTF-8
+                          validity (only relevant if
+                          PCRE_UTF8 is set)
+
+PCRE must be built with UTF-8 support in order to use PCRE_UTF8 and +PCRE_NO_UTF8_CHECK. +

+

+The yield of the function is a pointer to a private data structure that +contains the compiled pattern, or NULL if an error was detected. +

+

+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_compile2.html b/libs/pcre/doc/html/pcre_compile2.html new file mode 100644 index 0000000000..892ef6cfc7 --- /dev/null +++ b/libs/pcre/doc/html/pcre_compile2.html @@ -0,0 +1,85 @@ + + +pcre_compile2 specification + + +

pcre_compile2 man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+pcre *pcre_compile2(const char *pattern, int options, +int *errorcodeptr, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +

+
+DESCRIPTION +
+

+This function compiles a regular expression into an internal form. It is the +same as pcre_compile(), except for the addition of the errorcodeptr +argument. The arguments are: +

+

+

+  pattern       A zero-terminated string containing the
+                  regular expression to be compiled
+  options       Zero or more option bits
+  errorcodeptr  Where to put an error code
+  errptr        Where to put an error message
+  erroffset     Offset in pattern where error was found
+  tableptr      Pointer to character tables, or NULL to
+                  use the built-in default
+
+The option bits are: +
+  PCRE_ANCHORED         Force pattern anchoring
+  PCRE_AUTO_CALLOUT     Compile automatic callouts
+  PCRE_CASELESS         Do caseless matching
+  PCRE_DOLLAR_ENDONLY   $ not to match newline at end
+  PCRE_DOTALL           . matches anything including NL
+  PCRE_DUPNAMES         Allow duplicate names for subpatterns
+  PCRE_EXTENDED         Ignore whitespace and # comments
+  PCRE_EXTRA            PCRE extra features
+                          (not much use currently)
+  PCRE_FIRSTLINE        Force matching to be before newline
+  PCRE_MULTILINE        ^ and $ match newlines within data
+  PCRE_NEWLINE_CR       Set CR as the newline sequence
+  PCRE_NEWLINE_CRLF     Set CRLF as the newline sequence
+  PCRE_NEWLINE_LF       Set LF as the newline sequence
+  PCRE_NO_AUTO_CAPTURE  Disable numbered capturing paren-
+                          theses (named ones available)
+  PCRE_UNGREEDY         Invert greediness of quantifiers
+  PCRE_UTF8             Run in UTF-8 mode
+  PCRE_NO_UTF8_CHECK    Do not check the pattern for UTF-8
+                          validity (only relevant if
+                          PCRE_UTF8 is set)
+
+PCRE must be built with UTF-8 support in order to use PCRE_UTF8 and +PCRE_NO_UTF8_CHECK. +

+

+The yield of the function is a pointer to a private data structure that +contains the compiled pattern, or NULL if an error was detected. +

+

+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_config.html b/libs/pcre/doc/html/pcre_config.html new file mode 100644 index 0000000000..0ba0319490 --- /dev/null +++ b/libs/pcre/doc/html/pcre_config.html @@ -0,0 +1,62 @@ + + +pcre_config specification + + +

pcre_config man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_config(int what, void *where); +

+
+DESCRIPTION +
+

+This function makes it possible for a client program to find out which optional +features are available in the version of the PCRE library it is using. Its +arguments are as follows: +

+  what     A code specifying what information is required
+  where    Points to where to put the data
+
+The available codes are: +
+  PCRE_CONFIG_LINK_SIZE     Internal link size: 2, 3, or 4
+  PCRE_CONFIG_MATCH_LIMIT   Internal resource limit
+  PCRE_CONFIG_MATCH_LIMIT_RECURSION
+                            Internal recursion depth limit
+  PCRE_CONFIG_NEWLINE       Value of the newline sequence
+  PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
+                            Threshold of return slots, above
+                              which malloc() is used by
+                              the POSIX API
+  PCRE_CONFIG_STACKRECURSE  Recursion implementation (1=stack 0=heap)
+  PCRE_CONFIG_UTF8          Availability of UTF-8 support (1=yes 0=no)
+  PCRE_CONFIG_UNICODE_PROPERTIES
+                            Availability of Unicode property support
+                              (1=yes 0=no)
+
+The function yields 0 on success or PCRE_ERROR_BADOPTION otherwise. +

+

+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_copy_named_substring.html b/libs/pcre/doc/html/pcre_copy_named_substring.html new file mode 100644 index 0000000000..2185518c8a --- /dev/null +++ b/libs/pcre/doc/html/pcre_copy_named_substring.html @@ -0,0 +1,53 @@ + + +pcre_copy_named_substring specification + + +

pcre_copy_named_substring man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_copy_named_substring(const pcre *code, +const char *subject, int *ovector, +int stringcount, const char *stringname, +char *buffer, int buffersize); +

+
+DESCRIPTION +
+

+This is a convenience function for extracting a captured substring, identified +by name, into a given buffer. The arguments are: +

+  code          Pattern that was successfully matched
+  subject       Subject that has been successfully matched
+  ovector       Offset vector that pcre_exec() used
+  stringcount   Value returned by pcre_exec()
+  stringname    Name of the required substring
+  buffer        Buffer to receive the string
+  buffersize    Size of buffer
+
+The yield is the length of the substring, PCRE_ERROR_NOMEMORY if the buffer was +too small, or PCRE_ERROR_NOSUBSTRING if the string name is invalid. +

+

+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_copy_substring.html b/libs/pcre/doc/html/pcre_copy_substring.html new file mode 100644 index 0000000000..9aa87c1746 --- /dev/null +++ b/libs/pcre/doc/html/pcre_copy_substring.html @@ -0,0 +1,51 @@ + + +pcre_copy_substring specification + + +

pcre_copy_substring man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_copy_substring(const char *subject, int *ovector, +int stringcount, int stringnumber, char *buffer, +int buffersize); +

+
+DESCRIPTION +
+

+This is a convenience function for extracting a captured substring into a given +buffer. The arguments are: +

+  subject       Subject that has been successfully matched
+  ovector       Offset vector that pcre_exec() used
+  stringcount   Value returned by pcre_exec()
+  stringnumber  Number of the required substring
+  buffer        Buffer to receive the string
+  buffersize    Size of buffer
+
+The yield is the legnth of the string, PCRE_ERROR_NOMEMORY if the buffer was +too small, or PCRE_ERROR_NOSUBSTRING if the string number is invalid. +

+

+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_dfa_exec.html b/libs/pcre/doc/html/pcre_dfa_exec.html new file mode 100644 index 0000000000..d8522860b1 --- /dev/null +++ b/libs/pcre/doc/html/pcre_dfa_exec.html @@ -0,0 +1,93 @@ + + +pcre_dfa_exec specification + + +

pcre_dfa_exec man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_dfa_exec(const pcre *code, const pcre_extra *extra, +const char *subject, int length, int startoffset, +int options, int *ovector, int ovecsize, +int *workspace, int wscount); +

+
+DESCRIPTION +
+

+This function matches a compiled regular expression against a given subject +string, using a DFA matching algorithm (not Perl-compatible). Note that +the main, Perl-compatible, matching function is pcre_exec(). The +arguments for this function are: +

+  code         Points to the compiled pattern
+  extra        Points to an associated pcre_extra structure,
+                 or is NULL
+  subject      Points to the subject string
+  length       Length of the subject string, in bytes
+  startoffset  Offset in bytes in the subject at which to
+                 start matching
+  options      Option bits
+  ovector      Points to a vector of ints for result offsets
+  ovecsize     Number of elements in the vector
+  workspace    Points to a vector of ints used as working space
+  wscount      Number of elements in the vector
+
+The options are: +
+  PCRE_ANCHORED      Match only at the first position
+  PCRE_NEWLINE_CR    Set CR as the newline sequence
+  PCRE_NEWLINE_CRLF  Set CRLF as the newline sequence
+  PCRE_NEWLINE_LF    Set LF as the newline sequence
+  PCRE_NOTBOL        Subject is not the beginning of a line
+  PCRE_NOTEOL        Subject is not the end of a line
+  PCRE_NOTEMPTY      An empty string is not a valid match
+  PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8
+                       validity (only relevant if PCRE_UTF8
+                       was set at compile time)
+  PCRE_PARTIAL       Return PCRE_ERROR_PARTIAL for a partial match
+  PCRE_DFA_SHORTEST  Return only the shortest match
+  PCRE_DFA_RESTART   This is a restart after a partial match
+
+There are restrictions on what may appear in a pattern when matching using the +DFA algorithm is requested. Details are given in the +pcrematching +documentation. +

+

+A pcre_extra structure contains the following fields: +

+  flags        Bits indicating which fields are set
+  study_data   Opaque data from pcre_study()
+  match_limit  Limit on internal resource use
+  match_limit_recursion  Limit on internal recursion depth
+  callout_data Opaque data passed back to callouts
+  tables       Points to character tables or is NULL
+
+The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, +PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, and +PCRE_EXTRA_TABLES. For DFA matching, the match_limit and +match_limit_recursion fields are not used, and must not be set. +

+

+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_exec.html b/libs/pcre/doc/html/pcre_exec.html new file mode 100644 index 0000000000..229e418a75 --- /dev/null +++ b/libs/pcre/doc/html/pcre_exec.html @@ -0,0 +1,84 @@ + + +pcre_exec specification + + +

pcre_exec man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_exec(const pcre *code, const pcre_extra *extra, +const char *subject, int length, int startoffset, +int options, int *ovector, int ovecsize); +

+
+DESCRIPTION +
+

+This function matches a compiled regular expression against a given subject +string, using a matching algorithm that is similar to Perl's. It returns +offsets to captured substrings. Its arguments are: +

+  code         Points to the compiled pattern
+  extra        Points to an associated pcre_extra structure,
+                 or is NULL
+  subject      Points to the subject string
+  length       Length of the subject string, in bytes
+  startoffset  Offset in bytes in the subject at which to
+                 start matching
+  options      Option bits
+  ovector      Points to a vector of ints for result offsets
+  ovecsize     Number of elements in the vector (a multiple of 3)
+
+The options are: +
+  PCRE_ANCHORED      Match only at the first position
+  PCRE_NEWLINE_CR    Set CR as the newline sequence
+  PCRE_NEWLINE_CRLF  Set CRLF as the newline sequence
+  PCRE_NEWLINE_LF    Set LF as the newline sequence
+  PCRE_NOTBOL        Subject is not the beginning of a line
+  PCRE_NOTEOL        Subject is not the end of a line
+  PCRE_NOTEMPTY      An empty string is not a valid match
+  PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8
+                       validity (only relevant if PCRE_UTF8
+                       was set at compile time)
+  PCRE_PARTIAL       Return PCRE_ERROR_PARTIAL for a partial match
+
+There are restrictions on what may appear in a pattern when partial matching is +requested. +

+

+A pcre_extra structure contains the following fields: +

+  flags        Bits indicating which fields are set
+  study_data   Opaque data from pcre_study()
+  match_limit  Limit on internal resource use
+  match_limit_recursion  Limit on internal recursion depth
+  callout_data Opaque data passed back to callouts
+  tables       Points to character tables or is NULL
+
+The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, +PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, and +PCRE_EXTRA_TABLES. +

+

+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_free_substring.html b/libs/pcre/doc/html/pcre_free_substring.html new file mode 100644 index 0000000000..fe6261474c --- /dev/null +++ b/libs/pcre/doc/html/pcre_free_substring.html @@ -0,0 +1,40 @@ + + +pcre_free_substring specification + + +

pcre_free_substring man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+void pcre_free_substring(const char *stringptr); +

+
+DESCRIPTION +
+

+This is a convenience function for freeing the store obtained by a previous +call to pcre_get_substring() or pcre_get_named_substring(). Its +only argument is a pointer to the string. +

+

+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_free_substring_list.html b/libs/pcre/doc/html/pcre_free_substring_list.html new file mode 100644 index 0000000000..a92c9603f0 --- /dev/null +++ b/libs/pcre/doc/html/pcre_free_substring_list.html @@ -0,0 +1,40 @@ + + +pcre_free_substring_list specification + + +

pcre_free_substring_list man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+void pcre_free_substring_list(const char **stringptr); +

+
+DESCRIPTION +
+

+This is a convenience function for freeing the store obtained by a previous +call to pcre_get_substring_list(). Its only argument is a pointer to the +list of string pointers. +

+

+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_fullinfo.html b/libs/pcre/doc/html/pcre_fullinfo.html new file mode 100644 index 0000000000..3488285c2a --- /dev/null +++ b/libs/pcre/doc/html/pcre_fullinfo.html @@ -0,0 +1,71 @@ + + +pcre_fullinfo specification + + +

pcre_fullinfo man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_fullinfo(const pcre *code, const pcre_extra *extra, +int what, void *where); +

+
+DESCRIPTION +
+

+This function returns information about a compiled pattern. Its arguments are: +

+  code                      Compiled regular expression
+  extra                     Result of pcre_study() or NULL
+  what                      What information is required
+  where                     Where to put the information
+
+The following information is available: +
+  PCRE_INFO_BACKREFMAX      Number of highest back reference
+  PCRE_INFO_CAPTURECOUNT    Number of capturing subpatterns
+  PCRE_INFO_DEFAULT_TABLES  Pointer to default tables
+  PCRE_INFO_FIRSTBYTE       Fixed first byte for a match, or
+                              -1 for start of string
+                                 or after newline, or
+                              -2 otherwise
+  PCRE_INFO_FIRSTTABLE      Table of first bytes
+                              (after studying)
+  PCRE_INFO_LASTLITERAL     Literal last byte required
+  PCRE_INFO_NAMECOUNT       Number of named subpatterns
+  PCRE_INFO_NAMEENTRYSIZE   Size of name table entry
+  PCRE_INFO_NAMETABLE       Pointer to name table
+  PCRE_INFO_OPTIONS         Options used for compilation
+  PCRE_INFO_SIZE            Size of compiled pattern
+  PCRE_INFO_STUDYSIZE       Size of study data
+
+The yield of the function is zero on success or: +
+  PCRE_ERROR_NULL           the argument code was NULL
+                            the argument where was NULL
+  PCRE_ERROR_BADMAGIC       the "magic number" was not found
+  PCRE_ERROR_BADOPTION      the value of what was invalid
+
+

+

+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_get_named_substring.html b/libs/pcre/doc/html/pcre_get_named_substring.html new file mode 100644 index 0000000000..ff8456bb57 --- /dev/null +++ b/libs/pcre/doc/html/pcre_get_named_substring.html @@ -0,0 +1,54 @@ + + +pcre_get_named_substring specification + + +

pcre_get_named_substring man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_get_named_substring(const pcre *code, +const char *subject, int *ovector, +int stringcount, const char *stringname, +const char **stringptr); +

+
+DESCRIPTION +
+

+This is a convenience function for extracting a captured substring by name. The +arguments are: +

+  code          Compiled pattern
+  subject       Subject that has been successfully matched
+  ovector       Offset vector that pcre_exec() used
+  stringcount   Value returned by pcre_exec()
+  stringname    Name of the required substring
+  stringptr     Where to put the string pointer
+
+The memory in which the substring is placed is obtained by calling +pcre_malloc(). The yield of the function is the length of the extracted +substring, PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained, or +PCRE_ERROR_NOSUBSTRING if the string name is invalid. +

+

+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_get_stringnumber.html b/libs/pcre/doc/html/pcre_get_stringnumber.html new file mode 100644 index 0000000000..9c8bea0b4b --- /dev/null +++ b/libs/pcre/doc/html/pcre_get_stringnumber.html @@ -0,0 +1,46 @@ + + +pcre_get_stringnumber specification + + +

pcre_get_stringnumber man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_get_stringnumber(const pcre *code, +const char *name); +

+
+DESCRIPTION +
+

+This convenience function finds the number of a named substring capturing +parenthesis in a compiled pattern. Its arguments are: +

+  code    Compiled regular expression
+  name    Name whose number is required
+
+The yield of the function is the number of the parenthesis if the name is +found, or PCRE_ERROR_NOSUBSTRING otherwise. +

+

+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_get_stringtable_entries.html b/libs/pcre/doc/html/pcre_get_stringtable_entries.html new file mode 100644 index 0000000000..30733792b1 --- /dev/null +++ b/libs/pcre/doc/html/pcre_get_stringtable_entries.html @@ -0,0 +1,52 @@ + + +pcre_get_stringtable_entries specification + + +

pcre_get_stringtable_entries man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_get_stringtable_entries(const pcre *code, +const char *name, char **first, char **last); +

+
+DESCRIPTION +
+

+This convenience function finds, for a compiled pattern, the first and last +entries for a given name in the table that translates capturing parenthesis +names into numbers. When names are required to be unique (PCRE_DUPNAMES is +not set), it is usually easier to use pcre_get_stringnumber() +instead. +

+  code    Compiled regular expression
+  name    Name whose entries required
+  first   Where to return a pointer to the first entry
+  last    Where to return a pointer to the last entry
+
+The yield of the function is the length of each entry, or +PCRE_ERROR_NOSUBSTRING if none are found. +

+

+There is a complete description of the PCRE native API, including the format of +the table entries, in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_get_substring.html b/libs/pcre/doc/html/pcre_get_substring.html new file mode 100644 index 0000000000..14a413222a --- /dev/null +++ b/libs/pcre/doc/html/pcre_get_substring.html @@ -0,0 +1,52 @@ + + +pcre_get_substring specification + + +

pcre_get_substring man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_get_substring(const char *subject, int *ovector, +int stringcount, int stringnumber, +const char **stringptr); +

+
+DESCRIPTION +
+

+This is a convenience function for extracting a captured substring. The +arguments are: +

+  subject       Subject that has been successfully matched
+  ovector       Offset vector that pcre_exec() used
+  stringcount   Value returned by pcre_exec()
+  stringnumber  Number of the required substring
+  stringptr     Where to put the string pointer
+
+The memory in which the substring is placed is obtained by calling +pcre_malloc(). The yield of the function is the length of the substring, +PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained, or +PCRE_ERROR_NOSUBSTRING if the string number is invalid. +

+

+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_get_substring_list.html b/libs/pcre/doc/html/pcre_get_substring_list.html new file mode 100644 index 0000000000..d278b1793d --- /dev/null +++ b/libs/pcre/doc/html/pcre_get_substring_list.html @@ -0,0 +1,51 @@ + + +pcre_get_substring_list specification + + +

pcre_get_substring_list man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_get_substring_list(const char *subject, +int *ovector, int stringcount, const char ***listptr); +

+
+DESCRIPTION +
+

+This is a convenience function for extracting a list of all the captured +substrings. The arguments are: +

+  subject       Subject that has been successfully matched
+  ovector       Offset vector that pcre_exec used
+  stringcount   Value returned by pcre_exec
+  listptr       Where to put a pointer to the list
+
+The memory in which the substrings and the list are placed is obtained by +calling pcre_malloc(). A pointer to a list of pointers is put in +the variable whose address is in listptr. The list is terminated by a +NULL pointer. The yield of the function is zero on success or +PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained. +

+

+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_info.html b/libs/pcre/doc/html/pcre_info.html new file mode 100644 index 0000000000..6693ffee6c --- /dev/null +++ b/libs/pcre/doc/html/pcre_info.html @@ -0,0 +1,39 @@ + + +pcre_info specification + + +

pcre_info man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_info(const pcre *code, int *optptr, int +*firstcharptr); +

+
+DESCRIPTION +
+

+This function is obsolete. You should be using pcre_fullinfo() instead. +

+

+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_maketables.html b/libs/pcre/doc/html/pcre_maketables.html new file mode 100644 index 0000000000..cf8d69ecfd --- /dev/null +++ b/libs/pcre/doc/html/pcre_maketables.html @@ -0,0 +1,42 @@ + + +pcre_maketables specification + + +

pcre_maketables man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+const unsigned char *pcre_maketables(void); +

+
+DESCRIPTION +
+

+This function builds a set of character tables for character values less than +256. These can be passed to pcre_compile() to override PCRE's internal, +built-in tables (which were made by pcre_maketables() when PCRE was +compiled). You might want to do this if you are using a non-standard locale. +The function yields a pointer to the tables. +

+

+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_refcount.html b/libs/pcre/doc/html/pcre_refcount.html new file mode 100644 index 0000000000..b748df2f1d --- /dev/null +++ b/libs/pcre/doc/html/pcre_refcount.html @@ -0,0 +1,45 @@ + + +pcre_refcount specification + + +

pcre_refcount man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_refcount(pcre *code, int adjust); +

+
+DESCRIPTION +
+

+This function is used to maintain a reference count inside a data block that +contains a compiled pattern. Its arguments are: +

+  code                      Compiled regular expression
+  adjust                    Adjustment to reference value
+
+The yield of the function is the adjusted reference value, which is constrained +to lie between 0 and 65535. +

+

+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_study.html b/libs/pcre/doc/html/pcre_study.html new file mode 100644 index 0000000000..d290420e54 --- /dev/null +++ b/libs/pcre/doc/html/pcre_study.html @@ -0,0 +1,56 @@ + + +pcre_study specification + + +

pcre_study man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+pcre_extra *pcre_study(const pcre *code, int options, +const char **errptr); +

+
+DESCRIPTION +
+

+This function studies a compiled pattern, to see if additional information can +be extracted that might speed up matching. Its arguments are: +

+  code       A compiled regular expression
+  options    Options for pcre_study()
+  errptr     Where to put an error message
+
+If the function succeeds, it returns a value that can be passed to +pcre_exec() via its extra argument. +

+

+If the function returns NULL, either it could not find any additional +information, or there was an error. You can tell the difference by looking at +the error value. It is NULL in first case. +

+

+There are currently no options defined; the value of the second argument should +always be zero. +

+

+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcre_version.html b/libs/pcre/doc/html/pcre_version.html new file mode 100644 index 0000000000..7bc8f8653e --- /dev/null +++ b/libs/pcre/doc/html/pcre_version.html @@ -0,0 +1,39 @@ + + +pcre_version specification + + +

pcre_version man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+char *pcre_version(void); +

+
+DESCRIPTION +
+

+This function returns a character string that gives the version number of the +PCRE library and the date of its release. +

+

+There is a complete description of the PCRE native API in the +pcreapi +page and a description of the POSIX API in the +pcreposix +page. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcreapi.html b/libs/pcre/doc/html/pcreapi.html new file mode 100644 index 0000000000..a15df27dc0 --- /dev/null +++ b/libs/pcre/doc/html/pcreapi.html @@ -0,0 +1,1770 @@ + + +pcreapi specification + + +

pcreapi man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+

+
PCRE NATIVE API
+

+#include <pcre.h> +

+

+pcre *pcre_compile(const char *pattern, int options, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +

+

+pcre *pcre_compile2(const char *pattern, int options, +int *errorcodeptr, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +

+

+pcre_extra *pcre_study(const pcre *code, int options, +const char **errptr); +

+

+int pcre_exec(const pcre *code, const pcre_extra *extra, +const char *subject, int length, int startoffset, +int options, int *ovector, int ovecsize); +

+

+int pcre_dfa_exec(const pcre *code, const pcre_extra *extra, +const char *subject, int length, int startoffset, +int options, int *ovector, int ovecsize, +int *workspace, int wscount); +

+

+int pcre_copy_named_substring(const pcre *code, +const char *subject, int *ovector, +int stringcount, const char *stringname, +char *buffer, int buffersize); +

+

+int pcre_copy_substring(const char *subject, int *ovector, +int stringcount, int stringnumber, char *buffer, +int buffersize); +

+

+int pcre_get_named_substring(const pcre *code, +const char *subject, int *ovector, +int stringcount, const char *stringname, +const char **stringptr); +

+

+int pcre_get_stringnumber(const pcre *code, +const char *name); +

+

+int pcre_get_stringtable_entries(const pcre *code, +const char *name, char **first, char **last); +

+

+int pcre_get_substring(const char *subject, int *ovector, +int stringcount, int stringnumber, +const char **stringptr); +

+

+int pcre_get_substring_list(const char *subject, +int *ovector, int stringcount, const char ***listptr); +

+

+void pcre_free_substring(const char *stringptr); +

+

+void pcre_free_substring_list(const char **stringptr); +

+

+const unsigned char *pcre_maketables(void); +

+

+int pcre_fullinfo(const pcre *code, const pcre_extra *extra, +int what, void *where); +

+

+int pcre_info(const pcre *code, int *optptr, int +*firstcharptr); +

+

+int pcre_refcount(pcre *code, int adjust); +

+

+int pcre_config(int what, void *where); +

+

+char *pcre_version(void); +

+

+void *(*pcre_malloc)(size_t); +

+

+void (*pcre_free)(void *); +

+

+void *(*pcre_stack_malloc)(size_t); +

+

+void (*pcre_stack_free)(void *); +

+

+int (*pcre_callout)(pcre_callout_block *); +

+
PCRE API OVERVIEW
+

+PCRE has its own native API, which is described in this document. There is +also a set of wrapper functions that correspond to the POSIX regular expression +API. These are described in the +pcreposix +documentation. Both of these APIs define a set of C function calls. A C++ +wrapper is distributed with PCRE. It is documented in the +pcrecpp +page. +

+

+The native API C function prototypes are defined in the header file +pcre.h, and on Unix systems the library itself is called libpcre. +It can normally be accessed by adding -lpcre to the command for linking +an application that uses PCRE. The header file defines the macros PCRE_MAJOR +and PCRE_MINOR to contain the major and minor release numbers for the library. +Applications can use these to include support for different releases of PCRE. +

+

+The functions pcre_compile(), pcre_compile2(), pcre_study(), +and pcre_exec() are used for compiling and matching regular expressions +in a Perl-compatible manner. A sample program that demonstrates the simplest +way of using them is provided in the file called pcredemo.c in the source +distribution. The +pcresample +documentation describes how to run it. +

+

+A second matching function, pcre_dfa_exec(), which is not +Perl-compatible, is also provided. This uses a different algorithm for the +matching. The alternative algorithm finds all possible matches (at a given +point in the subject). However, this algorithm does not return captured +substrings. A description of the two matching algorithms and their advantages +and disadvantages is given in the +pcrematching +documentation. +

+

+In addition to the main compiling and matching functions, there are convenience +functions for extracting captured substrings from a subject string that is +matched by pcre_exec(). They are: +

+  pcre_copy_substring()
+  pcre_copy_named_substring()
+  pcre_get_substring()
+  pcre_get_named_substring()
+  pcre_get_substring_list()
+  pcre_get_stringnumber()
+  pcre_get_stringtable_entries()
+
+pcre_free_substring() and pcre_free_substring_list() are also +provided, to free the memory used for extracted strings. +

+

+The function pcre_maketables() is used to build a set of character tables +in the current locale for passing to pcre_compile(), pcre_exec(), +or pcre_dfa_exec(). This is an optional facility that is provided for +specialist use. Most commonly, no special tables are passed, in which case +internal tables that are generated when PCRE is built are used. +

+

+The function pcre_fullinfo() is used to find out information about a +compiled pattern; pcre_info() is an obsolete version that returns only +some of the available information, but is retained for backwards compatibility. +The function pcre_version() returns a pointer to a string containing the +version of PCRE and its date of release. +

+

+The function pcre_refcount() maintains a reference count in a data block +containing a compiled pattern. This is provided for the benefit of +object-oriented applications. +

+

+The global variables pcre_malloc and pcre_free initially contain +the entry points of the standard malloc() and free() functions, +respectively. PCRE calls the memory management functions via these variables, +so a calling program can replace them if it wishes to intercept the calls. This +should be done before calling any PCRE functions. +

+

+The global variables pcre_stack_malloc and pcre_stack_free are also +indirections to memory management functions. These special functions are used +only when PCRE is compiled to use the heap for remembering data, instead of +recursive function calls, when running the pcre_exec() function. See the +pcrebuild +documentation for details of how to do this. It is a non-standard way of +building PCRE, for use in environments that have limited stacks. Because of the +greater use of memory management, it runs more slowly. Separate functions are +provided so that special-purpose external code can be used for this case. When +used, these functions are always called in a stack-like manner (last obtained, +first freed), and always for memory blocks of the same size. There is a +discussion about PCRE's stack usage in the +pcrestack +documentation. +

+

+The global variable pcre_callout initially contains NULL. It can be set +by the caller to a "callout" function, which PCRE will then call at specified +points during a matching operation. Details are given in the +pcrecallout +documentation. +

+
NEWLINES
+

+PCRE supports three different conventions for indicating line breaks in +strings: a single CR character, a single LF character, or the two-character +sequence CRLF. All three are used as "standard" by different operating systems. +When PCRE is built, a default can be specified. The default default is LF, +which is the Unix standard. When PCRE is run, the default can be overridden, +either when a pattern is compiled, or when it is matched. +
+
+In the PCRE documentation the word "newline" is used to mean "the character or +pair of characters that indicate a line break". +

+
MULTITHREADING
+

+The PCRE functions can be used in multi-threading applications, with the +proviso that the memory management functions pointed to by pcre_malloc, +pcre_free, pcre_stack_malloc, and pcre_stack_free, and the +callout function pointed to by pcre_callout, are shared by all threads. +

+

+The compiled form of a regular expression is not altered during matching, so +the same compiled pattern can safely be used by several threads at once. +

+
SAVING PRECOMPILED PATTERNS FOR LATER USE
+

+The compiled form of a regular expression can be saved and re-used at a later +time, possibly by a different program, and even on a host other than the one on +which it was compiled. Details are given in the +pcreprecompile +documentation. +

+
CHECKING BUILD-TIME OPTIONS
+

+int pcre_config(int what, void *where); +

+

+The function pcre_config() makes it possible for a PCRE client to +discover which optional features have been compiled into the PCRE library. The +pcrebuild +documentation has more details about these optional features. +

+

+The first argument for pcre_config() is an integer, specifying which +information is required; the second argument is a pointer to a variable into +which the information is placed. The following information is available: +

+  PCRE_CONFIG_UTF8
+
+The output is an integer that is set to one if UTF-8 support is available; +otherwise it is set to zero. +
+  PCRE_CONFIG_UNICODE_PROPERTIES
+
+The output is an integer that is set to one if support for Unicode character +properties is available; otherwise it is set to zero. +
+  PCRE_CONFIG_NEWLINE
+
+The output is an integer whose value specifies the default character sequence +that is recognized as meaning "newline". The three values that are supported +are: 10 for LF, 13 for CR, and 3338 for CRLF. The default should normally be +the standard sequence for your operating system. +
+  PCRE_CONFIG_LINK_SIZE
+
+The output is an integer that contains the number of bytes used for internal +linkage in compiled regular expressions. The value is 2, 3, or 4. Larger values +allow larger regular expressions to be compiled, at the expense of slower +matching. The default value of 2 is sufficient for all but the most massive +patterns, since it allows the compiled pattern to be up to 64K in size. +
+  PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
+
+The output is an integer that contains the threshold above which the POSIX +interface uses malloc() for output vectors. Further details are given in +the +pcreposix +documentation. +
+  PCRE_CONFIG_MATCH_LIMIT
+
+The output is an integer that gives the default limit for the number of +internal matching function calls in a pcre_exec() execution. Further +details are given with pcre_exec() below. +
+  PCRE_CONFIG_MATCH_LIMIT_RECURSION
+
+The output is an integer that gives the default limit for the depth of +recursion when calling the internal matching function in a pcre_exec() +execution. Further details are given with pcre_exec() below. +
+  PCRE_CONFIG_STACKRECURSE
+
+The output is an integer that is set to one if internal recursion when running +pcre_exec() is implemented by recursive function calls that use the stack +to remember their state. This is the usual way that PCRE is compiled. The +output is zero if PCRE was compiled to use blocks of data on the heap instead +of recursive function calls. In this case, pcre_stack_malloc and +pcre_stack_free are called to manage memory blocks on the heap, thus +avoiding the use of the stack. +

+
COMPILING A PATTERN
+

+pcre *pcre_compile(const char *pattern, int options, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +pcre *pcre_compile2(const char *pattern, int options, +int *errorcodeptr, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +

+

+Either of the functions pcre_compile() or pcre_compile2() can be +called to compile a pattern into an internal form. The only difference between +the two interfaces is that pcre_compile2() has an additional argument, +errorcodeptr, via which a numerical error code can be returned. +

+

+The pattern is a C string terminated by a binary zero, and is passed in the +pattern argument. A pointer to a single block of memory that is obtained +via pcre_malloc is returned. This contains the compiled code and related +data. The pcre type is defined for the returned block; this is a typedef +for a structure whose contents are not externally defined. It is up to the +caller to free the memory (via pcre_free) when it is no longer required. +

+

+Although the compiled code of a PCRE regex is relocatable, that is, it does not +depend on memory location, the complete pcre data block is not +fully relocatable, because it may contain a copy of the tableptr +argument, which is an address (see below). +

+

+The options argument contains independent bits that affect the +compilation. It should be zero if no options are required. The available +options are described below. Some of them, in particular, those that are +compatible with Perl, can also be set and unset from within the pattern (see +the detailed description in the +pcrepattern +documentation). For these options, the contents of the options argument +specifies their initial settings at the start of compilation and execution. The +PCRE_ANCHORED and PCRE_NEWLINE_xxx options can be set at the time of +matching as well as at compile time. +

+

+If errptr is NULL, pcre_compile() returns NULL immediately. +Otherwise, if compilation of a pattern fails, pcre_compile() returns +NULL, and sets the variable pointed to by errptr to point to a textual +error message. This is a static string that is part of the library. You must +not try to free it. The offset from the start of the pattern to the character +where the error was discovered is placed in the variable pointed to by +erroffset, which must not be NULL. If it is, an immediate error is given. +

+

+If pcre_compile2() is used instead of pcre_compile(), and the +errorcodeptr argument is not NULL, a non-zero error code number is +returned via this argument in the event of an error. This is in addition to the +textual error message. Error codes and messages are listed below. +

+

+If the final argument, tableptr, is NULL, PCRE uses a default set of +character tables that are built when PCRE is compiled, using the default C +locale. Otherwise, tableptr must be an address that is the result of a +call to pcre_maketables(). This value is stored with the compiled +pattern, and used again by pcre_exec(), unless another table pointer is +passed to it. For more discussion, see the section on locale support below. +

+

+This code fragment shows a typical straightforward call to pcre_compile(): +

+  pcre *re;
+  const char *error;
+  int erroffset;
+  re = pcre_compile(
+    "^A.*Z",          /* the pattern */
+    0,                /* default options */
+    &error,           /* for error message */
+    &erroffset,       /* for error offset */
+    NULL);            /* use default character tables */
+
+The following names for option bits are defined in the pcre.h header +file: +
+  PCRE_ANCHORED
+
+If this bit is set, the pattern is forced to be "anchored", that is, it is +constrained to match only at the first matching point in the string that is +being searched (the "subject string"). This effect can also be achieved by +appropriate constructs in the pattern itself, which is the only way to do it in +Perl. +
+  PCRE_AUTO_CALLOUT
+
+If this bit is set, pcre_compile() automatically inserts callout items, +all with number 255, before each pattern item. For discussion of the callout +facility, see the +pcrecallout +documentation. +
+  PCRE_CASELESS
+
+If this bit is set, letters in the pattern match both upper and lower case +letters. It is equivalent to Perl's /i option, and it can be changed within a +pattern by a (?i) option setting. In UTF-8 mode, PCRE always understands the +concept of case for characters whose values are less than 128, so caseless +matching is always possible. For characters with higher values, the concept of +case is supported if PCRE is compiled with Unicode property support, but not +otherwise. If you want to use caseless matching for characters 128 and above, +you must ensure that PCRE is compiled with Unicode property support as well as +with UTF-8 support. +
+  PCRE_DOLLAR_ENDONLY
+
+If this bit is set, a dollar metacharacter in the pattern matches only at the +end of the subject string. Without this option, a dollar also matches +immediately before a newline at the end of the string (but not before any other +newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set. +There is no equivalent to this option in Perl, and no way to set it within a +pattern. +
+  PCRE_DOTALL
+
+If this bit is set, a dot metacharater in the pattern matches all characters, +including those that indicate newline. Without it, a dot does not match when +the current position is at a newline. This option is equivalent to Perl's /s +option, and it can be changed within a pattern by a (?s) option setting. A +negative class such as [^a] always matches newlines, independent of the setting +of this option. +
+  PCRE_DUPNAMES
+
+If this bit is set, names used to identify capturing subpatterns need not be +unique. This can be helpful for certain types of pattern when it is known that +only one instance of the named subpattern can ever be matched. There are more +details of named subpatterns below; see also the +pcrepattern +documentation. +
+  PCRE_EXTENDED
+
+If this bit is set, whitespace data characters in the pattern are totally +ignored except when escaped or inside a character class. Whitespace does not +include the VT character (code 11). In addition, characters between an +unescaped # outside a character class and the next newline, inclusive, are also +ignored. This is equivalent to Perl's /x option, and it can be changed within a +pattern by a (?x) option setting. +

+

+This option makes it possible to include comments inside complicated patterns. +Note, however, that this applies only to data characters. Whitespace characters +may never appear within special character sequences in a pattern, for example +within the sequence (?( which introduces a conditional subpattern. +

+  PCRE_EXTRA
+
+This option was invented in order to turn on additional functionality of PCRE +that is incompatible with Perl, but it is currently of very little use. When +set, any backslash in a pattern that is followed by a letter that has no +special meaning causes an error, thus reserving these combinations for future +expansion. By default, as in Perl, a backslash followed by a letter with no +special meaning is treated as a literal. (Perl can, however, be persuaded to +give a warning for this.) There are at present no other features controlled by +this option. It can also be set by a (?X) option setting within a pattern. +
+  PCRE_FIRSTLINE
+
+If this option is set, an unanchored pattern is required to match before or at +the first newline in the subject string, though the matched text may continue +over the newline. +
+  PCRE_MULTILINE
+
+By default, PCRE treats the subject string as consisting of a single line of +characters (even if it actually contains newlines). The "start of line" +metacharacter (^) matches only at the start of the string, while the "end of +line" metacharacter ($) matches only at the end of the string, or before a +terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as +Perl. +

+

+When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs +match immediately following or immediately before internal newlines in the +subject string, respectively, as well as at the very start and end. This is +equivalent to Perl's /m option, and it can be changed within a pattern by a +(?m) option setting. If there are no newlines in a subject string, or no +occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect. +

+  PCRE_NEWLINE_CR
+  PCRE_NEWLINE_LF
+  PCRE_NEWLINE_CRLF
+
+These options override the default newline definition that was chosen when PCRE +was built. Setting the first or the second specifies that a newline is +indicated by a single character (CR or LF, respectively). Setting both of them +specifies that a newline is indicated by the two-character CRLF sequence. For +convenience, PCRE_NEWLINE_CRLF is defined to contain both bits. The only time +that a line break is relevant when compiling a pattern is if PCRE_EXTENDED is +set, and an unescaped # outside a character class is encountered. This +indicates a comment that lasts until after the next newline. +

+

+The newline option set at compile time becomes the default that is used for +pcre_exec() and pcre_dfa_exec(), but it can be overridden. +

+  PCRE_NO_AUTO_CAPTURE
+
+If this option is set, it disables the use of numbered capturing parentheses in +the pattern. Any opening parenthesis that is not followed by ? behaves as if it +were followed by ?: but named parentheses can still be used for capturing (and +they acquire numbers in the usual way). There is no equivalent of this option +in Perl. +
+  PCRE_UNGREEDY
+
+This option inverts the "greediness" of the quantifiers so that they are not +greedy by default, but become greedy if followed by "?". It is not compatible +with Perl. It can also be set by a (?U) option setting within the pattern. +
+  PCRE_UTF8
+
+This option causes PCRE to regard both the pattern and the subject as strings +of UTF-8 characters instead of single-byte character strings. However, it is +available only when PCRE is built to include UTF-8 support. If not, the use +of this option provokes an error. Details of how this option changes the +behaviour of PCRE are given in the +section on UTF-8 support +in the main +pcre +page. +
+  PCRE_NO_UTF8_CHECK
+
+When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is +automatically checked. If an invalid UTF-8 sequence of bytes is found, +pcre_compile() returns an error. If you already know that your pattern is +valid, and you want to skip this check for performance reasons, you can set the +PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid +UTF-8 string as a pattern is undefined. It may cause your program to crash. +Note that this option can also be passed to pcre_exec() and +pcre_dfa_exec(), to suppress the UTF-8 validity checking of subject +strings. +

+
COMPILATION ERROR CODES
+

+The following table lists the error codes than may be returned by +pcre_compile2(), along with the error messages that may be returned by +both compiling functions. +

+   0  no error
+   1  \ at end of pattern
+   2  \c at end of pattern
+   3  unrecognized character follows \
+   4  numbers out of order in {} quantifier
+   5  number too big in {} quantifier
+   6  missing terminating ] for character class
+   7  invalid escape sequence in character class
+   8  range out of order in character class
+   9  nothing to repeat
+  10  operand of unlimited repeat could match the empty string
+  11  internal error: unexpected repeat
+  12  unrecognized character after (?
+  13  POSIX named classes are supported only within a class
+  14  missing )
+  15  reference to non-existent subpattern
+  16  erroffset passed as NULL
+  17  unknown option bit(s) set
+  18  missing ) after comment
+  19  parentheses nested too deeply
+  20  regular expression too large
+  21  failed to get memory
+  22  unmatched parentheses
+  23  internal error: code overflow
+  24  unrecognized character after (?<
+  25  lookbehind assertion is not fixed length
+  26  malformed number or name after (?(
+  27  conditional group contains more than two branches
+  28  assertion expected after (?(
+  29  (?R or (?digits must be followed by )
+  30  unknown POSIX class name
+  31  POSIX collating elements are not supported
+  32  this version of PCRE is not compiled with PCRE_UTF8 support
+  33  spare error
+  34  character value in \x{...} sequence is too large
+  35  invalid condition (?(0)
+  36  \C not allowed in lookbehind assertion
+  37  PCRE does not support \L, \l, \N, \U, or \u
+  38  number after (?C is > 255
+  39  closing ) for (?C expected
+  40  recursive call could loop indefinitely
+  41  unrecognized character after (?P
+  42  syntax error after (?P
+  43  two named subpatterns have the same name
+  44  invalid UTF-8 string
+  45  support for \P, \p, and \X has not been compiled
+  46  malformed \P or \p sequence
+  47  unknown property name after \P or \p
+  48  subpattern name is too long (maximum 32 characters)
+  49  too many named subpatterns (maximum 10,000)
+  50  repeated subpattern is too long
+  51  octal value is greater than \377 (not in UTF-8 mode)
+
+

+
STUDYING A PATTERN
+

+pcre_extra *pcre_study(const pcre *code, int options +const char **errptr); +

+

+If a compiled pattern is going to be used several times, it is worth spending +more time analyzing it in order to speed up the time taken for matching. The +function pcre_study() takes a pointer to a compiled pattern as its first +argument. If studying the pattern produces additional information that will +help speed up matching, pcre_study() returns a pointer to a +pcre_extra block, in which the study_data field points to the +results of the study. +

+

+The returned value from pcre_study() can be passed directly to +pcre_exec(). However, a pcre_extra block also contains other +fields that can be set by the caller before the block is passed; these are +described +below +in the section on matching a pattern. +

+

+If studying the pattern does not produce any additional information +pcre_study() returns NULL. In that circumstance, if the calling program +wants to pass any of the other fields to pcre_exec(), it must set up its +own pcre_extra block. +

+

+The second argument of pcre_study() contains option bits. At present, no +options are defined, and this argument should always be zero. +

+

+The third argument for pcre_study() is a pointer for an error message. If +studying succeeds (even if no data is returned), the variable it points to is +set to NULL. Otherwise it is set to point to a textual error message. This is a +static string that is part of the library. You must not try to free it. You +should test the error pointer for NULL after calling pcre_study(), to be +sure that it has run successfully. +

+

+This is a typical call to pcre_study(): +

+  pcre_extra *pe;
+  pe = pcre_study(
+    re,             /* result of pcre_compile() */
+    0,              /* no options exist */
+    &error);        /* set to NULL or points to a message */
+
+At present, studying a pattern is useful only for non-anchored patterns that do +not have a single fixed starting character. A bitmap of possible starting +bytes is created. +

+
LOCALE SUPPORT
+

+PCRE handles caseless matching, and determines whether characters are letters +digits, or whatever, by reference to a set of tables, indexed by character +value. When running in UTF-8 mode, this applies only to characters with codes +less than 128. Higher-valued codes never match escapes such as \w or \d, but +can be tested with \p if PCRE is built with Unicode character property +support. The use of locales with Unicode is discouraged. +

+

+An internal set of tables is created in the default C locale when PCRE is +built. This is used when the final argument of pcre_compile() is NULL, +and is sufficient for many applications. An alternative set of tables can, +however, be supplied. These may be created in a different locale from the +default. As more and more applications change to using Unicode, the need for +this locale support is expected to die away. +

+

+External tables are built by calling the pcre_maketables() function, +which has no arguments, in the relevant locale. The result can then be passed +to pcre_compile() or pcre_exec() as often as necessary. For +example, to build and use tables that are appropriate for the French locale +(where accented characters with values greater than 128 are treated as letters), +the following code could be used: +

+  setlocale(LC_CTYPE, "fr_FR");
+  tables = pcre_maketables();
+  re = pcre_compile(..., tables);
+
+When pcre_maketables() runs, the tables are built in memory that is +obtained via pcre_malloc. It is the caller's responsibility to ensure +that the memory containing the tables remains available for as long as it is +needed. +

+

+The pointer that is passed to pcre_compile() is saved with the compiled +pattern, and the same tables are used via this pointer by pcre_study() +and normally also by pcre_exec(). Thus, by default, for any single +pattern, compilation, studying and matching all happen in the same locale, but +different patterns can be compiled in different locales. +

+

+It is possible to pass a table pointer or NULL (indicating the use of the +internal tables) to pcre_exec(). Although not intended for this purpose, +this facility could be used to match a pattern in a different locale from the +one in which it was compiled. Passing table pointers at run time is discussed +below in the section on matching a pattern. +

+
INFORMATION ABOUT A PATTERN
+

+int pcre_fullinfo(const pcre *code, const pcre_extra *extra, +int what, void *where); +

+

+The pcre_fullinfo() function returns information about a compiled +pattern. It replaces the obsolete pcre_info() function, which is +nevertheless retained for backwards compability (and is documented below). +

+

+The first argument for pcre_fullinfo() is a pointer to the compiled +pattern. The second argument is the result of pcre_study(), or NULL if +the pattern was not studied. The third argument specifies which piece of +information is required, and the fourth argument is a pointer to a variable +to receive the data. The yield of the function is zero for success, or one of +the following negative numbers: +

+  PCRE_ERROR_NULL       the argument code was NULL
+                        the argument where was NULL
+  PCRE_ERROR_BADMAGIC   the "magic number" was not found
+  PCRE_ERROR_BADOPTION  the value of what was invalid
+
+The "magic number" is placed at the start of each compiled pattern as an simple +check against passing an arbitrary memory pointer. Here is a typical call of +pcre_fullinfo(), to obtain the length of the compiled pattern: +
+  int rc;
+  size_t length;
+  rc = pcre_fullinfo(
+    re,               /* result of pcre_compile() */
+    pe,               /* result of pcre_study(), or NULL */
+    PCRE_INFO_SIZE,   /* what is required */
+    &length);         /* where to put the data */
+
+The possible values for the third argument are defined in pcre.h, and are +as follows: +
+  PCRE_INFO_BACKREFMAX
+
+Return the number of the highest back reference in the pattern. The fourth +argument should point to an int variable. Zero is returned if there are +no back references. +
+  PCRE_INFO_CAPTURECOUNT
+
+Return the number of capturing subpatterns in the pattern. The fourth argument +should point to an int variable. +
+  PCRE_INFO_DEFAULT_TABLES
+
+Return a pointer to the internal default character tables within PCRE. The +fourth argument should point to an unsigned char * variable. This +information call is provided for internal use by the pcre_study() +function. External callers can cause PCRE to use its internal tables by passing +a NULL table pointer. +
+  PCRE_INFO_FIRSTBYTE
+
+Return information about the first byte of any matched string, for a +non-anchored pattern. The fourth argument should point to an int +variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is +still recognized for backwards compatibility.) +

+

+If there is a fixed first byte, for example, from a pattern such as +(cat|cow|coyote). Otherwise, if either +
+
+(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch +starts with "^", or +
+
+(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set +(if it were set, the pattern would be anchored), +
+
+-1 is returned, indicating that the pattern matches only at the start of a +subject string or after any newline within the string. Otherwise -2 is +returned. For anchored patterns, -2 is returned. +

+  PCRE_INFO_FIRSTTABLE
+
+If the pattern was studied, and this resulted in the construction of a 256-bit +table indicating a fixed set of bytes for the first byte in any matching +string, a pointer to the table is returned. Otherwise NULL is returned. The +fourth argument should point to an unsigned char * variable. +
+  PCRE_INFO_LASTLITERAL
+
+Return the value of the rightmost literal byte that must exist in any matched +string, other than at its start, if such a byte has been recorded. The fourth +argument should point to an int variable. If there is no such byte, -1 is +returned. For anchored patterns, a last literal byte is recorded only if it +follows something of variable length. For example, for the pattern +/^a\d+z\d+/ the returned value is "z", but for /^a\dz\d/ the returned value +is -1. +
+  PCRE_INFO_NAMECOUNT
+  PCRE_INFO_NAMEENTRYSIZE
+  PCRE_INFO_NAMETABLE
+
+PCRE supports the use of named as well as numbered capturing parentheses. The +names are just an additional way of identifying the parentheses, which still +acquire numbers. Several convenience functions such as +pcre_get_named_substring() are provided for extracting captured +substrings by name. It is also possible to extract the data directly, by first +converting the name to a number in order to access the correct pointers in the +output vector (described with pcre_exec() below). To do the conversion, +you need to use the name-to-number map, which is described by these three +values. +

+

+The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives +the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each +entry; both of these return an int value. The entry size depends on the +length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first +entry of the table (a pointer to char). The first two bytes of each entry +are the number of the capturing parenthesis, most significant byte first. The +rest of the entry is the corresponding name, zero terminated. The names are in +alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of +their parentheses numbers. For example, consider the following pattern (assume +PCRE_EXTENDED is set, so white space - including newlines - is ignored): +

+  (?P<date> (?P<year>(\d\d)?\d\d) - (?P<month>\d\d) - (?P<day>\d\d) )
+
+There are four named subpatterns, so the table has four entries, and each entry +in the table is eight bytes long. The table is as follows, with non-printing +bytes shows in hexadecimal, and undefined bytes shown as ??: +
+  00 01 d  a  t  e  00 ??
+  00 05 d  a  y  00 ?? ??
+  00 04 m  o  n  t  h  00
+  00 02 y  e  a  r  00 ??
+
+When writing code to extract data from named subpatterns using the +name-to-number map, remember that the length of the entries is likely to be +different for each compiled pattern. +
+  PCRE_INFO_OPTIONS
+
+Return a copy of the options with which the pattern was compiled. The fourth +argument should point to an unsigned long int variable. These option bits +are those specified in the call to pcre_compile(), modified by any +top-level option settings within the pattern itself. +

+

+A pattern is automatically anchored by PCRE if all of its top-level +alternatives begin with one of the following: +

+  ^     unless PCRE_MULTILINE is set
+  \A    always
+  \G    always
+  .*    if PCRE_DOTALL is set and there are no back references to the subpattern in which .* appears
+
+For such patterns, the PCRE_ANCHORED bit is set in the options returned by +pcre_fullinfo(). +
+  PCRE_INFO_SIZE
+
+Return the size of the compiled pattern, that is, the value that was passed as +the argument to pcre_malloc() when PCRE was getting memory in which to +place the compiled data. The fourth argument should point to a size_t +variable. +
+  PCRE_INFO_STUDYSIZE
+
+Return the size of the data block pointed to by the study_data field in +a pcre_extra block. That is, it is the value that was passed to +pcre_malloc() when PCRE was getting memory into which to place the data +created by pcre_study(). The fourth argument should point to a +size_t variable. +

+
OBSOLETE INFO FUNCTION
+

+int pcre_info(const pcre *code, int *optptr, int +*firstcharptr); +

+

+The pcre_info() function is now obsolete because its interface is too +restrictive to return all the available data about a compiled pattern. New +programs should use pcre_fullinfo() instead. The yield of +pcre_info() is the number of capturing subpatterns, or one of the +following negative numbers: +

+  PCRE_ERROR_NULL       the argument code was NULL
+  PCRE_ERROR_BADMAGIC   the "magic number" was not found
+
+If the optptr argument is not NULL, a copy of the options with which the +pattern was compiled is placed in the integer it points to (see +PCRE_INFO_OPTIONS above). +

+

+If the pattern is not anchored and the firstcharptr argument is not NULL, +it is used to pass back information about the first character of any matched +string (see PCRE_INFO_FIRSTBYTE above). +

+
REFERENCE COUNTS
+

+int pcre_refcount(pcre *code, int adjust); +

+

+The pcre_refcount() function is used to maintain a reference count in the +data block that contains a compiled pattern. It is provided for the benefit of +applications that operate in an object-oriented manner, where different parts +of the application may be using the same compiled pattern, but you want to free +the block when they are all done. +

+

+When a pattern is compiled, the reference count field is initialized to zero. +It is changed only by calling this function, whose action is to add the +adjust value (which may be positive or negative) to it. The yield of the +function is the new value. However, the value of the count is constrained to +lie between 0 and 65535, inclusive. If the new value is outside these limits, +it is forced to the appropriate limit value. +

+

+Except when it is zero, the reference count is not correctly preserved if a +pattern is compiled on one host and then transferred to a host whose byte-order +is different. (This seems a highly unlikely scenario.) +

+
MATCHING A PATTERN: THE TRADITIONAL FUNCTION
+

+int pcre_exec(const pcre *code, const pcre_extra *extra, +const char *subject, int length, int startoffset, +int options, int *ovector, int ovecsize); +

+

+The function pcre_exec() is called to match a subject string against a +compiled pattern, which is passed in the code argument. If the +pattern has been studied, the result of the study should be passed in the +extra argument. This function is the main matching facility of the +library, and it operates in a Perl-like manner. For specialist use there is +also an alternative matching function, which is described +below +in the section about the pcre_dfa_exec() function. +

+

+In most applications, the pattern will have been compiled (and optionally +studied) in the same process that calls pcre_exec(). However, it is +possible to save compiled patterns and study data, and then use them later +in different processes, possibly even on different hosts. For a discussion +about this, see the +pcreprecompile +documentation. +

+

+Here is an example of a simple call to pcre_exec(): +

+  int rc;
+  int ovector[30];
+  rc = pcre_exec(
+    re,             /* result of pcre_compile() */
+    NULL,           /* we didn't study the pattern */
+    "some string",  /* the subject string */
+    11,             /* the length of the subject string */
+    0,              /* start at offset 0 in the subject */
+    0,              /* default options */
+    ovector,        /* vector of integers for substring information */
+    30);            /* number of elements (NOT size in bytes) */
+
+

+
+Extra data for pcre_exec() +
+

+If the extra argument is not NULL, it must point to a pcre_extra +data block. The pcre_study() function returns such a block (when it +doesn't return NULL), but you can also create one for yourself, and pass +additional information in it. The pcre_extra block contains the following +fields (not necessarily in this order): +

+  unsigned long int flags;
+  void *study_data;
+  unsigned long int match_limit;
+  unsigned long int match_limit_recursion;
+  void *callout_data;
+  const unsigned char *tables;
+
+The flags field is a bitmap that specifies which of the other fields +are set. The flag bits are: +
+  PCRE_EXTRA_STUDY_DATA
+  PCRE_EXTRA_MATCH_LIMIT
+  PCRE_EXTRA_MATCH_LIMIT_RECURSION
+  PCRE_EXTRA_CALLOUT_DATA
+  PCRE_EXTRA_TABLES
+
+Other flag bits should be set to zero. The study_data field is set in the +pcre_extra block that is returned by pcre_study(), together with +the appropriate flag bit. You should not set this yourself, but you may add to +the block by setting the other fields and their corresponding flag bits. +

+

+The match_limit field provides a means of preventing PCRE from using up a +vast amount of resources when running patterns that are not going to match, +but which have a very large number of possibilities in their search trees. The +classic example is the use of nested unlimited repeats. +

+

+Internally, PCRE uses a function called match() which it calls repeatedly +(sometimes recursively). The limit set by match_limit is imposed on the +number of times this function is called during a match, which has the effect of +limiting the amount of backtracking that can take place. For patterns that are +not anchored, the count restarts from zero for each position in the subject +string. +

+

+The default value for the limit can be set when PCRE is built; the default +default is 10 million, which handles all but the most extreme cases. You can +override the default by suppling pcre_exec() with a pcre_extra +block in which match_limit is set, and PCRE_EXTRA_MATCH_LIMIT is set in +the flags field. If the limit is exceeded, pcre_exec() returns +PCRE_ERROR_MATCHLIMIT. +

+

+The match_limit_recursion field is similar to match_limit, but +instead of limiting the total number of times that match() is called, it +limits the depth of recursion. The recursion depth is a smaller number than the +total number of calls, because not all calls to match() are recursive. +This limit is of use only if it is set smaller than match_limit. +

+

+Limiting the recursion depth limits the amount of stack that can be used, or, +when PCRE has been compiled to use memory on the heap instead of the stack, the +amount of heap memory that can be used. +

+

+The default value for match_limit_recursion can be set when PCRE is +built; the default default is the same value as the default for +match_limit. You can override the default by suppling pcre_exec() +with a pcre_extra block in which match_limit_recursion is set, and +PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the flags field. If the limit +is exceeded, pcre_exec() returns PCRE_ERROR_RECURSIONLIMIT. +

+

+The pcre_callout field is used in conjunction with the "callout" feature, +which is described in the +pcrecallout +documentation. +

+

+The tables field is used to pass a character tables pointer to +pcre_exec(); this overrides the value that is stored with the compiled +pattern. A non-NULL value is stored with the compiled pattern only if custom +tables were supplied to pcre_compile() via its tableptr argument. +If NULL is passed to pcre_exec() using this mechanism, it forces PCRE's +internal tables to be used. This facility is helpful when re-using patterns +that have been saved after compiling with an external set of tables, because +the external tables might be at a different address when pcre_exec() is +called. See the +pcreprecompile +documentation for a discussion of saving compiled patterns for later use. +

+
+Option bits for pcre_exec() +
+

+The unused bits of the options argument for pcre_exec() must be +zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, +PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL. +

+  PCRE_ANCHORED
+
+The PCRE_ANCHORED option limits pcre_exec() to matching at the first +matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out +to be anchored by virtue of its contents, it cannot be made unachored at +matching time. +
+  PCRE_NEWLINE_CR
+  PCRE_NEWLINE_LF
+  PCRE_NEWLINE_CRLF
+
+These options override the newline definition that was chosen or defaulted when +the pattern was compiled. For details, see the description pcre_compile() +above. During matching, the newline choice affects the behaviour of the dot, +circumflex, and dollar metacharacters. +
+  PCRE_NOTBOL
+
+This option specifies that first character of the subject string is not the +beginning of a line, so the circumflex metacharacter should not match before +it. Setting this without PCRE_MULTILINE (at compile time) causes circumflex +never to match. This option affects only the behaviour of the circumflex +metacharacter. It does not affect \A. +
+  PCRE_NOTEOL
+
+This option specifies that the end of the subject string is not the end of a +line, so the dollar metacharacter should not match it nor (except in multiline +mode) a newline immediately before it. Setting this without PCRE_MULTILINE (at +compile time) causes dollar never to match. This option affects only the +behaviour of the dollar metacharacter. It does not affect \Z or \z. +
+  PCRE_NOTEMPTY
+
+An empty string is not considered to be a valid match if this option is set. If +there are alternatives in the pattern, they are tried. If all the alternatives +match the empty string, the entire match fails. For example, if the pattern +
+  a?b?
+
+is applied to a string not beginning with "a" or "b", it matches the empty +string at the start of the subject. With PCRE_NOTEMPTY set, this match is not +valid, so PCRE searches further into the string for occurrences of "a" or "b". +

+

+Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case +of a pattern match of the empty string within its split() function, and +when using the /g modifier. It is possible to emulate Perl's behaviour after +matching a null string by first trying the match again at the same offset with +PCRE_NOTEMPTY and PCRE_ANCHORED, and then if that fails by advancing the +starting offset (see below) and trying an ordinary match again. There is some +code that demonstrates how to do this in the pcredemo.c sample program. +

+  PCRE_NO_UTF8_CHECK
+
+When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8 +string is automatically checked when pcre_exec() is subsequently called. +The value of startoffset is also checked to ensure that it points to the +start of a UTF-8 character. If an invalid UTF-8 sequence of bytes is found, +pcre_exec() returns the error PCRE_ERROR_BADUTF8. If startoffset +contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned. +

+

+If you already know that your subject is valid, and you want to skip these +checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when +calling pcre_exec(). You might want to do this for the second and +subsequent calls to pcre_exec() if you are making repeated calls to find +all the matches in a single subject string. However, you should be sure that +the value of startoffset points to the start of a UTF-8 character. When +PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid UTF-8 string as a +subject, or a value of startoffset that does not point to the start of a +UTF-8 character, is undefined. Your program may crash. +

+  PCRE_PARTIAL
+
+This option turns on the partial matching feature. If the subject string fails +to match the pattern, but at some point during the matching process the end of +the subject was reached (that is, the subject partially matches the pattern and +the failure to match occurred only because there were not enough subject +characters), pcre_exec() returns PCRE_ERROR_PARTIAL instead of +PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is used, there are restrictions on what +may appear in the pattern. These are discussed in the +pcrepartial +documentation. +

+
+The string to be matched by pcre_exec() +
+

+The subject string is passed to pcre_exec() as a pointer in +subject, a length in length, and a starting byte offset in +startoffset. In UTF-8 mode, the byte offset must point to the start of a +UTF-8 character. Unlike the pattern string, the subject may contain binary zero +bytes. When the starting offset is zero, the search for a match starts at the +beginning of the subject, and this is by far the most common case. +

+

+A non-zero starting offset is useful when searching for another match in the +same subject by calling pcre_exec() again after a previous success. +Setting startoffset differs from just passing over a shortened string and +setting PCRE_NOTBOL in the case of a pattern that begins with any kind of +lookbehind. For example, consider the pattern +

+  \Biss\B
+
+which finds occurrences of "iss" in the middle of words. (\B matches only if +the current position in the subject is not a word boundary.) When applied to +the string "Mississipi" the first call to pcre_exec() finds the first +occurrence. If pcre_exec() is called again with just the remainder of the +subject, namely "issipi", it does not match, because \B is always false at the +start of the subject, which is deemed to be a word boundary. However, if +pcre_exec() is passed the entire string again, but with startoffset +set to 4, it finds the second occurrence of "iss" because it is able to look +behind the starting point to discover that it is preceded by a letter. +

+

+If a non-zero starting offset is passed when the pattern is anchored, one +attempt to match at the given offset is made. This can only succeed if the +pattern does not require the match to be at the start of the subject. +

+
+How pcre_exec() returns captured substrings +
+

+In general, a pattern matches a certain portion of the subject, and in +addition, further substrings from the subject may be picked out by parts of the +pattern. Following the usage in Jeffrey Friedl's book, this is called +"capturing" in what follows, and the phrase "capturing subpattern" is used for +a fragment of a pattern that picks out a substring. PCRE supports several other +kinds of parenthesized subpattern that do not cause substrings to be captured. +

+

+Captured substrings are returned to the caller via a vector of integer offsets +whose address is passed in ovector. The number of elements in the vector +is passed in ovecsize, which must be a non-negative number. Note: +this argument is NOT the size of ovector in bytes. +

+

+The first two-thirds of the vector is used to pass back captured substrings, +each substring using a pair of integers. The remaining third of the vector is +used as workspace by pcre_exec() while matching capturing subpatterns, +and is not available for passing back information. The length passed in +ovecsize should always be a multiple of three. If it is not, it is +rounded down. +

+

+When a match is successful, information about captured substrings is returned +in pairs of integers, starting at the beginning of ovector, and +continuing up to two-thirds of its length at the most. The first element of a +pair is set to the offset of the first character in a substring, and the second +is set to the offset of the first character after the end of a substring. The +first pair, ovector[0] and ovector[1], identify the portion of the +subject string matched by the entire pattern. The next pair is used for the +first capturing subpattern, and so on. The value returned by pcre_exec() +is one more than the highest numbered pair that has been set. For example, if +two substrings have been captured, the returned value is 3. If there are no +capturing subpatterns, the return value from a successful match is 1, +indicating that just the first pair of offsets has been set. +

+

+If a capturing subpattern is matched repeatedly, it is the last portion of the +string that it matched that is returned. +

+

+If the vector is too small to hold all the captured substring offsets, it is +used as far as possible (up to two-thirds of its length), and the function +returns a value of zero. In particular, if the substring offsets are not of +interest, pcre_exec() may be called with ovector passed as NULL and +ovecsize as zero. However, if the pattern contains back references and +the ovector is not big enough to remember the related substrings, PCRE +has to get additional memory for use during matching. Thus it is usually +advisable to supply an ovector. +

+

+The pcre_info() function can be used to find out how many capturing +subpatterns there are in a compiled pattern. The smallest size for +ovector that will allow for n captured substrings, in addition to +the offsets of the substring matched by the whole pattern, is (n+1)*3. +

+

+It is possible for capturing subpattern number n+1 to match some part of +the subject when subpattern n has not been used at all. For example, if +the string "abc" is matched against the pattern (a|(z))(bc) the return from the +function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this +happens, both values in the offset pairs corresponding to unused subpatterns +are set to -1. +

+

+Offset values that correspond to unused subpatterns at the end of the +expression are also set to -1. For example, if the string "abc" is matched +against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The +return from the function is 2, because the highest used capturing subpattern +number is 1. However, you can refer to the offsets for the second and third +capturing subpatterns if you wish (assuming the vector is large enough, of +course). +

+

+Some convenience functions are provided for extracting the captured substrings +as separate strings. These are described below. +

+
+Error return values from pcre_exec() +
+

+If pcre_exec() fails, it returns a negative number. The following are +defined in the header file: +

+  PCRE_ERROR_NOMATCH        (-1)
+
+The subject string did not match the pattern. +
+  PCRE_ERROR_NULL           (-2)
+
+Either code or subject was passed as NULL, or ovector was +NULL and ovecsize was not zero. +
+  PCRE_ERROR_BADOPTION      (-3)
+
+An unrecognized bit was set in the options argument. +
+  PCRE_ERROR_BADMAGIC       (-4)
+
+PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch +the case when it is passed a junk pointer and to detect when a pattern that was +compiled in an environment of one endianness is run in an environment with the +other endianness. This is the error that PCRE gives when the magic number is +not present. +
+  PCRE_ERROR_UNKNOWN_NODE   (-5)
+
+While running the pattern match, an unknown item was encountered in the +compiled pattern. This error could be caused by a bug in PCRE or by overwriting +of the compiled pattern. +
+  PCRE_ERROR_NOMEMORY       (-6)
+
+If a pattern contains back references, but the ovector that is passed to +pcre_exec() is not big enough to remember the referenced substrings, PCRE +gets a block of memory at the start of matching to use for this purpose. If the +call via pcre_malloc() fails, this error is given. The memory is +automatically freed at the end of matching. +
+  PCRE_ERROR_NOSUBSTRING    (-7)
+
+This error is used by the pcre_copy_substring(), +pcre_get_substring(), and pcre_get_substring_list() functions (see +below). It is never returned by pcre_exec(). +
+  PCRE_ERROR_MATCHLIMIT     (-8)
+
+The backtracking limit, as specified by the match_limit field in a +pcre_extra structure (or defaulted) was reached. See the description +above. +
+  PCRE_ERROR_RECURSIONLIMIT (-21)
+
+The internal recursion limit, as specified by the match_limit_recursion +field in a pcre_extra structure (or defaulted) was reached. See the +description above. +
+  PCRE_ERROR_CALLOUT        (-9)
+
+This error is never generated by pcre_exec() itself. It is provided for +use by callout functions that want to yield a distinctive error code. See the +pcrecallout +documentation for details. +
+  PCRE_ERROR_BADUTF8        (-10)
+
+A string that contains an invalid UTF-8 byte sequence was passed as a subject. +
+  PCRE_ERROR_BADUTF8_OFFSET (-11)
+
+The UTF-8 byte sequence that was passed as a subject was valid, but the value +of startoffset did not point to the beginning of a UTF-8 character. +
+  PCRE_ERROR_PARTIAL        (-12)
+
+The subject string did not match, but it did match partially. See the +pcrepartial +documentation for details of partial matching. +
+  PCRE_ERROR_BADPARTIAL     (-13)
+
+The PCRE_PARTIAL option was used with a compiled pattern containing items that +are not supported for partial matching. See the +pcrepartial +documentation for details of partial matching. +
+  PCRE_ERROR_INTERNAL       (-14)
+
+An unexpected internal error has occurred. This error could be caused by a bug +in PCRE or by overwriting of the compiled pattern. +
+  PCRE_ERROR_BADCOUNT       (-15)
+
+This error is given if the value of the ovecsize argument is negative. +

+
EXTRACTING CAPTURED SUBSTRINGS BY NUMBER
+

+int pcre_copy_substring(const char *subject, int *ovector, +int stringcount, int stringnumber, char *buffer, +int buffersize); +

+

+int pcre_get_substring(const char *subject, int *ovector, +int stringcount, int stringnumber, +const char **stringptr); +

+

+int pcre_get_substring_list(const char *subject, +int *ovector, int stringcount, const char ***listptr); +

+

+Captured substrings can be accessed directly by using the offsets returned by +pcre_exec() in ovector. For convenience, the functions +pcre_copy_substring(), pcre_get_substring(), and +pcre_get_substring_list() are provided for extracting captured substrings +as new, separate, zero-terminated strings. These functions identify substrings +by number. The next section describes functions for extracting named +substrings. +

+

+A substring that contains a binary zero is correctly extracted and has a +further zero added on the end, but the result is not, of course, a C string. +However, you can process such a string by referring to the length that is +returned by pcre_copy_substring() and pcre_get_substring(). +Unfortunately, the interface to pcre_get_substring_list() is not adequate +for handling strings containing binary zeros, because the end of the final +string is not independently indicated. +

+

+The first three arguments are the same for all three of these functions: +subject is the subject string that has just been successfully matched, +ovector is a pointer to the vector of integer offsets that was passed to +pcre_exec(), and stringcount is the number of substrings that were +captured by the match, including the substring that matched the entire regular +expression. This is the value returned by pcre_exec() if it is greater +than zero. If pcre_exec() returned zero, indicating that it ran out of +space in ovector, the value passed as stringcount should be the +number of elements in the vector divided by three. +

+

+The functions pcre_copy_substring() and pcre_get_substring() +extract a single substring, whose number is given as stringnumber. A +value of zero extracts the substring that matched the entire pattern, whereas +higher values extract the captured substrings. For pcre_copy_substring(), +the string is placed in buffer, whose length is given by +buffersize, while for pcre_get_substring() a new block of memory is +obtained via pcre_malloc, and its address is returned via +stringptr. The yield of the function is the length of the string, not +including the terminating zero, or one of +

+  PCRE_ERROR_NOMEMORY       (-6)
+
+The buffer was too small for pcre_copy_substring(), or the attempt to get +memory failed for pcre_get_substring(). +
+  PCRE_ERROR_NOSUBSTRING    (-7)
+
+There is no substring whose number is stringnumber. +

+

+The pcre_get_substring_list() function extracts all available substrings +and builds a list of pointers to them. All this is done in a single block of +memory that is obtained via pcre_malloc. The address of the memory block +is returned via listptr, which is also the start of the list of string +pointers. The end of the list is marked by a NULL pointer. The yield of the +function is zero if all went well, or +

+  PCRE_ERROR_NOMEMORY       (-6)
+
+if the attempt to get the memory block failed. +

+

+When any of these functions encounter a substring that is unset, which can +happen when capturing subpattern number n+1 matches some part of the +subject, but subpattern n has not been used at all, they return an empty +string. This can be distinguished from a genuine zero-length substring by +inspecting the appropriate offset in ovector, which is negative for unset +substrings. +

+

+The two convenience functions pcre_free_substring() and +pcre_free_substring_list() can be used to free the memory returned by +a previous call of pcre_get_substring() or +pcre_get_substring_list(), respectively. They do nothing more than call +the function pointed to by pcre_free, which of course could be called +directly from a C program. However, PCRE is used in some situations where it is +linked via a special interface to another programming language that cannot use +pcre_free directly; it is for these cases that the functions are +provided. +

+
EXTRACTING CAPTURED SUBSTRINGS BY NAME
+

+int pcre_get_stringnumber(const pcre *code, +const char *name); +

+

+int pcre_copy_named_substring(const pcre *code, +const char *subject, int *ovector, +int stringcount, const char *stringname, +char *buffer, int buffersize); +

+

+int pcre_get_named_substring(const pcre *code, +const char *subject, int *ovector, +int stringcount, const char *stringname, +const char **stringptr); +

+

+To extract a substring by name, you first have to find associated number. +For example, for this pattern +

+  (a+)b(?P<xxx>\d+)...
+
+the number of the subpattern called "xxx" is 2. If the name is known to be +unique (PCRE_DUPNAMES was not set), you can find the number from the name by +calling pcre_get_stringnumber(). The first argument is the compiled +pattern, and the second is the name. The yield of the function is the +subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of +that name. +

+

+Given the number, you can extract the substring directly, or use one of the +functions described in the previous section. For convenience, there are also +two functions that do the whole job. +

+

+Most of the arguments of pcre_copy_named_substring() and +pcre_get_named_substring() are the same as those for the similarly named +functions that extract by number. As these are described in the previous +section, they are not re-described here. There are just two differences: +

+

+First, instead of a substring number, a substring name is given. Second, there +is an extra argument, given at the start, which is a pointer to the compiled +pattern. This is needed in order to gain access to the name-to-number +translation table. +

+

+These functions call pcre_get_stringnumber(), and if it succeeds, they +then call pcre_copy_substring() or pcre_get_substring(), as +appropriate. +

+
DUPLICATE SUBPATTERN NAMES
+

+int pcre_get_stringtable_entries(const pcre *code, +const char *name, char **first, char **last); +

+

+When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns +are not required to be unique. Normally, patterns with duplicate names are such +that in any one match, only one of the named subpatterns participates. An +example is shown in the +pcrepattern +documentation. When duplicates are present, pcre_copy_named_substring() +and pcre_get_named_substring() return the first substring corresponding +to the given name that is set. If none are set, an empty string is returned. +The pcre_get_stringnumber() function returns one of the numbers that are +associated with the name, but it is not defined which it is. +
+
+If you want to get full details of all captured substrings for a given name, +you must use the pcre_get_stringtable_entries() function. The first +argument is the compiled pattern, and the second is the name. The third and +fourth are pointers to variables which are updated by the function. After it +has run, they point to the first and last entries in the name-to-number table +for the given name. The function itself returns the length of each entry, or +PCRE_ERROR_NOSUBSTRING if there are none. The format of the table is described +above in the section entitled Information about a pattern. Given all the +relevant entries for the name, you can extract each of their numbers, and hence +the captured data, if any. +

+
FINDING ALL POSSIBLE MATCHES
+

+The traditional matching function uses a similar algorithm to Perl, which stops +when it finds the first match, starting at a given point in the subject. If you +want to find all possible matches, or the longest possible match, consider +using the alternative matching function (see below) instead. If you cannot use +the alternative function, but still need to find all possible matches, you +can kludge it up by making use of the callout facility, which is described in +the +pcrecallout +documentation. +

+

+What you have to do is to insert a callout right at the end of the pattern. +When your callout function is called, extract and save the current matched +substring. Then return 1, which forces pcre_exec() to backtrack and try +other alternatives. Ultimately, when it runs out of matches, pcre_exec() +will yield PCRE_ERROR_NOMATCH. +

+
MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
+

+int pcre_dfa_exec(const pcre *code, const pcre_extra *extra, +const char *subject, int length, int startoffset, +int options, int *ovector, int ovecsize, +int *workspace, int wscount); +

+

+The function pcre_dfa_exec() is called to match a subject string against +a compiled pattern, using a "DFA" matching algorithm. This has different +characteristics to the normal algorithm, and is not compatible with Perl. Some +of the features of PCRE patterns are not supported. Nevertheless, there are +times when this kind of matching can be useful. For a discussion of the two +matching algorithms, see the +pcrematching +documentation. +

+

+The arguments for the pcre_dfa_exec() function are the same as for +pcre_exec(), plus two extras. The ovector argument is used in a +different way, and this is described below. The other common arguments are used +in the same way as for pcre_exec(), so their description is not repeated +here. +

+

+The two additional arguments provide workspace for the function. The workspace +vector should contain at least 20 elements. It is used for keeping track of +multiple paths through the pattern tree. More workspace will be needed for +patterns and subjects where there are a lot of potential matches. +

+

+Here is an example of a simple call to pcre_dfa_exec(): +

+  int rc;
+  int ovector[10];
+  int wspace[20];
+  rc = pcre_dfa_exec(
+    re,             /* result of pcre_compile() */
+    NULL,           /* we didn't study the pattern */
+    "some string",  /* the subject string */
+    11,             /* the length of the subject string */
+    0,              /* start at offset 0 in the subject */
+    0,              /* default options */
+    ovector,        /* vector of integers for substring information */
+    10,             /* number of elements (NOT size in bytes) */
+    wspace,         /* working space vector */
+    20);            /* number of elements (NOT size in bytes) */
+
+

+
+Option bits for pcre_dfa_exec() +
+

+The unused bits of the options argument for pcre_dfa_exec() must be +zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, +PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL, +PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are +the same as for pcre_exec(), so their description is not repeated here. +

+  PCRE_PARTIAL
+
+This has the same general effect as it does for pcre_exec(), but the +details are slightly different. When PCRE_PARTIAL is set for +pcre_dfa_exec(), the return code PCRE_ERROR_NOMATCH is converted into +PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no +complete matches, but there is still at least one matching possibility. The +portion of the string that provided the partial match is set as the first +matching string. +
+  PCRE_DFA_SHORTEST
+
+Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as +soon as it has found one match. Because of the way the DFA algorithm works, +this is necessarily the shortest possible match at the first possible matching +point in the subject string. +
+  PCRE_DFA_RESTART
+
+When pcre_dfa_exec() is called with the PCRE_PARTIAL option, and returns +a partial match, it is possible to call it again, with additional subject +characters, and have it continue with the same match. The PCRE_DFA_RESTART +option requests this action; when it is set, the workspace and +wscount options must reference the same vector as before because data +about the match so far is left in them after a partial match. There is more +discussion of this facility in the +pcrepartial +documentation. +

+
+Successful returns from pcre_dfa_exec() +
+

+When pcre_dfa_exec() succeeds, it may have matched more than one +substring in the subject. Note, however, that all the matches from one run of +the function start at the same point in the subject. The shorter matches are +all initial substrings of the longer matches. For example, if the pattern +

+  <.*>
+
+is matched against the string +
+  This is <something> <something else> <something further> no more
+
+the three matched strings are +
+  <something>
+  <something> <something else>
+  <something> <something else> <something further>
+
+On success, the yield of the function is a number greater than zero, which is +the number of matched substrings. The substrings themselves are returned in +ovector. Each string uses two elements; the first is the offset to the +start, and the second is the offset to the end. All the strings have the same +start offset. (Space could have been saved by giving this only once, but it was +decided to retain some compatibility with the way pcre_exec() returns +data, even though the meaning of the strings is different.) +

+

+The strings are returned in reverse order of length; that is, the longest +matching string is given first. If there were too many matches to fit into +ovector, the yield of the function is zero, and the vector is filled with +the longest matches. +

+
+Error returns from pcre_dfa_exec() +
+

+The pcre_dfa_exec() function returns a negative number when it fails. +Many of the errors are the same as for pcre_exec(), and these are +described +above. +There are in addition the following errors that are specific to +pcre_dfa_exec(): +

+  PCRE_ERROR_DFA_UITEM      (-16)
+
+This return is given if pcre_dfa_exec() encounters an item in the pattern +that it does not support, for instance, the use of \C or a back reference. +
+  PCRE_ERROR_DFA_UCOND      (-17)
+
+This return is given if pcre_dfa_exec() encounters a condition item in a +pattern that uses a back reference for the condition. This is not supported. +
+  PCRE_ERROR_DFA_UMLIMIT    (-18)
+
+This return is given if pcre_dfa_exec() is called with an extra +block that contains a setting of the match_limit field. This is not +supported (it is meaningless). +
+  PCRE_ERROR_DFA_WSSIZE     (-19)
+
+This return is given if pcre_dfa_exec() runs out of space in the +workspace vector. +
+  PCRE_ERROR_DFA_RECURSE    (-20)
+
+When a recursive subpattern is processed, the matching function calls itself +recursively, using private vectors for ovector and workspace. This +error is given if the output vector is not large enough. This should be +extremely rare, as a vector of size 1000 is used. +

+

+Last updated: 08 June 2006 +
+Copyright © 1997-2006 University of Cambridge. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcrebuild.html b/libs/pcre/doc/html/pcrebuild.html new file mode 100644 index 0000000000..d405b4d8ac --- /dev/null +++ b/libs/pcre/doc/html/pcrebuild.html @@ -0,0 +1,225 @@ + + +pcrebuild specification + + +

pcrebuild man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+

+
PCRE BUILD-TIME OPTIONS
+

+This document describes the optional features of PCRE that can be selected when +the library is compiled. They are all selected, or deselected, by providing +options to the configure script that is run before the make +command. The complete list of options for configure (which includes the +standard ones such as the selection of the installation directory) can be +obtained by running +

+  ./configure --help
+
+The following sections describe certain options whose names begin with --enable +or --disable. These settings specify changes to the defaults for the +configure command. Because of the way that configure works, +--enable and --disable always come in pairs, so the complementary option always +exists as well, but as it specifies the default, it is not described. +

+
C++ SUPPORT
+

+By default, the configure script will search for a C++ compiler and C++ +header files. If it finds them, it automatically builds the C++ wrapper library +for PCRE. You can disable this by adding +

+  --disable-cpp
+
+to the configure command. +

+
UTF-8 SUPPORT
+

+To build PCRE with support for UTF-8 character strings, add +

+  --enable-utf8
+
+to the configure command. Of itself, this does not make PCRE treat +strings as UTF-8. As well as compiling PCRE with this option, you also have +have to set the PCRE_UTF8 option when you call the pcre_compile() +function. +

+
UNICODE CHARACTER PROPERTY SUPPORT
+

+UTF-8 support allows PCRE to process character values greater than 255 in the +strings that it handles. On its own, however, it does not provide any +facilities for accessing the properties of such characters. If you want to be +able to use the pattern escapes \P, \p, and \X, which refer to Unicode +character properties, you must add +

+  --enable-unicode-properties
+
+to the configure command. This implies UTF-8 support, even if you have +not explicitly requested it. +

+

+Including Unicode property support adds around 90K of tables to the PCRE +library, approximately doubling its size. Only the general category properties +such as Lu and Nd are supported. Details are given in the +pcrepattern +documentation. +

+
CODE VALUE OF NEWLINE
+

+By default, PCRE interprets character 10 (linefeed, LF) as indicating the end +of a line. This is the normal newline character on Unix-like systems. You can +compile PCRE to use character 13 (carriage return, CR) instead, by adding +

+  --enable-newline-is-cr
+
+to the configure command. There is also a --enable-newline-is-lf option, +which explicitly specifies linefeed as the newline character. +
+
+Alternatively, you can specify that line endings are to be indicated by the two +character sequence CRLF. If you want this, add +
+  --enable-newline-is-crlf
+
+to the configure command. Whatever line ending convention is selected +when PCRE is built can be overridden when the library functions are called. At +build time it is conventional to use the standard for your operating system. +

+
BUILDING SHARED AND STATIC LIBRARIES
+

+The PCRE building process uses libtool to build both shared and static +Unix libraries by default. You can suppress one of these by adding one of +

+  --disable-shared
+  --disable-static
+
+to the configure command, as required. +

+
POSIX MALLOC USAGE
+

+When PCRE is called through the POSIX interface (see the +pcreposix +documentation), additional working storage is required for holding the pointers +to capturing substrings, because PCRE requires three integers per substring, +whereas the POSIX interface provides only two. If the number of expected +substrings is small, the wrapper function uses space on the stack, because this +is faster than using malloc() for each call. The default threshold above +which the stack is no longer used is 10; it can be changed by adding a setting +such as +

+  --with-posix-malloc-threshold=20
+
+to the configure command. +

+
HANDLING VERY LARGE PATTERNS
+

+Within a compiled pattern, offset values are used to point from one part to +another (for example, from an opening parenthesis to an alternation +metacharacter). By default, two-byte values are used for these offsets, leading +to a maximum size for a compiled pattern of around 64K. This is sufficient to +handle all but the most gigantic patterns. Nevertheless, some people do want to +process enormous patterns, so it is possible to compile PCRE to use three-byte +or four-byte offsets by adding a setting such as +

+  --with-link-size=3
+
+to the configure command. The value given must be 2, 3, or 4. Using +longer offsets slows down the operation of PCRE because it has to load +additional bytes when handling them. +

+

+If you build PCRE with an increased link size, test 2 (and test 5 if you are +using UTF-8) will fail. Part of the output of these tests is a representation +of the compiled pattern, and this changes with the link size. +

+
AVOIDING EXCESSIVE STACK USAGE
+

+When matching with the pcre_exec() function, PCRE implements backtracking +by making recursive calls to an internal function called match(). In +environments where the size of the stack is limited, this can severely limit +PCRE's operation. (The Unix environment does not usually suffer from this +problem, but it may sometimes be necessary to increase the maximum stack size. +There is a discussion in the +pcrestack +documentation.) An alternative approach to recursion that uses memory from the +heap to remember data, instead of using recursive function calls, has been +implemented to work round the problem of limited stack size. If you want to +build a version of PCRE that works this way, add +

+  --disable-stack-for-recursion
+
+to the configure command. With this configuration, PCRE will use the +pcre_stack_malloc and pcre_stack_free variables to call memory +management functions. Separate functions are provided because the usage is very +predictable: the block sizes requested are always the same, and the blocks are +always freed in reverse order. A calling program might be able to implement +optimized functions that perform better than the standard malloc() and +free() functions. PCRE runs noticeably more slowly when built in this +way. This option affects only the pcre_exec() function; it is not +relevant for the the pcre_dfa_exec() function. +

+
LIMITING PCRE RESOURCE USAGE
+

+Internally, PCRE has a function called match(), which it calls repeatedly +(sometimes recursively) when matching a pattern with the pcre_exec() +function. By controlling the maximum number of times this function may be +called during a single matching operation, a limit can be placed on the +resources used by a single call to pcre_exec(). The limit can be changed +at run time, as described in the +pcreapi +documentation. The default is 10 million, but this can be changed by adding a +setting such as +

+  --with-match-limit=500000
+
+to the configure command. This setting has no effect on the +pcre_dfa_exec() matching function. +

+

+In some environments it is desirable to limit the depth of recursive calls of +match() more strictly than the total number of calls, in order to +restrict the maximum amount of stack (or heap, if --disable-stack-for-recursion +is specified) that is used. A second limit controls this; it defaults to the +value that is set for --with-match-limit, which imposes no additional +constraints. However, you can set a lower limit by adding, for example, +

+  --with-match-limit-recursion=10000
+
+to the configure command. This value can also be overridden at run time. +

+
USING EBCDIC CODE
+

+PCRE assumes by default that it will run in an environment where the character +code is ASCII (or Unicode, which is a superset of ASCII). PCRE can, however, be +compiled to run in an EBCDIC environment by adding +

+  --enable-ebcdic
+
+to the configure command. +

+

+Last updated: 06 June 2006 +
+Copyright © 1997-2006 University of Cambridge. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcrecallout.html b/libs/pcre/doc/html/pcrecallout.html new file mode 100644 index 0000000000..5ccfd5c4e3 --- /dev/null +++ b/libs/pcre/doc/html/pcrecallout.html @@ -0,0 +1,186 @@ + + +pcrecallout specification + + +

pcrecallout man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+

+
PCRE CALLOUTS
+

+int (*pcre_callout)(pcre_callout_block *); +

+

+PCRE provides a feature called "callout", which is a means of temporarily +passing control to the caller of PCRE in the middle of pattern matching. The +caller of PCRE provides an external function by putting its entry point in the +global variable pcre_callout. By default, this variable contains NULL, +which disables all calling out. +

+

+Within a regular expression, (?C) indicates the points at which the external +function is to be called. Different callout points can be identified by putting +a number less than 256 after the letter C. The default value is zero. +For example, this pattern has two callout points: +

+  (?C1)\deabc(?C2)def
+
+If the PCRE_AUTO_CALLOUT option bit is set when pcre_compile() is called, +PCRE automatically inserts callouts, all with number 255, before each item in +the pattern. For example, if PCRE_AUTO_CALLOUT is used with the pattern +
+  A(\d{2}|--)
+
+it is processed as if it were +
+
+(?C255)A(?C255)((?C255)\d{2}(?C255)|(?C255)-(?C255)-(?C255))(?C255) +
+
+Notice that there is a callout before and after each parenthesis and +alternation bar. Automatic callouts can be used for tracking the progress of +pattern matching. The +pcretest +command has an option that sets automatic callouts; when it is used, the output +indicates how the pattern is matched. This is useful information when you are +trying to optimize the performance of a particular pattern. +

+
MISSING CALLOUTS
+

+You should be aware that, because of optimizations in the way PCRE matches +patterns, callouts sometimes do not happen. For example, if the pattern is +

+  ab(?C4)cd
+
+PCRE knows that any matching string must contain the letter "d". If the subject +string is "abyz", the lack of "d" means that matching doesn't ever start, and +the callout is never reached. However, with "abyd", though the result is still +no match, the callout is obeyed. +

+
THE CALLOUT INTERFACE
+

+During matching, when PCRE reaches a callout point, the external function +defined by pcre_callout is called (if it is set). This applies to both +the pcre_exec() and the pcre_dfa_exec() matching functions. The +only argument to the callout function is a pointer to a pcre_callout +block. This structure contains the following fields: +

+  int          version;
+  int          callout_number;
+  int         *offset_vector;
+  const char  *subject;
+  int          subject_length;
+  int          start_match;
+  int          current_position;
+  int          capture_top;
+  int          capture_last;
+  void        *callout_data;
+  int          pattern_position;
+  int          next_item_length;
+
+The version field is an integer containing the version number of the +block format. The initial version was 0; the current version is 1. The version +number will change again in future if additional fields are added, but the +intention is never to remove any of the existing fields. +

+

+The callout_number field contains the number of the callout, as compiled +into the pattern (that is, the number after ?C for manual callouts, and 255 for +automatically generated callouts). +

+

+The offset_vector field is a pointer to the vector of offsets that was +passed by the caller to pcre_exec() or pcre_dfa_exec(). When +pcre_exec() is used, the contents can be inspected in order to extract +substrings that have been matched so far, in the same way as for extracting +substrings after a match has completed. For pcre_dfa_exec() this field is +not useful. +

+

+The subject and subject_length fields contain copies of the values +that were passed to pcre_exec(). +

+

+The start_match field contains the offset within the subject at which the +current match attempt started. If the pattern is not anchored, the callout +function may be called several times from the same point in the pattern for +different starting points in the subject. +

+

+The current_position field contains the offset within the subject of the +current match pointer. +

+

+When the pcre_exec() function is used, the capture_top field +contains one more than the number of the highest numbered captured substring so +far. If no substrings have been captured, the value of capture_top is +one. This is always the case when pcre_dfa_exec() is used, because it +does not support captured substrings. +

+

+The capture_last field contains the number of the most recently captured +substring. If no substrings have been captured, its value is -1. This is always +the case when pcre_dfa_exec() is used. +

+

+The callout_data field contains a value that is passed to +pcre_exec() or pcre_dfa_exec() specifically so that it can be +passed back in callouts. It is passed in the pcre_callout field of the +pcre_extra data structure. If no such data was passed, the value of +callout_data in a pcre_callout block is NULL. There is a +description of the pcre_extra structure in the +pcreapi +documentation. +

+

+The pattern_position field is present from version 1 of the +pcre_callout structure. It contains the offset to the next item to be +matched in the pattern string. +

+

+The next_item_length field is present from version 1 of the +pcre_callout structure. It contains the length of the next item to be +matched in the pattern string. When the callout immediately precedes an +alternation bar, a closing parenthesis, or the end of the pattern, the length +is zero. When the callout precedes an opening parenthesis, the length is that +of the entire subpattern. +

+

+The pattern_position and next_item_length fields are intended to +help in distinguishing between different automatic callouts, which all have the +same callout number. However, they are set for all callouts. +

+
RETURN VALUES
+

+The external callout function returns an integer to PCRE. If the value is zero, +matching proceeds as normal. If the value is greater than zero, matching fails +at the current point, but the testing of other matching possibilities goes +ahead, just as if a lookahead assertion had failed. If the value is less than +zero, the match is abandoned, and pcre_exec() (or pcre_dfa_exec()) +returns the negative value. +

+

+Negative values should normally be chosen from the set of PCRE_ERROR_xxx +values. In particular, PCRE_ERROR_NOMATCH forces a standard "no match" failure. +The error number PCRE_ERROR_CALLOUT is reserved for use by callout functions; +it will never be used by PCRE itself. +

+

+Last updated: 28 February 2005 +
+Copyright © 1997-2005 University of Cambridge. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcrecompat.html b/libs/pcre/doc/html/pcrecompat.html new file mode 100644 index 0000000000..0d4e1df864 --- /dev/null +++ b/libs/pcre/doc/html/pcrecompat.html @@ -0,0 +1,156 @@ + + +pcrecompat specification + + +

pcrecompat man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+DIFFERENCES BETWEEN PCRE AND PERL +
+

+This document describes the differences in the ways that PCRE and Perl handle +regular expressions. The differences described here are with respect to Perl +5.8. +

+

+1. PCRE has only a subset of Perl's UTF-8 and Unicode support. Details of what +it does have are given in the +section on UTF-8 support +in the main +pcre +page. +

+

+2. PCRE does not allow repeat quantifiers on lookahead assertions. Perl permits +them, but they do not mean what you might think. For example, (?!a){3} does +not assert that the next three characters are not "a". It just asserts that the +next character is not "a" three times. +

+

+3. Capturing subpatterns that occur inside negative lookahead assertions are +counted, but their entries in the offsets vector are never set. Perl sets its +numerical variables from any such patterns that are matched before the +assertion fails to match something (thereby succeeding), but only if the +negative lookahead assertion contains just one branch. +

+

+4. Though binary zero characters are supported in the subject string, they are +not allowed in a pattern string because it is passed as a normal C string, +terminated by zero. The escape sequence \0 can be used in the pattern to +represent a binary zero. +

+

+5. The following Perl escape sequences are not supported: \l, \u, \L, +\U, and \N. In fact these are implemented by Perl's general string-handling +and are not part of its pattern matching engine. If any of these are +encountered by PCRE, an error is generated. +

+

+6. The Perl escape sequences \p, \P, and \X are supported only if PCRE is +built with Unicode character property support. The properties that can be +tested with \p and \P are limited to the general category properties such as +Lu and Nd, script names such as Greek or Han, and the derived properties Any +and L&. +

+

+7. PCRE does support the \Q...\E escape for quoting substrings. Characters in +between are treated as literals. This is slightly different from Perl in that $ +and @ are also handled as literals inside the quotes. In Perl, they cause +variable interpolation (but of course PCRE does not have variables). Note the +following examples: +

+    Pattern            PCRE matches      Perl matches
+
+    \Qabc$xyz\E        abc$xyz           abc followed by the contents of $xyz
+    \Qabc\$xyz\E       abc\$xyz          abc\$xyz
+    \Qabc\E\$\Qxyz\E   abc$xyz           abc$xyz
+
+The \Q...\E sequence is recognized both inside and outside character classes. +

+

+8. Fairly obviously, PCRE does not support the (?{code}) and (?p{code}) +constructions. However, there is support for recursive patterns using the +non-Perl items (?R), (?number), and (?P>name). Also, the PCRE "callout" feature +allows an external function to be called during pattern matching. See the +pcrecallout +documentation for details. +

+

+9. There are some differences that are concerned with the settings of captured +strings when part of a pattern is repeated. For example, matching "aba" against +the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE it is set to "b". +

+

+10. PCRE provides some extensions to the Perl regular expression facilities: +
+
+(a) Although lookbehind assertions must match fixed length strings, each +alternative branch of a lookbehind assertion can match a different length of +string. Perl requires them all to have the same length. +
+
+(b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ +meta-character matches only at the very end of the string. +
+
+(c) If PCRE_EXTRA is set, a backslash followed by a letter with no special +meaning is faulted. Otherwise, like Perl, the backslash is ignored. (Perl can +be made to issue a warning.) +
+
+(d) If PCRE_UNGREEDY is set, the greediness of the repetition quantifiers is +inverted, that is, by default they are not greedy, but if followed by a +question mark they are. +
+
+(e) PCRE_ANCHORED can be used at matching time to force a pattern to be tried +only at the first matching position in the subject string. +
+
+(f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NO_AUTO_CAPTURE +options for pcre_exec() have no Perl equivalents. +
+
+(g) The (?R), (?number), and (?P>name) constructs allows for recursive pattern +matching (Perl can do this using the (?p{code}) construct, which PCRE cannot +support.) +
+
+(h) PCRE supports named capturing substrings, using the Python syntax. +
+
+(i) PCRE supports the possessive quantifier "++" syntax, taken from Sun's Java +package. +
+
+(j) The (R) condition, for testing recursion, is a PCRE extension. +
+
+(k) The callout facility is PCRE-specific. +
+
+(l) The partial matching facility is PCRE-specific. +
+
+(m) Patterns compiled by PCRE can be saved and re-used at a later time, even on +different hosts that have the other endianness. +
+
+(n) The alternative matching function (pcre_dfa_exec()) matches in a +different way and is not Perl-compatible. +

+

+Last updated: 06 June 2006 +
+Copyright © 1997-2006 University of Cambridge. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcrecpp.html b/libs/pcre/doc/html/pcrecpp.html new file mode 100644 index 0000000000..8c3216daeb --- /dev/null +++ b/libs/pcre/doc/html/pcrecpp.html @@ -0,0 +1,337 @@ + + +pcrecpp specification + + +

pcrecpp man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+

+
SYNOPSIS OF C++ WRAPPER
+

+#include <pcrecpp.h> +

+

+

+
DESCRIPTION
+

+The C++ wrapper for PCRE was provided by Google Inc. Some additional +functionality was added by Giuseppe Maxia. This brief man page was constructed +from the notes in the pcrecpp.h file, which should be consulted for +further details. +

+
MATCHING INTERFACE
+

+The "FullMatch" operation checks that supplied text matches a supplied pattern +exactly. If pointer arguments are supplied, it copies matched sub-strings that +match sub-patterns into them. +

+  Example: successful match
+     pcrecpp::RE re("h.*o");
+     re.FullMatch("hello");
+
+  Example: unsuccessful match (requires full match):
+     pcrecpp::RE re("e");
+     !re.FullMatch("hello");
+
+  Example: creating a temporary RE object:
+     pcrecpp::RE("h.*o").FullMatch("hello");
+
+You can pass in a "const char*" or a "string" for "text". The examples below +tend to use a const char*. You can, as in the different examples above, store +the RE object explicitly in a variable or use a temporary RE object. The +examples below use one mode or the other arbitrarily. Either could correctly be +used for any of these examples. +

+

+You must supply extra pointer arguments to extract matched subpieces. +

+  Example: extracts "ruby" into "s" and 1234 into "i"
+     int i;
+     string s;
+     pcrecpp::RE re("(\\w+):(\\d+)");
+     re.FullMatch("ruby:1234", &s, &i);
+
+  Example: does not try to extract any extra sub-patterns
+     re.FullMatch("ruby:1234", &s);
+
+  Example: does not try to extract into NULL
+     re.FullMatch("ruby:1234", NULL, &i);
+
+  Example: integer overflow causes failure
+     !re.FullMatch("ruby:1234567891234", NULL, &i);
+
+  Example: fails because there aren't enough sub-patterns:
+     !pcrecpp::RE("\\w+:\\d+").FullMatch("ruby:1234", &s);
+
+  Example: fails because string cannot be stored in integer
+     !pcrecpp::RE("(.*)").FullMatch("ruby", &i);
+
+The provided pointer arguments can be pointers to any scalar numeric +type, or one of: +
+   string        (matched piece is copied to string)
+   StringPiece   (StringPiece is mutated to point to matched piece)
+   T             (where "bool T::ParseFrom(const char*, int)" exists)
+   NULL          (the corresponding matched sub-pattern is not copied)
+
+The function returns true iff all of the following conditions are satisfied: +
+  a. "text" matches "pattern" exactly;
+
+  b. The number of matched sub-patterns is >= number of supplied
+     pointers;
+
+  c. The "i"th argument has a suitable type for holding the
+     string captured as the "i"th sub-pattern. If you pass in
+     NULL for the "i"th argument, or pass fewer arguments than
+     number of sub-patterns, "i"th captured sub-pattern is
+     ignored.
+
+The matching interface supports at most 16 arguments per call. +If you need more, consider using the more general interface +pcrecpp::RE::DoMatch. See pcrecpp.h for the signature for +DoMatch. +

+
PARTIAL MATCHES
+

+You can use the "PartialMatch" operation when you want the pattern +to match any substring of the text. +

+  Example: simple search for a string:
+     pcrecpp::RE("ell").PartialMatch("hello");
+
+  Example: find first number in a string:
+     int number;
+     pcrecpp::RE re("(\\d+)");
+     re.PartialMatch("x*100 + 20", &number);
+     assert(number == 100);
+
+

+
UTF-8 AND THE MATCHING INTERFACE
+

+By default, pattern and text are plain text, one byte per character. The UTF8 +flag, passed to the constructor, causes both pattern and string to be treated +as UTF-8 text, still a byte stream but potentially multiple bytes per +character. In practice, the text is likelier to be UTF-8 than the pattern, but +the match returned may depend on the UTF8 flag, so always use it when matching +UTF8 text. For example, "." will match one byte normally but with UTF8 set may +match up to three bytes of a multi-byte character. +

+  Example:
+     pcrecpp::RE_Options options;
+     options.set_utf8();
+     pcrecpp::RE re(utf8_pattern, options);
+     re.FullMatch(utf8_string);
+
+  Example: using the convenience function UTF8():
+     pcrecpp::RE re(utf8_pattern, pcrecpp::UTF8());
+     re.FullMatch(utf8_string);
+
+NOTE: The UTF8 flag is ignored if pcre was not configured with the +
+      --enable-utf8 flag.
+
+

+
PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE
+

+PCRE defines some modifiers to change the behavior of the regular expression +engine. The C++ wrapper defines an auxiliary class, RE_Options, as a vehicle to +pass such modifiers to a RE class. Currently, the following modifiers are +supported: +

+   modifier              description               Perl corresponding
+
+   PCRE_CASELESS         case insensitive match      /i
+   PCRE_MULTILINE        multiple lines match        /m
+   PCRE_DOTALL           dot matches newlines        /s
+   PCRE_DOLLAR_ENDONLY   $ matches only at end       N/A
+   PCRE_EXTRA            strict escape parsing       N/A
+   PCRE_EXTENDED         ignore whitespaces          /x
+   PCRE_UTF8             handles UTF8 chars          built-in
+   PCRE_UNGREEDY         reverses * and *?           N/A
+   PCRE_NO_AUTO_CAPTURE  disables capturing parens   N/A (*)
+
+(*) Both Perl and PCRE allow non capturing parentheses by means of the +"?:" modifier within the pattern itself. e.g. (?:ab|cd) does not +capture, while (ab|cd) does. +

+

+For a full account on how each modifier works, please check the +PCRE API reference page. +

+

+For each modifier, there are two member functions whose name is made +out of the modifier in lowercase, without the "PCRE_" prefix. For +instance, PCRE_CASELESS is handled by +

+  bool caseless()
+
+which returns true if the modifier is set, and +
+  RE_Options & set_caseless(bool)
+
+which sets or unsets the modifier. Moreover, PCRE_EXTRA_MATCH_LIMIT can be +accessed through the set_match_limit() and match_limit() member +functions. Setting match_limit to a non-zero value will limit the +execution of pcre to keep it from doing bad things like blowing the stack or +taking an eternity to return a result. A value of 5000 is good enough to stop +stack blowup in a 2MB thread stack. Setting match_limit to zero disables +match limiting. Alternatively, you can call match_limit_recursion() +which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION to limit how much PCRE +recurses. match_limit() limits the number of matches PCRE does; +match_limit_recursion() limits the depth of internal recursion, and +therefore the amount of stack that is used. +

+

+Normally, to pass one or more modifiers to a RE class, you declare +a RE_Options object, set the appropriate options, and pass this +object to a RE constructor. Example: +

+   RE_options opt;
+   opt.set_caseless(true);
+   if (RE("HELLO", opt).PartialMatch("hello world")) ...
+
+RE_options has two constructors. The default constructor takes no arguments and +creates a set of flags that are off by default. The optional parameter +option_flags is to facilitate transfer of legacy code from C programs. +This lets you do +
+   RE(pattern,
+     RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str);
+
+However, new code is better off doing +
+   RE(pattern,
+     RE_Options().set_caseless(true).set_multiline(true))
+       .PartialMatch(str);
+
+If you are going to pass one of the most used modifiers, there are some +convenience functions that return a RE_Options class with the +appropriate modifier already set: CASELESS(), UTF8(), +MULTILINE(), DOTALL(), and EXTENDED(). +

+

+If you need to set several options at once, and you don't want to go through +the pains of declaring a RE_Options object and setting several options, there +is a parallel method that give you such ability on the fly. You can concatenate +several set_xxxxx() member functions, since each of them returns a +reference to its class object. For example, to pass PCRE_CASELESS, +PCRE_EXTENDED, and PCRE_MULTILINE to a RE with one statement, you may write: +

+   RE(" ^ xyz \\s+ .* blah$",
+     RE_Options()
+       .set_caseless(true)
+       .set_extended(true)
+       .set_multiline(true)).PartialMatch(sometext);
+
+
+

+
SCANNING TEXT INCREMENTALLY
+

+The "Consume" operation may be useful if you want to repeatedly +match regular expressions at the front of a string and skip over +them as they match. This requires use of the "StringPiece" type, +which represents a sub-range of a real string. Like RE, StringPiece +is defined in the pcrecpp namespace. +

+  Example: read lines of the form "var = value" from a string.
+     string contents = ...;                 // Fill string somehow
+     pcrecpp::StringPiece input(contents);  // Wrap in a StringPiece
+
+

+

+

+     string var;
+     int value;
+     pcrecpp::RE re("(\\w+) = (\\d+)\n");
+     while (re.Consume(&input, &var, &value)) {
+       ...;
+     }
+
+Each successful call to "Consume" will set "var/value", and also +advance "input" so it points past the matched text. +

+

+The "FindAndConsume" operation is similar to "Consume" but does not +anchor your match at the beginning of the string. For example, you +could extract all words from a string by repeatedly calling +

+  pcrecpp::RE("(\\w+)").FindAndConsume(&input, &word)
+
+

+
PARSING HEX/OCTAL/C-RADIX NUMBERS
+

+By default, if you pass a pointer to a numeric value, the +corresponding text is interpreted as a base-10 number. You can +instead wrap the pointer with a call to one of the operators Hex(), +Octal(), or CRadix() to interpret the text in another base. The +CRadix operator interprets C-style "0" (base-8) and "0x" (base-16) +prefixes, but defaults to base-10. +

+  Example:
+    int a, b, c, d;
+    pcrecpp::RE re("(.*) (.*) (.*) (.*)");
+    re.FullMatch("100 40 0100 0x40",
+                 pcrecpp::Octal(&a), pcrecpp::Hex(&b),
+                 pcrecpp::CRadix(&c), pcrecpp::CRadix(&d));
+
+will leave 64 in a, b, c, and d. +

+
REPLACING PARTS OF STRINGS
+

+You can replace the first match of "pattern" in "str" with "rewrite". +Within "rewrite", backslash-escaped digits (\1 to \9) can be +used to insert text matching corresponding parenthesized group +from the pattern. \0 in "rewrite" refers to the entire matching +text. For example: +

+  string s = "yabba dabba doo";
+  pcrecpp::RE("b+").Replace("d", &s);
+
+will leave "s" containing "yada dabba doo". The result is true if the pattern +matches and a replacement occurs, false otherwise. +

+

+GlobalReplace is like Replace except that it replaces all +occurrences of the pattern in the string with the rewrite. Replacements are +not subject to re-matching. For example: +

+  string s = "yabba dabba doo";
+  pcrecpp::RE("b+").GlobalReplace("d", &s);
+
+will leave "s" containing "yada dada doo". It returns the number of +replacements made. +

+

+Extract is like Replace, except that if the pattern matches, +"rewrite" is copied into "out" (an additional argument) with substitutions. +The non-matching portions of "text" are ignored. Returns true iff a match +occurred and the extraction happened successfully; if no match occurs, the +string is left unaffected. +

+
AUTHOR
+

+The C++ wrapper was contributed by Google Inc. +
+Copyright © 2005 Google Inc. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcregrep.html b/libs/pcre/doc/html/pcregrep.html new file mode 100644 index 0000000000..97ece8e664 --- /dev/null +++ b/libs/pcre/doc/html/pcregrep.html @@ -0,0 +1,424 @@ + + +pcregrep specification + + +

pcregrep man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+

+
SYNOPSIS
+

+pcregrep [options] [long options] [pattern] [path1 path2 ...] +

+
DESCRIPTION
+

+pcregrep searches files for character patterns, in the same way as other +grep commands do, but it uses the PCRE regular expression library to support +patterns that are compatible with the regular expressions of Perl 5. See +pcrepattern +for a full description of syntax and semantics of the regular expressions that +PCRE supports. +

+

+Patterns, whether supplied on the command line or in a separate file, are given +without delimiters. For example: +

+  pcregrep Thursday /etc/motd
+
+If you attempt to use delimiters (for example, by surrounding a pattern with +slashes, as is common in Perl scripts), they are interpreted as part of the +pattern. Quotes can of course be used on the command line because they are +interpreted by the shell, and indeed they are required if a pattern contains +white space or shell metacharacters. +

+

+The first argument that follows any option settings is treated as the single +pattern to be matched when neither -e nor -f is present. +Conversely, when one or both of these options are used to specify patterns, all +arguments are treated as path names. At least one of -e, -f, or an +argument pattern must be provided. +

+

+If no files are specified, pcregrep reads the standard input. The +standard input can also be referenced by a name consisting of a single hyphen. +For example: +

+  pcregrep some-pattern /file1 - /file3
+
+By default, each line that matches the pattern is copied to the standard +output, and if there is more than one file, the file name is output at the +start of each line. However, there are options that can change how +pcregrep behaves. In particular, the -M option makes it possible to +search for patterns that span line boundaries. What defines a line boundary is +controlled by the -N (--newline) option. +

+

+Patterns are limited to 8K or BUFSIZ characters, whichever is the greater. +BUFSIZ is defined in <stdio.h>. +

+

+If the LC_ALL or LC_CTYPE environment variable is set, +pcregrep uses the value to set a locale when calling the PCRE library. +The --locale option can be used to override this. +

+
OPTIONS
+

+-- +This terminate the list of options. It is useful if the next item on the +command line starts with a hyphen but is not an option. This allows for the +processing of patterns and filenames that start with hyphens. +

+

+-A number, --after-context=number +Output number lines of context after each matching line. If filenames +and/or line numbers are being output, a hyphen separator is used instead of a +colon for the context lines. A line containing "--" is output between each +group of lines, unless they are in fact contiguous in the input file. The value +of number is expected to be relatively small. However, pcregrep +guarantees to have up to 8K of following text available for context output. +

+

+-B number, --before-context=number +Output number lines of context before each matching line. If filenames +and/or line numbers are being output, a hyphen separator is used instead of a +colon for the context lines. A line containing "--" is output between each +group of lines, unless they are in fact contiguous in the input file. The value +of number is expected to be relatively small. However, pcregrep +guarantees to have up to 8K of preceding text available for context output. +

+

+-C number, --context=number +Output number lines of context both before and after each matching line. +This is equivalent to setting both -A and -B to the same value. +

+

+-c, --count +Do not output individual lines; instead just output a count of the number of +lines that would otherwise have been output. If several files are given, a +count is output for each of them. In this mode, the -A, -B, and +-C options are ignored. +

+

+--colour, --color +If this option is given without any data, it is equivalent to "--colour=auto". +If data is required, it must be given in the same shell item, separated by an +equals sign. +

+

+--colour=value, --color=value +This option specifies under what circumstances the part of a line that matched +a pattern should be coloured in the output. The value may be "never" (the +default), "always", or "auto". In the latter case, colouring happens only if +the standard output is connected to a terminal. The colour can be specified by +setting the environment variable PCREGREP_COLOUR or PCREGREP_COLOR. The value +of this variable should be a string of two numbers, separated by a semicolon. +They are copied directly into the control string for setting colour on a +terminal, so it is your responsibility to ensure that they make sense. If +neither of the environment variables is set, the default is "1;31", which gives +red. +

+

+-D action, --devices=action +If an input path is not a regular file or a directory, "action" specifies how +it is to be processed. Valid values are "read" (the default) or "skip" +(silently skip the path). +

+

+-d action, --directories=action +If an input path is a directory, "action" specifies how it is to be processed. +Valid values are "read" (the default), "recurse" (equivalent to the -r +option), or "skip" (silently skip the path). In the default case, directories +are read as if they were ordinary files. In some operating systems the effect +of reading a directory like this is an immediate end-of-file. +

+

+-e pattern, --regex=pattern, +--regexp=pattern Specify a pattern to be matched. This option can +be used multiple times in order to specify several patterns. It can also be +used as a way of specifying a single pattern that starts with a hyphen. When +-e is used, no argument pattern is taken from the command line; all +arguments are treated as file names. There is an overall maximum of 100 +patterns. They are applied to each line in the order in which they are defined +until one matches (or fails to match if -v is used). If -f is used +with -e, the command line patterns are matched first, followed by the +patterns from the file, independent of the order in which these options are +specified. Note that multiple use of -e is not the same as a single +pattern with alternatives. For example, X|Y finds the first character in a line +that is X or Y, whereas if the two patterns are given separately, +pcregrep finds X if it is present, even if it follows Y in the line. It +finds Y only if there is no X in the line. This really matters only if you are +using -o to show the portion of the line that matched. +

+

+--exclude=pattern +When pcregrep is searching the files in a directory as a consequence of +the -r (recursive search) option, any files whose names match the pattern +are excluded. The pattern is a PCRE regular expression. If a file name matches +both --include and --exclude, it is excluded. There is no short +form for this option. +

+

+-F, --fixed-strings +Interpret each pattern as a list of fixed strings, separated by newlines, +instead of as a regular expression. The -w (match as a word) and -x +(match whole line) options can be used with -F. They apply to each of the +fixed strings. A line is selected if any of the fixed strings are found in it +(subject to -w or -x, if present). +

+

+-f filename, --file=filename +Read a number of patterns from the file, one per line, and match them against +each line of input. A data line is output if any of the patterns match it. The +filename can be given as "-" to refer to the standard input. When -f is +used, patterns specified on the command line using -e may also be +present; they are tested before the file's patterns. However, no other pattern +is taken from the command line; all arguments are treated as file names. There +is an overall maximum of 100 patterns. Trailing white space is removed from +each line, and blank lines are ignored. An empty file contains no patterns and +therefore matches nothing. +

+

+-H, --with-filename +Force the inclusion of the filename at the start of output lines when searching +a single file. By default, the filename is not shown in this case. For matching +lines, the filename is followed by a colon and a space; for context lines, a +hyphen separator is used. If a line number is also being output, it follows the +file name without a space. +

+

+-h, --no-filename +Suppress the output filenames when searching multiple files. By default, +filenames are shown when multiple files are searched. For matching lines, the +filename is followed by a colon and a space; for context lines, a hyphen +separator is used. If a line number is also being output, it follows the file +name without a space. +

+

+--help +Output a brief help message and exit. +

+

+-i, --ignore-case +Ignore upper/lower case distinctions during comparisons. +

+

+--include=pattern +When pcregrep is searching the files in a directory as a consequence of +the -r (recursive search) option, only those files whose names match the +pattern are included. The pattern is a PCRE regular expression. If a file name +matches both --include and --exclude, it is excluded. There is no +short form for this option. +

+

+-L, --files-without-match +Instead of outputting lines from the files, just output the names of the files +that do not contain any lines that would have been output. Each file name is +output once, on a separate line. +

+

+-l, --files-with-matches +Instead of outputting lines from the files, just output the names of the files +containing lines that would have been output. Each file name is output +once, on a separate line. Searching stops as soon as a matching line is found +in a file. +

+

+--label=name +This option supplies a name to be used for the standard input when file names +are being output. If not supplied, "(standard input)" is used. There is no +short form for this option. +

+

+--locale=locale-name +This option specifies a locale to be used for pattern matching. It overrides +the value in the LC_ALL or LC_CTYPE environment variables. If no +locale is specified, the PCRE library's default (usually the "C" locale) is +used. There is no short form for this option. +

+

+-M, --multiline +Allow patterns to match more than one line. When this option is given, patterns +may usefully contain literal newline characters and internal occurrences of ^ +and $ characters. The output for any one match may consist of more than one +line. When this option is set, the PCRE library is called in "multiline" mode. +There is a limit to the number of lines that can be matched, imposed by the way +that pcregrep buffers the input file as it scans it. However, +pcregrep ensures that at least 8K characters or the rest of the document +(whichever is the shorter) are available for forward matching, and similarly +the previous 8K characters (or all the previous characters, if fewer than 8K) +are guaranteed to be available for lookbehind assertions. +

+

+-N newline-type, --newline=newline-type +The PCRE library supports three different character sequences for indicating +the ends of lines. They are the single-character sequences CR (carriage return) +and LF (linefeed), and the two-character sequence CR, LF. When the library is +built, a default line-ending sequence is specified. This is normally the +standard sequence for the operating system. Unless otherwise specified by this +option, pcregrep uses the default. The possible values for this option +are CR, LF, or CRLF. This makes it possible to use pcregrep on files that +have come from other environments without having to modify their line endings. +If the data that is being scanned does not agree with the convention set by +this option, pcregrep may behave in strange ways. +

+

+-n, --line-number +Precede each output line by its line number in the file, followed by a colon +and a space for matching lines or a hyphen and a space for context lines. If +the filename is also being output, it precedes the line number. +

+

+-o, --only-matching +Show only the part of the line that matched a pattern. In this mode, no +context is shown. That is, the -A, -B, and -C options are +ignored. +

+

+-q, --quiet +Work quietly, that is, display nothing except error messages. The exit +status indicates whether or not any matches were found. +

+

+-r, --recursive +If any given path is a directory, recursively scan the files it contains, +taking note of any --include and --exclude settings. By default, a +directory is read as a normal file; in some operating systems this gives an +immediate end-of-file. This option is a shorthand for setting the -d +option to "recurse". +

+

+-s, --no-messages +Suppress error messages about non-existent or unreadable files. Such files are +quietly skipped. However, the return code is still 2, even if matches were +found in other files. +

+

+-u, --utf-8 +Operate in UTF-8 mode. This option is available only if PCRE has been compiled +with UTF-8 support. Both patterns and subject lines must be valid strings of +UTF-8 characters. +

+

+-V, --version +Write the version numbers of pcregrep and the PCRE library that is being +used to the standard error stream. +

+

+-v, --invert-match +Invert the sense of the match, so that lines which do not match any of +the patterns are the ones that are found. +

+

+-w, --word-regex, --word-regexp +Force the patterns to match only whole words. This is equivalent to having \b +at the start and end of the pattern. +

+

+-x, --line-regex, \fP--line-regexp\fP +Force the patterns to be anchored (each must start matching at the beginning of +a line) and in addition, require them to match entire lines. This is +equivalent to having ^ and $ characters at the start and end of each +alternative branch in every pattern. +

+
ENVIRONMENT VARIABLES
+

+The environment variables LC_ALL and LC_CTYPE are examined, in that +order, for a locale. The first one that is set is used. This can be overridden +by the --locale option. If no locale is set, the PCRE library's default +(usually the "C" locale) is used. +

+
NEWLINES
+

+The -N (--newline) option allows pcregrep to scan files with +different newline conventions from the default. However, the setting of this +option does not affect the way in which pcregrep writes information to +the standard error and output streams. It uses the string "\n" in C +printf() calls to indicate newlines, relying on the C I/O library to +convert this to an appropriate sequence if the output is sent to a file. +

+
OPTIONS COMPATIBILITY
+

+The majority of short and long forms of pcregrep's options are the same +as in the GNU grep program. Any long option of the form +--xxx-regexp (GNU terminology) is also available as --xxx-regex +(PCRE terminology). However, the --locale, -M, --multiline, +-u, and --utf-8 options are specific to pcregrep. +

+
OPTIONS WITH DATA
+

+There are four different ways in which an option with data can be specified. +If a short form option is used, the data may follow immediately, or in the next +command line item. For example: +

+  -f/some/file
+  -f /some/file
+
+If a long form option is used, the data may appear in the same command line +item, separated by an equals character, or (with one exception) it may appear +in the next command line item. For example: +
+  --file=/some/file
+  --file /some/file
+
+Note, however, that if you want to supply a file name beginning with ~ as data +in a shell command, and have the shell expand ~ to a home directory, you must +separate the file name from the option, because the shell does not treat ~ +specially unless it is at the start of an item. +

+

+The exception to the above is the --colour (or --color) option, +for which the data is optional. If this option does have data, it must be given +in the first form, using an equals character. Otherwise it will be assumed that +it has no data. +

+
MATCHING ERRORS
+

+It is possible to supply a regular expression that takes a very long time to +fail to match certain lines. Such patterns normally involve nested indefinite +repeats, for example: (a+)*\d when matched against a line of a's with no final +digit. The PCRE matching function has a resource limit that causes it to abort +in these circumstances. If this happens, pcregrep outputs an error +message and the line that caused the problem to the standard error stream. If +there are more than 20 such errors, pcregrep gives up. +

+
DIAGNOSTICS
+

+Exit status is 0 if any matches were found, 1 if no matches were found, and 2 +for syntax errors and non-existent or inacessible files (even if matches were +found in other files) or too many matching errors. Using the -s option to +suppress error messages about inaccessble files does not affect the return +code. +

+
AUTHOR
+

+Philip Hazel +
+University Computing Service +
+Cambridge CB2 3QG, England. +

+

+Last updated: 06 June 2006 +
+Copyright © 1997-2006 University of Cambridge. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcrematching.html b/libs/pcre/doc/html/pcrematching.html new file mode 100644 index 0000000000..56740a5db2 --- /dev/null +++ b/libs/pcre/doc/html/pcrematching.html @@ -0,0 +1,192 @@ + + +pcrematching specification + + +

pcrematching man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+

+
PCRE MATCHING ALGORITHMS
+

+This document describes the two different algorithms that are available in PCRE +for matching a compiled regular expression against a given subject string. The +"standard" algorithm is the one provided by the pcre_exec() function. +This works in the same was as Perl's matching function, and provides a +Perl-compatible matching operation. +

+

+An alternative algorithm is provided by the pcre_dfa_exec() function; +this operates in a different way, and is not Perl-compatible. It has advantages +and disadvantages compared with the standard algorithm, and these are described +below. +

+

+When there is only one possible way in which a given subject string can match a +pattern, the two algorithms give the same answer. A difference arises, however, +when there are multiple possibilities. For example, if the pattern +

+  ^<.*>
+
+is matched against the string +
+  <something> <something else> <something further>
+
+there are three possible answers. The standard algorithm finds only one of +them, whereas the DFA algorithm finds all three. +

+
REGULAR EXPRESSIONS AS TREES
+

+The set of strings that are matched by a regular expression can be represented +as a tree structure. An unlimited repetition in the pattern makes the tree of +infinite size, but it is still a tree. Matching the pattern to a given subject +string (from a given starting point) can be thought of as a search of the tree. +There are two ways to search a tree: depth-first and breadth-first, and these +correspond to the two matching algorithms provided by PCRE. +

+
THE STANDARD MATCHING ALGORITHM
+

+In the terminology of Jeffrey Friedl's book \fIMastering Regular +Expressions\fP, the standard algorithm is an "NFA algorithm". It conducts a +depth-first search of the pattern tree. That is, it proceeds along a single +path through the tree, checking that the subject matches what is required. When +there is a mismatch, the algorithm tries any alternatives at the current point, +and if they all fail, it backs up to the previous branch point in the tree, and +tries the next alternative branch at that level. This often involves backing up +(moving to the left) in the subject string as well. The order in which +repetition branches are tried is controlled by the greedy or ungreedy nature of +the quantifier. +

+

+If a leaf node is reached, a matching string has been found, and at that point +the algorithm stops. Thus, if there is more than one possible match, this +algorithm returns the first one that it finds. Whether this is the shortest, +the longest, or some intermediate length depends on the way the greedy and +ungreedy repetition quantifiers are specified in the pattern. +

+

+Because it ends up with a single path through the tree, it is relatively +straightforward for this algorithm to keep track of the substrings that are +matched by portions of the pattern in parentheses. This provides support for +capturing parentheses and back references. +

+
THE DFA MATCHING ALGORITHM
+

+DFA stands for "deterministic finite automaton", but you do not need to +understand the origins of that name. This algorithm conducts a breadth-first +search of the tree. Starting from the first matching point in the subject, it +scans the subject string from left to right, once, character by character, and +as it does this, it remembers all the paths through the tree that represent +valid matches. +

+

+The scan continues until either the end of the subject is reached, or there are +no more unterminated paths. At this point, terminated paths represent the +different matching possibilities (if there are none, the match has failed). +Thus, if there is more than one possible match, this algorithm finds all of +them, and in particular, it finds the longest. In PCRE, there is an option to +stop the algorithm after the first match (which is necessarily the shortest) +has been found. +

+

+Note that all the matches that are found start at the same point in the +subject. If the pattern +

+  cat(er(pillar)?)
+
+is matched against the string "the caterpillar catchment", the result will be +the three strings "cat", "cater", and "caterpillar" that start at the fourth +character of the subject. The algorithm does not automatically move on to find +matches that start at later positions. +

+

+There are a number of features of PCRE regular expressions that are not +supported by the DFA matching algorithm. They are as follows: +

+

+1. Because the algorithm finds all possible matches, the greedy or ungreedy +nature of repetition quantifiers is not relevant. Greedy and ungreedy +quantifiers are treated in exactly the same way. +

+

+2. When dealing with multiple paths through the tree simultaneously, it is not +straightforward to keep track of captured substrings for the different matching +possibilities, and PCRE's implementation of this algorithm does not attempt to +do this. This means that no captured substrings are available. +

+

+3. Because no substrings are captured, back references within the pattern are +not supported, and cause errors if encountered. +

+

+4. For the same reason, conditional expressions that use a backreference as the +condition are not supported. +

+

+5. Callouts are supported, but the value of the capture_top field is +always 1, and the value of the capture_last field is always -1. +

+

+6. +The \C escape sequence, which (in the standard algorithm) matches a single +byte, even in UTF-8 mode, is not supported because the DFA algorithm moves +through the subject string one character at a time, for all active paths +through the tree. +

+
ADVANTAGES OF THE DFA ALGORITHM
+

+Using the DFA matching algorithm provides the following advantages: +

+

+1. All possible matches (at a single point in the subject) are automatically +found, and in particular, the longest match is found. To find more than one +match using the standard algorithm, you have to do kludgy things with +callouts. +

+

+2. There is much better support for partial matching. The restrictions on the +content of the pattern that apply when using the standard algorithm for partial +matching do not apply to the DFA algorithm. For non-anchored patterns, the +starting position of a partial match is available. +

+

+3. Because the DFA algorithm scans the subject string just once, and never +needs to backtrack, it is possible to pass very long subject strings to the +matching function in several pieces, checking for partial matching each time. +

+
DISADVANTAGES OF THE DFA ALGORITHM
+

+The DFA algorithm suffers from a number of disadvantages: +

+

+1. It is substantially slower than the standard algorithm. This is partly +because it has to search for all possible matches, but is also because it is +less susceptible to optimization. +

+

+2. Capturing parentheses and back references are not supported. +

+

+3. The "atomic group" feature of PCRE regular expressions is supported, but +does not provide the advantage that it does for the standard algorithm. +

+

+Last updated: 06 June 2006 +
+Copyright © 1997-2006 University of Cambridge. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcrepartial.html b/libs/pcre/doc/html/pcrepartial.html new file mode 100644 index 0000000000..acb93c2977 --- /dev/null +++ b/libs/pcre/doc/html/pcrepartial.html @@ -0,0 +1,225 @@ + + +pcrepartial specification + + +

pcrepartial man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+

+
PARTIAL MATCHING IN PCRE
+

+In normal use of PCRE, if the subject string that is passed to +pcre_exec() or pcre_dfa_exec() matches as far as it goes, but is +too short to match the entire pattern, PCRE_ERROR_NOMATCH is returned. There +are circumstances where it might be helpful to distinguish this case from other +cases in which there is no match. +

+

+Consider, for example, an application where a human is required to type in data +for a field with specific formatting requirements. An example might be a date +in the form ddmmmyy, defined by this pattern: +

+  ^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$
+
+If the application sees the user's keystrokes one by one, and can check that +what has been typed so far is potentially valid, it is able to raise an error +as soon as a mistake is made, possibly beeping and not reflecting the +character that has been typed. This immediate feedback is likely to be a better +user interface than a check that is delayed until the entire string has been +entered. +

+

+PCRE supports the concept of partial matching by means of the PCRE_PARTIAL +option, which can be set when calling pcre_exec() or +pcre_dfa_exec(). When this flag is set for pcre_exec(), the return +code PCRE_ERROR_NOMATCH is converted into PCRE_ERROR_PARTIAL if at any time +during the matching process the last part of the subject string matched part of +the pattern. Unfortunately, for non-anchored matching, it is not possible to +obtain the position of the start of the partial match. No captured data is set +when PCRE_ERROR_PARTIAL is returned. +

+

+When PCRE_PARTIAL is set for pcre_dfa_exec(), the return code +PCRE_ERROR_NOMATCH is converted into PCRE_ERROR_PARTIAL if the end of the +subject is reached, there have been no complete matches, but there is still at +least one matching possibility. The portion of the string that provided the +partial match is set as the first matching string. +

+

+Using PCRE_PARTIAL disables one of PCRE's optimizations. PCRE remembers the +last literal byte in a pattern, and abandons matching immediately if such a +byte is not present in the subject string. This optimization cannot be used +for a subject string that might match only partially. +

+
RESTRICTED PATTERNS FOR PCRE_PARTIAL
+

+Because of the way certain internal optimizations are implemented in the +pcre_exec() function, the PCRE_PARTIAL option cannot be used with all +patterns. These restrictions do not apply when pcre_dfa_exec() is used. +For pcre_exec(), repeated single characters such as +

+  a{2,4}
+
+and repeated single metasequences such as +
+  \d+
+
+are not permitted if the maximum number of occurrences is greater than one. +Optional items such as \d? (where the maximum is one) are permitted. +Quantifiers with any values are permitted after parentheses, so the invalid +examples above can be coded thus: +
+  (a){2,4}
+  (\d)+
+
+These constructions run more slowly, but for the kinds of application that are +envisaged for this facility, this is not felt to be a major restriction. +

+

+If PCRE_PARTIAL is set for a pattern that does not conform to the restrictions, +pcre_exec() returns the error code PCRE_ERROR_BADPARTIAL (-13). +

+
EXAMPLE OF PARTIAL MATCHING USING PCRETEST
+

+If the escape sequence \P is present in a pcretest data line, the +PCRE_PARTIAL flag is used for the match. Here is a run of pcretest that +uses the date example quoted above: +

+    re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
+  data> 25jun04\P
+   0: 25jun04
+   1: jun
+  data> 25dec3\P
+  Partial match
+  data> 3ju\P
+  Partial match
+  data> 3juj\P
+  No match
+  data> j\P
+  No match
+
+The first data string is matched completely, so pcretest shows the +matched substrings. The remaining four strings do not match the complete +pattern, but the first two are partial matches. The same test, using DFA +matching (by means of the \D escape sequence), produces the following output: +
+    re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
+  data> 25jun04\P\D
+   0: 25jun04
+  data> 23dec3\P\D
+  Partial match: 23dec3
+  data> 3ju\P\D
+  Partial match: 3ju
+  data> 3juj\P\D
+  No match
+  data> j\P\D
+  No match
+
+Notice that in this case the portion of the string that was matched is made +available. +

+
MULTI-SEGMENT MATCHING WITH pcre_dfa_exec()
+

+When a partial match has been found using pcre_dfa_exec(), it is possible +to continue the match by providing additional subject data and calling +pcre_dfa_exec() again with the PCRE_DFA_RESTART option and the same +working space (where details of the previous partial match are stored). Here is +an example using pcretest, where the \R escape sequence sets the +PCRE_DFA_RESTART option and the \D escape sequence requests the use of +pcre_dfa_exec(): +

+    re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
+  data> 23ja\P\D
+  Partial match: 23ja
+  data> n05\R\D
+   0: n05
+
+The first call has "23ja" as the subject, and requests partial matching; the +second call has "n05" as the subject for the continued (restarted) match. +Notice that when the match is complete, only the last part is shown; PCRE does +not retain the previously partially-matched string. It is up to the calling +program to do that if it needs to. +

+

+This facility can be used to pass very long subject strings to +pcre_dfa_exec(). However, some care is needed for certain types of +pattern. +

+

+1. If the pattern contains tests for the beginning or end of a line, you need +to pass the PCRE_NOTBOL or PCRE_NOTEOL options, as appropriate, when the +subject string for any call does not contain the beginning or end of a line. +

+

+2. If the pattern contains backward assertions (including \b or \B), you need +to arrange for some overlap in the subject strings to allow for this. For +example, you could pass the subject in chunks that were 500 bytes long, but in +a buffer of 700 bytes, with the starting offset set to 200 and the previous 200 +bytes at the start of the buffer. +

+

+3. Matching a subject string that is split into multiple segments does not +always produce exactly the same result as matching over one single long string. +The difference arises when there are multiple matching possibilities, because a +partial match result is given only when there are no completed matches in a +call to fBpcre_dfa_exec()\fP. This means that as soon as the shortest match has +been found, continuation to a new subject segment is no longer possible. +Consider this pcretest example: +

+    re> /dog(sbody)?/
+  data> do\P\D
+  Partial match: do
+  data> gsb\R\P\D
+   0: g
+  data> dogsbody\D
+   0: dogsbody
+   1: dog
+
+The pattern matches the words "dog" or "dogsbody". When the subject is +presented in several parts ("do" and "gsb" being the first two) the match stops +when "dog" has been found, and it is not possible to continue. On the other +hand, if "dogsbody" is presented as a single string, both matches are found. +

+

+Because of this phenomenon, it does not usually make sense to end a pattern +that is going to be matched in this way with a variable repeat. +

+

+4. Patterns that contain alternatives at the top level which do not all +start with the same pattern item may not work as expected. For example, +consider this pattern: +

+  1234|3789
+
+If the first part of the subject is "ABC123", a partial match of the first +alternative is found at offset 3. There is no partial match for the second +alternative, because such a match does not start at the same point in the +subject string. Attempting to continue with the string "789" does not yield a +match because only those alternatives that match at one point in the subject +are remembered. The problem arises because the start of the second alternative +matches within the first alternative. There is no problem with anchored +patterns or patterns such as: +
+  1234|ABCD
+
+where no string can be a partial match for both alternatives. +

+

+Last updated: 16 January 2006 +
+Copyright © 1997-2006 University of Cambridge. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcrepattern.html b/libs/pcre/doc/html/pcrepattern.html new file mode 100644 index 0000000000..8f10cad844 --- /dev/null +++ b/libs/pcre/doc/html/pcrepattern.html @@ -0,0 +1,1661 @@ + + +pcrepattern specification + + +

pcrepattern man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+

+
PCRE REGULAR EXPRESSION DETAILS
+

+The syntax and semantics of the regular expressions supported by PCRE are +described below. Regular expressions are also described in the Perl +documentation and in a number of books, some of which have copious examples. +Jeffrey Friedl's "Mastering Regular Expressions", published by O'Reilly, covers +regular expressions in great detail. This description of PCRE's regular +expressions is intended as reference material. +

+

+The original operation of PCRE was on strings of one-byte characters. However, +there is now also support for UTF-8 character strings. To use this, you must +build PCRE to include UTF-8 support, and then call pcre_compile() with +the PCRE_UTF8 option. How this affects pattern matching is mentioned in several +places below. There is also a summary of UTF-8 features in the +section on UTF-8 support +in the main +pcre +page. +

+

+The remainder of this document discusses the patterns that are supported by +PCRE when its main matching function, pcre_exec(), is used. +From release 6.0, PCRE offers a second matching function, +pcre_dfa_exec(), which matches using a different algorithm that is not +Perl-compatible. The advantages and disadvantages of the alternative function, +and how it differs from the normal function, are discussed in the +pcrematching +page. +

+

+A regular expression is a pattern that is matched against a subject string from +left to right. Most characters stand for themselves in a pattern, and match the +corresponding characters in the subject. As a trivial example, the pattern +

+  The quick brown fox
+
+matches a portion of a subject string that is identical to itself. When +caseless matching is specified (the PCRE_CASELESS option), letters are matched +independently of case. In UTF-8 mode, PCRE always understands the concept of +case for characters whose values are less than 128, so caseless matching is +always possible. For characters with higher values, the concept of case is +supported if PCRE is compiled with Unicode property support, but not otherwise. +If you want to use caseless matching for characters 128 and above, you must +ensure that PCRE is compiled with Unicode property support as well as with +UTF-8 support. +

+

+The power of regular expressions comes from the ability to include alternatives +and repetitions in the pattern. These are encoded in the pattern by the use of +metacharacters, which do not stand for themselves but instead are +interpreted in some special way. +

+

+There are two different sets of metacharacters: those that are recognized +anywhere in the pattern except within square brackets, and those that are +recognized in square brackets. Outside square brackets, the metacharacters are +as follows: +

+  \      general escape character with several uses
+  ^      assert start of string (or line, in multiline mode)
+  $      assert end of string (or line, in multiline mode)
+  .      match any character except newline (by default)
+  [      start character class definition
+  |      start of alternative branch
+  (      start subpattern
+  )      end subpattern
+  ?      extends the meaning of (
+         also 0 or 1 quantifier
+         also quantifier minimizer
+  *      0 or more quantifier
+  +      1 or more quantifier
+         also "possessive quantifier"
+  {      start min/max quantifier
+
+Part of a pattern that is in square brackets is called a "character class". In +a character class the only metacharacters are: +
+  \      general escape character
+  ^      negate the class, but only if the first character
+  -      indicates character range
+  [      POSIX character class (only if followed by POSIX syntax)
+  ]      terminates the character class
+
+The following sections describe the use of each of the metacharacters. +

+
BACKSLASH
+

+The backslash character has several uses. Firstly, if it is followed by a +non-alphanumeric character, it takes away any special meaning that character +may have. This use of backslash as an escape character applies both inside and +outside character classes. +

+

+For example, if you want to match a * character, you write \* in the pattern. +This escaping action applies whether or not the following character would +otherwise be interpreted as a metacharacter, so it is always safe to precede a +non-alphanumeric with backslash to specify that it stands for itself. In +particular, if you want to match a backslash, you write \\. +

+

+If a pattern is compiled with the PCRE_EXTENDED option, whitespace in the +pattern (other than in a character class) and characters between a # outside +a character class and the next newline are ignored. An escaping backslash can +be used to include a whitespace or # character as part of the pattern. +

+

+If you want to remove the special meaning from a sequence of characters, you +can do so by putting them between \Q and \E. This is different from Perl in +that $ and @ are handled as literals in \Q...\E sequences in PCRE, whereas in +Perl, $ and @ cause variable interpolation. Note the following examples: +

+  Pattern            PCRE matches   Perl matches
+
+  \Qabc$xyz\E        abc$xyz        abc followed by the contents of $xyz
+  \Qabc\$xyz\E       abc\$xyz       abc\$xyz
+  \Qabc\E\$\Qxyz\E   abc$xyz        abc$xyz
+
+The \Q...\E sequence is recognized both inside and outside character classes. +

+
+Non-printing characters +
+

+A second use of backslash provides a way of encoding non-printing characters +in patterns in a visible manner. There is no restriction on the appearance of +non-printing characters, apart from the binary zero that terminates a pattern, +but when a pattern is being prepared by text editing, it is usually easier to +use one of the following escape sequences than the binary character it +represents: +

+  \a        alarm, that is, the BEL character (hex 07)
+  \cx       "control-x", where x is any character
+  \e        escape (hex 1B)
+  \f        formfeed (hex 0C)
+  \n        newline (hex 0A)
+  \r        carriage return (hex 0D)
+  \t        tab (hex 09)
+  \ddd      character with octal code ddd, or backreference
+  \xhh      character with hex code hh
+  \x{hhh..} character with hex code hhh..
+
+The precise effect of \cx is as follows: if x is a lower case letter, it +is converted to upper case. Then bit 6 of the character (hex 40) is inverted. +Thus \cz becomes hex 1A, but \c{ becomes hex 3B, while \c; becomes hex +7B. +

+

+After \x, from zero to two hexadecimal digits are read (letters can be in +upper or lower case). Any number of hexadecimal digits may appear between \x{ +and }, but the value of the character code must be less than 256 in non-UTF-8 +mode, and less than 2**31 in UTF-8 mode (that is, the maximum hexadecimal value +is 7FFFFFFF). If characters other than hexadecimal digits appear between \x{ +and }, or if there is no terminating }, this form of escape is not recognized. +Instead, the initial \x will be interpreted as a basic hexadecimal escape, +with no following digits, giving a character whose value is zero. +

+

+Characters whose value is less than 256 can be defined by either of the two +syntaxes for \x. There is no difference in the way they are handled. For +example, \xdc is exactly the same as \x{dc}. +

+

+After \0 up to two further octal digits are read. If there are fewer than two +digits, just those that are present are used. Thus the sequence \0\x\07 +specifies two binary zeros followed by a BEL character (code value 7). Make +sure you supply two digits after the initial zero if the pattern character that +follows is itself an octal digit. +

+

+The handling of a backslash followed by a digit other than 0 is complicated. +Outside a character class, PCRE reads it and any following digits as a decimal +number. If the number is less than 10, or if there have been at least that many +previous capturing left parentheses in the expression, the entire sequence is +taken as a back reference. A description of how this works is given +later, +following the discussion of +parenthesized subpatterns. +

+

+Inside a character class, or if the decimal number is greater than 9 and there +have not been that many capturing subpatterns, PCRE re-reads up to three octal +digits following the backslash, ane uses them to generate a data character. Any +subsequent digits stand for themselves. In non-UTF-8 mode, the value of a +character specified in octal must be less than \400. In UTF-8 mode, values up +to \777 are permitted. For example: +

+  \040   is another way of writing a space
+  \40    is the same, provided there are fewer than 40 previous capturing subpatterns
+  \7     is always a back reference
+  \11    might be a back reference, or another way of writing a tab
+  \011   is always a tab
+  \0113  is a tab followed by the character "3"
+  \113   might be a back reference, otherwise the character with octal code 113
+  \377   might be a back reference, otherwise the byte consisting entirely of 1 bits
+  \81    is either a back reference, or a binary zero followed by the two characters "8" and "1"
+
+Note that octal values of 100 or greater must not be introduced by a leading +zero, because no more than three octal digits are ever read. +

+

+All the sequences that define a single character value can be used both inside +and outside character classes. In addition, inside a character class, the +sequence \b is interpreted as the backspace character (hex 08), and the +sequence \X is interpreted as the character "X". Outside a character class, +these sequences have different meanings +(see below). +

+
+Generic character types +
+

+The third use of backslash is for specifying generic character types. The +following are always recognized: +

+  \d     any decimal digit
+  \D     any character that is not a decimal digit
+  \s     any whitespace character
+  \S     any character that is not a whitespace character
+  \w     any "word" character
+  \W     any "non-word" character
+
+Each pair of escape sequences partitions the complete set of characters into +two disjoint sets. Any given character matches one, and only one, of each pair. +

+

+These character type sequences can appear both inside and outside character +classes. They each match one character of the appropriate type. If the current +matching point is at the end of the subject string, all of them fail, since +there is no character to match. +

+

+For compatibility with Perl, \s does not match the VT character (code 11). +This makes it different from the the POSIX "space" class. The \s characters +are HT (9), LF (10), FF (12), CR (13), and space (32). (If "use locale;" is +included in a Perl script, \s may match the VT character. In PCRE, it never +does.) +

+

+A "word" character is an underscore or any character less than 256 that is a +letter or digit. The definition of letters and digits is controlled by PCRE's +low-valued character tables, and may vary if locale-specific matching is taking +place (see +"Locale support" +in the +pcreapi +page). For example, in the "fr_FR" (French) locale, some character codes +greater than 128 are used for accented letters, and these are matched by \w. +

+

+In UTF-8 mode, characters with values greater than 128 never match \d, \s, or +\w, and always match \D, \S, and \W. This is true even when Unicode +character property support is available. The use of locales with Unicode is +discouraged. +

+
+Unicode character properties +
+

+When PCRE is built with Unicode character property support, three additional +escape sequences to match character properties are available when UTF-8 mode +is selected. They are: +

+  \p{xx}   a character with the xx property
+  \P{xx}   a character without the xx property
+  \X       an extended Unicode sequence
+
+The property names represented by xx above are limited to the Unicode +script names, the general category properties, and "Any", which matches any +character (including newline). Other properties such as "InMusicalSymbols" are +not currently supported by PCRE. Note that \P{Any} does not match any +characters, so always causes a match failure. +

+

+Sets of Unicode characters are defined as belonging to certain scripts. A +character from one of these sets can be matched using a script name. For +example: +

+  \p{Greek}
+  \P{Han}
+
+Those that are not part of an identified script are lumped together as +"Common". The current list of scripts is: +

+

+Arabic, +Armenian, +Bengali, +Bopomofo, +Braille, +Buginese, +Buhid, +Canadian_Aboriginal, +Cherokee, +Common, +Coptic, +Cypriot, +Cyrillic, +Deseret, +Devanagari, +Ethiopic, +Georgian, +Glagolitic, +Gothic, +Greek, +Gujarati, +Gurmukhi, +Han, +Hangul, +Hanunoo, +Hebrew, +Hiragana, +Inherited, +Kannada, +Katakana, +Kharoshthi, +Khmer, +Lao, +Latin, +Limbu, +Linear_B, +Malayalam, +Mongolian, +Myanmar, +New_Tai_Lue, +Ogham, +Old_Italic, +Old_Persian, +Oriya, +Osmanya, +Runic, +Shavian, +Sinhala, +Syloti_Nagri, +Syriac, +Tagalog, +Tagbanwa, +Tai_Le, +Tamil, +Telugu, +Thaana, +Thai, +Tibetan, +Tifinagh, +Ugaritic, +Yi. +

+

+Each character has exactly one general category property, specified by a +two-letter abbreviation. For compatibility with Perl, negation can be specified +by including a circumflex between the opening brace and the property name. For +example, \p{^Lu} is the same as \P{Lu}. +

+

+If only one letter is specified with \p or \P, it includes all the general +category properties that start with that letter. In this case, in the absence +of negation, the curly brackets in the escape sequence are optional; these two +examples have the same effect: +

+  \p{L}
+  \pL
+
+The following general category property codes are supported: +
+  C     Other
+  Cc    Control
+  Cf    Format
+  Cn    Unassigned
+  Co    Private use
+  Cs    Surrogate
+
+  L     Letter
+  Ll    Lower case letter
+  Lm    Modifier letter
+  Lo    Other letter
+  Lt    Title case letter
+  Lu    Upper case letter
+
+  M     Mark
+  Mc    Spacing mark
+  Me    Enclosing mark
+  Mn    Non-spacing mark
+
+  N     Number
+  Nd    Decimal number
+  Nl    Letter number
+  No    Other number
+
+  P     Punctuation
+  Pc    Connector punctuation
+  Pd    Dash punctuation
+  Pe    Close punctuation
+  Pf    Final punctuation
+  Pi    Initial punctuation
+  Po    Other punctuation
+  Ps    Open punctuation
+
+  S     Symbol
+  Sc    Currency symbol
+  Sk    Modifier symbol
+  Sm    Mathematical symbol
+  So    Other symbol
+
+  Z     Separator
+  Zl    Line separator
+  Zp    Paragraph separator
+  Zs    Space separator
+
+The special property L& is also supported: it matches a character that has +the Lu, Ll, or Lt property, in other words, a letter that is not classified as +a modifier or "other". +

+

+The long synonyms for these properties that Perl supports (such as \p{Letter}) +are not supported by PCRE, nor is it permitted to prefix any of these +properties with "Is". +

+

+No character that is in the Unicode table has the Cn (unassigned) property. +Instead, this property is assumed for any code point that is not in the +Unicode table. +

+

+Specifying caseless matching does not affect these escape sequences. For +example, \p{Lu} always matches only upper case letters. +

+

+The \X escape matches any number of Unicode characters that form an extended +Unicode sequence. \X is equivalent to +

+  (?>\PM\pM*)
+
+That is, it matches a character without the "mark" property, followed by zero +or more characters with the "mark" property, and treats the sequence as an +atomic group +(see below). +Characters with the "mark" property are typically accents that affect the +preceding character. +

+

+Matching characters by Unicode property is not fast, because PCRE has to search +a structure that contains data for over fifteen thousand characters. That is +why the traditional escape sequences such as \d and \w do not use Unicode +properties in PCRE. +

+
+Simple assertions +
+

+The fourth use of backslash is for certain simple assertions. An assertion +specifies a condition that has to be met at a particular point in a match, +without consuming any characters from the subject string. The use of +subpatterns for more complicated assertions is described +below. +The backslashed assertions are: +

+  \b     matches at a word boundary
+  \B     matches when not at a word boundary
+  \A     matches at start of subject
+  \Z     matches at end of subject or before newline at end
+  \z     matches at end of subject
+  \G     matches at first matching position in subject
+
+These assertions may not appear in character classes (but note that \b has a +different meaning, namely the backspace character, inside a character class). +

+

+A word boundary is a position in the subject string where the current character +and the previous character do not both match \w or \W (i.e. one matches +\w and the other matches \W), or the start or end of the string if the +first or last character matches \w, respectively. +

+

+The \A, \Z, and \z assertions differ from the traditional circumflex and +dollar (described in the next section) in that they only ever match at the very +start and end of the subject string, whatever options are set. Thus, they are +independent of multiline mode. These three assertions are not affected by the +PCRE_NOTBOL or PCRE_NOTEOL options, which affect only the behaviour of the +circumflex and dollar metacharacters. However, if the startoffset +argument of pcre_exec() is non-zero, indicating that matching is to start +at a point other than the beginning of the subject, \A can never match. The +difference between \Z and \z is that \Z matches before a newline at the end +of the string as well as at the very end, whereas \z matches only at the end. +

+

+The \G assertion is true only when the current matching position is at the +start point of the match, as specified by the startoffset argument of +pcre_exec(). It differs from \A when the value of startoffset is +non-zero. By calling pcre_exec() multiple times with appropriate +arguments, you can mimic Perl's /g option, and it is in this kind of +implementation where \G can be useful. +

+

+Note, however, that PCRE's interpretation of \G, as the start of the current +match, is subtly different from Perl's, which defines it as the end of the +previous match. In Perl, these can be different when the previously matched +string was empty. Because PCRE does just one match at a time, it cannot +reproduce this behaviour. +

+

+If all the alternatives of a pattern begin with \G, the expression is anchored +to the starting match position, and the "anchored" flag is set in the compiled +regular expression. +

+
CIRCUMFLEX AND DOLLAR
+

+Outside a character class, in the default matching mode, the circumflex +character is an assertion that is true only if the current matching point is +at the start of the subject string. If the startoffset argument of +pcre_exec() is non-zero, circumflex can never match if the PCRE_MULTILINE +option is unset. Inside a character class, circumflex has an entirely different +meaning +(see below). +

+

+Circumflex need not be the first character of the pattern if a number of +alternatives are involved, but it should be the first thing in each alternative +in which it appears if the pattern is ever to match that branch. If all +possible alternatives start with a circumflex, that is, if the pattern is +constrained to match only at the start of the subject, it is said to be an +"anchored" pattern. (There are also other constructs that can cause a pattern +to be anchored.) +

+

+A dollar character is an assertion that is true only if the current matching +point is at the end of the subject string, or immediately before a newline +at the end of the string (by default). Dollar need not be the last character of +the pattern if a number of alternatives are involved, but it should be the last +item in any branch in which it appears. Dollar has no special meaning in a +character class. +

+

+The meaning of dollar can be changed so that it matches only at the very end of +the string, by setting the PCRE_DOLLAR_ENDONLY option at compile time. This +does not affect the \Z assertion. +

+

+The meanings of the circumflex and dollar characters are changed if the +PCRE_MULTILINE option is set. When this is the case, a circumflex matches +immediately after internal newlines as well as at the start of the subject +string. It does not match after a newline that ends the string. A dollar +matches before any newlines in the string, as well as at the very end, when +PCRE_MULTILINE is set. When newline is specified as the two-character +sequence CRLF, isolated CR and LF characters do not indicate newlines. +

+

+For example, the pattern /^abc$/ matches the subject string "def\nabc" (where +\n represents a newline) in multiline mode, but not otherwise. Consequently, +patterns that are anchored in single line mode because all branches start with +^ are not anchored in multiline mode, and a match for circumflex is possible +when the startoffset argument of pcre_exec() is non-zero. The +PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set. +

+

+Note that the sequences \A, \Z, and \z can be used to match the start and +end of the subject in both modes, and if all branches of a pattern start with +\A it is always anchored, whether or not PCRE_MULTILINE is set. +

+
FULL STOP (PERIOD, DOT)
+

+Outside a character class, a dot in the pattern matches any one character in +the subject string except (by default) a character that signifies the end of a +line. In UTF-8 mode, the matched character may be more than one byte long. When +a line ending is defined as a single character (CR or LF), dot never matches +that character; when the two-character sequence CRLF is used, dot does not +match CR if it is immediately followed by LF, but otherwise it matches all +characters (including isolated CRs and LFs). +

+

+The behaviour of dot with regard to newlines can be changed. If the PCRE_DOTALL +option is set, a dot matches any one character, without exception. If newline +is defined as the two-character sequence CRLF, it takes two dots to match it. +

+

+The handling of dot is entirely independent of the handling of circumflex and +dollar, the only relationship being that they both involve newlines. Dot has no +special meaning in a character class. +

+
MATCHING A SINGLE BYTE
+

+Outside a character class, the escape sequence \C matches any one byte, both +in and out of UTF-8 mode. Unlike a dot, it always matches CR and LF. The +feature is provided in Perl in order to match individual bytes in UTF-8 mode. +Because it breaks up UTF-8 characters into individual bytes, what remains in +the string may be a malformed UTF-8 string. For this reason, the \C escape +sequence is best avoided. +

+

+PCRE does not allow \C to appear in lookbehind assertions +(described below), +because in UTF-8 mode this would make it impossible to calculate the length of +the lookbehind. +

+
SQUARE BRACKETS AND CHARACTER CLASSES
+

+An opening square bracket introduces a character class, terminated by a closing +square bracket. A closing square bracket on its own is not special. If a +closing square bracket is required as a member of the class, it should be the +first data character in the class (after an initial circumflex, if present) or +escaped with a backslash. +

+

+A character class matches a single character in the subject. In UTF-8 mode, the +character may occupy more than one byte. A matched character must be in the set +of characters defined by the class, unless the first character in the class +definition is a circumflex, in which case the subject character must not be in +the set defined by the class. If a circumflex is actually required as a member +of the class, ensure it is not the first character, or escape it with a +backslash. +

+

+For example, the character class [aeiou] matches any lower case vowel, while +[^aeiou] matches any character that is not a lower case vowel. Note that a +circumflex is just a convenient notation for specifying the characters that +are in the class by enumerating those that are not. A class that starts with a +circumflex is not an assertion: it still consumes a character from the subject +string, and therefore it fails if the current pointer is at the end of the +string. +

+

+In UTF-8 mode, characters with values greater than 255 can be included in a +class as a literal string of bytes, or by using the \x{ escaping mechanism. +

+

+When caseless matching is set, any letters in a class represent both their +upper case and lower case versions, so for example, a caseless [aeiou] matches +"A" as well as "a", and a caseless [^aeiou] does not match "A", whereas a +caseful version would. In UTF-8 mode, PCRE always understands the concept of +case for characters whose values are less than 128, so caseless matching is +always possible. For characters with higher values, the concept of case is +supported if PCRE is compiled with Unicode property support, but not otherwise. +If you want to use caseless matching for characters 128 and above, you must +ensure that PCRE is compiled with Unicode property support as well as with +UTF-8 support. +

+

+Characters that might indicate line breaks (CR and LF) are never treated in any +special way when matching character classes, whatever line-ending sequence is +in use, and whatever setting of the PCRE_DOTALL and PCRE_MULTILINE options is +used. A class such as [^a] always matches one of these characters. +

+

+The minus (hyphen) character can be used to specify a range of characters in a +character class. For example, [d-m] matches any letter between d and m, +inclusive. If a minus character is required in a class, it must be escaped with +a backslash or appear in a position where it cannot be interpreted as +indicating a range, typically as the first or last character in the class. +

+

+It is not possible to have the literal character "]" as the end character of a +range. A pattern such as [W-]46] is interpreted as a class of two characters +("W" and "-") followed by a literal string "46]", so it would match "W46]" or +"-46]". However, if the "]" is escaped with a backslash it is interpreted as +the end of range, so [W-\]46] is interpreted as a class containing a range +followed by two other characters. The octal or hexadecimal representation of +"]" can also be used to end a range. +

+

+Ranges operate in the collating sequence of character values. They can also be +used for characters specified numerically, for example [\000-\037]. In UTF-8 +mode, ranges can include characters whose values are greater than 255, for +example [\x{100}-\x{2ff}]. +

+

+If a range that includes letters is used when caseless matching is set, it +matches the letters in either case. For example, [W-c] is equivalent to +[][\\^_`wxyzabc], matched caselessly, and in non-UTF-8 mode, if character +tables for the "fr_FR" locale are in use, [\xc8-\xcb] matches accented E +characters in both cases. In UTF-8 mode, PCRE supports the concept of case for +characters with values greater than 128 only when it is compiled with Unicode +property support. +

+

+The character types \d, \D, \p, \P, \s, \S, \w, and \W may also appear +in a character class, and add the characters that they match to the class. For +example, [\dABCDEF] matches any hexadecimal digit. A circumflex can +conveniently be used with the upper case character types to specify a more +restricted set of characters than the matching lower case type. For example, +the class [^\W_] matches any letter or digit, but not underscore. +

+

+The only metacharacters that are recognized in character classes are backslash, +hyphen (only where it can be interpreted as specifying a range), circumflex +(only at the start), opening square bracket (only when it can be interpreted as +introducing a POSIX class name - see the next section), and the terminating +closing square bracket. However, escaping other non-alphanumeric characters +does no harm. +

+
POSIX CHARACTER CLASSES
+

+Perl supports the POSIX notation for character classes. This uses names +enclosed by [: and :] within the enclosing square brackets. PCRE also supports +this notation. For example, +

+  [01[:alpha:]%]
+
+matches "0", "1", any alphabetic character, or "%". The supported class names +are +
+  alnum    letters and digits
+  alpha    letters
+  ascii    character codes 0 - 127
+  blank    space or tab only
+  cntrl    control characters
+  digit    decimal digits (same as \d)
+  graph    printing characters, excluding space
+  lower    lower case letters
+  print    printing characters, including space
+  punct    printing characters, excluding letters and digits
+  space    white space (not quite the same as \s)
+  upper    upper case letters
+  word     "word" characters (same as \w)
+  xdigit   hexadecimal digits
+
+The "space" characters are HT (9), LF (10), VT (11), FF (12), CR (13), and +space (32). Notice that this list includes the VT character (code 11). This +makes "space" different to \s, which does not include VT (for Perl +compatibility). +

+

+The name "word" is a Perl extension, and "blank" is a GNU extension from Perl +5.8. Another Perl extension is negation, which is indicated by a ^ character +after the colon. For example, +

+  [12[:^digit:]]
+
+matches "1", "2", or any non-digit. PCRE (and Perl) also recognize the POSIX +syntax [.ch.] and [=ch=] where "ch" is a "collating element", but these are not +supported, and an error is given if they are encountered. +

+

+In UTF-8 mode, characters with values greater than 128 do not match any of +the POSIX character classes. +

+
VERTICAL BAR
+

+Vertical bar characters are used to separate alternative patterns. For example, +the pattern +

+  gilbert|sullivan
+
+matches either "gilbert" or "sullivan". Any number of alternatives may appear, +and an empty alternative is permitted (matching the empty string). The matching +process tries each alternative in turn, from left to right, and the first one +that succeeds is used. If the alternatives are within a subpattern +(defined below), +"succeeds" means matching the rest of the main pattern as well as the +alternative in the subpattern. +

+
INTERNAL OPTION SETTING
+

+The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and +PCRE_EXTENDED options can be changed from within the pattern by a sequence of +Perl option letters enclosed between "(?" and ")". The option letters are +

+  i  for PCRE_CASELESS
+  m  for PCRE_MULTILINE
+  s  for PCRE_DOTALL
+  x  for PCRE_EXTENDED
+
+For example, (?im) sets caseless, multiline matching. It is also possible to +unset these options by preceding the letter with a hyphen, and a combined +setting and unsetting such as (?im-sx), which sets PCRE_CASELESS and +PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, is also +permitted. If a letter appears both before and after the hyphen, the option is +unset. +

+

+When an option change occurs at top level (that is, not inside subpattern +parentheses), the change applies to the remainder of the pattern that follows. +If the change is placed right at the start of a pattern, PCRE extracts it into +the global options (and it will therefore show up in data extracted by the +pcre_fullinfo() function). +

+

+An option change within a subpattern affects only that part of the current +pattern that follows it, so +

+  (a(?i)b)c
+
+matches abc and aBc and no other strings (assuming PCRE_CASELESS is not used). +By this means, options can be made to have different settings in different +parts of the pattern. Any changes made in one alternative do carry on +into subsequent branches within the same subpattern. For example, +
+  (a(?i)b|c)
+
+matches "ab", "aB", "c", and "C", even though when matching "C" the first +branch is abandoned before the option setting. This is because the effects of +option settings happen at compile time. There would be some very weird +behaviour otherwise. +

+

+The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA can be +changed in the same way as the Perl-compatible options by using the characters +J, U and X respectively. +

+
SUBPATTERNS
+

+Subpatterns are delimited by parentheses (round brackets), which can be nested. +Turning part of a pattern into a subpattern does two things: +
+
+1. It localizes a set of alternatives. For example, the pattern +

+  cat(aract|erpillar|)
+
+matches one of the words "cat", "cataract", or "caterpillar". Without the +parentheses, it would match "cataract", "erpillar" or the empty string. +
+
+2. It sets up the subpattern as a capturing subpattern. This means that, when +the whole pattern matches, that portion of the subject string that matched the +subpattern is passed back to the caller via the ovector argument of +pcre_exec(). Opening parentheses are counted from left to right (starting +from 1) to obtain numbers for the capturing subpatterns. +

+

+For example, if the string "the red king" is matched against the pattern +

+  the ((red|white) (king|queen))
+
+the captured substrings are "red king", "red", and "king", and are numbered 1, +2, and 3, respectively. +

+

+The fact that plain parentheses fulfil two functions is not always helpful. +There are often times when a grouping subpattern is required without a +capturing requirement. If an opening parenthesis is followed by a question mark +and a colon, the subpattern does not do any capturing, and is not counted when +computing the number of any subsequent capturing subpatterns. For example, if +the string "the white queen" is matched against the pattern +

+  the ((?:red|white) (king|queen))
+
+the captured substrings are "white queen" and "queen", and are numbered 1 and +2. The maximum number of capturing subpatterns is 65535, and the maximum depth +of nesting of all subpatterns, both capturing and non-capturing, is 200. +

+

+As a convenient shorthand, if any option settings are required at the start of +a non-capturing subpattern, the option letters may appear between the "?" and +the ":". Thus the two patterns +

+  (?i:saturday|sunday)
+  (?:(?i)saturday|sunday)
+
+match exactly the same set of strings. Because alternative branches are tried +from left to right, and options are not reset until the end of the subpattern +is reached, an option setting in one branch does affect subsequent branches, so +the above patterns match "SUNDAY" as well as "Saturday". +

+
NAMED SUBPATTERNS
+

+Identifying capturing parentheses by number is simple, but it can be very hard +to keep track of the numbers in complicated regular expressions. Furthermore, +if an expression is modified, the numbers may change. To help with this +difficulty, PCRE supports the naming of subpatterns, something that Perl does +not provide. The Python syntax (?P<name>...) is used. References to capturing +parentheses from other parts of the pattern, such as +backreferences, +recursion, +and +conditions, +can be made by name as well as by number. +

+

+Names consist of up to 32 alphanumeric characters and underscores. Named +capturing parentheses are still allocated numbers as well as names. The PCRE +API provides function calls for extracting the name-to-number translation table +from a compiled pattern. There is also a convenience function for extracting a +captured substring by name. +

+

+By default, a name must be unique within a pattern, but it is possible to relax +this constraint by setting the PCRE_DUPNAMES option at compile time. This can +be useful for patterns where only one instance of the named parentheses can +match. Suppose you want to match the name of a weekday, either as a 3-letter +abbreviation or as the full name, and in both cases you want to extract the +abbreviation. This pattern (ignoring the line breaks) does the job: +

+  (?P<DN>Mon|Fri|Sun)(?:day)?|
+  (?P<DN>Tue)(?:sday)?|
+  (?P<DN>Wed)(?:nesday)?|
+  (?P<DN>Thu)(?:rsday)?|
+  (?P<DN>Sat)(?:urday)?
+
+There are five capturing substrings, but only one is ever set after a match. +The convenience function for extracting the data by name returns the substring +for the first, and in this example, the only, subpattern of that name that +matched. This saves searching to find which numbered subpattern it was. If you +make a reference to a non-unique named subpattern from elsewhere in the +pattern, the one that corresponds to the lowest number is used. For further +details of the interfaces for handling named subpatterns, see the +pcreapi +documentation. +

+
REPETITION
+

+Repetition is specified by quantifiers, which can follow any of the following +items: +

+  a literal data character
+  the . metacharacter
+  the \C escape sequence
+  the \X escape sequence (in UTF-8 mode with Unicode properties)
+  an escape such as \d that matches a single character
+  a character class
+  a back reference (see next section)
+  a parenthesized subpattern (unless it is an assertion)
+
+The general repetition quantifier specifies a minimum and maximum number of +permitted matches, by giving the two numbers in curly brackets (braces), +separated by a comma. The numbers must be less than 65536, and the first must +be less than or equal to the second. For example: +
+  z{2,4}
+
+matches "zz", "zzz", or "zzzz". A closing brace on its own is not a special +character. If the second number is omitted, but the comma is present, there is +no upper limit; if the second number and the comma are both omitted, the +quantifier specifies an exact number of required matches. Thus +
+  [aeiou]{3,}
+
+matches at least 3 successive vowels, but may match many more, while +
+  \d{8}
+
+matches exactly 8 digits. An opening curly bracket that appears in a position +where a quantifier is not allowed, or one that does not match the syntax of a +quantifier, is taken as a literal character. For example, {,6} is not a +quantifier, but a literal string of four characters. +

+

+In UTF-8 mode, quantifiers apply to UTF-8 characters rather than to individual +bytes. Thus, for example, \x{100}{2} matches two UTF-8 characters, each of +which is represented by a two-byte sequence. Similarly, when Unicode property +support is available, \X{3} matches three Unicode extended sequences, each of +which may be several bytes long (and they may be of different lengths). +

+

+The quantifier {0} is permitted, causing the expression to behave as if the +previous item and the quantifier were not present. +

+

+For convenience (and historical compatibility) the three most common +quantifiers have single-character abbreviations: +

+  *    is equivalent to {0,}
+  +    is equivalent to {1,}
+  ?    is equivalent to {0,1}
+
+It is possible to construct infinite loops by following a subpattern that can +match no characters with a quantifier that has no upper limit, for example: +
+  (a?)*
+
+Earlier versions of Perl and PCRE used to give an error at compile time for +such patterns. However, because there are cases where this can be useful, such +patterns are now accepted, but if any repetition of the subpattern does in fact +match no characters, the loop is forcibly broken. +

+

+By default, the quantifiers are "greedy", that is, they match as much as +possible (up to the maximum number of permitted times), without causing the +rest of the pattern to fail. The classic example of where this gives problems +is in trying to match comments in C programs. These appear between /* and */ +and within the comment, individual * and / characters may appear. An attempt to +match C comments by applying the pattern +

+  /\*.*\*/
+
+to the string +
+  /* first comment */  not comment  /* second comment */
+
+fails, because it matches the entire string owing to the greediness of the .* +item. +

+

+However, if a quantifier is followed by a question mark, it ceases to be +greedy, and instead matches the minimum number of times possible, so the +pattern +

+  /\*.*?\*/
+
+does the right thing with the C comments. The meaning of the various +quantifiers is not otherwise changed, just the preferred number of matches. +Do not confuse this use of question mark with its use as a quantifier in its +own right. Because it has two uses, it can sometimes appear doubled, as in +
+  \d??\d
+
+which matches one digit by preference, but can match two if that is the only +way the rest of the pattern matches. +

+

+If the PCRE_UNGREEDY option is set (an option which is not available in Perl), +the quantifiers are not greedy by default, but individual ones can be made +greedy by following them with a question mark. In other words, it inverts the +default behaviour. +

+

+When a parenthesized subpattern is quantified with a minimum repeat count that +is greater than 1 or with a limited maximum, more memory is required for the +compiled pattern, in proportion to the size of the minimum or maximum. +

+

+If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equivalent +to Perl's /s) is set, thus allowing the . to match newlines, the pattern is +implicitly anchored, because whatever follows will be tried against every +character position in the subject string, so there is no point in retrying the +overall match at any position after the first. PCRE normally treats such a +pattern as though it were preceded by \A. +

+

+In cases where it is known that the subject string contains no newlines, it is +worth setting PCRE_DOTALL in order to obtain this optimization, or +alternatively using ^ to indicate anchoring explicitly. +

+

+However, there is one situation where the optimization cannot be used. When .* +is inside capturing parentheses that are the subject of a backreference +elsewhere in the pattern, a match at the start may fail, and a later one +succeed. Consider, for example: +

+  (.*)abc\1
+
+If the subject is "xyz123abc123" the match point is the fourth character. For +this reason, such a pattern is not implicitly anchored. +

+

+When a capturing subpattern is repeated, the value captured is the substring +that matched the final iteration. For example, after +

+  (tweedle[dume]{3}\s*)+
+
+has matched "tweedledum tweedledee" the value of the captured substring is +"tweedledee". However, if there are nested capturing subpatterns, the +corresponding captured values may have been set in previous iterations. For +example, after +
+  /(a|(b))+/
+
+matches "aba" the value of the second captured substring is "b". +

+
ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS
+

+With both maximizing and minimizing repetition, failure of what follows +normally causes the repeated item to be re-evaluated to see if a different +number of repeats allows the rest of the pattern to match. Sometimes it is +useful to prevent this, either to change the nature of the match, or to cause +it fail earlier than it otherwise might, when the author of the pattern knows +there is no point in carrying on. +

+

+Consider, for example, the pattern \d+foo when applied to the subject line +

+  123456bar
+
+After matching all 6 digits and then failing to match "foo", the normal +action of the matcher is to try again with only 5 digits matching the \d+ +item, and then with 4, and so on, before ultimately failing. "Atomic grouping" +(a term taken from Jeffrey Friedl's book) provides the means for specifying +that once a subpattern has matched, it is not to be re-evaluated in this way. +

+

+If we use atomic grouping for the previous example, the matcher would give up +immediately on failing to match "foo" the first time. The notation is a kind of +special parenthesis, starting with (?> as in this example: +

+  (?>\d+)foo
+
+This kind of parenthesis "locks up" the part of the pattern it contains once +it has matched, and a failure further into the pattern is prevented from +backtracking into it. Backtracking past it to previous items, however, works as +normal. +

+

+An alternative description is that a subpattern of this type matches the string +of characters that an identical standalone pattern would match, if anchored at +the current point in the subject string. +

+

+Atomic grouping subpatterns are not capturing subpatterns. Simple cases such as +the above example can be thought of as a maximizing repeat that must swallow +everything it can. So, while both \d+ and \d+? are prepared to adjust the +number of digits they match in order to make the rest of the pattern match, +(?>\d+) can only match an entire sequence of digits. +

+

+Atomic groups in general can of course contain arbitrarily complicated +subpatterns, and can be nested. However, when the subpattern for an atomic +group is just a single repeated item, as in the example above, a simpler +notation, called a "possessive quantifier" can be used. This consists of an +additional + character following a quantifier. Using this notation, the +previous example can be rewritten as +

+  \d++foo
+
+Possessive quantifiers are always greedy; the setting of the PCRE_UNGREEDY +option is ignored. They are a convenient notation for the simpler forms of +atomic group. However, there is no difference in the meaning or processing of a +possessive quantifier and the equivalent atomic group. +

+

+The possessive quantifier syntax is an extension to the Perl syntax. Jeffrey +Friedl originated the idea (and the name) in the first edition of his book. +Mike McCloskey liked it, so implemented it when he built Sun's Java package, +and PCRE copied it from there. +

+

+When a pattern contains an unlimited repeat inside a subpattern that can itself +be repeated an unlimited number of times, the use of an atomic group is the +only way to avoid some failing matches taking a very long time indeed. The +pattern +

+  (\D+|<\d+>)*[!?]
+
+matches an unlimited number of substrings that either consist of non-digits, or +digits enclosed in <>, followed by either ! or ?. When it matches, it runs +quickly. However, if it is applied to +
+  aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
+
+it takes a long time before reporting failure. This is because the string can +be divided between the internal \D+ repeat and the external * repeat in a +large number of ways, and all have to be tried. (The example uses [!?] rather +than a single character at the end, because both PCRE and Perl have an +optimization that allows for fast failure when a single character is used. They +remember the last single character that is required for a match, and fail early +if it is not present in the string.) If the pattern is changed so that it uses +an atomic group, like this: +
+  ((?>\D+)|<\d+>)*[!?]
+
+sequences of non-digits cannot be broken, and failure happens quickly. +

+
BACK REFERENCES
+

+Outside a character class, a backslash followed by a digit greater than 0 (and +possibly further digits) is a back reference to a capturing subpattern earlier +(that is, to its left) in the pattern, provided there have been that many +previous capturing left parentheses. +

+

+However, if the decimal number following the backslash is less than 10, it is +always taken as a back reference, and causes an error only if there are not +that many capturing left parentheses in the entire pattern. In other words, the +parentheses that are referenced need not be to the left of the reference for +numbers less than 10. A "forward back reference" of this type can make sense +when a repetition is involved and the subpattern to the right has participated +in an earlier iteration. +

+

+It is not possible to have a numerical "forward back reference" to subpattern +whose number is 10 or more. However, a back reference to any subpattern is +possible using named parentheses (see below). See also the subsection entitled +"Non-printing characters" +above +for further details of the handling of digits following a backslash. +

+

+A back reference matches whatever actually matched the capturing subpattern in +the current subject string, rather than anything matching the subpattern +itself (see +"Subpatterns as subroutines" +below for a way of doing that). So the pattern +

+  (sens|respons)e and \1ibility
+
+matches "sense and sensibility" and "response and responsibility", but not +"sense and responsibility". If caseful matching is in force at the time of the +back reference, the case of letters is relevant. For example, +
+  ((?i)rah)\s+\1
+
+matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original +capturing subpattern is matched caselessly. +

+

+Back references to named subpatterns use the Python syntax (?P=name). We could +rewrite the above example as follows: +

+  (?P<p1>(?i)rah)\s+(?P=p1)
+
+A subpattern that is referenced by name may appear in the pattern before or +after the reference. +

+

+There may be more than one back reference to the same subpattern. If a +subpattern has not actually been used in a particular match, any back +references to it always fail. For example, the pattern +

+  (a|(bc))\2
+
+always fails if it starts to match "a" rather than "bc". Because there may be +many capturing parentheses in a pattern, all digits following the backslash are +taken as part of a potential back reference number. If the pattern continues +with a digit character, some delimiter must be used to terminate the back +reference. If the PCRE_EXTENDED option is set, this can be whitespace. +Otherwise an empty comment (see +"Comments" +below) can be used. +

+

+A back reference that occurs inside the parentheses to which it refers fails +when the subpattern is first used, so, for example, (a\1) never matches. +However, such references can be useful inside repeated subpatterns. For +example, the pattern +

+  (a|b\1)+
+
+matches any number of "a"s and also "aba", "ababbaa" etc. At each iteration of +the subpattern, the back reference matches the character string corresponding +to the previous iteration. In order for this to work, the pattern must be such +that the first iteration does not need to match the back reference. This can be +done using alternation, as in the example above, or by a quantifier with a +minimum of zero. +

+
ASSERTIONS
+

+An assertion is a test on the characters following or preceding the current +matching point that does not actually consume any characters. The simple +assertions coded as \b, \B, \A, \G, \Z, \z, ^ and $ are described +above. +

+

+More complicated assertions are coded as subpatterns. There are two kinds: +those that look ahead of the current position in the subject string, and those +that look behind it. An assertion subpattern is matched in the normal way, +except that it does not cause the current matching position to be changed. +

+

+Assertion subpatterns are not capturing subpatterns, and may not be repeated, +because it makes no sense to assert the same thing several times. If any kind +of assertion contains capturing subpatterns within it, these are counted for +the purposes of numbering the capturing subpatterns in the whole pattern. +However, substring capturing is carried out only for positive assertions, +because it does not make sense for negative assertions. +

+
+Lookahead assertions +
+

+Lookahead assertions start with (?= for positive assertions and (?! for +negative assertions. For example, +

+  \w+(?=;)
+
+matches a word followed by a semicolon, but does not include the semicolon in +the match, and +
+  foo(?!bar)
+
+matches any occurrence of "foo" that is not followed by "bar". Note that the +apparently similar pattern +
+  (?!foo)bar
+
+does not find an occurrence of "bar" that is preceded by something other than +"foo"; it finds any occurrence of "bar" whatsoever, because the assertion +(?!foo) is always true when the next three characters are "bar". A +lookbehind assertion is needed to achieve the other effect. +

+

+If you want to force a matching failure at some point in a pattern, the most +convenient way to do it is with (?!) because an empty string always matches, so +an assertion that requires there not to be an empty string must always fail. +

+
+Lookbehind assertions +
+

+Lookbehind assertions start with (?<= for positive assertions and (?<! for +negative assertions. For example, +

+  (?<!foo)bar
+
+does find an occurrence of "bar" that is not preceded by "foo". The contents of +a lookbehind assertion are restricted such that all the strings it matches must +have a fixed length. However, if there are several top-level alternatives, they +do not all have to have the same fixed length. Thus +
+  (?<=bullock|donkey)
+
+is permitted, but +
+  (?<!dogs?|cats?)
+
+causes an error at compile time. Branches that match different length strings +are permitted only at the top level of a lookbehind assertion. This is an +extension compared with Perl (at least for 5.8), which requires all branches to +match the same length of string. An assertion such as +
+  (?<=ab(c|de))
+
+is not permitted, because its single top-level branch can match two different +lengths, but it is acceptable if rewritten to use two top-level branches: +
+  (?<=abc|abde)
+
+The implementation of lookbehind assertions is, for each alternative, to +temporarily move the current position back by the fixed width and then try to +match. If there are insufficient characters before the current position, the +match is deemed to fail. +

+

+PCRE does not allow the \C escape (which matches a single byte in UTF-8 mode) +to appear in lookbehind assertions, because it makes it impossible to calculate +the length of the lookbehind. The \X escape, which can match different numbers +of bytes, is also not permitted. +

+

+Atomic groups can be used in conjunction with lookbehind assertions to specify +efficient matching at the end of the subject string. Consider a simple pattern +such as +

+  abcd$
+
+when applied to a long string that does not match. Because matching proceeds +from left to right, PCRE will look for each "a" in the subject and then see if +what follows matches the rest of the pattern. If the pattern is specified as +
+  ^.*abcd$
+
+the initial .* matches the entire string at first, but when this fails (because +there is no following "a"), it backtracks to match all but the last character, +then all but the last two characters, and so on. Once again the search for "a" +covers the entire string, from right to left, so we are no better off. However, +if the pattern is written as +
+  ^(?>.*)(?<=abcd)
+
+or, equivalently, using the possessive quantifier syntax, +
+  ^.*+(?<=abcd)
+
+there can be no backtracking for the .* item; it can match only the entire +string. The subsequent lookbehind assertion does a single test on the last four +characters. If it fails, the match fails immediately. For long strings, this +approach makes a significant difference to the processing time. +

+
+Using multiple assertions +
+

+Several assertions (of any sort) may occur in succession. For example, +

+  (?<=\d{3})(?<!999)foo
+
+matches "foo" preceded by three digits that are not "999". Notice that each of +the assertions is applied independently at the same point in the subject +string. First there is a check that the previous three characters are all +digits, and then there is a check that the same three characters are not "999". +This pattern does not match "foo" preceded by six characters, the first +of which are digits and the last three of which are not "999". For example, it +doesn't match "123abcfoo". A pattern to do that is +
+  (?<=\d{3}...)(?<!999)foo
+
+This time the first assertion looks at the preceding six characters, checking +that the first three are digits, and then the second assertion checks that the +preceding three characters are not "999". +

+

+Assertions can be nested in any combination. For example, +

+  (?<=(?<!foo)bar)baz
+
+matches an occurrence of "baz" that is preceded by "bar" which in turn is not +preceded by "foo", while +
+  (?<=\d{3}(?!999)...)foo
+
+is another pattern that matches "foo" preceded by three digits and any three +characters that are not "999". +

+
CONDITIONAL SUBPATTERNS
+

+It is possible to cause the matching process to obey a subpattern +conditionally or to choose between two alternative subpatterns, depending on +the result of an assertion, or whether a previous capturing subpattern matched +or not. The two possible forms of conditional subpattern are +

+  (?(condition)yes-pattern)
+  (?(condition)yes-pattern|no-pattern)
+
+If the condition is satisfied, the yes-pattern is used; otherwise the +no-pattern (if present) is used. If there are more than two alternatives in the +subpattern, a compile-time error occurs. +

+

+There are three kinds of condition. If the text between the parentheses +consists of a sequence of digits, or a sequence of alphanumeric characters and +underscores, the condition is satisfied if the capturing subpattern of that +number or name has previously matched. There is a possible ambiguity here, +because subpattern names may consist entirely of digits. PCRE looks first for a +named subpattern; if it cannot find one and the text consists entirely of +digits, it looks for a subpattern of that number, which must be greater than +zero. Using subpattern names that consist entirely of digits is not +recommended. +

+

+Consider the following pattern, which contains non-significant white space to +make it more readable (assume the PCRE_EXTENDED option) and to divide it into +three parts for ease of discussion: +

+  ( \( )?    [^()]+    (?(1) \) )
+
+The first part matches an optional opening parenthesis, and if that +character is present, sets it as the first captured substring. The second part +matches one or more characters that are not parentheses. The third part is a +conditional subpattern that tests whether the first set of parentheses matched +or not. If they did, that is, if subject started with an opening parenthesis, +the condition is true, and so the yes-pattern is executed and a closing +parenthesis is required. Otherwise, since no-pattern is not present, the +subpattern matches nothing. In other words, this pattern matches a sequence of +non-parentheses, optionally enclosed in parentheses. Rewriting it to use a +named subpattern gives this: +
+  (?P<OPEN> \( )?    [^()]+    (?(OPEN) \) )
+
+If the condition is the string (R), and there is no subpattern with the name R, +the condition is satisfied if a recursive call to the pattern or subpattern has +been made. At "top level", the condition is false. This is a PCRE extension. +Recursive patterns are described in the next section. +

+

+If the condition is not a sequence of digits or (R), it must be an assertion. +This may be a positive or negative lookahead or lookbehind assertion. Consider +this pattern, again containing non-significant white space, and with the two +alternatives on the second line: +

+  (?(?=[^a-z]*[a-z])
+  \d{2}-[a-z]{3}-\d{2}  |  \d{2}-\d{2}-\d{2} )
+
+The condition is a positive lookahead assertion that matches an optional +sequence of non-letters followed by a letter. In other words, it tests for the +presence of at least one letter in the subject. If a letter is found, the +subject is matched against the first alternative; otherwise it is matched +against the second. This pattern matches strings in one of the two forms +dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits. +

+
COMMENTS
+

+The sequence (?# marks the start of a comment that continues up to the next +closing parenthesis. Nested parentheses are not permitted. The characters +that make up a comment play no part in the pattern matching at all. +

+

+If the PCRE_EXTENDED option is set, an unescaped # character outside a +character class introduces a comment that continues to immediately after the +next newline in the pattern. +

+
RECURSIVE PATTERNS
+

+Consider the problem of matching a string in parentheses, allowing for +unlimited nested parentheses. Without the use of recursion, the best that can +be done is to use a pattern that matches up to some fixed depth of nesting. It +is not possible to handle an arbitrary nesting depth. Perl provides a facility +that allows regular expressions to recurse (amongst other things). It does this +by interpolating Perl code in the expression at run time, and the code can +refer to the expression itself. A Perl pattern to solve the parentheses problem +can be created like this: +

+  $re = qr{\( (?: (?>[^()]+) | (?p{$re}) )* \)}x;
+
+The (?p{...}) item interpolates Perl code at run time, and in this case refers +recursively to the pattern in which it appears. Obviously, PCRE cannot support +the interpolation of Perl code. Instead, it supports some special syntax for +recursion of the entire pattern, and also for individual subpattern recursion. +

+

+The special item that consists of (? followed by a number greater than zero and +a closing parenthesis is a recursive call of the subpattern of the given +number, provided that it occurs inside that subpattern. (If not, it is a +"subroutine" call, which is described in the next section.) The special item +(?R) is a recursive call of the entire regular expression. +

+

+A recursive subpattern call is always treated as an atomic group. That is, once +it has matched some of the subject string, it is never re-entered, even if +it contains untried alternatives and there is a subsequent matching failure. +

+

+This PCRE pattern solves the nested parentheses problem (assume the +PCRE_EXTENDED option is set so that white space is ignored): +

+  \( ( (?>[^()]+) | (?R) )* \)
+
+First it matches an opening parenthesis. Then it matches any number of +substrings which can either be a sequence of non-parentheses, or a recursive +match of the pattern itself (that is, a correctly parenthesized substring). +Finally there is a closing parenthesis. +

+

+If this were part of a larger pattern, you would not want to recurse the entire +pattern, so instead you could use this: +

+  ( \( ( (?>[^()]+) | (?1) )* \) )
+
+We have put the pattern into parentheses, and caused the recursion to refer to +them instead of the whole pattern. In a larger pattern, keeping track of +parenthesis numbers can be tricky. It may be more convenient to use named +parentheses instead. For this, PCRE uses (?P>name), which is an extension to +the Python syntax that PCRE uses for named parentheses (Perl does not provide +named parentheses). We could rewrite the above example as follows: +
+  (?P<pn> \( ( (?>[^()]+) | (?P>pn) )* \) )
+
+This particular example pattern contains nested unlimited repeats, and so the +use of atomic grouping for matching strings of non-parentheses is important +when applying the pattern to strings that do not match. For example, when this +pattern is applied to +
+  (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa()
+
+it yields "no match" quickly. However, if atomic grouping is not used, +the match runs for a very long time indeed because there are so many different +ways the + and * repeats can carve up the subject, and all have to be tested +before failure can be reported. +

+

+At the end of a match, the values set for any capturing subpatterns are those +from the outermost level of the recursion at which the subpattern value is set. +If you want to obtain intermediate values, a callout function can be used (see +the next section and the +pcrecallout +documentation). If the pattern above is matched against +

+  (ab(cd)ef)
+
+the value for the capturing parentheses is "ef", which is the last value taken +on at the top level. If additional parentheses are added, giving +
+  \( ( ( (?>[^()]+) | (?R) )* ) \)
+     ^                        ^
+     ^                        ^
+
+the string they capture is "ab(cd)ef", the contents of the top level +parentheses. If there are more than 15 capturing parentheses in a pattern, PCRE +has to obtain extra memory to store data during a recursion, which it does by +using pcre_malloc, freeing it via pcre_free afterwards. If no +memory can be obtained, the match fails with the PCRE_ERROR_NOMEMORY error. +

+

+Do not confuse the (?R) item with the condition (R), which tests for recursion. +Consider this pattern, which matches text in angle brackets, allowing for +arbitrary nesting. Only digits are allowed in nested brackets (that is, when +recursing), whereas any characters are permitted at the outer level. +

+  < (?: (?(R) \d++  | [^<>]*+) | (?R)) * >
+
+In this pattern, (?(R) is the start of a conditional subpattern, with two +different alternatives for the recursive and non-recursive cases. The (?R) item +is the actual recursive call. +

+
SUBPATTERNS AS SUBROUTINES
+

+If the syntax for a recursive subpattern reference (either by number or by +name) is used outside the parentheses to which it refers, it operates like a +subroutine in a programming language. An earlier example pointed out that the +pattern +

+  (sens|respons)e and \1ibility
+
+matches "sense and sensibility" and "response and responsibility", but not +"sense and responsibility". If instead the pattern +
+  (sens|respons)e and (?1)ibility
+
+is used, it does match "sense and responsibility" as well as the other two +strings. Such references, if given numerically, must follow the subpattern to +which they refer. However, named references can refer to later subpatterns. +

+

+Like recursive subpatterns, a "subroutine" call is always treated as an atomic +group. That is, once it has matched some of the subject string, it is never +re-entered, even if it contains untried alternatives and there is a subsequent +matching failure. +

+
CALLOUTS
+

+Perl has a feature whereby using the sequence (?{...}) causes arbitrary Perl +code to be obeyed in the middle of matching a regular expression. This makes it +possible, amongst other things, to extract different substrings that match the +same pair of parentheses when there is a repetition. +

+

+PCRE provides a similar feature, but of course it cannot obey arbitrary Perl +code. The feature is called "callout". The caller of PCRE provides an external +function by putting its entry point in the global variable pcre_callout. +By default, this variable contains NULL, which disables all calling out. +

+

+Within a regular expression, (?C) indicates the points at which the external +function is to be called. If you want to identify different callout points, you +can put a number less than 256 after the letter C. The default value is zero. +For example, this pattern has two callout points: +

+  (?C1)\dabc(?C2)def
+
+If the PCRE_AUTO_CALLOUT flag is passed to pcre_compile(), callouts are +automatically installed before each item in the pattern. They are all numbered +255. +

+

+During matching, when PCRE reaches a callout point (and pcre_callout is +set), the external function is called. It is provided with the number of the +callout, the position in the pattern, and, optionally, one item of data +originally supplied by the caller of pcre_exec(). The callout function +may cause matching to proceed, to backtrack, or to fail altogether. A complete +description of the interface to the callout function is given in the +pcrecallout +documentation. +

+

+Last updated: 06 June 2006 +
+Copyright © 1997-2006 University of Cambridge. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcreperform.html b/libs/pcre/doc/html/pcreperform.html new file mode 100644 index 0000000000..e97e748f1f --- /dev/null +++ b/libs/pcre/doc/html/pcreperform.html @@ -0,0 +1,97 @@ + + +pcreperform specification + + +

pcreperform man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+PCRE PERFORMANCE +
+

+Certain items that may appear in regular expression patterns are more efficient +than others. It is more efficient to use a character class like [aeiou] than a +set of alternatives such as (a|e|i|o|u). In general, the simplest construction +that provides the required behaviour is usually the most efficient. Jeffrey +Friedl's book contains a lot of useful general discussion about optimizing +regular expressions for efficient performance. This document contains a few +observations about PCRE. +

+

+Using Unicode character properties (the \p, \P, and \X escapes) is slow, +because PCRE has to scan a structure that contains data for over fifteen +thousand characters whenever it needs a character's property. If you can find +an alternative pattern that does not use character properties, it will probably +be faster. +

+

+When a pattern begins with .* not in parentheses, or in parentheses that are +not the subject of a backreference, and the PCRE_DOTALL option is set, the +pattern is implicitly anchored by PCRE, since it can match only at the start of +a subject string. However, if PCRE_DOTALL is not set, PCRE cannot make this +optimization, because the . metacharacter does not then match a newline, and if +the subject string contains newlines, the pattern may match from the character +immediately following one of them instead of from the very start. For example, +the pattern +

+  .*second
+
+matches the subject "first\nand second" (where \n stands for a newline +character), with the match starting at the seventh character. In order to do +this, PCRE has to retry the match starting after every newline in the subject. +

+

+If you are using such a pattern with subject strings that do not contain +newlines, the best performance is obtained by setting PCRE_DOTALL, or starting +the pattern with ^.* or ^.*? to indicate explicit anchoring. That saves PCRE +from having to scan along the subject looking for a newline to restart at. +

+

+Beware of patterns that contain nested indefinite repeats. These can take a +long time to run when applied to a string that does not match. Consider the +pattern fragment +

+  (a+)*
+
+This can match "aaaa" in 33 different ways, and this number increases very +rapidly as the string gets longer. (The * repeat can match 0, 1, 2, 3, or 4 +times, and for each of those cases other than 0, the + repeats can match +different numbers of times.) When the remainder of the pattern is such that the +entire match is going to fail, PCRE has in principle to try every possible +variation, and this can take an extremely long time. +

+

+An optimization catches some of the more simple cases such as +

+  (a+)*b
+
+where a literal character follows. Before embarking on the standard matching +procedure, PCRE checks that there is a "b" later in the subject string, and if +there is not, it fails the match immediately. However, when there is no +following literal this optimization cannot be used. You can see the difference +by comparing the behaviour of +
+  (a+)*\d
+
+with the pattern above. The former gives a failure almost instantly when +applied to a whole line of "a" characters, whereas the latter takes an +appreciable time with strings longer than about 20 characters. +

+

+In many cases, the solution to this kind of performance issue is to use an +atomic group or a possessive quantifier. +

+

+Last updated: 28 February 2005 +
+Copyright © 1997-2005 University of Cambridge. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcreposix.html b/libs/pcre/doc/html/pcreposix.html new file mode 100644 index 0000000000..9bf36ca1ef --- /dev/null +++ b/libs/pcre/doc/html/pcreposix.html @@ -0,0 +1,244 @@ + + +pcreposix specification + + +

pcreposix man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+

+
SYNOPSIS OF POSIX API
+

+#include <pcreposix.h> +

+

+int regcomp(regex_t *preg, const char *pattern, +int cflags); +

+

+int regexec(regex_t *preg, const char *string, +size_t nmatch, regmatch_t pmatch[], int eflags); +

+

+size_t regerror(int errcode, const regex_t *preg, +char *errbuf, size_t errbuf_size); +

+

+void regfree(regex_t *preg); +

+
DESCRIPTION
+

+This set of functions provides a POSIX-style API to the PCRE regular expression +package. See the +pcreapi +documentation for a description of PCRE's native API, which contains much +additional functionality. +

+

+The functions described here are just wrapper functions that ultimately call +the PCRE native API. Their prototypes are defined in the pcreposix.h +header file, and on Unix systems the library itself is called +pcreposix.a, so can be accessed by adding -lpcreposix to the +command for linking an application that uses them. Because the POSIX functions +call the native ones, it is also necessary to add -lpcre. +

+

+I have implemented only those option bits that can be reasonably mapped to PCRE +native options. In addition, the option REG_EXTENDED is defined with the value +zero. This has no effect, but since programs that are written to the POSIX +interface often use it, this makes it easier to slot in PCRE as a replacement +library. Other POSIX options are not even defined. +

+

+When PCRE is called via these functions, it is only the API that is POSIX-like +in style. The syntax and semantics of the regular expressions themselves are +still those of Perl, subject to the setting of various PCRE options, as +described below. "POSIX-like in style" means that the API approximates to the +POSIX definition; it is not fully POSIX-compatible, and in multi-byte encoding +domains it is probably even less compatible. +

+

+The header for these functions is supplied as pcreposix.h to avoid any +potential clash with other POSIX libraries. It can, of course, be renamed or +aliased as regex.h, which is the "correct" name. It provides two +structure types, regex_t for compiled internal forms, and +regmatch_t for returning captured substrings. It also defines some +constants whose names start with "REG_"; these are used for setting options and +identifying error codes. +

+

+

+
COMPILING A PATTERN
+

+The function regcomp() is called to compile a pattern into an +internal form. The pattern is a C string terminated by a binary zero, and +is passed in the argument pattern. The preg argument is a pointer +to a regex_t structure that is used as a base for storing information +about the compiled regular expression. +

+

+The argument cflags is either zero, or contains one or more of the bits +defined by the following macros: +

+  REG_DOTALL
+
+The PCRE_DOTALL option is set when the regular expression is passed for +compilation to the native function. Note that REG_DOTALL is not part of the +POSIX standard. +
+  REG_ICASE
+
+The PCRE_CASELESS option is set when the regular expression is passed for +compilation to the native function. +
+  REG_NEWLINE
+
+The PCRE_MULTILINE option is set when the regular expression is passed for +compilation to the native function. Note that this does not mimic the +defined POSIX behaviour for REG_NEWLINE (see the following section). +
+  REG_NOSUB
+
+The PCRE_NO_AUTO_CAPTURE option is set when the regular expression is passed +for compilation to the native function. In addition, when a pattern that is +compiled with this flag is passed to regexec() for matching, the +nmatch and pmatch arguments are ignored, and no captured strings +are returned. +
+  REG_UTF8
+
+The PCRE_UTF8 option is set when the regular expression is passed for +compilation to the native function. This causes the pattern itself and all data +strings used for matching it to be treated as UTF-8 strings. Note that REG_UTF8 +is not part of the POSIX standard. +

+

+In the absence of these flags, no options are passed to the native function. +This means the the regex is compiled with PCRE default semantics. In +particular, the way it handles newline characters in the subject string is the +Perl way, not the POSIX way. Note that setting PCRE_MULTILINE has only +some of the effects specified for REG_NEWLINE. It does not affect the way +newlines are matched by . (they aren't) or by a negative class such as [^a] +(they are). +

+

+The yield of regcomp() is zero on success, and non-zero otherwise. The +preg structure is filled in on success, and one member of the structure +is public: re_nsub contains the number of capturing subpatterns in +the regular expression. Various error codes are defined in the header file. +

+
MATCHING NEWLINE CHARACTERS
+

+This area is not simple, because POSIX and Perl take different views of things. +It is not possible to get PCRE to obey POSIX semantics, but then PCRE was never +intended to be a POSIX engine. The following table lists the different +possibilities for matching newline characters in PCRE: +

+                          Default   Change with
+
+  . matches newline          no     PCRE_DOTALL
+  newline matches [^a]       yes    not changeable
+  $ matches \n at end        yes    PCRE_DOLLARENDONLY
+  $ matches \n in middle     no     PCRE_MULTILINE
+  ^ matches \n in middle     no     PCRE_MULTILINE
+
+This is the equivalent table for POSIX: +
+                          Default   Change with
+
+  . matches newline          yes    REG_NEWLINE
+  newline matches [^a]       yes    REG_NEWLINE
+  $ matches \n at end        no     REG_NEWLINE
+  $ matches \n in middle     no     REG_NEWLINE
+  ^ matches \n in middle     no     REG_NEWLINE
+
+PCRE's behaviour is the same as Perl's, except that there is no equivalent for +PCRE_DOLLAR_ENDONLY in Perl. In both PCRE and Perl, there is no way to stop +newline from matching [^a]. +

+

+The default POSIX newline handling can be obtained by setting PCRE_DOTALL and +PCRE_DOLLAR_ENDONLY, but there is no way to make PCRE behave exactly as for the +REG_NEWLINE action. +

+
MATCHING A PATTERN
+

+The function regexec() is called to match a compiled pattern preg +against a given string, which is terminated by a zero byte, subject to +the options in eflags. These can be: +

+  REG_NOTBOL
+
+The PCRE_NOTBOL option is set when calling the underlying PCRE matching +function. +
+  REG_NOTEOL
+
+The PCRE_NOTEOL option is set when calling the underlying PCRE matching +function. +

+

+If the pattern was compiled with the REG_NOSUB flag, no data about any matched +strings is returned. The nmatch and pmatch arguments of +regexec() are ignored. +

+

+Otherwise,the portion of the string that was matched, and also any captured +substrings, are returned via the pmatch argument, which points to an +array of nmatch structures of type regmatch_t, containing the +members rm_so and rm_eo. These contain the offset to the first +character of each substring and the offset to the first character after the end +of each substring, respectively. The 0th element of the vector relates to the +entire portion of string that was matched; subsequent elements relate to +the capturing subpatterns of the regular expression. Unused entries in the +array have both structure members set to -1. +

+

+A successful match yields a zero return; various error codes are defined in the +header file, of which REG_NOMATCH is the "expected" failure code. +

+
ERROR MESSAGES
+

+The regerror() function maps a non-zero errorcode from either +regcomp() or regexec() to a printable message. If preg is not +NULL, the error should have arisen from the use of that structure. A message +terminated by a binary zero is placed in errbuf. The length of the +message, including the zero, is limited to errbuf_size. The yield of the +function is the size of buffer needed to hold the whole message. +

+
MEMORY USAGE
+

+Compiling a regular expression causes memory to be allocated and associated +with the preg structure. The function regfree() frees all such +memory, after which preg may no longer be used as a compiled expression. +

+
AUTHOR
+

+Philip Hazel +
+University Computing Service, +
+Cambridge CB2 3QG, England. +

+

+Last updated: 16 January 2006 +
+Copyright © 1997-2006 University of Cambridge. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcreprecompile.html b/libs/pcre/doc/html/pcreprecompile.html new file mode 100644 index 0000000000..00de3b0561 --- /dev/null +++ b/libs/pcre/doc/html/pcreprecompile.html @@ -0,0 +1,140 @@ + + +pcreprecompile specification + + +

pcreprecompile man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+

+
SAVING AND RE-USING PRECOMPILED PCRE PATTERNS
+

+If you are running an application that uses a large number of regular +expression patterns, it may be useful to store them in a precompiled form +instead of having to compile them every time the application is run. +If you are not using any private character tables (see the +pcre_maketables() +documentation), this is relatively straightforward. If you are using private +tables, it is a little bit more complicated. +

+

+If you save compiled patterns to a file, you can copy them to a different host +and run them there. This works even if the new host has the opposite endianness +to the one on which the patterns were compiled. There may be a small +performance penalty, but it should be insignificant. +

+
SAVING A COMPILED PATTERN
+

+The value returned by pcre_compile() points to a single block of memory +that holds the compiled pattern and associated data. You can find the length of +this block in bytes by calling pcre_fullinfo() with an argument of +PCRE_INFO_SIZE. You can then save the data in any appropriate manner. Here is +sample code that compiles a pattern and writes it to a file. It assumes that +the variable fd refers to a file that is open for output: +

+  int erroroffset, rc, size;
+  char *error;
+  pcre *re;
+
+  re = pcre_compile("my pattern", 0, &error, &erroroffset, NULL);
+  if (re == NULL) { ... handle errors ... }
+  rc = pcre_fullinfo(re, NULL, PCRE_INFO_SIZE, &size);
+  if (rc < 0) { ... handle errors ... }
+  rc = fwrite(re, 1, size, fd);
+  if (rc != size) { ... handle errors ... }
+
+In this example, the bytes that comprise the compiled pattern are copied +exactly. Note that this is binary data that may contain any of the 256 possible +byte values. On systems that make a distinction between binary and non-binary +data, be sure that the file is opened for binary output. +

+

+If you want to write more than one pattern to a file, you will have to devise a +way of separating them. For binary data, preceding each pattern with its length +is probably the most straightforward approach. Another possibility is to write +out the data in hexadecimal instead of binary, one pattern to a line. +

+

+Saving compiled patterns in a file is only one possible way of storing them for +later use. They could equally well be saved in a database, or in the memory of +some daemon process that passes them via sockets to the processes that want +them. +

+

+If the pattern has been studied, it is also possible to save the study data in +a similar way to the compiled pattern itself. When studying generates +additional information, pcre_study() returns a pointer to a +pcre_extra data block. Its format is defined in the +section on matching a pattern +in the +pcreapi +documentation. The study_data field points to the binary study data, and +this is what you must save (not the pcre_extra block itself). The length +of the study data can be obtained by calling pcre_fullinfo() with an +argument of PCRE_INFO_STUDYSIZE. Remember to check that pcre_study() did +return a non-NULL value before trying to save the study data. +

+
RE-USING A PRECOMPILED PATTERN
+

+Re-using a precompiled pattern is straightforward. Having reloaded it into main +memory, you pass its pointer to pcre_exec() or pcre_dfa_exec() in +the usual way. This should work even on another host, and even if that host has +the opposite endianness to the one where the pattern was compiled. +

+

+However, if you passed a pointer to custom character tables when the pattern +was compiled (the tableptr argument of pcre_compile()), you must +now pass a similar pointer to pcre_exec() or pcre_dfa_exec(), +because the value saved with the compiled pattern will obviously be nonsense. A +field in a pcre_extra() block is used to pass this data, as described in +the +section on matching a pattern +in the +pcreapi +documentation. +

+

+If you did not provide custom character tables when the pattern was compiled, +the pointer in the compiled pattern is NULL, which causes pcre_exec() to +use PCRE's internal tables. Thus, you do not need to take any special action at +run time in this case. +

+

+If you saved study data with the compiled pattern, you need to create your own +pcre_extra data block and set the study_data field to point to the +reloaded study data. You must also set the PCRE_EXTRA_STUDY_DATA bit in the +flags field to indicate that study data is present. Then pass the +pcre_extra block to pcre_exec() or pcre_dfa_exec() in the +usual way. +

+
COMPATIBILITY WITH DIFFERENT PCRE RELEASES
+

+The layout of the control block that is at the start of the data that makes up +a compiled pattern was changed for release 5.0. If you have any saved patterns +that were compiled with previous releases (not a facility that was previously +advertised), you will have to recompile them for release 5.0. However, from now +on, it should be possible to make changes in a compatible manner. +

+

+Notwithstanding the above, if you have any saved patterns in UTF-8 mode that +use \p or \P that were compiled with any release up to and including 6.4, you +will have to recompile them for release 6.5 and above. +

+

+Last updated: 01 February 2006 +
+Copyright © 1997-2006 University of Cambridge. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcresample.html b/libs/pcre/doc/html/pcresample.html new file mode 100644 index 0000000000..91cd41137d --- /dev/null +++ b/libs/pcre/doc/html/pcresample.html @@ -0,0 +1,81 @@ + + +pcresample specification + + +

pcresample man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+PCRE SAMPLE PROGRAM +
+

+A simple, complete demonstration program, to get you started with using PCRE, +is supplied in the file pcredemo.c in the PCRE distribution. +

+

+The program compiles the regular expression that is its first argument, and +matches it against the subject string in its second argument. No PCRE options +are set, and default character tables are used. If matching succeeds, the +program outputs the portion of the subject that matched, together with the +contents of any captured substrings. +

+

+If the -g option is given on the command line, the program then goes on to +check for further matches of the same regular expression in the same subject +string. The logic is a little bit tricky because of the possibility of matching +an empty string. Comments in the code explain what is going on. +

+

+If PCRE is installed in the standard include and library directories for your +system, you should be able to compile the demonstration program using this +command: +

+  gcc -o pcredemo pcredemo.c -lpcre
+
+If PCRE is installed elsewhere, you may need to add additional options to the +command line. For example, on a Unix-like system that has PCRE installed in +/usr/local, you can compile the demonstration program using a command +like this: +
+  gcc -o pcredemo -I/usr/local/include pcredemo.c -L/usr/local/lib -lpcre
+
+Once you have compiled the demonstration program, you can run simple tests like +this: +
+  ./pcredemo 'cat|dog' 'the cat sat on the mat'
+  ./pcredemo -g 'cat|dog' 'the dog sat on the cat'
+
+Note that there is a much more comprehensive test program, called +pcretest, +which supports many more facilities for testing regular expressions and the +PCRE library. The pcredemo program is provided as a simple coding +example. +

+

+On some operating systems (e.g. Solaris), when PCRE is not installed in the +standard library directory, you may get an error like this when you try to run +pcredemo: +

+  ld.so.1: a.out: fatal: libpcre.so.0: open failed: No such file or directory
+
+This is caused by the way shared library support works on those systems. You +need to add +
+  -R/usr/local/lib
+
+(for example) to the compile command to get round this problem. +

+

+Last updated: 09 September 2004 +
+Copyright © 1997-2004 University of Cambridge. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcrestack.html b/libs/pcre/doc/html/pcrestack.html new file mode 100644 index 0000000000..edca78e614 --- /dev/null +++ b/libs/pcre/doc/html/pcrestack.html @@ -0,0 +1,127 @@ + + +pcrestack specification + + +

pcrestack man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+
+PCRE DISCUSSION OF STACK USAGE +
+

+When you call pcre_exec(), it makes use of an internal function called +match(). This calls itself recursively at branch points in the pattern, +in order to remember the state of the match so that it can back up and try a +different alternative if the first one fails. As matching proceeds deeper and +deeper into the tree of possibilities, the recursion depth increases. +

+

+Not all calls of match() increase the recursion depth; for an item such +as a* it may be called several times at the same level, after matching +different numbers of a's. Furthermore, in a number of cases where the result of +the recursive call would immediately be passed back as the result of the +current call (a "tail recursion"), the function is just restarted instead. +

+

+The pcre_dfa_exec() function operates in an entirely different way, and +hardly uses recursion at all. The limit on its complexity is the amount of +workspace it is given. The comments that follow do NOT apply to +pcre_dfa_exec(); they are relevant only for pcre_exec(). +

+

+You can set limits on the number of times that match() is called, both in +total and recursively. If the limit is exceeded, an error occurs. For details, +see the +section on extra data for pcre_exec() +in the +pcreapi +documentation. +

+

+Each time that match() is actually called recursively, it uses memory +from the process stack. For certain kinds of pattern and data, very large +amounts of stack may be needed, despite the recognition of "tail recursion". +You can often reduce the amount of recursion, and therefore the amount of stack +used, by modifying the pattern that is being matched. Consider, for example, +this pattern: +

+  ([^<]|<(?!inet))+
+
+It matches from wherever it starts until it encounters "<inet" or the end of +the data, and is the kind of pattern that might be used when processing an XML +file. Each iteration of the outer parentheses matches either one character that +is not "<" or a "<" that is not followed by "inet". However, each time a +parenthesis is processed, a recursion occurs, so this formulation uses a stack +frame for each matched character. For a long string, a lot of stack is +required. Consider now this rewritten pattern, which matches exactly the same +strings: +
+  ([^<]++|<(?!inet))
+
+This uses very much less stack, because runs of characters that do not contain +"<" are "swallowed" in one item inside the parentheses. Recursion happens only +when a "<" character that is not followed by "inet" is encountered (and we +assume this is relatively rare). A possessive quantifier is used to stop any +backtracking into the runs of non-"<" characters, but that is not related to +stack usage. +

+

+In environments where stack memory is constrained, you might want to compile +PCRE to use heap memory instead of stack for remembering back-up points. This +makes it run a lot more slowly, however. Details of how to do this are given in +the +pcrebuild +documentation. +

+

+In Unix-like environments, there is not often a problem with the stack, though +the default limit on stack size varies from system to system. Values from 8Mb +to 64Mb are common. You can find your default limit by running the command: +

+  ulimit -s
+
+The effect of running out of stack is often SIGSEGV, though sometimes an error +message is given. You can normally increase the limit on stack size by code +such as this: +
+  struct rlimit rlim;
+  getrlimit(RLIMIT_STACK, &rlim);
+  rlim.rlim_cur = 100*1024*1024;
+  setrlimit(RLIMIT_STACK, &rlim);
+
+This reads the current limits (soft and hard) using getrlimit(), then +attempts to increase the soft limit to 100Mb using setrlimit(). You must +do this before calling pcre_exec(). +

+

+PCRE has an internal counter that can be used to limit the depth of recursion, +and thus cause pcre_exec() to give an error code before it runs out of +stack. By default, the limit is very large, and unlikely ever to operate. It +can be changed when PCRE is built, and it can also be set when +pcre_exec() is called. For details of these interfaces, see the +pcrebuild +and +pcreapi +documentation. +

+

+As a very rough rule of thumb, you should reckon on about 500 bytes per +recursion. Thus, if you want to limit your stack usage to 8Mb, you +should set the limit at 16000 recursions. A 64Mb stack, on the other hand, can +support around 128000 recursions. The pcretest test program has a command +line option (-S) that can be used to increase its stack. +

+

+Last updated: 29 June 2006 +
+Copyright © 1997-2006 University of Cambridge. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/html/pcretest.html b/libs/pcre/doc/html/pcretest.html new file mode 100644 index 0000000000..8ffd577efb --- /dev/null +++ b/libs/pcre/doc/html/pcretest.html @@ -0,0 +1,616 @@ + + +pcretest specification + + +

pcretest man page

+

+Return to the PCRE index page. +

+

+This page is part of the PCRE HTML documentation. It was generated automatically +from the original man page. If there is any nonsense in it, please consult the +man page, in case the conversion went wrong. +
+

+
SYNOPSIS
+

+pcretest [options] [source] [destination] +
+
+pcretest was written as a test program for the PCRE regular expression +library itself, but it can also be used for experimenting with regular +expressions. This document describes the features of the test program; for +details of the regular expressions themselves, see the +pcrepattern +documentation. For details of the PCRE library function calls and their +options, see the +pcreapi +documentation. +

+
OPTIONS
+

+-C +Output the version number of the PCRE library, and all available information +about the optional features that are included, and then exit. +

+

+-d +Behave as if each regex has the /D (debug) modifier; the internal +form is output after compilation. +

+

+-dfa +Behave as if each data line contains the \D escape sequence; this causes the +alternative matching function, pcre_dfa_exec(), to be used instead of the +standard pcre_exec() function (more detail is given below). +

+

+-i +Behave as if each regex has the /I modifier; information about the +compiled pattern is given after compilation. +

+

+-m +Output the size of each compiled pattern after it has been compiled. This is +equivalent to adding /M to each regular expression. For compatibility +with earlier versions of pcretest, -s is a synonym for -m. +

+

+-o osize +Set the number of elements in the output vector that is used when calling +pcre_exec() to be osize. The default value is 45, which is enough +for 14 capturing subexpressions. The vector size can be changed for individual +matching calls by including \O in the data line (see below). +

+

+-p +Behave as if each regex has the /P modifier; the POSIX wrapper API is +used to call PCRE. None of the other options has any effect when -p is +set. +

+

+-q +Do not output the version number of pcretest at the start of execution. +

+

+-S size +On Unix-like systems, set the size of the runtime stack to size +megabytes. +

+

+-t +Run each compile, study, and match many times with a timer, and output +resulting time per compile or match (in milliseconds). Do not set -m with +-t, because you will then get the size output a zillion times, and the +timing will be distorted. +

+
DESCRIPTION
+

+If pcretest is given two filename arguments, it reads from the first and +writes to the second. If it is given only one filename argument, it reads from +that file and writes to stdout. Otherwise, it reads from stdin and writes to +stdout, and prompts for each line of input, using "re>" to prompt for regular +expressions, and "data>" to prompt for data lines. +

+

+The program handles any number of sets of input on a single input file. Each +set starts with a regular expression, and continues with any number of data +lines to be matched against the pattern. +

+

+Each data line is matched separately and independently. If you want to do +multi-line matches, you have to use the \n escape sequence (or \r or \r\n, +depending on the newline setting) in a single line of input to encode the +newline characters. There is no limit on the length of data lines; the input +buffer is automatically extended if it is too small. +

+

+An empty line signals the end of the data lines, at which point a new regular +expression is read. The regular expressions are given enclosed in any +non-alphanumeric delimiters other than backslash, for example: +

+  /(a|bc)x+yz/
+
+White space before the initial delimiter is ignored. A regular expression may +be continued over several input lines, in which case the newline characters are +included within it. It is possible to include the delimiter within the pattern +by escaping it, for example +
+  /abc\/def/
+
+If you do so, the escape and the delimiter form part of the pattern, but since +delimiters are always non-alphanumeric, this does not affect its interpretation. +If the terminating delimiter is immediately followed by a backslash, for +example, +
+  /abc/\
+
+then a backslash is added to the end of the pattern. This is done to provide a +way of testing the error condition that arises if a pattern finishes with a +backslash, because +
+  /abc\/
+
+is interpreted as the first line of a pattern that starts with "abc/", causing +pcretest to read the next line as a continuation of the regular expression. +

+
PATTERN MODIFIERS
+

+A pattern may be followed by any number of modifiers, which are mostly single +characters. Following Perl usage, these are referred to below as, for example, +"the /i modifier", even though the delimiter of the pattern need not +always be a slash, and no slash is used when writing modifiers. Whitespace may +appear between the final pattern delimiter and the first modifier, and between +the modifiers themselves. +

+

+The /i, /m, /s, and /x modifiers set the PCRE_CASELESS, +PCRE_MULTILINE, PCRE_DOTALL, or PCRE_EXTENDED options, respectively, when +pcre_compile() is called. These four modifier letters have the same +effect as they do in Perl. For example: +

+  /caseless/i
+
+The following table shows additional modifiers for setting PCRE options that do +not correspond to anything in Perl: +
+  /A       PCRE_ANCHORED
+  /C       PCRE_AUTO_CALLOUT
+  /E       PCRE_DOLLAR_ENDONLY
+  /f       PCRE_FIRSTLINE
+  /J       PCRE_DUPNAMES
+  /N       PCRE_NO_AUTO_CAPTURE
+  /U       PCRE_UNGREEDY
+  /X       PCRE_EXTRA
+  /<cr>    PCRE_NEWLINE_CR
+  /<lf>    PCRE_NEWLINE_LF
+  /<crlf>  PCRE_NEWLINE_CRLF
+
+Those specifying line endings are literal strings as shown. Details of the +meanings of these PCRE options are given in the +pcreapi +documentation. +

+
+Finding all matches in a string +
+

+Searching for all possible matches within each subject string can be requested +by the /g or /G modifier. After finding a match, PCRE is called +again to search the remainder of the subject string. The difference between +/g and /G is that the former uses the startoffset argument to +pcre_exec() to start searching at a new point within the entire string +(which is in effect what Perl does), whereas the latter passes over a shortened +substring. This makes a difference to the matching process if the pattern +begins with a lookbehind assertion (including \b or \B). +

+

+If any call to pcre_exec() in a /g or /G sequence matches an +empty string, the next call is done with the PCRE_NOTEMPTY and PCRE_ANCHORED +flags set in order to search for another, non-empty, match at the same point. +If this second match fails, the start offset is advanced by one, and the normal +match is retried. This imitates the way Perl handles such cases when using the +/g modifier or the split() function. +

+
+Other modifiers +
+

+There are yet more modifiers for controlling the way pcretest +operates. +

+

+The /+ modifier requests that as well as outputting the substring that +matched the entire pattern, pcretest should in addition output the remainder of +the subject string. This is useful for tests where the subject contains +multiple copies of the same substring. +

+

+The /L modifier must be followed directly by the name of a locale, for +example, +

+  /pattern/Lfr_FR
+
+For this reason, it must be the last modifier. The given locale is set, +pcre_maketables() is called to build a set of character tables for the +locale, and this is then passed to pcre_compile() when compiling the +regular expression. Without an /L modifier, NULL is passed as the tables +pointer; that is, /L applies only to the expression on which it appears. +

+

+The /I modifier requests that pcretest output information about the +compiled pattern (whether it is anchored, has a fixed first character, and +so on). It does this by calling pcre_fullinfo() after compiling a +pattern. If the pattern is studied, the results of that are also output. +

+

+The /D modifier is a PCRE debugging feature, which also assumes /I. +It causes the internal form of compiled regular expressions to be output after +compilation. If the pattern was studied, the information returned is also +output. +

+

+The /F modifier causes pcretest to flip the byte order of the +fields in the compiled pattern that contain 2-byte and 4-byte numbers. This +facility is for testing the feature in PCRE that allows it to execute patterns +that were compiled on a host with a different endianness. This feature is not +available when the POSIX interface to PCRE is being used, that is, when the +/P pattern modifier is specified. See also the section about saving and +reloading compiled patterns below. +

+

+The /S modifier causes pcre_study() to be called after the +expression has been compiled, and the results used when the expression is +matched. +

+

+The /M modifier causes the size of memory block used to hold the compiled +pattern to be output. +

+

+The /P modifier causes pcretest to call PCRE via the POSIX wrapper +API rather than its native API. When this is done, all other modifiers except +/i, /m, and /+ are ignored. REG_ICASE is set if /i is +present, and REG_NEWLINE is set if /m is present. The wrapper functions +force PCRE_DOLLAR_ENDONLY always, and PCRE_DOTALL unless REG_NEWLINE is set. +

+

+The /8 modifier causes pcretest to call PCRE with the PCRE_UTF8 +option set. This turns on support for UTF-8 character handling in PCRE, +provided that it was compiled with this support enabled. This modifier also +causes any non-printing characters in output strings to be printed using the +\x{hh...} notation if they are valid UTF-8 sequences. +

+

+If the /? modifier is used with /8, it causes pcretest to +call pcre_compile() with the PCRE_NO_UTF8_CHECK option, to suppress the +checking of the string for UTF-8 validity. +

+
DATA LINES
+

+Before each data line is passed to pcre_exec(), leading and trailing +whitespace is removed, and it is then scanned for \ escapes. Some of these are +pretty esoteric features, intended for checking out some of the more +complicated features of PCRE. If you are just testing "ordinary" regular +expressions, you probably don't need any of these. The following escapes are +recognized: +

+  \a         alarm (= BEL)
+  \b         backspace
+  \e         escape
+  \f         formfeed
+  \n         newline
+  \qdd       set the PCRE_MATCH_LIMIT limit to dd (any number of digits)
+  \r         carriage return
+  \t         tab
+  \v         vertical tab
+  \nnn       octal character (up to 3 octal digits)
+  \xhh       hexadecimal character (up to 2 hex digits)
+  \x{hh...}  hexadecimal character, any number of digits in UTF-8 mode
+  \A         pass the PCRE_ANCHORED option to pcre_exec() or pcre_dfa_exec()
+  \B         pass the PCRE_NOTBOL option to pcre_exec() or pcre_dfa_exec()
+  \Cdd       call pcre_copy_substring() for substring dd after a successful match (number less than 32)
+  \Cname     call pcre_copy_named_substring() for substring "name" after a successful match (name termin-
+               ated by next non alphanumeric character)
+  \C+        show the current captured substrings at callout time
+  \C-        do not supply a callout function
+  \C!n       return 1 instead of 0 when callout number n is reached
+  \C!n!m     return 1 instead of 0 when callout number n is reached for the nth time
+  \C*n       pass the number n (may be negative) as callout data; this is used as the callout return value
+  \D         use the pcre_dfa_exec() match function
+  \F         only shortest match for pcre_dfa_exec()
+  \Gdd       call pcre_get_substring() for substring dd after a successful match (number less than 32)
+  \Gname     call pcre_get_named_substring() for substring "name" after a successful match (name termin-
+               ated by next non-alphanumeric character)
+  \L         call pcre_get_substringlist() after a successful match
+  \M         discover the minimum MATCH_LIMIT and MATCH_LIMIT_RECURSION settings
+  \N         pass the PCRE_NOTEMPTY option to pcre_exec() or pcre_dfa_exec()
+  \Odd       set the size of the output vector passed to pcre_exec() to dd (any number of digits)
+  \P         pass the PCRE_PARTIAL option to pcre_exec() or pcre_dfa_exec()
+  \Qdd       set the PCRE_MATCH_LIMIT_RECURSION limit to dd (any number of digits)
+  \R         pass the PCRE_DFA_RESTART option to pcre_dfa_exec()
+  \S         output details of memory get/free calls during matching
+  \Z         pass the PCRE_NOTEOL option to pcre_exec() or pcre_dfa_exec()
+  \?         pass the PCRE_NO_UTF8_CHECK option to pcre_exec() or pcre_dfa_exec()
+  \>dd       start the match at offset dd (any number of digits);
+               this sets the startoffset argument for pcre_exec() or pcre_dfa_exec()
+  \<cr>      pass the PCRE_NEWLINE_CR option to pcre_exec() or pcre_dfa_exec()
+  \<lf>      pass the PCRE_NEWLINE_LF option to pcre_exec() or pcre_dfa_exec()
+  \<crlf>    pass the PCRE_NEWLINE_CRLF option to pcre_exec() or pcre_dfa_exec()
+
+The escapes that specify line endings are literal strings, exactly as shown. +A backslash followed by anything else just escapes the anything else. If the +very last character is a backslash, it is ignored. This gives a way of passing +an empty line as data, since a real empty line terminates the data input. +

+

+If \M is present, pcretest calls pcre_exec() several times, with +different values in the match_limit and match_limit_recursion +fields of the pcre_extra data structure, until it finds the minimum +numbers for each parameter that allow pcre_exec() to complete. The +match_limit number is a measure of the amount of backtracking that takes +place, and checking it out can be instructive. For most simple matches, the +number is quite small, but for patterns with very large numbers of matching +possibilities, it can become large very quickly with increasing length of +subject string. The match_limit_recursion number is a measure of how much +stack (or, if PCRE is compiled with NO_RECURSE, how much heap) memory is needed +to complete the match attempt. +

+

+When \O is used, the value specified may be higher or lower than the size set +by the -O command line option (or defaulted to 45); \O applies only to +the call of pcre_exec() for the line in which it appears. +

+

+If the /P modifier was present on the pattern, causing the POSIX wrapper +API to be used, the only option-setting sequences that have any effect are \B +and \Z, causing REG_NOTBOL and REG_NOTEOL, respectively, to be passed to +regexec(). +

+

+The use of \x{hh...} to represent UTF-8 characters is not dependent on the use +of the /8 modifier on the pattern. It is recognized always. There may be +any number of hexadecimal digits inside the braces. The result is from one to +six bytes, encoded according to the UTF-8 rules. +

+
THE ALTERNATIVE MATCHING FUNCTION
+

+By default, pcretest uses the standard PCRE matching function, +pcre_exec() to match each data line. From release 6.0, PCRE supports an +alternative matching function, pcre_dfa_test(), which operates in a +different way, and has some restrictions. The differences between the two +functions are described in the +pcrematching +documentation. +

+

+If a data line contains the \D escape sequence, or if the command line +contains the -dfa option, the alternative matching function is called. +This function finds all possible matches at a given point. If, however, the \F +escape sequence is present in the data line, it stops after the first match is +found. This is always the shortest possible match. +

+
DEFAULT OUTPUT FROM PCRETEST
+

+This section describes the output when the normal matching function, +pcre_exec(), is being used. +

+

+When a match succeeds, pcretest outputs the list of captured substrings that +pcre_exec() returns, starting with number 0 for the string that matched +the whole pattern. Otherwise, it outputs "No match" or "Partial match" +when pcre_exec() returns PCRE_ERROR_NOMATCH or PCRE_ERROR_PARTIAL, +respectively, and otherwise the PCRE negative error number. Here is an example +of an interactive pcretest run. +

+  $ pcretest
+  PCRE version 5.00 07-Sep-2004
+
+    re> /^abc(\d+)/
+  data> abc123
+   0: abc123
+   1: 123
+  data> xyz
+  No match
+
+If the strings contain any non-printing characters, they are output as \0x +escapes, or as \x{...} escapes if the /8 modifier was present on the +pattern. If the pattern has the /+ modifier, the output for substring 0 +is followed by the the rest of the subject string, identified by "0+" like +this: +
+    re> /cat/+
+  data> cataract
+   0: cat
+   0+ aract
+
+If the pattern has the /g or /G modifier, the results of successive +matching attempts are output in sequence, like this: +
+    re> /\Bi(\w\w)/g
+  data> Mississippi
+   0: iss
+   1: ss
+   0: iss
+   1: ss
+   0: ipp
+   1: pp
+
+"No match" is output only if the first match attempt fails. +

+

+If any of the sequences \C, \G, or \L are present in a +data line that is successfully matched, the substrings extracted by the +convenience functions are output with C, G, or L after the string number +instead of a colon. This is in addition to the normal full list. The string +length (that is, the return from the extraction function) is given in +parentheses after each string for \C and \G. +

+

+Note that while patterns can be continued over several lines (a plain ">" +prompt is used for continuations), data lines may not. However newlines can be +included in data by means of the \n escape (or \r or \r\n for those newline +settings). +

+
OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION
+

+When the alternative matching function, pcre_dfa_exec(), is used (by +means of the \D escape sequence or the -dfa command line option), the +output consists of a list of all the matches that start at the first point in +the subject where there is at least one match. For example: +

+    re> /(tang|tangerine|tan)/
+  data> yellow tangerine\D
+   0: tangerine
+   1: tang
+   2: tan
+
+(Using the normal matching function on this data finds only "tang".) The +longest matching string is always given first (and numbered zero). +

+

+If \fB/g\P is present on the pattern, the search for further matches resumes +at the end of the longest match. For example: +

+    re> /(tang|tangerine|tan)/g
+  data> yellow tangerine and tangy sultana\D
+   0: tangerine
+   1: tang
+   2: tan
+   0: tang
+   1: tan
+   0: tan
+
+Since the matching function does not support substring capture, the escape +sequences that are concerned with captured substrings are not relevant. +

+
RESTARTING AFTER A PARTIAL MATCH
+

+When the alternative matching function has given the PCRE_ERROR_PARTIAL return, +indicating that the subject partially matched the pattern, you can restart the +match with additional subject data by means of the \R escape sequence. For +example: +

+    re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
+  data> 23ja\P\D
+  Partial match: 23ja
+  data> n05\R\D
+   0: n05
+
+For further information about partial matching, see the +pcrepartial +documentation. +

+
CALLOUTS
+

+If the pattern contains any callout requests, pcretest's callout function +is called during matching. This works with both matching functions. By default, +the called function displays the callout number, the start and current +positions in the text at the callout time, and the next pattern item to be +tested. For example, the output +

+  --->pqrabcdef
+    0    ^  ^     \d
+
+indicates that callout number 0 occurred for a match attempt starting at the +fourth character of the subject string, when the pointer was at the seventh +character of the data, and when the next pattern item was \d. Just one +circumflex is output if the start and current positions are the same. +

+

+Callouts numbered 255 are assumed to be automatic callouts, inserted as a +result of the /C pattern modifier. In this case, instead of showing the +callout number, the offset in the pattern, preceded by a plus, is output. For +example: +

+    re> /\d?[A-E]\*/C
+  data> E*
+  --->E*
+   +0 ^      \d?
+   +3 ^      [A-E]
+   +8 ^^     \*
+  +10 ^ ^
+   0: E*
+
+The callout function in pcretest returns zero (carry on matching) by +default, but you can use a \C item in a data line (as described above) to +change this. +

+

+Inserting callouts can be helpful when using pcretest to check +complicated regular expressions. For further information about callouts, see +the +pcrecallout +documentation. +

+
SAVING AND RELOADING COMPILED PATTERNS
+

+The facilities described in this section are not available when the POSIX +inteface to PCRE is being used, that is, when the /P pattern modifier is +specified. +

+

+When the POSIX interface is not in use, you can cause pcretest to write a +compiled pattern to a file, by following the modifiers with > and a file name. +For example: +

+  /pattern/im >/some/file
+
+See the +pcreprecompile +documentation for a discussion about saving and re-using compiled patterns. +

+

+The data that is written is binary. The first eight bytes are the length of the +compiled pattern data followed by the length of the optional study data, each +written as four bytes in big-endian order (most significant byte first). If +there is no study data (either the pattern was not studied, or studying did not +return any data), the second length is zero. The lengths are followed by an +exact copy of the compiled pattern. If there is additional study data, this +follows immediately after the compiled pattern. After writing the file, +pcretest expects to read a new pattern. +

+

+A saved pattern can be reloaded into pcretest by specifing < and a file +name instead of a pattern. The name of the file must not contain a < character, +as otherwise pcretest will interpret the line as a pattern delimited by < +characters. +For example: +

+   re> </some/file
+  Compiled regex loaded from /some/file
+  No study data
+
+When the pattern has been loaded, pcretest proceeds to read data lines in +the usual way. +

+

+You can copy a file written by pcretest to a different host and reload it +there, even if the new host has opposite endianness to the one on which the +pattern was compiled. For example, you can compile on an i86 machine and run on +a SPARC machine. +

+

+File names for saving and reloading can be absolute or relative, but note that +the shell facility of expanding a file name that starts with a tilde (~) is not +available. +

+

+The ability to save and reload files in pcretest is intended for testing +and experimentation. It is not intended for production use because only a +single pattern can be written to a file. Furthermore, there is no facility for +supplying custom character tables for use with a reloaded pattern. If the +original pattern was compiled with custom tables, an attempt to match a subject +string using a reloaded pattern is likely to cause pcretest to crash. +Finally, if you attempt to load a file that is not in the correct format, the +result is undefined. +

+
AUTHOR
+

+Philip Hazel +
+University Computing Service, +
+Cambridge CB2 3QG, England. +

+

+Last updated: 29 June 2006 +
+Copyright © 1997-2006 University of Cambridge. +

+Return to the PCRE index page. +

diff --git a/libs/pcre/doc/pcre.3 b/libs/pcre/doc/pcre.3 new file mode 100644 index 0000000000..62c18fac61 --- /dev/null +++ b/libs/pcre/doc/pcre.3 @@ -0,0 +1,244 @@ +.TH PCRE 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH INTRODUCTION +.rs +.sp +The PCRE library is a set of functions that implement regular expression +pattern matching using the same syntax and semantics as Perl, with just a few +differences. The current implementation of PCRE (release 6.x) corresponds +approximately with Perl 5.8, including support for UTF-8 encoded strings and +Unicode general category properties. However, this support has to be explicitly +enabled; it is not the default. +.P +In addition to the Perl-compatible matching function, PCRE also contains an +alternative matching function that matches the same compiled patterns in a +different way. In certain circumstances, the alternative function has some +advantages. For a discussion of the two matching algorithms, see the +.\" HREF +\fBpcrematching\fP +.\" +page. +.P +PCRE is written in C and released as a C library. A number of people have +written wrappers and interfaces of various kinds. In particular, Google Inc. +have provided a comprehensive C++ wrapper. This is now included as part of the +PCRE distribution. The +.\" HREF +\fBpcrecpp\fP +.\" +page has details of this interface. Other people's contributions can be found +in the \fIContrib\fR directory at the primary FTP site, which is: +.sp +.\" HTML +.\" +ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre +.P +Details of exactly which Perl regular expression features are and are not +supported by PCRE are given in separate documents. See the +.\" HREF +\fBpcrepattern\fR +.\" +and +.\" HREF +\fBpcrecompat\fR +.\" +pages. +.P +Some features of PCRE can be included, excluded, or changed when the library is +built. The +.\" HREF +\fBpcre_config()\fR +.\" +function makes it possible for a client to discover which features are +available. The features themselves are described in the +.\" HREF +\fBpcrebuild\fP +.\" +page. Documentation about building PCRE for various operating systems can be +found in the \fBREADME\fP file in the source distribution. +.P +The library contains a number of undocumented internal functions and data +tables that are used by more than one of the exported external functions, but +which are not intended for use by external callers. Their names all begin with +"_pcre_", which hopefully will not provoke any name clashes. In some +environments, it is possible to control which external symbols are exported +when a shared library is built, and in these cases the undocumented symbols are +not exported. +. +. +.SH "USER DOCUMENTATION" +.rs +.sp +The user documentation for PCRE comprises a number of different sections. In +the "man" format, each of these is a separate "man page". In the HTML format, +each is a separate page, linked from the index page. In the plain text format, +all the sections are concatenated, for ease of searching. The sections are as +follows: +.sp + pcre this document + pcreapi details of PCRE's native C API + pcrebuild options for building PCRE + pcrecallout details of the callout feature + pcrecompat discussion of Perl compatibility + pcrecpp details of the C++ wrapper + pcregrep description of the \fBpcregrep\fP command + pcrematching discussion of the two matching algorithms + pcrepartial details of the partial matching facility +.\" JOIN + pcrepattern syntax and semantics of supported + regular expressions + pcreperform discussion of performance issues + pcreposix the POSIX-compatible C API + pcreprecompile details of saving and re-using precompiled patterns + pcresample discussion of the sample program + pcrestack discussion of stack usage + pcretest description of the \fBpcretest\fP testing command +.sp +In addition, in the "man" and HTML formats, there is a short page for each +C library function, listing its arguments and results. +. +. +.SH LIMITATIONS +.rs +.sp +There are some size limitations in PCRE but it is hoped that they will never in +practice be relevant. +.P +The maximum length of a compiled pattern is 65539 (sic) bytes if PCRE is +compiled with the default internal linkage size of 2. If you want to process +regular expressions that are truly enormous, you can compile PCRE with an +internal linkage size of 3 or 4 (see the \fBREADME\fP file in the source +distribution and the +.\" HREF +\fBpcrebuild\fP +.\" +documentation for details). In these cases the limit is substantially larger. +However, the speed of execution will be slower. +.P +All values in repeating quantifiers must be less than 65536. The maximum +compiled length of subpattern with an explicit repeat count is 30000 bytes. The +maximum number of capturing subpatterns is 65535. +.P +There is no limit to the number of non-capturing subpatterns, but the maximum +depth of nesting of all kinds of parenthesized subpattern, including capturing +subpatterns, assertions, and other types of subpattern, is 200. +.P +The maximum length of name for a named subpattern is 32, and the maximum number +of named subpatterns is 10000. +.P +The maximum length of a subject string is the largest positive number that an +integer variable can hold. However, when using the traditional matching +function, PCRE uses recursion to handle subpatterns and indefinite repetition. +This means that the available stack space may limit the size of a subject +string that can be processed by certain patterns. For a discussion of stack +issues, see the +.\" HREF +\fBpcrestack\fP +.\" +documentation. +.sp +.\" HTML +. +. +.SH "UTF-8 AND UNICODE PROPERTY SUPPORT" +.rs +.sp +From release 3.3, PCRE has had some support for character strings encoded in +the UTF-8 format. For release 4.0 this was greatly extended to cover most +common requirements, and in release 5.0 additional support for Unicode general +category properties was added. +.P +In order process UTF-8 strings, you must build PCRE to include UTF-8 support in +the code, and, in addition, you must call +.\" HREF +\fBpcre_compile()\fP +.\" +with the PCRE_UTF8 option flag. When you do this, both the pattern and any +subject strings that are matched against it are treated as UTF-8 strings +instead of just strings of bytes. +.P +If you compile PCRE with UTF-8 support, but do not use it at run time, the +library will be a bit bigger, but the additional run time overhead is limited +to testing the PCRE_UTF8 flag in several places, so should not be very large. +.P +If PCRE is built with Unicode character property support (which implies UTF-8 +support), the escape sequences \ep{..}, \eP{..}, and \eX are supported. +The available properties that can be tested are limited to the general +category properties such as Lu for an upper case letter or Nd for a decimal +number, the Unicode script names such as Arabic or Han, and the derived +properties Any and L&. A full list is given in the +.\" HREF +\fBpcrepattern\fP +.\" +documentation. Only the short names for properties are supported. For example, +\ep{L} matches a letter. Its Perl synonym, \ep{Letter}, is not supported. +Furthermore, in Perl, many properties may optionally be prefixed by "Is", for +compatibility with Perl 5.6. PCRE does not support this. +.P +The following comments apply when PCRE is running in UTF-8 mode: +.P +1. When you set the PCRE_UTF8 flag, the strings passed as patterns and subjects +are checked for validity on entry to the relevant functions. If an invalid +UTF-8 string is passed, an error return is given. In some situations, you may +already know that your strings are valid, and therefore want to skip these +checks in order to improve performance. If you set the PCRE_NO_UTF8_CHECK flag +at compile time or at run time, PCRE assumes that the pattern or subject it +is given (respectively) contains only valid UTF-8 codes. In this case, it does +not diagnose an invalid UTF-8 string. If you pass an invalid UTF-8 string to +PCRE when PCRE_NO_UTF8_CHECK is set, the results are undefined. Your program +may crash. +.P +2. An unbraced hexadecimal escape sequence (such as \exb3) matches a two-byte +UTF-8 character if the value is greater than 127. +.P +3. Octal numbers up to \e777 are recognized, and match two-byte UTF-8 +characters for values greater than \e177. +.P +4. Repeat quantifiers apply to complete UTF-8 characters, not to individual +bytes, for example: \ex{100}{3}. +.P +5. The dot metacharacter matches one UTF-8 character instead of a single byte. +.P +6. The escape sequence \eC can be used to match a single byte in UTF-8 mode, +but its use can lead to some strange effects. This facility is not available in +the alternative matching function, \fBpcre_dfa_exec()\fP. +.P +7. The character escapes \eb, \eB, \ed, \eD, \es, \eS, \ew, and \eW correctly +test characters of any code value, but the characters that PCRE recognizes as +digits, spaces, or word characters remain the same set as before, all with +values less than 256. This remains true even when PCRE includes Unicode +property support, because to do otherwise would slow down PCRE in many common +cases. If you really want to test for a wider sense of, say, "digit", you +must use Unicode property tests such as \ep{Nd}. +.P +8. Similarly, characters that match the POSIX named character classes are all +low-valued characters. +.P +9. Case-insensitive matching applies only to characters whose values are less +than 128, unless PCRE is built with Unicode property support. Even when Unicode +property support is available, PCRE still uses its own character tables when +checking the case of low-valued characters, so as not to degrade performance. +The Unicode property information is used only for characters with higher +values. Even when Unicode property support is available, PCRE supports +case-insensitive matching only when there is a one-to-one mapping between a +letter's cases. There are a small number of many-to-one mappings in Unicode; +these are not supported by PCRE. +. +.SH AUTHOR +.rs +.sp +Philip Hazel +.br +University Computing Service, +.br +Cambridge CB2 3QG, England. +.P +Putting an actual email address here seems to have been a spam magnet, so I've +taken it away. If you want to email me, use my initial and surname, separated +by a dot, at the domain ucs.cam.ac.uk. +.sp +.in 0 +Last updated: 05 June 2006 +.br +Copyright (c) 1997-2006 University of Cambridge. diff --git a/libs/pcre/doc/pcre.txt b/libs/pcre/doc/pcre.txt new file mode 100644 index 0000000000..d6c204b574 --- /dev/null +++ b/libs/pcre/doc/pcre.txt @@ -0,0 +1,5153 @@ +----------------------------------------------------------------------------- +This file contains a concatenation of the PCRE man pages, converted to plain +text format for ease of searching with a text editor, or for use on systems +that do not have a man page processor. The small individual files that give +synopses of each function in the library have not been included. There are +separate text files for the pcregrep and pcretest commands. +----------------------------------------------------------------------------- + + +PCRE(3) PCRE(3) + + +NAME + PCRE - Perl-compatible regular expressions + + +INTRODUCTION + + The PCRE library is a set of functions that implement regular expres- + sion pattern matching using the same syntax and semantics as Perl, with + just a few differences. The current implementation of PCRE (release + 6.x) corresponds approximately with Perl 5.8, including support for + UTF-8 encoded strings and Unicode general category properties. However, + this support has to be explicitly enabled; it is not the default. + + In addition to the Perl-compatible matching function, PCRE also con- + tains an alternative matching function that matches the same compiled + patterns in a different way. In certain circumstances, the alternative + function has some advantages. For a discussion of the two matching + algorithms, see the pcrematching page. + + PCRE is written in C and released as a C library. A number of people + have written wrappers and interfaces of various kinds. In particular, + Google Inc. have provided a comprehensive C++ wrapper. This is now + included as part of the PCRE distribution. The pcrecpp page has details + of this interface. Other people's contributions can be found in the + Contrib directory at the primary FTP site, which is: + + ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre + + Details of exactly which Perl regular expression features are and are + not supported by PCRE are given in separate documents. See the pcrepat- + tern and pcrecompat pages. + + Some features of PCRE can be included, excluded, or changed when the + library is built. The pcre_config() function makes it possible for a + client to discover which features are available. The features them- + selves are described in the pcrebuild page. Documentation about build- + ing PCRE for various operating systems can be found in the README file + in the source distribution. + + The library contains a number of undocumented internal functions and + data tables that are used by more than one of the exported external + functions, but which are not intended for use by external callers. + Their names all begin with "_pcre_", which hopefully will not provoke + any name clashes. In some environments, it is possible to control which + external symbols are exported when a shared library is built, and in + these cases the undocumented symbols are not exported. + + +USER DOCUMENTATION + + The user documentation for PCRE comprises a number of different sec- + tions. In the "man" format, each of these is a separate "man page". In + the HTML format, each is a separate page, linked from the index page. + In the plain text format, all the sections are concatenated, for ease + of searching. The sections are as follows: + + pcre this document + pcreapi details of PCRE's native C API + pcrebuild options for building PCRE + pcrecallout details of the callout feature + pcrecompat discussion of Perl compatibility + pcrecpp details of the C++ wrapper + pcregrep description of the pcregrep command + pcrematching discussion of the two matching algorithms + pcrepartial details of the partial matching facility + pcrepattern syntax and semantics of supported + regular expressions + pcreperform discussion of performance issues + pcreposix the POSIX-compatible C API + pcreprecompile details of saving and re-using precompiled patterns + pcresample discussion of the sample program + pcrestack discussion of stack usage + pcretest description of the pcretest testing command + + In addition, in the "man" and HTML formats, there is a short page for + each C library function, listing its arguments and results. + + +LIMITATIONS + + There are some size limitations in PCRE but it is hoped that they will + never in practice be relevant. + + The maximum length of a compiled pattern is 65539 (sic) bytes if PCRE + is compiled with the default internal linkage size of 2. If you want to + process regular expressions that are truly enormous, you can compile + PCRE with an internal linkage size of 3 or 4 (see the README file in + the source distribution and the pcrebuild documentation for details). + In these cases the limit is substantially larger. However, the speed + of execution will be slower. + + All values in repeating quantifiers must be less than 65536. The maxi- + mum compiled length of subpattern with an explicit repeat count is + 30000 bytes. The maximum number of capturing subpatterns is 65535. + + There is no limit to the number of non-capturing subpatterns, but the + maximum depth of nesting of all kinds of parenthesized subpattern, + including capturing subpatterns, assertions, and other types of subpat- + tern, is 200. + + The maximum length of name for a named subpattern is 32, and the maxi- + mum number of named subpatterns is 10000. + + The maximum length of a subject string is the largest positive number + that an integer variable can hold. However, when using the traditional + matching function, PCRE uses recursion to handle subpatterns and indef- + inite repetition. This means that the available stack space may limit + the size of a subject string that can be processed by certain patterns. + For a discussion of stack issues, see the pcrestack documentation. + + +UTF-8 AND UNICODE PROPERTY SUPPORT + + From release 3.3, PCRE has had some support for character strings + encoded in the UTF-8 format. For release 4.0 this was greatly extended + to cover most common requirements, and in release 5.0 additional sup- + port for Unicode general category properties was added. + + In order process UTF-8 strings, you must build PCRE to include UTF-8 + support in the code, and, in addition, you must call pcre_compile() + with the PCRE_UTF8 option flag. When you do this, both the pattern and + any subject strings that are matched against it are treated as UTF-8 + strings instead of just strings of bytes. + + If you compile PCRE with UTF-8 support, but do not use it at run time, + the library will be a bit bigger, but the additional run time overhead + is limited to testing the PCRE_UTF8 flag in several places, so should + not be very large. + + If PCRE is built with Unicode character property support (which implies + UTF-8 support), the escape sequences \p{..}, \P{..}, and \X are sup- + ported. The available properties that can be tested are limited to the + general category properties such as Lu for an upper case letter or Nd + for a decimal number, the Unicode script names such as Arabic or Han, + and the derived properties Any and L&. A full list is given in the + pcrepattern documentation. Only the short names for properties are sup- + ported. For example, \p{L} matches a letter. Its Perl synonym, \p{Let- + ter}, is not supported. Furthermore, in Perl, many properties may + optionally be prefixed by "Is", for compatibility with Perl 5.6. PCRE + does not support this. + + The following comments apply when PCRE is running in UTF-8 mode: + + 1. When you set the PCRE_UTF8 flag, the strings passed as patterns and + subjects are checked for validity on entry to the relevant functions. + If an invalid UTF-8 string is passed, an error return is given. In some + situations, you may already know that your strings are valid, and + therefore want to skip these checks in order to improve performance. If + you set the PCRE_NO_UTF8_CHECK flag at compile time or at run time, + PCRE assumes that the pattern or subject it is given (respectively) + contains only valid UTF-8 codes. In this case, it does not diagnose an + invalid UTF-8 string. If you pass an invalid UTF-8 string to PCRE when + PCRE_NO_UTF8_CHECK is set, the results are undefined. Your program may + crash. + + 2. An unbraced hexadecimal escape sequence (such as \xb3) matches a + two-byte UTF-8 character if the value is greater than 127. + + 3. Octal numbers up to \777 are recognized, and match two-byte UTF-8 + characters for values greater than \177. + + 4. Repeat quantifiers apply to complete UTF-8 characters, not to indi- + vidual bytes, for example: \x{100}{3}. + + 5. The dot metacharacter matches one UTF-8 character instead of a sin- + gle byte. + + 6. The escape sequence \C can be used to match a single byte in UTF-8 + mode, but its use can lead to some strange effects. This facility is + not available in the alternative matching function, pcre_dfa_exec(). + + 7. The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly + test characters of any code value, but the characters that PCRE recog- + nizes as digits, spaces, or word characters remain the same set as + before, all with values less than 256. This remains true even when PCRE + includes Unicode property support, because to do otherwise would slow + down PCRE in many common cases. If you really want to test for a wider + sense of, say, "digit", you must use Unicode property tests such as + \p{Nd}. + + 8. Similarly, characters that match the POSIX named character classes + are all low-valued characters. + + 9. Case-insensitive matching applies only to characters whose values + are less than 128, unless PCRE is built with Unicode property support. + Even when Unicode property support is available, PCRE still uses its + own character tables when checking the case of low-valued characters, + so as not to degrade performance. The Unicode property information is + used only for characters with higher values. Even when Unicode property + support is available, PCRE supports case-insensitive matching only when + there is a one-to-one mapping between a letter's cases. There are a + small number of many-to-one mappings in Unicode; these are not sup- + ported by PCRE. + + +AUTHOR + + Philip Hazel + University Computing Service, + Cambridge CB2 3QG, England. + + Putting an actual email address here seems to have been a spam magnet, + so I've taken it away. If you want to email me, use my initial and sur- + name, separated by a dot, at the domain ucs.cam.ac.uk. + +Last updated: 05 June 2006 +Copyright (c) 1997-2006 University of Cambridge. +------------------------------------------------------------------------------ + + +PCREBUILD(3) PCREBUILD(3) + + +NAME + PCRE - Perl-compatible regular expressions + + +PCRE BUILD-TIME OPTIONS + + This document describes the optional features of PCRE that can be + selected when the library is compiled. They are all selected, or dese- + lected, by providing options to the configure script that is run before + the make command. The complete list of options for configure (which + includes the standard ones such as the selection of the installation + directory) can be obtained by running + + ./configure --help + + The following sections describe certain options whose names begin with + --enable or --disable. These settings specify changes to the defaults + for the configure command. Because of the way that configure works, + --enable and --disable always come in pairs, so the complementary + option always exists as well, but as it specifies the default, it is + not described. + + +C++ SUPPORT + + By default, the configure script will search for a C++ compiler and C++ + header files. If it finds them, it automatically builds the C++ wrapper + library for PCRE. You can disable this by adding + + --disable-cpp + + to the configure command. + + +UTF-8 SUPPORT + + To build PCRE with support for UTF-8 character strings, add + + --enable-utf8 + + to the configure command. Of itself, this does not make PCRE treat + strings as UTF-8. As well as compiling PCRE with this option, you also + have have to set the PCRE_UTF8 option when you call the pcre_compile() + function. + + +UNICODE CHARACTER PROPERTY SUPPORT + + UTF-8 support allows PCRE to process character values greater than 255 + in the strings that it handles. On its own, however, it does not pro- + vide any facilities for accessing the properties of such characters. If + you want to be able to use the pattern escapes \P, \p, and \X, which + refer to Unicode character properties, you must add + + --enable-unicode-properties + + to the configure command. This implies UTF-8 support, even if you have + not explicitly requested it. + + Including Unicode property support adds around 90K of tables to the + PCRE library, approximately doubling its size. Only the general cate- + gory properties such as Lu and Nd are supported. Details are given in + the pcrepattern documentation. + + +CODE VALUE OF NEWLINE + + By default, PCRE interprets character 10 (linefeed, LF) as indicating + the end of a line. This is the normal newline character on Unix-like + systems. You can compile PCRE to use character 13 (carriage return, CR) + instead, by adding + + --enable-newline-is-cr + + to the configure command. There is also a --enable-newline-is-lf + option, which explicitly specifies linefeed as the newline character. + + Alternatively, you can specify that line endings are to be indicated by + the two character sequence CRLF. If you want this, add + + --enable-newline-is-crlf + + to the configure command. Whatever line ending convention is selected + when PCRE is built can be overridden when the library functions are + called. At build time it is conventional to use the standard for your + operating system. + + +BUILDING SHARED AND STATIC LIBRARIES + + The PCRE building process uses libtool to build both shared and static + Unix libraries by default. You can suppress one of these by adding one + of + + --disable-shared + --disable-static + + to the configure command, as required. + + +POSIX MALLOC USAGE + + When PCRE is called through the POSIX interface (see the pcreposix doc- + umentation), additional working storage is required for holding the + pointers to capturing substrings, because PCRE requires three integers + per substring, whereas the POSIX interface provides only two. If the + number of expected substrings is small, the wrapper function uses space + on the stack, because this is faster than using malloc() for each call. + The default threshold above which the stack is no longer used is 10; it + can be changed by adding a setting such as + + --with-posix-malloc-threshold=20 + + to the configure command. + + +HANDLING VERY LARGE PATTERNS + + Within a compiled pattern, offset values are used to point from one + part to another (for example, from an opening parenthesis to an alter- + nation metacharacter). By default, two-byte values are used for these + offsets, leading to a maximum size for a compiled pattern of around + 64K. This is sufficient to handle all but the most gigantic patterns. + Nevertheless, some people do want to process enormous patterns, so it + is possible to compile PCRE to use three-byte or four-byte offsets by + adding a setting such as + + --with-link-size=3 + + to the configure command. The value given must be 2, 3, or 4. Using + longer offsets slows down the operation of PCRE because it has to load + additional bytes when handling them. + + If you build PCRE with an increased link size, test 2 (and test 5 if + you are using UTF-8) will fail. Part of the output of these tests is a + representation of the compiled pattern, and this changes with the link + size. + + +AVOIDING EXCESSIVE STACK USAGE + + When matching with the pcre_exec() function, PCRE implements backtrack- + ing by making recursive calls to an internal function called match(). + In environments where the size of the stack is limited, this can se- + verely limit PCRE's operation. (The Unix environment does not usually + suffer from this problem, but it may sometimes be necessary to increase + the maximum stack size. There is a discussion in the pcrestack docu- + mentation.) An alternative approach to recursion that uses memory from + the heap to remember data, instead of using recursive function calls, + has been implemented to work round the problem of limited stack size. + If you want to build a version of PCRE that works this way, add + + --disable-stack-for-recursion + + to the configure command. With this configuration, PCRE will use the + pcre_stack_malloc and pcre_stack_free variables to call memory manage- + ment functions. Separate functions are provided because the usage is + very predictable: the block sizes requested are always the same, and + the blocks are always freed in reverse order. A calling program might + be able to implement optimized functions that perform better than the + standard malloc() and free() functions. PCRE runs noticeably more + slowly when built in this way. This option affects only the pcre_exec() + function; it is not relevant for the the pcre_dfa_exec() function. + + +LIMITING PCRE RESOURCE USAGE + + Internally, PCRE has a function called match(), which it calls repeat- + edly (sometimes recursively) when matching a pattern with the + pcre_exec() function. By controlling the maximum number of times this + function may be called during a single matching operation, a limit can + be placed on the resources used by a single call to pcre_exec(). The + limit can be changed at run time, as described in the pcreapi documen- + tation. The default is 10 million, but this can be changed by adding a + setting such as + + --with-match-limit=500000 + + to the configure command. This setting has no effect on the + pcre_dfa_exec() matching function. + + In some environments it is desirable to limit the depth of recursive + calls of match() more strictly than the total number of calls, in order + to restrict the maximum amount of stack (or heap, if --disable-stack- + for-recursion is specified) that is used. A second limit controls this; + it defaults to the value that is set for --with-match-limit, which + imposes no additional constraints. However, you can set a lower limit + by adding, for example, + + --with-match-limit-recursion=10000 + + to the configure command. This value can also be overridden at run + time. + + +USING EBCDIC CODE + + PCRE assumes by default that it will run in an environment where the + character code is ASCII (or Unicode, which is a superset of ASCII). + PCRE can, however, be compiled to run in an EBCDIC environment by + adding + + --enable-ebcdic + + to the configure command. + +Last updated: 06 June 2006 +Copyright (c) 1997-2006 University of Cambridge. +------------------------------------------------------------------------------ + + +PCREMATCHING(3) PCREMATCHING(3) + + +NAME + PCRE - Perl-compatible regular expressions + + +PCRE MATCHING ALGORITHMS + + This document describes the two different algorithms that are available + in PCRE for matching a compiled regular expression against a given sub- + ject string. The "standard" algorithm is the one provided by the + pcre_exec() function. This works in the same was as Perl's matching + function, and provides a Perl-compatible matching operation. + + An alternative algorithm is provided by the pcre_dfa_exec() function; + this operates in a different way, and is not Perl-compatible. It has + advantages and disadvantages compared with the standard algorithm, and + these are described below. + + When there is only one possible way in which a given subject string can + match a pattern, the two algorithms give the same answer. A difference + arises, however, when there are multiple possibilities. For example, if + the pattern + + ^<.*> + + is matched against the string + + + + there are three possible answers. The standard algorithm finds only one + of them, whereas the DFA algorithm finds all three. + + +REGULAR EXPRESSIONS AS TREES + + The set of strings that are matched by a regular expression can be rep- + resented as a tree structure. An unlimited repetition in the pattern + makes the tree of infinite size, but it is still a tree. Matching the + pattern to a given subject string (from a given starting point) can be + thought of as a search of the tree. There are two ways to search a + tree: depth-first and breadth-first, and these correspond to the two + matching algorithms provided by PCRE. + + +THE STANDARD MATCHING ALGORITHM + + In the terminology of Jeffrey Friedl's book Mastering Regular Expres- + sions, the standard algorithm is an "NFA algorithm". It conducts a + depth-first search of the pattern tree. That is, it proceeds along a + single path through the tree, checking that the subject matches what is + required. When there is a mismatch, the algorithm tries any alterna- + tives at the current point, and if they all fail, it backs up to the + previous branch point in the tree, and tries the next alternative + branch at that level. This often involves backing up (moving to the + left) in the subject string as well. The order in which repetition + branches are tried is controlled by the greedy or ungreedy nature of + the quantifier. + + If a leaf node is reached, a matching string has been found, and at + that point the algorithm stops. Thus, if there is more than one possi- + ble match, this algorithm returns the first one that it finds. Whether + this is the shortest, the longest, or some intermediate length depends + on the way the greedy and ungreedy repetition quantifiers are specified + in the pattern. + + Because it ends up with a single path through the tree, it is rela- + tively straightforward for this algorithm to keep track of the sub- + strings that are matched by portions of the pattern in parentheses. + This provides support for capturing parentheses and back references. + + +THE DFA MATCHING ALGORITHM + + DFA stands for "deterministic finite automaton", but you do not need to + understand the origins of that name. This algorithm conducts a breadth- + first search of the tree. Starting from the first matching point in the + subject, it scans the subject string from left to right, once, charac- + ter by character, and as it does this, it remembers all the paths + through the tree that represent valid matches. + + The scan continues until either the end of the subject is reached, or + there are no more unterminated paths. At this point, terminated paths + represent the different matching possibilities (if there are none, the + match has failed). Thus, if there is more than one possible match, + this algorithm finds all of them, and in particular, it finds the long- + est. In PCRE, there is an option to stop the algorithm after the first + match (which is necessarily the shortest) has been found. + + Note that all the matches that are found start at the same point in the + subject. If the pattern + + cat(er(pillar)?) + + is matched against the string "the caterpillar catchment", the result + will be the three strings "cat", "cater", and "caterpillar" that start + at the fourth character of the subject. The algorithm does not automat- + ically move on to find matches that start at later positions. + + There are a number of features of PCRE regular expressions that are not + supported by the DFA matching algorithm. They are as follows: + + 1. Because the algorithm finds all possible matches, the greedy or + ungreedy nature of repetition quantifiers is not relevant. Greedy and + ungreedy quantifiers are treated in exactly the same way. + + 2. When dealing with multiple paths through the tree simultaneously, it + is not straightforward to keep track of captured substrings for the + different matching possibilities, and PCRE's implementation of this + algorithm does not attempt to do this. This means that no captured sub- + strings are available. + + 3. Because no substrings are captured, back references within the pat- + tern are not supported, and cause errors if encountered. + + 4. For the same reason, conditional expressions that use a backrefer- + ence as the condition are not supported. + + 5. Callouts are supported, but the value of the capture_top field is + always 1, and the value of the capture_last field is always -1. + + 6. The \C escape sequence, which (in the standard algorithm) matches a + single byte, even in UTF-8 mode, is not supported because the DFA algo- + rithm moves through the subject string one character at a time, for all + active paths through the tree. + + +ADVANTAGES OF THE DFA ALGORITHM + + Using the DFA matching algorithm provides the following advantages: + + 1. All possible matches (at a single point in the subject) are automat- + ically found, and in particular, the longest match is found. To find + more than one match using the standard algorithm, you have to do kludgy + things with callouts. + + 2. There is much better support for partial matching. The restrictions + on the content of the pattern that apply when using the standard algo- + rithm for partial matching do not apply to the DFA algorithm. For non- + anchored patterns, the starting position of a partial match is avail- + able. + + 3. Because the DFA algorithm scans the subject string just once, and + never needs to backtrack, it is possible to pass very long subject + strings to the matching function in several pieces, checking for par- + tial matching each time. + + +DISADVANTAGES OF THE DFA ALGORITHM + + The DFA algorithm suffers from a number of disadvantages: + + 1. It is substantially slower than the standard algorithm. This is + partly because it has to search for all possible matches, but is also + because it is less susceptible to optimization. + + 2. Capturing parentheses and back references are not supported. + + 3. The "atomic group" feature of PCRE regular expressions is supported, + but does not provide the advantage that it does for the standard algo- + rithm. + +Last updated: 06 June 2006 +Copyright (c) 1997-2006 University of Cambridge. +------------------------------------------------------------------------------ + + +PCREAPI(3) PCREAPI(3) + + +NAME + PCRE - Perl-compatible regular expressions + + +PCRE NATIVE API + + #include + + pcre *pcre_compile(const char *pattern, int options, + const char **errptr, int *erroffset, + const unsigned char *tableptr); + + pcre *pcre_compile2(const char *pattern, int options, + int *errorcodeptr, + const char **errptr, int *erroffset, + const unsigned char *tableptr); + + pcre_extra *pcre_study(const pcre *code, int options, + const char **errptr); + + int pcre_exec(const pcre *code, const pcre_extra *extra, + const char *subject, int length, int startoffset, + int options, int *ovector, int ovecsize); + + int pcre_dfa_exec(const pcre *code, const pcre_extra *extra, + const char *subject, int length, int startoffset, + int options, int *ovector, int ovecsize, + int *workspace, int wscount); + + int pcre_copy_named_substring(const pcre *code, + const char *subject, int *ovector, + int stringcount, const char *stringname, + char *buffer, int buffersize); + + int pcre_copy_substring(const char *subject, int *ovector, + int stringcount, int stringnumber, char *buffer, + int buffersize); + + int pcre_get_named_substring(const pcre *code, + const char *subject, int *ovector, + int stringcount, const char *stringname, + const char **stringptr); + + int pcre_get_stringnumber(const pcre *code, + const char *name); + + int pcre_get_stringtable_entries(const pcre *code, + const char *name, char **first, char **last); + + int pcre_get_substring(const char *subject, int *ovector, + int stringcount, int stringnumber, + const char **stringptr); + + int pcre_get_substring_list(const char *subject, + int *ovector, int stringcount, const char ***listptr); + + void pcre_free_substring(const char *stringptr); + + void pcre_free_substring_list(const char **stringptr); + + const unsigned char *pcre_maketables(void); + + int pcre_fullinfo(const pcre *code, const pcre_extra *extra, + int what, void *where); + + int pcre_info(const pcre *code, int *optptr, int *firstcharptr); + + int pcre_refcount(pcre *code, int adjust); + + int pcre_config(int what, void *where); + + char *pcre_version(void); + + void *(*pcre_malloc)(size_t); + + void (*pcre_free)(void *); + + void *(*pcre_stack_malloc)(size_t); + + void (*pcre_stack_free)(void *); + + int (*pcre_callout)(pcre_callout_block *); + + +PCRE API OVERVIEW + + PCRE has its own native API, which is described in this document. There + is also a set of wrapper functions that correspond to the POSIX regular + expression API. These are described in the pcreposix documentation. + Both of these APIs define a set of C function calls. A C++ wrapper is + distributed with PCRE. It is documented in the pcrecpp page. + + The native API C function prototypes are defined in the header file + pcre.h, and on Unix systems the library itself is called libpcre. It + can normally be accessed by adding -lpcre to the command for linking an + application that uses PCRE. The header file defines the macros + PCRE_MAJOR and PCRE_MINOR to contain the major and minor release num- + bers for the library. Applications can use these to include support + for different releases of PCRE. + + The functions pcre_compile(), pcre_compile2(), pcre_study(), and + pcre_exec() are used for compiling and matching regular expressions in + a Perl-compatible manner. A sample program that demonstrates the sim- + plest way of using them is provided in the file called pcredemo.c in + the source distribution. The pcresample documentation describes how to + run it. + + A second matching function, pcre_dfa_exec(), which is not Perl-compati- + ble, is also provided. This uses a different algorithm for the match- + ing. The alternative algorithm finds all possible matches (at a given + point in the subject). However, this algorithm does not return captured + substrings. A description of the two matching algorithms and their + advantages and disadvantages is given in the pcrematching documenta- + tion. + + In addition to the main compiling and matching functions, there are + convenience functions for extracting captured substrings from a subject + string that is matched by pcre_exec(). They are: + + pcre_copy_substring() + pcre_copy_named_substring() + pcre_get_substring() + pcre_get_named_substring() + pcre_get_substring_list() + pcre_get_stringnumber() + pcre_get_stringtable_entries() + + pcre_free_substring() and pcre_free_substring_list() are also provided, + to free the memory used for extracted strings. + + The function pcre_maketables() is used to build a set of character + tables in the current locale for passing to pcre_compile(), + pcre_exec(), or pcre_dfa_exec(). This is an optional facility that is + provided for specialist use. Most commonly, no special tables are + passed, in which case internal tables that are generated when PCRE is + built are used. + + The function pcre_fullinfo() is used to find out information about a + compiled pattern; pcre_info() is an obsolete version that returns only + some of the available information, but is retained for backwards com- + patibility. The function pcre_version() returns a pointer to a string + containing the version of PCRE and its date of release. + + The function pcre_refcount() maintains a reference count in a data + block containing a compiled pattern. This is provided for the benefit + of object-oriented applications. + + The global variables pcre_malloc and pcre_free initially contain the + entry points of the standard malloc() and free() functions, respec- + tively. PCRE calls the memory management functions via these variables, + so a calling program can replace them if it wishes to intercept the + calls. This should be done before calling any PCRE functions. + + The global variables pcre_stack_malloc and pcre_stack_free are also + indirections to memory management functions. These special functions + are used only when PCRE is compiled to use the heap for remembering + data, instead of recursive function calls, when running the pcre_exec() + function. See the pcrebuild documentation for details of how to do + this. It is a non-standard way of building PCRE, for use in environ- + ments that have limited stacks. Because of the greater use of memory + management, it runs more slowly. Separate functions are provided so + that special-purpose external code can be used for this case. When + used, these functions are always called in a stack-like manner (last + obtained, first freed), and always for memory blocks of the same size. + There is a discussion about PCRE's stack usage in the pcrestack docu- + mentation. + + The global variable pcre_callout initially contains NULL. It can be set + by the caller to a "callout" function, which PCRE will then call at + specified points during a matching operation. Details are given in the + pcrecallout documentation. + + +NEWLINES + PCRE supports three different conventions for indicating line breaks in + strings: a single CR character, a single LF character, or the two-char- + acter sequence CRLF. All three are used as "standard" by different + operating systems. When PCRE is built, a default can be specified. The + default default is LF, which is the Unix standard. When PCRE is run, + the default can be overridden, either when a pattern is compiled, or + when it is matched. + + In the PCRE documentation the word "newline" is used to mean "the char- + acter or pair of characters that indicate a line break". + + +MULTITHREADING + + The PCRE functions can be used in multi-threading applications, with + the proviso that the memory management functions pointed to by + pcre_malloc, pcre_free, pcre_stack_malloc, and pcre_stack_free, and the + callout function pointed to by pcre_callout, are shared by all threads. + + The compiled form of a regular expression is not altered during match- + ing, so the same compiled pattern can safely be used by several threads + at once. + + +SAVING PRECOMPILED PATTERNS FOR LATER USE + + The compiled form of a regular expression can be saved and re-used at a + later time, possibly by a different program, and even on a host other + than the one on which it was compiled. Details are given in the + pcreprecompile documentation. + + +CHECKING BUILD-TIME OPTIONS + + int pcre_config(int what, void *where); + + The function pcre_config() makes it possible for a PCRE client to dis- + cover which optional features have been compiled into the PCRE library. + The pcrebuild documentation has more details about these optional fea- + tures. + + The first argument for pcre_config() is an integer, specifying which + information is required; the second argument is a pointer to a variable + into which the information is placed. The following information is + available: + + PCRE_CONFIG_UTF8 + + The output is an integer that is set to one if UTF-8 support is avail- + able; otherwise it is set to zero. + + PCRE_CONFIG_UNICODE_PROPERTIES + + The output is an integer that is set to one if support for Unicode + character properties is available; otherwise it is set to zero. + + PCRE_CONFIG_NEWLINE + + The output is an integer whose value specifies the default character + sequence that is recognized as meaning "newline". The three values that + are supported are: 10 for LF, 13 for CR, and 3338 for CRLF. The default + should normally be the standard sequence for your operating system. + + PCRE_CONFIG_LINK_SIZE + + The output is an integer that contains the number of bytes used for + internal linkage in compiled regular expressions. The value is 2, 3, or + 4. Larger values allow larger regular expressions to be compiled, at + the expense of slower matching. The default value of 2 is sufficient + for all but the most massive patterns, since it allows the compiled + pattern to be up to 64K in size. + + PCRE_CONFIG_POSIX_MALLOC_THRESHOLD + + The output is an integer that contains the threshold above which the + POSIX interface uses malloc() for output vectors. Further details are + given in the pcreposix documentation. + + PCRE_CONFIG_MATCH_LIMIT + + The output is an integer that gives the default limit for the number of + internal matching function calls in a pcre_exec() execution. Further + details are given with pcre_exec() below. + + PCRE_CONFIG_MATCH_LIMIT_RECURSION + + The output is an integer that gives the default limit for the depth of + recursion when calling the internal matching function in a pcre_exec() + execution. Further details are given with pcre_exec() below. + + PCRE_CONFIG_STACKRECURSE + + The output is an integer that is set to one if internal recursion when + running pcre_exec() is implemented by recursive function calls that use + the stack to remember their state. This is the usual way that PCRE is + compiled. The output is zero if PCRE was compiled to use blocks of data + on the heap instead of recursive function calls. In this case, + pcre_stack_malloc and pcre_stack_free are called to manage memory + blocks on the heap, thus avoiding the use of the stack. + + +COMPILING A PATTERN + + pcre *pcre_compile(const char *pattern, int options, + const char **errptr, int *erroffset, + const unsigned char *tableptr); + + pcre *pcre_compile2(const char *pattern, int options, + int *errorcodeptr, + const char **errptr, int *erroffset, + const unsigned char *tableptr); + + Either of the functions pcre_compile() or pcre_compile2() can be called + to compile a pattern into an internal form. The only difference between + the two interfaces is that pcre_compile2() has an additional argument, + errorcodeptr, via which a numerical error code can be returned. + + The pattern is a C string terminated by a binary zero, and is passed in + the pattern argument. A pointer to a single block of memory that is + obtained via pcre_malloc is returned. This contains the compiled code + and related data. The pcre type is defined for the returned block; this + is a typedef for a structure whose contents are not externally defined. + It is up to the caller to free the memory (via pcre_free) when it is no + longer required. + + Although the compiled code of a PCRE regex is relocatable, that is, it + does not depend on memory location, the complete pcre data block is not + fully relocatable, because it may contain a copy of the tableptr argu- + ment, which is an address (see below). + + The options argument contains independent bits that affect the compila- + tion. It should be zero if no options are required. The available + options are described below. Some of them, in particular, those that + are compatible with Perl, can also be set and unset from within the + pattern (see the detailed description in the pcrepattern documenta- + tion). For these options, the contents of the options argument speci- + fies their initial settings at the start of compilation and execution. + The PCRE_ANCHORED and PCRE_NEWLINE_xxx options can be set at the time + of matching as well as at compile time. + + If errptr is NULL, pcre_compile() returns NULL immediately. Otherwise, + if compilation of a pattern fails, pcre_compile() returns NULL, and + sets the variable pointed to by errptr to point to a textual error mes- + sage. This is a static string that is part of the library. You must not + try to free it. The offset from the start of the pattern to the charac- + ter where the error was discovered is placed in the variable pointed to + by erroffset, which must not be NULL. If it is, an immediate error is + given. + + If pcre_compile2() is used instead of pcre_compile(), and the error- + codeptr argument is not NULL, a non-zero error code number is returned + via this argument in the event of an error. This is in addition to the + textual error message. Error codes and messages are listed below. + + If the final argument, tableptr, is NULL, PCRE uses a default set of + character tables that are built when PCRE is compiled, using the + default C locale. Otherwise, tableptr must be an address that is the + result of a call to pcre_maketables(). This value is stored with the + compiled pattern, and used again by pcre_exec(), unless another table + pointer is passed to it. For more discussion, see the section on locale + support below. + + This code fragment shows a typical straightforward call to pcre_com- + pile(): + + pcre *re; + const char *error; + int erroffset; + re = pcre_compile( + "^A.*Z", /* the pattern */ + 0, /* default options */ + &error, /* for error message */ + &erroffset, /* for error offset */ + NULL); /* use default character tables */ + + The following names for option bits are defined in the pcre.h header + file: + + PCRE_ANCHORED + + If this bit is set, the pattern is forced to be "anchored", that is, it + is constrained to match only at the first matching point in the string + that is being searched (the "subject string"). This effect can also be + achieved by appropriate constructs in the pattern itself, which is the + only way to do it in Perl. + + PCRE_AUTO_CALLOUT + + If this bit is set, pcre_compile() automatically inserts callout items, + all with number 255, before each pattern item. For discussion of the + callout facility, see the pcrecallout documentation. + + PCRE_CASELESS + + If this bit is set, letters in the pattern match both upper and lower + case letters. It is equivalent to Perl's /i option, and it can be + changed within a pattern by a (?i) option setting. In UTF-8 mode, PCRE + always understands the concept of case for characters whose values are + less than 128, so caseless matching is always possible. For characters + with higher values, the concept of case is supported if PCRE is com- + piled with Unicode property support, but not otherwise. If you want to + use caseless matching for characters 128 and above, you must ensure + that PCRE is compiled with Unicode property support as well as with + UTF-8 support. + + PCRE_DOLLAR_ENDONLY + + If this bit is set, a dollar metacharacter in the pattern matches only + at the end of the subject string. Without this option, a dollar also + matches immediately before a newline at the end of the string (but not + before any other newlines). The PCRE_DOLLAR_ENDONLY option is ignored + if PCRE_MULTILINE is set. There is no equivalent to this option in + Perl, and no way to set it within a pattern. + + PCRE_DOTALL + + If this bit is set, a dot metacharater in the pattern matches all char- + acters, including those that indicate newline. Without it, a dot does + not match when the current position is at a newline. This option is + equivalent to Perl's /s option, and it can be changed within a pattern + by a (?s) option setting. A negative class such as [^a] always matches + newlines, independent of the setting of this option. + + PCRE_DUPNAMES + + If this bit is set, names used to identify capturing subpatterns need + not be unique. This can be helpful for certain types of pattern when it + is known that only one instance of the named subpattern can ever be + matched. There are more details of named subpatterns below; see also + the pcrepattern documentation. + + PCRE_EXTENDED + + If this bit is set, whitespace data characters in the pattern are + totally ignored except when escaped or inside a character class. White- + space does not include the VT character (code 11). In addition, charac- + ters between an unescaped # outside a character class and the next new- + line, inclusive, are also ignored. This is equivalent to Perl's /x + option, and it can be changed within a pattern by a (?x) option set- + ting. + + This option makes it possible to include comments inside complicated + patterns. Note, however, that this applies only to data characters. + Whitespace characters may never appear within special character + sequences in a pattern, for example within the sequence (?( which + introduces a conditional subpattern. + + PCRE_EXTRA + + This option was invented in order to turn on additional functionality + of PCRE that is incompatible with Perl, but it is currently of very + little use. When set, any backslash in a pattern that is followed by a + letter that has no special meaning causes an error, thus reserving + these combinations for future expansion. By default, as in Perl, a + backslash followed by a letter with no special meaning is treated as a + literal. (Perl can, however, be persuaded to give a warning for this.) + There are at present no other features controlled by this option. It + can also be set by a (?X) option setting within a pattern. + + PCRE_FIRSTLINE + + If this option is set, an unanchored pattern is required to match + before or at the first newline in the subject string, though the + matched text may continue over the newline. + + PCRE_MULTILINE + + By default, PCRE treats the subject string as consisting of a single + line of characters (even if it actually contains newlines). The "start + of line" metacharacter (^) matches only at the start of the string, + while the "end of line" metacharacter ($) matches only at the end of + the string, or before a terminating newline (unless PCRE_DOLLAR_ENDONLY + is set). This is the same as Perl. + + When PCRE_MULTILINE it is set, the "start of line" and "end of line" + constructs match immediately following or immediately before internal + newlines in the subject string, respectively, as well as at the very + start and end. This is equivalent to Perl's /m option, and it can be + changed within a pattern by a (?m) option setting. If there are no new- + lines in a subject string, or no occurrences of ^ or $ in a pattern, + setting PCRE_MULTILINE has no effect. + + PCRE_NEWLINE_CR + PCRE_NEWLINE_LF + PCRE_NEWLINE_CRLF + + These options override the default newline definition that was chosen + when PCRE was built. Setting the first or the second specifies that a + newline is indicated by a single character (CR or LF, respectively). + Setting both of them specifies that a newline is indicated by the two- + character CRLF sequence. For convenience, PCRE_NEWLINE_CRLF is defined + to contain both bits. The only time that a line break is relevant when + compiling a pattern is if PCRE_EXTENDED is set, and an unescaped # out- + side a character class is encountered. This indicates a comment that + lasts until after the next newline. + + The newline option set at compile time becomes the default that is used + for pcre_exec() and pcre_dfa_exec(), but it can be overridden. + + PCRE_NO_AUTO_CAPTURE + + If this option is set, it disables the use of numbered capturing paren- + theses in the pattern. Any opening parenthesis that is not followed by + ? behaves as if it were followed by ?: but named parentheses can still + be used for capturing (and they acquire numbers in the usual way). + There is no equivalent of this option in Perl. + + PCRE_UNGREEDY + + This option inverts the "greediness" of the quantifiers so that they + are not greedy by default, but become greedy if followed by "?". It is + not compatible with Perl. It can also be set by a (?U) option setting + within the pattern. + + PCRE_UTF8 + + This option causes PCRE to regard both the pattern and the subject as + strings of UTF-8 characters instead of single-byte character strings. + However, it is available only when PCRE is built to include UTF-8 sup- + port. If not, the use of this option provokes an error. Details of how + this option changes the behaviour of PCRE are given in the section on + UTF-8 support in the main pcre page. + + PCRE_NO_UTF8_CHECK + + When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is + automatically checked. If an invalid UTF-8 sequence of bytes is found, + pcre_compile() returns an error. If you already know that your pattern + is valid, and you want to skip this check for performance reasons, you + can set the PCRE_NO_UTF8_CHECK option. When it is set, the effect of + passing an invalid UTF-8 string as a pattern is undefined. It may cause + your program to crash. Note that this option can also be passed to + pcre_exec() and pcre_dfa_exec(), to suppress the UTF-8 validity check- + ing of subject strings. + + +COMPILATION ERROR CODES + + The following table lists the error codes than may be returned by + pcre_compile2(), along with the error messages that may be returned by + both compiling functions. + + 0 no error + 1 \ at end of pattern + 2 \c at end of pattern + 3 unrecognized character follows \ + 4 numbers out of order in {} quantifier + 5 number too big in {} quantifier + 6 missing terminating ] for character class + 7 invalid escape sequence in character class + 8 range out of order in character class + 9 nothing to repeat + 10 operand of unlimited repeat could match the empty string + 11 internal error: unexpected repeat + 12 unrecognized character after (? + 13 POSIX named classes are supported only within a class + 14 missing ) + 15 reference to non-existent subpattern + 16 erroffset passed as NULL + 17 unknown option bit(s) set + 18 missing ) after comment + 19 parentheses nested too deeply + 20 regular expression too large + 21 failed to get memory + 22 unmatched parentheses + 23 internal error: code overflow + 24 unrecognized character after (?< + 25 lookbehind assertion is not fixed length + 26 malformed number or name after (?( + 27 conditional group contains more than two branches + 28 assertion expected after (?( + 29 (?R or (?digits must be followed by ) + 30 unknown POSIX class name + 31 POSIX collating elements are not supported + 32 this version of PCRE is not compiled with PCRE_UTF8 support + 33 spare error + 34 character value in \x{...} sequence is too large + 35 invalid condition (?(0) + 36 \C not allowed in lookbehind assertion + 37 PCRE does not support \L, \l, \N, \U, or \u + 38 number after (?C is > 255 + 39 closing ) for (?C expected + 40 recursive call could loop indefinitely + 41 unrecognized character after (?P + 42 syntax error after (?P + 43 two named subpatterns have the same name + 44 invalid UTF-8 string + 45 support for \P, \p, and \X has not been compiled + 46 malformed \P or \p sequence + 47 unknown property name after \P or \p + 48 subpattern name is too long (maximum 32 characters) + 49 too many named subpatterns (maximum 10,000) + 50 repeated subpattern is too long + 51 octal value is greater than \377 (not in UTF-8 mode) + + +STUDYING A PATTERN + + pcre_extra *pcre_study(const pcre *code, int options + const char **errptr); + + If a compiled pattern is going to be used several times, it is worth + spending more time analyzing it in order to speed up the time taken for + matching. The function pcre_study() takes a pointer to a compiled pat- + tern as its first argument. If studying the pattern produces additional + information that will help speed up matching, pcre_study() returns a + pointer to a pcre_extra block, in which the study_data field points to + the results of the study. + + The returned value from pcre_study() can be passed directly to + pcre_exec(). However, a pcre_extra block also contains other fields + that can be set by the caller before the block is passed; these are + described below in the section on matching a pattern. + + If studying the pattern does not produce any additional information + pcre_study() returns NULL. In that circumstance, if the calling program + wants to pass any of the other fields to pcre_exec(), it must set up + its own pcre_extra block. + + The second argument of pcre_study() contains option bits. At present, + no options are defined, and this argument should always be zero. + + The third argument for pcre_study() is a pointer for an error message. + If studying succeeds (even if no data is returned), the variable it + points to is set to NULL. Otherwise it is set to point to a textual + error message. This is a static string that is part of the library. You + must not try to free it. You should test the error pointer for NULL + after calling pcre_study(), to be sure that it has run successfully. + + This is a typical call to pcre_study(): + + pcre_extra *pe; + pe = pcre_study( + re, /* result of pcre_compile() */ + 0, /* no options exist */ + &error); /* set to NULL or points to a message */ + + At present, studying a pattern is useful only for non-anchored patterns + that do not have a single fixed starting character. A bitmap of possi- + ble starting bytes is created. + + +LOCALE SUPPORT + + PCRE handles caseless matching, and determines whether characters are + letters digits, or whatever, by reference to a set of tables, indexed + by character value. When running in UTF-8 mode, this applies only to + characters with codes less than 128. Higher-valued codes never match + escapes such as \w or \d, but can be tested with \p if PCRE is built + with Unicode character property support. The use of locales with Uni- + code is discouraged. + + An internal set of tables is created in the default C locale when PCRE + is built. This is used when the final argument of pcre_compile() is + NULL, and is sufficient for many applications. An alternative set of + tables can, however, be supplied. These may be created in a different + locale from the default. As more and more applications change to using + Unicode, the need for this locale support is expected to die away. + + External tables are built by calling the pcre_maketables() function, + which has no arguments, in the relevant locale. The result can then be + passed to pcre_compile() or pcre_exec() as often as necessary. For + example, to build and use tables that are appropriate for the French + locale (where accented characters with values greater than 128 are + treated as letters), the following code could be used: + + setlocale(LC_CTYPE, "fr_FR"); + tables = pcre_maketables(); + re = pcre_compile(..., tables); + + When pcre_maketables() runs, the tables are built in memory that is + obtained via pcre_malloc. It is the caller's responsibility to ensure + that the memory containing the tables remains available for as long as + it is needed. + + The pointer that is passed to pcre_compile() is saved with the compiled + pattern, and the same tables are used via this pointer by pcre_study() + and normally also by pcre_exec(). Thus, by default, for any single pat- + tern, compilation, studying and matching all happen in the same locale, + but different patterns can be compiled in different locales. + + It is possible to pass a table pointer or NULL (indicating the use of + the internal tables) to pcre_exec(). Although not intended for this + purpose, this facility could be used to match a pattern in a different + locale from the one in which it was compiled. Passing table pointers at + run time is discussed below in the section on matching a pattern. + + +INFORMATION ABOUT A PATTERN + + int pcre_fullinfo(const pcre *code, const pcre_extra *extra, + int what, void *where); + + The pcre_fullinfo() function returns information about a compiled pat- + tern. It replaces the obsolete pcre_info() function, which is neverthe- + less retained for backwards compability (and is documented below). + + The first argument for pcre_fullinfo() is a pointer to the compiled + pattern. The second argument is the result of pcre_study(), or NULL if + the pattern was not studied. The third argument specifies which piece + of information is required, and the fourth argument is a pointer to a + variable to receive the data. The yield of the function is zero for + success, or one of the following negative numbers: + + PCRE_ERROR_NULL the argument code was NULL + the argument where was NULL + PCRE_ERROR_BADMAGIC the "magic number" was not found + PCRE_ERROR_BADOPTION the value of what was invalid + + The "magic number" is placed at the start of each compiled pattern as + an simple check against passing an arbitrary memory pointer. Here is a + typical call of pcre_fullinfo(), to obtain the length of the compiled + pattern: + + int rc; + size_t length; + rc = pcre_fullinfo( + re, /* result of pcre_compile() */ + pe, /* result of pcre_study(), or NULL */ + PCRE_INFO_SIZE, /* what is required */ + &length); /* where to put the data */ + + The possible values for the third argument are defined in pcre.h, and + are as follows: + + PCRE_INFO_BACKREFMAX + + Return the number of the highest back reference in the pattern. The + fourth argument should point to an int variable. Zero is returned if + there are no back references. + + PCRE_INFO_CAPTURECOUNT + + Return the number of capturing subpatterns in the pattern. The fourth + argument should point to an int variable. + + PCRE_INFO_DEFAULT_TABLES + + Return a pointer to the internal default character tables within PCRE. + The fourth argument should point to an unsigned char * variable. This + information call is provided for internal use by the pcre_study() func- + tion. External callers can cause PCRE to use its internal tables by + passing a NULL table pointer. + + PCRE_INFO_FIRSTBYTE + + Return information about the first byte of any matched string, for a + non-anchored pattern. The fourth argument should point to an int vari- + able. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name + is still recognized for backwards compatibility.) + + If there is a fixed first byte, for example, from a pattern such as + (cat|cow|coyote). Otherwise, if either + + (a) the pattern was compiled with the PCRE_MULTILINE option, and every + branch starts with "^", or + + (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not + set (if it were set, the pattern would be anchored), + + -1 is returned, indicating that the pattern matches only at the start + of a subject string or after any newline within the string. Otherwise + -2 is returned. For anchored patterns, -2 is returned. + + PCRE_INFO_FIRSTTABLE + + If the pattern was studied, and this resulted in the construction of a + 256-bit table indicating a fixed set of bytes for the first byte in any + matching string, a pointer to the table is returned. Otherwise NULL is + returned. The fourth argument should point to an unsigned char * vari- + able. + + PCRE_INFO_LASTLITERAL + + Return the value of the rightmost literal byte that must exist in any + matched string, other than at its start, if such a byte has been + recorded. The fourth argument should point to an int variable. If there + is no such byte, -1 is returned. For anchored patterns, a last literal + byte is recorded only if it follows something of variable length. For + example, for the pattern /^a\d+z\d+/ the returned value is "z", but for + /^a\dz\d/ the returned value is -1. + + PCRE_INFO_NAMECOUNT + PCRE_INFO_NAMEENTRYSIZE + PCRE_INFO_NAMETABLE + + PCRE supports the use of named as well as numbered capturing parenthe- + ses. The names are just an additional way of identifying the parenthe- + ses, which still acquire numbers. Several convenience functions such as + pcre_get_named_substring() are provided for extracting captured sub- + strings by name. It is also possible to extract the data directly, by + first converting the name to a number in order to access the correct + pointers in the output vector (described with pcre_exec() below). To do + the conversion, you need to use the name-to-number map, which is + described by these three values. + + The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT + gives the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size + of each entry; both of these return an int value. The entry size + depends on the length of the longest name. PCRE_INFO_NAMETABLE returns + a pointer to the first entry of the table (a pointer to char). The + first two bytes of each entry are the number of the capturing parenthe- + sis, most significant byte first. The rest of the entry is the corre- + sponding name, zero terminated. The names are in alphabetical order. + When PCRE_DUPNAMES is set, duplicate names are in order of their paren- + theses numbers. For example, consider the following pattern (assume + PCRE_EXTENDED is set, so white space - including newlines - is + ignored): + + (?P (?P(\d\d)?\d\d) - + (?P\d\d) - (?P\d\d) ) + + There are four named subpatterns, so the table has four entries, and + each entry in the table is eight bytes long. The table is as follows, + with non-printing bytes shows in hexadecimal, and undefined bytes shown + as ??: + + 00 01 d a t e 00 ?? + 00 05 d a y 00 ?? ?? + 00 04 m o n t h 00 + 00 02 y e a r 00 ?? + + When writing code to extract data from named subpatterns using the + name-to-number map, remember that the length of the entries is likely + to be different for each compiled pattern. + + PCRE_INFO_OPTIONS + + Return a copy of the options with which the pattern was compiled. The + fourth argument should point to an unsigned long int variable. These + option bits are those specified in the call to pcre_compile(), modified + by any top-level option settings within the pattern itself. + + A pattern is automatically anchored by PCRE if all of its top-level + alternatives begin with one of the following: + + ^ unless PCRE_MULTILINE is set + \A always + \G always + .* if PCRE_DOTALL is set and there are no back + references to the subpattern in which .* appears + + For such patterns, the PCRE_ANCHORED bit is set in the options returned + by pcre_fullinfo(). + + PCRE_INFO_SIZE + + Return the size of the compiled pattern, that is, the value that was + passed as the argument to pcre_malloc() when PCRE was getting memory in + which to place the compiled data. The fourth argument should point to a + size_t variable. + + PCRE_INFO_STUDYSIZE + + Return the size of the data block pointed to by the study_data field in + a pcre_extra block. That is, it is the value that was passed to + pcre_malloc() when PCRE was getting memory into which to place the data + created by pcre_study(). The fourth argument should point to a size_t + variable. + + +OBSOLETE INFO FUNCTION + + int pcre_info(const pcre *code, int *optptr, int *firstcharptr); + + The pcre_info() function is now obsolete because its interface is too + restrictive to return all the available data about a compiled pattern. + New programs should use pcre_fullinfo() instead. The yield of + pcre_info() is the number of capturing subpatterns, or one of the fol- + lowing negative numbers: + + PCRE_ERROR_NULL the argument code was NULL + PCRE_ERROR_BADMAGIC the "magic number" was not found + + If the optptr argument is not NULL, a copy of the options with which + the pattern was compiled is placed in the integer it points to (see + PCRE_INFO_OPTIONS above). + + If the pattern is not anchored and the firstcharptr argument is not + NULL, it is used to pass back information about the first character of + any matched string (see PCRE_INFO_FIRSTBYTE above). + + +REFERENCE COUNTS + + int pcre_refcount(pcre *code, int adjust); + + The pcre_refcount() function is used to maintain a reference count in + the data block that contains a compiled pattern. It is provided for the + benefit of applications that operate in an object-oriented manner, + where different parts of the application may be using the same compiled + pattern, but you want to free the block when they are all done. + + When a pattern is compiled, the reference count field is initialized to + zero. It is changed only by calling this function, whose action is to + add the adjust value (which may be positive or negative) to it. The + yield of the function is the new value. However, the value of the count + is constrained to lie between 0 and 65535, inclusive. If the new value + is outside these limits, it is forced to the appropriate limit value. + + Except when it is zero, the reference count is not correctly preserved + if a pattern is compiled on one host and then transferred to a host + whose byte-order is different. (This seems a highly unlikely scenario.) + + +MATCHING A PATTERN: THE TRADITIONAL FUNCTION + + int pcre_exec(const pcre *code, const pcre_extra *extra, + const char *subject, int length, int startoffset, + int options, int *ovector, int ovecsize); + + The function pcre_exec() is called to match a subject string against a + compiled pattern, which is passed in the code argument. If the pattern + has been studied, the result of the study should be passed in the extra + argument. This function is the main matching facility of the library, + and it operates in a Perl-like manner. For specialist use there is also + an alternative matching function, which is described below in the sec- + tion about the pcre_dfa_exec() function. + + In most applications, the pattern will have been compiled (and option- + ally studied) in the same process that calls pcre_exec(). However, it + is possible to save compiled patterns and study data, and then use them + later in different processes, possibly even on different hosts. For a + discussion about this, see the pcreprecompile documentation. + + Here is an example of a simple call to pcre_exec(): + + int rc; + int ovector[30]; + rc = pcre_exec( + re, /* result of pcre_compile() */ + NULL, /* we didn't study the pattern */ + "some string", /* the subject string */ + 11, /* the length of the subject string */ + 0, /* start at offset 0 in the subject */ + 0, /* default options */ + ovector, /* vector of integers for substring information */ + 30); /* number of elements (NOT size in bytes) */ + + Extra data for pcre_exec() + + If the extra argument is not NULL, it must point to a pcre_extra data + block. The pcre_study() function returns such a block (when it doesn't + return NULL), but you can also create one for yourself, and pass addi- + tional information in it. The pcre_extra block contains the following + fields (not necessarily in this order): + + unsigned long int flags; + void *study_data; + unsigned long int match_limit; + unsigned long int match_limit_recursion; + void *callout_data; + const unsigned char *tables; + + The flags field is a bitmap that specifies which of the other fields + are set. The flag bits are: + + PCRE_EXTRA_STUDY_DATA + PCRE_EXTRA_MATCH_LIMIT + PCRE_EXTRA_MATCH_LIMIT_RECURSION + PCRE_EXTRA_CALLOUT_DATA + PCRE_EXTRA_TABLES + + Other flag bits should be set to zero. The study_data field is set in + the pcre_extra block that is returned by pcre_study(), together with + the appropriate flag bit. You should not set this yourself, but you may + add to the block by setting the other fields and their corresponding + flag bits. + + The match_limit field provides a means of preventing PCRE from using up + a vast amount of resources when running patterns that are not going to + match, but which have a very large number of possibilities in their + search trees. The classic example is the use of nested unlimited + repeats. + + Internally, PCRE uses a function called match() which it calls repeat- + edly (sometimes recursively). The limit set by match_limit is imposed + on the number of times this function is called during a match, which + has the effect of limiting the amount of backtracking that can take + place. For patterns that are not anchored, the count restarts from zero + for each position in the subject string. + + The default value for the limit can be set when PCRE is built; the + default default is 10 million, which handles all but the most extreme + cases. You can override the default by suppling pcre_exec() with a + pcre_extra block in which match_limit is set, and + PCRE_EXTRA_MATCH_LIMIT is set in the flags field. If the limit is + exceeded, pcre_exec() returns PCRE_ERROR_MATCHLIMIT. + + The match_limit_recursion field is similar to match_limit, but instead + of limiting the total number of times that match() is called, it limits + the depth of recursion. The recursion depth is a smaller number than + the total number of calls, because not all calls to match() are recur- + sive. This limit is of use only if it is set smaller than match_limit. + + Limiting the recursion depth limits the amount of stack that can be + used, or, when PCRE has been compiled to use memory on the heap instead + of the stack, the amount of heap memory that can be used. + + The default value for match_limit_recursion can be set when PCRE is + built; the default default is the same value as the default for + match_limit. You can override the default by suppling pcre_exec() with + a pcre_extra block in which match_limit_recursion is set, and + PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the flags field. If the + limit is exceeded, pcre_exec() returns PCRE_ERROR_RECURSIONLIMIT. + + The pcre_callout field is used in conjunction with the "callout" fea- + ture, which is described in the pcrecallout documentation. + + The tables field is used to pass a character tables pointer to + pcre_exec(); this overrides the value that is stored with the compiled + pattern. A non-NULL value is stored with the compiled pattern only if + custom tables were supplied to pcre_compile() via its tableptr argu- + ment. If NULL is passed to pcre_exec() using this mechanism, it forces + PCRE's internal tables to be used. This facility is helpful when re- + using patterns that have been saved after compiling with an external + set of tables, because the external tables might be at a different + address when pcre_exec() is called. See the pcreprecompile documenta- + tion for a discussion of saving compiled patterns for later use. + + Option bits for pcre_exec() + + The unused bits of the options argument for pcre_exec() must be zero. + The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, + PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and + PCRE_PARTIAL. + + PCRE_ANCHORED + + The PCRE_ANCHORED option limits pcre_exec() to matching at the first + matching position. If a pattern was compiled with PCRE_ANCHORED, or + turned out to be anchored by virtue of its contents, it cannot be made + unachored at matching time. + + PCRE_NEWLINE_CR + PCRE_NEWLINE_LF + PCRE_NEWLINE_CRLF + + These options override the newline definition that was chosen or + defaulted when the pattern was compiled. For details, see the descrip- + tion pcre_compile() above. During matching, the newline choice affects + the behaviour of the dot, circumflex, and dollar metacharacters. + + PCRE_NOTBOL + + This option specifies that first character of the subject string is not + the beginning of a line, so the circumflex metacharacter should not + match before it. Setting this without PCRE_MULTILINE (at compile time) + causes circumflex never to match. This option affects only the behav- + iour of the circumflex metacharacter. It does not affect \A. + + PCRE_NOTEOL + + This option specifies that the end of the subject string is not the end + of a line, so the dollar metacharacter should not match it nor (except + in multiline mode) a newline immediately before it. Setting this with- + out PCRE_MULTILINE (at compile time) causes dollar never to match. This + option affects only the behaviour of the dollar metacharacter. It does + not affect \Z or \z. + + PCRE_NOTEMPTY + + An empty string is not considered to be a valid match if this option is + set. If there are alternatives in the pattern, they are tried. If all + the alternatives match the empty string, the entire match fails. For + example, if the pattern + + a?b? + + is applied to a string not beginning with "a" or "b", it matches the + empty string at the start of the subject. With PCRE_NOTEMPTY set, this + match is not valid, so PCRE searches further into the string for occur- + rences of "a" or "b". + + Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a spe- + cial case of a pattern match of the empty string within its split() + function, and when using the /g modifier. It is possible to emulate + Perl's behaviour after matching a null string by first trying the match + again at the same offset with PCRE_NOTEMPTY and PCRE_ANCHORED, and then + if that fails by advancing the starting offset (see below) and trying + an ordinary match again. There is some code that demonstrates how to do + this in the pcredemo.c sample program. + + PCRE_NO_UTF8_CHECK + + When PCRE_UTF8 is set at compile time, the validity of the subject as a + UTF-8 string is automatically checked when pcre_exec() is subsequently + called. The value of startoffset is also checked to ensure that it + points to the start of a UTF-8 character. If an invalid UTF-8 sequence + of bytes is found, pcre_exec() returns the error PCRE_ERROR_BADUTF8. If + startoffset contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is + returned. + + If you already know that your subject is valid, and you want to skip + these checks for performance reasons, you can set the + PCRE_NO_UTF8_CHECK option when calling pcre_exec(). You might want to + do this for the second and subsequent calls to pcre_exec() if you are + making repeated calls to find all the matches in a single subject + string. However, you should be sure that the value of startoffset + points to the start of a UTF-8 character. When PCRE_NO_UTF8_CHECK is + set, the effect of passing an invalid UTF-8 string as a subject, or a + value of startoffset that does not point to the start of a UTF-8 char- + acter, is undefined. Your program may crash. + + PCRE_PARTIAL + + This option turns on the partial matching feature. If the subject + string fails to match the pattern, but at some point during the match- + ing process the end of the subject was reached (that is, the subject + partially matches the pattern and the failure to match occurred only + because there were not enough subject characters), pcre_exec() returns + PCRE_ERROR_PARTIAL instead of PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is + used, there are restrictions on what may appear in the pattern. These + are discussed in the pcrepartial documentation. + + The string to be matched by pcre_exec() + + The subject string is passed to pcre_exec() as a pointer in subject, a + length in length, and a starting byte offset in startoffset. In UTF-8 + mode, the byte offset must point to the start of a UTF-8 character. + Unlike the pattern string, the subject may contain binary zero bytes. + When the starting offset is zero, the search for a match starts at the + beginning of the subject, and this is by far the most common case. + + A non-zero starting offset is useful when searching for another match + in the same subject by calling pcre_exec() again after a previous suc- + cess. Setting startoffset differs from just passing over a shortened + string and setting PCRE_NOTBOL in the case of a pattern that begins + with any kind of lookbehind. For example, consider the pattern + + \Biss\B + + which finds occurrences of "iss" in the middle of words. (\B matches + only if the current position in the subject is not a word boundary.) + When applied to the string "Mississipi" the first call to pcre_exec() + finds the first occurrence. If pcre_exec() is called again with just + the remainder of the subject, namely "issipi", it does not match, + because \B is always false at the start of the subject, which is deemed + to be a word boundary. However, if pcre_exec() is passed the entire + string again, but with startoffset set to 4, it finds the second occur- + rence of "iss" because it is able to look behind the starting point to + discover that it is preceded by a letter. + + If a non-zero starting offset is passed when the pattern is anchored, + one attempt to match at the given offset is made. This can only succeed + if the pattern does not require the match to be at the start of the + subject. + + How pcre_exec() returns captured substrings + + In general, a pattern matches a certain portion of the subject, and in + addition, further substrings from the subject may be picked out by + parts of the pattern. Following the usage in Jeffrey Friedl's book, + this is called "capturing" in what follows, and the phrase "capturing + subpattern" is used for a fragment of a pattern that picks out a sub- + string. PCRE supports several other kinds of parenthesized subpattern + that do not cause substrings to be captured. + + Captured substrings are returned to the caller via a vector of integer + offsets whose address is passed in ovector. The number of elements in + the vector is passed in ovecsize, which must be a non-negative number. + Note: this argument is NOT the size of ovector in bytes. + + The first two-thirds of the vector is used to pass back captured sub- + strings, each substring using a pair of integers. The remaining third + of the vector is used as workspace by pcre_exec() while matching cap- + turing subpatterns, and is not available for passing back information. + The length passed in ovecsize should always be a multiple of three. If + it is not, it is rounded down. + + When a match is successful, information about captured substrings is + returned in pairs of integers, starting at the beginning of ovector, + and continuing up to two-thirds of its length at the most. The first + element of a pair is set to the offset of the first character in a sub- + string, and the second is set to the offset of the first character + after the end of a substring. The first pair, ovector[0] and ovec- + tor[1], identify the portion of the subject string matched by the + entire pattern. The next pair is used for the first capturing subpat- + tern, and so on. The value returned by pcre_exec() is one more than the + highest numbered pair that has been set. For example, if two substrings + have been captured, the returned value is 3. If there are no capturing + subpatterns, the return value from a successful match is 1, indicating + that just the first pair of offsets has been set. + + If a capturing subpattern is matched repeatedly, it is the last portion + of the string that it matched that is returned. + + If the vector is too small to hold all the captured substring offsets, + it is used as far as possible (up to two-thirds of its length), and the + function returns a value of zero. In particular, if the substring off- + sets are not of interest, pcre_exec() may be called with ovector passed + as NULL and ovecsize as zero. However, if the pattern contains back + references and the ovector is not big enough to remember the related + substrings, PCRE has to get additional memory for use during matching. + Thus it is usually advisable to supply an ovector. + + The pcre_info() function can be used to find out how many capturing + subpatterns there are in a compiled pattern. The smallest size for + ovector that will allow for n captured substrings, in addition to the + offsets of the substring matched by the whole pattern, is (n+1)*3. + + It is possible for capturing subpattern number n+1 to match some part + of the subject when subpattern n has not been used at all. For example, + if the string "abc" is matched against the pattern (a|(z))(bc) the + return from the function is 4, and subpatterns 1 and 3 are matched, but + 2 is not. When this happens, both values in the offset pairs corre- + sponding to unused subpatterns are set to -1. + + Offset values that correspond to unused subpatterns at the end of the + expression are also set to -1. For example, if the string "abc" is + matched against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not + matched. The return from the function is 2, because the highest used + capturing subpattern number is 1. However, you can refer to the offsets + for the second and third capturing subpatterns if you wish (assuming + the vector is large enough, of course). + + Some convenience functions are provided for extracting the captured + substrings as separate strings. These are described below. + + Error return values from pcre_exec() + + If pcre_exec() fails, it returns a negative number. The following are + defined in the header file: + + PCRE_ERROR_NOMATCH (-1) + + The subject string did not match the pattern. + + PCRE_ERROR_NULL (-2) + + Either code or subject was passed as NULL, or ovector was NULL and + ovecsize was not zero. + + PCRE_ERROR_BADOPTION (-3) + + An unrecognized bit was set in the options argument. + + PCRE_ERROR_BADMAGIC (-4) + + PCRE stores a 4-byte "magic number" at the start of the compiled code, + to catch the case when it is passed a junk pointer and to detect when a + pattern that was compiled in an environment of one endianness is run in + an environment with the other endianness. This is the error that PCRE + gives when the magic number is not present. + + PCRE_ERROR_UNKNOWN_NODE (-5) + + While running the pattern match, an unknown item was encountered in the + compiled pattern. This error could be caused by a bug in PCRE or by + overwriting of the compiled pattern. + + PCRE_ERROR_NOMEMORY (-6) + + If a pattern contains back references, but the ovector that is passed + to pcre_exec() is not big enough to remember the referenced substrings, + PCRE gets a block of memory at the start of matching to use for this + purpose. If the call via pcre_malloc() fails, this error is given. The + memory is automatically freed at the end of matching. + + PCRE_ERROR_NOSUBSTRING (-7) + + This error is used by the pcre_copy_substring(), pcre_get_substring(), + and pcre_get_substring_list() functions (see below). It is never + returned by pcre_exec(). + + PCRE_ERROR_MATCHLIMIT (-8) + + The backtracking limit, as specified by the match_limit field in a + pcre_extra structure (or defaulted) was reached. See the description + above. + + PCRE_ERROR_RECURSIONLIMIT (-21) + + The internal recursion limit, as specified by the match_limit_recursion + field in a pcre_extra structure (or defaulted) was reached. See the + description above. + + PCRE_ERROR_CALLOUT (-9) + + This error is never generated by pcre_exec() itself. It is provided for + use by callout functions that want to yield a distinctive error code. + See the pcrecallout documentation for details. + + PCRE_ERROR_BADUTF8 (-10) + + A string that contains an invalid UTF-8 byte sequence was passed as a + subject. + + PCRE_ERROR_BADUTF8_OFFSET (-11) + + The UTF-8 byte sequence that was passed as a subject was valid, but the + value of startoffset did not point to the beginning of a UTF-8 charac- + ter. + + PCRE_ERROR_PARTIAL (-12) + + The subject string did not match, but it did match partially. See the + pcrepartial documentation for details of partial matching. + + PCRE_ERROR_BADPARTIAL (-13) + + The PCRE_PARTIAL option was used with a compiled pattern containing + items that are not supported for partial matching. See the pcrepartial + documentation for details of partial matching. + + PCRE_ERROR_INTERNAL (-14) + + An unexpected internal error has occurred. This error could be caused + by a bug in PCRE or by overwriting of the compiled pattern. + + PCRE_ERROR_BADCOUNT (-15) + + This error is given if the value of the ovecsize argument is negative. + + +EXTRACTING CAPTURED SUBSTRINGS BY NUMBER + + int pcre_copy_substring(const char *subject, int *ovector, + int stringcount, int stringnumber, char *buffer, + int buffersize); + + int pcre_get_substring(const char *subject, int *ovector, + int stringcount, int stringnumber, + const char **stringptr); + + int pcre_get_substring_list(const char *subject, + int *ovector, int stringcount, const char ***listptr); + + Captured substrings can be accessed directly by using the offsets + returned by pcre_exec() in ovector. For convenience, the functions + pcre_copy_substring(), pcre_get_substring(), and pcre_get_sub- + string_list() are provided for extracting captured substrings as new, + separate, zero-terminated strings. These functions identify substrings + by number. The next section describes functions for extracting named + substrings. + + A substring that contains a binary zero is correctly extracted and has + a further zero added on the end, but the result is not, of course, a C + string. However, you can process such a string by referring to the + length that is returned by pcre_copy_substring() and pcre_get_sub- + string(). Unfortunately, the interface to pcre_get_substring_list() is + not adequate for handling strings containing binary zeros, because the + end of the final string is not independently indicated. + + The first three arguments are the same for all three of these func- + tions: subject is the subject string that has just been successfully + matched, ovector is a pointer to the vector of integer offsets that was + passed to pcre_exec(), and stringcount is the number of substrings that + were captured by the match, including the substring that matched the + entire regular expression. This is the value returned by pcre_exec() if + it is greater than zero. If pcre_exec() returned zero, indicating that + it ran out of space in ovector, the value passed as stringcount should + be the number of elements in the vector divided by three. + + The functions pcre_copy_substring() and pcre_get_substring() extract a + single substring, whose number is given as stringnumber. A value of + zero extracts the substring that matched the entire pattern, whereas + higher values extract the captured substrings. For pcre_copy_sub- + string(), the string is placed in buffer, whose length is given by + buffersize, while for pcre_get_substring() a new block of memory is + obtained via pcre_malloc, and its address is returned via stringptr. + The yield of the function is the length of the string, not including + the terminating zero, or one of + + PCRE_ERROR_NOMEMORY (-6) + + The buffer was too small for pcre_copy_substring(), or the attempt to + get memory failed for pcre_get_substring(). + + PCRE_ERROR_NOSUBSTRING (-7) + + There is no substring whose number is stringnumber. + + The pcre_get_substring_list() function extracts all available sub- + strings and builds a list of pointers to them. All this is done in a + single block of memory that is obtained via pcre_malloc. The address of + the memory block is returned via listptr, which is also the start of + the list of string pointers. The end of the list is marked by a NULL + pointer. The yield of the function is zero if all went well, or + + PCRE_ERROR_NOMEMORY (-6) + + if the attempt to get the memory block failed. + + When any of these functions encounter a substring that is unset, which + can happen when capturing subpattern number n+1 matches some part of + the subject, but subpattern n has not been used at all, they return an + empty string. This can be distinguished from a genuine zero-length sub- + string by inspecting the appropriate offset in ovector, which is nega- + tive for unset substrings. + + The two convenience functions pcre_free_substring() and pcre_free_sub- + string_list() can be used to free the memory returned by a previous + call of pcre_get_substring() or pcre_get_substring_list(), respec- + tively. They do nothing more than call the function pointed to by + pcre_free, which of course could be called directly from a C program. + However, PCRE is used in some situations where it is linked via a spe- + cial interface to another programming language that cannot use + pcre_free directly; it is for these cases that the functions are pro- + vided. + + +EXTRACTING CAPTURED SUBSTRINGS BY NAME + + int pcre_get_stringnumber(const pcre *code, + const char *name); + + int pcre_copy_named_substring(const pcre *code, + const char *subject, int *ovector, + int stringcount, const char *stringname, + char *buffer, int buffersize); + + int pcre_get_named_substring(const pcre *code, + const char *subject, int *ovector, + int stringcount, const char *stringname, + const char **stringptr); + + To extract a substring by name, you first have to find associated num- + ber. For example, for this pattern + + (a+)b(?P\d+)... + + the number of the subpattern called "xxx" is 2. If the name is known to + be unique (PCRE_DUPNAMES was not set), you can find the number from the + name by calling pcre_get_stringnumber(). The first argument is the com- + piled pattern, and the second is the name. The yield of the function is + the subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no + subpattern of that name. + + Given the number, you can extract the substring directly, or use one of + the functions described in the previous section. For convenience, there + are also two functions that do the whole job. + + Most of the arguments of pcre_copy_named_substring() and + pcre_get_named_substring() are the same as those for the similarly + named functions that extract by number. As these are described in the + previous section, they are not re-described here. There are just two + differences: + + First, instead of a substring number, a substring name is given. Sec- + ond, there is an extra argument, given at the start, which is a pointer + to the compiled pattern. This is needed in order to gain access to the + name-to-number translation table. + + These functions call pcre_get_stringnumber(), and if it succeeds, they + then call pcre_copy_substring() or pcre_get_substring(), as appropri- + ate. + + +DUPLICATE SUBPATTERN NAMES + + int pcre_get_stringtable_entries(const pcre *code, + const char *name, char **first, char **last); + + When a pattern is compiled with the PCRE_DUPNAMES option, names for + subpatterns are not required to be unique. Normally, patterns with + duplicate names are such that in any one match, only one of the named + subpatterns participates. An example is shown in the pcrepattern docu- + mentation. When duplicates are present, pcre_copy_named_substring() and + pcre_get_named_substring() return the first substring corresponding to + the given name that is set. If none are set, an empty string is + returned. The pcre_get_stringnumber() function returns one of the num- + bers that are associated with the name, but it is not defined which it + is. + + If you want to get full details of all captured substrings for a given + name, you must use the pcre_get_stringtable_entries() function. The + first argument is the compiled pattern, and the second is the name. The + third and fourth are pointers to variables which are updated by the + function. After it has run, they point to the first and last entries in + the name-to-number table for the given name. The function itself + returns the length of each entry, or PCRE_ERROR_NOSUBSTRING if there + are none. The format of the table is described above in the section + entitled Information about a pattern. Given all the relevant entries + for the name, you can extract each of their numbers, and hence the cap- + tured data, if any. + + +FINDING ALL POSSIBLE MATCHES + + The traditional matching function uses a similar algorithm to Perl, + which stops when it finds the first match, starting at a given point in + the subject. If you want to find all possible matches, or the longest + possible match, consider using the alternative matching function (see + below) instead. If you cannot use the alternative function, but still + need to find all possible matches, you can kludge it up by making use + of the callout facility, which is described in the pcrecallout documen- + tation. + + What you have to do is to insert a callout right at the end of the pat- + tern. When your callout function is called, extract and save the cur- + rent matched substring. Then return 1, which forces pcre_exec() to + backtrack and try other alternatives. Ultimately, when it runs out of + matches, pcre_exec() will yield PCRE_ERROR_NOMATCH. + + +MATCHING A PATTERN: THE ALTERNATIVE FUNCTION + + int pcre_dfa_exec(const pcre *code, const pcre_extra *extra, + const char *subject, int length, int startoffset, + int options, int *ovector, int ovecsize, + int *workspace, int wscount); + + The function pcre_dfa_exec() is called to match a subject string + against a compiled pattern, using a "DFA" matching algorithm. This has + different characteristics to the normal algorithm, and is not compati- + ble with Perl. Some of the features of PCRE patterns are not supported. + Nevertheless, there are times when this kind of matching can be useful. + For a discussion of the two matching algorithms, see the pcrematching + documentation. + + The arguments for the pcre_dfa_exec() function are the same as for + pcre_exec(), plus two extras. The ovector argument is used in a differ- + ent way, and this is described below. The other common arguments are + used in the same way as for pcre_exec(), so their description is not + repeated here. + + The two additional arguments provide workspace for the function. The + workspace vector should contain at least 20 elements. It is used for + keeping track of multiple paths through the pattern tree. More + workspace will be needed for patterns and subjects where there are a + lot of potential matches. + + Here is an example of a simple call to pcre_dfa_exec(): + + int rc; + int ovector[10]; + int wspace[20]; + rc = pcre_dfa_exec( + re, /* result of pcre_compile() */ + NULL, /* we didn't study the pattern */ + "some string", /* the subject string */ + 11, /* the length of the subject string */ + 0, /* start at offset 0 in the subject */ + 0, /* default options */ + ovector, /* vector of integers for substring information */ + 10, /* number of elements (NOT size in bytes) */ + wspace, /* working space vector */ + 20); /* number of elements (NOT size in bytes) */ + + Option bits for pcre_dfa_exec() + + The unused bits of the options argument for pcre_dfa_exec() must be + zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEW- + LINE_xxx, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, + PCRE_PARTIAL, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last + three of these are the same as for pcre_exec(), so their description is + not repeated here. + + PCRE_PARTIAL + + This has the same general effect as it does for pcre_exec(), but the + details are slightly different. When PCRE_PARTIAL is set for + pcre_dfa_exec(), the return code PCRE_ERROR_NOMATCH is converted into + PCRE_ERROR_PARTIAL if the end of the subject is reached, there have + been no complete matches, but there is still at least one matching pos- + sibility. The portion of the string that provided the partial match is + set as the first matching string. + + PCRE_DFA_SHORTEST + + Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to + stop as soon as it has found one match. Because of the way the DFA + algorithm works, this is necessarily the shortest possible match at the + first possible matching point in the subject string. + + PCRE_DFA_RESTART + + When pcre_dfa_exec() is called with the PCRE_PARTIAL option, and + returns a partial match, it is possible to call it again, with addi- + tional subject characters, and have it continue with the same match. + The PCRE_DFA_RESTART option requests this action; when it is set, the + workspace and wscount options must reference the same vector as before + because data about the match so far is left in them after a partial + match. There is more discussion of this facility in the pcrepartial + documentation. + + Successful returns from pcre_dfa_exec() + + When pcre_dfa_exec() succeeds, it may have matched more than one sub- + string in the subject. Note, however, that all the matches from one run + of the function start at the same point in the subject. The shorter + matches are all initial substrings of the longer matches. For example, + if the pattern + + <.*> + + is matched against the string + + This is no more + + the three matched strings are + + + + + + On success, the yield of the function is a number greater than zero, + which is the number of matched substrings. The substrings themselves + are returned in ovector. Each string uses two elements; the first is + the offset to the start, and the second is the offset to the end. All + the strings have the same start offset. (Space could have been saved by + giving this only once, but it was decided to retain some compatibility + with the way pcre_exec() returns data, even though the meaning of the + strings is different.) + + The strings are returned in reverse order of length; that is, the long- + est matching string is given first. If there were too many matches to + fit into ovector, the yield of the function is zero, and the vector is + filled with the longest matches. + + Error returns from pcre_dfa_exec() + + The pcre_dfa_exec() function returns a negative number when it fails. + Many of the errors are the same as for pcre_exec(), and these are + described above. There are in addition the following errors that are + specific to pcre_dfa_exec(): + + PCRE_ERROR_DFA_UITEM (-16) + + This return is given if pcre_dfa_exec() encounters an item in the pat- + tern that it does not support, for instance, the use of \C or a back + reference. + + PCRE_ERROR_DFA_UCOND (-17) + + This return is given if pcre_dfa_exec() encounters a condition item in + a pattern that uses a back reference for the condition. This is not + supported. + + PCRE_ERROR_DFA_UMLIMIT (-18) + + This return is given if pcre_dfa_exec() is called with an extra block + that contains a setting of the match_limit field. This is not supported + (it is meaningless). + + PCRE_ERROR_DFA_WSSIZE (-19) + + This return is given if pcre_dfa_exec() runs out of space in the + workspace vector. + + PCRE_ERROR_DFA_RECURSE (-20) + + When a recursive subpattern is processed, the matching function calls + itself recursively, using private vectors for ovector and workspace. + This error is given if the output vector is not large enough. This + should be extremely rare, as a vector of size 1000 is used. + +Last updated: 08 June 2006 +Copyright (c) 1997-2006 University of Cambridge. +------------------------------------------------------------------------------ + + +PCRECALLOUT(3) PCRECALLOUT(3) + + +NAME + PCRE - Perl-compatible regular expressions + + +PCRE CALLOUTS + + int (*pcre_callout)(pcre_callout_block *); + + PCRE provides a feature called "callout", which is a means of temporar- + ily passing control to the caller of PCRE in the middle of pattern + matching. The caller of PCRE provides an external function by putting + its entry point in the global variable pcre_callout. By default, this + variable contains NULL, which disables all calling out. + + Within a regular expression, (?C) indicates the points at which the + external function is to be called. Different callout points can be + identified by putting a number less than 256 after the letter C. The + default value is zero. For example, this pattern has two callout + points: + + (?C1)eabc(?C2)def + + If the PCRE_AUTO_CALLOUT option bit is set when pcre_compile() is + called, PCRE automatically inserts callouts, all with number 255, + before each item in the pattern. For example, if PCRE_AUTO_CALLOUT is + used with the pattern + + A(\d{2}|--) + + it is processed as if it were + + (?C255)A(?C255)((?C255)\d{2}(?C255)|(?C255)-(?C255)-(?C255))(?C255) + + Notice that there is a callout before and after each parenthesis and + alternation bar. Automatic callouts can be used for tracking the + progress of pattern matching. The pcretest command has an option that + sets automatic callouts; when it is used, the output indicates how the + pattern is matched. This is useful information when you are trying to + optimize the performance of a particular pattern. + + +MISSING CALLOUTS + + You should be aware that, because of optimizations in the way PCRE + matches patterns, callouts sometimes do not happen. For example, if the + pattern is + + ab(?C4)cd + + PCRE knows that any matching string must contain the letter "d". If the + subject string is "abyz", the lack of "d" means that matching doesn't + ever start, and the callout is never reached. However, with "abyd", + though the result is still no match, the callout is obeyed. + + +THE CALLOUT INTERFACE + + During matching, when PCRE reaches a callout point, the external func- + tion defined by pcre_callout is called (if it is set). This applies to + both the pcre_exec() and the pcre_dfa_exec() matching functions. The + only argument to the callout function is a pointer to a pcre_callout + block. This structure contains the following fields: + + int version; + int callout_number; + int *offset_vector; + const char *subject; + int subject_length; + int start_match; + int current_position; + int capture_top; + int capture_last; + void *callout_data; + int pattern_position; + int next_item_length; + + The version field is an integer containing the version number of the + block format. The initial version was 0; the current version is 1. The + version number will change again in future if additional fields are + added, but the intention is never to remove any of the existing fields. + + The callout_number field contains the number of the callout, as com- + piled into the pattern (that is, the number after ?C for manual call- + outs, and 255 for automatically generated callouts). + + The offset_vector field is a pointer to the vector of offsets that was + passed by the caller to pcre_exec() or pcre_dfa_exec(). When + pcre_exec() is used, the contents can be inspected in order to extract + substrings that have been matched so far, in the same way as for + extracting substrings after a match has completed. For pcre_dfa_exec() + this field is not useful. + + The subject and subject_length fields contain copies of the values that + were passed to pcre_exec(). + + The start_match field contains the offset within the subject at which + the current match attempt started. If the pattern is not anchored, the + callout function may be called several times from the same point in the + pattern for different starting points in the subject. + + The current_position field contains the offset within the subject of + the current match pointer. + + When the pcre_exec() function is used, the capture_top field contains + one more than the number of the highest numbered captured substring so + far. If no substrings have been captured, the value of capture_top is + one. This is always the case when pcre_dfa_exec() is used, because it + does not support captured substrings. + + The capture_last field contains the number of the most recently cap- + tured substring. If no substrings have been captured, its value is -1. + This is always the case when pcre_dfa_exec() is used. + + The callout_data field contains a value that is passed to pcre_exec() + or pcre_dfa_exec() specifically so that it can be passed back in call- + outs. It is passed in the pcre_callout field of the pcre_extra data + structure. If no such data was passed, the value of callout_data in a + pcre_callout block is NULL. There is a description of the pcre_extra + structure in the pcreapi documentation. + + The pattern_position field is present from version 1 of the pcre_call- + out structure. It contains the offset to the next item to be matched in + the pattern string. + + The next_item_length field is present from version 1 of the pcre_call- + out structure. It contains the length of the next item to be matched in + the pattern string. When the callout immediately precedes an alterna- + tion bar, a closing parenthesis, or the end of the pattern, the length + is zero. When the callout precedes an opening parenthesis, the length + is that of the entire subpattern. + + The pattern_position and next_item_length fields are intended to help + in distinguishing between different automatic callouts, which all have + the same callout number. However, they are set for all callouts. + + +RETURN VALUES + + The external callout function returns an integer to PCRE. If the value + is zero, matching proceeds as normal. If the value is greater than + zero, matching fails at the current point, but the testing of other + matching possibilities goes ahead, just as if a lookahead assertion had + failed. If the value is less than zero, the match is abandoned, and + pcre_exec() (or pcre_dfa_exec()) returns the negative value. + + Negative values should normally be chosen from the set of + PCRE_ERROR_xxx values. In particular, PCRE_ERROR_NOMATCH forces a stan- + dard "no match" failure. The error number PCRE_ERROR_CALLOUT is + reserved for use by callout functions; it will never be used by PCRE + itself. + +Last updated: 28 February 2005 +Copyright (c) 1997-2005 University of Cambridge. +------------------------------------------------------------------------------ + + +PCRECOMPAT(3) PCRECOMPAT(3) + + +NAME + PCRE - Perl-compatible regular expressions + + +DIFFERENCES BETWEEN PCRE AND PERL + + This document describes the differences in the ways that PCRE and Perl + handle regular expressions. The differences described here are with + respect to Perl 5.8. + + 1. PCRE has only a subset of Perl's UTF-8 and Unicode support. Details + of what it does have are given in the section on UTF-8 support in the + main pcre page. + + 2. PCRE does not allow repeat quantifiers on lookahead assertions. Perl + permits them, but they do not mean what you might think. For example, + (?!a){3} does not assert that the next three characters are not "a". It + just asserts that the next character is not "a" three times. + + 3. Capturing subpatterns that occur inside negative lookahead asser- + tions are counted, but their entries in the offsets vector are never + set. Perl sets its numerical variables from any such patterns that are + matched before the assertion fails to match something (thereby succeed- + ing), but only if the negative lookahead assertion contains just one + branch. + + 4. Though binary zero characters are supported in the subject string, + they are not allowed in a pattern string because it is passed as a nor- + mal C string, terminated by zero. The escape sequence \0 can be used in + the pattern to represent a binary zero. + + 5. The following Perl escape sequences are not supported: \l, \u, \L, + \U, and \N. In fact these are implemented by Perl's general string-han- + dling and are not part of its pattern matching engine. If any of these + are encountered by PCRE, an error is generated. + + 6. The Perl escape sequences \p, \P, and \X are supported only if PCRE + is built with Unicode character property support. The properties that + can be tested with \p and \P are limited to the general category prop- + erties such as Lu and Nd, script names such as Greek or Han, and the + derived properties Any and L&. + + 7. PCRE does support the \Q...\E escape for quoting substrings. Charac- + ters in between are treated as literals. This is slightly different + from Perl in that $ and @ are also handled as literals inside the + quotes. In Perl, they cause variable interpolation (but of course PCRE + does not have variables). Note the following examples: + + Pattern PCRE matches Perl matches + + \Qabc$xyz\E abc$xyz abc followed by the + contents of $xyz + \Qabc\$xyz\E abc\$xyz abc\$xyz + \Qabc\E\$\Qxyz\E abc$xyz abc$xyz + + The \Q...\E sequence is recognized both inside and outside character + classes. + + 8. Fairly obviously, PCRE does not support the (?{code}) and (?p{code}) + constructions. However, there is support for recursive patterns using + the non-Perl items (?R), (?number), and (?P>name). Also, the PCRE + "callout" feature allows an external function to be called during pat- + tern matching. See the pcrecallout documentation for details. + + 9. There are some differences that are concerned with the settings of + captured strings when part of a pattern is repeated. For example, + matching "aba" against the pattern /^(a(b)?)+$/ in Perl leaves $2 + unset, but in PCRE it is set to "b". + + 10. PCRE provides some extensions to the Perl regular expression facil- + ities: + + (a) Although lookbehind assertions must match fixed length strings, + each alternative branch of a lookbehind assertion can match a different + length of string. Perl requires them all to have the same length. + + (b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ + meta-character matches only at the very end of the string. + + (c) If PCRE_EXTRA is set, a backslash followed by a letter with no spe- + cial meaning is faulted. Otherwise, like Perl, the backslash is + ignored. (Perl can be made to issue a warning.) + + (d) If PCRE_UNGREEDY is set, the greediness of the repetition quanti- + fiers is inverted, that is, by default they are not greedy, but if fol- + lowed by a question mark they are. + + (e) PCRE_ANCHORED can be used at matching time to force a pattern to be + tried only at the first matching position in the subject string. + + (f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NO_AUTO_CAP- + TURE options for pcre_exec() have no Perl equivalents. + + (g) The (?R), (?number), and (?P>name) constructs allows for recursive + pattern matching (Perl can do this using the (?p{code}) construct, + which PCRE cannot support.) + + (h) PCRE supports named capturing substrings, using the Python syntax. + + (i) PCRE supports the possessive quantifier "++" syntax, taken from + Sun's Java package. + + (j) The (R) condition, for testing recursion, is a PCRE extension. + + (k) The callout facility is PCRE-specific. + + (l) The partial matching facility is PCRE-specific. + + (m) Patterns compiled by PCRE can be saved and re-used at a later time, + even on different hosts that have the other endianness. + + (n) The alternative matching function (pcre_dfa_exec()) matches in a + different way and is not Perl-compatible. + +Last updated: 06 June 2006 +Copyright (c) 1997-2006 University of Cambridge. +------------------------------------------------------------------------------ + + +PCREPATTERN(3) PCREPATTERN(3) + + +NAME + PCRE - Perl-compatible regular expressions + + +PCRE REGULAR EXPRESSION DETAILS + + The syntax and semantics of the regular expressions supported by PCRE + are described below. Regular expressions are also described in the Perl + documentation and in a number of books, some of which have copious + examples. Jeffrey Friedl's "Mastering Regular Expressions", published + by O'Reilly, covers regular expressions in great detail. This descrip- + tion of PCRE's regular expressions is intended as reference material. + + The original operation of PCRE was on strings of one-byte characters. + However, there is now also support for UTF-8 character strings. To use + this, you must build PCRE to include UTF-8 support, and then call + pcre_compile() with the PCRE_UTF8 option. How this affects pattern + matching is mentioned in several places below. There is also a summary + of UTF-8 features in the section on UTF-8 support in the main pcre + page. + + The remainder of this document discusses the patterns that are sup- + ported by PCRE when its main matching function, pcre_exec(), is used. + From release 6.0, PCRE offers a second matching function, + pcre_dfa_exec(), which matches using a different algorithm that is not + Perl-compatible. The advantages and disadvantages of the alternative + function, and how it differs from the normal function, are discussed in + the pcrematching page. + + A regular expression is a pattern that is matched against a subject + string from left to right. Most characters stand for themselves in a + pattern, and match the corresponding characters in the subject. As a + trivial example, the pattern + + The quick brown fox + + matches a portion of a subject string that is identical to itself. When + caseless matching is specified (the PCRE_CASELESS option), letters are + matched independently of case. In UTF-8 mode, PCRE always understands + the concept of case for characters whose values are less than 128, so + caseless matching is always possible. For characters with higher val- + ues, the concept of case is supported if PCRE is compiled with Unicode + property support, but not otherwise. If you want to use caseless + matching for characters 128 and above, you must ensure that PCRE is + compiled with Unicode property support as well as with UTF-8 support. + + The power of regular expressions comes from the ability to include + alternatives and repetitions in the pattern. These are encoded in the + pattern by the use of metacharacters, which do not stand for themselves + but instead are interpreted in some special way. + + There are two different sets of metacharacters: those that are recog- + nized anywhere in the pattern except within square brackets, and those + that are recognized in square brackets. Outside square brackets, the + metacharacters are as follows: + + \ general escape character with several uses + ^ assert start of string (or line, in multiline mode) + $ assert end of string (or line, in multiline mode) + . match any character except newline (by default) + [ start character class definition + | start of alternative branch + ( start subpattern + ) end subpattern + ? extends the meaning of ( + also 0 or 1 quantifier + also quantifier minimizer + * 0 or more quantifier + + 1 or more quantifier + also "possessive quantifier" + { start min/max quantifier + + Part of a pattern that is in square brackets is called a "character + class". In a character class the only metacharacters are: + + \ general escape character + ^ negate the class, but only if the first character + - indicates character range + [ POSIX character class (only if followed by POSIX + syntax) + ] terminates the character class + + The following sections describe the use of each of the metacharacters. + + +BACKSLASH + + The backslash character has several uses. Firstly, if it is followed by + a non-alphanumeric character, it takes away any special meaning that + character may have. This use of backslash as an escape character + applies both inside and outside character classes. + + For example, if you want to match a * character, you write \* in the + pattern. This escaping action applies whether or not the following + character would otherwise be interpreted as a metacharacter, so it is + always safe to precede a non-alphanumeric with backslash to specify + that it stands for itself. In particular, if you want to match a back- + slash, you write \\. + + If a pattern is compiled with the PCRE_EXTENDED option, whitespace in + the pattern (other than in a character class) and characters between a + # outside a character class and the next newline are ignored. An escap- + ing backslash can be used to include a whitespace or # character as + part of the pattern. + + If you want to remove the special meaning from a sequence of charac- + ters, you can do so by putting them between \Q and \E. This is differ- + ent from Perl in that $ and @ are handled as literals in \Q...\E + sequences in PCRE, whereas in Perl, $ and @ cause variable interpola- + tion. Note the following examples: + + Pattern PCRE matches Perl matches + + \Qabc$xyz\E abc$xyz abc followed by the + contents of $xyz + \Qabc\$xyz\E abc\$xyz abc\$xyz + \Qabc\E\$\Qxyz\E abc$xyz abc$xyz + + The \Q...\E sequence is recognized both inside and outside character + classes. + + Non-printing characters + + A second use of backslash provides a way of encoding non-printing char- + acters in patterns in a visible manner. There is no restriction on the + appearance of non-printing characters, apart from the binary zero that + terminates a pattern, but when a pattern is being prepared by text + editing, it is usually easier to use one of the following escape + sequences than the binary character it represents: + + \a alarm, that is, the BEL character (hex 07) + \cx "control-x", where x is any character + \e escape (hex 1B) + \f formfeed (hex 0C) + \n newline (hex 0A) + \r carriage return (hex 0D) + \t tab (hex 09) + \ddd character with octal code ddd, or backreference + \xhh character with hex code hh + \x{hhh..} character with hex code hhh.. + + The precise effect of \cx is as follows: if x is a lower case letter, + it is converted to upper case. Then bit 6 of the character (hex 40) is + inverted. Thus \cz becomes hex 1A, but \c{ becomes hex 3B, while \c; + becomes hex 7B. + + After \x, from zero to two hexadecimal digits are read (letters can be + in upper or lower case). Any number of hexadecimal digits may appear + between \x{ and }, but the value of the character code must be less + than 256 in non-UTF-8 mode, and less than 2**31 in UTF-8 mode (that is, + the maximum hexadecimal value is 7FFFFFFF). If characters other than + hexadecimal digits appear between \x{ and }, or if there is no termi- + nating }, this form of escape is not recognized. Instead, the initial + \x will be interpreted as a basic hexadecimal escape, with no following + digits, giving a character whose value is zero. + + Characters whose value is less than 256 can be defined by either of the + two syntaxes for \x. There is no difference in the way they are han- + dled. For example, \xdc is exactly the same as \x{dc}. + + After \0 up to two further octal digits are read. If there are fewer + than two digits, just those that are present are used. Thus the + sequence \0\x\07 specifies two binary zeros followed by a BEL character + (code value 7). Make sure you supply two digits after the initial zero + if the pattern character that follows is itself an octal digit. + + The handling of a backslash followed by a digit other than 0 is compli- + cated. Outside a character class, PCRE reads it and any following dig- + its as a decimal number. If the number is less than 10, or if there + have been at least that many previous capturing left parentheses in the + expression, the entire sequence is taken as a back reference. A + description of how this works is given later, following the discussion + of parenthesized subpatterns. + + Inside a character class, or if the decimal number is greater than 9 + and there have not been that many capturing subpatterns, PCRE re-reads + up to three octal digits following the backslash, ane uses them to gen- + erate a data character. Any subsequent digits stand for themselves. In + non-UTF-8 mode, the value of a character specified in octal must be + less than \400. In UTF-8 mode, values up to \777 are permitted. For + example: + + \040 is another way of writing a space + \40 is the same, provided there are fewer than 40 + previous capturing subpatterns + \7 is always a back reference + \11 might be a back reference, or another way of + writing a tab + \011 is always a tab + \0113 is a tab followed by the character "3" + \113 might be a back reference, otherwise the + character with octal code 113 + \377 might be a back reference, otherwise + the byte consisting entirely of 1 bits + \81 is either a back reference, or a binary zero + followed by the two characters "8" and "1" + + Note that octal values of 100 or greater must not be introduced by a + leading zero, because no more than three octal digits are ever read. + + All the sequences that define a single character value can be used both + inside and outside character classes. In addition, inside a character + class, the sequence \b is interpreted as the backspace character (hex + 08), and the sequence \X is interpreted as the character "X". Outside a + character class, these sequences have different meanings (see below). + + Generic character types + + The third use of backslash is for specifying generic character types. + The following are always recognized: + + \d any decimal digit + \D any character that is not a decimal digit + \s any whitespace character + \S any character that is not a whitespace character + \w any "word" character + \W any "non-word" character + + Each pair of escape sequences partitions the complete set of characters + into two disjoint sets. Any given character matches one, and only one, + of each pair. + + These character type sequences can appear both inside and outside char- + acter classes. They each match one character of the appropriate type. + If the current matching point is at the end of the subject string, all + of them fail, since there is no character to match. + + For compatibility with Perl, \s does not match the VT character (code + 11). This makes it different from the the POSIX "space" class. The \s + characters are HT (9), LF (10), FF (12), CR (13), and space (32). (If + "use locale;" is included in a Perl script, \s may match the VT charac- + ter. In PCRE, it never does.) + + A "word" character is an underscore or any character less than 256 that + is a letter or digit. The definition of letters and digits is con- + trolled by PCRE's low-valued character tables, and may vary if locale- + specific matching is taking place (see "Locale support" in the pcreapi + page). For example, in the "fr_FR" (French) locale, some character + codes greater than 128 are used for accented letters, and these are + matched by \w. + + In UTF-8 mode, characters with values greater than 128 never match \d, + \s, or \w, and always match \D, \S, and \W. This is true even when Uni- + code character property support is available. The use of locales with + Unicode is discouraged. + + Unicode character properties + + When PCRE is built with Unicode character property support, three addi- + tional escape sequences to match character properties are available + when UTF-8 mode is selected. They are: + + \p{xx} a character with the xx property + \P{xx} a character without the xx property + \X an extended Unicode sequence + + The property names represented by xx above are limited to the Unicode + script names, the general category properties, and "Any", which matches + any character (including newline). Other properties such as "InMusical- + Symbols" are not currently supported by PCRE. Note that \P{Any} does + not match any characters, so always causes a match failure. + + Sets of Unicode characters are defined as belonging to certain scripts. + A character from one of these sets can be matched using a script name. + For example: + + \p{Greek} + \P{Han} + + Those that are not part of an identified script are lumped together as + "Common". The current list of scripts is: + + Arabic, Armenian, Bengali, Bopomofo, Braille, Buginese, Buhid, Cana- + dian_Aboriginal, Cherokee, Common, Coptic, Cypriot, Cyrillic, Deseret, + Devanagari, Ethiopic, Georgian, Glagolitic, Gothic, Greek, Gujarati, + Gurmukhi, Han, Hangul, Hanunoo, Hebrew, Hiragana, Inherited, Kannada, + Katakana, Kharoshthi, Khmer, Lao, Latin, Limbu, Linear_B, Malayalam, + Mongolian, Myanmar, New_Tai_Lue, Ogham, Old_Italic, Old_Persian, Oriya, + Osmanya, Runic, Shavian, Sinhala, Syloti_Nagri, Syriac, Tagalog, Tag- + banwa, Tai_Le, Tamil, Telugu, Thaana, Thai, Tibetan, Tifinagh, + Ugaritic, Yi. + + Each character has exactly one general category property, specified by + a two-letter abbreviation. For compatibility with Perl, negation can be + specified by including a circumflex between the opening brace and the + property name. For example, \p{^Lu} is the same as \P{Lu}. + + If only one letter is specified with \p or \P, it includes all the gen- + eral category properties that start with that letter. In this case, in + the absence of negation, the curly brackets in the escape sequence are + optional; these two examples have the same effect: + + \p{L} + \pL + + The following general category property codes are supported: + + C Other + Cc Control + Cf Format + Cn Unassigned + Co Private use + Cs Surrogate + + L Letter + Ll Lower case letter + Lm Modifier letter + Lo Other letter + Lt Title case letter + Lu Upper case letter + + M Mark + Mc Spacing mark + Me Enclosing mark + Mn Non-spacing mark + + N Number + Nd Decimal number + Nl Letter number + No Other number + + P Punctuation + Pc Connector punctuation + Pd Dash punctuation + Pe Close punctuation + Pf Final punctuation + Pi Initial punctuation + Po Other punctuation + Ps Open punctuation + + S Symbol + Sc Currency symbol + Sk Modifier symbol + Sm Mathematical symbol + So Other symbol + + Z Separator + Zl Line separator + Zp Paragraph separator + Zs Space separator + + The special property L& is also supported: it matches a character that + has the Lu, Ll, or Lt property, in other words, a letter that is not + classified as a modifier or "other". + + The long synonyms for these properties that Perl supports (such as + \p{Letter}) are not supported by PCRE, nor is it permitted to prefix + any of these properties with "Is". + + No character that is in the Unicode table has the Cn (unassigned) prop- + erty. Instead, this property is assumed for any code point that is not + in the Unicode table. + + Specifying caseless matching does not affect these escape sequences. + For example, \p{Lu} always matches only upper case letters. + + The \X escape matches any number of Unicode characters that form an + extended Unicode sequence. \X is equivalent to + + (?>\PM\pM*) + + That is, it matches a character without the "mark" property, followed + by zero or more characters with the "mark" property, and treats the + sequence as an atomic group (see below). Characters with the "mark" + property are typically accents that affect the preceding character. + + Matching characters by Unicode property is not fast, because PCRE has + to search a structure that contains data for over fifteen thousand + characters. That is why the traditional escape sequences such as \d and + \w do not use Unicode properties in PCRE. + + Simple assertions + + The fourth use of backslash is for certain simple assertions. An asser- + tion specifies a condition that has to be met at a particular point in + a match, without consuming any characters from the subject string. The + use of subpatterns for more complicated assertions is described below. + The backslashed assertions are: + + \b matches at a word boundary + \B matches when not at a word boundary + \A matches at start of subject + \Z matches at end of subject or before newline at end + \z matches at end of subject + \G matches at first matching position in subject + + These assertions may not appear in character classes (but note that \b + has a different meaning, namely the backspace character, inside a char- + acter class). + + A word boundary is a position in the subject string where the current + character and the previous character do not both match \w or \W (i.e. + one matches \w and the other matches \W), or the start or end of the + string if the first or last character matches \w, respectively. + + The \A, \Z, and \z assertions differ from the traditional circumflex + and dollar (described in the next section) in that they only ever match + at the very start and end of the subject string, whatever options are + set. Thus, they are independent of multiline mode. These three asser- + tions are not affected by the PCRE_NOTBOL or PCRE_NOTEOL options, which + affect only the behaviour of the circumflex and dollar metacharacters. + However, if the startoffset argument of pcre_exec() is non-zero, indi- + cating that matching is to start at a point other than the beginning of + the subject, \A can never match. The difference between \Z and \z is + that \Z matches before a newline at the end of the string as well as at + the very end, whereas \z matches only at the end. + + The \G assertion is true only when the current matching position is at + the start point of the match, as specified by the startoffset argument + of pcre_exec(). It differs from \A when the value of startoffset is + non-zero. By calling pcre_exec() multiple times with appropriate argu- + ments, you can mimic Perl's /g option, and it is in this kind of imple- + mentation where \G can be useful. + + Note, however, that PCRE's interpretation of \G, as the start of the + current match, is subtly different from Perl's, which defines it as the + end of the previous match. In Perl, these can be different when the + previously matched string was empty. Because PCRE does just one match + at a time, it cannot reproduce this behaviour. + + If all the alternatives of a pattern begin with \G, the expression is + anchored to the starting match position, and the "anchored" flag is set + in the compiled regular expression. + + +CIRCUMFLEX AND DOLLAR + + Outside a character class, in the default matching mode, the circumflex + character is an assertion that is true only if the current matching + point is at the start of the subject string. If the startoffset argu- + ment of pcre_exec() is non-zero, circumflex can never match if the + PCRE_MULTILINE option is unset. Inside a character class, circumflex + has an entirely different meaning (see below). + + Circumflex need not be the first character of the pattern if a number + of alternatives are involved, but it should be the first thing in each + alternative in which it appears if the pattern is ever to match that + branch. If all possible alternatives start with a circumflex, that is, + if the pattern is constrained to match only at the start of the sub- + ject, it is said to be an "anchored" pattern. (There are also other + constructs that can cause a pattern to be anchored.) + + A dollar character is an assertion that is true only if the current + matching point is at the end of the subject string, or immediately + before a newline at the end of the string (by default). Dollar need not + be the last character of the pattern if a number of alternatives are + involved, but it should be the last item in any branch in which it + appears. Dollar has no special meaning in a character class. + + The meaning of dollar can be changed so that it matches only at the + very end of the string, by setting the PCRE_DOLLAR_ENDONLY option at + compile time. This does not affect the \Z assertion. + + The meanings of the circumflex and dollar characters are changed if the + PCRE_MULTILINE option is set. When this is the case, a circumflex + matches immediately after internal newlines as well as at the start of + the subject string. It does not match after a newline that ends the + string. A dollar matches before any newlines in the string, as well as + at the very end, when PCRE_MULTILINE is set. When newline is specified + as the two-character sequence CRLF, isolated CR and LF characters do + not indicate newlines. + + For example, the pattern /^abc$/ matches the subject string "def\nabc" + (where \n represents a newline) in multiline mode, but not otherwise. + Consequently, patterns that are anchored in single line mode because + all branches start with ^ are not anchored in multiline mode, and a + match for circumflex is possible when the startoffset argument of + pcre_exec() is non-zero. The PCRE_DOLLAR_ENDONLY option is ignored if + PCRE_MULTILINE is set. + + Note that the sequences \A, \Z, and \z can be used to match the start + and end of the subject in both modes, and if all branches of a pattern + start with \A it is always anchored, whether or not PCRE_MULTILINE is + set. + + +FULL STOP (PERIOD, DOT) + + Outside a character class, a dot in the pattern matches any one charac- + ter in the subject string except (by default) a character that signi- + fies the end of a line. In UTF-8 mode, the matched character may be + more than one byte long. When a line ending is defined as a single + character (CR or LF), dot never matches that character; when the two- + character sequence CRLF is used, dot does not match CR if it is immedi- + ately followed by LF, but otherwise it matches all characters (includ- + ing isolated CRs and LFs). + + The behaviour of dot with regard to newlines can be changed. If the + PCRE_DOTALL option is set, a dot matches any one character, without + exception. If newline is defined as the two-character sequence CRLF, it + takes two dots to match it. + + The handling of dot is entirely independent of the handling of circum- + flex and dollar, the only relationship being that they both involve + newlines. Dot has no special meaning in a character class. + + +MATCHING A SINGLE BYTE + + Outside a character class, the escape sequence \C matches any one byte, + both in and out of UTF-8 mode. Unlike a dot, it always matches CR and + LF. The feature is provided in Perl in order to match individual bytes + in UTF-8 mode. Because it breaks up UTF-8 characters into individual + bytes, what remains in the string may be a malformed UTF-8 string. For + this reason, the \C escape sequence is best avoided. + + PCRE does not allow \C to appear in lookbehind assertions (described + below), because in UTF-8 mode this would make it impossible to calcu- + late the length of the lookbehind. + + +SQUARE BRACKETS AND CHARACTER CLASSES + + An opening square bracket introduces a character class, terminated by a + closing square bracket. A closing square bracket on its own is not spe- + cial. If a closing square bracket is required as a member of the class, + it should be the first data character in the class (after an initial + circumflex, if present) or escaped with a backslash. + + A character class matches a single character in the subject. In UTF-8 + mode, the character may occupy more than one byte. A matched character + must be in the set of characters defined by the class, unless the first + character in the class definition is a circumflex, in which case the + subject character must not be in the set defined by the class. If a + circumflex is actually required as a member of the class, ensure it is + not the first character, or escape it with a backslash. + + For example, the character class [aeiou] matches any lower case vowel, + while [^aeiou] matches any character that is not a lower case vowel. + Note that a circumflex is just a convenient notation for specifying the + characters that are in the class by enumerating those that are not. A + class that starts with a circumflex is not an assertion: it still con- + sumes a character from the subject string, and therefore it fails if + the current pointer is at the end of the string. + + In UTF-8 mode, characters with values greater than 255 can be included + in a class as a literal string of bytes, or by using the \x{ escaping + mechanism. + + When caseless matching is set, any letters in a class represent both + their upper case and lower case versions, so for example, a caseless + [aeiou] matches "A" as well as "a", and a caseless [^aeiou] does not + match "A", whereas a caseful version would. In UTF-8 mode, PCRE always + understands the concept of case for characters whose values are less + than 128, so caseless matching is always possible. For characters with + higher values, the concept of case is supported if PCRE is compiled + with Unicode property support, but not otherwise. If you want to use + caseless matching for characters 128 and above, you must ensure that + PCRE is compiled with Unicode property support as well as with UTF-8 + support. + + Characters that might indicate line breaks (CR and LF) are never + treated in any special way when matching character classes, whatever + line-ending sequence is in use, and whatever setting of the PCRE_DOTALL + and PCRE_MULTILINE options is used. A class such as [^a] always matches + one of these characters. + + The minus (hyphen) character can be used to specify a range of charac- + ters in a character class. For example, [d-m] matches any letter + between d and m, inclusive. If a minus character is required in a + class, it must be escaped with a backslash or appear in a position + where it cannot be interpreted as indicating a range, typically as the + first or last character in the class. + + It is not possible to have the literal character "]" as the end charac- + ter of a range. A pattern such as [W-]46] is interpreted as a class of + two characters ("W" and "-") followed by a literal string "46]", so it + would match "W46]" or "-46]". However, if the "]" is escaped with a + backslash it is interpreted as the end of range, so [W-\]46] is inter- + preted as a class containing a range followed by two other characters. + The octal or hexadecimal representation of "]" can also be used to end + a range. + + Ranges operate in the collating sequence of character values. They can + also be used for characters specified numerically, for example + [\000-\037]. In UTF-8 mode, ranges can include characters whose values + are greater than 255, for example [\x{100}-\x{2ff}]. + + If a range that includes letters is used when caseless matching is set, + it matches the letters in either case. For example, [W-c] is equivalent + to [][\\^_`wxyzabc], matched caselessly, and in non-UTF-8 mode, if + character tables for the "fr_FR" locale are in use, [\xc8-\xcb] matches + accented E characters in both cases. In UTF-8 mode, PCRE supports the + concept of case for characters with values greater than 128 only when + it is compiled with Unicode property support. + + The character types \d, \D, \p, \P, \s, \S, \w, and \W may also appear + in a character class, and add the characters that they match to the + class. For example, [\dABCDEF] matches any hexadecimal digit. A circum- + flex can conveniently be used with the upper case character types to + specify a more restricted set of characters than the matching lower + case type. For example, the class [^\W_] matches any letter or digit, + but not underscore. + + The only metacharacters that are recognized in character classes are + backslash, hyphen (only where it can be interpreted as specifying a + range), circumflex (only at the start), opening square bracket (only + when it can be interpreted as introducing a POSIX class name - see the + next section), and the terminating closing square bracket. However, + escaping other non-alphanumeric characters does no harm. + + +POSIX CHARACTER CLASSES + + Perl supports the POSIX notation for character classes. This uses names + enclosed by [: and :] within the enclosing square brackets. PCRE also + supports this notation. For example, + + [01[:alpha:]%] + + matches "0", "1", any alphabetic character, or "%". The supported class + names are + + alnum letters and digits + alpha letters + ascii character codes 0 - 127 + blank space or tab only + cntrl control characters + digit decimal digits (same as \d) + graph printing characters, excluding space + lower lower case letters + print printing characters, including space + punct printing characters, excluding letters and digits + space white space (not quite the same as \s) + upper upper case letters + word "word" characters (same as \w) + xdigit hexadecimal digits + + The "space" characters are HT (9), LF (10), VT (11), FF (12), CR (13), + and space (32). Notice that this list includes the VT character (code + 11). This makes "space" different to \s, which does not include VT (for + Perl compatibility). + + The name "word" is a Perl extension, and "blank" is a GNU extension + from Perl 5.8. Another Perl extension is negation, which is indicated + by a ^ character after the colon. For example, + + [12[:^digit:]] + + matches "1", "2", or any non-digit. PCRE (and Perl) also recognize the + POSIX syntax [.ch.] and [=ch=] where "ch" is a "collating element", but + these are not supported, and an error is given if they are encountered. + + In UTF-8 mode, characters with values greater than 128 do not match any + of the POSIX character classes. + + +VERTICAL BAR + + Vertical bar characters are used to separate alternative patterns. For + example, the pattern + + gilbert|sullivan + + matches either "gilbert" or "sullivan". Any number of alternatives may + appear, and an empty alternative is permitted (matching the empty + string). The matching process tries each alternative in turn, from left + to right, and the first one that succeeds is used. If the alternatives + are within a subpattern (defined below), "succeeds" means matching the + rest of the main pattern as well as the alternative in the subpattern. + + +INTERNAL OPTION SETTING + + The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and + PCRE_EXTENDED options can be changed from within the pattern by a + sequence of Perl option letters enclosed between "(?" and ")". The + option letters are + + i for PCRE_CASELESS + m for PCRE_MULTILINE + s for PCRE_DOTALL + x for PCRE_EXTENDED + + For example, (?im) sets caseless, multiline matching. It is also possi- + ble to unset these options by preceding the letter with a hyphen, and a + combined setting and unsetting such as (?im-sx), which sets PCRE_CASE- + LESS and PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, + is also permitted. If a letter appears both before and after the + hyphen, the option is unset. + + When an option change occurs at top level (that is, not inside subpat- + tern parentheses), the change applies to the remainder of the pattern + that follows. If the change is placed right at the start of a pattern, + PCRE extracts it into the global options (and it will therefore show up + in data extracted by the pcre_fullinfo() function). + + An option change within a subpattern affects only that part of the cur- + rent pattern that follows it, so + + (a(?i)b)c + + matches abc and aBc and no other strings (assuming PCRE_CASELESS is not + used). By this means, options can be made to have different settings + in different parts of the pattern. Any changes made in one alternative + do carry on into subsequent branches within the same subpattern. For + example, + + (a(?i)b|c) + + matches "ab", "aB", "c", and "C", even though when matching "C" the + first branch is abandoned before the option setting. This is because + the effects of option settings happen at compile time. There would be + some very weird behaviour otherwise. + + The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA + can be changed in the same way as the Perl-compatible options by using + the characters J, U and X respectively. + + +SUBPATTERNS + + Subpatterns are delimited by parentheses (round brackets), which can be + nested. Turning part of a pattern into a subpattern does two things: + + 1. It localizes a set of alternatives. For example, the pattern + + cat(aract|erpillar|) + + matches one of the words "cat", "cataract", or "caterpillar". Without + the parentheses, it would match "cataract", "erpillar" or the empty + string. + + 2. It sets up the subpattern as a capturing subpattern. This means + that, when the whole pattern matches, that portion of the subject + string that matched the subpattern is passed back to the caller via the + ovector argument of pcre_exec(). Opening parentheses are counted from + left to right (starting from 1) to obtain numbers for the capturing + subpatterns. + + For example, if the string "the red king" is matched against the pat- + tern + + the ((red|white) (king|queen)) + + the captured substrings are "red king", "red", and "king", and are num- + bered 1, 2, and 3, respectively. + + The fact that plain parentheses fulfil two functions is not always + helpful. There are often times when a grouping subpattern is required + without a capturing requirement. If an opening parenthesis is followed + by a question mark and a colon, the subpattern does not do any captur- + ing, and is not counted when computing the number of any subsequent + capturing subpatterns. For example, if the string "the white queen" is + matched against the pattern + + the ((?:red|white) (king|queen)) + + the captured substrings are "white queen" and "queen", and are numbered + 1 and 2. The maximum number of capturing subpatterns is 65535, and the + maximum depth of nesting of all subpatterns, both capturing and non- + capturing, is 200. + + As a convenient shorthand, if any option settings are required at the + start of a non-capturing subpattern, the option letters may appear + between the "?" and the ":". Thus the two patterns + + (?i:saturday|sunday) + (?:(?i)saturday|sunday) + + match exactly the same set of strings. Because alternative branches are + tried from left to right, and options are not reset until the end of + the subpattern is reached, an option setting in one branch does affect + subsequent branches, so the above patterns match "SUNDAY" as well as + "Saturday". + + +NAMED SUBPATTERNS + + Identifying capturing parentheses by number is simple, but it can be + very hard to keep track of the numbers in complicated regular expres- + sions. Furthermore, if an expression is modified, the numbers may + change. To help with this difficulty, PCRE supports the naming of sub- + patterns, something that Perl does not provide. The Python syntax + (?P...) is used. References to capturing parentheses from other + parts of the pattern, such as backreferences, recursion, and condi- + tions, can be made by name as well as by number. + + Names consist of up to 32 alphanumeric characters and underscores. + Named capturing parentheses are still allocated numbers as well as + names. The PCRE API provides function calls for extracting the name-to- + number translation table from a compiled pattern. There is also a con- + venience function for extracting a captured substring by name. + + By default, a name must be unique within a pattern, but it is possible + to relax this constraint by setting the PCRE_DUPNAMES option at compile + time. This can be useful for patterns where only one instance of the + named parentheses can match. Suppose you want to match the name of a + weekday, either as a 3-letter abbreviation or as the full name, and in + both cases you want to extract the abbreviation. This pattern (ignoring + the line breaks) does the job: + + (?PMon|Fri|Sun)(?:day)?| + (?PTue)(?:sday)?| + (?PWed)(?:nesday)?| + (?PThu)(?:rsday)?| + (?PSat)(?:urday)? + + There are five capturing substrings, but only one is ever set after a + match. The convenience function for extracting the data by name + returns the substring for the first, and in this example, the only, + subpattern of that name that matched. This saves searching to find + which numbered subpattern it was. If you make a reference to a non- + unique named subpattern from elsewhere in the pattern, the one that + corresponds to the lowest number is used. For further details of the + interfaces for handling named subpatterns, see the pcreapi documenta- + tion. + + +REPETITION + + Repetition is specified by quantifiers, which can follow any of the + following items: + + a literal data character + the . metacharacter + the \C escape sequence + the \X escape sequence (in UTF-8 mode with Unicode properties) + an escape such as \d that matches a single character + a character class + a back reference (see next section) + a parenthesized subpattern (unless it is an assertion) + + The general repetition quantifier specifies a minimum and maximum num- + ber of permitted matches, by giving the two numbers in curly brackets + (braces), separated by a comma. The numbers must be less than 65536, + and the first must be less than or equal to the second. For example: + + z{2,4} + + matches "zz", "zzz", or "zzzz". A closing brace on its own is not a + special character. If the second number is omitted, but the comma is + present, there is no upper limit; if the second number and the comma + are both omitted, the quantifier specifies an exact number of required + matches. Thus + + [aeiou]{3,} + + matches at least 3 successive vowels, but may match many more, while + + \d{8} + + matches exactly 8 digits. An opening curly bracket that appears in a + position where a quantifier is not allowed, or one that does not match + the syntax of a quantifier, is taken as a literal character. For exam- + ple, {,6} is not a quantifier, but a literal string of four characters. + + In UTF-8 mode, quantifiers apply to UTF-8 characters rather than to + individual bytes. Thus, for example, \x{100}{2} matches two UTF-8 char- + acters, each of which is represented by a two-byte sequence. Similarly, + when Unicode property support is available, \X{3} matches three Unicode + extended sequences, each of which may be several bytes long (and they + may be of different lengths). + + The quantifier {0} is permitted, causing the expression to behave as if + the previous item and the quantifier were not present. + + For convenience (and historical compatibility) the three most common + quantifiers have single-character abbreviations: + + * is equivalent to {0,} + + is equivalent to {1,} + ? is equivalent to {0,1} + + It is possible to construct infinite loops by following a subpattern + that can match no characters with a quantifier that has no upper limit, + for example: + + (a?)* + + Earlier versions of Perl and PCRE used to give an error at compile time + for such patterns. However, because there are cases where this can be + useful, such patterns are now accepted, but if any repetition of the + subpattern does in fact match no characters, the loop is forcibly bro- + ken. + + By default, the quantifiers are "greedy", that is, they match as much + as possible (up to the maximum number of permitted times), without + causing the rest of the pattern to fail. The classic example of where + this gives problems is in trying to match comments in C programs. These + appear between /* and */ and within the comment, individual * and / + characters may appear. An attempt to match C comments by applying the + pattern + + /\*.*\*/ + + to the string + + /* first comment */ not comment /* second comment */ + + fails, because it matches the entire string owing to the greediness of + the .* item. + + However, if a quantifier is followed by a question mark, it ceases to + be greedy, and instead matches the minimum number of times possible, so + the pattern + + /\*.*?\*/ + + does the right thing with the C comments. The meaning of the various + quantifiers is not otherwise changed, just the preferred number of + matches. Do not confuse this use of question mark with its use as a + quantifier in its own right. Because it has two uses, it can sometimes + appear doubled, as in + + \d??\d + + which matches one digit by preference, but can match two if that is the + only way the rest of the pattern matches. + + If the PCRE_UNGREEDY option is set (an option which is not available in + Perl), the quantifiers are not greedy by default, but individual ones + can be made greedy by following them with a question mark. In other + words, it inverts the default behaviour. + + When a parenthesized subpattern is quantified with a minimum repeat + count that is greater than 1 or with a limited maximum, more memory is + required for the compiled pattern, in proportion to the size of the + minimum or maximum. + + If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equiv- + alent to Perl's /s) is set, thus allowing the . to match newlines, the + pattern is implicitly anchored, because whatever follows will be tried + against every character position in the subject string, so there is no + point in retrying the overall match at any position after the first. + PCRE normally treats such a pattern as though it were preceded by \A. + + In cases where it is known that the subject string contains no new- + lines, it is worth setting PCRE_DOTALL in order to obtain this opti- + mization, or alternatively using ^ to indicate anchoring explicitly. + + However, there is one situation where the optimization cannot be used. + When .* is inside capturing parentheses that are the subject of a + backreference elsewhere in the pattern, a match at the start may fail, + and a later one succeed. Consider, for example: + + (.*)abc\1 + + If the subject is "xyz123abc123" the match point is the fourth charac- + ter. For this reason, such a pattern is not implicitly anchored. + + When a capturing subpattern is repeated, the value captured is the sub- + string that matched the final iteration. For example, after + + (tweedle[dume]{3}\s*)+ + + has matched "tweedledum tweedledee" the value of the captured substring + is "tweedledee". However, if there are nested capturing subpatterns, + the corresponding captured values may have been set in previous itera- + tions. For example, after + + /(a|(b))+/ + + matches "aba" the value of the second captured substring is "b". + + +ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS + + With both maximizing and minimizing repetition, failure of what follows + normally causes the repeated item to be re-evaluated to see if a dif- + ferent number of repeats allows the rest of the pattern to match. Some- + times it is useful to prevent this, either to change the nature of the + match, or to cause it fail earlier than it otherwise might, when the + author of the pattern knows there is no point in carrying on. + + Consider, for example, the pattern \d+foo when applied to the subject + line + + 123456bar + + After matching all 6 digits and then failing to match "foo", the normal + action of the matcher is to try again with only 5 digits matching the + \d+ item, and then with 4, and so on, before ultimately failing. + "Atomic grouping" (a term taken from Jeffrey Friedl's book) provides + the means for specifying that once a subpattern has matched, it is not + to be re-evaluated in this way. + + If we use atomic grouping for the previous example, the matcher would + give up immediately on failing to match "foo" the first time. The nota- + tion is a kind of special parenthesis, starting with (?> as in this + example: + + (?>\d+)foo + + This kind of parenthesis "locks up" the part of the pattern it con- + tains once it has matched, and a failure further into the pattern is + prevented from backtracking into it. Backtracking past it to previous + items, however, works as normal. + + An alternative description is that a subpattern of this type matches + the string of characters that an identical standalone pattern would + match, if anchored at the current point in the subject string. + + Atomic grouping subpatterns are not capturing subpatterns. Simple cases + such as the above example can be thought of as a maximizing repeat that + must swallow everything it can. So, while both \d+ and \d+? are pre- + pared to adjust the number of digits they match in order to make the + rest of the pattern match, (?>\d+) can only match an entire sequence of + digits. + + Atomic groups in general can of course contain arbitrarily complicated + subpatterns, and can be nested. However, when the subpattern for an + atomic group is just a single repeated item, as in the example above, a + simpler notation, called a "possessive quantifier" can be used. This + consists of an additional + character following a quantifier. Using + this notation, the previous example can be rewritten as + + \d++foo + + Possessive quantifiers are always greedy; the setting of the + PCRE_UNGREEDY option is ignored. They are a convenient notation for the + simpler forms of atomic group. However, there is no difference in the + meaning or processing of a possessive quantifier and the equivalent + atomic group. + + The possessive quantifier syntax is an extension to the Perl syntax. + Jeffrey Friedl originated the idea (and the name) in the first edition + of his book. Mike McCloskey liked it, so implemented it when he built + Sun's Java package, and PCRE copied it from there. + + When a pattern contains an unlimited repeat inside a subpattern that + can itself be repeated an unlimited number of times, the use of an + atomic group is the only way to avoid some failing matches taking a + very long time indeed. The pattern + + (\D+|<\d+>)*[!?] + + matches an unlimited number of substrings that either consist of non- + digits, or digits enclosed in <>, followed by either ! or ?. When it + matches, it runs quickly. However, if it is applied to + + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + + it takes a long time before reporting failure. This is because the + string can be divided between the internal \D+ repeat and the external + * repeat in a large number of ways, and all have to be tried. (The + example uses [!?] rather than a single character at the end, because + both PCRE and Perl have an optimization that allows for fast failure + when a single character is used. They remember the last single charac- + ter that is required for a match, and fail early if it is not present + in the string.) If the pattern is changed so that it uses an atomic + group, like this: + + ((?>\D+)|<\d+>)*[!?] + + sequences of non-digits cannot be broken, and failure happens quickly. + + +BACK REFERENCES + + Outside a character class, a backslash followed by a digit greater than + 0 (and possibly further digits) is a back reference to a capturing sub- + pattern earlier (that is, to its left) in the pattern, provided there + have been that many previous capturing left parentheses. + + However, if the decimal number following the backslash is less than 10, + it is always taken as a back reference, and causes an error only if + there are not that many capturing left parentheses in the entire pat- + tern. In other words, the parentheses that are referenced need not be + to the left of the reference for numbers less than 10. A "forward back + reference" of this type can make sense when a repetition is involved + and the subpattern to the right has participated in an earlier itera- + tion. + + It is not possible to have a numerical "forward back reference" to sub- + pattern whose number is 10 or more. However, a back reference to any + subpattern is possible using named parentheses (see below). See also + the subsection entitled "Non-printing characters" above for further + details of the handling of digits following a backslash. + + A back reference matches whatever actually matched the capturing sub- + pattern in the current subject string, rather than anything matching + the subpattern itself (see "Subpatterns as subroutines" below for a way + of doing that). So the pattern + + (sens|respons)e and \1ibility + + matches "sense and sensibility" and "response and responsibility", but + not "sense and responsibility". If caseful matching is in force at the + time of the back reference, the case of letters is relevant. For exam- + ple, + + ((?i)rah)\s+\1 + + matches "rah rah" and "RAH RAH", but not "RAH rah", even though the + original capturing subpattern is matched caselessly. + + Back references to named subpatterns use the Python syntax (?P=name). + We could rewrite the above example as follows: + + (?P(?i)rah)\s+(?P=p1) + + A subpattern that is referenced by name may appear in the pattern + before or after the reference. + + There may be more than one back reference to the same subpattern. If a + subpattern has not actually been used in a particular match, any back + references to it always fail. For example, the pattern + + (a|(bc))\2 + + always fails if it starts to match "a" rather than "bc". Because there + may be many capturing parentheses in a pattern, all digits following + the backslash are taken as part of a potential back reference number. + If the pattern continues with a digit character, some delimiter must be + used to terminate the back reference. If the PCRE_EXTENDED option is + set, this can be whitespace. Otherwise an empty comment (see "Com- + ments" below) can be used. + + A back reference that occurs inside the parentheses to which it refers + fails when the subpattern is first used, so, for example, (a\1) never + matches. However, such references can be useful inside repeated sub- + patterns. For example, the pattern + + (a|b\1)+ + + matches any number of "a"s and also "aba", "ababbaa" etc. At each iter- + ation of the subpattern, the back reference matches the character + string corresponding to the previous iteration. In order for this to + work, the pattern must be such that the first iteration does not need + to match the back reference. This can be done using alternation, as in + the example above, or by a quantifier with a minimum of zero. + + +ASSERTIONS + + An assertion is a test on the characters following or preceding the + current matching point that does not actually consume any characters. + The simple assertions coded as \b, \B, \A, \G, \Z, \z, ^ and $ are + described above. + + More complicated assertions are coded as subpatterns. There are two + kinds: those that look ahead of the current position in the subject + string, and those that look behind it. An assertion subpattern is + matched in the normal way, except that it does not cause the current + matching position to be changed. + + Assertion subpatterns are not capturing subpatterns, and may not be + repeated, because it makes no sense to assert the same thing several + times. If any kind of assertion contains capturing subpatterns within + it, these are counted for the purposes of numbering the capturing sub- + patterns in the whole pattern. However, substring capturing is carried + out only for positive assertions, because it does not make sense for + negative assertions. + + Lookahead assertions + + Lookahead assertions start with (?= for positive assertions and (?! for + negative assertions. For example, + + \w+(?=;) + + matches a word followed by a semicolon, but does not include the semi- + colon in the match, and + + foo(?!bar) + + matches any occurrence of "foo" that is not followed by "bar". Note + that the apparently similar pattern + + (?!foo)bar + + does not find an occurrence of "bar" that is preceded by something + other than "foo"; it finds any occurrence of "bar" whatsoever, because + the assertion (?!foo) is always true when the next three characters are + "bar". A lookbehind assertion is needed to achieve the other effect. + + If you want to force a matching failure at some point in a pattern, the + most convenient way to do it is with (?!) because an empty string + always matches, so an assertion that requires there not to be an empty + string must always fail. + + Lookbehind assertions + + Lookbehind assertions start with (?<= for positive assertions and (?.*)(?<=abcd) + + or, equivalently, using the possessive quantifier syntax, + + ^.*+(?<=abcd) + + there can be no backtracking for the .* item; it can match only the + entire string. The subsequent lookbehind assertion does a single test + on the last four characters. If it fails, the match fails immediately. + For long strings, this approach makes a significant difference to the + processing time. + + Using multiple assertions + + Several assertions (of any sort) may occur in succession. For example, + + (?<=\d{3})(? \( )? [^()]+ (?(OPEN) \) ) + + If the condition is the string (R), and there is no subpattern with the + name R, the condition is satisfied if a recursive call to the pattern + or subpattern has been made. At "top level", the condition is false. + This is a PCRE extension. Recursive patterns are described in the next + section. + + If the condition is not a sequence of digits or (R), it must be an + assertion. This may be a positive or negative lookahead or lookbehind + assertion. Consider this pattern, again containing non-significant + white space, and with the two alternatives on the second line: + + (?(?=[^a-z]*[a-z]) + \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) + + The condition is a positive lookahead assertion that matches an + optional sequence of non-letters followed by a letter. In other words, + it tests for the presence of at least one letter in the subject. If a + letter is found, the subject is matched against the first alternative; + otherwise it is matched against the second. This pattern matches + strings in one of the two forms dd-aaa-dd or dd-dd-dd, where aaa are + letters and dd are digits. + + +COMMENTS + + The sequence (?# marks the start of a comment that continues up to the + next closing parenthesis. Nested parentheses are not permitted. The + characters that make up a comment play no part in the pattern matching + at all. + + If the PCRE_EXTENDED option is set, an unescaped # character outside a + character class introduces a comment that continues to immediately + after the next newline in the pattern. + + +RECURSIVE PATTERNS + + Consider the problem of matching a string in parentheses, allowing for + unlimited nested parentheses. Without the use of recursion, the best + that can be done is to use a pattern that matches up to some fixed + depth of nesting. It is not possible to handle an arbitrary nesting + depth. Perl provides a facility that allows regular expressions to + recurse (amongst other things). It does this by interpolating Perl code + in the expression at run time, and the code can refer to the expression + itself. A Perl pattern to solve the parentheses problem can be created + like this: + + $re = qr{\( (?: (?>[^()]+) | (?p{$re}) )* \)}x; + + The (?p{...}) item interpolates Perl code at run time, and in this case + refers recursively to the pattern in which it appears. Obviously, PCRE + cannot support the interpolation of Perl code. Instead, it supports + some special syntax for recursion of the entire pattern, and also for + individual subpattern recursion. + + The special item that consists of (? followed by a number greater than + zero and a closing parenthesis is a recursive call of the subpattern of + the given number, provided that it occurs inside that subpattern. (If + not, it is a "subroutine" call, which is described in the next sec- + tion.) The special item (?R) is a recursive call of the entire regular + expression. + + A recursive subpattern call is always treated as an atomic group. That + is, once it has matched some of the subject string, it is never re- + entered, even if it contains untried alternatives and there is a subse- + quent matching failure. + + This PCRE pattern solves the nested parentheses problem (assume the + PCRE_EXTENDED option is set so that white space is ignored): + + \( ( (?>[^()]+) | (?R) )* \) + + First it matches an opening parenthesis. Then it matches any number of + substrings which can either be a sequence of non-parentheses, or a + recursive match of the pattern itself (that is, a correctly parenthe- + sized substring). Finally there is a closing parenthesis. + + If this were part of a larger pattern, you would not want to recurse + the entire pattern, so instead you could use this: + + ( \( ( (?>[^()]+) | (?1) )* \) ) + + We have put the pattern into parentheses, and caused the recursion to + refer to them instead of the whole pattern. In a larger pattern, keep- + ing track of parenthesis numbers can be tricky. It may be more conve- + nient to use named parentheses instead. For this, PCRE uses (?P>name), + which is an extension to the Python syntax that PCRE uses for named + parentheses (Perl does not provide named parentheses). We could rewrite + the above example as follows: + + (?P \( ( (?>[^()]+) | (?P>pn) )* \) ) + + This particular example pattern contains nested unlimited repeats, and + so the use of atomic grouping for matching strings of non-parentheses + is important when applying the pattern to strings that do not match. + For example, when this pattern is applied to + + (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() + + it yields "no match" quickly. However, if atomic grouping is not used, + the match runs for a very long time indeed because there are so many + different ways the + and * repeats can carve up the subject, and all + have to be tested before failure can be reported. + + At the end of a match, the values set for any capturing subpatterns are + those from the outermost level of the recursion at which the subpattern + value is set. If you want to obtain intermediate values, a callout + function can be used (see the next section and the pcrecallout documen- + tation). If the pattern above is matched against + + (ab(cd)ef) + + the value for the capturing parentheses is "ef", which is the last + value taken on at the top level. If additional parentheses are added, + giving + + \( ( ( (?>[^()]+) | (?R) )* ) \) + ^ ^ + ^ ^ + + the string they capture is "ab(cd)ef", the contents of the top level + parentheses. If there are more than 15 capturing parentheses in a pat- + tern, PCRE has to obtain extra memory to store data during a recursion, + which it does by using pcre_malloc, freeing it via pcre_free after- + wards. If no memory can be obtained, the match fails with the + PCRE_ERROR_NOMEMORY error. + + Do not confuse the (?R) item with the condition (R), which tests for + recursion. Consider this pattern, which matches text in angle brack- + ets, allowing for arbitrary nesting. Only digits are allowed in nested + brackets (that is, when recursing), whereas any characters are permit- + ted at the outer level. + + < (?: (?(R) \d++ | [^<>]*+) | (?R)) * > + + In this pattern, (?(R) is the start of a conditional subpattern, with + two different alternatives for the recursive and non-recursive cases. + The (?R) item is the actual recursive call. + + +SUBPATTERNS AS SUBROUTINES + + If the syntax for a recursive subpattern reference (either by number or + by name) is used outside the parentheses to which it refers, it oper- + ates like a subroutine in a programming language. An earlier example + pointed out that the pattern + + (sens|respons)e and \1ibility + + matches "sense and sensibility" and "response and responsibility", but + not "sense and responsibility". If instead the pattern + + (sens|respons)e and (?1)ibility + + is used, it does match "sense and responsibility" as well as the other + two strings. Such references, if given numerically, must follow the + subpattern to which they refer. However, named references can refer to + later subpatterns. + + Like recursive subpatterns, a "subroutine" call is always treated as an + atomic group. That is, once it has matched some of the subject string, + it is never re-entered, even if it contains untried alternatives and + there is a subsequent matching failure. + + +CALLOUTS + + Perl has a feature whereby using the sequence (?{...}) causes arbitrary + Perl code to be obeyed in the middle of matching a regular expression. + This makes it possible, amongst other things, to extract different sub- + strings that match the same pair of parentheses when there is a repeti- + tion. + + PCRE provides a similar feature, but of course it cannot obey arbitrary + Perl code. The feature is called "callout". The caller of PCRE provides + an external function by putting its entry point in the global variable + pcre_callout. By default, this variable contains NULL, which disables + all calling out. + + Within a regular expression, (?C) indicates the points at which the + external function is to be called. If you want to identify different + callout points, you can put a number less than 256 after the letter C. + The default value is zero. For example, this pattern has two callout + points: + + (?C1)abc(?C2)def + + If the PCRE_AUTO_CALLOUT flag is passed to pcre_compile(), callouts are + automatically installed before each item in the pattern. They are all + numbered 255. + + During matching, when PCRE reaches a callout point (and pcre_callout is + set), the external function is called. It is provided with the number + of the callout, the position in the pattern, and, optionally, one item + of data originally supplied by the caller of pcre_exec(). The callout + function may cause matching to proceed, to backtrack, or to fail alto- + gether. A complete description of the interface to the callout function + is given in the pcrecallout documentation. + +Last updated: 06 June 2006 +Copyright (c) 1997-2006 University of Cambridge. +------------------------------------------------------------------------------ + + +PCREPARTIAL(3) PCREPARTIAL(3) + + +NAME + PCRE - Perl-compatible regular expressions + + +PARTIAL MATCHING IN PCRE + + In normal use of PCRE, if the subject string that is passed to + pcre_exec() or pcre_dfa_exec() matches as far as it goes, but is too + short to match the entire pattern, PCRE_ERROR_NOMATCH is returned. + There are circumstances where it might be helpful to distinguish this + case from other cases in which there is no match. + + Consider, for example, an application where a human is required to type + in data for a field with specific formatting requirements. An example + might be a date in the form ddmmmyy, defined by this pattern: + + ^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$ + + If the application sees the user's keystrokes one by one, and can check + that what has been typed so far is potentially valid, it is able to + raise an error as soon as a mistake is made, possibly beeping and not + reflecting the character that has been typed. This immediate feedback + is likely to be a better user interface than a check that is delayed + until the entire string has been entered. + + PCRE supports the concept of partial matching by means of the PCRE_PAR- + TIAL option, which can be set when calling pcre_exec() or + pcre_dfa_exec(). When this flag is set for pcre_exec(), the return code + PCRE_ERROR_NOMATCH is converted into PCRE_ERROR_PARTIAL if at any time + during the matching process the last part of the subject string matched + part of the pattern. Unfortunately, for non-anchored matching, it is + not possible to obtain the position of the start of the partial match. + No captured data is set when PCRE_ERROR_PARTIAL is returned. + + When PCRE_PARTIAL is set for pcre_dfa_exec(), the return code + PCRE_ERROR_NOMATCH is converted into PCRE_ERROR_PARTIAL if the end of + the subject is reached, there have been no complete matches, but there + is still at least one matching possibility. The portion of the string + that provided the partial match is set as the first matching string. + + Using PCRE_PARTIAL disables one of PCRE's optimizations. PCRE remembers + the last literal byte in a pattern, and abandons matching immediately + if such a byte is not present in the subject string. This optimization + cannot be used for a subject string that might match only partially. + + +RESTRICTED PATTERNS FOR PCRE_PARTIAL + + Because of the way certain internal optimizations are implemented in + the pcre_exec() function, the PCRE_PARTIAL option cannot be used with + all patterns. These restrictions do not apply when pcre_dfa_exec() is + used. For pcre_exec(), repeated single characters such as + + a{2,4} + + and repeated single metasequences such as + + \d+ + + are not permitted if the maximum number of occurrences is greater than + one. Optional items such as \d? (where the maximum is one) are permit- + ted. Quantifiers with any values are permitted after parentheses, so + the invalid examples above can be coded thus: + + (a){2,4} + (\d)+ + + These constructions run more slowly, but for the kinds of application + that are envisaged for this facility, this is not felt to be a major + restriction. + + If PCRE_PARTIAL is set for a pattern that does not conform to the + restrictions, pcre_exec() returns the error code PCRE_ERROR_BADPARTIAL + (-13). + + +EXAMPLE OF PARTIAL MATCHING USING PCRETEST + + If the escape sequence \P is present in a pcretest data line, the + PCRE_PARTIAL flag is used for the match. Here is a run of pcretest that + uses the date example quoted above: + + re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ + data> 25jun04\P + 0: 25jun04 + 1: jun + data> 25dec3\P + Partial match + data> 3ju\P + Partial match + data> 3juj\P + No match + data> j\P + No match + + The first data string is matched completely, so pcretest shows the + matched substrings. The remaining four strings do not match the com- + plete pattern, but the first two are partial matches. The same test, + using DFA matching (by means of the \D escape sequence), produces the + following output: + + re> /^?(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)$/ + data> 25jun04\P\D + 0: 25jun04 + data> 23dec3\P\D + Partial match: 23dec3 + data> 3ju\P\D + Partial match: 3ju + data> 3juj\P\D + No match + data> j\P\D + No match + + Notice that in this case the portion of the string that was matched is + made available. + + +MULTI-SEGMENT MATCHING WITH pcre_dfa_exec() + + When a partial match has been found using pcre_dfa_exec(), it is possi- + ble to continue the match by providing additional subject data and + calling pcre_dfa_exec() again with the PCRE_DFA_RESTART option and the + same working space (where details of the previous partial match are + stored). Here is an example using pcretest, where the \R escape + sequence sets the PCRE_DFA_RESTART option and the \D escape sequence + requests the use of pcre_dfa_exec(): + + re> /^?(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)$/ + data> 23ja\P\D + Partial match: 23ja + data> n05\R\D + 0: n05 + + The first call has "23ja" as the subject, and requests partial match- + ing; the second call has "n05" as the subject for the continued + (restarted) match. Notice that when the match is complete, only the + last part is shown; PCRE does not retain the previously partially- + matched string. It is up to the calling program to do that if it needs + to. + + This facility can be used to pass very long subject strings to + pcre_dfa_exec(). However, some care is needed for certain types of pat- + tern. + + 1. If the pattern contains tests for the beginning or end of a line, + you need to pass the PCRE_NOTBOL or PCRE_NOTEOL options, as appropri- + ate, when the subject string for any call does not contain the begin- + ning or end of a line. + + 2. If the pattern contains backward assertions (including \b or \B), + you need to arrange for some overlap in the subject strings to allow + for this. For example, you could pass the subject in chunks that were + 500 bytes long, but in a buffer of 700 bytes, with the starting offset + set to 200 and the previous 200 bytes at the start of the buffer. + + 3. Matching a subject string that is split into multiple segments does + not always produce exactly the same result as matching over one single + long string. The difference arises when there are multiple matching + possibilities, because a partial match result is given only when there + are no completed matches in a call to fBpcre_dfa_exec(). This means + that as soon as the shortest match has been found, continuation to a + new subject segment is no longer possible. Consider this pcretest + example: + + re> /dog(sbody)?/ + data> do\P\D + Partial match: do + data> gsb\R\P\D + 0: g + data> dogsbody\D + 0: dogsbody + 1: dog + + The pattern matches the words "dog" or "dogsbody". When the subject is + presented in several parts ("do" and "gsb" being the first two) the + match stops when "dog" has been found, and it is not possible to con- + tinue. On the other hand, if "dogsbody" is presented as a single + string, both matches are found. + + Because of this phenomenon, it does not usually make sense to end a + pattern that is going to be matched in this way with a variable repeat. + + 4. Patterns that contain alternatives at the top level which do not all + start with the same pattern item may not work as expected. For example, + consider this pattern: + + 1234|3789 + + If the first part of the subject is "ABC123", a partial match of the + first alternative is found at offset 3. There is no partial match for + the second alternative, because such a match does not start at the same + point in the subject string. Attempting to continue with the string + "789" does not yield a match because only those alternatives that match + at one point in the subject are remembered. The problem arises because + the start of the second alternative matches within the first alterna- + tive. There is no problem with anchored patterns or patterns such as: + + 1234|ABCD + + where no string can be a partial match for both alternatives. + +Last updated: 16 January 2006 +Copyright (c) 1997-2006 University of Cambridge. +------------------------------------------------------------------------------ + + +PCREPRECOMPILE(3) PCREPRECOMPILE(3) + + +NAME + PCRE - Perl-compatible regular expressions + + +SAVING AND RE-USING PRECOMPILED PCRE PATTERNS + + If you are running an application that uses a large number of regular + expression patterns, it may be useful to store them in a precompiled + form instead of having to compile them every time the application is + run. If you are not using any private character tables (see the + pcre_maketables() documentation), this is relatively straightforward. + If you are using private tables, it is a little bit more complicated. + + If you save compiled patterns to a file, you can copy them to a differ- + ent host and run them there. This works even if the new host has the + opposite endianness to the one on which the patterns were compiled. + There may be a small performance penalty, but it should be insignifi- + cant. + + +SAVING A COMPILED PATTERN + The value returned by pcre_compile() points to a single block of memory + that holds the compiled pattern and associated data. You can find the + length of this block in bytes by calling pcre_fullinfo() with an argu- + ment of PCRE_INFO_SIZE. You can then save the data in any appropriate + manner. Here is sample code that compiles a pattern and writes it to a + file. It assumes that the variable fd refers to a file that is open for + output: + + int erroroffset, rc, size; + char *error; + pcre *re; + + re = pcre_compile("my pattern", 0, &error, &erroroffset, NULL); + if (re == NULL) { ... handle errors ... } + rc = pcre_fullinfo(re, NULL, PCRE_INFO_SIZE, &size); + if (rc < 0) { ... handle errors ... } + rc = fwrite(re, 1, size, fd); + if (rc != size) { ... handle errors ... } + + In this example, the bytes that comprise the compiled pattern are + copied exactly. Note that this is binary data that may contain any of + the 256 possible byte values. On systems that make a distinction + between binary and non-binary data, be sure that the file is opened for + binary output. + + If you want to write more than one pattern to a file, you will have to + devise a way of separating them. For binary data, preceding each pat- + tern with its length is probably the most straightforward approach. + Another possibility is to write out the data in hexadecimal instead of + binary, one pattern to a line. + + Saving compiled patterns in a file is only one possible way of storing + them for later use. They could equally well be saved in a database, or + in the memory of some daemon process that passes them via sockets to + the processes that want them. + + If the pattern has been studied, it is also possible to save the study + data in a similar way to the compiled pattern itself. When studying + generates additional information, pcre_study() returns a pointer to a + pcre_extra data block. Its format is defined in the section on matching + a pattern in the pcreapi documentation. The study_data field points to + the binary study data, and this is what you must save (not the + pcre_extra block itself). The length of the study data can be obtained + by calling pcre_fullinfo() with an argument of PCRE_INFO_STUDYSIZE. + Remember to check that pcre_study() did return a non-NULL value before + trying to save the study data. + + +RE-USING A PRECOMPILED PATTERN + + Re-using a precompiled pattern is straightforward. Having reloaded it + into main memory, you pass its pointer to pcre_exec() or + pcre_dfa_exec() in the usual way. This should work even on another + host, and even if that host has the opposite endianness to the one + where the pattern was compiled. + + However, if you passed a pointer to custom character tables when the + pattern was compiled (the tableptr argument of pcre_compile()), you + must now pass a similar pointer to pcre_exec() or pcre_dfa_exec(), + because the value saved with the compiled pattern will obviously be + nonsense. A field in a pcre_extra() block is used to pass this data, as + described in the section on matching a pattern in the pcreapi documen- + tation. + + If you did not provide custom character tables when the pattern was + compiled, the pointer in the compiled pattern is NULL, which causes + pcre_exec() to use PCRE's internal tables. Thus, you do not need to + take any special action at run time in this case. + + If you saved study data with the compiled pattern, you need to create + your own pcre_extra data block and set the study_data field to point to + the reloaded study data. You must also set the PCRE_EXTRA_STUDY_DATA + bit in the flags field to indicate that study data is present. Then + pass the pcre_extra block to pcre_exec() or pcre_dfa_exec() in the + usual way. + + +COMPATIBILITY WITH DIFFERENT PCRE RELEASES + + The layout of the control block that is at the start of the data that + makes up a compiled pattern was changed for release 5.0. If you have + any saved patterns that were compiled with previous releases (not a + facility that was previously advertised), you will have to recompile + them for release 5.0. However, from now on, it should be possible to + make changes in a compatible manner. + + Notwithstanding the above, if you have any saved patterns in UTF-8 mode + that use \p or \P that were compiled with any release up to and includ- + ing 6.4, you will have to recompile them for release 6.5 and above. + +Last updated: 01 February 2006 +Copyright (c) 1997-2006 University of Cambridge. +------------------------------------------------------------------------------ + + +PCREPERFORM(3) PCREPERFORM(3) + + +NAME + PCRE - Perl-compatible regular expressions + + +PCRE PERFORMANCE + + Certain items that may appear in regular expression patterns are more + efficient than others. It is more efficient to use a character class + like [aeiou] than a set of alternatives such as (a|e|i|o|u). In gen- + eral, the simplest construction that provides the required behaviour is + usually the most efficient. Jeffrey Friedl's book contains a lot of + useful general discussion about optimizing regular expressions for + efficient performance. This document contains a few observations about + PCRE. + + Using Unicode character properties (the \p, \P, and \X escapes) is + slow, because PCRE has to scan a structure that contains data for over + fifteen thousand characters whenever it needs a character's property. + If you can find an alternative pattern that does not use character + properties, it will probably be faster. + + When a pattern begins with .* not in parentheses, or in parentheses + that are not the subject of a backreference, and the PCRE_DOTALL option + is set, the pattern is implicitly anchored by PCRE, since it can match + only at the start of a subject string. However, if PCRE_DOTALL is not + set, PCRE cannot make this optimization, because the . metacharacter + does not then match a newline, and if the subject string contains new- + lines, the pattern may match from the character immediately following + one of them instead of from the very start. For example, the pattern + + .*second + + matches the subject "first\nand second" (where \n stands for a newline + character), with the match starting at the seventh character. In order + to do this, PCRE has to retry the match starting after every newline in + the subject. + + If you are using such a pattern with subject strings that do not con- + tain newlines, the best performance is obtained by setting PCRE_DOTALL, + or starting the pattern with ^.* or ^.*? to indicate explicit anchor- + ing. That saves PCRE from having to scan along the subject looking for + a newline to restart at. + + Beware of patterns that contain nested indefinite repeats. These can + take a long time to run when applied to a string that does not match. + Consider the pattern fragment + + (a+)* + + This can match "aaaa" in 33 different ways, and this number increases + very rapidly as the string gets longer. (The * repeat can match 0, 1, + 2, 3, or 4 times, and for each of those cases other than 0, the + + repeats can match different numbers of times.) When the remainder of + the pattern is such that the entire match is going to fail, PCRE has in + principle to try every possible variation, and this can take an + extremely long time. + + An optimization catches some of the more simple cases such as + + (a+)*b + + where a literal character follows. Before embarking on the standard + matching procedure, PCRE checks that there is a "b" later in the sub- + ject string, and if there is not, it fails the match immediately. How- + ever, when there is no following literal this optimization cannot be + used. You can see the difference by comparing the behaviour of + + (a+)*\d + + with the pattern above. The former gives a failure almost instantly + when applied to a whole line of "a" characters, whereas the latter + takes an appreciable time with strings longer than about 20 characters. + + In many cases, the solution to this kind of performance issue is to use + an atomic group or a possessive quantifier. + +Last updated: 28 February 2005 +Copyright (c) 1997-2005 University of Cambridge. +------------------------------------------------------------------------------ + + +PCREPOSIX(3) PCREPOSIX(3) + + +NAME + PCRE - Perl-compatible regular expressions. + + +SYNOPSIS OF POSIX API + + #include + + int regcomp(regex_t *preg, const char *pattern, + int cflags); + + int regexec(regex_t *preg, const char *string, + size_t nmatch, regmatch_t pmatch[], int eflags); + + size_t regerror(int errcode, const regex_t *preg, + char *errbuf, size_t errbuf_size); + + void regfree(regex_t *preg); + + +DESCRIPTION + + This set of functions provides a POSIX-style API to the PCRE regular + expression package. See the pcreapi documentation for a description of + PCRE's native API, which contains much additional functionality. + + The functions described here are just wrapper functions that ultimately + call the PCRE native API. Their prototypes are defined in the + pcreposix.h header file, and on Unix systems the library itself is + called pcreposix.a, so can be accessed by adding -lpcreposix to the + command for linking an application that uses them. Because the POSIX + functions call the native ones, it is also necessary to add -lpcre. + + I have implemented only those option bits that can be reasonably mapped + to PCRE native options. In addition, the option REG_EXTENDED is defined + with the value zero. This has no effect, but since programs that are + written to the POSIX interface often use it, this makes it easier to + slot in PCRE as a replacement library. Other POSIX options are not even + defined. + + When PCRE is called via these functions, it is only the API that is + POSIX-like in style. The syntax and semantics of the regular expres- + sions themselves are still those of Perl, subject to the setting of + various PCRE options, as described below. "POSIX-like in style" means + that the API approximates to the POSIX definition; it is not fully + POSIX-compatible, and in multi-byte encoding domains it is probably + even less compatible. + + The header for these functions is supplied as pcreposix.h to avoid any + potential clash with other POSIX libraries. It can, of course, be + renamed or aliased as regex.h, which is the "correct" name. It provides + two structure types, regex_t for compiled internal forms, and reg- + match_t for returning captured substrings. It also defines some con- + stants whose names start with "REG_"; these are used for setting + options and identifying error codes. + + +COMPILING A PATTERN + + The function regcomp() is called to compile a pattern into an internal + form. The pattern is a C string terminated by a binary zero, and is + passed in the argument pattern. The preg argument is a pointer to a + regex_t structure that is used as a base for storing information about + the compiled regular expression. + + The argument cflags is either zero, or contains one or more of the bits + defined by the following macros: + + REG_DOTALL + + The PCRE_DOTALL option is set when the regular expression is passed for + compilation to the native function. Note that REG_DOTALL is not part of + the POSIX standard. + + REG_ICASE + + The PCRE_CASELESS option is set when the regular expression is passed + for compilation to the native function. + + REG_NEWLINE + + The PCRE_MULTILINE option is set when the regular expression is passed + for compilation to the native function. Note that this does not mimic + the defined POSIX behaviour for REG_NEWLINE (see the following sec- + tion). + + REG_NOSUB + + The PCRE_NO_AUTO_CAPTURE option is set when the regular expression is + passed for compilation to the native function. In addition, when a pat- + tern that is compiled with this flag is passed to regexec() for match- + ing, the nmatch and pmatch arguments are ignored, and no captured + strings are returned. + + REG_UTF8 + + The PCRE_UTF8 option is set when the regular expression is passed for + compilation to the native function. This causes the pattern itself and + all data strings used for matching it to be treated as UTF-8 strings. + Note that REG_UTF8 is not part of the POSIX standard. + + In the absence of these flags, no options are passed to the native + function. This means the the regex is compiled with PCRE default + semantics. In particular, the way it handles newline characters in the + subject string is the Perl way, not the POSIX way. Note that setting + PCRE_MULTILINE has only some of the effects specified for REG_NEWLINE. + It does not affect the way newlines are matched by . (they aren't) or + by a negative class such as [^a] (they are). + + The yield of regcomp() is zero on success, and non-zero otherwise. The + preg structure is filled in on success, and one member of the structure + is public: re_nsub contains the number of capturing subpatterns in the + regular expression. Various error codes are defined in the header file. + + +MATCHING NEWLINE CHARACTERS + + This area is not simple, because POSIX and Perl take different views of + things. It is not possible to get PCRE to obey POSIX semantics, but + then PCRE was never intended to be a POSIX engine. The following table + lists the different possibilities for matching newline characters in + PCRE: + + Default Change with + + . matches newline no PCRE_DOTALL + newline matches [^a] yes not changeable + $ matches \n at end yes PCRE_DOLLARENDONLY + $ matches \n in middle no PCRE_MULTILINE + ^ matches \n in middle no PCRE_MULTILINE + + This is the equivalent table for POSIX: + + Default Change with + + . matches newline yes REG_NEWLINE + newline matches [^a] yes REG_NEWLINE + $ matches \n at end no REG_NEWLINE + $ matches \n in middle no REG_NEWLINE + ^ matches \n in middle no REG_NEWLINE + + PCRE's behaviour is the same as Perl's, except that there is no equiva- + lent for PCRE_DOLLAR_ENDONLY in Perl. In both PCRE and Perl, there is + no way to stop newline from matching [^a]. + + The default POSIX newline handling can be obtained by setting + PCRE_DOTALL and PCRE_DOLLAR_ENDONLY, but there is no way to make PCRE + behave exactly as for the REG_NEWLINE action. + + +MATCHING A PATTERN + + The function regexec() is called to match a compiled pattern preg + against a given string, which is terminated by a zero byte, subject to + the options in eflags. These can be: + + REG_NOTBOL + + The PCRE_NOTBOL option is set when calling the underlying PCRE matching + function. + + REG_NOTEOL + + The PCRE_NOTEOL option is set when calling the underlying PCRE matching + function. + + If the pattern was compiled with the REG_NOSUB flag, no data about any + matched strings is returned. The nmatch and pmatch arguments of + regexec() are ignored. + + Otherwise,the portion of the string that was matched, and also any cap- + tured substrings, are returned via the pmatch argument, which points to + an array of nmatch structures of type regmatch_t, containing the mem- + bers rm_so and rm_eo. These contain the offset to the first character + of each substring and the offset to the first character after the end + of each substring, respectively. The 0th element of the vector relates + to the entire portion of string that was matched; subsequent elements + relate to the capturing subpatterns of the regular expression. Unused + entries in the array have both structure members set to -1. + + A successful match yields a zero return; various error codes are + defined in the header file, of which REG_NOMATCH is the "expected" + failure code. + + +ERROR MESSAGES + + The regerror() function maps a non-zero errorcode from either regcomp() + or regexec() to a printable message. If preg is not NULL, the error + should have arisen from the use of that structure. A message terminated + by a binary zero is placed in errbuf. The length of the message, + including the zero, is limited to errbuf_size. The yield of the func- + tion is the size of buffer needed to hold the whole message. + + +MEMORY USAGE + + Compiling a regular expression causes memory to be allocated and asso- + ciated with the preg structure. The function regfree() frees all such + memory, after which preg may no longer be used as a compiled expres- + sion. + + +AUTHOR + + Philip Hazel + University Computing Service, + Cambridge CB2 3QG, England. + +Last updated: 16 January 2006 +Copyright (c) 1997-2006 University of Cambridge. +------------------------------------------------------------------------------ + + +PCRECPP(3) PCRECPP(3) + + +NAME + PCRE - Perl-compatible regular expressions. + + +SYNOPSIS OF C++ WRAPPER + + #include + + +DESCRIPTION + + The C++ wrapper for PCRE was provided by Google Inc. Some additional + functionality was added by Giuseppe Maxia. This brief man page was con- + structed from the notes in the pcrecpp.h file, which should be con- + sulted for further details. + + +MATCHING INTERFACE + + The "FullMatch" operation checks that supplied text matches a supplied + pattern exactly. If pointer arguments are supplied, it copies matched + sub-strings that match sub-patterns into them. + + Example: successful match + pcrecpp::RE re("h.*o"); + re.FullMatch("hello"); + + Example: unsuccessful match (requires full match): + pcrecpp::RE re("e"); + !re.FullMatch("hello"); + + Example: creating a temporary RE object: + pcrecpp::RE("h.*o").FullMatch("hello"); + + You can pass in a "const char*" or a "string" for "text". The examples + below tend to use a const char*. You can, as in the different examples + above, store the RE object explicitly in a variable or use a temporary + RE object. The examples below use one mode or the other arbitrarily. + Either could correctly be used for any of these examples. + + You must supply extra pointer arguments to extract matched subpieces. + + Example: extracts "ruby" into "s" and 1234 into "i" + int i; + string s; + pcrecpp::RE re("(\\w+):(\\d+)"); + re.FullMatch("ruby:1234", &s, &i); + + Example: does not try to extract any extra sub-patterns + re.FullMatch("ruby:1234", &s); + + Example: does not try to extract into NULL + re.FullMatch("ruby:1234", NULL, &i); + + Example: integer overflow causes failure + !re.FullMatch("ruby:1234567891234", NULL, &i); + + Example: fails because there aren't enough sub-patterns: + !pcrecpp::RE("\\w+:\\d+").FullMatch("ruby:1234", &s); + + Example: fails because string cannot be stored in integer + !pcrecpp::RE("(.*)").FullMatch("ruby", &i); + + The provided pointer arguments can be pointers to any scalar numeric + type, or one of: + + string (matched piece is copied to string) + StringPiece (StringPiece is mutated to point to matched piece) + T (where "bool T::ParseFrom(const char*, int)" exists) + NULL (the corresponding matched sub-pattern is not copied) + + The function returns true iff all of the following conditions are sat- + isfied: + + a. "text" matches "pattern" exactly; + + b. The number of matched sub-patterns is >= number of supplied + pointers; + + c. The "i"th argument has a suitable type for holding the + string captured as the "i"th sub-pattern. If you pass in + NULL for the "i"th argument, or pass fewer arguments than + number of sub-patterns, "i"th captured sub-pattern is + ignored. + + The matching interface supports at most 16 arguments per call. If you + need more, consider using the more general interface + pcrecpp::RE::DoMatch. See pcrecpp.h for the signature for DoMatch. + + +PARTIAL MATCHES + + You can use the "PartialMatch" operation when you want the pattern to + match any substring of the text. + + Example: simple search for a string: + pcrecpp::RE("ell").PartialMatch("hello"); + + Example: find first number in a string: + int number; + pcrecpp::RE re("(\\d+)"); + re.PartialMatch("x*100 + 20", &number); + assert(number == 100); + + +UTF-8 AND THE MATCHING INTERFACE + + By default, pattern and text are plain text, one byte per character. + The UTF8 flag, passed to the constructor, causes both pattern and + string to be treated as UTF-8 text, still a byte stream but potentially + multiple bytes per character. In practice, the text is likelier to be + UTF-8 than the pattern, but the match returned may depend on the UTF8 + flag, so always use it when matching UTF8 text. For example, "." will + match one byte normally but with UTF8 set may match up to three bytes + of a multi-byte character. + + Example: + pcrecpp::RE_Options options; + options.set_utf8(); + pcrecpp::RE re(utf8_pattern, options); + re.FullMatch(utf8_string); + + Example: using the convenience function UTF8(): + pcrecpp::RE re(utf8_pattern, pcrecpp::UTF8()); + re.FullMatch(utf8_string); + + NOTE: The UTF8 flag is ignored if pcre was not configured with the + --enable-utf8 flag. + + +PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE + + PCRE defines some modifiers to change the behavior of the regular + expression engine. The C++ wrapper defines an auxiliary class, + RE_Options, as a vehicle to pass such modifiers to a RE class. Cur- + rently, the following modifiers are supported: + + modifier description Perl corresponding + + PCRE_CASELESS case insensitive match /i + PCRE_MULTILINE multiple lines match /m + PCRE_DOTALL dot matches newlines /s + PCRE_DOLLAR_ENDONLY $ matches only at end N/A + PCRE_EXTRA strict escape parsing N/A + PCRE_EXTENDED ignore whitespaces /x + PCRE_UTF8 handles UTF8 chars built-in + PCRE_UNGREEDY reverses * and *? N/A + PCRE_NO_AUTO_CAPTURE disables capturing parens N/A (*) + + (*) Both Perl and PCRE allow non capturing parentheses by means of the + "?:" modifier within the pattern itself. e.g. (?:ab|cd) does not cap- + ture, while (ab|cd) does. + + For a full account on how each modifier works, please check the PCRE + API reference page. + + For each modifier, there are two member functions whose name is made + out of the modifier in lowercase, without the "PCRE_" prefix. For + instance, PCRE_CASELESS is handled by + + bool caseless() + + which returns true if the modifier is set, and + + RE_Options & set_caseless(bool) + + which sets or unsets the modifier. Moreover, PCRE_EXTRA_MATCH_LIMIT can + be accessed through the set_match_limit() and match_limit() member + functions. Setting match_limit to a non-zero value will limit the exe- + cution of pcre to keep it from doing bad things like blowing the stack + or taking an eternity to return a result. A value of 5000 is good + enough to stop stack blowup in a 2MB thread stack. Setting match_limit + to zero disables match limiting. Alternatively, you can call + match_limit_recursion() which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION to + limit how much PCRE recurses. match_limit() limits the number of + matches PCRE does; match_limit_recursion() limits the depth of internal + recursion, and therefore the amount of stack that is used. + + Normally, to pass one or more modifiers to a RE class, you declare a + RE_Options object, set the appropriate options, and pass this object to + a RE constructor. Example: + + RE_options opt; + opt.set_caseless(true); + if (RE("HELLO", opt).PartialMatch("hello world")) ... + + RE_options has two constructors. The default constructor takes no argu- + ments and creates a set of flags that are off by default. The optional + parameter option_flags is to facilitate transfer of legacy code from C + programs. This lets you do + + RE(pattern, + RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str); + + However, new code is better off doing + + RE(pattern, + RE_Options().set_caseless(true).set_multiline(true)) + .PartialMatch(str); + + If you are going to pass one of the most used modifiers, there are some + convenience functions that return a RE_Options class with the appropri- + ate modifier already set: CASELESS(), UTF8(), MULTILINE(), DOTALL(), + and EXTENDED(). + + If you need to set several options at once, and you don't want to go + through the pains of declaring a RE_Options object and setting several + options, there is a parallel method that give you such ability on the + fly. You can concatenate several set_xxxxx() member functions, since + each of them returns a reference to its class object. For example, to + pass PCRE_CASELESS, PCRE_EXTENDED, and PCRE_MULTILINE to a RE with one + statement, you may write: + + RE(" ^ xyz \\s+ .* blah$", + RE_Options() + .set_caseless(true) + .set_extended(true) + .set_multiline(true)).PartialMatch(sometext); + + +SCANNING TEXT INCREMENTALLY + + The "Consume" operation may be useful if you want to repeatedly match + regular expressions at the front of a string and skip over them as they + match. This requires use of the "StringPiece" type, which represents a + sub-range of a real string. Like RE, StringPiece is defined in the + pcrecpp namespace. + + Example: read lines of the form "var = value" from a string. + string contents = ...; // Fill string somehow + pcrecpp::StringPiece input(contents); // Wrap in a StringPiece + + string var; + int value; + pcrecpp::RE re("(\\w+) = (\\d+)\n"); + while (re.Consume(&input, &var, &value)) { + ...; + } + + Each successful call to "Consume" will set "var/value", and also + advance "input" so it points past the matched text. + + The "FindAndConsume" operation is similar to "Consume" but does not + anchor your match at the beginning of the string. For example, you + could extract all words from a string by repeatedly calling + + pcrecpp::RE("(\\w+)").FindAndConsume(&input, &word) + + +PARSING HEX/OCTAL/C-RADIX NUMBERS + + By default, if you pass a pointer to a numeric value, the corresponding + text is interpreted as a base-10 number. You can instead wrap the + pointer with a call to one of the operators Hex(), Octal(), or CRadix() + to interpret the text in another base. The CRadix operator interprets + C-style "0" (base-8) and "0x" (base-16) prefixes, but defaults to + base-10. + + Example: + int a, b, c, d; + pcrecpp::RE re("(.*) (.*) (.*) (.*)"); + re.FullMatch("100 40 0100 0x40", + pcrecpp::Octal(&a), pcrecpp::Hex(&b), + pcrecpp::CRadix(&c), pcrecpp::CRadix(&d)); + + will leave 64 in a, b, c, and d. + + +REPLACING PARTS OF STRINGS + + You can replace the first match of "pattern" in "str" with "rewrite". + Within "rewrite", backslash-escaped digits (\1 to \9) can be used to + insert text matching corresponding parenthesized group from the pat- + tern. \0 in "rewrite" refers to the entire matching text. For example: + + string s = "yabba dabba doo"; + pcrecpp::RE("b+").Replace("d", &s); + + will leave "s" containing "yada dabba doo". The result is true if the + pattern matches and a replacement occurs, false otherwise. + + GlobalReplace is like Replace except that it replaces all occurrences + of the pattern in the string with the rewrite. Replacements are not + subject to re-matching. For example: + + string s = "yabba dabba doo"; + pcrecpp::RE("b+").GlobalReplace("d", &s); + + will leave "s" containing "yada dada doo". It returns the number of + replacements made. + + Extract is like Replace, except that if the pattern matches, "rewrite" + is copied into "out" (an additional argument) with substitutions. The + non-matching portions of "text" are ignored. Returns true iff a match + occurred and the extraction happened successfully; if no match occurs, + the string is left unaffected. + + +AUTHOR + + The C++ wrapper was contributed by Google Inc. + Copyright (c) 2005 Google Inc. +------------------------------------------------------------------------------ + + +PCRESAMPLE(3) PCRESAMPLE(3) + + +NAME + PCRE - Perl-compatible regular expressions + + +PCRE SAMPLE PROGRAM + + A simple, complete demonstration program, to get you started with using + PCRE, is supplied in the file pcredemo.c in the PCRE distribution. + + The program compiles the regular expression that is its first argument, + and matches it against the subject string in its second argument. No + PCRE options are set, and default character tables are used. If match- + ing succeeds, the program outputs the portion of the subject that + matched, together with the contents of any captured substrings. + + If the -g option is given on the command line, the program then goes on + to check for further matches of the same regular expression in the same + subject string. The logic is a little bit tricky because of the possi- + bility of matching an empty string. Comments in the code explain what + is going on. + + If PCRE is installed in the standard include and library directories + for your system, you should be able to compile the demonstration pro- + gram using this command: + + gcc -o pcredemo pcredemo.c -lpcre + + If PCRE is installed elsewhere, you may need to add additional options + to the command line. For example, on a Unix-like system that has PCRE + installed in /usr/local, you can compile the demonstration program + using a command like this: + + gcc -o pcredemo -I/usr/local/include pcredemo.c \ + -L/usr/local/lib -lpcre + + Once you have compiled the demonstration program, you can run simple + tests like this: + + ./pcredemo 'cat|dog' 'the cat sat on the mat' + ./pcredemo -g 'cat|dog' 'the dog sat on the cat' + + Note that there is a much more comprehensive test program, called + pcretest, which supports many more facilities for testing regular + expressions and the PCRE library. The pcredemo program is provided as a + simple coding example. + + On some operating systems (e.g. Solaris), when PCRE is not installed in + the standard library directory, you may get an error like this when you + try to run pcredemo: + + ld.so.1: a.out: fatal: libpcre.so.0: open failed: No such file or + directory + + This is caused by the way shared library support works on those sys- + tems. You need to add + + -R/usr/local/lib + + (for example) to the compile command to get round this problem. + +Last updated: 09 September 2004 +Copyright (c) 1997-2004 University of Cambridge. +------------------------------------------------------------------------------ +PCRESTACK(3) PCRESTACK(3) + + +NAME + PCRE - Perl-compatible regular expressions + + +PCRE DISCUSSION OF STACK USAGE + + When you call pcre_exec(), it makes use of an internal function called + match(). This calls itself recursively at branch points in the pattern, + in order to remember the state of the match so that it can back up and + try a different alternative if the first one fails. As matching pro- + ceeds deeper and deeper into the tree of possibilities, the recursion + depth increases. + + Not all calls of match() increase the recursion depth; for an item such + as a* it may be called several times at the same level, after matching + different numbers of a's. Furthermore, in a number of cases where the + result of the recursive call would immediately be passed back as the + result of the current call (a "tail recursion"), the function is just + restarted instead. + + The pcre_dfa_exec() function operates in an entirely different way, and + hardly uses recursion at all. The limit on its complexity is the amount + of workspace it is given. The comments that follow do NOT apply to + pcre_dfa_exec(); they are relevant only for pcre_exec(). + + You can set limits on the number of times that match() is called, both + in total and recursively. If the limit is exceeded, an error occurs. + For details, see the section on extra data for pcre_exec() in the + pcreapi documentation. + + Each time that match() is actually called recursively, it uses memory + from the process stack. For certain kinds of pattern and data, very + large amounts of stack may be needed, despite the recognition of "tail + recursion". You can often reduce the amount of recursion, and there- + fore the amount of stack used, by modifying the pattern that is being + matched. Consider, for example, this pattern: + + ([^<]|<(?!inet))+ + + It matches from wherever it starts until it encounters " +.PP +.SM +.br +.B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP, +.ti +5n +.B const char **\fIerrptr\fP, int *\fIerroffset\fP, +.ti +5n +.B const unsigned char *\fItableptr\fP); +. +.SH DESCRIPTION +.rs +.sp +This function compiles a regular expression into an internal form. Its +arguments are: +.sp + \fIpattern\fR A zero-terminated string containing the + regular expression to be compiled + \fIoptions\fR Zero or more option bits + \fIerrptr\fR Where to put an error message + \fIerroffset\fR Offset in pattern where error was found + \fItableptr\fR Pointer to character tables, or NULL to + use the built-in default +.sp +The option bits are: +.sp + PCRE_ANCHORED Force pattern anchoring + PCRE_AUTO_CALLOUT Compile automatic callouts + PCRE_CASELESS Do caseless matching + PCRE_DOLLAR_ENDONLY $ not to match newline at end + PCRE_DOTALL . matches anything including NL + PCRE_DUPNAMES Allow duplicate names for subpatterns + PCRE_EXTENDED Ignore whitespace and # comments + PCRE_EXTRA PCRE extra features + (not much use currently) + PCRE_FIRSTLINE Force matching to be before newline + PCRE_MULTILINE ^ and $ match newlines within data + PCRE_NEWLINE_CR Set CR as the newline sequence + PCRE_NEWLINE_CRLF Set CRLF as the newline sequence + PCRE_NEWLINE_LF Set LF as the newline sequence + PCRE_NO_AUTO_CAPTURE Disable numbered capturing paren- + theses (named ones available) + PCRE_UNGREEDY Invert greediness of quantifiers + PCRE_UTF8 Run in UTF-8 mode + PCRE_NO_UTF8_CHECK Do not check the pattern for UTF-8 + validity (only relevant if + PCRE_UTF8 is set) +.sp +PCRE must be built with UTF-8 support in order to use PCRE_UTF8 and +PCRE_NO_UTF8_CHECK. +.P +The yield of the function is a pointer to a private data structure that +contains the compiled pattern, or NULL if an error was detected. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fR +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fR +.\" +page. diff --git a/libs/pcre/doc/pcre_compile2.3 b/libs/pcre/doc/pcre_compile2.3 new file mode 100644 index 0000000000..26887855ef --- /dev/null +++ b/libs/pcre/doc/pcre_compile2.3 @@ -0,0 +1,74 @@ +.TH PCRE_COMPILE2 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include +.PP +.SM +.br +.B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP, +.ti +5n +.B int *\fIerrorcodeptr\fP, +.ti +5n +.B const char **\fIerrptr\fP, int *\fIerroffset\fP, +.ti +5n +.B const unsigned char *\fItableptr\fP); +. +.SH DESCRIPTION +.rs +.sp +This function compiles a regular expression into an internal form. It is the +same as \fBpcre_compile()\fP, except for the addition of the \fIerrorcodeptr\fP +argument. The arguments are: + +.sp + \fIpattern\fR A zero-terminated string containing the + regular expression to be compiled + \fIoptions\fR Zero or more option bits + \fIerrorcodeptr\fP Where to put an error code + \fIerrptr\fR Where to put an error message + \fIerroffset\fR Offset in pattern where error was found + \fItableptr\fR Pointer to character tables, or NULL to + use the built-in default +.sp +The option bits are: +.sp + PCRE_ANCHORED Force pattern anchoring + PCRE_AUTO_CALLOUT Compile automatic callouts + PCRE_CASELESS Do caseless matching + PCRE_DOLLAR_ENDONLY $ not to match newline at end + PCRE_DOTALL . matches anything including NL + PCRE_DUPNAMES Allow duplicate names for subpatterns + PCRE_EXTENDED Ignore whitespace and # comments + PCRE_EXTRA PCRE extra features + (not much use currently) + PCRE_FIRSTLINE Force matching to be before newline + PCRE_MULTILINE ^ and $ match newlines within data + PCRE_NEWLINE_CR Set CR as the newline sequence + PCRE_NEWLINE_CRLF Set CRLF as the newline sequence + PCRE_NEWLINE_LF Set LF as the newline sequence + PCRE_NO_AUTO_CAPTURE Disable numbered capturing paren- + theses (named ones available) + PCRE_UNGREEDY Invert greediness of quantifiers + PCRE_UTF8 Run in UTF-8 mode + PCRE_NO_UTF8_CHECK Do not check the pattern for UTF-8 + validity (only relevant if + PCRE_UTF8 is set) +.sp +PCRE must be built with UTF-8 support in order to use PCRE_UTF8 and +PCRE_NO_UTF8_CHECK. +.P +The yield of the function is a pointer to a private data structure that +contains the compiled pattern, or NULL if an error was detected. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fR +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fR +.\" +page. diff --git a/libs/pcre/doc/pcre_config.3 b/libs/pcre/doc/pcre_config.3 new file mode 100644 index 0000000000..03a27e82b5 --- /dev/null +++ b/libs/pcre/doc/pcre_config.3 @@ -0,0 +1,50 @@ +.TH PCRE_CONFIG 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include +.PP +.SM +.br +.B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP); +. +.SH DESCRIPTION +.rs +.sp +This function makes it possible for a client program to find out which optional +features are available in the version of the PCRE library it is using. Its +arguments are as follows: +.sp + \fIwhat\fR A code specifying what information is required + \fIwhere\fR Points to where to put the data +.sp +The available codes are: +.sp + PCRE_CONFIG_LINK_SIZE Internal link size: 2, 3, or 4 + PCRE_CONFIG_MATCH_LIMIT Internal resource limit + PCRE_CONFIG_MATCH_LIMIT_RECURSION + Internal recursion depth limit + PCRE_CONFIG_NEWLINE Value of the newline sequence + PCRE_CONFIG_POSIX_MALLOC_THRESHOLD + Threshold of return slots, above + which \fBmalloc()\fR is used by + the POSIX API + PCRE_CONFIG_STACKRECURSE Recursion implementation (1=stack 0=heap) + PCRE_CONFIG_UTF8 Availability of UTF-8 support (1=yes 0=no) + PCRE_CONFIG_UNICODE_PROPERTIES + Availability of Unicode property support + (1=yes 0=no) +.sp +The function yields 0 on success or PCRE_ERROR_BADOPTION otherwise. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fR +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fR +.\" +page. diff --git a/libs/pcre/doc/pcre_copy_named_substring.3 b/libs/pcre/doc/pcre_copy_named_substring.3 new file mode 100644 index 0000000000..f6c92330ff --- /dev/null +++ b/libs/pcre/doc/pcre_copy_named_substring.3 @@ -0,0 +1,44 @@ +.TH PCRE_COPY_NAMED_SUBSTRING 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include +.PP +.SM +.br +.B int pcre_copy_named_substring(const pcre *\fIcode\fP, +.ti +5n +.B const char *\fIsubject\fP, int *\fIovector\fP, +.ti +5n +.B int \fIstringcount\fP, const char *\fIstringname\fP, +.ti +5n +.B char *\fIbuffer\fP, int \fIbuffersize\fP); +. +.SH DESCRIPTION +.rs +.sp +This is a convenience function for extracting a captured substring, identified +by name, into a given buffer. The arguments are: +.sp + \fIcode\fP Pattern that was successfully matched + \fIsubject\fP Subject that has been successfully matched + \fIovector\fP Offset vector that \fBpcre_exec()\fP used + \fIstringcount\fP Value returned by \fBpcre_exec()\fP + \fIstringname\fP Name of the required substring + \fIbuffer\fP Buffer to receive the string + \fIbuffersize\fP Size of buffer +.sp +The yield is the length of the substring, PCRE_ERROR_NOMEMORY if the buffer was +too small, or PCRE_ERROR_NOSUBSTRING if the string name is invalid. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/libs/pcre/doc/pcre_copy_substring.3 b/libs/pcre/doc/pcre_copy_substring.3 new file mode 100644 index 0000000000..41c8dc3d47 --- /dev/null +++ b/libs/pcre/doc/pcre_copy_substring.3 @@ -0,0 +1,41 @@ +.TH PCRE_COPY_SUBSTRING 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include +.PP +.SM +.br +.B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP, +.ti +5n +.B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP, +.ti +5n +.B int \fIbuffersize\fP); +. +.SH DESCRIPTION +.rs +.sp +This is a convenience function for extracting a captured substring into a given +buffer. The arguments are: +.sp + \fIsubject\fP Subject that has been successfully matched + \fIovector\fP Offset vector that \fBpcre_exec()\fP used + \fIstringcount\fP Value returned by \fBpcre_exec()\fP + \fIstringnumber\fP Number of the required substring + \fIbuffer\fP Buffer to receive the string + \fIbuffersize\fP Size of buffer +.sp +The yield is the legnth of the string, PCRE_ERROR_NOMEMORY if the buffer was +too small, or PCRE_ERROR_NOSUBSTRING if the string number is invalid. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/libs/pcre/doc/pcre_dfa_exec.3 b/libs/pcre/doc/pcre_dfa_exec.3 new file mode 100644 index 0000000000..92c2872b49 --- /dev/null +++ b/libs/pcre/doc/pcre_dfa_exec.3 @@ -0,0 +1,85 @@ +.TH PCRE_DFA_EXEC 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include +.PP +.SM +.br +.B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.ti +5n +.B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, +.ti +5n +.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP, +.ti +5n +.B int *\fIworkspace\fP, int \fIwscount\fP); +. +.SH DESCRIPTION +.rs +.sp +This function matches a compiled regular expression against a given subject +string, using a DFA matching algorithm (\fInot\fP Perl-compatible). Note that +the main, Perl-compatible, matching function is \fBpcre_exec()\fP. The +arguments for this function are: +.sp + \fIcode\fP Points to the compiled pattern + \fIextra\fP Points to an associated \fBpcre_extra\fP structure, + or is NULL + \fIsubject\fP Points to the subject string + \fIlength\fP Length of the subject string, in bytes + \fIstartoffset\fP Offset in bytes in the subject at which to + start matching + \fIoptions\fP Option bits + \fIovector\fP Points to a vector of ints for result offsets + \fIovecsize\fP Number of elements in the vector + \fIworkspace\fP Points to a vector of ints used as working space + \fIwscount\fP Number of elements in the vector +.sp +The options are: +.sp + PCRE_ANCHORED Match only at the first position + PCRE_NEWLINE_CR Set CR as the newline sequence + PCRE_NEWLINE_CRLF Set CRLF as the newline sequence + PCRE_NEWLINE_LF Set LF as the newline sequence + PCRE_NOTBOL Subject is not the beginning of a line + PCRE_NOTEOL Subject is not the end of a line + PCRE_NOTEMPTY An empty string is not a valid match + PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 + validity (only relevant if PCRE_UTF8 + was set at compile time) + PCRE_PARTIAL Return PCRE_ERROR_PARTIAL for a partial match + PCRE_DFA_SHORTEST Return only the shortest match + PCRE_DFA_RESTART This is a restart after a partial match +.sp +There are restrictions on what may appear in a pattern when matching using the +DFA algorithm is requested. Details are given in the +.\" HREF +\fBpcrematching\fP +.\" +documentation. +.P +A \fBpcre_extra\fP structure contains the following fields: +.sp + \fIflags\fP Bits indicating which fields are set + \fIstudy_data\fP Opaque data from \fBpcre_study()\fP + \fImatch_limit\fP Limit on internal resource use + \fImatch_limit_recursion\fP Limit on internal recursion depth + \fIcallout_data\fP Opaque data passed back to callouts + \fItables\fP Points to character tables or is NULL +.sp +The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, +PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, and +PCRE_EXTRA_TABLES. For DFA matching, the \fImatch_limit\fP and +\fImatch_limit_recursion\fP fields are not used, and must not be set. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/libs/pcre/doc/pcre_exec.3 b/libs/pcre/doc/pcre_exec.3 new file mode 100644 index 0000000000..2a598128af --- /dev/null +++ b/libs/pcre/doc/pcre_exec.3 @@ -0,0 +1,73 @@ +.TH PCRE_EXEC 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include +.PP +.SM +.br +.B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.ti +5n +.B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, +.ti +5n +.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP); +. +.SH DESCRIPTION +.rs +.sp +This function matches a compiled regular expression against a given subject +string, using a matching algorithm that is similar to Perl's. It returns +offsets to captured substrings. Its arguments are: +.sp + \fIcode\fP Points to the compiled pattern + \fIextra\fP Points to an associated \fBpcre_extra\fP structure, + or is NULL + \fIsubject\fP Points to the subject string + \fIlength\fP Length of the subject string, in bytes + \fIstartoffset\fP Offset in bytes in the subject at which to + start matching + \fIoptions\fP Option bits + \fIovector\fP Points to a vector of ints for result offsets + \fIovecsize\fP Number of elements in the vector (a multiple of 3) +.sp +The options are: +.sp + PCRE_ANCHORED Match only at the first position + PCRE_NEWLINE_CR Set CR as the newline sequence + PCRE_NEWLINE_CRLF Set CRLF as the newline sequence + PCRE_NEWLINE_LF Set LF as the newline sequence + PCRE_NOTBOL Subject is not the beginning of a line + PCRE_NOTEOL Subject is not the end of a line + PCRE_NOTEMPTY An empty string is not a valid match + PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 + validity (only relevant if PCRE_UTF8 + was set at compile time) + PCRE_PARTIAL Return PCRE_ERROR_PARTIAL for a partial match +.sp +There are restrictions on what may appear in a pattern when partial matching is +requested. +.P +A \fBpcre_extra\fP structure contains the following fields: +.sp + \fIflags\fP Bits indicating which fields are set + \fIstudy_data\fP Opaque data from \fBpcre_study()\fP + \fImatch_limit\fP Limit on internal resource use + \fImatch_limit_recursion\fP Limit on internal recursion depth + \fIcallout_data\fP Opaque data passed back to callouts + \fItables\fP Points to character tables or is NULL +.sp +The flag bits are PCRE_EXTRA_STUDY_DATA, PCRE_EXTRA_MATCH_LIMIT, +PCRE_EXTRA_MATCH_LIMIT_RECURSION, PCRE_EXTRA_CALLOUT_DATA, and +PCRE_EXTRA_TABLES. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/libs/pcre/doc/pcre_free_substring.3 b/libs/pcre/doc/pcre_free_substring.3 new file mode 100644 index 0000000000..3628c263a1 --- /dev/null +++ b/libs/pcre/doc/pcre_free_substring.3 @@ -0,0 +1,28 @@ +.TH PCRE_FREE_SUBSTRING 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include +.PP +.SM +.br +.B void pcre_free_substring(const char *\fIstringptr\fP); +. +.SH DESCRIPTION +.rs +.sp +This is a convenience function for freeing the store obtained by a previous +call to \fBpcre_get_substring()\fP or \fBpcre_get_named_substring()\fP. Its +only argument is a pointer to the string. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/libs/pcre/doc/pcre_free_substring_list.3 b/libs/pcre/doc/pcre_free_substring_list.3 new file mode 100644 index 0000000000..9365d363f4 --- /dev/null +++ b/libs/pcre/doc/pcre_free_substring_list.3 @@ -0,0 +1,28 @@ +.TH PCRE_FREE_SUBSTRING_LIST 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include +.PP +.SM +.br +.B void pcre_free_substring_list(const char **\fIstringptr\fP); +. +.SH DESCRIPTION +.rs +.sp +This is a convenience function for freeing the store obtained by a previous +call to \fBpcre_get_substring_list()\fP. Its only argument is a pointer to the +list of string pointers. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/libs/pcre/doc/pcre_fullinfo.3 b/libs/pcre/doc/pcre_fullinfo.3 new file mode 100644 index 0000000000..4b528e2703 --- /dev/null +++ b/libs/pcre/doc/pcre_fullinfo.3 @@ -0,0 +1,59 @@ +.TH PCRE_FULLINFO 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include +.PP +.SM +.br +.B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.ti +5n +.B int \fIwhat\fP, void *\fIwhere\fP); +. +.SH DESCRIPTION +.rs +.sp +This function returns information about a compiled pattern. Its arguments are: +.sp + \fIcode\fP Compiled regular expression + \fIextra\fP Result of \fBpcre_study()\fP or NULL + \fIwhat\fP What information is required + \fIwhere\fP Where to put the information +.sp +The following information is available: +.sp + PCRE_INFO_BACKREFMAX Number of highest back reference + PCRE_INFO_CAPTURECOUNT Number of capturing subpatterns + PCRE_INFO_DEFAULT_TABLES Pointer to default tables + PCRE_INFO_FIRSTBYTE Fixed first byte for a match, or + -1 for start of string + or after newline, or + -2 otherwise + PCRE_INFO_FIRSTTABLE Table of first bytes + (after studying) + PCRE_INFO_LASTLITERAL Literal last byte required + PCRE_INFO_NAMECOUNT Number of named subpatterns + PCRE_INFO_NAMEENTRYSIZE Size of name table entry + PCRE_INFO_NAMETABLE Pointer to name table + PCRE_INFO_OPTIONS Options used for compilation + PCRE_INFO_SIZE Size of compiled pattern + PCRE_INFO_STUDYSIZE Size of study data +.sp +The yield of the function is zero on success or: +.sp + PCRE_ERROR_NULL the argument \fIcode\fP was NULL + the argument \fIwhere\fP was NULL + PCRE_ERROR_BADMAGIC the "magic number" was not found + PCRE_ERROR_BADOPTION the value of \fIwhat\fP was invalid +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/libs/pcre/doc/pcre_get_named_substring.3 b/libs/pcre/doc/pcre_get_named_substring.3 new file mode 100644 index 0000000000..2a1043d9da --- /dev/null +++ b/libs/pcre/doc/pcre_get_named_substring.3 @@ -0,0 +1,45 @@ +.TH PCRE_GET_NAMED_SUBSTRING 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include +.PP +.SM +.br +.B int pcre_get_named_substring(const pcre *\fIcode\fP, +.ti +5n +.B const char *\fIsubject\fP, int *\fIovector\fP, +.ti +5n +.B int \fIstringcount\fP, const char *\fIstringname\fP, +.ti +5n +.B const char **\fIstringptr\fP); +. +.SH DESCRIPTION +.rs +.sp +This is a convenience function for extracting a captured substring by name. The +arguments are: +.sp + \fIcode\fP Compiled pattern + \fIsubject\fP Subject that has been successfully matched + \fIovector\fP Offset vector that \fBpcre_exec()\fP used + \fIstringcount\fP Value returned by \fBpcre_exec()\fP + \fIstringname\fP Name of the required substring + \fIstringptr\fP Where to put the string pointer +.sp +The memory in which the substring is placed is obtained by calling +\fBpcre_malloc()\fP. The yield of the function is the length of the extracted +substring, PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained, or +PCRE_ERROR_NOSUBSTRING if the string name is invalid. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/libs/pcre/doc/pcre_get_stringnumber.3 b/libs/pcre/doc/pcre_get_stringnumber.3 new file mode 100644 index 0000000000..f6f46de263 --- /dev/null +++ b/libs/pcre/doc/pcre_get_stringnumber.3 @@ -0,0 +1,35 @@ +.TH PCRE_GET_STRINGNUMBER 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include +.PP +.SM +.br +.B int pcre_get_stringnumber(const pcre *\fIcode\fP, +.ti +5n +.B const char *\fIname\fP); +. +.SH DESCRIPTION +.rs +.sp +This convenience function finds the number of a named substring capturing +parenthesis in a compiled pattern. Its arguments are: +.sp + \fIcode\fP Compiled regular expression + \fIname\fP Name whose number is required +.sp +The yield of the function is the number of the parenthesis if the name is +found, or PCRE_ERROR_NOSUBSTRING otherwise. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/libs/pcre/doc/pcre_get_stringtable_entries.3 b/libs/pcre/doc/pcre_get_stringtable_entries.3 new file mode 100644 index 0000000000..423170d9f9 --- /dev/null +++ b/libs/pcre/doc/pcre_get_stringtable_entries.3 @@ -0,0 +1,41 @@ +.TH PCRE_GET_STRINGNUMBER 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include +.PP +.SM +.br +.B int pcre_get_stringtable_entries(const pcre *\fIcode\fP, +.ti +5n +.B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP); +. +.SH DESCRIPTION +.rs +.sp +This convenience function finds, for a compiled pattern, the first and last +entries for a given name in the table that translates capturing parenthesis +names into numbers. When names are required to be unique (PCRE_DUPNAMES is +\fInot\fP set), it is usually easier to use \fBpcre_get_stringnumber()\fP +instead. +.sp + \fIcode\fP Compiled regular expression + \fIname\fP Name whose entries required + \fIfirst\fP Where to return a pointer to the first entry + \fIlast\fP Where to return a pointer to the last entry +.sp +The yield of the function is the length of each entry, or +PCRE_ERROR_NOSUBSTRING if none are found. +.P +There is a complete description of the PCRE native API, including the format of +the table entries, in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/libs/pcre/doc/pcre_get_substring.3 b/libs/pcre/doc/pcre_get_substring.3 new file mode 100644 index 0000000000..cc35e4a8cb --- /dev/null +++ b/libs/pcre/doc/pcre_get_substring.3 @@ -0,0 +1,42 @@ +.TH PCRE_GET_SUBSTRING 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include +.PP +.SM +.br +.B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP, +.ti +5n +.B int \fIstringcount\fP, int \fIstringnumber\fP, +.ti +5n +.B const char **\fIstringptr\fP); +. +.SH DESCRIPTION +.rs +.sp +This is a convenience function for extracting a captured substring. The +arguments are: +.sp + \fIsubject\fP Subject that has been successfully matched + \fIovector\fP Offset vector that \fBpcre_exec()\fP used + \fIstringcount\fP Value returned by \fBpcre_exec()\fP + \fIstringnumber\fP Number of the required substring + \fIstringptr\fP Where to put the string pointer +.sp +The memory in which the substring is placed is obtained by calling +\fBpcre_malloc()\fP. The yield of the function is the length of the substring, +PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained, or +PCRE_ERROR_NOSUBSTRING if the string number is invalid. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/libs/pcre/doc/pcre_get_substring_list.3 b/libs/pcre/doc/pcre_get_substring_list.3 new file mode 100644 index 0000000000..51d8ba5d09 --- /dev/null +++ b/libs/pcre/doc/pcre_get_substring_list.3 @@ -0,0 +1,40 @@ +.TH PCRE_GET_SUBSTRING_LIST 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include +.PP +.SM +.br +.B int pcre_get_substring_list(const char *\fIsubject\fP, +.ti +5n +.B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);" +. +.SH DESCRIPTION +.rs +.sp +This is a convenience function for extracting a list of all the captured +substrings. The arguments are: +.sp + \fIsubject\fP Subject that has been successfully matched + \fIovector\fP Offset vector that \fBpcre_exec\fP used + \fIstringcount\fP Value returned by \fBpcre_exec\fP + \fIlistptr\fP Where to put a pointer to the list +.sp +The memory in which the substrings and the list are placed is obtained by +calling \fBpcre_malloc()\fP. A pointer to a list of pointers is put in +the variable whose address is in \fIlistptr\fP. The list is terminated by a +NULL pointer. The yield of the function is zero on success or +PCRE_ERROR_NOMEMORY if sufficient memory could not be obtained. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/libs/pcre/doc/pcre_info.3 b/libs/pcre/doc/pcre_info.3 new file mode 100644 index 0000000000..5974067533 --- /dev/null +++ b/libs/pcre/doc/pcre_info.3 @@ -0,0 +1,27 @@ +.TH PCRE_INFO 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include +.PP +.SM +.br +.B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int +.B *\fIfirstcharptr\fP); +. +.SH DESCRIPTION +.rs +.sp +This function is obsolete. You should be using \fBpcre_fullinfo()\fP instead. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/libs/pcre/doc/pcre_maketables.3 b/libs/pcre/doc/pcre_maketables.3 new file mode 100644 index 0000000000..45a9dd9c9e --- /dev/null +++ b/libs/pcre/doc/pcre_maketables.3 @@ -0,0 +1,30 @@ +.TH PCRE_MAKETABLES 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include +.PP +.SM +.br +.B const unsigned char *pcre_maketables(void); +. +.SH DESCRIPTION +.rs +.sp +This function builds a set of character tables for character values less than +256. These can be passed to \fBpcre_compile()\fP to override PCRE's internal, +built-in tables (which were made by \fBpcre_maketables()\fP when PCRE was +compiled). You might want to do this if you are using a non-standard locale. +The function yields a pointer to the tables. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/libs/pcre/doc/pcre_refcount.3 b/libs/pcre/doc/pcre_refcount.3 new file mode 100644 index 0000000000..e2b45026a2 --- /dev/null +++ b/libs/pcre/doc/pcre_refcount.3 @@ -0,0 +1,33 @@ +.TH PCRE_REFCOUNT 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include +.PP +.SM +.br +.B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP); +. +.SH DESCRIPTION +.rs +.sp +This function is used to maintain a reference count inside a data block that +contains a compiled pattern. Its arguments are: +.sp + \fIcode\fP Compiled regular expression + \fIadjust\fP Adjustment to reference value +.sp +The yield of the function is the adjusted reference value, which is constrained +to lie between 0 and 65535. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/libs/pcre/doc/pcre_study.3 b/libs/pcre/doc/pcre_study.3 new file mode 100644 index 0000000000..eafc910370 --- /dev/null +++ b/libs/pcre/doc/pcre_study.3 @@ -0,0 +1,43 @@ +.TH PCRE_STUDY 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include +.PP +.SM +.br +.B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP, +.ti +5n +.B const char **\fIerrptr\fP); +. +.SH DESCRIPTION +.rs +.sp +This function studies a compiled pattern, to see if additional information can +be extracted that might speed up matching. Its arguments are: +.sp + \fIcode\fP A compiled regular expression + \fIoptions\fP Options for \fBpcre_study()\fP + \fIerrptr\fP Where to put an error message +.sp +If the function succeeds, it returns a value that can be passed to +\fBpcre_exec()\fP via its \fIextra\fP argument. +.P +If the function returns NULL, either it could not find any additional +information, or there was an error. You can tell the difference by looking at +the error value. It is NULL in first case. +.P +There are currently no options defined; the value of the second argument should +always be zero. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/libs/pcre/doc/pcre_version.3 b/libs/pcre/doc/pcre_version.3 new file mode 100644 index 0000000000..e48a0e9eb0 --- /dev/null +++ b/libs/pcre/doc/pcre_version.3 @@ -0,0 +1,27 @@ +.TH PCRE_VERSION 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH SYNOPSIS +.rs +.sp +.B #include +.PP +.SM +.br +.B char *pcre_version(void); +. +.SH DESCRIPTION +.rs +.sp +This function returns a character string that gives the version number of the +PCRE library and the date of its release. +.P +There is a complete description of the PCRE native API in the +.\" HREF +\fBpcreapi\fP +.\" +page and a description of the POSIX API in the +.\" HREF +\fBpcreposix\fP +.\" +page. diff --git a/libs/pcre/doc/pcreapi.3 b/libs/pcre/doc/pcreapi.3 new file mode 100644 index 0000000000..9e4d23e9b6 --- /dev/null +++ b/libs/pcre/doc/pcreapi.3 @@ -0,0 +1,1789 @@ +.TH PCREAPI 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "PCRE NATIVE API" +.rs +.sp +.B #include +.PP +.SM +.br +.B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP, +.ti +5n +.B const char **\fIerrptr\fP, int *\fIerroffset\fP, +.ti +5n +.B const unsigned char *\fItableptr\fP); +.PP +.br +.B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP, +.ti +5n +.B int *\fIerrorcodeptr\fP, +.ti +5n +.B const char **\fIerrptr\fP, int *\fIerroffset\fP, +.ti +5n +.B const unsigned char *\fItableptr\fP); +.PP +.br +.B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP, +.ti +5n +.B const char **\fIerrptr\fP); +.PP +.br +.B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.ti +5n +.B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, +.ti +5n +.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP); +.PP +.br +.B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.ti +5n +.B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, +.ti +5n +.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP, +.ti +5n +.B int *\fIworkspace\fP, int \fIwscount\fP); +.PP +.br +.B int pcre_copy_named_substring(const pcre *\fIcode\fP, +.ti +5n +.B const char *\fIsubject\fP, int *\fIovector\fP, +.ti +5n +.B int \fIstringcount\fP, const char *\fIstringname\fP, +.ti +5n +.B char *\fIbuffer\fP, int \fIbuffersize\fP); +.PP +.br +.B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP, +.ti +5n +.B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP, +.ti +5n +.B int \fIbuffersize\fP); +.PP +.br +.B int pcre_get_named_substring(const pcre *\fIcode\fP, +.ti +5n +.B const char *\fIsubject\fP, int *\fIovector\fP, +.ti +5n +.B int \fIstringcount\fP, const char *\fIstringname\fP, +.ti +5n +.B const char **\fIstringptr\fP); +.PP +.br +.B int pcre_get_stringnumber(const pcre *\fIcode\fP, +.ti +5n +.B const char *\fIname\fP); +.PP +.br +.B int pcre_get_stringtable_entries(const pcre *\fIcode\fP, +.ti +5n +.B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP); +.PP +.br +.B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP, +.ti +5n +.B int \fIstringcount\fP, int \fIstringnumber\fP, +.ti +5n +.B const char **\fIstringptr\fP); +.PP +.br +.B int pcre_get_substring_list(const char *\fIsubject\fP, +.ti +5n +.B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);" +.PP +.br +.B void pcre_free_substring(const char *\fIstringptr\fP); +.PP +.br +.B void pcre_free_substring_list(const char **\fIstringptr\fP); +.PP +.br +.B const unsigned char *pcre_maketables(void); +.PP +.br +.B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.ti +5n +.B int \fIwhat\fP, void *\fIwhere\fP); +.PP +.br +.B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int +.B *\fIfirstcharptr\fP); +.PP +.br +.B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP); +.PP +.br +.B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP); +.PP +.br +.B char *pcre_version(void); +.PP +.br +.B void *(*pcre_malloc)(size_t); +.PP +.br +.B void (*pcre_free)(void *); +.PP +.br +.B void *(*pcre_stack_malloc)(size_t); +.PP +.br +.B void (*pcre_stack_free)(void *); +.PP +.br +.B int (*pcre_callout)(pcre_callout_block *); +. +. +.SH "PCRE API OVERVIEW" +.rs +.sp +PCRE has its own native API, which is described in this document. There is +also a set of wrapper functions that correspond to the POSIX regular expression +API. These are described in the +.\" HREF +\fBpcreposix\fP +.\" +documentation. Both of these APIs define a set of C function calls. A C++ +wrapper is distributed with PCRE. It is documented in the +.\" HREF +\fBpcrecpp\fP +.\" +page. +.P +The native API C function prototypes are defined in the header file +\fBpcre.h\fP, and on Unix systems the library itself is called \fBlibpcre\fP. +It can normally be accessed by adding \fB-lpcre\fP to the command for linking +an application that uses PCRE. The header file defines the macros PCRE_MAJOR +and PCRE_MINOR to contain the major and minor release numbers for the library. +Applications can use these to include support for different releases of PCRE. +.P +The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP, +and \fBpcre_exec()\fP are used for compiling and matching regular expressions +in a Perl-compatible manner. A sample program that demonstrates the simplest +way of using them is provided in the file called \fIpcredemo.c\fP in the source +distribution. The +.\" HREF +\fBpcresample\fP +.\" +documentation describes how to run it. +.P +A second matching function, \fBpcre_dfa_exec()\fP, which is not +Perl-compatible, is also provided. This uses a different algorithm for the +matching. The alternative algorithm finds all possible matches (at a given +point in the subject). However, this algorithm does not return captured +substrings. A description of the two matching algorithms and their advantages +and disadvantages is given in the +.\" HREF +\fBpcrematching\fP +.\" +documentation. +.P +In addition to the main compiling and matching functions, there are convenience +functions for extracting captured substrings from a subject string that is +matched by \fBpcre_exec()\fP. They are: +.sp + \fBpcre_copy_substring()\fP + \fBpcre_copy_named_substring()\fP + \fBpcre_get_substring()\fP + \fBpcre_get_named_substring()\fP + \fBpcre_get_substring_list()\fP + \fBpcre_get_stringnumber()\fP + \fBpcre_get_stringtable_entries()\fP +.sp +\fBpcre_free_substring()\fP and \fBpcre_free_substring_list()\fP are also +provided, to free the memory used for extracted strings. +.P +The function \fBpcre_maketables()\fP is used to build a set of character tables +in the current locale for passing to \fBpcre_compile()\fP, \fBpcre_exec()\fP, +or \fBpcre_dfa_exec()\fP. This is an optional facility that is provided for +specialist use. Most commonly, no special tables are passed, in which case +internal tables that are generated when PCRE is built are used. +.P +The function \fBpcre_fullinfo()\fP is used to find out information about a +compiled pattern; \fBpcre_info()\fP is an obsolete version that returns only +some of the available information, but is retained for backwards compatibility. +The function \fBpcre_version()\fP returns a pointer to a string containing the +version of PCRE and its date of release. +.P +The function \fBpcre_refcount()\fP maintains a reference count in a data block +containing a compiled pattern. This is provided for the benefit of +object-oriented applications. +.P +The global variables \fBpcre_malloc\fP and \fBpcre_free\fP initially contain +the entry points of the standard \fBmalloc()\fP and \fBfree()\fP functions, +respectively. PCRE calls the memory management functions via these variables, +so a calling program can replace them if it wishes to intercept the calls. This +should be done before calling any PCRE functions. +.P +The global variables \fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP are also +indirections to memory management functions. These special functions are used +only when PCRE is compiled to use the heap for remembering data, instead of +recursive function calls, when running the \fBpcre_exec()\fP function. See the +.\" HREF +\fBpcrebuild\fP +.\" +documentation for details of how to do this. It is a non-standard way of +building PCRE, for use in environments that have limited stacks. Because of the +greater use of memory management, it runs more slowly. Separate functions are +provided so that special-purpose external code can be used for this case. When +used, these functions are always called in a stack-like manner (last obtained, +first freed), and always for memory blocks of the same size. There is a +discussion about PCRE's stack usage in the +.\" HREF +\fBpcrestack\fP +.\" +documentation. +.P +The global variable \fBpcre_callout\fP initially contains NULL. It can be set +by the caller to a "callout" function, which PCRE will then call at specified +points during a matching operation. Details are given in the +.\" HREF +\fBpcrecallout\fP +.\" +documentation. +. +. +.SH NEWLINES +PCRE supports three different conventions for indicating line breaks in +strings: a single CR character, a single LF character, or the two-character +sequence CRLF. All three are used as "standard" by different operating systems. +When PCRE is built, a default can be specified. The default default is LF, +which is the Unix standard. When PCRE is run, the default can be overridden, +either when a pattern is compiled, or when it is matched. +.sp +In the PCRE documentation the word "newline" is used to mean "the character or +pair of characters that indicate a line break". +. +. +.SH MULTITHREADING +.rs +.sp +The PCRE functions can be used in multi-threading applications, with the +proviso that the memory management functions pointed to by \fBpcre_malloc\fP, +\fBpcre_free\fP, \fBpcre_stack_malloc\fP, and \fBpcre_stack_free\fP, and the +callout function pointed to by \fBpcre_callout\fP, are shared by all threads. +.P +The compiled form of a regular expression is not altered during matching, so +the same compiled pattern can safely be used by several threads at once. +. +. +.SH "SAVING PRECOMPILED PATTERNS FOR LATER USE" +.rs +.sp +The compiled form of a regular expression can be saved and re-used at a later +time, possibly by a different program, and even on a host other than the one on +which it was compiled. Details are given in the +.\" HREF +\fBpcreprecompile\fP +.\" +documentation. +. +. +.SH "CHECKING BUILD-TIME OPTIONS" +.rs +.sp +.B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP); +.PP +The function \fBpcre_config()\fP makes it possible for a PCRE client to +discover which optional features have been compiled into the PCRE library. The +.\" HREF +\fBpcrebuild\fP +.\" +documentation has more details about these optional features. +.P +The first argument for \fBpcre_config()\fP is an integer, specifying which +information is required; the second argument is a pointer to a variable into +which the information is placed. The following information is available: +.sp + PCRE_CONFIG_UTF8 +.sp +The output is an integer that is set to one if UTF-8 support is available; +otherwise it is set to zero. +.sp + PCRE_CONFIG_UNICODE_PROPERTIES +.sp +The output is an integer that is set to one if support for Unicode character +properties is available; otherwise it is set to zero. +.sp + PCRE_CONFIG_NEWLINE +.sp +The output is an integer whose value specifies the default character sequence +that is recognized as meaning "newline". The three values that are supported +are: 10 for LF, 13 for CR, and 3338 for CRLF. The default should normally be +the standard sequence for your operating system. +.sp + PCRE_CONFIG_LINK_SIZE +.sp +The output is an integer that contains the number of bytes used for internal +linkage in compiled regular expressions. The value is 2, 3, or 4. Larger values +allow larger regular expressions to be compiled, at the expense of slower +matching. The default value of 2 is sufficient for all but the most massive +patterns, since it allows the compiled pattern to be up to 64K in size. +.sp + PCRE_CONFIG_POSIX_MALLOC_THRESHOLD +.sp +The output is an integer that contains the threshold above which the POSIX +interface uses \fBmalloc()\fP for output vectors. Further details are given in +the +.\" HREF +\fBpcreposix\fP +.\" +documentation. +.sp + PCRE_CONFIG_MATCH_LIMIT +.sp +The output is an integer that gives the default limit for the number of +internal matching function calls in a \fBpcre_exec()\fP execution. Further +details are given with \fBpcre_exec()\fP below. +.sp + PCRE_CONFIG_MATCH_LIMIT_RECURSION +.sp +The output is an integer that gives the default limit for the depth of +recursion when calling the internal matching function in a \fBpcre_exec()\fP +execution. Further details are given with \fBpcre_exec()\fP below. +.sp + PCRE_CONFIG_STACKRECURSE +.sp +The output is an integer that is set to one if internal recursion when running +\fBpcre_exec()\fP is implemented by recursive function calls that use the stack +to remember their state. This is the usual way that PCRE is compiled. The +output is zero if PCRE was compiled to use blocks of data on the heap instead +of recursive function calls. In this case, \fBpcre_stack_malloc\fP and +\fBpcre_stack_free\fP are called to manage memory blocks on the heap, thus +avoiding the use of the stack. +. +. +.SH "COMPILING A PATTERN" +.rs +.sp +.B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP, +.ti +5n +.B const char **\fIerrptr\fP, int *\fIerroffset\fP, +.ti +5n +.B const unsigned char *\fItableptr\fP); +.sp +.B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP, +.ti +5n +.B int *\fIerrorcodeptr\fP, +.ti +5n +.B const char **\fIerrptr\fP, int *\fIerroffset\fP, +.ti +5n +.B const unsigned char *\fItableptr\fP); +.P +Either of the functions \fBpcre_compile()\fP or \fBpcre_compile2()\fP can be +called to compile a pattern into an internal form. The only difference between +the two interfaces is that \fBpcre_compile2()\fP has an additional argument, +\fIerrorcodeptr\fP, via which a numerical error code can be returned. +.P +The pattern is a C string terminated by a binary zero, and is passed in the +\fIpattern\fP argument. A pointer to a single block of memory that is obtained +via \fBpcre_malloc\fP is returned. This contains the compiled code and related +data. The \fBpcre\fP type is defined for the returned block; this is a typedef +for a structure whose contents are not externally defined. It is up to the +caller to free the memory (via \fBpcre_free\fP) when it is no longer required. +.P +Although the compiled code of a PCRE regex is relocatable, that is, it does not +depend on memory location, the complete \fBpcre\fP data block is not +fully relocatable, because it may contain a copy of the \fItableptr\fP +argument, which is an address (see below). +.P +The \fIoptions\fP argument contains independent bits that affect the +compilation. It should be zero if no options are required. The available +options are described below. Some of them, in particular, those that are +compatible with Perl, can also be set and unset from within the pattern (see +the detailed description in the +.\" HREF +\fBpcrepattern\fP +.\" +documentation). For these options, the contents of the \fIoptions\fP argument +specifies their initial settings at the start of compilation and execution. The +PCRE_ANCHORED and PCRE_NEWLINE_\fIxxx\fP options can be set at the time of +matching as well as at compile time. +.P +If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately. +Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns +NULL, and sets the variable pointed to by \fIerrptr\fP to point to a textual +error message. This is a static string that is part of the library. You must +not try to free it. The offset from the start of the pattern to the character +where the error was discovered is placed in the variable pointed to by +\fIerroffset\fP, which must not be NULL. If it is, an immediate error is given. +.P +If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the +\fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is +returned via this argument in the event of an error. This is in addition to the +textual error message. Error codes and messages are listed below. +.P +If the final argument, \fItableptr\fP, is NULL, PCRE uses a default set of +character tables that are built when PCRE is compiled, using the default C +locale. Otherwise, \fItableptr\fP must be an address that is the result of a +call to \fBpcre_maketables()\fP. This value is stored with the compiled +pattern, and used again by \fBpcre_exec()\fP, unless another table pointer is +passed to it. For more discussion, see the section on locale support below. +.P +This code fragment shows a typical straightforward call to \fBpcre_compile()\fP: +.sp + pcre *re; + const char *error; + int erroffset; + re = pcre_compile( + "^A.*Z", /* the pattern */ + 0, /* default options */ + &error, /* for error message */ + &erroffset, /* for error offset */ + NULL); /* use default character tables */ +.sp +The following names for option bits are defined in the \fBpcre.h\fP header +file: +.sp + PCRE_ANCHORED +.sp +If this bit is set, the pattern is forced to be "anchored", that is, it is +constrained to match only at the first matching point in the string that is +being searched (the "subject string"). This effect can also be achieved by +appropriate constructs in the pattern itself, which is the only way to do it in +Perl. +.sp + PCRE_AUTO_CALLOUT +.sp +If this bit is set, \fBpcre_compile()\fP automatically inserts callout items, +all with number 255, before each pattern item. For discussion of the callout +facility, see the +.\" HREF +\fBpcrecallout\fP +.\" +documentation. +.sp + PCRE_CASELESS +.sp +If this bit is set, letters in the pattern match both upper and lower case +letters. It is equivalent to Perl's /i option, and it can be changed within a +pattern by a (?i) option setting. In UTF-8 mode, PCRE always understands the +concept of case for characters whose values are less than 128, so caseless +matching is always possible. For characters with higher values, the concept of +case is supported if PCRE is compiled with Unicode property support, but not +otherwise. If you want to use caseless matching for characters 128 and above, +you must ensure that PCRE is compiled with Unicode property support as well as +with UTF-8 support. +.sp + PCRE_DOLLAR_ENDONLY +.sp +If this bit is set, a dollar metacharacter in the pattern matches only at the +end of the subject string. Without this option, a dollar also matches +immediately before a newline at the end of the string (but not before any other +newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set. +There is no equivalent to this option in Perl, and no way to set it within a +pattern. +.sp + PCRE_DOTALL +.sp +If this bit is set, a dot metacharater in the pattern matches all characters, +including those that indicate newline. Without it, a dot does not match when +the current position is at a newline. This option is equivalent to Perl's /s +option, and it can be changed within a pattern by a (?s) option setting. A +negative class such as [^a] always matches newlines, independent of the setting +of this option. +.sp + PCRE_DUPNAMES +.sp +If this bit is set, names used to identify capturing subpatterns need not be +unique. This can be helpful for certain types of pattern when it is known that +only one instance of the named subpattern can ever be matched. There are more +details of named subpatterns below; see also the +.\" HREF +\fBpcrepattern\fP +.\" +documentation. +.sp + PCRE_EXTENDED +.sp +If this bit is set, whitespace data characters in the pattern are totally +ignored except when escaped or inside a character class. Whitespace does not +include the VT character (code 11). In addition, characters between an +unescaped # outside a character class and the next newline, inclusive, are also +ignored. This is equivalent to Perl's /x option, and it can be changed within a +pattern by a (?x) option setting. +.P +This option makes it possible to include comments inside complicated patterns. +Note, however, that this applies only to data characters. Whitespace characters +may never appear within special character sequences in a pattern, for example +within the sequence (?( which introduces a conditional subpattern. +.sp + PCRE_EXTRA +.sp +This option was invented in order to turn on additional functionality of PCRE +that is incompatible with Perl, but it is currently of very little use. When +set, any backslash in a pattern that is followed by a letter that has no +special meaning causes an error, thus reserving these combinations for future +expansion. By default, as in Perl, a backslash followed by a letter with no +special meaning is treated as a literal. (Perl can, however, be persuaded to +give a warning for this.) There are at present no other features controlled by +this option. It can also be set by a (?X) option setting within a pattern. +.sp + PCRE_FIRSTLINE +.sp +If this option is set, an unanchored pattern is required to match before or at +the first newline in the subject string, though the matched text may continue +over the newline. +.sp + PCRE_MULTILINE +.sp +By default, PCRE treats the subject string as consisting of a single line of +characters (even if it actually contains newlines). The "start of line" +metacharacter (^) matches only at the start of the string, while the "end of +line" metacharacter ($) matches only at the end of the string, or before a +terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as +Perl. +.P +When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs +match immediately following or immediately before internal newlines in the +subject string, respectively, as well as at the very start and end. This is +equivalent to Perl's /m option, and it can be changed within a pattern by a +(?m) option setting. If there are no newlines in a subject string, or no +occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect. +.sp + PCRE_NEWLINE_CR + PCRE_NEWLINE_LF + PCRE_NEWLINE_CRLF +.sp +These options override the default newline definition that was chosen when PCRE +was built. Setting the first or the second specifies that a newline is +indicated by a single character (CR or LF, respectively). Setting both of them +specifies that a newline is indicated by the two-character CRLF sequence. For +convenience, PCRE_NEWLINE_CRLF is defined to contain both bits. The only time +that a line break is relevant when compiling a pattern is if PCRE_EXTENDED is +set, and an unescaped # outside a character class is encountered. This +indicates a comment that lasts until after the next newline. +.P +The newline option set at compile time becomes the default that is used for +\fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden. +.sp + PCRE_NO_AUTO_CAPTURE +.sp +If this option is set, it disables the use of numbered capturing parentheses in +the pattern. Any opening parenthesis that is not followed by ? behaves as if it +were followed by ?: but named parentheses can still be used for capturing (and +they acquire numbers in the usual way). There is no equivalent of this option +in Perl. +.sp + PCRE_UNGREEDY +.sp +This option inverts the "greediness" of the quantifiers so that they are not +greedy by default, but become greedy if followed by "?". It is not compatible +with Perl. It can also be set by a (?U) option setting within the pattern. +.sp + PCRE_UTF8 +.sp +This option causes PCRE to regard both the pattern and the subject as strings +of UTF-8 characters instead of single-byte character strings. However, it is +available only when PCRE is built to include UTF-8 support. If not, the use +of this option provokes an error. Details of how this option changes the +behaviour of PCRE are given in the +.\" HTML +.\" +section on UTF-8 support +.\" +in the main +.\" HREF +\fBpcre\fP +.\" +page. +.sp + PCRE_NO_UTF8_CHECK +.sp +When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is +automatically checked. If an invalid UTF-8 sequence of bytes is found, +\fBpcre_compile()\fP returns an error. If you already know that your pattern is +valid, and you want to skip this check for performance reasons, you can set the +PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid +UTF-8 string as a pattern is undefined. It may cause your program to crash. +Note that this option can also be passed to \fBpcre_exec()\fP and +\fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject +strings. +. +. +.SH "COMPILATION ERROR CODES" +.rs +.sp +The following table lists the error codes than may be returned by +\fBpcre_compile2()\fP, along with the error messages that may be returned by +both compiling functions. +.sp + 0 no error + 1 \e at end of pattern + 2 \ec at end of pattern + 3 unrecognized character follows \e + 4 numbers out of order in {} quantifier + 5 number too big in {} quantifier + 6 missing terminating ] for character class + 7 invalid escape sequence in character class + 8 range out of order in character class + 9 nothing to repeat + 10 operand of unlimited repeat could match the empty string + 11 internal error: unexpected repeat + 12 unrecognized character after (? + 13 POSIX named classes are supported only within a class + 14 missing ) + 15 reference to non-existent subpattern + 16 erroffset passed as NULL + 17 unknown option bit(s) set + 18 missing ) after comment + 19 parentheses nested too deeply + 20 regular expression too large + 21 failed to get memory + 22 unmatched parentheses + 23 internal error: code overflow + 24 unrecognized character after (?< + 25 lookbehind assertion is not fixed length + 26 malformed number or name after (?( + 27 conditional group contains more than two branches + 28 assertion expected after (?( + 29 (?R or (?digits must be followed by ) + 30 unknown POSIX class name + 31 POSIX collating elements are not supported + 32 this version of PCRE is not compiled with PCRE_UTF8 support + 33 spare error + 34 character value in \ex{...} sequence is too large + 35 invalid condition (?(0) + 36 \eC not allowed in lookbehind assertion + 37 PCRE does not support \eL, \el, \eN, \eU, or \eu + 38 number after (?C is > 255 + 39 closing ) for (?C expected + 40 recursive call could loop indefinitely + 41 unrecognized character after (?P + 42 syntax error after (?P + 43 two named subpatterns have the same name + 44 invalid UTF-8 string + 45 support for \eP, \ep, and \eX has not been compiled + 46 malformed \eP or \ep sequence + 47 unknown property name after \eP or \ep + 48 subpattern name is too long (maximum 32 characters) + 49 too many named subpatterns (maximum 10,000) + 50 repeated subpattern is too long + 51 octal value is greater than \e377 (not in UTF-8 mode) +. +. +.SH "STUDYING A PATTERN" +.rs +.sp +.B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP +.ti +5n +.B const char **\fIerrptr\fP); +.PP +If a compiled pattern is going to be used several times, it is worth spending +more time analyzing it in order to speed up the time taken for matching. The +function \fBpcre_study()\fP takes a pointer to a compiled pattern as its first +argument. If studying the pattern produces additional information that will +help speed up matching, \fBpcre_study()\fP returns a pointer to a +\fBpcre_extra\fP block, in which the \fIstudy_data\fP field points to the +results of the study. +.P +The returned value from \fBpcre_study()\fP can be passed directly to +\fBpcre_exec()\fP. However, a \fBpcre_extra\fP block also contains other +fields that can be set by the caller before the block is passed; these are +described +.\" HTML +.\" +below +.\" +in the section on matching a pattern. +.P +If studying the pattern does not produce any additional information +\fBpcre_study()\fP returns NULL. In that circumstance, if the calling program +wants to pass any of the other fields to \fBpcre_exec()\fP, it must set up its +own \fBpcre_extra\fP block. +.P +The second argument of \fBpcre_study()\fP contains option bits. At present, no +options are defined, and this argument should always be zero. +.P +The third argument for \fBpcre_study()\fP is a pointer for an error message. If +studying succeeds (even if no data is returned), the variable it points to is +set to NULL. Otherwise it is set to point to a textual error message. This is a +static string that is part of the library. You must not try to free it. You +should test the error pointer for NULL after calling \fBpcre_study()\fP, to be +sure that it has run successfully. +.P +This is a typical call to \fBpcre_study\fP(): +.sp + pcre_extra *pe; + pe = pcre_study( + re, /* result of pcre_compile() */ + 0, /* no options exist */ + &error); /* set to NULL or points to a message */ +.sp +At present, studying a pattern is useful only for non-anchored patterns that do +not have a single fixed starting character. A bitmap of possible starting +bytes is created. +. +. +.\" HTML +.SH "LOCALE SUPPORT" +.rs +.sp +PCRE handles caseless matching, and determines whether characters are letters +digits, or whatever, by reference to a set of tables, indexed by character +value. When running in UTF-8 mode, this applies only to characters with codes +less than 128. Higher-valued codes never match escapes such as \ew or \ed, but +can be tested with \ep if PCRE is built with Unicode character property +support. The use of locales with Unicode is discouraged. +.P +An internal set of tables is created in the default C locale when PCRE is +built. This is used when the final argument of \fBpcre_compile()\fP is NULL, +and is sufficient for many applications. An alternative set of tables can, +however, be supplied. These may be created in a different locale from the +default. As more and more applications change to using Unicode, the need for +this locale support is expected to die away. +.P +External tables are built by calling the \fBpcre_maketables()\fP function, +which has no arguments, in the relevant locale. The result can then be passed +to \fBpcre_compile()\fP or \fBpcre_exec()\fP as often as necessary. For +example, to build and use tables that are appropriate for the French locale +(where accented characters with values greater than 128 are treated as letters), +the following code could be used: +.sp + setlocale(LC_CTYPE, "fr_FR"); + tables = pcre_maketables(); + re = pcre_compile(..., tables); +.sp +When \fBpcre_maketables()\fP runs, the tables are built in memory that is +obtained via \fBpcre_malloc\fP. It is the caller's responsibility to ensure +that the memory containing the tables remains available for as long as it is +needed. +.P +The pointer that is passed to \fBpcre_compile()\fP is saved with the compiled +pattern, and the same tables are used via this pointer by \fBpcre_study()\fP +and normally also by \fBpcre_exec()\fP. Thus, by default, for any single +pattern, compilation, studying and matching all happen in the same locale, but +different patterns can be compiled in different locales. +.P +It is possible to pass a table pointer or NULL (indicating the use of the +internal tables) to \fBpcre_exec()\fP. Although not intended for this purpose, +this facility could be used to match a pattern in a different locale from the +one in which it was compiled. Passing table pointers at run time is discussed +below in the section on matching a pattern. +. +. +.SH "INFORMATION ABOUT A PATTERN" +.rs +.sp +.B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.ti +5n +.B int \fIwhat\fP, void *\fIwhere\fP); +.PP +The \fBpcre_fullinfo()\fP function returns information about a compiled +pattern. It replaces the obsolete \fBpcre_info()\fP function, which is +nevertheless retained for backwards compability (and is documented below). +.P +The first argument for \fBpcre_fullinfo()\fP is a pointer to the compiled +pattern. The second argument is the result of \fBpcre_study()\fP, or NULL if +the pattern was not studied. The third argument specifies which piece of +information is required, and the fourth argument is a pointer to a variable +to receive the data. The yield of the function is zero for success, or one of +the following negative numbers: +.sp + PCRE_ERROR_NULL the argument \fIcode\fP was NULL + the argument \fIwhere\fP was NULL + PCRE_ERROR_BADMAGIC the "magic number" was not found + PCRE_ERROR_BADOPTION the value of \fIwhat\fP was invalid +.sp +The "magic number" is placed at the start of each compiled pattern as an simple +check against passing an arbitrary memory pointer. Here is a typical call of +\fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern: +.sp + int rc; + size_t length; + rc = pcre_fullinfo( + re, /* result of pcre_compile() */ + pe, /* result of pcre_study(), or NULL */ + PCRE_INFO_SIZE, /* what is required */ + &length); /* where to put the data */ +.sp +The possible values for the third argument are defined in \fBpcre.h\fP, and are +as follows: +.sp + PCRE_INFO_BACKREFMAX +.sp +Return the number of the highest back reference in the pattern. The fourth +argument should point to an \fBint\fP variable. Zero is returned if there are +no back references. +.sp + PCRE_INFO_CAPTURECOUNT +.sp +Return the number of capturing subpatterns in the pattern. The fourth argument +should point to an \fBint\fP variable. +.sp + PCRE_INFO_DEFAULT_TABLES +.sp +Return a pointer to the internal default character tables within PCRE. The +fourth argument should point to an \fBunsigned char *\fP variable. This +information call is provided for internal use by the \fBpcre_study()\fP +function. External callers can cause PCRE to use its internal tables by passing +a NULL table pointer. +.sp + PCRE_INFO_FIRSTBYTE +.sp +Return information about the first byte of any matched string, for a +non-anchored pattern. The fourth argument should point to an \fBint\fP +variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is +still recognized for backwards compatibility.) +.P +If there is a fixed first byte, for example, from a pattern such as +(cat|cow|coyote). Otherwise, if either +.sp +(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch +starts with "^", or +.sp +(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set +(if it were set, the pattern would be anchored), +.sp +-1 is returned, indicating that the pattern matches only at the start of a +subject string or after any newline within the string. Otherwise -2 is +returned. For anchored patterns, -2 is returned. +.sp + PCRE_INFO_FIRSTTABLE +.sp +If the pattern was studied, and this resulted in the construction of a 256-bit +table indicating a fixed set of bytes for the first byte in any matching +string, a pointer to the table is returned. Otherwise NULL is returned. The +fourth argument should point to an \fBunsigned char *\fP variable. +.sp + PCRE_INFO_LASTLITERAL +.sp +Return the value of the rightmost literal byte that must exist in any matched +string, other than at its start, if such a byte has been recorded. The fourth +argument should point to an \fBint\fP variable. If there is no such byte, -1 is +returned. For anchored patterns, a last literal byte is recorded only if it +follows something of variable length. For example, for the pattern +/^a\ed+z\ed+/ the returned value is "z", but for /^a\edz\ed/ the returned value +is -1. +.sp + PCRE_INFO_NAMECOUNT + PCRE_INFO_NAMEENTRYSIZE + PCRE_INFO_NAMETABLE +.sp +PCRE supports the use of named as well as numbered capturing parentheses. The +names are just an additional way of identifying the parentheses, which still +acquire numbers. Several convenience functions such as +\fBpcre_get_named_substring()\fP are provided for extracting captured +substrings by name. It is also possible to extract the data directly, by first +converting the name to a number in order to access the correct pointers in the +output vector (described with \fBpcre_exec()\fP below). To do the conversion, +you need to use the name-to-number map, which is described by these three +values. +.P +The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives +the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each +entry; both of these return an \fBint\fP value. The entry size depends on the +length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first +entry of the table (a pointer to \fBchar\fP). The first two bytes of each entry +are the number of the capturing parenthesis, most significant byte first. The +rest of the entry is the corresponding name, zero terminated. The names are in +alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of +their parentheses numbers. For example, consider the following pattern (assume +PCRE_EXTENDED is set, so white space - including newlines - is ignored): +.sp +.\" JOIN + (?P (?P(\ed\ed)?\ed\ed) - + (?P\ed\ed) - (?P\ed\ed) ) +.sp +There are four named subpatterns, so the table has four entries, and each entry +in the table is eight bytes long. The table is as follows, with non-printing +bytes shows in hexadecimal, and undefined bytes shown as ??: +.sp + 00 01 d a t e 00 ?? + 00 05 d a y 00 ?? ?? + 00 04 m o n t h 00 + 00 02 y e a r 00 ?? +.sp +When writing code to extract data from named subpatterns using the +name-to-number map, remember that the length of the entries is likely to be +different for each compiled pattern. +.sp + PCRE_INFO_OPTIONS +.sp +Return a copy of the options with which the pattern was compiled. The fourth +argument should point to an \fBunsigned long int\fP variable. These option bits +are those specified in the call to \fBpcre_compile()\fP, modified by any +top-level option settings within the pattern itself. +.P +A pattern is automatically anchored by PCRE if all of its top-level +alternatives begin with one of the following: +.sp + ^ unless PCRE_MULTILINE is set + \eA always + \eG always +.\" JOIN + .* if PCRE_DOTALL is set and there are no back + references to the subpattern in which .* appears +.sp +For such patterns, the PCRE_ANCHORED bit is set in the options returned by +\fBpcre_fullinfo()\fP. +.sp + PCRE_INFO_SIZE +.sp +Return the size of the compiled pattern, that is, the value that was passed as +the argument to \fBpcre_malloc()\fP when PCRE was getting memory in which to +place the compiled data. The fourth argument should point to a \fBsize_t\fP +variable. +.sp + PCRE_INFO_STUDYSIZE +.sp +Return the size of the data block pointed to by the \fIstudy_data\fP field in +a \fBpcre_extra\fP block. That is, it is the value that was passed to +\fBpcre_malloc()\fP when PCRE was getting memory into which to place the data +created by \fBpcre_study()\fP. The fourth argument should point to a +\fBsize_t\fP variable. +. +. +.SH "OBSOLETE INFO FUNCTION" +.rs +.sp +.B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int +.B *\fIfirstcharptr\fP); +.PP +The \fBpcre_info()\fP function is now obsolete because its interface is too +restrictive to return all the available data about a compiled pattern. New +programs should use \fBpcre_fullinfo()\fP instead. The yield of +\fBpcre_info()\fP is the number of capturing subpatterns, or one of the +following negative numbers: +.sp + PCRE_ERROR_NULL the argument \fIcode\fP was NULL + PCRE_ERROR_BADMAGIC the "magic number" was not found +.sp +If the \fIoptptr\fP argument is not NULL, a copy of the options with which the +pattern was compiled is placed in the integer it points to (see +PCRE_INFO_OPTIONS above). +.P +If the pattern is not anchored and the \fIfirstcharptr\fP argument is not NULL, +it is used to pass back information about the first character of any matched +string (see PCRE_INFO_FIRSTBYTE above). +. +. +.SH "REFERENCE COUNTS" +.rs +.sp +.B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP); +.PP +The \fBpcre_refcount()\fP function is used to maintain a reference count in the +data block that contains a compiled pattern. It is provided for the benefit of +applications that operate in an object-oriented manner, where different parts +of the application may be using the same compiled pattern, but you want to free +the block when they are all done. +.P +When a pattern is compiled, the reference count field is initialized to zero. +It is changed only by calling this function, whose action is to add the +\fIadjust\fP value (which may be positive or negative) to it. The yield of the +function is the new value. However, the value of the count is constrained to +lie between 0 and 65535, inclusive. If the new value is outside these limits, +it is forced to the appropriate limit value. +.P +Except when it is zero, the reference count is not correctly preserved if a +pattern is compiled on one host and then transferred to a host whose byte-order +is different. (This seems a highly unlikely scenario.) +. +. +.SH "MATCHING A PATTERN: THE TRADITIONAL FUNCTION" +.rs +.sp +.B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.ti +5n +.B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, +.ti +5n +.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP); +.P +The function \fBpcre_exec()\fP is called to match a subject string against a +compiled pattern, which is passed in the \fIcode\fP argument. If the +pattern has been studied, the result of the study should be passed in the +\fIextra\fP argument. This function is the main matching facility of the +library, and it operates in a Perl-like manner. For specialist use there is +also an alternative matching function, which is described +.\" HTML +.\" +below +.\" +in the section about the \fBpcre_dfa_exec()\fP function. +.P +In most applications, the pattern will have been compiled (and optionally +studied) in the same process that calls \fBpcre_exec()\fP. However, it is +possible to save compiled patterns and study data, and then use them later +in different processes, possibly even on different hosts. For a discussion +about this, see the +.\" HREF +\fBpcreprecompile\fP +.\" +documentation. +.P +Here is an example of a simple call to \fBpcre_exec()\fP: +.sp + int rc; + int ovector[30]; + rc = pcre_exec( + re, /* result of pcre_compile() */ + NULL, /* we didn't study the pattern */ + "some string", /* the subject string */ + 11, /* the length of the subject string */ + 0, /* start at offset 0 in the subject */ + 0, /* default options */ + ovector, /* vector of integers for substring information */ + 30); /* number of elements (NOT size in bytes) */ +. +.\" HTML +.SS "Extra data for \fBpcre_exec()\fR" +.rs +.sp +If the \fIextra\fP argument is not NULL, it must point to a \fBpcre_extra\fP +data block. The \fBpcre_study()\fP function returns such a block (when it +doesn't return NULL), but you can also create one for yourself, and pass +additional information in it. The \fBpcre_extra\fP block contains the following +fields (not necessarily in this order): +.sp + unsigned long int \fIflags\fP; + void *\fIstudy_data\fP; + unsigned long int \fImatch_limit\fP; + unsigned long int \fImatch_limit_recursion\fP; + void *\fIcallout_data\fP; + const unsigned char *\fItables\fP; +.sp +The \fIflags\fP field is a bitmap that specifies which of the other fields +are set. The flag bits are: +.sp + PCRE_EXTRA_STUDY_DATA + PCRE_EXTRA_MATCH_LIMIT + PCRE_EXTRA_MATCH_LIMIT_RECURSION + PCRE_EXTRA_CALLOUT_DATA + PCRE_EXTRA_TABLES +.sp +Other flag bits should be set to zero. The \fIstudy_data\fP field is set in the +\fBpcre_extra\fP block that is returned by \fBpcre_study()\fP, together with +the appropriate flag bit. You should not set this yourself, but you may add to +the block by setting the other fields and their corresponding flag bits. +.P +The \fImatch_limit\fP field provides a means of preventing PCRE from using up a +vast amount of resources when running patterns that are not going to match, +but which have a very large number of possibilities in their search trees. The +classic example is the use of nested unlimited repeats. +.P +Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly +(sometimes recursively). The limit set by \fImatch_limit\fP is imposed on the +number of times this function is called during a match, which has the effect of +limiting the amount of backtracking that can take place. For patterns that are +not anchored, the count restarts from zero for each position in the subject +string. +.P +The default value for the limit can be set when PCRE is built; the default +default is 10 million, which handles all but the most extreme cases. You can +override the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP +block in which \fImatch_limit\fP is set, and PCRE_EXTRA_MATCH_LIMIT is set in +the \fIflags\fP field. If the limit is exceeded, \fBpcre_exec()\fP returns +PCRE_ERROR_MATCHLIMIT. +.P +The \fImatch_limit_recursion\fP field is similar to \fImatch_limit\fP, but +instead of limiting the total number of times that \fBmatch()\fP is called, it +limits the depth of recursion. The recursion depth is a smaller number than the +total number of calls, because not all calls to \fBmatch()\fP are recursive. +This limit is of use only if it is set smaller than \fImatch_limit\fP. +.P +Limiting the recursion depth limits the amount of stack that can be used, or, +when PCRE has been compiled to use memory on the heap instead of the stack, the +amount of heap memory that can be used. +.P +The default value for \fImatch_limit_recursion\fP can be set when PCRE is +built; the default default is the same value as the default for +\fImatch_limit\fP. You can override the default by suppling \fBpcre_exec()\fP +with a \fBpcre_extra\fP block in which \fImatch_limit_recursion\fP is set, and +PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit +is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT. +.P +The \fIpcre_callout\fP field is used in conjunction with the "callout" feature, +which is described in the +.\" HREF +\fBpcrecallout\fP +.\" +documentation. +.P +The \fItables\fP field is used to pass a character tables pointer to +\fBpcre_exec()\fP; this overrides the value that is stored with the compiled +pattern. A non-NULL value is stored with the compiled pattern only if custom +tables were supplied to \fBpcre_compile()\fP via its \fItableptr\fP argument. +If NULL is passed to \fBpcre_exec()\fP using this mechanism, it forces PCRE's +internal tables to be used. This facility is helpful when re-using patterns +that have been saved after compiling with an external set of tables, because +the external tables might be at a different address when \fBpcre_exec()\fP is +called. See the +.\" HREF +\fBpcreprecompile\fP +.\" +documentation for a discussion of saving compiled patterns for later use. +. +.SS "Option bits for \fBpcre_exec()\fP" +.rs +.sp +The unused bits of the \fIoptions\fP argument for \fBpcre_exec()\fP must be +zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP, +PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL. +.sp + PCRE_ANCHORED +.sp +The PCRE_ANCHORED option limits \fBpcre_exec()\fP to matching at the first +matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out +to be anchored by virtue of its contents, it cannot be made unachored at +matching time. +.sp + PCRE_NEWLINE_CR + PCRE_NEWLINE_LF + PCRE_NEWLINE_CRLF +.sp +These options override the newline definition that was chosen or defaulted when +the pattern was compiled. For details, see the description \fBpcre_compile()\fP +above. During matching, the newline choice affects the behaviour of the dot, +circumflex, and dollar metacharacters. +.sp + PCRE_NOTBOL +.sp +This option specifies that first character of the subject string is not the +beginning of a line, so the circumflex metacharacter should not match before +it. Setting this without PCRE_MULTILINE (at compile time) causes circumflex +never to match. This option affects only the behaviour of the circumflex +metacharacter. It does not affect \eA. +.sp + PCRE_NOTEOL +.sp +This option specifies that the end of the subject string is not the end of a +line, so the dollar metacharacter should not match it nor (except in multiline +mode) a newline immediately before it. Setting this without PCRE_MULTILINE (at +compile time) causes dollar never to match. This option affects only the +behaviour of the dollar metacharacter. It does not affect \eZ or \ez. +.sp + PCRE_NOTEMPTY +.sp +An empty string is not considered to be a valid match if this option is set. If +there are alternatives in the pattern, they are tried. If all the alternatives +match the empty string, the entire match fails. For example, if the pattern +.sp + a?b? +.sp +is applied to a string not beginning with "a" or "b", it matches the empty +string at the start of the subject. With PCRE_NOTEMPTY set, this match is not +valid, so PCRE searches further into the string for occurrences of "a" or "b". +.P +Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case +of a pattern match of the empty string within its \fBsplit()\fP function, and +when using the /g modifier. It is possible to emulate Perl's behaviour after +matching a null string by first trying the match again at the same offset with +PCRE_NOTEMPTY and PCRE_ANCHORED, and then if that fails by advancing the +starting offset (see below) and trying an ordinary match again. There is some +code that demonstrates how to do this in the \fIpcredemo.c\fP sample program. +.sp + PCRE_NO_UTF8_CHECK +.sp +When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8 +string is automatically checked when \fBpcre_exec()\fP is subsequently called. +The value of \fIstartoffset\fP is also checked to ensure that it points to the +start of a UTF-8 character. If an invalid UTF-8 sequence of bytes is found, +\fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP +contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned. +.P +If you already know that your subject is valid, and you want to skip these +checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when +calling \fBpcre_exec()\fP. You might want to do this for the second and +subsequent calls to \fBpcre_exec()\fP if you are making repeated calls to find +all the matches in a single subject string. However, you should be sure that +the value of \fIstartoffset\fP points to the start of a UTF-8 character. When +PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid UTF-8 string as a +subject, or a value of \fIstartoffset\fP that does not point to the start of a +UTF-8 character, is undefined. Your program may crash. +.sp + PCRE_PARTIAL +.sp +This option turns on the partial matching feature. If the subject string fails +to match the pattern, but at some point during the matching process the end of +the subject was reached (that is, the subject partially matches the pattern and +the failure to match occurred only because there were not enough subject +characters), \fBpcre_exec()\fP returns PCRE_ERROR_PARTIAL instead of +PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is used, there are restrictions on what +may appear in the pattern. These are discussed in the +.\" HREF +\fBpcrepartial\fP +.\" +documentation. +. +.SS "The string to be matched by \fBpcre_exec()\fP" +.rs +.sp +The subject string is passed to \fBpcre_exec()\fP as a pointer in +\fIsubject\fP, a length in \fIlength\fP, and a starting byte offset in +\fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of a +UTF-8 character. Unlike the pattern string, the subject may contain binary zero +bytes. When the starting offset is zero, the search for a match starts at the +beginning of the subject, and this is by far the most common case. +.P +A non-zero starting offset is useful when searching for another match in the +same subject by calling \fBpcre_exec()\fP again after a previous success. +Setting \fIstartoffset\fP differs from just passing over a shortened string and +setting PCRE_NOTBOL in the case of a pattern that begins with any kind of +lookbehind. For example, consider the pattern +.sp + \eBiss\eB +.sp +which finds occurrences of "iss" in the middle of words. (\eB matches only if +the current position in the subject is not a word boundary.) When applied to +the string "Mississipi" the first call to \fBpcre_exec()\fP finds the first +occurrence. If \fBpcre_exec()\fP is called again with just the remainder of the +subject, namely "issipi", it does not match, because \eB is always false at the +start of the subject, which is deemed to be a word boundary. However, if +\fBpcre_exec()\fP is passed the entire string again, but with \fIstartoffset\fP +set to 4, it finds the second occurrence of "iss" because it is able to look +behind the starting point to discover that it is preceded by a letter. +.P +If a non-zero starting offset is passed when the pattern is anchored, one +attempt to match at the given offset is made. This can only succeed if the +pattern does not require the match to be at the start of the subject. +. +.SS "How \fBpcre_exec()\fP returns captured substrings" +.rs +.sp +In general, a pattern matches a certain portion of the subject, and in +addition, further substrings from the subject may be picked out by parts of the +pattern. Following the usage in Jeffrey Friedl's book, this is called +"capturing" in what follows, and the phrase "capturing subpattern" is used for +a fragment of a pattern that picks out a substring. PCRE supports several other +kinds of parenthesized subpattern that do not cause substrings to be captured. +.P +Captured substrings are returned to the caller via a vector of integer offsets +whose address is passed in \fIovector\fP. The number of elements in the vector +is passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP: +this argument is NOT the size of \fIovector\fP in bytes. +.P +The first two-thirds of the vector is used to pass back captured substrings, +each substring using a pair of integers. The remaining third of the vector is +used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns, +and is not available for passing back information. The length passed in +\fIovecsize\fP should always be a multiple of three. If it is not, it is +rounded down. +.P +When a match is successful, information about captured substrings is returned +in pairs of integers, starting at the beginning of \fIovector\fP, and +continuing up to two-thirds of its length at the most. The first element of a +pair is set to the offset of the first character in a substring, and the second +is set to the offset of the first character after the end of a substring. The +first pair, \fIovector[0]\fP and \fIovector[1]\fP, identify the portion of the +subject string matched by the entire pattern. The next pair is used for the +first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP +is one more than the highest numbered pair that has been set. For example, if +two substrings have been captured, the returned value is 3. If there are no +capturing subpatterns, the return value from a successful match is 1, +indicating that just the first pair of offsets has been set. +.P +If a capturing subpattern is matched repeatedly, it is the last portion of the +string that it matched that is returned. +.P +If the vector is too small to hold all the captured substring offsets, it is +used as far as possible (up to two-thirds of its length), and the function +returns a value of zero. In particular, if the substring offsets are not of +interest, \fBpcre_exec()\fP may be called with \fIovector\fP passed as NULL and +\fIovecsize\fP as zero. However, if the pattern contains back references and +the \fIovector\fP is not big enough to remember the related substrings, PCRE +has to get additional memory for use during matching. Thus it is usually +advisable to supply an \fIovector\fP. +.P +The \fBpcre_info()\fP function can be used to find out how many capturing +subpatterns there are in a compiled pattern. The smallest size for +\fIovector\fP that will allow for \fIn\fP captured substrings, in addition to +the offsets of the substring matched by the whole pattern, is (\fIn\fP+1)*3. +.P +It is possible for capturing subpattern number \fIn+1\fP to match some part of +the subject when subpattern \fIn\fP has not been used at all. For example, if +the string "abc" is matched against the pattern (a|(z))(bc) the return from the +function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this +happens, both values in the offset pairs corresponding to unused subpatterns +are set to -1. +.P +Offset values that correspond to unused subpatterns at the end of the +expression are also set to -1. For example, if the string "abc" is matched +against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The +return from the function is 2, because the highest used capturing subpattern +number is 1. However, you can refer to the offsets for the second and third +capturing subpatterns if you wish (assuming the vector is large enough, of +course). +.P +Some convenience functions are provided for extracting the captured substrings +as separate strings. These are described below. +. +.\" HTML +.SS "Error return values from \fBpcre_exec()\fP" +.rs +.sp +If \fBpcre_exec()\fP fails, it returns a negative number. The following are +defined in the header file: +.sp + PCRE_ERROR_NOMATCH (-1) +.sp +The subject string did not match the pattern. +.sp + PCRE_ERROR_NULL (-2) +.sp +Either \fIcode\fP or \fIsubject\fP was passed as NULL, or \fIovector\fP was +NULL and \fIovecsize\fP was not zero. +.sp + PCRE_ERROR_BADOPTION (-3) +.sp +An unrecognized bit was set in the \fIoptions\fP argument. +.sp + PCRE_ERROR_BADMAGIC (-4) +.sp +PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch +the case when it is passed a junk pointer and to detect when a pattern that was +compiled in an environment of one endianness is run in an environment with the +other endianness. This is the error that PCRE gives when the magic number is +not present. +.sp + PCRE_ERROR_UNKNOWN_NODE (-5) +.sp +While running the pattern match, an unknown item was encountered in the +compiled pattern. This error could be caused by a bug in PCRE or by overwriting +of the compiled pattern. +.sp + PCRE_ERROR_NOMEMORY (-6) +.sp +If a pattern contains back references, but the \fIovector\fP that is passed to +\fBpcre_exec()\fP is not big enough to remember the referenced substrings, PCRE +gets a block of memory at the start of matching to use for this purpose. If the +call via \fBpcre_malloc()\fP fails, this error is given. The memory is +automatically freed at the end of matching. +.sp + PCRE_ERROR_NOSUBSTRING (-7) +.sp +This error is used by the \fBpcre_copy_substring()\fP, +\fBpcre_get_substring()\fP, and \fBpcre_get_substring_list()\fP functions (see +below). It is never returned by \fBpcre_exec()\fP. +.sp + PCRE_ERROR_MATCHLIMIT (-8) +.sp +The backtracking limit, as specified by the \fImatch_limit\fP field in a +\fBpcre_extra\fP structure (or defaulted) was reached. See the description +above. +.sp + PCRE_ERROR_RECURSIONLIMIT (-21) +.sp +The internal recursion limit, as specified by the \fImatch_limit_recursion\fP +field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the +description above. +.sp + PCRE_ERROR_CALLOUT (-9) +.sp +This error is never generated by \fBpcre_exec()\fP itself. It is provided for +use by callout functions that want to yield a distinctive error code. See the +.\" HREF +\fBpcrecallout\fP +.\" +documentation for details. +.sp + PCRE_ERROR_BADUTF8 (-10) +.sp +A string that contains an invalid UTF-8 byte sequence was passed as a subject. +.sp + PCRE_ERROR_BADUTF8_OFFSET (-11) +.sp +The UTF-8 byte sequence that was passed as a subject was valid, but the value +of \fIstartoffset\fP did not point to the beginning of a UTF-8 character. +.sp + PCRE_ERROR_PARTIAL (-12) +.sp +The subject string did not match, but it did match partially. See the +.\" HREF +\fBpcrepartial\fP +.\" +documentation for details of partial matching. +.sp + PCRE_ERROR_BADPARTIAL (-13) +.sp +The PCRE_PARTIAL option was used with a compiled pattern containing items that +are not supported for partial matching. See the +.\" HREF +\fBpcrepartial\fP +.\" +documentation for details of partial matching. +.sp + PCRE_ERROR_INTERNAL (-14) +.sp +An unexpected internal error has occurred. This error could be caused by a bug +in PCRE or by overwriting of the compiled pattern. +.sp + PCRE_ERROR_BADCOUNT (-15) +.sp +This error is given if the value of the \fIovecsize\fP argument is negative. +. +. +.SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER" +.rs +.sp +.B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP, +.ti +5n +.B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP, +.ti +5n +.B int \fIbuffersize\fP); +.PP +.br +.B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP, +.ti +5n +.B int \fIstringcount\fP, int \fIstringnumber\fP, +.ti +5n +.B const char **\fIstringptr\fP); +.PP +.br +.B int pcre_get_substring_list(const char *\fIsubject\fP, +.ti +5n +.B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);" +.PP +Captured substrings can be accessed directly by using the offsets returned by +\fBpcre_exec()\fP in \fIovector\fP. For convenience, the functions +\fBpcre_copy_substring()\fP, \fBpcre_get_substring()\fP, and +\fBpcre_get_substring_list()\fP are provided for extracting captured substrings +as new, separate, zero-terminated strings. These functions identify substrings +by number. The next section describes functions for extracting named +substrings. +.P +A substring that contains a binary zero is correctly extracted and has a +further zero added on the end, but the result is not, of course, a C string. +However, you can process such a string by referring to the length that is +returned by \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP. +Unfortunately, the interface to \fBpcre_get_substring_list()\fP is not adequate +for handling strings containing binary zeros, because the end of the final +string is not independently indicated. +.P +The first three arguments are the same for all three of these functions: +\fIsubject\fP is the subject string that has just been successfully matched, +\fIovector\fP is a pointer to the vector of integer offsets that was passed to +\fBpcre_exec()\fP, and \fIstringcount\fP is the number of substrings that were +captured by the match, including the substring that matched the entire regular +expression. This is the value returned by \fBpcre_exec()\fP if it is greater +than zero. If \fBpcre_exec()\fP returned zero, indicating that it ran out of +space in \fIovector\fP, the value passed as \fIstringcount\fP should be the +number of elements in the vector divided by three. +.P +The functions \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP +extract a single substring, whose number is given as \fIstringnumber\fP. A +value of zero extracts the substring that matched the entire pattern, whereas +higher values extract the captured substrings. For \fBpcre_copy_substring()\fP, +the string is placed in \fIbuffer\fP, whose length is given by +\fIbuffersize\fP, while for \fBpcre_get_substring()\fP a new block of memory is +obtained via \fBpcre_malloc\fP, and its address is returned via +\fIstringptr\fP. The yield of the function is the length of the string, not +including the terminating zero, or one of +.sp + PCRE_ERROR_NOMEMORY (-6) +.sp +The buffer was too small for \fBpcre_copy_substring()\fP, or the attempt to get +memory failed for \fBpcre_get_substring()\fP. +.sp + PCRE_ERROR_NOSUBSTRING (-7) +.sp +There is no substring whose number is \fIstringnumber\fP. +.P +The \fBpcre_get_substring_list()\fP function extracts all available substrings +and builds a list of pointers to them. All this is done in a single block of +memory that is obtained via \fBpcre_malloc\fP. The address of the memory block +is returned via \fIlistptr\fP, which is also the start of the list of string +pointers. The end of the list is marked by a NULL pointer. The yield of the +function is zero if all went well, or +.sp + PCRE_ERROR_NOMEMORY (-6) +.sp +if the attempt to get the memory block failed. +.P +When any of these functions encounter a substring that is unset, which can +happen when capturing subpattern number \fIn+1\fP matches some part of the +subject, but subpattern \fIn\fP has not been used at all, they return an empty +string. This can be distinguished from a genuine zero-length substring by +inspecting the appropriate offset in \fIovector\fP, which is negative for unset +substrings. +.P +The two convenience functions \fBpcre_free_substring()\fP and +\fBpcre_free_substring_list()\fP can be used to free the memory returned by +a previous call of \fBpcre_get_substring()\fP or +\fBpcre_get_substring_list()\fP, respectively. They do nothing more than call +the function pointed to by \fBpcre_free\fP, which of course could be called +directly from a C program. However, PCRE is used in some situations where it is +linked via a special interface to another programming language that cannot use +\fBpcre_free\fP directly; it is for these cases that the functions are +provided. +. +. +.SH "EXTRACTING CAPTURED SUBSTRINGS BY NAME" +.rs +.sp +.B int pcre_get_stringnumber(const pcre *\fIcode\fP, +.ti +5n +.B const char *\fIname\fP); +.PP +.br +.B int pcre_copy_named_substring(const pcre *\fIcode\fP, +.ti +5n +.B const char *\fIsubject\fP, int *\fIovector\fP, +.ti +5n +.B int \fIstringcount\fP, const char *\fIstringname\fP, +.ti +5n +.B char *\fIbuffer\fP, int \fIbuffersize\fP); +.PP +.br +.B int pcre_get_named_substring(const pcre *\fIcode\fP, +.ti +5n +.B const char *\fIsubject\fP, int *\fIovector\fP, +.ti +5n +.B int \fIstringcount\fP, const char *\fIstringname\fP, +.ti +5n +.B const char **\fIstringptr\fP); +.PP +To extract a substring by name, you first have to find associated number. +For example, for this pattern +.sp + (a+)b(?P\ed+)... +.sp +the number of the subpattern called "xxx" is 2. If the name is known to be +unique (PCRE_DUPNAMES was not set), you can find the number from the name by +calling \fBpcre_get_stringnumber()\fP. The first argument is the compiled +pattern, and the second is the name. The yield of the function is the +subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of +that name. +.P +Given the number, you can extract the substring directly, or use one of the +functions described in the previous section. For convenience, there are also +two functions that do the whole job. +.P +Most of the arguments of \fBpcre_copy_named_substring()\fP and +\fBpcre_get_named_substring()\fP are the same as those for the similarly named +functions that extract by number. As these are described in the previous +section, they are not re-described here. There are just two differences: +.P +First, instead of a substring number, a substring name is given. Second, there +is an extra argument, given at the start, which is a pointer to the compiled +pattern. This is needed in order to gain access to the name-to-number +translation table. +.P +These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they +then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as +appropriate. +. +. +.SH "DUPLICATE SUBPATTERN NAMES" +.rs +.sp +.B int pcre_get_stringtable_entries(const pcre *\fIcode\fP, +.ti +5n +.B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP); +.PP +When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns +are not required to be unique. Normally, patterns with duplicate names are such +that in any one match, only one of the named subpatterns participates. An +example is shown in the +.\" HREF +\fBpcrepattern\fP +.\" +documentation. When duplicates are present, \fBpcre_copy_named_substring()\fP +and \fBpcre_get_named_substring()\fP return the first substring corresponding +to the given name that is set. If none are set, an empty string is returned. +The \fBpcre_get_stringnumber()\fP function returns one of the numbers that are +associated with the name, but it is not defined which it is. +.sp +If you want to get full details of all captured substrings for a given name, +you must use the \fBpcre_get_stringtable_entries()\fP function. The first +argument is the compiled pattern, and the second is the name. The third and +fourth are pointers to variables which are updated by the function. After it +has run, they point to the first and last entries in the name-to-number table +for the given name. The function itself returns the length of each entry, or +PCRE_ERROR_NOSUBSTRING if there are none. The format of the table is described +above in the section entitled \fIInformation about a pattern\fP. Given all the +relevant entries for the name, you can extract each of their numbers, and hence +the captured data, if any. +. +. +.SH "FINDING ALL POSSIBLE MATCHES" +.rs +.sp +The traditional matching function uses a similar algorithm to Perl, which stops +when it finds the first match, starting at a given point in the subject. If you +want to find all possible matches, or the longest possible match, consider +using the alternative matching function (see below) instead. If you cannot use +the alternative function, but still need to find all possible matches, you +can kludge it up by making use of the callout facility, which is described in +the +.\" HREF +\fBpcrecallout\fP +.\" +documentation. +.P +What you have to do is to insert a callout right at the end of the pattern. +When your callout function is called, extract and save the current matched +substring. Then return 1, which forces \fBpcre_exec()\fP to backtrack and try +other alternatives. Ultimately, when it runs out of matches, \fBpcre_exec()\fP +will yield PCRE_ERROR_NOMATCH. +. +. +.\" HTML +.SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION" +.rs +.sp +.B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP," +.ti +5n +.B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP, +.ti +5n +.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP, +.ti +5n +.B int *\fIworkspace\fP, int \fIwscount\fP); +.P +The function \fBpcre_dfa_exec()\fP is called to match a subject string against +a compiled pattern, using a "DFA" matching algorithm. This has different +characteristics to the normal algorithm, and is not compatible with Perl. Some +of the features of PCRE patterns are not supported. Nevertheless, there are +times when this kind of matching can be useful. For a discussion of the two +matching algorithms, see the +.\" HREF +\fBpcrematching\fP +.\" +documentation. +.P +The arguments for the \fBpcre_dfa_exec()\fP function are the same as for +\fBpcre_exec()\fP, plus two extras. The \fIovector\fP argument is used in a +different way, and this is described below. The other common arguments are used +in the same way as for \fBpcre_exec()\fP, so their description is not repeated +here. +.P +The two additional arguments provide workspace for the function. The workspace +vector should contain at least 20 elements. It is used for keeping track of +multiple paths through the pattern tree. More workspace will be needed for +patterns and subjects where there are a lot of potential matches. +.P +Here is an example of a simple call to \fBpcre_dfa_exec()\fP: +.sp + int rc; + int ovector[10]; + int wspace[20]; + rc = pcre_dfa_exec( + re, /* result of pcre_compile() */ + NULL, /* we didn't study the pattern */ + "some string", /* the subject string */ + 11, /* the length of the subject string */ + 0, /* start at offset 0 in the subject */ + 0, /* default options */ + ovector, /* vector of integers for substring information */ + 10, /* number of elements (NOT size in bytes) */ + wspace, /* working space vector */ + 20); /* number of elements (NOT size in bytes) */ +. +.SS "Option bits for \fBpcre_dfa_exec()\fP" +.rs +.sp +The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be +zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP, +PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL, +PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are +the same as for \fBpcre_exec()\fP, so their description is not repeated here. +.sp + PCRE_PARTIAL +.sp +This has the same general effect as it does for \fBpcre_exec()\fP, but the +details are slightly different. When PCRE_PARTIAL is set for +\fBpcre_dfa_exec()\fP, the return code PCRE_ERROR_NOMATCH is converted into +PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no +complete matches, but there is still at least one matching possibility. The +portion of the string that provided the partial match is set as the first +matching string. +.sp + PCRE_DFA_SHORTEST +.sp +Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as +soon as it has found one match. Because of the way the DFA algorithm works, +this is necessarily the shortest possible match at the first possible matching +point in the subject string. +.sp + PCRE_DFA_RESTART +.sp +When \fBpcre_dfa_exec()\fP is called with the PCRE_PARTIAL option, and returns +a partial match, it is possible to call it again, with additional subject +characters, and have it continue with the same match. The PCRE_DFA_RESTART +option requests this action; when it is set, the \fIworkspace\fP and +\fIwscount\fP options must reference the same vector as before because data +about the match so far is left in them after a partial match. There is more +discussion of this facility in the +.\" HREF +\fBpcrepartial\fP +.\" +documentation. +. +.SS "Successful returns from \fBpcre_dfa_exec()\fP" +.rs +.sp +When \fBpcre_dfa_exec()\fP succeeds, it may have matched more than one +substring in the subject. Note, however, that all the matches from one run of +the function start at the same point in the subject. The shorter matches are +all initial substrings of the longer matches. For example, if the pattern +.sp + <.*> +.sp +is matched against the string +.sp + This is no more +.sp +the three matched strings are +.sp + + + +.sp +On success, the yield of the function is a number greater than zero, which is +the number of matched substrings. The substrings themselves are returned in +\fIovector\fP. Each string uses two elements; the first is the offset to the +start, and the second is the offset to the end. All the strings have the same +start offset. (Space could have been saved by giving this only once, but it was +decided to retain some compatibility with the way \fBpcre_exec()\fP returns +data, even though the meaning of the strings is different.) +.P +The strings are returned in reverse order of length; that is, the longest +matching string is given first. If there were too many matches to fit into +\fIovector\fP, the yield of the function is zero, and the vector is filled with +the longest matches. +. +.SS "Error returns from \fBpcre_dfa_exec()\fP" +.rs +.sp +The \fBpcre_dfa_exec()\fP function returns a negative number when it fails. +Many of the errors are the same as for \fBpcre_exec()\fP, and these are +described +.\" HTML +.\" +above. +.\" +There are in addition the following errors that are specific to +\fBpcre_dfa_exec()\fP: +.sp + PCRE_ERROR_DFA_UITEM (-16) +.sp +This return is given if \fBpcre_dfa_exec()\fP encounters an item in the pattern +that it does not support, for instance, the use of \eC or a back reference. +.sp + PCRE_ERROR_DFA_UCOND (-17) +.sp +This return is given if \fBpcre_dfa_exec()\fP encounters a condition item in a +pattern that uses a back reference for the condition. This is not supported. +.sp + PCRE_ERROR_DFA_UMLIMIT (-18) +.sp +This return is given if \fBpcre_dfa_exec()\fP is called with an \fIextra\fP +block that contains a setting of the \fImatch_limit\fP field. This is not +supported (it is meaningless). +.sp + PCRE_ERROR_DFA_WSSIZE (-19) +.sp +This return is given if \fBpcre_dfa_exec()\fP runs out of space in the +\fIworkspace\fP vector. +.sp + PCRE_ERROR_DFA_RECURSE (-20) +.sp +When a recursive subpattern is processed, the matching function calls itself +recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This +error is given if the output vector is not large enough. This should be +extremely rare, as a vector of size 1000 is used. +.P +.in 0 +Last updated: 08 June 2006 +.br +Copyright (c) 1997-2006 University of Cambridge. diff --git a/libs/pcre/doc/pcrebuild.3 b/libs/pcre/doc/pcrebuild.3 new file mode 100644 index 0000000000..dee499d6a8 --- /dev/null +++ b/libs/pcre/doc/pcrebuild.3 @@ -0,0 +1,213 @@ +.TH PCREBUILD 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "PCRE BUILD-TIME OPTIONS" +.rs +.sp +This document describes the optional features of PCRE that can be selected when +the library is compiled. They are all selected, or deselected, by providing +options to the \fBconfigure\fP script that is run before the \fBmake\fP +command. The complete list of options for \fBconfigure\fP (which includes the +standard ones such as the selection of the installation directory) can be +obtained by running +.sp + ./configure --help +.sp +The following sections describe certain options whose names begin with --enable +or --disable. These settings specify changes to the defaults for the +\fBconfigure\fP command. Because of the way that \fBconfigure\fP works, +--enable and --disable always come in pairs, so the complementary option always +exists as well, but as it specifies the default, it is not described. +. +.SH "C++ SUPPORT" +.rs +.sp +By default, the \fBconfigure\fP script will search for a C++ compiler and C++ +header files. If it finds them, it automatically builds the C++ wrapper library +for PCRE. You can disable this by adding +.sp + --disable-cpp +.sp +to the \fBconfigure\fP command. +. +.SH "UTF-8 SUPPORT" +.rs +.sp +To build PCRE with support for UTF-8 character strings, add +.sp + --enable-utf8 +.sp +to the \fBconfigure\fP command. Of itself, this does not make PCRE treat +strings as UTF-8. As well as compiling PCRE with this option, you also have +have to set the PCRE_UTF8 option when you call the \fBpcre_compile()\fP +function. +. +.SH "UNICODE CHARACTER PROPERTY SUPPORT" +.rs +.sp +UTF-8 support allows PCRE to process character values greater than 255 in the +strings that it handles. On its own, however, it does not provide any +facilities for accessing the properties of such characters. If you want to be +able to use the pattern escapes \eP, \ep, and \eX, which refer to Unicode +character properties, you must add +.sp + --enable-unicode-properties +.sp +to the \fBconfigure\fP command. This implies UTF-8 support, even if you have +not explicitly requested it. +.P +Including Unicode property support adds around 90K of tables to the PCRE +library, approximately doubling its size. Only the general category properties +such as \fILu\fP and \fINd\fP are supported. Details are given in the +.\" HREF +\fBpcrepattern\fP +.\" +documentation. +. +.SH "CODE VALUE OF NEWLINE" +.rs +.sp +By default, PCRE interprets character 10 (linefeed, LF) as indicating the end +of a line. This is the normal newline character on Unix-like systems. You can +compile PCRE to use character 13 (carriage return, CR) instead, by adding +.sp + --enable-newline-is-cr +.sp +to the \fBconfigure\fP command. There is also a --enable-newline-is-lf option, +which explicitly specifies linefeed as the newline character. +.sp +Alternatively, you can specify that line endings are to be indicated by the two +character sequence CRLF. If you want this, add +.sp + --enable-newline-is-crlf +.sp +to the \fBconfigure\fP command. Whatever line ending convention is selected +when PCRE is built can be overridden when the library functions are called. At +build time it is conventional to use the standard for your operating system. +. +.SH "BUILDING SHARED AND STATIC LIBRARIES" +.rs +.sp +The PCRE building process uses \fBlibtool\fP to build both shared and static +Unix libraries by default. You can suppress one of these by adding one of +.sp + --disable-shared + --disable-static +.sp +to the \fBconfigure\fP command, as required. +. +.SH "POSIX MALLOC USAGE" +.rs +.sp +When PCRE is called through the POSIX interface (see the +.\" HREF +\fBpcreposix\fP +.\" +documentation), additional working storage is required for holding the pointers +to capturing substrings, because PCRE requires three integers per substring, +whereas the POSIX interface provides only two. If the number of expected +substrings is small, the wrapper function uses space on the stack, because this +is faster than using \fBmalloc()\fP for each call. The default threshold above +which the stack is no longer used is 10; it can be changed by adding a setting +such as +.sp + --with-posix-malloc-threshold=20 +.sp +to the \fBconfigure\fP command. +. +.SH "HANDLING VERY LARGE PATTERNS" +.rs +.sp +Within a compiled pattern, offset values are used to point from one part to +another (for example, from an opening parenthesis to an alternation +metacharacter). By default, two-byte values are used for these offsets, leading +to a maximum size for a compiled pattern of around 64K. This is sufficient to +handle all but the most gigantic patterns. Nevertheless, some people do want to +process enormous patterns, so it is possible to compile PCRE to use three-byte +or four-byte offsets by adding a setting such as +.sp + --with-link-size=3 +.sp +to the \fBconfigure\fP command. The value given must be 2, 3, or 4. Using +longer offsets slows down the operation of PCRE because it has to load +additional bytes when handling them. +.P +If you build PCRE with an increased link size, test 2 (and test 5 if you are +using UTF-8) will fail. Part of the output of these tests is a representation +of the compiled pattern, and this changes with the link size. +. +.SH "AVOIDING EXCESSIVE STACK USAGE" +.rs +.sp +When matching with the \fBpcre_exec()\fP function, PCRE implements backtracking +by making recursive calls to an internal function called \fBmatch()\fP. In +environments where the size of the stack is limited, this can severely limit +PCRE's operation. (The Unix environment does not usually suffer from this +problem, but it may sometimes be necessary to increase the maximum stack size. +There is a discussion in the +.\" HREF +\fBpcrestack\fP +.\" +documentation.) An alternative approach to recursion that uses memory from the +heap to remember data, instead of using recursive function calls, has been +implemented to work round the problem of limited stack size. If you want to +build a version of PCRE that works this way, add +.sp + --disable-stack-for-recursion +.sp +to the \fBconfigure\fP command. With this configuration, PCRE will use the +\fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP variables to call memory +management functions. Separate functions are provided because the usage is very +predictable: the block sizes requested are always the same, and the blocks are +always freed in reverse order. A calling program might be able to implement +optimized functions that perform better than the standard \fBmalloc()\fP and +\fBfree()\fP functions. PCRE runs noticeably more slowly when built in this +way. This option affects only the \fBpcre_exec()\fP function; it is not +relevant for the the \fBpcre_dfa_exec()\fP function. +. +.SH "LIMITING PCRE RESOURCE USAGE" +.rs +.sp +Internally, PCRE has a function called \fBmatch()\fP, which it calls repeatedly +(sometimes recursively) when matching a pattern with the \fBpcre_exec()\fP +function. By controlling the maximum number of times this function may be +called during a single matching operation, a limit can be placed on the +resources used by a single call to \fBpcre_exec()\fP. The limit can be changed +at run time, as described in the +.\" HREF +\fBpcreapi\fP +.\" +documentation. The default is 10 million, but this can be changed by adding a +setting such as +.sp + --with-match-limit=500000 +.sp +to the \fBconfigure\fP command. This setting has no effect on the +\fBpcre_dfa_exec()\fP matching function. +.P +In some environments it is desirable to limit the depth of recursive calls of +\fBmatch()\fP more strictly than the total number of calls, in order to +restrict the maximum amount of stack (or heap, if --disable-stack-for-recursion +is specified) that is used. A second limit controls this; it defaults to the +value that is set for --with-match-limit, which imposes no additional +constraints. However, you can set a lower limit by adding, for example, +.sp + --with-match-limit-recursion=10000 +.sp +to the \fBconfigure\fP command. This value can also be overridden at run time. +. +.SH "USING EBCDIC CODE" +.rs +.sp +PCRE assumes by default that it will run in an environment where the character +code is ASCII (or Unicode, which is a superset of ASCII). PCRE can, however, be +compiled to run in an EBCDIC environment by adding +.sp + --enable-ebcdic +.sp +to the \fBconfigure\fP command. +.P +.in 0 +Last updated: 06 June 2006 +.br +Copyright (c) 1997-2006 University of Cambridge. diff --git a/libs/pcre/doc/pcrecallout.3 b/libs/pcre/doc/pcrecallout.3 new file mode 100644 index 0000000000..e7fec005b5 --- /dev/null +++ b/libs/pcre/doc/pcrecallout.3 @@ -0,0 +1,161 @@ +.TH PCRECALLOUT 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "PCRE CALLOUTS" +.rs +.sp +.B int (*pcre_callout)(pcre_callout_block *); +.PP +PCRE provides a feature called "callout", which is a means of temporarily +passing control to the caller of PCRE in the middle of pattern matching. The +caller of PCRE provides an external function by putting its entry point in the +global variable \fIpcre_callout\fP. By default, this variable contains NULL, +which disables all calling out. +.P +Within a regular expression, (?C) indicates the points at which the external +function is to be called. Different callout points can be identified by putting +a number less than 256 after the letter C. The default value is zero. +For example, this pattern has two callout points: +.sp + (?C1)\deabc(?C2)def +.sp +If the PCRE_AUTO_CALLOUT option bit is set when \fBpcre_compile()\fP is called, +PCRE automatically inserts callouts, all with number 255, before each item in +the pattern. For example, if PCRE_AUTO_CALLOUT is used with the pattern +.sp + A(\ed{2}|--) +.sp +it is processed as if it were +.sp +(?C255)A(?C255)((?C255)\ed{2}(?C255)|(?C255)-(?C255)-(?C255))(?C255) +.sp +Notice that there is a callout before and after each parenthesis and +alternation bar. Automatic callouts can be used for tracking the progress of +pattern matching. The +.\" HREF +\fBpcretest\fP +.\" +command has an option that sets automatic callouts; when it is used, the output +indicates how the pattern is matched. This is useful information when you are +trying to optimize the performance of a particular pattern. +. +. +.SH "MISSING CALLOUTS" +.rs +.sp +You should be aware that, because of optimizations in the way PCRE matches +patterns, callouts sometimes do not happen. For example, if the pattern is +.sp + ab(?C4)cd +.sp +PCRE knows that any matching string must contain the letter "d". If the subject +string is "abyz", the lack of "d" means that matching doesn't ever start, and +the callout is never reached. However, with "abyd", though the result is still +no match, the callout is obeyed. +. +. +.SH "THE CALLOUT INTERFACE" +.rs +.sp +During matching, when PCRE reaches a callout point, the external function +defined by \fIpcre_callout\fP is called (if it is set). This applies to both +the \fBpcre_exec()\fP and the \fBpcre_dfa_exec()\fP matching functions. The +only argument to the callout function is a pointer to a \fBpcre_callout\fP +block. This structure contains the following fields: +.sp + int \fIversion\fP; + int \fIcallout_number\fP; + int *\fIoffset_vector\fP; + const char *\fIsubject\fP; + int \fIsubject_length\fP; + int \fIstart_match\fP; + int \fIcurrent_position\fP; + int \fIcapture_top\fP; + int \fIcapture_last\fP; + void *\fIcallout_data\fP; + int \fIpattern_position\fP; + int \fInext_item_length\fP; +.sp +The \fIversion\fP field is an integer containing the version number of the +block format. The initial version was 0; the current version is 1. The version +number will change again in future if additional fields are added, but the +intention is never to remove any of the existing fields. +.P +The \fIcallout_number\fP field contains the number of the callout, as compiled +into the pattern (that is, the number after ?C for manual callouts, and 255 for +automatically generated callouts). +.P +The \fIoffset_vector\fP field is a pointer to the vector of offsets that was +passed by the caller to \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. When +\fBpcre_exec()\fP is used, the contents can be inspected in order to extract +substrings that have been matched so far, in the same way as for extracting +substrings after a match has completed. For \fBpcre_dfa_exec()\fP this field is +not useful. +.P +The \fIsubject\fP and \fIsubject_length\fP fields contain copies of the values +that were passed to \fBpcre_exec()\fP. +.P +The \fIstart_match\fP field contains the offset within the subject at which the +current match attempt started. If the pattern is not anchored, the callout +function may be called several times from the same point in the pattern for +different starting points in the subject. +.P +The \fIcurrent_position\fP field contains the offset within the subject of the +current match pointer. +.P +When the \fBpcre_exec()\fP function is used, the \fIcapture_top\fP field +contains one more than the number of the highest numbered captured substring so +far. If no substrings have been captured, the value of \fIcapture_top\fP is +one. This is always the case when \fBpcre_dfa_exec()\fP is used, because it +does not support captured substrings. +.P +The \fIcapture_last\fP field contains the number of the most recently captured +substring. If no substrings have been captured, its value is -1. This is always +the case when \fBpcre_dfa_exec()\fP is used. +.P +The \fIcallout_data\fP field contains a value that is passed to +\fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP specifically so that it can be +passed back in callouts. It is passed in the \fIpcre_callout\fP field of the +\fBpcre_extra\fP data structure. If no such data was passed, the value of +\fIcallout_data\fP in a \fBpcre_callout\fP block is NULL. There is a +description of the \fBpcre_extra\fP structure in the +.\" HREF +\fBpcreapi\fP +.\" +documentation. +.P +The \fIpattern_position\fP field is present from version 1 of the +\fIpcre_callout\fP structure. It contains the offset to the next item to be +matched in the pattern string. +.P +The \fInext_item_length\fP field is present from version 1 of the +\fIpcre_callout\fP structure. It contains the length of the next item to be +matched in the pattern string. When the callout immediately precedes an +alternation bar, a closing parenthesis, or the end of the pattern, the length +is zero. When the callout precedes an opening parenthesis, the length is that +of the entire subpattern. +.P +The \fIpattern_position\fP and \fInext_item_length\fP fields are intended to +help in distinguishing between different automatic callouts, which all have the +same callout number. However, they are set for all callouts. +. +. +.SH "RETURN VALUES" +.rs +.sp +The external callout function returns an integer to PCRE. If the value is zero, +matching proceeds as normal. If the value is greater than zero, matching fails +at the current point, but the testing of other matching possibilities goes +ahead, just as if a lookahead assertion had failed. If the value is less than +zero, the match is abandoned, and \fBpcre_exec()\fP (or \fBpcre_dfa_exec()\fP) +returns the negative value. +.P +Negative values should normally be chosen from the set of PCRE_ERROR_xxx +values. In particular, PCRE_ERROR_NOMATCH forces a standard "no match" failure. +The error number PCRE_ERROR_CALLOUT is reserved for use by callout functions; +it will never be used by PCRE itself. +.P +.in 0 +Last updated: 28 February 2005 +.br +Copyright (c) 1997-2005 University of Cambridge. diff --git a/libs/pcre/doc/pcrecompat.3 b/libs/pcre/doc/pcrecompat.3 new file mode 100644 index 0000000000..8929177ea0 --- /dev/null +++ b/libs/pcre/doc/pcrecompat.3 @@ -0,0 +1,126 @@ +.TH PCRECOMPAT 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "DIFFERENCES BETWEEN PCRE AND PERL" +.rs +.sp +This document describes the differences in the ways that PCRE and Perl handle +regular expressions. The differences described here are with respect to Perl +5.8. +.P +1. PCRE has only a subset of Perl's UTF-8 and Unicode support. Details of what +it does have are given in the +.\" HTML +.\" +section on UTF-8 support +.\" +in the main +.\" HREF +\fBpcre\fP +.\" +page. +.P +2. PCRE does not allow repeat quantifiers on lookahead assertions. Perl permits +them, but they do not mean what you might think. For example, (?!a){3} does +not assert that the next three characters are not "a". It just asserts that the +next character is not "a" three times. +.P +3. Capturing subpatterns that occur inside negative lookahead assertions are +counted, but their entries in the offsets vector are never set. Perl sets its +numerical variables from any such patterns that are matched before the +assertion fails to match something (thereby succeeding), but only if the +negative lookahead assertion contains just one branch. +.P +4. Though binary zero characters are supported in the subject string, they are +not allowed in a pattern string because it is passed as a normal C string, +terminated by zero. The escape sequence \e0 can be used in the pattern to +represent a binary zero. +.P +5. The following Perl escape sequences are not supported: \el, \eu, \eL, +\eU, and \eN. In fact these are implemented by Perl's general string-handling +and are not part of its pattern matching engine. If any of these are +encountered by PCRE, an error is generated. +.P +6. The Perl escape sequences \ep, \eP, and \eX are supported only if PCRE is +built with Unicode character property support. The properties that can be +tested with \ep and \eP are limited to the general category properties such as +Lu and Nd, script names such as Greek or Han, and the derived properties Any +and L&. +.P +7. PCRE does support the \eQ...\eE escape for quoting substrings. Characters in +between are treated as literals. This is slightly different from Perl in that $ +and @ are also handled as literals inside the quotes. In Perl, they cause +variable interpolation (but of course PCRE does not have variables). Note the +following examples: +.sp + Pattern PCRE matches Perl matches +.sp +.\" JOIN + \eQabc$xyz\eE abc$xyz abc followed by the + contents of $xyz + \eQabc\e$xyz\eE abc\e$xyz abc\e$xyz + \eQabc\eE\e$\eQxyz\eE abc$xyz abc$xyz +.sp +The \eQ...\eE sequence is recognized both inside and outside character classes. +.P +8. Fairly obviously, PCRE does not support the (?{code}) and (?p{code}) +constructions. However, there is support for recursive patterns using the +non-Perl items (?R), (?number), and (?P>name). Also, the PCRE "callout" feature +allows an external function to be called during pattern matching. See the +.\" HREF +\fBpcrecallout\fP +.\" +documentation for details. +.P +9. There are some differences that are concerned with the settings of captured +strings when part of a pattern is repeated. For example, matching "aba" against +the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE it is set to "b". +.P +10. PCRE provides some extensions to the Perl regular expression facilities: +.sp +(a) Although lookbehind assertions must match fixed length strings, each +alternative branch of a lookbehind assertion can match a different length of +string. Perl requires them all to have the same length. +.sp +(b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ +meta-character matches only at the very end of the string. +.sp +(c) If PCRE_EXTRA is set, a backslash followed by a letter with no special +meaning is faulted. Otherwise, like Perl, the backslash is ignored. (Perl can +be made to issue a warning.) +.sp +(d) If PCRE_UNGREEDY is set, the greediness of the repetition quantifiers is +inverted, that is, by default they are not greedy, but if followed by a +question mark they are. +.sp +(e) PCRE_ANCHORED can be used at matching time to force a pattern to be tried +only at the first matching position in the subject string. +.sp +(f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NO_AUTO_CAPTURE +options for \fBpcre_exec()\fP have no Perl equivalents. +.sp +(g) The (?R), (?number), and (?P>name) constructs allows for recursive pattern +matching (Perl can do this using the (?p{code}) construct, which PCRE cannot +support.) +.sp +(h) PCRE supports named capturing substrings, using the Python syntax. +.sp +(i) PCRE supports the possessive quantifier "++" syntax, taken from Sun's Java +package. +.sp +(j) The (R) condition, for testing recursion, is a PCRE extension. +.sp +(k) The callout facility is PCRE-specific. +.sp +(l) The partial matching facility is PCRE-specific. +.sp +(m) Patterns compiled by PCRE can be saved and re-used at a later time, even on +different hosts that have the other endianness. +.sp +(n) The alternative matching function (\fBpcre_dfa_exec()\fP) matches in a +different way and is not Perl-compatible. +.P +.in 0 +Last updated: 06 June 2006 +.br +Copyright (c) 1997-2006 University of Cambridge. diff --git a/libs/pcre/doc/pcrecpp.3 b/libs/pcre/doc/pcrecpp.3 new file mode 100644 index 0000000000..e1cec6df58 --- /dev/null +++ b/libs/pcre/doc/pcrecpp.3 @@ -0,0 +1,312 @@ +.TH PCRECPP 3 +.SH NAME +PCRE - Perl-compatible regular expressions. +.SH "SYNOPSIS OF C++ WRAPPER" +.rs +.sp +.B #include +.PP +.SM +.br +.SH DESCRIPTION +.rs +.sp +The C++ wrapper for PCRE was provided by Google Inc. Some additional +functionality was added by Giuseppe Maxia. This brief man page was constructed +from the notes in the \fIpcrecpp.h\fP file, which should be consulted for +further details. +. +. +.SH "MATCHING INTERFACE" +.rs +.sp +The "FullMatch" operation checks that supplied text matches a supplied pattern +exactly. If pointer arguments are supplied, it copies matched sub-strings that +match sub-patterns into them. +.sp + Example: successful match + pcrecpp::RE re("h.*o"); + re.FullMatch("hello"); +.sp + Example: unsuccessful match (requires full match): + pcrecpp::RE re("e"); + !re.FullMatch("hello"); +.sp + Example: creating a temporary RE object: + pcrecpp::RE("h.*o").FullMatch("hello"); +.sp +You can pass in a "const char*" or a "string" for "text". The examples below +tend to use a const char*. You can, as in the different examples above, store +the RE object explicitly in a variable or use a temporary RE object. The +examples below use one mode or the other arbitrarily. Either could correctly be +used for any of these examples. +.P +You must supply extra pointer arguments to extract matched subpieces. +.sp + Example: extracts "ruby" into "s" and 1234 into "i" + int i; + string s; + pcrecpp::RE re("(\e\ew+):(\e\ed+)"); + re.FullMatch("ruby:1234", &s, &i); +.sp + Example: does not try to extract any extra sub-patterns + re.FullMatch("ruby:1234", &s); +.sp + Example: does not try to extract into NULL + re.FullMatch("ruby:1234", NULL, &i); +.sp + Example: integer overflow causes failure + !re.FullMatch("ruby:1234567891234", NULL, &i); +.sp + Example: fails because there aren't enough sub-patterns: + !pcrecpp::RE("\e\ew+:\e\ed+").FullMatch("ruby:1234", &s); +.sp + Example: fails because string cannot be stored in integer + !pcrecpp::RE("(.*)").FullMatch("ruby", &i); +.sp +The provided pointer arguments can be pointers to any scalar numeric +type, or one of: +.sp + string (matched piece is copied to string) + StringPiece (StringPiece is mutated to point to matched piece) + T (where "bool T::ParseFrom(const char*, int)" exists) + NULL (the corresponding matched sub-pattern is not copied) +.sp +The function returns true iff all of the following conditions are satisfied: +.sp + a. "text" matches "pattern" exactly; +.sp + b. The number of matched sub-patterns is >= number of supplied + pointers; +.sp + c. The "i"th argument has a suitable type for holding the + string captured as the "i"th sub-pattern. If you pass in + NULL for the "i"th argument, or pass fewer arguments than + number of sub-patterns, "i"th captured sub-pattern is + ignored. +.sp +The matching interface supports at most 16 arguments per call. +If you need more, consider using the more general interface +\fBpcrecpp::RE::DoMatch\fP. See \fBpcrecpp.h\fP for the signature for +\fBDoMatch\fP. +. +.SH "PARTIAL MATCHES" +.rs +.sp +You can use the "PartialMatch" operation when you want the pattern +to match any substring of the text. +.sp + Example: simple search for a string: + pcrecpp::RE("ell").PartialMatch("hello"); +.sp + Example: find first number in a string: + int number; + pcrecpp::RE re("(\e\ed+)"); + re.PartialMatch("x*100 + 20", &number); + assert(number == 100); +. +. +.SH "UTF-8 AND THE MATCHING INTERFACE" +.rs +.sp +By default, pattern and text are plain text, one byte per character. The UTF8 +flag, passed to the constructor, causes both pattern and string to be treated +as UTF-8 text, still a byte stream but potentially multiple bytes per +character. In practice, the text is likelier to be UTF-8 than the pattern, but +the match returned may depend on the UTF8 flag, so always use it when matching +UTF8 text. For example, "." will match one byte normally but with UTF8 set may +match up to three bytes of a multi-byte character. +.sp + Example: + pcrecpp::RE_Options options; + options.set_utf8(); + pcrecpp::RE re(utf8_pattern, options); + re.FullMatch(utf8_string); +.sp + Example: using the convenience function UTF8(): + pcrecpp::RE re(utf8_pattern, pcrecpp::UTF8()); + re.FullMatch(utf8_string); +.sp +NOTE: The UTF8 flag is ignored if pcre was not configured with the + --enable-utf8 flag. +. +. +.SH "PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE" +.rs +.sp +PCRE defines some modifiers to change the behavior of the regular expression +engine. The C++ wrapper defines an auxiliary class, RE_Options, as a vehicle to +pass such modifiers to a RE class. Currently, the following modifiers are +supported: +.sp + modifier description Perl corresponding +.sp + PCRE_CASELESS case insensitive match /i + PCRE_MULTILINE multiple lines match /m + PCRE_DOTALL dot matches newlines /s + PCRE_DOLLAR_ENDONLY $ matches only at end N/A + PCRE_EXTRA strict escape parsing N/A + PCRE_EXTENDED ignore whitespaces /x + PCRE_UTF8 handles UTF8 chars built-in + PCRE_UNGREEDY reverses * and *? N/A + PCRE_NO_AUTO_CAPTURE disables capturing parens N/A (*) +.sp +(*) Both Perl and PCRE allow non capturing parentheses by means of the +"?:" modifier within the pattern itself. e.g. (?:ab|cd) does not +capture, while (ab|cd) does. +.P +For a full account on how each modifier works, please check the +PCRE API reference page. +.P +For each modifier, there are two member functions whose name is made +out of the modifier in lowercase, without the "PCRE_" prefix. For +instance, PCRE_CASELESS is handled by +.sp + bool caseless() +.sp +which returns true if the modifier is set, and +.sp + RE_Options & set_caseless(bool) +.sp +which sets or unsets the modifier. Moreover, PCRE_EXTRA_MATCH_LIMIT can be +accessed through the \fBset_match_limit()\fR and \fBmatch_limit()\fR member +functions. Setting \fImatch_limit\fR to a non-zero value will limit the +execution of pcre to keep it from doing bad things like blowing the stack or +taking an eternity to return a result. A value of 5000 is good enough to stop +stack blowup in a 2MB thread stack. Setting \fImatch_limit\fR to zero disables +match limiting. Alternatively, you can call \fBmatch_limit_recursion()\fP +which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION to limit how much PCRE +recurses. \fBmatch_limit()\fP limits the number of matches PCRE does; +\fBmatch_limit_recursion()\fP limits the depth of internal recursion, and +therefore the amount of stack that is used. +.P +Normally, to pass one or more modifiers to a RE class, you declare +a \fIRE_Options\fR object, set the appropriate options, and pass this +object to a RE constructor. Example: +.sp + RE_options opt; + opt.set_caseless(true); + if (RE("HELLO", opt).PartialMatch("hello world")) ... +.sp +RE_options has two constructors. The default constructor takes no arguments and +creates a set of flags that are off by default. The optional parameter +\fIoption_flags\fR is to facilitate transfer of legacy code from C programs. +This lets you do +.sp + RE(pattern, + RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str); +.sp +However, new code is better off doing +.sp + RE(pattern, + RE_Options().set_caseless(true).set_multiline(true)) + .PartialMatch(str); +.sp +If you are going to pass one of the most used modifiers, there are some +convenience functions that return a RE_Options class with the +appropriate modifier already set: \fBCASELESS()\fR, \fBUTF8()\fR, +\fBMULTILINE()\fR, \fBDOTALL\fR(), and \fBEXTENDED()\fR. +.P +If you need to set several options at once, and you don't want to go through +the pains of declaring a RE_Options object and setting several options, there +is a parallel method that give you such ability on the fly. You can concatenate +several \fBset_xxxxx()\fR member functions, since each of them returns a +reference to its class object. For example, to pass PCRE_CASELESS, +PCRE_EXTENDED, and PCRE_MULTILINE to a RE with one statement, you may write: +.sp + RE(" ^ xyz \e\es+ .* blah$", + RE_Options() + .set_caseless(true) + .set_extended(true) + .set_multiline(true)).PartialMatch(sometext); +.sp +. +. +.SH "SCANNING TEXT INCREMENTALLY" +.rs +.sp +The "Consume" operation may be useful if you want to repeatedly +match regular expressions at the front of a string and skip over +them as they match. This requires use of the "StringPiece" type, +which represents a sub-range of a real string. Like RE, StringPiece +is defined in the pcrecpp namespace. +.sp + Example: read lines of the form "var = value" from a string. + string contents = ...; // Fill string somehow + pcrecpp::StringPiece input(contents); // Wrap in a StringPiece + + string var; + int value; + pcrecpp::RE re("(\e\ew+) = (\e\ed+)\en"); + while (re.Consume(&input, &var, &value)) { + ...; + } +.sp +Each successful call to "Consume" will set "var/value", and also +advance "input" so it points past the matched text. +.P +The "FindAndConsume" operation is similar to "Consume" but does not +anchor your match at the beginning of the string. For example, you +could extract all words from a string by repeatedly calling +.sp + pcrecpp::RE("(\e\ew+)").FindAndConsume(&input, &word) +. +. +.SH "PARSING HEX/OCTAL/C-RADIX NUMBERS" +.rs +.sp +By default, if you pass a pointer to a numeric value, the +corresponding text is interpreted as a base-10 number. You can +instead wrap the pointer with a call to one of the operators Hex(), +Octal(), or CRadix() to interpret the text in another base. The +CRadix operator interprets C-style "0" (base-8) and "0x" (base-16) +prefixes, but defaults to base-10. +.sp + Example: + int a, b, c, d; + pcrecpp::RE re("(.*) (.*) (.*) (.*)"); + re.FullMatch("100 40 0100 0x40", + pcrecpp::Octal(&a), pcrecpp::Hex(&b), + pcrecpp::CRadix(&c), pcrecpp::CRadix(&d)); +.sp +will leave 64 in a, b, c, and d. +. +. +.SH "REPLACING PARTS OF STRINGS" +.rs +.sp +You can replace the first match of "pattern" in "str" with "rewrite". +Within "rewrite", backslash-escaped digits (\e1 to \e9) can be +used to insert text matching corresponding parenthesized group +from the pattern. \e0 in "rewrite" refers to the entire matching +text. For example: +.sp + string s = "yabba dabba doo"; + pcrecpp::RE("b+").Replace("d", &s); +.sp +will leave "s" containing "yada dabba doo". The result is true if the pattern +matches and a replacement occurs, false otherwise. +.P +\fBGlobalReplace\fP is like \fBReplace\fP except that it replaces all +occurrences of the pattern in the string with the rewrite. Replacements are +not subject to re-matching. For example: +.sp + string s = "yabba dabba doo"; + pcrecpp::RE("b+").GlobalReplace("d", &s); +.sp +will leave "s" containing "yada dada doo". It returns the number of +replacements made. +.P +\fBExtract\fP is like \fBReplace\fP, except that if the pattern matches, +"rewrite" is copied into "out" (an additional argument) with substitutions. +The non-matching portions of "text" are ignored. Returns true iff a match +occurred and the extraction happened successfully; if no match occurs, the +string is left unaffected. +. +. +.SH AUTHOR +.rs +.sp +The C++ wrapper was contributed by Google Inc. +.br +Copyright (c) 2005 Google Inc. diff --git a/libs/pcre/doc/pcregrep.1 b/libs/pcre/doc/pcregrep.1 new file mode 100644 index 0000000000..62fa1a2b9a --- /dev/null +++ b/libs/pcre/doc/pcregrep.1 @@ -0,0 +1,376 @@ +.TH PCREGREP 1 +.SH NAME +pcregrep - a grep with Perl-compatible regular expressions. +.SH SYNOPSIS +.B pcregrep [options] [long options] [pattern] [path1 path2 ...] +. +.SH DESCRIPTION +.rs +.sp +\fBpcregrep\fP searches files for character patterns, in the same way as other +grep commands do, but it uses the PCRE regular expression library to support +patterns that are compatible with the regular expressions of Perl 5. See +.\" HREF +\fBpcrepattern\fP +.\" +for a full description of syntax and semantics of the regular expressions that +PCRE supports. +.P +Patterns, whether supplied on the command line or in a separate file, are given +without delimiters. For example: +.sp + pcregrep Thursday /etc/motd +.sp +If you attempt to use delimiters (for example, by surrounding a pattern with +slashes, as is common in Perl scripts), they are interpreted as part of the +pattern. Quotes can of course be used on the command line because they are +interpreted by the shell, and indeed they are required if a pattern contains +white space or shell metacharacters. +.P +The first argument that follows any option settings is treated as the single +pattern to be matched when neither \fB-e\fP nor \fB-f\fP is present. +Conversely, when one or both of these options are used to specify patterns, all +arguments are treated as path names. At least one of \fB-e\fP, \fB-f\fP, or an +argument pattern must be provided. +.P +If no files are specified, \fBpcregrep\fP reads the standard input. The +standard input can also be referenced by a name consisting of a single hyphen. +For example: +.sp + pcregrep some-pattern /file1 - /file3 +.sp +By default, each line that matches the pattern is copied to the standard +output, and if there is more than one file, the file name is output at the +start of each line. However, there are options that can change how +\fBpcregrep\fP behaves. In particular, the \fB-M\fP option makes it possible to +search for patterns that span line boundaries. What defines a line boundary is +controlled by the \fB-N\fP (\fB--newline\fP) option. +.P +Patterns are limited to 8K or BUFSIZ characters, whichever is the greater. +BUFSIZ is defined in \fB\fP. +.P +If the \fBLC_ALL\fP or \fBLC_CTYPE\fP environment variable is set, +\fBpcregrep\fP uses the value to set a locale when calling the PCRE library. +The \fB--locale\fP option can be used to override this. +. +.SH OPTIONS +.rs +.TP 10 +\fB--\fP +This terminate the list of options. It is useful if the next item on the +command line starts with a hyphen but is not an option. This allows for the +processing of patterns and filenames that start with hyphens. +.TP +\fB-A\fP \fInumber\fP, \fB--after-context=\fP\fInumber\fP +Output \fInumber\fP lines of context after each matching line. If filenames +and/or line numbers are being output, a hyphen separator is used instead of a +colon for the context lines. A line containing "--" is output between each +group of lines, unless they are in fact contiguous in the input file. The value +of \fInumber\fP is expected to be relatively small. However, \fBpcregrep\fP +guarantees to have up to 8K of following text available for context output. +.TP +\fB-B\fP \fInumber\fP, \fB--before-context=\fP\fInumber\fP +Output \fInumber\fP lines of context before each matching line. If filenames +and/or line numbers are being output, a hyphen separator is used instead of a +colon for the context lines. A line containing "--" is output between each +group of lines, unless they are in fact contiguous in the input file. The value +of \fInumber\fP is expected to be relatively small. However, \fBpcregrep\fP +guarantees to have up to 8K of preceding text available for context output. +.TP +\fB-C\fP \fInumber\fP, \fB--context=\fP\fInumber\fP +Output \fInumber\fP lines of context both before and after each matching line. +This is equivalent to setting both \fB-A\fP and \fB-B\fP to the same value. +.TP +\fB-c\fP, \fB--count\fP +Do not output individual lines; instead just output a count of the number of +lines that would otherwise have been output. If several files are given, a +count is output for each of them. In this mode, the \fB-A\fP, \fB-B\fP, and +\fB-C\fP options are ignored. +.TP +\fB--colour\fP, \fB--color\fP +If this option is given without any data, it is equivalent to "--colour=auto". +If data is required, it must be given in the same shell item, separated by an +equals sign. +.TP +\fB--colour=\fP\fIvalue\fP, \fB--color=\fP\fIvalue\fP +This option specifies under what circumstances the part of a line that matched +a pattern should be coloured in the output. The value may be "never" (the +default), "always", or "auto". In the latter case, colouring happens only if +the standard output is connected to a terminal. The colour can be specified by +setting the environment variable PCREGREP_COLOUR or PCREGREP_COLOR. The value +of this variable should be a string of two numbers, separated by a semicolon. +They are copied directly into the control string for setting colour on a +terminal, so it is your responsibility to ensure that they make sense. If +neither of the environment variables is set, the default is "1;31", which gives +red. +.TP +\fB-D\fP \fIaction\fP, \fB--devices=\fP\fIaction\fP +If an input path is not a regular file or a directory, "action" specifies how +it is to be processed. Valid values are "read" (the default) or "skip" +(silently skip the path). +.TP +\fB-d\fP \fIaction\fP, \fB--directories=\fP\fIaction\fP +If an input path is a directory, "action" specifies how it is to be processed. +Valid values are "read" (the default), "recurse" (equivalent to the \fB-r\fP +option), or "skip" (silently skip the path). In the default case, directories +are read as if they were ordinary files. In some operating systems the effect +of reading a directory like this is an immediate end-of-file. +.TP +\fB-e\fP \fIpattern\fP, \fB--regex=\fP\fIpattern\fP, +\fB--regexp=\fP\fIpattern\fP Specify a pattern to be matched. This option can +be used multiple times in order to specify several patterns. It can also be +used as a way of specifying a single pattern that starts with a hyphen. When +\fB-e\fP is used, no argument pattern is taken from the command line; all +arguments are treated as file names. There is an overall maximum of 100 +patterns. They are applied to each line in the order in which they are defined +until one matches (or fails to match if \fB-v\fP is used). If \fB-f\fP is used +with \fB-e\fP, the command line patterns are matched first, followed by the +patterns from the file, independent of the order in which these options are +specified. Note that multiple use of \fB-e\fP is not the same as a single +pattern with alternatives. For example, X|Y finds the first character in a line +that is X or Y, whereas if the two patterns are given separately, +\fBpcregrep\fP finds X if it is present, even if it follows Y in the line. It +finds Y only if there is no X in the line. This really matters only if you are +using \fB-o\fP to show the portion of the line that matched. +.TP +\fB--exclude\fP=\fIpattern\fP +When \fBpcregrep\fP is searching the files in a directory as a consequence of +the \fB-r\fP (recursive search) option, any files whose names match the pattern +are excluded. The pattern is a PCRE regular expression. If a file name matches +both \fB--include\fP and \fB--exclude\fP, it is excluded. There is no short +form for this option. +.TP +\fB-F\fP, \fB--fixed-strings\fP +Interpret each pattern as a list of fixed strings, separated by newlines, +instead of as a regular expression. The \fB-w\fP (match as a word) and \fB-x\fP +(match whole line) options can be used with \fB-F\fP. They apply to each of the +fixed strings. A line is selected if any of the fixed strings are found in it +(subject to \fB-w\fP or \fB-x\fP, if present). +.TP +\fB-f\fP \fIfilename\fP, \fB--file=\fP\fIfilename\fP +Read a number of patterns from the file, one per line, and match them against +each line of input. A data line is output if any of the patterns match it. The +filename can be given as "-" to refer to the standard input. When \fB-f\fP is +used, patterns specified on the command line using \fB-e\fP may also be +present; they are tested before the file's patterns. However, no other pattern +is taken from the command line; all arguments are treated as file names. There +is an overall maximum of 100 patterns. Trailing white space is removed from +each line, and blank lines are ignored. An empty file contains no patterns and +therefore matches nothing. +.TP +\fB-H\fP, \fB--with-filename\fP +Force the inclusion of the filename at the start of output lines when searching +a single file. By default, the filename is not shown in this case. For matching +lines, the filename is followed by a colon and a space; for context lines, a +hyphen separator is used. If a line number is also being output, it follows the +file name without a space. +.TP +\fB-h\fP, \fB--no-filename\fP +Suppress the output filenames when searching multiple files. By default, +filenames are shown when multiple files are searched. For matching lines, the +filename is followed by a colon and a space; for context lines, a hyphen +separator is used. If a line number is also being output, it follows the file +name without a space. +.TP +\fB--help\fP +Output a brief help message and exit. +.TP +\fB-i\fP, \fB--ignore-case\fP +Ignore upper/lower case distinctions during comparisons. +.TP +\fB--include\fP=\fIpattern\fP +When \fBpcregrep\fP is searching the files in a directory as a consequence of +the \fB-r\fP (recursive search) option, only those files whose names match the +pattern are included. The pattern is a PCRE regular expression. If a file name +matches both \fB--include\fP and \fB--exclude\fP, it is excluded. There is no +short form for this option. +.TP +\fB-L\fP, \fB--files-without-match\fP +Instead of outputting lines from the files, just output the names of the files +that do not contain any lines that would have been output. Each file name is +output once, on a separate line. +.TP +\fB-l\fP, \fB--files-with-matches\fP +Instead of outputting lines from the files, just output the names of the files +containing lines that would have been output. Each file name is output +once, on a separate line. Searching stops as soon as a matching line is found +in a file. +.TP +\fB--label\fP=\fIname\fP +This option supplies a name to be used for the standard input when file names +are being output. If not supplied, "(standard input)" is used. There is no +short form for this option. +.TP +\fB--locale\fP=\fIlocale-name\fP +This option specifies a locale to be used for pattern matching. It overrides +the value in the \fBLC_ALL\fP or \fBLC_CTYPE\fP environment variables. If no +locale is specified, the PCRE library's default (usually the "C" locale) is +used. There is no short form for this option. +.TP +\fB-M\fP, \fB--multiline\fP +Allow patterns to match more than one line. When this option is given, patterns +may usefully contain literal newline characters and internal occurrences of ^ +and $ characters. The output for any one match may consist of more than one +line. When this option is set, the PCRE library is called in "multiline" mode. +There is a limit to the number of lines that can be matched, imposed by the way +that \fBpcregrep\fP buffers the input file as it scans it. However, +\fBpcregrep\fP ensures that at least 8K characters or the rest of the document +(whichever is the shorter) are available for forward matching, and similarly +the previous 8K characters (or all the previous characters, if fewer than 8K) +are guaranteed to be available for lookbehind assertions. +.TP +\fB-N\fP \fInewline-type\fP, \fB--newline=\fP\fInewline-type\fP +The PCRE library supports three different character sequences for indicating +the ends of lines. They are the single-character sequences CR (carriage return) +and LF (linefeed), and the two-character sequence CR, LF. When the library is +built, a default line-ending sequence is specified. This is normally the +standard sequence for the operating system. Unless otherwise specified by this +option, \fBpcregrep\fP uses the default. The possible values for this option +are CR, LF, or CRLF. This makes it possible to use \fBpcregrep\fP on files that +have come from other environments without having to modify their line endings. +If the data that is being scanned does not agree with the convention set by +this option, \fBpcregrep\fP may behave in strange ways. +.TP +\fB-n\fP, \fB--line-number\fP +Precede each output line by its line number in the file, followed by a colon +and a space for matching lines or a hyphen and a space for context lines. If +the filename is also being output, it precedes the line number. +.TP +\fB-o\fP, \fB--only-matching\fP +Show only the part of the line that matched a pattern. In this mode, no +context is shown. That is, the \fB-A\fP, \fB-B\fP, and \fB-C\fP options are +ignored. +.TP +\fB-q\fP, \fB--quiet\fP +Work quietly, that is, display nothing except error messages. The exit +status indicates whether or not any matches were found. +.TP +\fB-r\fP, \fB--recursive\fP +If any given path is a directory, recursively scan the files it contains, +taking note of any \fB--include\fP and \fB--exclude\fP settings. By default, a +directory is read as a normal file; in some operating systems this gives an +immediate end-of-file. This option is a shorthand for setting the \fB-d\fP +option to "recurse". +.TP +\fB-s\fP, \fB--no-messages\fP +Suppress error messages about non-existent or unreadable files. Such files are +quietly skipped. However, the return code is still 2, even if matches were +found in other files. +.TP +\fB-u\fP, \fB--utf-8\fP +Operate in UTF-8 mode. This option is available only if PCRE has been compiled +with UTF-8 support. Both patterns and subject lines must be valid strings of +UTF-8 characters. +.TP +\fB-V\fP, \fB--version\fP +Write the version numbers of \fBpcregrep\fP and the PCRE library that is being +used to the standard error stream. +.TP +\fB-v\fP, \fB--invert-match\fP +Invert the sense of the match, so that lines which do \fInot\fP match any of +the patterns are the ones that are found. +.TP +\fB-w\fP, \fB--word-regex\fP, \fB--word-regexp\fP +Force the patterns to match only whole words. This is equivalent to having \eb +at the start and end of the pattern. +.TP +\fB-x\fP, \fB--line-regex\fP, \fP--line-regexp\fP +Force the patterns to be anchored (each must start matching at the beginning of +a line) and in addition, require them to match entire lines. This is +equivalent to having ^ and $ characters at the start and end of each +alternative branch in every pattern. +. +. +.SH "ENVIRONMENT VARIABLES" +.rs +.sp +The environment variables \fBLC_ALL\fP and \fBLC_CTYPE\fP are examined, in that +order, for a locale. The first one that is set is used. This can be overridden +by the \fB--locale\fP option. If no locale is set, the PCRE library's default +(usually the "C" locale) is used. +. +. +.SH "NEWLINES" +.rs +.sp +The \fB-N\fP (\fB--newline\fP) option allows \fBpcregrep\fP to scan files with +different newline conventions from the default. However, the setting of this +option does not affect the way in which \fBpcregrep\fP writes information to +the standard error and output streams. It uses the string "\en" in C +\fBprintf()\fP calls to indicate newlines, relying on the C I/O library to +convert this to an appropriate sequence if the output is sent to a file. +. +. +.SH "OPTIONS COMPATIBILITY" +.rs +.sp +The majority of short and long forms of \fBpcregrep\fP's options are the same +as in the GNU \fBgrep\fP program. Any long option of the form +\fB--xxx-regexp\fP (GNU terminology) is also available as \fB--xxx-regex\fP +(PCRE terminology). However, the \fB--locale\fP, \fB-M\fP, \fB--multiline\fP, +\fB-u\fP, and \fB--utf-8\fP options are specific to \fBpcregrep\fP. +. +. +.SH "OPTIONS WITH DATA" +.rs +.sp +There are four different ways in which an option with data can be specified. +If a short form option is used, the data may follow immediately, or in the next +command line item. For example: +.sp + -f/some/file + -f /some/file +.sp +If a long form option is used, the data may appear in the same command line +item, separated by an equals character, or (with one exception) it may appear +in the next command line item. For example: +.sp + --file=/some/file + --file /some/file +.sp +Note, however, that if you want to supply a file name beginning with ~ as data +in a shell command, and have the shell expand ~ to a home directory, you must +separate the file name from the option, because the shell does not treat ~ +specially unless it is at the start of an item. +.P +The exception to the above is the \fB--colour\fP (or \fB--color\fP) option, +for which the data is optional. If this option does have data, it must be given +in the first form, using an equals character. Otherwise it will be assumed that +it has no data. +. +. +.SH MATCHING ERRORS +.rs +.sp +It is possible to supply a regular expression that takes a very long time to +fail to match certain lines. Such patterns normally involve nested indefinite +repeats, for example: (a+)*\ed when matched against a line of a's with no final +digit. The PCRE matching function has a resource limit that causes it to abort +in these circumstances. If this happens, \fBpcregrep\fP outputs an error +message and the line that caused the problem to the standard error stream. If +there are more than 20 such errors, \fBpcregrep\fP gives up. +. +. +.SH DIAGNOSTICS +.rs +.sp +Exit status is 0 if any matches were found, 1 if no matches were found, and 2 +for syntax errors and non-existent or inacessible files (even if matches were +found in other files) or too many matching errors. Using the \fB-s\fP option to +suppress error messages about inaccessble files does not affect the return +code. +. +. +.SH AUTHOR +.rs +.sp +Philip Hazel +.br +University Computing Service +.br +Cambridge CB2 3QG, England. +.P +.in 0 +Last updated: 06 June 2006 +.br +Copyright (c) 1997-2006 University of Cambridge. diff --git a/libs/pcre/doc/pcregrep.txt b/libs/pcre/doc/pcregrep.txt new file mode 100644 index 0000000000..69b0e2b84e --- /dev/null +++ b/libs/pcre/doc/pcregrep.txt @@ -0,0 +1,399 @@ +PCREGREP(1) PCREGREP(1) + + +NAME + pcregrep - a grep with Perl-compatible regular expressions. + + +SYNOPSIS + pcregrep [options] [long options] [pattern] [path1 path2 ...] + + +DESCRIPTION + + pcregrep searches files for character patterns, in the same way as + other grep commands do, but it uses the PCRE regular expression library + to support patterns that are compatible with the regular expressions of + Perl 5. See pcrepattern for a full description of syntax and semantics + of the regular expressions that PCRE supports. + + Patterns, whether supplied on the command line or in a separate file, + are given without delimiters. For example: + + pcregrep Thursday /etc/motd + + If you attempt to use delimiters (for example, by surrounding a pattern + with slashes, as is common in Perl scripts), they are interpreted as + part of the pattern. Quotes can of course be used on the command line + because they are interpreted by the shell, and indeed they are required + if a pattern contains white space or shell metacharacters. + + The first argument that follows any option settings is treated as the + single pattern to be matched when neither -e nor -f is present. Con- + versely, when one or both of these options are used to specify pat- + terns, all arguments are treated as path names. At least one of -e, -f, + or an argument pattern must be provided. + + If no files are specified, pcregrep reads the standard input. The stan- + dard input can also be referenced by a name consisting of a single + hyphen. For example: + + pcregrep some-pattern /file1 - /file3 + + By default, each line that matches the pattern is copied to the stan- + dard output, and if there is more than one file, the file name is out- + put at the start of each line. However, there are options that can + change how pcregrep behaves. In particular, the -M option makes it pos- + sible to search for patterns that span line boundaries. What defines a + line boundary is controlled by the -N (--newline) option. + + Patterns are limited to 8K or BUFSIZ characters, whichever is the + greater. BUFSIZ is defined in . + + If the LC_ALL or LC_CTYPE environment variable is set, pcregrep uses + the value to set a locale when calling the PCRE library. The --locale + option can be used to override this. + + +OPTIONS + + -- This terminate the list of options. It is useful if the next + item on the command line starts with a hyphen but is not an + option. This allows for the processing of patterns and file- + names that start with hyphens. + + -A number, --after-context=number + Output number lines of context after each matching line. If + filenames and/or line numbers are being output, a hyphen sep- + arator is used instead of a colon for the context lines. A + line containing "--" is output between each group of lines, + unless they are in fact contiguous in the input file. The + value of number is expected to be relatively small. However, + pcregrep guarantees to have up to 8K of following text avail- + able for context output. + + -B number, --before-context=number + Output number lines of context before each matching line. If + filenames and/or line numbers are being output, a hyphen sep- + arator is used instead of a colon for the context lines. A + line containing "--" is output between each group of lines, + unless they are in fact contiguous in the input file. The + value of number is expected to be relatively small. However, + pcregrep guarantees to have up to 8K of preceding text avail- + able for context output. + + -C number, --context=number + Output number lines of context both before and after each + matching line. This is equivalent to setting both -A and -B + to the same value. + + -c, --count + Do not output individual lines; instead just output a count + of the number of lines that would otherwise have been output. + If several files are given, a count is output for each of + them. In this mode, the -A, -B, and -C options are ignored. + + --colour, --color + If this option is given without any data, it is equivalent to + "--colour=auto". If data is required, it must be given in + the same shell item, separated by an equals sign. + + --colour=value, --color=value + This option specifies under what circumstances the part of a + line that matched a pattern should be coloured in the output. + The value may be "never" (the default), "always", or "auto". + In the latter case, colouring happens only if the standard + output is connected to a terminal. The colour can be speci- + fied by setting the environment variable PCREGREP_COLOUR or + PCREGREP_COLOR. The value of this variable should be a string + of two numbers, separated by a semicolon. They are copied + directly into the control string for setting colour on a ter- + minal, so it is your responsibility to ensure that they make + sense. If neither of the environment variables is set, the + default is "1;31", which gives red. + + -D action, --devices=action + If an input path is not a regular file or a directory, + "action" specifies how it is to be processed. Valid values + are "read" (the default) or "skip" (silently skip the path). + + -d action, --directories=action + If an input path is a directory, "action" specifies how it is + to be processed. Valid values are "read" (the default), + "recurse" (equivalent to the -r option), or "skip" (silently + skip the path). In the default case, directories are read as + if they were ordinary files. In some operating systems the + effect of reading a directory like this is an immediate end- + of-file. + + -e pattern, --regex=pattern, + --regexp=pattern Specify a pattern to be matched. This option + can be used multiple times in order to specify several pat- + terns. It can also be used as a way of specifying a single + pattern that starts with a hyphen. When -e is used, no argu- + ment pattern is taken from the command line; all arguments + are treated as file names. There is an overall maximum of 100 + patterns. They are applied to each line in the order in which + they are defined until one matches (or fails to match if -v + is used). If -f is used with -e, the command line patterns + are matched first, followed by the patterns from the file, + independent of the order in which these options are speci- + fied. Note that multiple use of -e is not the same as a sin- + gle pattern with alternatives. For example, X|Y finds the + first character in a line that is X or Y, whereas if the two + patterns are given separately, pcregrep finds X if it is + present, even if it follows Y in the line. It finds Y only if + there is no X in the line. This really matters only if you + are using -o to show the portion of the line that matched. + + --exclude=pattern + When pcregrep is searching the files in a directory as a con- + sequence of the -r (recursive search) option, any files whose + names match the pattern are excluded. The pattern is a PCRE + regular expression. If a file name matches both --include and + --exclude, it is excluded. There is no short form for this + option. + + -F, --fixed-strings + Interpret each pattern as a list of fixed strings, separated + by newlines, instead of as a regular expression. The -w + (match as a word) and -x (match whole line) options can be + used with -F. They apply to each of the fixed strings. A line + is selected if any of the fixed strings are found in it (sub- + ject to -w or -x, if present). + + -f filename, --file=filename + Read a number of patterns from the file, one per line, and + match them against each line of input. A data line is output + if any of the patterns match it. The filename can be given as + "-" to refer to the standard input. When -f is used, patterns + specified on the command line using -e may also be present; + they are tested before the file's patterns. However, no other + pattern is taken from the command line; all arguments are + treated as file names. There is an overall maximum of 100 + patterns. Trailing white space is removed from each line, and + blank lines are ignored. An empty file contains no patterns + and therefore matches nothing. + + -H, --with-filename + Force the inclusion of the filename at the start of output + lines when searching a single file. By default, the filename + is not shown in this case. For matching lines, the filename + is followed by a colon and a space; for context lines, a + hyphen separator is used. If a line number is also being out- + put, it follows the file name without a space. + + -h, --no-filename + Suppress the output filenames when searching multiple files. + By default, filenames are shown when multiple files are + searched. For matching lines, the filename is followed by a + colon and a space; for context lines, a hyphen separator is + used. If a line number is also being output, it follows the + file name without a space. + + --help Output a brief help message and exit. + + -i, --ignore-case + Ignore upper/lower case distinctions during comparisons. + + --include=pattern + When pcregrep is searching the files in a directory as a con- + sequence of the -r (recursive search) option, only those + files whose names match the pattern are included. The pattern + is a PCRE regular expression. If a file name matches both + --include and --exclude, it is excluded. There is no short + form for this option. + + -L, --files-without-match + Instead of outputting lines from the files, just output the + names of the files that do not contain any lines that would + have been output. Each file name is output once, on a sepa- + rate line. + + -l, --files-with-matches + Instead of outputting lines from the files, just output the + names of the files containing lines that would have been out- + put. Each file name is output once, on a separate line. + Searching stops as soon as a matching line is found in a + file. + + --label=name + This option supplies a name to be used for the standard input + when file names are being output. If not supplied, "(standard + input)" is used. There is no short form for this option. + + --locale=locale-name + This option specifies a locale to be used for pattern match- + ing. It overrides the value in the LC_ALL or LC_CTYPE envi- + ronment variables. If no locale is specified, the PCRE + library's default (usually the "C" locale) is used. There is + no short form for this option. + + -M, --multiline + Allow patterns to match more than one line. When this option + is given, patterns may usefully contain literal newline char- + acters and internal occurrences of ^ and $ characters. The + output for any one match may consist of more than one line. + When this option is set, the PCRE library is called in "mul- + tiline" mode. There is a limit to the number of lines that + can be matched, imposed by the way that pcregrep buffers the + input file as it scans it. However, pcregrep ensures that at + least 8K characters or the rest of the document (whichever is + the shorter) are available for forward matching, and simi- + larly the previous 8K characters (or all the previous charac- + ters, if fewer than 8K) are guaranteed to be available for + lookbehind assertions. + + -N newline-type, --newline=newline-type + The PCRE library supports three different character sequences + for indicating the ends of lines. They are the single-charac- + ter sequences CR (carriage return) and LF (linefeed), and the + two-character sequence CR, LF. When the library is built, a + default line-ending sequence is specified. This is normally + the standard sequence for the operating system. Unless other- + wise specified by this option, pcregrep uses the default. The + possible values for this option are CR, LF, or CRLF. This + makes it possible to use pcregrep on files that have come + from other environments without having to modify their line + endings. If the data that is being scanned does not agree + with the convention set by this option, pcregrep may behave + in strange ways. + + -n, --line-number + Precede each output line by its line number in the file, fol- + lowed by a colon and a space for matching lines or a hyphen + and a space for context lines. If the filename is also being + output, it precedes the line number. + + -o, --only-matching + Show only the part of the line that matched a pattern. In + this mode, no context is shown. That is, the -A, -B, and -C + options are ignored. + + -q, --quiet + Work quietly, that is, display nothing except error messages. + The exit status indicates whether or not any matches were + found. + + -r, --recursive + If any given path is a directory, recursively scan the files + it contains, taking note of any --include and --exclude set- + tings. By default, a directory is read as a normal file; in + some operating systems this gives an immediate end-of-file. + This option is a shorthand for setting the -d option to + "recurse". + + -s, --no-messages + Suppress error messages about non-existent or unreadable + files. Such files are quietly skipped. However, the return + code is still 2, even if matches were found in other files. + + -u, --utf-8 + Operate in UTF-8 mode. This option is available only if PCRE + has been compiled with UTF-8 support. Both patterns and sub- + ject lines must be valid strings of UTF-8 characters. + + -V, --version + Write the version numbers of pcregrep and the PCRE library + that is being used to the standard error stream. + + -v, --invert-match + Invert the sense of the match, so that lines which do not + match any of the patterns are the ones that are found. + + -w, --word-regex, --word-regexp + Force the patterns to match only whole words. This is equiva- + lent to having \b at the start and end of the pattern. + + -x, --line-regex, --line-regexp + Force the patterns to be anchored (each must start matching + at the beginning of a line) and in addition, require them to + match entire lines. This is equivalent to having ^ and $ + characters at the start and end of each alternative branch in + every pattern. + + +ENVIRONMENT VARIABLES + + The environment variables LC_ALL and LC_CTYPE are examined, in that + order, for a locale. The first one that is set is used. This can be + overridden by the --locale option. If no locale is set, the PCRE + library's default (usually the "C" locale) is used. + + +NEWLINES + + The -N (--newline) option allows pcregrep to scan files with different + newline conventions from the default. However, the setting of this + option does not affect the way in which pcregrep writes information to + the standard error and output streams. It uses the string "\n" in C + printf() calls to indicate newlines, relying on the C I/O library to + convert this to an appropriate sequence if the output is sent to a + file. + + +OPTIONS COMPATIBILITY + + The majority of short and long forms of pcregrep's options are the same + as in the GNU grep program. Any long option of the form --xxx-regexp + (GNU terminology) is also available as --xxx-regex (PCRE terminology). + However, the --locale, -M, --multiline, -u, and --utf-8 options are + specific to pcregrep. + + +OPTIONS WITH DATA + + There are four different ways in which an option with data can be spec- + ified. If a short form option is used, the data may follow immedi- + ately, or in the next command line item. For example: + + -f/some/file + -f /some/file + + If a long form option is used, the data may appear in the same command + line item, separated by an equals character, or (with one exception) it + may appear in the next command line item. For example: + + --file=/some/file + --file /some/file + + Note, however, that if you want to supply a file name beginning with ~ + as data in a shell command, and have the shell expand ~ to a home + directory, you must separate the file name from the option, because the + shell does not treat ~ specially unless it is at the start of an item. + + The exception to the above is the --colour (or --color) option, for + which the data is optional. If this option does have data, it must be + given in the first form, using an equals character. Otherwise it will + be assumed that it has no data. + + +MATCHING ERRORS + + It is possible to supply a regular expression that takes a very long + time to fail to match certain lines. Such patterns normally involve + nested indefinite repeats, for example: (a+)*\d when matched against a + line of a's with no final digit. The PCRE matching function has a + resource limit that causes it to abort in these circumstances. If this + happens, pcregrep outputs an error message and the line that caused the + problem to the standard error stream. If there are more than 20 such + errors, pcregrep gives up. + + +DIAGNOSTICS + + Exit status is 0 if any matches were found, 1 if no matches were found, + and 2 for syntax errors and non-existent or inacessible files (even if + matches were found in other files) or too many matching errors. Using + the -s option to suppress error messages about inaccessble files does + not affect the return code. + + +AUTHOR + + Philip Hazel + University Computing Service + Cambridge CB2 3QG, England. + +Last updated: 06 June 2006 +Copyright (c) 1997-2006 University of Cambridge. diff --git a/libs/pcre/doc/pcrematching.3 b/libs/pcre/doc/pcrematching.3 new file mode 100644 index 0000000000..ff582c4177 --- /dev/null +++ b/libs/pcre/doc/pcrematching.3 @@ -0,0 +1,157 @@ +.TH PCREMATCHING 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "PCRE MATCHING ALGORITHMS" +.rs +.sp +This document describes the two different algorithms that are available in PCRE +for matching a compiled regular expression against a given subject string. The +"standard" algorithm is the one provided by the \fBpcre_exec()\fP function. +This works in the same was as Perl's matching function, and provides a +Perl-compatible matching operation. +.P +An alternative algorithm is provided by the \fBpcre_dfa_exec()\fP function; +this operates in a different way, and is not Perl-compatible. It has advantages +and disadvantages compared with the standard algorithm, and these are described +below. +.P +When there is only one possible way in which a given subject string can match a +pattern, the two algorithms give the same answer. A difference arises, however, +when there are multiple possibilities. For example, if the pattern +.sp + ^<.*> +.sp +is matched against the string +.sp + +.sp +there are three possible answers. The standard algorithm finds only one of +them, whereas the DFA algorithm finds all three. +. +.SH "REGULAR EXPRESSIONS AS TREES" +.rs +.sp +The set of strings that are matched by a regular expression can be represented +as a tree structure. An unlimited repetition in the pattern makes the tree of +infinite size, but it is still a tree. Matching the pattern to a given subject +string (from a given starting point) can be thought of as a search of the tree. +There are two ways to search a tree: depth-first and breadth-first, and these +correspond to the two matching algorithms provided by PCRE. +. +.SH "THE STANDARD MATCHING ALGORITHM" +.rs +.sp +In the terminology of Jeffrey Friedl's book \fIMastering Regular +Expressions\fP, the standard algorithm is an "NFA algorithm". It conducts a +depth-first search of the pattern tree. That is, it proceeds along a single +path through the tree, checking that the subject matches what is required. When +there is a mismatch, the algorithm tries any alternatives at the current point, +and if they all fail, it backs up to the previous branch point in the tree, and +tries the next alternative branch at that level. This often involves backing up +(moving to the left) in the subject string as well. The order in which +repetition branches are tried is controlled by the greedy or ungreedy nature of +the quantifier. +.P +If a leaf node is reached, a matching string has been found, and at that point +the algorithm stops. Thus, if there is more than one possible match, this +algorithm returns the first one that it finds. Whether this is the shortest, +the longest, or some intermediate length depends on the way the greedy and +ungreedy repetition quantifiers are specified in the pattern. +.P +Because it ends up with a single path through the tree, it is relatively +straightforward for this algorithm to keep track of the substrings that are +matched by portions of the pattern in parentheses. This provides support for +capturing parentheses and back references. +. +.SH "THE DFA MATCHING ALGORITHM" +.rs +.sp +DFA stands for "deterministic finite automaton", but you do not need to +understand the origins of that name. This algorithm conducts a breadth-first +search of the tree. Starting from the first matching point in the subject, it +scans the subject string from left to right, once, character by character, and +as it does this, it remembers all the paths through the tree that represent +valid matches. +.P +The scan continues until either the end of the subject is reached, or there are +no more unterminated paths. At this point, terminated paths represent the +different matching possibilities (if there are none, the match has failed). +Thus, if there is more than one possible match, this algorithm finds all of +them, and in particular, it finds the longest. In PCRE, there is an option to +stop the algorithm after the first match (which is necessarily the shortest) +has been found. +.P +Note that all the matches that are found start at the same point in the +subject. If the pattern +.sp + cat(er(pillar)?) +.sp +is matched against the string "the caterpillar catchment", the result will be +the three strings "cat", "cater", and "caterpillar" that start at the fourth +character of the subject. The algorithm does not automatically move on to find +matches that start at later positions. +.P +There are a number of features of PCRE regular expressions that are not +supported by the DFA matching algorithm. They are as follows: +.P +1. Because the algorithm finds all possible matches, the greedy or ungreedy +nature of repetition quantifiers is not relevant. Greedy and ungreedy +quantifiers are treated in exactly the same way. +.P +2. When dealing with multiple paths through the tree simultaneously, it is not +straightforward to keep track of captured substrings for the different matching +possibilities, and PCRE's implementation of this algorithm does not attempt to +do this. This means that no captured substrings are available. +.P +3. Because no substrings are captured, back references within the pattern are +not supported, and cause errors if encountered. +.P +4. For the same reason, conditional expressions that use a backreference as the +condition are not supported. +.P +5. Callouts are supported, but the value of the \fIcapture_top\fP field is +always 1, and the value of the \fIcapture_last\fP field is always -1. +.P +6. +The \eC escape sequence, which (in the standard algorithm) matches a single +byte, even in UTF-8 mode, is not supported because the DFA algorithm moves +through the subject string one character at a time, for all active paths +through the tree. +. +.SH "ADVANTAGES OF THE DFA ALGORITHM" +.rs +.sp +Using the DFA matching algorithm provides the following advantages: +.P +1. All possible matches (at a single point in the subject) are automatically +found, and in particular, the longest match is found. To find more than one +match using the standard algorithm, you have to do kludgy things with +callouts. +.P +2. There is much better support for partial matching. The restrictions on the +content of the pattern that apply when using the standard algorithm for partial +matching do not apply to the DFA algorithm. For non-anchored patterns, the +starting position of a partial match is available. +.P +3. Because the DFA algorithm scans the subject string just once, and never +needs to backtrack, it is possible to pass very long subject strings to the +matching function in several pieces, checking for partial matching each time. +. +.SH "DISADVANTAGES OF THE DFA ALGORITHM" +.rs +.sp +The DFA algorithm suffers from a number of disadvantages: +.P +1. It is substantially slower than the standard algorithm. This is partly +because it has to search for all possible matches, but is also because it is +less susceptible to optimization. +.P +2. Capturing parentheses and back references are not supported. +.P +3. The "atomic group" feature of PCRE regular expressions is supported, but +does not provide the advantage that it does for the standard algorithm. +.P +.in 0 +Last updated: 06 June 2006 +.br +Copyright (c) 1997-2006 University of Cambridge. diff --git a/libs/pcre/doc/pcrepartial.3 b/libs/pcre/doc/pcrepartial.3 new file mode 100644 index 0000000000..c4e0acae4d --- /dev/null +++ b/libs/pcre/doc/pcrepartial.3 @@ -0,0 +1,203 @@ +.TH PCREPARTIAL 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "PARTIAL MATCHING IN PCRE" +.rs +.sp +In normal use of PCRE, if the subject string that is passed to +\fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP matches as far as it goes, but is +too short to match the entire pattern, PCRE_ERROR_NOMATCH is returned. There +are circumstances where it might be helpful to distinguish this case from other +cases in which there is no match. +.P +Consider, for example, an application where a human is required to type in data +for a field with specific formatting requirements. An example might be a date +in the form \fIddmmmyy\fP, defined by this pattern: +.sp + ^\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed$ +.sp +If the application sees the user's keystrokes one by one, and can check that +what has been typed so far is potentially valid, it is able to raise an error +as soon as a mistake is made, possibly beeping and not reflecting the +character that has been typed. This immediate feedback is likely to be a better +user interface than a check that is delayed until the entire string has been +entered. +.P +PCRE supports the concept of partial matching by means of the PCRE_PARTIAL +option, which can be set when calling \fBpcre_exec()\fP or +\fBpcre_dfa_exec()\fP. When this flag is set for \fBpcre_exec()\fP, the return +code PCRE_ERROR_NOMATCH is converted into PCRE_ERROR_PARTIAL if at any time +during the matching process the last part of the subject string matched part of +the pattern. Unfortunately, for non-anchored matching, it is not possible to +obtain the position of the start of the partial match. No captured data is set +when PCRE_ERROR_PARTIAL is returned. +.P +When PCRE_PARTIAL is set for \fBpcre_dfa_exec()\fP, the return code +PCRE_ERROR_NOMATCH is converted into PCRE_ERROR_PARTIAL if the end of the +subject is reached, there have been no complete matches, but there is still at +least one matching possibility. The portion of the string that provided the +partial match is set as the first matching string. +.P +Using PCRE_PARTIAL disables one of PCRE's optimizations. PCRE remembers the +last literal byte in a pattern, and abandons matching immediately if such a +byte is not present in the subject string. This optimization cannot be used +for a subject string that might match only partially. +. +. +.SH "RESTRICTED PATTERNS FOR PCRE_PARTIAL" +.rs +.sp +Because of the way certain internal optimizations are implemented in the +\fBpcre_exec()\fP function, the PCRE_PARTIAL option cannot be used with all +patterns. These restrictions do not apply when \fBpcre_dfa_exec()\fP is used. +For \fBpcre_exec()\fP, repeated single characters such as +.sp + a{2,4} +.sp +and repeated single metasequences such as +.sp + \ed+ +.sp +are not permitted if the maximum number of occurrences is greater than one. +Optional items such as \ed? (where the maximum is one) are permitted. +Quantifiers with any values are permitted after parentheses, so the invalid +examples above can be coded thus: +.sp + (a){2,4} + (\ed)+ +.sp +These constructions run more slowly, but for the kinds of application that are +envisaged for this facility, this is not felt to be a major restriction. +.P +If PCRE_PARTIAL is set for a pattern that does not conform to the restrictions, +\fBpcre_exec()\fP returns the error code PCRE_ERROR_BADPARTIAL (-13). +. +. +.SH "EXAMPLE OF PARTIAL MATCHING USING PCRETEST" +.rs +.sp +If the escape sequence \eP is present in a \fBpcretest\fP data line, the +PCRE_PARTIAL flag is used for the match. Here is a run of \fBpcretest\fP that +uses the date example quoted above: +.sp + re> /^\ed?\ed(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\ed\ed$/ + data> 25jun04\eP + 0: 25jun04 + 1: jun + data> 25dec3\eP + Partial match + data> 3ju\eP + Partial match + data> 3juj\eP + No match + data> j\eP + No match +.sp +The first data string is matched completely, so \fBpcretest\fP shows the +matched substrings. The remaining four strings do not match the complete +pattern, but the first two are partial matches. The same test, using DFA +matching (by means of the \eD escape sequence), produces the following output: +.sp + re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ + data> 25jun04\eP\eD + 0: 25jun04 + data> 23dec3\eP\eD + Partial match: 23dec3 + data> 3ju\eP\eD + Partial match: 3ju + data> 3juj\eP\eD + No match + data> j\eP\eD + No match +.sp +Notice that in this case the portion of the string that was matched is made +available. +. +. +.SH "MULTI-SEGMENT MATCHING WITH pcre_dfa_exec()" +.rs +.sp +When a partial match has been found using \fBpcre_dfa_exec()\fP, it is possible +to continue the match by providing additional subject data and calling +\fBpcre_dfa_exec()\fP again with the PCRE_DFA_RESTART option and the same +working space (where details of the previous partial match are stored). Here is +an example using \fBpcretest\fP, where the \eR escape sequence sets the +PCRE_DFA_RESTART option and the \eD escape sequence requests the use of +\fBpcre_dfa_exec()\fP: +.sp + re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ + data> 23ja\eP\eD + Partial match: 23ja + data> n05\eR\eD + 0: n05 +.sp +The first call has "23ja" as the subject, and requests partial matching; the +second call has "n05" as the subject for the continued (restarted) match. +Notice that when the match is complete, only the last part is shown; PCRE does +not retain the previously partially-matched string. It is up to the calling +program to do that if it needs to. +.P +This facility can be used to pass very long subject strings to +\fBpcre_dfa_exec()\fP. However, some care is needed for certain types of +pattern. +.P +1. If the pattern contains tests for the beginning or end of a line, you need +to pass the PCRE_NOTBOL or PCRE_NOTEOL options, as appropriate, when the +subject string for any call does not contain the beginning or end of a line. +.P +2. If the pattern contains backward assertions (including \eb or \eB), you need +to arrange for some overlap in the subject strings to allow for this. For +example, you could pass the subject in chunks that were 500 bytes long, but in +a buffer of 700 bytes, with the starting offset set to 200 and the previous 200 +bytes at the start of the buffer. +.P +3. Matching a subject string that is split into multiple segments does not +always produce exactly the same result as matching over one single long string. +The difference arises when there are multiple matching possibilities, because a +partial match result is given only when there are no completed matches in a +call to fBpcre_dfa_exec()\fP. This means that as soon as the shortest match has +been found, continuation to a new subject segment is no longer possible. +Consider this \fBpcretest\fP example: +.sp + re> /dog(sbody)?/ + data> do\eP\eD + Partial match: do + data> gsb\eR\eP\eD + 0: g + data> dogsbody\eD + 0: dogsbody + 1: dog +.sp +The pattern matches the words "dog" or "dogsbody". When the subject is +presented in several parts ("do" and "gsb" being the first two) the match stops +when "dog" has been found, and it is not possible to continue. On the other +hand, if "dogsbody" is presented as a single string, both matches are found. +.P +Because of this phenomenon, it does not usually make sense to end a pattern +that is going to be matched in this way with a variable repeat. +.P +4. Patterns that contain alternatives at the top level which do not all +start with the same pattern item may not work as expected. For example, +consider this pattern: +.sp + 1234|3789 +.sp +If the first part of the subject is "ABC123", a partial match of the first +alternative is found at offset 3. There is no partial match for the second +alternative, because such a match does not start at the same point in the +subject string. Attempting to continue with the string "789" does not yield a +match because only those alternatives that match at one point in the subject +are remembered. The problem arises because the start of the second alternative +matches within the first alternative. There is no problem with anchored +patterns or patterns such as: +.sp + 1234|ABCD +.sp +where no string can be a partial match for both alternatives. +. +. +.P +.in 0 +Last updated: 16 January 2006 +.br +Copyright (c) 1997-2006 University of Cambridge. diff --git a/libs/pcre/doc/pcrepattern.3 b/libs/pcre/doc/pcrepattern.3 new file mode 100644 index 0000000000..84c4b4d61e --- /dev/null +++ b/libs/pcre/doc/pcrepattern.3 @@ -0,0 +1,1645 @@ +.TH PCREPATTERN 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "PCRE REGULAR EXPRESSION DETAILS" +.rs +.sp +The syntax and semantics of the regular expressions supported by PCRE are +described below. Regular expressions are also described in the Perl +documentation and in a number of books, some of which have copious examples. +Jeffrey Friedl's "Mastering Regular Expressions", published by O'Reilly, covers +regular expressions in great detail. This description of PCRE's regular +expressions is intended as reference material. +.P +The original operation of PCRE was on strings of one-byte characters. However, +there is now also support for UTF-8 character strings. To use this, you must +build PCRE to include UTF-8 support, and then call \fBpcre_compile()\fP with +the PCRE_UTF8 option. How this affects pattern matching is mentioned in several +places below. There is also a summary of UTF-8 features in the +.\" HTML +.\" +section on UTF-8 support +.\" +in the main +.\" HREF +\fBpcre\fP +.\" +page. +.P +The remainder of this document discusses the patterns that are supported by +PCRE when its main matching function, \fBpcre_exec()\fP, is used. +From release 6.0, PCRE offers a second matching function, +\fBpcre_dfa_exec()\fP, which matches using a different algorithm that is not +Perl-compatible. The advantages and disadvantages of the alternative function, +and how it differs from the normal function, are discussed in the +.\" HREF +\fBpcrematching\fP +.\" +page. +.P +A regular expression is a pattern that is matched against a subject string from +left to right. Most characters stand for themselves in a pattern, and match the +corresponding characters in the subject. As a trivial example, the pattern +.sp + The quick brown fox +.sp +matches a portion of a subject string that is identical to itself. When +caseless matching is specified (the PCRE_CASELESS option), letters are matched +independently of case. In UTF-8 mode, PCRE always understands the concept of +case for characters whose values are less than 128, so caseless matching is +always possible. For characters with higher values, the concept of case is +supported if PCRE is compiled with Unicode property support, but not otherwise. +If you want to use caseless matching for characters 128 and above, you must +ensure that PCRE is compiled with Unicode property support as well as with +UTF-8 support. +.P +The power of regular expressions comes from the ability to include alternatives +and repetitions in the pattern. These are encoded in the pattern by the use of +\fImetacharacters\fP, which do not stand for themselves but instead are +interpreted in some special way. +.P +There are two different sets of metacharacters: those that are recognized +anywhere in the pattern except within square brackets, and those that are +recognized in square brackets. Outside square brackets, the metacharacters are +as follows: +.sp + \e general escape character with several uses + ^ assert start of string (or line, in multiline mode) + $ assert end of string (or line, in multiline mode) + . match any character except newline (by default) + [ start character class definition + | start of alternative branch + ( start subpattern + ) end subpattern + ? extends the meaning of ( + also 0 or 1 quantifier + also quantifier minimizer + * 0 or more quantifier + + 1 or more quantifier + also "possessive quantifier" + { start min/max quantifier +.sp +Part of a pattern that is in square brackets is called a "character class". In +a character class the only metacharacters are: +.sp + \e general escape character + ^ negate the class, but only if the first character + - indicates character range +.\" JOIN + [ POSIX character class (only if followed by POSIX + syntax) + ] terminates the character class +.sp +The following sections describe the use of each of the metacharacters. +. +.SH BACKSLASH +.rs +.sp +The backslash character has several uses. Firstly, if it is followed by a +non-alphanumeric character, it takes away any special meaning that character +may have. This use of backslash as an escape character applies both inside and +outside character classes. +.P +For example, if you want to match a * character, you write \e* in the pattern. +This escaping action applies whether or not the following character would +otherwise be interpreted as a metacharacter, so it is always safe to precede a +non-alphanumeric with backslash to specify that it stands for itself. In +particular, if you want to match a backslash, you write \e\e. +.P +If a pattern is compiled with the PCRE_EXTENDED option, whitespace in the +pattern (other than in a character class) and characters between a # outside +a character class and the next newline are ignored. An escaping backslash can +be used to include a whitespace or # character as part of the pattern. +.P +If you want to remove the special meaning from a sequence of characters, you +can do so by putting them between \eQ and \eE. This is different from Perl in +that $ and @ are handled as literals in \eQ...\eE sequences in PCRE, whereas in +Perl, $ and @ cause variable interpolation. Note the following examples: +.sp + Pattern PCRE matches Perl matches +.sp +.\" JOIN + \eQabc$xyz\eE abc$xyz abc followed by the + contents of $xyz + \eQabc\e$xyz\eE abc\e$xyz abc\e$xyz + \eQabc\eE\e$\eQxyz\eE abc$xyz abc$xyz +.sp +The \eQ...\eE sequence is recognized both inside and outside character classes. +. +. +.\" HTML +.SS "Non-printing characters" +.rs +.sp +A second use of backslash provides a way of encoding non-printing characters +in patterns in a visible manner. There is no restriction on the appearance of +non-printing characters, apart from the binary zero that terminates a pattern, +but when a pattern is being prepared by text editing, it is usually easier to +use one of the following escape sequences than the binary character it +represents: +.sp + \ea alarm, that is, the BEL character (hex 07) + \ecx "control-x", where x is any character + \ee escape (hex 1B) + \ef formfeed (hex 0C) + \en newline (hex 0A) + \er carriage return (hex 0D) + \et tab (hex 09) + \eddd character with octal code ddd, or backreference + \exhh character with hex code hh + \ex{hhh..} character with hex code hhh.. +.sp +The precise effect of \ecx is as follows: if x is a lower case letter, it +is converted to upper case. Then bit 6 of the character (hex 40) is inverted. +Thus \ecz becomes hex 1A, but \ec{ becomes hex 3B, while \ec; becomes hex +7B. +.P +After \ex, from zero to two hexadecimal digits are read (letters can be in +upper or lower case). Any number of hexadecimal digits may appear between \ex{ +and }, but the value of the character code must be less than 256 in non-UTF-8 +mode, and less than 2**31 in UTF-8 mode (that is, the maximum hexadecimal value +is 7FFFFFFF). If characters other than hexadecimal digits appear between \ex{ +and }, or if there is no terminating }, this form of escape is not recognized. +Instead, the initial \ex will be interpreted as a basic hexadecimal escape, +with no following digits, giving a character whose value is zero. +.P +Characters whose value is less than 256 can be defined by either of the two +syntaxes for \ex. There is no difference in the way they are handled. For +example, \exdc is exactly the same as \ex{dc}. +.P +After \e0 up to two further octal digits are read. If there are fewer than two +digits, just those that are present are used. Thus the sequence \e0\ex\e07 +specifies two binary zeros followed by a BEL character (code value 7). Make +sure you supply two digits after the initial zero if the pattern character that +follows is itself an octal digit. +.P +The handling of a backslash followed by a digit other than 0 is complicated. +Outside a character class, PCRE reads it and any following digits as a decimal +number. If the number is less than 10, or if there have been at least that many +previous capturing left parentheses in the expression, the entire sequence is +taken as a \fIback reference\fP. A description of how this works is given +.\" HTML +.\" +later, +.\" +following the discussion of +.\" HTML +.\" +parenthesized subpatterns. +.\" +.P +Inside a character class, or if the decimal number is greater than 9 and there +have not been that many capturing subpatterns, PCRE re-reads up to three octal +digits following the backslash, ane uses them to generate a data character. Any +subsequent digits stand for themselves. In non-UTF-8 mode, the value of a +character specified in octal must be less than \e400. In UTF-8 mode, values up +to \e777 are permitted. For example: +.sp + \e040 is another way of writing a space +.\" JOIN + \e40 is the same, provided there are fewer than 40 + previous capturing subpatterns + \e7 is always a back reference +.\" JOIN + \e11 might be a back reference, or another way of + writing a tab + \e011 is always a tab + \e0113 is a tab followed by the character "3" +.\" JOIN + \e113 might be a back reference, otherwise the + character with octal code 113 +.\" JOIN + \e377 might be a back reference, otherwise + the byte consisting entirely of 1 bits +.\" JOIN + \e81 is either a back reference, or a binary zero + followed by the two characters "8" and "1" +.sp +Note that octal values of 100 or greater must not be introduced by a leading +zero, because no more than three octal digits are ever read. +.P +All the sequences that define a single character value can be used both inside +and outside character classes. In addition, inside a character class, the +sequence \eb is interpreted as the backspace character (hex 08), and the +sequence \eX is interpreted as the character "X". Outside a character class, +these sequences have different meanings +.\" HTML +.\" +(see below). +.\" +. +. +.SS "Generic character types" +.rs +.sp +The third use of backslash is for specifying generic character types. The +following are always recognized: +.sp + \ed any decimal digit + \eD any character that is not a decimal digit + \es any whitespace character + \eS any character that is not a whitespace character + \ew any "word" character + \eW any "non-word" character +.sp +Each pair of escape sequences partitions the complete set of characters into +two disjoint sets. Any given character matches one, and only one, of each pair. +.P +These character type sequences can appear both inside and outside character +classes. They each match one character of the appropriate type. If the current +matching point is at the end of the subject string, all of them fail, since +there is no character to match. +.P +For compatibility with Perl, \es does not match the VT character (code 11). +This makes it different from the the POSIX "space" class. The \es characters +are HT (9), LF (10), FF (12), CR (13), and space (32). (If "use locale;" is +included in a Perl script, \es may match the VT character. In PCRE, it never +does.) +.P +A "word" character is an underscore or any character less than 256 that is a +letter or digit. The definition of letters and digits is controlled by PCRE's +low-valued character tables, and may vary if locale-specific matching is taking +place (see +.\" HTML +.\" +"Locale support" +.\" +in the +.\" HREF +\fBpcreapi\fP +.\" +page). For example, in the "fr_FR" (French) locale, some character codes +greater than 128 are used for accented letters, and these are matched by \ew. +.P +In UTF-8 mode, characters with values greater than 128 never match \ed, \es, or +\ew, and always match \eD, \eS, and \eW. This is true even when Unicode +character property support is available. The use of locales with Unicode is +discouraged. +. +. +.\" HTML +.SS Unicode character properties +.rs +.sp +When PCRE is built with Unicode character property support, three additional +escape sequences to match character properties are available when UTF-8 mode +is selected. They are: +.sp + \ep{\fIxx\fP} a character with the \fIxx\fP property + \eP{\fIxx\fP} a character without the \fIxx\fP property + \eX an extended Unicode sequence +.sp +The property names represented by \fIxx\fP above are limited to the Unicode +script names, the general category properties, and "Any", which matches any +character (including newline). Other properties such as "InMusicalSymbols" are +not currently supported by PCRE. Note that \eP{Any} does not match any +characters, so always causes a match failure. +.P +Sets of Unicode characters are defined as belonging to certain scripts. A +character from one of these sets can be matched using a script name. For +example: +.sp + \ep{Greek} + \eP{Han} +.sp +Those that are not part of an identified script are lumped together as +"Common". The current list of scripts is: +.P +Arabic, +Armenian, +Bengali, +Bopomofo, +Braille, +Buginese, +Buhid, +Canadian_Aboriginal, +Cherokee, +Common, +Coptic, +Cypriot, +Cyrillic, +Deseret, +Devanagari, +Ethiopic, +Georgian, +Glagolitic, +Gothic, +Greek, +Gujarati, +Gurmukhi, +Han, +Hangul, +Hanunoo, +Hebrew, +Hiragana, +Inherited, +Kannada, +Katakana, +Kharoshthi, +Khmer, +Lao, +Latin, +Limbu, +Linear_B, +Malayalam, +Mongolian, +Myanmar, +New_Tai_Lue, +Ogham, +Old_Italic, +Old_Persian, +Oriya, +Osmanya, +Runic, +Shavian, +Sinhala, +Syloti_Nagri, +Syriac, +Tagalog, +Tagbanwa, +Tai_Le, +Tamil, +Telugu, +Thaana, +Thai, +Tibetan, +Tifinagh, +Ugaritic, +Yi. +.P +Each character has exactly one general category property, specified by a +two-letter abbreviation. For compatibility with Perl, negation can be specified +by including a circumflex between the opening brace and the property name. For +example, \ep{^Lu} is the same as \eP{Lu}. +.P +If only one letter is specified with \ep or \eP, it includes all the general +category properties that start with that letter. In this case, in the absence +of negation, the curly brackets in the escape sequence are optional; these two +examples have the same effect: +.sp + \ep{L} + \epL +.sp +The following general category property codes are supported: +.sp + C Other + Cc Control + Cf Format + Cn Unassigned + Co Private use + Cs Surrogate +.sp + L Letter + Ll Lower case letter + Lm Modifier letter + Lo Other letter + Lt Title case letter + Lu Upper case letter +.sp + M Mark + Mc Spacing mark + Me Enclosing mark + Mn Non-spacing mark +.sp + N Number + Nd Decimal number + Nl Letter number + No Other number +.sp + P Punctuation + Pc Connector punctuation + Pd Dash punctuation + Pe Close punctuation + Pf Final punctuation + Pi Initial punctuation + Po Other punctuation + Ps Open punctuation +.sp + S Symbol + Sc Currency symbol + Sk Modifier symbol + Sm Mathematical symbol + So Other symbol +.sp + Z Separator + Zl Line separator + Zp Paragraph separator + Zs Space separator +.sp +The special property L& is also supported: it matches a character that has +the Lu, Ll, or Lt property, in other words, a letter that is not classified as +a modifier or "other". +.P +The long synonyms for these properties that Perl supports (such as \ep{Letter}) +are not supported by PCRE, nor is it permitted to prefix any of these +properties with "Is". +.P +No character that is in the Unicode table has the Cn (unassigned) property. +Instead, this property is assumed for any code point that is not in the +Unicode table. +.P +Specifying caseless matching does not affect these escape sequences. For +example, \ep{Lu} always matches only upper case letters. +.P +The \eX escape matches any number of Unicode characters that form an extended +Unicode sequence. \eX is equivalent to +.sp + (?>\ePM\epM*) +.sp +That is, it matches a character without the "mark" property, followed by zero +or more characters with the "mark" property, and treats the sequence as an +atomic group +.\" HTML +.\" +(see below). +.\" +Characters with the "mark" property are typically accents that affect the +preceding character. +.P +Matching characters by Unicode property is not fast, because PCRE has to search +a structure that contains data for over fifteen thousand characters. That is +why the traditional escape sequences such as \ed and \ew do not use Unicode +properties in PCRE. +. +. +.\" HTML +.SS "Simple assertions" +.rs +.sp +The fourth use of backslash is for certain simple assertions. An assertion +specifies a condition that has to be met at a particular point in a match, +without consuming any characters from the subject string. The use of +subpatterns for more complicated assertions is described +.\" HTML +.\" +below. +.\" +The backslashed assertions are: +.sp + \eb matches at a word boundary + \eB matches when not at a word boundary + \eA matches at start of subject + \eZ matches at end of subject or before newline at end + \ez matches at end of subject + \eG matches at first matching position in subject +.sp +These assertions may not appear in character classes (but note that \eb has a +different meaning, namely the backspace character, inside a character class). +.P +A word boundary is a position in the subject string where the current character +and the previous character do not both match \ew or \eW (i.e. one matches +\ew and the other matches \eW), or the start or end of the string if the +first or last character matches \ew, respectively. +.P +The \eA, \eZ, and \ez assertions differ from the traditional circumflex and +dollar (described in the next section) in that they only ever match at the very +start and end of the subject string, whatever options are set. Thus, they are +independent of multiline mode. These three assertions are not affected by the +PCRE_NOTBOL or PCRE_NOTEOL options, which affect only the behaviour of the +circumflex and dollar metacharacters. However, if the \fIstartoffset\fP +argument of \fBpcre_exec()\fP is non-zero, indicating that matching is to start +at a point other than the beginning of the subject, \eA can never match. The +difference between \eZ and \ez is that \eZ matches before a newline at the end +of the string as well as at the very end, whereas \ez matches only at the end. +.P +The \eG assertion is true only when the current matching position is at the +start point of the match, as specified by the \fIstartoffset\fP argument of +\fBpcre_exec()\fP. It differs from \eA when the value of \fIstartoffset\fP is +non-zero. By calling \fBpcre_exec()\fP multiple times with appropriate +arguments, you can mimic Perl's /g option, and it is in this kind of +implementation where \eG can be useful. +.P +Note, however, that PCRE's interpretation of \eG, as the start of the current +match, is subtly different from Perl's, which defines it as the end of the +previous match. In Perl, these can be different when the previously matched +string was empty. Because PCRE does just one match at a time, it cannot +reproduce this behaviour. +.P +If all the alternatives of a pattern begin with \eG, the expression is anchored +to the starting match position, and the "anchored" flag is set in the compiled +regular expression. +. +. +.SH "CIRCUMFLEX AND DOLLAR" +.rs +.sp +Outside a character class, in the default matching mode, the circumflex +character is an assertion that is true only if the current matching point is +at the start of the subject string. If the \fIstartoffset\fP argument of +\fBpcre_exec()\fP is non-zero, circumflex can never match if the PCRE_MULTILINE +option is unset. Inside a character class, circumflex has an entirely different +meaning +.\" HTML +.\" +(see below). +.\" +.P +Circumflex need not be the first character of the pattern if a number of +alternatives are involved, but it should be the first thing in each alternative +in which it appears if the pattern is ever to match that branch. If all +possible alternatives start with a circumflex, that is, if the pattern is +constrained to match only at the start of the subject, it is said to be an +"anchored" pattern. (There are also other constructs that can cause a pattern +to be anchored.) +.P +A dollar character is an assertion that is true only if the current matching +point is at the end of the subject string, or immediately before a newline +at the end of the string (by default). Dollar need not be the last character of +the pattern if a number of alternatives are involved, but it should be the last +item in any branch in which it appears. Dollar has no special meaning in a +character class. +.P +The meaning of dollar can be changed so that it matches only at the very end of +the string, by setting the PCRE_DOLLAR_ENDONLY option at compile time. This +does not affect the \eZ assertion. +.P +The meanings of the circumflex and dollar characters are changed if the +PCRE_MULTILINE option is set. When this is the case, a circumflex matches +immediately after internal newlines as well as at the start of the subject +string. It does not match after a newline that ends the string. A dollar +matches before any newlines in the string, as well as at the very end, when +PCRE_MULTILINE is set. When newline is specified as the two-character +sequence CRLF, isolated CR and LF characters do not indicate newlines. +.P +For example, the pattern /^abc$/ matches the subject string "def\enabc" (where +\en represents a newline) in multiline mode, but not otherwise. Consequently, +patterns that are anchored in single line mode because all branches start with +^ are not anchored in multiline mode, and a match for circumflex is possible +when the \fIstartoffset\fP argument of \fBpcre_exec()\fP is non-zero. The +PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set. +.P +Note that the sequences \eA, \eZ, and \ez can be used to match the start and +end of the subject in both modes, and if all branches of a pattern start with +\eA it is always anchored, whether or not PCRE_MULTILINE is set. +. +. +.SH "FULL STOP (PERIOD, DOT)" +.rs +.sp +Outside a character class, a dot in the pattern matches any one character in +the subject string except (by default) a character that signifies the end of a +line. In UTF-8 mode, the matched character may be more than one byte long. When +a line ending is defined as a single character (CR or LF), dot never matches +that character; when the two-character sequence CRLF is used, dot does not +match CR if it is immediately followed by LF, but otherwise it matches all +characters (including isolated CRs and LFs). +.P +The behaviour of dot with regard to newlines can be changed. If the PCRE_DOTALL +option is set, a dot matches any one character, without exception. If newline +is defined as the two-character sequence CRLF, it takes two dots to match it. +.P +The handling of dot is entirely independent of the handling of circumflex and +dollar, the only relationship being that they both involve newlines. Dot has no +special meaning in a character class. +. +. +.SH "MATCHING A SINGLE BYTE" +.rs +.sp +Outside a character class, the escape sequence \eC matches any one byte, both +in and out of UTF-8 mode. Unlike a dot, it always matches CR and LF. The +feature is provided in Perl in order to match individual bytes in UTF-8 mode. +Because it breaks up UTF-8 characters into individual bytes, what remains in +the string may be a malformed UTF-8 string. For this reason, the \eC escape +sequence is best avoided. +.P +PCRE does not allow \eC to appear in lookbehind assertions +.\" HTML +.\" +(described below), +.\" +because in UTF-8 mode this would make it impossible to calculate the length of +the lookbehind. +. +. +.\" HTML +.SH "SQUARE BRACKETS AND CHARACTER CLASSES" +.rs +.sp +An opening square bracket introduces a character class, terminated by a closing +square bracket. A closing square bracket on its own is not special. If a +closing square bracket is required as a member of the class, it should be the +first data character in the class (after an initial circumflex, if present) or +escaped with a backslash. +.P +A character class matches a single character in the subject. In UTF-8 mode, the +character may occupy more than one byte. A matched character must be in the set +of characters defined by the class, unless the first character in the class +definition is a circumflex, in which case the subject character must not be in +the set defined by the class. If a circumflex is actually required as a member +of the class, ensure it is not the first character, or escape it with a +backslash. +.P +For example, the character class [aeiou] matches any lower case vowel, while +[^aeiou] matches any character that is not a lower case vowel. Note that a +circumflex is just a convenient notation for specifying the characters that +are in the class by enumerating those that are not. A class that starts with a +circumflex is not an assertion: it still consumes a character from the subject +string, and therefore it fails if the current pointer is at the end of the +string. +.P +In UTF-8 mode, characters with values greater than 255 can be included in a +class as a literal string of bytes, or by using the \ex{ escaping mechanism. +.P +When caseless matching is set, any letters in a class represent both their +upper case and lower case versions, so for example, a caseless [aeiou] matches +"A" as well as "a", and a caseless [^aeiou] does not match "A", whereas a +caseful version would. In UTF-8 mode, PCRE always understands the concept of +case for characters whose values are less than 128, so caseless matching is +always possible. For characters with higher values, the concept of case is +supported if PCRE is compiled with Unicode property support, but not otherwise. +If you want to use caseless matching for characters 128 and above, you must +ensure that PCRE is compiled with Unicode property support as well as with +UTF-8 support. +.P +Characters that might indicate line breaks (CR and LF) are never treated in any +special way when matching character classes, whatever line-ending sequence is +in use, and whatever setting of the PCRE_DOTALL and PCRE_MULTILINE options is +used. A class such as [^a] always matches one of these characters. +.P +The minus (hyphen) character can be used to specify a range of characters in a +character class. For example, [d-m] matches any letter between d and m, +inclusive. If a minus character is required in a class, it must be escaped with +a backslash or appear in a position where it cannot be interpreted as +indicating a range, typically as the first or last character in the class. +.P +It is not possible to have the literal character "]" as the end character of a +range. A pattern such as [W-]46] is interpreted as a class of two characters +("W" and "-") followed by a literal string "46]", so it would match "W46]" or +"-46]". However, if the "]" is escaped with a backslash it is interpreted as +the end of range, so [W-\e]46] is interpreted as a class containing a range +followed by two other characters. The octal or hexadecimal representation of +"]" can also be used to end a range. +.P +Ranges operate in the collating sequence of character values. They can also be +used for characters specified numerically, for example [\e000-\e037]. In UTF-8 +mode, ranges can include characters whose values are greater than 255, for +example [\ex{100}-\ex{2ff}]. +.P +If a range that includes letters is used when caseless matching is set, it +matches the letters in either case. For example, [W-c] is equivalent to +[][\e\e^_`wxyzabc], matched caselessly, and in non-UTF-8 mode, if character +tables for the "fr_FR" locale are in use, [\exc8-\excb] matches accented E +characters in both cases. In UTF-8 mode, PCRE supports the concept of case for +characters with values greater than 128 only when it is compiled with Unicode +property support. +.P +The character types \ed, \eD, \ep, \eP, \es, \eS, \ew, and \eW may also appear +in a character class, and add the characters that they match to the class. For +example, [\edABCDEF] matches any hexadecimal digit. A circumflex can +conveniently be used with the upper case character types to specify a more +restricted set of characters than the matching lower case type. For example, +the class [^\eW_] matches any letter or digit, but not underscore. +.P +The only metacharacters that are recognized in character classes are backslash, +hyphen (only where it can be interpreted as specifying a range), circumflex +(only at the start), opening square bracket (only when it can be interpreted as +introducing a POSIX class name - see the next section), and the terminating +closing square bracket. However, escaping other non-alphanumeric characters +does no harm. +. +. +.SH "POSIX CHARACTER CLASSES" +.rs +.sp +Perl supports the POSIX notation for character classes. This uses names +enclosed by [: and :] within the enclosing square brackets. PCRE also supports +this notation. For example, +.sp + [01[:alpha:]%] +.sp +matches "0", "1", any alphabetic character, or "%". The supported class names +are +.sp + alnum letters and digits + alpha letters + ascii character codes 0 - 127 + blank space or tab only + cntrl control characters + digit decimal digits (same as \ed) + graph printing characters, excluding space + lower lower case letters + print printing characters, including space + punct printing characters, excluding letters and digits + space white space (not quite the same as \es) + upper upper case letters + word "word" characters (same as \ew) + xdigit hexadecimal digits +.sp +The "space" characters are HT (9), LF (10), VT (11), FF (12), CR (13), and +space (32). Notice that this list includes the VT character (code 11). This +makes "space" different to \es, which does not include VT (for Perl +compatibility). +.P +The name "word" is a Perl extension, and "blank" is a GNU extension from Perl +5.8. Another Perl extension is negation, which is indicated by a ^ character +after the colon. For example, +.sp + [12[:^digit:]] +.sp +matches "1", "2", or any non-digit. PCRE (and Perl) also recognize the POSIX +syntax [.ch.] and [=ch=] where "ch" is a "collating element", but these are not +supported, and an error is given if they are encountered. +.P +In UTF-8 mode, characters with values greater than 128 do not match any of +the POSIX character classes. +. +. +.SH "VERTICAL BAR" +.rs +.sp +Vertical bar characters are used to separate alternative patterns. For example, +the pattern +.sp + gilbert|sullivan +.sp +matches either "gilbert" or "sullivan". Any number of alternatives may appear, +and an empty alternative is permitted (matching the empty string). The matching +process tries each alternative in turn, from left to right, and the first one +that succeeds is used. If the alternatives are within a subpattern +.\" HTML +.\" +(defined below), +.\" +"succeeds" means matching the rest of the main pattern as well as the +alternative in the subpattern. +. +. +.SH "INTERNAL OPTION SETTING" +.rs +.sp +The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and +PCRE_EXTENDED options can be changed from within the pattern by a sequence of +Perl option letters enclosed between "(?" and ")". The option letters are +.sp + i for PCRE_CASELESS + m for PCRE_MULTILINE + s for PCRE_DOTALL + x for PCRE_EXTENDED +.sp +For example, (?im) sets caseless, multiline matching. It is also possible to +unset these options by preceding the letter with a hyphen, and a combined +setting and unsetting such as (?im-sx), which sets PCRE_CASELESS and +PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, is also +permitted. If a letter appears both before and after the hyphen, the option is +unset. +.P +When an option change occurs at top level (that is, not inside subpattern +parentheses), the change applies to the remainder of the pattern that follows. +If the change is placed right at the start of a pattern, PCRE extracts it into +the global options (and it will therefore show up in data extracted by the +\fBpcre_fullinfo()\fP function). +.P +An option change within a subpattern affects only that part of the current +pattern that follows it, so +.sp + (a(?i)b)c +.sp +matches abc and aBc and no other strings (assuming PCRE_CASELESS is not used). +By this means, options can be made to have different settings in different +parts of the pattern. Any changes made in one alternative do carry on +into subsequent branches within the same subpattern. For example, +.sp + (a(?i)b|c) +.sp +matches "ab", "aB", "c", and "C", even though when matching "C" the first +branch is abandoned before the option setting. This is because the effects of +option settings happen at compile time. There would be some very weird +behaviour otherwise. +.P +The PCRE-specific options PCRE_DUPNAMES, PCRE_UNGREEDY, and PCRE_EXTRA can be +changed in the same way as the Perl-compatible options by using the characters +J, U and X respectively. +. +. +.\" HTML +.SH SUBPATTERNS +.rs +.sp +Subpatterns are delimited by parentheses (round brackets), which can be nested. +Turning part of a pattern into a subpattern does two things: +.sp +1. It localizes a set of alternatives. For example, the pattern +.sp + cat(aract|erpillar|) +.sp +matches one of the words "cat", "cataract", or "caterpillar". Without the +parentheses, it would match "cataract", "erpillar" or the empty string. +.sp +2. It sets up the subpattern as a capturing subpattern. This means that, when +the whole pattern matches, that portion of the subject string that matched the +subpattern is passed back to the caller via the \fIovector\fP argument of +\fBpcre_exec()\fP. Opening parentheses are counted from left to right (starting +from 1) to obtain numbers for the capturing subpatterns. +.P +For example, if the string "the red king" is matched against the pattern +.sp + the ((red|white) (king|queen)) +.sp +the captured substrings are "red king", "red", and "king", and are numbered 1, +2, and 3, respectively. +.P +The fact that plain parentheses fulfil two functions is not always helpful. +There are often times when a grouping subpattern is required without a +capturing requirement. If an opening parenthesis is followed by a question mark +and a colon, the subpattern does not do any capturing, and is not counted when +computing the number of any subsequent capturing subpatterns. For example, if +the string "the white queen" is matched against the pattern +.sp + the ((?:red|white) (king|queen)) +.sp +the captured substrings are "white queen" and "queen", and are numbered 1 and +2. The maximum number of capturing subpatterns is 65535, and the maximum depth +of nesting of all subpatterns, both capturing and non-capturing, is 200. +.P +As a convenient shorthand, if any option settings are required at the start of +a non-capturing subpattern, the option letters may appear between the "?" and +the ":". Thus the two patterns +.sp + (?i:saturday|sunday) + (?:(?i)saturday|sunday) +.sp +match exactly the same set of strings. Because alternative branches are tried +from left to right, and options are not reset until the end of the subpattern +is reached, an option setting in one branch does affect subsequent branches, so +the above patterns match "SUNDAY" as well as "Saturday". +. +. +.SH "NAMED SUBPATTERNS" +.rs +.sp +Identifying capturing parentheses by number is simple, but it can be very hard +to keep track of the numbers in complicated regular expressions. Furthermore, +if an expression is modified, the numbers may change. To help with this +difficulty, PCRE supports the naming of subpatterns, something that Perl does +not provide. The Python syntax (?P...) is used. References to capturing +parentheses from other parts of the pattern, such as +.\" HTML +.\" +backreferences, +.\" +.\" HTML +.\" +recursion, +.\" +and +.\" HTML +.\" +conditions, +.\" +can be made by name as well as by number. +.P +Names consist of up to 32 alphanumeric characters and underscores. Named +capturing parentheses are still allocated numbers as well as names. The PCRE +API provides function calls for extracting the name-to-number translation table +from a compiled pattern. There is also a convenience function for extracting a +captured substring by name. +.P +By default, a name must be unique within a pattern, but it is possible to relax +this constraint by setting the PCRE_DUPNAMES option at compile time. This can +be useful for patterns where only one instance of the named parentheses can +match. Suppose you want to match the name of a weekday, either as a 3-letter +abbreviation or as the full name, and in both cases you want to extract the +abbreviation. This pattern (ignoring the line breaks) does the job: +.sp + (?PMon|Fri|Sun)(?:day)?| + (?PTue)(?:sday)?| + (?PWed)(?:nesday)?| + (?PThu)(?:rsday)?| + (?PSat)(?:urday)? +.sp +There are five capturing substrings, but only one is ever set after a match. +The convenience function for extracting the data by name returns the substring +for the first, and in this example, the only, subpattern of that name that +matched. This saves searching to find which numbered subpattern it was. If you +make a reference to a non-unique named subpattern from elsewhere in the +pattern, the one that corresponds to the lowest number is used. For further +details of the interfaces for handling named subpatterns, see the +.\" HREF +\fBpcreapi\fP +.\" +documentation. +. +. +.SH REPETITION +.rs +.sp +Repetition is specified by quantifiers, which can follow any of the following +items: +.sp + a literal data character + the . metacharacter + the \eC escape sequence + the \eX escape sequence (in UTF-8 mode with Unicode properties) + an escape such as \ed that matches a single character + a character class + a back reference (see next section) + a parenthesized subpattern (unless it is an assertion) +.sp +The general repetition quantifier specifies a minimum and maximum number of +permitted matches, by giving the two numbers in curly brackets (braces), +separated by a comma. The numbers must be less than 65536, and the first must +be less than or equal to the second. For example: +.sp + z{2,4} +.sp +matches "zz", "zzz", or "zzzz". A closing brace on its own is not a special +character. If the second number is omitted, but the comma is present, there is +no upper limit; if the second number and the comma are both omitted, the +quantifier specifies an exact number of required matches. Thus +.sp + [aeiou]{3,} +.sp +matches at least 3 successive vowels, but may match many more, while +.sp + \ed{8} +.sp +matches exactly 8 digits. An opening curly bracket that appears in a position +where a quantifier is not allowed, or one that does not match the syntax of a +quantifier, is taken as a literal character. For example, {,6} is not a +quantifier, but a literal string of four characters. +.P +In UTF-8 mode, quantifiers apply to UTF-8 characters rather than to individual +bytes. Thus, for example, \ex{100}{2} matches two UTF-8 characters, each of +which is represented by a two-byte sequence. Similarly, when Unicode property +support is available, \eX{3} matches three Unicode extended sequences, each of +which may be several bytes long (and they may be of different lengths). +.P +The quantifier {0} is permitted, causing the expression to behave as if the +previous item and the quantifier were not present. +.P +For convenience (and historical compatibility) the three most common +quantifiers have single-character abbreviations: +.sp + * is equivalent to {0,} + + is equivalent to {1,} + ? is equivalent to {0,1} +.sp +It is possible to construct infinite loops by following a subpattern that can +match no characters with a quantifier that has no upper limit, for example: +.sp + (a?)* +.sp +Earlier versions of Perl and PCRE used to give an error at compile time for +such patterns. However, because there are cases where this can be useful, such +patterns are now accepted, but if any repetition of the subpattern does in fact +match no characters, the loop is forcibly broken. +.P +By default, the quantifiers are "greedy", that is, they match as much as +possible (up to the maximum number of permitted times), without causing the +rest of the pattern to fail. The classic example of where this gives problems +is in trying to match comments in C programs. These appear between /* and */ +and within the comment, individual * and / characters may appear. An attempt to +match C comments by applying the pattern +.sp + /\e*.*\e*/ +.sp +to the string +.sp + /* first comment */ not comment /* second comment */ +.sp +fails, because it matches the entire string owing to the greediness of the .* +item. +.P +However, if a quantifier is followed by a question mark, it ceases to be +greedy, and instead matches the minimum number of times possible, so the +pattern +.sp + /\e*.*?\e*/ +.sp +does the right thing with the C comments. The meaning of the various +quantifiers is not otherwise changed, just the preferred number of matches. +Do not confuse this use of question mark with its use as a quantifier in its +own right. Because it has two uses, it can sometimes appear doubled, as in +.sp + \ed??\ed +.sp +which matches one digit by preference, but can match two if that is the only +way the rest of the pattern matches. +.P +If the PCRE_UNGREEDY option is set (an option which is not available in Perl), +the quantifiers are not greedy by default, but individual ones can be made +greedy by following them with a question mark. In other words, it inverts the +default behaviour. +.P +When a parenthesized subpattern is quantified with a minimum repeat count that +is greater than 1 or with a limited maximum, more memory is required for the +compiled pattern, in proportion to the size of the minimum or maximum. +.P +If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equivalent +to Perl's /s) is set, thus allowing the . to match newlines, the pattern is +implicitly anchored, because whatever follows will be tried against every +character position in the subject string, so there is no point in retrying the +overall match at any position after the first. PCRE normally treats such a +pattern as though it were preceded by \eA. +.P +In cases where it is known that the subject string contains no newlines, it is +worth setting PCRE_DOTALL in order to obtain this optimization, or +alternatively using ^ to indicate anchoring explicitly. +.P +However, there is one situation where the optimization cannot be used. When .* +is inside capturing parentheses that are the subject of a backreference +elsewhere in the pattern, a match at the start may fail, and a later one +succeed. Consider, for example: +.sp + (.*)abc\e1 +.sp +If the subject is "xyz123abc123" the match point is the fourth character. For +this reason, such a pattern is not implicitly anchored. +.P +When a capturing subpattern is repeated, the value captured is the substring +that matched the final iteration. For example, after +.sp + (tweedle[dume]{3}\es*)+ +.sp +has matched "tweedledum tweedledee" the value of the captured substring is +"tweedledee". However, if there are nested capturing subpatterns, the +corresponding captured values may have been set in previous iterations. For +example, after +.sp + /(a|(b))+/ +.sp +matches "aba" the value of the second captured substring is "b". +. +. +.\" HTML +.SH "ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS" +.rs +.sp +With both maximizing and minimizing repetition, failure of what follows +normally causes the repeated item to be re-evaluated to see if a different +number of repeats allows the rest of the pattern to match. Sometimes it is +useful to prevent this, either to change the nature of the match, or to cause +it fail earlier than it otherwise might, when the author of the pattern knows +there is no point in carrying on. +.P +Consider, for example, the pattern \ed+foo when applied to the subject line +.sp + 123456bar +.sp +After matching all 6 digits and then failing to match "foo", the normal +action of the matcher is to try again with only 5 digits matching the \ed+ +item, and then with 4, and so on, before ultimately failing. "Atomic grouping" +(a term taken from Jeffrey Friedl's book) provides the means for specifying +that once a subpattern has matched, it is not to be re-evaluated in this way. +.P +If we use atomic grouping for the previous example, the matcher would give up +immediately on failing to match "foo" the first time. The notation is a kind of +special parenthesis, starting with (?> as in this example: +.sp + (?>\ed+)foo +.sp +This kind of parenthesis "locks up" the part of the pattern it contains once +it has matched, and a failure further into the pattern is prevented from +backtracking into it. Backtracking past it to previous items, however, works as +normal. +.P +An alternative description is that a subpattern of this type matches the string +of characters that an identical standalone pattern would match, if anchored at +the current point in the subject string. +.P +Atomic grouping subpatterns are not capturing subpatterns. Simple cases such as +the above example can be thought of as a maximizing repeat that must swallow +everything it can. So, while both \ed+ and \ed+? are prepared to adjust the +number of digits they match in order to make the rest of the pattern match, +(?>\ed+) can only match an entire sequence of digits. +.P +Atomic groups in general can of course contain arbitrarily complicated +subpatterns, and can be nested. However, when the subpattern for an atomic +group is just a single repeated item, as in the example above, a simpler +notation, called a "possessive quantifier" can be used. This consists of an +additional + character following a quantifier. Using this notation, the +previous example can be rewritten as +.sp + \ed++foo +.sp +Possessive quantifiers are always greedy; the setting of the PCRE_UNGREEDY +option is ignored. They are a convenient notation for the simpler forms of +atomic group. However, there is no difference in the meaning or processing of a +possessive quantifier and the equivalent atomic group. +.P +The possessive quantifier syntax is an extension to the Perl syntax. Jeffrey +Friedl originated the idea (and the name) in the first edition of his book. +Mike McCloskey liked it, so implemented it when he built Sun's Java package, +and PCRE copied it from there. +.P +When a pattern contains an unlimited repeat inside a subpattern that can itself +be repeated an unlimited number of times, the use of an atomic group is the +only way to avoid some failing matches taking a very long time indeed. The +pattern +.sp + (\eD+|<\ed+>)*[!?] +.sp +matches an unlimited number of substrings that either consist of non-digits, or +digits enclosed in <>, followed by either ! or ?. When it matches, it runs +quickly. However, if it is applied to +.sp + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +.sp +it takes a long time before reporting failure. This is because the string can +be divided between the internal \eD+ repeat and the external * repeat in a +large number of ways, and all have to be tried. (The example uses [!?] rather +than a single character at the end, because both PCRE and Perl have an +optimization that allows for fast failure when a single character is used. They +remember the last single character that is required for a match, and fail early +if it is not present in the string.) If the pattern is changed so that it uses +an atomic group, like this: +.sp + ((?>\eD+)|<\ed+>)*[!?] +.sp +sequences of non-digits cannot be broken, and failure happens quickly. +. +. +.\" HTML +.SH "BACK REFERENCES" +.rs +.sp +Outside a character class, a backslash followed by a digit greater than 0 (and +possibly further digits) is a back reference to a capturing subpattern earlier +(that is, to its left) in the pattern, provided there have been that many +previous capturing left parentheses. +.P +However, if the decimal number following the backslash is less than 10, it is +always taken as a back reference, and causes an error only if there are not +that many capturing left parentheses in the entire pattern. In other words, the +parentheses that are referenced need not be to the left of the reference for +numbers less than 10. A "forward back reference" of this type can make sense +when a repetition is involved and the subpattern to the right has participated +in an earlier iteration. +.P +It is not possible to have a numerical "forward back reference" to subpattern +whose number is 10 or more. However, a back reference to any subpattern is +possible using named parentheses (see below). See also the subsection entitled +"Non-printing characters" +.\" HTML +.\" +above +.\" +for further details of the handling of digits following a backslash. +.P +A back reference matches whatever actually matched the capturing subpattern in +the current subject string, rather than anything matching the subpattern +itself (see +.\" HTML +.\" +"Subpatterns as subroutines" +.\" +below for a way of doing that). So the pattern +.sp + (sens|respons)e and \e1ibility +.sp +matches "sense and sensibility" and "response and responsibility", but not +"sense and responsibility". If caseful matching is in force at the time of the +back reference, the case of letters is relevant. For example, +.sp + ((?i)rah)\es+\e1 +.sp +matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original +capturing subpattern is matched caselessly. +.P +Back references to named subpatterns use the Python syntax (?P=name). We could +rewrite the above example as follows: +.sp + (?P(?i)rah)\es+(?P=p1) +.sp +A subpattern that is referenced by name may appear in the pattern before or +after the reference. +.P +There may be more than one back reference to the same subpattern. If a +subpattern has not actually been used in a particular match, any back +references to it always fail. For example, the pattern +.sp + (a|(bc))\e2 +.sp +always fails if it starts to match "a" rather than "bc". Because there may be +many capturing parentheses in a pattern, all digits following the backslash are +taken as part of a potential back reference number. If the pattern continues +with a digit character, some delimiter must be used to terminate the back +reference. If the PCRE_EXTENDED option is set, this can be whitespace. +Otherwise an empty comment (see +.\" HTML +.\" +"Comments" +.\" +below) can be used. +.P +A back reference that occurs inside the parentheses to which it refers fails +when the subpattern is first used, so, for example, (a\e1) never matches. +However, such references can be useful inside repeated subpatterns. For +example, the pattern +.sp + (a|b\e1)+ +.sp +matches any number of "a"s and also "aba", "ababbaa" etc. At each iteration of +the subpattern, the back reference matches the character string corresponding +to the previous iteration. In order for this to work, the pattern must be such +that the first iteration does not need to match the back reference. This can be +done using alternation, as in the example above, or by a quantifier with a +minimum of zero. +. +. +.\" HTML +.SH ASSERTIONS +.rs +.sp +An assertion is a test on the characters following or preceding the current +matching point that does not actually consume any characters. The simple +assertions coded as \eb, \eB, \eA, \eG, \eZ, \ez, ^ and $ are described +.\" HTML +.\" +above. +.\" +.P +More complicated assertions are coded as subpatterns. There are two kinds: +those that look ahead of the current position in the subject string, and those +that look behind it. An assertion subpattern is matched in the normal way, +except that it does not cause the current matching position to be changed. +.P +Assertion subpatterns are not capturing subpatterns, and may not be repeated, +because it makes no sense to assert the same thing several times. If any kind +of assertion contains capturing subpatterns within it, these are counted for +the purposes of numbering the capturing subpatterns in the whole pattern. +However, substring capturing is carried out only for positive assertions, +because it does not make sense for negative assertions. +. +. +.SS "Lookahead assertions" +.rs +.sp +Lookahead assertions start with (?= for positive assertions and (?! for +negative assertions. For example, +.sp + \ew+(?=;) +.sp +matches a word followed by a semicolon, but does not include the semicolon in +the match, and +.sp + foo(?!bar) +.sp +matches any occurrence of "foo" that is not followed by "bar". Note that the +apparently similar pattern +.sp + (?!foo)bar +.sp +does not find an occurrence of "bar" that is preceded by something other than +"foo"; it finds any occurrence of "bar" whatsoever, because the assertion +(?!foo) is always true when the next three characters are "bar". A +lookbehind assertion is needed to achieve the other effect. +.P +If you want to force a matching failure at some point in a pattern, the most +convenient way to do it is with (?!) because an empty string always matches, so +an assertion that requires there not to be an empty string must always fail. +. +. +.\" HTML +.SS "Lookbehind assertions" +.rs +.sp +Lookbehind assertions start with (?<= for positive assertions and (?.*)(?<=abcd) +.sp +or, equivalently, using the possessive quantifier syntax, +.sp + ^.*+(?<=abcd) +.sp +there can be no backtracking for the .* item; it can match only the entire +string. The subsequent lookbehind assertion does a single test on the last four +characters. If it fails, the match fails immediately. For long strings, this +approach makes a significant difference to the processing time. +. +. +.SS "Using multiple assertions" +.rs +.sp +Several assertions (of any sort) may occur in succession. For example, +.sp + (?<=\ed{3})(? +.SH "CONDITIONAL SUBPATTERNS" +.rs +.sp +It is possible to cause the matching process to obey a subpattern +conditionally or to choose between two alternative subpatterns, depending on +the result of an assertion, or whether a previous capturing subpattern matched +or not. The two possible forms of conditional subpattern are +.sp + (?(condition)yes-pattern) + (?(condition)yes-pattern|no-pattern) +.sp +If the condition is satisfied, the yes-pattern is used; otherwise the +no-pattern (if present) is used. If there are more than two alternatives in the +subpattern, a compile-time error occurs. +.P +There are three kinds of condition. If the text between the parentheses +consists of a sequence of digits, or a sequence of alphanumeric characters and +underscores, the condition is satisfied if the capturing subpattern of that +number or name has previously matched. There is a possible ambiguity here, +because subpattern names may consist entirely of digits. PCRE looks first for a +named subpattern; if it cannot find one and the text consists entirely of +digits, it looks for a subpattern of that number, which must be greater than +zero. Using subpattern names that consist entirely of digits is not +recommended. +.P +Consider the following pattern, which contains non-significant white space to +make it more readable (assume the PCRE_EXTENDED option) and to divide it into +three parts for ease of discussion: +.sp + ( \e( )? [^()]+ (?(1) \e) ) +.sp +The first part matches an optional opening parenthesis, and if that +character is present, sets it as the first captured substring. The second part +matches one or more characters that are not parentheses. The third part is a +conditional subpattern that tests whether the first set of parentheses matched +or not. If they did, that is, if subject started with an opening parenthesis, +the condition is true, and so the yes-pattern is executed and a closing +parenthesis is required. Otherwise, since no-pattern is not present, the +subpattern matches nothing. In other words, this pattern matches a sequence of +non-parentheses, optionally enclosed in parentheses. Rewriting it to use a +named subpattern gives this: +.sp + (?P \e( )? [^()]+ (?(OPEN) \e) ) +.sp +If the condition is the string (R), and there is no subpattern with the name R, +the condition is satisfied if a recursive call to the pattern or subpattern has +been made. At "top level", the condition is false. This is a PCRE extension. +Recursive patterns are described in the next section. +.P +If the condition is not a sequence of digits or (R), it must be an assertion. +This may be a positive or negative lookahead or lookbehind assertion. Consider +this pattern, again containing non-significant white space, and with the two +alternatives on the second line: +.sp + (?(?=[^a-z]*[a-z]) + \ed{2}-[a-z]{3}-\ed{2} | \ed{2}-\ed{2}-\ed{2} ) +.sp +The condition is a positive lookahead assertion that matches an optional +sequence of non-letters followed by a letter. In other words, it tests for the +presence of at least one letter in the subject. If a letter is found, the +subject is matched against the first alternative; otherwise it is matched +against the second. This pattern matches strings in one of the two forms +dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits. +. +. +.\" HTML +.SH COMMENTS +.rs +.sp +The sequence (?# marks the start of a comment that continues up to the next +closing parenthesis. Nested parentheses are not permitted. The characters +that make up a comment play no part in the pattern matching at all. +.P +If the PCRE_EXTENDED option is set, an unescaped # character outside a +character class introduces a comment that continues to immediately after the +next newline in the pattern. +. +. +.\" HTML +.SH "RECURSIVE PATTERNS" +.rs +.sp +Consider the problem of matching a string in parentheses, allowing for +unlimited nested parentheses. Without the use of recursion, the best that can +be done is to use a pattern that matches up to some fixed depth of nesting. It +is not possible to handle an arbitrary nesting depth. Perl provides a facility +that allows regular expressions to recurse (amongst other things). It does this +by interpolating Perl code in the expression at run time, and the code can +refer to the expression itself. A Perl pattern to solve the parentheses problem +can be created like this: +.sp + $re = qr{\e( (?: (?>[^()]+) | (?p{$re}) )* \e)}x; +.sp +The (?p{...}) item interpolates Perl code at run time, and in this case refers +recursively to the pattern in which it appears. Obviously, PCRE cannot support +the interpolation of Perl code. Instead, it supports some special syntax for +recursion of the entire pattern, and also for individual subpattern recursion. +.P +The special item that consists of (? followed by a number greater than zero and +a closing parenthesis is a recursive call of the subpattern of the given +number, provided that it occurs inside that subpattern. (If not, it is a +"subroutine" call, which is described in the next section.) The special item +(?R) is a recursive call of the entire regular expression. +.P +A recursive subpattern call is always treated as an atomic group. That is, once +it has matched some of the subject string, it is never re-entered, even if +it contains untried alternatives and there is a subsequent matching failure. +.P +This PCRE pattern solves the nested parentheses problem (assume the +PCRE_EXTENDED option is set so that white space is ignored): +.sp + \e( ( (?>[^()]+) | (?R) )* \e) +.sp +First it matches an opening parenthesis. Then it matches any number of +substrings which can either be a sequence of non-parentheses, or a recursive +match of the pattern itself (that is, a correctly parenthesized substring). +Finally there is a closing parenthesis. +.P +If this were part of a larger pattern, you would not want to recurse the entire +pattern, so instead you could use this: +.sp + ( \e( ( (?>[^()]+) | (?1) )* \e) ) +.sp +We have put the pattern into parentheses, and caused the recursion to refer to +them instead of the whole pattern. In a larger pattern, keeping track of +parenthesis numbers can be tricky. It may be more convenient to use named +parentheses instead. For this, PCRE uses (?P>name), which is an extension to +the Python syntax that PCRE uses for named parentheses (Perl does not provide +named parentheses). We could rewrite the above example as follows: +.sp + (?P \e( ( (?>[^()]+) | (?P>pn) )* \e) ) +.sp +This particular example pattern contains nested unlimited repeats, and so the +use of atomic grouping for matching strings of non-parentheses is important +when applying the pattern to strings that do not match. For example, when this +pattern is applied to +.sp + (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() +.sp +it yields "no match" quickly. However, if atomic grouping is not used, +the match runs for a very long time indeed because there are so many different +ways the + and * repeats can carve up the subject, and all have to be tested +before failure can be reported. +.P +At the end of a match, the values set for any capturing subpatterns are those +from the outermost level of the recursion at which the subpattern value is set. +If you want to obtain intermediate values, a callout function can be used (see +the next section and the +.\" HREF +\fBpcrecallout\fP +.\" +documentation). If the pattern above is matched against +.sp + (ab(cd)ef) +.sp +the value for the capturing parentheses is "ef", which is the last value taken +on at the top level. If additional parentheses are added, giving +.sp + \e( ( ( (?>[^()]+) | (?R) )* ) \e) + ^ ^ + ^ ^ +.sp +the string they capture is "ab(cd)ef", the contents of the top level +parentheses. If there are more than 15 capturing parentheses in a pattern, PCRE +has to obtain extra memory to store data during a recursion, which it does by +using \fBpcre_malloc\fP, freeing it via \fBpcre_free\fP afterwards. If no +memory can be obtained, the match fails with the PCRE_ERROR_NOMEMORY error. +.P +Do not confuse the (?R) item with the condition (R), which tests for recursion. +Consider this pattern, which matches text in angle brackets, allowing for +arbitrary nesting. Only digits are allowed in nested brackets (that is, when +recursing), whereas any characters are permitted at the outer level. +.sp + < (?: (?(R) \ed++ | [^<>]*+) | (?R)) * > +.sp +In this pattern, (?(R) is the start of a conditional subpattern, with two +different alternatives for the recursive and non-recursive cases. The (?R) item +is the actual recursive call. +. +. +.\" HTML +.SH "SUBPATTERNS AS SUBROUTINES" +.rs +.sp +If the syntax for a recursive subpattern reference (either by number or by +name) is used outside the parentheses to which it refers, it operates like a +subroutine in a programming language. An earlier example pointed out that the +pattern +.sp + (sens|respons)e and \e1ibility +.sp +matches "sense and sensibility" and "response and responsibility", but not +"sense and responsibility". If instead the pattern +.sp + (sens|respons)e and (?1)ibility +.sp +is used, it does match "sense and responsibility" as well as the other two +strings. Such references, if given numerically, must follow the subpattern to +which they refer. However, named references can refer to later subpatterns. +.P +Like recursive subpatterns, a "subroutine" call is always treated as an atomic +group. That is, once it has matched some of the subject string, it is never +re-entered, even if it contains untried alternatives and there is a subsequent +matching failure. +. +. +.SH CALLOUTS +.rs +.sp +Perl has a feature whereby using the sequence (?{...}) causes arbitrary Perl +code to be obeyed in the middle of matching a regular expression. This makes it +possible, amongst other things, to extract different substrings that match the +same pair of parentheses when there is a repetition. +.P +PCRE provides a similar feature, but of course it cannot obey arbitrary Perl +code. The feature is called "callout". The caller of PCRE provides an external +function by putting its entry point in the global variable \fIpcre_callout\fP. +By default, this variable contains NULL, which disables all calling out. +.P +Within a regular expression, (?C) indicates the points at which the external +function is to be called. If you want to identify different callout points, you +can put a number less than 256 after the letter C. The default value is zero. +For example, this pattern has two callout points: +.sp + (?C1)\dabc(?C2)def +.sp +If the PCRE_AUTO_CALLOUT flag is passed to \fBpcre_compile()\fP, callouts are +automatically installed before each item in the pattern. They are all numbered +255. +.P +During matching, when PCRE reaches a callout point (and \fIpcre_callout\fP is +set), the external function is called. It is provided with the number of the +callout, the position in the pattern, and, optionally, one item of data +originally supplied by the caller of \fBpcre_exec()\fP. The callout function +may cause matching to proceed, to backtrack, or to fail altogether. A complete +description of the interface to the callout function is given in the +.\" HREF +\fBpcrecallout\fP +.\" +documentation. +.P +.in 0 +Last updated: 06 June 2006 +.br +Copyright (c) 1997-2006 University of Cambridge. diff --git a/libs/pcre/doc/pcreperform.3 b/libs/pcre/doc/pcreperform.3 new file mode 100644 index 0000000000..75e8a1661d --- /dev/null +++ b/libs/pcre/doc/pcreperform.3 @@ -0,0 +1,76 @@ +.TH PCREPERFORM 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "PCRE PERFORMANCE" +.rs +.sp +Certain items that may appear in regular expression patterns are more efficient +than others. It is more efficient to use a character class like [aeiou] than a +set of alternatives such as (a|e|i|o|u). In general, the simplest construction +that provides the required behaviour is usually the most efficient. Jeffrey +Friedl's book contains a lot of useful general discussion about optimizing +regular expressions for efficient performance. This document contains a few +observations about PCRE. +.P +Using Unicode character properties (the \ep, \eP, and \eX escapes) is slow, +because PCRE has to scan a structure that contains data for over fifteen +thousand characters whenever it needs a character's property. If you can find +an alternative pattern that does not use character properties, it will probably +be faster. +.P +When a pattern begins with .* not in parentheses, or in parentheses that are +not the subject of a backreference, and the PCRE_DOTALL option is set, the +pattern is implicitly anchored by PCRE, since it can match only at the start of +a subject string. However, if PCRE_DOTALL is not set, PCRE cannot make this +optimization, because the . metacharacter does not then match a newline, and if +the subject string contains newlines, the pattern may match from the character +immediately following one of them instead of from the very start. For example, +the pattern +.sp + .*second +.sp +matches the subject "first\enand second" (where \en stands for a newline +character), with the match starting at the seventh character. In order to do +this, PCRE has to retry the match starting after every newline in the subject. +.P +If you are using such a pattern with subject strings that do not contain +newlines, the best performance is obtained by setting PCRE_DOTALL, or starting +the pattern with ^.* or ^.*? to indicate explicit anchoring. That saves PCRE +from having to scan along the subject looking for a newline to restart at. +.P +Beware of patterns that contain nested indefinite repeats. These can take a +long time to run when applied to a string that does not match. Consider the +pattern fragment +.sp + (a+)* +.sp +This can match "aaaa" in 33 different ways, and this number increases very +rapidly as the string gets longer. (The * repeat can match 0, 1, 2, 3, or 4 +times, and for each of those cases other than 0, the + repeats can match +different numbers of times.) When the remainder of the pattern is such that the +entire match is going to fail, PCRE has in principle to try every possible +variation, and this can take an extremely long time. +.P +An optimization catches some of the more simple cases such as +.sp + (a+)*b +.sp +where a literal character follows. Before embarking on the standard matching +procedure, PCRE checks that there is a "b" later in the subject string, and if +there is not, it fails the match immediately. However, when there is no +following literal this optimization cannot be used. You can see the difference +by comparing the behaviour of +.sp + (a+)*\ed +.sp +with the pattern above. The former gives a failure almost instantly when +applied to a whole line of "a" characters, whereas the latter takes an +appreciable time with strings longer than about 20 characters. +.P +In many cases, the solution to this kind of performance issue is to use an +atomic group or a possessive quantifier. +.P +.in 0 +Last updated: 28 February 2005 +.br +Copyright (c) 1997-2005 University of Cambridge. diff --git a/libs/pcre/doc/pcreposix.3 b/libs/pcre/doc/pcreposix.3 new file mode 100644 index 0000000000..0e9c8601df --- /dev/null +++ b/libs/pcre/doc/pcreposix.3 @@ -0,0 +1,226 @@ +.TH PCREPOSIX 3 +.SH NAME +PCRE - Perl-compatible regular expressions. +.SH "SYNOPSIS OF POSIX API" +.rs +.sp +.B #include +.PP +.SM +.br +.B int regcomp(regex_t *\fIpreg\fP, const char *\fIpattern\fP, +.ti +5n +.B int \fIcflags\fP); +.PP +.br +.B int regexec(regex_t *\fIpreg\fP, const char *\fIstring\fP, +.ti +5n +.B size_t \fInmatch\fP, regmatch_t \fIpmatch\fP[], int \fIeflags\fP); +.PP +.br +.B size_t regerror(int \fIerrcode\fP, const regex_t *\fIpreg\fP, +.ti +5n +.B char *\fIerrbuf\fP, size_t \fIerrbuf_size\fP); +.PP +.br +.B void regfree(regex_t *\fIpreg\fP); +. +.SH DESCRIPTION +.rs +.sp +This set of functions provides a POSIX-style API to the PCRE regular expression +package. See the +.\" HREF +\fBpcreapi\fP +.\" +documentation for a description of PCRE's native API, which contains much +additional functionality. +.P +The functions described here are just wrapper functions that ultimately call +the PCRE native API. Their prototypes are defined in the \fBpcreposix.h\fP +header file, and on Unix systems the library itself is called +\fBpcreposix.a\fP, so can be accessed by adding \fB-lpcreposix\fP to the +command for linking an application that uses them. Because the POSIX functions +call the native ones, it is also necessary to add \fB-lpcre\fP. +.P +I have implemented only those option bits that can be reasonably mapped to PCRE +native options. In addition, the option REG_EXTENDED is defined with the value +zero. This has no effect, but since programs that are written to the POSIX +interface often use it, this makes it easier to slot in PCRE as a replacement +library. Other POSIX options are not even defined. +.P +When PCRE is called via these functions, it is only the API that is POSIX-like +in style. The syntax and semantics of the regular expressions themselves are +still those of Perl, subject to the setting of various PCRE options, as +described below. "POSIX-like in style" means that the API approximates to the +POSIX definition; it is not fully POSIX-compatible, and in multi-byte encoding +domains it is probably even less compatible. +.P +The header for these functions is supplied as \fBpcreposix.h\fP to avoid any +potential clash with other POSIX libraries. It can, of course, be renamed or +aliased as \fBregex.h\fP, which is the "correct" name. It provides two +structure types, \fIregex_t\fP for compiled internal forms, and +\fIregmatch_t\fP for returning captured substrings. It also defines some +constants whose names start with "REG_"; these are used for setting options and +identifying error codes. +.P +.SH "COMPILING A PATTERN" +.rs +.sp +The function \fBregcomp()\fP is called to compile a pattern into an +internal form. The pattern is a C string terminated by a binary zero, and +is passed in the argument \fIpattern\fP. The \fIpreg\fP argument is a pointer +to a \fBregex_t\fP structure that is used as a base for storing information +about the compiled regular expression. +.P +The argument \fIcflags\fP is either zero, or contains one or more of the bits +defined by the following macros: +.sp + REG_DOTALL +.sp +The PCRE_DOTALL option is set when the regular expression is passed for +compilation to the native function. Note that REG_DOTALL is not part of the +POSIX standard. +.sp + REG_ICASE +.sp +The PCRE_CASELESS option is set when the regular expression is passed for +compilation to the native function. +.sp + REG_NEWLINE +.sp +The PCRE_MULTILINE option is set when the regular expression is passed for +compilation to the native function. Note that this does \fInot\fP mimic the +defined POSIX behaviour for REG_NEWLINE (see the following section). +.sp + REG_NOSUB +.sp +The PCRE_NO_AUTO_CAPTURE option is set when the regular expression is passed +for compilation to the native function. In addition, when a pattern that is +compiled with this flag is passed to \fBregexec()\fP for matching, the +\fInmatch\fP and \fIpmatch\fP arguments are ignored, and no captured strings +are returned. +.sp + REG_UTF8 +.sp +The PCRE_UTF8 option is set when the regular expression is passed for +compilation to the native function. This causes the pattern itself and all data +strings used for matching it to be treated as UTF-8 strings. Note that REG_UTF8 +is not part of the POSIX standard. +.P +In the absence of these flags, no options are passed to the native function. +This means the the regex is compiled with PCRE default semantics. In +particular, the way it handles newline characters in the subject string is the +Perl way, not the POSIX way. Note that setting PCRE_MULTILINE has only +\fIsome\fP of the effects specified for REG_NEWLINE. It does not affect the way +newlines are matched by . (they aren't) or by a negative class such as [^a] +(they are). +.P +The yield of \fBregcomp()\fP is zero on success, and non-zero otherwise. The +\fIpreg\fP structure is filled in on success, and one member of the structure +is public: \fIre_nsub\fP contains the number of capturing subpatterns in +the regular expression. Various error codes are defined in the header file. +. +. +.SH "MATCHING NEWLINE CHARACTERS" +.rs +.sp +This area is not simple, because POSIX and Perl take different views of things. +It is not possible to get PCRE to obey POSIX semantics, but then PCRE was never +intended to be a POSIX engine. The following table lists the different +possibilities for matching newline characters in PCRE: +.sp + Default Change with +.sp + . matches newline no PCRE_DOTALL + newline matches [^a] yes not changeable + $ matches \en at end yes PCRE_DOLLARENDONLY + $ matches \en in middle no PCRE_MULTILINE + ^ matches \en in middle no PCRE_MULTILINE +.sp +This is the equivalent table for POSIX: +.sp + Default Change with +.sp + . matches newline yes REG_NEWLINE + newline matches [^a] yes REG_NEWLINE + $ matches \en at end no REG_NEWLINE + $ matches \en in middle no REG_NEWLINE + ^ matches \en in middle no REG_NEWLINE +.sp +PCRE's behaviour is the same as Perl's, except that there is no equivalent for +PCRE_DOLLAR_ENDONLY in Perl. In both PCRE and Perl, there is no way to stop +newline from matching [^a]. +.P +The default POSIX newline handling can be obtained by setting PCRE_DOTALL and +PCRE_DOLLAR_ENDONLY, but there is no way to make PCRE behave exactly as for the +REG_NEWLINE action. +. +. +.SH "MATCHING A PATTERN" +.rs +.sp +The function \fBregexec()\fP is called to match a compiled pattern \fIpreg\fP +against a given \fIstring\fP, which is terminated by a zero byte, subject to +the options in \fIeflags\fP. These can be: +.sp + REG_NOTBOL +.sp +The PCRE_NOTBOL option is set when calling the underlying PCRE matching +function. +.sp + REG_NOTEOL +.sp +The PCRE_NOTEOL option is set when calling the underlying PCRE matching +function. +.P +If the pattern was compiled with the REG_NOSUB flag, no data about any matched +strings is returned. The \fInmatch\fP and \fIpmatch\fP arguments of +\fBregexec()\fP are ignored. +.P +Otherwise,the portion of the string that was matched, and also any captured +substrings, are returned via the \fIpmatch\fP argument, which points to an +array of \fInmatch\fP structures of type \fIregmatch_t\fP, containing the +members \fIrm_so\fP and \fIrm_eo\fP. These contain the offset to the first +character of each substring and the offset to the first character after the end +of each substring, respectively. The 0th element of the vector relates to the +entire portion of \fIstring\fP that was matched; subsequent elements relate to +the capturing subpatterns of the regular expression. Unused entries in the +array have both structure members set to -1. +.P +A successful match yields a zero return; various error codes are defined in the +header file, of which REG_NOMATCH is the "expected" failure code. +. +. +.SH "ERROR MESSAGES" +.rs +.sp +The \fBregerror()\fP function maps a non-zero errorcode from either +\fBregcomp()\fP or \fBregexec()\fP to a printable message. If \fIpreg\fP is not +NULL, the error should have arisen from the use of that structure. A message +terminated by a binary zero is placed in \fIerrbuf\fP. The length of the +message, including the zero, is limited to \fIerrbuf_size\fP. The yield of the +function is the size of buffer needed to hold the whole message. +. +. +.SH MEMORY USAGE +.rs +.sp +Compiling a regular expression causes memory to be allocated and associated +with the \fIpreg\fP structure. The function \fBregfree()\fP frees all such +memory, after which \fIpreg\fP may no longer be used as a compiled expression. +. +. +.SH AUTHOR +.rs +.sp +Philip Hazel +.br +University Computing Service, +.br +Cambridge CB2 3QG, England. +.P +.in 0 +Last updated: 16 January 2006 +.br +Copyright (c) 1997-2006 University of Cambridge. diff --git a/libs/pcre/doc/pcreprecompile.3 b/libs/pcre/doc/pcreprecompile.3 new file mode 100644 index 0000000000..556fa7fed3 --- /dev/null +++ b/libs/pcre/doc/pcreprecompile.3 @@ -0,0 +1,131 @@ +.TH PCREPRECOMPILE 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "SAVING AND RE-USING PRECOMPILED PCRE PATTERNS" +.rs +.sp +If you are running an application that uses a large number of regular +expression patterns, it may be useful to store them in a precompiled form +instead of having to compile them every time the application is run. +If you are not using any private character tables (see the +.\" HREF +\fBpcre_maketables()\fP +.\" +documentation), this is relatively straightforward. If you are using private +tables, it is a little bit more complicated. +.P +If you save compiled patterns to a file, you can copy them to a different host +and run them there. This works even if the new host has the opposite endianness +to the one on which the patterns were compiled. There may be a small +performance penalty, but it should be insignificant. +. +. +.SH "SAVING A COMPILED PATTERN" +.rs +.sh +The value returned by \fBpcre_compile()\fP points to a single block of memory +that holds the compiled pattern and associated data. You can find the length of +this block in bytes by calling \fBpcre_fullinfo()\fP with an argument of +PCRE_INFO_SIZE. You can then save the data in any appropriate manner. Here is +sample code that compiles a pattern and writes it to a file. It assumes that +the variable \fIfd\fP refers to a file that is open for output: +.sp + int erroroffset, rc, size; + char *error; + pcre *re; +.sp + re = pcre_compile("my pattern", 0, &error, &erroroffset, NULL); + if (re == NULL) { ... handle errors ... } + rc = pcre_fullinfo(re, NULL, PCRE_INFO_SIZE, &size); + if (rc < 0) { ... handle errors ... } + rc = fwrite(re, 1, size, fd); + if (rc != size) { ... handle errors ... } +.sp +In this example, the bytes that comprise the compiled pattern are copied +exactly. Note that this is binary data that may contain any of the 256 possible +byte values. On systems that make a distinction between binary and non-binary +data, be sure that the file is opened for binary output. +.P +If you want to write more than one pattern to a file, you will have to devise a +way of separating them. For binary data, preceding each pattern with its length +is probably the most straightforward approach. Another possibility is to write +out the data in hexadecimal instead of binary, one pattern to a line. +.P +Saving compiled patterns in a file is only one possible way of storing them for +later use. They could equally well be saved in a database, or in the memory of +some daemon process that passes them via sockets to the processes that want +them. +.P +If the pattern has been studied, it is also possible to save the study data in +a similar way to the compiled pattern itself. When studying generates +additional information, \fBpcre_study()\fP returns a pointer to a +\fBpcre_extra\fP data block. Its format is defined in the +.\" HTML +.\" +section on matching a pattern +.\" +in the +.\" HREF +\fBpcreapi\fP +.\" +documentation. The \fIstudy_data\fP field points to the binary study data, and +this is what you must save (not the \fBpcre_extra\fP block itself). The length +of the study data can be obtained by calling \fBpcre_fullinfo()\fP with an +argument of PCRE_INFO_STUDYSIZE. Remember to check that \fBpcre_study()\fP did +return a non-NULL value before trying to save the study data. +. +. +.SH "RE-USING A PRECOMPILED PATTERN" +.rs +.sp +Re-using a precompiled pattern is straightforward. Having reloaded it into main +memory, you pass its pointer to \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP in +the usual way. This should work even on another host, and even if that host has +the opposite endianness to the one where the pattern was compiled. +.P +However, if you passed a pointer to custom character tables when the pattern +was compiled (the \fItableptr\fP argument of \fBpcre_compile()\fP), you must +now pass a similar pointer to \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP, +because the value saved with the compiled pattern will obviously be nonsense. A +field in a \fBpcre_extra()\fP block is used to pass this data, as described in +the +.\" HTML +.\" +section on matching a pattern +.\" +in the +.\" HREF +\fBpcreapi\fP +.\" +documentation. +.P +If you did not provide custom character tables when the pattern was compiled, +the pointer in the compiled pattern is NULL, which causes \fBpcre_exec()\fP to +use PCRE's internal tables. Thus, you do not need to take any special action at +run time in this case. +.P +If you saved study data with the compiled pattern, you need to create your own +\fBpcre_extra\fP data block and set the \fIstudy_data\fP field to point to the +reloaded study data. You must also set the PCRE_EXTRA_STUDY_DATA bit in the +\fIflags\fP field to indicate that study data is present. Then pass the +\fBpcre_extra\fP block to \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP in the +usual way. +. +. +.SH "COMPATIBILITY WITH DIFFERENT PCRE RELEASES" +.rs +.sp +The layout of the control block that is at the start of the data that makes up +a compiled pattern was changed for release 5.0. If you have any saved patterns +that were compiled with previous releases (not a facility that was previously +advertised), you will have to recompile them for release 5.0. However, from now +on, it should be possible to make changes in a compatible manner. +.P +Notwithstanding the above, if you have any saved patterns in UTF-8 mode that +use \ep or \eP that were compiled with any release up to and including 6.4, you +will have to recompile them for release 6.5 and above. +.P +.in 0 +Last updated: 01 February 2006 +.br +Copyright (c) 1997-2006 University of Cambridge. diff --git a/libs/pcre/doc/pcresample.3 b/libs/pcre/doc/pcresample.3 new file mode 100644 index 0000000000..7f82979697 --- /dev/null +++ b/libs/pcre/doc/pcresample.3 @@ -0,0 +1,66 @@ +.TH PCRESAMPLE 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "PCRE SAMPLE PROGRAM" +.rs +.sp +A simple, complete demonstration program, to get you started with using PCRE, +is supplied in the file \fIpcredemo.c\fP in the PCRE distribution. +.P +The program compiles the regular expression that is its first argument, and +matches it against the subject string in its second argument. No PCRE options +are set, and default character tables are used. If matching succeeds, the +program outputs the portion of the subject that matched, together with the +contents of any captured substrings. +.P +If the -g option is given on the command line, the program then goes on to +check for further matches of the same regular expression in the same subject +string. The logic is a little bit tricky because of the possibility of matching +an empty string. Comments in the code explain what is going on. +.P +If PCRE is installed in the standard include and library directories for your +system, you should be able to compile the demonstration program using this +command: +.sp + gcc -o pcredemo pcredemo.c -lpcre +.sp +If PCRE is installed elsewhere, you may need to add additional options to the +command line. For example, on a Unix-like system that has PCRE installed in +\fI/usr/local\fP, you can compile the demonstration program using a command +like this: +.sp +.\" JOINSH + gcc -o pcredemo -I/usr/local/include pcredemo.c \e + -L/usr/local/lib -lpcre +.sp +Once you have compiled the demonstration program, you can run simple tests like +this: +.sp + ./pcredemo 'cat|dog' 'the cat sat on the mat' + ./pcredemo -g 'cat|dog' 'the dog sat on the cat' +.sp +Note that there is a much more comprehensive test program, called +.\" HREF +\fBpcretest\fP, +.\" +which supports many more facilities for testing regular expressions and the +PCRE library. The \fBpcredemo\fP program is provided as a simple coding +example. +.P +On some operating systems (e.g. Solaris), when PCRE is not installed in the +standard library directory, you may get an error like this when you try to run +\fBpcredemo\fP: +.sp + ld.so.1: a.out: fatal: libpcre.so.0: open failed: No such file or directory +.sp +This is caused by the way shared library support works on those systems. You +need to add +.sp + -R/usr/local/lib +.sp +(for example) to the compile command to get round this problem. +.P +.in 0 +Last updated: 09 September 2004 +.br +Copyright (c) 1997-2004 University of Cambridge. diff --git a/libs/pcre/doc/pcrestack.3 b/libs/pcre/doc/pcrestack.3 new file mode 100644 index 0000000000..76855733e2 --- /dev/null +++ b/libs/pcre/doc/pcrestack.3 @@ -0,0 +1,115 @@ +.TH PCRESTACK 3 +.SH NAME +PCRE - Perl-compatible regular expressions +.SH "PCRE DISCUSSION OF STACK USAGE" +.rs +.sp +When you call \fBpcre_exec()\fP, it makes use of an internal function called +\fBmatch()\fP. This calls itself recursively at branch points in the pattern, +in order to remember the state of the match so that it can back up and try a +different alternative if the first one fails. As matching proceeds deeper and +deeper into the tree of possibilities, the recursion depth increases. +.P +Not all calls of \fBmatch()\fP increase the recursion depth; for an item such +as a* it may be called several times at the same level, after matching +different numbers of a's. Furthermore, in a number of cases where the result of +the recursive call would immediately be passed back as the result of the +current call (a "tail recursion"), the function is just restarted instead. +.P +The \fBpcre_dfa_exec()\fP function operates in an entirely different way, and +hardly uses recursion at all. The limit on its complexity is the amount of +workspace it is given. The comments that follow do NOT apply to +\fBpcre_dfa_exec()\fP; they are relevant only for \fBpcre_exec()\fP. +.P +You can set limits on the number of times that \fBmatch()\fP is called, both in +total and recursively. If the limit is exceeded, an error occurs. For details, +see the +.\" HTML +.\" +section on extra data for \fBpcre_exec()\fP +.\" +in the +.\" HREF +\fBpcreapi\fP +.\" +documentation. +.P +Each time that \fBmatch()\fP is actually called recursively, it uses memory +from the process stack. For certain kinds of pattern and data, very large +amounts of stack may be needed, despite the recognition of "tail recursion". +You can often reduce the amount of recursion, and therefore the amount of stack +used, by modifying the pattern that is being matched. Consider, for example, +this pattern: +.sp + ([^<]|<(?!inet))+ +.sp +It matches from wherever it starts until it encounters "" to prompt for regular +expressions, and "data>" to prompt for data lines. +.P +The program handles any number of sets of input on a single input file. Each +set starts with a regular expression, and continues with any number of data +lines to be matched against the pattern. +.P +Each data line is matched separately and independently. If you want to do +multi-line matches, you have to use the \en escape sequence (or \er or \er\en, +depending on the newline setting) in a single line of input to encode the +newline characters. There is no limit on the length of data lines; the input +buffer is automatically extended if it is too small. +.P +An empty line signals the end of the data lines, at which point a new regular +expression is read. The regular expressions are given enclosed in any +non-alphanumeric delimiters other than backslash, for example: +.sp + /(a|bc)x+yz/ +.sp +White space before the initial delimiter is ignored. A regular expression may +be continued over several input lines, in which case the newline characters are +included within it. It is possible to include the delimiter within the pattern +by escaping it, for example +.sp + /abc\e/def/ +.sp +If you do so, the escape and the delimiter form part of the pattern, but since +delimiters are always non-alphanumeric, this does not affect its interpretation. +If the terminating delimiter is immediately followed by a backslash, for +example, +.sp + /abc/\e +.sp +then a backslash is added to the end of the pattern. This is done to provide a +way of testing the error condition that arises if a pattern finishes with a +backslash, because +.sp + /abc\e/ +.sp +is interpreted as the first line of a pattern that starts with "abc/", causing +pcretest to read the next line as a continuation of the regular expression. +. +. +.SH "PATTERN MODIFIERS" +.rs +.sp +A pattern may be followed by any number of modifiers, which are mostly single +characters. Following Perl usage, these are referred to below as, for example, +"the \fB/i\fP modifier", even though the delimiter of the pattern need not +always be a slash, and no slash is used when writing modifiers. Whitespace may +appear between the final pattern delimiter and the first modifier, and between +the modifiers themselves. +.P +The \fB/i\fP, \fB/m\fP, \fB/s\fP, and \fB/x\fP modifiers set the PCRE_CASELESS, +PCRE_MULTILINE, PCRE_DOTALL, or PCRE_EXTENDED options, respectively, when +\fBpcre_compile()\fP is called. These four modifier letters have the same +effect as they do in Perl. For example: +.sp + /caseless/i +.sp +The following table shows additional modifiers for setting PCRE options that do +not correspond to anything in Perl: +.sp + \fB/A\fP PCRE_ANCHORED + \fB/C\fP PCRE_AUTO_CALLOUT + \fB/E\fP PCRE_DOLLAR_ENDONLY + \fB/f\fP PCRE_FIRSTLINE + \fB/J\fP PCRE_DUPNAMES + \fB/N\fP PCRE_NO_AUTO_CAPTURE + \fB/U\fP PCRE_UNGREEDY + \fB/X\fP PCRE_EXTRA + \fB/\fP PCRE_NEWLINE_CR + \fB/\fP PCRE_NEWLINE_LF + \fB/\fP PCRE_NEWLINE_CRLF +.sp +Those specifying line endings are literal strings as shown. Details of the +meanings of these PCRE options are given in the +.\" HREF +\fBpcreapi\fP +.\" +documentation. +. +. +.SS "Finding all matches in a string" +.rs +.sp +Searching for all possible matches within each subject string can be requested +by the \fB/g\fP or \fB/G\fP modifier. After finding a match, PCRE is called +again to search the remainder of the subject string. The difference between +\fB/g\fP and \fB/G\fP is that the former uses the \fIstartoffset\fP argument to +\fBpcre_exec()\fP to start searching at a new point within the entire string +(which is in effect what Perl does), whereas the latter passes over a shortened +substring. This makes a difference to the matching process if the pattern +begins with a lookbehind assertion (including \eb or \eB). +.P +If any call to \fBpcre_exec()\fP in a \fB/g\fP or \fB/G\fP sequence matches an +empty string, the next call is done with the PCRE_NOTEMPTY and PCRE_ANCHORED +flags set in order to search for another, non-empty, match at the same point. +If this second match fails, the start offset is advanced by one, and the normal +match is retried. This imitates the way Perl handles such cases when using the +\fB/g\fP modifier or the \fBsplit()\fP function. +. +. +.SS "Other modifiers" +.rs +.sp +There are yet more modifiers for controlling the way \fBpcretest\fP +operates. +.P +The \fB/+\fP modifier requests that as well as outputting the substring that +matched the entire pattern, pcretest should in addition output the remainder of +the subject string. This is useful for tests where the subject contains +multiple copies of the same substring. +.P +The \fB/L\fP modifier must be followed directly by the name of a locale, for +example, +.sp + /pattern/Lfr_FR +.sp +For this reason, it must be the last modifier. The given locale is set, +\fBpcre_maketables()\fP is called to build a set of character tables for the +locale, and this is then passed to \fBpcre_compile()\fP when compiling the +regular expression. Without an \fB/L\fP modifier, NULL is passed as the tables +pointer; that is, \fB/L\fP applies only to the expression on which it appears. +.P +The \fB/I\fP modifier requests that \fBpcretest\fP output information about the +compiled pattern (whether it is anchored, has a fixed first character, and +so on). It does this by calling \fBpcre_fullinfo()\fP after compiling a +pattern. If the pattern is studied, the results of that are also output. +.P +The \fB/D\fP modifier is a PCRE debugging feature, which also assumes \fB/I\fP. +It causes the internal form of compiled regular expressions to be output after +compilation. If the pattern was studied, the information returned is also +output. +.P +The \fB/F\fP modifier causes \fBpcretest\fP to flip the byte order of the +fields in the compiled pattern that contain 2-byte and 4-byte numbers. This +facility is for testing the feature in PCRE that allows it to execute patterns +that were compiled on a host with a different endianness. This feature is not +available when the POSIX interface to PCRE is being used, that is, when the +\fB/P\fP pattern modifier is specified. See also the section about saving and +reloading compiled patterns below. +.P +The \fB/S\fP modifier causes \fBpcre_study()\fP to be called after the +expression has been compiled, and the results used when the expression is +matched. +.P +The \fB/M\fP modifier causes the size of memory block used to hold the compiled +pattern to be output. +.P +The \fB/P\fP modifier causes \fBpcretest\fP to call PCRE via the POSIX wrapper +API rather than its native API. When this is done, all other modifiers except +\fB/i\fP, \fB/m\fP, and \fB/+\fP are ignored. REG_ICASE is set if \fB/i\fP is +present, and REG_NEWLINE is set if \fB/m\fP is present. The wrapper functions +force PCRE_DOLLAR_ENDONLY always, and PCRE_DOTALL unless REG_NEWLINE is set. +.P +The \fB/8\fP modifier causes \fBpcretest\fP to call PCRE with the PCRE_UTF8 +option set. This turns on support for UTF-8 character handling in PCRE, +provided that it was compiled with this support enabled. This modifier also +causes any non-printing characters in output strings to be printed using the +\ex{hh...} notation if they are valid UTF-8 sequences. +.P +If the \fB/?\fP modifier is used with \fB/8\fP, it causes \fBpcretest\fP to +call \fBpcre_compile()\fP with the PCRE_NO_UTF8_CHECK option, to suppress the +checking of the string for UTF-8 validity. +. +. +.SH "DATA LINES" +.rs +.sp +Before each data line is passed to \fBpcre_exec()\fP, leading and trailing +whitespace is removed, and it is then scanned for \e escapes. Some of these are +pretty esoteric features, intended for checking out some of the more +complicated features of PCRE. If you are just testing "ordinary" regular +expressions, you probably don't need any of these. The following escapes are +recognized: +.sp + \ea alarm (= BEL) + \eb backspace + \ee escape + \ef formfeed + \en newline +.\" JOIN + \eqdd set the PCRE_MATCH_LIMIT limit to dd + (any number of digits) + \er carriage return + \et tab + \ev vertical tab + \ennn octal character (up to 3 octal digits) + \exhh hexadecimal character (up to 2 hex digits) +.\" JOIN + \ex{hh...} hexadecimal character, any number of digits + in UTF-8 mode +.\" JOIN + \eA pass the PCRE_ANCHORED option to \fBpcre_exec()\fP + or \fBpcre_dfa_exec()\fP +.\" JOIN + \eB pass the PCRE_NOTBOL option to \fBpcre_exec()\fP + or \fBpcre_dfa_exec()\fP +.\" JOIN + \eCdd call pcre_copy_substring() for substring dd + after a successful match (number less than 32) +.\" JOIN + \eCname call pcre_copy_named_substring() for substring + "name" after a successful match (name termin- + ated by next non alphanumeric character) +.\" JOIN + \eC+ show the current captured substrings at callout + time + \eC- do not supply a callout function +.\" JOIN + \eC!n return 1 instead of 0 when callout number n is + reached +.\" JOIN + \eC!n!m return 1 instead of 0 when callout number n is + reached for the nth time +.\" JOIN + \eC*n pass the number n (may be negative) as callout + data; this is used as the callout return value + \eD use the \fBpcre_dfa_exec()\fP match function + \eF only shortest match for \fBpcre_dfa_exec()\fP +.\" JOIN + \eGdd call pcre_get_substring() for substring dd + after a successful match (number less than 32) +.\" JOIN + \eGname call pcre_get_named_substring() for substring + "name" after a successful match (name termin- + ated by next non-alphanumeric character) +.\" JOIN + \eL call pcre_get_substringlist() after a + successful match +.\" JOIN + \eM discover the minimum MATCH_LIMIT and + MATCH_LIMIT_RECURSION settings +.\" JOIN + \eN pass the PCRE_NOTEMPTY option to \fBpcre_exec()\fP + or \fBpcre_dfa_exec()\fP +.\" JOIN + \eOdd set the size of the output vector passed to + \fBpcre_exec()\fP to dd (any number of digits) +.\" JOIN + \eP pass the PCRE_PARTIAL option to \fBpcre_exec()\fP + or \fBpcre_dfa_exec()\fP +.\" JOIN + \eQdd set the PCRE_MATCH_LIMIT_RECURSION limit to dd + (any number of digits) + \eR pass the PCRE_DFA_RESTART option to \fBpcre_dfa_exec()\fP + \eS output details of memory get/free calls during matching +.\" JOIN + \eZ pass the PCRE_NOTEOL option to \fBpcre_exec()\fP + or \fBpcre_dfa_exec()\fP +.\" JOIN + \e? pass the PCRE_NO_UTF8_CHECK option to + \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP + \e>dd start the match at offset dd (any number of digits); +.\" JOIN + this sets the \fIstartoffset\fP argument for \fBpcre_exec()\fP + or \fBpcre_dfa_exec()\fP +.\" JOIN + \e pass the PCRE_NEWLINE_CR option to \fBpcre_exec()\fP + or \fBpcre_dfa_exec()\fP +.\" JOIN + \e pass the PCRE_NEWLINE_LF option to \fBpcre_exec()\fP + or \fBpcre_dfa_exec()\fP +.\" JOIN + \e pass the PCRE_NEWLINE_CRLF option to \fBpcre_exec()\fP + or \fBpcre_dfa_exec()\fP +.sp +The escapes that specify line endings are literal strings, exactly as shown. +A backslash followed by anything else just escapes the anything else. If the +very last character is a backslash, it is ignored. This gives a way of passing +an empty line as data, since a real empty line terminates the data input. +.P +If \eM is present, \fBpcretest\fP calls \fBpcre_exec()\fP several times, with +different values in the \fImatch_limit\fP and \fImatch_limit_recursion\fP +fields of the \fBpcre_extra\fP data structure, until it finds the minimum +numbers for each parameter that allow \fBpcre_exec()\fP to complete. The +\fImatch_limit\fP number is a measure of the amount of backtracking that takes +place, and checking it out can be instructive. For most simple matches, the +number is quite small, but for patterns with very large numbers of matching +possibilities, it can become large very quickly with increasing length of +subject string. The \fImatch_limit_recursion\fP number is a measure of how much +stack (or, if PCRE is compiled with NO_RECURSE, how much heap) memory is needed +to complete the match attempt. +.P +When \eO is used, the value specified may be higher or lower than the size set +by the \fB-O\fP command line option (or defaulted to 45); \eO applies only to +the call of \fBpcre_exec()\fP for the line in which it appears. +.P +If the \fB/P\fP modifier was present on the pattern, causing the POSIX wrapper +API to be used, the only option-setting sequences that have any effect are \eB +and \eZ, causing REG_NOTBOL and REG_NOTEOL, respectively, to be passed to +\fBregexec()\fP. +.P +The use of \ex{hh...} to represent UTF-8 characters is not dependent on the use +of the \fB/8\fP modifier on the pattern. It is recognized always. There may be +any number of hexadecimal digits inside the braces. The result is from one to +six bytes, encoded according to the UTF-8 rules. +. +. +.SH "THE ALTERNATIVE MATCHING FUNCTION" +.rs +.sp +By default, \fBpcretest\fP uses the standard PCRE matching function, +\fBpcre_exec()\fP to match each data line. From release 6.0, PCRE supports an +alternative matching function, \fBpcre_dfa_test()\fP, which operates in a +different way, and has some restrictions. The differences between the two +functions are described in the +.\" HREF +\fBpcrematching\fP +.\" +documentation. +.P +If a data line contains the \eD escape sequence, or if the command line +contains the \fB-dfa\fP option, the alternative matching function is called. +This function finds all possible matches at a given point. If, however, the \eF +escape sequence is present in the data line, it stops after the first match is +found. This is always the shortest possible match. +. +. +.SH "DEFAULT OUTPUT FROM PCRETEST" +.rs +.sp +This section describes the output when the normal matching function, +\fBpcre_exec()\fP, is being used. +.P +When a match succeeds, pcretest outputs the list of captured substrings that +\fBpcre_exec()\fP returns, starting with number 0 for the string that matched +the whole pattern. Otherwise, it outputs "No match" or "Partial match" +when \fBpcre_exec()\fP returns PCRE_ERROR_NOMATCH or PCRE_ERROR_PARTIAL, +respectively, and otherwise the PCRE negative error number. Here is an example +of an interactive \fBpcretest\fP run. +.sp + $ pcretest + PCRE version 5.00 07-Sep-2004 +.sp + re> /^abc(\ed+)/ + data> abc123 + 0: abc123 + 1: 123 + data> xyz + No match +.sp +If the strings contain any non-printing characters, they are output as \e0x +escapes, or as \ex{...} escapes if the \fB/8\fP modifier was present on the +pattern. If the pattern has the \fB/+\fP modifier, the output for substring 0 +is followed by the the rest of the subject string, identified by "0+" like +this: +.sp + re> /cat/+ + data> cataract + 0: cat + 0+ aract +.sp +If the pattern has the \fB/g\fP or \fB/G\fP modifier, the results of successive +matching attempts are output in sequence, like this: +.sp + re> /\eBi(\ew\ew)/g + data> Mississippi + 0: iss + 1: ss + 0: iss + 1: ss + 0: ipp + 1: pp +.sp +"No match" is output only if the first match attempt fails. +.P +If any of the sequences \fB\eC\fP, \fB\eG\fP, or \fB\eL\fP are present in a +data line that is successfully matched, the substrings extracted by the +convenience functions are output with C, G, or L after the string number +instead of a colon. This is in addition to the normal full list. The string +length (that is, the return from the extraction function) is given in +parentheses after each string for \fB\eC\fP and \fB\eG\fP. +.P +Note that while patterns can be continued over several lines (a plain ">" +prompt is used for continuations), data lines may not. However newlines can be +included in data by means of the \en escape (or \er or \er\en for those newline +settings). +. +. +.SH "OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION" +.rs +.sp +When the alternative matching function, \fBpcre_dfa_exec()\fP, is used (by +means of the \eD escape sequence or the \fB-dfa\fP command line option), the +output consists of a list of all the matches that start at the first point in +the subject where there is at least one match. For example: +.sp + re> /(tang|tangerine|tan)/ + data> yellow tangerine\eD + 0: tangerine + 1: tang + 2: tan +.sp +(Using the normal matching function on this data finds only "tang".) The +longest matching string is always given first (and numbered zero). +.P +If \fB/g\P is present on the pattern, the search for further matches resumes +at the end of the longest match. For example: +.sp + re> /(tang|tangerine|tan)/g + data> yellow tangerine and tangy sultana\eD + 0: tangerine + 1: tang + 2: tan + 0: tang + 1: tan + 0: tan +.sp +Since the matching function does not support substring capture, the escape +sequences that are concerned with captured substrings are not relevant. +. +. +.SH "RESTARTING AFTER A PARTIAL MATCH" +.rs +.sp +When the alternative matching function has given the PCRE_ERROR_PARTIAL return, +indicating that the subject partially matched the pattern, you can restart the +match with additional subject data by means of the \eR escape sequence. For +example: +.sp + re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/ + data> 23ja\eP\eD + Partial match: 23ja + data> n05\eR\eD + 0: n05 +.sp +For further information about partial matching, see the +.\" HREF +\fBpcrepartial\fP +.\" +documentation. +. +. +.SH CALLOUTS +.rs +.sp +If the pattern contains any callout requests, \fBpcretest\fP's callout function +is called during matching. This works with both matching functions. By default, +the called function displays the callout number, the start and current +positions in the text at the callout time, and the next pattern item to be +tested. For example, the output +.sp + --->pqrabcdef + 0 ^ ^ \ed +.sp +indicates that callout number 0 occurred for a match attempt starting at the +fourth character of the subject string, when the pointer was at the seventh +character of the data, and when the next pattern item was \ed. Just one +circumflex is output if the start and current positions are the same. +.P +Callouts numbered 255 are assumed to be automatic callouts, inserted as a +result of the \fB/C\fP pattern modifier. In this case, instead of showing the +callout number, the offset in the pattern, preceded by a plus, is output. For +example: +.sp + re> /\ed?[A-E]\e*/C + data> E* + --->E* + +0 ^ \ed? + +3 ^ [A-E] + +8 ^^ \e* + +10 ^ ^ + 0: E* +.sp +The callout function in \fBpcretest\fP returns zero (carry on matching) by +default, but you can use a \eC item in a data line (as described above) to +change this. +.P +Inserting callouts can be helpful when using \fBpcretest\fP to check +complicated regular expressions. For further information about callouts, see +the +.\" HREF +\fBpcrecallout\fP +.\" +documentation. +. +. +.SH "SAVING AND RELOADING COMPILED PATTERNS" +.rs +.sp +The facilities described in this section are not available when the POSIX +inteface to PCRE is being used, that is, when the \fB/P\fP pattern modifier is +specified. +.P +When the POSIX interface is not in use, you can cause \fBpcretest\fP to write a +compiled pattern to a file, by following the modifiers with > and a file name. +For example: +.sp + /pattern/im >/some/file +.sp +See the +.\" HREF +\fBpcreprecompile\fP +.\" +documentation for a discussion about saving and re-using compiled patterns. +.P +The data that is written is binary. The first eight bytes are the length of the +compiled pattern data followed by the length of the optional study data, each +written as four bytes in big-endian order (most significant byte first). If +there is no study data (either the pattern was not studied, or studying did not +return any data), the second length is zero. The lengths are followed by an +exact copy of the compiled pattern. If there is additional study data, this +follows immediately after the compiled pattern. After writing the file, +\fBpcretest\fP expects to read a new pattern. +.P +A saved pattern can be reloaded into \fBpcretest\fP by specifing < and a file +name instead of a pattern. The name of the file must not contain a < character, +as otherwise \fBpcretest\fP will interpret the line as a pattern delimited by < +characters. +For example: +.sp + re> " to prompt for regular expressions, and "data>" to prompt for data + lines. + + The program handles any number of sets of input on a single input file. + Each set starts with a regular expression, and continues with any num- + ber of data lines to be matched against the pattern. + + Each data line is matched separately and independently. If you want to + do multi-line matches, you have to use the \n escape sequence (or \r or + \r\n, depending on the newline setting) in a single line of input to + encode the newline characters. There is no limit on the length of data + lines; the input buffer is automatically extended if it is too small. + + An empty line signals the end of the data lines, at which point a new + regular expression is read. The regular expressions are given enclosed + in any non-alphanumeric delimiters other than backslash, for example: + + /(a|bc)x+yz/ + + White space before the initial delimiter is ignored. A regular expres- + sion may be continued over several input lines, in which case the new- + line characters are included within it. It is possible to include the + delimiter within the pattern by escaping it, for example + + /abc\/def/ + + If you do so, the escape and the delimiter form part of the pattern, + but since delimiters are always non-alphanumeric, this does not affect + its interpretation. If the terminating delimiter is immediately fol- + lowed by a backslash, for example, + + /abc/\ + + then a backslash is added to the end of the pattern. This is done to + provide a way of testing the error condition that arises if a pattern + finishes with a backslash, because + + /abc\/ + + is interpreted as the first line of a pattern that starts with "abc/", + causing pcretest to read the next line as a continuation of the regular + expression. + + +PATTERN MODIFIERS + + A pattern may be followed by any number of modifiers, which are mostly + single characters. Following Perl usage, these are referred to below + as, for example, "the /i modifier", even though the delimiter of the + pattern need not always be a slash, and no slash is used when writing + modifiers. Whitespace may appear between the final pattern delimiter + and the first modifier, and between the modifiers themselves. + + The /i, /m, /s, and /x modifiers set the PCRE_CASELESS, PCRE_MULTILINE, + PCRE_DOTALL, or PCRE_EXTENDED options, respectively, when pcre_com- + pile() is called. These four modifier letters have the same effect as + they do in Perl. For example: + + /caseless/i + + The following table shows additional modifiers for setting PCRE options + that do not correspond to anything in Perl: + + /A PCRE_ANCHORED + /C PCRE_AUTO_CALLOUT + /E PCRE_DOLLAR_ENDONLY + /f PCRE_FIRSTLINE + /J PCRE_DUPNAMES + /N PCRE_NO_AUTO_CAPTURE + /U PCRE_UNGREEDY + /X PCRE_EXTRA + / PCRE_NEWLINE_CR + / PCRE_NEWLINE_LF + / PCRE_NEWLINE_CRLF + + Those specifying line endings are literal strings as shown. Details of + the meanings of these PCRE options are given in the pcreapi documenta- + tion. + + Finding all matches in a string + + Searching for all possible matches within each subject string can be + requested by the /g or /G modifier. After finding a match, PCRE is + called again to search the remainder of the subject string. The differ- + ence between /g and /G is that the former uses the startoffset argument + to pcre_exec() to start searching at a new point within the entire + string (which is in effect what Perl does), whereas the latter passes + over a shortened substring. This makes a difference to the matching + process if the pattern begins with a lookbehind assertion (including \b + or \B). + + If any call to pcre_exec() in a /g or /G sequence matches an empty + string, the next call is done with the PCRE_NOTEMPTY and PCRE_ANCHORED + flags set in order to search for another, non-empty, match at the same + point. If this second match fails, the start offset is advanced by + one, and the normal match is retried. This imitates the way Perl han- + dles such cases when using the /g modifier or the split() function. + + Other modifiers + + There are yet more modifiers for controlling the way pcretest operates. + + The /+ modifier requests that as well as outputting the substring that + matched the entire pattern, pcretest should in addition output the + remainder of the subject string. This is useful for tests where the + subject contains multiple copies of the same substring. + + The /L modifier must be followed directly by the name of a locale, for + example, + + /pattern/Lfr_FR + + For this reason, it must be the last modifier. The given locale is set, + pcre_maketables() is called to build a set of character tables for the + locale, and this is then passed to pcre_compile() when compiling the + regular expression. Without an /L modifier, NULL is passed as the + tables pointer; that is, /L applies only to the expression on which it + appears. + + The /I modifier requests that pcretest output information about the + compiled pattern (whether it is anchored, has a fixed first character, + and so on). It does this by calling pcre_fullinfo() after compiling a + pattern. If the pattern is studied, the results of that are also out- + put. + + The /D modifier is a PCRE debugging feature, which also assumes /I. It + causes the internal form of compiled regular expressions to be output + after compilation. If the pattern was studied, the information returned + is also output. + + The /F modifier causes pcretest to flip the byte order of the fields in + the compiled pattern that contain 2-byte and 4-byte numbers. This + facility is for testing the feature in PCRE that allows it to execute + patterns that were compiled on a host with a different endianness. This + feature is not available when the POSIX interface to PCRE is being + used, that is, when the /P pattern modifier is specified. See also the + section about saving and reloading compiled patterns below. + + The /S modifier causes pcre_study() to be called after the expression + has been compiled, and the results used when the expression is matched. + + The /M modifier causes the size of memory block used to hold the com- + piled pattern to be output. + + The /P modifier causes pcretest to call PCRE via the POSIX wrapper API + rather than its native API. When this is done, all other modifiers + except /i, /m, and /+ are ignored. REG_ICASE is set if /i is present, + and REG_NEWLINE is set if /m is present. The wrapper functions force + PCRE_DOLLAR_ENDONLY always, and PCRE_DOTALL unless REG_NEWLINE is set. + + The /8 modifier causes pcretest to call PCRE with the PCRE_UTF8 option + set. This turns on support for UTF-8 character handling in PCRE, pro- + vided that it was compiled with this support enabled. This modifier + also causes any non-printing characters in output strings to be printed + using the \x{hh...} notation if they are valid UTF-8 sequences. + + If the /? modifier is used with /8, it causes pcretest to call + pcre_compile() with the PCRE_NO_UTF8_CHECK option, to suppress the + checking of the string for UTF-8 validity. + + +DATA LINES + + Before each data line is passed to pcre_exec(), leading and trailing + whitespace is removed, and it is then scanned for \ escapes. Some of + these are pretty esoteric features, intended for checking out some of + the more complicated features of PCRE. If you are just testing "ordi- + nary" regular expressions, you probably don't need any of these. The + following escapes are recognized: + + \a alarm (= BEL) + \b backspace + \e escape + \f formfeed + \n newline + \qdd set the PCRE_MATCH_LIMIT limit to dd + (any number of digits) + \r carriage return + \t tab + \v vertical tab + \nnn octal character (up to 3 octal digits) + \xhh hexadecimal character (up to 2 hex digits) + \x{hh...} hexadecimal character, any number of digits + in UTF-8 mode + \A pass the PCRE_ANCHORED option to pcre_exec() + or pcre_dfa_exec() + \B pass the PCRE_NOTBOL option to pcre_exec() + or pcre_dfa_exec() + \Cdd call pcre_copy_substring() for substring dd + after a successful match (number less than 32) + \Cname call pcre_copy_named_substring() for substring + "name" after a successful match (name termin- + ated by next non alphanumeric character) + \C+ show the current captured substrings at callout + time + \C- do not supply a callout function + \C!n return 1 instead of 0 when callout number n is + reached + \C!n!m return 1 instead of 0 when callout number n is + reached for the nth time + \C*n pass the number n (may be negative) as callout + data; this is used as the callout return value + \D use the pcre_dfa_exec() match function + \F only shortest match for pcre_dfa_exec() + \Gdd call pcre_get_substring() for substring dd + after a successful match (number less than 32) + \Gname call pcre_get_named_substring() for substring + "name" after a successful match (name termin- + ated by next non-alphanumeric character) + \L call pcre_get_substringlist() after a + successful match + \M discover the minimum MATCH_LIMIT and + MATCH_LIMIT_RECURSION settings + \N pass the PCRE_NOTEMPTY option to pcre_exec() + or pcre_dfa_exec() + \Odd set the size of the output vector passed to + pcre_exec() to dd (any number of digits) + \P pass the PCRE_PARTIAL option to pcre_exec() + or pcre_dfa_exec() + \Qdd set the PCRE_MATCH_LIMIT_RECURSION limit to dd + (any number of digits) + \R pass the PCRE_DFA_RESTART option to pcre_dfa_exec() + \S output details of memory get/free calls during matching + \Z pass the PCRE_NOTEOL option to pcre_exec() + or pcre_dfa_exec() + \? pass the PCRE_NO_UTF8_CHECK option to + pcre_exec() or pcre_dfa_exec() + \>dd start the match at offset dd (any number of digits); + this sets the startoffset argument for pcre_exec() + or pcre_dfa_exec() + \ pass the PCRE_NEWLINE_CR option to pcre_exec() + or pcre_dfa_exec() + \ pass the PCRE_NEWLINE_LF option to pcre_exec() + or pcre_dfa_exec() + \ pass the PCRE_NEWLINE_CRLF option to pcre_exec() + or pcre_dfa_exec() + + The escapes that specify line endings are literal strings, exactly as + shown. A backslash followed by anything else just escapes the anything + else. If the very last character is a backslash, it is ignored. This + gives a way of passing an empty line as data, since a real empty line + terminates the data input. + + If \M is present, pcretest calls pcre_exec() several times, with dif- + ferent values in the match_limit and match_limit_recursion fields of + the pcre_extra data structure, until it finds the minimum numbers for + each parameter that allow pcre_exec() to complete. The match_limit num- + ber is a measure of the amount of backtracking that takes place, and + checking it out can be instructive. For most simple matches, the number + is quite small, but for patterns with very large numbers of matching + possibilities, it can become large very quickly with increasing length + of subject string. The match_limit_recursion number is a measure of how + much stack (or, if PCRE is compiled with NO_RECURSE, how much heap) + memory is needed to complete the match attempt. + + When \O is used, the value specified may be higher or lower than the + size set by the -O command line option (or defaulted to 45); \O applies + only to the call of pcre_exec() for the line in which it appears. + + If the /P modifier was present on the pattern, causing the POSIX wrap- + per API to be used, the only option-setting sequences that have any + effect are \B and \Z, causing REG_NOTBOL and REG_NOTEOL, respectively, + to be passed to regexec(). + + The use of \x{hh...} to represent UTF-8 characters is not dependent on + the use of the /8 modifier on the pattern. It is recognized always. + There may be any number of hexadecimal digits inside the braces. The + result is from one to six bytes, encoded according to the UTF-8 rules. + + +THE ALTERNATIVE MATCHING FUNCTION + + By default, pcretest uses the standard PCRE matching function, + pcre_exec() to match each data line. From release 6.0, PCRE supports an + alternative matching function, pcre_dfa_test(), which operates in a + different way, and has some restrictions. The differences between the + two functions are described in the pcrematching documentation. + + If a data line contains the \D escape sequence, or if the command line + contains the -dfa option, the alternative matching function is called. + This function finds all possible matches at a given point. If, however, + the \F escape sequence is present in the data line, it stops after the + first match is found. This is always the shortest possible match. + + +DEFAULT OUTPUT FROM PCRETEST + + This section describes the output when the normal matching function, + pcre_exec(), is being used. + + When a match succeeds, pcretest outputs the list of captured substrings + that pcre_exec() returns, starting with number 0 for the string that + matched the whole pattern. Otherwise, it outputs "No match" or "Partial + match" when pcre_exec() returns PCRE_ERROR_NOMATCH or PCRE_ERROR_PAR- + TIAL, respectively, and otherwise the PCRE negative error number. Here + is an example of an interactive pcretest run. + + $ pcretest + PCRE version 5.00 07-Sep-2004 + + re> /^abc(\d+)/ + data> abc123 + 0: abc123 + 1: 123 + data> xyz + No match + + If the strings contain any non-printing characters, they are output as + \0x escapes, or as \x{...} escapes if the /8 modifier was present on + the pattern. If the pattern has the /+ modifier, the output for sub- + string 0 is followed by the the rest of the subject string, identified + by "0+" like this: + + re> /cat/+ + data> cataract + 0: cat + 0+ aract + + If the pattern has the /g or /G modifier, the results of successive + matching attempts are output in sequence, like this: + + re> /\Bi(\w\w)/g + data> Mississippi + 0: iss + 1: ss + 0: iss + 1: ss + 0: ipp + 1: pp + + "No match" is output only if the first match attempt fails. + + If any of the sequences \C, \G, or \L are present in a data line that + is successfully matched, the substrings extracted by the convenience + functions are output with C, G, or L after the string number instead of + a colon. This is in addition to the normal full list. The string length + (that is, the return from the extraction function) is given in paren- + theses after each string for \C and \G. + + Note that while patterns can be continued over several lines (a plain + ">" prompt is used for continuations), data lines may not. However new- + lines can be included in data by means of the \n escape (or \r or \r\n + for those newline settings). + + +OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION + + When the alternative matching function, pcre_dfa_exec(), is used (by + means of the \D escape sequence or the -dfa command line option), the + output consists of a list of all the matches that start at the first + point in the subject where there is at least one match. For example: + + re> /(tang|tangerine|tan)/ + data> yellow tangerine\D + 0: tangerine + 1: tang + 2: tan + + (Using the normal matching function on this data finds only "tang".) + The longest matching string is always given first (and numbered zero). + + If /gP is present on the pattern, the search for further matches + resumes at the end of the longest match. For example: + + re> /(tang|tangerine|tan)/g + data> yellow tangerine and tangy sultana\D + 0: tangerine + 1: tang + 2: tan + 0: tang + 1: tan + 0: tan + + Since the matching function does not support substring capture, the + escape sequences that are concerned with captured substrings are not + relevant. + + +RESTARTING AFTER A PARTIAL MATCH + + When the alternative matching function has given the PCRE_ERROR_PARTIAL + return, indicating that the subject partially matched the pattern, you + can restart the match with additional subject data by means of the \R + escape sequence. For example: + + re> /^?(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)$/ + data> 23ja\P\D + Partial match: 23ja + data> n05\R\D + 0: n05 + + For further information about partial matching, see the pcrepartial + documentation. + + +CALLOUTS + + If the pattern contains any callout requests, pcretest's callout func- + tion is called during matching. This works with both matching func- + tions. By default, the called function displays the callout number, the + start and current positions in the text at the callout time, and the + next pattern item to be tested. For example, the output + + --->pqrabcdef + 0 ^ ^ \d + + indicates that callout number 0 occurred for a match attempt starting + at the fourth character of the subject string, when the pointer was at + the seventh character of the data, and when the next pattern item was + \d. Just one circumflex is output if the start and current positions + are the same. + + Callouts numbered 255 are assumed to be automatic callouts, inserted as + a result of the /C pattern modifier. In this case, instead of showing + the callout number, the offset in the pattern, preceded by a plus, is + output. For example: + + re> /\d?[A-E]\*/C + data> E* + --->E* + +0 ^ \d? + +3 ^ [A-E] + +8 ^^ \* + +10 ^ ^ + 0: E* + + The callout function in pcretest returns zero (carry on matching) by + default, but you can use a \C item in a data line (as described above) + to change this. + + Inserting callouts can be helpful when using pcretest to check compli- + cated regular expressions. For further information about callouts, see + the pcrecallout documentation. + + +SAVING AND RELOADING COMPILED PATTERNS + + The facilities described in this section are not available when the + POSIX inteface to PCRE is being used, that is, when the /P pattern mod- + ifier is specified. + + When the POSIX interface is not in use, you can cause pcretest to write + a compiled pattern to a file, by following the modifiers with > and a + file name. For example: + + /pattern/im >/some/file + + See the pcreprecompile documentation for a discussion about saving and + re-using compiled patterns. + + The data that is written is binary. The first eight bytes are the + length of the compiled pattern data followed by the length of the + optional study data, each written as four bytes in big-endian order + (most significant byte first). If there is no study data (either the + pattern was not studied, or studying did not return any data), the sec- + ond length is zero. The lengths are followed by an exact copy of the + compiled pattern. If there is additional study data, this follows imme- + diately after the compiled pattern. After writing the file, pcretest + expects to read a new pattern. + + A saved pattern can be reloaded into pcretest by specifing < and a file + name instead of a pattern. The name of the file must not contain a < + character, as otherwise pcretest will interpret the line as a pattern + delimited by < characters. For example: + + re> , 1996 +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, but +# WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +# General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. +# +# As a special exception to the GNU General Public License, if you +# distribute this file as part of a program that contains a +# configuration script generated by Autoconf, you may include it under +# the same distribution terms that you use for the rest of that program. + +basename="s,^.*/,,g" + +# Work around backward compatibility issue on IRIX 6.5. On IRIX 6.4+, sh +# is ksh but when the shell is invoked as "sh" and the current value of +# the _XPG environment variable is not equal to 1 (one), the special +# positional parameter $0, within a function call, is the name of the +# function. +progpath="$0" + +# define SED for historic ltconfig's generated by Libtool 1.3 +test -z "$SED" && SED=sed + +# The name of this program: +progname=`echo "$progpath" | $SED $basename` +modename="$progname" + +# Global variables: +EXIT_SUCCESS=0 +EXIT_FAILURE=1 + +PROGRAM=ltmain.sh +PACKAGE=libtool +VERSION=1.5.22 +TIMESTAMP=" (1.1220.2.365 2005/12/18 22:14:06)" + +# See if we are running on zsh, and set the options which allow our +# commands through without removal of \ escapes. +if test -n "${ZSH_VERSION+set}" ; then + setopt NO_GLOB_SUBST +fi +# Same for EGREP, and just to be sure, do LTCC as well +if test "X$EGREP" = X ; then + EGREP=egrep +fi +if test "X$LTCC" = X ; then + LTCC=${CC-gcc} +fi + +# Check that we have a working $echo. +if test "X$1" = X--no-reexec; then + # Discard the --no-reexec flag, and continue. + shift +elif test "X$1" = X--fallback-echo; then + # Avoid inline document here, it may be left over + : +elif test "X`($echo '\t') 2>/dev/null`" = 'X\t'; then + # Yippee, $echo works! + : +else + # Restart under the correct shell, and then maybe $echo will work. + exec $SHELL "$progpath" --no-reexec ${1+"$@"} +fi + +if test "X$1" = X--fallback-echo; then + # used as fallback echo + shift + cat <&2 + $echo "Fatal configuration error. See the $PACKAGE docs for more information." 1>&2 + exit $EXIT_FAILURE +fi + +# Global variables. +mode=$default_mode +nonopt= +prev= +prevopt= +run= +show="$echo" +show_help= +execute_dlfiles= +duplicate_deps=no +preserve_args= +lo2o="s/\\.lo\$/.${objext}/" +o2lo="s/\\.${objext}\$/.lo/" + +if test -z "$max_cmd_len"; then + i=0 + testring="ABCD" + new_result= + + # If test is not a shell built-in, we'll probably end up computing a + # maximum length that is only half of the actual maximum length, but + # we can't tell. + while (test "X"`$SHELL $0 --fallback-echo "X$testring" 2>/dev/null` \ + = "XX$testring") >/dev/null 2>&1 && + new_result=`expr "X$testring" : ".*" 2>&1` && + max_cmd_len="$new_result" && + test "$i" != 17 # 1/2 MB should be enough + do + i=`expr $i + 1` + testring="$testring$testring" + done + testring= + # Add a significant safety factor because C++ compilers can tack on massive + # amounts of additional arguments before passing them to the linker. + # It appears as though 1/2 is a usable value. + max_cmd_len=`expr $max_cmd_len \/ 2` +fi + +##################################### +# Shell function definitions: +# This seems to be the best place for them + +# func_mktempdir [string] +# Make a temporary directory that won't clash with other running +# libtool processes, and avoids race conditions if possible. If +# given, STRING is the basename for that directory. +func_mktempdir () +{ + my_template="${TMPDIR-/tmp}/${1-$progname}" + + if test "$run" = ":"; then + # Return a directory name, but don't create it in dry-run mode + my_tmpdir="${my_template}-$$" + else + + # If mktemp works, use that first and foremost + my_tmpdir=`mktemp -d "${my_template}-XXXXXXXX" 2>/dev/null` + + if test ! -d "$my_tmpdir"; then + # Failing that, at least try and use $RANDOM to avoid a race + my_tmpdir="${my_template}-${RANDOM-0}$$" + + save_mktempdir_umask=`umask` + umask 0077 + $mkdir "$my_tmpdir" + umask $save_mktempdir_umask + fi + + # If we're not in dry-run mode, bomb out on failure + test -d "$my_tmpdir" || { + $echo "cannot create temporary directory \`$my_tmpdir'" 1>&2 + exit $EXIT_FAILURE + } + fi + + $echo "X$my_tmpdir" | $Xsed +} + + +# func_win32_libid arg +# return the library type of file 'arg' +# +# Need a lot of goo to handle *both* DLLs and import libs +# Has to be a shell function in order to 'eat' the argument +# that is supplied when $file_magic_command is called. +func_win32_libid () +{ + win32_libid_type="unknown" + win32_fileres=`file -L $1 2>/dev/null` + case $win32_fileres in + *ar\ archive\ import\ library*) # definitely import + win32_libid_type="x86 archive import" + ;; + *ar\ archive*) # could be an import, or static + if eval $OBJDUMP -f $1 | $SED -e '10q' 2>/dev/null | \ + $EGREP -e 'file format pe-i386(.*architecture: i386)?' >/dev/null ; then + win32_nmres=`eval $NM -f posix -A $1 | \ + $SED -n -e '1,100{/ I /{s,.*,import,;p;q;};}'` + case $win32_nmres in + import*) win32_libid_type="x86 archive import";; + *) win32_libid_type="x86 archive static";; + esac + fi + ;; + *DLL*) + win32_libid_type="x86 DLL" + ;; + *executable*) # but shell scripts are "executable" too... + case $win32_fileres in + *MS\ Windows\ PE\ Intel*) + win32_libid_type="x86 DLL" + ;; + esac + ;; + esac + $echo $win32_libid_type +} + + +# func_infer_tag arg +# Infer tagged configuration to use if any are available and +# if one wasn't chosen via the "--tag" command line option. +# Only attempt this if the compiler in the base compile +# command doesn't match the default compiler. +# arg is usually of the form 'gcc ...' +func_infer_tag () +{ + if test -n "$available_tags" && test -z "$tagname"; then + CC_quoted= + for arg in $CC; do + case $arg in + *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") + arg="\"$arg\"" + ;; + esac + CC_quoted="$CC_quoted $arg" + done + case $@ in + # Blanks in the command may have been stripped by the calling shell, + # but not from the CC environment variable when configure was run. + " $CC "* | "$CC "* | " `$echo $CC` "* | "`$echo $CC` "* | " $CC_quoted"* | "$CC_quoted "* | " `$echo $CC_quoted` "* | "`$echo $CC_quoted` "*) ;; + # Blanks at the start of $base_compile will cause this to fail + # if we don't check for them as well. + *) + for z in $available_tags; do + if grep "^# ### BEGIN LIBTOOL TAG CONFIG: $z$" < "$progpath" > /dev/null; then + # Evaluate the configuration. + eval "`${SED} -n -e '/^# ### BEGIN LIBTOOL TAG CONFIG: '$z'$/,/^# ### END LIBTOOL TAG CONFIG: '$z'$/p' < $progpath`" + CC_quoted= + for arg in $CC; do + # Double-quote args containing other shell metacharacters. + case $arg in + *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") + arg="\"$arg\"" + ;; + esac + CC_quoted="$CC_quoted $arg" + done + # user sometimes does CC=-gcc so we need to match that to 'gcc' + trimedcc=`echo ${CC} | $SED -e "s/${host}-//g"` + # and sometimes libtool has CC=-gcc but user does CC=gcc + extendcc=${host}-${CC} + # and sometimes libtool has CC=-gcc but user has CC=-gcc + # (Gentoo-specific hack because we always export $CHOST) + mungedcc=${CHOST-${host}}-${trimedcc} + case "$@ " in + "cc "* | " cc "* | "${host}-cc "* | " ${host}-cc "*|\ + "gcc "* | " gcc "* | "${host}-gcc "* | " ${host}-gcc "*) + tagname=CC + break ;; + "$trimedcc "* | " $trimedcc "* | "`$echo $trimedcc` "* | " `$echo $trimedcc` "*|\ + "$extendcc "* | " $extendcc "* | "`$echo $extendcc` "* | " `$echo $extendcc` "*|\ + "$mungedcc "* | " $mungedcc "* | "`$echo $mungedcc` "* | " `$echo $mungedcc` "*|\ + " $CC "* | "$CC "* | " `$echo $CC` "* | "`$echo $CC` "* | " $CC_quoted"* | "$CC_quoted "* | " `$echo $CC_quoted` "* | "`$echo $CC_quoted` "*) + # The compiler in the base compile command matches + # the one in the tagged configuration. + # Assume this is the tagged configuration we want. + tagname=$z + break + ;; + esac + fi + done + # If $tagname still isn't set, then no tagged configuration + # was found and let the user know that the "--tag" command + # line option must be used. + if test -z "$tagname"; then + $echo "$modename: unable to infer tagged configuration" + $echo "$modename: specify a tag with \`--tag'" 1>&2 + exit $EXIT_FAILURE +# else +# $echo "$modename: using $tagname tagged configuration" + fi + ;; + esac + fi +} + + +# func_extract_an_archive dir oldlib +func_extract_an_archive () +{ + f_ex_an_ar_dir="$1"; shift + f_ex_an_ar_oldlib="$1" + + $show "(cd $f_ex_an_ar_dir && $AR x $f_ex_an_ar_oldlib)" + $run eval "(cd \$f_ex_an_ar_dir && $AR x \$f_ex_an_ar_oldlib)" || exit $? + if ($AR t "$f_ex_an_ar_oldlib" | sort | sort -uc >/dev/null 2>&1); then + : + else + $echo "$modename: ERROR: object name conflicts: $f_ex_an_ar_dir/$f_ex_an_ar_oldlib" 1>&2 + exit $EXIT_FAILURE + fi +} + +# func_extract_archives gentop oldlib ... +func_extract_archives () +{ + my_gentop="$1"; shift + my_oldlibs=${1+"$@"} + my_oldobjs="" + my_xlib="" + my_xabs="" + my_xdir="" + my_status="" + + $show "${rm}r $my_gentop" + $run ${rm}r "$my_gentop" + $show "$mkdir $my_gentop" + $run $mkdir "$my_gentop" + my_status=$? + if test "$my_status" -ne 0 && test ! -d "$my_gentop"; then + exit $my_status + fi + + for my_xlib in $my_oldlibs; do + # Extract the objects. + case $my_xlib in + [\\/]* | [A-Za-z]:[\\/]*) my_xabs="$my_xlib" ;; + *) my_xabs=`pwd`"/$my_xlib" ;; + esac + my_xlib=`$echo "X$my_xlib" | $Xsed -e 's%^.*/%%'` + my_xdir="$my_gentop/$my_xlib" + + $show "${rm}r $my_xdir" + $run ${rm}r "$my_xdir" + $show "$mkdir $my_xdir" + $run $mkdir "$my_xdir" + exit_status=$? + if test "$exit_status" -ne 0 && test ! -d "$my_xdir"; then + exit $exit_status + fi + case $host in + *-darwin*) + $show "Extracting $my_xabs" + # Do not bother doing anything if just a dry run + if test -z "$run"; then + darwin_orig_dir=`pwd` + cd $my_xdir || exit $? + darwin_archive=$my_xabs + darwin_curdir=`pwd` + darwin_base_archive=`$echo "X$darwin_archive" | $Xsed -e 's%^.*/%%'` + darwin_arches=`lipo -info "$darwin_archive" 2>/dev/null | $EGREP Architectures 2>/dev/null` + if test -n "$darwin_arches"; then + darwin_arches=`echo "$darwin_arches" | $SED -e 's/.*are://'` + darwin_arch= + $show "$darwin_base_archive has multiple architectures $darwin_arches" + for darwin_arch in $darwin_arches ; do + mkdir -p "unfat-$$/${darwin_base_archive}-${darwin_arch}" + lipo -thin $darwin_arch -output "unfat-$$/${darwin_base_archive}-${darwin_arch}/${darwin_base_archive}" "${darwin_archive}" + cd "unfat-$$/${darwin_base_archive}-${darwin_arch}" + func_extract_an_archive "`pwd`" "${darwin_base_archive}" + cd "$darwin_curdir" + $rm "unfat-$$/${darwin_base_archive}-${darwin_arch}/${darwin_base_archive}" + done # $darwin_arches + ## Okay now we have a bunch of thin objects, gotta fatten them up :) + darwin_filelist=`find unfat-$$ -type f -name \*.o -print -o -name \*.lo -print| xargs basename | sort -u | $NL2SP` + darwin_file= + darwin_files= + for darwin_file in $darwin_filelist; do + darwin_files=`find unfat-$$ -name $darwin_file -print | $NL2SP` + lipo -create -output "$darwin_file" $darwin_files + done # $darwin_filelist + ${rm}r unfat-$$ + cd "$darwin_orig_dir" + else + cd "$darwin_orig_dir" + func_extract_an_archive "$my_xdir" "$my_xabs" + fi # $darwin_arches + fi # $run + ;; + *) + func_extract_an_archive "$my_xdir" "$my_xabs" + ;; + esac + my_oldobjs="$my_oldobjs "`find $my_xdir -name \*.$objext -print -o -name \*.lo -print | $NL2SP` + done + func_extract_archives_result="$my_oldobjs" +} +# End of Shell function definitions +##################################### + +# Darwin sucks +eval std_shrext=\"$shrext_cmds\" + +disable_libs=no + +# Parse our command line options once, thoroughly. +while test "$#" -gt 0 +do + arg="$1" + shift + + case $arg in + -*=*) optarg=`$echo "X$arg" | $Xsed -e 's/[-_a-zA-Z0-9]*=//'` ;; + *) optarg= ;; + esac + + # If the previous option needs an argument, assign it. + if test -n "$prev"; then + case $prev in + execute_dlfiles) + execute_dlfiles="$execute_dlfiles $arg" + ;; + tag) + tagname="$arg" + preserve_args="${preserve_args}=$arg" + + # Check whether tagname contains only valid characters + case $tagname in + *[!-_A-Za-z0-9,/]*) + $echo "$progname: invalid tag name: $tagname" 1>&2 + exit $EXIT_FAILURE + ;; + esac + + case $tagname in + CC) + # Don't test for the "default" C tag, as we know, it's there, but + # not specially marked. + ;; + *) + if grep "^# ### BEGIN LIBTOOL TAG CONFIG: $tagname$" < "$progpath" > /dev/null; then + taglist="$taglist $tagname" + # Evaluate the configuration. + eval "`${SED} -n -e '/^# ### BEGIN LIBTOOL TAG CONFIG: '$tagname'$/,/^# ### END LIBTOOL TAG CONFIG: '$tagname'$/p' < $progpath`" + else + $echo "$progname: ignoring unknown tag $tagname" 1>&2 + fi + ;; + esac + ;; + *) + eval "$prev=\$arg" + ;; + esac + + prev= + prevopt= + continue + fi + + # Have we seen a non-optional argument yet? + case $arg in + --help) + show_help=yes + ;; + + --version) + $echo "$PROGRAM (GNU $PACKAGE) $VERSION$TIMESTAMP" + $echo + $echo "Copyright (C) 2005 Free Software Foundation, Inc." + $echo "This is free software; see the source for copying conditions. There is NO" + $echo "warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE." + exit $? + ;; + + --config) + ${SED} -e '1,/^# ### BEGIN LIBTOOL CONFIG/d' -e '/^# ### END LIBTOOL CONFIG/,$d' $progpath + # Now print the configurations for the tags. + for tagname in $taglist; do + ${SED} -n -e "/^# ### BEGIN LIBTOOL TAG CONFIG: $tagname$/,/^# ### END LIBTOOL TAG CONFIG: $tagname$/p" < "$progpath" + done + exit $? + ;; + + --debug) + $echo "$progname: enabling shell trace mode" + set -x + preserve_args="$preserve_args $arg" + ;; + + --dry-run | -n) + run=: + ;; + + --features) + $echo "host: $host" + if test "$build_libtool_libs" = yes; then + $echo "enable shared libraries" + else + $echo "disable shared libraries" + fi + if test "$build_old_libs" = yes; then + $echo "enable static libraries" + else + $echo "disable static libraries" + fi + exit $? + ;; + + --finish) mode="finish" ;; + + --mode) prevopt="--mode" prev=mode ;; + --mode=*) mode="$optarg" ;; + + --preserve-dup-deps) duplicate_deps="yes" ;; + + --quiet | --silent) + show=: + preserve_args="$preserve_args $arg" + ;; + + --tag) + prevopt="--tag" + prev=tag + preserve_args="$preserve_args --tag" + ;; + --tag=*) + set tag "$optarg" ${1+"$@"} + shift + prev=tag + preserve_args="$preserve_args --tag" + ;; + + -dlopen) + prevopt="-dlopen" + prev=execute_dlfiles + ;; + + -*) + $echo "$modename: unrecognized option \`$arg'" 1>&2 + $echo "$help" 1>&2 + exit $EXIT_FAILURE + ;; + + *) + nonopt="$arg" + break + ;; + esac +done + +if test -n "$prevopt"; then + $echo "$modename: option \`$prevopt' requires an argument" 1>&2 + $echo "$help" 1>&2 + exit $EXIT_FAILURE +fi + +case $disable_libs in +no) + ;; +shared) + build_libtool_libs=no + build_old_libs=yes + ;; +static) + build_old_libs=`case $build_libtool_libs in yes) echo no;; *) echo yes;; esac` + ;; +esac + +# If this variable is set in any of the actions, the command in it +# will be execed at the end. This prevents here-documents from being +# left over by shells. +exec_cmd= + +if test -z "$show_help"; then + + # Infer the operation mode. + if test -z "$mode"; then + $echo "*** Warning: inferring the mode of operation is deprecated." 1>&2 + $echo "*** Future versions of Libtool will require --mode=MODE be specified." 1>&2 + case $nonopt in + *cc | cc* | *++ | gcc* | *-gcc* | g++* | xlc*) + mode=link + for arg + do + case $arg in + -c) + mode=compile + break + ;; + esac + done + ;; + *db | *dbx | *strace | *truss) + mode=execute + ;; + *install*|cp|mv) + mode=install + ;; + *rm) + mode=uninstall + ;; + *) + # If we have no mode, but dlfiles were specified, then do execute mode. + test -n "$execute_dlfiles" && mode=execute + + # Just use the default operation mode. + if test -z "$mode"; then + if test -n "$nonopt"; then + $echo "$modename: warning: cannot infer operation mode from \`$nonopt'" 1>&2 + else + $echo "$modename: warning: cannot infer operation mode without MODE-ARGS" 1>&2 + fi + fi + ;; + esac + fi + + # Only execute mode is allowed to have -dlopen flags. + if test -n "$execute_dlfiles" && test "$mode" != execute; then + $echo "$modename: unrecognized option \`-dlopen'" 1>&2 + $echo "$help" 1>&2 + exit $EXIT_FAILURE + fi + + # Change the help message to a mode-specific one. + generic_help="$help" + help="Try \`$modename --help --mode=$mode' for more information." + + # These modes are in order of execution frequency so that they run quickly. + case $mode in + # libtool compile mode + compile) + modename="$modename: compile" + # Get the compilation command and the source file. + base_compile= + srcfile="$nonopt" # always keep a non-empty value in "srcfile" + suppress_opt=yes + suppress_output= + arg_mode=normal + libobj= + later= + + for arg + do + case $arg_mode in + arg ) + # do not "continue". Instead, add this to base_compile + lastarg="$arg" + arg_mode=normal + ;; + + target ) + libobj="$arg" + arg_mode=normal + continue + ;; + + normal ) + # Accept any command-line options. + case $arg in + -o) + if test -n "$libobj" ; then + $echo "$modename: you cannot specify \`-o' more than once" 1>&2 + exit $EXIT_FAILURE + fi + arg_mode=target + continue + ;; + + -static | -prefer-pic | -prefer-non-pic) + later="$later $arg" + continue + ;; + + -no-suppress) + suppress_opt=no + continue + ;; + + -Xcompiler) + arg_mode=arg # the next one goes into the "base_compile" arg list + continue # The current "srcfile" will either be retained or + ;; # replaced later. I would guess that would be a bug. + + -Wc,*) + args=`$echo "X$arg" | $Xsed -e "s/^-Wc,//"` + lastarg= + save_ifs="$IFS"; IFS=',' + for arg in $args; do + IFS="$save_ifs" + + # Double-quote args containing other shell metacharacters. + # Many Bourne shells cannot handle close brackets correctly + # in scan sets, so we specify it separately. + case $arg in + *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") + arg="\"$arg\"" + ;; + esac + lastarg="$lastarg $arg" + done + IFS="$save_ifs" + lastarg=`$echo "X$lastarg" | $Xsed -e "s/^ //"` + + # Add the arguments to base_compile. + base_compile="$base_compile $lastarg" + continue + ;; + + * ) + # Accept the current argument as the source file. + # The previous "srcfile" becomes the current argument. + # + lastarg="$srcfile" + srcfile="$arg" + ;; + esac # case $arg + ;; + esac # case $arg_mode + + # Aesthetically quote the previous argument. + lastarg=`$echo "X$lastarg" | $Xsed -e "$sed_quote_subst"` + + case $lastarg in + # Double-quote args containing other shell metacharacters. + # Many Bourne shells cannot handle close brackets correctly + # in scan sets, and some SunOS ksh mistreat backslash-escaping + # in scan sets (worked around with variable expansion), + # and furthermore cannot handle '|' '&' '(' ')' in scan sets + # at all, so we specify them separately. + *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") + lastarg="\"$lastarg\"" + ;; + esac + + base_compile="$base_compile $lastarg" + done # for arg + + case $arg_mode in + arg) + $echo "$modename: you must specify an argument for -Xcompile" + exit $EXIT_FAILURE + ;; + target) + $echo "$modename: you must specify a target with \`-o'" 1>&2 + exit $EXIT_FAILURE + ;; + *) + # Get the name of the library object. + [ -z "$libobj" ] && libobj=`$echo "X$srcfile" | $Xsed -e 's%^.*/%%'` + ;; + esac + + # Recognize several different file suffixes. + # If the user specifies -o file.o, it is replaced with file.lo + xform='[cCFSifmso]' + case $libobj in + *.ada) xform=ada ;; + *.adb) xform=adb ;; + *.ads) xform=ads ;; + *.asm) xform=asm ;; + *.c++) xform=c++ ;; + *.cc) xform=cc ;; + *.ii) xform=ii ;; + *.class) xform=class ;; + *.cpp) xform=cpp ;; + *.cxx) xform=cxx ;; + *.f90) xform=f90 ;; + *.for) xform=for ;; + *.java) xform=java ;; + esac + + libobj=`$echo "X$libobj" | $Xsed -e "s/\.$xform$/.lo/"` + + case $libobj in + *.lo) obj=`$echo "X$libobj" | $Xsed -e "$lo2o"` ;; + *) + $echo "$modename: cannot determine name of library object from \`$libobj'" 1>&2 + exit $EXIT_FAILURE + ;; + esac + + func_infer_tag $base_compile + + for arg in $later; do + case $arg in + -static) + build_old_libs=yes + continue + ;; + + -prefer-pic) + pic_mode=yes + continue + ;; + + -prefer-non-pic) + pic_mode=no + continue + ;; + esac + done + + qlibobj=`$echo "X$libobj" | $Xsed -e "$sed_quote_subst"` + case $qlibobj in + *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") + qlibobj="\"$qlibobj\"" ;; + esac + test "X$libobj" != "X$qlibobj" \ + && $echo "X$libobj" | grep '[]~#^*{};<>?"'"'"' &()|`$[]' \ + && $echo "$modename: libobj name \`$libobj' may not contain shell special characters." + objname=`$echo "X$obj" | $Xsed -e 's%^.*/%%'` + xdir=`$echo "X$obj" | $Xsed -e 's%/[^/]*$%%'` + if test "X$xdir" = "X$obj"; then + xdir= + else + xdir=$xdir/ + fi + lobj=${xdir}$objdir/$objname + + if test -z "$base_compile"; then + $echo "$modename: you must specify a compilation command" 1>&2 + $echo "$help" 1>&2 + exit $EXIT_FAILURE + fi + + # Delete any leftover library objects. + if test "$build_old_libs" = yes; then + removelist="$obj $lobj $libobj ${libobj}T" + else + removelist="$lobj $libobj ${libobj}T" + fi + + $run $rm $removelist + trap "$run $rm $removelist; exit $EXIT_FAILURE" 1 2 15 + + # On Cygwin there's no "real" PIC flag so we must build both object types + case $host_os in + cygwin* | mingw* | pw32* | os2*) + pic_mode=default + ;; + esac + if test "$pic_mode" = no && test "$deplibs_check_method" != pass_all; then + # non-PIC code in shared libraries is not supported + pic_mode=default + fi + + # Calculate the filename of the output object if compiler does + # not support -o with -c + if test "$compiler_c_o" = no; then + output_obj=`$echo "X$srcfile" | $Xsed -e 's%^.*/%%' -e 's%\.[^.]*$%%'`.${objext} + lockfile="$output_obj.lock" + removelist="$removelist $output_obj $lockfile" + trap "$run $rm $removelist; exit $EXIT_FAILURE" 1 2 15 + else + output_obj= + need_locks=no + lockfile= + fi + + # Lock this critical section if it is needed + # We use this script file to make the link, it avoids creating a new file + if test "$need_locks" = yes; then + until $run ln "$srcfile" "$lockfile" 2>/dev/null; do + $show "Waiting for $lockfile to be removed" + sleep 2 + done + elif test "$need_locks" = warn; then + if test -f "$lockfile"; then + $echo "\ +*** ERROR, $lockfile exists and contains: +`cat $lockfile 2>/dev/null` + +This indicates that another process is trying to use the same +temporary object file, and libtool could not work around it because +your compiler does not support \`-c' and \`-o' together. If you +repeat this compilation, it may succeed, by chance, but you had better +avoid parallel builds (make -j) in this platform, or get a better +compiler." + + $run $rm $removelist + exit $EXIT_FAILURE + fi + $echo "$srcfile" > "$lockfile" + fi + + if test -n "$fix_srcfile_path"; then + eval srcfile=\"$fix_srcfile_path\" + fi + qsrcfile=`$echo "X$srcfile" | $Xsed -e "$sed_quote_subst"` + case $qsrcfile in + *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") + qsrcfile="\"$qsrcfile\"" ;; + esac + + $run $rm "$libobj" "${libobj}T" + + # Create a libtool object file (analogous to a ".la" file), + # but don't create it if we're doing a dry run. + test -z "$run" && cat > ${libobj}T </dev/null`" != "X$srcfile"; then + $echo "\ +*** ERROR, $lockfile contains: +`cat $lockfile 2>/dev/null` + +but it should contain: +$srcfile + +This indicates that another process is trying to use the same +temporary object file, and libtool could not work around it because +your compiler does not support \`-c' and \`-o' together. If you +repeat this compilation, it may succeed, by chance, but you had better +avoid parallel builds (make -j) in this platform, or get a better +compiler." + + $run $rm $removelist + exit $EXIT_FAILURE + fi + + # Just move the object if needed, then go on to compile the next one + if test -n "$output_obj" && test "X$output_obj" != "X$lobj"; then + $show "$mv $output_obj $lobj" + if $run $mv $output_obj $lobj; then : + else + error=$? + $run $rm $removelist + exit $error + fi + fi + + # Append the name of the PIC object to the libtool object file. + test -z "$run" && cat >> ${libobj}T <> ${libobj}T </dev/null`" != "X$srcfile"; then + $echo "\ +*** ERROR, $lockfile contains: +`cat $lockfile 2>/dev/null` + +but it should contain: +$srcfile + +This indicates that another process is trying to use the same +temporary object file, and libtool could not work around it because +your compiler does not support \`-c' and \`-o' together. If you +repeat this compilation, it may succeed, by chance, but you had better +avoid parallel builds (make -j) in this platform, or get a better +compiler." + + $run $rm $removelist + exit $EXIT_FAILURE + fi + + # Just move the object if needed + if test -n "$output_obj" && test "X$output_obj" != "X$obj"; then + $show "$mv $output_obj $obj" + if $run $mv $output_obj $obj; then : + else + error=$? + $run $rm $removelist + exit $error + fi + fi + + # Append the name of the non-PIC object the libtool object file. + # Only append if the libtool object file exists. + test -z "$run" && cat >> ${libobj}T <> ${libobj}T <&2 + fi + if test -n "$link_static_flag"; then + dlopen_self=$dlopen_self_static + fi + prefer_static_libs=yes + else + if test -z "$pic_flag" && test -n "$link_static_flag"; then + dlopen_self=$dlopen_self_static + fi + prefer_static_libs=built + fi + build_libtool_libs=no + build_old_libs=yes + break + ;; + esac + done + + # See if our shared archives depend on static archives. + test -n "$old_archive_from_new_cmds" && build_old_libs=yes + + # Go through the arguments, transforming them on the way. + while test "$#" -gt 0; do + arg="$1" + shift + case $arg in + *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") + qarg=\"`$echo "X$arg" | $Xsed -e "$sed_quote_subst"`\" ### testsuite: skip nested quoting test + ;; + *) qarg=$arg ;; + esac + libtool_args="$libtool_args $qarg" + + # If the previous option needs an argument, assign it. + if test -n "$prev"; then + case $prev in + output) + compile_command="$compile_command @OUTPUT@" + finalize_command="$finalize_command @OUTPUT@" + ;; + esac + + case $prev in + dlfiles|dlprefiles) + if test "$preload" = no; then + # Add the symbol object into the linking commands. + compile_command="$compile_command @SYMFILE@" + finalize_command="$finalize_command @SYMFILE@" + preload=yes + fi + case $arg in + *.la | *.lo) ;; # We handle these cases below. + force) + if test "$dlself" = no; then + dlself=needless + export_dynamic=yes + fi + prev= + continue + ;; + self) + if test "$prev" = dlprefiles; then + dlself=yes + elif test "$prev" = dlfiles && test "$dlopen_self" != yes; then + dlself=yes + else + dlself=needless + export_dynamic=yes + fi + prev= + continue + ;; + *) + if test "$prev" = dlfiles; then + dlfiles="$dlfiles $arg" + else + dlprefiles="$dlprefiles $arg" + fi + prev= + continue + ;; + esac + ;; + expsyms) + export_symbols="$arg" + if test ! -f "$arg"; then + $echo "$modename: symbol file \`$arg' does not exist" + exit $EXIT_FAILURE + fi + prev= + continue + ;; + expsyms_regex) + export_symbols_regex="$arg" + prev= + continue + ;; + inst_prefix) + inst_prefix_dir="$arg" + prev= + continue + ;; + precious_regex) + precious_files_regex="$arg" + prev= + continue + ;; + release) + release="-$arg" + prev= + continue + ;; + objectlist) + if test -f "$arg"; then + save_arg=$arg + moreargs= + for fil in `cat $save_arg` + do +# moreargs="$moreargs $fil" + arg=$fil + # A libtool-controlled object. + + # Check to see that this really is a libtool object. + if (${SED} -e '2q' $arg | grep "^# Generated by .*$PACKAGE") >/dev/null 2>&1; then + pic_object= + non_pic_object= + + # Read the .lo file + # If there is no directory component, then add one. + case $arg in + */* | *\\*) . $arg ;; + *) . ./$arg ;; + esac + + if test -z "$pic_object" || \ + test -z "$non_pic_object" || + test "$pic_object" = none && \ + test "$non_pic_object" = none; then + $echo "$modename: cannot find name of object for \`$arg'" 1>&2 + exit $EXIT_FAILURE + fi + + # Extract subdirectory from the argument. + xdir=`$echo "X$arg" | $Xsed -e 's%/[^/]*$%%'` + if test "X$xdir" = "X$arg"; then + xdir= + else + xdir="$xdir/" + fi + + if test "$pic_object" != none; then + # Prepend the subdirectory the object is found in. + pic_object="$xdir$pic_object" + + if test "$prev" = dlfiles; then + if test "$build_libtool_libs" = yes && test "$dlopen_support" = yes; then + dlfiles="$dlfiles $pic_object" + prev= + continue + else + # If libtool objects are unsupported, then we need to preload. + prev=dlprefiles + fi + fi + + # CHECK ME: I think I busted this. -Ossama + if test "$prev" = dlprefiles; then + # Preload the old-style object. + dlprefiles="$dlprefiles $pic_object" + prev= + fi + + # A PIC object. + libobjs="$libobjs $pic_object" + arg="$pic_object" + fi + + # Non-PIC object. + if test "$non_pic_object" != none; then + # Prepend the subdirectory the object is found in. + non_pic_object="$xdir$non_pic_object" + + # A standard non-PIC object + non_pic_objects="$non_pic_objects $non_pic_object" + if test -z "$pic_object" || test "$pic_object" = none ; then + arg="$non_pic_object" + fi + else + # If the PIC object exists, use it instead. + # $xdir was prepended to $pic_object above. + non_pic_object="$pic_object" + non_pic_objects="$non_pic_objects $non_pic_object" + fi + else + # Only an error if not doing a dry-run. + if test -z "$run"; then + $echo "$modename: \`$arg' is not a valid libtool object" 1>&2 + exit $EXIT_FAILURE + else + # Dry-run case. + + # Extract subdirectory from the argument. + xdir=`$echo "X$arg" | $Xsed -e 's%/[^/]*$%%'` + if test "X$xdir" = "X$arg"; then + xdir= + else + xdir="$xdir/" + fi + + pic_object=`$echo "X${xdir}${objdir}/${arg}" | $Xsed -e "$lo2o"` + non_pic_object=`$echo "X${xdir}${arg}" | $Xsed -e "$lo2o"` + libobjs="$libobjs $pic_object" + non_pic_objects="$non_pic_objects $non_pic_object" + fi + fi + done + else + $echo "$modename: link input file \`$save_arg' does not exist" + exit $EXIT_FAILURE + fi + arg=$save_arg + prev= + continue + ;; + rpath | xrpath) + # We need an absolute path. + case $arg in + [\\/]* | [A-Za-z]:[\\/]*) ;; + *) + $echo "$modename: only absolute run-paths are allowed" 1>&2 + exit $EXIT_FAILURE + ;; + esac + if test "$prev" = rpath; then + case "$rpath " in + *" $arg "*) ;; + *) rpath="$rpath $arg" ;; + esac + else + case "$xrpath " in + *" $arg "*) ;; + *) xrpath="$xrpath $arg" ;; + esac + fi + prev= + continue + ;; + xcompiler) + compiler_flags="$compiler_flags $qarg" + prev= + compile_command="$compile_command $qarg" + finalize_command="$finalize_command $qarg" + continue + ;; + xlinker) + linker_flags="$linker_flags $qarg" + compiler_flags="$compiler_flags $wl$qarg" + prev= + compile_command="$compile_command $wl$qarg" + finalize_command="$finalize_command $wl$qarg" + continue + ;; + xcclinker) + linker_flags="$linker_flags $qarg" + compiler_flags="$compiler_flags $qarg" + prev= + compile_command="$compile_command $qarg" + finalize_command="$finalize_command $qarg" + continue + ;; + shrext) + shrext_cmds="$arg" + prev= + continue + ;; + darwin_framework|darwin_framework_skip) + test "$prev" = "darwin_framework" && compiler_flags="$compiler_flags $arg" + compile_command="$compile_command $arg" + finalize_command="$finalize_command $arg" + prev= + continue + ;; + *) + eval "$prev=\"\$arg\"" + prev= + continue + ;; + esac + fi # test -n "$prev" + + prevarg="$arg" + + case $arg in + -all-static) + if test -n "$link_static_flag"; then + compile_command="$compile_command $link_static_flag" + finalize_command="$finalize_command $link_static_flag" + fi + continue + ;; + + -allow-undefined) + # FIXME: remove this flag sometime in the future. + $echo "$modename: \`-allow-undefined' is deprecated because it is the default" 1>&2 + continue + ;; + + -avoid-version) + avoid_version=yes + continue + ;; + + -dlopen) + prev=dlfiles + continue + ;; + + -dlpreopen) + prev=dlprefiles + continue + ;; + + -export-dynamic) + export_dynamic=yes + continue + ;; + + -export-symbols | -export-symbols-regex) + if test -n "$export_symbols" || test -n "$export_symbols_regex"; then + $echo "$modename: more than one -exported-symbols argument is not allowed" + exit $EXIT_FAILURE + fi + if test "X$arg" = "X-export-symbols"; then + prev=expsyms + else + prev=expsyms_regex + fi + continue + ;; + + -framework|-arch|-isysroot) + case " $CC " in + *" ${arg} ${1} "* | *" ${arg} ${1} "*) + prev=darwin_framework_skip ;; + *) compiler_flags="$compiler_flags $arg" + prev=darwin_framework ;; + esac + compile_command="$compile_command $arg" + finalize_command="$finalize_command $arg" + continue + ;; + + -inst-prefix-dir) + prev=inst_prefix + continue + ;; + + # The native IRIX linker understands -LANG:*, -LIST:* and -LNO:* + # so, if we see these flags be careful not to treat them like -L + -L[A-Z][A-Z]*:*) + case $with_gcc/$host in + no/*-*-irix* | /*-*-irix*) + compile_command="$compile_command $arg" + finalize_command="$finalize_command $arg" + ;; + esac + continue + ;; + + -L*) + dir=`$echo "X$arg" | $Xsed -e 's/^-L//'` + # We need an absolute path. + case $dir in + [\\/]* | [A-Za-z]:[\\/]*) ;; + *) + absdir=`cd "$dir" && pwd` + if test -z "$absdir"; then + $echo "$modename: cannot determine absolute directory name of \`$dir'" 1>&2 + absdir="$dir" + notinst_path="$notinst_path $dir" + fi + dir="$absdir" + ;; + esac + case "$deplibs " in + *" -L$dir "*) ;; + *) + deplibs="$deplibs -L$dir" + lib_search_path="$lib_search_path $dir" + ;; + esac + case $host in + *-*-cygwin* | *-*-mingw* | *-*-pw32* | *-*-os2*) + testbindir=`$echo "X$dir" | $Xsed -e 's*/lib$*/bin*'` + case :$dllsearchpath: in + *":$dir:"*) ;; + *) dllsearchpath="$dllsearchpath:$dir";; + esac + case :$dllsearchpath: in + *":$testbindir:"*) ;; + *) dllsearchpath="$dllsearchpath:$testbindir";; + esac + ;; + esac + continue + ;; + + -l*) + if test "X$arg" = "X-lc" || test "X$arg" = "X-lm"; then + case $host in + *-*-cygwin* | *-*-mingw* | *-*-pw32* | *-*-beos*) + # These systems don't actually have a C or math library (as such) + continue + ;; + *-*-os2*) + # These systems don't actually have a C library (as such) + test "X$arg" = "X-lc" && continue + ;; + *-*-openbsd* | *-*-freebsd* | *-*-dragonfly*) + # Do not include libc due to us having libc/libc_r. + test "X$arg" = "X-lc" && continue + ;; + *-*-rhapsody* | *-*-darwin1.[012]) + # Rhapsody C and math libraries are in the System framework + deplibs="$deplibs -framework System" + continue + ;; + *-*-sco3.2v5* | *-*-sco5v6*) + # Causes problems with __ctype + test "X$arg" = "X-lc" && continue + ;; + *-*-sysv4.2uw2* | *-*-sysv5* | *-*-unixware* | *-*-OpenUNIX*) + # Compiler inserts libc in the correct place for threads to work + test "X$arg" = "X-lc" && continue + ;; + esac + elif test "X$arg" = "X-lc_r"; then + case $host in + *-*-openbsd* | *-*-freebsd* | *-*-dragonfly*) + # Do not include libc_r directly, use -pthread flag. + continue + ;; + esac + fi + deplibs="$deplibs $arg" + continue + ;; + + # Tru64 UNIX uses -model [arg] to determine the layout of C++ + # classes, name mangling, and exception handling. + -model) + compile_command="$compile_command $arg" + compiler_flags="$compiler_flags $arg" + finalize_command="$finalize_command $arg" + prev=xcompiler + continue + ;; + + -mt|-mthreads|-kthread|-Kthread|-pthread|-pthreads|--thread-safe) + compiler_flags="$compiler_flags $arg" + compile_command="$compile_command $arg" + finalize_command="$finalize_command $arg" + continue + ;; + + -module) + module=yes + continue + ;; + + # -64, -mips[0-9] enable 64-bit mode on the SGI compiler + # -r[0-9][0-9]* specifies the processor on the SGI compiler + # -xarch=*, -xtarget=* enable 64-bit mode on the Sun compiler + # +DA*, +DD* enable 64-bit mode on the HP compiler + # -q* pass through compiler args for the IBM compiler + # -m* pass through architecture-specific compiler args for GCC + # -m*, -t[45]*, -txscale* pass through architecture-specific + # compiler args for GCC + # -pg pass through profiling flag for GCC + # @file GCC response files + -64|-mips[0-9]|-r[0-9][0-9]*|-xarch=*|-xtarget=*|+DA*|+DD*|-q*|-m*|-pg| \ + -t[45]*|-txscale*|@*) + + # Unknown arguments in both finalize_command and compile_command need + # to be aesthetically quoted because they are evaled later. + arg=`$echo "X$arg" | $Xsed -e "$sed_quote_subst"` + case $arg in + *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") + arg="\"$arg\"" + ;; + esac + compile_command="$compile_command $arg" + finalize_command="$finalize_command $arg" + compiler_flags="$compiler_flags $arg" + continue + ;; + + -shrext) + prev=shrext + continue + ;; + + -no-fast-install) + fast_install=no + continue + ;; + + -no-install) + case $host in + *-*-cygwin* | *-*-mingw* | *-*-pw32* | *-*-os2*) + # The PATH hackery in wrapper scripts is required on Windows + # in order for the loader to find any dlls it needs. + $echo "$modename: warning: \`-no-install' is ignored for $host" 1>&2 + $echo "$modename: warning: assuming \`-no-fast-install' instead" 1>&2 + fast_install=no + ;; + *) no_install=yes ;; + esac + continue + ;; + + -no-undefined) + allow_undefined=no + continue + ;; + + -objectlist) + prev=objectlist + continue + ;; + + -o) prev=output ;; + + -precious-files-regex) + prev=precious_regex + continue + ;; + + -release) + prev=release + continue + ;; + + -rpath) + prev=rpath + continue + ;; + + -R) + prev=xrpath + continue + ;; + + -R*) + dir=`$echo "X$arg" | $Xsed -e 's/^-R//'` + # We need an absolute path. + case $dir in + [\\/]* | [A-Za-z]:[\\/]*) ;; + *) + $echo "$modename: only absolute run-paths are allowed" 1>&2 + exit $EXIT_FAILURE + ;; + esac + case "$xrpath " in + *" $dir "*) ;; + *) xrpath="$xrpath $dir" ;; + esac + continue + ;; + + -static) + # The effects of -static are defined in a previous loop. + # We used to do the same as -all-static on platforms that + # didn't have a PIC flag, but the assumption that the effects + # would be equivalent was wrong. It would break on at least + # Digital Unix and AIX. + continue + ;; + + -thread-safe) + thread_safe=yes + continue + ;; + + -version-info) + prev=vinfo + continue + ;; + -version-number) + prev=vinfo + vinfo_number=yes + continue + ;; + + -Wc,*) + args=`$echo "X$arg" | $Xsed -e "$sed_quote_subst" -e 's/^-Wc,//'` + arg= + save_ifs="$IFS"; IFS=',' + for flag in $args; do + IFS="$save_ifs" + case $flag in + *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") + flag="\"$flag\"" + ;; + esac + arg="$arg $wl$flag" + compiler_flags="$compiler_flags $flag" + done + IFS="$save_ifs" + arg=`$echo "X$arg" | $Xsed -e "s/^ //"` + ;; + + -Wl,*) + args=`$echo "X$arg" | $Xsed -e "$sed_quote_subst" -e 's/^-Wl,//'` + arg= + save_ifs="$IFS"; IFS=',' + for flag in $args; do + IFS="$save_ifs" + case $flag in + *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") + flag="\"$flag\"" + ;; + esac + arg="$arg $wl$flag" + compiler_flags="$compiler_flags $wl$flag" + linker_flags="$linker_flags $flag" + done + IFS="$save_ifs" + arg=`$echo "X$arg" | $Xsed -e "s/^ //"` + ;; + + -Xcompiler) + prev=xcompiler + continue + ;; + + -Xlinker) + prev=xlinker + continue + ;; + + -XCClinker) + prev=xcclinker + continue + ;; + + # Some other compiler flag. + -* | +*) + # Unknown arguments in both finalize_command and compile_command need + # to be aesthetically quoted because they are evaled later. + arg=`$echo "X$arg" | $Xsed -e "$sed_quote_subst"` + case $arg in + *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") + arg="\"$arg\"" + ;; + esac + ;; + + *.$objext) + # A standard object. + objs="$objs $arg" + ;; + + *.lo) + # A libtool-controlled object. + + # Check to see that this really is a libtool object. + if (${SED} -e '2q' $arg | grep "^# Generated by .*$PACKAGE") >/dev/null 2>&1; then + pic_object= + non_pic_object= + + # Read the .lo file + # If there is no directory component, then add one. + case $arg in + */* | *\\*) . $arg ;; + *) . ./$arg ;; + esac + + if test -z "$pic_object" || \ + test -z "$non_pic_object" || + test "$pic_object" = none && \ + test "$non_pic_object" = none; then + $echo "$modename: cannot find name of object for \`$arg'" 1>&2 + exit $EXIT_FAILURE + fi + + # Extract subdirectory from the argument. + xdir=`$echo "X$arg" | $Xsed -e 's%/[^/]*$%%'` + if test "X$xdir" = "X$arg"; then + xdir= + else + xdir="$xdir/" + fi + + if test "$pic_object" != none; then + # Prepend the subdirectory the object is found in. + pic_object="$xdir$pic_object" + + if test "$prev" = dlfiles; then + if test "$build_libtool_libs" = yes && test "$dlopen_support" = yes; then + dlfiles="$dlfiles $pic_object" + prev= + continue + else + # If libtool objects are unsupported, then we need to preload. + prev=dlprefiles + fi + fi + + # CHECK ME: I think I busted this. -Ossama + if test "$prev" = dlprefiles; then + # Preload the old-style object. + dlprefiles="$dlprefiles $pic_object" + prev= + fi + + # A PIC object. + libobjs="$libobjs $pic_object" + arg="$pic_object" + fi + + # Non-PIC object. + if test "$non_pic_object" != none; then + # Prepend the subdirectory the object is found in. + non_pic_object="$xdir$non_pic_object" + + # A standard non-PIC object + non_pic_objects="$non_pic_objects $non_pic_object" + if test -z "$pic_object" || test "$pic_object" = none ; then + arg="$non_pic_object" + fi + else + # If the PIC object exists, use it instead. + # $xdir was prepended to $pic_object above. + non_pic_object="$pic_object" + non_pic_objects="$non_pic_objects $non_pic_object" + fi + else + # Only an error if not doing a dry-run. + if test -z "$run"; then + $echo "$modename: \`$arg' is not a valid libtool object" 1>&2 + exit $EXIT_FAILURE + else + # Dry-run case. + + # Extract subdirectory from the argument. + xdir=`$echo "X$arg" | $Xsed -e 's%/[^/]*$%%'` + if test "X$xdir" = "X$arg"; then + xdir= + else + xdir="$xdir/" + fi + + pic_object=`$echo "X${xdir}${objdir}/${arg}" | $Xsed -e "$lo2o"` + non_pic_object=`$echo "X${xdir}${arg}" | $Xsed -e "$lo2o"` + libobjs="$libobjs $pic_object" + non_pic_objects="$non_pic_objects $non_pic_object" + fi + fi + ;; + + *.$libext) + # An archive. + deplibs="$deplibs $arg" + old_deplibs="$old_deplibs $arg" + continue + ;; + + *.la) + # A libtool-controlled library. + + if test "$prev" = dlfiles; then + # This library was specified with -dlopen. + dlfiles="$dlfiles $arg" + prev= + elif test "$prev" = dlprefiles; then + # The library was specified with -dlpreopen. + dlprefiles="$dlprefiles $arg" + prev= + else + deplibs="$deplibs $arg" + fi + continue + ;; + + # Some other compiler argument. + *) + # Unknown arguments in both finalize_command and compile_command need + # to be aesthetically quoted because they are evaled later. + arg=`$echo "X$arg" | $Xsed -e "$sed_quote_subst"` + case $arg in + *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") + arg="\"$arg\"" + ;; + esac + ;; + esac # arg + + # Now actually substitute the argument into the commands. + if test -n "$arg"; then + compile_command="$compile_command $arg" + finalize_command="$finalize_command $arg" + fi + done # argument parsing loop + + if test -n "$prev"; then + $echo "$modename: the \`$prevarg' option requires an argument" 1>&2 + $echo "$help" 1>&2 + exit $EXIT_FAILURE + fi + + if test "$export_dynamic" = yes && test -n "$export_dynamic_flag_spec"; then + eval arg=\"$export_dynamic_flag_spec\" + compile_command="$compile_command $arg" + finalize_command="$finalize_command $arg" + fi + + oldlibs= + # calculate the name of the file, without its directory + outputname=`$echo "X$output" | $Xsed -e 's%^.*/%%'` + libobjs_save="$libobjs" + + if test -n "$shlibpath_var"; then + # get the directories listed in $shlibpath_var + eval shlib_search_path=\`\$echo \"X\${$shlibpath_var}\" \| \$Xsed -e \'s/:/ /g\'\` + else + shlib_search_path= + fi + eval sys_lib_search_path=\"$sys_lib_search_path_spec\" + eval sys_lib_dlsearch_path=\"$sys_lib_dlsearch_path_spec\" + + output_objdir=`$echo "X$output" | $Xsed -e 's%/[^/]*$%%'` + if test "X$output_objdir" = "X$output"; then + output_objdir="$objdir" + else + output_objdir="$output_objdir/$objdir" + fi + # Create the object directory. + if test ! -d "$output_objdir"; then + $show "$mkdir $output_objdir" + $run $mkdir $output_objdir + exit_status=$? + if test "$exit_status" -ne 0 && test ! -d "$output_objdir"; then + exit $exit_status + fi + fi + + # Determine the type of output + case $output in + "") + $echo "$modename: you must specify an output file" 1>&2 + $echo "$help" 1>&2 + exit $EXIT_FAILURE + ;; + *.$libext) linkmode=oldlib ;; + *.lo | *.$objext) linkmode=obj ;; + *.la) linkmode=lib ;; + *) linkmode=prog ;; # Anything else should be a program. + esac + + case $host in + *cygwin* | *mingw* | *pw32*) + # don't eliminate duplications in $postdeps and $predeps + duplicate_compiler_generated_deps=yes + ;; + *) + duplicate_compiler_generated_deps=$duplicate_deps + ;; + esac + specialdeplibs= + + libs= + # Find all interdependent deplibs by searching for libraries + # that are linked more than once (e.g. -la -lb -la) + for deplib in $deplibs; do + if test "X$duplicate_deps" = "Xyes" ; then + case "$libs " in + *" $deplib "*) specialdeplibs="$specialdeplibs $deplib" ;; + esac + fi + libs="$libs $deplib" + done + + if test "$linkmode" = lib; then + libs="$predeps $libs $compiler_lib_search_path $postdeps" + + # Compute libraries that are listed more than once in $predeps + # $postdeps and mark them as special (i.e., whose duplicates are + # not to be eliminated). + pre_post_deps= + if test "X$duplicate_compiler_generated_deps" = "Xyes" ; then + for pre_post_dep in $predeps $postdeps; do + case "$pre_post_deps " in + *" $pre_post_dep "*) specialdeplibs="$specialdeplibs $pre_post_deps" ;; + esac + pre_post_deps="$pre_post_deps $pre_post_dep" + done + fi + pre_post_deps= + fi + + deplibs= + newdependency_libs= + newlib_search_path= + need_relink=no # whether we're linking any uninstalled libtool libraries + notinst_deplibs= # not-installed libtool libraries + case $linkmode in + lib) + passes="conv link" + for file in $dlfiles $dlprefiles; do + case $file in + *.la) ;; + *) + $echo "$modename: libraries can \`-dlopen' only libtool libraries: $file" 1>&2 + exit $EXIT_FAILURE + ;; + esac + done + ;; + prog) + compile_deplibs= + finalize_deplibs= + alldeplibs=no + newdlfiles= + newdlprefiles= + passes="conv scan dlopen dlpreopen link" + ;; + *) passes="conv" + ;; + esac + for pass in $passes; do + if test "$linkmode,$pass" = "lib,link" || + test "$linkmode,$pass" = "prog,scan"; then + libs="$deplibs" + deplibs= + fi + if test "$linkmode" = prog; then + case $pass in + dlopen) libs="$dlfiles" ;; + dlpreopen) libs="$dlprefiles" ;; + link) libs="$deplibs %DEPLIBS% $dependency_libs" ;; + esac + fi + if test "$pass" = dlopen; then + # Collect dlpreopened libraries + save_deplibs="$deplibs" + deplibs= + fi + for deplib in $libs; do + lib= + found=no + case $deplib in + -mt|-mthreads|-kthread|-Kthread|-pthread|-pthreads|--thread-safe) + if test "$linkmode,$pass" = "prog,link"; then + compile_deplibs="$deplib $compile_deplibs" + finalize_deplibs="$deplib $finalize_deplibs" + else + compiler_flags="$compiler_flags $deplib" + fi + continue + ;; + -l*) + if test "$linkmode" != lib && test "$linkmode" != prog; then + $echo "$modename: warning: \`-l' is ignored for archives/objects" 1>&2 + continue + fi + name=`$echo "X$deplib" | $Xsed -e 's/^-l//'` + for searchdir in $newlib_search_path $lib_search_path $sys_lib_search_path $shlib_search_path; do + for search_ext in .la $std_shrext .so .a; do + # Search the libtool library + lib="$searchdir/lib${name}${search_ext}" + if test -f "$lib"; then + if test "$search_ext" = ".la"; then + found=yes + else + found=no + fi + break 2 + fi + done + done + if test "$found" != yes; then + # deplib doesn't seem to be a libtool library + if test "$linkmode,$pass" = "prog,link"; then + compile_deplibs="$deplib $compile_deplibs" + finalize_deplibs="$deplib $finalize_deplibs" + else + deplibs="$deplib $deplibs" + test "$linkmode" = lib && newdependency_libs="$deplib $newdependency_libs" + fi + continue + else # deplib is a libtool library + # If $allow_libtool_libs_with_static_runtimes && $deplib is a stdlib, + # We need to do some special things here, and not later. + if test "X$allow_libtool_libs_with_static_runtimes" = "Xyes" ; then + case " $predeps $postdeps " in + *" $deplib "*) + if (${SED} -e '2q' $lib | + grep "^# Generated by .*$PACKAGE") >/dev/null 2>&1; then + library_names= + old_library= + case $lib in + */* | *\\*) . $lib ;; + *) . ./$lib ;; + esac + for l in $old_library $library_names; do + ll="$l" + done + if test "X$ll" = "X$old_library" ; then # only static version available + found=no + ladir=`$echo "X$lib" | $Xsed -e 's%/[^/]*$%%'` + test "X$ladir" = "X$lib" && ladir="." + lib=$ladir/$old_library + if test "$linkmode,$pass" = "prog,link"; then + compile_deplibs="$deplib $compile_deplibs" + finalize_deplibs="$deplib $finalize_deplibs" + else + deplibs="$deplib $deplibs" + test "$linkmode" = lib && newdependency_libs="$deplib $newdependency_libs" + fi + continue + fi + fi + ;; + *) ;; + esac + fi + fi + ;; # -l + -L*) + case $linkmode in + lib) + deplibs="$deplib $deplibs" + test "$pass" = conv && continue + newdependency_libs="$deplib $newdependency_libs" + newlib_search_path="$newlib_search_path "`$echo "X$deplib" | $Xsed -e 's/^-L//'` + ;; + prog) + if test "$pass" = conv; then + deplibs="$deplib $deplibs" + continue + fi + if test "$pass" = scan; then + deplibs="$deplib $deplibs" + else + compile_deplibs="$deplib $compile_deplibs" + finalize_deplibs="$deplib $finalize_deplibs" + fi + newlib_search_path="$newlib_search_path "`$echo "X$deplib" | $Xsed -e 's/^-L//'` + ;; + *) + $echo "$modename: warning: \`-L' is ignored for archives/objects" 1>&2 + ;; + esac # linkmode + continue + ;; # -L + -R*) + if test "$pass" = link; then + dir=`$echo "X$deplib" | $Xsed -e 's/^-R//'` + # Make sure the xrpath contains only unique directories. + case "$xrpath " in + *" $dir "*) ;; + *) xrpath="$xrpath $dir" ;; + esac + fi + deplibs="$deplib $deplibs" + continue + ;; + *.la) lib="$deplib" ;; + *.$libext) + if test "$pass" = conv; then + deplibs="$deplib $deplibs" + continue + fi + case $linkmode in + lib) + valid_a_lib=no + case $deplibs_check_method in + match_pattern*) + set dummy $deplibs_check_method + match_pattern_regex=`expr "$deplibs_check_method" : "$2 \(.*\)"` + if eval $echo \"$deplib\" 2>/dev/null \ + | $SED 10q \ + | $EGREP "$match_pattern_regex" > /dev/null; then + valid_a_lib=yes + fi + ;; + pass_all) + valid_a_lib=yes + ;; + esac + if test "$valid_a_lib" != yes; then + $echo + $echo "*** Warning: Trying to link with static lib archive $deplib." + $echo "*** I have the capability to make that library automatically link in when" + $echo "*** you link to this library. But I can only do this if you have a" + $echo "*** shared version of the library, which you do not appear to have" + $echo "*** because the file extensions .$libext of this argument makes me believe" + $echo "*** that it is just a static archive that I should not used here." + else + $echo + $echo "*** Warning: Linking the shared library $output against the" + $echo "*** static library $deplib is not portable!" + deplibs="$deplib $deplibs" + fi + continue + ;; + prog) + if test "$pass" != link; then + deplibs="$deplib $deplibs" + else + compile_deplibs="$deplib $compile_deplibs" + finalize_deplibs="$deplib $finalize_deplibs" + fi + continue + ;; + esac # linkmode + ;; # *.$libext + *.lo | *.$objext) + if test "$pass" = conv; then + deplibs="$deplib $deplibs" + elif test "$linkmode" = prog; then + if test "$pass" = dlpreopen || test "$dlopen_support" != yes || test "$build_libtool_libs" = no; then + # If there is no dlopen support or we're linking statically, + # we need to preload. + newdlprefiles="$newdlprefiles $deplib" + compile_deplibs="$deplib $compile_deplibs" + finalize_deplibs="$deplib $finalize_deplibs" + else + newdlfiles="$newdlfiles $deplib" + fi + fi + continue + ;; + %DEPLIBS%) + alldeplibs=yes + continue + ;; + esac # case $deplib + if test "$found" = yes || test -f "$lib"; then : + else + $echo "$modename: cannot find the library \`$lib' or unhandled argument \`$deplib'" 1>&2 + exit $EXIT_FAILURE + fi + + # Check to see that this really is a libtool archive. + if (${SED} -e '2q' $lib | grep "^# Generated by .*$PACKAGE") >/dev/null 2>&1; then : + else + $echo "$modename: \`$lib' is not a valid libtool archive" 1>&2 + exit $EXIT_FAILURE + fi + + ladir=`$echo "X$lib" | $Xsed -e 's%/[^/]*$%%'` + test "X$ladir" = "X$lib" && ladir="." + + dlname= + dlopen= + dlpreopen= + libdir= + library_names= + old_library= + # If the library was installed with an old release of libtool, + # it will not redefine variables installed, or shouldnotlink + installed=yes + shouldnotlink=no + avoidtemprpath= + + + # Read the .la file + case $lib in + */* | *\\*) . $lib ;; + *) . ./$lib ;; + esac + + if test "$linkmode,$pass" = "lib,link" || + test "$linkmode,$pass" = "prog,scan" || + { test "$linkmode" != prog && test "$linkmode" != lib; }; then + test -n "$dlopen" && dlfiles="$dlfiles $dlopen" + test -n "$dlpreopen" && dlprefiles="$dlprefiles $dlpreopen" + fi + + if test "$pass" = conv; then + # Only check for convenience libraries + deplibs="$lib $deplibs" + if test -z "$libdir"; then + if test -z "$old_library"; then + $echo "$modename: cannot find name of link library for \`$lib'" 1>&2 + exit $EXIT_FAILURE + fi + # It is a libtool convenience library, so add in its objects. + convenience="$convenience $ladir/$objdir/$old_library" + old_convenience="$old_convenience $ladir/$objdir/$old_library" + tmp_libs= + for deplib in $dependency_libs; do + deplibs="$deplib $deplibs" + if test "X$duplicate_deps" = "Xyes" ; then + case "$tmp_libs " in + *" $deplib "*) specialdeplibs="$specialdeplibs $deplib" ;; + esac + fi + tmp_libs="$tmp_libs $deplib" + done + elif test "$linkmode" != prog && test "$linkmode" != lib; then + $echo "$modename: \`$lib' is not a convenience library" 1>&2 + exit $EXIT_FAILURE + fi + continue + fi # $pass = conv + + + # Get the name of the library we link against. + linklib= + for l in $old_library $library_names; do + linklib="$l" + done + if test -z "$linklib"; then + $echo "$modename: cannot find name of link library for \`$lib'" 1>&2 + exit $EXIT_FAILURE + fi + + # This library was specified with -dlopen. + if test "$pass" = dlopen; then + if test -z "$libdir"; then + $echo "$modename: cannot -dlopen a convenience library: \`$lib'" 1>&2 + exit $EXIT_FAILURE + fi + if test -z "$dlname" || + test "$dlopen_support" != yes || + test "$build_libtool_libs" = no; then + # If there is no dlname, no dlopen support or we're linking + # statically, we need to preload. We also need to preload any + # dependent libraries so libltdl's deplib preloader doesn't + # bomb out in the load deplibs phase. + dlprefiles="$dlprefiles $lib $dependency_libs" + else + newdlfiles="$newdlfiles $lib" + fi + continue + fi # $pass = dlopen + + # We need an absolute path. + case $ladir in + [\\/]* | [A-Za-z]:[\\/]*) abs_ladir="$ladir" ;; + *) + abs_ladir=`cd "$ladir" && pwd` + if test -z "$abs_ladir"; then + $echo "$modename: warning: cannot determine absolute directory name of \`$ladir'" 1>&2 + $echo "$modename: passing it literally to the linker, although it might fail" 1>&2 + abs_ladir="$ladir" + fi + ;; + esac + laname=`$echo "X$lib" | $Xsed -e 's%^.*/%%'` + + # Find the relevant object directory and library name. + if test "X$installed" = Xyes; then + if test ! -f "$libdir/$linklib" && test -f "$abs_ladir/$linklib"; then + $echo "$modename: warning: library \`$lib' was moved." 1>&2 + dir="$ladir" + absdir="$abs_ladir" + libdir="$abs_ladir" + else + dir="$libdir" + absdir="$libdir" + fi + test "X$hardcode_automatic" = Xyes && avoidtemprpath=yes + else + if test ! -f "$ladir/$objdir/$linklib" && test -f "$abs_ladir/$linklib"; then + dir="$ladir" + absdir="$abs_ladir" + # Remove this search path later + notinst_path="$notinst_path $abs_ladir" + else + dir="$ladir/$objdir" + absdir="$abs_ladir/$objdir" + # Remove this search path later + notinst_path="$notinst_path $abs_ladir" + fi + fi # $installed = yes + name=`$echo "X$laname" | $Xsed -e 's/\.la$//' -e 's/^lib//'` + + # This library was specified with -dlpreopen. + if test "$pass" = dlpreopen; then + if test -z "$libdir"; then + $echo "$modename: cannot -dlpreopen a convenience library: \`$lib'" 1>&2 + exit $EXIT_FAILURE + fi + # Prefer using a static library (so that no silly _DYNAMIC symbols + # are required to link). + if test -n "$old_library"; then + newdlprefiles="$newdlprefiles $dir/$old_library" + # Otherwise, use the dlname, so that lt_dlopen finds it. + elif test -n "$dlname"; then + newdlprefiles="$newdlprefiles $dir/$dlname" + else + newdlprefiles="$newdlprefiles $dir/$linklib" + fi + fi # $pass = dlpreopen + + if test -z "$libdir"; then + # Link the convenience library + if test "$linkmode" = lib; then + deplibs="$dir/$old_library $deplibs" + elif test "$linkmode,$pass" = "prog,link"; then + compile_deplibs="$dir/$old_library $compile_deplibs" + finalize_deplibs="$dir/$old_library $finalize_deplibs" + else + deplibs="$lib $deplibs" # used for prog,scan pass + fi + continue + fi + + + if test "$linkmode" = prog && test "$pass" != link; then + newlib_search_path="$newlib_search_path $ladir" + deplibs="$lib $deplibs" + + linkalldeplibs=no + if test "$link_all_deplibs" != no || test -z "$library_names" || + test "$build_libtool_libs" = no; then + linkalldeplibs=yes + fi + + tmp_libs= + for deplib in $dependency_libs; do + case $deplib in + -L*) newlib_search_path="$newlib_search_path "`$echo "X$deplib" | $Xsed -e 's/^-L//'`;; ### testsuite: skip nested quoting test + esac + # Need to link against all dependency_libs? + if test "$linkalldeplibs" = yes; then + deplibs="$deplib $deplibs" + else + # Need to hardcode shared library paths + # or/and link against static libraries + newdependency_libs="$deplib $newdependency_libs" + fi + if test "X$duplicate_deps" = "Xyes" ; then + case "$tmp_libs " in + *" $deplib "*) specialdeplibs="$specialdeplibs $deplib" ;; + esac + fi + tmp_libs="$tmp_libs $deplib" + done # for deplib + continue + fi # $linkmode = prog... + + if test "$linkmode,$pass" = "prog,link"; then + if test -n "$library_names" && + { test "$prefer_static_libs" = no || test -z "$old_library"; }; then + # We need to hardcode the library path + if test -n "$shlibpath_var" && test -z "$avoidtemprpath" ; then + # Make sure the rpath contains only unique directories. + case "$temp_rpath " in + *" $dir "*) ;; + *" $absdir "*) ;; + *) temp_rpath="$temp_rpath $absdir" ;; + esac + fi + + # Hardcode the library path. + # Skip directories that are in the system default run-time + # search path. + case " $sys_lib_dlsearch_path " in + *" $absdir "*) ;; + *) + case "$compile_rpath " in + *" $absdir "*) ;; + *) compile_rpath="$compile_rpath $absdir" + esac + ;; + esac + case " $sys_lib_dlsearch_path " in + *" $libdir "*) ;; + *) + case "$finalize_rpath " in + *" $libdir "*) ;; + *) finalize_rpath="$finalize_rpath $libdir" + esac + ;; + esac + fi # $linkmode,$pass = prog,link... + + if test "$alldeplibs" = yes && + { test "$deplibs_check_method" = pass_all || + { test "$build_libtool_libs" = yes && + test -n "$library_names"; }; }; then + # We only need to search for static libraries + continue + fi + fi + + link_static=no # Whether the deplib will be linked statically + use_static_libs=$prefer_static_libs + if test "$use_static_libs" = built && test "$installed" = yes ; then + use_static_libs=no + fi + if test -n "$library_names" && + { test "$use_static_libs" = no || test -z "$old_library"; }; then + if test "$installed" = no; then + notinst_deplibs="$notinst_deplibs $lib" + need_relink=yes + fi + # This is a shared library + + # Warn about portability, can't link against -module's on + # some systems (darwin) + if test "$shouldnotlink" = yes && test "$pass" = link ; then + $echo + if test "$linkmode" = prog; then + $echo "*** Warning: Linking the executable $output against the loadable module" + else + $echo "*** Warning: Linking the shared library $output against the loadable module" + fi + $echo "*** $linklib is not portable!" + fi + if test "$linkmode" = lib && + test "$hardcode_into_libs" = yes; then + # Hardcode the library path. + # Skip directories that are in the system default run-time + # search path. + case " $sys_lib_dlsearch_path " in + *" $absdir "*) ;; + *) + case "$compile_rpath " in + *" $absdir "*) ;; + *) compile_rpath="$compile_rpath $absdir" + esac + ;; + esac + case " $sys_lib_dlsearch_path " in + *" $libdir "*) ;; + *) + case "$finalize_rpath " in + *" $libdir "*) ;; + *) finalize_rpath="$finalize_rpath $libdir" + esac + ;; + esac + fi + + if test -n "$old_archive_from_expsyms_cmds"; then + # figure out the soname + set dummy $library_names + realname="$2" + shift; shift + libname=`eval \\$echo \"$libname_spec\"` + # use dlname if we got it. it's perfectly good, no? + if test -n "$dlname"; then + soname="$dlname" + elif test -n "$soname_spec"; then + # bleh windows + case $host in + *cygwin* | mingw*) + major=`expr $current - $age` + versuffix="-$major" + ;; + esac + eval soname=\"$soname_spec\" + else + soname="$realname" + fi + + # Make a new name for the extract_expsyms_cmds to use + soroot="$soname" + soname=`$echo $soroot | ${SED} -e 's/^.*\///'` + newlib="libimp-`$echo $soname | ${SED} 's/^lib//;s/\.dll$//'`.a" + + # If the library has no export list, then create one now + if test -f "$output_objdir/$soname-def"; then : + else + $show "extracting exported symbol list from \`$soname'" + save_ifs="$IFS"; IFS='~' + cmds=$extract_expsyms_cmds + for cmd in $cmds; do + IFS="$save_ifs" + eval cmd=\"$cmd\" + $show "$cmd" + $run eval "$cmd" || exit $? + done + IFS="$save_ifs" + fi + + # Create $newlib + if test -f "$output_objdir/$newlib"; then :; else + $show "generating import library for \`$soname'" + save_ifs="$IFS"; IFS='~' + cmds=$old_archive_from_expsyms_cmds + for cmd in $cmds; do + IFS="$save_ifs" + eval cmd=\"$cmd\" + $show "$cmd" + $run eval "$cmd" || exit $? + done + IFS="$save_ifs" + fi + # make sure the library variables are pointing to the new library + dir=$output_objdir + linklib=$newlib + fi # test -n "$old_archive_from_expsyms_cmds" + + if test "$linkmode" = prog || test "$mode" != relink; then + add_shlibpath= + add_dir= + add= + lib_linked=yes + case $hardcode_action in + immediate | unsupported) + if test "$hardcode_direct" = no; then + add="$dir/$linklib" + case $host in + *-*-sco3.2v5.0.[024]*) add_dir="-L$dir" ;; + *-*-sysv4*uw2*) add_dir="-L$dir" ;; + *-*-sysv5OpenUNIX* | *-*-sysv5UnixWare7.[01].[10]* | \ + *-*-unixware7*) add_dir="-L$dir" ;; + *-*-darwin* ) + # if the lib is a module then we can not link against + # it, someone is ignoring the new warnings I added + if /usr/bin/file -L $add 2> /dev/null | + $EGREP ": [^:]* bundle" >/dev/null ; then + $echo "** Warning, lib $linklib is a module, not a shared library" + if test -z "$old_library" ; then + $echo + $echo "** And there doesn't seem to be a static archive available" + $echo "** The link will probably fail, sorry" + else + add="$dir/$old_library" + fi + fi + esac + elif test "$hardcode_minus_L" = no; then + case $host in + *-*-sunos*) add_shlibpath="$dir" ;; + esac + add_dir="-L$dir" + add="-l$name" + elif test "$hardcode_shlibpath_var" = no; then + add_shlibpath="$dir" + add="-l$name" + else + lib_linked=no + fi + ;; + relink) + if test "$hardcode_direct" = yes; then + add="$dir/$linklib" + elif test "$hardcode_minus_L" = yes; then + add_dir="-L$dir" + # Try looking first in the location we're being installed to. + if test -n "$inst_prefix_dir"; then + case $libdir in + [\\/]*) + add_dir="$add_dir -L$inst_prefix_dir$libdir" + ;; + esac + fi + add="-l$name" + elif test "$hardcode_shlibpath_var" = yes; then + add_shlibpath="$dir" + add="-l$name" + else + lib_linked=no + fi + ;; + *) lib_linked=no ;; + esac + + if test "$lib_linked" != yes; then + $echo "$modename: configuration error: unsupported hardcode properties" + exit $EXIT_FAILURE + fi + + if test -n "$add_shlibpath"; then + case :$compile_shlibpath: in + *":$add_shlibpath:"*) ;; + *) compile_shlibpath="$compile_shlibpath$add_shlibpath:" ;; + esac + fi + if test "$linkmode" = prog; then + test -n "$add_dir" && compile_deplibs="$add_dir $compile_deplibs" + test -n "$add" && compile_deplibs="$add $compile_deplibs" + else + test -n "$add_dir" && deplibs="$add_dir $deplibs" + test -n "$add" && deplibs="$add $deplibs" + if test "$hardcode_direct" != yes && \ + test "$hardcode_minus_L" != yes && \ + test "$hardcode_shlibpath_var" = yes; then + case :$finalize_shlibpath: in + *":$libdir:"*) ;; + *) finalize_shlibpath="$finalize_shlibpath$libdir:" ;; + esac + fi + fi + fi + + if test "$linkmode" = prog || test "$mode" = relink; then + add_shlibpath= + add_dir= + add= + # Finalize command for both is simple: just hardcode it. + if test "$hardcode_direct" = yes; then + add="$libdir/$linklib" + elif test "$hardcode_minus_L" = yes; then + add_dir="-L$libdir" + add="-l$name" + elif test "$hardcode_shlibpath_var" = yes; then + case :$finalize_shlibpath: in + *":$libdir:"*) ;; + *) finalize_shlibpath="$finalize_shlibpath$libdir:" ;; + esac + add="-l$name" + elif test "$hardcode_automatic" = yes; then + if test -n "$inst_prefix_dir" && + test -f "$inst_prefix_dir$libdir/$linklib" ; then + add="$inst_prefix_dir$libdir/$linklib" + else + add="$libdir/$linklib" + fi + else + # We cannot seem to hardcode it, guess we'll fake it. + add_dir="-L$libdir" + # Try looking first in the location we're being installed to. + if test -n "$inst_prefix_dir"; then + case $libdir in + [\\/]*) + add_dir="$add_dir -L$inst_prefix_dir$libdir" + ;; + esac + fi + add="-l$name" + fi + + if test "$linkmode" = prog; then + test -n "$add_dir" && finalize_deplibs="$add_dir $finalize_deplibs" + test -n "$add" && finalize_deplibs="$add $finalize_deplibs" + else + test -n "$add_dir" && deplibs="$add_dir $deplibs" + test -n "$add" && deplibs="$add $deplibs" + fi + fi + elif test "$linkmode" = prog; then + # Here we assume that one of hardcode_direct or hardcode_minus_L + # is not unsupported. This is valid on all known static and + # shared platforms. + if test "$hardcode_direct" != unsupported; then + test -n "$old_library" && linklib="$old_library" + compile_deplibs="$dir/$linklib $compile_deplibs" + finalize_deplibs="$dir/$linklib $finalize_deplibs" + else + compile_deplibs="-l$name -L$dir $compile_deplibs" + finalize_deplibs="-l$name -L$dir $finalize_deplibs" + fi + elif test "$build_libtool_libs" = yes; then + # Not a shared library + if test "$deplibs_check_method" != pass_all; then + # We're trying link a shared library against a static one + # but the system doesn't support it. + + # Just print a warning and add the library to dependency_libs so + # that the program can be linked against the static library. + $echo + $echo "*** Warning: This system can not link to static lib archive $lib." + $echo "*** I have the capability to make that library automatically link in when" + $echo "*** you link to this library. But I can only do this if you have a" + $echo "*** shared version of the library, which you do not appear to have." + if test "$module" = yes; then + $echo "*** But as you try to build a module library, libtool will still create " + $echo "*** a static module, that should work as long as the dlopening application" + $echo "*** is linked with the -dlopen flag to resolve symbols at runtime." + if test -z "$global_symbol_pipe"; then + $echo + $echo "*** However, this would only work if libtool was able to extract symbol" + $echo "*** lists from a program, using \`nm' or equivalent, but libtool could" + $echo "*** not find such a program. So, this module is probably useless." + $echo "*** \`nm' from GNU binutils and a full rebuild may help." + fi + if test "$build_old_libs" = no; then + build_libtool_libs=module + build_old_libs=yes + else + build_libtool_libs=no + fi + fi + else + deplibs="$dir/$old_library $deplibs" + link_static=yes + fi + fi # link shared/static library? + + if test "$linkmode" = lib; then + if test -n "$dependency_libs" && + { test "$hardcode_into_libs" != yes || + test "$build_old_libs" = yes || + test "$link_static" = yes; }; then + # Extract -R from dependency_libs + temp_deplibs= + for libdir in $dependency_libs; do + case $libdir in + -R*) temp_xrpath=`$echo "X$libdir" | $Xsed -e 's/^-R//'` + case " $xrpath " in + *" $temp_xrpath "*) ;; + *) xrpath="$xrpath $temp_xrpath";; + esac;; + *) temp_deplibs="$temp_deplibs $libdir";; + esac + done + dependency_libs="$temp_deplibs" + fi + + newlib_search_path="$newlib_search_path $absdir" + # Link against this library + test "$link_static" = no && newdependency_libs="$abs_ladir/$laname $newdependency_libs" + # ... and its dependency_libs + tmp_libs= + for deplib in $dependency_libs; do + newdependency_libs="$deplib $newdependency_libs" + if test "X$duplicate_deps" = "Xyes" ; then + case "$tmp_libs " in + *" $deplib "*) specialdeplibs="$specialdeplibs $deplib" ;; + esac + fi + tmp_libs="$tmp_libs $deplib" + done + + if test "$link_all_deplibs" != no; then + # Add the search paths of all dependency libraries + for deplib in $dependency_libs; do + case $deplib in + -L*) path="$deplib" ;; + *.la) + dir=`$echo "X$deplib" | $Xsed -e 's%/[^/]*$%%'` + test "X$dir" = "X$deplib" && dir="." + # We need an absolute path. + case $dir in + [\\/]* | [A-Za-z]:[\\/]*) absdir="$dir" ;; + *) + absdir=`cd "$dir" && pwd` + if test -z "$absdir"; then + $echo "$modename: warning: cannot determine absolute directory name of \`$dir'" 1>&2 + absdir="$dir" + fi + ;; + esac + if grep "^installed=no" $deplib > /dev/null; then + path="$absdir/$objdir" + else + eval libdir=`${SED} -n -e 's/^libdir=\(.*\)$/\1/p' $deplib` + if test -z "$libdir"; then + $echo "$modename: \`$deplib' is not a valid libtool archive" 1>&2 + exit $EXIT_FAILURE + fi + if test "$absdir" != "$libdir"; then + $echo "$modename: warning: \`$deplib' seems to be moved" 1>&2 + fi + path="$absdir" + fi + depdepl= + case $host in + *-*-darwin*) + # we do not want to link against static libs, + # but need to link against shared + eval deplibrary_names=`${SED} -n -e 's/^library_names=\(.*\)$/\1/p' $deplib` + if test -n "$deplibrary_names" ; then + for tmp in $deplibrary_names ; do + depdepl=$tmp + done + if test -f "$path/$depdepl" ; then + depdepl="$path/$depdepl" + fi + # do not add paths which are already there + case " $newlib_search_path " in + *" $path "*) ;; + *) newlib_search_path="$newlib_search_path $path";; + esac + fi + path="" + ;; + *) + path="-L$path" + ;; + esac + ;; + -l*) + case $host in + *-*-darwin*) + # Again, we only want to link against shared libraries + eval tmp_libs=`$echo "X$deplib" | $Xsed -e "s,^\-l,,"` + for tmp in $newlib_search_path ; do + if test -f "$tmp/lib$tmp_libs.dylib" ; then + eval depdepl="$tmp/lib$tmp_libs.dylib" + break + fi + done + path="" + ;; + *) continue ;; + esac + ;; + *) continue ;; + esac + case " $deplibs " in + *" $path "*) ;; + *) deplibs="$path $deplibs" ;; + esac + case " $deplibs " in + *" $depdepl "*) ;; + *) deplibs="$depdepl $deplibs" ;; + esac + done + fi # link_all_deplibs != no + fi # linkmode = lib + done # for deplib in $libs + dependency_libs="$newdependency_libs" + if test "$pass" = dlpreopen; then + # Link the dlpreopened libraries before other libraries + for deplib in $save_deplibs; do + deplibs="$deplib $deplibs" + done + fi + if test "$pass" != dlopen; then + if test "$pass" != conv; then + # Make sure lib_search_path contains only unique directories. + lib_search_path= + for dir in $newlib_search_path; do + case "$lib_search_path " in + *" $dir "*) ;; + *) lib_search_path="$lib_search_path $dir" ;; + esac + done + newlib_search_path= + fi + + if test "$linkmode,$pass" != "prog,link"; then + vars="deplibs" + else + vars="compile_deplibs finalize_deplibs" + fi + for var in $vars dependency_libs; do + # Add libraries to $var in reverse order + eval tmp_libs=\"\$$var\" + new_libs= + for deplib in $tmp_libs; do + # FIXME: Pedantically, this is the right thing to do, so + # that some nasty dependency loop isn't accidentally + # broken: + #new_libs="$deplib $new_libs" + # Pragmatically, this seems to cause very few problems in + # practice: + case $deplib in + -L*) new_libs="$deplib $new_libs" ;; + -R*) ;; + *) + # And here is the reason: when a library appears more + # than once as an explicit dependence of a library, or + # is implicitly linked in more than once by the + # compiler, it is considered special, and multiple + # occurrences thereof are not removed. Compare this + # with having the same library being listed as a + # dependency of multiple other libraries: in this case, + # we know (pedantically, we assume) the library does not + # need to be listed more than once, so we keep only the + # last copy. This is not always right, but it is rare + # enough that we require users that really mean to play + # such unportable linking tricks to link the library + # using -Wl,-lname, so that libtool does not consider it + # for duplicate removal. + case " $specialdeplibs " in + *" $deplib "*) new_libs="$deplib $new_libs" ;; + *) + case " $new_libs " in + *" $deplib "*) ;; + *) new_libs="$deplib $new_libs" ;; + esac + ;; + esac + ;; + esac + done + tmp_libs= + for deplib in $new_libs; do + case $deplib in + -L*) + case " $tmp_libs " in + *" $deplib "*) ;; + *) tmp_libs="$tmp_libs $deplib" ;; + esac + ;; + *) tmp_libs="$tmp_libs $deplib" ;; + esac + done + eval $var=\"$tmp_libs\" + done # for var + fi + # Last step: remove runtime libs from dependency_libs + # (they stay in deplibs) + tmp_libs= + for i in $dependency_libs ; do + case " $predeps $postdeps $compiler_lib_search_path " in + *" $i "*) + i="" + ;; + esac + if test -n "$i" ; then + tmp_libs="$tmp_libs $i" + fi + done + dependency_libs=$tmp_libs + done # for pass + if test "$linkmode" = prog; then + dlfiles="$newdlfiles" + dlprefiles="$newdlprefiles" + fi + + case $linkmode in + oldlib) + if test -n "$deplibs"; then + $echo "$modename: warning: \`-l' and \`-L' are ignored for archives" 1>&2 + fi + + if test -n "$dlfiles$dlprefiles" || test "$dlself" != no; then + $echo "$modename: warning: \`-dlopen' is ignored for archives" 1>&2 + fi + + if test -n "$rpath"; then + $echo "$modename: warning: \`-rpath' is ignored for archives" 1>&2 + fi + + if test -n "$xrpath"; then + $echo "$modename: warning: \`-R' is ignored for archives" 1>&2 + fi + + if test -n "$vinfo"; then + $echo "$modename: warning: \`-version-info/-version-number' is ignored for archives" 1>&2 + fi + + if test -n "$release"; then + $echo "$modename: warning: \`-release' is ignored for archives" 1>&2 + fi + + if test -n "$export_symbols" || test -n "$export_symbols_regex"; then + $echo "$modename: warning: \`-export-symbols' is ignored for archives" 1>&2 + fi + + # Now set the variables for building old libraries. + build_libtool_libs=no + oldlibs="$output" + objs="$objs$old_deplibs" + ;; + + lib) + # Make sure we only generate libraries of the form `libNAME.la'. + case $outputname in + lib*) + name=`$echo "X$outputname" | $Xsed -e 's/\.la$//' -e 's/^lib//'` + eval shared_ext=\"$shrext_cmds\" + eval libname=\"$libname_spec\" + ;; + *) + if test "$module" = no; then + $echo "$modename: libtool library \`$output' must begin with \`lib'" 1>&2 + $echo "$help" 1>&2 + exit $EXIT_FAILURE + fi + if test "$need_lib_prefix" != no; then + # Add the "lib" prefix for modules if required + name=`$echo "X$outputname" | $Xsed -e 's/\.la$//'` + eval shared_ext=\"$shrext_cmds\" + eval libname=\"$libname_spec\" + else + libname=`$echo "X$outputname" | $Xsed -e 's/\.la$//'` + fi + ;; + esac + + if test -n "$objs"; then + if test "$deplibs_check_method" != pass_all; then + $echo "$modename: cannot build libtool library \`$output' from non-libtool objects on this host:$objs" 2>&1 + exit $EXIT_FAILURE + else + $echo + $echo "*** Warning: Linking the shared library $output against the non-libtool" + $echo "*** objects $objs is not portable!" + libobjs="$libobjs $objs" + fi + fi + + if test "$dlself" != no; then + $echo "$modename: warning: \`-dlopen self' is ignored for libtool libraries" 1>&2 + fi + + set dummy $rpath + if test "$#" -gt 2; then + $echo "$modename: warning: ignoring multiple \`-rpath's for a libtool library" 1>&2 + fi + install_libdir="$2" + + oldlibs= + if test -z "$rpath"; then + if test "$build_libtool_libs" = yes; then + # Building a libtool convenience library. + # Some compilers have problems with a `.al' extension so + # convenience libraries should have the same extension an + # archive normally would. + oldlibs="$output_objdir/$libname.$libext $oldlibs" + build_libtool_libs=convenience + build_old_libs=yes + fi + + if test -n "$vinfo"; then + $echo "$modename: warning: \`-version-info/-version-number' is ignored for convenience libraries" 1>&2 + fi + + if test -n "$release"; then + $echo "$modename: warning: \`-release' is ignored for convenience libraries" 1>&2 + fi + else + + # Parse the version information argument. + save_ifs="$IFS"; IFS=':' + set dummy $vinfo 0 0 0 + IFS="$save_ifs" + + if test -n "$8"; then + $echo "$modename: too many parameters to \`-version-info'" 1>&2 + $echo "$help" 1>&2 + exit $EXIT_FAILURE + fi + + # convert absolute version numbers to libtool ages + # this retains compatibility with .la files and attempts + # to make the code below a bit more comprehensible + + case $vinfo_number in + yes) + number_major="$2" + number_minor="$3" + number_revision="$4" + # + # There are really only two kinds -- those that + # use the current revision as the major version + # and those that subtract age and use age as + # a minor version. But, then there is irix + # which has an extra 1 added just for fun + # + case $version_type in + darwin|linux|osf|windows) + current=`expr $number_major + $number_minor` + age="$number_minor" + revision="$number_revision" + ;; + freebsd-aout|freebsd-elf|sunos) + current="$number_major" + revision="$number_minor" + age="0" + ;; + irix|nonstopux) + current=`expr $number_major + $number_minor - 1` + age="$number_minor" + revision="$number_minor" + ;; + esac + ;; + no) + current="$2" + revision="$3" + age="$4" + ;; + esac + + # Check that each of the things are valid numbers. + case $current in + 0|[1-9]|[1-9][0-9]|[1-9][0-9][0-9]|[1-9][0-9][0-9][0-9]|[1-9][0-9][0-9][0-9][0-9]) ;; + *) + $echo "$modename: CURRENT \`$current' must be a nonnegative integer" 1>&2 + $echo "$modename: \`$vinfo' is not valid version information" 1>&2 + exit $EXIT_FAILURE + ;; + esac + + case $revision in + 0|[1-9]|[1-9][0-9]|[1-9][0-9][0-9]|[1-9][0-9][0-9][0-9]|[1-9][0-9][0-9][0-9][0-9]) ;; + *) + $echo "$modename: REVISION \`$revision' must be a nonnegative integer" 1>&2 + $echo "$modename: \`$vinfo' is not valid version information" 1>&2 + exit $EXIT_FAILURE + ;; + esac + + case $age in + 0|[1-9]|[1-9][0-9]|[1-9][0-9][0-9]|[1-9][0-9][0-9][0-9]|[1-9][0-9][0-9][0-9][0-9]) ;; + *) + $echo "$modename: AGE \`$age' must be a nonnegative integer" 1>&2 + $echo "$modename: \`$vinfo' is not valid version information" 1>&2 + exit $EXIT_FAILURE + ;; + esac + + if test "$age" -gt "$current"; then + $echo "$modename: AGE \`$age' is greater than the current interface number \`$current'" 1>&2 + $echo "$modename: \`$vinfo' is not valid version information" 1>&2 + exit $EXIT_FAILURE + fi + + # Calculate the version variables. + major= + versuffix= + verstring= + case $version_type in + none) ;; + + darwin) + # Like Linux, but with the current version available in + # verstring for coding it into the library header + major=.`expr $current - $age` + versuffix="$major.$age.$revision" + # Darwin ld doesn't like 0 for these options... + minor_current=`expr $current + 1` + verstring="${wl}-compatibility_version ${wl}$minor_current ${wl}-current_version ${wl}$minor_current.$revision" + ;; + + freebsd-aout) + major=".$current" + versuffix=".$current.$revision"; + ;; + + freebsd-elf) + major=".$current" + versuffix=".$current"; + ;; + + irix | nonstopux) + major=`expr $current - $age + 1` + + case $version_type in + nonstopux) verstring_prefix=nonstopux ;; + *) verstring_prefix=sgi ;; + esac + verstring="$verstring_prefix$major.$revision" + + # Add in all the interfaces that we are compatible with. + loop=$revision + while test "$loop" -ne 0; do + iface=`expr $revision - $loop` + loop=`expr $loop - 1` + verstring="$verstring_prefix$major.$iface:$verstring" + done + + # Before this point, $major must not contain `.'. + major=.$major + versuffix="$major.$revision" + ;; + + linux) + major=.`expr $current - $age` + versuffix="$major.$age.$revision" + ;; + + osf) + major=.`expr $current - $age` + versuffix=".$current.$age.$revision" + verstring="$current.$age.$revision" + + # Add in all the interfaces that we are compatible with. + loop=$age + while test "$loop" -ne 0; do + iface=`expr $current - $loop` + loop=`expr $loop - 1` + verstring="$verstring:${iface}.0" + done + + # Make executables depend on our current version. + verstring="$verstring:${current}.0" + ;; + + sunos) + major=".$current" + versuffix=".$current.$revision" + ;; + + windows) + # Use '-' rather than '.', since we only want one + # extension on DOS 8.3 filesystems. + major=`expr $current - $age` + versuffix="-$major" + ;; + + *) + $echo "$modename: unknown library version type \`$version_type'" 1>&2 + $echo "Fatal configuration error. See the $PACKAGE docs for more information." 1>&2 + exit $EXIT_FAILURE + ;; + esac + + # Clear the version info if we defaulted, and they specified a release. + if test -z "$vinfo" && test -n "$release"; then + major= + case $version_type in + darwin) + # we can't check for "0.0" in archive_cmds due to quoting + # problems, so we reset it completely + verstring= + ;; + *) + verstring="0.0" + ;; + esac + if test "$need_version" = no; then + versuffix= + else + versuffix=".0.0" + fi + fi + + # Remove version info from name if versioning should be avoided + if test "$avoid_version" = yes && test "$need_version" = no; then + major= + versuffix= + verstring="" + fi + + # Check to see if the archive will have undefined symbols. + if test "$allow_undefined" = yes; then + if test "$allow_undefined_flag" = unsupported; then + $echo "$modename: warning: undefined symbols not allowed in $host shared libraries" 1>&2 + build_libtool_libs=no + build_old_libs=yes + fi + else + # Don't allow undefined symbols. + allow_undefined_flag="$no_undefined_flag" + fi + fi + + if test "$mode" != relink; then + # Remove our outputs, but don't remove object files since they + # may have been created when compiling PIC objects. + removelist= + tempremovelist=`$echo "$output_objdir/*"` + for p in $tempremovelist; do + case $p in + *.$objext) + ;; + $output_objdir/$outputname | $output_objdir/$libname.* | $output_objdir/${libname}${release}.*) + if test "X$precious_files_regex" != "X"; then + if echo $p | $EGREP -e "$precious_files_regex" >/dev/null 2>&1 + then + continue + fi + fi + removelist="$removelist $p" + ;; + *) ;; + esac + done + if test -n "$removelist"; then + $show "${rm}r $removelist" + $run ${rm}r $removelist + fi + fi + + # Now set the variables for building old libraries. + if test "$build_old_libs" = yes && test "$build_libtool_libs" != convenience ; then + oldlibs="$oldlibs $output_objdir/$libname.$libext" + + # Transform .lo files to .o files. + oldobjs="$objs "`$echo "X$libobjs" | $SP2NL | $Xsed -e '/\.'${libext}'$/d' -e "$lo2o" | $NL2SP` + fi + + # Eliminate all temporary directories. + for path in $notinst_path; do + lib_search_path=`$echo "$lib_search_path " | ${SED} -e "s% $path % %g"` + deplibs=`$echo "$deplibs " | ${SED} -e "s% -L$path % %g"` + dependency_libs=`$echo "$dependency_libs " | ${SED} -e "s% -L$path % %g"` + done + + if test -n "$xrpath"; then + # If the user specified any rpath flags, then add them. + temp_xrpath= + for libdir in $xrpath; do + temp_xrpath="$temp_xrpath -R$libdir" + case "$finalize_rpath " in + *" $libdir "*) ;; + *) finalize_rpath="$finalize_rpath $libdir" ;; + esac + done + if test "$hardcode_into_libs" != yes || test "$build_old_libs" = yes; then + dependency_libs="$temp_xrpath $dependency_libs" + fi + fi + + # Make sure dlfiles contains only unique files that won't be dlpreopened + old_dlfiles="$dlfiles" + dlfiles= + for lib in $old_dlfiles; do + case " $dlprefiles $dlfiles " in + *" $lib "*) ;; + *) dlfiles="$dlfiles $lib" ;; + esac + done + + # Make sure dlprefiles contains only unique files + old_dlprefiles="$dlprefiles" + dlprefiles= + for lib in $old_dlprefiles; do + case "$dlprefiles " in + *" $lib "*) ;; + *) dlprefiles="$dlprefiles $lib" ;; + esac + done + + if test "$build_libtool_libs" = yes; then + if test -n "$rpath"; then + case $host in + *-*-cygwin* | *-*-mingw* | *-*-pw32* | *-*-os2* | *-*-beos*) + # these systems don't actually have a c library (as such)! + ;; + *-*-rhapsody* | *-*-darwin1.[012]) + # Rhapsody C library is in the System framework + deplibs="$deplibs -framework System" + ;; + *-*-netbsd*) + # Don't link with libc until the a.out ld.so is fixed. + ;; + *-*-openbsd* | *-*-freebsd* | *-*-dragonfly*) + # Do not include libc due to us having libc/libc_r. + ;; + *-*-sco3.2v5* | *-*-sco5v6*) + # Causes problems with __ctype + ;; + *-*-sysv4.2uw2* | *-*-sysv5* | *-*-unixware* | *-*-OpenUNIX*) + # Compiler inserts libc in the correct place for threads to work + ;; + *) + # Add libc to deplibs on all other systems if necessary. + if test "$build_libtool_need_lc" = "yes"; then + deplibs="$deplibs -lc" + fi + ;; + esac + fi + + # Transform deplibs into only deplibs that can be linked in shared. + name_save=$name + libname_save=$libname + release_save=$release + versuffix_save=$versuffix + major_save=$major + # I'm not sure if I'm treating the release correctly. I think + # release should show up in the -l (ie -lgmp5) so we don't want to + # add it in twice. Is that correct? + release="" + versuffix="" + major="" + newdeplibs= + droppeddeps=no + case $deplibs_check_method in + pass_all) + # Don't check for shared/static. Everything works. + # This might be a little naive. We might want to check + # whether the library exists or not. But this is on + # osf3 & osf4 and I'm not really sure... Just + # implementing what was already the behavior. + newdeplibs=$deplibs + ;; + test_compile) + # This code stresses the "libraries are programs" paradigm to its + # limits. Maybe even breaks it. We compile a program, linking it + # against the deplibs as a proxy for the library. Then we can check + # whether they linked in statically or dynamically with ldd. + $rm conftest.c + cat > conftest.c </dev/null` + for potent_lib in $potential_libs; do + # Follow soft links. + if ls -lLd "$potent_lib" 2>/dev/null \ + | grep " -> " >/dev/null; then + continue + fi + # The statement above tries to avoid entering an + # endless loop below, in case of cyclic links. + # We might still enter an endless loop, since a link + # loop can be closed while we follow links, + # but so what? + potlib="$potent_lib" + while test -h "$potlib" 2>/dev/null; do + potliblink=`ls -ld $potlib | ${SED} 's/.* -> //'` + case $potliblink in + [\\/]* | [A-Za-z]:[\\/]*) potlib="$potliblink";; + *) potlib=`$echo "X$potlib" | $Xsed -e 's,[^/]*$,,'`"$potliblink";; + esac + done + # It is ok to link against an archive when + # building a shared library. + if $AR -t $potlib > /dev/null 2>&1; then + newdeplibs="$newdeplibs $a_deplib" + a_deplib="" + break 2 + fi + if eval $file_magic_cmd \"\$potlib\" 2>/dev/null \ + | ${SED} 10q \ + | $EGREP "$file_magic_regex" > /dev/null; then + newdeplibs="$newdeplibs $a_deplib" + a_deplib="" + break 2 + fi + done + done + fi + if test -n "$a_deplib" ; then + droppeddeps=yes + $echo + $echo "*** Warning: linker path does not have real file for library $a_deplib." + $echo "*** I have the capability to make that library automatically link in when" + $echo "*** you link to this library. But I can only do this if you have a" + $echo "*** shared version of the library, which you do not appear to have" + $echo "*** because I did check the linker path looking for a file starting" + if test -z "$potlib" ; then + $echo "*** with $libname but no candidates were found. (...for file magic test)" + else + $echo "*** with $libname and none of the candidates passed a file format test" + $echo "*** using a file magic. Last file checked: $potlib" + fi + fi + else + # Add a -L argument. + newdeplibs="$newdeplibs $a_deplib" + fi + done # Gone through all deplibs. + ;; + match_pattern*) + set dummy $deplibs_check_method + match_pattern_regex=`expr "$deplibs_check_method" : "$2 \(.*\)"` + for a_deplib in $deplibs; do + name=`expr $a_deplib : '-l\(.*\)'` + # If $name is empty we are operating on a -L argument. + if test -n "$name" && test "$name" != "0"; then + if test "X$allow_libtool_libs_with_static_runtimes" = "Xyes" ; then + case " $predeps $postdeps " in + *" $a_deplib "*) + newdeplibs="$newdeplibs $a_deplib" + a_deplib="" + ;; + esac + fi + if test -n "$a_deplib" ; then + libname=`eval \\$echo \"$libname_spec\"` + for i in $lib_search_path $sys_lib_search_path $shlib_search_path; do + potential_libs=`ls $i/$libname[.-]* 2>/dev/null` + for potent_lib in $potential_libs; do + potlib="$potent_lib" # see symlink-check above in file_magic test + if eval $echo \"$potent_lib\" 2>/dev/null \ + | ${SED} 10q \ + | $EGREP "$match_pattern_regex" > /dev/null; then + newdeplibs="$newdeplibs $a_deplib" + a_deplib="" + break 2 + fi + done + done + fi + if test -n "$a_deplib" ; then + droppeddeps=yes + $echo + $echo "*** Warning: linker path does not have real file for library $a_deplib." + $echo "*** I have the capability to make that library automatically link in when" + $echo "*** you link to this library. But I can only do this if you have a" + $echo "*** shared version of the library, which you do not appear to have" + $echo "*** because I did check the linker path looking for a file starting" + if test -z "$potlib" ; then + $echo "*** with $libname but no candidates were found. (...for regex pattern test)" + else + $echo "*** with $libname and none of the candidates passed a file format test" + $echo "*** using a regex pattern. Last file checked: $potlib" + fi + fi + else + # Add a -L argument. + newdeplibs="$newdeplibs $a_deplib" + fi + done # Gone through all deplibs. + ;; + none | unknown | *) + newdeplibs="" + tmp_deplibs=`$echo "X $deplibs" | $Xsed -e 's/ -lc$//' \ + -e 's/ -[LR][^ ]*//g'` + if test "X$allow_libtool_libs_with_static_runtimes" = "Xyes" ; then + for i in $predeps $postdeps ; do + # can't use Xsed below, because $i might contain '/' + tmp_deplibs=`$echo "X $tmp_deplibs" | ${SED} -e "1s,^X,," -e "s,$i,,"` + done + fi + if $echo "X $tmp_deplibs" | $Xsed -e 's/[ ]//g' \ + | grep . >/dev/null; then + $echo + if test "X$deplibs_check_method" = "Xnone"; then + $echo "*** Warning: inter-library dependencies are not supported in this platform." + else + $echo "*** Warning: inter-library dependencies are not known to be supported." + fi + $echo "*** All declared inter-library dependencies are being dropped." + droppeddeps=yes + fi + ;; + esac + versuffix=$versuffix_save + major=$major_save + release=$release_save + libname=$libname_save + name=$name_save + + case $host in + *-*-rhapsody* | *-*-darwin1.[012]) + # On Rhapsody replace the C library is the System framework + newdeplibs=`$echo "X $newdeplibs" | $Xsed -e 's/ -lc / -framework System /'` + ;; + esac + + if test "$droppeddeps" = yes; then + if test "$module" = yes; then + $echo + $echo "*** Warning: libtool could not satisfy all declared inter-library" + $echo "*** dependencies of module $libname. Therefore, libtool will create" + $echo "*** a static module, that should work as long as the dlopening" + $echo "*** application is linked with the -dlopen flag." + if test -z "$global_symbol_pipe"; then + $echo + $echo "*** However, this would only work if libtool was able to extract symbol" + $echo "*** lists from a program, using \`nm' or equivalent, but libtool could" + $echo "*** not find such a program. So, this module is probably useless." + $echo "*** \`nm' from GNU binutils and a full rebuild may help." + fi + if test "$build_old_libs" = no; then + oldlibs="$output_objdir/$libname.$libext" + build_libtool_libs=module + build_old_libs=yes + else + build_libtool_libs=no + fi + else + $echo "*** The inter-library dependencies that have been dropped here will be" + $echo "*** automatically added whenever a program is linked with this library" + $echo "*** or is declared to -dlopen it." + + if test "$allow_undefined" = no; then + $echo + $echo "*** Since this library must not contain undefined symbols," + $echo "*** because either the platform does not support them or" + $echo "*** it was explicitly requested with -no-undefined," + $echo "*** libtool will only create a static version of it." + if test "$build_old_libs" = no; then + oldlibs="$output_objdir/$libname.$libext" + build_libtool_libs=module + build_old_libs=yes + else + build_libtool_libs=no + fi + fi + fi + fi + # Done checking deplibs! + deplibs=$newdeplibs + fi + + + # move library search paths that coincide with paths to not yet + # installed libraries to the beginning of the library search list + new_libs= + for path in $notinst_path; do + case " $new_libs " in + *" -L$path/$objdir "*) ;; + *) + case " $deplibs " in + *" -L$path/$objdir "*) + new_libs="$new_libs -L$path/$objdir" ;; + esac + ;; + esac + done + for deplib in $deplibs; do + case $deplib in + -L*) + case " $new_libs " in + *" $deplib "*) ;; + *) new_libs="$new_libs $deplib" ;; + esac + ;; + *) new_libs="$new_libs $deplib" ;; + esac + done + deplibs="$new_libs" + + + # All the library-specific variables (install_libdir is set above). + library_names= + old_library= + dlname= + + # Test again, we may have decided not to build it any more + if test "$build_libtool_libs" = yes; then + if test "$hardcode_into_libs" = yes; then + # Hardcode the library paths + hardcode_libdirs= + dep_rpath= + rpath="$finalize_rpath" + test "$mode" != relink && rpath="$compile_rpath$rpath" + for libdir in $rpath; do + if test -n "$hardcode_libdir_flag_spec"; then + if test -n "$hardcode_libdir_separator"; then + if test -z "$hardcode_libdirs"; then + hardcode_libdirs="$libdir" + else + # Just accumulate the unique libdirs. + case $hardcode_libdir_separator$hardcode_libdirs$hardcode_libdir_separator in + *"$hardcode_libdir_separator$libdir$hardcode_libdir_separator"*) + ;; + *) + hardcode_libdirs="$hardcode_libdirs$hardcode_libdir_separator$libdir" + ;; + esac + fi + else + eval flag=\"$hardcode_libdir_flag_spec\" + dep_rpath="$dep_rpath $flag" + fi + elif test -n "$runpath_var"; then + case "$perm_rpath " in + *" $libdir "*) ;; + *) perm_rpath="$perm_rpath $libdir" ;; + esac + fi + done + # Substitute the hardcoded libdirs into the rpath. + if test -n "$hardcode_libdir_separator" && + test -n "$hardcode_libdirs"; then + libdir="$hardcode_libdirs" + if test -n "$hardcode_libdir_flag_spec_ld"; then + eval dep_rpath=\"$hardcode_libdir_flag_spec_ld\" + else + eval dep_rpath=\"$hardcode_libdir_flag_spec\" + fi + fi + if test -n "$runpath_var" && test -n "$perm_rpath"; then + # We should set the runpath_var. + rpath= + for dir in $perm_rpath; do + rpath="$rpath$dir:" + done + eval "$runpath_var='$rpath\$$runpath_var'; export $runpath_var" + fi + test -n "$dep_rpath" && deplibs="$dep_rpath $deplibs" + fi + + shlibpath="$finalize_shlibpath" + test "$mode" != relink && shlibpath="$compile_shlibpath$shlibpath" + if test -n "$shlibpath"; then + eval "$shlibpath_var='$shlibpath\$$shlibpath_var'; export $shlibpath_var" + fi + + # Get the real and link names of the library. + eval shared_ext=\"$shrext_cmds\" + eval library_names=\"$library_names_spec\" + set dummy $library_names + realname="$2" + shift; shift + + if test -n "$soname_spec"; then + eval soname=\"$soname_spec\" + else + soname="$realname" + fi + if test -z "$dlname"; then + dlname=$soname + fi + + lib="$output_objdir/$realname" + linknames= + for link + do + linknames="$linknames $link" + done + + # Use standard objects if they are pic + test -z "$pic_flag" && libobjs=`$echo "X$libobjs" | $SP2NL | $Xsed -e "$lo2o" | $NL2SP` + + # Prepare the list of exported symbols + if test -z "$export_symbols"; then + if test "$always_export_symbols" = yes || test -n "$export_symbols_regex"; then + $show "generating symbol list for \`$libname.la'" + export_symbols="$output_objdir/$libname.exp" + $run $rm $export_symbols + cmds=$export_symbols_cmds + save_ifs="$IFS"; IFS='~' + for cmd in $cmds; do + IFS="$save_ifs" + eval cmd=\"$cmd\" + if len=`expr "X$cmd" : ".*"` && + test "$len" -le "$max_cmd_len" || test "$max_cmd_len" -le -1; then + $show "$cmd" + $run eval "$cmd" || exit $? + skipped_export=false + else + # The command line is too long to execute in one step. + $show "using reloadable object file for export list..." + skipped_export=: + # Break out early, otherwise skipped_export may be + # set to false by a later but shorter cmd. + break + fi + done + IFS="$save_ifs" + if test -n "$export_symbols_regex"; then + $show "$EGREP -e \"$export_symbols_regex\" \"$export_symbols\" > \"${export_symbols}T\"" + $run eval '$EGREP -e "$export_symbols_regex" "$export_symbols" > "${export_symbols}T"' + $show "$mv \"${export_symbols}T\" \"$export_symbols\"" + $run eval '$mv "${export_symbols}T" "$export_symbols"' + fi + fi + fi + + if test -n "$export_symbols" && test -n "$include_expsyms"; then + $run eval '$echo "X$include_expsyms" | $SP2NL >> "$export_symbols"' + fi + + tmp_deplibs= + for test_deplib in $deplibs; do + case " $convenience " in + *" $test_deplib "*) ;; + *) + tmp_deplibs="$tmp_deplibs $test_deplib" + ;; + esac + done + deplibs="$tmp_deplibs" + + if test -n "$convenience"; then + if test -n "$whole_archive_flag_spec"; then + save_libobjs=$libobjs + eval libobjs=\"\$libobjs $whole_archive_flag_spec\" + else + gentop="$output_objdir/${outputname}x" + generated="$generated $gentop" + + func_extract_archives $gentop $convenience + libobjs="$libobjs $func_extract_archives_result" + fi + fi + + if test "$thread_safe" = yes && test -n "$thread_safe_flag_spec"; then + eval flag=\"$thread_safe_flag_spec\" + linker_flags="$linker_flags $flag" + fi + + # Make a backup of the uninstalled library when relinking + if test "$mode" = relink; then + $run eval '(cd $output_objdir && $rm ${realname}U && $mv $realname ${realname}U)' || exit $? + fi + + # Do each of the archive commands. + if test "$module" = yes && test -n "$module_cmds" ; then + if test -n "$export_symbols" && test -n "$module_expsym_cmds"; then + eval test_cmds=\"$module_expsym_cmds\" + cmds=$module_expsym_cmds + else + eval test_cmds=\"$module_cmds\" + cmds=$module_cmds + fi + else + if test -n "$export_symbols" && test -n "$archive_expsym_cmds"; then + eval test_cmds=\"$archive_expsym_cmds\" + cmds=$archive_expsym_cmds + else + eval test_cmds=\"$archive_cmds\" + cmds=$archive_cmds + fi + fi + + if test "X$skipped_export" != "X:" && + len=`expr "X$test_cmds" : ".*" 2>/dev/null` && + test "$len" -le "$max_cmd_len" || test "$max_cmd_len" -le -1; then + : + else + # The command line is too long to link in one step, link piecewise. + $echo "creating reloadable object files..." + + # Save the value of $output and $libobjs because we want to + # use them later. If we have whole_archive_flag_spec, we + # want to use save_libobjs as it was before + # whole_archive_flag_spec was expanded, because we can't + # assume the linker understands whole_archive_flag_spec. + # This may have to be revisited, in case too many + # convenience libraries get linked in and end up exceeding + # the spec. + if test -z "$convenience" || test -z "$whole_archive_flag_spec"; then + save_libobjs=$libobjs + fi + save_output=$output + output_la=`$echo "X$output" | $Xsed -e "$basename"` + + # Clear the reloadable object creation command queue and + # initialize k to one. + test_cmds= + concat_cmds= + objlist= + delfiles= + last_robj= + k=1 + output=$output_objdir/$output_la-${k}.$objext + # Loop over the list of objects to be linked. + for obj in $save_libobjs + do + eval test_cmds=\"$reload_cmds $objlist $last_robj\" + if test "X$objlist" = X || + { len=`expr "X$test_cmds" : ".*" 2>/dev/null` && + test "$len" -le "$max_cmd_len"; }; then + objlist="$objlist $obj" + else + # The command $test_cmds is almost too long, add a + # command to the queue. + if test "$k" -eq 1 ; then + # The first file doesn't have a previous command to add. + eval concat_cmds=\"$reload_cmds $objlist $last_robj\" + else + # All subsequent reloadable object files will link in + # the last one created. + eval concat_cmds=\"\$concat_cmds~$reload_cmds $objlist $last_robj\" + fi + last_robj=$output_objdir/$output_la-${k}.$objext + k=`expr $k + 1` + output=$output_objdir/$output_la-${k}.$objext + objlist=$obj + len=1 + fi + done + # Handle the remaining objects by creating one last + # reloadable object file. All subsequent reloadable object + # files will link in the last one created. + test -z "$concat_cmds" || concat_cmds=$concat_cmds~ + eval concat_cmds=\"\${concat_cmds}$reload_cmds $objlist $last_robj\" + + if ${skipped_export-false}; then + $show "generating symbol list for \`$libname.la'" + export_symbols="$output_objdir/$libname.exp" + $run $rm $export_symbols + libobjs=$output + # Append the command to create the export file. + eval concat_cmds=\"\$concat_cmds~$export_symbols_cmds\" + fi + + # Set up a command to remove the reloadable object files + # after they are used. + i=0 + while test "$i" -lt "$k" + do + i=`expr $i + 1` + delfiles="$delfiles $output_objdir/$output_la-${i}.$objext" + done + + $echo "creating a temporary reloadable object file: $output" + + # Loop through the commands generated above and execute them. + save_ifs="$IFS"; IFS='~' + for cmd in $concat_cmds; do + IFS="$save_ifs" + $show "$cmd" + $run eval "$cmd" || exit $? + done + IFS="$save_ifs" + + libobjs=$output + # Restore the value of output. + output=$save_output + + if test -n "$convenience" && test -n "$whole_archive_flag_spec"; then + eval libobjs=\"\$libobjs $whole_archive_flag_spec\" + fi + # Expand the library linking commands again to reset the + # value of $libobjs for piecewise linking. + + # Do each of the archive commands. + if test "$module" = yes && test -n "$module_cmds" ; then + if test -n "$export_symbols" && test -n "$module_expsym_cmds"; then + cmds=$module_expsym_cmds + else + cmds=$module_cmds + fi + else + if test -n "$export_symbols" && test -n "$archive_expsym_cmds"; then + cmds=$archive_expsym_cmds + else + cmds=$archive_cmds + fi + fi + + # Append the command to remove the reloadable object files + # to the just-reset $cmds. + eval cmds=\"\$cmds~\$rm $delfiles\" + fi + save_ifs="$IFS"; IFS='~' + for cmd in $cmds; do + IFS="$save_ifs" + eval cmd=\"$cmd\" + $show "$cmd" + $run eval "$cmd" || { + lt_exit=$? + + # Restore the uninstalled library and exit + if test "$mode" = relink; then + $run eval '(cd $output_objdir && $rm ${realname}T && $mv ${realname}U $realname)' + fi + + exit $lt_exit + } + done + IFS="$save_ifs" + + # Restore the uninstalled library and exit + if test "$mode" = relink; then + $run eval '(cd $output_objdir && $rm ${realname}T && $mv $realname ${realname}T && $mv "$realname"U $realname)' || exit $? + + if test -n "$convenience"; then + if test -z "$whole_archive_flag_spec"; then + $show "${rm}r $gentop" + $run ${rm}r "$gentop" + fi + fi + + exit $EXIT_SUCCESS + fi + + # Create links to the real library. + for linkname in $linknames; do + if test "$realname" != "$linkname"; then + $show "(cd $output_objdir && $rm $linkname && $LN_S $realname $linkname)" + $run eval '(cd $output_objdir && $rm $linkname && $LN_S $realname $linkname)' || exit $? + fi + done + + # If -module or -export-dynamic was specified, set the dlname. + if test "$module" = yes || test "$export_dynamic" = yes; then + # On all known operating systems, these are identical. + dlname="$soname" + fi + fi + ;; + + obj) + if test -n "$deplibs"; then + $echo "$modename: warning: \`-l' and \`-L' are ignored for objects" 1>&2 + fi + + if test -n "$dlfiles$dlprefiles" || test "$dlself" != no; then + $echo "$modename: warning: \`-dlopen' is ignored for objects" 1>&2 + fi + + if test -n "$rpath"; then + $echo "$modename: warning: \`-rpath' is ignored for objects" 1>&2 + fi + + if test -n "$xrpath"; then + $echo "$modename: warning: \`-R' is ignored for objects" 1>&2 + fi + + if test -n "$vinfo"; then + $echo "$modename: warning: \`-version-info' is ignored for objects" 1>&2 + fi + + if test -n "$release"; then + $echo "$modename: warning: \`-release' is ignored for objects" 1>&2 + fi + + case $output in + *.lo) + if test -n "$objs$old_deplibs"; then + $echo "$modename: cannot build library object \`$output' from non-libtool objects" 1>&2 + exit $EXIT_FAILURE + fi + libobj="$output" + obj=`$echo "X$output" | $Xsed -e "$lo2o"` + ;; + *) + libobj= + obj="$output" + ;; + esac + + # Delete the old objects. + $run $rm $obj $libobj + + # Objects from convenience libraries. This assumes + # single-version convenience libraries. Whenever we create + # different ones for PIC/non-PIC, this we'll have to duplicate + # the extraction. + reload_conv_objs= + gentop= + # reload_cmds runs $LD directly, so let us get rid of + # -Wl from whole_archive_flag_spec + wl= + + if test -n "$convenience"; then + if test -n "$whole_archive_flag_spec"; then + eval reload_conv_objs=\"\$reload_objs $whole_archive_flag_spec\" + else + gentop="$output_objdir/${obj}x" + generated="$generated $gentop" + + func_extract_archives $gentop $convenience + reload_conv_objs="$reload_objs $func_extract_archives_result" + fi + fi + + # Create the old-style object. + reload_objs="$objs$old_deplibs "`$echo "X$libobjs" | $SP2NL | $Xsed -e '/\.'${libext}$'/d' -e '/\.lib$/d' -e "$lo2o" | $NL2SP`" $reload_conv_objs" ### testsuite: skip nested quoting test + + output="$obj" + cmds=$reload_cmds + save_ifs="$IFS"; IFS='~' + for cmd in $cmds; do + IFS="$save_ifs" + eval cmd=\"$cmd\" + $show "$cmd" + $run eval "$cmd" || exit $? + done + IFS="$save_ifs" + + # Exit if we aren't doing a library object file. + if test -z "$libobj"; then + if test -n "$gentop"; then + $show "${rm}r $gentop" + $run ${rm}r $gentop + fi + + exit $EXIT_SUCCESS + fi + + if test "$build_libtool_libs" != yes; then + if test -n "$gentop"; then + $show "${rm}r $gentop" + $run ${rm}r $gentop + fi + + # Create an invalid libtool object if no PIC, so that we don't + # accidentally link it into a program. + # $show "echo timestamp > $libobj" + # $run eval "echo timestamp > $libobj" || exit $? + exit $EXIT_SUCCESS + fi + + if test -n "$pic_flag" || test "$pic_mode" != default; then + # Only do commands if we really have different PIC objects. + reload_objs="$libobjs $reload_conv_objs" + output="$libobj" + cmds=$reload_cmds + save_ifs="$IFS"; IFS='~' + for cmd in $cmds; do + IFS="$save_ifs" + eval cmd=\"$cmd\" + $show "$cmd" + $run eval "$cmd" || exit $? + done + IFS="$save_ifs" + fi + + if test -n "$gentop"; then + $show "${rm}r $gentop" + $run ${rm}r $gentop + fi + + exit $EXIT_SUCCESS + ;; + + prog) + case $host in + *cygwin*) output=`$echo $output | ${SED} -e 's,.exe$,,;s,$,.exe,'` ;; + esac + if test -n "$vinfo"; then + $echo "$modename: warning: \`-version-info' is ignored for programs" 1>&2 + fi + + if test -n "$release"; then + $echo "$modename: warning: \`-release' is ignored for programs" 1>&2 + fi + + if test "$preload" = yes; then + if test "$dlopen_support" = unknown && test "$dlopen_self" = unknown && + test "$dlopen_self_static" = unknown; then + $echo "$modename: warning: \`AC_LIBTOOL_DLOPEN' not used. Assuming no dlopen support." + fi + fi + + case $host in + *-*-rhapsody* | *-*-darwin1.[012]) + # On Rhapsody replace the C library is the System framework + compile_deplibs=`$echo "X $compile_deplibs" | $Xsed -e 's/ -lc / -framework System /'` + finalize_deplibs=`$echo "X $finalize_deplibs" | $Xsed -e 's/ -lc / -framework System /'` + ;; + esac + + case $host in + *darwin*) + # Don't allow lazy linking, it breaks C++ global constructors + if test "$tagname" = CXX ; then + compile_command="$compile_command ${wl}-bind_at_load" + finalize_command="$finalize_command ${wl}-bind_at_load" + fi + ;; + esac + + + # move library search paths that coincide with paths to not yet + # installed libraries to the beginning of the library search list + new_libs= + for path in $notinst_path; do + case " $new_libs " in + *" -L$path/$objdir "*) ;; + *) + case " $compile_deplibs " in + *" -L$path/$objdir "*) + new_libs="$new_libs -L$path/$objdir" ;; + esac + ;; + esac + done + for deplib in $compile_deplibs; do + case $deplib in + -L*) + case " $new_libs " in + *" $deplib "*) ;; + *) new_libs="$new_libs $deplib" ;; + esac + ;; + *) new_libs="$new_libs $deplib" ;; + esac + done + compile_deplibs="$new_libs" + + + compile_command="$compile_command $compile_deplibs" + finalize_command="$finalize_command $finalize_deplibs" + + if test -n "$rpath$xrpath"; then + # If the user specified any rpath flags, then add them. + for libdir in $rpath $xrpath; do + # This is the magic to use -rpath. + case "$finalize_rpath " in + *" $libdir "*) ;; + *) finalize_rpath="$finalize_rpath $libdir" ;; + esac + done + fi + + # Now hardcode the library paths + rpath= + hardcode_libdirs= + for libdir in $compile_rpath $finalize_rpath; do + if test -n "$hardcode_libdir_flag_spec"; then + if test -n "$hardcode_libdir_separator"; then + if test -z "$hardcode_libdirs"; then + hardcode_libdirs="$libdir" + else + # Just accumulate the unique libdirs. + case $hardcode_libdir_separator$hardcode_libdirs$hardcode_libdir_separator in + *"$hardcode_libdir_separator$libdir$hardcode_libdir_separator"*) + ;; + *) + hardcode_libdirs="$hardcode_libdirs$hardcode_libdir_separator$libdir" + ;; + esac + fi + else + eval flag=\"$hardcode_libdir_flag_spec\" + rpath="$rpath $flag" + fi + elif test -n "$runpath_var"; then + case "$perm_rpath " in + *" $libdir "*) ;; + *) perm_rpath="$perm_rpath $libdir" ;; + esac + fi + case $host in + *-*-cygwin* | *-*-mingw* | *-*-pw32* | *-*-os2*) + testbindir=`$echo "X$libdir" | $Xsed -e 's*/lib$*/bin*'` + case :$dllsearchpath: in + *":$libdir:"*) ;; + *) dllsearchpath="$dllsearchpath:$libdir";; + esac + case :$dllsearchpath: in + *":$testbindir:"*) ;; + *) dllsearchpath="$dllsearchpath:$testbindir";; + esac + ;; + esac + done + # Substitute the hardcoded libdirs into the rpath. + if test -n "$hardcode_libdir_separator" && + test -n "$hardcode_libdirs"; then + libdir="$hardcode_libdirs" + eval rpath=\" $hardcode_libdir_flag_spec\" + fi + compile_rpath="$rpath" + + rpath= + hardcode_libdirs= + for libdir in $finalize_rpath; do + if test -n "$hardcode_libdir_flag_spec"; then + if test -n "$hardcode_libdir_separator"; then + if test -z "$hardcode_libdirs"; then + hardcode_libdirs="$libdir" + else + # Just accumulate the unique libdirs. + case $hardcode_libdir_separator$hardcode_libdirs$hardcode_libdir_separator in + *"$hardcode_libdir_separator$libdir$hardcode_libdir_separator"*) + ;; + *) + hardcode_libdirs="$hardcode_libdirs$hardcode_libdir_separator$libdir" + ;; + esac + fi + else + eval flag=\"$hardcode_libdir_flag_spec\" + rpath="$rpath $flag" + fi + elif test -n "$runpath_var"; then + case "$finalize_perm_rpath " in + *" $libdir "*) ;; + *) finalize_perm_rpath="$finalize_perm_rpath $libdir" ;; + esac + fi + done + # Substitute the hardcoded libdirs into the rpath. + if test -n "$hardcode_libdir_separator" && + test -n "$hardcode_libdirs"; then + libdir="$hardcode_libdirs" + eval rpath=\" $hardcode_libdir_flag_spec\" + fi + finalize_rpath="$rpath" + + if test -n "$libobjs" && test "$build_old_libs" = yes; then + # Transform all the library objects into standard objects. + compile_command=`$echo "X$compile_command" | $SP2NL | $Xsed -e "$lo2o" | $NL2SP` + finalize_command=`$echo "X$finalize_command" | $SP2NL | $Xsed -e "$lo2o" | $NL2SP` + fi + + dlsyms= + if test -n "$dlfiles$dlprefiles" || test "$dlself" != no; then + if test -n "$NM" && test -n "$global_symbol_pipe"; then + dlsyms="${outputname}S.c" + else + $echo "$modename: not configured to extract global symbols from dlpreopened files" 1>&2 + fi + fi + + if test -n "$dlsyms"; then + case $dlsyms in + "") ;; + *.c) + # Discover the nlist of each of the dlfiles. + nlist="$output_objdir/${outputname}.nm" + + $show "$rm $nlist ${nlist}S ${nlist}T" + $run $rm "$nlist" "${nlist}S" "${nlist}T" + + # Parse the name list into a source file. + $show "creating $output_objdir/$dlsyms" + + test -z "$run" && $echo > "$output_objdir/$dlsyms" "\ +/* $dlsyms - symbol resolution table for \`$outputname' dlsym emulation. */ +/* Generated by $PROGRAM - GNU $PACKAGE $VERSION$TIMESTAMP */ + +#ifdef __cplusplus +extern \"C\" { +#endif + +/* Prevent the only kind of declaration conflicts we can make. */ +#define lt_preloaded_symbols some_other_symbol + +/* External symbol declarations for the compiler. */\ +" + + if test "$dlself" = yes; then + $show "generating symbol list for \`$output'" + + test -z "$run" && $echo ': @PROGRAM@ ' > "$nlist" + + # Add our own program objects to the symbol list. + progfiles=`$echo "X$objs$old_deplibs" | $SP2NL | $Xsed -e "$lo2o" | $NL2SP` + for arg in $progfiles; do + $show "extracting global C symbols from \`$arg'" + $run eval "$NM $arg | $global_symbol_pipe >> '$nlist'" + done + + if test -n "$exclude_expsyms"; then + $run eval '$EGREP -v " ($exclude_expsyms)$" "$nlist" > "$nlist"T' + $run eval '$mv "$nlist"T "$nlist"' + fi + + if test -n "$export_symbols_regex"; then + $run eval '$EGREP -e "$export_symbols_regex" "$nlist" > "$nlist"T' + $run eval '$mv "$nlist"T "$nlist"' + fi + + # Prepare the list of exported symbols + if test -z "$export_symbols"; then + export_symbols="$output_objdir/$outputname.exp" + $run $rm $export_symbols + $run eval "${SED} -n -e '/^: @PROGRAM@ $/d' -e 's/^.* \(.*\)$/\1/p' "'< "$nlist" > "$export_symbols"' + case $host in + *cygwin* | *mingw* ) + $run eval "echo EXPORTS "'> "$output_objdir/$outputname.def"' + $run eval 'cat "$export_symbols" >> "$output_objdir/$outputname.def"' + ;; + esac + else + $run eval "${SED} -e 's/\([].[*^$]\)/\\\\\1/g' -e 's/^/ /' -e 's/$/$/'"' < "$export_symbols" > "$output_objdir/$outputname.exp"' + $run eval 'grep -f "$output_objdir/$outputname.exp" < "$nlist" > "$nlist"T' + $run eval 'mv "$nlist"T "$nlist"' + case $host in + *cygwin* | *mingw* ) + $run eval "echo EXPORTS "'> "$output_objdir/$outputname.def"' + $run eval 'cat "$nlist" >> "$output_objdir/$outputname.def"' + ;; + esac + fi + fi + + for arg in $dlprefiles; do + $show "extracting global C symbols from \`$arg'" + name=`$echo "$arg" | ${SED} -e 's%^.*/%%'` + $run eval '$echo ": $name " >> "$nlist"' + $run eval "$NM $arg | $global_symbol_pipe >> '$nlist'" + done + + if test -z "$run"; then + # Make sure we have at least an empty file. + test -f "$nlist" || : > "$nlist" + + if test -n "$exclude_expsyms"; then + $EGREP -v " ($exclude_expsyms)$" "$nlist" > "$nlist"T + $mv "$nlist"T "$nlist" + fi + + # Try sorting and uniquifying the output. + if grep -v "^: " < "$nlist" | + if sort -k 3 /dev/null 2>&1; then + sort -k 3 + else + sort +2 + fi | + uniq > "$nlist"S; then + : + else + grep -v "^: " < "$nlist" > "$nlist"S + fi + + if test -f "$nlist"S; then + eval "$global_symbol_to_cdecl"' < "$nlist"S >> "$output_objdir/$dlsyms"' + else + $echo '/* NONE */' >> "$output_objdir/$dlsyms" + fi + + $echo >> "$output_objdir/$dlsyms" "\ + +#undef lt_preloaded_symbols + +#if defined (__STDC__) && __STDC__ +# define lt_ptr void * +#else +# define lt_ptr char * +# define const +#endif + +/* The mapping between symbol names and symbols. */ +" + + case $host in + *cygwin* | *mingw* ) + $echo >> "$output_objdir/$dlsyms" "\ +/* DATA imports from DLLs on WIN32 can't be const, because + runtime relocations are performed -- see ld's documentation + on pseudo-relocs */ +struct { +" + ;; + * ) + $echo >> "$output_objdir/$dlsyms" "\ +const struct { +" + ;; + esac + + + $echo >> "$output_objdir/$dlsyms" "\ + const char *name; + lt_ptr address; +} +lt_preloaded_symbols[] = +{\ +" + + eval "$global_symbol_to_c_name_address" < "$nlist" >> "$output_objdir/$dlsyms" + + $echo >> "$output_objdir/$dlsyms" "\ + {0, (lt_ptr) 0} +}; + +/* This works around a problem in FreeBSD linker */ +#ifdef FREEBSD_WORKAROUND +static const void *lt_preloaded_setup() { + return lt_preloaded_symbols; +} +#endif + +#ifdef __cplusplus +} +#endif\ +" + fi + + pic_flag_for_symtable= + case $host in + # compiling the symbol table file with pic_flag works around + # a FreeBSD bug that causes programs to crash when -lm is + # linked before any other PIC object. But we must not use + # pic_flag when linking with -static. The problem exists in + # FreeBSD 2.2.6 and is fixed in FreeBSD 3.1. + *-*-freebsd2*|*-*-freebsd3.0*|*-*-freebsdelf3.0*) + case "$compile_command " in + *" -static "*) ;; + *) pic_flag_for_symtable=" $pic_flag -DFREEBSD_WORKAROUND";; + esac;; + *-*-hpux*) + case "$compile_command " in + *" -static "*) ;; + *) pic_flag_for_symtable=" $pic_flag";; + esac + esac + + # Now compile the dynamic symbol file. + $show "(cd $output_objdir && $LTCC $LTCFLAGS -c$no_builtin_flag$pic_flag_for_symtable \"$dlsyms\")" + $run eval '(cd $output_objdir && $LTCC $LTCFLAGS -c$no_builtin_flag$pic_flag_for_symtable "$dlsyms")' || exit $? + + # Clean up the generated files. + $show "$rm $output_objdir/$dlsyms $nlist ${nlist}S ${nlist}T" + $run $rm "$output_objdir/$dlsyms" "$nlist" "${nlist}S" "${nlist}T" + + # Transform the symbol file into the correct name. + case $host in + *cygwin* | *mingw* ) + if test -f "$output_objdir/${outputname}.def" ; then + compile_command=`$echo "X$compile_command" | $Xsed -e "s%@SYMFILE@%$output_objdir/${outputname}.def $output_objdir/${outputname}S.${objext}%"` + finalize_command=`$echo "X$finalize_command" | $Xsed -e "s%@SYMFILE@%$output_objdir/${outputname}.def $output_objdir/${outputname}S.${objext}%"` + else + compile_command=`$echo "X$compile_command" | $Xsed -e "s%@SYMFILE@%$output_objdir/${outputname}S.${objext}%"` + finalize_command=`$echo "X$finalize_command" | $Xsed -e "s%@SYMFILE@%$output_objdir/${outputname}S.${objext}%"` + fi + ;; + * ) + compile_command=`$echo "X$compile_command" | $Xsed -e "s%@SYMFILE@%$output_objdir/${outputname}S.${objext}%"` + finalize_command=`$echo "X$finalize_command" | $Xsed -e "s%@SYMFILE@%$output_objdir/${outputname}S.${objext}%"` + ;; + esac + ;; + *) + $echo "$modename: unknown suffix for \`$dlsyms'" 1>&2 + exit $EXIT_FAILURE + ;; + esac + else + # We keep going just in case the user didn't refer to + # lt_preloaded_symbols. The linker will fail if global_symbol_pipe + # really was required. + + # Nullify the symbol file. + compile_command=`$echo "X$compile_command" | $Xsed -e "s% @SYMFILE@%%"` + finalize_command=`$echo "X$finalize_command" | $Xsed -e "s% @SYMFILE@%%"` + fi + + if test "$need_relink" = no || test "$build_libtool_libs" != yes; then + # Replace the output file specification. + compile_command=`$echo "X$compile_command" | $Xsed -e 's%@OUTPUT@%'"$output"'%g'` + link_command="$compile_command$compile_rpath" + + # We have no uninstalled library dependencies, so finalize right now. + $show "$link_command" + $run eval "$link_command" + exit_status=$? + + # Delete the generated files. + if test -n "$dlsyms"; then + $show "$rm $output_objdir/${outputname}S.${objext}" + $run $rm "$output_objdir/${outputname}S.${objext}" + fi + + exit $exit_status + fi + + if test -n "$shlibpath_var"; then + # We should set the shlibpath_var + rpath= + for dir in $temp_rpath; do + case $dir in + [\\/]* | [A-Za-z]:[\\/]*) + # Absolute path. + rpath="$rpath$dir:" + ;; + *) + # Relative path: add a thisdir entry. + rpath="$rpath\$thisdir/$dir:" + ;; + esac + done + temp_rpath="$rpath" + fi + + if test -n "$compile_shlibpath$finalize_shlibpath"; then + compile_command="$shlibpath_var=\"$compile_shlibpath$finalize_shlibpath\$$shlibpath_var\" $compile_command" + fi + if test -n "$finalize_shlibpath"; then + finalize_command="$shlibpath_var=\"$finalize_shlibpath\$$shlibpath_var\" $finalize_command" + fi + + compile_var= + finalize_var= + if test -n "$runpath_var"; then + if test -n "$perm_rpath"; then + # We should set the runpath_var. + rpath= + for dir in $perm_rpath; do + rpath="$rpath$dir:" + done + compile_var="$runpath_var=\"$rpath\$$runpath_var\" " + fi + if test -n "$finalize_perm_rpath"; then + # We should set the runpath_var. + rpath= + for dir in $finalize_perm_rpath; do + rpath="$rpath$dir:" + done + finalize_var="$runpath_var=\"$rpath\$$runpath_var\" " + fi + fi + + if test "$no_install" = yes; then + # We don't need to create a wrapper script. + link_command="$compile_var$compile_command$compile_rpath" + # Replace the output file specification. + link_command=`$echo "X$link_command" | $Xsed -e 's%@OUTPUT@%'"$output"'%g'` + # Delete the old output file. + $run $rm $output + # Link the executable and exit + $show "$link_command" + $run eval "$link_command" || exit $? + exit $EXIT_SUCCESS + fi + + if test "$hardcode_action" = relink; then + # Fast installation is not supported + link_command="$compile_var$compile_command$compile_rpath" + relink_command="$finalize_var$finalize_command$finalize_rpath" + + $echo "$modename: warning: this platform does not like uninstalled shared libraries" 1>&2 + $echo "$modename: \`$output' will be relinked during installation" 1>&2 + else + if test "$fast_install" != no; then + link_command="$finalize_var$compile_command$finalize_rpath" + if test "$fast_install" = yes; then + relink_command=`$echo "X$compile_var$compile_command$compile_rpath" | $Xsed -e 's%@OUTPUT@%\$progdir/\$file%g'` + else + # fast_install is set to needless + relink_command= + fi + else + link_command="$compile_var$compile_command$compile_rpath" + relink_command="$finalize_var$finalize_command$finalize_rpath" + fi + fi + + # Replace the output file specification. + link_command=`$echo "X$link_command" | $Xsed -e 's%@OUTPUT@%'"$output_objdir/$outputname"'%g'` + + # Delete the old output files. + $run $rm $output $output_objdir/$outputname $output_objdir/lt-$outputname + + $show "$link_command" + $run eval "$link_command" || exit $? + + # Now create the wrapper script. + $show "creating $output" + + # Quote the relink command for shipping. + if test -n "$relink_command"; then + # Preserve any variables that may affect compiler behavior + for var in $variables_saved_for_relink; do + if eval test -z \"\${$var+set}\"; then + relink_command="{ test -z \"\${$var+set}\" || unset $var || { $var=; export $var; }; }; $relink_command" + elif eval var_value=\$$var; test -z "$var_value"; then + relink_command="$var=; export $var; $relink_command" + else + var_value=`$echo "X$var_value" | $Xsed -e "$sed_quote_subst"` + relink_command="$var=\"$var_value\"; export $var; $relink_command" + fi + done + relink_command="(cd `pwd`; $relink_command)" + relink_command=`$echo "X$relink_command" | $Xsed -e "$sed_quote_subst"` + fi + + # Quote $echo for shipping. + if test "X$echo" = "X$SHELL $progpath --fallback-echo"; then + case $progpath in + [\\/]* | [A-Za-z]:[\\/]*) qecho="$SHELL $progpath --fallback-echo";; + *) qecho="$SHELL `pwd`/$progpath --fallback-echo";; + esac + qecho=`$echo "X$qecho" | $Xsed -e "$sed_quote_subst"` + else + qecho=`$echo "X$echo" | $Xsed -e "$sed_quote_subst"` + fi + + # Only actually do things if our run command is non-null. + if test -z "$run"; then + # win32 will think the script is a binary if it has + # a .exe suffix, so we strip it off here. + case $output in + *.exe) output=`$echo $output|${SED} 's,.exe$,,'` ;; + esac + # test for cygwin because mv fails w/o .exe extensions + case $host in + *cygwin*) + exeext=.exe + outputname=`$echo $outputname|${SED} 's,.exe$,,'` ;; + *) exeext= ;; + esac + case $host in + *cygwin* | *mingw* ) + output_name=`basename $output` + output_path=`dirname $output` + cwrappersource="$output_path/$objdir/lt-$output_name.c" + cwrapper="$output_path/$output_name.exe" + $rm $cwrappersource $cwrapper + trap "$rm $cwrappersource $cwrapper; exit $EXIT_FAILURE" 1 2 15 + + cat > $cwrappersource <> $cwrappersource<<"EOF" +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#if defined(PATH_MAX) +# define LT_PATHMAX PATH_MAX +#elif defined(MAXPATHLEN) +# define LT_PATHMAX MAXPATHLEN +#else +# define LT_PATHMAX 1024 +#endif + +#ifndef DIR_SEPARATOR +# define DIR_SEPARATOR '/' +# define PATH_SEPARATOR ':' +#endif + +#if defined (_WIN32) || defined (__MSDOS__) || defined (__DJGPP__) || \ + defined (__OS2__) +# define HAVE_DOS_BASED_FILE_SYSTEM +# ifndef DIR_SEPARATOR_2 +# define DIR_SEPARATOR_2 '\\' +# endif +# ifndef PATH_SEPARATOR_2 +# define PATH_SEPARATOR_2 ';' +# endif +#endif + +#ifndef DIR_SEPARATOR_2 +# define IS_DIR_SEPARATOR(ch) ((ch) == DIR_SEPARATOR) +#else /* DIR_SEPARATOR_2 */ +# define IS_DIR_SEPARATOR(ch) \ + (((ch) == DIR_SEPARATOR) || ((ch) == DIR_SEPARATOR_2)) +#endif /* DIR_SEPARATOR_2 */ + +#ifndef PATH_SEPARATOR_2 +# define IS_PATH_SEPARATOR(ch) ((ch) == PATH_SEPARATOR) +#else /* PATH_SEPARATOR_2 */ +# define IS_PATH_SEPARATOR(ch) ((ch) == PATH_SEPARATOR_2) +#endif /* PATH_SEPARATOR_2 */ + +#define XMALLOC(type, num) ((type *) xmalloc ((num) * sizeof(type))) +#define XFREE(stale) do { \ + if (stale) { free ((void *) stale); stale = 0; } \ +} while (0) + +/* -DDEBUG is fairly common in CFLAGS. */ +#undef DEBUG +#if defined DEBUGWRAPPER +# define DEBUG(format, ...) fprintf(stderr, format, __VA_ARGS__) +#else +# define DEBUG(format, ...) +#endif + +const char *program_name = NULL; + +void * xmalloc (size_t num); +char * xstrdup (const char *string); +const char * base_name (const char *name); +char * find_executable(const char *wrapper); +int check_executable(const char *path); +char * strendzap(char *str, const char *pat); +void lt_fatal (const char *message, ...); + +int +main (int argc, char *argv[]) +{ + char **newargz; + int i; + + program_name = (char *) xstrdup (base_name (argv[0])); + DEBUG("(main) argv[0] : %s\n",argv[0]); + DEBUG("(main) program_name : %s\n",program_name); + newargz = XMALLOC(char *, argc+2); +EOF + + cat >> $cwrappersource <> $cwrappersource <<"EOF" + newargz[1] = find_executable(argv[0]); + if (newargz[1] == NULL) + lt_fatal("Couldn't find %s", argv[0]); + DEBUG("(main) found exe at : %s\n",newargz[1]); + /* we know the script has the same name, without the .exe */ + /* so make sure newargz[1] doesn't end in .exe */ + strendzap(newargz[1],".exe"); + for (i = 1; i < argc; i++) + newargz[i+1] = xstrdup(argv[i]); + newargz[argc+1] = NULL; + + for (i=0; i> $cwrappersource <> $cwrappersource <> $cwrappersource <<"EOF" + return 127; +} + +void * +xmalloc (size_t num) +{ + void * p = (void *) malloc (num); + if (!p) + lt_fatal ("Memory exhausted"); + + return p; +} + +char * +xstrdup (const char *string) +{ + return string ? strcpy ((char *) xmalloc (strlen (string) + 1), string) : NULL +; +} + +const char * +base_name (const char *name) +{ + const char *base; + +#if defined (HAVE_DOS_BASED_FILE_SYSTEM) + /* Skip over the disk name in MSDOS pathnames. */ + if (isalpha ((unsigned char)name[0]) && name[1] == ':') + name += 2; +#endif + + for (base = name; *name; name++) + if (IS_DIR_SEPARATOR (*name)) + base = name + 1; + return base; +} + +int +check_executable(const char * path) +{ + struct stat st; + + DEBUG("(check_executable) : %s\n", path ? (*path ? path : "EMPTY!") : "NULL!"); + if ((!path) || (!*path)) + return 0; + + if ((stat (path, &st) >= 0) && + ( + /* MinGW & native WIN32 do not support S_IXOTH or S_IXGRP */ +#if defined (S_IXOTH) + ((st.st_mode & S_IXOTH) == S_IXOTH) || +#endif +#if defined (S_IXGRP) + ((st.st_mode & S_IXGRP) == S_IXGRP) || +#endif + ((st.st_mode & S_IXUSR) == S_IXUSR)) + ) + return 1; + else + return 0; +} + +/* Searches for the full path of the wrapper. Returns + newly allocated full path name if found, NULL otherwise */ +char * +find_executable (const char* wrapper) +{ + int has_slash = 0; + const char* p; + const char* p_next; + /* static buffer for getcwd */ + char tmp[LT_PATHMAX + 1]; + int tmp_len; + char* concat_name; + + DEBUG("(find_executable) : %s\n", wrapper ? (*wrapper ? wrapper : "EMPTY!") : "NULL!"); + + if ((wrapper == NULL) || (*wrapper == '\0')) + return NULL; + + /* Absolute path? */ +#if defined (HAVE_DOS_BASED_FILE_SYSTEM) + if (isalpha ((unsigned char)wrapper[0]) && wrapper[1] == ':') + { + concat_name = xstrdup (wrapper); + if (check_executable(concat_name)) + return concat_name; + XFREE(concat_name); + } + else + { +#endif + if (IS_DIR_SEPARATOR (wrapper[0])) + { + concat_name = xstrdup (wrapper); + if (check_executable(concat_name)) + return concat_name; + XFREE(concat_name); + } +#if defined (HAVE_DOS_BASED_FILE_SYSTEM) + } +#endif + + for (p = wrapper; *p; p++) + if (*p == '/') + { + has_slash = 1; + break; + } + if (!has_slash) + { + /* no slashes; search PATH */ + const char* path = getenv ("PATH"); + if (path != NULL) + { + for (p = path; *p; p = p_next) + { + const char* q; + size_t p_len; + for (q = p; *q; q++) + if (IS_PATH_SEPARATOR(*q)) + break; + p_len = q - p; + p_next = (*q == '\0' ? q : q + 1); + if (p_len == 0) + { + /* empty path: current directory */ + if (getcwd (tmp, LT_PATHMAX) == NULL) + lt_fatal ("getcwd failed"); + tmp_len = strlen(tmp); + concat_name = XMALLOC(char, tmp_len + 1 + strlen(wrapper) + 1); + memcpy (concat_name, tmp, tmp_len); + concat_name[tmp_len] = '/'; + strcpy (concat_name + tmp_len + 1, wrapper); + } + else + { + concat_name = XMALLOC(char, p_len + 1 + strlen(wrapper) + 1); + memcpy (concat_name, p, p_len); + concat_name[p_len] = '/'; + strcpy (concat_name + p_len + 1, wrapper); + } + if (check_executable(concat_name)) + return concat_name; + XFREE(concat_name); + } + } + /* not found in PATH; assume curdir */ + } + /* Relative path | not found in path: prepend cwd */ + if (getcwd (tmp, LT_PATHMAX) == NULL) + lt_fatal ("getcwd failed"); + tmp_len = strlen(tmp); + concat_name = XMALLOC(char, tmp_len + 1 + strlen(wrapper) + 1); + memcpy (concat_name, tmp, tmp_len); + concat_name[tmp_len] = '/'; + strcpy (concat_name + tmp_len + 1, wrapper); + + if (check_executable(concat_name)) + return concat_name; + XFREE(concat_name); + return NULL; +} + +char * +strendzap(char *str, const char *pat) +{ + size_t len, patlen; + + assert(str != NULL); + assert(pat != NULL); + + len = strlen(str); + patlen = strlen(pat); + + if (patlen <= len) + { + str += len - patlen; + if (strcmp(str, pat) == 0) + *str = '\0'; + } + return str; +} + +static void +lt_error_core (int exit_status, const char * mode, + const char * message, va_list ap) +{ + fprintf (stderr, "%s: %s: ", program_name, mode); + vfprintf (stderr, message, ap); + fprintf (stderr, ".\n"); + + if (exit_status >= 0) + exit (exit_status); +} + +void +lt_fatal (const char *message, ...) +{ + va_list ap; + va_start (ap, message); + lt_error_core (EXIT_FAILURE, "FATAL", message, ap); + va_end (ap); +} +EOF + # we should really use a build-platform specific compiler + # here, but OTOH, the wrappers (shell script and this C one) + # are only useful if you want to execute the "real" binary. + # Since the "real" binary is built for $host, then this + # wrapper might as well be built for $host, too. + $run $LTCC $LTCFLAGS -s -o $cwrapper $cwrappersource + ;; + esac + $rm $output + trap "$rm $output; exit $EXIT_FAILURE" 1 2 15 + + $echo > $output "\ +#! $SHELL + +# $output - temporary wrapper script for $objdir/$outputname +# Generated by $PROGRAM - GNU $PACKAGE $VERSION$TIMESTAMP +# +# The $output program cannot be directly executed until all the libtool +# libraries that it depends on are installed. +# +# This wrapper script should never be moved out of the build directory. +# If it is, it will not operate correctly. + +# Sed substitution that helps us do robust quoting. It backslashifies +# metacharacters that are still active within double-quoted strings. +Xsed='${SED} -e 1s/^X//' +sed_quote_subst='$sed_quote_subst' + +# The HP-UX ksh and POSIX shell print the target directory to stdout +# if CDPATH is set. +(unset CDPATH) >/dev/null 2>&1 && unset CDPATH + +relink_command=\"$relink_command\" + +# This environment variable determines our operation mode. +if test \"\$libtool_install_magic\" = \"$magic\"; then + # install mode needs the following variable: + notinst_deplibs='$notinst_deplibs' +else + # When we are sourced in execute mode, \$file and \$echo are already set. + if test \"\$libtool_execute_magic\" != \"$magic\"; then + echo=\"$qecho\" + file=\"\$0\" + # Make sure echo works. + if test \"X\$1\" = X--no-reexec; then + # Discard the --no-reexec flag, and continue. + shift + elif test \"X\`(\$echo '\t') 2>/dev/null\`\" = 'X\t'; then + # Yippee, \$echo works! + : + else + # Restart under the correct shell, and then maybe \$echo will work. + exec $SHELL \"\$0\" --no-reexec \${1+\"\$@\"} + fi + fi\ +" + $echo >> $output "\ + + # Find the directory that this script lives in. + thisdir=\`\$echo \"X\$file\" | \$Xsed -e 's%/[^/]*$%%'\` + test \"x\$thisdir\" = \"x\$file\" && thisdir=. + + # Follow symbolic links until we get to the real thisdir. + file=\`ls -ld \"\$file\" | ${SED} -n 's/.*-> //p'\` + while test -n \"\$file\"; do + destdir=\`\$echo \"X\$file\" | \$Xsed -e 's%/[^/]*\$%%'\` + + # If there was a directory component, then change thisdir. + if test \"x\$destdir\" != \"x\$file\"; then + case \"\$destdir\" in + [\\\\/]* | [A-Za-z]:[\\\\/]*) thisdir=\"\$destdir\" ;; + *) thisdir=\"\$thisdir/\$destdir\" ;; + esac + fi + + file=\`\$echo \"X\$file\" | \$Xsed -e 's%^.*/%%'\` + file=\`ls -ld \"\$thisdir/\$file\" | ${SED} -n 's/.*-> //p'\` + done + + # Try to get the absolute directory name. + absdir=\`cd \"\$thisdir\" && pwd\` + test -n \"\$absdir\" && thisdir=\"\$absdir\" +" + + if test "$fast_install" = yes; then + $echo >> $output "\ + program=lt-'$outputname'$exeext + progdir=\"\$thisdir/$objdir\" + + if test ! -f \"\$progdir/\$program\" || \\ + { file=\`ls -1dt \"\$progdir/\$program\" \"\$progdir/../\$program\" 2>/dev/null | ${SED} 1q\`; \\ + test \"X\$file\" != \"X\$progdir/\$program\"; }; then + + file=\"\$\$-\$program\" + + if test ! -d \"\$progdir\"; then + $mkdir \"\$progdir\" + else + $rm \"\$progdir/\$file\" + fi" + + $echo >> $output "\ + + # relink executable if necessary + if test -n \"\$relink_command\"; then + if relink_command_output=\`eval \$relink_command 2>&1\`; then : + else + $echo \"\$relink_command_output\" >&2 + $rm \"\$progdir/\$file\" + exit $EXIT_FAILURE + fi + fi + + $mv \"\$progdir/\$file\" \"\$progdir/\$program\" 2>/dev/null || + { $rm \"\$progdir/\$program\"; + $mv \"\$progdir/\$file\" \"\$progdir/\$program\"; } + $rm \"\$progdir/\$file\" + fi" + else + $echo >> $output "\ + program='$outputname' + progdir=\"\$thisdir/$objdir\" +" + fi + + $echo >> $output "\ + + if test -f \"\$progdir/\$program\"; then" + + # Export our shlibpath_var if we have one. + if test "$shlibpath_overrides_runpath" = yes && test -n "$shlibpath_var" && test -n "$temp_rpath"; then + $echo >> $output "\ + # Add our own library path to $shlibpath_var + $shlibpath_var=\"$temp_rpath\$$shlibpath_var\" + + # Some systems cannot cope with colon-terminated $shlibpath_var + # The second colon is a workaround for a bug in BeOS R4 sed + $shlibpath_var=\`\$echo \"X\$$shlibpath_var\" | \$Xsed -e 's/::*\$//'\` + + export $shlibpath_var +" + fi + + # fixup the dll searchpath if we need to. + if test -n "$dllsearchpath"; then + $echo >> $output "\ + # Add the dll search path components to the executable PATH + PATH=$dllsearchpath:\$PATH +" + fi + + $echo >> $output "\ + if test \"\$libtool_execute_magic\" != \"$magic\"; then + # Run the actual program with our arguments. + + # Make sure env LD_LIBRARY_PATH does not mess us up + if test -n \"\${LD_LIBRARY_PATH+set}\"; then + export LD_LIBRARY_PATH=\$progdir:\$LD_LIBRARY_PATH + fi +" + case $host in + # Backslashes separate directories on plain windows + *-*-mingw | *-*-os2*) + $echo >> $output "\ + exec \"\$progdir\\\\\$program\" \${1+\"\$@\"} +" + ;; + + *) + $echo >> $output "\ + exec \"\$progdir/\$program\" \${1+\"\$@\"} +" + ;; + esac + $echo >> $output "\ + \$echo \"\$0: cannot exec \$program \${1+\"\$@\"}\" + exit $EXIT_FAILURE + fi + else + # The program doesn't exist. + \$echo \"\$0: error: \\\`\$progdir/\$program' does not exist\" 1>&2 + \$echo \"This script is just a wrapper for \$program.\" 1>&2 + $echo \"See the $PACKAGE documentation for more information.\" 1>&2 + exit $EXIT_FAILURE + fi +fi\ +" + chmod +x $output + fi + exit $EXIT_SUCCESS + ;; + esac + + # See if we need to build an old-fashioned archive. + for oldlib in $oldlibs; do + + if test "$build_libtool_libs" = convenience; then + oldobjs="$libobjs_save" + addlibs="$convenience" + build_libtool_libs=no + else + if test "$build_libtool_libs" = module; then + oldobjs="$libobjs_save" + build_libtool_libs=no + else + oldobjs="$old_deplibs $non_pic_objects" + fi + addlibs="$old_convenience" + fi + + if test -n "$addlibs"; then + gentop="$output_objdir/${outputname}x" + generated="$generated $gentop" + + func_extract_archives $gentop $addlibs + oldobjs="$oldobjs $func_extract_archives_result" + fi + + # Do each command in the archive commands. + if test -n "$old_archive_from_new_cmds" && test "$build_libtool_libs" = yes; then + cmds=$old_archive_from_new_cmds + else + # POSIX demands no paths to be encoded in archives. We have + # to avoid creating archives with duplicate basenames if we + # might have to extract them afterwards, e.g., when creating a + # static archive out of a convenience library, or when linking + # the entirety of a libtool archive into another (currently + # not supported by libtool). + if (for obj in $oldobjs + do + $echo "X$obj" | $Xsed -e 's%^.*/%%' + done | sort | sort -uc >/dev/null 2>&1); then + : + else + $echo "copying selected object files to avoid basename conflicts..." + + if test -z "$gentop"; then + gentop="$output_objdir/${outputname}x" + generated="$generated $gentop" + + $show "${rm}r $gentop" + $run ${rm}r "$gentop" + $show "$mkdir $gentop" + $run $mkdir "$gentop" + exit_status=$? + if test "$exit_status" -ne 0 && test ! -d "$gentop"; then + exit $exit_status + fi + fi + + save_oldobjs=$oldobjs + oldobjs= + counter=1 + for obj in $save_oldobjs + do + objbase=`$echo "X$obj" | $Xsed -e 's%^.*/%%'` + case " $oldobjs " in + " ") oldobjs=$obj ;; + *[\ /]"$objbase "*) + while :; do + # Make sure we don't pick an alternate name that also + # overlaps. + newobj=lt$counter-$objbase + counter=`expr $counter + 1` + case " $oldobjs " in + *[\ /]"$newobj "*) ;; + *) if test ! -f "$gentop/$newobj"; then break; fi ;; + esac + done + $show "ln $obj $gentop/$newobj || cp $obj $gentop/$newobj" + $run ln "$obj" "$gentop/$newobj" || + $run cp "$obj" "$gentop/$newobj" + oldobjs="$oldobjs $gentop/$newobj" + ;; + *) oldobjs="$oldobjs $obj" ;; + esac + done + fi + + eval cmds=\"$old_archive_cmds\" + + if len=`expr "X$cmds" : ".*"` && + test "$len" -le "$max_cmd_len" || test "$max_cmd_len" -le -1; then + cmds=$old_archive_cmds + else + # the command line is too long to link in one step, link in parts + $echo "using piecewise archive linking..." + save_RANLIB=$RANLIB + RANLIB=: + objlist= + concat_cmds= + save_oldobjs=$oldobjs + + # Is there a better way of finding the last object in the list? + for obj in $save_oldobjs + do + last_oldobj=$obj + done + for obj in $save_oldobjs + do + oldobjs="$objlist $obj" + objlist="$objlist $obj" + eval test_cmds=\"$old_archive_cmds\" + if len=`expr "X$test_cmds" : ".*" 2>/dev/null` && + test "$len" -le "$max_cmd_len"; then + : + else + # the above command should be used before it gets too long + oldobjs=$objlist + if test "$obj" = "$last_oldobj" ; then + RANLIB=$save_RANLIB + fi + test -z "$concat_cmds" || concat_cmds=$concat_cmds~ + eval concat_cmds=\"\${concat_cmds}$old_archive_cmds\" + objlist= + fi + done + RANLIB=$save_RANLIB + oldobjs=$objlist + if test "X$oldobjs" = "X" ; then + eval cmds=\"\$concat_cmds\" + else + eval cmds=\"\$concat_cmds~\$old_archive_cmds\" + fi + fi + fi + save_ifs="$IFS"; IFS='~' + for cmd in $cmds; do + eval cmd=\"$cmd\" + IFS="$save_ifs" + $show "$cmd" + $run eval "$cmd" || exit $? + done + IFS="$save_ifs" + done + + if test -n "$generated"; then + $show "${rm}r$generated" + $run ${rm}r$generated + fi + + # Now create the libtool archive. + case $output in + *.la) + old_library= + test "$build_old_libs" = yes && old_library="$libname.$libext" + $show "creating $output" + + # Preserve any variables that may affect compiler behavior + for var in $variables_saved_for_relink; do + if eval test -z \"\${$var+set}\"; then + relink_command="{ test -z \"\${$var+set}\" || unset $var || { $var=; export $var; }; }; $relink_command" + elif eval var_value=\$$var; test -z "$var_value"; then + relink_command="$var=; export $var; $relink_command" + else + var_value=`$echo "X$var_value" | $Xsed -e "$sed_quote_subst"` + relink_command="$var=\"$var_value\"; export $var; $relink_command" + fi + done + # Quote the link command for shipping. + relink_command="(cd `pwd`; $SHELL $progpath $preserve_args --mode=relink $libtool_args @inst_prefix_dir@)" + relink_command=`$echo "X$relink_command" | $Xsed -e "$sed_quote_subst"` + if test "$hardcode_automatic" = yes ; then + relink_command= + fi + + + # Only create the output if not a dry run. + if test -z "$run"; then + for installed in no yes; do + if test "$installed" = yes; then + if test -z "$install_libdir"; then + break + fi + output="$output_objdir/$outputname"i + # Replace all uninstalled libtool libraries with the installed ones + newdependency_libs= + for deplib in $dependency_libs; do + case $deplib in + *.la) + name=`$echo "X$deplib" | $Xsed -e 's%^.*/%%'` + eval libdir=`${SED} -n -e 's/^libdir=\(.*\)$/\1/p' $deplib` + if test -z "$libdir"; then + $echo "$modename: \`$deplib' is not a valid libtool archive" 1>&2 + exit $EXIT_FAILURE + fi + if test "X$EGREP" = X ; then + EGREP=egrep + fi + # We do not want portage's install root ($D) present. Check only for + # this if the .la is being installed. + if test "$installed" = yes && test "$D"; then + eval mynewdependency_lib=`echo "$libdir/$name" |sed -e "s:$D:/:g" -e 's:/\+:/:g'` + else + mynewdependency_lib="$libdir/$name" + fi + # Do not add duplicates + if test "$mynewdependency_lib"; then + my_little_ninja_foo_1=`echo $newdependency_libs |$EGREP -e "$mynewdependency_lib"` + if test -z "$my_little_ninja_foo_1"; then + newdependency_libs="$newdependency_libs $mynewdependency_lib" + fi + fi + ;; + *) + if test "$installed" = yes; then + # Rather use S=WORKDIR if our version of portage supports it. + # This is because some ebuild (gcc) do not use $S as buildroot. + if test "$PWORKDIR"; then + S="$PWORKDIR" + fi + # We do not want portage's build root ($S) present. + my_little_ninja_foo_2=`echo $deplib |$EGREP -e "$S"` + # We do not want portage's install root ($D) present. + my_little_ninja_foo_3=`echo $deplib |$EGREP -e "$D"` + if test -n "$my_little_ninja_foo_2" && test "$S"; then + mynewdependency_lib="" + elif test -n "$my_little_ninja_foo_3" && test "$D"; then + eval mynewdependency_lib=`echo "$deplib" |sed -e "s:$D:/:g" -e 's:/\+:/:g'` + else + mynewdependency_lib="$deplib" + fi + else + mynewdependency_lib="$deplib" + fi + # Do not add duplicates + if test "$mynewdependency_lib"; then + my_little_ninja_foo_4=`echo $newdependency_libs |$EGREP -e "$mynewdependency_lib"` + if test -z "$my_little_ninja_foo_4"; then + newdependency_libs="$newdependency_libs $mynewdependency_lib" + fi + fi + ;; + esac + done + dependency_libs="$newdependency_libs" + newdlfiles= + for lib in $dlfiles; do + name=`$echo "X$lib" | $Xsed -e 's%^.*/%%'` + eval libdir=`${SED} -n -e 's/^libdir=\(.*\)$/\1/p' $lib` + if test -z "$libdir"; then + $echo "$modename: \`$lib' is not a valid libtool archive" 1>&2 + exit $EXIT_FAILURE + fi + newdlfiles="$newdlfiles $libdir/$name" + done + dlfiles="$newdlfiles" + newdlprefiles= + for lib in $dlprefiles; do + name=`$echo "X$lib" | $Xsed -e 's%^.*/%%'` + eval libdir=`${SED} -n -e 's/^libdir=\(.*\)$/\1/p' $lib` + if test -z "$libdir"; then + $echo "$modename: \`$lib' is not a valid libtool archive" 1>&2 + exit $EXIT_FAILURE + fi + newdlprefiles="$newdlprefiles $libdir/$name" + done + dlprefiles="$newdlprefiles" + else + newdlfiles= + for lib in $dlfiles; do + case $lib in + [\\/]* | [A-Za-z]:[\\/]*) abs="$lib" ;; + *) abs=`pwd`"/$lib" ;; + esac + newdlfiles="$newdlfiles $abs" + done + dlfiles="$newdlfiles" + newdlprefiles= + for lib in $dlprefiles; do + case $lib in + [\\/]* | [A-Za-z]:[\\/]*) abs="$lib" ;; + *) abs=`pwd`"/$lib" ;; + esac + newdlprefiles="$newdlprefiles $abs" + done + dlprefiles="$newdlprefiles" + fi + $rm $output + # place dlname in correct position for cygwin + tdlname=$dlname + case $host,$output,$installed,$module,$dlname in + *cygwin*,*lai,yes,no,*.dll | *mingw*,*lai,yes,no,*.dll) tdlname=../bin/$dlname ;; + esac + # Do not add duplicates + if test "$installed" = yes && test "$D"; then + install_libdir=`echo "$install_libdir" |sed -e "s:$D:/:g" -e 's:/\+:/:g'` + fi + $echo > $output "\ +# $outputname - a libtool library file +# Generated by $PROGRAM - GNU $PACKAGE $VERSION$TIMESTAMP +# +# Please DO NOT delete this file! +# It is necessary for linking the library. + +# The name that we can dlopen(3). +dlname='$tdlname' + +# Names of this library. +library_names='$library_names' + +# The name of the static archive. +old_library='$old_library' + +# Libraries that this one depends upon. +dependency_libs='$dependency_libs' + +# Version information for $libname. +current=$current +age=$age +revision=$revision + +# Is this an already installed library? +installed=$installed + +# Should we warn about portability when linking against -modules? +shouldnotlink=$module + +# Files to dlopen/dlpreopen +dlopen='$dlfiles' +dlpreopen='$dlprefiles' + +# Directory that this library needs to be installed in: +libdir='$install_libdir'" + if test "$installed" = no && test "$need_relink" = yes; then + $echo >> $output "\ +relink_command=\"$relink_command\"" + fi + done + fi + + # Do a symbolic link so that the libtool archive can be found in + # LD_LIBRARY_PATH before the program is installed. + $show "(cd $output_objdir && $rm $outputname && $LN_S ../$outputname $outputname)" + $run eval '(cd $output_objdir && $rm $outputname && $LN_S ../$outputname $outputname)' || exit $? + ;; + esac + exit $EXIT_SUCCESS + ;; + + # libtool install mode + install) + modename="$modename: install" + + # There may be an optional sh(1) argument at the beginning of + # install_prog (especially on Windows NT). + if test "$nonopt" = "$SHELL" || test "$nonopt" = /bin/sh || + # Allow the use of GNU shtool's install command. + $echo "X$nonopt" | grep shtool > /dev/null; then + # Aesthetically quote it. + arg=`$echo "X$nonopt" | $Xsed -e "$sed_quote_subst"` + case $arg in + *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") + arg="\"$arg\"" + ;; + esac + install_prog="$arg " + arg="$1" + shift + else + install_prog= + arg=$nonopt + fi + + # The real first argument should be the name of the installation program. + # Aesthetically quote it. + arg=`$echo "X$arg" | $Xsed -e "$sed_quote_subst"` + case $arg in + *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") + arg="\"$arg\"" + ;; + esac + install_prog="$install_prog$arg" + + # We need to accept at least all the BSD install flags. + dest= + files= + opts= + prev= + install_type= + isdir=no + stripme= + for arg + do + if test -n "$dest"; then + files="$files $dest" + dest=$arg + continue + fi + + case $arg in + -d) isdir=yes ;; + -f) + case " $install_prog " in + *[\\\ /]cp\ *) ;; + *) prev=$arg ;; + esac + ;; + -g | -m | -o) prev=$arg ;; + -s) + stripme=" -s" + continue + ;; + -*) + ;; + *) + # If the previous option needed an argument, then skip it. + if test -n "$prev"; then + prev= + else + dest=$arg + continue + fi + ;; + esac + + # Aesthetically quote the argument. + arg=`$echo "X$arg" | $Xsed -e "$sed_quote_subst"` + case $arg in + *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") + arg="\"$arg\"" + ;; + esac + install_prog="$install_prog $arg" + done + + if test -z "$install_prog"; then + $echo "$modename: you must specify an install program" 1>&2 + $echo "$help" 1>&2 + exit $EXIT_FAILURE + fi + + if test -n "$prev"; then + $echo "$modename: the \`$prev' option requires an argument" 1>&2 + $echo "$help" 1>&2 + exit $EXIT_FAILURE + fi + + if test -z "$files"; then + if test -z "$dest"; then + $echo "$modename: no file or destination specified" 1>&2 + else + $echo "$modename: you must specify a destination" 1>&2 + fi + $echo "$help" 1>&2 + exit $EXIT_FAILURE + fi + + # Strip any trailing slash from the destination. + dest=`$echo "X$dest" | $Xsed -e 's%/$%%'` + + # Check to see that the destination is a directory. + test -d "$dest" && isdir=yes + if test "$isdir" = yes; then + destdir="$dest" + destname= + else + destdir=`$echo "X$dest" | $Xsed -e 's%/[^/]*$%%'` + test "X$destdir" = "X$dest" && destdir=. + destname=`$echo "X$dest" | $Xsed -e 's%^.*/%%'` + + # Not a directory, so check to see that there is only one file specified. + set dummy $files + if test "$#" -gt 2; then + $echo "$modename: \`$dest' is not a directory" 1>&2 + $echo "$help" 1>&2 + exit $EXIT_FAILURE + fi + fi + case $destdir in + [\\/]* | [A-Za-z]:[\\/]*) ;; + *) + for file in $files; do + case $file in + *.lo) ;; + *) + $echo "$modename: \`$destdir' must be an absolute directory name" 1>&2 + $echo "$help" 1>&2 + exit $EXIT_FAILURE + ;; + esac + done + ;; + esac + + # This variable tells wrapper scripts just to set variables rather + # than running their programs. + libtool_install_magic="$magic" + + staticlibs= + future_libdirs= + current_libdirs= + for file in $files; do + + # Do each installation. + case $file in + *.$libext) + # Do the static libraries later. + staticlibs="$staticlibs $file" + ;; + + *.la) + # Check to see that this really is a libtool archive. + if (${SED} -e '2q' $file | grep "^# Generated by .*$PACKAGE") >/dev/null 2>&1; then : + else + $echo "$modename: \`$file' is not a valid libtool archive" 1>&2 + $echo "$help" 1>&2 + exit $EXIT_FAILURE + fi + + library_names= + old_library= + relink_command= + # If there is no directory component, then add one. + case $file in + */* | *\\*) . $file ;; + *) . ./$file ;; + esac + + # Add the libdir to current_libdirs if it is the destination. + if test "X$destdir" = "X$libdir"; then + case "$current_libdirs " in + *" $libdir "*) ;; + *) current_libdirs="$current_libdirs $libdir" ;; + esac + else + # Note the libdir as a future libdir. + case "$future_libdirs " in + *" $libdir "*) ;; + *) future_libdirs="$future_libdirs $libdir" ;; + esac + fi + + dir=`$echo "X$file" | $Xsed -e 's%/[^/]*$%%'`/ + test "X$dir" = "X$file/" && dir= + dir="$dir$objdir" + + if test -n "$relink_command"; then + # Determine the prefix the user has applied to our future dir. + inst_prefix_dir=`$echo "$destdir" | $SED "s%$libdir\$%%"` + + # Don't allow the user to place us outside of our expected + # location b/c this prevents finding dependent libraries that + # are installed to the same prefix. + # At present, this check doesn't affect windows .dll's that + # are installed into $libdir/../bin (currently, that works fine) + # but it's something to keep an eye on. + if test "$inst_prefix_dir" = "$destdir"; then + $echo "$modename: error: cannot install \`$file' to a directory not ending in $libdir" 1>&2 + exit $EXIT_FAILURE + fi + + if test -n "$inst_prefix_dir"; then + # Stick the inst_prefix_dir data into the link command. + relink_command=`$echo "$relink_command" | $SED "s%@inst_prefix_dir@%-inst-prefix-dir $inst_prefix_dir%"` + else + relink_command=`$echo "$relink_command" | $SED "s%@inst_prefix_dir@%%"` + fi + + $echo "$modename: warning: relinking \`$file'" 1>&2 + $show "$relink_command" + if $run eval "$relink_command"; then : + else + $echo "$modename: error: relink \`$file' with the above command before installing it" 1>&2 + exit $EXIT_FAILURE + fi + fi + + # See the names of the shared library. + set dummy $library_names + if test -n "$2"; then + realname="$2" + shift + shift + + srcname="$realname" + test -n "$relink_command" && srcname="$realname"T + + # Install the shared library and build the symlinks. + $show "$install_prog $dir/$srcname $destdir/$realname" + $run eval "$install_prog $dir/$srcname $destdir/$realname" || exit $? + if test -n "$stripme" && test -n "$striplib"; then + $show "$striplib $destdir/$realname" + $run eval "$striplib $destdir/$realname" || exit $? + fi + + if test "$#" -gt 0; then + # Delete the old symlinks, and create new ones. + # Try `ln -sf' first, because the `ln' binary might depend on + # the symlink we replace! Solaris /bin/ln does not understand -f, + # so we also need to try rm && ln -s. + for linkname + do + if test "$linkname" != "$realname"; then + $show "(cd $destdir && { $LN_S -f $realname $linkname || { $rm $linkname && $LN_S $realname $linkname; }; })" + $run eval "(cd $destdir && { $LN_S -f $realname $linkname || { $rm $linkname && $LN_S $realname $linkname; }; })" + fi + done + fi + + # Do each command in the postinstall commands. + lib="$destdir/$realname" + cmds=$postinstall_cmds + save_ifs="$IFS"; IFS='~' + for cmd in $cmds; do + IFS="$save_ifs" + eval cmd=\"$cmd\" + $show "$cmd" + $run eval "$cmd" || { + lt_exit=$? + + # Restore the uninstalled library and exit + if test "$mode" = relink; then + $run eval '(cd $output_objdir && $rm ${realname}T && $mv ${realname}U $realname)' + fi + + exit $lt_exit + } + done + IFS="$save_ifs" + fi + + # Install the pseudo-library for information purposes. + name=`$echo "X$file" | $Xsed -e 's%^.*/%%'` + instname="$dir/$name"i + $show "$install_prog $instname $destdir/$name" + $run eval "$install_prog $instname $destdir/$name" || exit $? + + # Maybe install the static library, too. + test -n "$old_library" && staticlibs="$staticlibs $dir/$old_library" + ;; + + *.lo) + # Install (i.e. copy) a libtool object. + + # Figure out destination file name, if it wasn't already specified. + if test -n "$destname"; then + destfile="$destdir/$destname" + else + destfile=`$echo "X$file" | $Xsed -e 's%^.*/%%'` + destfile="$destdir/$destfile" + fi + + # Deduce the name of the destination old-style object file. + case $destfile in + *.lo) + staticdest=`$echo "X$destfile" | $Xsed -e "$lo2o"` + ;; + *.$objext) + staticdest="$destfile" + destfile= + ;; + *) + $echo "$modename: cannot copy a libtool object to \`$destfile'" 1>&2 + $echo "$help" 1>&2 + exit $EXIT_FAILURE + ;; + esac + + # Install the libtool object if requested. + if test -n "$destfile"; then + $show "$install_prog $file $destfile" + $run eval "$install_prog $file $destfile" || exit $? + fi + + # Install the old object if enabled. + if test "$build_old_libs" = yes; then + # Deduce the name of the old-style object file. + staticobj=`$echo "X$file" | $Xsed -e "$lo2o"` + + $show "$install_prog $staticobj $staticdest" + $run eval "$install_prog \$staticobj \$staticdest" || exit $? + fi + exit $EXIT_SUCCESS + ;; + + *) + # Figure out destination file name, if it wasn't already specified. + if test -n "$destname"; then + destfile="$destdir/$destname" + else + destfile=`$echo "X$file" | $Xsed -e 's%^.*/%%'` + destfile="$destdir/$destfile" + fi + + # If the file is missing, and there is a .exe on the end, strip it + # because it is most likely a libtool script we actually want to + # install + stripped_ext="" + case $file in + *.exe) + if test ! -f "$file"; then + file=`$echo $file|${SED} 's,.exe$,,'` + stripped_ext=".exe" + fi + ;; + esac + + # Do a test to see if this is really a libtool program. + case $host in + *cygwin*|*mingw*) + wrapper=`$echo $file | ${SED} -e 's,.exe$,,'` + ;; + *) + wrapper=$file + ;; + esac + if (${SED} -e '4q' $wrapper | grep "^# Generated by .*$PACKAGE")>/dev/null 2>&1; then + notinst_deplibs= + relink_command= + + # Note that it is not necessary on cygwin/mingw to append a dot to + # foo even if both foo and FILE.exe exist: automatic-append-.exe + # behavior happens only for exec(3), not for open(2)! Also, sourcing + # `FILE.' does not work on cygwin managed mounts. + # + # If there is no directory component, then add one. + case $wrapper in + */* | *\\*) . ${wrapper} ;; + *) . ./${wrapper} ;; + esac + + # Check the variables that should have been set. + if test -z "$notinst_deplibs"; then + $echo "$modename: invalid libtool wrapper script \`$wrapper'" 1>&2 + exit $EXIT_FAILURE + fi + + finalize=yes + for lib in $notinst_deplibs; do + # Check to see that each library is installed. + libdir= + if test -f "$lib"; then + # If there is no directory component, then add one. + case $lib in + */* | *\\*) . $lib ;; + *) . ./$lib ;; + esac + fi + libfile="$libdir/"`$echo "X$lib" | $Xsed -e 's%^.*/%%g'` ### testsuite: skip nested quoting test + if test -n "$libdir" && test ! -f "$libfile"; then + $echo "$modename: warning: \`$lib' has not been installed in \`$libdir'" 1>&2 + finalize=no + fi + done + + relink_command= + # Note that it is not necessary on cygwin/mingw to append a dot to + # foo even if both foo and FILE.exe exist: automatic-append-.exe + # behavior happens only for exec(3), not for open(2)! Also, sourcing + # `FILE.' does not work on cygwin managed mounts. + # + # If there is no directory component, then add one. + case $wrapper in + */* | *\\*) . ${wrapper} ;; + *) . ./${wrapper} ;; + esac + + outputname= + if test "$fast_install" = no && test -n "$relink_command"; then + if test "$finalize" = yes && test -z "$run"; then + tmpdir=`func_mktempdir` + file=`$echo "X$file$stripped_ext" | $Xsed -e 's%^.*/%%'` + outputname="$tmpdir/$file" + # Replace the output file specification. + relink_command=`$echo "X$relink_command" | $Xsed -e 's%@OUTPUT@%'"$outputname"'%g'` + + $show "$relink_command" + if $run eval "$relink_command"; then : + else + $echo "$modename: error: relink \`$file' with the above command before installing it" 1>&2 + ${rm}r "$tmpdir" + continue + fi + file="$outputname" + else + $echo "$modename: warning: cannot relink \`$file'" 1>&2 + fi + else + # Install the binary that we compiled earlier. + file=`$echo "X$file$stripped_ext" | $Xsed -e "s%\([^/]*\)$%$objdir/\1%"` + fi + fi + + # remove .exe since cygwin /usr/bin/install will append another + # one anyway + case $install_prog,$host in + */usr/bin/install*,*cygwin*) + case $file:$destfile in + *.exe:*.exe) + # this is ok + ;; + *.exe:*) + destfile=$destfile.exe + ;; + *:*.exe) + destfile=`$echo $destfile | ${SED} -e 's,.exe$,,'` + ;; + esac + ;; + esac + $show "$install_prog$stripme $file $destfile" + $run eval "$install_prog\$stripme \$file \$destfile" || exit $? + test -n "$outputname" && ${rm}r "$tmpdir" + ;; + esac + done + + for file in $staticlibs; do + name=`$echo "X$file" | $Xsed -e 's%^.*/%%'` + + # Set up the ranlib parameters. + oldlib="$destdir/$name" + + $show "$install_prog $file $oldlib" + $run eval "$install_prog \$file \$oldlib" || exit $? + + if test -n "$stripme" && test -n "$old_striplib"; then + $show "$old_striplib $oldlib" + $run eval "$old_striplib $oldlib" || exit $? + fi + + # Do each command in the postinstall commands. + cmds=$old_postinstall_cmds + save_ifs="$IFS"; IFS='~' + for cmd in $cmds; do + IFS="$save_ifs" + eval cmd=\"$cmd\" + $show "$cmd" + $run eval "$cmd" || exit $? + done + IFS="$save_ifs" + done + + if test -n "$future_libdirs"; then + $echo "$modename: warning: remember to run \`$progname --finish$future_libdirs'" 1>&2 + fi + + if test -n "$current_libdirs"; then + # Maybe just do a dry run. + test -n "$run" && current_libdirs=" -n$current_libdirs" + exec_cmd='$SHELL $progpath $preserve_args --finish$current_libdirs' + else + exit $EXIT_SUCCESS + fi + ;; + + # libtool finish mode + finish) + modename="$modename: finish" + libdirs="$nonopt" + admincmds= + + if test -n "$finish_cmds$finish_eval" && test -n "$libdirs"; then + for dir + do + libdirs="$libdirs $dir" + done + + for libdir in $libdirs; do + if test -n "$finish_cmds"; then + # Do each command in the finish commands. + cmds=$finish_cmds + save_ifs="$IFS"; IFS='~' + for cmd in $cmds; do + IFS="$save_ifs" + eval cmd=\"$cmd\" + $show "$cmd" + $run eval "$cmd" || admincmds="$admincmds + $cmd" + done + IFS="$save_ifs" + fi + if test -n "$finish_eval"; then + # Do the single finish_eval. + eval cmds=\"$finish_eval\" + $run eval "$cmds" || admincmds="$admincmds + $cmds" + fi + done + fi + + # Exit here if they wanted silent mode. + test "$show" = : && exit $EXIT_SUCCESS + + $echo "X----------------------------------------------------------------------" | $Xsed + $echo "Libraries have been installed in:" + for libdir in $libdirs; do + $echo " $libdir" + done + $echo + $echo "If you ever happen to want to link against installed libraries" + $echo "in a given directory, LIBDIR, you must either use libtool, and" + $echo "specify the full pathname of the library, or use the \`-LLIBDIR'" + $echo "flag during linking and do at least one of the following:" + if test -n "$shlibpath_var"; then + $echo " - add LIBDIR to the \`$shlibpath_var' environment variable" + $echo " during execution" + fi + if test -n "$runpath_var"; then + $echo " - add LIBDIR to the \`$runpath_var' environment variable" + $echo " during linking" + fi + if test -n "$hardcode_libdir_flag_spec"; then + libdir=LIBDIR + eval flag=\"$hardcode_libdir_flag_spec\" + + $echo " - use the \`$flag' linker flag" + fi + if test -n "$admincmds"; then + $echo " - have your system administrator run these commands:$admincmds" + fi + if test -f /etc/ld.so.conf; then + $echo " - have your system administrator add LIBDIR to \`/etc/ld.so.conf'" + fi + $echo + $echo "See any operating system documentation about shared libraries for" + $echo "more information, such as the ld(1) and ld.so(8) manual pages." + $echo "X----------------------------------------------------------------------" | $Xsed + exit $EXIT_SUCCESS + ;; + + # libtool execute mode + execute) + modename="$modename: execute" + + # The first argument is the command name. + cmd="$nonopt" + if test -z "$cmd"; then + $echo "$modename: you must specify a COMMAND" 1>&2 + $echo "$help" + exit $EXIT_FAILURE + fi + + # Handle -dlopen flags immediately. + for file in $execute_dlfiles; do + if test ! -f "$file"; then + $echo "$modename: \`$file' is not a file" 1>&2 + $echo "$help" 1>&2 + exit $EXIT_FAILURE + fi + + dir= + case $file in + *.la) + # Check to see that this really is a libtool archive. + if (${SED} -e '2q' $file | grep "^# Generated by .*$PACKAGE") >/dev/null 2>&1; then : + else + $echo "$modename: \`$lib' is not a valid libtool archive" 1>&2 + $echo "$help" 1>&2 + exit $EXIT_FAILURE + fi + + # Read the libtool library. + dlname= + library_names= + + # If there is no directory component, then add one. + case $file in + */* | *\\*) . $file ;; + *) . ./$file ;; + esac + + # Skip this library if it cannot be dlopened. + if test -z "$dlname"; then + # Warn if it was a shared library. + test -n "$library_names" && $echo "$modename: warning: \`$file' was not linked with \`-export-dynamic'" + continue + fi + + dir=`$echo "X$file" | $Xsed -e 's%/[^/]*$%%'` + test "X$dir" = "X$file" && dir=. + + if test -f "$dir/$objdir/$dlname"; then + dir="$dir/$objdir" + else + $echo "$modename: cannot find \`$dlname' in \`$dir' or \`$dir/$objdir'" 1>&2 + exit $EXIT_FAILURE + fi + ;; + + *.lo) + # Just add the directory containing the .lo file. + dir=`$echo "X$file" | $Xsed -e 's%/[^/]*$%%'` + test "X$dir" = "X$file" && dir=. + ;; + + *) + $echo "$modename: warning \`-dlopen' is ignored for non-libtool libraries and objects" 1>&2 + continue + ;; + esac + + # Get the absolute pathname. + absdir=`cd "$dir" && pwd` + test -n "$absdir" && dir="$absdir" + + # Now add the directory to shlibpath_var. + if eval "test -z \"\$$shlibpath_var\""; then + eval "$shlibpath_var=\"\$dir\"" + else + eval "$shlibpath_var=\"\$dir:\$$shlibpath_var\"" + fi + done + + # This variable tells wrapper scripts just to set shlibpath_var + # rather than running their programs. + libtool_execute_magic="$magic" + + # Check if any of the arguments is a wrapper script. + args= + for file + do + case $file in + -*) ;; + *) + # Do a test to see if this is really a libtool program. + if (${SED} -e '4q' $file | grep "^# Generated by .*$PACKAGE") >/dev/null 2>&1; then + # If there is no directory component, then add one. + case $file in + */* | *\\*) . $file ;; + *) . ./$file ;; + esac + + # Transform arg to wrapped name. + file="$progdir/$program" + fi + ;; + esac + # Quote arguments (to preserve shell metacharacters). + file=`$echo "X$file" | $Xsed -e "$sed_quote_subst"` + args="$args \"$file\"" + done + + if test -z "$run"; then + if test -n "$shlibpath_var"; then + # Export the shlibpath_var. + eval "export $shlibpath_var" + fi + + # Restore saved environment variables + if test "${save_LC_ALL+set}" = set; then + LC_ALL="$save_LC_ALL"; export LC_ALL + fi + if test "${save_LANG+set}" = set; then + LANG="$save_LANG"; export LANG + fi + + # Now prepare to actually exec the command. + exec_cmd="\$cmd$args" + else + # Display what would be done. + if test -n "$shlibpath_var"; then + eval "\$echo \"\$shlibpath_var=\$$shlibpath_var\"" + $echo "export $shlibpath_var" + fi + $echo "$cmd$args" + exit $EXIT_SUCCESS + fi + ;; + + # libtool clean and uninstall mode + clean | uninstall) + modename="$modename: $mode" + rm="$nonopt" + files= + rmforce= + exit_status=0 + + # This variable tells wrapper scripts just to set variables rather + # than running their programs. + libtool_install_magic="$magic" + + for arg + do + case $arg in + -f) rm="$rm $arg"; rmforce=yes ;; + -*) rm="$rm $arg" ;; + *) files="$files $arg" ;; + esac + done + + if test -z "$rm"; then + $echo "$modename: you must specify an RM program" 1>&2 + $echo "$help" 1>&2 + exit $EXIT_FAILURE + fi + + rmdirs= + + origobjdir="$objdir" + for file in $files; do + dir=`$echo "X$file" | $Xsed -e 's%/[^/]*$%%'` + if test "X$dir" = "X$file"; then + dir=. + objdir="$origobjdir" + else + objdir="$dir/$origobjdir" + fi + name=`$echo "X$file" | $Xsed -e 's%^.*/%%'` + test "$mode" = uninstall && objdir="$dir" + + # Remember objdir for removal later, being careful to avoid duplicates + if test "$mode" = clean; then + case " $rmdirs " in + *" $objdir "*) ;; + *) rmdirs="$rmdirs $objdir" ;; + esac + fi + + # Don't error if the file doesn't exist and rm -f was used. + if (test -L "$file") >/dev/null 2>&1 \ + || (test -h "$file") >/dev/null 2>&1 \ + || test -f "$file"; then + : + elif test -d "$file"; then + exit_status=1 + continue + elif test "$rmforce" = yes; then + continue + fi + + rmfiles="$file" + + case $name in + *.la) + # Possibly a libtool archive, so verify it. + if (${SED} -e '2q' $file | grep "^# Generated by .*$PACKAGE") >/dev/null 2>&1; then + . $dir/$name + + # Delete the libtool libraries and symlinks. + for n in $library_names; do + rmfiles="$rmfiles $objdir/$n" + done + test -n "$old_library" && rmfiles="$rmfiles $objdir/$old_library" + + case "$mode" in + clean) + case " $library_names " in + # " " in the beginning catches empty $dlname + *" $dlname "*) ;; + *) rmfiles="$rmfiles $objdir/$dlname" ;; + esac + test -n "$libdir" && rmfiles="$rmfiles $objdir/$name $objdir/${name}i" + ;; + uninstall) + if test -n "$library_names"; then + # Do each command in the postuninstall commands. + cmds=$postuninstall_cmds + save_ifs="$IFS"; IFS='~' + for cmd in $cmds; do + IFS="$save_ifs" + eval cmd=\"$cmd\" + $show "$cmd" + $run eval "$cmd" + if test "$?" -ne 0 && test "$rmforce" != yes; then + exit_status=1 + fi + done + IFS="$save_ifs" + fi + + if test -n "$old_library"; then + # Do each command in the old_postuninstall commands. + cmds=$old_postuninstall_cmds + save_ifs="$IFS"; IFS='~' + for cmd in $cmds; do + IFS="$save_ifs" + eval cmd=\"$cmd\" + $show "$cmd" + $run eval "$cmd" + if test "$?" -ne 0 && test "$rmforce" != yes; then + exit_status=1 + fi + done + IFS="$save_ifs" + fi + # FIXME: should reinstall the best remaining shared library. + ;; + esac + fi + ;; + + *.lo) + # Possibly a libtool object, so verify it. + if (${SED} -e '2q' $file | grep "^# Generated by .*$PACKAGE") >/dev/null 2>&1; then + + # Read the .lo file + . $dir/$name + + # Add PIC object to the list of files to remove. + if test -n "$pic_object" \ + && test "$pic_object" != none; then + rmfiles="$rmfiles $dir/$pic_object" + fi + + # Add non-PIC object to the list of files to remove. + if test -n "$non_pic_object" \ + && test "$non_pic_object" != none; then + rmfiles="$rmfiles $dir/$non_pic_object" + fi + fi + ;; + + *) + if test "$mode" = clean ; then + noexename=$name + case $file in + *.exe) + file=`$echo $file|${SED} 's,.exe$,,'` + noexename=`$echo $name|${SED} 's,.exe$,,'` + # $file with .exe has already been added to rmfiles, + # add $file without .exe + rmfiles="$rmfiles $file" + ;; + esac + # Do a test to see if this is a libtool program. + if (${SED} -e '4q' $file | grep "^# Generated by .*$PACKAGE") >/dev/null 2>&1; then + relink_command= + . $dir/$noexename + + # note $name still contains .exe if it was in $file originally + # as does the version of $file that was added into $rmfiles + rmfiles="$rmfiles $objdir/$name $objdir/${name}S.${objext}" + if test "$fast_install" = yes && test -n "$relink_command"; then + rmfiles="$rmfiles $objdir/lt-$name" + fi + if test "X$noexename" != "X$name" ; then + rmfiles="$rmfiles $objdir/lt-${noexename}.c" + fi + fi + fi + ;; + esac + $show "$rm $rmfiles" + $run $rm $rmfiles || exit_status=1 + done + objdir="$origobjdir" + + # Try to remove the ${objdir}s in the directories where we deleted files + for dir in $rmdirs; do + if test -d "$dir"; then + $show "rmdir $dir" + $run rmdir $dir >/dev/null 2>&1 + fi + done + + exit $exit_status + ;; + + "") + $echo "$modename: you must specify a MODE" 1>&2 + $echo "$generic_help" 1>&2 + exit $EXIT_FAILURE + ;; + esac + + if test -z "$exec_cmd"; then + $echo "$modename: invalid operation mode \`$mode'" 1>&2 + $echo "$generic_help" 1>&2 + exit $EXIT_FAILURE + fi +fi # test -z "$show_help" + +if test -n "$exec_cmd"; then + eval exec $exec_cmd + exit $EXIT_FAILURE +fi + +# We need to display help for each of the modes. +case $mode in +"") $echo \ +"Usage: $modename [OPTION]... [MODE-ARG]... + +Provide generalized library-building support services. + + --config show all configuration variables + --debug enable verbose shell tracing +-n, --dry-run display commands without modifying any files + --features display basic configuration information and exit + --finish same as \`--mode=finish' + --help display this help message and exit + --mode=MODE use operation mode MODE [default=inferred from MODE-ARGS] + --quiet same as \`--silent' + --silent don't print informational messages + --tag=TAG use configuration variables from tag TAG + --version print version information + +MODE must be one of the following: + + clean remove files from the build directory + compile compile a source file into a libtool object + execute automatically set library path, then run a program + finish complete the installation of libtool libraries + install install libraries or executables + link create a library or an executable + uninstall remove libraries from an installed directory + +MODE-ARGS vary depending on the MODE. Try \`$modename --help --mode=MODE' for +a more detailed description of MODE. + +Report bugs to ." + exit $EXIT_SUCCESS + ;; + +clean) + $echo \ +"Usage: $modename [OPTION]... --mode=clean RM [RM-OPTION]... FILE... + +Remove files from the build directory. + +RM is the name of the program to use to delete files associated with each FILE +(typically \`/bin/rm'). RM-OPTIONS are options (such as \`-f') to be passed +to RM. + +If FILE is a libtool library, object or program, all the files associated +with it are deleted. Otherwise, only FILE itself is deleted using RM." + ;; + +compile) + $echo \ +"Usage: $modename [OPTION]... --mode=compile COMPILE-COMMAND... SOURCEFILE + +Compile a source file into a libtool library object. + +This mode accepts the following additional options: + + -o OUTPUT-FILE set the output file name to OUTPUT-FILE + -prefer-pic try to building PIC objects only + -prefer-non-pic try to building non-PIC objects only + -static always build a \`.o' file suitable for static linking + +COMPILE-COMMAND is a command to be used in creating a \`standard' object file +from the given SOURCEFILE. + +The output file name is determined by removing the directory component from +SOURCEFILE, then substituting the C source code suffix \`.c' with the +library object suffix, \`.lo'." + ;; + +execute) + $echo \ +"Usage: $modename [OPTION]... --mode=execute COMMAND [ARGS]... + +Automatically set library path, then run a program. + +This mode accepts the following additional options: + + -dlopen FILE add the directory containing FILE to the library path + +This mode sets the library path environment variable according to \`-dlopen' +flags. + +If any of the ARGS are libtool executable wrappers, then they are translated +into their corresponding uninstalled binary, and any of their required library +directories are added to the library path. + +Then, COMMAND is executed, with ARGS as arguments." + ;; + +finish) + $echo \ +"Usage: $modename [OPTION]... --mode=finish [LIBDIR]... + +Complete the installation of libtool libraries. + +Each LIBDIR is a directory that contains libtool libraries. + +The commands that this mode executes may require superuser privileges. Use +the \`--dry-run' option if you just want to see what would be executed." + ;; + +install) + $echo \ +"Usage: $modename [OPTION]... --mode=install INSTALL-COMMAND... + +Install executables or libraries. + +INSTALL-COMMAND is the installation command. The first component should be +either the \`install' or \`cp' program. + +The rest of the components are interpreted as arguments to that command (only +BSD-compatible install options are recognized)." + ;; + +link) + $echo \ +"Usage: $modename [OPTION]... --mode=link LINK-COMMAND... + +Link object files or libraries together to form another library, or to +create an executable program. + +LINK-COMMAND is a command using the C compiler that you would use to create +a program from several object files. + +The following components of LINK-COMMAND are treated specially: + + -all-static do not do any dynamic linking at all + -avoid-version do not add a version suffix if possible + -dlopen FILE \`-dlpreopen' FILE if it cannot be dlopened at runtime + -dlpreopen FILE link in FILE and add its symbols to lt_preloaded_symbols + -export-dynamic allow symbols from OUTPUT-FILE to be resolved with dlsym(3) + -export-symbols SYMFILE + try to export only the symbols listed in SYMFILE + -export-symbols-regex REGEX + try to export only the symbols matching REGEX + -LLIBDIR search LIBDIR for required installed libraries + -lNAME OUTPUT-FILE requires the installed library libNAME + -module build a library that can dlopened + -no-fast-install disable the fast-install mode + -no-install link a not-installable executable + -no-undefined declare that a library does not refer to external symbols + -o OUTPUT-FILE create OUTPUT-FILE from the specified objects + -objectlist FILE Use a list of object files found in FILE to specify objects + -precious-files-regex REGEX + don't remove output files matching REGEX + -release RELEASE specify package release information + -rpath LIBDIR the created library will eventually be installed in LIBDIR + -R[ ]LIBDIR add LIBDIR to the runtime path of programs and libraries + -static do not do any dynamic linking of libtool libraries + -version-info CURRENT[:REVISION[:AGE]] + specify library version info [each variable defaults to 0] + +All other options (arguments beginning with \`-') are ignored. + +Every other argument is treated as a filename. Files ending in \`.la' are +treated as uninstalled libtool libraries, other files are standard or library +object files. + +If the OUTPUT-FILE ends in \`.la', then a libtool library is created, +only library objects (\`.lo' files) may be specified, and \`-rpath' is +required, except when creating a convenience library. + +If OUTPUT-FILE ends in \`.a' or \`.lib', then a standard library is created +using \`ar' and \`ranlib', or on Windows using \`lib'. + +If OUTPUT-FILE ends in \`.lo' or \`.${objext}', then a reloadable object file +is created, otherwise an executable program is created." + ;; + +uninstall) + $echo \ +"Usage: $modename [OPTION]... --mode=uninstall RM [RM-OPTION]... FILE... + +Remove libraries from an installation directory. + +RM is the name of the program to use to delete files associated with each FILE +(typically \`/bin/rm'). RM-OPTIONS are options (such as \`-f') to be passed +to RM. + +If FILE is a libtool library, all the files associated with it are deleted. +Otherwise, only FILE itself is deleted using RM." + ;; + +*) + $echo "$modename: invalid operation mode \`$mode'" 1>&2 + $echo "$help" 1>&2 + exit $EXIT_FAILURE + ;; +esac + +$echo +$echo "Try \`$modename --help' for more information about other modes." + +exit $? + +# The TAGs below are defined such that we never get into a situation +# in which we disable both kinds of libraries. Given conflicting +# choices, we go for a static library, that is the most portable, +# since we can't tell whether shared libraries were disabled because +# the user asked for that or because the platform doesn't support +# them. This is particularly important on AIX, because we don't +# support having both static and shared libraries enabled at the same +# time on that platform, so we default to a shared-only configuration. +# If a disable-shared tag is given, we'll fallback to a static-only +# configuration. But we'll never go from static-only to shared-only. + +# ### BEGIN LIBTOOL TAG CONFIG: disable-shared +disable_libs=shared +# ### END LIBTOOL TAG CONFIG: disable-shared + +# ### BEGIN LIBTOOL TAG CONFIG: disable-static +disable_libs=static +# ### END LIBTOOL TAG CONFIG: disable-static + +# Local Variables: +# mode:shell-script +# sh-indentation:2 +# End: diff --git a/libs/pcre/makevp.bat b/libs/pcre/makevp.bat new file mode 100644 index 0000000000..10bd2487a4 --- /dev/null +++ b/libs/pcre/makevp.bat @@ -0,0 +1,25 @@ +@echo off + +REM This file was contributed by Alexander Tokarev for building PCRE for use +REM with Virtual Pascal. It has not been tested with the latest PCRE release. + +REM CHANGE THIS FOR YOUR BORLAND C++ COMPILER PATH + +SET BORLAND=c:\usr\apps\bcc55 + +sh configure + +bcc32 -DDFTABLES -DSTATIC -DVPCOMPAT -I%BORLAND%\include -L%BORLAND%\lib dftables.c + +dftables > chartables.c + +bcc32 -c -RT- -y- -v- -u- -P- -O2 -5 -DSTATIC -DVPCOMPAT -UDFTABLES -I%BORLAND%\include get.c maketables.c pcre.c study.c + +tlib %BORLAND%\lib\cw32.lib *calloc *del *strncmp *memcpy *memmove *memset +tlib pcre.lib +get.obj +maketables.obj +pcre.obj +study.obj +calloc.obj +del.obj +strncmp.obj +memcpy.obj +memmove.obj +memset.obj + +del *.obj *.exe *.tds *.bak >nul 2>nul + +echo --- +echo Now the library should be complete. Please check all messages above. +echo Don't care for warnings, it's OK. diff --git a/libs/pcre/mkinstalldirs b/libs/pcre/mkinstalldirs new file mode 100755 index 0000000000..70f983f5cf --- /dev/null +++ b/libs/pcre/mkinstalldirs @@ -0,0 +1,40 @@ +#! /bin/sh +# mkinstalldirs --- make directory hierarchy +# Author: Noah Friedman +# Created: 1993-05-16 +# Public domain + +# $Id: mkinstalldirs,v 1.12.2.1 1998/12/26 17:32:14 bje Exp $ + +errstatus=0 + +for file +do + set fnord `echo ":$file" | sed -ne 's/^:\//#/;s/^://;s/\// /g;s/^#/\//;p'` + shift + + pathcomp= + for d + do + pathcomp="$pathcomp$d" + case "$pathcomp" in + -* ) pathcomp=./$pathcomp ;; + esac + + if test ! -d "$pathcomp"; then + echo "mkdir $pathcomp" + + mkdir "$pathcomp" || lasterr=$? + + if test ! -d "$pathcomp"; then + errstatus=$lasterr + fi + fi + + pathcomp="$pathcomp/" + done +done + +exit $errstatus + +# mkinstalldirs ends here diff --git a/libs/pcre/pcre-config.in b/libs/pcre/pcre-config.in new file mode 100644 index 0000000000..30d66ced36 --- /dev/null +++ b/libs/pcre/pcre-config.in @@ -0,0 +1,66 @@ +#!/bin/sh + +prefix=@prefix@ +exec_prefix=@exec_prefix@ +exec_prefix_set=no + +usage="\ +Usage: pcre-config [--prefix] [--exec-prefix] [--version] [--libs] [--libs-posix] [--cflags] [--cflags-posix]" + +if test $# -eq 0; then + echo "${usage}" 1>&2 + exit 1 +fi + +libR= +case `uname -s` in + *SunOS*) + libR=" -R@libdir@" + ;; +esac + +while test $# -gt 0; do + case "$1" in + -*=*) optarg=`echo "$1" | sed 's/[-_a-zA-Z0-9]*=//'` ;; + *) optarg= ;; + esac + + case $1 in + --prefix=*) + prefix=$optarg + if test $exec_prefix_set = no ; then + exec_prefix=$optarg + fi + ;; + --prefix) + echo $prefix + ;; + --exec-prefix=*) + exec_prefix=$optarg + exec_prefix_set=yes + ;; + --exec-prefix) + echo $exec_prefix + ;; + --version) + echo @PCRE_VERSION@ + ;; + --cflags | --cflags-posix) + if test @includedir@ != /usr/include ; then + includes=-I@includedir@ + fi + echo $includes + ;; + --libs-posix) + echo -L@libdir@$libR -lpcreposix -lpcre + ;; + --libs) + echo -L@libdir@$libR -lpcre + ;; + *) + echo "${usage}" 1>&2 + exit 1 + ;; + esac + shift +done diff --git a/libs/pcre/pcre.def b/libs/pcre/pcre.def new file mode 100644 index 0000000000..ec2c7b395b --- /dev/null +++ b/libs/pcre/pcre.def @@ -0,0 +1,29 @@ +EXPORTS + +pcre_malloc DATA +pcre_free DATA + +pcre_compile +pcre_compile2 +pcre_config +pcre_copy_named_substring +pcre_copy_substring +pcre_dfa_exec +pcre_exec +pcre_free_substring +pcre_free_substring_list +pcre_fullinfo +pcre_get_named_substring +pcre_get_stringnumber +pcre_get_substring +pcre_get_substring_list +pcre_info +pcre_maketables +pcre_refcount +pcre_study +pcre_version + +regcomp +regexec +regerror +regfree diff --git a/libs/pcre/pcre.h b/libs/pcre/pcre.h new file mode 100644 index 0000000000..7a7051ca10 --- /dev/null +++ b/libs/pcre/pcre.h @@ -0,0 +1,290 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* This is the public header file for the PCRE library, to be #included by +applications that call the PCRE functions. + + Copyright (c) 1997-2005 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +#ifndef _PCRE_H +#define _PCRE_H + +/* The current PCRE version information. */ + +/* NOTES FOR FUTURE MAINTAINERS: Do not use numbers with leading zeros, because +they may be treated as octal constants. The PCRE_PRERELEASE feature is for +identifying release candidates. It might be defined as -RC2, for example. In +real releases, it should be defined empty. Do not change the alignment of these +statments. The code in ./configure greps out the version numbers by using "cut" +to get values from column 29 onwards. These are substituted into pcre-config +and libpcre.pc. The values are not put into configure.ac and substituted here +(which would simplify this issue) because that makes life harder for those who +cannot run ./configure. As it now stands, this file need not be edited in that +circumstance. */ + +#define PCRE_MAJOR 6 +#define PCRE_MINOR 7 +#define PCRE_PRERELEASE +#define PCRE_DATE 04-Jul-2006 + +/* Win32 uses DLL by default; it needs special stuff for exported functions +when building PCRE. */ + +#ifdef _WIN32 +# ifdef PCRE_DEFINITION +# ifdef DLL_EXPORT +# define PCRE_DATA_SCOPE __declspec(dllexport) +# endif +# else +# ifndef PCRE_STATIC +# define PCRE_DATA_SCOPE extern __declspec(dllimport) +# endif +# endif +#endif + +/* Otherwise, we use the standard "extern". */ + +#ifndef PCRE_DATA_SCOPE +# ifdef __cplusplus +# define PCRE_DATA_SCOPE extern "C" +# else +# define PCRE_DATA_SCOPE extern +# endif +#endif + +/* Have to include stdlib.h in order to ensure that size_t is defined; +it is needed here for malloc. */ + +#include + +/* Allow for C++ users */ + +#ifdef __cplusplus +extern "C" { +#endif + +/* Options */ + +#define PCRE_CASELESS 0x00000001 +#define PCRE_MULTILINE 0x00000002 +#define PCRE_DOTALL 0x00000004 +#define PCRE_EXTENDED 0x00000008 +#define PCRE_ANCHORED 0x00000010 +#define PCRE_DOLLAR_ENDONLY 0x00000020 +#define PCRE_EXTRA 0x00000040 +#define PCRE_NOTBOL 0x00000080 +#define PCRE_NOTEOL 0x00000100 +#define PCRE_UNGREEDY 0x00000200 +#define PCRE_NOTEMPTY 0x00000400 +#define PCRE_UTF8 0x00000800 +#define PCRE_NO_AUTO_CAPTURE 0x00001000 +#define PCRE_NO_UTF8_CHECK 0x00002000 +#define PCRE_AUTO_CALLOUT 0x00004000 +#define PCRE_PARTIAL 0x00008000 +#define PCRE_DFA_SHORTEST 0x00010000 +#define PCRE_DFA_RESTART 0x00020000 +#define PCRE_FIRSTLINE 0x00040000 +#define PCRE_DUPNAMES 0x00080000 +#define PCRE_NEWLINE_CR 0x00100000 +#define PCRE_NEWLINE_LF 0x00200000 +#define PCRE_NEWLINE_CRLF 0x00300000 + +/* Exec-time and get/set-time error codes */ + +#define PCRE_ERROR_NOMATCH (-1) +#define PCRE_ERROR_NULL (-2) +#define PCRE_ERROR_BADOPTION (-3) +#define PCRE_ERROR_BADMAGIC (-4) +#define PCRE_ERROR_UNKNOWN_NODE (-5) +#define PCRE_ERROR_NOMEMORY (-6) +#define PCRE_ERROR_NOSUBSTRING (-7) +#define PCRE_ERROR_MATCHLIMIT (-8) +#define PCRE_ERROR_CALLOUT (-9) /* Never used by PCRE itself */ +#define PCRE_ERROR_BADUTF8 (-10) +#define PCRE_ERROR_BADUTF8_OFFSET (-11) +#define PCRE_ERROR_PARTIAL (-12) +#define PCRE_ERROR_BADPARTIAL (-13) +#define PCRE_ERROR_INTERNAL (-14) +#define PCRE_ERROR_BADCOUNT (-15) +#define PCRE_ERROR_DFA_UITEM (-16) +#define PCRE_ERROR_DFA_UCOND (-17) +#define PCRE_ERROR_DFA_UMLIMIT (-18) +#define PCRE_ERROR_DFA_WSSIZE (-19) +#define PCRE_ERROR_DFA_RECURSE (-20) +#define PCRE_ERROR_RECURSIONLIMIT (-21) + +/* Request types for pcre_fullinfo() */ + +#define PCRE_INFO_OPTIONS 0 +#define PCRE_INFO_SIZE 1 +#define PCRE_INFO_CAPTURECOUNT 2 +#define PCRE_INFO_BACKREFMAX 3 +#define PCRE_INFO_FIRSTBYTE 4 +#define PCRE_INFO_FIRSTCHAR 4 /* For backwards compatibility */ +#define PCRE_INFO_FIRSTTABLE 5 +#define PCRE_INFO_LASTLITERAL 6 +#define PCRE_INFO_NAMEENTRYSIZE 7 +#define PCRE_INFO_NAMECOUNT 8 +#define PCRE_INFO_NAMETABLE 9 +#define PCRE_INFO_STUDYSIZE 10 +#define PCRE_INFO_DEFAULT_TABLES 11 + +/* Request types for pcre_config(). Do not re-arrange, in order to remain +compatible. */ + +#define PCRE_CONFIG_UTF8 0 +#define PCRE_CONFIG_NEWLINE 1 +#define PCRE_CONFIG_LINK_SIZE 2 +#define PCRE_CONFIG_POSIX_MALLOC_THRESHOLD 3 +#define PCRE_CONFIG_MATCH_LIMIT 4 +#define PCRE_CONFIG_STACKRECURSE 5 +#define PCRE_CONFIG_UNICODE_PROPERTIES 6 +#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7 + +/* Bit flags for the pcre_extra structure. Do not re-arrange or redefine +these bits, just add new ones on the end, in order to remain compatible. */ + +#define PCRE_EXTRA_STUDY_DATA 0x0001 +#define PCRE_EXTRA_MATCH_LIMIT 0x0002 +#define PCRE_EXTRA_CALLOUT_DATA 0x0004 +#define PCRE_EXTRA_TABLES 0x0008 +#define PCRE_EXTRA_MATCH_LIMIT_RECURSION 0x0010 + +/* Types */ + +struct real_pcre; /* declaration; the definition is private */ +typedef struct real_pcre pcre; + +/* When PCRE is compiled as a C++ library, the subject pointer type can be +replaced with a custom type. For conventional use, the public interface is a +const char *. */ + +#ifndef PCRE_SPTR +#define PCRE_SPTR const char * +#endif + +/* The structure for passing additional data to pcre_exec(). This is defined in +such as way as to be extensible. Always add new fields at the end, in order to +remain compatible. */ + +typedef struct pcre_extra { + unsigned long int flags; /* Bits for which fields are set */ + void *study_data; /* Opaque data from pcre_study() */ + unsigned long int match_limit; /* Maximum number of calls to match() */ + void *callout_data; /* Data passed back in callouts */ + const unsigned char *tables; /* Pointer to character tables */ + unsigned long int match_limit_recursion; /* Max recursive calls to match() */ +} pcre_extra; + +/* The structure for passing out data via the pcre_callout_function. We use a +structure so that new fields can be added on the end in future versions, +without changing the API of the function, thereby allowing old clients to work +without modification. */ + +typedef struct pcre_callout_block { + int version; /* Identifies version of block */ + /* ------------------------ Version 0 ------------------------------- */ + int callout_number; /* Number compiled into pattern */ + int *offset_vector; /* The offset vector */ + PCRE_SPTR subject; /* The subject being matched */ + int subject_length; /* The length of the subject */ + int start_match; /* Offset to start of this match attempt */ + int current_position; /* Where we currently are in the subject */ + int capture_top; /* Max current capture */ + int capture_last; /* Most recently closed capture */ + void *callout_data; /* Data passed in with the call */ + /* ------------------- Added for Version 1 -------------------------- */ + int pattern_position; /* Offset to next item in the pattern */ + int next_item_length; /* Length of next item in the pattern */ + /* ------------------------------------------------------------------ */ +} pcre_callout_block; + +/* Indirection for store get and free functions. These can be set to +alternative malloc/free functions if required. Special ones are used in the +non-recursive case for "frames". There is also an optional callout function +that is triggered by the (?) regex item. For Virtual Pascal, these definitions +have to take another form. */ + +#ifndef VPCOMPAT +PCRE_DATA_SCOPE void *(*pcre_malloc)(size_t); +PCRE_DATA_SCOPE void (*pcre_free)(void *); +PCRE_DATA_SCOPE void *(*pcre_stack_malloc)(size_t); +PCRE_DATA_SCOPE void (*pcre_stack_free)(void *); +PCRE_DATA_SCOPE int (*pcre_callout)(pcre_callout_block *); +#else /* VPCOMPAT */ +PCRE_DATA_SCOPE void *pcre_malloc(size_t); +PCRE_DATA_SCOPE void pcre_free(void *); +PCRE_DATA_SCOPE void *pcre_stack_malloc(size_t); +PCRE_DATA_SCOPE void pcre_stack_free(void *); +PCRE_DATA_SCOPE int pcre_callout(pcre_callout_block *); +#endif /* VPCOMPAT */ + +/* Exported PCRE functions */ + +PCRE_DATA_SCOPE pcre *pcre_compile(const char *, int, const char **, int *, + const unsigned char *); +PCRE_DATA_SCOPE pcre *pcre_compile2(const char *, int, int *, const char **, + int *, const unsigned char *); +PCRE_DATA_SCOPE int pcre_config(int, void *); +PCRE_DATA_SCOPE int pcre_copy_named_substring(const pcre *, const char *, + int *, int, const char *, char *, int); +PCRE_DATA_SCOPE int pcre_copy_substring(const char *, int *, int, int, char *, + int); +PCRE_DATA_SCOPE int pcre_dfa_exec(const pcre *, const pcre_extra *, + const char *, int, int, int, int *, int , int *, int); +PCRE_DATA_SCOPE int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, + int, int, int, int *, int); +PCRE_DATA_SCOPE void pcre_free_substring(const char *); +PCRE_DATA_SCOPE void pcre_free_substring_list(const char **); +PCRE_DATA_SCOPE int pcre_fullinfo(const pcre *, const pcre_extra *, int, + void *); +PCRE_DATA_SCOPE int pcre_get_named_substring(const pcre *, const char *, + int *, int, const char *, const char **); +PCRE_DATA_SCOPE int pcre_get_stringnumber(const pcre *, const char *); +PCRE_DATA_SCOPE int pcre_get_stringtable_entries(const pcre *, const char *, + char **, char **); +PCRE_DATA_SCOPE int pcre_get_substring(const char *, int *, int, int, + const char **); +PCRE_DATA_SCOPE int pcre_get_substring_list(const char *, int *, int, + const char ***); +PCRE_DATA_SCOPE int pcre_info(const pcre *, int *, int *); +PCRE_DATA_SCOPE const unsigned char *pcre_maketables(void); +PCRE_DATA_SCOPE int pcre_refcount(pcre *, int); +PCRE_DATA_SCOPE pcre_extra *pcre_study(const pcre *, int, const char **); +PCRE_DATA_SCOPE const char *pcre_version(void); + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* End of pcre.h */ diff --git a/libs/pcre/pcre_compile.c b/libs/pcre/pcre_compile.c new file mode 100644 index 0000000000..4ea73d9d30 --- /dev/null +++ b/libs/pcre/pcre_compile.c @@ -0,0 +1,5281 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains the external function pcre_compile(), along with +supporting internal functions that are not used by other modules. */ + + +#define NLBLOCK cd /* The block containing newline information */ +#include "pcre_internal.h" + + +/* When DEBUG is defined, we need the pcre_printint() function, which is also +used by pcretest. DEBUG is not defined when building a production library. */ + +#ifdef DEBUG +#include "pcre_printint.src" +#endif + + + +/************************************************* +* Code parameters and static tables * +*************************************************/ + +/* Maximum number of items on the nested bracket stacks at compile time. This +applies to the nesting of all kinds of parentheses. It does not limit +un-nested, non-capturing parentheses. This number can be made bigger if +necessary - it is used to dimension one int and one unsigned char vector at +compile time. */ + +#define BRASTACK_SIZE 200 + + +/* Table for handling escaped characters in the range '0'-'z'. Positive returns +are simple data values; negative values are for special things like \d and so +on. Zero means further processing is needed (for things like \x), or the escape +is invalid. */ + +#if !EBCDIC /* This is the "normal" table for ASCII systems */ +static const short int escapes[] = { + 0, 0, 0, 0, 0, 0, 0, 0, /* 0 - 7 */ + 0, 0, ':', ';', '<', '=', '>', '?', /* 8 - ? */ + '@', -ESC_A, -ESC_B, -ESC_C, -ESC_D, -ESC_E, 0, -ESC_G, /* @ - G */ + 0, 0, 0, 0, 0, 0, 0, 0, /* H - O */ +-ESC_P, -ESC_Q, 0, -ESC_S, 0, 0, 0, -ESC_W, /* P - W */ +-ESC_X, 0, -ESC_Z, '[', '\\', ']', '^', '_', /* X - _ */ + '`', 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, /* ` - g */ + 0, 0, 0, 0, 0, 0, ESC_n, 0, /* h - o */ +-ESC_p, 0, ESC_r, -ESC_s, ESC_tee, 0, 0, -ESC_w, /* p - w */ + 0, 0, -ESC_z /* x - z */ +}; + +#else /* This is the "abnormal" table for EBCDIC systems */ +static const short int escapes[] = { +/* 48 */ 0, 0, 0, '.', '<', '(', '+', '|', +/* 50 */ '&', 0, 0, 0, 0, 0, 0, 0, +/* 58 */ 0, 0, '!', '$', '*', ')', ';', '~', +/* 60 */ '-', '/', 0, 0, 0, 0, 0, 0, +/* 68 */ 0, 0, '|', ',', '%', '_', '>', '?', +/* 70 */ 0, 0, 0, 0, 0, 0, 0, 0, +/* 78 */ 0, '`', ':', '#', '@', '\'', '=', '"', +/* 80 */ 0, 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, +/* 88 */ 0, 0, 0, '{', 0, 0, 0, 0, +/* 90 */ 0, 0, 0, 'l', 0, ESC_n, 0, -ESC_p, +/* 98 */ 0, ESC_r, 0, '}', 0, 0, 0, 0, +/* A0 */ 0, '~', -ESC_s, ESC_tee, 0, 0, -ESC_w, 0, +/* A8 */ 0,-ESC_z, 0, 0, 0, '[', 0, 0, +/* B0 */ 0, 0, 0, 0, 0, 0, 0, 0, +/* B8 */ 0, 0, 0, 0, 0, ']', '=', '-', +/* C0 */ '{',-ESC_A, -ESC_B, -ESC_C, -ESC_D,-ESC_E, 0, -ESC_G, +/* C8 */ 0, 0, 0, 0, 0, 0, 0, 0, +/* D0 */ '}', 0, 0, 0, 0, 0, 0, -ESC_P, +/* D8 */-ESC_Q, 0, 0, 0, 0, 0, 0, 0, +/* E0 */ '\\', 0, -ESC_S, 0, 0, 0, -ESC_W, -ESC_X, +/* E8 */ 0,-ESC_Z, 0, 0, 0, 0, 0, 0, +/* F0 */ 0, 0, 0, 0, 0, 0, 0, 0, +/* F8 */ 0, 0, 0, 0, 0, 0, 0, 0 +}; +#endif + + +/* Tables of names of POSIX character classes and their lengths. The list is +terminated by a zero length entry. The first three must be alpha, lower, upper, +as this is assumed for handling case independence. */ + +static const char *const posix_names[] = { + "alpha", "lower", "upper", + "alnum", "ascii", "blank", "cntrl", "digit", "graph", + "print", "punct", "space", "word", "xdigit" }; + +static const uschar posix_name_lengths[] = { + 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 4, 6, 0 }; + +/* Table of class bit maps for each POSIX class. Each class is formed from a +base map, with an optional addition or removal of another map. Then, for some +classes, there is some additional tweaking: for [:blank:] the vertical space +characters are removed, and for [:alpha:] and [:alnum:] the underscore +character is removed. The triples in the table consist of the base map offset, +second map offset or -1 if no second map, and a non-negative value for map +addition or a negative value for map subtraction (if there are two maps). The +absolute value of the third field has these meanings: 0 => no tweaking, 1 => +remove vertical space characters, 2 => remove underscore. */ + +static const int posix_class_maps[] = { + cbit_word, cbit_digit, -2, /* alpha */ + cbit_lower, -1, 0, /* lower */ + cbit_upper, -1, 0, /* upper */ + cbit_word, -1, 2, /* alnum - word without underscore */ + cbit_print, cbit_cntrl, 0, /* ascii */ + cbit_space, -1, 1, /* blank - a GNU extension */ + cbit_cntrl, -1, 0, /* cntrl */ + cbit_digit, -1, 0, /* digit */ + cbit_graph, -1, 0, /* graph */ + cbit_print, -1, 0, /* print */ + cbit_punct, -1, 0, /* punct */ + cbit_space, -1, 0, /* space */ + cbit_word, -1, 0, /* word - a Perl extension */ + cbit_xdigit,-1, 0 /* xdigit */ +}; + + +/* The texts of compile-time error messages. These are "char *" because they +are passed to the outside world. */ + +static const char *error_texts[] = { + "no error", + "\\ at end of pattern", + "\\c at end of pattern", + "unrecognized character follows \\", + "numbers out of order in {} quantifier", + /* 5 */ + "number too big in {} quantifier", + "missing terminating ] for character class", + "invalid escape sequence in character class", + "range out of order in character class", + "nothing to repeat", + /* 10 */ + "operand of unlimited repeat could match the empty string", + "internal error: unexpected repeat", + "unrecognized character after (?", + "POSIX named classes are supported only within a class", + "missing )", + /* 15 */ + "reference to non-existent subpattern", + "erroffset passed as NULL", + "unknown option bit(s) set", + "missing ) after comment", + "parentheses nested too deeply", + /* 20 */ + "regular expression too large", + "failed to get memory", + "unmatched parentheses", + "internal error: code overflow", + "unrecognized character after (?<", + /* 25 */ + "lookbehind assertion is not fixed length", + "malformed number or name after (?(", + "conditional group contains more than two branches", + "assertion expected after (?(", + "(?R or (?digits must be followed by )", + /* 30 */ + "unknown POSIX class name", + "POSIX collating elements are not supported", + "this version of PCRE is not compiled with PCRE_UTF8 support", + "spare error", + "character value in \\x{...} sequence is too large", + /* 35 */ + "invalid condition (?(0)", + "\\C not allowed in lookbehind assertion", + "PCRE does not support \\L, \\l, \\N, \\U, or \\u", + "number after (?C is > 255", + "closing ) for (?C expected", + /* 40 */ + "recursive call could loop indefinitely", + "unrecognized character after (?P", + "syntax error after (?P", + "two named subpatterns have the same name", + "invalid UTF-8 string", + /* 45 */ + "support for \\P, \\p, and \\X has not been compiled", + "malformed \\P or \\p sequence", + "unknown property name after \\P or \\p", + "subpattern name is too long (maximum 32 characters)", + "too many named subpatterns (maximum 10,000)", + /* 50 */ + "repeated subpattern is too long", + "octal value is greater than \\377 (not in UTF-8 mode)" +}; + + +/* Table to identify digits and hex digits. This is used when compiling +patterns. Note that the tables in chartables are dependent on the locale, and +may mark arbitrary characters as digits - but the PCRE compiling code expects +to handle only 0-9, a-z, and A-Z as digits when compiling. That is why we have +a private table here. It costs 256 bytes, but it is a lot faster than doing +character value tests (at least in some simple cases I timed), and in some +applications one wants PCRE to compile efficiently as well as match +efficiently. + +For convenience, we use the same bit definitions as in chartables: + + 0x04 decimal digit + 0x08 hexadecimal digit + +Then we can use ctype_digit and ctype_xdigit in the code. */ + +#if !EBCDIC /* This is the "normal" case, for ASCII systems */ +static const unsigned char digitab[] = + { + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 8- 15 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - ' */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ( - / */ + 0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c, /* 0 - 7 */ + 0x0c,0x0c,0x00,0x00,0x00,0x00,0x00,0x00, /* 8 - ? */ + 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* @ - G */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* H - O */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* P - W */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* X - _ */ + 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* ` - g */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* h - o */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* p - w */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* x -127 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ + +#else /* This is the "abnormal" case, for EBCDIC systems */ +static const unsigned char digitab[] = + { + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 0 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 8- 15 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 10 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 32- 39 20 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 40- 47 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 48- 55 30 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 56- 63 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 40 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 72- | */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 50 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 88- ¬ */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 60 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 104- ? */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 70 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 120- " */ + 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* 128- g 80 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* h -143 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144- p 90 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* q -159 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160- x A0 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* y -175 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ^ -183 B0 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ + 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* { - G C0 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* H -207 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* } - P D0 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Q -223 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* \ - X E0 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Y -239 */ + 0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c, /* 0 - 7 F0 */ + 0x0c,0x0c,0x00,0x00,0x00,0x00,0x00,0x00};/* 8 -255 */ + +static const unsigned char ebcdic_chartab[] = { /* chartable partial dup */ + 0x80,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 0- 7 */ + 0x00,0x00,0x00,0x00,0x01,0x01,0x00,0x00, /* 8- 15 */ + 0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 16- 23 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ + 0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 32- 39 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 40- 47 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 48- 55 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 56- 63 */ + 0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 */ + 0x00,0x00,0x00,0x80,0x00,0x80,0x80,0x80, /* 72- | */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 */ + 0x00,0x00,0x00,0x80,0x80,0x80,0x00,0x00, /* 88- ¬ */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 */ + 0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x80, /* 104- ? */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 */ + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 120- " */ + 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* 128- g */ + 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* h -143 */ + 0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* 144- p */ + 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* q -159 */ + 0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /* 160- x */ + 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* y -175 */ + 0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ^ -183 */ + 0x00,0x00,0x80,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ + 0x80,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* { - G */ + 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* H -207 */ + 0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* } - P */ + 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* Q -223 */ + 0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /* \ - X */ + 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* Y -239 */ + 0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */ + 0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x00};/* 8 -255 */ +#endif + + +/* Definition to allow mutual recursion */ + +static BOOL + compile_regex(int, int, int *, uschar **, const uschar **, int *, BOOL, int, + int *, int *, branch_chain *, compile_data *); + + + +/************************************************* +* Handle escapes * +*************************************************/ + +/* This function is called when a \ has been encountered. It either returns a +positive value for a simple escape such as \n, or a negative value which +encodes one of the more complicated things such as \d. When UTF-8 is enabled, +a positive value greater than 255 may be returned. On entry, ptr is pointing at +the \. On exit, it is on the final character of the escape sequence. + +Arguments: + ptrptr points to the pattern position pointer + errorcodeptr points to the errorcode variable + bracount number of previous extracting brackets + options the options bits + isclass TRUE if inside a character class + +Returns: zero or positive => a data character + negative => a special escape sequence + on error, errorptr is set +*/ + +static int +check_escape(const uschar **ptrptr, int *errorcodeptr, int bracount, + int options, BOOL isclass) +{ +BOOL utf8 = (options & PCRE_UTF8) != 0; +const uschar *ptr = *ptrptr + 1; +int c, i; + +GETCHARINCTEST(c, ptr); /* Get character value, increment pointer */ +ptr--; /* Set pointer back to the last byte */ + +/* If backslash is at the end of the pattern, it's an error. */ + +if (c == 0) *errorcodeptr = ERR1; + +/* Non-alphamerics are literals. For digits or letters, do an initial lookup in +a table. A non-zero result is something that can be returned immediately. +Otherwise further processing may be required. */ + +#if !EBCDIC /* ASCII coding */ +else if (c < '0' || c > 'z') {} /* Not alphameric */ +else if ((i = escapes[c - '0']) != 0) c = i; + +#else /* EBCDIC coding */ +else if (c < 'a' || (ebcdic_chartab[c] & 0x0E) == 0) {} /* Not alphameric */ +else if ((i = escapes[c - 0x48]) != 0) c = i; +#endif + +/* Escapes that need further processing, or are illegal. */ + +else + { + const uschar *oldptr; + switch (c) + { + /* A number of Perl escapes are not handled by PCRE. We give an explicit + error. */ + + case 'l': + case 'L': + case 'N': + case 'u': + case 'U': + *errorcodeptr = ERR37; + break; + + /* The handling of escape sequences consisting of a string of digits + starting with one that is not zero is not straightforward. By experiment, + the way Perl works seems to be as follows: + + Outside a character class, the digits are read as a decimal number. If the + number is less than 10, or if there are that many previous extracting + left brackets, then it is a back reference. Otherwise, up to three octal + digits are read to form an escaped byte. Thus \123 is likely to be octal + 123 (cf \0123, which is octal 012 followed by the literal 3). If the octal + value is greater than 377, the least significant 8 bits are taken. Inside a + character class, \ followed by a digit is always an octal number. */ + + case '1': case '2': case '3': case '4': case '5': + case '6': case '7': case '8': case '9': + + if (!isclass) + { + oldptr = ptr; + c -= '0'; + while ((digitab[ptr[1]] & ctype_digit) != 0) + c = c * 10 + *(++ptr) - '0'; + if (c < 10 || c <= bracount) + { + c = -(ESC_REF + c); + break; + } + ptr = oldptr; /* Put the pointer back and fall through */ + } + + /* Handle an octal number following \. If the first digit is 8 or 9, Perl + generates a binary zero byte and treats the digit as a following literal. + Thus we have to pull back the pointer by one. */ + + if ((c = *ptr) >= '8') + { + ptr--; + c = 0; + break; + } + + /* \0 always starts an octal number, but we may drop through to here with a + larger first octal digit. The original code used just to take the least + significant 8 bits of octal numbers (I think this is what early Perls used + to do). Nowadays we allow for larger numbers in UTF-8 mode, but no more + than 3 octal digits. */ + + case '0': + c -= '0'; + while(i++ < 2 && ptr[1] >= '0' && ptr[1] <= '7') + c = c * 8 + *(++ptr) - '0'; + if (!utf8 && c > 255) *errorcodeptr = ERR51; + break; + + /* \x is complicated. \x{ddd} is a character number which can be greater + than 0xff in utf8 mode, but only if the ddd are hex digits. If not, { is + treated as a data character. */ + + case 'x': + if (ptr[1] == '{') + { + const uschar *pt = ptr + 2; + int count = 0; + + c = 0; + while ((digitab[*pt] & ctype_xdigit) != 0) + { + register int cc = *pt++; + if (c == 0 && cc == '0') continue; /* Leading zeroes */ + count++; + +#if !EBCDIC /* ASCII coding */ + if (cc >= 'a') cc -= 32; /* Convert to upper case */ + c = (c << 4) + cc - ((cc < 'A')? '0' : ('A' - 10)); +#else /* EBCDIC coding */ + if (cc >= 'a' && cc <= 'z') cc += 64; /* Convert to upper case */ + c = (c << 4) + cc - ((cc >= '0')? '0' : ('A' - 10)); +#endif + } + + if (*pt == '}') + { + if (c < 0 || count > (utf8? 8 : 2)) *errorcodeptr = ERR34; + ptr = pt; + break; + } + + /* If the sequence of hex digits does not end with '}', then we don't + recognize this construct; fall through to the normal \x handling. */ + } + + /* Read just a single-byte hex-defined char */ + + c = 0; + while (i++ < 2 && (digitab[ptr[1]] & ctype_xdigit) != 0) + { + int cc; /* Some compilers don't like ++ */ + cc = *(++ptr); /* in initializers */ +#if !EBCDIC /* ASCII coding */ + if (cc >= 'a') cc -= 32; /* Convert to upper case */ + c = c * 16 + cc - ((cc < 'A')? '0' : ('A' - 10)); +#else /* EBCDIC coding */ + if (cc <= 'z') cc += 64; /* Convert to upper case */ + c = c * 16 + cc - ((cc >= '0')? '0' : ('A' - 10)); +#endif + } + break; + + /* Other special escapes not starting with a digit are straightforward */ + + case 'c': + c = *(++ptr); + if (c == 0) + { + *errorcodeptr = ERR2; + return 0; + } + + /* A letter is upper-cased; then the 0x40 bit is flipped. This coding + is ASCII-specific, but then the whole concept of \cx is ASCII-specific. + (However, an EBCDIC equivalent has now been added.) */ + +#if !EBCDIC /* ASCII coding */ + if (c >= 'a' && c <= 'z') c -= 32; + c ^= 0x40; +#else /* EBCDIC coding */ + if (c >= 'a' && c <= 'z') c += 64; + c ^= 0xC0; +#endif + break; + + /* PCRE_EXTRA enables extensions to Perl in the matter of escapes. Any + other alphameric following \ is an error if PCRE_EXTRA was set; otherwise, + for Perl compatibility, it is a literal. This code looks a bit odd, but + there used to be some cases other than the default, and there may be again + in future, so I haven't "optimized" it. */ + + default: + if ((options & PCRE_EXTRA) != 0) switch(c) + { + default: + *errorcodeptr = ERR3; + break; + } + break; + } + } + +*ptrptr = ptr; +return c; +} + + + +#ifdef SUPPORT_UCP +/************************************************* +* Handle \P and \p * +*************************************************/ + +/* This function is called after \P or \p has been encountered, provided that +PCRE is compiled with support for Unicode properties. On entry, ptrptr is +pointing at the P or p. On exit, it is pointing at the final character of the +escape sequence. + +Argument: + ptrptr points to the pattern position pointer + negptr points to a boolean that is set TRUE for negation else FALSE + dptr points to an int that is set to the detailed property value + errorcodeptr points to the error code variable + +Returns: type value from ucp_type_table, or -1 for an invalid type +*/ + +static int +get_ucp(const uschar **ptrptr, BOOL *negptr, int *dptr, int *errorcodeptr) +{ +int c, i, bot, top; +const uschar *ptr = *ptrptr; +char name[32]; + +c = *(++ptr); +if (c == 0) goto ERROR_RETURN; + +*negptr = FALSE; + +/* \P or \p can be followed by a name in {}, optionally preceded by ^ for +negation. */ + +if (c == '{') + { + if (ptr[1] == '^') + { + *negptr = TRUE; + ptr++; + } + for (i = 0; i < sizeof(name) - 1; i++) + { + c = *(++ptr); + if (c == 0) goto ERROR_RETURN; + if (c == '}') break; + name[i] = c; + } + if (c !='}') goto ERROR_RETURN; + name[i] = 0; + } + +/* Otherwise there is just one following character */ + +else + { + name[0] = c; + name[1] = 0; + } + +*ptrptr = ptr; + +/* Search for a recognized property name using binary chop */ + +bot = 0; +top = _pcre_utt_size; + +while (bot < top) + { + i = (bot + top) >> 1; + c = strcmp(name, _pcre_utt[i].name); + if (c == 0) + { + *dptr = _pcre_utt[i].value; + return _pcre_utt[i].type; + } + if (c > 0) bot = i + 1; else top = i; + } + +*errorcodeptr = ERR47; +*ptrptr = ptr; +return -1; + +ERROR_RETURN: +*errorcodeptr = ERR46; +*ptrptr = ptr; +return -1; +} +#endif + + + + +/************************************************* +* Check for counted repeat * +*************************************************/ + +/* This function is called when a '{' is encountered in a place where it might +start a quantifier. It looks ahead to see if it really is a quantifier or not. +It is only a quantifier if it is one of the forms {ddd} {ddd,} or {ddd,ddd} +where the ddds are digits. + +Arguments: + p pointer to the first char after '{' + +Returns: TRUE or FALSE +*/ + +static BOOL +is_counted_repeat(const uschar *p) +{ +if ((digitab[*p++] & ctype_digit) == 0) return FALSE; +while ((digitab[*p] & ctype_digit) != 0) p++; +if (*p == '}') return TRUE; + +if (*p++ != ',') return FALSE; +if (*p == '}') return TRUE; + +if ((digitab[*p++] & ctype_digit) == 0) return FALSE; +while ((digitab[*p] & ctype_digit) != 0) p++; + +return (*p == '}'); +} + + + +/************************************************* +* Read repeat counts * +*************************************************/ + +/* Read an item of the form {n,m} and return the values. This is called only +after is_counted_repeat() has confirmed that a repeat-count quantifier exists, +so the syntax is guaranteed to be correct, but we need to check the values. + +Arguments: + p pointer to first char after '{' + minp pointer to int for min + maxp pointer to int for max + returned as -1 if no max + errorcodeptr points to error code variable + +Returns: pointer to '}' on success; + current ptr on error, with errorcodeptr set non-zero +*/ + +static const uschar * +read_repeat_counts(const uschar *p, int *minp, int *maxp, int *errorcodeptr) +{ +int min = 0; +int max = -1; + +/* Read the minimum value and do a paranoid check: a negative value indicates +an integer overflow. */ + +while ((digitab[*p] & ctype_digit) != 0) min = min * 10 + *p++ - '0'; +if (min < 0 || min > 65535) + { + *errorcodeptr = ERR5; + return p; + } + +/* Read the maximum value if there is one, and again do a paranoid on its size. +Also, max must not be less than min. */ + +if (*p == '}') max = min; else + { + if (*(++p) != '}') + { + max = 0; + while((digitab[*p] & ctype_digit) != 0) max = max * 10 + *p++ - '0'; + if (max < 0 || max > 65535) + { + *errorcodeptr = ERR5; + return p; + } + if (max < min) + { + *errorcodeptr = ERR4; + return p; + } + } + } + +/* Fill in the required variables, and pass back the pointer to the terminating +'}'. */ + +*minp = min; +*maxp = max; +return p; +} + + + +/************************************************* +* Find forward referenced named subpattern * +*************************************************/ + +/* This function scans along a pattern looking for capturing subpatterns, and +counting them. If it finds a named pattern that matches the name it is given, +it returns its number. This is used for forward references to named +subpatterns. We know that if (?P< is encountered, the name will be terminated +by '>' because that is checked in the first pass. + +Arguments: + pointer current position in the pattern + count current count of capturing parens + name name to seek + namelen name length + +Returns: the number of the named subpattern, or -1 if not found +*/ + +static int +find_named_parens(const uschar *ptr, int count, const uschar *name, int namelen) +{ +const uschar *thisname; +for (; *ptr != 0; ptr++) + { + if (*ptr == '\\' && ptr[1] != 0) { ptr++; continue; } + if (*ptr != '(') continue; + if (ptr[1] != '?') { count++; continue; } + if (ptr[2] == '(') { ptr += 2; continue; } + if (ptr[2] != 'P' || ptr[3] != '<') continue; + count++; + ptr += 4; + thisname = ptr; + while (*ptr != '>') ptr++; + if (namelen == ptr - thisname && strncmp(name, thisname, namelen) == 0) + return count; + } +return -1; +} + + + +/************************************************* +* Find first significant op code * +*************************************************/ + +/* This is called by several functions that scan a compiled expression looking +for a fixed first character, or an anchoring op code etc. It skips over things +that do not influence this. For some calls, a change of option is important. +For some calls, it makes sense to skip negative forward and all backward +assertions, and also the \b assertion; for others it does not. + +Arguments: + code pointer to the start of the group + options pointer to external options + optbit the option bit whose changing is significant, or + zero if none are + skipassert TRUE if certain assertions are to be skipped + +Returns: pointer to the first significant opcode +*/ + +static const uschar* +first_significant_code(const uschar *code, int *options, int optbit, + BOOL skipassert) +{ +for (;;) + { + switch ((int)*code) + { + case OP_OPT: + if (optbit > 0 && ((int)code[1] & optbit) != (*options & optbit)) + *options = (int)code[1]; + code += 2; + break; + + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + if (!skipassert) return code; + do code += GET(code, 1); while (*code == OP_ALT); + code += _pcre_OP_lengths[*code]; + break; + + case OP_WORD_BOUNDARY: + case OP_NOT_WORD_BOUNDARY: + if (!skipassert) return code; + /* Fall through */ + + case OP_CALLOUT: + case OP_CREF: + case OP_BRANUMBER: + code += _pcre_OP_lengths[*code]; + break; + + default: + return code; + } + } +/* Control never reaches here */ +} + + + + +/************************************************* +* Find the fixed length of a pattern * +*************************************************/ + +/* Scan a pattern and compute the fixed length of subject that will match it, +if the length is fixed. This is needed for dealing with backward assertions. +In UTF8 mode, the result is in characters rather than bytes. + +Arguments: + code points to the start of the pattern (the bracket) + options the compiling options + +Returns: the fixed length, or -1 if there is no fixed length, + or -2 if \C was encountered +*/ + +static int +find_fixedlength(uschar *code, int options) +{ +int length = -1; + +register int branchlength = 0; +register uschar *cc = code + 1 + LINK_SIZE; + +/* Scan along the opcodes for this branch. If we get to the end of the +branch, check the length against that of the other branches. */ + +for (;;) + { + int d; + register int op = *cc; + if (op >= OP_BRA) op = OP_BRA; + + switch (op) + { + case OP_BRA: + case OP_ONCE: + case OP_COND: + d = find_fixedlength(cc, options); + if (d < 0) return d; + branchlength += d; + do cc += GET(cc, 1); while (*cc == OP_ALT); + cc += 1 + LINK_SIZE; + break; + + /* Reached end of a branch; if it's a ket it is the end of a nested + call. If it's ALT it is an alternation in a nested call. If it is + END it's the end of the outer call. All can be handled by the same code. */ + + case OP_ALT: + case OP_KET: + case OP_KETRMAX: + case OP_KETRMIN: + case OP_END: + if (length < 0) length = branchlength; + else if (length != branchlength) return -1; + if (*cc != OP_ALT) return length; + cc += 1 + LINK_SIZE; + branchlength = 0; + break; + + /* Skip over assertive subpatterns */ + + case OP_ASSERT: + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + do cc += GET(cc, 1); while (*cc == OP_ALT); + /* Fall through */ + + /* Skip over things that don't match chars */ + + case OP_REVERSE: + case OP_BRANUMBER: + case OP_CREF: + case OP_OPT: + case OP_CALLOUT: + case OP_SOD: + case OP_SOM: + case OP_EOD: + case OP_EODN: + case OP_CIRC: + case OP_DOLL: + case OP_NOT_WORD_BOUNDARY: + case OP_WORD_BOUNDARY: + cc += _pcre_OP_lengths[*cc]; + break; + + /* Handle literal characters */ + + case OP_CHAR: + case OP_CHARNC: + case OP_NOT: + branchlength++; + cc += 2; +#ifdef SUPPORT_UTF8 + if ((options & PCRE_UTF8) != 0) + { + while ((*cc & 0xc0) == 0x80) cc++; + } +#endif + break; + + /* Handle exact repetitions. The count is already in characters, but we + need to skip over a multibyte character in UTF8 mode. */ + + case OP_EXACT: + branchlength += GET2(cc,1); + cc += 4; +#ifdef SUPPORT_UTF8 + if ((options & PCRE_UTF8) != 0) + { + while((*cc & 0x80) == 0x80) cc++; + } +#endif + break; + + case OP_TYPEEXACT: + branchlength += GET2(cc,1); + cc += 4; + break; + + /* Handle single-char matchers */ + + case OP_PROP: + case OP_NOTPROP: + cc += 2; + /* Fall through */ + + case OP_NOT_DIGIT: + case OP_DIGIT: + case OP_NOT_WHITESPACE: + case OP_WHITESPACE: + case OP_NOT_WORDCHAR: + case OP_WORDCHAR: + case OP_ANY: + branchlength++; + cc++; + break; + + /* The single-byte matcher isn't allowed */ + + case OP_ANYBYTE: + return -2; + + /* Check a class for variable quantification */ + +#ifdef SUPPORT_UTF8 + case OP_XCLASS: + cc += GET(cc, 1) - 33; + /* Fall through */ +#endif + + case OP_CLASS: + case OP_NCLASS: + cc += 33; + + switch (*cc) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + case OP_CRQUERY: + case OP_CRMINQUERY: + return -1; + + case OP_CRRANGE: + case OP_CRMINRANGE: + if (GET2(cc,1) != GET2(cc,3)) return -1; + branchlength += GET2(cc,1); + cc += 5; + break; + + default: + branchlength++; + } + break; + + /* Anything else is variable length */ + + default: + return -1; + } + } +/* Control never gets here */ +} + + + + +/************************************************* +* Scan compiled regex for numbered bracket * +*************************************************/ + +/* This little function scans through a compiled pattern until it finds a +capturing bracket with the given number. + +Arguments: + code points to start of expression + utf8 TRUE in UTF-8 mode + number the required bracket number + +Returns: pointer to the opcode for the bracket, or NULL if not found +*/ + +static const uschar * +find_bracket(const uschar *code, BOOL utf8, int number) +{ +for (;;) + { + register int c = *code; + if (c == OP_END) return NULL; + + /* XCLASS is used for classes that cannot be represented just by a bit + map. This includes negated single high-valued characters. The length in + the table is zero; the actual length is stored in the compiled code. */ + + if (c == OP_XCLASS) code += GET(code, 1); + + /* Handle bracketed group */ + + else if (c > OP_BRA) + { + int n = c - OP_BRA; + if (n > EXTRACT_BASIC_MAX) n = GET2(code, 2+LINK_SIZE); + if (n == number) return (uschar *)code; + code += _pcre_OP_lengths[OP_BRA]; + } + + /* Otherwise, we get the item's length from the table. In UTF-8 mode, opcodes + that are followed by a character may be followed by a multi-byte character. + The length in the table is a minimum, so we have to scan along to skip the + extra bytes. All opcodes are less than 128, so we can use relatively + efficient code. */ + + else + { + code += _pcre_OP_lengths[c]; + if (utf8) switch(c) + { + case OP_CHAR: + case OP_CHARNC: + case OP_EXACT: + case OP_UPTO: + case OP_MINUPTO: + case OP_STAR: + case OP_MINSTAR: + case OP_PLUS: + case OP_MINPLUS: + case OP_QUERY: + case OP_MINQUERY: + while ((*code & 0xc0) == 0x80) code++; + break; + } + } + } +} + + + +/************************************************* +* Scan compiled regex for recursion reference * +*************************************************/ + +/* This little function scans through a compiled pattern until it finds an +instance of OP_RECURSE. + +Arguments: + code points to start of expression + utf8 TRUE in UTF-8 mode + +Returns: pointer to the opcode for OP_RECURSE, or NULL if not found +*/ + +static const uschar * +find_recurse(const uschar *code, BOOL utf8) +{ +for (;;) + { + register int c = *code; + if (c == OP_END) return NULL; + if (c == OP_RECURSE) return code; + + /* XCLASS is used for classes that cannot be represented just by a bit + map. This includes negated single high-valued characters. The length in + the table is zero; the actual length is stored in the compiled code. */ + + if (c == OP_XCLASS) code += GET(code, 1); + + /* All bracketed groups have the same length. */ + + else if (c > OP_BRA) + { + code += _pcre_OP_lengths[OP_BRA]; + } + + /* Otherwise, we get the item's length from the table. In UTF-8 mode, opcodes + that are followed by a character may be followed by a multi-byte character. + The length in the table is a minimum, so we have to scan along to skip the + extra bytes. All opcodes are less than 128, so we can use relatively + efficient code. */ + + else + { + code += _pcre_OP_lengths[c]; + if (utf8) switch(c) + { + case OP_CHAR: + case OP_CHARNC: + case OP_EXACT: + case OP_UPTO: + case OP_MINUPTO: + case OP_STAR: + case OP_MINSTAR: + case OP_PLUS: + case OP_MINPLUS: + case OP_QUERY: + case OP_MINQUERY: + while ((*code & 0xc0) == 0x80) code++; + break; + } + } + } +} + + + +/************************************************* +* Scan compiled branch for non-emptiness * +*************************************************/ + +/* This function scans through a branch of a compiled pattern to see whether it +can match the empty string or not. It is called only from could_be_empty() +below. Note that first_significant_code() skips over assertions. If we hit an +unclosed bracket, we return "empty" - this means we've struck an inner bracket +whose current branch will already have been scanned. + +Arguments: + code points to start of search + endcode points to where to stop + utf8 TRUE if in UTF8 mode + +Returns: TRUE if what is matched could be empty +*/ + +static BOOL +could_be_empty_branch(const uschar *code, const uschar *endcode, BOOL utf8) +{ +register int c; +for (code = first_significant_code(code + 1 + LINK_SIZE, NULL, 0, TRUE); + code < endcode; + code = first_significant_code(code + _pcre_OP_lengths[c], NULL, 0, TRUE)) + { + const uschar *ccode; + + c = *code; + + if (c >= OP_BRA) + { + BOOL empty_branch; + if (GET(code, 1) == 0) return TRUE; /* Hit unclosed bracket */ + + /* Scan a closed bracket */ + + empty_branch = FALSE; + do + { + if (!empty_branch && could_be_empty_branch(code, endcode, utf8)) + empty_branch = TRUE; + code += GET(code, 1); + } + while (*code == OP_ALT); + if (!empty_branch) return FALSE; /* All branches are non-empty */ + code += 1 + LINK_SIZE; + c = *code; + } + + else switch (c) + { + /* Check for quantifiers after a class */ + +#ifdef SUPPORT_UTF8 + case OP_XCLASS: + ccode = code + GET(code, 1); + goto CHECK_CLASS_REPEAT; +#endif + + case OP_CLASS: + case OP_NCLASS: + ccode = code + 33; + +#ifdef SUPPORT_UTF8 + CHECK_CLASS_REPEAT: +#endif + + switch (*ccode) + { + case OP_CRSTAR: /* These could be empty; continue */ + case OP_CRMINSTAR: + case OP_CRQUERY: + case OP_CRMINQUERY: + break; + + default: /* Non-repeat => class must match */ + case OP_CRPLUS: /* These repeats aren't empty */ + case OP_CRMINPLUS: + return FALSE; + + case OP_CRRANGE: + case OP_CRMINRANGE: + if (GET2(ccode, 1) > 0) return FALSE; /* Minimum > 0 */ + break; + } + break; + + /* Opcodes that must match a character */ + + case OP_PROP: + case OP_NOTPROP: + case OP_EXTUNI: + case OP_NOT_DIGIT: + case OP_DIGIT: + case OP_NOT_WHITESPACE: + case OP_WHITESPACE: + case OP_NOT_WORDCHAR: + case OP_WORDCHAR: + case OP_ANY: + case OP_ANYBYTE: + case OP_CHAR: + case OP_CHARNC: + case OP_NOT: + case OP_PLUS: + case OP_MINPLUS: + case OP_EXACT: + case OP_NOTPLUS: + case OP_NOTMINPLUS: + case OP_NOTEXACT: + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEEXACT: + return FALSE; + + /* End of branch */ + + case OP_KET: + case OP_KETRMAX: + case OP_KETRMIN: + case OP_ALT: + return TRUE; + + /* In UTF-8 mode, STAR, MINSTAR, QUERY, MINQUERY, UPTO, and MINUPTO may be + followed by a multibyte character */ + +#ifdef SUPPORT_UTF8 + case OP_STAR: + case OP_MINSTAR: + case OP_QUERY: + case OP_MINQUERY: + case OP_UPTO: + case OP_MINUPTO: + if (utf8) while ((code[2] & 0xc0) == 0x80) code++; + break; +#endif + } + } + +return TRUE; +} + + + +/************************************************* +* Scan compiled regex for non-emptiness * +*************************************************/ + +/* This function is called to check for left recursive calls. We want to check +the current branch of the current pattern to see if it could match the empty +string. If it could, we must look outwards for branches at other levels, +stopping when we pass beyond the bracket which is the subject of the recursion. + +Arguments: + code points to start of the recursion + endcode points to where to stop (current RECURSE item) + bcptr points to the chain of current (unclosed) branch starts + utf8 TRUE if in UTF-8 mode + +Returns: TRUE if what is matched could be empty +*/ + +static BOOL +could_be_empty(const uschar *code, const uschar *endcode, branch_chain *bcptr, + BOOL utf8) +{ +while (bcptr != NULL && bcptr->current >= code) + { + if (!could_be_empty_branch(bcptr->current, endcode, utf8)) return FALSE; + bcptr = bcptr->outer; + } +return TRUE; +} + + + +/************************************************* +* Check for POSIX class syntax * +*************************************************/ + +/* This function is called when the sequence "[:" or "[." or "[=" is +encountered in a character class. It checks whether this is followed by an +optional ^ and then a sequence of letters, terminated by a matching ":]" or +".]" or "=]". + +Argument: + ptr pointer to the initial [ + endptr where to return the end pointer + cd pointer to compile data + +Returns: TRUE or FALSE +*/ + +static BOOL +check_posix_syntax(const uschar *ptr, const uschar **endptr, compile_data *cd) +{ +int terminator; /* Don't combine these lines; the Solaris cc */ +terminator = *(++ptr); /* compiler warns about "non-constant" initializer. */ +if (*(++ptr) == '^') ptr++; +while ((cd->ctypes[*ptr] & ctype_letter) != 0) ptr++; +if (*ptr == terminator && ptr[1] == ']') + { + *endptr = ptr; + return TRUE; + } +return FALSE; +} + + + + +/************************************************* +* Check POSIX class name * +*************************************************/ + +/* This function is called to check the name given in a POSIX-style class entry +such as [:alnum:]. + +Arguments: + ptr points to the first letter + len the length of the name + +Returns: a value representing the name, or -1 if unknown +*/ + +static int +check_posix_name(const uschar *ptr, int len) +{ +register int yield = 0; +while (posix_name_lengths[yield] != 0) + { + if (len == posix_name_lengths[yield] && + strncmp((const char *)ptr, posix_names[yield], len) == 0) return yield; + yield++; + } +return -1; +} + + +/************************************************* +* Adjust OP_RECURSE items in repeated group * +*************************************************/ + +/* OP_RECURSE items contain an offset from the start of the regex to the group +that is referenced. This means that groups can be replicated for fixed +repetition simply by copying (because the recursion is allowed to refer to +earlier groups that are outside the current group). However, when a group is +optional (i.e. the minimum quantifier is zero), OP_BRAZERO is inserted before +it, after it has been compiled. This means that any OP_RECURSE items within it +that refer to the group itself or any contained groups have to have their +offsets adjusted. That is the job of this function. Before it is called, the +partially compiled regex must be temporarily terminated with OP_END. + +Arguments: + group points to the start of the group + adjust the amount by which the group is to be moved + utf8 TRUE in UTF-8 mode + cd contains pointers to tables etc. + +Returns: nothing +*/ + +static void +adjust_recurse(uschar *group, int adjust, BOOL utf8, compile_data *cd) +{ +uschar *ptr = group; +while ((ptr = (uschar *)find_recurse(ptr, utf8)) != NULL) + { + int offset = GET(ptr, 1); + if (cd->start_code + offset >= group) PUT(ptr, 1, offset + adjust); + ptr += 1 + LINK_SIZE; + } +} + + + +/************************************************* +* Insert an automatic callout point * +*************************************************/ + +/* This function is called when the PCRE_AUTO_CALLOUT option is set, to insert +callout points before each pattern item. + +Arguments: + code current code pointer + ptr current pattern pointer + cd pointers to tables etc + +Returns: new code pointer +*/ + +static uschar * +auto_callout(uschar *code, const uschar *ptr, compile_data *cd) +{ +*code++ = OP_CALLOUT; +*code++ = 255; +PUT(code, 0, ptr - cd->start_pattern); /* Pattern offset */ +PUT(code, LINK_SIZE, 0); /* Default length */ +return code + 2*LINK_SIZE; +} + + + +/************************************************* +* Complete a callout item * +*************************************************/ + +/* A callout item contains the length of the next item in the pattern, which +we can't fill in till after we have reached the relevant point. This is used +for both automatic and manual callouts. + +Arguments: + previous_callout points to previous callout item + ptr current pattern pointer + cd pointers to tables etc + +Returns: nothing +*/ + +static void +complete_callout(uschar *previous_callout, const uschar *ptr, compile_data *cd) +{ +int length = ptr - cd->start_pattern - GET(previous_callout, 2); +PUT(previous_callout, 2 + LINK_SIZE, length); +} + + + +#ifdef SUPPORT_UCP +/************************************************* +* Get othercase range * +*************************************************/ + +/* This function is passed the start and end of a class range, in UTF-8 mode +with UCP support. It searches up the characters, looking for internal ranges of +characters in the "other" case. Each call returns the next one, updating the +start address. + +Arguments: + cptr points to starting character value; updated + d end value + ocptr where to put start of othercase range + odptr where to put end of othercase range + +Yield: TRUE when range returned; FALSE when no more +*/ + +static BOOL +get_othercase_range(int *cptr, int d, int *ocptr, int *odptr) +{ +int c, othercase, next; + +for (c = *cptr; c <= d; c++) + { if ((othercase = _pcre_ucp_othercase(c)) >= 0) break; } + +if (c > d) return FALSE; + +*ocptr = othercase; +next = othercase + 1; + +for (++c; c <= d; c++) + { + if (_pcre_ucp_othercase(c) != next) break; + next++; + } + +*odptr = next - 1; +*cptr = c; + +return TRUE; +} +#endif /* SUPPORT_UCP */ + + +/************************************************* +* Compile one branch * +*************************************************/ + +/* Scan the pattern, compiling it into the code vector. If the options are +changed during the branch, the pointer is used to change the external options +bits. + +Arguments: + optionsptr pointer to the option bits + brackets points to number of extracting brackets used + codeptr points to the pointer to the current code point + ptrptr points to the current pattern pointer + errorcodeptr points to error code variable + firstbyteptr set to initial literal character, or < 0 (REQ_UNSET, REQ_NONE) + reqbyteptr set to the last literal character required, else < 0 + bcptr points to current branch chain + cd contains pointers to tables etc. + +Returns: TRUE on success + FALSE, with *errorcodeptr set non-zero on error +*/ + +static BOOL +compile_branch(int *optionsptr, int *brackets, uschar **codeptr, + const uschar **ptrptr, int *errorcodeptr, int *firstbyteptr, + int *reqbyteptr, branch_chain *bcptr, compile_data *cd) +{ +int repeat_type, op_type; +int repeat_min = 0, repeat_max = 0; /* To please picky compilers */ +int bravalue = 0; +int greedy_default, greedy_non_default; +int firstbyte, reqbyte; +int zeroreqbyte, zerofirstbyte; +int req_caseopt, reqvary, tempreqvary; +int options = *optionsptr; +int after_manual_callout = 0; +register int c; +register uschar *code = *codeptr; +uschar *tempcode; +BOOL inescq = FALSE; +BOOL groupsetfirstbyte = FALSE; +const uschar *ptr = *ptrptr; +const uschar *tempptr; +uschar *previous = NULL; +uschar *previous_callout = NULL; +uschar classbits[32]; + +#ifdef SUPPORT_UTF8 +BOOL class_utf8; +BOOL utf8 = (options & PCRE_UTF8) != 0; +uschar *class_utf8data; +uschar utf8_char[6]; +#else +BOOL utf8 = FALSE; +#endif + +/* Set up the default and non-default settings for greediness */ + +greedy_default = ((options & PCRE_UNGREEDY) != 0); +greedy_non_default = greedy_default ^ 1; + +/* Initialize no first byte, no required byte. REQ_UNSET means "no char +matching encountered yet". It gets changed to REQ_NONE if we hit something that +matches a non-fixed char first char; reqbyte just remains unset if we never +find one. + +When we hit a repeat whose minimum is zero, we may have to adjust these values +to take the zero repeat into account. This is implemented by setting them to +zerofirstbyte and zeroreqbyte when such a repeat is encountered. The individual +item types that can be repeated set these backoff variables appropriately. */ + +firstbyte = reqbyte = zerofirstbyte = zeroreqbyte = REQ_UNSET; + +/* The variable req_caseopt contains either the REQ_CASELESS value or zero, +according to the current setting of the caseless flag. REQ_CASELESS is a bit +value > 255. It is added into the firstbyte or reqbyte variables to record the +case status of the value. This is used only for ASCII characters. */ + +req_caseopt = ((options & PCRE_CASELESS) != 0)? REQ_CASELESS : 0; + +/* Switch on next character until the end of the branch */ + +for (;; ptr++) + { + BOOL negate_class; + BOOL possessive_quantifier; + BOOL is_quantifier; + int class_charcount; + int class_lastchar; + int newoptions; + int recno; + int skipbytes; + int subreqbyte; + int subfirstbyte; + int mclength; + uschar mcbuffer[8]; + + /* Next byte in the pattern */ + + c = *ptr; + + /* If in \Q...\E, check for the end; if not, we have a literal */ + + if (inescq && c != 0) + { + if (c == '\\' && ptr[1] == 'E') + { + inescq = FALSE; + ptr++; + continue; + } + else + { + if (previous_callout != NULL) + { + complete_callout(previous_callout, ptr, cd); + previous_callout = NULL; + } + if ((options & PCRE_AUTO_CALLOUT) != 0) + { + previous_callout = code; + code = auto_callout(code, ptr, cd); + } + goto NORMAL_CHAR; + } + } + + /* Fill in length of a previous callout, except when the next thing is + a quantifier. */ + + is_quantifier = c == '*' || c == '+' || c == '?' || + (c == '{' && is_counted_repeat(ptr+1)); + + if (!is_quantifier && previous_callout != NULL && + after_manual_callout-- <= 0) + { + complete_callout(previous_callout, ptr, cd); + previous_callout = NULL; + } + + /* In extended mode, skip white space and comments */ + + if ((options & PCRE_EXTENDED) != 0) + { + if ((cd->ctypes[c] & ctype_space) != 0) continue; + if (c == '#') + { + while (*(++ptr) != 0) if (IS_NEWLINE(ptr)) break; + if (*ptr != 0) + { + ptr += cd->nllen - 1; + continue; + } + /* Else fall through to handle end of string */ + c = 0; + } + } + + /* No auto callout for quantifiers. */ + + if ((options & PCRE_AUTO_CALLOUT) != 0 && !is_quantifier) + { + previous_callout = code; + code = auto_callout(code, ptr, cd); + } + + switch(c) + { + /* The branch terminates at end of string, |, or ). */ + + case 0: + case '|': + case ')': + *firstbyteptr = firstbyte; + *reqbyteptr = reqbyte; + *codeptr = code; + *ptrptr = ptr; + return TRUE; + + /* Handle single-character metacharacters. In multiline mode, ^ disables + the setting of any following char as a first character. */ + + case '^': + if ((options & PCRE_MULTILINE) != 0) + { + if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; + } + previous = NULL; + *code++ = OP_CIRC; + break; + + case '$': + previous = NULL; + *code++ = OP_DOLL; + break; + + /* There can never be a first char if '.' is first, whatever happens about + repeats. The value of reqbyte doesn't change either. */ + + case '.': + if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; + zerofirstbyte = firstbyte; + zeroreqbyte = reqbyte; + previous = code; + *code++ = OP_ANY; + break; + + /* Character classes. If the included characters are all < 256, we build a + 32-byte bitmap of the permitted characters, except in the special case + where there is only one such character. For negated classes, we build the + map as usual, then invert it at the end. However, we use a different opcode + so that data characters > 255 can be handled correctly. + + If the class contains characters outside the 0-255 range, a different + opcode is compiled. It may optionally have a bit map for characters < 256, + but those above are are explicitly listed afterwards. A flag byte tells + whether the bitmap is present, and whether this is a negated class or not. + */ + + case '[': + previous = code; + + /* PCRE supports POSIX class stuff inside a class. Perl gives an error if + they are encountered at the top level, so we'll do that too. */ + + if ((ptr[1] == ':' || ptr[1] == '.' || ptr[1] == '=') && + check_posix_syntax(ptr, &tempptr, cd)) + { + *errorcodeptr = (ptr[1] == ':')? ERR13 : ERR31; + goto FAILED; + } + + /* If the first character is '^', set the negation flag and skip it. */ + + if ((c = *(++ptr)) == '^') + { + negate_class = TRUE; + c = *(++ptr); + } + else + { + negate_class = FALSE; + } + + /* Keep a count of chars with values < 256 so that we can optimize the case + of just a single character (as long as it's < 256). For higher valued UTF-8 + characters, we don't yet do any optimization. */ + + class_charcount = 0; + class_lastchar = -1; + +#ifdef SUPPORT_UTF8 + class_utf8 = FALSE; /* No chars >= 256 */ + class_utf8data = code + LINK_SIZE + 34; /* For UTF-8 items */ +#endif + + /* Initialize the 32-char bit map to all zeros. We have to build the + map in a temporary bit of store, in case the class contains only 1 + character (< 256), because in that case the compiled code doesn't use the + bit map. */ + + memset(classbits, 0, 32 * sizeof(uschar)); + + /* Process characters until ] is reached. By writing this as a "do" it + means that an initial ] is taken as a data character. The first pass + through the regex checked the overall syntax, so we don't need to be very + strict here. At the start of the loop, c contains the first byte of the + character. */ + + do + { +#ifdef SUPPORT_UTF8 + if (utf8 && c > 127) + { /* Braces are required because the */ + GETCHARLEN(c, ptr, ptr); /* macro generates multiple statements */ + } +#endif + + /* Inside \Q...\E everything is literal except \E */ + + if (inescq) + { + if (c == '\\' && ptr[1] == 'E') + { + inescq = FALSE; + ptr++; + continue; + } + else goto LONE_SINGLE_CHARACTER; + } + + /* Handle POSIX class names. Perl allows a negation extension of the + form [:^name:]. A square bracket that doesn't match the syntax is + treated as a literal. We also recognize the POSIX constructions + [.ch.] and [=ch=] ("collating elements") and fault them, as Perl + 5.6 and 5.8 do. */ + + if (c == '[' && + (ptr[1] == ':' || ptr[1] == '.' || ptr[1] == '=') && + check_posix_syntax(ptr, &tempptr, cd)) + { + BOOL local_negate = FALSE; + int posix_class, taboffset, tabopt; + register const uschar *cbits = cd->cbits; + uschar pbits[32]; + + if (ptr[1] != ':') + { + *errorcodeptr = ERR31; + goto FAILED; + } + + ptr += 2; + if (*ptr == '^') + { + local_negate = TRUE; + ptr++; + } + + posix_class = check_posix_name(ptr, tempptr - ptr); + if (posix_class < 0) + { + *errorcodeptr = ERR30; + goto FAILED; + } + + /* If matching is caseless, upper and lower are converted to + alpha. This relies on the fact that the class table starts with + alpha, lower, upper as the first 3 entries. */ + + if ((options & PCRE_CASELESS) != 0 && posix_class <= 2) + posix_class = 0; + + /* We build the bit map for the POSIX class in a chunk of local store + because we may be adding and subtracting from it, and we don't want to + subtract bits that may be in the main map already. At the end we or the + result into the bit map that is being built. */ + + posix_class *= 3; + + /* Copy in the first table (always present) */ + + memcpy(pbits, cbits + posix_class_maps[posix_class], + 32 * sizeof(uschar)); + + /* If there is a second table, add or remove it as required. */ + + taboffset = posix_class_maps[posix_class + 1]; + tabopt = posix_class_maps[posix_class + 2]; + + if (taboffset >= 0) + { + if (tabopt >= 0) + for (c = 0; c < 32; c++) pbits[c] |= cbits[c + taboffset]; + else + for (c = 0; c < 32; c++) pbits[c] &= ~cbits[c + taboffset]; + } + + /* Not see if we need to remove any special characters. An option + value of 1 removes vertical space and 2 removes underscore. */ + + if (tabopt < 0) tabopt = -tabopt; + if (tabopt == 1) pbits[1] &= ~0x3c; + else if (tabopt == 2) pbits[11] &= 0x7f; + + /* Add the POSIX table or its complement into the main table that is + being built and we are done. */ + + if (local_negate) + for (c = 0; c < 32; c++) classbits[c] |= ~pbits[c]; + else + for (c = 0; c < 32; c++) classbits[c] |= pbits[c]; + + ptr = tempptr + 1; + class_charcount = 10; /* Set > 1; assumes more than 1 per class */ + continue; /* End of POSIX syntax handling */ + } + + /* Backslash may introduce a single character, or it may introduce one + of the specials, which just set a flag. Escaped items are checked for + validity in the pre-compiling pass. The sequence \b is a special case. + Inside a class (and only there) it is treated as backspace. Elsewhere + it marks a word boundary. Other escapes have preset maps ready to + or into the one we are building. We assume they have more than one + character in them, so set class_charcount bigger than one. */ + + if (c == '\\') + { + c = check_escape(&ptr, errorcodeptr, *brackets, options, TRUE); + + if (-c == ESC_b) c = '\b'; /* \b is backslash in a class */ + else if (-c == ESC_X) c = 'X'; /* \X is literal X in a class */ + else if (-c == ESC_Q) /* Handle start of quoted string */ + { + if (ptr[1] == '\\' && ptr[2] == 'E') + { + ptr += 2; /* avoid empty string */ + } + else inescq = TRUE; + continue; + } + + if (c < 0) + { + register const uschar *cbits = cd->cbits; + class_charcount += 2; /* Greater than 1 is what matters */ + switch (-c) + { + case ESC_d: + for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_digit]; + continue; + + case ESC_D: + for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_digit]; + continue; + + case ESC_w: + for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_word]; + continue; + + case ESC_W: + for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_word]; + continue; + + case ESC_s: + for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_space]; + classbits[1] &= ~0x08; /* Perl 5.004 onwards omits VT from \s */ + continue; + + case ESC_S: + for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_space]; + classbits[1] |= 0x08; /* Perl 5.004 onwards omits VT from \s */ + continue; + +#ifdef SUPPORT_UCP + case ESC_p: + case ESC_P: + { + BOOL negated; + int pdata; + int ptype = get_ucp(&ptr, &negated, &pdata, errorcodeptr); + if (ptype < 0) goto FAILED; + class_utf8 = TRUE; + *class_utf8data++ = ((-c == ESC_p) != negated)? + XCL_PROP : XCL_NOTPROP; + *class_utf8data++ = ptype; + *class_utf8data++ = pdata; + class_charcount -= 2; /* Not a < 256 character */ + } + continue; +#endif + + /* Unrecognized escapes are faulted if PCRE is running in its + strict mode. By default, for compatibility with Perl, they are + treated as literals. */ + + default: + if ((options & PCRE_EXTRA) != 0) + { + *errorcodeptr = ERR7; + goto FAILED; + } + c = *ptr; /* The final character */ + class_charcount -= 2; /* Undo the default count from above */ + } + } + + /* Fall through if we have a single character (c >= 0). This may be + > 256 in UTF-8 mode. */ + + } /* End of backslash handling */ + + /* A single character may be followed by '-' to form a range. However, + Perl does not permit ']' to be the end of the range. A '-' character + here is treated as a literal. */ + + if (ptr[1] == '-' && ptr[2] != ']') + { + int d; + ptr += 2; + +#ifdef SUPPORT_UTF8 + if (utf8) + { /* Braces are required because the */ + GETCHARLEN(d, ptr, ptr); /* macro generates multiple statements */ + } + else +#endif + d = *ptr; /* Not UTF-8 mode */ + + /* The second part of a range can be a single-character escape, but + not any of the other escapes. Perl 5.6 treats a hyphen as a literal + in such circumstances. */ + + if (d == '\\') + { + const uschar *oldptr = ptr; + d = check_escape(&ptr, errorcodeptr, *brackets, options, TRUE); + + /* \b is backslash; \X is literal X; any other special means the '-' + was literal */ + + if (d < 0) + { + if (d == -ESC_b) d = '\b'; + else if (d == -ESC_X) d = 'X'; else + { + ptr = oldptr - 2; + goto LONE_SINGLE_CHARACTER; /* A few lines below */ + } + } + } + + /* The check that the two values are in the correct order happens in + the pre-pass. Optimize one-character ranges */ + + if (d == c) goto LONE_SINGLE_CHARACTER; /* A few lines below */ + + /* In UTF-8 mode, if the upper limit is > 255, or > 127 for caseless + matching, we have to use an XCLASS with extra data items. Caseless + matching for characters > 127 is available only if UCP support is + available. */ + +#ifdef SUPPORT_UTF8 + if (utf8 && (d > 255 || ((options & PCRE_CASELESS) != 0 && d > 127))) + { + class_utf8 = TRUE; + + /* With UCP support, we can find the other case equivalents of + the relevant characters. There may be several ranges. Optimize how + they fit with the basic range. */ + +#ifdef SUPPORT_UCP + if ((options & PCRE_CASELESS) != 0) + { + int occ, ocd; + int cc = c; + int origd = d; + while (get_othercase_range(&cc, origd, &occ, &ocd)) + { + if (occ >= c && ocd <= d) continue; /* Skip embedded ranges */ + + if (occ < c && ocd >= c - 1) /* Extend the basic range */ + { /* if there is overlap, */ + c = occ; /* noting that if occ < c */ + continue; /* we can't have ocd > d */ + } /* because a subrange is */ + if (ocd > d && occ <= d + 1) /* always shorter than */ + { /* the basic range. */ + d = ocd; + continue; + } + + if (occ == ocd) + { + *class_utf8data++ = XCL_SINGLE; + } + else + { + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(occ, class_utf8data); + } + class_utf8data += _pcre_ord2utf8(ocd, class_utf8data); + } + } +#endif /* SUPPORT_UCP */ + + /* Now record the original range, possibly modified for UCP caseless + overlapping ranges. */ + + *class_utf8data++ = XCL_RANGE; + class_utf8data += _pcre_ord2utf8(c, class_utf8data); + class_utf8data += _pcre_ord2utf8(d, class_utf8data); + + /* With UCP support, we are done. Without UCP support, there is no + caseless matching for UTF-8 characters > 127; we can use the bit map + for the smaller ones. */ + +#ifdef SUPPORT_UCP + continue; /* With next character in the class */ +#else + if ((options & PCRE_CASELESS) == 0 || c > 127) continue; + + /* Adjust upper limit and fall through to set up the map */ + + d = 127; + +#endif /* SUPPORT_UCP */ + } +#endif /* SUPPORT_UTF8 */ + + /* We use the bit map for all cases when not in UTF-8 mode; else + ranges that lie entirely within 0-127 when there is UCP support; else + for partial ranges without UCP support. */ + + for (; c <= d; c++) + { + classbits[c/8] |= (1 << (c&7)); + if ((options & PCRE_CASELESS) != 0) + { + int uc = cd->fcc[c]; /* flip case */ + classbits[uc/8] |= (1 << (uc&7)); + } + class_charcount++; /* in case a one-char range */ + class_lastchar = c; + } + + continue; /* Go get the next char in the class */ + } + + /* Handle a lone single character - we can get here for a normal + non-escape char, or after \ that introduces a single character or for an + apparent range that isn't. */ + + LONE_SINGLE_CHARACTER: + + /* Handle a character that cannot go in the bit map */ + +#ifdef SUPPORT_UTF8 + if (utf8 && (c > 255 || ((options & PCRE_CASELESS) != 0 && c > 127))) + { + class_utf8 = TRUE; + *class_utf8data++ = XCL_SINGLE; + class_utf8data += _pcre_ord2utf8(c, class_utf8data); + +#ifdef SUPPORT_UCP + if ((options & PCRE_CASELESS) != 0) + { + int othercase; + if ((othercase = _pcre_ucp_othercase(c)) >= 0) + { + *class_utf8data++ = XCL_SINGLE; + class_utf8data += _pcre_ord2utf8(othercase, class_utf8data); + } + } +#endif /* SUPPORT_UCP */ + + } + else +#endif /* SUPPORT_UTF8 */ + + /* Handle a single-byte character */ + { + classbits[c/8] |= (1 << (c&7)); + if ((options & PCRE_CASELESS) != 0) + { + c = cd->fcc[c]; /* flip case */ + classbits[c/8] |= (1 << (c&7)); + } + class_charcount++; + class_lastchar = c; + } + } + + /* Loop until ']' reached; the check for end of string happens inside the + loop. This "while" is the end of the "do" above. */ + + while ((c = *(++ptr)) != ']' || inescq); + + /* If class_charcount is 1, we saw precisely one character whose value is + less than 256. In non-UTF-8 mode we can always optimize. In UTF-8 mode, we + can optimize the negative case only if there were no characters >= 128 + because OP_NOT and the related opcodes like OP_NOTSTAR operate on + single-bytes only. This is an historical hangover. Maybe one day we can + tidy these opcodes to handle multi-byte characters. + + The optimization throws away the bit map. We turn the item into a + 1-character OP_CHAR[NC] if it's positive, or OP_NOT if it's negative. Note + that OP_NOT does not support multibyte characters. In the positive case, it + can cause firstbyte to be set. Otherwise, there can be no first char if + this item is first, whatever repeat count may follow. In the case of + reqbyte, save the previous value for reinstating. */ + +#ifdef SUPPORT_UTF8 + if (class_charcount == 1 && + (!utf8 || + (!class_utf8 && (!negate_class || class_lastchar < 128)))) + +#else + if (class_charcount == 1) +#endif + { + zeroreqbyte = reqbyte; + + /* The OP_NOT opcode works on one-byte characters only. */ + + if (negate_class) + { + if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; + zerofirstbyte = firstbyte; + *code++ = OP_NOT; + *code++ = class_lastchar; + break; + } + + /* For a single, positive character, get the value into mcbuffer, and + then we can handle this with the normal one-character code. */ + +#ifdef SUPPORT_UTF8 + if (utf8 && class_lastchar > 127) + mclength = _pcre_ord2utf8(class_lastchar, mcbuffer); + else +#endif + { + mcbuffer[0] = class_lastchar; + mclength = 1; + } + goto ONE_CHAR; + } /* End of 1-char optimization */ + + /* The general case - not the one-char optimization. If this is the first + thing in the branch, there can be no first char setting, whatever the + repeat count. Any reqbyte setting must remain unchanged after any kind of + repeat. */ + + if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; + zerofirstbyte = firstbyte; + zeroreqbyte = reqbyte; + + /* If there are characters with values > 255, we have to compile an + extended class, with its own opcode. If there are no characters < 256, + we can omit the bitmap. */ + +#ifdef SUPPORT_UTF8 + if (class_utf8) + { + *class_utf8data++ = XCL_END; /* Marks the end of extra data */ + *code++ = OP_XCLASS; + code += LINK_SIZE; + *code = negate_class? XCL_NOT : 0; + + /* If the map is required, install it, and move on to the end of + the extra data */ + + if (class_charcount > 0) + { + *code++ |= XCL_MAP; + memcpy(code, classbits, 32); + code = class_utf8data; + } + + /* If the map is not required, slide down the extra data. */ + + else + { + int len = class_utf8data - (code + 33); + memmove(code + 1, code + 33, len); + code += len + 1; + } + + /* Now fill in the complete length of the item */ + + PUT(previous, 1, code - previous); + break; /* End of class handling */ + } +#endif + + /* If there are no characters > 255, negate the 32-byte map if necessary, + and copy it into the code vector. If this is the first thing in the branch, + there can be no first char setting, whatever the repeat count. Any reqbyte + setting must remain unchanged after any kind of repeat. */ + + if (negate_class) + { + *code++ = OP_NCLASS; + for (c = 0; c < 32; c++) code[c] = ~classbits[c]; + } + else + { + *code++ = OP_CLASS; + memcpy(code, classbits, 32); + } + code += 32; + break; + + /* Various kinds of repeat; '{' is not necessarily a quantifier, but this + has been tested above. */ + + case '{': + if (!is_quantifier) goto NORMAL_CHAR; + ptr = read_repeat_counts(ptr+1, &repeat_min, &repeat_max, errorcodeptr); + if (*errorcodeptr != 0) goto FAILED; + goto REPEAT; + + case '*': + repeat_min = 0; + repeat_max = -1; + goto REPEAT; + + case '+': + repeat_min = 1; + repeat_max = -1; + goto REPEAT; + + case '?': + repeat_min = 0; + repeat_max = 1; + + REPEAT: + if (previous == NULL) + { + *errorcodeptr = ERR9; + goto FAILED; + } + + if (repeat_min == 0) + { + firstbyte = zerofirstbyte; /* Adjust for zero repeat */ + reqbyte = zeroreqbyte; /* Ditto */ + } + + /* Remember whether this is a variable length repeat */ + + reqvary = (repeat_min == repeat_max)? 0 : REQ_VARY; + + op_type = 0; /* Default single-char op codes */ + possessive_quantifier = FALSE; /* Default not possessive quantifier */ + + /* Save start of previous item, in case we have to move it up to make space + for an inserted OP_ONCE for the additional '+' extension. */ + + tempcode = previous; + + /* If the next character is '+', we have a possessive quantifier. This + implies greediness, whatever the setting of the PCRE_UNGREEDY option. + If the next character is '?' this is a minimizing repeat, by default, + but if PCRE_UNGREEDY is set, it works the other way round. We change the + repeat type to the non-default. */ + + if (ptr[1] == '+') + { + repeat_type = 0; /* Force greedy */ + possessive_quantifier = TRUE; + ptr++; + } + else if (ptr[1] == '?') + { + repeat_type = greedy_non_default; + ptr++; + } + else repeat_type = greedy_default; + + /* If previous was a recursion, we need to wrap it inside brackets so that + it can be replicated if necessary. */ + + if (*previous == OP_RECURSE) + { + memmove(previous + 1 + LINK_SIZE, previous, 1 + LINK_SIZE); + code += 1 + LINK_SIZE; + *previous = OP_BRA; + PUT(previous, 1, code - previous); + *code = OP_KET; + PUT(code, 1, code - previous); + code += 1 + LINK_SIZE; + } + + /* If previous was a character match, abolish the item and generate a + repeat item instead. If a char item has a minumum of more than one, ensure + that it is set in reqbyte - it might not be if a sequence such as x{3} is + the first thing in a branch because the x will have gone into firstbyte + instead. */ + + if (*previous == OP_CHAR || *previous == OP_CHARNC) + { + /* Deal with UTF-8 characters that take up more than one byte. It's + easier to write this out separately than try to macrify it. Use c to + hold the length of the character in bytes, plus 0x80 to flag that it's a + length rather than a small character. */ + +#ifdef SUPPORT_UTF8 + if (utf8 && (code[-1] & 0x80) != 0) + { + uschar *lastchar = code - 1; + while((*lastchar & 0xc0) == 0x80) lastchar--; + c = code - lastchar; /* Length of UTF-8 character */ + memcpy(utf8_char, lastchar, c); /* Save the char */ + c |= 0x80; /* Flag c as a length */ + } + else +#endif + + /* Handle the case of a single byte - either with no UTF8 support, or + with UTF-8 disabled, or for a UTF-8 character < 128. */ + + { + c = code[-1]; + if (repeat_min > 1) reqbyte = c | req_caseopt | cd->req_varyopt; + } + + goto OUTPUT_SINGLE_REPEAT; /* Code shared with single character types */ + } + + /* If previous was a single negated character ([^a] or similar), we use + one of the special opcodes, replacing it. The code is shared with single- + character repeats by setting opt_type to add a suitable offset into + repeat_type. OP_NOT is currently used only for single-byte chars. */ + + else if (*previous == OP_NOT) + { + op_type = OP_NOTSTAR - OP_STAR; /* Use "not" opcodes */ + c = previous[1]; + goto OUTPUT_SINGLE_REPEAT; + } + + /* If previous was a character type match (\d or similar), abolish it and + create a suitable repeat item. The code is shared with single-character + repeats by setting op_type to add a suitable offset into repeat_type. Note + the the Unicode property types will be present only when SUPPORT_UCP is + defined, but we don't wrap the little bits of code here because it just + makes it horribly messy. */ + + else if (*previous < OP_EODN) + { + uschar *oldcode; + int prop_type, prop_value; + op_type = OP_TYPESTAR - OP_STAR; /* Use type opcodes */ + c = *previous; + + OUTPUT_SINGLE_REPEAT: + if (*previous == OP_PROP || *previous == OP_NOTPROP) + { + prop_type = previous[1]; + prop_value = previous[2]; + } + else prop_type = prop_value = -1; + + oldcode = code; + code = previous; /* Usually overwrite previous item */ + + /* If the maximum is zero then the minimum must also be zero; Perl allows + this case, so we do too - by simply omitting the item altogether. */ + + if (repeat_max == 0) goto END_REPEAT; + + /* All real repeats make it impossible to handle partial matching (maybe + one day we will be able to remove this restriction). */ + + if (repeat_max != 1) cd->nopartial = TRUE; + + /* Combine the op_type with the repeat_type */ + + repeat_type += op_type; + + /* A minimum of zero is handled either as the special case * or ?, or as + an UPTO, with the maximum given. */ + + if (repeat_min == 0) + { + if (repeat_max == -1) *code++ = OP_STAR + repeat_type; + else if (repeat_max == 1) *code++ = OP_QUERY + repeat_type; + else + { + *code++ = OP_UPTO + repeat_type; + PUT2INC(code, 0, repeat_max); + } + } + + /* A repeat minimum of 1 is optimized into some special cases. If the + maximum is unlimited, we use OP_PLUS. Otherwise, the original item it + left in place and, if the maximum is greater than 1, we use OP_UPTO with + one less than the maximum. */ + + else if (repeat_min == 1) + { + if (repeat_max == -1) + *code++ = OP_PLUS + repeat_type; + else + { + code = oldcode; /* leave previous item in place */ + if (repeat_max == 1) goto END_REPEAT; + *code++ = OP_UPTO + repeat_type; + PUT2INC(code, 0, repeat_max - 1); + } + } + + /* The case {n,n} is just an EXACT, while the general case {n,m} is + handled as an EXACT followed by an UPTO. */ + + else + { + *code++ = OP_EXACT + op_type; /* NB EXACT doesn't have repeat_type */ + PUT2INC(code, 0, repeat_min); + + /* If the maximum is unlimited, insert an OP_STAR. Before doing so, + we have to insert the character for the previous code. For a repeated + Unicode property match, there are two extra bytes that define the + required property. In UTF-8 mode, long characters have their length in + c, with the 0x80 bit as a flag. */ + + if (repeat_max < 0) + { +#ifdef SUPPORT_UTF8 + if (utf8 && c >= 128) + { + memcpy(code, utf8_char, c & 7); + code += c & 7; + } + else +#endif + { + *code++ = c; + if (prop_type >= 0) + { + *code++ = prop_type; + *code++ = prop_value; + } + } + *code++ = OP_STAR + repeat_type; + } + + /* Else insert an UPTO if the max is greater than the min, again + preceded by the character, for the previously inserted code. */ + + else if (repeat_max != repeat_min) + { +#ifdef SUPPORT_UTF8 + if (utf8 && c >= 128) + { + memcpy(code, utf8_char, c & 7); + code += c & 7; + } + else +#endif + *code++ = c; + if (prop_type >= 0) + { + *code++ = prop_type; + *code++ = prop_value; + } + repeat_max -= repeat_min; + *code++ = OP_UPTO + repeat_type; + PUT2INC(code, 0, repeat_max); + } + } + + /* The character or character type itself comes last in all cases. */ + +#ifdef SUPPORT_UTF8 + if (utf8 && c >= 128) + { + memcpy(code, utf8_char, c & 7); + code += c & 7; + } + else +#endif + *code++ = c; + + /* For a repeated Unicode property match, there are two extra bytes that + define the required property. */ + +#ifdef SUPPORT_UCP + if (prop_type >= 0) + { + *code++ = prop_type; + *code++ = prop_value; + } +#endif + } + + /* If previous was a character class or a back reference, we put the repeat + stuff after it, but just skip the item if the repeat was {0,0}. */ + + else if (*previous == OP_CLASS || + *previous == OP_NCLASS || +#ifdef SUPPORT_UTF8 + *previous == OP_XCLASS || +#endif + *previous == OP_REF) + { + if (repeat_max == 0) + { + code = previous; + goto END_REPEAT; + } + + /* All real repeats make it impossible to handle partial matching (maybe + one day we will be able to remove this restriction). */ + + if (repeat_max != 1) cd->nopartial = TRUE; + + if (repeat_min == 0 && repeat_max == -1) + *code++ = OP_CRSTAR + repeat_type; + else if (repeat_min == 1 && repeat_max == -1) + *code++ = OP_CRPLUS + repeat_type; + else if (repeat_min == 0 && repeat_max == 1) + *code++ = OP_CRQUERY + repeat_type; + else + { + *code++ = OP_CRRANGE + repeat_type; + PUT2INC(code, 0, repeat_min); + if (repeat_max == -1) repeat_max = 0; /* 2-byte encoding for max */ + PUT2INC(code, 0, repeat_max); + } + } + + /* If previous was a bracket group, we may have to replicate it in certain + cases. */ + + else if (*previous >= OP_BRA || *previous == OP_ONCE || + *previous == OP_COND) + { + register int i; + int ketoffset = 0; + int len = code - previous; + uschar *bralink = NULL; + + /* If the maximum repeat count is unlimited, find the end of the bracket + by scanning through from the start, and compute the offset back to it + from the current code pointer. There may be an OP_OPT setting following + the final KET, so we can't find the end just by going back from the code + pointer. */ + + if (repeat_max == -1) + { + register uschar *ket = previous; + do ket += GET(ket, 1); while (*ket != OP_KET); + ketoffset = code - ket; + } + + /* The case of a zero minimum is special because of the need to stick + OP_BRAZERO in front of it, and because the group appears once in the + data, whereas in other cases it appears the minimum number of times. For + this reason, it is simplest to treat this case separately, as otherwise + the code gets far too messy. There are several special subcases when the + minimum is zero. */ + + if (repeat_min == 0) + { + /* If the maximum is also zero, we just omit the group from the output + altogether. */ + + if (repeat_max == 0) + { + code = previous; + goto END_REPEAT; + } + + /* If the maximum is 1 or unlimited, we just have to stick in the + BRAZERO and do no more at this point. However, we do need to adjust + any OP_RECURSE calls inside the group that refer to the group itself or + any internal group, because the offset is from the start of the whole + regex. Temporarily terminate the pattern while doing this. */ + + if (repeat_max <= 1) + { + *code = OP_END; + adjust_recurse(previous, 1, utf8, cd); + memmove(previous+1, previous, len); + code++; + *previous++ = OP_BRAZERO + repeat_type; + } + + /* If the maximum is greater than 1 and limited, we have to replicate + in a nested fashion, sticking OP_BRAZERO before each set of brackets. + The first one has to be handled carefully because it's the original + copy, which has to be moved up. The remainder can be handled by code + that is common with the non-zero minimum case below. We have to + adjust the value or repeat_max, since one less copy is required. Once + again, we may have to adjust any OP_RECURSE calls inside the group. */ + + else + { + int offset; + *code = OP_END; + adjust_recurse(previous, 2 + LINK_SIZE, utf8, cd); + memmove(previous + 2 + LINK_SIZE, previous, len); + code += 2 + LINK_SIZE; + *previous++ = OP_BRAZERO + repeat_type; + *previous++ = OP_BRA; + + /* We chain together the bracket offset fields that have to be + filled in later when the ends of the brackets are reached. */ + + offset = (bralink == NULL)? 0 : previous - bralink; + bralink = previous; + PUTINC(previous, 0, offset); + } + + repeat_max--; + } + + /* If the minimum is greater than zero, replicate the group as many + times as necessary, and adjust the maximum to the number of subsequent + copies that we need. If we set a first char from the group, and didn't + set a required char, copy the latter from the former. */ + + else + { + if (repeat_min > 1) + { + if (groupsetfirstbyte && reqbyte < 0) reqbyte = firstbyte; + for (i = 1; i < repeat_min; i++) + { + memcpy(code, previous, len); + code += len; + } + } + if (repeat_max > 0) repeat_max -= repeat_min; + } + + /* This code is common to both the zero and non-zero minimum cases. If + the maximum is limited, it replicates the group in a nested fashion, + remembering the bracket starts on a stack. In the case of a zero minimum, + the first one was set up above. In all cases the repeat_max now specifies + the number of additional copies needed. */ + + if (repeat_max >= 0) + { + for (i = repeat_max - 1; i >= 0; i--) + { + *code++ = OP_BRAZERO + repeat_type; + + /* All but the final copy start a new nesting, maintaining the + chain of brackets outstanding. */ + + if (i != 0) + { + int offset; + *code++ = OP_BRA; + offset = (bralink == NULL)? 0 : code - bralink; + bralink = code; + PUTINC(code, 0, offset); + } + + memcpy(code, previous, len); + code += len; + } + + /* Now chain through the pending brackets, and fill in their length + fields (which are holding the chain links pro tem). */ + + while (bralink != NULL) + { + int oldlinkoffset; + int offset = code - bralink + 1; + uschar *bra = code - offset; + oldlinkoffset = GET(bra, 1); + bralink = (oldlinkoffset == 0)? NULL : bralink - oldlinkoffset; + *code++ = OP_KET; + PUTINC(code, 0, offset); + PUT(bra, 1, offset); + } + } + + /* If the maximum is unlimited, set a repeater in the final copy. We + can't just offset backwards from the current code point, because we + don't know if there's been an options resetting after the ket. The + correct offset was computed above. */ + + else code[-ketoffset] = OP_KETRMAX + repeat_type; + } + + /* Else there's some kind of shambles */ + + else + { + *errorcodeptr = ERR11; + goto FAILED; + } + + /* If the character following a repeat is '+', we wrap the entire repeated + item inside OP_ONCE brackets. This is just syntactic sugar, taken from + Sun's Java package. The repeated item starts at tempcode, not at previous, + which might be the first part of a string whose (former) last char we + repeated. However, we don't support '+' after a greediness '?'. */ + + if (possessive_quantifier) + { + int len = code - tempcode; + memmove(tempcode + 1+LINK_SIZE, tempcode, len); + code += 1 + LINK_SIZE; + len += 1 + LINK_SIZE; + tempcode[0] = OP_ONCE; + *code++ = OP_KET; + PUTINC(code, 0, len); + PUT(tempcode, 1, len); + } + + /* In all case we no longer have a previous item. We also set the + "follows varying string" flag for subsequently encountered reqbytes if + it isn't already set and we have just passed a varying length item. */ + + END_REPEAT: + previous = NULL; + cd->req_varyopt |= reqvary; + break; + + + /* Start of nested bracket sub-expression, or comment or lookahead or + lookbehind or option setting or condition. First deal with special things + that can come after a bracket; all are introduced by ?, and the appearance + of any of them means that this is not a referencing group. They were + checked for validity in the first pass over the string, so we don't have to + check for syntax errors here. */ + + case '(': + newoptions = options; + skipbytes = 0; + + if (*(++ptr) == '?') + { + int set, unset; + int *optset; + + switch (*(++ptr)) + { + case '#': /* Comment; skip to ket */ + ptr++; + while (*ptr != ')') ptr++; + continue; + + case ':': /* Non-extracting bracket */ + bravalue = OP_BRA; + ptr++; + break; + + case '(': + bravalue = OP_COND; /* Conditional group */ + + /* A condition can be a number, referring to a numbered group, a name, + referring to a named group, 'R', referring to recursion, or an + assertion. There are two unfortunate ambiguities, caused by history. + (a) 'R' can be the recursive thing or the name 'R', and (b) a number + could be a name that consists of digits. In both cases, we look for a + name first; if not found, we try the other cases. If the first + character after (?( is a word character, we know the rest up to ) will + also be word characters because the syntax was checked in the first + pass. */ + + if ((cd->ctypes[ptr[1]] & ctype_word) != 0) + { + int i, namelen; + int condref = 0; + const uschar *name; + uschar *slot = cd->name_table; + + /* This is needed for all successful cases. */ + + skipbytes = 3; + + /* Read the name, but also get it as a number if it's all digits */ + + name = ++ptr; + while (*ptr != ')') + { + if (condref >= 0) + condref = ((digitab[*ptr] & ctype_digit) != 0)? + condref * 10 + *ptr - '0' : -1; + ptr++; + } + namelen = ptr - name; + ptr++; + + for (i = 0; i < cd->names_found; i++) + { + if (strncmp((char *)name, (char *)slot+2, namelen) == 0) break; + slot += cd->name_entry_size; + } + + /* Found a previous named subpattern */ + + if (i < cd->names_found) + { + condref = GET2(slot, 0); + code[1+LINK_SIZE] = OP_CREF; + PUT2(code, 2+LINK_SIZE, condref); + } + + /* Search the pattern for a forward reference */ + + else if ((i = find_named_parens(ptr, *brackets, name, namelen)) > 0) + { + code[1+LINK_SIZE] = OP_CREF; + PUT2(code, 2+LINK_SIZE, i); + } + + /* Check for 'R' for recursion */ + + else if (namelen == 1 && *name == 'R') + { + code[1+LINK_SIZE] = OP_CREF; + PUT2(code, 2+LINK_SIZE, CREF_RECURSE); + } + + /* Check for a subpattern number */ + + else if (condref > 0) + { + code[1+LINK_SIZE] = OP_CREF; + PUT2(code, 2+LINK_SIZE, condref); + } + + /* Either an unidentified subpattern, or a reference to (?(0) */ + + else + { + *errorcodeptr = (condref == 0)? ERR35: ERR15; + goto FAILED; + } + } + + /* For conditions that are assertions, we just fall through, having + set bravalue above. */ + + break; + + case '=': /* Positive lookahead */ + bravalue = OP_ASSERT; + ptr++; + break; + + case '!': /* Negative lookahead */ + bravalue = OP_ASSERT_NOT; + ptr++; + break; + + case '<': /* Lookbehinds */ + switch (*(++ptr)) + { + case '=': /* Positive lookbehind */ + bravalue = OP_ASSERTBACK; + ptr++; + break; + + case '!': /* Negative lookbehind */ + bravalue = OP_ASSERTBACK_NOT; + ptr++; + break; + } + break; + + case '>': /* One-time brackets */ + bravalue = OP_ONCE; + ptr++; + break; + + case 'C': /* Callout - may be followed by digits; */ + previous_callout = code; /* Save for later completion */ + after_manual_callout = 1; /* Skip one item before completing */ + *code++ = OP_CALLOUT; /* Already checked that the terminating */ + { /* closing parenthesis is present. */ + int n = 0; + while ((digitab[*(++ptr)] & ctype_digit) != 0) + n = n * 10 + *ptr - '0'; + if (n > 255) + { + *errorcodeptr = ERR38; + goto FAILED; + } + *code++ = n; + PUT(code, 0, ptr - cd->start_pattern + 1); /* Pattern offset */ + PUT(code, LINK_SIZE, 0); /* Default length */ + code += 2 * LINK_SIZE; + } + previous = NULL; + continue; + + case 'P': /* Named subpattern handling */ + if (*(++ptr) == '<') /* Definition */ + { + int i, namelen; + uschar *slot = cd->name_table; + const uschar *name; /* Don't amalgamate; some compilers */ + name = ++ptr; /* grumble at autoincrement in declaration */ + + while (*ptr++ != '>'); + namelen = ptr - name - 1; + + for (i = 0; i < cd->names_found; i++) + { + int crc = memcmp(name, slot+2, namelen); + if (crc == 0) + { + if (slot[2+namelen] == 0) + { + if ((options & PCRE_DUPNAMES) == 0) + { + *errorcodeptr = ERR43; + goto FAILED; + } + } + else crc = -1; /* Current name is substring */ + } + if (crc < 0) + { + memmove(slot + cd->name_entry_size, slot, + (cd->names_found - i) * cd->name_entry_size); + break; + } + slot += cd->name_entry_size; + } + + PUT2(slot, 0, *brackets + 1); + memcpy(slot + 2, name, namelen); + slot[2+namelen] = 0; + cd->names_found++; + goto NUMBERED_GROUP; + } + + if (*ptr == '=' || *ptr == '>') /* Reference or recursion */ + { + int i, namelen; + int type = *ptr++; + const uschar *name = ptr; + uschar *slot = cd->name_table; + + while (*ptr != ')') ptr++; + namelen = ptr - name; + + for (i = 0; i < cd->names_found; i++) + { + if (strncmp((char *)name, (char *)slot+2, namelen) == 0) break; + slot += cd->name_entry_size; + } + + if (i < cd->names_found) /* Back reference */ + { + recno = GET2(slot, 0); + } + else if ((recno = /* Forward back reference */ + find_named_parens(ptr, *brackets, name, namelen)) <= 0) + { + *errorcodeptr = ERR15; + goto FAILED; + } + + if (type == '>') goto HANDLE_RECURSION; /* A few lines below */ + + /* Back reference */ + + previous = code; + *code++ = OP_REF; + PUT2INC(code, 0, recno); + cd->backref_map |= (recno < 32)? (1 << recno) : 1; + if (recno > cd->top_backref) cd->top_backref = recno; + continue; + } + + /* Should never happen */ + break; + + case 'R': /* Pattern recursion */ + ptr++; /* Same as (?0) */ + /* Fall through */ + + /* Recursion or "subroutine" call */ + + case '0': case '1': case '2': case '3': case '4': + case '5': case '6': case '7': case '8': case '9': + { + const uschar *called; + recno = 0; + while((digitab[*ptr] & ctype_digit) != 0) + recno = recno * 10 + *ptr++ - '0'; + + /* Come here from code above that handles a named recursion */ + + HANDLE_RECURSION: + + previous = code; + + /* Find the bracket that is being referenced. Temporarily end the + regex in case it doesn't exist. */ + + *code = OP_END; + called = (recno == 0)? cd->start_code : + find_bracket(cd->start_code, utf8, recno); + if (called == NULL) + { + *errorcodeptr = ERR15; + goto FAILED; + } + + /* If the subpattern is still open, this is a recursive call. We + check to see if this is a left recursion that could loop for ever, + and diagnose that case. */ + + if (GET(called, 1) == 0 && could_be_empty(called, code, bcptr, utf8)) + { + *errorcodeptr = ERR40; + goto FAILED; + } + + /* Insert the recursion/subroutine item, automatically wrapped inside + "once" brackets. */ + + *code = OP_ONCE; + PUT(code, 1, 2 + 2*LINK_SIZE); + code += 1 + LINK_SIZE; + + *code = OP_RECURSE; + PUT(code, 1, called - cd->start_code); + code += 1 + LINK_SIZE; + + *code = OP_KET; + PUT(code, 1, 2 + 2*LINK_SIZE); + code += 1 + LINK_SIZE; + } + continue; + + /* Character after (? not specially recognized */ + + default: /* Option setting */ + set = unset = 0; + optset = &set; + + while (*ptr != ')' && *ptr != ':') + { + switch (*ptr++) + { + case '-': optset = &unset; break; + + case 'i': *optset |= PCRE_CASELESS; break; + case 'J': *optset |= PCRE_DUPNAMES; break; + case 'm': *optset |= PCRE_MULTILINE; break; + case 's': *optset |= PCRE_DOTALL; break; + case 'x': *optset |= PCRE_EXTENDED; break; + case 'U': *optset |= PCRE_UNGREEDY; break; + case 'X': *optset |= PCRE_EXTRA; break; + } + } + + /* Set up the changed option bits, but don't change anything yet. */ + + newoptions = (options | set) & (~unset); + + /* If the options ended with ')' this is not the start of a nested + group with option changes, so the options change at this level. Compile + code to change the ims options if this setting actually changes any of + them. We also pass the new setting back so that it can be put at the + start of any following branches, and when this group ends (if we are in + a group), a resetting item can be compiled. + + Note that if this item is right at the start of the pattern, the + options will have been abstracted and made global, so there will be no + change to compile. */ + + if (*ptr == ')') + { + if ((options & PCRE_IMS) != (newoptions & PCRE_IMS)) + { + *code++ = OP_OPT; + *code++ = newoptions & PCRE_IMS; + } + + /* Change options at this level, and pass them back for use + in subsequent branches. Reset the greedy defaults and the case + value for firstbyte and reqbyte. */ + + *optionsptr = options = newoptions; + greedy_default = ((newoptions & PCRE_UNGREEDY) != 0); + greedy_non_default = greedy_default ^ 1; + req_caseopt = ((options & PCRE_CASELESS) != 0)? REQ_CASELESS : 0; + + previous = NULL; /* This item can't be repeated */ + continue; /* It is complete */ + } + + /* If the options ended with ':' we are heading into a nested group + with possible change of options. Such groups are non-capturing and are + not assertions of any kind. All we need to do is skip over the ':'; + the newoptions value is handled below. */ + + bravalue = OP_BRA; + ptr++; + } + } + + /* If PCRE_NO_AUTO_CAPTURE is set, all unadorned brackets become + non-capturing and behave like (?:...) brackets */ + + else if ((options & PCRE_NO_AUTO_CAPTURE) != 0) + { + bravalue = OP_BRA; + } + + /* Else we have a referencing group; adjust the opcode. If the bracket + number is greater than EXTRACT_BASIC_MAX, we set the opcode one higher, and + arrange for the true number to follow later, in an OP_BRANUMBER item. */ + + else + { + NUMBERED_GROUP: + if (++(*brackets) > EXTRACT_BASIC_MAX) + { + bravalue = OP_BRA + EXTRACT_BASIC_MAX + 1; + code[1+LINK_SIZE] = OP_BRANUMBER; + PUT2(code, 2+LINK_SIZE, *brackets); + skipbytes = 3; + } + else bravalue = OP_BRA + *brackets; + } + + /* Process nested bracketed re. Assertions may not be repeated, but other + kinds can be. We copy code into a non-register variable in order to be able + to pass its address because some compilers complain otherwise. Pass in a + new setting for the ims options if they have changed. */ + + previous = (bravalue >= OP_ONCE)? code : NULL; + *code = bravalue; + tempcode = code; + tempreqvary = cd->req_varyopt; /* Save value before bracket */ + + if (!compile_regex( + newoptions, /* The complete new option state */ + options & PCRE_IMS, /* The previous ims option state */ + brackets, /* Extracting bracket count */ + &tempcode, /* Where to put code (updated) */ + &ptr, /* Input pointer (updated) */ + errorcodeptr, /* Where to put an error message */ + (bravalue == OP_ASSERTBACK || + bravalue == OP_ASSERTBACK_NOT), /* TRUE if back assert */ + skipbytes, /* Skip over OP_COND/OP_BRANUMBER */ + &subfirstbyte, /* For possible first char */ + &subreqbyte, /* For possible last char */ + bcptr, /* Current branch chain */ + cd)) /* Tables block */ + goto FAILED; + + /* At the end of compiling, code is still pointing to the start of the + group, while tempcode has been updated to point past the end of the group + and any option resetting that may follow it. The pattern pointer (ptr) + is on the bracket. */ + + /* If this is a conditional bracket, check that there are no more than + two branches in the group. */ + + else if (bravalue == OP_COND) + { + uschar *tc = code; + int condcount = 0; + + do { + condcount++; + tc += GET(tc,1); + } + while (*tc != OP_KET); + + if (condcount > 2) + { + *errorcodeptr = ERR27; + goto FAILED; + } + + /* If there is just one branch, we must not make use of its firstbyte or + reqbyte, because this is equivalent to an empty second branch. */ + + if (condcount == 1) subfirstbyte = subreqbyte = REQ_NONE; + } + + /* Handle updating of the required and first characters. Update for normal + brackets of all kinds, and conditions with two branches (see code above). + If the bracket is followed by a quantifier with zero repeat, we have to + back off. Hence the definition of zeroreqbyte and zerofirstbyte outside the + main loop so that they can be accessed for the back off. */ + + zeroreqbyte = reqbyte; + zerofirstbyte = firstbyte; + groupsetfirstbyte = FALSE; + + if (bravalue >= OP_BRA || bravalue == OP_ONCE || bravalue == OP_COND) + { + /* If we have not yet set a firstbyte in this branch, take it from the + subpattern, remembering that it was set here so that a repeat of more + than one can replicate it as reqbyte if necessary. If the subpattern has + no firstbyte, set "none" for the whole branch. In both cases, a zero + repeat forces firstbyte to "none". */ + + if (firstbyte == REQ_UNSET) + { + if (subfirstbyte >= 0) + { + firstbyte = subfirstbyte; + groupsetfirstbyte = TRUE; + } + else firstbyte = REQ_NONE; + zerofirstbyte = REQ_NONE; + } + + /* If firstbyte was previously set, convert the subpattern's firstbyte + into reqbyte if there wasn't one, using the vary flag that was in + existence beforehand. */ + + else if (subfirstbyte >= 0 && subreqbyte < 0) + subreqbyte = subfirstbyte | tempreqvary; + + /* If the subpattern set a required byte (or set a first byte that isn't + really the first byte - see above), set it. */ + + if (subreqbyte >= 0) reqbyte = subreqbyte; + } + + /* For a forward assertion, we take the reqbyte, if set. This can be + helpful if the pattern that follows the assertion doesn't set a different + char. For example, it's useful for /(?=abcde).+/. We can't set firstbyte + for an assertion, however because it leads to incorrect effect for patterns + such as /(?=a)a.+/ when the "real" "a" would then become a reqbyte instead + of a firstbyte. This is overcome by a scan at the end if there's no + firstbyte, looking for an asserted first char. */ + + else if (bravalue == OP_ASSERT && subreqbyte >= 0) reqbyte = subreqbyte; + + /* Now update the main code pointer to the end of the group. */ + + code = tempcode; + + /* Error if hit end of pattern */ + + if (*ptr != ')') + { + *errorcodeptr = ERR14; + goto FAILED; + } + break; + + /* Check \ for being a real metacharacter; if not, fall through and handle + it as a data character at the start of a string. Escape items are checked + for validity in the pre-compiling pass. */ + + case '\\': + tempptr = ptr; + c = check_escape(&ptr, errorcodeptr, *brackets, options, FALSE); + + /* Handle metacharacters introduced by \. For ones like \d, the ESC_ values + are arranged to be the negation of the corresponding OP_values. For the + back references, the values are ESC_REF plus the reference number. Only + back references and those types that consume a character may be repeated. + We can test for values between ESC_b and ESC_Z for the latter; this may + have to change if any new ones are ever created. */ + + if (c < 0) + { + if (-c == ESC_Q) /* Handle start of quoted string */ + { + if (ptr[1] == '\\' && ptr[2] == 'E') ptr += 2; /* avoid empty string */ + else inescq = TRUE; + continue; + } + + /* For metasequences that actually match a character, we disable the + setting of a first character if it hasn't already been set. */ + + if (firstbyte == REQ_UNSET && -c > ESC_b && -c < ESC_Z) + firstbyte = REQ_NONE; + + /* Set values to reset to if this is followed by a zero repeat. */ + + zerofirstbyte = firstbyte; + zeroreqbyte = reqbyte; + + /* Back references are handled specially */ + + if (-c >= ESC_REF) + { + int number = -c - ESC_REF; + previous = code; + *code++ = OP_REF; + PUT2INC(code, 0, number); + } + + /* So are Unicode property matches, if supported. We know that get_ucp + won't fail because it was tested in the pre-pass. */ + +#ifdef SUPPORT_UCP + else if (-c == ESC_P || -c == ESC_p) + { + BOOL negated; + int pdata; + int ptype = get_ucp(&ptr, &negated, &pdata, errorcodeptr); + previous = code; + *code++ = ((-c == ESC_p) != negated)? OP_PROP : OP_NOTPROP; + *code++ = ptype; + *code++ = pdata; + } +#endif + + /* For the rest, we can obtain the OP value by negating the escape + value */ + + else + { + previous = (-c > ESC_b && -c < ESC_Z)? code : NULL; + *code++ = -c; + } + continue; + } + + /* We have a data character whose value is in c. In UTF-8 mode it may have + a value > 127. We set its representation in the length/buffer, and then + handle it as a data character. */ + +#ifdef SUPPORT_UTF8 + if (utf8 && c > 127) + mclength = _pcre_ord2utf8(c, mcbuffer); + else +#endif + + { + mcbuffer[0] = c; + mclength = 1; + } + + goto ONE_CHAR; + + /* Handle a literal character. It is guaranteed not to be whitespace or # + when the extended flag is set. If we are in UTF-8 mode, it may be a + multi-byte literal character. */ + + default: + NORMAL_CHAR: + mclength = 1; + mcbuffer[0] = c; + +#ifdef SUPPORT_UTF8 + if (utf8 && (c & 0xc0) == 0xc0) + { + while ((ptr[1] & 0xc0) == 0x80) + mcbuffer[mclength++] = *(++ptr); + } +#endif + + /* At this point we have the character's bytes in mcbuffer, and the length + in mclength. When not in UTF-8 mode, the length is always 1. */ + + ONE_CHAR: + previous = code; + *code++ = ((options & PCRE_CASELESS) != 0)? OP_CHARNC : OP_CHAR; + for (c = 0; c < mclength; c++) *code++ = mcbuffer[c]; + + /* Set the first and required bytes appropriately. If no previous first + byte, set it from this character, but revert to none on a zero repeat. + Otherwise, leave the firstbyte value alone, and don't change it on a zero + repeat. */ + + if (firstbyte == REQ_UNSET) + { + zerofirstbyte = REQ_NONE; + zeroreqbyte = reqbyte; + + /* If the character is more than one byte long, we can set firstbyte + only if it is not to be matched caselessly. */ + + if (mclength == 1 || req_caseopt == 0) + { + firstbyte = mcbuffer[0] | req_caseopt; + if (mclength != 1) reqbyte = code[-1] | cd->req_varyopt; + } + else firstbyte = reqbyte = REQ_NONE; + } + + /* firstbyte was previously set; we can set reqbyte only the length is + 1 or the matching is caseful. */ + + else + { + zerofirstbyte = firstbyte; + zeroreqbyte = reqbyte; + if (mclength == 1 || req_caseopt == 0) + reqbyte = code[-1] | req_caseopt | cd->req_varyopt; + } + + break; /* End of literal character handling */ + } + } /* end of big loop */ + +/* Control never reaches here by falling through, only by a goto for all the +error states. Pass back the position in the pattern so that it can be displayed +to the user for diagnosing the error. */ + +FAILED: +*ptrptr = ptr; +return FALSE; +} + + + + +/************************************************* +* Compile sequence of alternatives * +*************************************************/ + +/* On entry, ptr is pointing past the bracket character, but on return +it points to the closing bracket, or vertical bar, or end of string. +The code variable is pointing at the byte into which the BRA operator has been +stored. If the ims options are changed at the start (for a (?ims: group) or +during any branch, we need to insert an OP_OPT item at the start of every +following branch to ensure they get set correctly at run time, and also pass +the new options into every subsequent branch compile. + +Argument: + options option bits, including any changes for this subpattern + oldims previous settings of ims option bits + brackets -> int containing the number of extracting brackets used + codeptr -> the address of the current code pointer + ptrptr -> the address of the current pattern pointer + errorcodeptr -> pointer to error code variable + lookbehind TRUE if this is a lookbehind assertion + skipbytes skip this many bytes at start (for OP_COND, OP_BRANUMBER) + firstbyteptr place to put the first required character, or a negative number + reqbyteptr place to put the last required character, or a negative number + bcptr pointer to the chain of currently open branches + cd points to the data block with tables pointers etc. + +Returns: TRUE on success +*/ + +static BOOL +compile_regex(int options, int oldims, int *brackets, uschar **codeptr, + const uschar **ptrptr, int *errorcodeptr, BOOL lookbehind, int skipbytes, + int *firstbyteptr, int *reqbyteptr, branch_chain *bcptr, compile_data *cd) +{ +const uschar *ptr = *ptrptr; +uschar *code = *codeptr; +uschar *last_branch = code; +uschar *start_bracket = code; +uschar *reverse_count = NULL; +int firstbyte, reqbyte; +int branchfirstbyte, branchreqbyte; +branch_chain bc; + +bc.outer = bcptr; +bc.current = code; + +firstbyte = reqbyte = REQ_UNSET; + +/* Offset is set zero to mark that this bracket is still open */ + +PUT(code, 1, 0); +code += 1 + LINK_SIZE + skipbytes; + +/* Loop for each alternative branch */ + +for (;;) + { + /* Handle a change of ims options at the start of the branch */ + + if ((options & PCRE_IMS) != oldims) + { + *code++ = OP_OPT; + *code++ = options & PCRE_IMS; + } + + /* Set up dummy OP_REVERSE if lookbehind assertion */ + + if (lookbehind) + { + *code++ = OP_REVERSE; + reverse_count = code; + PUTINC(code, 0, 0); + } + + /* Now compile the branch */ + + if (!compile_branch(&options, brackets, &code, &ptr, errorcodeptr, + &branchfirstbyte, &branchreqbyte, &bc, cd)) + { + *ptrptr = ptr; + return FALSE; + } + + /* If this is the first branch, the firstbyte and reqbyte values for the + branch become the values for the regex. */ + + if (*last_branch != OP_ALT) + { + firstbyte = branchfirstbyte; + reqbyte = branchreqbyte; + } + + /* If this is not the first branch, the first char and reqbyte have to + match the values from all the previous branches, except that if the previous + value for reqbyte didn't have REQ_VARY set, it can still match, and we set + REQ_VARY for the regex. */ + + else + { + /* If we previously had a firstbyte, but it doesn't match the new branch, + we have to abandon the firstbyte for the regex, but if there was previously + no reqbyte, it takes on the value of the old firstbyte. */ + + if (firstbyte >= 0 && firstbyte != branchfirstbyte) + { + if (reqbyte < 0) reqbyte = firstbyte; + firstbyte = REQ_NONE; + } + + /* If we (now or from before) have no firstbyte, a firstbyte from the + branch becomes a reqbyte if there isn't a branch reqbyte. */ + + if (firstbyte < 0 && branchfirstbyte >= 0 && branchreqbyte < 0) + branchreqbyte = branchfirstbyte; + + /* Now ensure that the reqbytes match */ + + if ((reqbyte & ~REQ_VARY) != (branchreqbyte & ~REQ_VARY)) + reqbyte = REQ_NONE; + else reqbyte |= branchreqbyte; /* To "or" REQ_VARY */ + } + + /* If lookbehind, check that this branch matches a fixed-length string, + and put the length into the OP_REVERSE item. Temporarily mark the end of + the branch with OP_END. */ + + if (lookbehind) + { + int length; + *code = OP_END; + length = find_fixedlength(last_branch, options); + DPRINTF(("fixed length = %d\n", length)); + if (length < 0) + { + *errorcodeptr = (length == -2)? ERR36 : ERR25; + *ptrptr = ptr; + return FALSE; + } + PUT(reverse_count, 0, length); + } + + /* Reached end of expression, either ')' or end of pattern. Go back through + the alternative branches and reverse the chain of offsets, with the field in + the BRA item now becoming an offset to the first alternative. If there are + no alternatives, it points to the end of the group. The length in the + terminating ket is always the length of the whole bracketed item. If any of + the ims options were changed inside the group, compile a resetting op-code + following, except at the very end of the pattern. Return leaving the pointer + at the terminating char. */ + + if (*ptr != '|') + { + int length = code - last_branch; + do + { + int prev_length = GET(last_branch, 1); + PUT(last_branch, 1, length); + length = prev_length; + last_branch -= length; + } + while (length > 0); + + /* Fill in the ket */ + + *code = OP_KET; + PUT(code, 1, code - start_bracket); + code += 1 + LINK_SIZE; + + /* Resetting option if needed */ + + if ((options & PCRE_IMS) != oldims && *ptr == ')') + { + *code++ = OP_OPT; + *code++ = oldims; + } + + /* Set values to pass back */ + + *codeptr = code; + *ptrptr = ptr; + *firstbyteptr = firstbyte; + *reqbyteptr = reqbyte; + return TRUE; + } + + /* Another branch follows; insert an "or" node. Its length field points back + to the previous branch while the bracket remains open. At the end the chain + is reversed. It's done like this so that the start of the bracket has a + zero offset until it is closed, making it possible to detect recursion. */ + + *code = OP_ALT; + PUT(code, 1, code - last_branch); + bc.current = last_branch = code; + code += 1 + LINK_SIZE; + ptr++; + } +/* Control never reaches here */ +} + + + + +/************************************************* +* Check for anchored expression * +*************************************************/ + +/* Try to find out if this is an anchored regular expression. Consider each +alternative branch. If they all start with OP_SOD or OP_CIRC, or with a bracket +all of whose alternatives start with OP_SOD or OP_CIRC (recurse ad lib), then +it's anchored. However, if this is a multiline pattern, then only OP_SOD +counts, since OP_CIRC can match in the middle. + +We can also consider a regex to be anchored if OP_SOM starts all its branches. +This is the code for \G, which means "match at start of match position, taking +into account the match offset". + +A branch is also implicitly anchored if it starts with .* and DOTALL is set, +because that will try the rest of the pattern at all possible matching points, +so there is no point trying again.... er .... + +.... except when the .* appears inside capturing parentheses, and there is a +subsequent back reference to those parentheses. We haven't enough information +to catch that case precisely. + +At first, the best we could do was to detect when .* was in capturing brackets +and the highest back reference was greater than or equal to that level. +However, by keeping a bitmap of the first 31 back references, we can catch some +of the more common cases more precisely. + +Arguments: + code points to start of expression (the bracket) + options points to the options setting + bracket_map a bitmap of which brackets we are inside while testing; this + handles up to substring 31; after that we just have to take + the less precise approach + backref_map the back reference bitmap + +Returns: TRUE or FALSE +*/ + +static BOOL +is_anchored(register const uschar *code, int *options, unsigned int bracket_map, + unsigned int backref_map) +{ +do { + const uschar *scode = + first_significant_code(code + 1+LINK_SIZE, options, PCRE_MULTILINE, FALSE); + register int op = *scode; + + /* Capturing brackets */ + + if (op > OP_BRA) + { + int new_map; + op -= OP_BRA; + if (op > EXTRACT_BASIC_MAX) op = GET2(scode, 2+LINK_SIZE); + new_map = bracket_map | ((op < 32)? (1 << op) : 1); + if (!is_anchored(scode, options, new_map, backref_map)) return FALSE; + } + + /* Other brackets */ + + else if (op == OP_BRA || op == OP_ASSERT || op == OP_ONCE || op == OP_COND) + { + if (!is_anchored(scode, options, bracket_map, backref_map)) return FALSE; + } + + /* .* is not anchored unless DOTALL is set and it isn't in brackets that + are or may be referenced. */ + + else if ((op == OP_TYPESTAR || op == OP_TYPEMINSTAR) && + (*options & PCRE_DOTALL) != 0) + { + if (scode[1] != OP_ANY || (bracket_map & backref_map) != 0) return FALSE; + } + + /* Check for explicit anchoring */ + + else if (op != OP_SOD && op != OP_SOM && + ((*options & PCRE_MULTILINE) != 0 || op != OP_CIRC)) + return FALSE; + code += GET(code, 1); + } +while (*code == OP_ALT); /* Loop for each alternative */ +return TRUE; +} + + + +/************************************************* +* Check for starting with ^ or .* * +*************************************************/ + +/* This is called to find out if every branch starts with ^ or .* so that +"first char" processing can be done to speed things up in multiline +matching and for non-DOTALL patterns that start with .* (which must start at +the beginning or after \n). As in the case of is_anchored() (see above), we +have to take account of back references to capturing brackets that contain .* +because in that case we can't make the assumption. + +Arguments: + code points to start of expression (the bracket) + bracket_map a bitmap of which brackets we are inside while testing; this + handles up to substring 31; after that we just have to take + the less precise approach + backref_map the back reference bitmap + +Returns: TRUE or FALSE +*/ + +static BOOL +is_startline(const uschar *code, unsigned int bracket_map, + unsigned int backref_map) +{ +do { + const uschar *scode = first_significant_code(code + 1+LINK_SIZE, NULL, 0, + FALSE); + register int op = *scode; + + /* Capturing brackets */ + + if (op > OP_BRA) + { + int new_map; + op -= OP_BRA; + if (op > EXTRACT_BASIC_MAX) op = GET2(scode, 2+LINK_SIZE); + new_map = bracket_map | ((op < 32)? (1 << op) : 1); + if (!is_startline(scode, new_map, backref_map)) return FALSE; + } + + /* Other brackets */ + + else if (op == OP_BRA || op == OP_ASSERT || op == OP_ONCE || op == OP_COND) + { if (!is_startline(scode, bracket_map, backref_map)) return FALSE; } + + /* .* means "start at start or after \n" if it isn't in brackets that + may be referenced. */ + + else if (op == OP_TYPESTAR || op == OP_TYPEMINSTAR) + { + if (scode[1] != OP_ANY || (bracket_map & backref_map) != 0) return FALSE; + } + + /* Check for explicit circumflex */ + + else if (op != OP_CIRC) return FALSE; + + /* Move on to the next alternative */ + + code += GET(code, 1); + } +while (*code == OP_ALT); /* Loop for each alternative */ +return TRUE; +} + + + +/************************************************* +* Check for asserted fixed first char * +*************************************************/ + +/* During compilation, the "first char" settings from forward assertions are +discarded, because they can cause conflicts with actual literals that follow. +However, if we end up without a first char setting for an unanchored pattern, +it is worth scanning the regex to see if there is an initial asserted first +char. If all branches start with the same asserted char, or with a bracket all +of whose alternatives start with the same asserted char (recurse ad lib), then +we return that char, otherwise -1. + +Arguments: + code points to start of expression (the bracket) + options pointer to the options (used to check casing changes) + inassert TRUE if in an assertion + +Returns: -1 or the fixed first char +*/ + +static int +find_firstassertedchar(const uschar *code, int *options, BOOL inassert) +{ +register int c = -1; +do { + int d; + const uschar *scode = + first_significant_code(code + 1+LINK_SIZE, options, PCRE_CASELESS, TRUE); + register int op = *scode; + + if (op >= OP_BRA) op = OP_BRA; + + switch(op) + { + default: + return -1; + + case OP_BRA: + case OP_ASSERT: + case OP_ONCE: + case OP_COND: + if ((d = find_firstassertedchar(scode, options, op == OP_ASSERT)) < 0) + return -1; + if (c < 0) c = d; else if (c != d) return -1; + break; + + case OP_EXACT: /* Fall through */ + scode += 2; + + case OP_CHAR: + case OP_CHARNC: + case OP_PLUS: + case OP_MINPLUS: + if (!inassert) return -1; + if (c < 0) + { + c = scode[1]; + if ((*options & PCRE_CASELESS) != 0) c |= REQ_CASELESS; + } + else if (c != scode[1]) return -1; + break; + } + + code += GET(code, 1); + } +while (*code == OP_ALT); +return c; +} + + + +/************************************************* +* Compile a Regular Expression * +*************************************************/ + +/* This function takes a string and returns a pointer to a block of store +holding a compiled version of the expression. The original API for this +function had no error code return variable; it is retained for backwards +compatibility. The new function is given a new name. + +Arguments: + pattern the regular expression + options various option bits + errorcodeptr pointer to error code variable (pcre_compile2() only) + can be NULL if you don't want a code value + errorptr pointer to pointer to error text + erroroffset ptr offset in pattern where error was detected + tables pointer to character tables or NULL + +Returns: pointer to compiled data block, or NULL on error, + with errorptr and erroroffset set +*/ + +PCRE_DATA_SCOPE pcre * +pcre_compile(const char *pattern, int options, const char **errorptr, + int *erroroffset, const unsigned char *tables) +{ +return pcre_compile2(pattern, options, NULL, errorptr, erroroffset, tables); +} + + + +PCRE_DATA_SCOPE pcre * +pcre_compile2(const char *pattern, int options, int *errorcodeptr, + const char **errorptr, int *erroroffset, const unsigned char *tables) +{ +real_pcre *re; +int length = 1 + LINK_SIZE; /* For initial BRA plus length */ +int c, firstbyte, reqbyte, newline; +int bracount = 0; +int branch_extra = 0; +int branch_newextra; +int item_count = -1; +int name_count = 0; +int max_name_size = 0; +int lastitemlength = 0; +int errorcode = 0; +#ifdef SUPPORT_UTF8 +BOOL utf8; +BOOL class_utf8; +#endif +BOOL inescq = FALSE; +BOOL capturing; +unsigned int brastackptr = 0; +size_t size; +uschar *code; +const uschar *codestart; +const uschar *ptr; +compile_data compile_block; +compile_data *cd = &compile_block; +int brastack[BRASTACK_SIZE]; +uschar bralenstack[BRASTACK_SIZE]; + +/* We can't pass back an error message if errorptr is NULL; I guess the best we +can do is just return NULL, but we can set a code value if there is a code +pointer. */ + +if (errorptr == NULL) + { + if (errorcodeptr != NULL) *errorcodeptr = 99; + return NULL; + } + +*errorptr = NULL; +if (errorcodeptr != NULL) *errorcodeptr = ERR0; + +/* However, we can give a message for this error */ + +if (erroroffset == NULL) + { + errorcode = ERR16; + goto PCRE_EARLY_ERROR_RETURN; + } + +*erroroffset = 0; + +/* Can't support UTF8 unless PCRE has been compiled to include the code. */ + +#ifdef SUPPORT_UTF8 +utf8 = (options & PCRE_UTF8) != 0; +if (utf8 && (options & PCRE_NO_UTF8_CHECK) == 0 && + (*erroroffset = _pcre_valid_utf8((uschar *)pattern, -1)) >= 0) + { + errorcode = ERR44; + goto PCRE_EARLY_ERROR_RETURN; + } +#else +if ((options & PCRE_UTF8) != 0) + { + errorcode = ERR32; + goto PCRE_EARLY_ERROR_RETURN; + } +#endif + +if ((options & ~PUBLIC_OPTIONS) != 0) + { + errorcode = ERR17; + goto PCRE_EARLY_ERROR_RETURN; + } + +/* Set up pointers to the individual character tables */ + +if (tables == NULL) tables = _pcre_default_tables; +cd->lcc = tables + lcc_offset; +cd->fcc = tables + fcc_offset; +cd->cbits = tables + cbits_offset; +cd->ctypes = tables + ctypes_offset; + +/* Handle different types of newline. The two bits give four cases. The current +code allows for one- or two-byte sequences. */ + +switch (options & PCRE_NEWLINE_CRLF) + { + default: newline = NEWLINE; break; /* Compile-time default */ + case PCRE_NEWLINE_CR: newline = '\r'; break; + case PCRE_NEWLINE_LF: newline = '\n'; break; + case PCRE_NEWLINE_CR+ + PCRE_NEWLINE_LF: newline = ('\r' << 8) | '\n'; break; + } + +if (newline > 255) + { + cd->nllen = 2; + cd->nl[0] = (newline >> 8) & 255; + cd->nl[1] = newline & 255; + } +else + { + cd->nllen = 1; + cd->nl[0] = newline; + } + +/* Maximum back reference and backref bitmap. This is updated for numeric +references during the first pass, but for named references during the actual +compile pass. The bitmap records up to 31 back references to help in deciding +whether (.*) can be treated as anchored or not. */ + +cd->top_backref = 0; +cd->backref_map = 0; + +/* Reflect pattern for debugging output */ + +DPRINTF(("------------------------------------------------------------------\n")); +DPRINTF(("%s\n", pattern)); + +/* The first thing to do is to make a pass over the pattern to compute the +amount of store required to hold the compiled code. This does not have to be +perfect as long as errors are overestimates. At the same time we can detect any +flag settings right at the start, and extract them. Make an attempt to correct +for any counted white space if an "extended" flag setting appears late in the +pattern. We can't be so clever for #-comments. */ + +ptr = (const uschar *)(pattern - 1); +while ((c = *(++ptr)) != 0) + { + int min, max; + int class_optcount; + int bracket_length; + int duplength; + + /* If we are inside a \Q...\E sequence, all chars are literal */ + + if (inescq) + { + if ((options & PCRE_AUTO_CALLOUT) != 0) length += 2 + 2*LINK_SIZE; + goto NORMAL_CHAR; + } + + /* Otherwise, first check for ignored whitespace and comments */ + + if ((options & PCRE_EXTENDED) != 0) + { + if ((cd->ctypes[c] & ctype_space) != 0) continue; + if (c == '#') + { + while (*(++ptr) != 0) if (IS_NEWLINE(ptr)) break; + if (*ptr != 0) + { + ptr += cd->nllen - 1; + continue; + } + break; /* End loop at end of pattern */ + } + } + + item_count++; /* Is zero for the first non-comment item */ + + /* Allow space for auto callout before every item except quantifiers. */ + + if ((options & PCRE_AUTO_CALLOUT) != 0 && + c != '*' && c != '+' && c != '?' && + (c != '{' || !is_counted_repeat(ptr + 1))) + length += 2 + 2*LINK_SIZE; + + switch(c) + { + /* A backslashed item may be an escaped data character or it may be a + character type. */ + + case '\\': + c = check_escape(&ptr, &errorcode, bracount, options, FALSE); + if (errorcode != 0) goto PCRE_ERROR_RETURN; + + lastitemlength = 1; /* Default length of last item for repeats */ + + if (c >= 0) /* Data character */ + { + length += 2; /* For a one-byte character */ + +#ifdef SUPPORT_UTF8 + if (utf8 && c > 127) + { + int i; + for (i = 0; i < _pcre_utf8_table1_size; i++) + if (c <= _pcre_utf8_table1[i]) break; + length += i; + lastitemlength += i; + } +#endif + + continue; + } + + /* If \Q, enter "literal" mode */ + + if (-c == ESC_Q) + { + inescq = TRUE; + continue; + } + + /* \X is supported only if Unicode property support is compiled */ + +#ifndef SUPPORT_UCP + if (-c == ESC_X) + { + errorcode = ERR45; + goto PCRE_ERROR_RETURN; + } +#endif + + /* \P and \p are for Unicode properties, but only when the support has + been compiled. Each item needs 3 bytes. */ + + else if (-c == ESC_P || -c == ESC_p) + { +#ifdef SUPPORT_UCP + BOOL negated; + BOOL pdata; + length += 3; + lastitemlength = 3; + if (get_ucp(&ptr, &negated, &pdata, &errorcode) < 0) + goto PCRE_ERROR_RETURN; + continue; +#else + errorcode = ERR45; + goto PCRE_ERROR_RETURN; +#endif + } + + /* Other escapes need one byte */ + + length++; + + /* A back reference needs an additional 2 bytes, plus either one or 5 + bytes for a repeat. We also need to keep the value of the highest + back reference. */ + + if (c <= -ESC_REF) + { + int refnum = -c - ESC_REF; + cd->backref_map |= (refnum < 32)? (1 << refnum) : 1; + if (refnum > cd->top_backref) + cd->top_backref = refnum; + length += 2; /* For single back reference */ + if (ptr[1] == '{' && is_counted_repeat(ptr+2)) + { + ptr = read_repeat_counts(ptr+2, &min, &max, &errorcode); + if (errorcode != 0) goto PCRE_ERROR_RETURN; + if ((min == 0 && (max == 1 || max == -1)) || + (min == 1 && max == -1)) + length++; + else length += 5; + if (ptr[1] == '?') ptr++; + } + } + continue; + + case '^': /* Single-byte metacharacters */ + case '.': + case '$': + length++; + lastitemlength = 1; + continue; + + case '*': /* These repeats won't be after brackets; */ + case '+': /* those are handled separately */ + case '?': + length++; + goto POSESSIVE; /* A few lines below */ + + /* This covers the cases of braced repeats after a single char, metachar, + class, or back reference. */ + + case '{': + if (!is_counted_repeat(ptr+1)) goto NORMAL_CHAR; + ptr = read_repeat_counts(ptr+1, &min, &max, &errorcode); + if (errorcode != 0) goto PCRE_ERROR_RETURN; + + /* These special cases just insert one extra opcode */ + + if ((min == 0 && (max == 1 || max == -1)) || + (min == 1 && max == -1)) + length++; + + /* These cases might insert additional copies of a preceding character. */ + + else + { + if (min != 1) + { + length -= lastitemlength; /* Uncount the original char or metachar */ + if (min > 0) length += 3 + lastitemlength; + } + length += lastitemlength + ((max > 0)? 3 : 1); + } + + if (ptr[1] == '?') ptr++; /* Needs no extra length */ + + POSESSIVE: /* Test for possessive quantifier */ + if (ptr[1] == '+') + { + ptr++; + length += 2 + 2*LINK_SIZE; /* Allow for atomic brackets */ + } + continue; + + /* An alternation contains an offset to the next branch or ket. If any ims + options changed in the previous branch(es), and/or if we are in a + lookbehind assertion, extra space will be needed at the start of the + branch. This is handled by branch_extra. */ + + case '|': + length += 1 + LINK_SIZE + branch_extra; + continue; + + /* A character class uses 33 characters provided that all the character + values are less than 256. Otherwise, it uses a bit map for low valued + characters, and individual items for others. Don't worry about character + types that aren't allowed in classes - they'll get picked up during the + compile. A character class that contains only one single-byte character + uses 2 or 3 bytes, depending on whether it is negated or not. Notice this + where we can. (In UTF-8 mode we can do this only for chars < 128.) */ + + case '[': + if (*(++ptr) == '^') + { + class_optcount = 10; /* Greater than one */ + ptr++; + } + else class_optcount = 0; + +#ifdef SUPPORT_UTF8 + class_utf8 = FALSE; +#endif + + /* Written as a "do" so that an initial ']' is taken as data */ + + if (*ptr != 0) do + { + /* Inside \Q...\E everything is literal except \E */ + + if (inescq) + { + if (*ptr != '\\' || ptr[1] != 'E') goto GET_ONE_CHARACTER; + inescq = FALSE; + ptr += 1; + continue; + } + + /* Outside \Q...\E, check for escapes */ + + if (*ptr == '\\') + { + c = check_escape(&ptr, &errorcode, bracount, options, TRUE); + if (errorcode != 0) goto PCRE_ERROR_RETURN; + + /* \b is backspace inside a class; \X is literal */ + + if (-c == ESC_b) c = '\b'; + else if (-c == ESC_X) c = 'X'; + + /* \Q enters quoting mode */ + + else if (-c == ESC_Q) + { + inescq = TRUE; + continue; + } + + /* Handle escapes that turn into characters */ + + if (c >= 0) goto NON_SPECIAL_CHARACTER; + + /* Escapes that are meta-things. The normal ones just affect the + bit map, but Unicode properties require an XCLASS extended item. */ + + else + { + class_optcount = 10; /* \d, \s etc; make sure > 1 */ +#ifdef SUPPORT_UTF8 + if (-c == ESC_p || -c == ESC_P) + { + if (!class_utf8) + { + class_utf8 = TRUE; + length += LINK_SIZE + 2; + } + length += 3; + } +#endif + } + } + + /* Check the syntax for POSIX stuff. The bits we actually handle are + checked during the real compile phase. */ + + else if (*ptr == '[' && + (ptr[1] == ':' || ptr[1] == '.' || ptr[1] == '=') && + check_posix_syntax(ptr, &ptr, cd)) + { + ptr++; + class_optcount = 10; /* Make sure > 1 */ + } + + /* Anything else increments the possible optimization count. We have to + detect ranges here so that we can compute the number of extra ranges for + caseless wide characters when UCP support is available. If there are wide + characters, we are going to have to use an XCLASS, even for single + characters. */ + + else + { + int d; + + GET_ONE_CHARACTER: + +#ifdef SUPPORT_UTF8 + if (utf8) + { + int extra = 0; + GETCHARLEN(c, ptr, extra); + ptr += extra; + } + else c = *ptr; +#else + c = *ptr; +#endif + + /* Come here from handling \ above when it escapes to a char value */ + + NON_SPECIAL_CHARACTER: + class_optcount++; + + d = -1; + if (ptr[1] == '-') + { + uschar const *hyptr = ptr++; + if (ptr[1] == '\\') + { + ptr++; + d = check_escape(&ptr, &errorcode, bracount, options, TRUE); + if (errorcode != 0) goto PCRE_ERROR_RETURN; + if (-d == ESC_b) d = '\b'; /* backspace */ + else if (-d == ESC_X) d = 'X'; /* literal X in a class */ + } + else if (ptr[1] != 0 && ptr[1] != ']') + { + ptr++; +#ifdef SUPPORT_UTF8 + if (utf8) + { + int extra = 0; + GETCHARLEN(d, ptr, extra); + ptr += extra; + } + else +#endif + d = *ptr; + } + if (d < 0) ptr = hyptr; /* go back to hyphen as data */ + } + + /* If d >= 0 we have a range. In UTF-8 mode, if the end is > 255, or > + 127 for caseless matching, we will need to use an XCLASS. */ + + if (d >= 0) + { + class_optcount = 10; /* Ensure > 1 */ + if (d < c) + { + errorcode = ERR8; + goto PCRE_ERROR_RETURN; + } + +#ifdef SUPPORT_UTF8 + if (utf8 && (d > 255 || ((options & PCRE_CASELESS) != 0 && d > 127))) + { + uschar buffer[6]; + if (!class_utf8) /* Allow for XCLASS overhead */ + { + class_utf8 = TRUE; + length += LINK_SIZE + 2; + } + +#ifdef SUPPORT_UCP + /* If we have UCP support, find out how many extra ranges are + needed to map the other case of characters within this range. We + have to mimic the range optimization here, because extending the + range upwards might push d over a boundary that makes is use + another byte in the UTF-8 representation. */ + + if ((options & PCRE_CASELESS) != 0) + { + int occ, ocd; + int cc = c; + int origd = d; + while (get_othercase_range(&cc, origd, &occ, &ocd)) + { + if (occ >= c && ocd <= d) continue; /* Skip embedded */ + + if (occ < c && ocd >= c - 1) /* Extend the basic range */ + { /* if there is overlap, */ + c = occ; /* noting that if occ < c */ + continue; /* we can't have ocd > d */ + } /* because a subrange is */ + if (ocd > d && occ <= d + 1) /* always shorter than */ + { /* the basic range. */ + d = ocd; + continue; + } + + /* An extra item is needed */ + + length += 1 + _pcre_ord2utf8(occ, buffer) + + ((occ == ocd)? 0 : _pcre_ord2utf8(ocd, buffer)); + } + } +#endif /* SUPPORT_UCP */ + + /* The length of the (possibly extended) range */ + + length += 1 + _pcre_ord2utf8(c, buffer) + _pcre_ord2utf8(d, buffer); + } +#endif /* SUPPORT_UTF8 */ + + } + + /* We have a single character. There is nothing to be done unless we + are in UTF-8 mode. If the char is > 255, or 127 when caseless, we must + allow for an XCL_SINGLE item, doubled for caselessness if there is UCP + support. */ + + else + { +#ifdef SUPPORT_UTF8 + if (utf8 && (c > 255 || ((options & PCRE_CASELESS) != 0 && c > 127))) + { + uschar buffer[6]; + class_optcount = 10; /* Ensure > 1 */ + if (!class_utf8) /* Allow for XCLASS overhead */ + { + class_utf8 = TRUE; + length += LINK_SIZE + 2; + } +#ifdef SUPPORT_UCP + length += (((options & PCRE_CASELESS) != 0)? 2 : 1) * + (1 + _pcre_ord2utf8(c, buffer)); +#else /* SUPPORT_UCP */ + length += 1 + _pcre_ord2utf8(c, buffer); +#endif /* SUPPORT_UCP */ + } +#endif /* SUPPORT_UTF8 */ + } + } + } + while (*(++ptr) != 0 && (inescq || *ptr != ']')); /* Concludes "do" above */ + + if (*ptr == 0) /* Missing terminating ']' */ + { + errorcode = ERR6; + goto PCRE_ERROR_RETURN; + } + + /* We can optimize when there was only one optimizable character. Repeats + for positive and negated single one-byte chars are handled by the general + code. Here, we handle repeats for the class opcodes. */ + + if (class_optcount == 1) length += 3; else + { + length += 33; + + /* A repeat needs either 1 or 5 bytes. If it is a possessive quantifier, + we also need extra for wrapping the whole thing in a sub-pattern. */ + + if (*ptr != 0 && ptr[1] == '{' && is_counted_repeat(ptr+2)) + { + ptr = read_repeat_counts(ptr+2, &min, &max, &errorcode); + if (errorcode != 0) goto PCRE_ERROR_RETURN; + if ((min == 0 && (max == 1 || max == -1)) || + (min == 1 && max == -1)) + length++; + else length += 5; + if (ptr[1] == '+') + { + ptr++; + length += 2 + 2*LINK_SIZE; + } + else if (ptr[1] == '?') ptr++; + } + } + continue; + + /* Brackets may be genuine groups or special things */ + + case '(': + branch_newextra = 0; + bracket_length = 1 + LINK_SIZE; + capturing = FALSE; + + /* Handle special forms of bracket, which all start (? */ + + if (ptr[1] == '?') + { + int set, unset; + int *optset; + + switch (c = ptr[2]) + { + /* Skip over comments entirely */ + case '#': + ptr += 3; + while (*ptr != 0 && *ptr != ')') ptr++; + if (*ptr == 0) + { + errorcode = ERR18; + goto PCRE_ERROR_RETURN; + } + continue; + + /* Non-referencing groups and lookaheads just move the pointer on, and + then behave like a non-special bracket, except that they don't increment + the count of extracting brackets. Ditto for the "once only" bracket, + which is in Perl from version 5.005. */ + + case ':': + case '=': + case '!': + case '>': + ptr += 2; + break; + + /* Named subpatterns are an extension copied from Python */ + + case 'P': + ptr += 3; + + /* Handle the definition of a named subpattern */ + + if (*ptr == '<') + { + const uschar *p; /* Don't amalgamate; some compilers */ + p = ++ptr; /* grumble at autoincrement in declaration */ + while ((cd->ctypes[*ptr] & ctype_word) != 0) ptr++; + if (*ptr != '>') + { + errorcode = ERR42; + goto PCRE_ERROR_RETURN; + } + name_count++; + if (name_count > MAX_NAME_COUNT) + { + errorcode = ERR49; + goto PCRE_ERROR_RETURN; + } + if (ptr - p > max_name_size) + { + max_name_size = (ptr - p); + if (max_name_size > MAX_NAME_SIZE) + { + errorcode = ERR48; + goto PCRE_ERROR_RETURN; + } + } + capturing = TRUE; /* Named parentheses are always capturing */ + break; /* Go handle capturing parentheses */ + } + + /* Handle back references and recursive calls to named subpatterns */ + + if (*ptr == '=' || *ptr == '>') + { + length += 3 + 3*LINK_SIZE; /* Allow for the automatic "once" */ + while ((cd->ctypes[*(++ptr)] & ctype_word) != 0); + if (*ptr != ')') + { + errorcode = ERR42; + goto PCRE_ERROR_RETURN; + } + goto RECURSE_CHECK_QUANTIFIED; + } + + /* Unknown character after (?P */ + + errorcode = ERR41; + goto PCRE_ERROR_RETURN; + + /* (?R) specifies a recursive call to the regex, which is an extension + to provide the facility which can be obtained by (?p{perl-code}) in + Perl 5.6. In Perl 5.8 this has become (??{perl-code}). + + From PCRE 4.00, items such as (?3) specify subroutine-like "calls" to + the appropriate numbered brackets. This includes both recursive and + non-recursive calls. (?R) is now synonymous with (?0). */ + + case 'R': + ptr++; + + case '0': case '1': case '2': case '3': case '4': + case '5': case '6': case '7': case '8': case '9': + ptr += 2; + if (c != 'R') + while ((digitab[*(++ptr)] & ctype_digit) != 0); + if (*ptr != ')') + { + errorcode = ERR29; + goto PCRE_ERROR_RETURN; + } + length += 3 + 3*LINK_SIZE; /* Allows for the automatic "once" */ + + /* If this item is quantified, it will get wrapped inside brackets so + as to use the code for quantified brackets. We jump down and use the + code that handles this for real brackets. Come here from code for + named recursions/subroutines. */ + + RECURSE_CHECK_QUANTIFIED: + if (ptr[1] == '+' || ptr[1] == '*' || ptr[1] == '?' || ptr[1] == '{') + { + length += 2 + 2 * LINK_SIZE; /* to make bracketed */ + duplength = 5 + 3 * LINK_SIZE; + goto HANDLE_QUANTIFIED_BRACKETS; + } + continue; + + /* (?C) is an extension which provides "callout" - to provide a bit of + the functionality of the Perl (?{...}) feature. An optional number may + follow (default is zero). */ + + case 'C': + ptr += 2; + while ((digitab[*(++ptr)] & ctype_digit) != 0); + if (*ptr != ')') + { + errorcode = ERR39; + goto PCRE_ERROR_RETURN; + } + length += 2 + 2*LINK_SIZE; + continue; + + /* Lookbehinds are in Perl from version 5.005 */ + + case '<': + ptr += 3; + if (*ptr == '=' || *ptr == '!') + { + branch_newextra = 1 + LINK_SIZE; + length += 1 + LINK_SIZE; /* For the first branch */ + break; + } + errorcode = ERR24; + goto PCRE_ERROR_RETURN; + + /* Conditionals are in Perl from version 5.005. The bracket must either + be followed by a number (for bracket reference) or by an assertion + group. PCRE extends this by allowing a name to reference a named group; + unfortunately, previously 'R' was implemented for a recursion test. + When this is compiled, we look for the named group 'R' first. At this + point we just do a basic syntax check. */ + + case '(': + if ((cd->ctypes[ptr[3]] & ctype_word) != 0) + { + ptr += 4; + length += 3; + while ((cd->ctypes[*ptr] & ctype_word) != 0) ptr++; + if (*ptr != ')') + { + errorcode = ERR26; + goto PCRE_ERROR_RETURN; + } + } + else /* An assertion must follow */ + { + ptr++; /* Can treat like ':' as far as spacing is concerned */ + if (ptr[2] != '?' || + (ptr[3] != '=' && ptr[3] != '!' && ptr[3] != '<') ) + { + ptr += 2; /* To get right offset in message */ + errorcode = ERR28; + goto PCRE_ERROR_RETURN; + } + } + break; + + /* Else loop checking valid options until ) is met. Anything else is an + error. If we are without any brackets, i.e. at top level, the settings + act as if specified in the options, so massage the options immediately. + This is for backward compatibility with Perl 5.004. */ + + default: + set = unset = 0; + optset = &set; + ptr += 2; + + for (;; ptr++) + { + c = *ptr; + switch (c) + { + case 'i': + *optset |= PCRE_CASELESS; + continue; + + case 'J': + *optset |= PCRE_DUPNAMES; + options |= PCRE_JCHANGED; /* Record that it changed */ + continue; + + case 'm': + *optset |= PCRE_MULTILINE; + continue; + + case 's': + *optset |= PCRE_DOTALL; + continue; + + case 'x': + *optset |= PCRE_EXTENDED; + continue; + + case 'X': + *optset |= PCRE_EXTRA; + continue; + + case 'U': + *optset |= PCRE_UNGREEDY; + continue; + + case '-': + optset = &unset; + continue; + + /* A termination by ')' indicates an options-setting-only item; if + this is at the very start of the pattern (indicated by item_count + being zero), we use it to set the global options. This is helpful + when analyzing the pattern for first characters, etc. Otherwise + nothing is done here and it is handled during the compiling + process. + + We allow for more than one options setting at the start. If such + settings do not change the existing options, nothing is compiled. + However, we must leave space just in case something is compiled. + This can happen for pathological sequences such as (?i)(?-i) + because the global options will end up with -i set. The space is + small and not significant. (Before I did this there was a reported + bug with (?i)(?-i) in a machine-generated pattern.) + + [Historical note: Up to Perl 5.8, options settings at top level + were always global settings, wherever they appeared in the pattern. + That is, they were equivalent to an external setting. From 5.8 + onwards, they apply only to what follows (which is what you might + expect).] */ + + case ')': + if (item_count == 0) + { + options = (options | set) & (~unset); + set = unset = 0; /* To save length */ + item_count--; /* To allow for several */ + length += 2; + } + + /* Fall through */ + + /* A termination by ':' indicates the start of a nested group with + the given options set. This is again handled at compile time, but + we must allow for compiled space if any of the ims options are + set. We also have to allow for resetting space at the end of + the group, which is why 4 is added to the length and not just 2. + If there are several changes of options within the same group, this + will lead to an over-estimate on the length, but this shouldn't + matter very much. We also have to allow for resetting options at + the start of any alternations, which we do by setting + branch_newextra to 2. */ + + case ':': + if (((set|unset) & PCRE_IMS) != 0) + { + length += 4; + branch_newextra = 2; + } + goto END_OPTIONS; + + /* Unrecognized option character */ + + default: + errorcode = ERR12; + goto PCRE_ERROR_RETURN; + } + } + + /* If we hit a closing bracket, that's it - this is a freestanding + option-setting. We need to ensure that branch_extra is updated if + necessary. The only values branch_newextra can have here are 0 or 2. + If the value is 2, then branch_extra must either be 2 or 5, depending + on whether this is a lookbehind group or not. */ + + END_OPTIONS: + if (c == ')') + { + if (branch_newextra == 2 && + (branch_extra == 0 || branch_extra == 1+LINK_SIZE)) + branch_extra += branch_newextra; + continue; + } + + /* If options were terminated by ':' control comes here. This is a + non-capturing group with an options change. There is nothing more that + needs to be done because "capturing" is already set FALSE by default; + we can just fall through. */ + + } + } + + /* Ordinary parentheses, not followed by '?', are capturing unless + PCRE_NO_AUTO_CAPTURE is set. */ + + else capturing = (options & PCRE_NO_AUTO_CAPTURE) == 0; + + /* Capturing brackets must be counted so we can process escapes in a + Perlish way. If the number exceeds EXTRACT_BASIC_MAX we are going to need + an additional 3 bytes of memory per capturing bracket. */ + + if (capturing) + { + bracount++; + if (bracount > EXTRACT_BASIC_MAX) bracket_length += 3; + } + + /* Save length for computing whole length at end if there's a repeat that + requires duplication of the group. Also save the current value of + branch_extra, and start the new group with the new value. If non-zero, this + will either be 2 for a (?imsx: group, or 3 for a lookbehind assertion. */ + + if (brastackptr >= sizeof(brastack)/sizeof(int)) + { + errorcode = ERR19; + goto PCRE_ERROR_RETURN; + } + + bralenstack[brastackptr] = branch_extra; + branch_extra = branch_newextra; + + brastack[brastackptr++] = length; + length += bracket_length; + continue; + + /* Handle ket. Look for subsequent max/min; for certain sets of values we + have to replicate this bracket up to that many times. If brastackptr is + 0 this is an unmatched bracket which will generate an error, but take care + not to try to access brastack[-1] when computing the length and restoring + the branch_extra value. */ + + case ')': + length += 1 + LINK_SIZE; + if (brastackptr > 0) + { + duplength = length - brastack[--brastackptr]; + branch_extra = bralenstack[brastackptr]; + /* This is a paranoid check to stop integer overflow later on */ + if (duplength > MAX_DUPLENGTH) + { + errorcode = ERR50; + goto PCRE_ERROR_RETURN; + } + } + else duplength = 0; + + /* The following code is also used when a recursion such as (?3) is + followed by a quantifier, because in that case, it has to be wrapped inside + brackets so that the quantifier works. The value of duplength must be + set before arrival. */ + + HANDLE_QUANTIFIED_BRACKETS: + + /* Leave ptr at the final char; for read_repeat_counts this happens + automatically; for the others we need an increment. */ + + if ((c = ptr[1]) == '{' && is_counted_repeat(ptr+2)) + { + ptr = read_repeat_counts(ptr+2, &min, &max, &errorcode); + if (errorcode != 0) goto PCRE_ERROR_RETURN; + } + else if (c == '*') { min = 0; max = -1; ptr++; } + else if (c == '+') { min = 1; max = -1; ptr++; } + else if (c == '?') { min = 0; max = 1; ptr++; } + else { min = 1; max = 1; } + + /* If the minimum is zero, we have to allow for an OP_BRAZERO before the + group, and if the maximum is greater than zero, we have to replicate + maxval-1 times; each replication acquires an OP_BRAZERO plus a nesting + bracket set. */ + + if (min == 0) + { + length++; + if (max > 0) length += (max - 1) * (duplength + 3 + 2*LINK_SIZE); + } + + /* When the minimum is greater than zero, we have to replicate up to + minval-1 times, with no additions required in the copies. Then, if there + is a limited maximum we have to replicate up to maxval-1 times allowing + for a BRAZERO item before each optional copy and nesting brackets for all + but one of the optional copies. */ + + else + { + length += (min - 1) * duplength; + if (max > min) /* Need this test as max=-1 means no limit */ + length += (max - min) * (duplength + 3 + 2*LINK_SIZE) + - (2 + 2*LINK_SIZE); + } + + /* Allow space for once brackets for "possessive quantifier" */ + + if (ptr[1] == '+') + { + ptr++; + length += 2 + 2*LINK_SIZE; + } + continue; + + /* Non-special character. It won't be space or # in extended mode, so it is + always a genuine character. If we are in a \Q...\E sequence, check for the + end; if not, we have a literal. */ + + default: + NORMAL_CHAR: + + if (inescq && c == '\\' && ptr[1] == 'E') + { + inescq = FALSE; + ptr++; + continue; + } + + length += 2; /* For a one-byte character */ + lastitemlength = 1; /* Default length of last item for repeats */ + + /* In UTF-8 mode, check for additional bytes. */ + +#ifdef SUPPORT_UTF8 + if (utf8 && (c & 0xc0) == 0xc0) + { + while ((ptr[1] & 0xc0) == 0x80) /* Can't flow over the end */ + { /* because the end is marked */ + lastitemlength++; /* by a zero byte. */ + length++; + ptr++; + } + } +#endif + + continue; + } + } + +length += 2 + LINK_SIZE; /* For final KET and END */ + +if ((options & PCRE_AUTO_CALLOUT) != 0) + length += 2 + 2*LINK_SIZE; /* For final callout */ + +if (length > MAX_PATTERN_SIZE) + { + errorcode = ERR20; + goto PCRE_EARLY_ERROR_RETURN; + } + +/* Compute the size of data block needed and get it, either from malloc or +externally provided function. Integer overflow should no longer be possible +because nowadays we limit the maximum value of name_count and max_name size. */ + +size = length + sizeof(real_pcre) + name_count * (max_name_size + 3); +re = (real_pcre *)(pcre_malloc)(size); + +if (re == NULL) + { + errorcode = ERR21; + goto PCRE_EARLY_ERROR_RETURN; + } + +/* Put in the magic number, and save the sizes, options, and character table +pointer. NULL is used for the default character tables. The nullpad field is at +the end; it's there to help in the case when a regex compiled on a system with +4-byte pointers is run on another with 8-byte pointers. */ + +re->magic_number = MAGIC_NUMBER; +re->size = size; +re->options = options; +re->dummy1 = 0; +re->name_table_offset = sizeof(real_pcre); +re->name_entry_size = max_name_size + 3; +re->name_count = name_count; +re->ref_count = 0; +re->tables = (tables == _pcre_default_tables)? NULL : tables; +re->nullpad = NULL; + +/* The starting points of the name/number translation table and of the code are +passed around in the compile data block. */ + +cd->names_found = 0; +cd->name_entry_size = max_name_size + 3; +cd->name_table = (uschar *)re + re->name_table_offset; +codestart = cd->name_table + re->name_entry_size * re->name_count; +cd->start_code = codestart; +cd->start_pattern = (const uschar *)pattern; +cd->req_varyopt = 0; +cd->nopartial = FALSE; + +/* Set up a starting, non-extracting bracket, then compile the expression. On +error, errorcode will be set non-zero, so we don't need to look at the result +of the function here. */ + +ptr = (const uschar *)pattern; +code = (uschar *)codestart; +*code = OP_BRA; +bracount = 0; +(void)compile_regex(options, options & PCRE_IMS, &bracount, &code, &ptr, + &errorcode, FALSE, 0, &firstbyte, &reqbyte, NULL, cd); +re->top_bracket = bracount; +re->top_backref = cd->top_backref; + +if (cd->nopartial) re->options |= PCRE_NOPARTIAL; + +/* If not reached end of pattern on success, there's an excess bracket. */ + +if (errorcode == 0 && *ptr != 0) errorcode = ERR22; + +/* Fill in the terminating state and check for disastrous overflow, but +if debugging, leave the test till after things are printed out. */ + +*code++ = OP_END; + +#ifndef DEBUG +if (code - codestart > length) errorcode = ERR23; +#endif + +/* Give an error if there's back reference to a non-existent capturing +subpattern. */ + +if (re->top_backref > re->top_bracket) errorcode = ERR15; + +/* Failed to compile, or error while post-processing */ + +if (errorcode != 0) + { + (pcre_free)(re); + PCRE_ERROR_RETURN: + *erroroffset = ptr - (const uschar *)pattern; + PCRE_EARLY_ERROR_RETURN: + *errorptr = error_texts[errorcode]; + if (errorcodeptr != NULL) *errorcodeptr = errorcode; + return NULL; + } + +/* If the anchored option was not passed, set the flag if we can determine that +the pattern is anchored by virtue of ^ characters or \A or anything else (such +as starting with .* when DOTALL is set). + +Otherwise, if we know what the first character has to be, save it, because that +speeds up unanchored matches no end. If not, see if we can set the +PCRE_STARTLINE flag. This is helpful for multiline matches when all branches +start with ^. and also when all branches start with .* for non-DOTALL matches. +*/ + +if ((options & PCRE_ANCHORED) == 0) + { + int temp_options = options; + if (is_anchored(codestart, &temp_options, 0, cd->backref_map)) + re->options |= PCRE_ANCHORED; + else + { + if (firstbyte < 0) + firstbyte = find_firstassertedchar(codestart, &temp_options, FALSE); + if (firstbyte >= 0) /* Remove caseless flag for non-caseable chars */ + { + int ch = firstbyte & 255; + re->first_byte = ((firstbyte & REQ_CASELESS) != 0 && + cd->fcc[ch] == ch)? ch : firstbyte; + re->options |= PCRE_FIRSTSET; + } + else if (is_startline(codestart, 0, cd->backref_map)) + re->options |= PCRE_STARTLINE; + } + } + +/* For an anchored pattern, we use the "required byte" only if it follows a +variable length item in the regex. Remove the caseless flag for non-caseable +bytes. */ + +if (reqbyte >= 0 && + ((re->options & PCRE_ANCHORED) == 0 || (reqbyte & REQ_VARY) != 0)) + { + int ch = reqbyte & 255; + re->req_byte = ((reqbyte & REQ_CASELESS) != 0 && + cd->fcc[ch] == ch)? (reqbyte & ~REQ_CASELESS) : reqbyte; + re->options |= PCRE_REQCHSET; + } + +/* Print out the compiled data if debugging is enabled. This is never the +case when building a production library. */ + +#ifdef DEBUG + +printf("Length = %d top_bracket = %d top_backref = %d\n", + length, re->top_bracket, re->top_backref); + +if (re->options != 0) + { + printf("%s%s%s%s%s%s%s%s%s\n", + ((re->options & PCRE_NOPARTIAL) != 0)? "nopartial " : "", + ((re->options & PCRE_ANCHORED) != 0)? "anchored " : "", + ((re->options & PCRE_CASELESS) != 0)? "caseless " : "", + ((re->options & PCRE_EXTENDED) != 0)? "extended " : "", + ((re->options & PCRE_MULTILINE) != 0)? "multiline " : "", + ((re->options & PCRE_DOTALL) != 0)? "dotall " : "", + ((re->options & PCRE_DOLLAR_ENDONLY) != 0)? "endonly " : "", + ((re->options & PCRE_EXTRA) != 0)? "extra " : "", + ((re->options & PCRE_UNGREEDY) != 0)? "ungreedy " : ""); + } + +if ((re->options & PCRE_FIRSTSET) != 0) + { + int ch = re->first_byte & 255; + const char *caseless = ((re->first_byte & REQ_CASELESS) == 0)? + "" : " (caseless)"; + if (isprint(ch)) printf("First char = %c%s\n", ch, caseless); + else printf("First char = \\x%02x%s\n", ch, caseless); + } + +if ((re->options & PCRE_REQCHSET) != 0) + { + int ch = re->req_byte & 255; + const char *caseless = ((re->req_byte & REQ_CASELESS) == 0)? + "" : " (caseless)"; + if (isprint(ch)) printf("Req char = %c%s\n", ch, caseless); + else printf("Req char = \\x%02x%s\n", ch, caseless); + } + +pcre_printint(re, stdout); + +/* This check is done here in the debugging case so that the code that +was compiled can be seen. */ + +if (code - codestart > length) + { + (pcre_free)(re); + *errorptr = error_texts[ERR23]; + *erroroffset = ptr - (uschar *)pattern; + if (errorcodeptr != NULL) *errorcodeptr = ERR23; + return NULL; + } +#endif + +return (pcre *)re; +} + +/* End of pcre_compile.c */ diff --git a/libs/pcre/pcre_config.c b/libs/pcre/pcre_config.c new file mode 100644 index 0000000000..29e6c1a358 --- /dev/null +++ b/libs/pcre/pcre_config.c @@ -0,0 +1,116 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains the external function pcre_config(). */ + + +#include "pcre_internal.h" + + +/************************************************* +* Return info about what features are configured * +*************************************************/ + +/* This function has an extensible interface so that additional items can be +added compatibly. + +Arguments: + what what information is required + where where to put the information + +Returns: 0 if data returned, negative on error +*/ + +PCRE_DATA_SCOPE int +pcre_config(int what, void *where) +{ +switch (what) + { + case PCRE_CONFIG_UTF8: +#ifdef SUPPORT_UTF8 + *((int *)where) = 1; +#else + *((int *)where) = 0; +#endif + break; + + case PCRE_CONFIG_UNICODE_PROPERTIES: +#ifdef SUPPORT_UCP + *((int *)where) = 1; +#else + *((int *)where) = 0; +#endif + break; + + case PCRE_CONFIG_NEWLINE: + *((int *)where) = NEWLINE; + break; + + case PCRE_CONFIG_LINK_SIZE: + *((int *)where) = LINK_SIZE; + break; + + case PCRE_CONFIG_POSIX_MALLOC_THRESHOLD: + *((int *)where) = POSIX_MALLOC_THRESHOLD; + break; + + case PCRE_CONFIG_MATCH_LIMIT: + *((unsigned int *)where) = MATCH_LIMIT; + break; + + case PCRE_CONFIG_MATCH_LIMIT_RECURSION: + *((unsigned int *)where) = MATCH_LIMIT_RECURSION; + break; + + case PCRE_CONFIG_STACKRECURSE: +#ifdef NO_RECURSE + *((int *)where) = 0; +#else + *((int *)where) = 1; +#endif + break; + + default: return PCRE_ERROR_BADOPTION; + } + +return 0; +} + +/* End of pcre_config.c */ diff --git a/libs/pcre/pcre_dfa_exec.c b/libs/pcre/pcre_dfa_exec.c new file mode 100644 index 0000000000..d05d7666fc --- /dev/null +++ b/libs/pcre/pcre_dfa_exec.c @@ -0,0 +1,2088 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains the external function pcre_dfa_exec(), which is an +alternative matching function that uses a DFA algorithm. This is NOT Perl- +compatible, but it has advantages in certain applications. */ + + +#define NLBLOCK md /* The block containing newline information */ +#include "pcre_internal.h" + + +/* For use to indent debugging output */ + +#define SP " " + + + +/************************************************* +* Code parameters and static tables * +*************************************************/ + +/* These are offsets that are used to turn the OP_TYPESTAR and friends opcodes +into others, under special conditions. A gap of 10 between the blocks should be +enough. */ + +#define OP_PROP_EXTRA (EXTRACT_BASIC_MAX+1) +#define OP_EXTUNI_EXTRA (EXTRACT_BASIC_MAX+11) + + +/* This table identifies those opcodes that are followed immediately by a +character that is to be tested in some way. This makes is possible to +centralize the loading of these characters. In the case of Type * etc, the +"character" is the opcode for \D, \d, \S, \s, \W, or \w, which will always be a +small value. */ + +static uschar coptable[] = { + 0, /* End */ + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* \A, \G, \B, \b, \D, \d, \S, \s, \W, \w */ + 0, 0, /* Any, Anybyte */ + 0, 0, 0, /* NOTPROP, PROP, EXTUNI */ + 0, 0, 0, 0, 0, /* \Z, \z, Opt, ^, $ */ + 1, /* Char */ + 1, /* Charnc */ + 1, /* not */ + /* Positive single-char repeats */ + 1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ + 3, 3, 3, /* upto, minupto, exact */ + /* Negative single-char repeats - only for chars < 256 */ + 1, 1, 1, 1, 1, 1, /* NOT *, *?, +, +?, ?, ?? */ + 3, 3, 3, /* NOT upto, minupto, exact */ + /* Positive type repeats */ + 1, 1, 1, 1, 1, 1, /* Type *, *?, +, +?, ?, ?? */ + 3, 3, 3, /* Type upto, minupto, exact */ + /* Character class & ref repeats */ + 0, 0, 0, 0, 0, 0, /* *, *?, +, +?, ?, ?? */ + 0, 0, /* CRRANGE, CRMINRANGE */ + 0, /* CLASS */ + 0, /* NCLASS */ + 0, /* XCLASS - variable length */ + 0, /* REF */ + 0, /* RECURSE */ + 0, /* CALLOUT */ + 0, /* Alt */ + 0, /* Ket */ + 0, /* KetRmax */ + 0, /* KetRmin */ + 0, /* Assert */ + 0, /* Assert not */ + 0, /* Assert behind */ + 0, /* Assert behind not */ + 0, /* Reverse */ + 0, /* Once */ + 0, /* COND */ + 0, /* CREF */ + 0, 0, /* BRAZERO, BRAMINZERO */ + 0, /* BRANUMBER */ + 0 /* BRA */ +}; + +/* These 2 tables allow for compact code for testing for \D, \d, \S, \s, \W, +and \w */ + +static uschar toptable1[] = { + 0, 0, 0, 0, 0, + ctype_digit, ctype_digit, + ctype_space, ctype_space, + ctype_word, ctype_word, + 0 /* OP_ANY */ +}; + +static uschar toptable2[] = { + 0, 0, 0, 0, 0, + ctype_digit, 0, + ctype_space, 0, + ctype_word, 0, + 1 /* OP_ANY */ +}; + + +/* Structure for holding data about a particular state, which is in effect the +current data for an active path through the match tree. It must consist +entirely of ints because the working vector we are passed, and which we put +these structures in, is a vector of ints. */ + +typedef struct stateblock { + int offset; /* Offset to opcode */ + int count; /* Count for repeats */ + int ims; /* ims flag bits */ + int data; /* Some use extra data */ +} stateblock; + +#define INTS_PER_STATEBLOCK (sizeof(stateblock)/sizeof(int)) + + +#ifdef DEBUG +/************************************************* +* Print character string * +*************************************************/ + +/* Character string printing function for debugging. + +Arguments: + p points to string + length number of bytes + f where to print + +Returns: nothing +*/ + +static void +pchars(unsigned char *p, int length, FILE *f) +{ +int c; +while (length-- > 0) + { + if (isprint(c = *(p++))) + fprintf(f, "%c", c); + else + fprintf(f, "\\x%02x", c); + } +} +#endif + + + +/************************************************* +* Execute a Regular Expression - DFA engine * +*************************************************/ + +/* This internal function applies a compiled pattern to a subject string, +starting at a given point, using a DFA engine. This function is called from the +external one, possibly multiple times if the pattern is not anchored. The +function calls itself recursively for some kinds of subpattern. + +Arguments: + md the match_data block with fixed information + this_start_code the opening bracket of this subexpression's code + current_subject where we currently are in the subject string + start_offset start offset in the subject string + offsets vector to contain the matching string offsets + offsetcount size of same + workspace vector of workspace + wscount size of same + ims the current ims flags + rlevel function call recursion level + recursing regex recursive call level + +Returns: > 0 => + = 0 => + -1 => failed to match + < -1 => some kind of unexpected problem + +The following macros are used for adding states to the two state vectors (one +for the current character, one for the following character). */ + +#define ADD_ACTIVE(x,y) \ + if (active_count++ < wscount) \ + { \ + next_active_state->offset = (x); \ + next_active_state->count = (y); \ + next_active_state->ims = ims; \ + next_active_state++; \ + DPRINTF(("%.*sADD_ACTIVE(%d,%d)\n", rlevel*2-2, SP, (x), (y))); \ + } \ + else return PCRE_ERROR_DFA_WSSIZE + +#define ADD_ACTIVE_DATA(x,y,z) \ + if (active_count++ < wscount) \ + { \ + next_active_state->offset = (x); \ + next_active_state->count = (y); \ + next_active_state->ims = ims; \ + next_active_state->data = (z); \ + next_active_state++; \ + DPRINTF(("%.*sADD_ACTIVE_DATA(%d,%d,%d)\n", rlevel*2-2, SP, (x), (y), (z))); \ + } \ + else return PCRE_ERROR_DFA_WSSIZE + +#define ADD_NEW(x,y) \ + if (new_count++ < wscount) \ + { \ + next_new_state->offset = (x); \ + next_new_state->count = (y); \ + next_new_state->ims = ims; \ + next_new_state++; \ + DPRINTF(("%.*sADD_NEW(%d,%d)\n", rlevel*2-2, SP, (x), (y))); \ + } \ + else return PCRE_ERROR_DFA_WSSIZE + +#define ADD_NEW_DATA(x,y,z) \ + if (new_count++ < wscount) \ + { \ + next_new_state->offset = (x); \ + next_new_state->count = (y); \ + next_new_state->ims = ims; \ + next_new_state->data = (z); \ + next_new_state++; \ + DPRINTF(("%.*sADD_NEW_DATA(%d,%d,%d)\n", rlevel*2-2, SP, (x), (y), (z))); \ + } \ + else return PCRE_ERROR_DFA_WSSIZE + +/* And now, here is the code */ + +static int +internal_dfa_exec( + dfa_match_data *md, + const uschar *this_start_code, + const uschar *current_subject, + int start_offset, + int *offsets, + int offsetcount, + int *workspace, + int wscount, + int ims, + int rlevel, + int recursing) +{ +stateblock *active_states, *new_states, *temp_states; +stateblock *next_active_state, *next_new_state; + +const uschar *ctypes, *lcc, *fcc; +const uschar *ptr; +const uschar *end_code; + +int active_count, new_count, match_count; + +/* Some fields in the md block are frequently referenced, so we load them into +independent variables in the hope that this will perform better. */ + +const uschar *start_subject = md->start_subject; +const uschar *end_subject = md->end_subject; +const uschar *start_code = md->start_code; + +#ifdef SUPPORT_UTF8 +BOOL utf8 = (md->poptions & PCRE_UTF8) != 0; +#endif + +rlevel++; +offsetcount &= (-2); + +wscount -= 2; +wscount = (wscount - (wscount % (INTS_PER_STATEBLOCK * 2))) / + (2 * INTS_PER_STATEBLOCK); + +DPRINTF(("\n%.*s---------------------\n" + "%.*sCall to internal_dfa_exec f=%d r=%d\n", + rlevel*2-2, SP, rlevel*2-2, SP, rlevel, recursing)); + +ctypes = md->tables + ctypes_offset; +lcc = md->tables + lcc_offset; +fcc = md->tables + fcc_offset; + +match_count = PCRE_ERROR_NOMATCH; /* A negative number */ + +active_states = (stateblock *)(workspace + 2); +next_new_state = new_states = active_states + wscount; +new_count = 0; + +/* The first thing in any (sub) pattern is a bracket of some sort. Push all +the alternative states onto the list, and find out where the end is. This +makes is possible to use this function recursively, when we want to stop at a +matching internal ket rather than at the end. + +If the first opcode in the first alternative is OP_REVERSE, we are dealing with +a backward assertion. In that case, we have to find out the maximum amount to +move back, and set up each alternative appropriately. */ + +if (this_start_code[1+LINK_SIZE] == OP_REVERSE) + { + int max_back = 0; + int gone_back; + + end_code = this_start_code; + do + { + int back = GET(end_code, 2+LINK_SIZE); + if (back > max_back) max_back = back; + end_code += GET(end_code, 1); + } + while (*end_code == OP_ALT); + + /* If we can't go back the amount required for the longest lookbehind + pattern, go back as far as we can; some alternatives may still be viable. */ + +#ifdef SUPPORT_UTF8 + /* In character mode we have to step back character by character */ + + if (utf8) + { + for (gone_back = 0; gone_back < max_back; gone_back++) + { + if (current_subject <= start_subject) break; + current_subject--; + while (current_subject > start_subject && + (*current_subject & 0xc0) == 0x80) + current_subject--; + } + } + else +#endif + + /* In byte-mode we can do this quickly. */ + + { + gone_back = (current_subject - max_back < start_subject)? + current_subject - start_subject : max_back; + current_subject -= gone_back; + } + + /* Now we can process the individual branches. */ + + end_code = this_start_code; + do + { + int back = GET(end_code, 2+LINK_SIZE); + if (back <= gone_back) + { + int bstate = end_code - start_code + 2 + 2*LINK_SIZE; + ADD_NEW_DATA(-bstate, 0, gone_back - back); + } + end_code += GET(end_code, 1); + } + while (*end_code == OP_ALT); + } + +/* This is the code for a "normal" subpattern (not a backward assertion). The +start of a whole pattern is always one of these. If we are at the top level, +we may be asked to restart matching from the same point that we reached for a +previous partial match. We still have to scan through the top-level branches to +find the end state. */ + +else + { + end_code = this_start_code; + + /* Restarting */ + + if (rlevel == 1 && (md->moptions & PCRE_DFA_RESTART) != 0) + { + do { end_code += GET(end_code, 1); } while (*end_code == OP_ALT); + new_count = workspace[1]; + if (!workspace[0]) + memcpy(new_states, active_states, new_count * sizeof(stateblock)); + } + + /* Not restarting */ + + else + { + do + { + ADD_NEW(end_code - start_code + 1 + LINK_SIZE, 0); + end_code += GET(end_code, 1); + } + while (*end_code == OP_ALT); + } + } + +workspace[0] = 0; /* Bit indicating which vector is current */ + +DPRINTF(("%.*sEnd state = %d\n", rlevel*2-2, SP, end_code - start_code)); + +/* Loop for scanning the subject */ + +ptr = current_subject; +for (;;) + { + int i, j; + int clen, dlen; + unsigned int c, d; + + /* Make the new state list into the active state list and empty the + new state list. */ + + temp_states = active_states; + active_states = new_states; + new_states = temp_states; + active_count = new_count; + new_count = 0; + + workspace[0] ^= 1; /* Remember for the restarting feature */ + workspace[1] = active_count; + +#ifdef DEBUG + printf("%.*sNext character: rest of subject = \"", rlevel*2-2, SP); + pchars((uschar *)ptr, strlen((char *)ptr), stdout); + printf("\"\n"); + + printf("%.*sActive states: ", rlevel*2-2, SP); + for (i = 0; i < active_count; i++) + printf("%d/%d ", active_states[i].offset, active_states[i].count); + printf("\n"); +#endif + + /* Set the pointers for adding new states */ + + next_active_state = active_states + active_count; + next_new_state = new_states; + + /* Load the current character from the subject outside the loop, as many + different states may want to look at it, and we assume that at least one + will. */ + + if (ptr < end_subject) + { + clen = 1; +#ifdef SUPPORT_UTF8 + if (utf8) { GETCHARLEN(c, ptr, clen); } else +#endif /* SUPPORT_UTF8 */ + c = *ptr; + } + else + { + clen = 0; /* At end subject */ + c = -1; + } + + /* Scan up the active states and act on each one. The result of an action + may be to add more states to the currently active list (e.g. on hitting a + parenthesis) or it may be to put states on the new list, for considering + when we move the character pointer on. */ + + for (i = 0; i < active_count; i++) + { + stateblock *current_state = active_states + i; + const uschar *code; + int state_offset = current_state->offset; + int count, codevalue; + int chartype, script; + +#ifdef DEBUG + printf ("%.*sProcessing state %d c=", rlevel*2-2, SP, state_offset); + if (c < 0) printf("-1\n"); + else if (c > 32 && c < 127) printf("'%c'\n", c); + else printf("0x%02x\n", c); +#endif + + /* This variable is referred to implicity in the ADD_xxx macros. */ + + ims = current_state->ims; + + /* A negative offset is a special case meaning "hold off going to this + (negated) state until the number of characters in the data field have + been skipped". */ + + if (state_offset < 0) + { + if (current_state->data > 0) + { + DPRINTF(("%.*sSkipping this character\n", rlevel*2-2, SP)); + ADD_NEW_DATA(state_offset, current_state->count, + current_state->data - 1); + continue; + } + else + { + current_state->offset = state_offset = -state_offset; + } + } + + /* Check for a duplicate state with the same count, and skip if found. */ + + for (j = 0; j < i; j++) + { + if (active_states[j].offset == state_offset && + active_states[j].count == current_state->count) + { + DPRINTF(("%.*sDuplicate state: skipped\n", rlevel*2-2, SP)); + goto NEXT_ACTIVE_STATE; + } + } + + /* The state offset is the offset to the opcode */ + + code = start_code + state_offset; + codevalue = *code; + if (codevalue >= OP_BRA) codevalue = OP_BRA; /* All brackets are equal */ + + /* If this opcode is followed by an inline character, load it. It is + tempting to test for the presence of a subject character here, but that + is wrong, because sometimes zero repetitions of the subject are + permitted. + + We also use this mechanism for opcodes such as OP_TYPEPLUS that take an + argument that is not a data character - but is always one byte long. + Unfortunately, we have to take special action to deal with \P, \p, and + \X in this case. To keep the other cases fast, convert these ones to new + opcodes. */ + + if (coptable[codevalue] > 0) + { + dlen = 1; +#ifdef SUPPORT_UTF8 + if (utf8) { GETCHARLEN(d, (code + coptable[codevalue]), dlen); } else +#endif /* SUPPORT_UTF8 */ + d = code[coptable[codevalue]]; + if (codevalue >= OP_TYPESTAR) + { + if (d == OP_ANYBYTE) return PCRE_ERROR_DFA_UITEM; + if (d >= OP_NOTPROP) + codevalue += (d == OP_EXTUNI)? OP_EXTUNI_EXTRA : OP_PROP_EXTRA; + } + } + else + { + dlen = 0; /* Not strictly necessary, but compilers moan */ + d = -1; /* if these variables are not set. */ + } + + + /* Now process the individual opcodes */ + + switch (codevalue) + { + +/* ========================================================================== */ + /* Reached a closing bracket. If not at the end of the pattern, carry + on with the next opcode. Otherwise, unless we have an empty string and + PCRE_NOTEMPTY is set, save the match data, shifting up all previous + matches so we always have the longest first. */ + + case OP_KET: + case OP_KETRMIN: + case OP_KETRMAX: + if (code != end_code) + { + ADD_ACTIVE(state_offset + 1 + LINK_SIZE, 0); + if (codevalue != OP_KET) + { + ADD_ACTIVE(state_offset - GET(code, 1), 0); + } + } + else if (ptr > current_subject || (md->moptions & PCRE_NOTEMPTY) == 0) + { + if (match_count < 0) match_count = (offsetcount >= 2)? 1 : 0; + else if (match_count > 0 && ++match_count * 2 >= offsetcount) + match_count = 0; + count = ((match_count == 0)? offsetcount : match_count * 2) - 2; + if (count > 0) memmove(offsets + 2, offsets, count * sizeof(int)); + if (offsetcount >= 2) + { + offsets[0] = current_subject - start_subject; + offsets[1] = ptr - start_subject; + DPRINTF(("%.*sSet matched string = \"%.*s\"\n", rlevel*2-2, SP, + offsets[1] - offsets[0], current_subject)); + } + if ((md->moptions & PCRE_DFA_SHORTEST) != 0) + { + DPRINTF(("%.*sEnd of internal_dfa_exec %d: returning %d\n" + "%.*s---------------------\n\n", rlevel*2-2, SP, rlevel, + match_count, rlevel*2-2, SP)); + return match_count; + } + } + break; + +/* ========================================================================== */ + /* These opcodes add to the current list of states without looking + at the current character. */ + + /*-----------------------------------------------------------------*/ + case OP_ALT: + do { code += GET(code, 1); } while (*code == OP_ALT); + ADD_ACTIVE(code - start_code, 0); + break; + + /*-----------------------------------------------------------------*/ + case OP_BRA: + do + { + ADD_ACTIVE(code - start_code + 1 + LINK_SIZE, 0); + code += GET(code, 1); + } + while (*code == OP_ALT); + break; + + /*-----------------------------------------------------------------*/ + case OP_BRAZERO: + case OP_BRAMINZERO: + ADD_ACTIVE(state_offset + 1, 0); + code += 1 + GET(code, 2); + while (*code == OP_ALT) code += GET(code, 1); + ADD_ACTIVE(code - start_code + 1 + LINK_SIZE, 0); + break; + + /*-----------------------------------------------------------------*/ + case OP_BRANUMBER: + ADD_ACTIVE(state_offset + 1 + LINK_SIZE, 0); + break; + + /*-----------------------------------------------------------------*/ + case OP_CIRC: + if ((ptr == start_subject && (md->moptions & PCRE_NOTBOL) == 0) || + ((ims & PCRE_MULTILINE) != 0 && + ptr >= start_subject + md->nllen && + ptr != end_subject && + IS_NEWLINE(ptr - md->nllen))) + { ADD_ACTIVE(state_offset + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + case OP_EOD: + if (ptr >= end_subject) { ADD_ACTIVE(state_offset + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + case OP_OPT: + ims = code[1]; + ADD_ACTIVE(state_offset + 2, 0); + break; + + /*-----------------------------------------------------------------*/ + case OP_SOD: + if (ptr == start_subject) { ADD_ACTIVE(state_offset + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + case OP_SOM: + if (ptr == start_subject + start_offset) { ADD_ACTIVE(state_offset + 1, 0); } + break; + + +/* ========================================================================== */ + /* These opcodes inspect the next subject character, and sometimes + the previous one as well, but do not have an argument. The variable + clen contains the length of the current character and is zero if we are + at the end of the subject. */ + + /*-----------------------------------------------------------------*/ + case OP_ANY: + if (clen > 0 && ((ims & PCRE_DOTALL) != 0 || + ptr > end_subject - md->nllen || + !IS_NEWLINE(ptr))) + { ADD_NEW(state_offset + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + case OP_EODN: + if (clen == 0 || + (ptr == end_subject - md->nllen && IS_NEWLINE(ptr))) + { ADD_ACTIVE(state_offset + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + case OP_DOLL: + if ((md->moptions & PCRE_NOTEOL) == 0) + { + if (clen == 0 || + (ptr <= end_subject - md->nllen && IS_NEWLINE(ptr) && + ((ims & PCRE_MULTILINE) != 0 || ptr == end_subject - md->nllen) + )) + { ADD_ACTIVE(state_offset + 1, 0); } + } + else if ((ims & PCRE_MULTILINE) != 0 && + ptr <= end_subject - md->nllen && IS_NEWLINE(ptr)) + { ADD_ACTIVE(state_offset + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + + case OP_DIGIT: + case OP_WHITESPACE: + case OP_WORDCHAR: + if (clen > 0 && c < 256 && + ((ctypes[c] & toptable1[codevalue]) ^ toptable2[codevalue]) != 0) + { ADD_NEW(state_offset + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + case OP_NOT_DIGIT: + case OP_NOT_WHITESPACE: + case OP_NOT_WORDCHAR: + if (clen > 0 && (c >= 256 || + ((ctypes[c] & toptable1[codevalue]) ^ toptable2[codevalue]) != 0)) + { ADD_NEW(state_offset + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + case OP_WORD_BOUNDARY: + case OP_NOT_WORD_BOUNDARY: + { + int left_word, right_word; + + if (ptr > start_subject) + { + const uschar *temp = ptr - 1; +#ifdef SUPPORT_UTF8 + if (utf8) BACKCHAR(temp); +#endif + GETCHARTEST(d, temp); + left_word = d < 256 && (ctypes[d] & ctype_word) != 0; + } + else left_word = 0; + + if (clen > 0) right_word = c < 256 && (ctypes[c] & ctype_word) != 0; + else right_word = 0; + + if ((left_word == right_word) == (codevalue == OP_NOT_WORD_BOUNDARY)) + { ADD_ACTIVE(state_offset + 1, 0); } + } + break; + + +#ifdef SUPPORT_UCP + + /*-----------------------------------------------------------------*/ + /* Check the next character by Unicode property. We will get here only + if the support is in the binary; otherwise a compile-time error occurs. + */ + + case OP_PROP: + case OP_NOTPROP: + if (clen > 0) + { + BOOL OK; + int category = _pcre_ucp_findprop(c, &chartype, &script); + switch(code[1]) + { + case PT_ANY: + OK = TRUE; + break; + + case PT_LAMP: + OK = chartype == ucp_Lu || chartype == ucp_Ll || chartype == ucp_Lt; + break; + + case PT_GC: + OK = category == code[2]; + break; + + case PT_PC: + OK = chartype == code[2]; + break; + + case PT_SC: + OK = script == code[2]; + break; + + /* Should never occur, but keep compilers from grumbling. */ + + default: + OK = codevalue != OP_PROP; + break; + } + + if (OK == (codevalue == OP_PROP)) { ADD_NEW(state_offset + 3, 0); } + } + break; +#endif + + + +/* ========================================================================== */ + /* These opcodes likewise inspect the subject character, but have an + argument that is not a data character. It is one of these opcodes: + OP_ANY, OP_DIGIT, OP_NOT_DIGIT, OP_WHITESPACE, OP_NOT_SPACE, OP_WORDCHAR, + OP_NOT_WORDCHAR. The value is loaded into d. */ + + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + count = current_state->count; /* Already matched */ + if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } + if (clen > 0) + { + if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || + (c < 256 && + (d != OP_ANY || + (ims & PCRE_DOTALL) != 0 || + ptr > end_subject - md->nllen || + !IS_NEWLINE(ptr) + ) && + ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) + { + count++; + ADD_NEW(state_offset, count); + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + ADD_ACTIVE(state_offset + 2, 0); + if (clen > 0) + { + if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || + (c < 256 && + (d != OP_ANY || + (ims & PCRE_DOTALL) != 0 || + ptr > end_subject - md->nllen || + !IS_NEWLINE(ptr) + ) && + ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) + { + ADD_NEW(state_offset + 2, 0); + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + ADD_ACTIVE(state_offset + 2, 0); + if (clen > 0) + { + if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || + (c < 256 && + (d != OP_ANY || + (ims & PCRE_DOTALL) != 0 || + ptr > end_subject - md->nllen || + !IS_NEWLINE(ptr) + ) && + ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) + { + ADD_NEW(state_offset, 0); + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_TYPEEXACT: + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + if (codevalue != OP_TYPEEXACT) + { ADD_ACTIVE(state_offset + 4, 0); } + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + if ((c >= 256 && d != OP_DIGIT && d != OP_WHITESPACE && d != OP_WORDCHAR) || + (c < 256 && + (d != OP_ANY || + (ims & PCRE_DOTALL) != 0 || + ptr > end_subject - md->nllen || + !IS_NEWLINE(ptr) + ) && + ((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) + { + if (++count >= GET2(code, 1)) + { ADD_NEW(state_offset + 4, 0); } + else + { ADD_NEW(state_offset, count); } + } + } + break; + +/* ========================================================================== */ + /* These are virtual opcodes that are used when something like + OP_TYPEPLUS has OP_PROP, OP_NOTPROP, or OP_EXTUNI as its argument. It + keeps the code above fast for the other cases. The argument is in the + d variable. */ + + case OP_PROP_EXTRA + OP_TYPEPLUS: + case OP_PROP_EXTRA + OP_TYPEMINPLUS: + count = current_state->count; /* Already matched */ + if (count > 0) { ADD_ACTIVE(state_offset + 4, 0); } + if (clen > 0) + { + BOOL OK; + int category = _pcre_ucp_findprop(c, &chartype, &script); + switch(code[2]) + { + case PT_ANY: + OK = TRUE; + break; + + case PT_LAMP: + OK = chartype == ucp_Lu || chartype == ucp_Ll || chartype == ucp_Lt; + break; + + case PT_GC: + OK = category == code[3]; + break; + + case PT_PC: + OK = chartype == code[3]; + break; + + case PT_SC: + OK = script == code[3]; + break; + + /* Should never occur, but keep compilers from grumbling. */ + + default: + OK = codevalue != OP_PROP; + break; + } + + if (OK == (d == OP_PROP)) { count++; ADD_NEW(state_offset, count); } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_EXTUNI_EXTRA + OP_TYPEPLUS: + case OP_EXTUNI_EXTRA + OP_TYPEMINPLUS: + count = current_state->count; /* Already matched */ + if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } + if (clen > 0 && _pcre_ucp_findprop(c, &chartype, &script) != ucp_M) + { + const uschar *nptr = ptr + clen; + int ncount = 0; + while (nptr < end_subject) + { + int nd; + int ndlen = 1; + GETCHARLEN(nd, nptr, ndlen); + if (_pcre_ucp_findprop(nd, &chartype, &script) != ucp_M) break; + ncount++; + nptr += ndlen; + } + count++; + ADD_NEW_DATA(-state_offset, count, ncount); + } + break; + + /*-----------------------------------------------------------------*/ + case OP_PROP_EXTRA + OP_TYPEQUERY: + case OP_PROP_EXTRA + OP_TYPEMINQUERY: + count = 4; + goto QS1; + + case OP_PROP_EXTRA + OP_TYPESTAR: + case OP_PROP_EXTRA + OP_TYPEMINSTAR: + count = 0; + + QS1: + + ADD_ACTIVE(state_offset + 4, 0); + if (clen > 0) + { + BOOL OK; + int category = _pcre_ucp_findprop(c, &chartype, &script); + switch(code[2]) + { + case PT_ANY: + OK = TRUE; + break; + + case PT_LAMP: + OK = chartype == ucp_Lu || chartype == ucp_Ll || chartype == ucp_Lt; + break; + + case PT_GC: + OK = category == code[3]; + break; + + case PT_PC: + OK = chartype == code[3]; + break; + + case PT_SC: + OK = script == code[3]; + break; + + /* Should never occur, but keep compilers from grumbling. */ + + default: + OK = codevalue != OP_PROP; + break; + } + + if (OK == (d == OP_PROP)) { ADD_NEW(state_offset + count, 0); } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_EXTUNI_EXTRA + OP_TYPEQUERY: + case OP_EXTUNI_EXTRA + OP_TYPEMINQUERY: + count = 2; + goto QS2; + + case OP_EXTUNI_EXTRA + OP_TYPESTAR: + case OP_EXTUNI_EXTRA + OP_TYPEMINSTAR: + count = 0; + + QS2: + + ADD_ACTIVE(state_offset + 2, 0); + if (clen > 0 && _pcre_ucp_findprop(c, &chartype, &script) != ucp_M) + { + const uschar *nptr = ptr + clen; + int ncount = 0; + while (nptr < end_subject) + { + int nd; + int ndlen = 1; + GETCHARLEN(nd, nptr, ndlen); + if (_pcre_ucp_findprop(nd, &chartype, &script) != ucp_M) break; + ncount++; + nptr += ndlen; + } + ADD_NEW_DATA(-(state_offset + count), 0, ncount); + } + break; + + /*-----------------------------------------------------------------*/ + case OP_PROP_EXTRA + OP_TYPEEXACT: + case OP_PROP_EXTRA + OP_TYPEUPTO: + case OP_PROP_EXTRA + OP_TYPEMINUPTO: + if (codevalue != OP_PROP_EXTRA + OP_TYPEEXACT) + { ADD_ACTIVE(state_offset + 6, 0); } + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + BOOL OK; + int category = _pcre_ucp_findprop(c, &chartype, &script); + switch(code[4]) + { + case PT_ANY: + OK = TRUE; + break; + + case PT_LAMP: + OK = chartype == ucp_Lu || chartype == ucp_Ll || chartype == ucp_Lt; + break; + + case PT_GC: + OK = category == code[5]; + break; + + case PT_PC: + OK = chartype == code[5]; + break; + + case PT_SC: + OK = script == code[5]; + break; + + /* Should never occur, but keep compilers from grumbling. */ + + default: + OK = codevalue != OP_PROP; + break; + } + + if (OK == (d == OP_PROP)) + { + if (++count >= GET2(code, 1)) + { ADD_NEW(state_offset + 6, 0); } + else + { ADD_NEW(state_offset, count); } + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_EXTUNI_EXTRA + OP_TYPEEXACT: + case OP_EXTUNI_EXTRA + OP_TYPEUPTO: + case OP_EXTUNI_EXTRA + OP_TYPEMINUPTO: + if (codevalue != OP_EXTUNI_EXTRA + OP_TYPEEXACT) + { ADD_ACTIVE(state_offset + 4, 0); } + count = current_state->count; /* Number already matched */ + if (clen > 0 && _pcre_ucp_findprop(c, &chartype, &script) != ucp_M) + { + const uschar *nptr = ptr + clen; + int ncount = 0; + while (nptr < end_subject) + { + int nd; + int ndlen = 1; + GETCHARLEN(nd, nptr, ndlen); + if (_pcre_ucp_findprop(nd, &chartype, &script) != ucp_M) break; + ncount++; + nptr += ndlen; + } + if (++count >= GET2(code, 1)) + { ADD_NEW_DATA(-(state_offset + 4), 0, ncount); } + else + { ADD_NEW_DATA(-state_offset, count, ncount); } + } + break; + +/* ========================================================================== */ + /* These opcodes are followed by a character that is usually compared + to the current subject character; it is loaded into d. We still get + here even if there is no subject character, because in some cases zero + repetitions are permitted. */ + + /*-----------------------------------------------------------------*/ + case OP_CHAR: + if (clen > 0 && c == d) { ADD_NEW(state_offset + dlen + 1, 0); } + break; + + /*-----------------------------------------------------------------*/ + case OP_CHARNC: + if (clen == 0) break; + +#ifdef SUPPORT_UTF8 + if (utf8) + { + if (c == d) { ADD_NEW(state_offset + dlen + 1, 0); } else + { + int othercase; + if (c < 128) othercase = fcc[c]; else + + /* If we have Unicode property support, we can use it to test the + other case of the character. */ + +#ifdef SUPPORT_UCP + othercase = _pcre_ucp_othercase(c); +#else + othercase = -1; +#endif + + if (d == othercase) { ADD_NEW(state_offset + dlen + 1, 0); } + } + } + else +#endif /* SUPPORT_UTF8 */ + + /* Non-UTF-8 mode */ + { + if (lcc[c] == lcc[d]) { ADD_NEW(state_offset + 2, 0); } + } + break; + + +#ifdef SUPPORT_UCP + /*-----------------------------------------------------------------*/ + /* This is a tricky one because it can match more than one character. + Find out how many characters to skip, and then set up a negative state + to wait for them to pass before continuing. */ + + case OP_EXTUNI: + if (clen > 0 && _pcre_ucp_findprop(c, &chartype, &script) != ucp_M) + { + const uschar *nptr = ptr + clen; + int ncount = 0; + while (nptr < end_subject) + { + int nclen = 1; + GETCHARLEN(c, nptr, nclen); + if (_pcre_ucp_findprop(c, &chartype, &script) != ucp_M) break; + ncount++; + nptr += nclen; + } + ADD_NEW_DATA(-(state_offset + 1), 0, ncount); + } + break; +#endif + + /*-----------------------------------------------------------------*/ + /* Match a negated single character. This is only used for one-byte + characters, that is, we know that d < 256. The character we are + checking (c) can be multibyte. */ + + case OP_NOT: + if (clen > 0) + { + int otherd = ((ims & PCRE_CASELESS) != 0)? fcc[d] : d; + if (c != d && c != otherd) { ADD_NEW(state_offset + dlen + 1, 0); } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_PLUS: + case OP_MINPLUS: + case OP_NOTPLUS: + case OP_NOTMINPLUS: + count = current_state->count; /* Already matched */ + if (count > 0) { ADD_ACTIVE(state_offset + dlen + 1, 0); } + if (clen > 0) + { + int otherd = -1; + if ((ims & PCRE_CASELESS) != 0) + { +#ifdef SUPPORT_UTF8 + if (utf8 && d >= 128) + { +#ifdef SUPPORT_UCP + otherd = _pcre_ucp_othercase(d); +#endif /* SUPPORT_UCP */ + } + else +#endif /* SUPPORT_UTF8 */ + otherd = fcc[d]; + } + if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) + { count++; ADD_NEW(state_offset, count); } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_QUERY: + case OP_MINQUERY: + case OP_NOTQUERY: + case OP_NOTMINQUERY: + ADD_ACTIVE(state_offset + dlen + 1, 0); + if (clen > 0) + { + int otherd = -1; + if ((ims & PCRE_CASELESS) != 0) + { +#ifdef SUPPORT_UTF8 + if (utf8 && d >= 128) + { +#ifdef SUPPORT_UCP + otherd = _pcre_ucp_othercase(d); +#endif /* SUPPORT_UCP */ + } + else +#endif /* SUPPORT_UTF8 */ + otherd = fcc[d]; + } + if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) + { ADD_NEW(state_offset + dlen + 1, 0); } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_STAR: + case OP_MINSTAR: + case OP_NOTSTAR: + case OP_NOTMINSTAR: + ADD_ACTIVE(state_offset + dlen + 1, 0); + if (clen > 0) + { + int otherd = -1; + if ((ims & PCRE_CASELESS) != 0) + { +#ifdef SUPPORT_UTF8 + if (utf8 && d >= 128) + { +#ifdef SUPPORT_UCP + otherd = _pcre_ucp_othercase(d); +#endif /* SUPPORT_UCP */ + } + else +#endif /* SUPPORT_UTF8 */ + otherd = fcc[d]; + } + if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) + { ADD_NEW(state_offset, 0); } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_EXACT: + case OP_UPTO: + case OP_MINUPTO: + case OP_NOTEXACT: + case OP_NOTUPTO: + case OP_NOTMINUPTO: + if (codevalue != OP_EXACT && codevalue != OP_NOTEXACT) + { ADD_ACTIVE(state_offset + dlen + 3, 0); } + count = current_state->count; /* Number already matched */ + if (clen > 0) + { + int otherd = -1; + if ((ims & PCRE_CASELESS) != 0) + { +#ifdef SUPPORT_UTF8 + if (utf8 && d >= 128) + { +#ifdef SUPPORT_UCP + otherd = _pcre_ucp_othercase(d); +#endif /* SUPPORT_UCP */ + } + else +#endif /* SUPPORT_UTF8 */ + otherd = fcc[d]; + } + if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) + { + if (++count >= GET2(code, 1)) + { ADD_NEW(state_offset + dlen + 3, 0); } + else + { ADD_NEW(state_offset, count); } + } + } + break; + + +/* ========================================================================== */ + /* These are the class-handling opcodes */ + + case OP_CLASS: + case OP_NCLASS: + case OP_XCLASS: + { + BOOL isinclass = FALSE; + int next_state_offset; + const uschar *ecode; + + /* For a simple class, there is always just a 32-byte table, and we + can set isinclass from it. */ + + if (codevalue != OP_XCLASS) + { + ecode = code + 33; + if (clen > 0) + { + isinclass = (c > 255)? (codevalue == OP_NCLASS) : + ((code[1 + c/8] & (1 << (c&7))) != 0); + } + } + + /* An extended class may have a table or a list of single characters, + ranges, or both, and it may be positive or negative. There's a + function that sorts all this out. */ + + else + { + ecode = code + GET(code, 1); + if (clen > 0) isinclass = _pcre_xclass(c, code + 1 + LINK_SIZE); + } + + /* At this point, isinclass is set for all kinds of class, and ecode + points to the byte after the end of the class. If there is a + quantifier, this is where it will be. */ + + next_state_offset = ecode - start_code; + + switch (*ecode) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + ADD_ACTIVE(next_state_offset + 1, 0); + if (isinclass) { ADD_NEW(state_offset, 0); } + break; + + case OP_CRPLUS: + case OP_CRMINPLUS: + count = current_state->count; /* Already matched */ + if (count > 0) { ADD_ACTIVE(next_state_offset + 1, 0); } + if (isinclass) { count++; ADD_NEW(state_offset, count); } + break; + + case OP_CRQUERY: + case OP_CRMINQUERY: + ADD_ACTIVE(next_state_offset + 1, 0); + if (isinclass) { ADD_NEW(next_state_offset + 1, 0); } + break; + + case OP_CRRANGE: + case OP_CRMINRANGE: + count = current_state->count; /* Already matched */ + if (count >= GET2(ecode, 1)) + { ADD_ACTIVE(next_state_offset + 5, 0); } + if (isinclass) + { + int max = GET2(ecode, 3); + if (++count >= max && max != 0) /* Max 0 => no limit */ + { ADD_NEW(next_state_offset + 5, 0); } + else + { ADD_NEW(state_offset, count); } + } + break; + + default: + if (isinclass) { ADD_NEW(next_state_offset, 0); } + break; + } + } + break; + +/* ========================================================================== */ + /* These are the opcodes for fancy brackets of various kinds. We have + to use recursion in order to handle them. */ + + case OP_ASSERT: + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + { + int rc; + int local_offsets[2]; + int local_workspace[1000]; + const uschar *endasscode = code + GET(code, 1); + + while (*endasscode == OP_ALT) endasscode += GET(endasscode, 1); + + rc = internal_dfa_exec( + md, /* static match data */ + code, /* this subexpression's code */ + ptr, /* where we currently are */ + ptr - start_subject, /* start offset */ + local_offsets, /* offset vector */ + sizeof(local_offsets)/sizeof(int), /* size of same */ + local_workspace, /* workspace vector */ + sizeof(local_workspace)/sizeof(int), /* size of same */ + ims, /* the current ims flags */ + rlevel, /* function recursion level */ + recursing); /* pass on regex recursion */ + + if ((rc >= 0) == (codevalue == OP_ASSERT || codevalue == OP_ASSERTBACK)) + { ADD_ACTIVE(endasscode + LINK_SIZE + 1 - start_code, 0); } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_COND: + { + int local_offsets[1000]; + int local_workspace[1000]; + int condcode = code[LINK_SIZE+1]; + + /* The only supported version of OP_CREF is for the value 0xffff, which + means "test if in a recursion". */ + + if (condcode == OP_CREF) + { + int value = GET2(code, LINK_SIZE+2); + if (value != 0xffff) return PCRE_ERROR_DFA_UCOND; + if (recursing > 0) { ADD_ACTIVE(state_offset + LINK_SIZE + 4, 0); } + else { ADD_ACTIVE(state_offset + GET(code, 1) + LINK_SIZE + 1, 0); } + } + + /* Otherwise, the condition is an assertion */ + + else + { + int rc; + const uschar *asscode = code + LINK_SIZE + 1; + const uschar *endasscode = asscode + GET(asscode, 1); + + while (*endasscode == OP_ALT) endasscode += GET(endasscode, 1); + + rc = internal_dfa_exec( + md, /* fixed match data */ + asscode, /* this subexpression's code */ + ptr, /* where we currently are */ + ptr - start_subject, /* start offset */ + local_offsets, /* offset vector */ + sizeof(local_offsets)/sizeof(int), /* size of same */ + local_workspace, /* workspace vector */ + sizeof(local_workspace)/sizeof(int), /* size of same */ + ims, /* the current ims flags */ + rlevel, /* function recursion level */ + recursing); /* pass on regex recursion */ + + if ((rc >= 0) == + (condcode == OP_ASSERT || condcode == OP_ASSERTBACK)) + { ADD_ACTIVE(endasscode + LINK_SIZE + 1 - start_code, 0); } + else + { ADD_ACTIVE(state_offset + GET(code, 1) + LINK_SIZE + 1, 0); } + } + } + break; + + /*-----------------------------------------------------------------*/ + case OP_RECURSE: + { + int local_offsets[1000]; + int local_workspace[1000]; + int rc; + + DPRINTF(("%.*sStarting regex recursion %d\n", rlevel*2-2, SP, + recursing + 1)); + + rc = internal_dfa_exec( + md, /* fixed match data */ + start_code + GET(code, 1), /* this subexpression's code */ + ptr, /* where we currently are */ + ptr - start_subject, /* start offset */ + local_offsets, /* offset vector */ + sizeof(local_offsets)/sizeof(int), /* size of same */ + local_workspace, /* workspace vector */ + sizeof(local_workspace)/sizeof(int), /* size of same */ + ims, /* the current ims flags */ + rlevel, /* function recursion level */ + recursing + 1); /* regex recurse level */ + + DPRINTF(("%.*sReturn from regex recursion %d: rc=%d\n", rlevel*2-2, SP, + recursing + 1, rc)); + + /* Ran out of internal offsets */ + + if (rc == 0) return PCRE_ERROR_DFA_RECURSE; + + /* For each successful matched substring, set up the next state with a + count of characters to skip before trying it. Note that the count is in + characters, not bytes. */ + + if (rc > 0) + { + for (rc = rc*2 - 2; rc >= 0; rc -= 2) + { + const uschar *p = start_subject + local_offsets[rc]; + const uschar *pp = start_subject + local_offsets[rc+1]; + int charcount = local_offsets[rc+1] - local_offsets[rc]; + while (p < pp) if ((*p++ & 0xc0) == 0x80) charcount--; + if (charcount > 0) + { + ADD_NEW_DATA(-(state_offset + LINK_SIZE + 1), 0, (charcount - 1)); + } + else + { + ADD_ACTIVE(state_offset + LINK_SIZE + 1, 0); + } + } + } + else if (rc != PCRE_ERROR_NOMATCH) return rc; + } + break; + + /*-----------------------------------------------------------------*/ + case OP_ONCE: + { + int local_offsets[2]; + int local_workspace[1000]; + + int rc = internal_dfa_exec( + md, /* fixed match data */ + code, /* this subexpression's code */ + ptr, /* where we currently are */ + ptr - start_subject, /* start offset */ + local_offsets, /* offset vector */ + sizeof(local_offsets)/sizeof(int), /* size of same */ + local_workspace, /* workspace vector */ + sizeof(local_workspace)/sizeof(int), /* size of same */ + ims, /* the current ims flags */ + rlevel, /* function recursion level */ + recursing); /* pass on regex recursion */ + + if (rc >= 0) + { + const uschar *end_subpattern = code; + int charcount = local_offsets[1] - local_offsets[0]; + int next_state_offset, repeat_state_offset; + + do { end_subpattern += GET(end_subpattern, 1); } + while (*end_subpattern == OP_ALT); + next_state_offset = end_subpattern - start_code + LINK_SIZE + 1; + + /* If the end of this subpattern is KETRMAX or KETRMIN, we must + arrange for the repeat state also to be added to the relevant list. + Calculate the offset, or set -1 for no repeat. */ + + repeat_state_offset = (*end_subpattern == OP_KETRMAX || + *end_subpattern == OP_KETRMIN)? + end_subpattern - start_code - GET(end_subpattern, 1) : -1; + + /* If we have matched an empty string, add the next state at the + current character pointer. This is important so that the duplicate + checking kicks in, which is what breaks infinite loops that match an + empty string. */ + + if (charcount == 0) + { + ADD_ACTIVE(next_state_offset, 0); + } + + /* Optimization: if there are no more active states, and there + are no new states yet set up, then skip over the subject string + right here, to save looping. Otherwise, set up the new state to swing + into action when the end of the substring is reached. */ + + else if (i + 1 >= active_count && new_count == 0) + { + ptr += charcount; + clen = 0; + ADD_NEW(next_state_offset, 0); + + /* If we are adding a repeat state at the new character position, + we must fudge things so that it is the only current state. + Otherwise, it might be a duplicate of one we processed before, and + that would cause it to be skipped. */ + + if (repeat_state_offset >= 0) + { + next_active_state = active_states; + active_count = 0; + i = -1; + ADD_ACTIVE(repeat_state_offset, 0); + } + } + else + { + const uschar *p = start_subject + local_offsets[0]; + const uschar *pp = start_subject + local_offsets[1]; + while (p < pp) if ((*p++ & 0xc0) == 0x80) charcount--; + ADD_NEW_DATA(-next_state_offset, 0, (charcount - 1)); + if (repeat_state_offset >= 0) + { ADD_NEW_DATA(-repeat_state_offset, 0, (charcount - 1)); } + } + + } + else if (rc != PCRE_ERROR_NOMATCH) return rc; + } + break; + + +/* ========================================================================== */ + /* Handle callouts */ + + case OP_CALLOUT: + if (pcre_callout != NULL) + { + int rrc; + pcre_callout_block cb; + cb.version = 1; /* Version 1 of the callout block */ + cb.callout_number = code[1]; + cb.offset_vector = offsets; + cb.subject = (PCRE_SPTR)start_subject; + cb.subject_length = end_subject - start_subject; + cb.start_match = current_subject - start_subject; + cb.current_position = ptr - start_subject; + cb.pattern_position = GET(code, 2); + cb.next_item_length = GET(code, 2 + LINK_SIZE); + cb.capture_top = 1; + cb.capture_last = -1; + cb.callout_data = md->callout_data; + if ((rrc = (*pcre_callout)(&cb)) < 0) return rrc; /* Abandon */ + if (rrc == 0) { ADD_ACTIVE(state_offset + 2 + 2*LINK_SIZE, 0); } + } + break; + + +/* ========================================================================== */ + default: /* Unsupported opcode */ + return PCRE_ERROR_DFA_UITEM; + } + + NEXT_ACTIVE_STATE: continue; + + } /* End of loop scanning active states */ + + /* We have finished the processing at the current subject character. If no + new states have been set for the next character, we have found all the + matches that we are going to find. If we are at the top level and partial + matching has been requested, check for appropriate conditions. */ + + if (new_count <= 0) + { + if (match_count < 0 && /* No matches found */ + rlevel == 1 && /* Top level match function */ + (md->moptions & PCRE_PARTIAL) != 0 && /* Want partial matching */ + ptr >= end_subject && /* Reached end of subject */ + ptr > current_subject) /* Matched non-empty string */ + { + if (offsetcount >= 2) + { + offsets[0] = current_subject - start_subject; + offsets[1] = end_subject - start_subject; + } + match_count = PCRE_ERROR_PARTIAL; + } + + DPRINTF(("%.*sEnd of internal_dfa_exec %d: returning %d\n" + "%.*s---------------------\n\n", rlevel*2-2, SP, rlevel, match_count, + rlevel*2-2, SP)); + break; /* In effect, "return", but see the comment below */ + } + + /* One or more states are active for the next character. */ + + ptr += clen; /* Advance to next subject character */ + } /* Loop to move along the subject string */ + +/* Control gets here from "break" a few lines above. We do it this way because +if we use "return" above, we have compiler trouble. Some compilers warn if +there's nothing here because they think the function doesn't return a value. On +the other hand, if we put a dummy statement here, some more clever compilers +complain that it can't be reached. Sigh. */ + +return match_count; +} + + + + +/************************************************* +* Execute a Regular Expression - DFA engine * +*************************************************/ + +/* This external function applies a compiled re to a subject string using a DFA +engine. This function calls the internal function multiple times if the pattern +is not anchored. + +Arguments: + argument_re points to the compiled expression + extra_data points to extra data or is NULL (not currently used) + subject points to the subject string + length length of subject string (may contain binary zeros) + start_offset where to start in the subject string + options option bits + offsets vector of match offsets + offsetcount size of same + workspace workspace vector + wscount size of same + +Returns: > 0 => number of match offset pairs placed in offsets + = 0 => offsets overflowed; longest matches are present + -1 => failed to match + < -1 => some kind of unexpected problem +*/ + +PCRE_DATA_SCOPE int +pcre_dfa_exec(const pcre *argument_re, const pcre_extra *extra_data, + const char *subject, int length, int start_offset, int options, int *offsets, + int offsetcount, int *workspace, int wscount) +{ +real_pcre *re = (real_pcre *)argument_re; +dfa_match_data match_block; +dfa_match_data *md = &match_block; +BOOL utf8, anchored, startline, firstline; +const uschar *current_subject, *end_subject, *lcc; + +pcre_study_data internal_study; +const pcre_study_data *study = NULL; +real_pcre internal_re; + +const uschar *req_byte_ptr; +const uschar *start_bits = NULL; +BOOL first_byte_caseless = FALSE; +BOOL req_byte_caseless = FALSE; +int first_byte = -1; +int req_byte = -1; +int req_byte2 = -1; +int newline; + +/* Plausibility checks */ + +if ((options & ~PUBLIC_DFA_EXEC_OPTIONS) != 0) return PCRE_ERROR_BADOPTION; +if (re == NULL || subject == NULL || workspace == NULL || + (offsets == NULL && offsetcount > 0)) return PCRE_ERROR_NULL; +if (offsetcount < 0) return PCRE_ERROR_BADCOUNT; +if (wscount < 20) return PCRE_ERROR_DFA_WSSIZE; + +/* We need to find the pointer to any study data before we test for byte +flipping, so we scan the extra_data block first. This may set two fields in the +match block, so we must initialize them beforehand. However, the other fields +in the match block must not be set until after the byte flipping. */ + +md->tables = re->tables; +md->callout_data = NULL; + +if (extra_data != NULL) + { + unsigned int flags = extra_data->flags; + if ((flags & PCRE_EXTRA_STUDY_DATA) != 0) + study = (const pcre_study_data *)extra_data->study_data; + if ((flags & PCRE_EXTRA_MATCH_LIMIT) != 0) return PCRE_ERROR_DFA_UMLIMIT; + if ((flags & PCRE_EXTRA_MATCH_LIMIT_RECURSION) != 0) + return PCRE_ERROR_DFA_UMLIMIT; + if ((flags & PCRE_EXTRA_CALLOUT_DATA) != 0) + md->callout_data = extra_data->callout_data; + if ((flags & PCRE_EXTRA_TABLES) != 0) + md->tables = extra_data->tables; + } + +/* Check that the first field in the block is the magic number. If it is not, +test for a regex that was compiled on a host of opposite endianness. If this is +the case, flipped values are put in internal_re and internal_study if there was +study data too. */ + +if (re->magic_number != MAGIC_NUMBER) + { + re = _pcre_try_flipped(re, &internal_re, study, &internal_study); + if (re == NULL) return PCRE_ERROR_BADMAGIC; + if (study != NULL) study = &internal_study; + } + +/* Set some local values */ + +current_subject = (const unsigned char *)subject + start_offset; +end_subject = (const unsigned char *)subject + length; +req_byte_ptr = current_subject - 1; + +#ifdef SUPPORT_UTF8 +utf8 = (re->options & PCRE_UTF8) != 0; +#else +utf8 = FALSE; +#endif + +anchored = (options & (PCRE_ANCHORED|PCRE_DFA_RESTART)) != 0 || + (re->options & PCRE_ANCHORED) != 0; + +/* The remaining fixed data for passing around. */ + +md->start_code = (const uschar *)argument_re + + re->name_table_offset + re->name_count * re->name_entry_size; +md->start_subject = (const unsigned char *)subject; +md->end_subject = end_subject; +md->moptions = options; +md->poptions = re->options; + +/* Handle different types of newline. The two bits give four cases. If nothing +is set at run time, whatever was used at compile time applies. */ + +switch ((((options & PCRE_NEWLINE_CRLF) == 0)? re->options : options) & + PCRE_NEWLINE_CRLF) + { + default: newline = NEWLINE; break; /* Compile-time default */ + case PCRE_NEWLINE_CR: newline = '\r'; break; + case PCRE_NEWLINE_LF: newline = '\n'; break; + case PCRE_NEWLINE_CR+ + PCRE_NEWLINE_LF: newline = ('\r' << 8) | '\n'; break; + } + +if (newline > 255) + { + md->nllen = 2; + md->nl[0] = (newline >> 8) & 255; + md->nl[1] = newline & 255; + } +else + { + md->nllen = 1; + md->nl[0] = newline; + } + +/* Check a UTF-8 string if required. Unfortunately there's no way of passing +back the character offset. */ + +#ifdef SUPPORT_UTF8 +if (utf8 && (options & PCRE_NO_UTF8_CHECK) == 0) + { + if (_pcre_valid_utf8((uschar *)subject, length) >= 0) + return PCRE_ERROR_BADUTF8; + if (start_offset > 0 && start_offset < length) + { + int tb = ((uschar *)subject)[start_offset]; + if (tb > 127) + { + tb &= 0xc0; + if (tb != 0 && tb != 0xc0) return PCRE_ERROR_BADUTF8_OFFSET; + } + } + } +#endif + +/* If the exec call supplied NULL for tables, use the inbuilt ones. This +is a feature that makes it possible to save compiled regex and re-use them +in other programs later. */ + +if (md->tables == NULL) md->tables = _pcre_default_tables; + +/* The lower casing table and the "must be at the start of a line" flag are +used in a loop when finding where to start. */ + +lcc = md->tables + lcc_offset; +startline = (re->options & PCRE_STARTLINE) != 0; +firstline = (re->options & PCRE_FIRSTLINE) != 0; + +/* Set up the first character to match, if available. The first_byte value is +never set for an anchored regular expression, but the anchoring may be forced +at run time, so we have to test for anchoring. The first char may be unset for +an unanchored pattern, of course. If there's no first char and the pattern was +studied, there may be a bitmap of possible first characters. */ + +if (!anchored) + { + if ((re->options & PCRE_FIRSTSET) != 0) + { + first_byte = re->first_byte & 255; + if ((first_byte_caseless = ((re->first_byte & REQ_CASELESS) != 0)) == TRUE) + first_byte = lcc[first_byte]; + } + else + { + if (startline && study != NULL && + (study->options & PCRE_STUDY_MAPPED) != 0) + start_bits = study->start_bits; + } + } + +/* For anchored or unanchored matches, there may be a "last known required +character" set. */ + +if ((re->options & PCRE_REQCHSET) != 0) + { + req_byte = re->req_byte & 255; + req_byte_caseless = (re->req_byte & REQ_CASELESS) != 0; + req_byte2 = (md->tables + fcc_offset)[req_byte]; /* case flipped */ + } + +/* Call the main matching function, looping for a non-anchored regex after a +failed match. Unless restarting, optimize by moving to the first match +character if possible, when not anchored. Then unless wanting a partial match, +check for a required later character. */ + +for (;;) + { + int rc; + + if ((options & PCRE_DFA_RESTART) == 0) + { + const uschar *save_end_subject = end_subject; + + /* Advance to a unique first char if possible. If firstline is TRUE, the + start of the match is constrained to the first line of a multiline string. + Implement this by temporarily adjusting end_subject so that we stop + scanning at a newline. If the match fails at the newline, later code breaks + this loop. */ + + if (firstline) + { + const uschar *t = current_subject; + while (t <= save_end_subject - md->nllen && !IS_NEWLINE(t)) t++; + end_subject = t; + } + + if (first_byte >= 0) + { + if (first_byte_caseless) + while (current_subject < end_subject && + lcc[*current_subject] != first_byte) + current_subject++; + else + while (current_subject < end_subject && *current_subject != first_byte) + current_subject++; + } + + /* Or to just after a linebreak for a multiline match if possible */ + + else if (startline) + { + if (current_subject > md->start_subject + md->nllen + + start_offset) + { + while (current_subject <= end_subject && + !IS_NEWLINE(current_subject - md->nllen)) + current_subject++; + } + } + + /* Or to a non-unique first char after study */ + + else if (start_bits != NULL) + { + while (current_subject < end_subject) + { + register unsigned int c = *current_subject; + if ((start_bits[c/8] & (1 << (c&7))) == 0) current_subject++; + else break; + } + } + + /* Restore fudged end_subject */ + + end_subject = save_end_subject; + } + + /* If req_byte is set, we know that that character must appear in the subject + for the match to succeed. If the first character is set, req_byte must be + later in the subject; otherwise the test starts at the match point. This + optimization can save a huge amount of work in patterns with nested unlimited + repeats that aren't going to match. Writing separate code for cased/caseless + versions makes it go faster, as does using an autoincrement and backing off + on a match. + + HOWEVER: when the subject string is very, very long, searching to its end can + take a long time, and give bad performance on quite ordinary patterns. This + showed up when somebody was matching /^C/ on a 32-megabyte string... so we + don't do this when the string is sufficiently long. + + ALSO: this processing is disabled when partial matching is requested. + */ + + if (req_byte >= 0 && + end_subject - current_subject < REQ_BYTE_MAX && + (options & PCRE_PARTIAL) == 0) + { + register const uschar *p = current_subject + ((first_byte >= 0)? 1 : 0); + + /* We don't need to repeat the search if we haven't yet reached the + place we found it at last time. */ + + if (p > req_byte_ptr) + { + if (req_byte_caseless) + { + while (p < end_subject) + { + register int pp = *p++; + if (pp == req_byte || pp == req_byte2) { p--; break; } + } + } + else + { + while (p < end_subject) + { + if (*p++ == req_byte) { p--; break; } + } + } + + /* If we can't find the required character, break the matching loop, + which will cause a return or PCRE_ERROR_NOMATCH. */ + + if (p >= end_subject) break; + + /* If we have found the required character, save the point where we + found it, so that we don't search again next time round the loop if + the start hasn't passed this character yet. */ + + req_byte_ptr = p; + } + } + + /* OK, now we can do the business */ + + rc = internal_dfa_exec( + md, /* fixed match data */ + md->start_code, /* this subexpression's code */ + current_subject, /* where we currently are */ + start_offset, /* start offset in subject */ + offsets, /* offset vector */ + offsetcount, /* size of same */ + workspace, /* workspace vector */ + wscount, /* size of same */ + re->options & (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL), /* ims flags */ + 0, /* function recurse level */ + 0); /* regex recurse level */ + + /* Anything other than "no match" means we are done, always; otherwise, carry + on only if not anchored. */ + + if (rc != PCRE_ERROR_NOMATCH || anchored) return rc; + + /* Advance to the next subject character unless we are at the end of a line + and firstline is set. */ + + if (firstline && + current_subject <= end_subject - md->nllen && + IS_NEWLINE(current_subject)) break; + current_subject++; + if (utf8) + { + while (current_subject < end_subject && (*current_subject & 0xc0) == 0x80) + current_subject++; + } + if (current_subject > end_subject) break; + } + +return PCRE_ERROR_NOMATCH; +} + +/* End of pcre_dfa_exec.c */ diff --git a/libs/pcre/pcre_exec.c b/libs/pcre/pcre_exec.c new file mode 100644 index 0000000000..882a1d1c06 --- /dev/null +++ b/libs/pcre/pcre_exec.c @@ -0,0 +1,3933 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains pcre_exec(), the externally visible function that does +pattern matching using an NFA algorithm, trying to mimic Perl as closely as +possible. There are also some static supporting functions. */ + +#define NLBLOCK md /* The block containing newline information */ +#include "pcre_internal.h" + + +/* Structure for building a chain of data that actually lives on the +stack, for holding the values of the subject pointer at the start of each +subpattern, so as to detect when an empty string has been matched by a +subpattern - to break infinite loops. When NO_RECURSE is set, these blocks +are on the heap, not on the stack. */ + +typedef struct eptrblock { + struct eptrblock *epb_prev; + USPTR epb_saved_eptr; +} eptrblock; + +/* Flag bits for the match() function */ + +#define match_condassert 0x01 /* Called to check a condition assertion */ +#define match_isgroup 0x02 /* Set if start of bracketed group */ + +/* Non-error returns from the match() function. Error returns are externally +defined PCRE_ERROR_xxx codes, which are all negative. */ + +#define MATCH_MATCH 1 +#define MATCH_NOMATCH 0 + +/* Maximum number of ints of offset to save on the stack for recursive calls. +If the offset vector is bigger, malloc is used. This should be a multiple of 3, +because the offset vector is always a multiple of 3 long. */ + +#define REC_STACK_SAVE_MAX 30 + +/* Min and max values for the common repeats; for the maxima, 0 => infinity */ + +static const char rep_min[] = { 0, 0, 1, 1, 0, 0 }; +static const char rep_max[] = { 0, 0, 0, 0, 1, 1 }; + + + +#ifdef DEBUG +/************************************************* +* Debugging function to print chars * +*************************************************/ + +/* Print a sequence of chars in printable format, stopping at the end of the +subject if the requested. + +Arguments: + p points to characters + length number to print + is_subject TRUE if printing from within md->start_subject + md pointer to matching data block, if is_subject is TRUE + +Returns: nothing +*/ + +static void +pchars(const uschar *p, int length, BOOL is_subject, match_data *md) +{ +int c; +if (is_subject && length > md->end_subject - p) length = md->end_subject - p; +while (length-- > 0) + if (isprint(c = *(p++))) printf("%c", c); else printf("\\x%02x", c); +} +#endif + + + +/************************************************* +* Match a back-reference * +*************************************************/ + +/* If a back reference hasn't been set, the length that is passed is greater +than the number of characters left in the string, so the match fails. + +Arguments: + offset index into the offset vector + eptr points into the subject + length length to be matched + md points to match data block + ims the ims flags + +Returns: TRUE if matched +*/ + +static BOOL +match_ref(int offset, register USPTR eptr, int length, match_data *md, + unsigned long int ims) +{ +USPTR p = md->start_subject + md->offset_vector[offset]; + +#ifdef DEBUG +if (eptr >= md->end_subject) + printf("matching subject "); +else + { + printf("matching subject "); + pchars(eptr, length, TRUE, md); + } +printf(" against backref "); +pchars(p, length, FALSE, md); +printf("\n"); +#endif + +/* Always fail if not enough characters left */ + +if (length > md->end_subject - eptr) return FALSE; + +/* Separate the caselesss case for speed */ + +if ((ims & PCRE_CASELESS) != 0) + { + while (length-- > 0) + if (md->lcc[*p++] != md->lcc[*eptr++]) return FALSE; + } +else + { while (length-- > 0) if (*p++ != *eptr++) return FALSE; } + +return TRUE; +} + + + +/*************************************************************************** +**************************************************************************** + RECURSION IN THE match() FUNCTION + +The match() function is highly recursive, though not every recursive call +increases the recursive depth. Nevertheless, some regular expressions can cause +it to recurse to a great depth. I was writing for Unix, so I just let it call +itself recursively. This uses the stack for saving everything that has to be +saved for a recursive call. On Unix, the stack can be large, and this works +fine. + +It turns out that on some non-Unix-like systems there are problems with +programs that use a lot of stack. (This despite the fact that every last chip +has oodles of memory these days, and techniques for extending the stack have +been known for decades.) So.... + +There is a fudge, triggered by defining NO_RECURSE, which avoids recursive +calls by keeping local variables that need to be preserved in blocks of memory +obtained from malloc() instead instead of on the stack. Macros are used to +achieve this so that the actual code doesn't look very different to what it +always used to. +**************************************************************************** +***************************************************************************/ + + +/* These versions of the macros use the stack, as normal. There are debugging +versions and production versions. */ + +#ifndef NO_RECURSE +#define REGISTER register +#ifdef DEBUG +#define RMATCH(rx,ra,rb,rc,rd,re,rf,rg) \ + { \ + printf("match() called in line %d\n", __LINE__); \ + rx = match(ra,rb,rc,rd,re,rf,rg,rdepth+1); \ + printf("to line %d\n", __LINE__); \ + } +#define RRETURN(ra) \ + { \ + printf("match() returned %d from line %d ", ra, __LINE__); \ + return ra; \ + } +#else +#define RMATCH(rx,ra,rb,rc,rd,re,rf,rg) \ + rx = match(ra,rb,rc,rd,re,rf,rg,rdepth+1) +#define RRETURN(ra) return ra +#endif + +#else + + +/* These versions of the macros manage a private stack on the heap. Note +that the rd argument of RMATCH isn't actually used. It's the md argument of +match(), which never changes. */ + +#define REGISTER + +#define RMATCH(rx,ra,rb,rc,rd,re,rf,rg)\ + {\ + heapframe *newframe = (pcre_stack_malloc)(sizeof(heapframe));\ + if (setjmp(frame->Xwhere) == 0)\ + {\ + newframe->Xeptr = ra;\ + newframe->Xecode = rb;\ + newframe->Xoffset_top = rc;\ + newframe->Xims = re;\ + newframe->Xeptrb = rf;\ + newframe->Xflags = rg;\ + newframe->Xrdepth = frame->Xrdepth + 1;\ + newframe->Xprevframe = frame;\ + frame = newframe;\ + DPRINTF(("restarting from line %d\n", __LINE__));\ + goto HEAP_RECURSE;\ + }\ + else\ + {\ + DPRINTF(("longjumped back to line %d\n", __LINE__));\ + frame = md->thisframe;\ + rx = frame->Xresult;\ + }\ + } + +#define RRETURN(ra)\ + {\ + heapframe *newframe = frame;\ + frame = newframe->Xprevframe;\ + (pcre_stack_free)(newframe);\ + if (frame != NULL)\ + {\ + frame->Xresult = ra;\ + md->thisframe = frame;\ + longjmp(frame->Xwhere, 1);\ + }\ + return ra;\ + } + + +/* Structure for remembering the local variables in a private frame */ + +typedef struct heapframe { + struct heapframe *Xprevframe; + + /* Function arguments that may change */ + + const uschar *Xeptr; + const uschar *Xecode; + int Xoffset_top; + long int Xims; + eptrblock *Xeptrb; + int Xflags; + unsigned int Xrdepth; + + /* Function local variables */ + + const uschar *Xcallpat; + const uschar *Xcharptr; + const uschar *Xdata; + const uschar *Xnext; + const uschar *Xpp; + const uschar *Xprev; + const uschar *Xsaved_eptr; + + recursion_info Xnew_recursive; + + BOOL Xcur_is_word; + BOOL Xcondition; + BOOL Xminimize; + BOOL Xprev_is_word; + + unsigned long int Xoriginal_ims; + +#ifdef SUPPORT_UCP + int Xprop_type; + int Xprop_value; + int Xprop_fail_result; + int Xprop_category; + int Xprop_chartype; + int Xprop_script; + int *Xprop_test_variable; +#endif + + int Xctype; + int Xfc; + int Xfi; + int Xlength; + int Xmax; + int Xmin; + int Xnumber; + int Xoffset; + int Xop; + int Xsave_capture_last; + int Xsave_offset1, Xsave_offset2, Xsave_offset3; + int Xstacksave[REC_STACK_SAVE_MAX]; + + eptrblock Xnewptrb; + + /* Place to pass back result, and where to jump back to */ + + int Xresult; + jmp_buf Xwhere; + +} heapframe; + +#endif + + +/*************************************************************************** +***************************************************************************/ + + + +/************************************************* +* Match from current position * +*************************************************/ + +/* On entry ecode points to the first opcode, and eptr to the first character +in the subject string, while eptrb holds the value of eptr at the start of the +last bracketed group - used for breaking infinite loops matching zero-length +strings. This function is called recursively in many circumstances. Whenever it +returns a negative (error) response, the outer incarnation must also return the +same response. + +Performance note: It might be tempting to extract commonly used fields from the +md structure (e.g. utf8, end_subject) into individual variables to improve +performance. Tests using gcc on a SPARC disproved this; in the first case, it +made performance worse. + +Arguments: + eptr pointer in subject + ecode position in code + offset_top current top pointer + md pointer to "static" info for the match + ims current /i, /m, and /s options + eptrb pointer to chain of blocks containing eptr at start of + brackets - for testing for empty matches + flags can contain + match_condassert - this is an assertion condition + match_isgroup - this is the start of a bracketed group + rdepth the recursion depth + +Returns: MATCH_MATCH if matched ) these values are >= 0 + MATCH_NOMATCH if failed to match ) + a negative PCRE_ERROR_xxx value if aborted by an error condition + (e.g. stopped by repeated call or recursion limit) +*/ + +static int +match(REGISTER USPTR eptr, REGISTER const uschar *ecode, + int offset_top, match_data *md, unsigned long int ims, eptrblock *eptrb, + int flags, unsigned int rdepth) +{ +/* These variables do not need to be preserved over recursion in this function, +so they can be ordinary variables in all cases. Mark them with "register" +because they are used a lot in loops. */ + +register int rrc; /* Returns from recursive calls */ +register int i; /* Used for loops not involving calls to RMATCH() */ +register unsigned int c; /* Character values not kept over RMATCH() calls */ +register BOOL utf8; /* Local copy of UTF-8 flag for speed */ + +/* When recursion is not being used, all "local" variables that have to be +preserved over calls to RMATCH() are part of a "frame" which is obtained from +heap storage. Set up the top-level frame here; others are obtained from the +heap whenever RMATCH() does a "recursion". See the macro definitions above. */ + +#ifdef NO_RECURSE +heapframe *frame = (pcre_stack_malloc)(sizeof(heapframe)); +frame->Xprevframe = NULL; /* Marks the top level */ + +/* Copy in the original argument variables */ + +frame->Xeptr = eptr; +frame->Xecode = ecode; +frame->Xoffset_top = offset_top; +frame->Xims = ims; +frame->Xeptrb = eptrb; +frame->Xflags = flags; +frame->Xrdepth = rdepth; + +/* This is where control jumps back to to effect "recursion" */ + +HEAP_RECURSE: + +/* Macros make the argument variables come from the current frame */ + +#define eptr frame->Xeptr +#define ecode frame->Xecode +#define offset_top frame->Xoffset_top +#define ims frame->Xims +#define eptrb frame->Xeptrb +#define flags frame->Xflags +#define rdepth frame->Xrdepth + +/* Ditto for the local variables */ + +#ifdef SUPPORT_UTF8 +#define charptr frame->Xcharptr +#endif +#define callpat frame->Xcallpat +#define data frame->Xdata +#define next frame->Xnext +#define pp frame->Xpp +#define prev frame->Xprev +#define saved_eptr frame->Xsaved_eptr + +#define new_recursive frame->Xnew_recursive + +#define cur_is_word frame->Xcur_is_word +#define condition frame->Xcondition +#define minimize frame->Xminimize +#define prev_is_word frame->Xprev_is_word + +#define original_ims frame->Xoriginal_ims + +#ifdef SUPPORT_UCP +#define prop_type frame->Xprop_type +#define prop_value frame->Xprop_value +#define prop_fail_result frame->Xprop_fail_result +#define prop_category frame->Xprop_category +#define prop_chartype frame->Xprop_chartype +#define prop_script frame->Xprop_script +#define prop_test_variable frame->Xprop_test_variable +#endif + +#define ctype frame->Xctype +#define fc frame->Xfc +#define fi frame->Xfi +#define length frame->Xlength +#define max frame->Xmax +#define min frame->Xmin +#define number frame->Xnumber +#define offset frame->Xoffset +#define op frame->Xop +#define save_capture_last frame->Xsave_capture_last +#define save_offset1 frame->Xsave_offset1 +#define save_offset2 frame->Xsave_offset2 +#define save_offset3 frame->Xsave_offset3 +#define stacksave frame->Xstacksave + +#define newptrb frame->Xnewptrb + +/* When recursion is being used, local variables are allocated on the stack and +get preserved during recursion in the normal way. In this environment, fi and +i, and fc and c, can be the same variables. */ + +#else +#define fi i +#define fc c + + +#ifdef SUPPORT_UTF8 /* Many of these variables are used only */ +const uschar *charptr; /* in small blocks of the code. My normal */ +#endif /* style of coding would have declared */ +const uschar *callpat; /* them within each of those blocks. */ +const uschar *data; /* However, in order to accommodate the */ +const uschar *next; /* version of this code that uses an */ +USPTR pp; /* external "stack" implemented on the */ +const uschar *prev; /* heap, it is easier to declare them all */ +USPTR saved_eptr; /* here, so the declarations can be cut */ + /* out in a block. The only declarations */ +recursion_info new_recursive; /* within blocks below are for variables */ + /* that do not have to be preserved over */ +BOOL cur_is_word; /* a recursive call to RMATCH(). */ +BOOL condition; +BOOL minimize; +BOOL prev_is_word; + +unsigned long int original_ims; + +#ifdef SUPPORT_UCP +int prop_type; +int prop_value; +int prop_fail_result; +int prop_category; +int prop_chartype; +int prop_script; +int *prop_test_variable; +#endif + +int ctype; +int length; +int max; +int min; +int number; +int offset; +int op; +int save_capture_last; +int save_offset1, save_offset2, save_offset3; +int stacksave[REC_STACK_SAVE_MAX]; + +eptrblock newptrb; +#endif + +/* These statements are here to stop the compiler complaining about unitialized +variables. */ + +#ifdef SUPPORT_UCP +prop_value = 0; +prop_fail_result = 0; +prop_test_variable = NULL; +#endif + +/* This label is used for tail recursion, which is used in a few cases even +when NO_RECURSE is not defined, in order to reduce the amount of stack that is +used. Thanks to Ian Taylor for noticing this possibility and sending the +original patch. */ + +TAIL_RECURSE: + +/* OK, now we can get on with the real code of the function. Recursive calls +are specified by the macro RMATCH and RRETURN is used to return. When +NO_RECURSE is *not* defined, these just turn into a recursive call to match() +and a "return", respectively (possibly with some debugging if DEBUG is +defined). However, RMATCH isn't like a function call because it's quite a +complicated macro. It has to be used in one particular way. This shouldn't, +however, impact performance when true recursion is being used. */ + +/* First check that we haven't called match() too many times, or that we +haven't exceeded the recursive call limit. */ + +if (md->match_call_count++ >= md->match_limit) RRETURN(PCRE_ERROR_MATCHLIMIT); +if (rdepth >= md->match_limit_recursion) RRETURN(PCRE_ERROR_RECURSIONLIMIT); + +original_ims = ims; /* Save for resetting on ')' */ + +#ifdef SUPPORT_UTF8 +utf8 = md->utf8; /* Local copy of the flag */ +#else +utf8 = FALSE; +#endif + +/* At the start of a bracketed group, add the current subject pointer to the +stack of such pointers, to be re-instated at the end of the group when we hit +the closing ket. When match() is called in other circumstances, we don't add to +this stack. */ + +if ((flags & match_isgroup) != 0) + { + newptrb.epb_prev = eptrb; + newptrb.epb_saved_eptr = eptr; + eptrb = &newptrb; + } + +/* Now start processing the operations. */ + +for (;;) + { + op = *ecode; + minimize = FALSE; + + /* For partial matching, remember if we ever hit the end of the subject after + matching at least one subject character. */ + + if (md->partial && + eptr >= md->end_subject && + eptr > md->start_match) + md->hitend = TRUE; + + /* Opening capturing bracket. If there is space in the offset vector, save + the current subject position in the working slot at the top of the vector. We + mustn't change the current values of the data slot, because they may be set + from a previous iteration of this group, and be referred to by a reference + inside the group. + + If the bracket fails to match, we need to restore this value and also the + values of the final offsets, in case they were set by a previous iteration of + the same bracket. + + If there isn't enough space in the offset vector, treat this as if it were a + non-capturing bracket. Don't worry about setting the flag for the error case + here; that is handled in the code for KET. */ + + if (op > OP_BRA) + { + number = op - OP_BRA; + + /* For extended extraction brackets (large number), we have to fish out the + number from a dummy opcode at the start. */ + + if (number > EXTRACT_BASIC_MAX) + number = GET2(ecode, 2+LINK_SIZE); + offset = number << 1; + +#ifdef DEBUG + printf("start bracket %d subject=", number); + pchars(eptr, 16, TRUE, md); + printf("\n"); +#endif + + if (offset < md->offset_max) + { + save_offset1 = md->offset_vector[offset]; + save_offset2 = md->offset_vector[offset+1]; + save_offset3 = md->offset_vector[md->offset_end - number]; + save_capture_last = md->capture_last; + + DPRINTF(("saving %d %d %d\n", save_offset1, save_offset2, save_offset3)); + md->offset_vector[md->offset_end - number] = eptr - md->start_subject; + + do + { + RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, + match_isgroup); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + md->capture_last = save_capture_last; + ecode += GET(ecode, 1); + } + while (*ecode == OP_ALT); + + DPRINTF(("bracket %d failed\n", number)); + + md->offset_vector[offset] = save_offset1; + md->offset_vector[offset+1] = save_offset2; + md->offset_vector[md->offset_end - number] = save_offset3; + + RRETURN(MATCH_NOMATCH); + } + + /* Insufficient room for saving captured contents */ + + else op = OP_BRA; + } + + /* Other types of node can be handled by a switch */ + + switch(op) + { + case OP_BRA: /* Non-capturing bracket: optimized */ + DPRINTF(("start bracket 0\n")); + + /* Loop for all the alternatives */ + + for (;;) + { + /* When we get to the final alternative within the brackets, we would + return the result of a recursive call to match() whatever happened. We + can reduce stack usage by turning this into a tail recursion. */ + + if (ecode[GET(ecode, 1)] != OP_ALT) + { + ecode += 1 + LINK_SIZE; + flags = match_isgroup; + DPRINTF(("bracket 0 tail recursion\n")); + goto TAIL_RECURSE; + } + + /* For non-final alternatives, continue the loop for a NOMATCH result; + otherwise return. */ + + RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, + match_isgroup); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + ecode += GET(ecode, 1); + } + /* Control never reaches here. */ + + /* Conditional group: compilation checked that there are no more than + two branches. If the condition is false, skipping the first branch takes us + past the end if there is only one branch, but that's OK because that is + exactly what going to the ket would do. As there is only one branch to be + obeyed, we can use tail recursion to avoid using another stack frame. */ + + case OP_COND: + if (ecode[LINK_SIZE+1] == OP_CREF) /* Condition extract or recurse test */ + { + offset = GET2(ecode, LINK_SIZE+2) << 1; /* Doubled ref number */ + condition = (offset == CREF_RECURSE * 2)? + (md->recursive != NULL) : + (offset < offset_top && md->offset_vector[offset] >= 0); + ecode += condition? (LINK_SIZE + 4) : (LINK_SIZE + 1 + GET(ecode, 1)); + flags = match_isgroup; + goto TAIL_RECURSE; + } + + /* The condition is an assertion. Call match() to evaluate it - setting + the final argument TRUE causes it to stop at the end of an assertion. */ + + else + { + RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, + match_condassert | match_isgroup); + if (rrc == MATCH_MATCH) + { + ecode += 1 + LINK_SIZE + GET(ecode, LINK_SIZE+2); + while (*ecode == OP_ALT) ecode += GET(ecode, 1); + } + else if (rrc != MATCH_NOMATCH) + { + RRETURN(rrc); /* Need braces because of following else */ + } + else ecode += GET(ecode, 1); + + /* We are now at the branch that is to be obeyed. As there is only one, + we can use tail recursion to avoid using another stack frame. */ + + ecode += 1 + LINK_SIZE; + flags = match_isgroup; + goto TAIL_RECURSE; + } + /* Control never reaches here */ + + /* Skip over conditional reference or large extraction number data if + encountered. */ + + case OP_CREF: + case OP_BRANUMBER: + ecode += 3; + break; + + /* End of the pattern. If we are in a recursion, we should restore the + offsets appropriately and continue from after the call. */ + + case OP_END: + if (md->recursive != NULL && md->recursive->group_num == 0) + { + recursion_info *rec = md->recursive; + DPRINTF(("End of pattern in a (?0) recursion\n")); + md->recursive = rec->prevrec; + memmove(md->offset_vector, rec->offset_save, + rec->saved_max * sizeof(int)); + md->start_match = rec->save_start; + ims = original_ims; + ecode = rec->after_call; + break; + } + + /* Otherwise, if PCRE_NOTEMPTY is set, fail if we have matched an empty + string - backtracking will then try other alternatives, if any. */ + + if (md->notempty && eptr == md->start_match) RRETURN(MATCH_NOMATCH); + md->end_match_ptr = eptr; /* Record where we ended */ + md->end_offset_top = offset_top; /* and how many extracts were taken */ + RRETURN(MATCH_MATCH); + + /* Change option settings */ + + case OP_OPT: + ims = ecode[1]; + ecode += 2; + DPRINTF(("ims set to %02lx\n", ims)); + break; + + /* Assertion brackets. Check the alternative branches in turn - the + matching won't pass the KET for an assertion. If any one branch matches, + the assertion is true. Lookbehind assertions have an OP_REVERSE item at the + start of each branch to move the current point backwards, so the code at + this level is identical to the lookahead case. */ + + case OP_ASSERT: + case OP_ASSERTBACK: + do + { + RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, + match_isgroup); + if (rrc == MATCH_MATCH) break; + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + ecode += GET(ecode, 1); + } + while (*ecode == OP_ALT); + if (*ecode == OP_KET) RRETURN(MATCH_NOMATCH); + + /* If checking an assertion for a condition, return MATCH_MATCH. */ + + if ((flags & match_condassert) != 0) RRETURN(MATCH_MATCH); + + /* Continue from after the assertion, updating the offsets high water + mark, since extracts may have been taken during the assertion. */ + + do ecode += GET(ecode,1); while (*ecode == OP_ALT); + ecode += 1 + LINK_SIZE; + offset_top = md->end_offset_top; + continue; + + /* Negative assertion: all branches must fail to match */ + + case OP_ASSERT_NOT: + case OP_ASSERTBACK_NOT: + do + { + RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, + match_isgroup); + if (rrc == MATCH_MATCH) RRETURN(MATCH_NOMATCH); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + ecode += GET(ecode,1); + } + while (*ecode == OP_ALT); + + if ((flags & match_condassert) != 0) RRETURN(MATCH_MATCH); + + ecode += 1 + LINK_SIZE; + continue; + + /* Move the subject pointer back. This occurs only at the start of + each branch of a lookbehind assertion. If we are too close to the start to + move back, this match function fails. When working with UTF-8 we move + back a number of characters, not bytes. */ + + case OP_REVERSE: +#ifdef SUPPORT_UTF8 + if (utf8) + { + c = GET(ecode,1); + for (i = 0; i < c; i++) + { + eptr--; + if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH); + BACKCHAR(eptr) + } + } + else +#endif + + /* No UTF-8 support, or not in UTF-8 mode: count is byte count */ + + { + eptr -= GET(ecode,1); + if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH); + } + + /* Skip to next op code */ + + ecode += 1 + LINK_SIZE; + break; + + /* The callout item calls an external function, if one is provided, passing + details of the match so far. This is mainly for debugging, though the + function is able to force a failure. */ + + case OP_CALLOUT: + if (pcre_callout != NULL) + { + pcre_callout_block cb; + cb.version = 1; /* Version 1 of the callout block */ + cb.callout_number = ecode[1]; + cb.offset_vector = md->offset_vector; + cb.subject = (PCRE_SPTR)md->start_subject; + cb.subject_length = md->end_subject - md->start_subject; + cb.start_match = md->start_match - md->start_subject; + cb.current_position = eptr - md->start_subject; + cb.pattern_position = GET(ecode, 2); + cb.next_item_length = GET(ecode, 2 + LINK_SIZE); + cb.capture_top = offset_top/2; + cb.capture_last = md->capture_last; + cb.callout_data = md->callout_data; + if ((rrc = (*pcre_callout)(&cb)) > 0) RRETURN(MATCH_NOMATCH); + if (rrc < 0) RRETURN(rrc); + } + ecode += 2 + 2*LINK_SIZE; + break; + + /* Recursion either matches the current regex, or some subexpression. The + offset data is the offset to the starting bracket from the start of the + whole pattern. (This is so that it works from duplicated subpatterns.) + + If there are any capturing brackets started but not finished, we have to + save their starting points and reinstate them after the recursion. However, + we don't know how many such there are (offset_top records the completed + total) so we just have to save all the potential data. There may be up to + 65535 such values, which is too large to put on the stack, but using malloc + for small numbers seems expensive. As a compromise, the stack is used when + there are no more than REC_STACK_SAVE_MAX values to store; otherwise malloc + is used. A problem is what to do if the malloc fails ... there is no way of + returning to the top level with an error. Save the top REC_STACK_SAVE_MAX + values on the stack, and accept that the rest may be wrong. + + There are also other values that have to be saved. We use a chained + sequence of blocks that actually live on the stack. Thanks to Robin Houston + for the original version of this logic. */ + + case OP_RECURSE: + { + callpat = md->start_code + GET(ecode, 1); + new_recursive.group_num = *callpat - OP_BRA; + + /* For extended extraction brackets (large number), we have to fish out + the number from a dummy opcode at the start. */ + + if (new_recursive.group_num > EXTRACT_BASIC_MAX) + new_recursive.group_num = GET2(callpat, 2+LINK_SIZE); + + /* Add to "recursing stack" */ + + new_recursive.prevrec = md->recursive; + md->recursive = &new_recursive; + + /* Find where to continue from afterwards */ + + ecode += 1 + LINK_SIZE; + new_recursive.after_call = ecode; + + /* Now save the offset data. */ + + new_recursive.saved_max = md->offset_end; + if (new_recursive.saved_max <= REC_STACK_SAVE_MAX) + new_recursive.offset_save = stacksave; + else + { + new_recursive.offset_save = + (int *)(pcre_malloc)(new_recursive.saved_max * sizeof(int)); + if (new_recursive.offset_save == NULL) RRETURN(PCRE_ERROR_NOMEMORY); + } + + memcpy(new_recursive.offset_save, md->offset_vector, + new_recursive.saved_max * sizeof(int)); + new_recursive.save_start = md->start_match; + md->start_match = eptr; + + /* OK, now we can do the recursion. For each top-level alternative we + restore the offset and recursion data. */ + + DPRINTF(("Recursing into group %d\n", new_recursive.group_num)); + do + { + RMATCH(rrc, eptr, callpat + 1 + LINK_SIZE, offset_top, md, ims, + eptrb, match_isgroup); + if (rrc == MATCH_MATCH) + { + DPRINTF(("Recursion matched\n")); + md->recursive = new_recursive.prevrec; + if (new_recursive.offset_save != stacksave) + (pcre_free)(new_recursive.offset_save); + RRETURN(MATCH_MATCH); + } + else if (rrc != MATCH_NOMATCH) + { + DPRINTF(("Recursion gave error %d\n", rrc)); + RRETURN(rrc); + } + + md->recursive = &new_recursive; + memcpy(md->offset_vector, new_recursive.offset_save, + new_recursive.saved_max * sizeof(int)); + callpat += GET(callpat, 1); + } + while (*callpat == OP_ALT); + + DPRINTF(("Recursion didn't match\n")); + md->recursive = new_recursive.prevrec; + if (new_recursive.offset_save != stacksave) + (pcre_free)(new_recursive.offset_save); + RRETURN(MATCH_NOMATCH); + } + /* Control never reaches here */ + + /* "Once" brackets are like assertion brackets except that after a match, + the point in the subject string is not moved back. Thus there can never be + a move back into the brackets. Friedl calls these "atomic" subpatterns. + Check the alternative branches in turn - the matching won't pass the KET + for this kind of subpattern. If any one branch matches, we carry on as at + the end of a normal bracket, leaving the subject pointer. */ + + case OP_ONCE: + prev = ecode; + saved_eptr = eptr; + + do + { + RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, + eptrb, match_isgroup); + if (rrc == MATCH_MATCH) break; + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + ecode += GET(ecode,1); + } + while (*ecode == OP_ALT); + + /* If hit the end of the group (which could be repeated), fail */ + + if (*ecode != OP_ONCE && *ecode != OP_ALT) RRETURN(MATCH_NOMATCH); + + /* Continue as from after the assertion, updating the offsets high water + mark, since extracts may have been taken. */ + + do ecode += GET(ecode,1); while (*ecode == OP_ALT); + + offset_top = md->end_offset_top; + eptr = md->end_match_ptr; + + /* For a non-repeating ket, just continue at this level. This also + happens for a repeating ket if no characters were matched in the group. + This is the forcible breaking of infinite loops as implemented in Perl + 5.005. If there is an options reset, it will get obeyed in the normal + course of events. */ + + if (*ecode == OP_KET || eptr == saved_eptr) + { + ecode += 1+LINK_SIZE; + break; + } + + /* The repeating kets try the rest of the pattern or restart from the + preceding bracket, in the appropriate order. The second "call" of match() + uses tail recursion, to avoid using another stack frame. We need to reset + any options that changed within the bracket before re-running it, so + check the next opcode. */ + + if (ecode[1+LINK_SIZE] == OP_OPT) + { + ims = (ims & ~PCRE_IMS) | ecode[4]; + DPRINTF(("ims set to %02lx at group repeat\n", ims)); + } + + if (*ecode == OP_KETRMIN) + { + RMATCH(rrc, eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + ecode = prev; + flags = match_isgroup; + goto TAIL_RECURSE; + } + else /* OP_KETRMAX */ + { + RMATCH(rrc, eptr, prev, offset_top, md, ims, eptrb, match_isgroup); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + ecode += 1 + LINK_SIZE; + flags = 0; + goto TAIL_RECURSE; + } + /* Control never gets here */ + + /* An alternation is the end of a branch; scan along to find the end of the + bracketed group and go to there. */ + + case OP_ALT: + do ecode += GET(ecode,1); while (*ecode == OP_ALT); + break; + + /* BRAZERO and BRAMINZERO occur just before a bracket group, indicating + that it may occur zero times. It may repeat infinitely, or not at all - + i.e. it could be ()* or ()? in the pattern. Brackets with fixed upper + repeat limits are compiled as a number of copies, with the optional ones + preceded by BRAZERO or BRAMINZERO. */ + + case OP_BRAZERO: + { + next = ecode+1; + RMATCH(rrc, eptr, next, offset_top, md, ims, eptrb, match_isgroup); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + do next += GET(next,1); while (*next == OP_ALT); + ecode = next + 1+LINK_SIZE; + } + break; + + case OP_BRAMINZERO: + { + next = ecode+1; + do next += GET(next,1); while (*next == OP_ALT); + RMATCH(rrc, eptr, next + 1+LINK_SIZE, offset_top, md, ims, eptrb, + match_isgroup); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + ecode++; + } + break; + + /* End of a group, repeated or non-repeating. If we are at the end of + an assertion "group", stop matching and return MATCH_MATCH, but record the + current high water mark for use by positive assertions. Do this also + for the "once" (not-backup up) groups. */ + + case OP_KET: + case OP_KETRMIN: + case OP_KETRMAX: + prev = ecode - GET(ecode, 1); + saved_eptr = eptrb->epb_saved_eptr; + + /* Back up the stack of bracket start pointers. */ + + eptrb = eptrb->epb_prev; + + if (*prev == OP_ASSERT || *prev == OP_ASSERT_NOT || + *prev == OP_ASSERTBACK || *prev == OP_ASSERTBACK_NOT || + *prev == OP_ONCE) + { + md->end_match_ptr = eptr; /* For ONCE */ + md->end_offset_top = offset_top; + RRETURN(MATCH_MATCH); + } + + /* In all other cases except a conditional group we have to check the + group number back at the start and if necessary complete handling an + extraction by setting the offsets and bumping the high water mark. */ + + if (*prev != OP_COND) + { + number = *prev - OP_BRA; + + /* For extended extraction brackets (large number), we have to fish out + the number from a dummy opcode at the start. */ + + if (number > EXTRACT_BASIC_MAX) number = GET2(prev, 2+LINK_SIZE); + offset = number << 1; + +#ifdef DEBUG + printf("end bracket %d", number); + printf("\n"); +#endif + + /* Test for a numbered group. This includes groups called as a result + of recursion. Note that whole-pattern recursion is coded as a recurse + into group 0, so it won't be picked up here. Instead, we catch it when + the OP_END is reached. */ + + if (number > 0) + { + md->capture_last = number; + if (offset >= md->offset_max) md->offset_overflow = TRUE; else + { + md->offset_vector[offset] = + md->offset_vector[md->offset_end - number]; + md->offset_vector[offset+1] = eptr - md->start_subject; + if (offset_top <= offset) offset_top = offset + 2; + } + + /* Handle a recursively called group. Restore the offsets + appropriately and continue from after the call. */ + + if (md->recursive != NULL && md->recursive->group_num == number) + { + recursion_info *rec = md->recursive; + DPRINTF(("Recursion (%d) succeeded - continuing\n", number)); + md->recursive = rec->prevrec; + md->start_match = rec->save_start; + memcpy(md->offset_vector, rec->offset_save, + rec->saved_max * sizeof(int)); + ecode = rec->after_call; + ims = original_ims; + break; + } + } + } + + /* Reset the value of the ims flags, in case they got changed during + the group. */ + + ims = original_ims; + DPRINTF(("ims reset to %02lx\n", ims)); + + /* For a non-repeating ket, just continue at this level. This also + happens for a repeating ket if no characters were matched in the group. + This is the forcible breaking of infinite loops as implemented in Perl + 5.005. If there is an options reset, it will get obeyed in the normal + course of events. */ + + if (*ecode == OP_KET || eptr == saved_eptr) + { + ecode += 1 + LINK_SIZE; + break; + } + + /* The repeating kets try the rest of the pattern or restart from the + preceding bracket, in the appropriate order. In the second case, we can use + tail recursion to avoid using another stack frame. */ + + if (*ecode == OP_KETRMIN) + { + RMATCH(rrc, eptr, ecode + 1+LINK_SIZE, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + ecode = prev; + flags = match_isgroup; + goto TAIL_RECURSE; + } + else /* OP_KETRMAX */ + { + RMATCH(rrc, eptr, prev, offset_top, md, ims, eptrb, match_isgroup); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + ecode += 1 + LINK_SIZE; + flags = 0; + goto TAIL_RECURSE; + } + /* Control never gets here */ + + /* Start of subject unless notbol, or after internal newline if multiline */ + + case OP_CIRC: + if (md->notbol && eptr == md->start_subject) RRETURN(MATCH_NOMATCH); + if ((ims & PCRE_MULTILINE) != 0) + { + if (eptr != md->start_subject && + (eptr == md->end_subject || + eptr < md->start_subject + md->nllen || + !IS_NEWLINE(eptr - md->nllen))) + RRETURN(MATCH_NOMATCH); + ecode++; + break; + } + /* ... else fall through */ + + /* Start of subject assertion */ + + case OP_SOD: + if (eptr != md->start_subject) RRETURN(MATCH_NOMATCH); + ecode++; + break; + + /* Start of match assertion */ + + case OP_SOM: + if (eptr != md->start_subject + md->start_offset) RRETURN(MATCH_NOMATCH); + ecode++; + break; + + /* Assert before internal newline if multiline, or before a terminating + newline unless endonly is set, else end of subject unless noteol is set. */ + + case OP_DOLL: + if ((ims & PCRE_MULTILINE) != 0) + { + if (eptr < md->end_subject) + { if (!IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); } + else + { if (md->noteol) RRETURN(MATCH_NOMATCH); } + ecode++; + break; + } + else + { + if (md->noteol) RRETURN(MATCH_NOMATCH); + if (!md->endonly) + { + if (eptr != md->end_subject && + (eptr != md->end_subject - md->nllen || !IS_NEWLINE(eptr))) + RRETURN(MATCH_NOMATCH); + ecode++; + break; + } + } + /* ... else fall through for endonly */ + + /* End of subject assertion (\z) */ + + case OP_EOD: + if (eptr < md->end_subject) RRETURN(MATCH_NOMATCH); + ecode++; + break; + + /* End of subject or ending \n assertion (\Z) */ + + case OP_EODN: + if (eptr != md->end_subject && + (eptr != md->end_subject - md->nllen || !IS_NEWLINE(eptr))) + RRETURN(MATCH_NOMATCH); + ecode++; + break; + + /* Word boundary assertions */ + + case OP_NOT_WORD_BOUNDARY: + case OP_WORD_BOUNDARY: + { + + /* Find out if the previous and current characters are "word" characters. + It takes a bit more work in UTF-8 mode. Characters > 255 are assumed to + be "non-word" characters. */ + +#ifdef SUPPORT_UTF8 + if (utf8) + { + if (eptr == md->start_subject) prev_is_word = FALSE; else + { + const uschar *lastptr = eptr - 1; + while((*lastptr & 0xc0) == 0x80) lastptr--; + GETCHAR(c, lastptr); + prev_is_word = c < 256 && (md->ctypes[c] & ctype_word) != 0; + } + if (eptr >= md->end_subject) cur_is_word = FALSE; else + { + GETCHAR(c, eptr); + cur_is_word = c < 256 && (md->ctypes[c] & ctype_word) != 0; + } + } + else +#endif + + /* More streamlined when not in UTF-8 mode */ + + { + prev_is_word = (eptr != md->start_subject) && + ((md->ctypes[eptr[-1]] & ctype_word) != 0); + cur_is_word = (eptr < md->end_subject) && + ((md->ctypes[*eptr] & ctype_word) != 0); + } + + /* Now see if the situation is what we want */ + + if ((*ecode++ == OP_WORD_BOUNDARY)? + cur_is_word == prev_is_word : cur_is_word != prev_is_word) + RRETURN(MATCH_NOMATCH); + } + break; + + /* Match a single character type; inline for speed */ + + case OP_ANY: + if ((ims & PCRE_DOTALL) == 0) + { + if (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr)) + RRETURN(MATCH_NOMATCH); + } + if (eptr++ >= md->end_subject) RRETURN(MATCH_NOMATCH); + if (utf8) + while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; + ecode++; + break; + + /* Match a single byte, even in UTF-8 mode. This opcode really does match + any byte, even newline, independent of the setting of PCRE_DOTALL. */ + + case OP_ANYBYTE: + if (eptr++ >= md->end_subject) RRETURN(MATCH_NOMATCH); + ecode++; + break; + + case OP_NOT_DIGIT: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + if ( +#ifdef SUPPORT_UTF8 + c < 256 && +#endif + (md->ctypes[c] & ctype_digit) != 0 + ) + RRETURN(MATCH_NOMATCH); + ecode++; + break; + + case OP_DIGIT: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + if ( +#ifdef SUPPORT_UTF8 + c >= 256 || +#endif + (md->ctypes[c] & ctype_digit) == 0 + ) + RRETURN(MATCH_NOMATCH); + ecode++; + break; + + case OP_NOT_WHITESPACE: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + if ( +#ifdef SUPPORT_UTF8 + c < 256 && +#endif + (md->ctypes[c] & ctype_space) != 0 + ) + RRETURN(MATCH_NOMATCH); + ecode++; + break; + + case OP_WHITESPACE: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + if ( +#ifdef SUPPORT_UTF8 + c >= 256 || +#endif + (md->ctypes[c] & ctype_space) == 0 + ) + RRETURN(MATCH_NOMATCH); + ecode++; + break; + + case OP_NOT_WORDCHAR: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + if ( +#ifdef SUPPORT_UTF8 + c < 256 && +#endif + (md->ctypes[c] & ctype_word) != 0 + ) + RRETURN(MATCH_NOMATCH); + ecode++; + break; + + case OP_WORDCHAR: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + if ( +#ifdef SUPPORT_UTF8 + c >= 256 || +#endif + (md->ctypes[c] & ctype_word) == 0 + ) + RRETURN(MATCH_NOMATCH); + ecode++; + break; + +#ifdef SUPPORT_UCP + /* Check the next character by Unicode property. We will get here only + if the support is in the binary; otherwise a compile-time error occurs. */ + + case OP_PROP: + case OP_NOTPROP: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + { + int chartype, script; + int category = _pcre_ucp_findprop(c, &chartype, &script); + + switch(ecode[1]) + { + case PT_ANY: + if (op == OP_NOTPROP) RRETURN(MATCH_NOMATCH); + break; + + case PT_LAMP: + if ((chartype == ucp_Lu || + chartype == ucp_Ll || + chartype == ucp_Lt) == (op == OP_NOTPROP)) + RRETURN(MATCH_NOMATCH); + break; + + case PT_GC: + if ((ecode[2] != category) == (op == OP_PROP)) + RRETURN(MATCH_NOMATCH); + break; + + case PT_PC: + if ((ecode[2] != chartype) == (op == OP_PROP)) + RRETURN(MATCH_NOMATCH); + break; + + case PT_SC: + if ((ecode[2] != script) == (op == OP_PROP)) + RRETURN(MATCH_NOMATCH); + break; + + default: + RRETURN(PCRE_ERROR_INTERNAL); + break; + } + + ecode += 3; + } + break; + + /* Match an extended Unicode sequence. We will get here only if the support + is in the binary; otherwise a compile-time error occurs. */ + + case OP_EXTUNI: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + { + int chartype, script; + int category = _pcre_ucp_findprop(c, &chartype, &script); + if (category == ucp_M) RRETURN(MATCH_NOMATCH); + while (eptr < md->end_subject) + { + int len = 1; + if (!utf8) c = *eptr; else + { + GETCHARLEN(c, eptr, len); + } + category = _pcre_ucp_findprop(c, &chartype, &script); + if (category != ucp_M) break; + eptr += len; + } + } + ecode++; + break; +#endif + + + /* Match a back reference, possibly repeatedly. Look past the end of the + item to see if there is repeat information following. The code is similar + to that for character classes, but repeated for efficiency. Then obey + similar code to character type repeats - written out again for speed. + However, if the referenced string is the empty string, always treat + it as matched, any number of times (otherwise there could be infinite + loops). */ + + case OP_REF: + { + offset = GET2(ecode, 1) << 1; /* Doubled ref number */ + ecode += 3; /* Advance past item */ + + /* If the reference is unset, set the length to be longer than the amount + of subject left; this ensures that every attempt at a match fails. We + can't just fail here, because of the possibility of quantifiers with zero + minima. */ + + length = (offset >= offset_top || md->offset_vector[offset] < 0)? + md->end_subject - eptr + 1 : + md->offset_vector[offset+1] - md->offset_vector[offset]; + + /* Set up for repetition, or handle the non-repeated case */ + + switch (*ecode) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + case OP_CRPLUS: + case OP_CRMINPLUS: + case OP_CRQUERY: + case OP_CRMINQUERY: + c = *ecode++ - OP_CRSTAR; + minimize = (c & 1) != 0; + min = rep_min[c]; /* Pick up values from tables; */ + max = rep_max[c]; /* zero for max => infinity */ + if (max == 0) max = INT_MAX; + break; + + case OP_CRRANGE: + case OP_CRMINRANGE: + minimize = (*ecode == OP_CRMINRANGE); + min = GET2(ecode, 1); + max = GET2(ecode, 3); + if (max == 0) max = INT_MAX; + ecode += 5; + break; + + default: /* No repeat follows */ + if (!match_ref(offset, eptr, length, md, ims)) RRETURN(MATCH_NOMATCH); + eptr += length; + continue; /* With the main loop */ + } + + /* If the length of the reference is zero, just continue with the + main loop. */ + + if (length == 0) continue; + + /* First, ensure the minimum number of matches are present. We get back + the length of the reference string explicitly rather than passing the + address of eptr, so that eptr can be a register variable. */ + + for (i = 1; i <= min; i++) + { + if (!match_ref(offset, eptr, length, md, ims)) RRETURN(MATCH_NOMATCH); + eptr += length; + } + + /* If min = max, continue at the same level without recursion. + They are not both allowed to be zero. */ + + if (min == max) continue; + + /* If minimizing, keep trying and advancing the pointer */ + + if (minimize) + { + for (fi = min;; fi++) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || !match_ref(offset, eptr, length, md, ims)) + RRETURN(MATCH_NOMATCH); + eptr += length; + } + /* Control never gets here */ + } + + /* If maximizing, find the longest string and work backwards */ + + else + { + pp = eptr; + for (i = min; i < max; i++) + { + if (!match_ref(offset, eptr, length, md, ims)) break; + eptr += length; + } + while (eptr >= pp) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + eptr -= length; + } + RRETURN(MATCH_NOMATCH); + } + } + /* Control never gets here */ + + + + /* Match a bit-mapped character class, possibly repeatedly. This op code is + used when all the characters in the class have values in the range 0-255, + and either the matching is caseful, or the characters are in the range + 0-127 when UTF-8 processing is enabled. The only difference between + OP_CLASS and OP_NCLASS occurs when a data character outside the range is + encountered. + + First, look past the end of the item to see if there is repeat information + following. Then obey similar code to character type repeats - written out + again for speed. */ + + case OP_NCLASS: + case OP_CLASS: + { + data = ecode + 1; /* Save for matching */ + ecode += 33; /* Advance past the item */ + + switch (*ecode) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + case OP_CRPLUS: + case OP_CRMINPLUS: + case OP_CRQUERY: + case OP_CRMINQUERY: + c = *ecode++ - OP_CRSTAR; + minimize = (c & 1) != 0; + min = rep_min[c]; /* Pick up values from tables; */ + max = rep_max[c]; /* zero for max => infinity */ + if (max == 0) max = INT_MAX; + break; + + case OP_CRRANGE: + case OP_CRMINRANGE: + minimize = (*ecode == OP_CRMINRANGE); + min = GET2(ecode, 1); + max = GET2(ecode, 3); + if (max == 0) max = INT_MAX; + ecode += 5; + break; + + default: /* No repeat follows */ + min = max = 1; + break; + } + + /* First, ensure the minimum number of matches are present. */ + +#ifdef SUPPORT_UTF8 + /* UTF-8 mode */ + if (utf8) + { + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + if (c > 255) + { + if (op == OP_CLASS) RRETURN(MATCH_NOMATCH); + } + else + { + if ((data[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); + } + } + } + else +#endif + /* Not UTF-8 mode */ + { + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + c = *eptr++; + if ((data[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); + } + } + + /* If max == min we can continue with the main loop without the + need to recurse. */ + + if (min == max) continue; + + /* If minimizing, keep testing the rest of the expression and advancing + the pointer while it matches the class. */ + + if (minimize) + { +#ifdef SUPPORT_UTF8 + /* UTF-8 mode */ + if (utf8) + { + for (fi = min;; fi++) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + if (c > 255) + { + if (op == OP_CLASS) RRETURN(MATCH_NOMATCH); + } + else + { + if ((data[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); + } + } + } + else +#endif + /* Not UTF-8 mode */ + { + for (fi = min;; fi++) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + c = *eptr++; + if ((data[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); + } + } + /* Control never gets here */ + } + + /* If maximizing, find the longest possible run, then work backwards. */ + + else + { + pp = eptr; + +#ifdef SUPPORT_UTF8 + /* UTF-8 mode */ + if (utf8) + { + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + if (c > 255) + { + if (op == OP_CLASS) break; + } + else + { + if ((data[c/8] & (1 << (c&7))) == 0) break; + } + eptr += len; + } + for (;;) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (eptr-- == pp) break; /* Stop if tried at original pos */ + BACKCHAR(eptr); + } + } + else +#endif + /* Not UTF-8 mode */ + { + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) break; + c = *eptr; + if ((data[c/8] & (1 << (c&7))) == 0) break; + eptr++; + } + while (eptr >= pp) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + eptr--; + } + } + + RRETURN(MATCH_NOMATCH); + } + } + /* Control never gets here */ + + + /* Match an extended character class. This opcode is encountered only + in UTF-8 mode, because that's the only time it is compiled. */ + +#ifdef SUPPORT_UTF8 + case OP_XCLASS: + { + data = ecode + 1 + LINK_SIZE; /* Save for matching */ + ecode += GET(ecode, 1); /* Advance past the item */ + + switch (*ecode) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + case OP_CRPLUS: + case OP_CRMINPLUS: + case OP_CRQUERY: + case OP_CRMINQUERY: + c = *ecode++ - OP_CRSTAR; + minimize = (c & 1) != 0; + min = rep_min[c]; /* Pick up values from tables; */ + max = rep_max[c]; /* zero for max => infinity */ + if (max == 0) max = INT_MAX; + break; + + case OP_CRRANGE: + case OP_CRMINRANGE: + minimize = (*ecode == OP_CRMINRANGE); + min = GET2(ecode, 1); + max = GET2(ecode, 3); + if (max == 0) max = INT_MAX; + ecode += 5; + break; + + default: /* No repeat follows */ + min = max = 1; + break; + } + + /* First, ensure the minimum number of matches are present. */ + + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + if (!_pcre_xclass(c, data)) RRETURN(MATCH_NOMATCH); + } + + /* If max == min we can continue with the main loop without the + need to recurse. */ + + if (min == max) continue; + + /* If minimizing, keep testing the rest of the expression and advancing + the pointer while it matches the class. */ + + if (minimize) + { + for (fi = min;; fi++) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + if (!_pcre_xclass(c, data)) RRETURN(MATCH_NOMATCH); + } + /* Control never gets here */ + } + + /* If maximizing, find the longest possible run, then work backwards. */ + + else + { + pp = eptr; + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + if (!_pcre_xclass(c, data)) break; + eptr += len; + } + for(;;) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (eptr-- == pp) break; /* Stop if tried at original pos */ + BACKCHAR(eptr) + } + RRETURN(MATCH_NOMATCH); + } + + /* Control never gets here */ + } +#endif /* End of XCLASS */ + + /* Match a single character, casefully */ + + case OP_CHAR: +#ifdef SUPPORT_UTF8 + if (utf8) + { + length = 1; + ecode++; + GETCHARLEN(fc, ecode, length); + if (length > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); + while (length-- > 0) if (*ecode++ != *eptr++) RRETURN(MATCH_NOMATCH); + } + else +#endif + + /* Non-UTF-8 mode */ + { + if (md->end_subject - eptr < 1) RRETURN(MATCH_NOMATCH); + if (ecode[1] != *eptr++) RRETURN(MATCH_NOMATCH); + ecode += 2; + } + break; + + /* Match a single character, caselessly */ + + case OP_CHARNC: +#ifdef SUPPORT_UTF8 + if (utf8) + { + length = 1; + ecode++; + GETCHARLEN(fc, ecode, length); + + if (length > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); + + /* If the pattern character's value is < 128, we have only one byte, and + can use the fast lookup table. */ + + if (fc < 128) + { + if (md->lcc[*ecode++] != md->lcc[*eptr++]) RRETURN(MATCH_NOMATCH); + } + + /* Otherwise we must pick up the subject character */ + + else + { + int dc; + GETCHARINC(dc, eptr); + ecode += length; + + /* If we have Unicode property support, we can use it to test the other + case of the character, if there is one. */ + + if (fc != dc) + { +#ifdef SUPPORT_UCP + if (dc != _pcre_ucp_othercase(fc)) +#endif + RRETURN(MATCH_NOMATCH); + } + } + } + else +#endif /* SUPPORT_UTF8 */ + + /* Non-UTF-8 mode */ + { + if (md->end_subject - eptr < 1) RRETURN(MATCH_NOMATCH); + if (md->lcc[ecode[1]] != md->lcc[*eptr++]) RRETURN(MATCH_NOMATCH); + ecode += 2; + } + break; + + /* Match a single character repeatedly; different opcodes share code. */ + + case OP_EXACT: + min = max = GET2(ecode, 1); + ecode += 3; + goto REPEATCHAR; + + case OP_UPTO: + case OP_MINUPTO: + min = 0; + max = GET2(ecode, 1); + minimize = *ecode == OP_MINUPTO; + ecode += 3; + goto REPEATCHAR; + + case OP_STAR: + case OP_MINSTAR: + case OP_PLUS: + case OP_MINPLUS: + case OP_QUERY: + case OP_MINQUERY: + c = *ecode++ - OP_STAR; + minimize = (c & 1) != 0; + min = rep_min[c]; /* Pick up values from tables; */ + max = rep_max[c]; /* zero for max => infinity */ + if (max == 0) max = INT_MAX; + + /* Common code for all repeated single-character matches. We can give + up quickly if there are fewer than the minimum number of characters left in + the subject. */ + + REPEATCHAR: +#ifdef SUPPORT_UTF8 + if (utf8) + { + length = 1; + charptr = ecode; + GETCHARLEN(fc, ecode, length); + if (min * length > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); + ecode += length; + + /* Handle multibyte character matching specially here. There is + support for caseless matching if UCP support is present. */ + + if (length > 1) + { + int oclength = 0; + uschar occhars[8]; + +#ifdef SUPPORT_UCP + int othercase; + if ((ims & PCRE_CASELESS) != 0 && + (othercase = _pcre_ucp_othercase(fc)) >= 0 && + othercase >= 0) + oclength = _pcre_ord2utf8(othercase, occhars); +#endif /* SUPPORT_UCP */ + + for (i = 1; i <= min; i++) + { + if (memcmp(eptr, charptr, length) == 0) eptr += length; + /* Need braces because of following else */ + else if (oclength == 0) { RRETURN(MATCH_NOMATCH); } + else + { + if (memcmp(eptr, occhars, oclength) != 0) RRETURN(MATCH_NOMATCH); + eptr += oclength; + } + } + + if (min == max) continue; + + if (minimize) + { + for (fi = min;; fi++) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + if (memcmp(eptr, charptr, length) == 0) eptr += length; + /* Need braces because of following else */ + else if (oclength == 0) { RRETURN(MATCH_NOMATCH); } + else + { + if (memcmp(eptr, occhars, oclength) != 0) RRETURN(MATCH_NOMATCH); + eptr += oclength; + } + } + /* Control never gets here */ + } + else + { + pp = eptr; + for (i = min; i < max; i++) + { + if (eptr > md->end_subject - length) break; + if (memcmp(eptr, charptr, length) == 0) eptr += length; + else if (oclength == 0) break; + else + { + if (memcmp(eptr, occhars, oclength) != 0) break; + eptr += oclength; + } + } + while (eptr >= pp) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + eptr -= length; + } + RRETURN(MATCH_NOMATCH); + } + /* Control never gets here */ + } + + /* If the length of a UTF-8 character is 1, we fall through here, and + obey the code as for non-UTF-8 characters below, though in this case the + value of fc will always be < 128. */ + } + else +#endif /* SUPPORT_UTF8 */ + + /* When not in UTF-8 mode, load a single-byte character. */ + { + if (min > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); + fc = *ecode++; + } + + /* The value of fc at this point is always less than 256, though we may or + may not be in UTF-8 mode. The code is duplicated for the caseless and + caseful cases, for speed, since matching characters is likely to be quite + common. First, ensure the minimum number of matches are present. If min = + max, continue at the same level without recursing. Otherwise, if + minimizing, keep trying the rest of the expression and advancing one + matching character if failing, up to the maximum. Alternatively, if + maximizing, find the maximum number of characters and work backwards. */ + + DPRINTF(("matching %c{%d,%d} against subject %.*s\n", fc, min, max, + max, eptr)); + + if ((ims & PCRE_CASELESS) != 0) + { + fc = md->lcc[fc]; + for (i = 1; i <= min; i++) + if (fc != md->lcc[*eptr++]) RRETURN(MATCH_NOMATCH); + if (min == max) continue; + if (minimize) + { + for (fi = min;; fi++) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || eptr >= md->end_subject || + fc != md->lcc[*eptr++]) + RRETURN(MATCH_NOMATCH); + } + /* Control never gets here */ + } + else + { + pp = eptr; + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject || fc != md->lcc[*eptr]) break; + eptr++; + } + while (eptr >= pp) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + eptr--; + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + } + RRETURN(MATCH_NOMATCH); + } + /* Control never gets here */ + } + + /* Caseful comparisons (includes all multi-byte characters) */ + + else + { + for (i = 1; i <= min; i++) if (fc != *eptr++) RRETURN(MATCH_NOMATCH); + if (min == max) continue; + if (minimize) + { + for (fi = min;; fi++) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || eptr >= md->end_subject || fc != *eptr++) + RRETURN(MATCH_NOMATCH); + } + /* Control never gets here */ + } + else + { + pp = eptr; + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject || fc != *eptr) break; + eptr++; + } + while (eptr >= pp) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + eptr--; + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + } + RRETURN(MATCH_NOMATCH); + } + } + /* Control never gets here */ + + /* Match a negated single one-byte character. The character we are + checking can be multibyte. */ + + case OP_NOT: + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + ecode++; + GETCHARINCTEST(c, eptr); + if ((ims & PCRE_CASELESS) != 0) + { +#ifdef SUPPORT_UTF8 + if (c < 256) +#endif + c = md->lcc[c]; + if (md->lcc[*ecode++] == c) RRETURN(MATCH_NOMATCH); + } + else + { + if (*ecode++ == c) RRETURN(MATCH_NOMATCH); + } + break; + + /* Match a negated single one-byte character repeatedly. This is almost a + repeat of the code for a repeated single character, but I haven't found a + nice way of commoning these up that doesn't require a test of the + positive/negative option for each character match. Maybe that wouldn't add + very much to the time taken, but character matching *is* what this is all + about... */ + + case OP_NOTEXACT: + min = max = GET2(ecode, 1); + ecode += 3; + goto REPEATNOTCHAR; + + case OP_NOTUPTO: + case OP_NOTMINUPTO: + min = 0; + max = GET2(ecode, 1); + minimize = *ecode == OP_NOTMINUPTO; + ecode += 3; + goto REPEATNOTCHAR; + + case OP_NOTSTAR: + case OP_NOTMINSTAR: + case OP_NOTPLUS: + case OP_NOTMINPLUS: + case OP_NOTQUERY: + case OP_NOTMINQUERY: + c = *ecode++ - OP_NOTSTAR; + minimize = (c & 1) != 0; + min = rep_min[c]; /* Pick up values from tables; */ + max = rep_max[c]; /* zero for max => infinity */ + if (max == 0) max = INT_MAX; + + /* Common code for all repeated single-byte matches. We can give up quickly + if there are fewer than the minimum number of bytes left in the + subject. */ + + REPEATNOTCHAR: + if (min > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); + fc = *ecode++; + + /* The code is duplicated for the caseless and caseful cases, for speed, + since matching characters is likely to be quite common. First, ensure the + minimum number of matches are present. If min = max, continue at the same + level without recursing. Otherwise, if minimizing, keep trying the rest of + the expression and advancing one matching character if failing, up to the + maximum. Alternatively, if maximizing, find the maximum number of + characters and work backwards. */ + + DPRINTF(("negative matching %c{%d,%d} against subject %.*s\n", fc, min, max, + max, eptr)); + + if ((ims & PCRE_CASELESS) != 0) + { + fc = md->lcc[fc]; + +#ifdef SUPPORT_UTF8 + /* UTF-8 mode */ + if (utf8) + { + register int d; + for (i = 1; i <= min; i++) + { + GETCHARINC(d, eptr); + if (d < 256) d = md->lcc[d]; + if (fc == d) RRETURN(MATCH_NOMATCH); + } + } + else +#endif + + /* Not UTF-8 mode */ + { + for (i = 1; i <= min; i++) + if (fc == md->lcc[*eptr++]) RRETURN(MATCH_NOMATCH); + } + + if (min == max) continue; + + if (minimize) + { +#ifdef SUPPORT_UTF8 + /* UTF-8 mode */ + if (utf8) + { + register int d; + for (fi = min;; fi++) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + GETCHARINC(d, eptr); + if (d < 256) d = md->lcc[d]; + if (fi >= max || eptr >= md->end_subject || fc == d) + RRETURN(MATCH_NOMATCH); + } + } + else +#endif + /* Not UTF-8 mode */ + { + for (fi = min;; fi++) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || eptr >= md->end_subject || fc == md->lcc[*eptr++]) + RRETURN(MATCH_NOMATCH); + } + } + /* Control never gets here */ + } + + /* Maximize case */ + + else + { + pp = eptr; + +#ifdef SUPPORT_UTF8 + /* UTF-8 mode */ + if (utf8) + { + register int d; + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(d, eptr, len); + if (d < 256) d = md->lcc[d]; + if (fc == d) break; + eptr += len; + } + for(;;) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (eptr-- == pp) break; /* Stop if tried at original pos */ + BACKCHAR(eptr); + } + } + else +#endif + /* Not UTF-8 mode */ + { + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject || fc == md->lcc[*eptr]) break; + eptr++; + } + while (eptr >= pp) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + eptr--; + } + } + + RRETURN(MATCH_NOMATCH); + } + /* Control never gets here */ + } + + /* Caseful comparisons */ + + else + { +#ifdef SUPPORT_UTF8 + /* UTF-8 mode */ + if (utf8) + { + register int d; + for (i = 1; i <= min; i++) + { + GETCHARINC(d, eptr); + if (fc == d) RRETURN(MATCH_NOMATCH); + } + } + else +#endif + /* Not UTF-8 mode */ + { + for (i = 1; i <= min; i++) + if (fc == *eptr++) RRETURN(MATCH_NOMATCH); + } + + if (min == max) continue; + + if (minimize) + { +#ifdef SUPPORT_UTF8 + /* UTF-8 mode */ + if (utf8) + { + register int d; + for (fi = min;; fi++) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + GETCHARINC(d, eptr); + if (fi >= max || eptr >= md->end_subject || fc == d) + RRETURN(MATCH_NOMATCH); + } + } + else +#endif + /* Not UTF-8 mode */ + { + for (fi = min;; fi++) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || eptr >= md->end_subject || fc == *eptr++) + RRETURN(MATCH_NOMATCH); + } + } + /* Control never gets here */ + } + + /* Maximize case */ + + else + { + pp = eptr; + +#ifdef SUPPORT_UTF8 + /* UTF-8 mode */ + if (utf8) + { + register int d; + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(d, eptr, len); + if (fc == d) break; + eptr += len; + } + for(;;) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (eptr-- == pp) break; /* Stop if tried at original pos */ + BACKCHAR(eptr); + } + } + else +#endif + /* Not UTF-8 mode */ + { + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject || fc == *eptr) break; + eptr++; + } + while (eptr >= pp) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + eptr--; + } + } + + RRETURN(MATCH_NOMATCH); + } + } + /* Control never gets here */ + + /* Match a single character type repeatedly; several different opcodes + share code. This is very similar to the code for single characters, but we + repeat it in the interests of efficiency. */ + + case OP_TYPEEXACT: + min = max = GET2(ecode, 1); + minimize = TRUE; + ecode += 3; + goto REPEATTYPE; + + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + min = 0; + max = GET2(ecode, 1); + minimize = *ecode == OP_TYPEMINUPTO; + ecode += 3; + goto REPEATTYPE; + + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + c = *ecode++ - OP_TYPESTAR; + minimize = (c & 1) != 0; + min = rep_min[c]; /* Pick up values from tables; */ + max = rep_max[c]; /* zero for max => infinity */ + if (max == 0) max = INT_MAX; + + /* Common code for all repeated single character type matches. Note that + in UTF-8 mode, '.' matches a character of any length, but for the other + character types, the valid characters are all one-byte long. */ + + REPEATTYPE: + ctype = *ecode++; /* Code for the character type */ + +#ifdef SUPPORT_UCP + if (ctype == OP_PROP || ctype == OP_NOTPROP) + { + prop_fail_result = ctype == OP_NOTPROP; + prop_type = *ecode++; + prop_value = *ecode++; + } + else prop_type = -1; +#endif + + /* First, ensure the minimum number of matches are present. Use inline + code for maximizing the speed, and do the type test once at the start + (i.e. keep it out of the loop). Also we can test that there are at least + the minimum number of bytes before we start. This isn't as effective in + UTF-8 mode, but it does no harm. Separate the UTF-8 code completely as that + is tidier. Also separate the UCP code, which can be the same for both UTF-8 + and single-bytes. */ + + if (min > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); + if (min > 0) + { +#ifdef SUPPORT_UCP + if (prop_type >= 0) + { + switch(prop_type) + { + case PT_ANY: + if (prop_fail_result) RRETURN(MATCH_NOMATCH); + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + } + break; + + case PT_LAMP: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + if ((prop_chartype == ucp_Lu || + prop_chartype == ucp_Ll || + prop_chartype == ucp_Lt) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + break; + + case PT_GC: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + if ((prop_category == prop_value) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + break; + + case PT_PC: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + if ((prop_chartype == prop_value) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + break; + + case PT_SC: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + if ((prop_script == prop_value) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + break; + + default: + RRETURN(PCRE_ERROR_INTERNAL); + break; + } + } + + /* Match extended Unicode sequences. We will get here only if the + support is in the binary; otherwise a compile-time error occurs. */ + + else if (ctype == OP_EXTUNI) + { + for (i = 1; i <= min; i++) + { + GETCHARINCTEST(c, eptr); + prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH); + while (eptr < md->end_subject) + { + int len = 1; + if (!utf8) c = *eptr; else + { + GETCHARLEN(c, eptr, len); + } + prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + if (prop_category != ucp_M) break; + eptr += len; + } + } + } + + else +#endif /* SUPPORT_UCP */ + +/* Handle all other cases when the coding is UTF-8 */ + +#ifdef SUPPORT_UTF8 + if (utf8) switch(ctype) + { + case OP_ANY: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject || + ((ims & PCRE_DOTALL) == 0 && + eptr <= md->end_subject - md->nllen && + IS_NEWLINE(eptr))) + RRETURN(MATCH_NOMATCH); + eptr++; + while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; + } + break; + + case OP_ANYBYTE: + eptr += min; + break; + + case OP_NOT_DIGIT: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + if (c < 128 && (md->ctypes[c] & ctype_digit) != 0) + RRETURN(MATCH_NOMATCH); + } + break; + + case OP_DIGIT: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject || + *eptr >= 128 || (md->ctypes[*eptr++] & ctype_digit) == 0) + RRETURN(MATCH_NOMATCH); + /* No need to skip more bytes - we know it's a 1-byte character */ + } + break; + + case OP_NOT_WHITESPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject || + (*eptr < 128 && (md->ctypes[*eptr++] & ctype_space) != 0)) + RRETURN(MATCH_NOMATCH); + while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; + } + break; + + case OP_WHITESPACE: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject || + *eptr >= 128 || (md->ctypes[*eptr++] & ctype_space) == 0) + RRETURN(MATCH_NOMATCH); + /* No need to skip more bytes - we know it's a 1-byte character */ + } + break; + + case OP_NOT_WORDCHAR: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject || + (*eptr < 128 && (md->ctypes[*eptr++] & ctype_word) != 0)) + RRETURN(MATCH_NOMATCH); + while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; + } + break; + + case OP_WORDCHAR: + for (i = 1; i <= min; i++) + { + if (eptr >= md->end_subject || + *eptr >= 128 || (md->ctypes[*eptr++] & ctype_word) == 0) + RRETURN(MATCH_NOMATCH); + /* No need to skip more bytes - we know it's a 1-byte character */ + } + break; + + default: + RRETURN(PCRE_ERROR_INTERNAL); + } /* End switch(ctype) */ + + else +#endif /* SUPPORT_UTF8 */ + + /* Code for the non-UTF-8 case for minimum matching of operators other + than OP_PROP and OP_NOTPROP. */ + + switch(ctype) + { + case OP_ANY: + if ((ims & PCRE_DOTALL) == 0) + { + for (i = 1; i <= min; i++) + { + if (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr)) + RRETURN(MATCH_NOMATCH); + eptr++; + } + } + else eptr += min; + break; + + case OP_ANYBYTE: + eptr += min; + break; + + case OP_NOT_DIGIT: + for (i = 1; i <= min; i++) + if ((md->ctypes[*eptr++] & ctype_digit) != 0) RRETURN(MATCH_NOMATCH); + break; + + case OP_DIGIT: + for (i = 1; i <= min; i++) + if ((md->ctypes[*eptr++] & ctype_digit) == 0) RRETURN(MATCH_NOMATCH); + break; + + case OP_NOT_WHITESPACE: + for (i = 1; i <= min; i++) + if ((md->ctypes[*eptr++] & ctype_space) != 0) RRETURN(MATCH_NOMATCH); + break; + + case OP_WHITESPACE: + for (i = 1; i <= min; i++) + if ((md->ctypes[*eptr++] & ctype_space) == 0) RRETURN(MATCH_NOMATCH); + break; + + case OP_NOT_WORDCHAR: + for (i = 1; i <= min; i++) + if ((md->ctypes[*eptr++] & ctype_word) != 0) + RRETURN(MATCH_NOMATCH); + break; + + case OP_WORDCHAR: + for (i = 1; i <= min; i++) + if ((md->ctypes[*eptr++] & ctype_word) == 0) + RRETURN(MATCH_NOMATCH); + break; + + default: + RRETURN(PCRE_ERROR_INTERNAL); + } + } + + /* If min = max, continue at the same level without recursing */ + + if (min == max) continue; + + /* If minimizing, we have to test the rest of the pattern before each + subsequent match. Again, separate the UTF-8 case for speed, and also + separate the UCP cases. */ + + if (minimize) + { +#ifdef SUPPORT_UCP + if (prop_type >= 0) + { + switch(prop_type) + { + case PT_ANY: + for (fi = min;; fi++) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + if (prop_fail_result) RRETURN(MATCH_NOMATCH); + } + break; + + case PT_LAMP: + for (fi = min;; fi++) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + if ((prop_chartype == ucp_Lu || + prop_chartype == ucp_Ll || + prop_chartype == ucp_Lt) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + break; + + case PT_GC: + for (fi = min;; fi++) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + if ((prop_category == prop_value) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + break; + + case PT_PC: + for (fi = min;; fi++) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + if ((prop_chartype == prop_value) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + break; + + case PT_SC: + for (fi = min;; fi++) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINC(c, eptr); + prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + if ((prop_script == prop_value) == prop_fail_result) + RRETURN(MATCH_NOMATCH); + } + break; + + default: + RRETURN(PCRE_ERROR_INTERNAL); + break; + } + } + + /* Match extended Unicode sequences. We will get here only if the + support is in the binary; otherwise a compile-time error occurs. */ + + else if (ctype == OP_EXTUNI) + { + for (fi = min;; fi++) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); + GETCHARINCTEST(c, eptr); + prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH); + while (eptr < md->end_subject) + { + int len = 1; + if (!utf8) c = *eptr; else + { + GETCHARLEN(c, eptr, len); + } + prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + if (prop_category != ucp_M) break; + eptr += len; + } + } + } + + else +#endif /* SUPPORT_UCP */ + +#ifdef SUPPORT_UTF8 + /* UTF-8 mode */ + if (utf8) + { + for (fi = min;; fi++) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || eptr >= md->end_subject || + (ctype == OP_ANY && (ims & PCRE_DOTALL) == 0 && + eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) + RRETURN(MATCH_NOMATCH); + + GETCHARINC(c, eptr); + switch(ctype) + { + case OP_ANY: /* This is the DOTALL case */ + break; + + case OP_ANYBYTE: + break; + + case OP_NOT_DIGIT: + if (c < 256 && (md->ctypes[c] & ctype_digit) != 0) + RRETURN(MATCH_NOMATCH); + break; + + case OP_DIGIT: + if (c >= 256 || (md->ctypes[c] & ctype_digit) == 0) + RRETURN(MATCH_NOMATCH); + break; + + case OP_NOT_WHITESPACE: + if (c < 256 && (md->ctypes[c] & ctype_space) != 0) + RRETURN(MATCH_NOMATCH); + break; + + case OP_WHITESPACE: + if (c >= 256 || (md->ctypes[c] & ctype_space) == 0) + RRETURN(MATCH_NOMATCH); + break; + + case OP_NOT_WORDCHAR: + if (c < 256 && (md->ctypes[c] & ctype_word) != 0) + RRETURN(MATCH_NOMATCH); + break; + + case OP_WORDCHAR: + if (c >= 256 || (md->ctypes[c] & ctype_word) == 0) + RRETURN(MATCH_NOMATCH); + break; + + default: + RRETURN(PCRE_ERROR_INTERNAL); + } + } + } + else +#endif + /* Not UTF-8 mode */ + { + for (fi = min;; fi++) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (fi >= max || eptr >= md->end_subject || + ((ims & PCRE_DOTALL) == 0 && + eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) + RRETURN(MATCH_NOMATCH); + + c = *eptr++; + switch(ctype) + { + case OP_ANY: /* This is the DOTALL case */ + break; + + case OP_ANYBYTE: + break; + + case OP_NOT_DIGIT: + if ((md->ctypes[c] & ctype_digit) != 0) RRETURN(MATCH_NOMATCH); + break; + + case OP_DIGIT: + if ((md->ctypes[c] & ctype_digit) == 0) RRETURN(MATCH_NOMATCH); + break; + + case OP_NOT_WHITESPACE: + if ((md->ctypes[c] & ctype_space) != 0) RRETURN(MATCH_NOMATCH); + break; + + case OP_WHITESPACE: + if ((md->ctypes[c] & ctype_space) == 0) RRETURN(MATCH_NOMATCH); + break; + + case OP_NOT_WORDCHAR: + if ((md->ctypes[c] & ctype_word) != 0) RRETURN(MATCH_NOMATCH); + break; + + case OP_WORDCHAR: + if ((md->ctypes[c] & ctype_word) == 0) RRETURN(MATCH_NOMATCH); + break; + + default: + RRETURN(PCRE_ERROR_INTERNAL); + } + } + } + /* Control never gets here */ + } + + /* If maximizing it is worth using inline code for speed, doing the type + test once at the start (i.e. keep it out of the loop). Again, keep the + UTF-8 and UCP stuff separate. */ + + else + { + pp = eptr; /* Remember where we started */ + +#ifdef SUPPORT_UCP + if (prop_type >= 0) + { + switch(prop_type) + { + case PT_ANY: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + if (prop_fail_result) break; + eptr+= len; + } + break; + + case PT_LAMP: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + if ((prop_chartype == ucp_Lu || + prop_chartype == ucp_Ll || + prop_chartype == ucp_Lt) == prop_fail_result) + break; + eptr+= len; + } + break; + + case PT_GC: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + if ((prop_category == prop_value) == prop_fail_result) + break; + eptr+= len; + } + break; + + case PT_PC: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + if ((prop_chartype == prop_value) == prop_fail_result) + break; + eptr+= len; + } + break; + + case PT_SC: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + if ((prop_script == prop_value) == prop_fail_result) + break; + eptr+= len; + } + break; + } + + /* eptr is now past the end of the maximum run */ + + for(;;) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (eptr-- == pp) break; /* Stop if tried at original pos */ + BACKCHAR(eptr); + } + } + + /* Match extended Unicode sequences. We will get here only if the + support is in the binary; otherwise a compile-time error occurs. */ + + else if (ctype == OP_EXTUNI) + { + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) break; + GETCHARINCTEST(c, eptr); + prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + if (prop_category == ucp_M) break; + while (eptr < md->end_subject) + { + int len = 1; + if (!utf8) c = *eptr; else + { + GETCHARLEN(c, eptr, len); + } + prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + if (prop_category != ucp_M) break; + eptr += len; + } + } + + /* eptr is now past the end of the maximum run */ + + for(;;) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (eptr-- == pp) break; /* Stop if tried at original pos */ + for (;;) /* Move back over one extended */ + { + int len = 1; + BACKCHAR(eptr); + if (!utf8) c = *eptr; else + { + GETCHARLEN(c, eptr, len); + } + prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); + if (prop_category != ucp_M) break; + eptr--; + } + } + } + + else +#endif /* SUPPORT_UCP */ + +#ifdef SUPPORT_UTF8 + /* UTF-8 mode */ + + if (utf8) + { + switch(ctype) + { + case OP_ANY: + + /* Special code is required for UTF8, but when the maximum is + unlimited we don't need it, so we repeat the non-UTF8 code. This is + probably worth it, because .* is quite a common idiom. */ + + if (max < INT_MAX) + { + if ((ims & PCRE_DOTALL) == 0) + { + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject || + (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) + break; + eptr++; + while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; + } + } + else + { + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject) break; + eptr++; + while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; + } + } + } + + /* Handle unlimited UTF-8 repeat */ + + else + { + if ((ims & PCRE_DOTALL) == 0) + { + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject || + (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) + break; + eptr++; + } + break; + } + else + { + c = max - min; + if (c > md->end_subject - eptr) c = md->end_subject - eptr; + eptr += c; + } + } + break; + + /* The byte case is the same as non-UTF8 */ + + case OP_ANYBYTE: + c = max - min; + if (c > md->end_subject - eptr) c = md->end_subject - eptr; + eptr += c; + break; + + case OP_NOT_DIGIT: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + if (c < 256 && (md->ctypes[c] & ctype_digit) != 0) break; + eptr+= len; + } + break; + + case OP_DIGIT: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + if (c >= 256 ||(md->ctypes[c] & ctype_digit) == 0) break; + eptr+= len; + } + break; + + case OP_NOT_WHITESPACE: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + if (c < 256 && (md->ctypes[c] & ctype_space) != 0) break; + eptr+= len; + } + break; + + case OP_WHITESPACE: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + if (c >= 256 ||(md->ctypes[c] & ctype_space) == 0) break; + eptr+= len; + } + break; + + case OP_NOT_WORDCHAR: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + if (c < 256 && (md->ctypes[c] & ctype_word) != 0) break; + eptr+= len; + } + break; + + case OP_WORDCHAR: + for (i = min; i < max; i++) + { + int len = 1; + if (eptr >= md->end_subject) break; + GETCHARLEN(c, eptr, len); + if (c >= 256 || (md->ctypes[c] & ctype_word) == 0) break; + eptr+= len; + } + break; + + default: + RRETURN(PCRE_ERROR_INTERNAL); + } + + /* eptr is now past the end of the maximum run */ + + for(;;) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + if (eptr-- == pp) break; /* Stop if tried at original pos */ + BACKCHAR(eptr); + } + } + else +#endif + + /* Not UTF-8 mode */ + { + switch(ctype) + { + case OP_ANY: + if ((ims & PCRE_DOTALL) == 0) + { + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject || + (eptr <= md->end_subject - md->nllen && IS_NEWLINE(eptr))) + break; + eptr++; + } + break; + } + /* For DOTALL case, fall through and treat as \C */ + + case OP_ANYBYTE: + c = max - min; + if (c > md->end_subject - eptr) c = md->end_subject - eptr; + eptr += c; + break; + + case OP_NOT_DIGIT: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_digit) != 0) + break; + eptr++; + } + break; + + case OP_DIGIT: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_digit) == 0) + break; + eptr++; + } + break; + + case OP_NOT_WHITESPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_space) != 0) + break; + eptr++; + } + break; + + case OP_WHITESPACE: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_space) == 0) + break; + eptr++; + } + break; + + case OP_NOT_WORDCHAR: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_word) != 0) + break; + eptr++; + } + break; + + case OP_WORDCHAR: + for (i = min; i < max; i++) + { + if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_word) == 0) + break; + eptr++; + } + break; + + default: + RRETURN(PCRE_ERROR_INTERNAL); + } + + /* eptr is now past the end of the maximum run */ + + while (eptr >= pp) + { + RMATCH(rrc, eptr, ecode, offset_top, md, ims, eptrb, 0); + eptr--; + if (rrc != MATCH_NOMATCH) RRETURN(rrc); + } + } + + /* Get here if we can't make it match with any permitted repetitions */ + + RRETURN(MATCH_NOMATCH); + } + /* Control never gets here */ + + /* There's been some horrible disaster. Since all codes > OP_BRA are + for capturing brackets, and there shouldn't be any gaps between 0 and + OP_BRA, arrival here can only mean there is something seriously wrong + in the code above or the OP_xxx definitions. */ + + default: + DPRINTF(("Unknown opcode %d\n", *ecode)); + RRETURN(PCRE_ERROR_UNKNOWN_NODE); + } + + /* Do not stick any code in here without much thought; it is assumed + that "continue" in the code above comes out to here to repeat the main + loop. */ + + } /* End of main loop */ +/* Control never reaches here */ +} + + +/*************************************************************************** +**************************************************************************** + RECURSION IN THE match() FUNCTION + +Undefine all the macros that were defined above to handle this. */ + +#ifdef NO_RECURSE +#undef eptr +#undef ecode +#undef offset_top +#undef ims +#undef eptrb +#undef flags + +#undef callpat +#undef charptr +#undef data +#undef next +#undef pp +#undef prev +#undef saved_eptr + +#undef new_recursive + +#undef cur_is_word +#undef condition +#undef minimize +#undef prev_is_word + +#undef original_ims + +#undef ctype +#undef length +#undef max +#undef min +#undef number +#undef offset +#undef op +#undef save_capture_last +#undef save_offset1 +#undef save_offset2 +#undef save_offset3 +#undef stacksave + +#undef newptrb + +#endif + +/* These two are defined as macros in both cases */ + +#undef fc +#undef fi + +/*************************************************************************** +***************************************************************************/ + + + +/************************************************* +* Execute a Regular Expression * +*************************************************/ + +/* This function applies a compiled re to a subject string and picks out +portions of the string if it matches. Two elements in the vector are set for +each substring: the offsets to the start and end of the substring. + +Arguments: + argument_re points to the compiled expression + extra_data points to extra data or is NULL + subject points to the subject string + length length of subject string (may contain binary zeros) + start_offset where to start in the subject string + options option bits + offsets points to a vector of ints to be filled in with offsets + offsetcount the number of elements in the vector + +Returns: > 0 => success; value is the number of elements filled in + = 0 => success, but offsets is not big enough + -1 => failed to match + < -1 => some kind of unexpected problem +*/ + +PCRE_DATA_SCOPE int +pcre_exec(const pcre *argument_re, const pcre_extra *extra_data, + PCRE_SPTR subject, int length, int start_offset, int options, int *offsets, + int offsetcount) +{ +int rc, resetcount, ocount; +int first_byte = -1; +int req_byte = -1; +int req_byte2 = -1; +int newline; +unsigned long int ims; +BOOL using_temporary_offsets = FALSE; +BOOL anchored; +BOOL startline; +BOOL firstline; +BOOL first_byte_caseless = FALSE; +BOOL req_byte_caseless = FALSE; +match_data match_block; +match_data *md = &match_block; +const uschar *tables; +const uschar *start_bits = NULL; +USPTR start_match = (USPTR)subject + start_offset; +USPTR end_subject; +USPTR req_byte_ptr = start_match - 1; + +pcre_study_data internal_study; +const pcre_study_data *study; + +real_pcre internal_re; +const real_pcre *external_re = (const real_pcre *)argument_re; +const real_pcre *re = external_re; + +/* Plausibility checks */ + +if ((options & ~PUBLIC_EXEC_OPTIONS) != 0) return PCRE_ERROR_BADOPTION; +if (re == NULL || subject == NULL || + (offsets == NULL && offsetcount > 0)) return PCRE_ERROR_NULL; +if (offsetcount < 0) return PCRE_ERROR_BADCOUNT; + +/* Fish out the optional data from the extra_data structure, first setting +the default values. */ + +study = NULL; +md->match_limit = MATCH_LIMIT; +md->match_limit_recursion = MATCH_LIMIT_RECURSION; +md->callout_data = NULL; + +/* The table pointer is always in native byte order. */ + +tables = external_re->tables; + +if (extra_data != NULL) + { + register unsigned int flags = extra_data->flags; + if ((flags & PCRE_EXTRA_STUDY_DATA) != 0) + study = (const pcre_study_data *)extra_data->study_data; + if ((flags & PCRE_EXTRA_MATCH_LIMIT) != 0) + md->match_limit = extra_data->match_limit; + if ((flags & PCRE_EXTRA_MATCH_LIMIT_RECURSION) != 0) + md->match_limit_recursion = extra_data->match_limit_recursion; + if ((flags & PCRE_EXTRA_CALLOUT_DATA) != 0) + md->callout_data = extra_data->callout_data; + if ((flags & PCRE_EXTRA_TABLES) != 0) tables = extra_data->tables; + } + +/* If the exec call supplied NULL for tables, use the inbuilt ones. This +is a feature that makes it possible to save compiled regex and re-use them +in other programs later. */ + +if (tables == NULL) tables = _pcre_default_tables; + +/* Check that the first field in the block is the magic number. If it is not, +test for a regex that was compiled on a host of opposite endianness. If this is +the case, flipped values are put in internal_re and internal_study if there was +study data too. */ + +if (re->magic_number != MAGIC_NUMBER) + { + re = _pcre_try_flipped(re, &internal_re, study, &internal_study); + if (re == NULL) return PCRE_ERROR_BADMAGIC; + if (study != NULL) study = &internal_study; + } + +/* Set up other data */ + +anchored = ((re->options | options) & PCRE_ANCHORED) != 0; +startline = (re->options & PCRE_STARTLINE) != 0; +firstline = (re->options & PCRE_FIRSTLINE) != 0; + +/* The code starts after the real_pcre block and the capture name table. */ + +md->start_code = (const uschar *)external_re + re->name_table_offset + + re->name_count * re->name_entry_size; + +md->start_subject = (USPTR)subject; +md->start_offset = start_offset; +md->end_subject = md->start_subject + length; +end_subject = md->end_subject; + +md->endonly = (re->options & PCRE_DOLLAR_ENDONLY) != 0; +md->utf8 = (re->options & PCRE_UTF8) != 0; + +md->notbol = (options & PCRE_NOTBOL) != 0; +md->noteol = (options & PCRE_NOTEOL) != 0; +md->notempty = (options & PCRE_NOTEMPTY) != 0; +md->partial = (options & PCRE_PARTIAL) != 0; +md->hitend = FALSE; + +md->recursive = NULL; /* No recursion at top level */ + +md->lcc = tables + lcc_offset; +md->ctypes = tables + ctypes_offset; + +/* Handle different types of newline. The two bits give four cases. If nothing +is set at run time, whatever was used at compile time applies. */ + +switch ((((options & PCRE_NEWLINE_CRLF) == 0)? re->options : options) & + PCRE_NEWLINE_CRLF) + { + default: newline = NEWLINE; break; /* Compile-time default */ + case PCRE_NEWLINE_CR: newline = '\r'; break; + case PCRE_NEWLINE_LF: newline = '\n'; break; + case PCRE_NEWLINE_CR+ + PCRE_NEWLINE_LF: newline = ('\r' << 8) | '\n'; break; + } + +if (newline > 255) + { + md->nllen = 2; + md->nl[0] = (newline >> 8) & 255; + md->nl[1] = newline & 255; + } +else + { + md->nllen = 1; + md->nl[0] = newline; + } + +/* Partial matching is supported only for a restricted set of regexes at the +moment. */ + +if (md->partial && (re->options & PCRE_NOPARTIAL) != 0) + return PCRE_ERROR_BADPARTIAL; + +/* Check a UTF-8 string if required. Unfortunately there's no way of passing +back the character offset. */ + +#ifdef SUPPORT_UTF8 +if (md->utf8 && (options & PCRE_NO_UTF8_CHECK) == 0) + { + if (_pcre_valid_utf8((uschar *)subject, length) >= 0) + return PCRE_ERROR_BADUTF8; + if (start_offset > 0 && start_offset < length) + { + int tb = ((uschar *)subject)[start_offset]; + if (tb > 127) + { + tb &= 0xc0; + if (tb != 0 && tb != 0xc0) return PCRE_ERROR_BADUTF8_OFFSET; + } + } + } +#endif + +/* The ims options can vary during the matching as a result of the presence +of (?ims) items in the pattern. They are kept in a local variable so that +restoring at the exit of a group is easy. */ + +ims = re->options & (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL); + +/* If the expression has got more back references than the offsets supplied can +hold, we get a temporary chunk of working store to use during the matching. +Otherwise, we can use the vector supplied, rounding down its size to a multiple +of 3. */ + +ocount = offsetcount - (offsetcount % 3); + +if (re->top_backref > 0 && re->top_backref >= ocount/3) + { + ocount = re->top_backref * 3 + 3; + md->offset_vector = (int *)(pcre_malloc)(ocount * sizeof(int)); + if (md->offset_vector == NULL) return PCRE_ERROR_NOMEMORY; + using_temporary_offsets = TRUE; + DPRINTF(("Got memory to hold back references\n")); + } +else md->offset_vector = offsets; + +md->offset_end = ocount; +md->offset_max = (2*ocount)/3; +md->offset_overflow = FALSE; +md->capture_last = -1; + +/* Compute the minimum number of offsets that we need to reset each time. Doing +this makes a huge difference to execution time when there aren't many brackets +in the pattern. */ + +resetcount = 2 + re->top_bracket * 2; +if (resetcount > offsetcount) resetcount = ocount; + +/* Reset the working variable associated with each extraction. These should +never be used unless previously set, but they get saved and restored, and so we +initialize them to avoid reading uninitialized locations. */ + +if (md->offset_vector != NULL) + { + register int *iptr = md->offset_vector + ocount; + register int *iend = iptr - resetcount/2 + 1; + while (--iptr >= iend) *iptr = -1; + } + +/* Set up the first character to match, if available. The first_byte value is +never set for an anchored regular expression, but the anchoring may be forced +at run time, so we have to test for anchoring. The first char may be unset for +an unanchored pattern, of course. If there's no first char and the pattern was +studied, there may be a bitmap of possible first characters. */ + +if (!anchored) + { + if ((re->options & PCRE_FIRSTSET) != 0) + { + first_byte = re->first_byte & 255; + if ((first_byte_caseless = ((re->first_byte & REQ_CASELESS) != 0)) == TRUE) + first_byte = md->lcc[first_byte]; + } + else + if (!startline && study != NULL && + (study->options & PCRE_STUDY_MAPPED) != 0) + start_bits = study->start_bits; + } + +/* For anchored or unanchored matches, there may be a "last known required +character" set. */ + +if ((re->options & PCRE_REQCHSET) != 0) + { + req_byte = re->req_byte & 255; + req_byte_caseless = (re->req_byte & REQ_CASELESS) != 0; + req_byte2 = (tables + fcc_offset)[req_byte]; /* case flipped */ + } + +/* Loop for handling unanchored repeated matching attempts; for anchored regexs +the loop runs just once. */ + +do + { + USPTR save_end_subject = end_subject; + + /* Reset the maximum number of extractions we might see. */ + + if (md->offset_vector != NULL) + { + register int *iptr = md->offset_vector; + register int *iend = iptr + resetcount; + while (iptr < iend) *iptr++ = -1; + } + + /* Advance to a unique first char if possible. If firstline is TRUE, the + start of the match is constrained to the first line of a multiline string. + Implement this by temporarily adjusting end_subject so that we stop scanning + at a newline. If the match fails at the newline, later code breaks this loop. + */ + + if (firstline) + { + USPTR t = start_match; + while (t <= save_end_subject - md->nllen && !IS_NEWLINE(t)) t++; + end_subject = t; + } + + /* Now test for a unique first byte */ + + if (first_byte >= 0) + { + if (first_byte_caseless) + while (start_match < end_subject && + md->lcc[*start_match] != first_byte) + start_match++; + else + while (start_match < end_subject && *start_match != first_byte) + start_match++; + } + + /* Or to just after a linebreak for a multiline match if possible */ + + else if (startline) + { + if (start_match >= md->start_subject + md->nllen + + start_offset) + { + while (start_match <= end_subject && + !IS_NEWLINE(start_match - md->nllen)) + start_match++; + } + } + + /* Or to a non-unique first char after study */ + + else if (start_bits != NULL) + { + while (start_match < end_subject) + { + register unsigned int c = *start_match; + if ((start_bits[c/8] & (1 << (c&7))) == 0) start_match++; else break; + } + } + + /* Restore fudged end_subject */ + + end_subject = save_end_subject; + +#ifdef DEBUG /* Sigh. Some compilers never learn. */ + printf(">>>> Match against: "); + pchars(start_match, end_subject - start_match, TRUE, md); + printf("\n"); +#endif + + /* If req_byte is set, we know that that character must appear in the subject + for the match to succeed. If the first character is set, req_byte must be + later in the subject; otherwise the test starts at the match point. This + optimization can save a huge amount of backtracking in patterns with nested + unlimited repeats that aren't going to match. Writing separate code for + cased/caseless versions makes it go faster, as does using an autoincrement + and backing off on a match. + + HOWEVER: when the subject string is very, very long, searching to its end can + take a long time, and give bad performance on quite ordinary patterns. This + showed up when somebody was matching /^C/ on a 32-megabyte string... so we + don't do this when the string is sufficiently long. + + ALSO: this processing is disabled when partial matching is requested. + */ + + if (req_byte >= 0 && + end_subject - start_match < REQ_BYTE_MAX && + !md->partial) + { + register USPTR p = start_match + ((first_byte >= 0)? 1 : 0); + + /* We don't need to repeat the search if we haven't yet reached the + place we found it at last time. */ + + if (p > req_byte_ptr) + { + if (req_byte_caseless) + { + while (p < end_subject) + { + register int pp = *p++; + if (pp == req_byte || pp == req_byte2) { p--; break; } + } + } + else + { + while (p < end_subject) + { + if (*p++ == req_byte) { p--; break; } + } + } + + /* If we can't find the required character, break the matching loop */ + + if (p >= end_subject) break; + + /* If we have found the required character, save the point where we + found it, so that we don't search again next time round the loop if + the start hasn't passed this character yet. */ + + req_byte_ptr = p; + } + } + + /* When a match occurs, substrings will be set for all internal extractions; + we just need to set up the whole thing as substring 0 before returning. If + there were too many extractions, set the return code to zero. In the case + where we had to get some local store to hold offsets for backreferences, copy + those back references that we can. In this case there need not be overflow + if certain parts of the pattern were not used. */ + + md->start_match = start_match; + md->match_call_count = 0; + + rc = match(start_match, md->start_code, 2, md, ims, NULL, match_isgroup, 0); + + /* When the result is no match, if the subject's first character was a + newline and the PCRE_FIRSTLINE option is set, break (which will return + PCRE_ERROR_NOMATCH). The option requests that a match occur before the first + newline in the subject. Otherwise, advance the pointer to the next character + and continue - but the continuation will actually happen only when the + pattern is not anchored. */ + + if (rc == MATCH_NOMATCH) + { + if (firstline && + start_match <= md->end_subject - md->nllen && + IS_NEWLINE(start_match)) + break; + start_match++; +#ifdef SUPPORT_UTF8 + if (md->utf8) + while(start_match < end_subject && (*start_match & 0xc0) == 0x80) + start_match++; +#endif + continue; + } + + if (rc != MATCH_MATCH) + { + DPRINTF((">>>> error: returning %d\n", rc)); + return rc; + } + + /* We have a match! Copy the offset information from temporary store if + necessary */ + + if (using_temporary_offsets) + { + if (offsetcount >= 4) + { + memcpy(offsets + 2, md->offset_vector + 2, + (offsetcount - 2) * sizeof(int)); + DPRINTF(("Copied offsets from temporary memory\n")); + } + if (md->end_offset_top > offsetcount) + md->offset_overflow = TRUE; + + DPRINTF(("Freeing temporary memory\n")); + (pcre_free)(md->offset_vector); + } + + rc = md->offset_overflow? 0 : md->end_offset_top/2; + + if (offsetcount < 2) rc = 0; else + { + offsets[0] = start_match - md->start_subject; + offsets[1] = md->end_match_ptr - md->start_subject; + } + + DPRINTF((">>>> returning %d\n", rc)); + return rc; + } + +/* This "while" is the end of the "do" above */ + +while (!anchored && start_match <= end_subject); + +if (using_temporary_offsets) + { + DPRINTF(("Freeing temporary memory\n")); + (pcre_free)(md->offset_vector); + } + +if (md->partial && md->hitend) + { + DPRINTF((">>>> returning PCRE_ERROR_PARTIAL\n")); + return PCRE_ERROR_PARTIAL; + } +else + { + DPRINTF((">>>> returning PCRE_ERROR_NOMATCH\n")); + return PCRE_ERROR_NOMATCH; + } +} + +/* End of pcre_exec.c */ diff --git a/libs/pcre/pcre_fullinfo.c b/libs/pcre/pcre_fullinfo.c new file mode 100644 index 0000000000..4a8edc6f47 --- /dev/null +++ b/libs/pcre/pcre_fullinfo.c @@ -0,0 +1,149 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/*PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains the external function pcre_fullinfo(), which returns +information about a compiled pattern. */ + + +#include "pcre_internal.h" + + +/************************************************* +* Return info about compiled pattern * +*************************************************/ + +/* This is a newer "info" function which has an extensible interface so +that additional items can be added compatibly. + +Arguments: + argument_re points to compiled code + extra_data points extra data, or NULL + what what information is required + where where to put the information + +Returns: 0 if data returned, negative on error +*/ + +PCRE_DATA_SCOPE int +pcre_fullinfo(const pcre *argument_re, const pcre_extra *extra_data, int what, + void *where) +{ +real_pcre internal_re; +pcre_study_data internal_study; +const real_pcre *re = (const real_pcre *)argument_re; +const pcre_study_data *study = NULL; + +if (re == NULL || where == NULL) return PCRE_ERROR_NULL; + +if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_STUDY_DATA) != 0) + study = (const pcre_study_data *)extra_data->study_data; + +if (re->magic_number != MAGIC_NUMBER) + { + re = _pcre_try_flipped(re, &internal_re, study, &internal_study); + if (re == NULL) return PCRE_ERROR_BADMAGIC; + if (study != NULL) study = &internal_study; + } + +switch (what) + { + case PCRE_INFO_OPTIONS: + *((unsigned long int *)where) = re->options & PUBLIC_OPTIONS; + break; + + case PCRE_INFO_SIZE: + *((size_t *)where) = re->size; + break; + + case PCRE_INFO_STUDYSIZE: + *((size_t *)where) = (study == NULL)? 0 : study->size; + break; + + case PCRE_INFO_CAPTURECOUNT: + *((int *)where) = re->top_bracket; + break; + + case PCRE_INFO_BACKREFMAX: + *((int *)where) = re->top_backref; + break; + + case PCRE_INFO_FIRSTBYTE: + *((int *)where) = + ((re->options & PCRE_FIRSTSET) != 0)? re->first_byte : + ((re->options & PCRE_STARTLINE) != 0)? -1 : -2; + break; + + /* Make sure we pass back the pointer to the bit vector in the external + block, not the internal copy (with flipped integer fields). */ + + case PCRE_INFO_FIRSTTABLE: + *((const uschar **)where) = + (study != NULL && (study->options & PCRE_STUDY_MAPPED) != 0)? + ((const pcre_study_data *)extra_data->study_data)->start_bits : NULL; + break; + + case PCRE_INFO_LASTLITERAL: + *((int *)where) = + ((re->options & PCRE_REQCHSET) != 0)? re->req_byte : -1; + break; + + case PCRE_INFO_NAMEENTRYSIZE: + *((int *)where) = re->name_entry_size; + break; + + case PCRE_INFO_NAMECOUNT: + *((int *)where) = re->name_count; + break; + + case PCRE_INFO_NAMETABLE: + *((const uschar **)where) = (const uschar *)re + re->name_table_offset; + break; + + case PCRE_INFO_DEFAULT_TABLES: + *((const uschar **)where) = (const uschar *)(_pcre_default_tables); + break; + + default: return PCRE_ERROR_BADOPTION; + } + +return 0; +} + +/* End of pcre_fullinfo.c */ diff --git a/libs/pcre/pcre_get.c b/libs/pcre/pcre_get.c new file mode 100644 index 0000000000..0588c61a7f --- /dev/null +++ b/libs/pcre/pcre_get.c @@ -0,0 +1,462 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains some convenience functions for extracting substrings +from the subject string after a regex match has succeeded. The original idea +for these functions came from Scott Wimer. */ + + +#include "pcre_internal.h" + + +/************************************************* +* Find number for named string * +*************************************************/ + +/* This function is used by the get_first_set() function below, as well +as being generally available. It assumes that names are unique. + +Arguments: + code the compiled regex + stringname the name whose number is required + +Returns: the number of the named parentheses, or a negative number + (PCRE_ERROR_NOSUBSTRING) if not found +*/ + +int +pcre_get_stringnumber(const pcre *code, const char *stringname) +{ +int rc; +int entrysize; +int top, bot; +uschar *nametable; + +if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0) + return rc; +if (top <= 0) return PCRE_ERROR_NOSUBSTRING; + +if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0) + return rc; +if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0) + return rc; + +bot = 0; +while (top > bot) + { + int mid = (top + bot) / 2; + uschar *entry = nametable + entrysize*mid; + int c = strcmp(stringname, (char *)(entry + 2)); + if (c == 0) return (entry[0] << 8) + entry[1]; + if (c > 0) bot = mid + 1; else top = mid; + } + +return PCRE_ERROR_NOSUBSTRING; +} + + + +/************************************************* +* Find (multiple) entries for named string * +*************************************************/ + +/* This is used by the get_first_set() function below, as well as being +generally available. It is used when duplicated names are permitted. + +Arguments: + code the compiled regex + stringname the name whose entries required + firstptr where to put the pointer to the first entry + lastptr where to put the pointer to the last entry + +Returns: the length of each entry, or a negative number + (PCRE_ERROR_NOSUBSTRING) if not found +*/ + +int +pcre_get_stringtable_entries(const pcre *code, const char *stringname, + char **firstptr, char **lastptr) +{ +int rc; +int entrysize; +int top, bot; +uschar *nametable, *lastentry; + +if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0) + return rc; +if (top <= 0) return PCRE_ERROR_NOSUBSTRING; + +if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0) + return rc; +if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0) + return rc; + +lastentry = nametable + entrysize * (top - 1); +bot = 0; +while (top > bot) + { + int mid = (top + bot) / 2; + uschar *entry = nametable + entrysize*mid; + int c = strcmp(stringname, (char *)(entry + 2)); + if (c == 0) + { + uschar *first = entry; + uschar *last = entry; + while (first > nametable) + { + if (strcmp(stringname, (char *)(first - entrysize + 2)) != 0) break; + first -= entrysize; + } + while (last < lastentry) + { + if (strcmp(stringname, (char *)(last + entrysize + 2)) != 0) break; + last += entrysize; + } + *firstptr = (char *)first; + *lastptr = (char *)last; + return entrysize; + } + if (c > 0) bot = mid + 1; else top = mid; + } + +return PCRE_ERROR_NOSUBSTRING; +} + + + +/************************************************* +* Find first set of multiple named strings * +*************************************************/ + +/* This function allows for duplicate names in the table of named substrings. +It returns the number of the first one that was set in a pattern match. + +Arguments: + code the compiled regex + stringname the name of the capturing substring + ovector the vector of matched substrings + +Returns: the number of the first that is set, + or the number of the last one if none are set, + or a negative number on error +*/ + +static int +get_first_set(const pcre *code, const char *stringname, int *ovector) +{ +const real_pcre *re = (const real_pcre *)code; +int entrysize; +char *first, *last; +uschar *entry; +if ((re->options & (PCRE_DUPNAMES | PCRE_JCHANGED)) == 0) + return pcre_get_stringnumber(code, stringname); +entrysize = pcre_get_stringtable_entries(code, stringname, &first, &last); +if (entrysize <= 0) return entrysize; +for (entry = (uschar *)first; entry <= (uschar *)last; entry += entrysize) + { + int n = (entry[0] << 8) + entry[1]; + if (ovector[n*2] >= 0) return n; + } +return (first[0] << 8) + first[1]; +} + + + + +/************************************************* +* Copy captured string to given buffer * +*************************************************/ + +/* This function copies a single captured substring into a given buffer. +Note that we use memcpy() rather than strncpy() in case there are binary zeros +in the string. + +Arguments: + subject the subject string that was matched + ovector pointer to the offsets table + stringcount the number of substrings that were captured + (i.e. the yield of the pcre_exec call, unless + that was zero, in which case it should be 1/3 + of the offset table size) + stringnumber the number of the required substring + buffer where to put the substring + size the size of the buffer + +Returns: if successful: + the length of the copied string, not including the zero + that is put on the end; can be zero + if not successful: + PCRE_ERROR_NOMEMORY (-6) buffer too small + PCRE_ERROR_NOSUBSTRING (-7) no such captured substring +*/ + +int +pcre_copy_substring(const char *subject, int *ovector, int stringcount, + int stringnumber, char *buffer, int size) +{ +int yield; +if (stringnumber < 0 || stringnumber >= stringcount) + return PCRE_ERROR_NOSUBSTRING; +stringnumber *= 2; +yield = ovector[stringnumber+1] - ovector[stringnumber]; +if (size < yield + 1) return PCRE_ERROR_NOMEMORY; +memcpy(buffer, subject + ovector[stringnumber], yield); +buffer[yield] = 0; +return yield; +} + + + +/************************************************* +* Copy named captured string to given buffer * +*************************************************/ + +/* This function copies a single captured substring into a given buffer, +identifying it by name. If the regex permits duplicate names, the first +substring that is set is chosen. + +Arguments: + code the compiled regex + subject the subject string that was matched + ovector pointer to the offsets table + stringcount the number of substrings that were captured + (i.e. the yield of the pcre_exec call, unless + that was zero, in which case it should be 1/3 + of the offset table size) + stringname the name of the required substring + buffer where to put the substring + size the size of the buffer + +Returns: if successful: + the length of the copied string, not including the zero + that is put on the end; can be zero + if not successful: + PCRE_ERROR_NOMEMORY (-6) buffer too small + PCRE_ERROR_NOSUBSTRING (-7) no such captured substring +*/ + +int +pcre_copy_named_substring(const pcre *code, const char *subject, int *ovector, + int stringcount, const char *stringname, char *buffer, int size) +{ +int n = get_first_set(code, stringname, ovector); +if (n <= 0) return n; +return pcre_copy_substring(subject, ovector, stringcount, n, buffer, size); +} + + + +/************************************************* +* Copy all captured strings to new store * +*************************************************/ + +/* This function gets one chunk of store and builds a list of pointers and all +of the captured substrings in it. A NULL pointer is put on the end of the list. + +Arguments: + subject the subject string that was matched + ovector pointer to the offsets table + stringcount the number of substrings that were captured + (i.e. the yield of the pcre_exec call, unless + that was zero, in which case it should be 1/3 + of the offset table size) + listptr set to point to the list of pointers + +Returns: if successful: 0 + if not successful: + PCRE_ERROR_NOMEMORY (-6) failed to get store +*/ + +int +pcre_get_substring_list(const char *subject, int *ovector, int stringcount, + const char ***listptr) +{ +int i; +int size = sizeof(char *); +int double_count = stringcount * 2; +char **stringlist; +char *p; + +for (i = 0; i < double_count; i += 2) + size += sizeof(char *) + ovector[i+1] - ovector[i] + 1; + +stringlist = (char **)(pcre_malloc)(size); +if (stringlist == NULL) return PCRE_ERROR_NOMEMORY; + +*listptr = (const char **)stringlist; +p = (char *)(stringlist + stringcount + 1); + +for (i = 0; i < double_count; i += 2) + { + int len = ovector[i+1] - ovector[i]; + memcpy(p, subject + ovector[i], len); + *stringlist++ = p; + p += len; + *p++ = 0; + } + +*stringlist = NULL; +return 0; +} + + + +/************************************************* +* Free store obtained by get_substring_list * +*************************************************/ + +/* This function exists for the benefit of people calling PCRE from non-C +programs that can call its functions, but not free() or (pcre_free)() directly. + +Argument: the result of a previous pcre_get_substring_list() +Returns: nothing +*/ + +void +pcre_free_substring_list(const char **pointer) +{ +(pcre_free)((void *)pointer); +} + + + +/************************************************* +* Copy captured string to new store * +*************************************************/ + +/* This function copies a single captured substring into a piece of new +store + +Arguments: + subject the subject string that was matched + ovector pointer to the offsets table + stringcount the number of substrings that were captured + (i.e. the yield of the pcre_exec call, unless + that was zero, in which case it should be 1/3 + of the offset table size) + stringnumber the number of the required substring + stringptr where to put a pointer to the substring + +Returns: if successful: + the length of the string, not including the zero that + is put on the end; can be zero + if not successful: + PCRE_ERROR_NOMEMORY (-6) failed to get store + PCRE_ERROR_NOSUBSTRING (-7) substring not present +*/ + +int +pcre_get_substring(const char *subject, int *ovector, int stringcount, + int stringnumber, const char **stringptr) +{ +int yield; +char *substring; +if (stringnumber < 0 || stringnumber >= stringcount) + return PCRE_ERROR_NOSUBSTRING; +stringnumber *= 2; +yield = ovector[stringnumber+1] - ovector[stringnumber]; +substring = (char *)(pcre_malloc)(yield + 1); +if (substring == NULL) return PCRE_ERROR_NOMEMORY; +memcpy(substring, subject + ovector[stringnumber], yield); +substring[yield] = 0; +*stringptr = substring; +return yield; +} + + + +/************************************************* +* Copy named captured string to new store * +*************************************************/ + +/* This function copies a single captured substring, identified by name, into +new store. If the regex permits duplicate names, the first substring that is +set is chosen. + +Arguments: + code the compiled regex + subject the subject string that was matched + ovector pointer to the offsets table + stringcount the number of substrings that were captured + (i.e. the yield of the pcre_exec call, unless + that was zero, in which case it should be 1/3 + of the offset table size) + stringname the name of the required substring + stringptr where to put the pointer + +Returns: if successful: + the length of the copied string, not including the zero + that is put on the end; can be zero + if not successful: + PCRE_ERROR_NOMEMORY (-6) couldn't get memory + PCRE_ERROR_NOSUBSTRING (-7) no such captured substring +*/ + +int +pcre_get_named_substring(const pcre *code, const char *subject, int *ovector, + int stringcount, const char *stringname, const char **stringptr) +{ +int n = get_first_set(code, stringname, ovector); +if (n <= 0) return n; +return pcre_get_substring(subject, ovector, stringcount, n, stringptr); + +} + + + + +/************************************************* +* Free store obtained by get_substring * +*************************************************/ + +/* This function exists for the benefit of people calling PCRE from non-C +programs that can call its functions, but not free() or (pcre_free)() directly. + +Argument: the result of a previous pcre_get_substring() +Returns: nothing +*/ + +void +pcre_free_substring(const char *pointer) +{ +(pcre_free)((void *)pointer); +} + +/* End of pcre_get.c */ diff --git a/libs/pcre/pcre_globals.c b/libs/pcre/pcre_globals.c new file mode 100644 index 0000000000..f829acfb1b --- /dev/null +++ b/libs/pcre/pcre_globals.c @@ -0,0 +1,69 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains global variables that are exported by the PCRE library. +PCRE is thread-clean and doesn't use any global variables in the normal sense. +However, it calls memory allocation and freeing functions via the four +indirections below, and it can optionally do callouts, using the fifth +indirection. These values can be changed by the caller, but are shared between +all threads. However, when compiling for Virtual Pascal, things are done +differently, and global variables are not used (see pcre.in). */ + + +#include "pcre_internal.h" + + +#ifndef VPCOMPAT +#ifdef __cplusplus +extern "C" void *(*pcre_malloc)(size_t) = malloc; +extern "C" void (*pcre_free)(void *) = free; +extern "C" void *(*pcre_stack_malloc)(size_t) = malloc; +extern "C" void (*pcre_stack_free)(void *) = free; +extern "C" int (*pcre_callout)(pcre_callout_block *) = NULL; +#else +void *(*pcre_malloc)(size_t) = malloc; +void (*pcre_free)(void *) = free; +void *(*pcre_stack_malloc)(size_t) = malloc; +void (*pcre_stack_free)(void *) = free; +int (*pcre_callout)(pcre_callout_block *) = NULL; +#endif +#endif + +/* End of pcre_globals.c */ diff --git a/libs/pcre/pcre_info.c b/libs/pcre/pcre_info.c new file mode 100644 index 0000000000..b318b93eaa --- /dev/null +++ b/libs/pcre/pcre_info.c @@ -0,0 +1,89 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains the external function pcre_info(), which gives some +information about a compiled pattern. However, use of this function is now +deprecated, as it has been superseded by pcre_fullinfo(). */ + + +#include "pcre_internal.h" + + +/************************************************* +* (Obsolete) Return info about compiled pattern * +*************************************************/ + +/* This is the original "info" function. It picks potentially useful data out +of the private structure, but its interface was too rigid. It remains for +backwards compatibility. The public options are passed back in an int - though +the re->options field has been expanded to a long int, all the public options +at the low end of it, and so even on 16-bit systems this will still be OK. +Therefore, I haven't changed the API for pcre_info(). + +Arguments: + argument_re points to compiled code + optptr where to pass back the options + first_byte where to pass back the first character, + or -1 if multiline and all branches start ^, + or -2 otherwise + +Returns: number of capturing subpatterns + or negative values on error +*/ + +PCRE_DATA_SCOPE int +pcre_info(const pcre *argument_re, int *optptr, int *first_byte) +{ +real_pcre internal_re; +const real_pcre *re = (const real_pcre *)argument_re; +if (re == NULL) return PCRE_ERROR_NULL; +if (re->magic_number != MAGIC_NUMBER) + { + re = _pcre_try_flipped(re, &internal_re, NULL, NULL); + if (re == NULL) return PCRE_ERROR_BADMAGIC; + } +if (optptr != NULL) *optptr = (int)(re->options & PUBLIC_OPTIONS); +if (first_byte != NULL) + *first_byte = ((re->options & PCRE_FIRSTSET) != 0)? re->first_byte : + ((re->options & PCRE_STARTLINE) != 0)? -1 : -2; +return re->top_bracket; +} + +/* End of pcre_info.c */ diff --git a/libs/pcre/pcre_internal.h b/libs/pcre/pcre_internal.h new file mode 100644 index 0000000000..952598e0c2 --- /dev/null +++ b/libs/pcre/pcre_internal.h @@ -0,0 +1,950 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* This header contains definitions that are shared between the different +modules, but which are not relevant to the exported API. This includes some +functions whose names all begin with "_pcre_". */ + +#ifndef PCRE_INTERNAL_H +#define PCRE_INTERNAL_H + +/* Define DEBUG to get debugging output on stdout. */ + +#if 0 +#define DEBUG +#endif + +/* Use a macro for debugging printing, 'cause that eliminates the use of #ifdef +inline, and there are *still* stupid compilers about that don't like indented +pre-processor statements, or at least there were when I first wrote this. After +all, it had only been about 10 years then... */ + +#ifdef DEBUG +#define DPRINTF(p) printf p +#else +#define DPRINTF(p) /*nothing*/ +#endif + + +/* Get the definitions provided by running "configure" */ + +#include "config.h" + +/* Standard C headers plus the external interface definition. The only time +setjmp and stdarg are used is when NO_RECURSE is set. */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#ifndef PCRE_SPY +#define PCRE_DEFINITION /* Win32 __declspec(export) trigger for .dll */ +#endif + +/* We need to have types that specify unsigned 16-bit and 32-bit integers. We +cannot determine these outside the compilation (e.g. by running a program as +part of "configure") because PCRE is often cross-compiled for use on other +systems. Instead we make use of the maximum sizes that are available at +preprocessor time in standard C environments. */ + +#if USHRT_MAX == 65535 + typedef unsigned short pcre_uint16; +#elif UINT_MAX == 65535 + typedef unsigned int pcre_uint16; +#else + #error Cannot determine a type for 16-bit unsigned integers +#endif + +#if UINT_MAX == 4294967295 + typedef unsigned int pcre_uint32; +#elif ULONG_MAX == 4294967295 + typedef unsigned long int pcre_uint32; +#else + #error Cannot determine a type for 32-bit unsigned integers +#endif + +/* All character handling must be done as unsigned characters. Otherwise there +are problems with top-bit-set characters and functions such as isspace(). +However, we leave the interface to the outside world as char *, because that +should make things easier for callers. We define a short type for unsigned char +to save lots of typing. I tried "uchar", but it causes problems on Digital +Unix, where it is defined in sys/types, so use "uschar" instead. */ + +typedef unsigned char uschar; + +/* PCRE is able to support 3 different kinds of newline (CR, LF, CRLF). The +following macro is used to package up testing for newlines. NLBLOCK is defined +in the various modules to indicate in which datablock the parameters exist. */ + +#define IS_NEWLINE(p) \ + ((p)[0] == NLBLOCK->nl[0] && \ + (NLBLOCK->nllen == 1 || (p)[1] == NLBLOCK->nl[1])) + +/* When PCRE is compiled as a C++ library, the subject pointer can be replaced +with a custom type. This makes it possible, for example, to allow pcre_exec() +to process subject strings that are discontinuous by using a smart pointer +class. It must always be possible to inspect all of the subject string in +pcre_exec() because of the way it backtracks. Two macros are required in the +normal case, for sign-unspecified and unsigned char pointers. The former is +used for the external interface and appears in pcre.h, which is why its name +must begin with PCRE_. */ + +#ifdef CUSTOM_SUBJECT_PTR +#define PCRE_SPTR CUSTOM_SUBJECT_PTR +#define USPTR CUSTOM_SUBJECT_PTR +#else +#define PCRE_SPTR const char * +#define USPTR const unsigned char * +#endif + +/* Include the public PCRE header and the definitions of UCP character property +values. */ + +#include "pcre.h" +#include "ucp.h" + +/* When compiling for use with the Virtual Pascal compiler, these functions +need to have their names changed. PCRE must be compiled with the -DVPCOMPAT +option on the command line. */ + +#ifdef VPCOMPAT +#define strncmp(s1,s2,m) _strncmp(s1,s2,m) +#define memcpy(d,s,n) _memcpy(d,s,n) +#define memmove(d,s,n) _memmove(d,s,n) +#define memset(s,c,n) _memset(s,c,n) +#else /* VPCOMPAT */ + +/* To cope with SunOS4 and other systems that lack memmove() but have bcopy(), +define a macro for memmove() if HAVE_MEMMOVE is false, provided that HAVE_BCOPY +is set. Otherwise, include an emulating function for those systems that have +neither (there some non-Unix environments where this is the case). This assumes +that all calls to memmove are moving strings upwards in store, which is the +case in PCRE. */ + +#if ! HAVE_MEMMOVE +#undef memmove /* some systems may have a macro */ +#if HAVE_BCOPY +#define memmove(a, b, c) bcopy(b, a, c) +#else /* HAVE_BCOPY */ +static void * +pcre_memmove(unsigned char *dest, const unsigned char *src, size_t n) +{ +size_t i; +dest += n; +src += n; +for (i = 0; i < n; ++i) *(--dest) = *(--src); +return dest; +} +#define memmove(a, b, c) pcre_memmove(a, b, c) +#endif /* not HAVE_BCOPY */ +#endif /* not HAVE_MEMMOVE */ +#endif /* not VPCOMPAT */ + + +/* PCRE keeps offsets in its compiled code as 2-byte quantities (always stored +in big-endian order) by default. These are used, for example, to link from the +start of a subpattern to its alternatives and its end. The use of 2 bytes per +offset limits the size of the compiled regex to around 64K, which is big enough +for almost everybody. However, I received a request for an even bigger limit. +For this reason, and also to make the code easier to maintain, the storing and +loading of offsets from the byte string is now handled by the macros that are +defined here. + +The macros are controlled by the value of LINK_SIZE. This defaults to 2 in +the config.h file, but can be overridden by using -D on the command line. This +is automated on Unix systems via the "configure" command. */ + +#if LINK_SIZE == 2 + +#define PUT(a,n,d) \ + (a[n] = (d) >> 8), \ + (a[(n)+1] = (d) & 255) + +#define GET(a,n) \ + (((a)[n] << 8) | (a)[(n)+1]) + +#define MAX_PATTERN_SIZE (1 << 16) + + +#elif LINK_SIZE == 3 + +#define PUT(a,n,d) \ + (a[n] = (d) >> 16), \ + (a[(n)+1] = (d) >> 8), \ + (a[(n)+2] = (d) & 255) + +#define GET(a,n) \ + (((a)[n] << 16) | ((a)[(n)+1] << 8) | (a)[(n)+2]) + +#define MAX_PATTERN_SIZE (1 << 24) + + +#elif LINK_SIZE == 4 + +#define PUT(a,n,d) \ + (a[n] = (d) >> 24), \ + (a[(n)+1] = (d) >> 16), \ + (a[(n)+2] = (d) >> 8), \ + (a[(n)+3] = (d) & 255) + +#define GET(a,n) \ + (((a)[n] << 24) | ((a)[(n)+1] << 16) | ((a)[(n)+2] << 8) | (a)[(n)+3]) + +#define MAX_PATTERN_SIZE (1 << 30) /* Keep it positive */ + + +#else +#error LINK_SIZE must be either 2, 3, or 4 +#endif + + +/* Convenience macro defined in terms of the others */ + +#define PUTINC(a,n,d) PUT(a,n,d), a += LINK_SIZE + + +/* PCRE uses some other 2-byte quantities that do not change when the size of +offsets changes. There are used for repeat counts and for other things such as +capturing parenthesis numbers in back references. */ + +#define PUT2(a,n,d) \ + a[n] = (d) >> 8; \ + a[(n)+1] = (d) & 255 + +#define GET2(a,n) \ + (((a)[n] << 8) | (a)[(n)+1]) + +#define PUT2INC(a,n,d) PUT2(a,n,d), a += 2 + + +/* When UTF-8 encoding is being used, a character is no longer just a single +byte. The macros for character handling generate simple sequences when used in +byte-mode, and more complicated ones for UTF-8 characters. */ + +#ifndef SUPPORT_UTF8 +#define GETCHAR(c, eptr) c = *eptr; +#define GETCHARTEST(c, eptr) c = *eptr; +#define GETCHARINC(c, eptr) c = *eptr++; +#define GETCHARINCTEST(c, eptr) c = *eptr++; +#define GETCHARLEN(c, eptr, len) c = *eptr; +#define BACKCHAR(eptr) + +#else /* SUPPORT_UTF8 */ + +/* Get the next UTF-8 character, not advancing the pointer. This is called when +we know we are in UTF-8 mode. */ + +#define GETCHAR(c, eptr) \ + c = *eptr; \ + if ((c & 0xc0) == 0xc0) \ + { \ + int gcii; \ + int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ + int gcss = 6*gcaa; \ + c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ + for (gcii = 1; gcii <= gcaa; gcii++) \ + { \ + gcss -= 6; \ + c |= (eptr[gcii] & 0x3f) << gcss; \ + } \ + } + +/* Get the next UTF-8 character, testing for UTF-8 mode, and not advancing the +pointer. */ + +#define GETCHARTEST(c, eptr) \ + c = *eptr; \ + if (utf8 && (c & 0xc0) == 0xc0) \ + { \ + int gcii; \ + int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ + int gcss = 6*gcaa; \ + c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ + for (gcii = 1; gcii <= gcaa; gcii++) \ + { \ + gcss -= 6; \ + c |= (eptr[gcii] & 0x3f) << gcss; \ + } \ + } + +/* Get the next UTF-8 character, advancing the pointer. This is called when we +know we are in UTF-8 mode. */ + +#define GETCHARINC(c, eptr) \ + c = *eptr++; \ + if ((c & 0xc0) == 0xc0) \ + { \ + int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ + int gcss = 6*gcaa; \ + c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ + while (gcaa-- > 0) \ + { \ + gcss -= 6; \ + c |= (*eptr++ & 0x3f) << gcss; \ + } \ + } + +/* Get the next character, testing for UTF-8 mode, and advancing the pointer */ + +#define GETCHARINCTEST(c, eptr) \ + c = *eptr++; \ + if (utf8 && (c & 0xc0) == 0xc0) \ + { \ + int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ + int gcss = 6*gcaa; \ + c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ + while (gcaa-- > 0) \ + { \ + gcss -= 6; \ + c |= (*eptr++ & 0x3f) << gcss; \ + } \ + } + +/* Get the next UTF-8 character, not advancing the pointer, incrementing length +if there are extra bytes. This is called when we know we are in UTF-8 mode. */ + +#define GETCHARLEN(c, eptr, len) \ + c = *eptr; \ + if ((c & 0xc0) == 0xc0) \ + { \ + int gcii; \ + int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ + int gcss = 6*gcaa; \ + c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ + for (gcii = 1; gcii <= gcaa; gcii++) \ + { \ + gcss -= 6; \ + c |= (eptr[gcii] & 0x3f) << gcss; \ + } \ + len += gcaa; \ + } + +/* If the pointer is not at the start of a character, move it back until +it is. Called only in UTF-8 mode. */ + +#define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr--; + +#endif + + +/* In case there is no definition of offsetof() provided - though any proper +Standard C system should have one. */ + +#ifndef offsetof +#define offsetof(p_type,field) ((size_t)&(((p_type *)0)->field)) +#endif + + +/* These are the public options that can change during matching. */ + +#define PCRE_IMS (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL) + +/* Private options flags start at the most significant end of the four bytes. +The public options defined in pcre.h start at the least significant end. Make +sure they don't overlap! The bits are getting a bit scarce now -- when we run +out, there is a dummy word in the structure that could be used for the private +bits. */ + +#define PCRE_NOPARTIAL 0x80000000 /* can't use partial with this regex */ +#define PCRE_FIRSTSET 0x40000000 /* first_byte is set */ +#define PCRE_REQCHSET 0x20000000 /* req_byte is set */ +#define PCRE_STARTLINE 0x10000000 /* start after \n for multiline */ +#define PCRE_JCHANGED 0x08000000 /* j option changes within regex */ + +/* Options for the "extra" block produced by pcre_study(). */ + +#define PCRE_STUDY_MAPPED 0x01 /* a map of starting chars exists */ + +/* Masks for identifying the public options that are permitted at compile +time, run time, or study time, respectively. */ + +#define PUBLIC_OPTIONS \ + (PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \ + PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8| \ + PCRE_NO_AUTO_CAPTURE|PCRE_NO_UTF8_CHECK|PCRE_AUTO_CALLOUT|PCRE_FIRSTLINE| \ + PCRE_DUPNAMES|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF) + +#define PUBLIC_EXEC_OPTIONS \ + (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \ + PCRE_PARTIAL|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF) + +#define PUBLIC_DFA_EXEC_OPTIONS \ + (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \ + PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART|PCRE_NEWLINE_CR| \ + PCRE_NEWLINE_LF) + +#define PUBLIC_STUDY_OPTIONS 0 /* None defined */ + +/* Magic number to provide a small check against being handed junk. Also used +to detect whether a pattern was compiled on a host of different endianness. */ + +#define MAGIC_NUMBER 0x50435245UL /* 'PCRE' */ + +/* Negative values for the firstchar and reqchar variables */ + +#define REQ_UNSET (-2) +#define REQ_NONE (-1) + +/* The maximum remaining length of subject we are prepared to search for a +req_byte match. */ + +#define REQ_BYTE_MAX 1000 + +/* Flags added to firstbyte or reqbyte; a "non-literal" item is either a +variable-length repeat, or a anything other than literal characters. */ + +#define REQ_CASELESS 0x0100 /* indicates caselessness */ +#define REQ_VARY 0x0200 /* reqbyte followed non-literal item */ + +/* Miscellaneous definitions */ + +typedef int BOOL; + +#define FALSE 0 +#define TRUE 1 + +/* Escape items that are just an encoding of a particular data value. Note that +ESC_n is defined as yet another macro, which is set in config.h to either \n +(the default) or \r (which some people want). */ + +#ifndef ESC_e +#define ESC_e 27 +#endif + +#ifndef ESC_f +#define ESC_f '\f' +#endif + +#ifndef ESC_n +#define ESC_n NEWLINE +#endif + +#ifndef ESC_r +#define ESC_r '\r' +#endif + +/* We can't officially use ESC_t because it is a POSIX reserved identifier +(presumably because of all the others like size_t). */ + +#ifndef ESC_tee +#define ESC_tee '\t' +#endif + +/* Codes for different types of Unicode property */ + +#define PT_ANY 0 /* Any property - matches all chars */ +#define PT_LAMP 1 /* L& - the union of Lu, Ll, Lt */ +#define PT_GC 2 /* General characteristic (e.g. L) */ +#define PT_PC 3 /* Particular characteristic (e.g. Lu) */ +#define PT_SC 4 /* Script (e.g. Han) */ + +/* Flag bits and data types for the extended class (OP_XCLASS) for classes that +contain UTF-8 characters with values greater than 255. */ + +#define XCL_NOT 0x01 /* Flag: this is a negative class */ +#define XCL_MAP 0x02 /* Flag: a 32-byte map is present */ + +#define XCL_END 0 /* Marks end of individual items */ +#define XCL_SINGLE 1 /* Single item (one multibyte char) follows */ +#define XCL_RANGE 2 /* A range (two multibyte chars) follows */ +#define XCL_PROP 3 /* Unicode property (2-byte property code follows) */ +#define XCL_NOTPROP 4 /* Unicode inverted property (ditto) */ + +/* These are escaped items that aren't just an encoding of a particular data +value such as \n. They must have non-zero values, as check_escape() returns +their negation. Also, they must appear in the same order as in the opcode +definitions below, up to ESC_z. There's a dummy for OP_ANY because it +corresponds to "." rather than an escape sequence. The final one must be +ESC_REF as subsequent values are used for \1, \2, \3, etc. There is are two +tests in the code for an escape greater than ESC_b and less than ESC_Z to +detect the types that may be repeated. These are the types that consume +characters. If any new escapes are put in between that don't consume a +character, that code will have to change. */ + +enum { ESC_A = 1, ESC_G, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, ESC_W, + ESC_w, ESC_dum1, ESC_C, ESC_P, ESC_p, ESC_X, ESC_Z, ESC_z, ESC_E, + ESC_Q, ESC_REF }; + +/* Opcode table: OP_BRA must be last, as all values >= it are used for brackets +that extract substrings. Starting from 1 (i.e. after OP_END), the values up to +OP_EOD must correspond in order to the list of escapes immediately above. +Note that whenever this list is updated, the two macro definitions that follow +must also be updated to match. */ + +enum { + OP_END, /* 0 End of pattern */ + + /* Values corresponding to backslashed metacharacters */ + + OP_SOD, /* 1 Start of data: \A */ + OP_SOM, /* 2 Start of match (subject + offset): \G */ + OP_NOT_WORD_BOUNDARY, /* 3 \B */ + OP_WORD_BOUNDARY, /* 4 \b */ + OP_NOT_DIGIT, /* 5 \D */ + OP_DIGIT, /* 6 \d */ + OP_NOT_WHITESPACE, /* 7 \S */ + OP_WHITESPACE, /* 8 \s */ + OP_NOT_WORDCHAR, /* 9 \W */ + OP_WORDCHAR, /* 10 \w */ + OP_ANY, /* 11 Match any character */ + OP_ANYBYTE, /* 12 Match any byte (\C); different to OP_ANY for UTF-8 */ + OP_NOTPROP, /* 13 \P (not Unicode property) */ + OP_PROP, /* 14 \p (Unicode property) */ + OP_EXTUNI, /* 15 \X (extended Unicode sequence */ + OP_EODN, /* 16 End of data or \n at end of data: \Z. */ + OP_EOD, /* 17 End of data: \z */ + + OP_OPT, /* 18 Set runtime options */ + OP_CIRC, /* 19 Start of line - varies with multiline switch */ + OP_DOLL, /* 20 End of line - varies with multiline switch */ + OP_CHAR, /* 21 Match one character, casefully */ + OP_CHARNC, /* 22 Match one character, caselessly */ + OP_NOT, /* 23 Match one character, not the following one */ + + OP_STAR, /* 24 The maximizing and minimizing versions of */ + OP_MINSTAR, /* 25 all these opcodes must come in pairs, with */ + OP_PLUS, /* 26 the minimizing one second. */ + OP_MINPLUS, /* 27 This first set applies to single characters */ + OP_QUERY, /* 28 */ + OP_MINQUERY, /* 29 */ + OP_UPTO, /* 30 From 0 to n matches */ + OP_MINUPTO, /* 31 */ + OP_EXACT, /* 32 Exactly n matches */ + + OP_NOTSTAR, /* 33 The maximizing and minimizing versions of */ + OP_NOTMINSTAR, /* 34 all these opcodes must come in pairs, with */ + OP_NOTPLUS, /* 35 the minimizing one second. */ + OP_NOTMINPLUS, /* 36 This set applies to "not" single characters */ + OP_NOTQUERY, /* 37 */ + OP_NOTMINQUERY, /* 38 */ + OP_NOTUPTO, /* 39 From 0 to n matches */ + OP_NOTMINUPTO, /* 40 */ + OP_NOTEXACT, /* 41 Exactly n matches */ + + OP_TYPESTAR, /* 42 The maximizing and minimizing versions of */ + OP_TYPEMINSTAR, /* 43 all these opcodes must come in pairs, with */ + OP_TYPEPLUS, /* 44 the minimizing one second. These codes must */ + OP_TYPEMINPLUS, /* 45 be in exactly the same order as those above. */ + OP_TYPEQUERY, /* 46 This set applies to character types such as \d */ + OP_TYPEMINQUERY, /* 47 */ + OP_TYPEUPTO, /* 48 From 0 to n matches */ + OP_TYPEMINUPTO, /* 49 */ + OP_TYPEEXACT, /* 50 Exactly n matches */ + + OP_CRSTAR, /* 51 The maximizing and minimizing versions of */ + OP_CRMINSTAR, /* 52 all these opcodes must come in pairs, with */ + OP_CRPLUS, /* 53 the minimizing one second. These codes must */ + OP_CRMINPLUS, /* 54 be in exactly the same order as those above. */ + OP_CRQUERY, /* 55 These are for character classes and back refs */ + OP_CRMINQUERY, /* 56 */ + OP_CRRANGE, /* 57 These are different to the three sets above. */ + OP_CRMINRANGE, /* 58 */ + + OP_CLASS, /* 59 Match a character class, chars < 256 only */ + OP_NCLASS, /* 60 Same, but the bitmap was created from a negative + class - the difference is relevant only when a UTF-8 + character > 255 is encountered. */ + + OP_XCLASS, /* 61 Extended class for handling UTF-8 chars within the + class. This does both positive and negative. */ + + OP_REF, /* 62 Match a back reference */ + OP_RECURSE, /* 63 Match a numbered subpattern (possibly recursive) */ + OP_CALLOUT, /* 64 Call out to external function if provided */ + + OP_ALT, /* 65 Start of alternation */ + OP_KET, /* 66 End of group that doesn't have an unbounded repeat */ + OP_KETRMAX, /* 67 These two must remain together and in this */ + OP_KETRMIN, /* 68 order. They are for groups the repeat for ever. */ + + /* The assertions must come before ONCE and COND */ + + OP_ASSERT, /* 69 Positive lookahead */ + OP_ASSERT_NOT, /* 70 Negative lookahead */ + OP_ASSERTBACK, /* 71 Positive lookbehind */ + OP_ASSERTBACK_NOT, /* 72 Negative lookbehind */ + OP_REVERSE, /* 73 Move pointer back - used in lookbehind assertions */ + + /* ONCE and COND must come after the assertions, with ONCE first, as there's + a test for >= ONCE for a subpattern that isn't an assertion. */ + + OP_ONCE, /* 74 Once matched, don't back up into the subpattern */ + OP_COND, /* 75 Conditional group */ + OP_CREF, /* 76 Used to hold an extraction string number (cond ref) */ + + OP_BRAZERO, /* 77 These two must remain together and in this */ + OP_BRAMINZERO, /* 78 order. */ + + OP_BRANUMBER, /* 79 Used for extracting brackets whose number is greater + than can fit into an opcode. */ + + OP_BRA /* 80 This and greater values are used for brackets that + extract substrings up to EXTRACT_BASIC_MAX. After + that, use is made of OP_BRANUMBER. */ +}; + +/* WARNING WARNING WARNING: There is an implicit assumption in pcre.c and +study.c that all opcodes are less than 128 in value. This makes handling UTF-8 +character sequences easier. */ + +/* The highest extraction number before we have to start using additional +bytes. (Originally PCRE didn't have support for extraction counts highter than +this number.) The value is limited by the number of opcodes left after OP_BRA, +i.e. 255 - OP_BRA. We actually set it a bit lower to leave room for additional +opcodes. */ + +#define EXTRACT_BASIC_MAX 100 + + +/* This macro defines textual names for all the opcodes. These are used only +for debugging. The macro is referenced only in pcre_printint.c. */ + +#define OP_NAME_LIST \ + "End", "\\A", "\\G", "\\B", "\\b", "\\D", "\\d", \ + "\\S", "\\s", "\\W", "\\w", "Any", "Anybyte", \ + "notprop", "prop", "extuni", \ + "\\Z", "\\z", \ + "Opt", "^", "$", "char", "charnc", "not", \ + "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ + "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ + "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ + "*", "*?", "+", "+?", "?", "??", "{", "{", \ + "class", "nclass", "xclass", "Ref", "Recurse", "Callout", \ + "Alt", "Ket", "KetRmax", "KetRmin", "Assert", "Assert not", \ + "AssertB", "AssertB not", "Reverse", "Once", "Cond", "Cond ref",\ + "Brazero", "Braminzero", "Branumber", "Bra" + + +/* This macro defines the length of fixed length operations in the compiled +regex. The lengths are used when searching for specific things, and also in the +debugging printing of a compiled regex. We use a macro so that it can be +defined close to the definitions of the opcodes themselves. + +As things have been extended, some of these are no longer fixed lenths, but are +minima instead. For example, the length of a single-character repeat may vary +in UTF-8 mode. The code that uses this table must know about such things. */ + +#define OP_LENGTHS \ + 1, /* End */ \ + 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* \A, \G, \B, \B, \D, \d, \S, \s, \W, \w */ \ + 1, 1, /* Any, Anybyte */ \ + 3, 3, 1, /* NOTPROP, PROP, EXTUNI */ \ + 1, 1, 2, 1, 1, /* \Z, \z, Opt, ^, $ */ \ + 2, /* Char - the minimum length */ \ + 2, /* Charnc - the minimum length */ \ + 2, /* not */ \ + /* Positive single-char repeats ** These are */ \ + 2, 2, 2, 2, 2, 2, /* *, *?, +, +?, ?, ?? ** minima in */ \ + 4, 4, 4, /* upto, minupto, exact ** UTF-8 mode */ \ + /* Negative single-char repeats - only for chars < 256 */ \ + 2, 2, 2, 2, 2, 2, /* NOT *, *?, +, +?, ?, ?? */ \ + 4, 4, 4, /* NOT upto, minupto, exact */ \ + /* Positive type repeats */ \ + 2, 2, 2, 2, 2, 2, /* Type *, *?, +, +?, ?, ?? */ \ + 4, 4, 4, /* Type upto, minupto, exact */ \ + /* Character class & ref repeats */ \ + 1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ \ + 5, 5, /* CRRANGE, CRMINRANGE */ \ + 33, /* CLASS */ \ + 33, /* NCLASS */ \ + 0, /* XCLASS - variable length */ \ + 3, /* REF */ \ + 1+LINK_SIZE, /* RECURSE */ \ + 2+2*LINK_SIZE, /* CALLOUT */ \ + 1+LINK_SIZE, /* Alt */ \ + 1+LINK_SIZE, /* Ket */ \ + 1+LINK_SIZE, /* KetRmax */ \ + 1+LINK_SIZE, /* KetRmin */ \ + 1+LINK_SIZE, /* Assert */ \ + 1+LINK_SIZE, /* Assert not */ \ + 1+LINK_SIZE, /* Assert behind */ \ + 1+LINK_SIZE, /* Assert behind not */ \ + 1+LINK_SIZE, /* Reverse */ \ + 1+LINK_SIZE, /* Once */ \ + 1+LINK_SIZE, /* COND */ \ + 3, /* CREF */ \ + 1, 1, /* BRAZERO, BRAMINZERO */ \ + 3, /* BRANUMBER */ \ + 1+LINK_SIZE /* BRA */ \ + + +/* A magic value for OP_CREF to indicate the "in recursion" condition. */ + +#define CREF_RECURSE 0xffff + +/* Error code numbers. They are given names so that they can more easily be +tracked. */ + +enum { ERR0, ERR1, ERR2, ERR3, ERR4, ERR5, ERR6, ERR7, ERR8, ERR9, + ERR10, ERR11, ERR12, ERR13, ERR14, ERR15, ERR16, ERR17, ERR18, ERR19, + ERR20, ERR21, ERR22, ERR23, ERR24, ERR25, ERR26, ERR27, ERR28, ERR29, + ERR30, ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39, + ERR40, ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47, ERR48, ERR49, + ERR50, ERR51 }; + +/* The real format of the start of the pcre block; the index of names and the +code vector run on as long as necessary after the end. We store an explicit +offset to the name table so that if a regex is compiled on one host, saved, and +then run on another where the size of pointers is different, all might still +be well. For the case of compiled-on-4 and run-on-8, we include an extra +pointer that is always NULL. For future-proofing, a few dummy fields were +originally included - even though you can never get this planning right - but +there is only one left now. + +NOTE NOTE NOTE: +Because people can now save and re-use compiled patterns, any additions to this +structure should be made at the end, and something earlier (e.g. a new +flag in the options or one of the dummy fields) should indicate that the new +fields are present. Currently PCRE always sets the dummy fields to zero. +NOTE NOTE NOTE: +*/ + +typedef struct real_pcre { + pcre_uint32 magic_number; + pcre_uint32 size; /* Total that was malloced */ + pcre_uint32 options; + pcre_uint32 dummy1; /* For future use, maybe */ + + pcre_uint16 top_bracket; + pcre_uint16 top_backref; + pcre_uint16 first_byte; + pcre_uint16 req_byte; + pcre_uint16 name_table_offset; /* Offset to name table that follows */ + pcre_uint16 name_entry_size; /* Size of any name items */ + pcre_uint16 name_count; /* Number of name items */ + pcre_uint16 ref_count; /* Reference count */ + + const unsigned char *tables; /* Pointer to tables or NULL for std */ + const unsigned char *nullpad; /* NULL padding */ +} real_pcre; + +/* The format of the block used to store data from pcre_study(). The same +remark (see NOTE above) about extending this structure applies. */ + +typedef struct pcre_study_data { + pcre_uint32 size; /* Total that was malloced */ + pcre_uint32 options; + uschar start_bits[32]; +} pcre_study_data; + +/* Structure for passing "static" information around between the functions +doing the compiling, so that they are thread-safe. */ + +typedef struct compile_data { + const uschar *lcc; /* Points to lower casing table */ + const uschar *fcc; /* Points to case-flipping table */ + const uschar *cbits; /* Points to character type table */ + const uschar *ctypes; /* Points to table of type maps */ + const uschar *start_code; /* The start of the compiled code */ + const uschar *start_pattern; /* The start of the pattern */ + uschar *name_table; /* The name/number table */ + int names_found; /* Number of entries so far */ + int name_entry_size; /* Size of each entry */ + int top_backref; /* Maximum back reference */ + unsigned int backref_map; /* Bitmap of low back refs */ + int req_varyopt; /* "After variable item" flag for reqbyte */ + BOOL nopartial; /* Set TRUE if partial won't work */ + int nllen; /* 1 or 2 for newline string length */ + uschar nl[4]; /* Newline string */ +} compile_data; + +/* Structure for maintaining a chain of pointers to the currently incomplete +branches, for testing for left recursion. */ + +typedef struct branch_chain { + struct branch_chain *outer; + uschar *current; +} branch_chain; + +/* Structure for items in a linked list that represents an explicit recursive +call within the pattern. */ + +typedef struct recursion_info { + struct recursion_info *prevrec; /* Previous recursion record (or NULL) */ + int group_num; /* Number of group that was called */ + const uschar *after_call; /* "Return value": points after the call in the expr */ + USPTR save_start; /* Old value of md->start_match */ + int *offset_save; /* Pointer to start of saved offsets */ + int saved_max; /* Number of saved offsets */ +} recursion_info; + +/* When compiling in a mode that doesn't use recursive calls to match(), +a structure is used to remember local variables on the heap. It is defined in +pcre_exec.c, close to the match() function, so that it is easy to keep it in +step with any changes of local variable. However, the pointer to the current +frame must be saved in some "static" place over a longjmp(). We declare the +structure here so that we can put a pointer in the match_data structure. NOTE: +This isn't used for a "normal" compilation of pcre. */ + +struct heapframe; + +/* Structure for passing "static" information around between the functions +doing traditional NFA matching, so that they are thread-safe. */ + +typedef struct match_data { + unsigned long int match_call_count; /* As it says */ + unsigned long int match_limit; /* As it says */ + unsigned long int match_limit_recursion; /* As it says */ + int *offset_vector; /* Offset vector */ + int offset_end; /* One past the end */ + int offset_max; /* The maximum usable for return data */ + int nllen; /* 1 or 2 for newline string length */ + uschar nl[4]; /* Newline string */ + const uschar *lcc; /* Points to lower casing table */ + const uschar *ctypes; /* Points to table of type maps */ + BOOL offset_overflow; /* Set if too many extractions */ + BOOL notbol; /* NOTBOL flag */ + BOOL noteol; /* NOTEOL flag */ + BOOL utf8; /* UTF8 flag */ + BOOL endonly; /* Dollar not before final \n */ + BOOL notempty; /* Empty string match not wanted */ + BOOL partial; /* PARTIAL flag */ + BOOL hitend; /* Hit the end of the subject at some point */ + const uschar *start_code; /* For use when recursing */ + USPTR start_subject; /* Start of the subject string */ + USPTR end_subject; /* End of the subject string */ + USPTR start_match; /* Start of this match attempt */ + USPTR end_match_ptr; /* Subject position at end match */ + int end_offset_top; /* Highwater mark at end of match */ + int capture_last; /* Most recent capture number */ + int start_offset; /* The start offset value */ + recursion_info *recursive; /* Linked list of recursion data */ + void *callout_data; /* To pass back to callouts */ + struct heapframe *thisframe; /* Used only when compiling for no recursion */ +} match_data; + +/* A similar structure is used for the same purpose by the DFA matching +functions. */ + +typedef struct dfa_match_data { + const uschar *start_code; /* Start of the compiled pattern */ + const uschar *start_subject; /* Start of the subject string */ + const uschar *end_subject; /* End of subject string */ + const uschar *tables; /* Character tables */ + int moptions; /* Match options */ + int poptions; /* Pattern options */ + int nllen; /* 1 or 2 for newline string length */ + uschar nl[4]; /* Newline string */ + void *callout_data; /* To pass back to callouts */ +} dfa_match_data; + +/* Bit definitions for entries in the pcre_ctypes table. */ + +#define ctype_space 0x01 +#define ctype_letter 0x02 +#define ctype_digit 0x04 +#define ctype_xdigit 0x08 +#define ctype_word 0x10 /* alphameric or '_' */ +#define ctype_meta 0x80 /* regexp meta char or zero (end pattern) */ + +/* Offsets for the bitmap tables in pcre_cbits. Each table contains a set +of bits for a class map. Some classes are built by combining these tables. */ + +#define cbit_space 0 /* [:space:] or \s */ +#define cbit_xdigit 32 /* [:xdigit:] */ +#define cbit_digit 64 /* [:digit:] or \d */ +#define cbit_upper 96 /* [:upper:] */ +#define cbit_lower 128 /* [:lower:] */ +#define cbit_word 160 /* [:word:] or \w */ +#define cbit_graph 192 /* [:graph:] */ +#define cbit_print 224 /* [:print:] */ +#define cbit_punct 256 /* [:punct:] */ +#define cbit_cntrl 288 /* [:cntrl:] */ +#define cbit_length 320 /* Length of the cbits table */ + +/* Offsets of the various tables from the base tables pointer, and +total length. */ + +#define lcc_offset 0 +#define fcc_offset 256 +#define cbits_offset 512 +#define ctypes_offset (cbits_offset + cbit_length) +#define tables_length (ctypes_offset + 256) + +/* Layout of the UCP type table that translates property names into types and +codes. */ + +typedef struct { + const char *name; + pcre_uint16 type; + pcre_uint16 value; +} ucp_type_table; + + +/* Internal shared data tables. These are tables that are used by more than one +of the exported public functions. They have to be "external" in the C sense, +but are not part of the PCRE public API. The data for these tables is in the +pcre_tables.c module. */ + +extern const int _pcre_utf8_table1[]; +extern const int _pcre_utf8_table2[]; +extern const int _pcre_utf8_table3[]; +extern const uschar _pcre_utf8_table4[]; + +extern const int _pcre_utf8_table1_size; + +extern const ucp_type_table _pcre_utt[]; +extern const int _pcre_utt_size; + +extern const uschar _pcre_default_tables[]; + +extern const uschar _pcre_OP_lengths[]; + + +/* Internal shared functions. These are functions that are used by more than +one of the exported public functions. They have to be "external" in the C +sense, but are not part of the PCRE public API. */ + +extern int _pcre_ord2utf8(int, uschar *); +extern real_pcre * _pcre_try_flipped(const real_pcre *, real_pcre *, + const pcre_study_data *, pcre_study_data *); +extern int _pcre_ucp_findprop(const unsigned int, int *, int *); +extern int _pcre_ucp_othercase(const int); +extern int _pcre_valid_utf8(const uschar *, int); +extern BOOL _pcre_xclass(int, const uschar *); + +#endif + +/* End of pcre_internal.h */ diff --git a/libs/pcre/pcre_maketables.c b/libs/pcre/pcre_maketables.c new file mode 100644 index 0000000000..afe63d1b18 --- /dev/null +++ b/libs/pcre/pcre_maketables.c @@ -0,0 +1,140 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains the external function pcre_maketables(), which builds +character tables for PCRE in the current locale. The file is compiled on its +own as part of the PCRE library. However, it is also included in the +compilation of dftables.c, in which case the macro DFTABLES is defined. */ + + +#ifndef DFTABLES +#include "pcre_internal.h" +#endif + + +/************************************************* +* Create PCRE character tables * +*************************************************/ + +/* This function builds a set of character tables for use by PCRE and returns +a pointer to them. They are build using the ctype functions, and consequently +their contents will depend upon the current locale setting. When compiled as +part of the library, the store is obtained via pcre_malloc(), but when compiled +inside dftables, use malloc(). + +Arguments: none +Returns: pointer to the contiguous block of data +*/ + +const unsigned char * +pcre_maketables(void) +{ +unsigned char *yield, *p; +int i; + +#ifndef DFTABLES +yield = (unsigned char*)(pcre_malloc)(tables_length); +#else +yield = (unsigned char*)malloc(tables_length); +#endif + +if (yield == NULL) return NULL; +p = yield; + +/* First comes the lower casing table */ + +for (i = 0; i < 256; i++) *p++ = tolower(i); + +/* Next the case-flipping table */ + +for (i = 0; i < 256; i++) *p++ = islower(i)? toupper(i) : tolower(i); + +/* Then the character class tables. Don't try to be clever and save effort on +exclusive ones - in some locales things may be different. Note that the table +for "space" includes everything "isspace" gives, including VT in the default +locale. This makes it work for the POSIX class [:space:]. Note also that it is +possible for a character to be alnum or alpha without being lower or upper, +such as "male and female ordinals" (\xAA and \xBA) in the fr_FR locale (at +least under Debian Linux's locales as of 12/2005). So we must test for alnum +specially. */ + +memset(p, 0, cbit_length); +for (i = 0; i < 256; i++) + { + if (isdigit(i)) p[cbit_digit + i/8] |= 1 << (i&7); + if (isupper(i)) p[cbit_upper + i/8] |= 1 << (i&7); + if (islower(i)) p[cbit_lower + i/8] |= 1 << (i&7); + if (isalnum(i)) p[cbit_word + i/8] |= 1 << (i&7); + if (i == '_') p[cbit_word + i/8] |= 1 << (i&7); + if (isspace(i)) p[cbit_space + i/8] |= 1 << (i&7); + if (isxdigit(i))p[cbit_xdigit + i/8] |= 1 << (i&7); + if (isgraph(i)) p[cbit_graph + i/8] |= 1 << (i&7); + if (isprint(i)) p[cbit_print + i/8] |= 1 << (i&7); + if (ispunct(i)) p[cbit_punct + i/8] |= 1 << (i&7); + if (iscntrl(i)) p[cbit_cntrl + i/8] |= 1 << (i&7); + } +p += cbit_length; + +/* Finally, the character type table. In this, we exclude VT from the white +space chars, because Perl doesn't recognize it as such for \s and for comments +within regexes. */ + +for (i = 0; i < 256; i++) + { + int x = 0; + if (i != 0x0b && isspace(i)) x += ctype_space; + if (isalpha(i)) x += ctype_letter; + if (isdigit(i)) x += ctype_digit; + if (isxdigit(i)) x += ctype_xdigit; + if (isalnum(i) || i == '_') x += ctype_word; + + /* Note: strchr includes the terminating zero in the characters it considers. + In this instance, that is ok because we want binary zero to be flagged as a + meta-character, which in this sense is any character that terminates a run + of data characters. */ + + if (strchr("*+?{^.$|()[", i) != 0) x += ctype_meta; + *p++ = x; + } + +return yield; +} + +/* End of pcre_maketables.c */ diff --git a/libs/pcre/pcre_ord2utf8.c b/libs/pcre/pcre_ord2utf8.c new file mode 100644 index 0000000000..fc4d6de812 --- /dev/null +++ b/libs/pcre/pcre_ord2utf8.c @@ -0,0 +1,78 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This file contains a private PCRE function that converts an ordinal +character value into a UTF8 string. */ + + +#include "pcre_internal.h" + + +/************************************************* +* Convert character value to UTF-8 * +*************************************************/ + +/* This function takes an integer value in the range 0 - 0x7fffffff +and encodes it as a UTF-8 character in 0 to 6 bytes. + +Arguments: + cvalue the character value + buffer pointer to buffer for result - at least 6 bytes long + +Returns: number of characters placed in the buffer +*/ + +int +_pcre_ord2utf8(int cvalue, uschar *buffer) +{ +register int i, j; +for (i = 0; i < _pcre_utf8_table1_size; i++) + if (cvalue <= _pcre_utf8_table1[i]) break; +buffer += i; +for (j = i; j > 0; j--) + { + *buffer-- = 0x80 | (cvalue & 0x3f); + cvalue >>= 6; + } +*buffer = _pcre_utf8_table2[i] | cvalue; +return i + 1; +} + +/* End of pcre_ord2utf8.c */ diff --git a/libs/pcre/pcre_printint.src b/libs/pcre/pcre_printint.src new file mode 100644 index 0000000000..e4de825a9b --- /dev/null +++ b/libs/pcre/pcre_printint.src @@ -0,0 +1,460 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2005 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains a PCRE private debugging function for printing out the +internal form of a compiled regular expression, along with some supporting +local functions. This source file is used in two places: + +(1) It is #included by pcre_compile.c when it is compiled in debugging mode +(DEBUG defined in pcre_internal.h). It is not included in production compiles. + +(2) It is always #included by pcretest.c, which can be asked to print out a +compiled regex for debugging purposes. */ + + +static const char *OP_names[] = { OP_NAME_LIST }; + + +/************************************************* +* Print single- or multi-byte character * +*************************************************/ + +static int +print_char(FILE *f, uschar *ptr, BOOL utf8) +{ +int c = *ptr; + +if (!utf8 || (c & 0xc0) != 0xc0) + { + if (isprint(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c); + return 0; + } +else + { + int i; + int a = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ + int s = 6*a; + c = (c & _pcre_utf8_table3[a]) << s; + for (i = 1; i <= a; i++) + { + /* This is a check for malformed UTF-8; it should only occur if the sanity + check has been turned off. Rather than swallow random bytes, just stop if + we hit a bad one. Print it with \X instead of \x as an indication. */ + + if ((ptr[i] & 0xc0) != 0x80) + { + fprintf(f, "\\X{%x}", c); + return i - 1; + } + + /* The byte is OK */ + + s -= 6; + c |= (ptr[i] & 0x3f) << s; + } + if (c < 128) fprintf(f, "\\x%02x", c); else fprintf(f, "\\x{%x}", c); + return a; + } +} + + + +/************************************************* +* Find Unicode property name * +*************************************************/ + +static const char * +get_ucpname(int ptype, int pvalue) +{ +#ifdef SUPPORT_UCP +int i; +for (i = _pcre_utt_size; i >= 0; i--) + { + if (ptype == _pcre_utt[i].type && pvalue == _pcre_utt[i].value) break; + } +return (i >= 0)? _pcre_utt[i].name : "??"; +#else +/* It gets harder and harder to shut off unwanted compiler warnings. */ +ptype = ptype * pvalue; +return (ptype == pvalue)? "??" : "??"; +#endif +} + + + +/************************************************* +* Print compiled regex * +*************************************************/ + +/* Make this function work for a regex with integers either byte order. +However, we assume that what we are passed is a compiled regex. */ + +static void +pcre_printint(pcre *external_re, FILE *f) +{ +real_pcre *re = (real_pcre *)external_re; +uschar *codestart, *code; +BOOL utf8; + +unsigned int options = re->options; +int offset = re->name_table_offset; +int count = re->name_count; +int size = re->name_entry_size; + +if (re->magic_number != MAGIC_NUMBER) + { + offset = ((offset << 8) & 0xff00) | ((offset >> 8) & 0xff); + count = ((count << 8) & 0xff00) | ((count >> 8) & 0xff); + size = ((size << 8) & 0xff00) | ((size >> 8) & 0xff); + options = ((options << 24) & 0xff000000) | + ((options << 8) & 0x00ff0000) | + ((options >> 8) & 0x0000ff00) | + ((options >> 24) & 0x000000ff); + } + +code = codestart = (uschar *)re + offset + count * size; +utf8 = (options & PCRE_UTF8) != 0; + +for(;;) + { + uschar *ccode; + int c; + int extra = 0; + + fprintf(f, "%3d ", (int)(code - codestart)); + + if (*code >= OP_BRA) + { + if (*code - OP_BRA > EXTRACT_BASIC_MAX) + fprintf(f, "%3d Bra extra\n", GET(code, 1)); + else + fprintf(f, "%3d Bra %d\n", GET(code, 1), *code - OP_BRA); + code += _pcre_OP_lengths[OP_BRA]; + continue; + } + + switch(*code) + { + case OP_END: + fprintf(f, " %s\n", OP_names[*code]); + fprintf(f, "------------------------------------------------------------------\n"); + return; + + case OP_OPT: + fprintf(f, " %.2x %s", code[1], OP_names[*code]); + break; + + case OP_CHAR: + fprintf(f, " "); + do + { + code++; + code += 1 + print_char(f, code, utf8); + } + while (*code == OP_CHAR); + fprintf(f, "\n"); + continue; + + case OP_CHARNC: + fprintf(f, " NC "); + do + { + code++; + code += 1 + print_char(f, code, utf8); + } + while (*code == OP_CHARNC); + fprintf(f, "\n"); + continue; + + case OP_KETRMAX: + case OP_KETRMIN: + case OP_ALT: + case OP_KET: + case OP_ASSERT: + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + case OP_ONCE: + case OP_COND: + case OP_REVERSE: + fprintf(f, "%3d %s", GET(code, 1), OP_names[*code]); + break; + + case OP_BRANUMBER: + printf("%3d %s", GET2(code, 1), OP_names[*code]); + break; + + case OP_CREF: + if (GET2(code, 1) == CREF_RECURSE) + fprintf(f, " Cond recurse"); + else + fprintf(f, "%3d %s", GET2(code,1), OP_names[*code]); + break; + + case OP_STAR: + case OP_MINSTAR: + case OP_PLUS: + case OP_MINPLUS: + case OP_QUERY: + case OP_MINQUERY: + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + fprintf(f, " "); + if (*code >= OP_TYPESTAR) + { + fprintf(f, "%s", OP_names[code[1]]); + if (code[1] == OP_PROP || code[1] == OP_NOTPROP) + { + fprintf(f, " %s ", get_ucpname(code[2], code[3])); + extra = 2; + } + } + else extra = print_char(f, code+1, utf8); + fprintf(f, "%s", OP_names[*code]); + break; + + case OP_EXACT: + case OP_UPTO: + case OP_MINUPTO: + fprintf(f, " "); + extra = print_char(f, code+3, utf8); + fprintf(f, "{"); + if (*code != OP_EXACT) fprintf(f, ","); + fprintf(f, "%d}", GET2(code,1)); + if (*code == OP_MINUPTO) fprintf(f, "?"); + break; + + case OP_TYPEEXACT: + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + fprintf(f, " %s", OP_names[code[3]]); + if (code[3] == OP_PROP || code[3] == OP_NOTPROP) + { + fprintf(f, " %s ", get_ucpname(code[4], code[5])); + extra = 2; + } + fprintf(f, "{"); + if (*code != OP_TYPEEXACT) fprintf(f, "0,"); + fprintf(f, "%d}", GET2(code,1)); + if (*code == OP_TYPEMINUPTO) fprintf(f, "?"); + break; + + case OP_NOT: + if (isprint(c = code[1])) fprintf(f, " [^%c]", c); + else fprintf(f, " [^\\x%02x]", c); + break; + + case OP_NOTSTAR: + case OP_NOTMINSTAR: + case OP_NOTPLUS: + case OP_NOTMINPLUS: + case OP_NOTQUERY: + case OP_NOTMINQUERY: + if (isprint(c = code[1])) fprintf(f, " [^%c]", c); + else fprintf(f, " [^\\x%02x]", c); + fprintf(f, "%s", OP_names[*code]); + break; + + case OP_NOTEXACT: + case OP_NOTUPTO: + case OP_NOTMINUPTO: + if (isprint(c = code[3])) fprintf(f, " [^%c]{", c); + else fprintf(f, " [^\\x%02x]{", c); + if (*code != OP_NOTEXACT) fprintf(f, "0,"); + fprintf(f, "%d}", GET2(code,1)); + if (*code == OP_NOTMINUPTO) fprintf(f, "?"); + break; + + case OP_RECURSE: + fprintf(f, "%3d %s", GET(code, 1), OP_names[*code]); + break; + + case OP_REF: + fprintf(f, " \\%d", GET2(code,1)); + ccode = code + _pcre_OP_lengths[*code]; + goto CLASS_REF_REPEAT; + + case OP_CALLOUT: + fprintf(f, " %s %d %d %d", OP_names[*code], code[1], GET(code,2), + GET(code, 2 + LINK_SIZE)); + break; + + case OP_PROP: + case OP_NOTPROP: + fprintf(f, " %s %s", OP_names[*code], get_ucpname(code[1], code[2])); + break; + + /* OP_XCLASS can only occur in UTF-8 mode. However, there's no harm in + having this code always here, and it makes it less messy without all those + #ifdefs. */ + + case OP_CLASS: + case OP_NCLASS: + case OP_XCLASS: + { + int i, min, max; + BOOL printmap; + + fprintf(f, " ["); + + if (*code == OP_XCLASS) + { + extra = GET(code, 1); + ccode = code + LINK_SIZE + 1; + printmap = (*ccode & XCL_MAP) != 0; + if ((*ccode++ & XCL_NOT) != 0) fprintf(f, "^"); + } + else + { + printmap = TRUE; + ccode = code + 1; + } + + /* Print a bit map */ + + if (printmap) + { + for (i = 0; i < 256; i++) + { + if ((ccode[i/8] & (1 << (i&7))) != 0) + { + int j; + for (j = i+1; j < 256; j++) + if ((ccode[j/8] & (1 << (j&7))) == 0) break; + if (i == '-' || i == ']') fprintf(f, "\\"); + if (isprint(i)) fprintf(f, "%c", i); else fprintf(f, "\\x%02x", i); + if (--j > i) + { + if (j != i + 1) fprintf(f, "-"); + if (j == '-' || j == ']') fprintf(f, "\\"); + if (isprint(j)) fprintf(f, "%c", j); else fprintf(f, "\\x%02x", j); + } + i = j; + } + } + ccode += 32; + } + + /* For an XCLASS there is always some additional data */ + + if (*code == OP_XCLASS) + { + int ch; + while ((ch = *ccode++) != XCL_END) + { + if (ch == XCL_PROP) + { + int ptype = *ccode++; + int pvalue = *ccode++; + fprintf(f, "\\p{%s}", get_ucpname(ptype, pvalue)); + } + else if (ch == XCL_NOTPROP) + { + int ptype = *ccode++; + int pvalue = *ccode++; + fprintf(f, "\\P{%s}", get_ucpname(ptype, pvalue)); + } + else + { + ccode += 1 + print_char(f, ccode, TRUE); + if (ch == XCL_RANGE) + { + fprintf(f, "-"); + ccode += 1 + print_char(f, ccode, TRUE); + } + } + } + } + + /* Indicate a non-UTF8 class which was created by negation */ + + fprintf(f, "]%s", (*code == OP_NCLASS)? " (neg)" : ""); + + /* Handle repeats after a class or a back reference */ + + CLASS_REF_REPEAT: + switch(*ccode) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + case OP_CRPLUS: + case OP_CRMINPLUS: + case OP_CRQUERY: + case OP_CRMINQUERY: + fprintf(f, "%s", OP_names[*ccode]); + extra += _pcre_OP_lengths[*ccode]; + break; + + case OP_CRRANGE: + case OP_CRMINRANGE: + min = GET2(ccode,1); + max = GET2(ccode,3); + if (max == 0) fprintf(f, "{%d,}", min); + else fprintf(f, "{%d,%d}", min, max); + if (*ccode == OP_CRMINRANGE) fprintf(f, "?"); + extra += _pcre_OP_lengths[*ccode]; + break; + + /* Do nothing if it's not a repeat; this code stops picky compilers + warning about the lack of a default code path. */ + + default: + break; + } + } + break; + + /* Anything else is just an item with no data*/ + + default: + fprintf(f, " %s", OP_names[*code]); + break; + } + + code += _pcre_OP_lengths[*code] + extra; + fprintf(f, "\n"); + } +} + +/* End of pcre_printint.src */ diff --git a/libs/pcre/pcre_refcount.c b/libs/pcre/pcre_refcount.c new file mode 100644 index 0000000000..e6965812ef --- /dev/null +++ b/libs/pcre/pcre_refcount.c @@ -0,0 +1,77 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains the external function pcre_refcount(), which is an +auxiliary function that can be used to maintain a reference count in a compiled +pattern data block. This might be helpful in applications where the block is +shared by different users. */ + +#include "pcre_internal.h" + + +/************************************************* +* Maintain reference count * +*************************************************/ + +/* The reference count is a 16-bit field, initialized to zero. It is not +possible to transfer a non-zero count from one host to a different host that +has a different byte order - though I can't see why anyone in their right mind +would ever want to do that! + +Arguments: + argument_re points to compiled code + adjust value to add to the count + +Returns: the (possibly updated) count value (a non-negative number), or + a negative error number +*/ + +PCRE_DATA_SCOPE int +pcre_refcount(pcre *argument_re, int adjust) +{ +real_pcre *re = (real_pcre *)argument_re; +if (re == NULL) return PCRE_ERROR_NULL; +re->ref_count = (-adjust > re->ref_count)? 0 : + (adjust + re->ref_count > 65535)? 65535 : + re->ref_count + adjust; +return re->ref_count; +} + +/* End of pcre_refcount.c */ diff --git a/libs/pcre/pcre_scanner.cc b/libs/pcre/pcre_scanner.cc new file mode 100644 index 0000000000..29e0d8400b --- /dev/null +++ b/libs/pcre/pcre_scanner.cc @@ -0,0 +1,173 @@ +// Copyright (c) 2005, Google Inc. +// All rights reserved. +// +// Redistribution and use in source and binary forms, with or without +// modification, are permitted provided that the following conditions are +// met: +// +// * Redistributions of source code must retain the above copyright +// notice, this list of conditions and the following disclaimer. +// * Redistributions in binary form must reproduce the above +// copyright notice, this list of conditions and the following disclaimer +// in the documentation and/or other materials provided with the +// distribution. +// * Neither the name of Google Inc. nor the names of its +// contributors may be used to endorse or promote products derived from +// this software without specific prior written permission. +// +// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +// +// Author: Sanjay Ghemawat + +#include +#include +#include "config.h" +#include "pcre_scanner.h" + +using std::vector; + +namespace pcrecpp { + +Scanner::Scanner() + : data_(), + input_(data_), + skip_(NULL), + should_skip_(false), + save_comments_(false), + comments_(NULL), + comments_offset_(0) { +} + +Scanner::Scanner(const string& in) + : data_(in), + input_(data_), + skip_(NULL), + should_skip_(false), + save_comments_(false), + comments_(NULL), + comments_offset_(0) { +} + +Scanner::~Scanner() { + delete skip_; + delete comments_; +} + +void Scanner::Skip(const char* re) { + delete skip_; + if (re != NULL) { + skip_ = new RE(re); + should_skip_ = true; + ConsumeSkip(); + } else { + skip_ = NULL; + should_skip_ = false; + } +} + +void Scanner::DisableSkip() { + assert(skip_ != NULL); + should_skip_ = false; +} + +void Scanner::EnableSkip() { + assert(skip_ != NULL); + should_skip_ = true; + ConsumeSkip(); +} + +int Scanner::LineNumber() const { + // TODO: Make it more efficient by keeping track of the last point + // where we computed line numbers and counting newlines since then. + // We could use std:count, but not all systems have it. :-( + int count = 1; + for (const char* p = data_.data(); p < input_.data(); ++p) + if (*p == '\n') + ++count; + return count; +} + +int Scanner::Offset() const { + return input_.data() - data_.c_str(); +} + +bool Scanner::LookingAt(const RE& re) const { + int consumed; + return re.DoMatch(input_, RE::ANCHOR_START, &consumed, 0, 0); +} + + +bool Scanner::Consume(const RE& re, + const Arg& arg0, + const Arg& arg1, + const Arg& arg2) { + const bool result = re.Consume(&input_, arg0, arg1, arg2); + if (result && should_skip_) ConsumeSkip(); + return result; +} + +// helper function to consume *skip_ and honour save_comments_ +void Scanner::ConsumeSkip() { + if (save_comments_) { + if (NULL == comments_) { + comments_ = new vector; + } + const char *start_data = input_.data(); + skip_->Consume(&input_); + // already pointing one past end, so no need to +1 + int length = input_.data() - start_data; + if (length > 0) { + comments_->push_back(StringPiece(start_data, length)); + } + } else { + skip_->Consume(&input_); + } +} + + +void Scanner::GetComments(int start, int end, vector *ranges) { + // short circuit out if we've not yet initialized comments_ + // (e.g., when save_comments is false) + if (!comments_) { + return; + } + // TODO: if we guarantee that comments_ will contain StringPieces + // that are ordered by their start, then we can do a binary search + // for the first StringPiece at or past start and then scan for the + // ones contained in the range, quit early (use equal_range or + // lower_bound) + for (vector::const_iterator it = comments_->begin(); + it != comments_->end(); ++it) { + if ((it->data() >= data_.c_str() + start && + it->data() + it->size() <= data_.c_str() + end)) { + ranges->push_back(*it); + } + } +} + + +void Scanner::GetNextComments(vector *ranges) { + // short circuit out if we've not yet initialized comments_ + // (e.g., when save_comments is false) + if (!comments_) { + return; + } + for (vector::const_iterator it = + comments_->begin() + comments_offset_; + it != comments_->end(); ++it) { + ranges->push_back(*it); + ++comments_offset_; + } +} + +} // namespace pcrecpp diff --git a/libs/pcre/pcre_scanner.h b/libs/pcre/pcre_scanner.h new file mode 100644 index 0000000000..a73b72fd2d --- /dev/null +++ b/libs/pcre/pcre_scanner.h @@ -0,0 +1,163 @@ +// Copyright (c) 2005, Google Inc. +// All rights reserved. +// +// Redistribution and use in source and binary forms, with or without +// modification, are permitted provided that the following conditions are +// met: +// +// * Redistributions of source code must retain the above copyright +// notice, this list of conditions and the following disclaimer. +// * Redistributions in binary form must reproduce the above +// copyright notice, this list of conditions and the following disclaimer +// in the documentation and/or other materials provided with the +// distribution. +// * Neither the name of Google Inc. nor the names of its +// contributors may be used to endorse or promote products derived from +// this software without specific prior written permission. +// +// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +// +// Author: Sanjay Ghemawat +// +// Regular-expression based scanner for parsing an input stream. +// +// Example 1: parse a sequence of "var = number" entries from input: +// +// Scanner scanner(input); +// string var; +// int number; +// scanner.Skip("\\s+"); // Skip any white space we encounter +// while (scanner.Consume("(\\w+) = (\\d+)", &var, &number)) { +// ...; +// } + +#ifndef _PCRE_SCANNER_H +#define _PCRE_SCANNER_H + +#include +#include +#include +#include +#include + +namespace pcrecpp { + +class Scanner { + public: + Scanner(); + explicit Scanner(const std::string& input); + ~Scanner(); + + // Return current line number. The returned line-number is + // one-based. I.e. it returns 1 + the number of consumed newlines. + // + // Note: this method may be slow. It may take time proportional to + // the size of the input. + int LineNumber() const; + + // Return the byte-offset that the scanner is looking in the + // input data; + int Offset() const; + + // Return true iff the start of the remaining input matches "re" + bool LookingAt(const RE& re) const; + + // Return true iff all of the following are true + // a. the start of the remaining input matches "re", + // b. if any arguments are supplied, matched sub-patterns can be + // parsed and stored into the arguments. + // If it returns true, it skips over the matched input and any + // following input that matches the "skip" regular expression. + bool Consume(const RE& re, + const Arg& arg0 = no_arg, + const Arg& arg1 = no_arg, + const Arg& arg2 = no_arg + // TODO: Allow more arguments? + ); + + // Set the "skip" regular expression. If after consuming some data, + // a prefix of the input matches this RE, it is automatically + // skipped. For example, a programming language scanner would use + // a skip RE that matches white space and comments. + // + // scanner.Skip("(\\s|//.*|/[*](.|\n)*?[*]/)*"); + // + // You can pass NULL for "re" if you do not want any data to be skipped. + void Skip(const char* re); + + // Temporarily pause "skip"ing. This + // Skip("Foo"); code ; DisableSkip(); code; EnableSkip() + // is similar to + // Skip("Foo"); code ; Skip(NULL); code ; Skip("Foo"); + // but avoids creating/deleting new RE objects. + void DisableSkip(); + + // Reenable previously paused skipping. Any prefix of the input + // that matches the skip pattern is immediately dropped. + void EnableSkip(); + + /***** Special wrappers around SetSkip() for some common idioms *****/ + + // Arranges to skip whitespace, C comments, C++ comments. + // The overall RE is a repeated disjunction of the following REs: + // \\s whitespace + // //.*\n C++ comment + // /[*](.|\n)*?[*]/ C comment (x*? means minimal repetitions of x) + void SkipCXXComments() { + Skip("((\\s|//.*\n|/[*](.|\n)*?[*]/)*)"); + } + + void set_save_comments(bool comments) { + save_comments_ = comments; + } + + bool save_comments() { + return save_comments_; + } + + // Append to vector ranges the comments found in the + // byte range [start,end] (inclusive) of the input data. + // Only comments that were extracted entirely within that + // range are returned: no range splitting of atomically-extracted + // comments is performed. + void GetComments(int start, int end, std::vector *ranges); + + // Append to vector ranges the comments added + // since the last time this was called. This + // functionality is provided for efficiency when + // interleaving scanning with parsing. + void GetNextComments(std::vector *ranges); + + private: + std::string data_; // All the input data + StringPiece input_; // Unprocessed input + RE* skip_; // If non-NULL, RE for skipping input + bool should_skip_; // If true, use skip_ + bool save_comments_; // If true, aggregate the skip expression + + // the skipped comments + // TODO: later consider requiring that the StringPieces be added + // in order by their start position + std::vector *comments_; + + // the offset into comments_ that has been returned by GetNextComments + int comments_offset_; + + // helper function to consume *skip_ and honour + // save_comments_ + void ConsumeSkip(); +}; + +} // namespace pcrecpp + +#endif /* _PCRE_SCANNER_H */ diff --git a/libs/pcre/pcre_scanner_unittest.cc b/libs/pcre/pcre_scanner_unittest.cc new file mode 100644 index 0000000000..756823cbb1 --- /dev/null +++ b/libs/pcre/pcre_scanner_unittest.cc @@ -0,0 +1,126 @@ +// Copyright (c) 2005, Google Inc. +// All rights reserved. +// +// Redistribution and use in source and binary forms, with or without +// modification, are permitted provided that the following conditions are +// met: +// +// * Redistributions of source code must retain the above copyright +// notice, this list of conditions and the following disclaimer. +// * Redistributions in binary form must reproduce the above +// copyright notice, this list of conditions and the following disclaimer +// in the documentation and/or other materials provided with the +// distribution. +// * Neither the name of Google Inc. nor the names of its +// contributors may be used to endorse or promote products derived from +// this software without specific prior written permission. +// +// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +// +// Author: Greg J. Badros +// +// Unittest for scanner, especially GetNextComments and GetComments() +// functionality. + +#include +#include +#include +#include + +// Dies with a fatal error if the two values are not equal. +#define CHECK_EQ(a, b) do { \ + if ( (a) != (b) ) { \ + fprintf(stderr, "%s:%d: Check failed because %s != %s\n", \ + __FILE__, __LINE__, #a, #b); \ + exit(1); \ + } \ +} while (0) + +using std::vector; +using pcrecpp::StringPiece; +using pcrecpp::Scanner; + +static void TestScanner() { + const char input[] = "\n" + "alpha = 1; // this sets alpha\n" + "bravo = 2; // bravo is set here\n" + "gamma = 33; /* and here is gamma */\n"; + + const char *re = "(\\w+) = (\\d+);"; + + Scanner s(input); + string var; + int number; + s.SkipCXXComments(); + s.set_save_comments(true); + vector comments; + + s.Consume(re, &var, &number); + CHECK_EQ(var, "alpha"); + CHECK_EQ(number, 1); + CHECK_EQ(s.LineNumber(), 3); + s.GetNextComments(&comments); + CHECK_EQ(comments.size(), 1); + CHECK_EQ(comments[0].as_string(), " // this sets alpha\n"); + comments.resize(0); + + s.Consume(re, &var, &number); + CHECK_EQ(var, "bravo"); + CHECK_EQ(number, 2); + s.GetNextComments(&comments); + CHECK_EQ(comments.size(), 1); + CHECK_EQ(comments[0].as_string(), " // bravo is set here\n"); + comments.resize(0); + + s.Consume(re, &var, &number); + CHECK_EQ(var, "gamma"); + CHECK_EQ(number, 33); + s.GetNextComments(&comments); + CHECK_EQ(comments.size(), 1); + CHECK_EQ(comments[0].as_string(), " /* and here is gamma */\n"); + comments.resize(0); + + s.GetComments(0, sizeof(input), &comments); + CHECK_EQ(comments.size(), 3); + CHECK_EQ(comments[0].as_string(), " // this sets alpha\n"); + CHECK_EQ(comments[1].as_string(), " // bravo is set here\n"); + CHECK_EQ(comments[2].as_string(), " /* and here is gamma */\n"); + comments.resize(0); + + s.GetComments(0, strchr(input, '/') - input, &comments); + CHECK_EQ(comments.size(), 0); + comments.resize(0); + + s.GetComments(strchr(input, '/') - input - 1, sizeof(input), + &comments); + CHECK_EQ(comments.size(), 3); + CHECK_EQ(comments[0].as_string(), " // this sets alpha\n"); + CHECK_EQ(comments[1].as_string(), " // bravo is set here\n"); + CHECK_EQ(comments[2].as_string(), " /* and here is gamma */\n"); + comments.resize(0); + + s.GetComments(strchr(input, '/') - input - 1, + strchr(input + 1, '\n') - input + 1, &comments); + CHECK_EQ(comments.size(), 1); + CHECK_EQ(comments[0].as_string(), " // this sets alpha\n"); + comments.resize(0); +} + +int main(int argc, char** argv) { + TestScanner(); + + // Done + printf("OK\n"); + + return 0; +} diff --git a/libs/pcre/pcre_stringpiece.cc b/libs/pcre/pcre_stringpiece.cc new file mode 100644 index 0000000000..dbdb509b3b --- /dev/null +++ b/libs/pcre/pcre_stringpiece.cc @@ -0,0 +1,39 @@ +// Copyright (c) 2005, Google Inc. +// All rights reserved. +// +// Redistribution and use in source and binary forms, with or without +// modification, are permitted provided that the following conditions are +// met: +// +// * Redistributions of source code must retain the above copyright +// notice, this list of conditions and the following disclaimer. +// * Redistributions in binary form must reproduce the above +// copyright notice, this list of conditions and the following disclaimer +// in the documentation and/or other materials provided with the +// distribution. +// * Neither the name of Google Inc. nor the names of its +// contributors may be used to endorse or promote products derived from +// this software without specific prior written permission. +// +// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +// +// Author: wilsonh@google.com (Wilson Hsieh) +// + +#include +#include "config.h" +#include "pcre_stringpiece.h" + +std::ostream& operator<<(std::ostream& o, const pcrecpp::StringPiece& piece) { + return (o << piece.as_string()); +} diff --git a/libs/pcre/pcre_stringpiece.h.in b/libs/pcre/pcre_stringpiece.h.in new file mode 100644 index 0000000000..7cc074d137 --- /dev/null +++ b/libs/pcre/pcre_stringpiece.h.in @@ -0,0 +1,172 @@ +// Copyright (c) 2005, Google Inc. +// All rights reserved. +// +// Redistribution and use in source and binary forms, with or without +// modification, are permitted provided that the following conditions are +// met: +// +// * Redistributions of source code must retain the above copyright +// notice, this list of conditions and the following disclaimer. +// * Redistributions in binary form must reproduce the above +// copyright notice, this list of conditions and the following disclaimer +// in the documentation and/or other materials provided with the +// distribution. +// * Neither the name of Google Inc. nor the names of its +// contributors may be used to endorse or promote products derived from +// this software without specific prior written permission. +// +// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +// +// Author: Sanjay Ghemawat +// +// A string like object that points into another piece of memory. +// Useful for providing an interface that allows clients to easily +// pass in either a "const char*" or a "string". +// +// Arghh! I wish C++ literals were automatically of type "string". + +#ifndef _PCRE_STRINGPIECE_H +#define _PCRE_STRINGPIECE_H + +#include +#include +#include // for ostream forward-declaration + +#if @pcre_have_type_traits@ +#define HAVE_TYPE_TRAITS +#include +#elif @pcre_have_bits_type_traits@ +#define HAVE_TYPE_TRAITS +#include +#endif + +using std::string; + +namespace pcrecpp { + +class StringPiece { + private: + const char* ptr_; + int length_; + + public: + // We provide non-explicit singleton constructors so users can pass + // in a "const char*" or a "string" wherever a "StringPiece" is + // expected. + StringPiece() + : ptr_(NULL), length_(0) { } + StringPiece(const char* str) + : ptr_(str), length_(static_cast(strlen(str))) { } + StringPiece(const string& str) + : ptr_(str.data()), length_(static_cast(str.size())) { } + StringPiece(const char* offset, int len) + : ptr_(offset), length_(len) { } + + // data() may return a pointer to a buffer with embedded NULs, and the + // returned buffer may or may not be null terminated. Therefore it is + // typically a mistake to pass data() to a routine that expects a NUL + // terminated string. Use "as_string().c_str()" if you really need to do + // this. Or better yet, change your routine so it does not rely on NUL + // termination. + const char* data() const { return ptr_; } + int size() const { return length_; } + bool empty() const { return length_ == 0; } + + void clear() { ptr_ = NULL; length_ = 0; } + void set(const char* buffer, int len) { ptr_ = buffer; length_ = len; } + void set(const char* str) { + ptr_ = str; + length_ = static_cast(strlen(str)); + } + void set(const void* buffer, int len) { + ptr_ = reinterpret_cast(buffer); + length_ = len; + } + + char operator[](int i) const { return ptr_[i]; } + + void remove_prefix(int n) { + ptr_ += n; + length_ -= n; + } + + void remove_suffix(int n) { + length_ -= n; + } + + bool operator==(const StringPiece& x) const { + return ((length_ == x.length_) && + (memcmp(ptr_, x.ptr_, length_) == 0)); + } + bool operator!=(const StringPiece& x) const { + return !(*this == x); + } + +#define STRINGPIECE_BINARY_PREDICATE(cmp,auxcmp) \ + bool operator cmp (const StringPiece& x) const { \ + int r = memcmp(ptr_, x.ptr_, length_ < x.length_ ? length_ : x.length_); \ + return ((r auxcmp 0) || ((r == 0) && (length_ cmp x.length_))); \ + } + STRINGPIECE_BINARY_PREDICATE(<, <); + STRINGPIECE_BINARY_PREDICATE(<=, <); + STRINGPIECE_BINARY_PREDICATE(>=, >); + STRINGPIECE_BINARY_PREDICATE(>, >); +#undef STRINGPIECE_BINARY_PREDICATE + + int compare(const StringPiece& x) const { + int r = memcmp(ptr_, x.ptr_, length_ < x.length_ ? length_ : x.length_); + if (r == 0) { + if (length_ < x.length_) r = -1; + else if (length_ > x.length_) r = +1; + } + return r; + } + + string as_string() const { + return string(data(), size()); + } + + void CopyToString(string* target) const { + target->assign(ptr_, length_); + } + + // Does "this" start with "x" + bool starts_with(const StringPiece& x) const { + return ((length_ >= x.length_) && (memcmp(ptr_, x.ptr_, x.length_) == 0)); + } +}; + +} // namespace pcrecpp + +// ------------------------------------------------------------------ +// Functions used to create STL containers that use StringPiece +// Remember that a StringPiece's lifetime had better be less than +// that of the underlying string or char*. If it is not, then you +// cannot safely store a StringPiece into an STL container +// ------------------------------------------------------------------ + +#ifdef HAVE_TYPE_TRAITS +// This makes vector really fast for some STL implementations +template<> struct __type_traits { + typedef __true_type has_trivial_default_constructor; + typedef __true_type has_trivial_copy_constructor; + typedef __true_type has_trivial_assignment_operator; + typedef __true_type has_trivial_destructor; + typedef __true_type is_POD_type; +}; +#endif + +// allow StringPiece to be logged +std::ostream& operator<<(std::ostream& o, const pcrecpp::StringPiece& piece); + +#endif /* _PCRE_STRINGPIECE_H */ diff --git a/libs/pcre/pcre_stringpiece_unittest.cc b/libs/pcre/pcre_stringpiece_unittest.cc new file mode 100644 index 0000000000..d6a89e8c7a --- /dev/null +++ b/libs/pcre/pcre_stringpiece_unittest.cc @@ -0,0 +1,145 @@ +// Copyright 2003 and onwards Google Inc. +// Author: Sanjay Ghemawat + +#include +#include +#include // for make_pair +#include + +// CHECK dies with a fatal error if condition is not true. It is *not* +// controlled by NDEBUG, so the check will be executed regardless of +// compilation mode. Therefore, it is safe to do things like: +// CHECK(fp->Write(x) == 4) +#define CHECK(condition) do { \ + if (!(condition)) { \ + fprintf(stderr, "%s:%d: Check failed: %s\n", \ + __FILE__, __LINE__, #condition); \ + exit(1); \ + } \ +} while (0) + +using std::map; +using std::make_pair; +using pcrecpp::StringPiece; + +static void CheckSTLComparator() { + string s1("foo"); + string s2("bar"); + string s3("baz"); + + StringPiece p1(s1); + StringPiece p2(s2); + StringPiece p3(s3); + + typedef map TestMap; + TestMap map; + + map.insert(make_pair(p1, 0)); + map.insert(make_pair(p2, 1)); + map.insert(make_pair(p3, 2)); + CHECK(map.size() == 3); + + TestMap::const_iterator iter = map.begin(); + CHECK(iter->second == 1); + ++iter; + CHECK(iter->second == 2); + ++iter; + CHECK(iter->second == 0); + ++iter; + CHECK(iter == map.end()); + + TestMap::iterator new_iter = map.find("zot"); + CHECK(new_iter == map.end()); + + new_iter = map.find("bar"); + CHECK(new_iter != map.end()); + + map.erase(new_iter); + CHECK(map.size() == 2); + + iter = map.begin(); + CHECK(iter->second == 2); + ++iter; + CHECK(iter->second == 0); + ++iter; + CHECK(iter == map.end()); +} + +static void CheckComparisonOperators() { +#define CMP_Y(op, x, y) \ + CHECK( (StringPiece((x)) op StringPiece((y)))); \ + CHECK( (StringPiece((x)).compare(StringPiece((y))) op 0)) + +#define CMP_N(op, x, y) \ + CHECK(!(StringPiece((x)) op StringPiece((y)))); \ + CHECK(!(StringPiece((x)).compare(StringPiece((y))) op 0)) + + CMP_Y(==, "", ""); + CMP_Y(==, "a", "a"); + CMP_Y(==, "aa", "aa"); + CMP_N(==, "a", ""); + CMP_N(==, "", "a"); + CMP_N(==, "a", "b"); + CMP_N(==, "a", "aa"); + CMP_N(==, "aa", "a"); + + CMP_N(!=, "", ""); + CMP_N(!=, "a", "a"); + CMP_N(!=, "aa", "aa"); + CMP_Y(!=, "a", ""); + CMP_Y(!=, "", "a"); + CMP_Y(!=, "a", "b"); + CMP_Y(!=, "a", "aa"); + CMP_Y(!=, "aa", "a"); + + CMP_Y(<, "a", "b"); + CMP_Y(<, "a", "aa"); + CMP_Y(<, "aa", "b"); + CMP_Y(<, "aa", "bb"); + CMP_N(<, "a", "a"); + CMP_N(<, "b", "a"); + CMP_N(<, "aa", "a"); + CMP_N(<, "b", "aa"); + CMP_N(<, "bb", "aa"); + + CMP_Y(<=, "a", "a"); + CMP_Y(<=, "a", "b"); + CMP_Y(<=, "a", "aa"); + CMP_Y(<=, "aa", "b"); + CMP_Y(<=, "aa", "bb"); + CMP_N(<=, "b", "a"); + CMP_N(<=, "aa", "a"); + CMP_N(<=, "b", "aa"); + CMP_N(<=, "bb", "aa"); + + CMP_N(>=, "a", "b"); + CMP_N(>=, "a", "aa"); + CMP_N(>=, "aa", "b"); + CMP_N(>=, "aa", "bb"); + CMP_Y(>=, "a", "a"); + CMP_Y(>=, "b", "a"); + CMP_Y(>=, "aa", "a"); + CMP_Y(>=, "b", "aa"); + CMP_Y(>=, "bb", "aa"); + + CMP_N(>, "a", "a"); + CMP_N(>, "a", "b"); + CMP_N(>, "a", "aa"); + CMP_N(>, "aa", "b"); + CMP_N(>, "aa", "bb"); + CMP_Y(>, "b", "a"); + CMP_Y(>, "aa", "a"); + CMP_Y(>, "b", "aa"); + CMP_Y(>, "bb", "aa"); + +#undef CMP_Y +#undef CMP_N +} + +int main(int argc, char** argv) { + CheckComparisonOperators(); + CheckSTLComparator(); + + printf("OK\n"); + return 0; +} diff --git a/libs/pcre/pcre_study.c b/libs/pcre/pcre_study.c new file mode 100644 index 0000000000..5091324ae6 --- /dev/null +++ b/libs/pcre/pcre_study.c @@ -0,0 +1,525 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains the external function pcre_study(), along with local +supporting functions. */ + + +#include "pcre_internal.h" + + +/************************************************* +* Set a bit and maybe its alternate case * +*************************************************/ + +/* Given a character, set its bit in the table, and also the bit for the other +version of a letter if we are caseless. + +Arguments: + start_bits points to the bit map + c is the character + caseless the caseless flag + cd the block with char table pointers + +Returns: nothing +*/ + +static void +set_bit(uschar *start_bits, unsigned int c, BOOL caseless, compile_data *cd) +{ +start_bits[c/8] |= (1 << (c&7)); +if (caseless && (cd->ctypes[c] & ctype_letter) != 0) + start_bits[cd->fcc[c]/8] |= (1 << (cd->fcc[c]&7)); +} + + + +/************************************************* +* Create bitmap of starting chars * +*************************************************/ + +/* This function scans a compiled unanchored expression and attempts to build a +bitmap of the set of initial characters. If it can't, it returns FALSE. As time +goes by, we may be able to get more clever at doing this. + +Arguments: + code points to an expression + start_bits points to a 32-byte table, initialized to 0 + caseless the current state of the caseless flag + utf8 TRUE if in UTF-8 mode + cd the block with char table pointers + +Returns: TRUE if table built, FALSE otherwise +*/ + +static BOOL +set_start_bits(const uschar *code, uschar *start_bits, BOOL caseless, + BOOL utf8, compile_data *cd) +{ +register int c; + +#if 0 +/* ========================================================================= */ +/* The following comment and code was inserted in January 1999. In May 2006, +when it was observed to cause compiler warnings about unused values, I took it +out again. If anybody is still using OS/2, they will have to put it back +manually. */ + +/* This next statement and the later reference to dummy are here in order to +trick the optimizer of the IBM C compiler for OS/2 into generating correct +code. Apparently IBM isn't going to fix the problem, and we would rather not +disable optimization (in this module it actually makes a big difference, and +the pcre module can use all the optimization it can get). */ + +volatile int dummy; +/* ========================================================================= */ +#endif + +do + { + const uschar *tcode = code + 1 + LINK_SIZE; + BOOL try_next = TRUE; + + while (try_next) + { + /* If a branch starts with a bracket or a positive lookahead assertion, + recurse to set bits from within them. That's all for this branch. */ + + if ((int)*tcode >= OP_BRA || *tcode == OP_ASSERT) + { + if (!set_start_bits(tcode, start_bits, caseless, utf8, cd)) + return FALSE; + try_next = FALSE; + } + + else switch(*tcode) + { + default: + return FALSE; + + /* Skip over callout */ + + case OP_CALLOUT: + tcode += 2 + 2*LINK_SIZE; + break; + + /* Skip over extended extraction bracket number */ + + case OP_BRANUMBER: + tcode += 3; + break; + + /* Skip over lookbehind and negative lookahead assertions */ + + case OP_ASSERT_NOT: + case OP_ASSERTBACK: + case OP_ASSERTBACK_NOT: + do tcode += GET(tcode, 1); while (*tcode == OP_ALT); + tcode += 1+LINK_SIZE; + break; + + /* Skip over an option setting, changing the caseless flag */ + + case OP_OPT: + caseless = (tcode[1] & PCRE_CASELESS) != 0; + tcode += 2; + break; + + /* BRAZERO does the bracket, but carries on. */ + + case OP_BRAZERO: + case OP_BRAMINZERO: + if (!set_start_bits(++tcode, start_bits, caseless, utf8, cd)) + return FALSE; +/* ========================================================================= + See the comment at the head of this function concerning the next line, + which was an old fudge for the benefit of OS/2. + dummy = 1; + ========================================================================= */ + do tcode += GET(tcode,1); while (*tcode == OP_ALT); + tcode += 1+LINK_SIZE; + break; + + /* Single-char * or ? sets the bit and tries the next item */ + + case OP_STAR: + case OP_MINSTAR: + case OP_QUERY: + case OP_MINQUERY: + set_bit(start_bits, tcode[1], caseless, cd); + tcode += 2; +#ifdef SUPPORT_UTF8 + if (utf8) while ((*tcode & 0xc0) == 0x80) tcode++; +#endif + break; + + /* Single-char upto sets the bit and tries the next */ + + case OP_UPTO: + case OP_MINUPTO: + set_bit(start_bits, tcode[3], caseless, cd); + tcode += 4; +#ifdef SUPPORT_UTF8 + if (utf8) while ((*tcode & 0xc0) == 0x80) tcode++; +#endif + break; + + /* At least one single char sets the bit and stops */ + + case OP_EXACT: /* Fall through */ + tcode += 2; + + case OP_CHAR: + case OP_CHARNC: + case OP_PLUS: + case OP_MINPLUS: + set_bit(start_bits, tcode[1], caseless, cd); + try_next = FALSE; + break; + + /* Single character type sets the bits and stops */ + + case OP_NOT_DIGIT: + for (c = 0; c < 32; c++) + start_bits[c] |= ~cd->cbits[c+cbit_digit]; + try_next = FALSE; + break; + + case OP_DIGIT: + for (c = 0; c < 32; c++) + start_bits[c] |= cd->cbits[c+cbit_digit]; + try_next = FALSE; + break; + + /* The cbit_space table has vertical tab as whitespace; we have to + discard it. */ + + case OP_NOT_WHITESPACE: + for (c = 0; c < 32; c++) + { + int d = cd->cbits[c+cbit_space]; + if (c == 1) d &= ~0x08; + start_bits[c] |= ~d; + } + try_next = FALSE; + break; + + /* The cbit_space table has vertical tab as whitespace; we have to + discard it. */ + + case OP_WHITESPACE: + for (c = 0; c < 32; c++) + { + int d = cd->cbits[c+cbit_space]; + if (c == 1) d &= ~0x08; + start_bits[c] |= d; + } + try_next = FALSE; + break; + + case OP_NOT_WORDCHAR: + for (c = 0; c < 32; c++) + start_bits[c] |= ~cd->cbits[c+cbit_word]; + try_next = FALSE; + break; + + case OP_WORDCHAR: + for (c = 0; c < 32; c++) + start_bits[c] |= cd->cbits[c+cbit_word]; + try_next = FALSE; + break; + + /* One or more character type fudges the pointer and restarts, knowing + it will hit a single character type and stop there. */ + + case OP_TYPEPLUS: + case OP_TYPEMINPLUS: + tcode++; + break; + + case OP_TYPEEXACT: + tcode += 3; + break; + + /* Zero or more repeats of character types set the bits and then + try again. */ + + case OP_TYPEUPTO: + case OP_TYPEMINUPTO: + tcode += 2; /* Fall through */ + + case OP_TYPESTAR: + case OP_TYPEMINSTAR: + case OP_TYPEQUERY: + case OP_TYPEMINQUERY: + switch(tcode[1]) + { + case OP_ANY: + return FALSE; + + case OP_NOT_DIGIT: + for (c = 0; c < 32; c++) + start_bits[c] |= ~cd->cbits[c+cbit_digit]; + break; + + case OP_DIGIT: + for (c = 0; c < 32; c++) + start_bits[c] |= cd->cbits[c+cbit_digit]; + break; + + /* The cbit_space table has vertical tab as whitespace; we have to + discard it. */ + + case OP_NOT_WHITESPACE: + for (c = 0; c < 32; c++) + { + int d = cd->cbits[c+cbit_space]; + if (c == 1) d &= ~0x08; + start_bits[c] |= ~d; + } + break; + + /* The cbit_space table has vertical tab as whitespace; we have to + discard it. */ + + case OP_WHITESPACE: + for (c = 0; c < 32; c++) + { + int d = cd->cbits[c+cbit_space]; + if (c == 1) d &= ~0x08; + start_bits[c] |= d; + } + break; + + case OP_NOT_WORDCHAR: + for (c = 0; c < 32; c++) + start_bits[c] |= ~cd->cbits[c+cbit_word]; + break; + + case OP_WORDCHAR: + for (c = 0; c < 32; c++) + start_bits[c] |= cd->cbits[c+cbit_word]; + break; + } + + tcode += 2; + break; + + /* Character class where all the information is in a bit map: set the + bits and either carry on or not, according to the repeat count. If it was + a negative class, and we are operating with UTF-8 characters, any byte + with a value >= 0xc4 is a potentially valid starter because it starts a + character with a value > 255. */ + + case OP_NCLASS: + if (utf8) + { + start_bits[24] |= 0xf0; /* Bits for 0xc4 - 0xc8 */ + memset(start_bits+25, 0xff, 7); /* Bits for 0xc9 - 0xff */ + } + /* Fall through */ + + case OP_CLASS: + { + tcode++; + + /* In UTF-8 mode, the bits in a bit map correspond to character + values, not to byte values. However, the bit map we are constructing is + for byte values. So we have to do a conversion for characters whose + value is > 127. In fact, there are only two possible starting bytes for + characters in the range 128 - 255. */ + + if (utf8) + { + for (c = 0; c < 16; c++) start_bits[c] |= tcode[c]; + for (c = 128; c < 256; c++) + { + if ((tcode[c/8] && (1 << (c&7))) != 0) + { + int d = (c >> 6) | 0xc0; /* Set bit for this starter */ + start_bits[d/8] |= (1 << (d&7)); /* and then skip on to the */ + c = (c & 0xc0) + 0x40 - 1; /* next relevant character. */ + } + } + } + + /* In non-UTF-8 mode, the two bit maps are completely compatible. */ + + else + { + for (c = 0; c < 32; c++) start_bits[c] |= tcode[c]; + } + + /* Advance past the bit map, and act on what follows */ + + tcode += 32; + switch (*tcode) + { + case OP_CRSTAR: + case OP_CRMINSTAR: + case OP_CRQUERY: + case OP_CRMINQUERY: + tcode++; + break; + + case OP_CRRANGE: + case OP_CRMINRANGE: + if (((tcode[1] << 8) + tcode[2]) == 0) tcode += 5; + else try_next = FALSE; + break; + + default: + try_next = FALSE; + break; + } + } + break; /* End of bitmap class handling */ + + } /* End of switch */ + } /* End of try_next loop */ + + code += GET(code, 1); /* Advance to next branch */ + } +while (*code == OP_ALT); +return TRUE; +} + + + +/************************************************* +* Study a compiled expression * +*************************************************/ + +/* This function is handed a compiled expression that it must study to produce +information that will speed up the matching. It returns a pcre_extra block +which then gets handed back to pcre_exec(). + +Arguments: + re points to the compiled expression + options contains option bits + errorptr points to where to place error messages; + set NULL unless error + +Returns: pointer to a pcre_extra block, with study_data filled in and the + appropriate flag set; + NULL on error or if no optimization possible +*/ + +PCRE_DATA_SCOPE pcre_extra * +pcre_study(const pcre *external_re, int options, const char **errorptr) +{ +uschar start_bits[32]; +pcre_extra *extra; +pcre_study_data *study; +const uschar *tables; +uschar *code; +compile_data compile_block; +const real_pcre *re = (const real_pcre *)external_re; + +*errorptr = NULL; + +if (re == NULL || re->magic_number != MAGIC_NUMBER) + { + *errorptr = "argument is not a compiled regular expression"; + return NULL; + } + +if ((options & ~PUBLIC_STUDY_OPTIONS) != 0) + { + *errorptr = "unknown or incorrect option bit(s) set"; + return NULL; + } + +code = (uschar *)re + re->name_table_offset + + (re->name_count * re->name_entry_size); + +/* For an anchored pattern, or an unanchored pattern that has a first char, or +a multiline pattern that matches only at "line starts", no further processing +at present. */ + +if ((re->options & (PCRE_ANCHORED|PCRE_FIRSTSET|PCRE_STARTLINE)) != 0) + return NULL; + +/* Set the character tables in the block that is passed around */ + +tables = re->tables; +if (tables == NULL) + (void)pcre_fullinfo(external_re, NULL, PCRE_INFO_DEFAULT_TABLES, + (void *)(&tables)); + +compile_block.lcc = tables + lcc_offset; +compile_block.fcc = tables + fcc_offset; +compile_block.cbits = tables + cbits_offset; +compile_block.ctypes = tables + ctypes_offset; + +/* See if we can find a fixed set of initial characters for the pattern. */ + +memset(start_bits, 0, 32 * sizeof(uschar)); +if (!set_start_bits(code, start_bits, (re->options & PCRE_CASELESS) != 0, + (re->options & PCRE_UTF8) != 0, &compile_block)) return NULL; + +/* Get a pcre_extra block and a pcre_study_data block. The study data is put in +the latter, which is pointed to by the former, which may also get additional +data set later by the calling program. At the moment, the size of +pcre_study_data is fixed. We nevertheless save it in a field for returning via +the pcre_fullinfo() function so that if it becomes variable in the future, we +don't have to change that code. */ + +extra = (pcre_extra *)(pcre_malloc) + (sizeof(pcre_extra) + sizeof(pcre_study_data)); + +if (extra == NULL) + { + *errorptr = "failed to get memory"; + return NULL; + } + +study = (pcre_study_data *)((char *)extra + sizeof(pcre_extra)); +extra->flags = PCRE_EXTRA_STUDY_DATA; +extra->study_data = study; + +study->size = sizeof(pcre_study_data); +study->options = PCRE_STUDY_MAPPED; +memcpy(study->start_bits, start_bits, sizeof(start_bits)); + +return extra; +} + +/* End of pcre_study.c */ diff --git a/libs/pcre/pcre_tables.c b/libs/pcre/pcre_tables.c new file mode 100644 index 0000000000..480257cab8 --- /dev/null +++ b/libs/pcre/pcre_tables.c @@ -0,0 +1,193 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains some fixed tables that are used by more than one of the +PCRE code modules. The tables are also #included by the pcretest program, which +uses macros to change their names from _pcre_xxx to xxxx, thereby avoiding name +clashes with the library. */ + + +#include "pcre_internal.h" + + +/* Table of sizes for the fixed-length opcodes. It's defined in a macro so that +the definition is next to the definition of the opcodes in pcre_internal.h. */ + +const uschar _pcre_OP_lengths[] = { OP_LENGTHS }; + + + +/************************************************* +* Tables for UTF-8 support * +*************************************************/ + +/* These are the breakpoints for different numbers of bytes in a UTF-8 +character. */ + +const int _pcre_utf8_table1[] = + { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff}; + +const int _pcre_utf8_table1_size = sizeof(_pcre_utf8_table1)/sizeof(int); + +/* These are the indicator bits and the mask for the data bits to set in the +first byte of a character, indexed by the number of additional bytes. */ + +const int _pcre_utf8_table2[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc}; +const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01}; + +/* Table of the number of extra characters, indexed by the first character +masked with 0x3f. The highest number for a valid UTF-8 character is in fact +0x3d. */ + +const uschar _pcre_utf8_table4[] = { + 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, + 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, + 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, + 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 }; + +/* This table translates Unicode property names into type and code values. It +is searched by binary chop, so must be in collating sequence of name. */ + +const ucp_type_table _pcre_utt[] = { + { "Any", PT_ANY, 0 }, + { "Arabic", PT_SC, ucp_Arabic }, + { "Armenian", PT_SC, ucp_Armenian }, + { "Bengali", PT_SC, ucp_Bengali }, + { "Bopomofo", PT_SC, ucp_Bopomofo }, + { "Braille", PT_SC, ucp_Braille }, + { "Buginese", PT_SC, ucp_Buginese }, + { "Buhid", PT_SC, ucp_Buhid }, + { "C", PT_GC, ucp_C }, + { "Canadian_Aboriginal", PT_SC, ucp_Canadian_Aboriginal }, + { "Cc", PT_PC, ucp_Cc }, + { "Cf", PT_PC, ucp_Cf }, + { "Cherokee", PT_SC, ucp_Cherokee }, + { "Cn", PT_PC, ucp_Cn }, + { "Co", PT_PC, ucp_Co }, + { "Common", PT_SC, ucp_Common }, + { "Coptic", PT_SC, ucp_Coptic }, + { "Cs", PT_PC, ucp_Cs }, + { "Cypriot", PT_SC, ucp_Cypriot }, + { "Cyrillic", PT_SC, ucp_Cyrillic }, + { "Deseret", PT_SC, ucp_Deseret }, + { "Devanagari", PT_SC, ucp_Devanagari }, + { "Ethiopic", PT_SC, ucp_Ethiopic }, + { "Georgian", PT_SC, ucp_Georgian }, + { "Glagolitic", PT_SC, ucp_Glagolitic }, + { "Gothic", PT_SC, ucp_Gothic }, + { "Greek", PT_SC, ucp_Greek }, + { "Gujarati", PT_SC, ucp_Gujarati }, + { "Gurmukhi", PT_SC, ucp_Gurmukhi }, + { "Han", PT_SC, ucp_Han }, + { "Hangul", PT_SC, ucp_Hangul }, + { "Hanunoo", PT_SC, ucp_Hanunoo }, + { "Hebrew", PT_SC, ucp_Hebrew }, + { "Hiragana", PT_SC, ucp_Hiragana }, + { "Inherited", PT_SC, ucp_Inherited }, + { "Kannada", PT_SC, ucp_Kannada }, + { "Katakana", PT_SC, ucp_Katakana }, + { "Kharoshthi", PT_SC, ucp_Kharoshthi }, + { "Khmer", PT_SC, ucp_Khmer }, + { "L", PT_GC, ucp_L }, + { "L&", PT_LAMP, 0 }, + { "Lao", PT_SC, ucp_Lao }, + { "Latin", PT_SC, ucp_Latin }, + { "Limbu", PT_SC, ucp_Limbu }, + { "Linear_B", PT_SC, ucp_Linear_B }, + { "Ll", PT_PC, ucp_Ll }, + { "Lm", PT_PC, ucp_Lm }, + { "Lo", PT_PC, ucp_Lo }, + { "Lt", PT_PC, ucp_Lt }, + { "Lu", PT_PC, ucp_Lu }, + { "M", PT_GC, ucp_M }, + { "Malayalam", PT_SC, ucp_Malayalam }, + { "Mc", PT_PC, ucp_Mc }, + { "Me", PT_PC, ucp_Me }, + { "Mn", PT_PC, ucp_Mn }, + { "Mongolian", PT_SC, ucp_Mongolian }, + { "Myanmar", PT_SC, ucp_Myanmar }, + { "N", PT_GC, ucp_N }, + { "Nd", PT_PC, ucp_Nd }, + { "New_Tai_Lue", PT_SC, ucp_New_Tai_Lue }, + { "Nl", PT_PC, ucp_Nl }, + { "No", PT_PC, ucp_No }, + { "Ogham", PT_SC, ucp_Ogham }, + { "Old_Italic", PT_SC, ucp_Old_Italic }, + { "Old_Persian", PT_SC, ucp_Old_Persian }, + { "Oriya", PT_SC, ucp_Oriya }, + { "Osmanya", PT_SC, ucp_Osmanya }, + { "P", PT_GC, ucp_P }, + { "Pc", PT_PC, ucp_Pc }, + { "Pd", PT_PC, ucp_Pd }, + { "Pe", PT_PC, ucp_Pe }, + { "Pf", PT_PC, ucp_Pf }, + { "Pi", PT_PC, ucp_Pi }, + { "Po", PT_PC, ucp_Po }, + { "Ps", PT_PC, ucp_Ps }, + { "Runic", PT_SC, ucp_Runic }, + { "S", PT_GC, ucp_S }, + { "Sc", PT_PC, ucp_Sc }, + { "Shavian", PT_SC, ucp_Shavian }, + { "Sinhala", PT_SC, ucp_Sinhala }, + { "Sk", PT_PC, ucp_Sk }, + { "Sm", PT_PC, ucp_Sm }, + { "So", PT_PC, ucp_So }, + { "Syloti_Nagri", PT_SC, ucp_Syloti_Nagri }, + { "Syriac", PT_SC, ucp_Syriac }, + { "Tagalog", PT_SC, ucp_Tagalog }, + { "Tagbanwa", PT_SC, ucp_Tagbanwa }, + { "Tai_Le", PT_SC, ucp_Tai_Le }, + { "Tamil", PT_SC, ucp_Tamil }, + { "Telugu", PT_SC, ucp_Telugu }, + { "Thaana", PT_SC, ucp_Thaana }, + { "Thai", PT_SC, ucp_Thai }, + { "Tibetan", PT_SC, ucp_Tibetan }, + { "Tifinagh", PT_SC, ucp_Tifinagh }, + { "Ugaritic", PT_SC, ucp_Ugaritic }, + { "Yi", PT_SC, ucp_Yi }, + { "Z", PT_GC, ucp_Z }, + { "Zl", PT_PC, ucp_Zl }, + { "Zp", PT_PC, ucp_Zp }, + { "Zs", PT_PC, ucp_Zs } +}; + +const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table); + +/* End of pcre_tables.c */ diff --git a/libs/pcre/pcre_try_flipped.c b/libs/pcre/pcre_try_flipped.c new file mode 100644 index 0000000000..00c94fccf5 --- /dev/null +++ b/libs/pcre/pcre_try_flipped.c @@ -0,0 +1,132 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains an internal function that tests a compiled pattern to +see if it was compiled with the opposite endianness. If so, it uses an +auxiliary local function to flip the appropriate bytes. */ + + +#include "pcre_internal.h" + + +/************************************************* +* Flip bytes in an integer * +*************************************************/ + +/* This function is called when the magic number in a regex doesn't match, in +order to flip its bytes to see if we are dealing with a pattern that was +compiled on a host of different endianness. If so, this function is used to +flip other byte values. + +Arguments: + value the number to flip + n the number of bytes to flip (assumed to be 2 or 4) + +Returns: the flipped value +*/ + +static unsigned long int +byteflip(unsigned long int value, int n) +{ +if (n == 2) return ((value & 0x00ff) << 8) | ((value & 0xff00) >> 8); +return ((value & 0x000000ff) << 24) | + ((value & 0x0000ff00) << 8) | + ((value & 0x00ff0000) >> 8) | + ((value & 0xff000000) >> 24); +} + + + +/************************************************* +* Test for a byte-flipped compiled regex * +*************************************************/ + +/* This function is called from pcre_exec(), pcre_dfa_exec(), and also from +pcre_fullinfo(). Its job is to test whether the regex is byte-flipped - that +is, it was compiled on a system of opposite endianness. The function is called +only when the native MAGIC_NUMBER test fails. If the regex is indeed flipped, +we flip all the relevant values into a different data block, and return it. + +Arguments: + re points to the regex + study points to study data, or NULL + internal_re points to a new regex block + internal_study points to a new study block + +Returns: the new block if is is indeed a byte-flipped regex + NULL if it is not +*/ + +real_pcre * +_pcre_try_flipped(const real_pcre *re, real_pcre *internal_re, + const pcre_study_data *study, pcre_study_data *internal_study) +{ +if (byteflip(re->magic_number, sizeof(re->magic_number)) != MAGIC_NUMBER) + return NULL; + +*internal_re = *re; /* To copy other fields */ +internal_re->size = byteflip(re->size, sizeof(re->size)); +internal_re->options = byteflip(re->options, sizeof(re->options)); +internal_re->top_bracket = + (pcre_uint16)byteflip(re->top_bracket, sizeof(re->top_bracket)); +internal_re->top_backref = + (pcre_uint16)byteflip(re->top_backref, sizeof(re->top_backref)); +internal_re->first_byte = + (pcre_uint16)byteflip(re->first_byte, sizeof(re->first_byte)); +internal_re->req_byte = + (pcre_uint16)byteflip(re->req_byte, sizeof(re->req_byte)); +internal_re->name_table_offset = + (pcre_uint16)byteflip(re->name_table_offset, sizeof(re->name_table_offset)); +internal_re->name_entry_size = + (pcre_uint16)byteflip(re->name_entry_size, sizeof(re->name_entry_size)); +internal_re->name_count = + (pcre_uint16)byteflip(re->name_count, sizeof(re->name_count)); + +if (study != NULL) + { + *internal_study = *study; /* To copy other fields */ + internal_study->size = byteflip(study->size, sizeof(study->size)); + internal_study->options = byteflip(study->options, sizeof(study->options)); + } + +return internal_re; +} + +/* End of pcre_tryflipped.c */ diff --git a/libs/pcre/pcre_ucp_searchfuncs.c b/libs/pcre/pcre_ucp_searchfuncs.c new file mode 100644 index 0000000000..7a4be94861 --- /dev/null +++ b/libs/pcre/pcre_ucp_searchfuncs.c @@ -0,0 +1,175 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains code for searching the table of Unicode character +properties. */ + +#include "pcre_internal.h" + +#include "ucp.h" /* Category definitions */ +#include "ucpinternal.h" /* Internal table details */ +#include "ucptable.c" /* The table itself */ + + +/* Table to translate from particular type value to the general value. */ + +static int ucp_gentype[] = { + ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */ + ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */ + ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */ + ucp_N, ucp_N, ucp_N, /* Nd, Nl, No */ + ucp_P, ucp_P, ucp_P, ucp_P, ucp_P, /* Pc, Pd, Pe, Pf, Pi */ + ucp_P, ucp_P, /* Ps, Po */ + ucp_S, ucp_S, ucp_S, ucp_S, /* Sc, Sk, Sm, So */ + ucp_Z, ucp_Z, ucp_Z /* Zl, Zp, Zs */ +}; + + + +/************************************************* +* Search table and return type * +*************************************************/ + +/* Three values are returned: the category is ucp_C, ucp_L, etc. The detailed +character type is ucp_Lu, ucp_Nd, etc. The script is ucp_Latin, etc. + +Arguments: + c the character value + type_ptr the detailed character type is returned here + script_ptr the script is returned here + +Returns: the character type category +*/ + +int +_pcre_ucp_findprop(const unsigned int c, int *type_ptr, int *script_ptr) +{ +int bot = 0; +int top = sizeof(ucp_table)/sizeof(cnode); +int mid; + +/* The table is searched using a binary chop. You might think that using +intermediate variables to hold some of the common expressions would speed +things up, but tests with gcc 3.4.4 on Linux showed that, on the contrary, it +makes things a lot slower. */ + +for (;;) + { + if (top <= bot) + { + *type_ptr = ucp_Cn; + *script_ptr = ucp_Common; + return ucp_C; + } + mid = (bot + top) >> 1; + if (c == (ucp_table[mid].f0 & f0_charmask)) break; + if (c < (ucp_table[mid].f0 & f0_charmask)) top = mid; + else + { + if ((ucp_table[mid].f0 & f0_rangeflag) != 0 && + c <= (ucp_table[mid].f0 & f0_charmask) + + (ucp_table[mid].f1 & f1_rangemask)) break; + bot = mid + 1; + } + } + +/* Found an entry in the table. Set the script and detailed type values, and +return the general type. */ + +*script_ptr = (ucp_table[mid].f0 & f0_scriptmask) >> f0_scriptshift; +*type_ptr = (ucp_table[mid].f1 & f1_typemask) >> f1_typeshift; + +return ucp_gentype[*type_ptr]; +} + + + +/************************************************* +* Search table and return other case * +*************************************************/ + +/* If the given character is a letter, and there is another case for the +letter, return the other case. Otherwise, return -1. + +Arguments: + c the character value + +Returns: the other case or -1 if none +*/ + +int +_pcre_ucp_othercase(const int c) +{ +int bot = 0; +int top = sizeof(ucp_table)/sizeof(cnode); +int mid, offset; + +/* The table is searched using a binary chop. You might think that using +intermediate variables to hold some of the common expressions would speed +things up, but tests with gcc 3.4.4 on Linux showed that, on the contrary, it +makes things a lot slower. */ + +for (;;) + { + if (top <= bot) return -1; + mid = (bot + top) >> 1; + if (c == (ucp_table[mid].f0 & f0_charmask)) break; + if (c < (ucp_table[mid].f0 & f0_charmask)) top = mid; + else + { + if ((ucp_table[mid].f0 & f0_rangeflag) != 0 && + c <= (ucp_table[mid].f0 & f0_charmask) + + (ucp_table[mid].f1 & f1_rangemask)) break; + bot = mid + 1; + } + } + +/* Found an entry in the table. Return -1 for a range entry. Otherwise return +the other case if there is one, else -1. */ + +if ((ucp_table[mid].f0 & f0_rangeflag) != 0) return -1; + +offset = ucp_table[mid].f1 & f1_casemask; +if ((offset & f1_caseneg) != 0) offset |= f1_caseneg; +return (offset == 0)? -1 : c + offset; +} + + +/* End of pcre_ucp_searchfuncs.c */ diff --git a/libs/pcre/pcre_valid_utf8.c b/libs/pcre/pcre_valid_utf8.c new file mode 100644 index 0000000000..1c6094a0c9 --- /dev/null +++ b/libs/pcre/pcre_valid_utf8.c @@ -0,0 +1,130 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains an internal function for validating UTF-8 character +strings. */ + + +#include "pcre_internal.h" + + +/************************************************* +* Validate a UTF-8 string * +*************************************************/ + +/* This function is called (optionally) at the start of compile or match, to +validate that a supposed UTF-8 string is actually valid. The early check means +that subsequent code can assume it is dealing with a valid string. The check +can be turned off for maximum performance, but the consequences of supplying +an invalid string are then undefined. + +Arguments: + string points to the string + length length of string, or -1 if the string is zero-terminated + +Returns: < 0 if the string is a valid UTF-8 string + >= 0 otherwise; the value is the offset of the bad byte +*/ + +int +_pcre_valid_utf8(const uschar *string, int length) +{ +register const uschar *p; + +if (length < 0) + { + for (p = string; *p != 0; p++); + length = p - string; + } + +for (p = string; length-- > 0; p++) + { + register int ab; + register int c = *p; + if (c < 128) continue; + if ((c & 0xc0) != 0xc0) return p - string; + ab = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ + if (length < ab) return p - string; + length -= ab; + + /* Check top bits in the second byte */ + if ((*(++p) & 0xc0) != 0x80) return p - string; + + /* Check for overlong sequences for each different length */ + switch (ab) + { + /* Check for xx00 000x */ + case 1: + if ((c & 0x3e) == 0) return p - string; + continue; /* We know there aren't any more bytes to check */ + + /* Check for 1110 0000, xx0x xxxx */ + case 2: + if (c == 0xe0 && (*p & 0x20) == 0) return p - string; + break; + + /* Check for 1111 0000, xx00 xxxx */ + case 3: + if (c == 0xf0 && (*p & 0x30) == 0) return p - string; + break; + + /* Check for 1111 1000, xx00 0xxx */ + case 4: + if (c == 0xf8 && (*p & 0x38) == 0) return p - string; + break; + + /* Check for leading 0xfe or 0xff, and then for 1111 1100, xx00 00xx */ + case 5: + if (c == 0xfe || c == 0xff || + (c == 0xfc && (*p & 0x3c) == 0)) return p - string; + break; + } + + /* Check for valid bytes after the 2nd, if any; all must start 10 */ + while (--ab > 0) + { + if ((*(++p) & 0xc0) != 0x80) return p - string; + } + } + +return -1; +} + +/* End of pcre_valid_utf8.c */ diff --git a/libs/pcre/pcre_version.c b/libs/pcre/pcre_version.c new file mode 100644 index 0000000000..c2aad4da06 --- /dev/null +++ b/libs/pcre/pcre_version.c @@ -0,0 +1,64 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains the external function pcre_version(), which returns a +string that identifies the PCRE version that is in use. */ + + +#include "pcre_internal.h" + + +/************************************************* +* Return version string * +*************************************************/ + +#define STRING(a) # a +#define XSTRING(s) STRING(s) + +PCRE_DATA_SCOPE const char * +pcre_version(void) +{ +return XSTRING(PCRE_MAJOR) + "." XSTRING(PCRE_MINOR) + XSTRING(PCRE_PRERELEASE) + " " XSTRING(PCRE_DATE); +} + +/* End of pcre_version.c */ diff --git a/libs/pcre/pcre_xclass.c b/libs/pcre/pcre_xclass.c new file mode 100644 index 0000000000..57c514b78a --- /dev/null +++ b/libs/pcre/pcre_xclass.c @@ -0,0 +1,144 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module contains an internal function that is used to match an extended +class (one that contains characters whose values are > 255). It is used by both +pcre_exec() and pcre_def_exec(). */ + + +#include "pcre_internal.h" + + +/************************************************* +* Match character against an XCLASS * +*************************************************/ + +/* This function is called to match a character against an extended class that +might contain values > 255. + +Arguments: + c the character + data points to the flag byte of the XCLASS data + +Returns: TRUE if character matches, else FALSE +*/ + +BOOL +_pcre_xclass(int c, const uschar *data) +{ +int t; +BOOL negated = (*data & XCL_NOT) != 0; + +/* Character values < 256 are matched against a bitmap, if one is present. If +not, we still carry on, because there may be ranges that start below 256 in the +additional data. */ + +if (c < 256) + { + if ((*data & XCL_MAP) != 0 && (data[1 + c/8] & (1 << (c&7))) != 0) + return !negated; /* char found */ + } + +/* First skip the bit map if present. Then match against the list of Unicode +properties or large chars or ranges that end with a large char. We won't ever +encounter XCL_PROP or XCL_NOTPROP when UCP support is not compiled. */ + +if ((*data++ & XCL_MAP) != 0) data += 32; + +while ((t = *data++) != XCL_END) + { + int x, y; + if (t == XCL_SINGLE) + { + GETCHARINC(x, data); + if (c == x) return !negated; + } + else if (t == XCL_RANGE) + { + GETCHARINC(x, data); + GETCHARINC(y, data); + if (c >= x && c <= y) return !negated; + } + +#ifdef SUPPORT_UCP + else /* XCL_PROP & XCL_NOTPROP */ + { + int chartype, script; + int category = _pcre_ucp_findprop(c, &chartype, &script); + + switch(*data) + { + case PT_ANY: + if (t == XCL_PROP) return !negated; + break; + + case PT_LAMP: + if ((chartype == ucp_Lu || chartype == ucp_Ll || chartype == ucp_Lt) == + (t == XCL_PROP)) return !negated; + break; + + case PT_GC: + if ((data[1] == category) == (t == XCL_PROP)) return !negated; + break; + + case PT_PC: + if ((data[1] == chartype) == (t == XCL_PROP)) return !negated; + break; + + case PT_SC: + if ((data[1] == script) == (t == XCL_PROP)) return !negated; + break; + + /* This should never occur, but compilers may mutter if there is no + default. */ + + default: + return FALSE; + } + + data += 2; + } +#endif /* SUPPORT_UCP */ + } + +return negated; /* char did not match */ +} + +/* End of pcre_xclass.c */ diff --git a/libs/pcre/pcrecpp.cc b/libs/pcre/pcrecpp.cc new file mode 100644 index 0000000000..f828de732e --- /dev/null +++ b/libs/pcre/pcrecpp.cc @@ -0,0 +1,823 @@ +// Copyright (c) 2005, Google Inc. +// All rights reserved. +// +// Redistribution and use in source and binary forms, with or without +// modification, are permitted provided that the following conditions are +// met: +// +// * Redistributions of source code must retain the above copyright +// notice, this list of conditions and the following disclaimer. +// * Redistributions in binary form must reproduce the above +// copyright notice, this list of conditions and the following disclaimer +// in the documentation and/or other materials provided with the +// distribution. +// * Neither the name of Google Inc. nor the names of its +// contributors may be used to endorse or promote products derived from +// this software without specific prior written permission. +// +// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +// +// Author: Sanjay Ghemawat + +#include +#include +#include +#include /* for SHRT_MIN, USHRT_MAX, etc */ +#include +#include +#include +#include +#include "config.h" +// We need this to compile the proper dll on windows/msys. This is copied +// from pcre_internal.h. It would probably be better just to include that. +#define PCRE_DEFINITION /* Win32 __declspec(export) trigger for .dll */ +#include "pcre.h" +#include "pcre_stringpiece.h" +#include "pcrecpp.h" + + +namespace pcrecpp { + +// Maximum number of args we can set +static const int kMaxArgs = 16; +static const int kVecSize = (1 + kMaxArgs) * 3; // results + PCRE workspace + +// Special object that stands-in for no argument +Arg no_arg((void*)NULL); + +// If a regular expression has no error, its error_ field points here +static const string empty_string; + +// If the user doesn't ask for any options, we just use this one +static RE_Options default_options; + +void RE::Init(const char* pat, const RE_Options* options) { + pattern_ = pat; + if (options == NULL) { + options_ = default_options; + } else { + options_ = *options; + } + error_ = &empty_string; + re_full_ = NULL; + re_partial_ = NULL; + + re_partial_ = Compile(UNANCHORED); + if (re_partial_ != NULL) { + // Check for complicated patterns. The following change is + // conservative in that it may treat some "simple" patterns + // as "complex" (e.g., if the vertical bar is in a character + // class or is escaped). But it seems good enough. + if (strchr(pat, '|') == NULL) { + // Simple pattern: we can use position-based checks to perform + // fully anchored matches + re_full_ = re_partial_; + } else { + // We need a special pattern for anchored matches + re_full_ = Compile(ANCHOR_BOTH); + } + } +} + +RE::~RE() { + if (re_full_ != NULL && re_full_ != re_partial_) (*pcre_free)(re_full_); + if (re_partial_ != NULL) (*pcre_free)(re_partial_); + if (error_ != &empty_string) delete error_; +} + +pcre* RE::Compile(Anchor anchor) { + // First, convert RE_Options into pcre options + int pcre_options = 0; + pcre_options = options_.all_options(); + + // Special treatment for anchoring. This is needed because at + // runtime pcre only provides an option for anchoring at the + // beginning of a string (unless you use offset). + // + // There are three types of anchoring we want: + // UNANCHORED Compile the original pattern, and use + // a pcre unanchored match. + // ANCHOR_START Compile the original pattern, and use + // a pcre anchored match. + // ANCHOR_BOTH Tack a "\z" to the end of the original pattern + // and use a pcre anchored match. + + const char* compile_error; + int eoffset; + pcre* re; + if (anchor != ANCHOR_BOTH) { + re = pcre_compile(pattern_.c_str(), pcre_options, + &compile_error, &eoffset, NULL); + } else { + // Tack a '\z' at the end of RE. Parenthesize it first so that + // the '\z' applies to all top-level alternatives in the regexp. + string wrapped = "(?:"; // A non-counting grouping operator + wrapped += pattern_; + wrapped += ")\\z"; + re = pcre_compile(wrapped.c_str(), pcre_options, + &compile_error, &eoffset, NULL); + } + if (re == NULL) { + if (error_ == &empty_string) error_ = new string(compile_error); + } + return re; +} + +/***** Matching interfaces *****/ + +bool RE::FullMatch(const StringPiece& text, + const Arg& ptr1, + const Arg& ptr2, + const Arg& ptr3, + const Arg& ptr4, + const Arg& ptr5, + const Arg& ptr6, + const Arg& ptr7, + const Arg& ptr8, + const Arg& ptr9, + const Arg& ptr10, + const Arg& ptr11, + const Arg& ptr12, + const Arg& ptr13, + const Arg& ptr14, + const Arg& ptr15, + const Arg& ptr16) const { + const Arg* args[kMaxArgs]; + int n = 0; + if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1; + if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2; + if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3; + if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4; + if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5; + if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6; + if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7; + if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8; + if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9; + if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10; + if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11; + if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12; + if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13; + if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14; + if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15; + if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16; + done: + + int consumed; + int vec[kVecSize]; + return DoMatchImpl(text, ANCHOR_BOTH, &consumed, args, n, vec, kVecSize); +} + +bool RE::PartialMatch(const StringPiece& text, + const Arg& ptr1, + const Arg& ptr2, + const Arg& ptr3, + const Arg& ptr4, + const Arg& ptr5, + const Arg& ptr6, + const Arg& ptr7, + const Arg& ptr8, + const Arg& ptr9, + const Arg& ptr10, + const Arg& ptr11, + const Arg& ptr12, + const Arg& ptr13, + const Arg& ptr14, + const Arg& ptr15, + const Arg& ptr16) const { + const Arg* args[kMaxArgs]; + int n = 0; + if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1; + if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2; + if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3; + if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4; + if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5; + if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6; + if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7; + if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8; + if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9; + if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10; + if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11; + if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12; + if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13; + if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14; + if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15; + if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16; + done: + + int consumed; + int vec[kVecSize]; + return DoMatchImpl(text, UNANCHORED, &consumed, args, n, vec, kVecSize); +} + +bool RE::Consume(StringPiece* input, + const Arg& ptr1, + const Arg& ptr2, + const Arg& ptr3, + const Arg& ptr4, + const Arg& ptr5, + const Arg& ptr6, + const Arg& ptr7, + const Arg& ptr8, + const Arg& ptr9, + const Arg& ptr10, + const Arg& ptr11, + const Arg& ptr12, + const Arg& ptr13, + const Arg& ptr14, + const Arg& ptr15, + const Arg& ptr16) const { + const Arg* args[kMaxArgs]; + int n = 0; + if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1; + if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2; + if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3; + if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4; + if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5; + if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6; + if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7; + if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8; + if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9; + if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10; + if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11; + if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12; + if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13; + if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14; + if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15; + if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16; + done: + + int consumed; + int vec[kVecSize]; + if (DoMatchImpl(*input, ANCHOR_START, &consumed, + args, n, vec, kVecSize)) { + input->remove_prefix(consumed); + return true; + } else { + return false; + } +} + +bool RE::FindAndConsume(StringPiece* input, + const Arg& ptr1, + const Arg& ptr2, + const Arg& ptr3, + const Arg& ptr4, + const Arg& ptr5, + const Arg& ptr6, + const Arg& ptr7, + const Arg& ptr8, + const Arg& ptr9, + const Arg& ptr10, + const Arg& ptr11, + const Arg& ptr12, + const Arg& ptr13, + const Arg& ptr14, + const Arg& ptr15, + const Arg& ptr16) const { + const Arg* args[kMaxArgs]; + int n = 0; + if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1; + if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2; + if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3; + if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4; + if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5; + if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6; + if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7; + if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8; + if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9; + if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10; + if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11; + if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12; + if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13; + if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14; + if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15; + if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16; + done: + + int consumed; + int vec[kVecSize]; + if (DoMatchImpl(*input, UNANCHORED, &consumed, + args, n, vec, kVecSize)) { + input->remove_prefix(consumed); + return true; + } else { + return false; + } +} + +bool RE::Replace(const StringPiece& rewrite, + string *str) const { + int vec[kVecSize]; + int matches = TryMatch(*str, 0, UNANCHORED, vec, kVecSize); + if (matches == 0) + return false; + + string s; + if (!Rewrite(&s, rewrite, *str, vec, matches)) + return false; + + assert(vec[0] >= 0); + assert(vec[1] >= 0); + str->replace(vec[0], vec[1] - vec[0], s); + return true; +} + +// Returns PCRE_NEWLINE_CRLF, PCRE_NEWLINE_CR, or PCRE_NEWLINE_LF. +// Note that PCRE_NEWLINE_CRLF is defined to be P_N_CR | P_N_LF. +static int NewlineMode(int pcre_options) { + // TODO: if we can make it threadsafe, cache this var + int newline_mode = 0; + /* if (newline_mode) return newline_mode; */ // do this once it's cached + if (pcre_options & (PCRE_NEWLINE_CRLF|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF)) { + newline_mode = (pcre_options & + (PCRE_NEWLINE_CRLF|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF)); + } else { + int newline; + pcre_config(PCRE_CONFIG_NEWLINE, &newline); + if (newline == 10) + newline_mode = PCRE_NEWLINE_LF; + else if (newline == 13) + newline_mode = PCRE_NEWLINE_CR; + else if (newline == 3338) + newline_mode = PCRE_NEWLINE_CRLF; + else + assert("" == "Unexpected return value from pcre_config(NEWLINE)"); + } + return newline_mode; +} + +int RE::GlobalReplace(const StringPiece& rewrite, + string *str) const { + int count = 0; + int vec[kVecSize]; + string out; + int start = 0; + int lastend = -1; + + for (; start <= static_cast(str->length()); count++) { + int matches = TryMatch(*str, start, UNANCHORED, vec, kVecSize); + if (matches <= 0) + break; + int matchstart = vec[0], matchend = vec[1]; + assert(matchstart >= start); + assert(matchend >= matchstart); + if (matchstart == matchend && matchstart == lastend) { + // advance one character if we matched an empty string at the same + // place as the last match occurred + matchend = start + 1; + // If the current char is CR and we're in CRLF mode, skip LF too. + // Note it's better to call pcre_fullinfo() than to examine + // all_options(), since options_ could have changed bewteen + // compile-time and now, but this is simpler and safe enough. + if (start+1 < static_cast(str->length()) && + (*str)[start] == '\r' && (*str)[start+1] == '\n' && + NewlineMode(options_.all_options()) == PCRE_NEWLINE_CRLF) { + matchend++; + } + // We also need to advance more than one char if we're in utf8 mode. +#ifdef SUPPORT_UTF8 + if (options_.utf8()) { + while (matchend < static_cast(str->length()) && + ((*str)[matchend] & 0xc0) == 0x80) + matchend++; + } +#endif + if (matchend <= static_cast(str->length())) + out.append(*str, start, matchend - start); + start = matchend; + } else { + out.append(*str, start, matchstart - start); + Rewrite(&out, rewrite, *str, vec, matches); + start = matchend; + lastend = matchend; + count++; + } + } + + if (count == 0) + return 0; + + if (start < static_cast(str->length())) + out.append(*str, start, str->length() - start); + swap(out, *str); + return count; +} + +bool RE::Extract(const StringPiece& rewrite, + const StringPiece& text, + string *out) const { + int vec[kVecSize]; + int matches = TryMatch(text, 0, UNANCHORED, vec, kVecSize); + if (matches == 0) + return false; + out->erase(); + return Rewrite(out, rewrite, text, vec, matches); +} + +/***** Actual matching and rewriting code *****/ + +int RE::TryMatch(const StringPiece& text, + int startpos, + Anchor anchor, + int *vec, + int vecsize) const { + pcre* re = (anchor == ANCHOR_BOTH) ? re_full_ : re_partial_; + if (re == NULL) { + //fprintf(stderr, "Matching against invalid re: %s\n", error_->c_str()); + return 0; + } + + pcre_extra extra = { 0 }; + if (options_.match_limit() > 0) { + extra.flags |= PCRE_EXTRA_MATCH_LIMIT; + extra.match_limit = options_.match_limit(); + } + if (options_.match_limit_recursion() > 0) { + extra.flags |= PCRE_EXTRA_MATCH_LIMIT_RECURSION; + extra.match_limit_recursion = options_.match_limit_recursion(); + } + int rc = pcre_exec(re, // The regular expression object + &extra, + (text.data() == NULL) ? "" : text.data(), + text.size(), + startpos, + (anchor == UNANCHORED) ? 0 : PCRE_ANCHORED, + vec, + vecsize); + + // Handle errors + if (rc == PCRE_ERROR_NOMATCH) { + return 0; + } else if (rc < 0) { + //fprintf(stderr, "Unexpected return code: %d when matching '%s'\n", + // re, pattern_.c_str()); + return 0; + } else if (rc == 0) { + // pcre_exec() returns 0 as a special case when the number of + // capturing subpatterns exceeds the size of the vector. + // When this happens, there is a match and the output vector + // is filled, but we miss out on the positions of the extra subpatterns. + rc = vecsize / 2; + } + + if ((anchor == ANCHOR_BOTH) && (re_full_ == re_partial_)) { + // We need an extra check to make sure that the match extended + // to the end of the input string + assert(vec[0] == 0); // PCRE_ANCHORED forces starting match + if (vec[1] != text.size()) return 0; // Did not get ending match + } + + return rc; +} + +bool RE::DoMatchImpl(const StringPiece& text, + Anchor anchor, + int* consumed, + const Arg* const* args, + int n, + int* vec, + int vecsize) const { + assert((1 + n) * 3 <= vecsize); // results + PCRE workspace + int matches = TryMatch(text, 0, anchor, vec, vecsize); + assert(matches >= 0); // TryMatch never returns negatives + if (matches == 0) + return false; + + *consumed = vec[1]; + + if (n == 0 || args == NULL) { + // We are not interested in results + return true; + } + + if (NumberOfCapturingGroups() < n) { + // RE has fewer capturing groups than number of arg pointers passed in + return false; + } + + // If we got here, we must have matched the whole pattern. + // We do not need (can not do) any more checks on the value of 'matches' here + // -- see the comment for TryMatch. + for (int i = 0; i < n; i++) { + const int start = vec[2*(i+1)]; + const int limit = vec[2*(i+1)+1]; + if (!args[i]->Parse(text.data() + start, limit-start)) { + // TODO: Should we indicate what the error was? + return false; + } + } + + return true; +} + +bool RE::DoMatch(const StringPiece& text, + Anchor anchor, + int* consumed, + const Arg* const args[], + int n) const { + assert(n >= 0); + size_t const vecsize = (1 + n) * 3; // results + PCRE workspace + // (as for kVecSize) + int space[21]; // use stack allocation for small vecsize (common case) + int* vec = vecsize <= 21 ? space : new int[vecsize]; + bool retval = DoMatchImpl(text, anchor, consumed, args, n, vec, vecsize); + if (vec != space) delete [] vec; + return retval; +} + +bool RE::Rewrite(string *out, const StringPiece &rewrite, + const StringPiece &text, int *vec, int veclen) const { + for (const char *s = rewrite.data(), *end = s + rewrite.size(); + s < end; s++) { + int c = *s; + if (c == '\\') { + c = *++s; + if (isdigit(c)) { + int n = (c - '0'); + if (n >= veclen) { + //fprintf(stderr, requested group %d in regexp %.*s\n", + // n, rewrite.size(), rewrite.data()); + return false; + } + int start = vec[2 * n]; + if (start >= 0) + out->append(text.data() + start, vec[2 * n + 1] - start); + } else if (c == '\\') { + out->push_back('\\'); + } else { + //fprintf(stderr, "invalid rewrite pattern: %.*s\n", + // rewrite.size(), rewrite.data()); + return false; + } + } else { + out->push_back(c); + } + } + return true; +} + +// Return the number of capturing subpatterns, or -1 if the +// regexp wasn't valid on construction. +int RE::NumberOfCapturingGroups() const { + if (re_partial_ == NULL) return -1; + + int result; + int pcre_retval = pcre_fullinfo(re_partial_, // The regular expression object + NULL, // We did not study the pattern + PCRE_INFO_CAPTURECOUNT, + &result); + assert(pcre_retval == 0); + return result; +} + +/***** Parsers for various types *****/ + +bool Arg::parse_null(const char* str, int n, void* dest) { + // We fail if somebody asked us to store into a non-NULL void* pointer + return (dest == NULL); +} + +bool Arg::parse_string(const char* str, int n, void* dest) { + reinterpret_cast(dest)->assign(str, n); + return true; +} + +bool Arg::parse_stringpiece(const char* str, int n, void* dest) { + reinterpret_cast(dest)->set(str, n); + return true; +} + +bool Arg::parse_char(const char* str, int n, void* dest) { + if (n != 1) return false; + *(reinterpret_cast(dest)) = str[0]; + return true; +} + +bool Arg::parse_uchar(const char* str, int n, void* dest) { + if (n != 1) return false; + *(reinterpret_cast(dest)) = str[0]; + return true; +} + +// Largest number spec that we are willing to parse +static const int kMaxNumberLength = 32; + +// REQUIRES "buf" must have length at least kMaxNumberLength+1 +// REQUIRES "n > 0" +// Copies "str" into "buf" and null-terminates if necessary. +// Returns one of: +// a. "str" if no termination is needed +// b. "buf" if the string was copied and null-terminated +// c. "" if the input was invalid and has no hope of being parsed +static const char* TerminateNumber(char* buf, const char* str, int n) { + if ((n > 0) && isspace(*str)) { + // We are less forgiving than the strtoxxx() routines and do not + // allow leading spaces. + return ""; + } + + // See if the character right after the input text may potentially + // look like a digit. + if (isdigit(str[n]) || + ((str[n] >= 'a') && (str[n] <= 'f')) || + ((str[n] >= 'A') && (str[n] <= 'F'))) { + if (n > kMaxNumberLength) return ""; // Input too big to be a valid number + memcpy(buf, str, n); + buf[n] = '\0'; + return buf; + } else { + // We can parse right out of the supplied string, so return it. + return str; + } +} + +bool Arg::parse_long_radix(const char* str, + int n, + void* dest, + int radix) { + if (n == 0) return false; + char buf[kMaxNumberLength+1]; + str = TerminateNumber(buf, str, n); + char* end; + errno = 0; + long r = strtol(str, &end, radix); + if (end != str + n) return false; // Leftover junk + if (errno) return false; + *(reinterpret_cast(dest)) = r; + return true; +} + +bool Arg::parse_ulong_radix(const char* str, + int n, + void* dest, + int radix) { + if (n == 0) return false; + char buf[kMaxNumberLength+1]; + str = TerminateNumber(buf, str, n); + if (str[0] == '-') return false; // strtoul() on a negative number?! + char* end; + errno = 0; + unsigned long r = strtoul(str, &end, radix); + if (end != str + n) return false; // Leftover junk + if (errno) return false; + *(reinterpret_cast(dest)) = r; + return true; +} + +bool Arg::parse_short_radix(const char* str, + int n, + void* dest, + int radix) { + long r; + if (!parse_long_radix(str, n, &r, radix)) return false; // Could not parse + if (r < SHRT_MIN || r > SHRT_MAX) return false; // Out of range + *(reinterpret_cast(dest)) = r; + return true; +} + +bool Arg::parse_ushort_radix(const char* str, + int n, + void* dest, + int radix) { + unsigned long r; + if (!parse_ulong_radix(str, n, &r, radix)) return false; // Could not parse + if (r > USHRT_MAX) return false; // Out of range + *(reinterpret_cast(dest)) = r; + return true; +} + +bool Arg::parse_int_radix(const char* str, + int n, + void* dest, + int radix) { + long r; + if (!parse_long_radix(str, n, &r, radix)) return false; // Could not parse + if (r < INT_MIN || r > INT_MAX) return false; // Out of range + *(reinterpret_cast(dest)) = r; + return true; +} + +bool Arg::parse_uint_radix(const char* str, + int n, + void* dest, + int radix) { + unsigned long r; + if (!parse_ulong_radix(str, n, &r, radix)) return false; // Could not parse + if (r > UINT_MAX) return false; // Out of range + *(reinterpret_cast(dest)) = r; + return true; +} + +bool Arg::parse_longlong_radix(const char* str, + int n, + void* dest, + int radix) { +#ifndef HAVE_LONG_LONG + return false; +#else + if (n == 0) return false; + char buf[kMaxNumberLength+1]; + str = TerminateNumber(buf, str, n); + char* end; + errno = 0; +#if defined HAVE_STRTOQ + long long r = strtoq(str, &end, radix); +#elif defined HAVE_STRTOLL + long long r = strtoll(str, &end, radix); +#else +#error parse_longlong_radix: cannot convert input to a long-long +#endif + if (end != str + n) return false; // Leftover junk + if (errno) return false; + *(reinterpret_cast(dest)) = r; + return true; +#endif /* HAVE_LONG_LONG */ +} + +bool Arg::parse_ulonglong_radix(const char* str, + int n, + void* dest, + int radix) { +#ifndef HAVE_UNSIGNED_LONG_LONG + return false; +#else + if (n == 0) return false; + char buf[kMaxNumberLength+1]; + str = TerminateNumber(buf, str, n); + if (str[0] == '-') return false; // strtoull() on a negative number?! + char* end; + errno = 0; +#if defined HAVE_STRTOQ + unsigned long long r = strtouq(str, &end, radix); +#elif defined HAVE_STRTOLL + unsigned long long r = strtoull(str, &end, radix); +#else +#error parse_ulonglong_radix: cannot convert input to a long-long +#endif + if (end != str + n) return false; // Leftover junk + if (errno) return false; + *(reinterpret_cast(dest)) = r; + return true; +#endif /* HAVE_UNSIGNED_LONG_LONG */ +} + +bool Arg::parse_double(const char* str, int n, void* dest) { + if (n == 0) return false; + static const int kMaxLength = 200; + char buf[kMaxLength]; + if (n >= kMaxLength) return false; + memcpy(buf, str, n); + buf[n] = '\0'; + errno = 0; + char* end; + double r = strtod(buf, &end); + if (end != buf + n) return false; // Leftover junk + if (errno) return false; + *(reinterpret_cast(dest)) = r; + return true; +} + +bool Arg::parse_float(const char* str, int n, void* dest) { + double r; + if (!parse_double(str, n, &r)) return false; + *(reinterpret_cast(dest)) = static_cast(r); + return true; +} + + +#define DEFINE_INTEGER_PARSERS(name) \ + bool Arg::parse_##name(const char* str, int n, void* dest) { \ + return parse_##name##_radix(str, n, dest, 10); \ + } \ + bool Arg::parse_##name##_hex(const char* str, int n, void* dest) { \ + return parse_##name##_radix(str, n, dest, 16); \ + } \ + bool Arg::parse_##name##_octal(const char* str, int n, void* dest) { \ + return parse_##name##_radix(str, n, dest, 8); \ + } \ + bool Arg::parse_##name##_cradix(const char* str, int n, void* dest) { \ + return parse_##name##_radix(str, n, dest, 0); \ + } + +DEFINE_INTEGER_PARSERS(short); +DEFINE_INTEGER_PARSERS(ushort); +DEFINE_INTEGER_PARSERS(int); +DEFINE_INTEGER_PARSERS(uint); +DEFINE_INTEGER_PARSERS(long); +DEFINE_INTEGER_PARSERS(ulong); +DEFINE_INTEGER_PARSERS(longlong); +DEFINE_INTEGER_PARSERS(ulonglong); + +#undef DEFINE_INTEGER_PARSERS + +} // namespace pcrecpp diff --git a/libs/pcre/pcrecpp.h b/libs/pcre/pcrecpp.h new file mode 100644 index 0000000000..5916d86432 --- /dev/null +++ b/libs/pcre/pcrecpp.h @@ -0,0 +1,667 @@ +// Copyright (c) 2005, Google Inc. +// All rights reserved. +// +// Redistribution and use in source and binary forms, with or without +// modification, are permitted provided that the following conditions are +// met: +// +// * Redistributions of source code must retain the above copyright +// notice, this list of conditions and the following disclaimer. +// * Redistributions in binary form must reproduce the above +// copyright notice, this list of conditions and the following disclaimer +// in the documentation and/or other materials provided with the +// distribution. +// * Neither the name of Google Inc. nor the names of its +// contributors may be used to endorse or promote products derived from +// this software without specific prior written permission. +// +// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +// +// Author: Sanjay Ghemawat +// Support for PCRE_XXX modifiers added by Giuseppe Maxia, July 2005 + +#ifndef _PCRECPP_H +#define _PCRECPP_H + +// C++ interface to the pcre regular-expression library. RE supports +// Perl-style regular expressions (with extensions like \d, \w, \s, +// ...). +// +// ----------------------------------------------------------------------- +// REGEXP SYNTAX: +// +// This module is part of the pcre library and hence supports its syntax +// for regular expressions. +// +// The syntax is pretty similar to Perl's. For those not familiar +// with Perl's regular expressions, here are some examples of the most +// commonly used extensions: +// +// "hello (\\w+) world" -- \w matches a "word" character +// "version (\\d+)" -- \d matches a digit +// "hello\\s+world" -- \s matches any whitespace character +// "\\b(\\w+)\\b" -- \b matches empty string at a word boundary +// "(?i)hello" -- (?i) turns on case-insensitive matching +// "/\\*(.*?)\\*/" -- .*? matches . minimum no. of times possible +// +// ----------------------------------------------------------------------- +// MATCHING INTERFACE: +// +// The "FullMatch" operation checks that supplied text matches a +// supplied pattern exactly. +// +// Example: successful match +// pcrecpp::RE re("h.*o"); +// re.FullMatch("hello"); +// +// Example: unsuccessful match (requires full match): +// pcrecpp::RE re("e"); +// !re.FullMatch("hello"); +// +// Example: creating a temporary RE object: +// pcrecpp::RE("h.*o").FullMatch("hello"); +// +// You can pass in a "const char*" or a "string" for "text". The +// examples below tend to use a const char*. +// +// You can, as in the different examples above, store the RE object +// explicitly in a variable or use a temporary RE object. The +// examples below use one mode or the other arbitrarily. Either +// could correctly be used for any of these examples. +// +// ----------------------------------------------------------------------- +// MATCHING WITH SUB-STRING EXTRACTION: +// +// You can supply extra pointer arguments to extract matched subpieces. +// +// Example: extracts "ruby" into "s" and 1234 into "i" +// int i; +// string s; +// pcrecpp::RE re("(\\w+):(\\d+)"); +// re.FullMatch("ruby:1234", &s, &i); +// +// Example: does not try to extract any extra sub-patterns +// re.FullMatch("ruby:1234", &s); +// +// Example: does not try to extract into NULL +// re.FullMatch("ruby:1234", NULL, &i); +// +// Example: integer overflow causes failure +// !re.FullMatch("ruby:1234567891234", NULL, &i); +// +// Example: fails because there aren't enough sub-patterns: +// !pcrecpp::RE("\\w+:\\d+").FullMatch("ruby:1234", &s); +// +// Example: fails because string cannot be stored in integer +// !pcrecpp::RE("(.*)").FullMatch("ruby", &i); +// +// The provided pointer arguments can be pointers to any scalar numeric +// type, or one of +// string (matched piece is copied to string) +// StringPiece (StringPiece is mutated to point to matched piece) +// T (where "bool T::ParseFrom(const char*, int)" exists) +// NULL (the corresponding matched sub-pattern is not copied) +// +// ----------------------------------------------------------------------- +// DO_MATCH +// +// The matching interface supports at most 16 arguments per call. +// If you need more, consider using the more general interface +// pcrecpp::RE::DoMatch(). See pcrecpp.h for the signature for DoMatch. +// +// ----------------------------------------------------------------------- +// PARTIAL MATCHES +// +// You can use the "PartialMatch" operation when you want the pattern +// to match any substring of the text. +// +// Example: simple search for a string: +// pcrecpp::RE("ell").PartialMatch("hello"); +// +// Example: find first number in a string: +// int number; +// pcrecpp::RE re("(\\d+)"); +// re.PartialMatch("x*100 + 20", &number); +// assert(number == 100); +// +// ----------------------------------------------------------------------- +// UTF-8 AND THE MATCHING INTERFACE: +// +// By default, pattern and text are plain text, one byte per character. +// The UTF8 flag, passed to the constructor, causes both pattern +// and string to be treated as UTF-8 text, still a byte stream but +// potentially multiple bytes per character. In practice, the text +// is likelier to be UTF-8 than the pattern, but the match returned +// may depend on the UTF8 flag, so always use it when matching +// UTF8 text. E.g., "." will match one byte normally but with UTF8 +// set may match up to three bytes of a multi-byte character. +// +// Example: +// pcrecpp::RE_Options options; +// options.set_utf8(); +// pcrecpp::RE re(utf8_pattern, options); +// re.FullMatch(utf8_string); +// +// Example: using the convenience function UTF8(): +// pcrecpp::RE re(utf8_pattern, pcrecpp::UTF8()); +// re.FullMatch(utf8_string); +// +// NOTE: The UTF8 option is ignored if pcre was not configured with the +// --enable-utf8 flag. +// +// ----------------------------------------------------------------------- +// PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE +// +// PCRE defines some modifiers to change the behavior of the regular +// expression engine. +// The C++ wrapper defines an auxiliary class, RE_Options, as a vehicle +// to pass such modifiers to a RE class. +// +// Currently, the following modifiers are supported +// +// modifier description Perl corresponding +// +// PCRE_CASELESS case insensitive match /i +// PCRE_MULTILINE multiple lines match /m +// PCRE_DOTALL dot matches newlines /s +// PCRE_DOLLAR_ENDONLY $ matches only at end N/A +// PCRE_EXTRA strict escape parsing N/A +// PCRE_EXTENDED ignore whitespaces /x +// PCRE_UTF8 handles UTF8 chars built-in +// PCRE_UNGREEDY reverses * and *? N/A +// PCRE_NO_AUTO_CAPTURE disables matching parens N/A (*) +// +// (For a full account on how each modifier works, please check the +// PCRE API reference manual). +// +// (*) Both Perl and PCRE allow non matching parentheses by means of the +// "?:" modifier within the pattern itself. e.g. (?:ab|cd) does not +// capture, while (ab|cd) does. +// +// For each modifier, there are two member functions whose name is made +// out of the modifier in lowercase, without the "PCRE_" prefix. For +// instance, PCRE_CASELESS is handled by +// bool caseless(), +// which returns true if the modifier is set, and +// RE_Options & set_caseless(bool), +// which sets or unsets the modifier. +// +// Moreover, PCRE_EXTRA_MATCH_LIMIT can be accessed through the +// set_match_limit() and match_limit() member functions. +// Setting match_limit to a non-zero value will limit the executation of +// pcre to keep it from doing bad things like blowing the stack or taking +// an eternity to return a result. A value of 5000 is good enough to stop +// stack blowup in a 2MB thread stack. Setting match_limit to zero will +// disable match limiting. Alternately, you can set match_limit_recursion() +// which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION to limit how much pcre +// recurses. match_limit() caps the number of matches pcre does; +// match_limit_recrusion() caps the depth of recursion. +// +// Normally, to pass one or more modifiers to a RE class, you declare +// a RE_Options object, set the appropriate options, and pass this +// object to a RE constructor. Example: +// +// RE_options opt; +// opt.set_caseless(true); +// +// if (RE("HELLO", opt).PartialMatch("hello world")) ... +// +// RE_options has two constructors. The default constructor takes no +// arguments and creates a set of flags that are off by default. +// +// The optional parameter 'option_flags' is to facilitate transfer +// of legacy code from C programs. This lets you do +// RE(pattern, RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str); +// +// But new code is better off doing +// RE(pattern, +// RE_Options().set_caseless(true).set_multiline(true)).PartialMatch(str); +// (See below) +// +// If you are going to pass one of the most used modifiers, there are some +// convenience functions that return a RE_Options class with the +// appropriate modifier already set: +// CASELESS(), UTF8(), MULTILINE(), DOTALL(), EXTENDED() +// +// If you need to set several options at once, and you don't want to go +// through the pains of declaring a RE_Options object and setting several +// options, there is a parallel method that give you such ability on the +// fly. You can concatenate several set_xxxxx member functions, since each +// of them returns a reference to its class object. e.g.: to pass +// PCRE_CASELESS, PCRE_EXTENDED, and PCRE_MULTILINE to a RE with one +// statement, you may write +// +// RE(" ^ xyz \\s+ .* blah$", RE_Options() +// .set_caseless(true) +// .set_extended(true) +// .set_multiline(true)).PartialMatch(sometext); +// +// ----------------------------------------------------------------------- +// SCANNING TEXT INCREMENTALLY +// +// The "Consume" operation may be useful if you want to repeatedly +// match regular expressions at the front of a string and skip over +// them as they match. This requires use of the "StringPiece" type, +// which represents a sub-range of a real string. Like RE, StringPiece +// is defined in the pcrecpp namespace. +// +// Example: read lines of the form "var = value" from a string. +// string contents = ...; // Fill string somehow +// pcrecpp::StringPiece input(contents); // Wrap in a StringPiece +// +// string var; +// int value; +// pcrecpp::RE re("(\\w+) = (\\d+)\n"); +// while (re.Consume(&input, &var, &value)) { +// ...; +// } +// +// Each successful call to "Consume" will set "var/value", and also +// advance "input" so it points past the matched text. +// +// The "FindAndConsume" operation is similar to "Consume" but does not +// anchor your match at the beginning of the string. For example, you +// could extract all words from a string by repeatedly calling +// pcrecpp::RE("(\\w+)").FindAndConsume(&input, &word) +// +// ----------------------------------------------------------------------- +// PARSING HEX/OCTAL/C-RADIX NUMBERS +// +// By default, if you pass a pointer to a numeric value, the +// corresponding text is interpreted as a base-10 number. You can +// instead wrap the pointer with a call to one of the operators Hex(), +// Octal(), or CRadix() to interpret the text in another base. The +// CRadix operator interprets C-style "0" (base-8) and "0x" (base-16) +// prefixes, but defaults to base-10. +// +// Example: +// int a, b, c, d; +// pcrecpp::RE re("(.*) (.*) (.*) (.*)"); +// re.FullMatch("100 40 0100 0x40", +// pcrecpp::Octal(&a), pcrecpp::Hex(&b), +// pcrecpp::CRadix(&c), pcrecpp::CRadix(&d)); +// will leave 64 in a, b, c, and d. +// +// ----------------------------------------------------------------------- +// REPLACING PARTS OF STRINGS +// +// You can replace the first match of "pattern" in "str" with +// "rewrite". Within "rewrite", backslash-escaped digits (\1 to \9) +// can be used to insert text matching corresponding parenthesized +// group from the pattern. \0 in "rewrite" refers to the entire +// matching text. E.g., +// +// string s = "yabba dabba doo"; +// pcrecpp::RE("b+").Replace("d", &s); +// +// will leave "s" containing "yada dabba doo". The result is true if +// the pattern matches and a replacement occurs, or false otherwise. +// +// GlobalReplace() is like Replace(), except that it replaces all +// occurrences of the pattern in the string with the rewrite. +// Replacements are not subject to re-matching. E.g., +// +// string s = "yabba dabba doo"; +// pcrecpp::RE("b+").GlobalReplace("d", &s); +// +// will leave "s" containing "yada dada doo". It returns the number +// of replacements made. +// +// Extract() is like Replace(), except that if the pattern matches, +// "rewrite" is copied into "out" (an additional argument) with +// substitutions. The non-matching portions of "text" are ignored. +// Returns true iff a match occurred and the extraction happened +// successfully. If no match occurs, the string is left unaffected. + + +#include +#include // defines the Arg class +// These aren't technically needed here, but we include them +// anyway so folks who include pcrecpp.h don't have to include +// all these other header files as well. +#include +#include + +namespace pcrecpp { + +#define PCRE_SET_OR_CLEAR(b, o) \ + if (b) all_options_ |= (o); else all_options_ &= ~(o); \ + return *this + +#define PCRE_IS_SET(o) \ + (all_options_ & o) == o + +// We convert user-passed pointers into special Arg objects +extern Arg no_arg; + +/***** Compiling regular expressions: the RE class *****/ + +// RE_Options allow you to set options to be passed along to pcre, +// along with other options we put on top of pcre. +// Only 9 modifiers, plus match_limit and match_limit_recursion, +// are supported now. +class RE_Options { + public: + // constructor + RE_Options() : match_limit_(0), match_limit_recursion_(0), all_options_(0) {} + + // alternative constructor. + // To facilitate transfer of legacy code from C programs + // + // This lets you do + // RE(pattern, RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str); + // But new code is better off doing + // RE(pattern, + // RE_Options().set_caseless(true).set_multiline(true)).PartialMatch(str); + RE_Options(int option_flags) : match_limit_(0), match_limit_recursion_(0), + all_options_(option_flags) {} + // we're fine with the default destructor, copy constructor, etc. + + // accessors and mutators + int match_limit() const { return match_limit_; }; + RE_Options &set_match_limit(int limit) { + match_limit_ = limit; + return *this; + } + + int match_limit_recursion() const { return match_limit_recursion_; }; + RE_Options &set_match_limit_recursion(int limit) { + match_limit_recursion_ = limit; + return *this; + } + + bool caseless() const { + return PCRE_IS_SET(PCRE_CASELESS); + } + RE_Options &set_caseless(bool x) { + PCRE_SET_OR_CLEAR(x, PCRE_CASELESS); + } + + bool multiline() const { + return PCRE_IS_SET(PCRE_MULTILINE); + } + RE_Options &set_multiline(bool x) { + PCRE_SET_OR_CLEAR(x, PCRE_MULTILINE); + } + + bool dotall() const { + return PCRE_IS_SET(PCRE_DOTALL); + } + RE_Options &set_dotall(bool x) { + PCRE_SET_OR_CLEAR(x,PCRE_DOTALL); + } + + bool extended() const { + return PCRE_IS_SET(PCRE_EXTENDED); + } + RE_Options &set_extended(bool x) { + PCRE_SET_OR_CLEAR(x,PCRE_EXTENDED); + } + + bool dollar_endonly() const { + return PCRE_IS_SET(PCRE_DOLLAR_ENDONLY); + } + RE_Options &set_dollar_endonly(bool x) { + PCRE_SET_OR_CLEAR(x,PCRE_DOLLAR_ENDONLY); + } + + bool extra() const { + return PCRE_IS_SET( PCRE_EXTRA); + } + RE_Options &set_extra(bool x) { + PCRE_SET_OR_CLEAR(x, PCRE_EXTRA); + } + + bool ungreedy() const { + return PCRE_IS_SET(PCRE_UNGREEDY); + } + RE_Options &set_ungreedy(bool x) { + PCRE_SET_OR_CLEAR(x, PCRE_UNGREEDY); + } + + bool utf8() const { + return PCRE_IS_SET(PCRE_UTF8); + } + RE_Options &set_utf8(bool x) { + PCRE_SET_OR_CLEAR(x, PCRE_UTF8); + } + + bool no_auto_capture() const { + return PCRE_IS_SET(PCRE_NO_AUTO_CAPTURE); + } + RE_Options &set_no_auto_capture(bool x) { + PCRE_SET_OR_CLEAR(x, PCRE_NO_AUTO_CAPTURE); + } + + RE_Options &set_all_options(int opt) { + all_options_ = opt; + return *this; + } + int all_options() const { + return all_options_ ; + } + + // TODO: add other pcre flags + + private: + int match_limit_; + int match_limit_recursion_; + int all_options_; +}; + +// These functions return some common RE_Options +static inline RE_Options UTF8() { + return RE_Options().set_utf8(true); +} + +static inline RE_Options CASELESS() { + return RE_Options().set_caseless(true); +} +static inline RE_Options MULTILINE() { + return RE_Options().set_multiline(true); +} + +static inline RE_Options DOTALL() { + return RE_Options().set_dotall(true); +} + +static inline RE_Options EXTENDED() { + return RE_Options().set_extended(true); +} + +// Interface for regular expression matching. Also corresponds to a +// pre-compiled regular expression. An "RE" object is safe for +// concurrent use by multiple threads. +class RE { + public: + // We provide implicit conversions from strings so that users can + // pass in a string or a "const char*" wherever an "RE" is expected. + RE(const char* pat) { Init(pat, NULL); } + RE(const char *pat, const RE_Options& option) { Init(pat, &option); } + RE(const string& pat) { Init(pat.c_str(), NULL); } + RE(const string& pat, const RE_Options& option) { Init(pat.c_str(), &option); } + + ~RE(); + + // The string specification for this RE. E.g. + // RE re("ab*c?d+"); + // re.pattern(); // "ab*c?d+" + const string& pattern() const { return pattern_; } + + // If RE could not be created properly, returns an error string. + // Else returns the empty string. + const string& error() const { return *error_; } + + /***** The useful part: the matching interface *****/ + + // This is provided so one can do pattern.ReplaceAll() just as + // easily as ReplaceAll(pattern-text, ....) + + bool FullMatch(const StringPiece& text, + const Arg& ptr1 = no_arg, + const Arg& ptr2 = no_arg, + const Arg& ptr3 = no_arg, + const Arg& ptr4 = no_arg, + const Arg& ptr5 = no_arg, + const Arg& ptr6 = no_arg, + const Arg& ptr7 = no_arg, + const Arg& ptr8 = no_arg, + const Arg& ptr9 = no_arg, + const Arg& ptr10 = no_arg, + const Arg& ptr11 = no_arg, + const Arg& ptr12 = no_arg, + const Arg& ptr13 = no_arg, + const Arg& ptr14 = no_arg, + const Arg& ptr15 = no_arg, + const Arg& ptr16 = no_arg) const; + + bool PartialMatch(const StringPiece& text, + const Arg& ptr1 = no_arg, + const Arg& ptr2 = no_arg, + const Arg& ptr3 = no_arg, + const Arg& ptr4 = no_arg, + const Arg& ptr5 = no_arg, + const Arg& ptr6 = no_arg, + const Arg& ptr7 = no_arg, + const Arg& ptr8 = no_arg, + const Arg& ptr9 = no_arg, + const Arg& ptr10 = no_arg, + const Arg& ptr11 = no_arg, + const Arg& ptr12 = no_arg, + const Arg& ptr13 = no_arg, + const Arg& ptr14 = no_arg, + const Arg& ptr15 = no_arg, + const Arg& ptr16 = no_arg) const; + + bool Consume(StringPiece* input, + const Arg& ptr1 = no_arg, + const Arg& ptr2 = no_arg, + const Arg& ptr3 = no_arg, + const Arg& ptr4 = no_arg, + const Arg& ptr5 = no_arg, + const Arg& ptr6 = no_arg, + const Arg& ptr7 = no_arg, + const Arg& ptr8 = no_arg, + const Arg& ptr9 = no_arg, + const Arg& ptr10 = no_arg, + const Arg& ptr11 = no_arg, + const Arg& ptr12 = no_arg, + const Arg& ptr13 = no_arg, + const Arg& ptr14 = no_arg, + const Arg& ptr15 = no_arg, + const Arg& ptr16 = no_arg) const; + + bool FindAndConsume(StringPiece* input, + const Arg& ptr1 = no_arg, + const Arg& ptr2 = no_arg, + const Arg& ptr3 = no_arg, + const Arg& ptr4 = no_arg, + const Arg& ptr5 = no_arg, + const Arg& ptr6 = no_arg, + const Arg& ptr7 = no_arg, + const Arg& ptr8 = no_arg, + const Arg& ptr9 = no_arg, + const Arg& ptr10 = no_arg, + const Arg& ptr11 = no_arg, + const Arg& ptr12 = no_arg, + const Arg& ptr13 = no_arg, + const Arg& ptr14 = no_arg, + const Arg& ptr15 = no_arg, + const Arg& ptr16 = no_arg) const; + + bool Replace(const StringPiece& rewrite, + string *str) const; + + int GlobalReplace(const StringPiece& rewrite, + string *str) const; + + bool Extract(const StringPiece &rewrite, + const StringPiece &text, + string *out) const; + + /***** Generic matching interface *****/ + + // Type of match (TODO: Should be restructured as part of RE_Options) + enum Anchor { + UNANCHORED, // No anchoring + ANCHOR_START, // Anchor at start only + ANCHOR_BOTH // Anchor at start and end + }; + + // General matching routine. Stores the length of the match in + // "*consumed" if successful. + bool DoMatch(const StringPiece& text, + Anchor anchor, + int* consumed, + const Arg* const* args, int n) const; + + // Return the number of capturing subpatterns, or -1 if the + // regexp wasn't valid on construction. + int NumberOfCapturingGroups() const; + + private: + + void Init(const char* pattern, const RE_Options* options); + + // Match against "text", filling in "vec" (up to "vecsize" * 2/3) with + // pairs of integers for the beginning and end positions of matched + // text. The first pair corresponds to the entire matched text; + // subsequent pairs correspond, in order, to parentheses-captured + // matches. Returns the number of pairs (one more than the number of + // the last subpattern with a match) if matching was successful + // and zero if the match failed. + // I.e. for RE("(foo)|(bar)|(baz)") it will return 2, 3, and 4 when matching + // against "foo", "bar", and "baz" respectively. + // When matching RE("(foo)|hello") against "hello", it will return 1. + // But the values for all subpattern are filled in into "vec". + int TryMatch(const StringPiece& text, + int startpos, + Anchor anchor, + int *vec, + int vecsize) const; + + // Append the "rewrite" string, with backslash subsitutions from "text" + // and "vec", to string "out". + bool Rewrite(string *out, + const StringPiece& rewrite, + const StringPiece& text, + int *vec, + int veclen) const; + + // internal implementation for DoMatch + bool DoMatchImpl(const StringPiece& text, + Anchor anchor, + int* consumed, + const Arg* const args[], + int n, + int* vec, + int vecsize) const; + + // Compile the regexp for the specified anchoring mode + pcre* Compile(Anchor anchor); + + string pattern_; + RE_Options options_; + pcre* re_full_; // For full matches + pcre* re_partial_; // For partial matches + const string* error_; // Error indicator (or points to empty string) + + // Don't allow the default copy or assignment constructors -- + // they're expensive and too easy to do by accident. + RE(const RE&); + void operator=(const RE&); +}; + +} // namespace pcrecpp + +#endif /* _PCRECPP_H */ diff --git a/libs/pcre/pcrecpp_unittest.cc b/libs/pcre/pcrecpp_unittest.cc new file mode 100644 index 0000000000..ccd876d081 --- /dev/null +++ b/libs/pcre/pcrecpp_unittest.cc @@ -0,0 +1,1116 @@ +// Copyright (c) 2005, Google Inc. +// All rights reserved. +// +// Redistribution and use in source and binary forms, with or without +// modification, are permitted provided that the following conditions are +// met: +// +// * Redistributions of source code must retain the above copyright +// notice, this list of conditions and the following disclaimer. +// * Redistributions in binary form must reproduce the above +// copyright notice, this list of conditions and the following disclaimer +// in the documentation and/or other materials provided with the +// distribution. +// * Neither the name of Google Inc. nor the names of its +// contributors may be used to endorse or promote products derived from +// this software without specific prior written permission. +// +// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +// +// Author: Sanjay Ghemawat +// +// TODO: Test extractions for PartialMatch/Consume + +#include +#include +#include +#include "config.h" +#include "pcrecpp.h" + +using pcrecpp::StringPiece; +using pcrecpp::RE; +using pcrecpp::RE_Options; +using pcrecpp::Hex; +using pcrecpp::Octal; +using pcrecpp::CRadix; + +static bool VERBOSE_TEST = false; + +// CHECK dies with a fatal error if condition is not true. It is *not* +// controlled by NDEBUG, so the check will be executed regardless of +// compilation mode. Therefore, it is safe to do things like: +// CHECK_EQ(fp->Write(x), 4) +#define CHECK(condition) do { \ + if (!(condition)) { \ + fprintf(stderr, "%s:%d: Check failed: %s\n", \ + __FILE__, __LINE__, #condition); \ + exit(1); \ + } \ +} while (0) + +#define CHECK_EQ(a, b) CHECK(a == b) + +static void Timing1(int num_iters) { + // Same pattern lots of times + RE pattern("ruby:\\d+"); + StringPiece p("ruby:1234"); + for (int j = num_iters; j > 0; j--) { + CHECK(pattern.FullMatch(p)); + } +} + +static void Timing2(int num_iters) { + // Same pattern lots of times + RE pattern("ruby:(\\d+)"); + int i; + for (int j = num_iters; j > 0; j--) { + CHECK(pattern.FullMatch("ruby:1234", &i)); + CHECK_EQ(i, 1234); + } +} + +static void Timing3(int num_iters) { + string text_string; + for (int j = num_iters; j > 0; j--) { + text_string += "this is another line\n"; + } + + RE line_matcher(".*\n"); + string line; + StringPiece text(text_string); + int counter = 0; + while (line_matcher.Consume(&text)) { + counter++; + } + printf("Matched %d lines\n", counter); +} + +#if 0 // uncomment this if you have a way of defining VirtualProcessSize() + +static void LeakTest() { + // Check for memory leaks + unsigned long long initial_size = 0; + for (int i = 0; i < 100000; i++) { + if (i == 50000) { + initial_size = VirtualProcessSize(); + printf("Size after 50000: %llu\n", initial_size); + } + char buf[100]; + snprintf(buf, sizeof(buf), "pat%09d", i); + RE newre(buf); + } + uint64 final_size = VirtualProcessSize(); + printf("Size after 100000: %llu\n", final_size); + const double growth = double(final_size - initial_size) / final_size; + printf("Growth: %0.2f%%", growth * 100); + CHECK(growth < 0.02); // Allow < 2% growth +} + +#endif + +static void RadixTests() { + printf("Testing hex\n"); + +#define CHECK_HEX(type, value) \ + do { \ + type v; \ + CHECK(RE("([0-9a-fA-F]+)[uUlL]*").FullMatch(#value, Hex(&v))); \ + CHECK_EQ(v, 0x ## value); \ + CHECK(RE("([0-9a-fA-FxX]+)[uUlL]*").FullMatch("0x" #value, CRadix(&v))); \ + CHECK_EQ(v, 0x ## value); \ + } while(0) + + CHECK_HEX(short, 2bad); + CHECK_HEX(unsigned short, 2badU); + CHECK_HEX(int, dead); + CHECK_HEX(unsigned int, deadU); + CHECK_HEX(long, 7eadbeefL); + CHECK_HEX(unsigned long, deadbeefUL); +#ifdef HAVE_LONG_LONG + CHECK_HEX(long long, 12345678deadbeefLL); +#endif +#ifdef HAVE_UNSIGNED_LONG_LONG + CHECK_HEX(unsigned long long, cafebabedeadbeefULL); +#endif + +#undef CHECK_HEX + + printf("Testing octal\n"); + +#define CHECK_OCTAL(type, value) \ + do { \ + type v; \ + CHECK(RE("([0-7]+)[uUlL]*").FullMatch(#value, Octal(&v))); \ + CHECK_EQ(v, 0 ## value); \ + CHECK(RE("([0-9a-fA-FxX]+)[uUlL]*").FullMatch("0" #value, CRadix(&v))); \ + CHECK_EQ(v, 0 ## value); \ + } while(0) + + CHECK_OCTAL(short, 77777); + CHECK_OCTAL(unsigned short, 177777U); + CHECK_OCTAL(int, 17777777777); + CHECK_OCTAL(unsigned int, 37777777777U); + CHECK_OCTAL(long, 17777777777L); + CHECK_OCTAL(unsigned long, 37777777777UL); +#ifdef HAVE_LONG_LONG + CHECK_OCTAL(long long, 777777777777777777777LL); +#endif +#ifdef HAVE_UNSIGNED_LONG_LONG + CHECK_OCTAL(unsigned long long, 1777777777777777777777ULL); +#endif + +#undef CHECK_OCTAL + + printf("Testing decimal\n"); + +#define CHECK_DECIMAL(type, value) \ + do { \ + type v; \ + CHECK(RE("(-?[0-9]+)[uUlL]*").FullMatch(#value, &v)); \ + CHECK_EQ(v, value); \ + CHECK(RE("(-?[0-9a-fA-FxX]+)[uUlL]*").FullMatch(#value, CRadix(&v))); \ + CHECK_EQ(v, value); \ + } while(0) + + CHECK_DECIMAL(short, -1); + CHECK_DECIMAL(unsigned short, 9999); + CHECK_DECIMAL(int, -1000); + CHECK_DECIMAL(unsigned int, 12345U); + CHECK_DECIMAL(long, -10000000L); + CHECK_DECIMAL(unsigned long, 3083324652U); +#ifdef HAVE_LONG_LONG + CHECK_DECIMAL(long long, -100000000000000LL); +#endif +#ifdef HAVE_UNSIGNED_LONG_LONG + CHECK_DECIMAL(unsigned long long, 1234567890987654321ULL); +#endif + +#undef CHECK_DECIMAL + +} + +static void TestReplace() { + printf("Testing Replace\n"); + + struct ReplaceTest { + const char *regexp; + const char *rewrite; + const char *original; + const char *single; + const char *global; + }; + static const ReplaceTest tests[] = { + { "(qu|[b-df-hj-np-tv-z]*)([a-z]+)", + "\\2\\1ay", + "the quick brown fox jumps over the lazy dogs.", + "ethay quick brown fox jumps over the lazy dogs.", + "ethay ickquay ownbray oxfay umpsjay overay ethay azylay ogsday." }, + { "\\w+", + "\\0-NOSPAM", + "paul.haahr@google.com", + "paul-NOSPAM.haahr@google.com", + "paul-NOSPAM.haahr-NOSPAM@google-NOSPAM.com-NOSPAM" }, + { "^", + "(START)", + "foo", + "(START)foo", + "(START)foo" }, + { "^", + "(START)", + "", + "(START)", + "(START)" }, + { "$", + "(END)", + "", + "(END)", + "(END)" }, + { "b", + "bb", + "ababababab", + "abbabababab", + "abbabbabbabbabb" }, + { "b", + "bb", + "bbbbbb", + "bbbbbbb", + "bbbbbbbbbbbb" }, + { "b+", + "bb", + "bbbbbb", + "bb", + "bb" }, + { "b*", + "bb", + "bbbbbb", + "bb", + "bb" }, + { "b*", + "bb", + "aaaaa", + "bbaaaaa", + "bbabbabbabbabbabb" }, + { "b*", + "bb", + "aa\naa\n", + "bbaa\naa\n", + "bbabbabb\nbbabbabb\nbb" }, + { "b*", + "bb", + "aa\raa\r", + "bbaa\raa\r", + "bbabbabb\rbbabbabb\rbb" }, + { "b*", + "bb", + "aa\r\naa\r\n", + "bbaa\r\naa\r\n", + "bbabbabb\r\nbbabbabb\r\nbb" }, +#ifdef SUPPORT_UTF8 + { "b*", + "bb", + "\xE3\x83\x9B\xE3\x83\xBC\xE3\x83\xA0\xE3\x81\xB8", // utf8 + "bb\xE3\x83\x9B\xE3\x83\xBC\xE3\x83\xA0\xE3\x81\xB8", + "bb\xE3\x83\x9B""bb""\xE3\x83\xBC""bb""\xE3\x83\xA0""bb""\xE3\x81\xB8""bb" }, + { "b*", + "bb", + "\xE3\x83\x9B\r\n\xE3\x83\xBC\r\xE3\x83\xA0\n\xE3\x81\xB8\r\n", // utf8 + "bb\xE3\x83\x9B\r\n\xE3\x83\xBC\r\xE3\x83\xA0\n\xE3\x81\xB8\r\n", + ("bb\xE3\x83\x9B""bb\r\nbb""\xE3\x83\xBC""bb\rbb""\xE3\x83\xA0" + "bb\nbb""\xE3\x81\xB8""bb\r\nbb") }, +#endif + { "", NULL, NULL, NULL, NULL } + }; + +#ifdef SUPPORT_UTF8 + const bool support_utf8 = true; +#else + const bool support_utf8 = false; +#endif + + for (const ReplaceTest *t = tests; t->original != NULL; ++t) { + RE re(t->regexp, RE_Options(PCRE_NEWLINE_CRLF).set_utf8(support_utf8)); + assert(re.error().empty()); + string one(t->original); + CHECK(re.Replace(t->rewrite, &one)); + CHECK_EQ(one, t->single); + string all(t->original); + CHECK(re.GlobalReplace(t->rewrite, &all) > 0); + CHECK_EQ(all, t->global); + } + + // One final test: test \r\n replacement when we're not in CRLF mode + { + RE re("b*", RE_Options(PCRE_NEWLINE_CR).set_utf8(support_utf8)); + assert(re.error().empty()); + string all("aa\r\naa\r\n"); + CHECK(re.GlobalReplace("bb", &all) > 0); + CHECK_EQ(all, string("bbabbabb\rbb\nbbabbabb\rbb\nbb")); + } + { + RE re("b*", RE_Options(PCRE_NEWLINE_LF).set_utf8(support_utf8)); + assert(re.error().empty()); + string all("aa\r\naa\r\n"); + CHECK(re.GlobalReplace("bb", &all) > 0); + CHECK_EQ(all, string("bbabbabb\rbb\nbbabbabb\rbb\nbb")); + } + // TODO: test what happens when no PCRE_NEWLINE_* flag is set. + // Alas, the answer depends on how pcre was compiled. +} + +static void TestExtract() { + printf("Testing Extract\n"); + + string s; + + CHECK(RE("(.*)@([^.]*)").Extract("\\2!\\1", "boris@kremvax.ru", &s)); + CHECK_EQ(s, "kremvax!boris"); + + // check the RE interface as well + CHECK(RE(".*").Extract("'\\0'", "foo", &s)); + CHECK_EQ(s, "'foo'"); + CHECK(!RE("bar").Extract("'\\0'", "baz", &s)); + CHECK_EQ(s, "'foo'"); +} + +static void TestConsume() { + printf("Testing Consume\n"); + + string word; + + string s(" aaa b!@#$@#$cccc"); + StringPiece input(s); + + RE r("\\s*(\\w+)"); // matches a word, possibly proceeded by whitespace + CHECK(r.Consume(&input, &word)); + CHECK_EQ(word, "aaa"); + CHECK(r.Consume(&input, &word)); + CHECK_EQ(word, "b"); + CHECK(! r.Consume(&input, &word)); +} + +static void TestFindAndConsume() { + printf("Testing FindAndConsume\n"); + + string word; + + string s(" aaa b!@#$@#$cccc"); + StringPiece input(s); + + RE r("(\\w+)"); // matches a word + CHECK(r.FindAndConsume(&input, &word)); + CHECK_EQ(word, "aaa"); + CHECK(r.FindAndConsume(&input, &word)); + CHECK_EQ(word, "b"); + CHECK(r.FindAndConsume(&input, &word)); + CHECK_EQ(word, "cccc"); + CHECK(! r.FindAndConsume(&input, &word)); +} + +static void TestMatchNumberPeculiarity() { + printf("Testing match-number peculiaraity\n"); + + string word1; + string word2; + string word3; + + RE r("(foo)|(bar)|(baz)"); + CHECK(r.PartialMatch("foo", &word1, &word2, &word3)); + CHECK_EQ(word1, "foo"); + CHECK_EQ(word2, ""); + CHECK_EQ(word3, ""); + CHECK(r.PartialMatch("bar", &word1, &word2, &word3)); + CHECK_EQ(word1, ""); + CHECK_EQ(word2, "bar"); + CHECK_EQ(word3, ""); + CHECK(r.PartialMatch("baz", &word1, &word2, &word3)); + CHECK_EQ(word1, ""); + CHECK_EQ(word2, ""); + CHECK_EQ(word3, "baz"); + CHECK(!r.PartialMatch("f", &word1, &word2, &word3)); + + string a; + CHECK(RE("(foo)|hello").FullMatch("hello", &a)); + CHECK_EQ(a, ""); +} + +static void TestRecursion() { + printf("Testing recursion\n"); + + // Get one string that passes (sometimes), one that never does. + string text_good("abcdefghijk"); + string text_bad("acdefghijkl"); + + // According to pcretest, matching text_good against (\w+)*b + // requires match_limit of at least 8192, and match_recursion_limit + // of at least 37. + + RE_Options options_ml; + options_ml.set_match_limit(8192); + RE re("(\\w+)*b", options_ml); + CHECK(re.PartialMatch(text_good) == true); + CHECK(re.PartialMatch(text_bad) == false); + CHECK(re.FullMatch(text_good) == false); + CHECK(re.FullMatch(text_bad) == false); + + options_ml.set_match_limit(1024); + RE re2("(\\w+)*b", options_ml); + CHECK(re2.PartialMatch(text_good) == false); // because of match_limit + CHECK(re2.PartialMatch(text_bad) == false); + CHECK(re2.FullMatch(text_good) == false); + CHECK(re2.FullMatch(text_bad) == false); + + RE_Options options_mlr; + options_mlr.set_match_limit_recursion(50); + RE re3("(\\w+)*b", options_mlr); + CHECK(re3.PartialMatch(text_good) == true); + CHECK(re3.PartialMatch(text_bad) == false); + CHECK(re3.FullMatch(text_good) == false); + CHECK(re3.FullMatch(text_bad) == false); + + options_mlr.set_match_limit_recursion(10); + RE re4("(\\w+)*b", options_mlr); + CHECK(re4.PartialMatch(text_good) == false); + CHECK(re4.PartialMatch(text_bad) == false); + CHECK(re4.FullMatch(text_good) == false); + CHECK(re4.FullMatch(text_bad) == false); +} + +// +// Options tests contributed by +// Giuseppe Maxia, CTO, Stardata s.r.l. +// July 2005 +// +static void GetOneOptionResult( + const char *option_name, + const char *regex, + const char *str, + RE_Options options, + bool full, + string expected) { + + printf("Testing Option <%s>\n", option_name); + if(VERBOSE_TEST) + printf("/%s/ finds \"%s\" within \"%s\" \n", + regex, + expected.c_str(), + str); + string captured(""); + if (full) + RE(regex,options).FullMatch(str, &captured); + else + RE(regex,options).PartialMatch(str, &captured); + CHECK_EQ(captured, expected); +} + +static void TestOneOption( + const char *option_name, + const char *regex, + const char *str, + RE_Options options, + bool full, + bool assertive = true) { + + printf("Testing Option <%s>\n", option_name); + if (VERBOSE_TEST) + printf("'%s' %s /%s/ \n", + str, + (assertive? "matches" : "doesn't match"), + regex); + if (assertive) { + if (full) + CHECK(RE(regex,options).FullMatch(str)); + else + CHECK(RE(regex,options).PartialMatch(str)); + } else { + if (full) + CHECK(!RE(regex,options).FullMatch(str)); + else + CHECK(!RE(regex,options).PartialMatch(str)); + } +} + +static void Test_CASELESS() { + RE_Options options; + RE_Options options2; + + options.set_caseless(true); + TestOneOption("CASELESS (class)", "HELLO", "hello", options, false); + TestOneOption("CASELESS (class2)", "HELLO", "hello", options2.set_caseless(true), false); + TestOneOption("CASELESS (class)", "^[A-Z]+$", "Hello", options, false); + + TestOneOption("CASELESS (function)", "HELLO", "hello", pcrecpp::CASELESS(), false); + TestOneOption("CASELESS (function)", "^[A-Z]+$", "Hello", pcrecpp::CASELESS(), false); + options.set_caseless(false); + TestOneOption("no CASELESS", "HELLO", "hello", options, false, false); +} + +static void Test_MULTILINE() { + RE_Options options; + RE_Options options2; + const char *str = "HELLO\n" "cruel\n" "world\n"; + + options.set_multiline(true); + TestOneOption("MULTILINE (class)", "^cruel$", str, options, false); + TestOneOption("MULTILINE (class2)", "^cruel$", str, options2.set_multiline(true), false); + TestOneOption("MULTILINE (function)", "^cruel$", str, pcrecpp::MULTILINE(), false); + options.set_multiline(false); + TestOneOption("no MULTILINE", "^cruel$", str, options, false, false); +} + +static void Test_DOTALL() { + RE_Options options; + RE_Options options2; + const char *str = "HELLO\n" "cruel\n" "world"; + + options.set_dotall(true); + TestOneOption("DOTALL (class)", "HELLO.*world", str, options, true); + TestOneOption("DOTALL (class2)", "HELLO.*world", str, options2.set_dotall(true), true); + TestOneOption("DOTALL (function)", "HELLO.*world", str, pcrecpp::DOTALL(), true); + options.set_dotall(false); + TestOneOption("no DOTALL", "HELLO.*world", str, options, true, false); +} + +static void Test_DOLLAR_ENDONLY() { + RE_Options options; + RE_Options options2; + const char *str = "HELLO world\n"; + + TestOneOption("no DOLLAR_ENDONLY", "world$", str, options, false); + options.set_dollar_endonly(true); + TestOneOption("DOLLAR_ENDONLY 1", "world$", str, options, false, false); + TestOneOption("DOLLAR_ENDONLY 2", "world$", str, options2.set_dollar_endonly(true), false, false); +} + +static void Test_EXTRA() { + RE_Options options; + const char *str = "HELLO"; + + options.set_extra(true); + TestOneOption("EXTRA 1", "\\HELL\\O", str, options, true, false ); + TestOneOption("EXTRA 2", "\\HELL\\O", str, RE_Options().set_extra(true), true, false ); + options.set_extra(false); + TestOneOption("no EXTRA", "\\HELL\\O", str, options, true ); +} + +static void Test_EXTENDED() { + RE_Options options; + RE_Options options2; + const char *str = "HELLO world"; + + options.set_extended(true); + TestOneOption("EXTENDED (class)", "HELLO world", str, options, false, false); + TestOneOption("EXTENDED (class2)", "HELLO world", str, options2.set_extended(true), false, false); + TestOneOption("EXTENDED (class)", + "^ HE L{2} O " + "\\s+ " + "\\w+ $ ", + str, + options, + false); + + TestOneOption("EXTENDED (function)", "HELLO world", str, pcrecpp::EXTENDED(), false, false); + TestOneOption("EXTENDED (function)", + "^ HE L{2} O " + "\\s+ " + "\\w+ $ ", + str, + pcrecpp::EXTENDED(), + false); + + options.set_extended(false); + TestOneOption("no EXTENDED", "HELLO world", str, options, false); +} + +static void Test_NO_AUTO_CAPTURE() { + RE_Options options; + const char *str = "HELLO world"; + string captured; + + printf("Testing Option \n"); + if (VERBOSE_TEST) + printf("parentheses capture text\n"); + RE re("(world|universe)$", options); + CHECK(re.Extract("\\1", str , &captured)); + CHECK_EQ(captured, "world"); + options.set_no_auto_capture(true); + printf("testing Option \n"); + if (VERBOSE_TEST) + printf("parentheses do not capture text\n"); + re.Extract("\\1",str, &captured ); + CHECK_EQ(captured, "world"); +} + +static void Test_UNGREEDY() { + RE_Options options; + const char *str = "HELLO, 'this' is the 'world'"; + + options.set_ungreedy(true); + GetOneOptionResult("UNGREEDY 1", "('.*')", str, options, false, "'this'" ); + GetOneOptionResult("UNGREEDY 2", "('.*')", str, RE_Options().set_ungreedy(true), false, "'this'" ); + GetOneOptionResult("UNGREEDY", "('.*?')", str, options, false, "'this' is the 'world'" ); + + options.set_ungreedy(false); + GetOneOptionResult("no UNGREEDY", "('.*')", str, options, false, "'this' is the 'world'" ); + GetOneOptionResult("no UNGREEDY", "('.*?')", str, options, false, "'this'" ); +} + +static void Test_all_options() { + const char *str = "HELLO\n" "cruel\n" "world"; + RE_Options options; + options.set_all_options(PCRE_CASELESS | PCRE_DOTALL); + + TestOneOption("all_options (CASELESS|DOTALL)", "^hello.*WORLD", str , options, false); + options.set_all_options(0); + TestOneOption("all_options (0)", "^hello.*WORLD", str , options, false, false); + options.set_all_options(PCRE_MULTILINE | PCRE_EXTENDED); + + TestOneOption("all_options (MULTILINE|EXTENDED)", " ^ c r u e l $ ", str, options, false); + TestOneOption("all_options (MULTILINE|EXTENDED) with constructor", + " ^ c r u e l $ ", + str, + RE_Options(PCRE_MULTILINE | PCRE_EXTENDED), + false); + + TestOneOption("all_options (MULTILINE|EXTENDED) with concatenation", + " ^ c r u e l $ ", + str, + RE_Options() + .set_multiline(true) + .set_extended(true), + false); + + options.set_all_options(0); + TestOneOption("all_options (0)", "^ c r u e l $", str, options, false, false); + +} + +static void TestOptions() { + printf("Testing Options\n"); + Test_CASELESS(); + Test_MULTILINE(); + Test_DOTALL(); + Test_DOLLAR_ENDONLY(); + Test_EXTENDED(); + Test_NO_AUTO_CAPTURE(); + Test_UNGREEDY(); + Test_EXTRA(); + Test_all_options(); +} + +int main(int argc, char** argv) { + // Treat any flag as --help + if (argc > 1 && argv[1][0] == '-') { + printf("Usage: %s [timing1|timing2|timing3 num-iters]\n" + " If 'timingX ###' is specified, run the given timing test\n" + " with the given number of iterations, rather than running\n" + " the default corectness test.\n", argv[0]); + return 0; + } + + if (argc > 1) { + if ( argc == 2 || atoi(argv[2]) == 0) { + printf("timing mode needs a num-iters argument\n"); + return 1; + } + if (!strcmp(argv[1], "timing1")) + Timing1(atoi(argv[2])); + else if (!strcmp(argv[1], "timing2")) + Timing2(atoi(argv[2])); + else if (!strcmp(argv[1], "timing3")) + Timing3(atoi(argv[2])); + else + printf("Unknown argument '%s'\n", argv[1]); + return 0; + } + + printf("Testing FullMatch\n"); + + int i; + string s; + + /***** FullMatch with no args *****/ + + CHECK(RE("h.*o").FullMatch("hello")); + CHECK(!RE("h.*o").FullMatch("othello")); + CHECK(!RE("h.*o").FullMatch("hello!")); + + /***** FullMatch with args *****/ + + // Zero-arg + CHECK(RE("\\d+").FullMatch("1001")); + + // Single-arg + CHECK(RE("(\\d+)").FullMatch("1001", &i)); + CHECK_EQ(i, 1001); + CHECK(RE("(-?\\d+)").FullMatch("-123", &i)); + CHECK_EQ(i, -123); + CHECK(!RE("()\\d+").FullMatch("10", &i)); + CHECK(!RE("(\\d+)").FullMatch("1234567890123456789012345678901234567890", + &i)); + + // Digits surrounding integer-arg + CHECK(RE("1(\\d*)4").FullMatch("1234", &i)); + CHECK_EQ(i, 23); + CHECK(RE("(\\d)\\d+").FullMatch("1234", &i)); + CHECK_EQ(i, 1); + CHECK(RE("(-\\d)\\d+").FullMatch("-1234", &i)); + CHECK_EQ(i, -1); + CHECK(RE("(\\d)").PartialMatch("1234", &i)); + CHECK_EQ(i, 1); + CHECK(RE("(-\\d)").PartialMatch("-1234", &i)); + CHECK_EQ(i, -1); + + // String-arg + CHECK(RE("h(.*)o").FullMatch("hello", &s)); + CHECK_EQ(s, string("ell")); + + // StringPiece-arg + StringPiece sp; + CHECK(RE("(\\w+):(\\d+)").FullMatch("ruby:1234", &sp, &i)); + CHECK_EQ(sp.size(), 4); + CHECK(memcmp(sp.data(), "ruby", 4) == 0); + CHECK_EQ(i, 1234); + + // Multi-arg + CHECK(RE("(\\w+):(\\d+)").FullMatch("ruby:1234", &s, &i)); + CHECK_EQ(s, string("ruby")); + CHECK_EQ(i, 1234); + + // Ignored arg + CHECK(RE("(\\w+)(:)(\\d+)").FullMatch("ruby:1234", &s, (void*)NULL, &i)); + CHECK_EQ(s, string("ruby")); + CHECK_EQ(i, 1234); + + // Type tests + { + char c; + CHECK(RE("(H)ello").FullMatch("Hello", &c)); + CHECK_EQ(c, 'H'); + } + { + unsigned char c; + CHECK(RE("(H)ello").FullMatch("Hello", &c)); + CHECK_EQ(c, static_cast('H')); + } + { + short v; + CHECK(RE("(-?\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); + CHECK(RE("(-?\\d+)").FullMatch("-100", &v)); CHECK_EQ(v, -100); + CHECK(RE("(-?\\d+)").FullMatch("32767", &v)); CHECK_EQ(v, 32767); + CHECK(RE("(-?\\d+)").FullMatch("-32768", &v)); CHECK_EQ(v, -32768); + CHECK(!RE("(-?\\d+)").FullMatch("-32769", &v)); + CHECK(!RE("(-?\\d+)").FullMatch("32768", &v)); + } + { + unsigned short v; + CHECK(RE("(\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); + CHECK(RE("(\\d+)").FullMatch("32767", &v)); CHECK_EQ(v, 32767); + CHECK(RE("(\\d+)").FullMatch("65535", &v)); CHECK_EQ(v, 65535); + CHECK(!RE("(\\d+)").FullMatch("65536", &v)); + } + { + int v; + static const int max_value = 0x7fffffff; + static const int min_value = -max_value - 1; + CHECK(RE("(-?\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); + CHECK(RE("(-?\\d+)").FullMatch("-100", &v)); CHECK_EQ(v, -100); + CHECK(RE("(-?\\d+)").FullMatch("2147483647", &v)); CHECK_EQ(v, max_value); + CHECK(RE("(-?\\d+)").FullMatch("-2147483648", &v)); CHECK_EQ(v, min_value); + CHECK(!RE("(-?\\d+)").FullMatch("-2147483649", &v)); + CHECK(!RE("(-?\\d+)").FullMatch("2147483648", &v)); + } + { + unsigned int v; + static const unsigned int max_value = 0xfffffffful; + CHECK(RE("(\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); + CHECK(RE("(\\d+)").FullMatch("4294967295", &v)); CHECK_EQ(v, max_value); + CHECK(!RE("(\\d+)").FullMatch("4294967296", &v)); + } +#ifdef HAVE_LONG_LONG + { + long long v; + static const long long max_value = 0x7fffffffffffffffLL; + static const long long min_value = -max_value - 1; + char buf[32]; + + CHECK(RE("(-?\\d+)").FullMatch("100", &v)); CHECK_EQ(v, 100); + CHECK(RE("(-?\\d+)").FullMatch("-100",&v)); CHECK_EQ(v, -100); + + snprintf(buf, sizeof(buf), "%lld", max_value); + CHECK(RE("(-?\\d+)").FullMatch(buf,&v)); CHECK_EQ(v, max_value); + + snprintf(buf, sizeof(buf), "%lld", min_value); + CHECK(RE("(-?\\d+)").FullMatch(buf,&v)); CHECK_EQ(v, min_value); + + snprintf(buf, sizeof(buf), "%lld", max_value); + assert(buf[strlen(buf)-1] != '9'); + buf[strlen(buf)-1]++; + CHECK(!RE("(-?\\d+)").FullMatch(buf, &v)); + + snprintf(buf, sizeof(buf), "%lld", min_value); + assert(buf[strlen(buf)-1] != '9'); + buf[strlen(buf)-1]++; + CHECK(!RE("(-?\\d+)").FullMatch(buf, &v)); + } +#endif +#if defined HAVE_UNSIGNED_LONG_LONG && defined HAVE_LONG_LONG + { + unsigned long long v; + long long v2; + static const unsigned long long max_value = 0xffffffffffffffffULL; + char buf[32]; + + CHECK(RE("(-?\\d+)").FullMatch("100",&v)); CHECK_EQ(v, 100); + CHECK(RE("(-?\\d+)").FullMatch("-100",&v2)); CHECK_EQ(v2, -100); + + snprintf(buf, sizeof(buf), "%llu", max_value); + CHECK(RE("(-?\\d+)").FullMatch(buf,&v)); CHECK_EQ(v, max_value); + + assert(buf[strlen(buf)-1] != '9'); + buf[strlen(buf)-1]++; + CHECK(!RE("(-?\\d+)").FullMatch(buf, &v)); + } +#endif + { + float v; + CHECK(RE("(.*)").FullMatch("100", &v)); + CHECK(RE("(.*)").FullMatch("-100.", &v)); + CHECK(RE("(.*)").FullMatch("1e23", &v)); + } + { + double v; + CHECK(RE("(.*)").FullMatch("100", &v)); + CHECK(RE("(.*)").FullMatch("-100.", &v)); + CHECK(RE("(.*)").FullMatch("1e23", &v)); + } + + // Check that matching is fully anchored + CHECK(!RE("(\\d+)").FullMatch("x1001", &i)); + CHECK(!RE("(\\d+)").FullMatch("1001x", &i)); + CHECK(RE("x(\\d+)").FullMatch("x1001", &i)); CHECK_EQ(i, 1001); + CHECK(RE("(\\d+)x").FullMatch("1001x", &i)); CHECK_EQ(i, 1001); + + // Braces + CHECK(RE("[0-9a-f+.-]{5,}").FullMatch("0abcd")); + CHECK(RE("[0-9a-f+.-]{5,}").FullMatch("0abcde")); + CHECK(!RE("[0-9a-f+.-]{5,}").FullMatch("0abc")); + + // Complicated RE + CHECK(RE("foo|bar|[A-Z]").FullMatch("foo")); + CHECK(RE("foo|bar|[A-Z]").FullMatch("bar")); + CHECK(RE("foo|bar|[A-Z]").FullMatch("X")); + CHECK(!RE("foo|bar|[A-Z]").FullMatch("XY")); + + // Check full-match handling (needs '$' tacked on internally) + CHECK(RE("fo|foo").FullMatch("fo")); + CHECK(RE("fo|foo").FullMatch("foo")); + CHECK(RE("fo|foo$").FullMatch("fo")); + CHECK(RE("fo|foo$").FullMatch("foo")); + CHECK(RE("foo$").FullMatch("foo")); + CHECK(!RE("foo\\$").FullMatch("foo$bar")); + CHECK(!RE("fo|bar").FullMatch("fox")); + + // Uncomment the following if we change the handling of '$' to + // prevent it from matching a trailing newline + if (false) { + // Check that we don't get bitten by pcre's special handling of a + // '\n' at the end of the string matching '$' + CHECK(!RE("foo$").PartialMatch("foo\n")); + } + + // Number of args + int a[16]; + CHECK(RE("").FullMatch("")); + + memset(a, 0, sizeof(0)); + CHECK(RE("(\\d){1}").FullMatch("1", + &a[0])); + CHECK_EQ(a[0], 1); + + memset(a, 0, sizeof(0)); + CHECK(RE("(\\d)(\\d)").FullMatch("12", + &a[0], &a[1])); + CHECK_EQ(a[0], 1); + CHECK_EQ(a[1], 2); + + memset(a, 0, sizeof(0)); + CHECK(RE("(\\d)(\\d)(\\d)").FullMatch("123", + &a[0], &a[1], &a[2])); + CHECK_EQ(a[0], 1); + CHECK_EQ(a[1], 2); + CHECK_EQ(a[2], 3); + + memset(a, 0, sizeof(0)); + CHECK(RE("(\\d)(\\d)(\\d)(\\d)").FullMatch("1234", + &a[0], &a[1], &a[2], &a[3])); + CHECK_EQ(a[0], 1); + CHECK_EQ(a[1], 2); + CHECK_EQ(a[2], 3); + CHECK_EQ(a[3], 4); + + memset(a, 0, sizeof(0)); + CHECK(RE("(\\d)(\\d)(\\d)(\\d)(\\d)").FullMatch("12345", + &a[0], &a[1], &a[2], + &a[3], &a[4])); + CHECK_EQ(a[0], 1); + CHECK_EQ(a[1], 2); + CHECK_EQ(a[2], 3); + CHECK_EQ(a[3], 4); + CHECK_EQ(a[4], 5); + + memset(a, 0, sizeof(0)); + CHECK(RE("(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)").FullMatch("123456", + &a[0], &a[1], &a[2], + &a[3], &a[4], &a[5])); + CHECK_EQ(a[0], 1); + CHECK_EQ(a[1], 2); + CHECK_EQ(a[2], 3); + CHECK_EQ(a[3], 4); + CHECK_EQ(a[4], 5); + CHECK_EQ(a[5], 6); + + memset(a, 0, sizeof(0)); + CHECK(RE("(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)").FullMatch("1234567", + &a[0], &a[1], &a[2], &a[3], + &a[4], &a[5], &a[6])); + CHECK_EQ(a[0], 1); + CHECK_EQ(a[1], 2); + CHECK_EQ(a[2], 3); + CHECK_EQ(a[3], 4); + CHECK_EQ(a[4], 5); + CHECK_EQ(a[5], 6); + CHECK_EQ(a[6], 7); + + memset(a, 0, sizeof(0)); + CHECK(RE("(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)" + "(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)(\\d)").FullMatch( + "1234567890123456", + &a[0], &a[1], &a[2], &a[3], + &a[4], &a[5], &a[6], &a[7], + &a[8], &a[9], &a[10], &a[11], + &a[12], &a[13], &a[14], &a[15])); + CHECK_EQ(a[0], 1); + CHECK_EQ(a[1], 2); + CHECK_EQ(a[2], 3); + CHECK_EQ(a[3], 4); + CHECK_EQ(a[4], 5); + CHECK_EQ(a[5], 6); + CHECK_EQ(a[6], 7); + CHECK_EQ(a[7], 8); + CHECK_EQ(a[8], 9); + CHECK_EQ(a[9], 0); + CHECK_EQ(a[10], 1); + CHECK_EQ(a[11], 2); + CHECK_EQ(a[12], 3); + CHECK_EQ(a[13], 4); + CHECK_EQ(a[14], 5); + CHECK_EQ(a[15], 6); + + /***** PartialMatch *****/ + + printf("Testing PartialMatch\n"); + + CHECK(RE("h.*o").PartialMatch("hello")); + CHECK(RE("h.*o").PartialMatch("othello")); + CHECK(RE("h.*o").PartialMatch("hello!")); + CHECK(RE("((((((((((((((((((((x))))))))))))))))))))").PartialMatch("x")); + + RadixTests(); + TestReplace(); + TestExtract(); + TestConsume(); + TestFindAndConsume(); + TestMatchNumberPeculiarity(); + + // Check the pattern() accessor + { + const string kPattern = "http://([^/]+)/.*"; + const RE re(kPattern); + CHECK_EQ(kPattern, re.pattern()); + } + + // Check RE error field. + { + RE re("foo"); + CHECK(re.error().empty()); // Must have no error + } + +#ifdef SUPPORT_UTF8 + // Check UTF-8 handling + { + printf("Testing UTF-8 handling\n"); + + // Three Japanese characters (nihongo) + const char utf8_string[] = { + 0xe6, 0x97, 0xa5, // 65e5 + 0xe6, 0x9c, 0xac, // 627c + 0xe8, 0xaa, 0x9e, // 8a9e + 0 + }; + const char utf8_pattern[] = { + '.', + 0xe6, 0x9c, 0xac, // 627c + '.', + 0 + }; + + // Both should match in either mode, bytes or UTF-8 + RE re_test1("........."); + CHECK(re_test1.FullMatch(utf8_string)); + RE re_test2("...", pcrecpp::UTF8()); + CHECK(re_test2.FullMatch(utf8_string)); + + // Check that '.' matches one byte or UTF-8 character + // according to the mode. + string ss; + RE re_test3("(.)"); + CHECK(re_test3.PartialMatch(utf8_string, &ss)); + CHECK_EQ(ss, string("\xe6")); + RE re_test4("(.)", pcrecpp::UTF8()); + CHECK(re_test4.PartialMatch(utf8_string, &ss)); + CHECK_EQ(ss, string("\xe6\x97\xa5")); + + // Check that string matches itself in either mode + RE re_test5(utf8_string); + CHECK(re_test5.FullMatch(utf8_string)); + RE re_test6(utf8_string, pcrecpp::UTF8()); + CHECK(re_test6.FullMatch(utf8_string)); + + // Check that pattern matches string only in UTF8 mode + RE re_test7(utf8_pattern); + CHECK(!re_test7.FullMatch(utf8_string)); + RE re_test8(utf8_pattern, pcrecpp::UTF8()); + CHECK(re_test8.FullMatch(utf8_string)); + } + + // Check that ungreedy, UTF8 regular expressions don't match when they + // oughtn't -- see bug 82246. + { + // This code always worked. + const char* pattern = "\\w+X"; + const string target = "a aX"; + RE match_sentence(pattern); + RE match_sentence_re(pattern, pcrecpp::UTF8()); + + CHECK(!match_sentence.FullMatch(target)); + CHECK(!match_sentence_re.FullMatch(target)); + } + + { + const char* pattern = "(?U)\\w+X"; + const string target = "a aX"; + RE match_sentence(pattern); + RE match_sentence_re(pattern, pcrecpp::UTF8()); + + CHECK(!match_sentence.FullMatch(target)); + CHECK(!match_sentence_re.FullMatch(target)); + } +#endif /* def SUPPORT_UTF8 */ + + printf("Testing error reporting\n"); + + { RE re("a\\1"); CHECK(!re.error().empty()); } + { + RE re("a[x"); + CHECK(!re.error().empty()); + } + { + RE re("a[z-a]"); + CHECK(!re.error().empty()); + } + { + RE re("a[[:foobar:]]"); + CHECK(!re.error().empty()); + } + { + RE re("a(b"); + CHECK(!re.error().empty()); + } + { + RE re("a\\"); + CHECK(!re.error().empty()); + } + + // Test that recursion is stopped + TestRecursion(); + + // Test Options + if (getenv("VERBOSE_TEST") != NULL) + VERBOSE_TEST = true; + TestOptions(); + + // Done + printf("OK\n"); + + return 0; +} diff --git a/libs/pcre/pcrecpparg.h.in b/libs/pcre/pcrecpparg.h.in new file mode 100644 index 0000000000..ad17296a93 --- /dev/null +++ b/libs/pcre/pcrecpparg.h.in @@ -0,0 +1,171 @@ +// Copyright (c) 2005, Google Inc. +// All rights reserved. +// +// Redistribution and use in source and binary forms, with or without +// modification, are permitted provided that the following conditions are +// met: +// +// * Redistributions of source code must retain the above copyright +// notice, this list of conditions and the following disclaimer. +// * Redistributions in binary form must reproduce the above +// copyright notice, this list of conditions and the following disclaimer +// in the documentation and/or other materials provided with the +// distribution. +// * Neither the name of Google Inc. nor the names of its +// contributors may be used to endorse or promote products derived from +// this software without specific prior written permission. +// +// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +// +// Author: Sanjay Ghemawat + +#ifndef _PCRECPPARG_H +#define _PCRECPPARG_H + +#include // for NULL +#include + +namespace pcrecpp { + +class StringPiece; + +// Hex/Octal/Binary? + +// Special class for parsing into objects that define a ParseFrom() method +template +class _RE_MatchObject { + public: + static inline bool Parse(const char* str, int n, void* dest) { + T* object = reinterpret_cast(dest); + return object->ParseFrom(str, n); + } +}; + +class Arg { + public: + // Empty constructor so we can declare arrays of Arg + Arg(); + + // Constructor specially designed for NULL arguments + Arg(void*); + + typedef bool (*Parser)(const char* str, int n, void* dest); + +// Type-specific parsers +#define PCRE_MAKE_PARSER(type,name) \ + Arg(type* p) : arg_(p), parser_(name) { } \ + Arg(type* p, Parser parser) : arg_(p), parser_(parser) { } + + + PCRE_MAKE_PARSER(char, parse_char); + PCRE_MAKE_PARSER(unsigned char, parse_uchar); + PCRE_MAKE_PARSER(short, parse_short); + PCRE_MAKE_PARSER(unsigned short, parse_ushort); + PCRE_MAKE_PARSER(int, parse_int); + PCRE_MAKE_PARSER(unsigned int, parse_uint); + PCRE_MAKE_PARSER(long, parse_long); + PCRE_MAKE_PARSER(unsigned long, parse_ulong); +#if @pcre_have_long_long@ + PCRE_MAKE_PARSER(long long, parse_longlong); +#endif +#if @pcre_have_ulong_long@ + PCRE_MAKE_PARSER(unsigned long long, parse_ulonglong); +#endif + PCRE_MAKE_PARSER(float, parse_float); + PCRE_MAKE_PARSER(double, parse_double); + PCRE_MAKE_PARSER(std::string, parse_string); + PCRE_MAKE_PARSER(StringPiece, parse_stringpiece); + +#undef PCRE_MAKE_PARSER + + // Generic constructor + template Arg(T*, Parser parser); + // Generic constructor template + template Arg(T* p) + : arg_(p), parser_(_RE_MatchObject::Parse) { + } + + // Parse the data + bool Parse(const char* str, int n) const; + + private: + void* arg_; + Parser parser_; + + static bool parse_null (const char* str, int n, void* dest); + static bool parse_char (const char* str, int n, void* dest); + static bool parse_uchar (const char* str, int n, void* dest); + static bool parse_float (const char* str, int n, void* dest); + static bool parse_double (const char* str, int n, void* dest); + static bool parse_string (const char* str, int n, void* dest); + static bool parse_stringpiece (const char* str, int n, void* dest); + +#define PCRE_DECLARE_INTEGER_PARSER(name) \ + private: \ + static bool parse_ ## name(const char* str, int n, void* dest); \ + static bool parse_ ## name ## _radix( \ + const char* str, int n, void* dest, int radix); \ + public: \ + static bool parse_ ## name ## _hex(const char* str, int n, void* dest); \ + static bool parse_ ## name ## _octal(const char* str, int n, void* dest); \ + static bool parse_ ## name ## _cradix(const char* str, int n, void* dest) + + PCRE_DECLARE_INTEGER_PARSER(short); + PCRE_DECLARE_INTEGER_PARSER(ushort); + PCRE_DECLARE_INTEGER_PARSER(int); + PCRE_DECLARE_INTEGER_PARSER(uint); + PCRE_DECLARE_INTEGER_PARSER(long); + PCRE_DECLARE_INTEGER_PARSER(ulong); + PCRE_DECLARE_INTEGER_PARSER(longlong); + PCRE_DECLARE_INTEGER_PARSER(ulonglong); + +#undef PCRE_DECLARE_INTEGER_PARSER +}; + +inline Arg::Arg() : arg_(NULL), parser_(parse_null) { } +inline Arg::Arg(void* p) : arg_(p), parser_(parse_null) { } + +inline bool Arg::Parse(const char* str, int n) const { + return (*parser_)(str, n, arg_); +} + +// This part of the parser, appropriate only for ints, deals with bases +#define MAKE_INTEGER_PARSER(type, name) \ + inline Arg Hex(type* ptr) { \ + return Arg(ptr, Arg::parse_ ## name ## _hex); } \ + inline Arg Octal(type* ptr) { \ + return Arg(ptr, Arg::parse_ ## name ## _octal); } \ + inline Arg CRadix(type* ptr) { \ + return Arg(ptr, Arg::parse_ ## name ## _cradix); } + +MAKE_INTEGER_PARSER(short, short); +MAKE_INTEGER_PARSER(unsigned short, ushort); +MAKE_INTEGER_PARSER(int, int); +MAKE_INTEGER_PARSER(unsigned int, uint); +MAKE_INTEGER_PARSER(long, long); +MAKE_INTEGER_PARSER(unsigned long, ulong); +#if @pcre_have_long_long@ +MAKE_INTEGER_PARSER(long long, longlong); +#endif +#if @pcre_have_ulong_long@ +MAKE_INTEGER_PARSER(unsigned long long, ulonglong); +#endif + +#undef PCRE_IS_SET +#undef PCRE_SET_OR_CLEAR +#undef MAKE_INTEGER_PARSER + +} // namespace pcrecpp + + +#endif /* _PCRECPPARG_H */ diff --git a/libs/pcre/pcredemo.c b/libs/pcre/pcredemo.c new file mode 100644 index 0000000000..8b06a9ce63 --- /dev/null +++ b/libs/pcre/pcredemo.c @@ -0,0 +1,324 @@ +/************************************************* +* PCRE DEMONSTRATION PROGRAM * +*************************************************/ + +/* This is a demonstration program to illustrate the most straightforward ways +of calling the PCRE regular expression library from a C program. See the +pcresample documentation for a short discussion. + +Compile thuswise: + gcc -Wall pcredemo.c -I/usr/local/include -L/usr/local/lib \ + -R/usr/local/lib -lpcre + +Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and +library files for PCRE are installed on your system. Only some operating +systems (e.g. Solaris) use the -R option. +*/ + + +#include +#include +#include + +#define OVECCOUNT 30 /* should be a multiple of 3 */ + + +int main(int argc, char **argv) +{ +pcre *re; +const char *error; +char *pattern; +char *subject; +unsigned char *name_table; +int erroffset; +int find_all; +int namecount; +int name_entry_size; +int ovector[OVECCOUNT]; +int subject_length; +int rc, i; + + +/************************************************************************** +* First, sort out the command line. There is only one possible option at * +* the moment, "-g" to request repeated matching to find all occurrences, * +* like Perl's /g option. We set the variable find_all to a non-zero value * +* if the -g option is present. Apart from that, there must be exactly two * +* arguments. * +**************************************************************************/ + +find_all = 0; +for (i = 1; i < argc; i++) + { + if (strcmp(argv[i], "-g") == 0) find_all = 1; + else break; + } + +/* After the options, we require exactly two arguments, which are the pattern, +and the subject string. */ + +if (argc - i != 2) + { + printf("Two arguments required: a regex and a subject string\n"); + return 1; + } + +pattern = argv[i]; +subject = argv[i+1]; +subject_length = (int)strlen(subject); + + +/************************************************************************* +* Now we are going to compile the regular expression pattern, and handle * +* and errors that are detected. * +*************************************************************************/ + +re = pcre_compile( + pattern, /* the pattern */ + 0, /* default options */ + &error, /* for error message */ + &erroffset, /* for error offset */ + NULL); /* use default character tables */ + +/* Compilation failed: print the error message and exit */ + +if (re == NULL) + { + printf("PCRE compilation failed at offset %d: %s\n", erroffset, error); + return 1; + } + + +/************************************************************************* +* If the compilation succeeded, we call PCRE again, in order to do a * +* pattern match against the subject string. This does just ONE match. If * +* further matching is needed, it will be done below. * +*************************************************************************/ + +rc = pcre_exec( + re, /* the compiled pattern */ + NULL, /* no extra data - we didn't study the pattern */ + subject, /* the subject string */ + subject_length, /* the length of the subject */ + 0, /* start at offset 0 in the subject */ + 0, /* default options */ + ovector, /* output vector for substring information */ + OVECCOUNT); /* number of elements in the output vector */ + +/* Matching failed: handle error cases */ + +if (rc < 0) + { + switch(rc) + { + case PCRE_ERROR_NOMATCH: printf("No match\n"); break; + /* + Handle other special cases if you like + */ + default: printf("Matching error %d\n", rc); break; + } + pcre_free(re); /* Release memory used for the compiled pattern */ + return 1; + } + +/* Match succeded */ + +printf("\nMatch succeeded at offset %d\n", ovector[0]); + + +/************************************************************************* +* We have found the first match within the subject string. If the output * +* vector wasn't big enough, set its size to the maximum. Then output any * +* substrings that were captured. * +*************************************************************************/ + +/* The output vector wasn't big enough */ + +if (rc == 0) + { + rc = OVECCOUNT/3; + printf("ovector only has room for %d captured substrings\n", rc - 1); + } + +/* Show substrings stored in the output vector by number. Obviously, in a real +application you might want to do things other than print them. */ + +for (i = 0; i < rc; i++) + { + char *substring_start = subject + ovector[2*i]; + int substring_length = ovector[2*i+1] - ovector[2*i]; + printf("%2d: %.*s\n", i, substring_length, substring_start); + } + + +/************************************************************************** +* That concludes the basic part of this demonstration program. We have * +* compiled a pattern, and performed a single match. The code that follows * +* first shows how to access named substrings, and then how to code for * +* repeated matches on the same subject. * +**************************************************************************/ + +/* See if there are any named substrings, and if so, show them by name. First +we have to extract the count of named parentheses from the pattern. */ + +(void)pcre_fullinfo( + re, /* the compiled pattern */ + NULL, /* no extra data - we didn't study the pattern */ + PCRE_INFO_NAMECOUNT, /* number of named substrings */ + &namecount); /* where to put the answer */ + +if (namecount <= 0) printf("No named substrings\n"); else + { + unsigned char *tabptr; + printf("Named substrings\n"); + + /* Before we can access the substrings, we must extract the table for + translating names to numbers, and the size of each entry in the table. */ + + (void)pcre_fullinfo( + re, /* the compiled pattern */ + NULL, /* no extra data - we didn't study the pattern */ + PCRE_INFO_NAMETABLE, /* address of the table */ + &name_table); /* where to put the answer */ + + (void)pcre_fullinfo( + re, /* the compiled pattern */ + NULL, /* no extra data - we didn't study the pattern */ + PCRE_INFO_NAMEENTRYSIZE, /* size of each entry in the table */ + &name_entry_size); /* where to put the answer */ + + /* Now we can scan the table and, for each entry, print the number, the name, + and the substring itself. */ + + tabptr = name_table; + for (i = 0; i < namecount; i++) + { + int n = (tabptr[0] << 8) | tabptr[1]; + printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2, + ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]); + tabptr += name_entry_size; + } + } + + +/************************************************************************* +* If the "-g" option was given on the command line, we want to continue * +* to search for additional matches in the subject string, in a similar * +* way to the /g option in Perl. This turns out to be trickier than you * +* might think because of the possibility of matching an empty string. * +* What happens is as follows: * +* * +* If the previous match was NOT for an empty string, we can just start * +* the next match at the end of the previous one. * +* * +* If the previous match WAS for an empty string, we can't do that, as it * +* would lead to an infinite loop. Instead, a special call of pcre_exec() * +* is made with the PCRE_NOTEMPTY and PCRE_ANCHORED flags set. The first * +* of these tells PCRE that an empty string is not a valid match; other * +* possibilities must be tried. The second flag restricts PCRE to one * +* match attempt at the initial string position. If this match succeeds, * +* an alternative to the empty string match has been found, and we can * +* proceed round the loop. * +*************************************************************************/ + +if (!find_all) + { + pcre_free(re); /* Release the memory used for the compiled pattern */ + return 0; /* Finish unless -g was given */ + } + +/* Loop for second and subsequent matches */ + +for (;;) + { + int options = 0; /* Normally no options */ + int start_offset = ovector[1]; /* Start at end of previous match */ + + /* If the previous match was for an empty string, we are finished if we are + at the end of the subject. Otherwise, arrange to run another match at the + same point to see if a non-empty match can be found. */ + + if (ovector[0] == ovector[1]) + { + if (ovector[0] == subject_length) break; + options = PCRE_NOTEMPTY | PCRE_ANCHORED; + } + + /* Run the next matching operation */ + + rc = pcre_exec( + re, /* the compiled pattern */ + NULL, /* no extra data - we didn't study the pattern */ + subject, /* the subject string */ + subject_length, /* the length of the subject */ + start_offset, /* starting offset in the subject */ + options, /* options */ + ovector, /* output vector for substring information */ + OVECCOUNT); /* number of elements in the output vector */ + + /* This time, a result of NOMATCH isn't an error. If the value in "options" + is zero, it just means we have found all possible matches, so the loop ends. + Otherwise, it means we have failed to find a non-empty-string match at a + point where there was a previous empty-string match. In this case, we do what + Perl does: advance the matching position by one, and continue. We do this by + setting the "end of previous match" offset, because that is picked up at the + top of the loop as the point at which to start again. */ + + if (rc == PCRE_ERROR_NOMATCH) + { + if (options == 0) break; + ovector[1] = start_offset + 1; + continue; /* Go round the loop again */ + } + + /* Other matching errors are not recoverable. */ + + if (rc < 0) + { + printf("Matching error %d\n", rc); + pcre_free(re); /* Release memory used for the compiled pattern */ + return 1; + } + + /* Match succeded */ + + printf("\nMatch succeeded again at offset %d\n", ovector[0]); + + /* The match succeeded, but the output vector wasn't big enough. */ + + if (rc == 0) + { + rc = OVECCOUNT/3; + printf("ovector only has room for %d captured substrings\n", rc - 1); + } + + /* As before, show substrings stored in the output vector by number, and then + also any named substrings. */ + + for (i = 0; i < rc; i++) + { + char *substring_start = subject + ovector[2*i]; + int substring_length = ovector[2*i+1] - ovector[2*i]; + printf("%2d: %.*s\n", i, substring_length, substring_start); + } + + if (namecount <= 0) printf("No named substrings\n"); else + { + unsigned char *tabptr = name_table; + printf("Named substrings\n"); + for (i = 0; i < namecount; i++) + { + int n = (tabptr[0] << 8) | tabptr[1]; + printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2, + ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]); + tabptr += name_entry_size; + } + } + } /* End of loop to find second and subsequent matches */ + +printf("\n"); +pcre_free(re); /* Release memory used for the compiled pattern */ +return 0; +} + +/* End of pcredemo.c */ diff --git a/libs/pcre/pcregrep.c b/libs/pcre/pcregrep.c new file mode 100644 index 0000000000..001588be2c --- /dev/null +++ b/libs/pcre/pcregrep.c @@ -0,0 +1,1758 @@ +/************************************************* +* pcregrep program * +*************************************************/ + +/* This is a grep program that uses the PCRE regular expression library to do +its pattern matching. On a Unix or Win32 system it can recurse into +directories. + + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#include "config.h" +#include "pcre.h" + +#define FALSE 0 +#define TRUE 1 + +typedef int BOOL; + +#define VERSION "4.3 01-Jun-2006" +#define MAX_PATTERN_COUNT 100 + +#if BUFSIZ > 8192 +#define MBUFTHIRD BUFSIZ +#else +#define MBUFTHIRD 8192 +#endif + + +/* Values for the "filenames" variable, which specifies options for file name +output. The order is important; it is assumed that a file name is wanted for +all values greater than FN_DEFAULT. */ + +enum { FN_NONE, FN_DEFAULT, FN_ONLY, FN_NOMATCH_ONLY, FN_FORCE }; + +/* Actions for the -d and -D options */ + +enum { dee_READ, dee_SKIP, dee_RECURSE }; +enum { DEE_READ, DEE_SKIP }; + +/* Actions for special processing options (flag bits) */ + +#define PO_WORD_MATCH 0x0001 +#define PO_LINE_MATCH 0x0002 +#define PO_FIXED_STRINGS 0x0004 + + + +/************************************************* +* Global variables * +*************************************************/ + +/* Jeffrey Friedl has some debugging requirements that are not part of the +regular code. */ + +#ifdef JFRIEDL_DEBUG +static int S_arg = -1; +static unsigned int jfriedl_XR = 0; /* repeat regex attempt this many times */ +static unsigned int jfriedl_XT = 0; /* replicate text this many times */ +static const char *jfriedl_prefix = ""; +static const char *jfriedl_postfix = ""; +#endif + +static int endlinebyte = '\n'; /* Last byte of endline sequence */ +static int endlineextra = 0; /* Extra bytes for endline sequence */ + +static char *colour_string = (char *)"1;31"; +static char *colour_option = NULL; +static char *dee_option = NULL; +static char *DEE_option = NULL; +static char *newline = NULL; +static char *pattern_filename = NULL; +static char *stdin_name = (char *)"(standard input)"; +static char *locale = NULL; + +static const unsigned char *pcretables = NULL; + +static int pattern_count = 0; +static pcre **pattern_list; +static pcre_extra **hints_list; + +static char *include_pattern = NULL; +static char *exclude_pattern = NULL; + +static pcre *include_compiled = NULL; +static pcre *exclude_compiled = NULL; + +static int after_context = 0; +static int before_context = 0; +static int both_context = 0; +static int dee_action = dee_READ; +static int DEE_action = DEE_READ; +static int error_count = 0; +static int filenames = FN_DEFAULT; +static int process_options = 0; + +static BOOL count_only = FALSE; +static BOOL do_colour = FALSE; +static BOOL hyphenpending = FALSE; +static BOOL invert = FALSE; +static BOOL multiline = FALSE; +static BOOL number = FALSE; +static BOOL only_matching = FALSE; +static BOOL quiet = FALSE; +static BOOL silent = FALSE; + +/* Structure for options and list of them */ + +enum { OP_NODATA, OP_STRING, OP_OP_STRING, OP_NUMBER, OP_OP_NUMBER, + OP_PATLIST }; + +typedef struct option_item { + int type; + int one_char; + void *dataptr; + const char *long_name; + const char *help_text; +} option_item; + +/* Options without a single-letter equivalent get a negative value. This can be +used to identify them. */ + +#define N_COLOUR (-1) +#define N_EXCLUDE (-2) +#define N_HELP (-3) +#define N_INCLUDE (-4) +#define N_LABEL (-5) +#define N_LOCALE (-6) +#define N_NULL (-7) + +static option_item optionlist[] = { + { OP_NODATA, N_NULL, NULL, "", " terminate options" }, + { OP_NODATA, N_HELP, NULL, "help", "display this help and exit" }, + { OP_NUMBER, 'A', &after_context, "after-context=number", "set number of following context lines" }, + { OP_NUMBER, 'B', &before_context, "before-context=number", "set number of prior context lines" }, + { OP_OP_STRING, N_COLOUR, &colour_option, "color=option", "matched text color option" }, + { OP_NUMBER, 'C', &both_context, "context=number", "set number of context lines, before & after" }, + { OP_NODATA, 'c', NULL, "count", "print only a count of matching lines per FILE" }, + { OP_OP_STRING, N_COLOUR, &colour_option, "colour=option", "matched text colour option" }, + { OP_STRING, 'D', &DEE_option, "devices=action","how to handle devices, FIFOs, and sockets" }, + { OP_STRING, 'd', &dee_option, "directories=action", "how to handle directories" }, + { OP_PATLIST, 'e', NULL, "regex(p)", "specify pattern (may be used more than once)" }, + { OP_NODATA, 'F', NULL, "fixed_strings", "patterns are sets of newline-separated strings" }, + { OP_STRING, 'f', &pattern_filename, "file=path", "read patterns from file" }, + { OP_NODATA, 'H', NULL, "with-filename", "force the prefixing filename on output" }, + { OP_NODATA, 'h', NULL, "no-filename", "suppress the prefixing filename on output" }, + { OP_NODATA, 'i', NULL, "ignore-case", "ignore case distinctions" }, + { OP_NODATA, 'l', NULL, "files-with-matches", "print only FILE names containing matches" }, + { OP_NODATA, 'L', NULL, "files-without-match","print only FILE names not containing matches" }, + { OP_STRING, N_LABEL, &stdin_name, "label=name", "set name for standard input" }, + { OP_STRING, N_LOCALE, &locale, "locale=locale", "use the named locale" }, + { OP_NODATA, 'M', NULL, "multiline", "run in multiline mode" }, + { OP_STRING, 'N', &newline, "newline=type", "specify newline type (CR, LR, CRLF)" }, + { OP_NODATA, 'n', NULL, "line-number", "print line number with output lines" }, + { OP_NODATA, 'o', NULL, "only-matching", "show only the part of the line that matched" }, + { OP_NODATA, 'q', NULL, "quiet", "suppress output, just set return code" }, + { OP_NODATA, 'r', NULL, "recursive", "recursively scan sub-directories" }, + { OP_STRING, N_EXCLUDE,&exclude_pattern, "exclude=pattern","exclude matching files when recursing" }, + { OP_STRING, N_INCLUDE,&include_pattern, "include=pattern","include matching files when recursing" }, +#ifdef JFRIEDL_DEBUG + { OP_OP_NUMBER, 'S', &S_arg, "jeffS", "replace matched (sub)string with X" }, +#endif + { OP_NODATA, 's', NULL, "no-messages", "suppress error messages" }, + { OP_NODATA, 'u', NULL, "utf-8", "use UTF-8 mode" }, + { OP_NODATA, 'V', NULL, "version", "print version information and exit" }, + { OP_NODATA, 'v', NULL, "invert-match", "select non-matching lines" }, + { OP_NODATA, 'w', NULL, "word-regex(p)", "force patterns to match only as words" }, + { OP_NODATA, 'x', NULL, "line-regex(p)", "force patterns to match only whole lines" }, + { OP_NODATA, 0, NULL, NULL, NULL } +}; + +/* Tables for prefixing and suffixing patterns, according to the -w, -x, and -F +options. These set the 1, 2, and 4 bits in process_options, respectively. Note +that the combination of -w and -x has the same effect as -x on its own, so we +can treat them as the same. */ + +static const char *prefix[] = { + "", "\\b", "^(?:", "^(?:", "\\Q", "\\b\\Q", "^(?:\\Q", "^(?:\\Q" }; + +static const char *suffix[] = { + "", "\\b", ")$", ")$", "\\E", "\\E\\b", "\\E)$", "\\E)$" }; + + + +/************************************************* +* OS-specific functions * +*************************************************/ + +/* These functions are defined so that they can be made system specific, +although at present the only ones are for Unix, Win32, and for "no support". */ + + +/************* Directory scanning in Unix ***********/ + +#if IS_UNIX +#include +#include +#include + +typedef DIR directory_type; + +static int +isdirectory(char *filename) +{ +struct stat statbuf; +if (stat(filename, &statbuf) < 0) + return 0; /* In the expectation that opening as a file will fail */ +return ((statbuf.st_mode & S_IFMT) == S_IFDIR)? '/' : 0; +} + +static directory_type * +opendirectory(char *filename) +{ +return opendir(filename); +} + +static char * +readdirectory(directory_type *dir) +{ +for (;;) + { + struct dirent *dent = readdir(dir); + if (dent == NULL) return NULL; + if (strcmp(dent->d_name, ".") != 0 && strcmp(dent->d_name, "..") != 0) + return dent->d_name; + } +return NULL; /* Keep compiler happy; never executed */ +} + +static void +closedirectory(directory_type *dir) +{ +closedir(dir); +} + + +/************* Test for regular file in Unix **********/ + +static int +isregfile(char *filename) +{ +struct stat statbuf; +if (stat(filename, &statbuf) < 0) + return 1; /* In the expectation that opening as a file will fail */ +return (statbuf.st_mode & S_IFMT) == S_IFREG; +} + + +/************* Test stdout for being a terminal in Unix **********/ + +static BOOL +is_stdout_tty(void) +{ +return isatty(fileno(stdout)); +} + + +/************* Directory scanning in Win32 ***********/ + +/* I (Philip Hazel) have no means of testing this code. It was contributed by +Lionel Fourquaux. David Burgess added a patch to define INVALID_FILE_ATTRIBUTES +when it did not exist. */ + + +#elif HAVE_WIN32API + +#ifndef STRICT +# define STRICT +#endif +#ifndef WIN32_LEAN_AND_MEAN +# define WIN32_LEAN_AND_MEAN +#endif +#ifndef INVALID_FILE_ATTRIBUTES +#define INVALID_FILE_ATTRIBUTES 0xFFFFFFFF +#endif + +#include + +typedef struct directory_type +{ +HANDLE handle; +BOOL first; +WIN32_FIND_DATA data; +} directory_type; + +int +isdirectory(char *filename) +{ +DWORD attr = GetFileAttributes(filename); +if (attr == INVALID_FILE_ATTRIBUTES) + return 0; +return ((attr & FILE_ATTRIBUTE_DIRECTORY) != 0) ? '/' : 0; +} + +directory_type * +opendirectory(char *filename) +{ +size_t len; +char *pattern; +directory_type *dir; +DWORD err; +len = strlen(filename); +pattern = (char *) malloc(len + 3); +dir = (directory_type *) malloc(sizeof(*dir)); +if ((pattern == NULL) || (dir == NULL)) + { + fprintf(stderr, "pcregrep: malloc failed\n"); + exit(2); + } +memcpy(pattern, filename, len); +memcpy(&(pattern[len]), "\\*", 3); +dir->handle = FindFirstFile(pattern, &(dir->data)); +if (dir->handle != INVALID_HANDLE_VALUE) + { + free(pattern); + dir->first = TRUE; + return dir; + } +err = GetLastError(); +free(pattern); +free(dir); +errno = (err == ERROR_ACCESS_DENIED) ? EACCES : ENOENT; +return NULL; +} + +char * +readdirectory(directory_type *dir) +{ +for (;;) + { + if (!dir->first) + { + if (!FindNextFile(dir->handle, &(dir->data))) + return NULL; + } + else + { + dir->first = FALSE; + } + if (strcmp(dir->data.cFileName, ".") != 0 && strcmp(dir->data.cFileName, "..") != 0) + return dir->data.cFileName; + } +#ifndef _MSC_VER +return NULL; /* Keep compiler happy; never executed */ +#endif +} + +void +closedirectory(directory_type *dir) +{ +FindClose(dir->handle); +free(dir); +} + + +/************* Test for regular file in Win32 **********/ + +/* I don't know how to do this, or if it can be done; assume all paths are +regular if they are not directories. */ + +int isregfile(char *filename) +{ +return !isdirectory(filename) +} + + +/************* Test stdout for being a terminal in Win32 **********/ + +/* I don't know how to do this; assume never */ + +static BOOL +is_stdout_tty(void) +{ +FALSE; +} + + +/************* Directory scanning when we can't do it ***********/ + +/* The type is void, and apart from isdirectory(), the functions do nothing. */ + +#else + +typedef void directory_type; + +int isdirectory(char *filename) { return 0; } +directory_type * opendirectory(char *filename) {} +char *readdirectory(directory_type *dir) {} +void closedirectory(directory_type *dir) {} + + +/************* Test for regular when we can't do it **********/ + +/* Assume all files are regular. */ + +int isregfile(char *filename) { return 1; } + + +/************* Test stdout for being a terminal when we can't do it **********/ + +static BOOL +is_stdout_tty(void) +{ +return FALSE; +} + + +#endif + + + +#if ! HAVE_STRERROR +/************************************************* +* Provide strerror() for non-ANSI libraries * +*************************************************/ + +/* Some old-fashioned systems still around (e.g. SunOS4) don't have strerror() +in their libraries, but can provide the same facility by this simple +alternative function. */ + +extern int sys_nerr; +extern char *sys_errlist[]; + +char * +strerror(int n) +{ +if (n < 0 || n >= sys_nerr) return "unknown error number"; +return sys_errlist[n]; +} +#endif /* HAVE_STRERROR */ + + + +/************************************************* +* Print the previous "after" lines * +*************************************************/ + +/* This is called if we are about to lose said lines because of buffer filling, +and at the end of the file. The data in the line is written using fwrite() so +that a binary zero does not terminate it. + +Arguments: + lastmatchnumber the number of the last matching line, plus one + lastmatchrestart where we restarted after the last match + endptr end of available data + printname filename for printing + +Returns: nothing +*/ + +static void do_after_lines(int lastmatchnumber, char *lastmatchrestart, + char *endptr, char *printname) +{ +if (after_context > 0 && lastmatchnumber > 0) + { + int count = 0; + while (lastmatchrestart < endptr && count++ < after_context) + { + char *pp = lastmatchrestart; + if (printname != NULL) fprintf(stdout, "%s-", printname); + if (number) fprintf(stdout, "%d-", lastmatchnumber++); + while (*pp != endlinebyte) pp++; + fwrite(lastmatchrestart, 1, pp - lastmatchrestart + (1 + endlineextra), + stdout); + lastmatchrestart = pp + 1; + } + hyphenpending = TRUE; + } +} + + + +/************************************************* +* Grep an individual file * +*************************************************/ + +/* This is called from grep_or_recurse() below. It uses a buffer that is three +times the value of MBUFTHIRD. The matching point is never allowed to stray into +the top third of the buffer, thus keeping more of the file available for +context printing or for multiline scanning. For large files, the pointer will +be in the middle third most of the time, so the bottom third is available for +"before" context printing. + +Arguments: + in the fopened FILE stream + printname the file name if it is to be printed for each match + or NULL if the file name is not to be printed + it cannot be NULL if filenames[_nomatch]_only is set + +Returns: 0 if there was at least one match + 1 otherwise (no matches) +*/ + +static int +pcregrep(FILE *in, char *printname) +{ +int rc = 1; +int linenumber = 1; +int lastmatchnumber = 0; +int count = 0; +int offsets[99]; +char *lastmatchrestart = NULL; +char buffer[3*MBUFTHIRD]; +char *ptr = buffer; +char *endptr; +size_t bufflength; +BOOL endhyphenpending = FALSE; + +/* Do the first read into the start of the buffer and set up the pointer to +end of what we have. */ + +bufflength = fread(buffer, 1, 3*MBUFTHIRD, in); +endptr = buffer + bufflength; + +/* Loop while the current pointer is not at the end of the file. For large +files, endptr will be at the end of the buffer when we are in the middle of the +file, but ptr will never get there, because as soon as it gets over 2/3 of the +way, the buffer is shifted left and re-filled. */ + +while (ptr < endptr) + { + int i; + int mrc = 0; + BOOL match = FALSE; + char *t = ptr; + size_t length, linelength; + + /* At this point, ptr is at the start of a line. We need to find the length + of the subject string to pass to pcre_exec(). In multiline mode, it is the + length remainder of the data in the buffer. Otherwise, it is the length of + the next line. After matching, we always advance by the length of the next + line. In multiline mode the PCRE_FIRSTLINE option is used for compiling, so + that any match is constrained to be in the first line. */ + + linelength = 0; + while (t < endptr && *t++ != endlinebyte) linelength++; + length = multiline? endptr - ptr : linelength; + + + /* Extra processing for Jeffrey Friedl's debugging. */ + +#ifdef JFRIEDL_DEBUG + if (jfriedl_XT || jfriedl_XR) + { + #include + #include + struct timeval start_time, end_time; + struct timezone dummy; + + if (jfriedl_XT) + { + unsigned long newlen = length * jfriedl_XT + strlen(jfriedl_prefix) + strlen(jfriedl_postfix); + const char *orig = ptr; + ptr = malloc(newlen + 1); + if (!ptr) { + printf("out of memory"); + exit(2); + } + endptr = ptr; + strcpy(endptr, jfriedl_prefix); endptr += strlen(jfriedl_prefix); + for (i = 0; i < jfriedl_XT; i++) { + strncpy(endptr, orig, length); + endptr += length; + } + strcpy(endptr, jfriedl_postfix); endptr += strlen(jfriedl_postfix); + length = newlen; + } + + if (gettimeofday(&start_time, &dummy) != 0) + perror("bad gettimeofday"); + + + for (i = 0; i < jfriedl_XR; i++) + match = (pcre_exec(pattern_list[0], hints_list[0], ptr, length, 0, 0, offsets, 99) >= 0); + + if (gettimeofday(&end_time, &dummy) != 0) + perror("bad gettimeofday"); + + double delta = ((end_time.tv_sec + (end_time.tv_usec / 1000000.0)) + - + (start_time.tv_sec + (start_time.tv_usec / 1000000.0))); + + printf("%s TIMER[%.4f]\n", match ? "MATCH" : "FAIL", delta); + return 0; + } +#endif + + + /* Run through all the patterns until one matches. Note that we don't include + the final newline in the subject string. */ + + for (i = 0; i < pattern_count; i++) + { + mrc = pcre_exec(pattern_list[i], hints_list[i], ptr, length, 0, 0, + offsets, 99); + if (mrc >= 0) { match = TRUE; break; } + if (mrc != PCRE_ERROR_NOMATCH) + { + fprintf(stderr, "pcregrep: pcre_exec() error %d while matching ", mrc); + if (pattern_count > 1) fprintf(stderr, "pattern number %d to ", i+1); + fprintf(stderr, "this line:\n"); + fwrite(ptr, 1, linelength, stderr); /* In case binary zero included */ + fprintf(stderr, "\n"); + if (error_count == 0 && + (mrc == PCRE_ERROR_MATCHLIMIT || mrc == PCRE_ERROR_RECURSIONLIMIT)) + { + fprintf(stderr, "pcregrep: error %d means that a resource limit " + "was exceeded\n", mrc); + fprintf(stderr, "pcregrep: check your regex for nested unlimited loops\n"); + } + if (error_count++ > 20) + { + fprintf(stderr, "pcregrep: too many errors - abandoned\n"); + exit(2); + } + match = invert; /* No more matching; don't show the line again */ + break; + } + } + + /* If it's a match or a not-match (as required), do what's wanted. */ + + if (match != invert) + { + BOOL hyphenprinted = FALSE; + + /* We've failed if we want a file that doesn't have any matches. */ + + if (filenames == FN_NOMATCH_ONLY) return 1; + + /* Just count if just counting is wanted. */ + + if (count_only) count++; + + /* If all we want is a file name, there is no need to scan any more lines + in the file. */ + + else if (filenames == FN_ONLY) + { + fprintf(stdout, "%s\n", printname); + return 0; + } + + /* Likewise, if all we want is a yes/no answer. */ + + else if (quiet) return 0; + + /* The --only-matching option prints just the substring that matched, and + does not pring any context. */ + + else if (only_matching) + { + if (printname != NULL) fprintf(stdout, "%s:", printname); + if (number) fprintf(stdout, "%d:", linenumber); + fwrite(ptr + offsets[0], 1, offsets[1] - offsets[0], stdout); + fprintf(stdout, "\n"); + } + + /* This is the default case when none of the above options is set. We print + the matching lines(s), possibly preceded and/or followed by other lines of + context. */ + + else + { + /* See if there is a requirement to print some "after" lines from a + previous match. We never print any overlaps. */ + + if (after_context > 0 && lastmatchnumber > 0) + { + int linecount = 0; + char *p = lastmatchrestart; + + while (p < ptr && linecount < after_context) + { + while (*p != endlinebyte) p++; + p++; + linecount++; + } + + /* It is important to advance lastmatchrestart during this printing so + that it interacts correctly with any "before" printing below. Print + each line's data using fwrite() in case there are binary zeroes. */ + + while (lastmatchrestart < p) + { + char *pp = lastmatchrestart; + if (printname != NULL) fprintf(stdout, "%s-", printname); + if (number) fprintf(stdout, "%d-", lastmatchnumber++); + while (*pp != endlinebyte) pp++; + fwrite(lastmatchrestart, 1, pp - lastmatchrestart + + (1 + endlineextra), stdout); + lastmatchrestart = pp + 1; + } + if (lastmatchrestart != ptr) hyphenpending = TRUE; + } + + /* If there were non-contiguous lines printed above, insert hyphens. */ + + if (hyphenpending) + { + fprintf(stdout, "--\n"); + hyphenpending = FALSE; + hyphenprinted = TRUE; + } + + /* See if there is a requirement to print some "before" lines for this + match. Again, don't print overlaps. */ + + if (before_context > 0) + { + int linecount = 0; + char *p = ptr; + + while (p > buffer && (lastmatchnumber == 0 || p > lastmatchrestart) && + linecount < before_context) + { + linecount++; + p--; + while (p > buffer && p[-1] != endlinebyte) p--; + } + + if (lastmatchnumber > 0 && p > lastmatchrestart && !hyphenprinted) + fprintf(stdout, "--\n"); + + while (p < ptr) + { + char *pp = p; + if (printname != NULL) fprintf(stdout, "%s-", printname); + if (number) fprintf(stdout, "%d-", linenumber - linecount--); + while (*pp != endlinebyte) pp++; + fwrite(p, 1, pp - p + (1 + endlineextra), stdout); + p = pp + 1; + } + } + + /* Now print the matching line(s); ensure we set hyphenpending at the end + of the file if any context lines are being output. */ + + if (after_context > 0 || before_context > 0) + endhyphenpending = TRUE; + + if (printname != NULL) fprintf(stdout, "%s:", printname); + if (number) fprintf(stdout, "%d:", linenumber); + + /* In multiline mode, we want to print to the end of the line in which + the end of the matched string is found, so we adjust linelength and the + line number appropriately. Because the PCRE_FIRSTLINE option is set, the + start of the match will always be before the first newline sequence. */ + + if (multiline) + { + char *endmatch = ptr + offsets[1]; + t = ptr; + while (t < endmatch) { if (*t++ == endlinebyte) linenumber++; } + while (endmatch < endptr && *endmatch != endlinebyte) endmatch++; + linelength = endmatch - ptr; + } + + /*** NOTE: Use only fwrite() to output the data line, so that binary + zeroes are treated as just another data character. */ + + /* This extra option, for Jeffrey Friedl's debugging requirements, + replaces the matched string, or a specific captured string if it exists, + with X. When this happens, colouring is ignored. */ + +#ifdef JFRIEDL_DEBUG + if (S_arg >= 0 && S_arg < mrc) + { + int first = S_arg * 2; + int last = first + 1; + fwrite(ptr, 1, offsets[first], stdout); + fprintf(stdout, "X"); + fwrite(ptr + offsets[last], 1, linelength - offsets[last], stdout); + } + else +#endif + + /* We have to split the line(s) up if colouring. */ + + if (do_colour) + { + fwrite(ptr, 1, offsets[0], stdout); + fprintf(stdout, "%c[%sm", 0x1b, colour_string); + fwrite(ptr + offsets[0], 1, offsets[1] - offsets[0], stdout); + fprintf(stdout, "%c[00m", 0x1b); + fwrite(ptr + offsets[1], 1, linelength - offsets[1], stdout); + } + else fwrite(ptr, 1, linelength, stdout); + + fprintf(stdout, "\n"); + } + + /* End of doing what has to be done for a match */ + + rc = 0; /* Had some success */ + + /* Remember where the last match happened for after_context. We remember + where we are about to restart, and that line's number. */ + + lastmatchrestart = ptr + linelength + 1; + lastmatchnumber = linenumber + 1; + } + + /* Advance to after the newline and increment the line number. */ + + ptr += linelength + 1; + linenumber++; + + /* If we haven't yet reached the end of the file (the buffer is full), and + the current point is in the top 1/3 of the buffer, slide the buffer down by + 1/3 and refill it. Before we do this, if some unprinted "after" lines are + about to be lost, print them. */ + + if (bufflength >= sizeof(buffer) && ptr > buffer + 2*MBUFTHIRD) + { + if (after_context > 0 && + lastmatchnumber > 0 && + lastmatchrestart < buffer + MBUFTHIRD) + { + do_after_lines(lastmatchnumber, lastmatchrestart, endptr, printname); + lastmatchnumber = 0; + } + + /* Now do the shuffle */ + + memmove(buffer, buffer + MBUFTHIRD, 2*MBUFTHIRD); + ptr -= MBUFTHIRD; + bufflength = 2*MBUFTHIRD + fread(buffer + 2*MBUFTHIRD, 1, MBUFTHIRD, in); + endptr = buffer + bufflength; + + /* Adjust any last match point */ + + if (lastmatchnumber > 0) lastmatchrestart -= MBUFTHIRD; + } + } /* Loop through the whole file */ + +/* End of file; print final "after" lines if wanted; do_after_lines sets +hyphenpending if it prints something. */ + +if (!only_matching && !count_only) + { + do_after_lines(lastmatchnumber, lastmatchrestart, endptr, printname); + hyphenpending |= endhyphenpending; + } + +/* Print the file name if we are looking for those without matches and there +were none. If we found a match, we won't have got this far. */ + +if (filenames == FN_NOMATCH_ONLY) + { + fprintf(stdout, "%s\n", printname); + return 0; + } + +/* Print the match count if wanted */ + +if (count_only) + { + if (printname != NULL) fprintf(stdout, "%s:", printname); + fprintf(stdout, "%d\n", count); + } + +return rc; +} + + + +/************************************************* +* Grep a file or recurse into a directory * +*************************************************/ + +/* Given a path name, if it's a directory, scan all the files if we are +recursing; if it's a file, grep it. + +Arguments: + pathname the path to investigate + dir_recurse TRUE if recursing is wanted (-r or -drecurse) + only_one_at_top TRUE if the path is the only one at toplevel + +Returns: 0 if there was at least one match + 1 if there were no matches + 2 there was some kind of error + +However, file opening failures are suppressed if "silent" is set. +*/ + +static int +grep_or_recurse(char *pathname, BOOL dir_recurse, BOOL only_one_at_top) +{ +int rc = 1; +int sep; +FILE *in; + +/* If the file name is "-" we scan stdin */ + +if (strcmp(pathname, "-") == 0) + { + return pcregrep(stdin, + (filenames > FN_DEFAULT || (filenames == FN_DEFAULT && !only_one_at_top))? + stdin_name : NULL); + } + + +/* If the file is a directory, skip if skipping or if we are recursing, scan +each file within it, subject to any include or exclude patterns that were set. +The scanning code is localized so it can be made system-specific. */ + +if ((sep = isdirectory(pathname)) != 0) + { + if (dee_action == dee_SKIP) return 1; + if (dee_action == dee_RECURSE) + { + char buffer[1024]; + char *nextfile; + directory_type *dir = opendirectory(pathname); + + if (dir == NULL) + { + if (!silent) + fprintf(stderr, "pcregrep: Failed to open directory %s: %s\n", pathname, + strerror(errno)); + return 2; + } + + while ((nextfile = readdirectory(dir)) != NULL) + { + int frc, blen; + sprintf(buffer, "%.512s%c%.128s", pathname, sep, nextfile); + blen = strlen(buffer); + + if (exclude_compiled != NULL && + pcre_exec(exclude_compiled, NULL, buffer, blen, 0, 0, NULL, 0) >= 0) + continue; + + if (include_compiled != NULL && + pcre_exec(include_compiled, NULL, buffer, blen, 0, 0, NULL, 0) < 0) + continue; + + frc = grep_or_recurse(buffer, dir_recurse, FALSE); + if (frc > 1) rc = frc; + else if (frc == 0 && rc == 1) rc = 0; + } + + closedirectory(dir); + return rc; + } + } + +/* If the file is not a directory and not a regular file, skip it if that's +been requested. */ + +else if (!isregfile(pathname) && DEE_action == DEE_SKIP) return 1; + +/* Control reaches here if we have a regular file, or if we have a directory +and recursion or skipping was not requested, or if we have anything else and +skipping was not requested. The scan proceeds. If this is the first and only +argument at top level, we don't show the file name, unless we are only showing +the file name, or the filename was forced (-H). */ + +in = fopen(pathname, "r"); +if (in == NULL) + { + if (!silent) + fprintf(stderr, "pcregrep: Failed to open %s: %s\n", pathname, + strerror(errno)); + return 2; + } + +rc = pcregrep(in, (filenames > FN_DEFAULT || + (filenames == FN_DEFAULT && !only_one_at_top))? pathname : NULL); + +fclose(in); +return rc; +} + + + + +/************************************************* +* Usage function * +*************************************************/ + +static int +usage(int rc) +{ +option_item *op; +fprintf(stderr, "Usage: pcregrep [-"); +for (op = optionlist; op->one_char != 0; op++) + { + if (op->one_char > 0) fprintf(stderr, "%c", op->one_char); + } +fprintf(stderr, "] [long options] [pattern] [files]\n"); +fprintf(stderr, "Type `pcregrep --help' for more information.\n"); +return rc; +} + + + + +/************************************************* +* Help function * +*************************************************/ + +static void +help(void) +{ +option_item *op; + +printf("Usage: pcregrep [OPTION]... [PATTERN] [FILE1 FILE2 ...]\n"); +printf("Search for PATTERN in each FILE or standard input.\n"); +printf("PATTERN must be present if neither -e nor -f is used.\n"); +printf("\"-\" can be used as a file name to mean STDIN.\n\n"); +printf("Example: pcregrep -i 'hello.*world' menu.h main.c\n\n"); + +printf("Options:\n"); + +for (op = optionlist; op->one_char != 0; op++) + { + int n; + char s[4]; + if (op->one_char > 0) sprintf(s, "-%c,", op->one_char); else strcpy(s, " "); + printf(" %s --%s%n", s, op->long_name, &n); + n = 30 - n; + if (n < 1) n = 1; + printf("%.*s%s\n", n, " ", op->help_text); + } + +printf("\nWhen reading patterns from a file instead of using a command line option,\n"); +printf("trailing white space is removed and blank lines are ignored.\n"); +printf("There is a maximum of %d patterns.\n", MAX_PATTERN_COUNT); + +printf("\nWith no FILEs, read standard input. If fewer than two FILEs given, assume -h.\n"); +printf("Exit status is 0 if any matches, 1 if no matches, and 2 if trouble.\n"); +} + + + + +/************************************************* +* Handle a single-letter, no data option * +*************************************************/ + +static int +handle_option(int letter, int options) +{ +switch(letter) + { + case N_HELP: help(); exit(0); + case 'c': count_only = TRUE; break; + case 'F': process_options |= PO_FIXED_STRINGS; break; + case 'H': filenames = FN_FORCE; break; + case 'h': filenames = FN_NONE; break; + case 'i': options |= PCRE_CASELESS; break; + case 'l': filenames = FN_ONLY; break; + case 'L': filenames = FN_NOMATCH_ONLY; break; + case 'M': multiline = TRUE; options |= PCRE_MULTILINE|PCRE_FIRSTLINE; break; + case 'n': number = TRUE; break; + case 'o': only_matching = TRUE; break; + case 'q': quiet = TRUE; break; + case 'r': dee_action = dee_RECURSE; break; + case 's': silent = TRUE; break; + case 'u': options |= PCRE_UTF8; break; + case 'v': invert = TRUE; break; + case 'w': process_options |= PO_WORD_MATCH; break; + case 'x': process_options |= PO_LINE_MATCH; break; + + case 'V': + fprintf(stderr, "pcregrep version %s using ", VERSION); + fprintf(stderr, "PCRE version %s\n", pcre_version()); + exit(0); + break; + + default: + fprintf(stderr, "pcregrep: Unknown option -%c\n", letter); + exit(usage(2)); + } + +return options; +} + + + + +/************************************************* +* Construct printed ordinal * +*************************************************/ + +/* This turns a number into "1st", "3rd", etc. */ + +static char * +ordin(int n) +{ +static char buffer[8]; +char *p = buffer; +sprintf(p, "%d", n); +while (*p != 0) p++; +switch (n%10) + { + case 1: strcpy(p, "st"); break; + case 2: strcpy(p, "nd"); break; + case 3: strcpy(p, "rd"); break; + default: strcpy(p, "th"); break; + } +return buffer; +} + + + +/************************************************* +* Compile a single pattern * +*************************************************/ + +/* When the -F option has been used, this is called for each substring. +Otherwise it's called for each supplied pattern. + +Arguments: + pattern the pattern string + options the PCRE options + filename the file name, or NULL for a command-line pattern + count 0 if this is the only command line pattern, or + number of the command line pattern, or + linenumber for a pattern from a file + +Returns: TRUE on success, FALSE after an error +*/ + +static BOOL +compile_single_pattern(char *pattern, int options, char *filename, int count) +{ +char buffer[MBUFTHIRD + 16]; +const char *error; +int errptr; + +if (pattern_count >= MAX_PATTERN_COUNT) + { + fprintf(stderr, "pcregrep: Too many %spatterns (max %d)\n", + (filename == NULL)? "command-line " : "", MAX_PATTERN_COUNT); + return FALSE; + } + +sprintf(buffer, "%s%.*s%s", prefix[process_options], MBUFTHIRD, pattern, + suffix[process_options]); +pattern_list[pattern_count] = + pcre_compile(buffer, options, &error, &errptr, pcretables); +if (pattern_list[pattern_count++] != NULL) return TRUE; + +/* Handle compile errors */ + +errptr -= (int)strlen(prefix[process_options]); +if (errptr > (int)strlen(pattern)) errptr = (int)strlen(pattern); + +if (filename == NULL) + { + if (count == 0) + fprintf(stderr, "pcregrep: Error in command-line regex " + "at offset %d: %s\n", errptr, error); + else + fprintf(stderr, "pcregrep: Error in %s command-line regex " + "at offset %d: %s\n", ordin(count), errptr, error); + } +else + { + fprintf(stderr, "pcregrep: Error in regex in line %d of %s " + "at offset %d: %s\n", count, filename, errptr, error); + } + +return FALSE; +} + + + +/************************************************* +* Compile one supplied pattern * +*************************************************/ + +/* When the -F option has been used, each string may be a list of strings, +separated by line breaks. They will be matched literally. + +Arguments: + pattern the pattern string + options the PCRE options + filename the file name, or NULL for a command-line pattern + count 0 if this is the only command line pattern, or + number of the command line pattern, or + linenumber for a pattern from a file + +Returns: TRUE on success, FALSE after an error +*/ + +static BOOL +compile_pattern(char *pattern, int options, char *filename, int count) +{ +if ((process_options & PO_FIXED_STRINGS) != 0) + { + char buffer[MBUFTHIRD]; + for(;;) + { + char *p = strchr(pattern, endlinebyte); + if (p == NULL) + return compile_single_pattern(pattern, options, filename, count); + sprintf(buffer, "%.*s", p - pattern - endlineextra, pattern); + pattern = p + 1; + if (!compile_single_pattern(buffer, options, filename, count)) + return FALSE; + } + } +else return compile_single_pattern(pattern, options, filename, count); +} + + + +/************************************************* +* Main program * +*************************************************/ + +/* Returns 0 if something matched, 1 if nothing matched, 2 after an error. */ + +int +main(int argc, char **argv) +{ +int i, j; +int rc = 1; +int pcre_options = 0; +int cmd_pattern_count = 0; +int errptr; +BOOL only_one_at_top; +char *patterns[MAX_PATTERN_COUNT]; +const char *locale_from = "--locale"; +const char *error; + +/* Set the default line ending value from the default in the PCRE library. */ + +(void)pcre_config(PCRE_CONFIG_NEWLINE, &i); +switch(i) + { + default: newline = (char *)"lf"; break; + case '\r': newline = (char *)"cr"; break; + case ('\r' << 8) | '\n': newline = (char *)"crlf"; break; + } + +/* Process the options */ + +for (i = 1; i < argc; i++) + { + option_item *op = NULL; + char *option_data = (char *)""; /* default to keep compiler happy */ + BOOL longop; + BOOL longopwasequals = FALSE; + + if (argv[i][0] != '-') break; + + /* If we hit an argument that is just "-", it may be a reference to STDIN, + but only if we have previously had -e or -f to define the patterns. */ + + if (argv[i][1] == 0) + { + if (pattern_filename != NULL || pattern_count > 0) break; + else exit(usage(2)); + } + + /* Handle a long name option, or -- to terminate the options */ + + if (argv[i][1] == '-') + { + char *arg = argv[i] + 2; + char *argequals = strchr(arg, '='); + + if (*arg == 0) /* -- terminates options */ + { + i++; + break; /* out of the options-handling loop */ + } + + longop = TRUE; + + /* Some long options have data that follows after =, for example file=name. + Some options have variations in the long name spelling: specifically, we + allow "regexp" because GNU grep allows it, though I personally go along + with Jeffrey Friedl and Larry Wall in preferring "regex" without the "p". + These options are entered in the table as "regex(p)". No option is in both + these categories, fortunately. */ + + for (op = optionlist; op->one_char != 0; op++) + { + char *opbra = strchr(op->long_name, '('); + char *equals = strchr(op->long_name, '='); + if (opbra == NULL) /* Not a (p) case */ + { + if (equals == NULL) /* Not thing=data case */ + { + if (strcmp(arg, op->long_name) == 0) break; + } + else /* Special case xxx=data */ + { + int oplen = equals - op->long_name; + int arglen = (argequals == NULL)? strlen(arg) : argequals - arg; + if (oplen == arglen && strncmp(arg, op->long_name, oplen) == 0) + { + option_data = arg + arglen; + if (*option_data == '=') + { + option_data++; + longopwasequals = TRUE; + } + break; + } + } + } + else /* Special case xxxx(p) */ + { + char buff1[24]; + char buff2[24]; + int baselen = opbra - op->long_name; + sprintf(buff1, "%.*s", baselen, op->long_name); + sprintf(buff2, "%s%.*s", buff1, strlen(op->long_name) - baselen - 2, + opbra + 1); + if (strcmp(arg, buff1) == 0 || strcmp(arg, buff2) == 0) + break; + } + } + + if (op->one_char == 0) + { + fprintf(stderr, "pcregrep: Unknown option %s\n", argv[i]); + exit(usage(2)); + } + } + + + /* Jeffrey Friedl's debugging harness uses these additional options which + are not in the right form for putting in the option table because they use + only one hyphen, yet are more than one character long. By putting them + separately here, they will not get displayed as part of the help() output, + but I don't think Jeffrey will care about that. */ + +#ifdef JFRIEDL_DEBUG + else if (strcmp(argv[i], "-pre") == 0) { + jfriedl_prefix = argv[++i]; + continue; + } else if (strcmp(argv[i], "-post") == 0) { + jfriedl_postfix = argv[++i]; + continue; + } else if (strcmp(argv[i], "-XT") == 0) { + sscanf(argv[++i], "%d", &jfriedl_XT); + continue; + } else if (strcmp(argv[i], "-XR") == 0) { + sscanf(argv[++i], "%d", &jfriedl_XR); + continue; + } +#endif + + + /* One-char options; many that have no data may be in a single argument; we + continue till we hit the last one or one that needs data. */ + + else + { + char *s = argv[i] + 1; + longop = FALSE; + while (*s != 0) + { + for (op = optionlist; op->one_char != 0; op++) + { if (*s == op->one_char) break; } + if (op->one_char == 0) + { + fprintf(stderr, "pcregrep: Unknown option letter '%c' in \"%s\"\n", + *s, argv[i]); + exit(usage(2)); + } + if (op->type != OP_NODATA || s[1] == 0) + { + option_data = s+1; + break; + } + pcre_options = handle_option(*s++, pcre_options); + } + } + + /* At this point we should have op pointing to a matched option. If the type + is NO_DATA, it means that there is no data, and the option might set + something in the PCRE options. */ + + if (op->type == OP_NODATA) + { + pcre_options = handle_option(op->one_char, pcre_options); + continue; + } + + /* If the option type is OP_OP_STRING or OP_OP_NUMBER, it's an option that + either has a value or defaults to something. It cannot have data in a + separate item. At the moment, the only such options are "colo(u)r" and + Jeffrey Friedl's special -S debugging option. */ + + if (*option_data == 0 && + (op->type == OP_OP_STRING || op->type == OP_OP_NUMBER)) + { + switch (op->one_char) + { + case N_COLOUR: + colour_option = (char *)"auto"; + break; +#ifdef JFRIEDL_DEBUG + case 'S': + S_arg = 0; + break; +#endif + } + continue; + } + + /* Otherwise, find the data string for the option. */ + + if (*option_data == 0) + { + if (i >= argc - 1 || longopwasequals) + { + fprintf(stderr, "pcregrep: Data missing after %s\n", argv[i]); + exit(usage(2)); + } + option_data = argv[++i]; + } + + /* If the option type is OP_PATLIST, it's the -e option, which can be called + multiple times to create a list of patterns. */ + + if (op->type == OP_PATLIST) + { + if (cmd_pattern_count >= MAX_PATTERN_COUNT) + { + fprintf(stderr, "pcregrep: Too many command-line patterns (max %d)\n", + MAX_PATTERN_COUNT); + return 2; + } + patterns[cmd_pattern_count++] = option_data; + } + + /* Otherwise, deal with single string or numeric data values. */ + + else if (op->type != OP_NUMBER && op->type != OP_OP_NUMBER) + { + *((char **)op->dataptr) = option_data; + } + else + { + char *endptr; + int n = strtoul(option_data, &endptr, 10); + if (*endptr != 0) + { + if (longop) + { + char *equals = strchr(op->long_name, '='); + int nlen = (equals == NULL)? (int)strlen(op->long_name) : + equals - op->long_name; + fprintf(stderr, "pcregrep: Malformed number \"%s\" after --%.*s\n", + option_data, nlen, op->long_name); + } + else + fprintf(stderr, "pcregrep: Malformed number \"%s\" after -%c\n", + option_data, op->one_char); + exit(usage(2)); + } + *((int *)op->dataptr) = n; + } + } + +/* Options have been decoded. If -C was used, its value is used as a default +for -A and -B. */ + +if (both_context > 0) + { + if (after_context == 0) after_context = both_context; + if (before_context == 0) before_context = both_context; + } + +/* If a locale has not been provided as an option, see if the LC_CTYPE or +LC_ALL environment variable is set, and if so, use it. */ + +if (locale == NULL) + { + locale = getenv("LC_ALL"); + locale_from = "LCC_ALL"; + } + +if (locale == NULL) + { + locale = getenv("LC_CTYPE"); + locale_from = "LC_CTYPE"; + } + +/* If a locale has been provided, set it, and generate the tables the PCRE +needs. Otherwise, pcretables==NULL, which causes the use of default tables. */ + +if (locale != NULL) + { + if (setlocale(LC_CTYPE, locale) == NULL) + { + fprintf(stderr, "pcregrep: Failed to set locale %s (obtained from %s)\n", + locale, locale_from); + return 2; + } + pcretables = pcre_maketables(); + } + +/* Sort out colouring */ + +if (colour_option != NULL && strcmp(colour_option, "never") != 0) + { + if (strcmp(colour_option, "always") == 0) do_colour = TRUE; + else if (strcmp(colour_option, "auto") == 0) do_colour = is_stdout_tty(); + else + { + fprintf(stderr, "pcregrep: Unknown colour setting \"%s\"\n", + colour_option); + return 2; + } + if (do_colour) + { + char *cs = getenv("PCREGREP_COLOUR"); + if (cs == NULL) cs = getenv("PCREGREP_COLOR"); + if (cs != NULL) colour_string = cs; + } + } + +/* Interpret the newline type; the default settings are Unix-like. */ + +if (strcmp(newline, "cr") == 0 || strcmp(newline, "CR") == 0) + { + pcre_options |= PCRE_NEWLINE_CR; + endlinebyte = '\r'; + } +else if (strcmp(newline, "lf") == 0 || strcmp(newline, "LF") == 0) + { + pcre_options |= PCRE_NEWLINE_LF; + } +else if (strcmp(newline, "crlf") == 0 || strcmp(newline, "CRLF") == 0) + { + pcre_options |= PCRE_NEWLINE_CRLF; + endlineextra = 1; + } +else + { + fprintf(stderr, "pcregrep: Invalid newline specifier \"%s\"\n", newline); + return 2; + } + +/* Interpret the text values for -d and -D */ + +if (dee_option != NULL) + { + if (strcmp(dee_option, "read") == 0) dee_action = dee_READ; + else if (strcmp(dee_option, "recurse") == 0) dee_action = dee_RECURSE; + else if (strcmp(dee_option, "skip") == 0) dee_action = dee_SKIP; + else + { + fprintf(stderr, "pcregrep: Invalid value \"%s\" for -d\n", dee_option); + return 2; + } + } + +if (DEE_option != NULL) + { + if (strcmp(DEE_option, "read") == 0) DEE_action = DEE_READ; + else if (strcmp(DEE_option, "skip") == 0) DEE_action = DEE_SKIP; + else + { + fprintf(stderr, "pcregrep: Invalid value \"%s\" for -D\n", DEE_option); + return 2; + } + } + +/* Check the values for Jeffrey Friedl's debugging options. */ + +#ifdef JFRIEDL_DEBUG +if (S_arg > 9) + { + fprintf(stderr, "pcregrep: bad value for -S option\n"); + return 2; + } +if (jfriedl_XT != 0 || jfriedl_XR != 0) + { + if (jfriedl_XT == 0) jfriedl_XT = 1; + if (jfriedl_XR == 0) jfriedl_XR = 1; + } +#endif + +/* Get memory to store the pattern and hints lists. */ + +pattern_list = (pcre **)malloc(MAX_PATTERN_COUNT * sizeof(pcre *)); +hints_list = (pcre_extra **)malloc(MAX_PATTERN_COUNT * sizeof(pcre_extra *)); + +if (pattern_list == NULL || hints_list == NULL) + { + fprintf(stderr, "pcregrep: malloc failed\n"); + return 2; + } + +/* If no patterns were provided by -e, and there is no file provided by -f, +the first argument is the one and only pattern, and it must exist. */ + +if (cmd_pattern_count == 0 && pattern_filename == NULL) + { + if (i >= argc) return usage(2); + patterns[cmd_pattern_count++] = argv[i++]; + } + +/* Compile the patterns that were provided on the command line, either by +multiple uses of -e or as a single unkeyed pattern. */ + +for (j = 0; j < cmd_pattern_count; j++) + { + if (!compile_pattern(patterns[j], pcre_options, NULL, + (j == 0 && cmd_pattern_count == 1)? 0 : j + 1)) + return 2; + } + +/* Compile the regular expressions that are provided in a file. */ + +if (pattern_filename != NULL) + { + int linenumber = 0; + FILE *f; + char *filename; + char buffer[MBUFTHIRD]; + + if (strcmp(pattern_filename, "-") == 0) + { + f = stdin; + filename = stdin_name; + } + else + { + f = fopen(pattern_filename, "r"); + if (f == NULL) + { + fprintf(stderr, "pcregrep: Failed to open %s: %s\n", pattern_filename, + strerror(errno)); + return 2; + } + filename = pattern_filename; + } + + while (fgets(buffer, MBUFTHIRD, f) != NULL) + { + char *s = buffer + (int)strlen(buffer); + while (s > buffer && isspace((unsigned char)(s[-1]))) s--; + *s = 0; + linenumber++; + if (buffer[0] == 0) continue; /* Skip blank lines */ + if (!compile_pattern(buffer, pcre_options, filename, linenumber)) + return 2; + } + + if (f != stdin) fclose(f); + } + +/* Study the regular expressions, as we will be running them many times */ + +for (j = 0; j < pattern_count; j++) + { + hints_list[j] = pcre_study(pattern_list[j], 0, &error); + if (error != NULL) + { + char s[16]; + if (pattern_count == 1) s[0] = 0; else sprintf(s, " number %d", j); + fprintf(stderr, "pcregrep: Error while studying regex%s: %s\n", s, error); + return 2; + } + } + +/* If there are include or exclude patterns, compile them. */ + +if (exclude_pattern != NULL) + { + exclude_compiled = pcre_compile(exclude_pattern, 0, &error, &errptr, + pcretables); + if (exclude_compiled == NULL) + { + fprintf(stderr, "pcregrep: Error in 'exclude' regex at offset %d: %s\n", + errptr, error); + return 2; + } + } + +if (include_pattern != NULL) + { + include_compiled = pcre_compile(include_pattern, 0, &error, &errptr, + pcretables); + if (include_compiled == NULL) + { + fprintf(stderr, "pcregrep: Error in 'include' regex at offset %d: %s\n", + errptr, error); + return 2; + } + } + +/* If there are no further arguments, do the business on stdin and exit. */ + +if (i >= argc) + return pcregrep(stdin, (filenames > FN_DEFAULT)? stdin_name : NULL); + +/* Otherwise, work through the remaining arguments as files or directories. +Pass in the fact that there is only one argument at top level - this suppresses +the file name if the argument is not a directory and filenames are not +otherwise forced. */ + +only_one_at_top = i == argc - 1; /* Catch initial value of i */ + +for (; i < argc; i++) + { + int frc = grep_or_recurse(argv[i], dee_action == dee_RECURSE, + only_one_at_top); + if (frc > 1) rc = frc; + else if (frc == 0 && rc == 1) rc = 0; + } + +return rc; +} + +/* End of pcregrep */ diff --git a/libs/pcre/pcreposix.c b/libs/pcre/pcreposix.c new file mode 100644 index 0000000000..b3472361c9 --- /dev/null +++ b/libs/pcre/pcreposix.c @@ -0,0 +1,315 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +/* PCRE is a library of functions to support regular expressions whose syntax +and semantics are as close as possible to those of the Perl 5 language. + + Written by Philip Hazel + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +/* This module is a wrapper that provides a POSIX API to the underlying PCRE +functions. */ + + +#include "pcre_internal.h" +#include "pcreposix.h" +#include "stdlib.h" + + + +/* Table to translate PCRE compile time error codes into POSIX error codes. */ + +static const int eint[] = { + 0, /* no error */ + REG_EESCAPE, /* \ at end of pattern */ + REG_EESCAPE, /* \c at end of pattern */ + REG_EESCAPE, /* unrecognized character follows \ */ + REG_BADBR, /* numbers out of order in {} quantifier */ + REG_BADBR, /* number too big in {} quantifier */ + REG_EBRACK, /* missing terminating ] for character class */ + REG_ECTYPE, /* invalid escape sequence in character class */ + REG_ERANGE, /* range out of order in character class */ + REG_BADRPT, /* nothing to repeat */ + REG_BADRPT, /* operand of unlimited repeat could match the empty string */ + REG_ASSERT, /* internal error: unexpected repeat */ + REG_BADPAT, /* unrecognized character after (? */ + REG_BADPAT, /* POSIX named classes are supported only within a class */ + REG_EPAREN, /* missing ) */ + REG_ESUBREG, /* reference to non-existent subpattern */ + REG_INVARG, /* erroffset passed as NULL */ + REG_INVARG, /* unknown option bit(s) set */ + REG_EPAREN, /* missing ) after comment */ + REG_ESIZE, /* parentheses nested too deeply */ + REG_ESIZE, /* regular expression too large */ + REG_ESPACE, /* failed to get memory */ + REG_EPAREN, /* unmatched brackets */ + REG_ASSERT, /* internal error: code overflow */ + REG_BADPAT, /* unrecognized character after (?< */ + REG_BADPAT, /* lookbehind assertion is not fixed length */ + REG_BADPAT, /* malformed number or name after (?( */ + REG_BADPAT, /* conditional group containe more than two branches */ + REG_BADPAT, /* assertion expected after (?( */ + REG_BADPAT, /* (?R or (?digits must be followed by ) */ + REG_ECTYPE, /* unknown POSIX class name */ + REG_BADPAT, /* POSIX collating elements are not supported */ + REG_INVARG, /* this version of PCRE is not compiled with PCRE_UTF8 support */ + REG_BADPAT, /* spare error */ + REG_BADPAT, /* character value in \x{...} sequence is too large */ + REG_BADPAT, /* invalid condition (?(0) */ + REG_BADPAT, /* \C not allowed in lookbehind assertion */ + REG_EESCAPE, /* PCRE does not support \L, \l, \N, \U, or \u */ + REG_BADPAT, /* number after (?C is > 255 */ + REG_BADPAT, /* closing ) for (?C expected */ + REG_BADPAT, /* recursive call could loop indefinitely */ + REG_BADPAT, /* unrecognized character after (?P */ + REG_BADPAT, /* syntax error after (?P */ + REG_BADPAT, /* two named subpatterns have the same name */ + REG_BADPAT, /* invalid UTF-8 string */ + REG_BADPAT, /* support for \P, \p, and \X has not been compiled */ + REG_BADPAT, /* malformed \P or \p sequence */ + REG_BADPAT, /* unknown property name after \P or \p */ + REG_BADPAT, /* subpattern name is too long (maximum 32 characters) */ + REG_BADPAT, /* too many named subpatterns (maximum 10,000) */ + REG_BADPAT, /* repeated subpattern is too long */ + REG_BADPAT /* octal value is greater than \377 (not in UTF-8 mode) */ +}; + +/* Table of texts corresponding to POSIX error codes */ + +static const char *const pstring[] = { + "", /* Dummy for value 0 */ + "internal error", /* REG_ASSERT */ + "invalid repeat counts in {}", /* BADBR */ + "pattern error", /* BADPAT */ + "? * + invalid", /* BADRPT */ + "unbalanced {}", /* EBRACE */ + "unbalanced []", /* EBRACK */ + "collation error - not relevant", /* ECOLLATE */ + "bad class", /* ECTYPE */ + "bad escape sequence", /* EESCAPE */ + "empty expression", /* EMPTY */ + "unbalanced ()", /* EPAREN */ + "bad range inside []", /* ERANGE */ + "expression too big", /* ESIZE */ + "failed to get memory", /* ESPACE */ + "bad back reference", /* ESUBREG */ + "bad argument", /* INVARG */ + "match failed" /* NOMATCH */ +}; + + + + +/************************************************* +* Translate error code to string * +*************************************************/ + +PCRE_DATA_SCOPE size_t +regerror(int errcode, const regex_t *preg, char *errbuf, size_t errbuf_size) +{ +const char *message, *addmessage; +size_t length, addlength; + +message = (errcode >= (int)(sizeof(pstring)/sizeof(char *)))? + "unknown error code" : pstring[errcode]; +length = strlen(message) + 1; + +addmessage = " at offset "; +addlength = (preg != NULL && (int)preg->re_erroffset != -1)? + strlen(addmessage) + 6 : 0; + +if (errbuf_size > 0) + { + if (addlength > 0 && errbuf_size >= length + addlength) + sprintf(errbuf, "%s%s%-6d", message, addmessage, (int)preg->re_erroffset); + else + { + strncpy(errbuf, message, errbuf_size - 1); + errbuf[errbuf_size-1] = 0; + } + } + +return length + addlength; +} + + + + +/************************************************* +* Free store held by a regex * +*************************************************/ + +PCRE_DATA_SCOPE void +regfree(regex_t *preg) +{ +(pcre_free)(preg->re_pcre); +} + + + + +/************************************************* +* Compile a regular expression * +*************************************************/ + +/* +Arguments: + preg points to a structure for recording the compiled expression + pattern the pattern to compile + cflags compilation flags + +Returns: 0 on success + various non-zero codes on failure +*/ + +PCRE_DATA_SCOPE int +regcomp(regex_t *preg, const char *pattern, int cflags) +{ +const char *errorptr; +int erroffset; +int errorcode; +int options = 0; + +if ((cflags & REG_ICASE) != 0) options |= PCRE_CASELESS; +if ((cflags & REG_NEWLINE) != 0) options |= PCRE_MULTILINE; +if ((cflags & REG_DOTALL) != 0) options |= PCRE_DOTALL; +if ((cflags & REG_NOSUB) != 0) options |= PCRE_NO_AUTO_CAPTURE; +if ((cflags & REG_UTF8) != 0) options |= PCRE_UTF8; + +preg->re_pcre = pcre_compile2(pattern, options, &errorcode, &errorptr, + &erroffset, NULL); +preg->re_erroffset = erroffset; + +if (preg->re_pcre == NULL) return eint[errorcode]; + +preg->re_nsub = pcre_info((const pcre *)preg->re_pcre, NULL, NULL); +return 0; +} + + + + +/************************************************* +* Match a regular expression * +*************************************************/ + +/* Unfortunately, PCRE requires 3 ints of working space for each captured +substring, so we have to get and release working store instead of just using +the POSIX structures as was done in earlier releases when PCRE needed only 2 +ints. However, if the number of possible capturing brackets is small, use a +block of store on the stack, to reduce the use of malloc/free. The threshold is +in a macro that can be changed at configure time. + +If REG_NOSUB was specified at compile time, the PCRE_NO_AUTO_CAPTURE flag will +be set. When this is the case, the nmatch and pmatch arguments are ignored, and +the only result is yes/no/error. */ + +PCRE_DATA_SCOPE int +regexec(const regex_t *preg, const char *string, size_t nmatch, + regmatch_t pmatch[], int eflags) +{ +int rc; +int options = 0; +int *ovector = NULL; +int small_ovector[POSIX_MALLOC_THRESHOLD * 3]; +BOOL allocated_ovector = FALSE; +BOOL nosub = + (((const pcre *)preg->re_pcre)->options & PCRE_NO_AUTO_CAPTURE) != 0; + +if ((eflags & REG_NOTBOL) != 0) options |= PCRE_NOTBOL; +if ((eflags & REG_NOTEOL) != 0) options |= PCRE_NOTEOL; + +((regex_t *)preg)->re_erroffset = (size_t)(-1); /* Only has meaning after compile */ + +/* When no string data is being returned, ensure that nmatch is zero. +Otherwise, ensure the vector for holding the return data is large enough. */ + +if (nosub) nmatch = 0; + +else if (nmatch > 0) + { + if (nmatch <= POSIX_MALLOC_THRESHOLD) + { + ovector = &(small_ovector[0]); + } + else + { + if (nmatch > INT_MAX/(sizeof(int) * 3)) return REG_ESPACE; + ovector = (int *)malloc(sizeof(int) * nmatch * 3); + if (ovector == NULL) return REG_ESPACE; + allocated_ovector = TRUE; + } + } + +rc = pcre_exec((const pcre *)preg->re_pcre, NULL, string, (int)strlen(string), + 0, options, ovector, nmatch * 3); + +if (rc == 0) rc = nmatch; /* All captured slots were filled in */ + +if (rc >= 0) + { + size_t i; + if (!nosub) + { + for (i = 0; i < (size_t)rc; i++) + { + pmatch[i].rm_so = ovector[i*2]; + pmatch[i].rm_eo = ovector[i*2+1]; + } + if (allocated_ovector) free(ovector); + for (; i < nmatch; i++) pmatch[i].rm_so = pmatch[i].rm_eo = -1; + } + return 0; + } + +else + { + if (allocated_ovector) free(ovector); + switch(rc) + { + case PCRE_ERROR_NOMATCH: return REG_NOMATCH; + case PCRE_ERROR_NULL: return REG_INVARG; + case PCRE_ERROR_BADOPTION: return REG_INVARG; + case PCRE_ERROR_BADMAGIC: return REG_INVARG; + case PCRE_ERROR_UNKNOWN_NODE: return REG_ASSERT; + case PCRE_ERROR_NOMEMORY: return REG_ESPACE; + case PCRE_ERROR_MATCHLIMIT: return REG_ESPACE; + case PCRE_ERROR_BADUTF8: return REG_INVARG; + case PCRE_ERROR_BADUTF8_OFFSET: return REG_INVARG; + default: return REG_ASSERT; + } + } +} + +/* End of pcreposix.c */ diff --git a/libs/pcre/pcreposix.h b/libs/pcre/pcreposix.h new file mode 100644 index 0000000000..31ee03749c --- /dev/null +++ b/libs/pcre/pcreposix.h @@ -0,0 +1,147 @@ +/************************************************* +* Perl-Compatible Regular Expressions * +*************************************************/ + +#ifndef _PCREPOSIX_H +#define _PCREPOSIX_H + +/* This is the header for the POSIX wrapper interface to the PCRE Perl- +Compatible Regular Expression library. It defines the things POSIX says should +be there. I hope. + + Copyright (c) 1997-2006 University of Cambridge + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + +/* Have to include stdlib.h in order to ensure that size_t is defined. */ + +#include + +/* Allow for C++ users */ + +#ifdef __cplusplus +extern "C" { +#endif + +/* Options, mostly defined by POSIX, but with a couple of extras. */ + +#define REG_ICASE 0x0001 +#define REG_NEWLINE 0x0002 +#define REG_NOTBOL 0x0004 +#define REG_NOTEOL 0x0008 +#define REG_DOTALL 0x0010 /* NOT defined by POSIX. */ +#define REG_NOSUB 0x0020 +#define REG_UTF8 0x0040 /* NOT defined by POSIX. */ + +/* This is not used by PCRE, but by defining it we make it easier +to slot PCRE into existing programs that make POSIX calls. */ + +#define REG_EXTENDED 0 + +/* Error values. Not all these are relevant or used by the wrapper. */ + +enum { + REG_ASSERT = 1, /* internal error ? */ + REG_BADBR, /* invalid repeat counts in {} */ + REG_BADPAT, /* pattern error */ + REG_BADRPT, /* ? * + invalid */ + REG_EBRACE, /* unbalanced {} */ + REG_EBRACK, /* unbalanced [] */ + REG_ECOLLATE, /* collation error - not relevant */ + REG_ECTYPE, /* bad class */ + REG_EESCAPE, /* bad escape sequence */ + REG_EMPTY, /* empty expression */ + REG_EPAREN, /* unbalanced () */ + REG_ERANGE, /* bad range inside [] */ + REG_ESIZE, /* expression too big */ + REG_ESPACE, /* failed to get memory */ + REG_ESUBREG, /* bad back reference */ + REG_INVARG, /* bad argument */ + REG_NOMATCH /* match failed */ +}; + + +/* The structure representing a compiled regular expression. */ + +typedef struct { + void *re_pcre; + size_t re_nsub; + size_t re_erroffset; +} regex_t; + +/* The structure in which a captured offset is returned. */ + +typedef int regoff_t; + +typedef struct { + regoff_t rm_so; + regoff_t rm_eo; +} regmatch_t; + +/* Win32 uses DLL by default; it needs special stuff for exported functions +when building PCRE. */ + +#ifndef PCRE_DATA_SCOPE +#ifdef _WIN32 +# ifdef PCRE_DEFINITION +# ifdef DLL_EXPORT +# define PCRE_DATA_SCOPE __declspec(dllexport) +# endif +# else +# ifndef PCRE_STATIC +# define PCRE_DATA_SCOPE extern __declspec(dllimport) +# endif +# endif +#endif +#endif + +/* Otherwise, we use the standard "extern". */ + +#ifndef PCRE_DATA_SCOPE +# ifdef __cplusplus +# define PCRE_DATA_SCOPE extern "C" +# else +# define PCRE_DATA_SCOPE extern +# endif +#endif + +/* The functions */ + +PCRE_DATA_SCOPE int regcomp(regex_t *, const char *, int); +PCRE_DATA_SCOPE int regexec(const regex_t *, const char *, size_t, + regmatch_t *, int); +PCRE_DATA_SCOPE size_t regerror(int, const regex_t *, char *, size_t); +PCRE_DATA_SCOPE void regfree(regex_t *); + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* End of pcreposix.h */ diff --git a/libs/pcre/pcretest.c b/libs/pcre/pcretest.c new file mode 100644 index 0000000000..431378c6dc --- /dev/null +++ b/libs/pcre/pcretest.c @@ -0,0 +1,2186 @@ +/************************************************* +* PCRE testing program * +*************************************************/ + +/* This program was hacked up as a tester for PCRE. I really should have +written it more tidily in the first place. Will I ever learn? It has grown and +been extended and consequently is now rather, er, *very* untidy in places. + +----------------------------------------------------------------------------- +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright notice, + this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + + * Neither the name of the University of Cambridge nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE +LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR +CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF +SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN +CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) +ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE +POSSIBILITY OF SUCH DAMAGE. +----------------------------------------------------------------------------- +*/ + + +#include +#include +#include +#include +#include +#include +#include + +#ifndef _WIN32 +#include +#endif + +#define PCRE_SPY /* For Win32 build, import data, not export */ + +/* We include pcre_internal.h because we need the internal info for displaying +the results of pcre_study() and we also need to know about the internal +macros, structures, and other internal data values; pcretest has "inside +information" compared to a program that strictly follows the PCRE API. */ + +#include "pcre_internal.h" + +/* We need access to the data tables that PCRE uses. So as not to have to keep +two copies, we include the source file here, changing the names of the external +symbols to prevent clashes. */ + +#define _pcre_utf8_table1 utf8_table1 +#define _pcre_utf8_table1_size utf8_table1_size +#define _pcre_utf8_table2 utf8_table2 +#define _pcre_utf8_table3 utf8_table3 +#define _pcre_utf8_table4 utf8_table4 +#define _pcre_utt utt +#define _pcre_utt_size utt_size +#define _pcre_OP_lengths OP_lengths + +#include "pcre_tables.c" + +/* We also need the pcre_printint() function for printing out compiled +patterns. This function is in a separate file so that it can be included in +pcre_compile.c when that module is compiled with debugging enabled. */ + +#include "pcre_printint.src" + + +/* It is possible to compile this test program without including support for +testing the POSIX interface, though this is not available via the standard +Makefile. */ + +#if !defined NOPOSIX +#include "pcreposix.h" +#endif + +/* It is also possible, for the benefit of the version imported into Exim, to +build pcretest without support for UTF8 (define NOUTF8), without the interface +to the DFA matcher (NODFA), and without the doublecheck of the old "info" +function (define NOINFOCHECK). */ + + +/* Other parameters */ + +#ifndef CLOCKS_PER_SEC +#ifdef CLK_TCK +#define CLOCKS_PER_SEC CLK_TCK +#else +#define CLOCKS_PER_SEC 100 +#endif +#endif + +#define LOOPREPEAT 500000 + +/* Static variables */ + +static FILE *outfile; +static int log_store = 0; +static int callout_count; +static int callout_extra; +static int callout_fail_count; +static int callout_fail_id; +static int first_callout; +static int show_malloc; +static int use_utf8; +static size_t gotten_store; + +/* The buffers grow automatically if very long input lines are encountered. */ + +static int buffer_size = 50000; +static uschar *buffer = NULL; +static uschar *dbuffer = NULL; +static uschar *pbuffer = NULL; + + + +/************************************************* +* Read or extend an input line * +*************************************************/ + +/* Input lines are read into buffer, but both patterns and data lines can be +continued over multiple input lines. In addition, if the buffer fills up, we +want to automatically expand it so as to be able to handle extremely large +lines that are needed for certain stress tests. When the input buffer is +expanded, the other two buffers must also be expanded likewise, and the +contents of pbuffer, which are a copy of the input for callouts, must be +preserved (for when expansion happens for a data line). This is not the most +optimal way of handling this, but hey, this is just a test program! + +Arguments: + f the file to read + start where in buffer to start (this *must* be within buffer) + +Returns: pointer to the start of new data + could be a copy of start, or could be moved + NULL if no data read and EOF reached +*/ + +static uschar * +extend_inputline(FILE *f, uschar *start) +{ +uschar *here = start; + +for (;;) + { + int rlen = buffer_size - (here - buffer); + if (rlen > 1000) + { + int dlen; + if (fgets((char *)here, rlen, f) == NULL) + return (here == start)? NULL : start; + dlen = (int)strlen((char *)here); + if (dlen > 0 && here[dlen - 1] == '\n') return start; + here += dlen; + } + + else + { + int new_buffer_size = 2*buffer_size; + uschar *new_buffer = (unsigned char *)malloc(new_buffer_size); + uschar *new_dbuffer = (unsigned char *)malloc(new_buffer_size); + uschar *new_pbuffer = (unsigned char *)malloc(new_buffer_size); + + if (new_buffer == NULL || new_dbuffer == NULL || new_pbuffer == NULL) + { + fprintf(stderr, "pcretest: malloc(%d) failed\n", new_buffer_size); + exit(1); + } + + memcpy(new_buffer, buffer, buffer_size); + memcpy(new_pbuffer, pbuffer, buffer_size); + + buffer_size = new_buffer_size; + + start = new_buffer + (start - buffer); + here = new_buffer + (here - buffer); + + free(buffer); + free(dbuffer); + free(pbuffer); + + buffer = new_buffer; + dbuffer = new_dbuffer; + pbuffer = new_pbuffer; + } + } + +return NULL; /* Control never gets here */ +} + + + + + + + +/************************************************* +* Read number from string * +*************************************************/ + +/* We don't use strtoul() because SunOS4 doesn't have it. Rather than mess +around with conditional compilation, just do the job by hand. It is only used +for unpicking the -o argument, so just keep it simple. + +Arguments: + str string to be converted + endptr where to put the end pointer + +Returns: the unsigned long +*/ + +static int +get_value(unsigned char *str, unsigned char **endptr) +{ +int result = 0; +while(*str != 0 && isspace(*str)) str++; +while (isdigit(*str)) result = result * 10 + (int)(*str++ - '0'); +*endptr = str; +return(result); +} + + + + +/************************************************* +* Convert UTF-8 string to value * +*************************************************/ + +/* This function takes one or more bytes that represents a UTF-8 character, +and returns the value of the character. + +Argument: + utf8bytes a pointer to the byte vector + vptr a pointer to an int to receive the value + +Returns: > 0 => the number of bytes consumed + -6 to 0 => malformed UTF-8 character at offset = (-return) +*/ + +#if !defined NOUTF8 + +static int +utf82ord(unsigned char *utf8bytes, int *vptr) +{ +int c = *utf8bytes++; +int d = c; +int i, j, s; + +for (i = -1; i < 6; i++) /* i is number of additional bytes */ + { + if ((d & 0x80) == 0) break; + d <<= 1; + } + +if (i == -1) { *vptr = c; return 1; } /* ascii character */ +if (i == 0 || i == 6) return 0; /* invalid UTF-8 */ + +/* i now has a value in the range 1-5 */ + +s = 6*i; +d = (c & utf8_table3[i]) << s; + +for (j = 0; j < i; j++) + { + c = *utf8bytes++; + if ((c & 0xc0) != 0x80) return -(j+1); + s -= 6; + d |= (c & 0x3f) << s; + } + +/* Check that encoding was the correct unique one */ + +for (j = 0; j < utf8_table1_size; j++) + if (d <= utf8_table1[j]) break; +if (j != i) return -(i+1); + +/* Valid value */ + +*vptr = d; +return i+1; +} + +#endif + + + +/************************************************* +* Convert character value to UTF-8 * +*************************************************/ + +/* This function takes an integer value in the range 0 - 0x7fffffff +and encodes it as a UTF-8 character in 0 to 6 bytes. + +Arguments: + cvalue the character value + utf8bytes pointer to buffer for result - at least 6 bytes long + +Returns: number of characters placed in the buffer +*/ + +static int +ord2utf8(int cvalue, uschar *utf8bytes) +{ +register int i, j; +for (i = 0; i < utf8_table1_size; i++) + if (cvalue <= utf8_table1[i]) break; +utf8bytes += i; +for (j = i; j > 0; j--) + { + *utf8bytes-- = 0x80 | (cvalue & 0x3f); + cvalue >>= 6; + } +*utf8bytes = utf8_table2[i] | cvalue; +return i + 1; +} + + + +/************************************************* +* Print character string * +*************************************************/ + +/* Character string printing function. Must handle UTF-8 strings in utf8 +mode. Yields number of characters printed. If handed a NULL file, just counts +chars without printing. */ + +static int pchars(unsigned char *p, int length, FILE *f) +{ +int c = 0; +int yield = 0; + +while (length-- > 0) + { +#if !defined NOUTF8 + if (use_utf8) + { + int rc = utf82ord(p, &c); + + if (rc > 0 && rc <= length + 1) /* Mustn't run over the end */ + { + length -= rc - 1; + p += rc; + if (c < 256 && isprint(c)) + { + if (f != NULL) fprintf(f, "%c", c); + yield++; + } + else + { + int n; + if (f != NULL) fprintf(f, "\\x{%02x}%n", c, &n); + yield += n; + } + continue; + } + } +#endif + + /* Not UTF-8, or malformed UTF-8 */ + + if (isprint(c = *(p++))) + { + if (f != NULL) fprintf(f, "%c", c); + yield++; + } + else + { + if (f != NULL) fprintf(f, "\\x%02x", c); + yield += 4; + } + } + +return yield; +} + + + +/************************************************* +* Callout function * +*************************************************/ + +/* Called from PCRE as a result of the (?C) item. We print out where we are in +the match. Yield zero unless more callouts than the fail count, or the callout +data is not zero. */ + +static int callout(pcre_callout_block *cb) +{ +FILE *f = (first_callout | callout_extra)? outfile : NULL; +int i, pre_start, post_start, subject_length; + +if (callout_extra) + { + fprintf(f, "Callout %d: last capture = %d\n", + cb->callout_number, cb->capture_last); + + for (i = 0; i < cb->capture_top * 2; i += 2) + { + if (cb->offset_vector[i] < 0) + fprintf(f, "%2d: \n", i/2); + else + { + fprintf(f, "%2d: ", i/2); + (void)pchars((unsigned char *)cb->subject + cb->offset_vector[i], + cb->offset_vector[i+1] - cb->offset_vector[i], f); + fprintf(f, "\n"); + } + } + } + +/* Re-print the subject in canonical form, the first time or if giving full +datails. On subsequent calls in the same match, we use pchars just to find the +printed lengths of the substrings. */ + +if (f != NULL) fprintf(f, "--->"); + +pre_start = pchars((unsigned char *)cb->subject, cb->start_match, f); +post_start = pchars((unsigned char *)(cb->subject + cb->start_match), + cb->current_position - cb->start_match, f); + +subject_length = pchars((unsigned char *)cb->subject, cb->subject_length, NULL); + +(void)pchars((unsigned char *)(cb->subject + cb->current_position), + cb->subject_length - cb->current_position, f); + +if (f != NULL) fprintf(f, "\n"); + +/* Always print appropriate indicators, with callout number if not already +shown. For automatic callouts, show the pattern offset. */ + +if (cb->callout_number == 255) + { + fprintf(outfile, "%+3d ", cb->pattern_position); + if (cb->pattern_position > 99) fprintf(outfile, "\n "); + } +else + { + if (callout_extra) fprintf(outfile, " "); + else fprintf(outfile, "%3d ", cb->callout_number); + } + +for (i = 0; i < pre_start; i++) fprintf(outfile, " "); +fprintf(outfile, "^"); + +if (post_start > 0) + { + for (i = 0; i < post_start - 1; i++) fprintf(outfile, " "); + fprintf(outfile, "^"); + } + +for (i = 0; i < subject_length - pre_start - post_start + 4; i++) + fprintf(outfile, " "); + +fprintf(outfile, "%.*s", (cb->next_item_length == 0)? 1 : cb->next_item_length, + pbuffer + cb->pattern_position); + +fprintf(outfile, "\n"); +first_callout = 0; + +if (cb->callout_data != NULL) + { + int callout_data = *((int *)(cb->callout_data)); + if (callout_data != 0) + { + fprintf(outfile, "Callout data = %d\n", callout_data); + return callout_data; + } + } + +return (cb->callout_number != callout_fail_id)? 0 : + (++callout_count >= callout_fail_count)? 1 : 0; +} + + +/************************************************* +* Local malloc functions * +*************************************************/ + +/* Alternative malloc function, to test functionality and show the size of the +compiled re. */ + +static void *new_malloc(size_t size) +{ +void *block = malloc(size); +gotten_store = size; +if (show_malloc) + fprintf(outfile, "malloc %3d %p\n", (int)size, block); +return block; +} + +static void new_free(void *block) +{ +if (show_malloc) + fprintf(outfile, "free %p\n", block); +free(block); +} + + +/* For recursion malloc/free, to test stacking calls */ + +static void *stack_malloc(size_t size) +{ +void *block = malloc(size); +if (show_malloc) + fprintf(outfile, "stack_malloc %3d %p\n", (int)size, block); +return block; +} + +static void stack_free(void *block) +{ +if (show_malloc) + fprintf(outfile, "stack_free %p\n", block); +free(block); +} + + +/************************************************* +* Call pcre_fullinfo() * +*************************************************/ + +/* Get one piece of information from the pcre_fullinfo() function */ + +static void new_info(pcre *re, pcre_extra *study, int option, void *ptr) +{ +int rc; +if ((rc = pcre_fullinfo(re, study, option, ptr)) < 0) + fprintf(outfile, "Error %d from pcre_fullinfo(%d)\n", rc, option); +} + + + +/************************************************* +* Byte flipping function * +*************************************************/ + +static unsigned long int +byteflip(unsigned long int value, int n) +{ +if (n == 2) return ((value & 0x00ff) << 8) | ((value & 0xff00) >> 8); +return ((value & 0x000000ff) << 24) | + ((value & 0x0000ff00) << 8) | + ((value & 0x00ff0000) >> 8) | + ((value & 0xff000000) >> 24); +} + + + + +/************************************************* +* Check match or recursion limit * +*************************************************/ + +static int +check_match_limit(pcre *re, pcre_extra *extra, uschar *bptr, int len, + int start_offset, int options, int *use_offsets, int use_size_offsets, + int flag, unsigned long int *limit, int errnumber, const char *msg) +{ +int count; +int min = 0; +int mid = 64; +int max = -1; + +extra->flags |= flag; + +for (;;) + { + *limit = mid; + + count = pcre_exec(re, extra, (char *)bptr, len, start_offset, options, + use_offsets, use_size_offsets); + + if (count == errnumber) + { + /* fprintf(outfile, "Testing %s limit = %d\n", msg, mid); */ + min = mid; + mid = (mid == max - 1)? max : (max > 0)? (min + max)/2 : mid*2; + } + + else if (count >= 0 || count == PCRE_ERROR_NOMATCH || + count == PCRE_ERROR_PARTIAL) + { + if (mid == min + 1) + { + fprintf(outfile, "Minimum %s limit = %d\n", msg, mid); + break; + } + /* fprintf(outfile, "Testing %s limit = %d\n", msg, mid); */ + max = mid; + mid = (min + mid)/2; + } + else break; /* Some other error */ + } + +extra->flags &= ~flag; +return count; +} + + + +/************************************************* +* Check newline indicator * +*************************************************/ + +/* This is used both at compile and run-time to check for escapes, where +xxx is LF, CR, or CRLF. Print a message and return 0 if there is no match. + +Arguments: + p points after the leading '<' + f file for error message + +Returns: appropriate PCRE_NEWLINE_xxx flags, or 0 +*/ + +static int +check_newline(uschar *p, FILE *f) +{ +if (strncmp((char *)p, "cr>", 3) == 0) return PCRE_NEWLINE_CR; +if (strncmp((char *)p, "lf>", 3) == 0) return PCRE_NEWLINE_LF; +if (strncmp((char *)p, "crlf>", 5) == 0) return PCRE_NEWLINE_CRLF; +fprintf(f, "Unknown newline type at: <%s\n", p); +return 0; +} + + + +/************************************************* +* Main Program * +*************************************************/ + +/* Read lines from named file or stdin and write to named file or stdout; lines +consist of a regular expression, in delimiters and optionally followed by +options, followed by a set of test data, terminated by an empty line. */ + +int main(int argc, char **argv) +{ +FILE *infile = stdin; +int options = 0; +int study_options = 0; +int op = 1; +int timeit = 0; +int showinfo = 0; +int showstore = 0; +int quiet = 0; +int size_offsets = 45; +int size_offsets_max; +int *offsets = NULL; +#if !defined NOPOSIX +int posix = 0; +#endif +int debug = 0; +int done = 0; +int all_use_dfa = 0; +int yield = 0; +int stack_size; + +/* These vectors store, end-to-end, a list of captured substring names. Assume +that 1024 is plenty long enough for the few names we'll be testing. */ + +uschar copynames[1024]; +uschar getnames[1024]; + +uschar *copynamesptr; +uschar *getnamesptr; + +/* Get buffers from malloc() so that Electric Fence will check their misuse +when I am debugging. They grow automatically when very long lines are read. */ + +buffer = (unsigned char *)malloc(buffer_size); +dbuffer = (unsigned char *)malloc(buffer_size); +pbuffer = (unsigned char *)malloc(buffer_size); + +/* The outfile variable is static so that new_malloc can use it. The _setmode() +stuff is some magic that I don't understand, but which apparently does good +things in Windows. It's related to line terminations. */ + +#if defined(_WIN32) || defined(WIN32) +_setmode( _fileno( stdout ), 0x8000 ); +#endif /* defined(_WIN32) || defined(WIN32) */ + +outfile = stdout; + +/* Scan options */ + +while (argc > 1 && argv[op][0] == '-') + { + unsigned char *endptr; + + if (strcmp(argv[op], "-s") == 0 || strcmp(argv[op], "-m") == 0) + showstore = 1; + else if (strcmp(argv[op], "-t") == 0) timeit = 1; + else if (strcmp(argv[op], "-q") == 0) quiet = 1; + else if (strcmp(argv[op], "-i") == 0) showinfo = 1; + else if (strcmp(argv[op], "-d") == 0) showinfo = debug = 1; +#if !defined NODFA + else if (strcmp(argv[op], "-dfa") == 0) all_use_dfa = 1; +#endif + else if (strcmp(argv[op], "-o") == 0 && argc > 2 && + ((size_offsets = get_value((unsigned char *)argv[op+1], &endptr)), + *endptr == 0)) + { + op++; + argc--; + } + else if (strcmp(argv[op], "-S") == 0 && argc > 2 && + ((stack_size = get_value((unsigned char *)argv[op+1], &endptr)), + *endptr == 0)) + { +#ifdef _WIN32 + printf("PCRE: -S not supported on this OS\n"); + exit(1); +#else + int rc; + struct rlimit rlim; + getrlimit(RLIMIT_STACK, &rlim); + rlim.rlim_cur = stack_size * 1024 * 1024; + rc = setrlimit(RLIMIT_STACK, &rlim); + if (rc != 0) + { + printf("PCRE: setrlimit() failed with error %d\n", rc); + exit(1); + } + op++; + argc--; +#endif + } +#if !defined NOPOSIX + else if (strcmp(argv[op], "-p") == 0) posix = 1; +#endif + else if (strcmp(argv[op], "-C") == 0) + { + int rc; + printf("PCRE version %s\n", pcre_version()); + printf("Compiled with\n"); + (void)pcre_config(PCRE_CONFIG_UTF8, &rc); + printf(" %sUTF-8 support\n", rc? "" : "No "); + (void)pcre_config(PCRE_CONFIG_UNICODE_PROPERTIES, &rc); + printf(" %sUnicode properties support\n", rc? "" : "No "); + (void)pcre_config(PCRE_CONFIG_NEWLINE, &rc); + printf(" Newline sequence is %s\n", (rc == '\r')? "CR" : + (rc == '\n')? "LF" : "CRLF"); + (void)pcre_config(PCRE_CONFIG_LINK_SIZE, &rc); + printf(" Internal link size = %d\n", rc); + (void)pcre_config(PCRE_CONFIG_POSIX_MALLOC_THRESHOLD, &rc); + printf(" POSIX malloc threshold = %d\n", rc); + (void)pcre_config(PCRE_CONFIG_MATCH_LIMIT, &rc); + printf(" Default match limit = %d\n", rc); + (void)pcre_config(PCRE_CONFIG_MATCH_LIMIT_RECURSION, &rc); + printf(" Default recursion depth limit = %d\n", rc); + (void)pcre_config(PCRE_CONFIG_STACKRECURSE, &rc); + printf(" Match recursion uses %s\n", rc? "stack" : "heap"); + exit(0); + } + else + { + printf("** Unknown or malformed option %s\n", argv[op]); + printf("Usage: pcretest [options] [ []]\n"); + printf(" -C show PCRE compile-time options and exit\n"); + printf(" -d debug: show compiled code; implies -i\n"); +#if !defined NODFA + printf(" -dfa force DFA matching for all subjects\n"); +#endif + printf(" -i show information about compiled pattern\n" + " -m output memory used information\n" + " -o set size of offsets vector to \n"); +#if !defined NOPOSIX + printf(" -p use POSIX interface\n"); +#endif + printf(" -S set stack size to megabytes\n"); + printf(" -s output store (memory) used information\n" + " -t time compilation and execution\n"); + yield = 1; + goto EXIT; + } + op++; + argc--; + } + +/* Get the store for the offsets vector, and remember what it was */ + +size_offsets_max = size_offsets; +offsets = (int *)malloc(size_offsets_max * sizeof(int)); +if (offsets == NULL) + { + printf("** Failed to get %d bytes of memory for offsets vector\n", + size_offsets_max * sizeof(int)); + yield = 1; + goto EXIT; + } + +/* Sort out the input and output files */ + +if (argc > 1) + { + infile = fopen(argv[op], "rb"); + if (infile == NULL) + { + printf("** Failed to open %s\n", argv[op]); + yield = 1; + goto EXIT; + } + } + +if (argc > 2) + { + outfile = fopen(argv[op+1], "wb"); + if (outfile == NULL) + { + printf("** Failed to open %s\n", argv[op+1]); + yield = 1; + goto EXIT; + } + } + +/* Set alternative malloc function */ + +pcre_malloc = new_malloc; +pcre_free = new_free; +pcre_stack_malloc = stack_malloc; +pcre_stack_free = stack_free; + +/* Heading line unless quiet, then prompt for first regex if stdin */ + +if (!quiet) fprintf(outfile, "PCRE version %s\n\n", pcre_version()); + +/* Main loop */ + +while (!done) + { + pcre *re = NULL; + pcre_extra *extra = NULL; + +#if !defined NOPOSIX /* There are still compilers that require no indent */ + regex_t preg; + int do_posix = 0; +#endif + + const char *error; + unsigned char *p, *pp, *ppp; + unsigned char *to_file = NULL; + const unsigned char *tables = NULL; + unsigned long int true_size, true_study_size = 0; + size_t size, regex_gotten_store; + int do_study = 0; + int do_debug = debug; + int do_G = 0; + int do_g = 0; + int do_showinfo = showinfo; + int do_showrest = 0; + int do_flip = 0; + int erroroffset, len, delimiter; + + use_utf8 = 0; + + if (infile == stdin) printf(" re> "); + if (extend_inputline(infile, buffer) == NULL) break; + if (infile != stdin) fprintf(outfile, "%s", (char *)buffer); + fflush(outfile); + + p = buffer; + while (isspace(*p)) p++; + if (*p == 0) continue; + + /* See if the pattern is to be loaded pre-compiled from a file. */ + + if (*p == '<' && strchr((char *)(p+1), '<') == NULL) + { + unsigned long int magic, get_options; + uschar sbuf[8]; + FILE *f; + + p++; + pp = p + (int)strlen((char *)p); + while (isspace(pp[-1])) pp--; + *pp = 0; + + f = fopen((char *)p, "rb"); + if (f == NULL) + { + fprintf(outfile, "Failed to open %s: %s\n", p, strerror(errno)); + continue; + } + + if (fread(sbuf, 1, 8, f) != 8) goto FAIL_READ; + + true_size = + (sbuf[0] << 24) | (sbuf[1] << 16) | (sbuf[2] << 8) | sbuf[3]; + true_study_size = + (sbuf[4] << 24) | (sbuf[5] << 16) | (sbuf[6] << 8) | sbuf[7]; + + re = (real_pcre *)new_malloc(true_size); + regex_gotten_store = gotten_store; + + if (fread(re, 1, true_size, f) != true_size) goto FAIL_READ; + + magic = ((real_pcre *)re)->magic_number; + if (magic != MAGIC_NUMBER) + { + if (byteflip(magic, sizeof(magic)) == MAGIC_NUMBER) + { + do_flip = 1; + } + else + { + fprintf(outfile, "Data in %s is not a compiled PCRE regex\n", p); + fclose(f); + continue; + } + } + + fprintf(outfile, "Compiled regex%s loaded from %s\n", + do_flip? " (byte-inverted)" : "", p); + + /* Need to know if UTF-8 for printing data strings */ + + new_info(re, NULL, PCRE_INFO_OPTIONS, &get_options); + use_utf8 = (get_options & PCRE_UTF8) != 0; + + /* Now see if there is any following study data */ + + if (true_study_size != 0) + { + pcre_study_data *psd; + + extra = (pcre_extra *)new_malloc(sizeof(pcre_extra) + true_study_size); + extra->flags = PCRE_EXTRA_STUDY_DATA; + + psd = (pcre_study_data *)(((char *)extra) + sizeof(pcre_extra)); + extra->study_data = psd; + + if (fread(psd, 1, true_study_size, f) != true_study_size) + { + FAIL_READ: + fprintf(outfile, "Failed to read data from %s\n", p); + if (extra != NULL) new_free(extra); + if (re != NULL) new_free(re); + fclose(f); + continue; + } + fprintf(outfile, "Study data loaded from %s\n", p); + do_study = 1; /* To get the data output if requested */ + } + else fprintf(outfile, "No study data\n"); + + fclose(f); + goto SHOW_INFO; + } + + /* In-line pattern (the usual case). Get the delimiter and seek the end of + the pattern; if is isn't complete, read more. */ + + delimiter = *p++; + + if (isalnum(delimiter) || delimiter == '\\') + { + fprintf(outfile, "** Delimiter must not be alphameric or \\\n"); + goto SKIP_DATA; + } + + pp = p; + + for(;;) + { + while (*pp != 0) + { + if (*pp == '\\' && pp[1] != 0) pp++; + else if (*pp == delimiter) break; + pp++; + } + if (*pp != 0) break; + if (infile == stdin) printf(" > "); + if ((pp = extend_inputline(infile, pp)) == NULL) + { + fprintf(outfile, "** Unexpected EOF\n"); + done = 1; + goto CONTINUE; + } + if (infile != stdin) fprintf(outfile, "%s", (char *)pp); + } + + /* If the first character after the delimiter is backslash, make + the pattern end with backslash. This is purely to provide a way + of testing for the error message when a pattern ends with backslash. */ + + if (pp[1] == '\\') *pp++ = '\\'; + + /* Terminate the pattern at the delimiter, and save a copy of the pattern + for callouts. */ + + *pp++ = 0; + strcpy((char *)pbuffer, (char *)p); + + /* Look for options after final delimiter */ + + options = 0; + study_options = 0; + log_store = showstore; /* default from command line */ + + while (*pp != 0) + { + switch (*pp++) + { + case 'f': options |= PCRE_FIRSTLINE; break; + case 'g': do_g = 1; break; + case 'i': options |= PCRE_CASELESS; break; + case 'm': options |= PCRE_MULTILINE; break; + case 's': options |= PCRE_DOTALL; break; + case 'x': options |= PCRE_EXTENDED; break; + + case '+': do_showrest = 1; break; + case 'A': options |= PCRE_ANCHORED; break; + case 'C': options |= PCRE_AUTO_CALLOUT; break; + case 'D': do_debug = do_showinfo = 1; break; + case 'E': options |= PCRE_DOLLAR_ENDONLY; break; + case 'F': do_flip = 1; break; + case 'G': do_G = 1; break; + case 'I': do_showinfo = 1; break; + case 'J': options |= PCRE_DUPNAMES; break; + case 'M': log_store = 1; break; + case 'N': options |= PCRE_NO_AUTO_CAPTURE; break; + +#if !defined NOPOSIX + case 'P': do_posix = 1; break; +#endif + + case 'S': do_study = 1; break; + case 'U': options |= PCRE_UNGREEDY; break; + case 'X': options |= PCRE_EXTRA; break; + case '8': options |= PCRE_UTF8; use_utf8 = 1; break; + case '?': options |= PCRE_NO_UTF8_CHECK; break; + + case 'L': + ppp = pp; + /* The '\r' test here is so that it works on Windows */ + while (*ppp != '\n' && *ppp != '\r' && *ppp != ' ') ppp++; + *ppp = 0; + if (setlocale(LC_CTYPE, (const char *)pp) == NULL) + { + fprintf(outfile, "** Failed to set locale \"%s\"\n", pp); + goto SKIP_DATA; + } + tables = pcre_maketables(); + pp = ppp; + break; + + case '>': + to_file = pp; + while (*pp != 0) pp++; + while (isspace(pp[-1])) pp--; + *pp = 0; + break; + + case '<': + { + int x = check_newline(pp, outfile); + if (x == 0) goto SKIP_DATA; + options |= x; + while (*pp++ != '>'); + } + break; + + case '\r': /* So that it works in Windows */ + case '\n': + case ' ': + break; + + default: + fprintf(outfile, "** Unknown option '%c'\n", pp[-1]); + goto SKIP_DATA; + } + } + + /* Handle compiling via the POSIX interface, which doesn't support the + timing, showing, or debugging options, nor the ability to pass over + local character tables. */ + +#if !defined NOPOSIX + if (posix || do_posix) + { + int rc; + int cflags = 0; + + if ((options & PCRE_CASELESS) != 0) cflags |= REG_ICASE; + if ((options & PCRE_MULTILINE) != 0) cflags |= REG_NEWLINE; + if ((options & PCRE_DOTALL) != 0) cflags |= REG_DOTALL; + if ((options & PCRE_NO_AUTO_CAPTURE) != 0) cflags |= REG_NOSUB; + if ((options & PCRE_UTF8) != 0) cflags |= REG_UTF8; + + rc = regcomp(&preg, (char *)p, cflags); + + /* Compilation failed; go back for another re, skipping to blank line + if non-interactive. */ + + if (rc != 0) + { + (void)regerror(rc, &preg, (char *)buffer, buffer_size); + fprintf(outfile, "Failed: POSIX code %d: %s\n", rc, buffer); + goto SKIP_DATA; + } + } + + /* Handle compiling via the native interface */ + + else +#endif /* !defined NOPOSIX */ + + { + if (timeit) + { + register int i; + clock_t time_taken; + clock_t start_time = clock(); + for (i = 0; i < LOOPREPEAT; i++) + { + re = pcre_compile((char *)p, options, &error, &erroroffset, tables); + if (re != NULL) free(re); + } + time_taken = clock() - start_time; + fprintf(outfile, "Compile time %.3f milliseconds\n", + (((double)time_taken * 1000.0) / (double)LOOPREPEAT) / + (double)CLOCKS_PER_SEC); + } + + re = pcre_compile((char *)p, options, &error, &erroroffset, tables); + + /* Compilation failed; go back for another re, skipping to blank line + if non-interactive. */ + + if (re == NULL) + { + fprintf(outfile, "Failed: %s at offset %d\n", error, erroroffset); + SKIP_DATA: + if (infile != stdin) + { + for (;;) + { + if (extend_inputline(infile, buffer) == NULL) + { + done = 1; + goto CONTINUE; + } + len = (int)strlen((char *)buffer); + while (len > 0 && isspace(buffer[len-1])) len--; + if (len == 0) break; + } + fprintf(outfile, "\n"); + } + goto CONTINUE; + } + + /* Compilation succeeded; print data if required. There are now two + info-returning functions. The old one has a limited interface and + returns only limited data. Check that it agrees with the newer one. */ + + if (log_store) + fprintf(outfile, "Memory allocation (code space): %d\n", + (int)(gotten_store - + sizeof(real_pcre) - + ((real_pcre *)re)->name_count * ((real_pcre *)re)->name_entry_size)); + + /* Extract the size for possible writing before possibly flipping it, + and remember the store that was got. */ + + true_size = ((real_pcre *)re)->size; + regex_gotten_store = gotten_store; + + /* If /S was present, study the regexp to generate additional info to + help with the matching. */ + + if (do_study) + { + if (timeit) + { + register int i; + clock_t time_taken; + clock_t start_time = clock(); + for (i = 0; i < LOOPREPEAT; i++) + extra = pcre_study(re, study_options, &error); + time_taken = clock() - start_time; + if (extra != NULL) free(extra); + fprintf(outfile, " Study time %.3f milliseconds\n", + (((double)time_taken * 1000.0) / (double)LOOPREPEAT) / + (double)CLOCKS_PER_SEC); + } + extra = pcre_study(re, study_options, &error); + if (error != NULL) + fprintf(outfile, "Failed to study: %s\n", error); + else if (extra != NULL) + true_study_size = ((pcre_study_data *)(extra->study_data))->size; + } + + /* If the 'F' option was present, we flip the bytes of all the integer + fields in the regex data block and the study block. This is to make it + possible to test PCRE's handling of byte-flipped patterns, e.g. those + compiled on a different architecture. */ + + if (do_flip) + { + real_pcre *rre = (real_pcre *)re; + rre->magic_number = byteflip(rre->magic_number, sizeof(rre->magic_number)); + rre->size = byteflip(rre->size, sizeof(rre->size)); + rre->options = byteflip(rre->options, sizeof(rre->options)); + rre->top_bracket = byteflip(rre->top_bracket, sizeof(rre->top_bracket)); + rre->top_backref = byteflip(rre->top_backref, sizeof(rre->top_backref)); + rre->first_byte = byteflip(rre->first_byte, sizeof(rre->first_byte)); + rre->req_byte = byteflip(rre->req_byte, sizeof(rre->req_byte)); + rre->name_table_offset = byteflip(rre->name_table_offset, + sizeof(rre->name_table_offset)); + rre->name_entry_size = byteflip(rre->name_entry_size, + sizeof(rre->name_entry_size)); + rre->name_count = byteflip(rre->name_count, sizeof(rre->name_count)); + + if (extra != NULL) + { + pcre_study_data *rsd = (pcre_study_data *)(extra->study_data); + rsd->size = byteflip(rsd->size, sizeof(rsd->size)); + rsd->options = byteflip(rsd->options, sizeof(rsd->options)); + } + } + + /* Extract information from the compiled data if required */ + + SHOW_INFO: + + if (do_showinfo) + { + unsigned long int get_options, all_options; +#if !defined NOINFOCHECK + int old_first_char, old_options, old_count; +#endif + int count, backrefmax, first_char, need_char; + int nameentrysize, namecount; + const uschar *nametable; + + if (do_debug) + { + fprintf(outfile, "------------------------------------------------------------------\n"); + pcre_printint(re, outfile); + } + + new_info(re, NULL, PCRE_INFO_OPTIONS, &get_options); + new_info(re, NULL, PCRE_INFO_SIZE, &size); + new_info(re, NULL, PCRE_INFO_CAPTURECOUNT, &count); + new_info(re, NULL, PCRE_INFO_BACKREFMAX, &backrefmax); + new_info(re, NULL, PCRE_INFO_FIRSTBYTE, &first_char); + new_info(re, NULL, PCRE_INFO_LASTLITERAL, &need_char); + new_info(re, NULL, PCRE_INFO_NAMEENTRYSIZE, &nameentrysize); + new_info(re, NULL, PCRE_INFO_NAMECOUNT, &namecount); + new_info(re, NULL, PCRE_INFO_NAMETABLE, (void *)&nametable); + +#if !defined NOINFOCHECK + old_count = pcre_info(re, &old_options, &old_first_char); + if (count < 0) fprintf(outfile, + "Error %d from pcre_info()\n", count); + else + { + if (old_count != count) fprintf(outfile, + "Count disagreement: pcre_fullinfo=%d pcre_info=%d\n", count, + old_count); + + if (old_first_char != first_char) fprintf(outfile, + "First char disagreement: pcre_fullinfo=%d pcre_info=%d\n", + first_char, old_first_char); + + if (old_options != (int)get_options) fprintf(outfile, + "Options disagreement: pcre_fullinfo=%ld pcre_info=%d\n", + get_options, old_options); + } +#endif + + if (size != regex_gotten_store) fprintf(outfile, + "Size disagreement: pcre_fullinfo=%d call to malloc for %d\n", + (int)size, (int)regex_gotten_store); + + fprintf(outfile, "Capturing subpattern count = %d\n", count); + if (backrefmax > 0) + fprintf(outfile, "Max back reference = %d\n", backrefmax); + + if (namecount > 0) + { + fprintf(outfile, "Named capturing subpatterns:\n"); + while (namecount-- > 0) + { + fprintf(outfile, " %s %*s%3d\n", nametable + 2, + nameentrysize - 3 - (int)strlen((char *)nametable + 2), "", + GET2(nametable, 0)); + nametable += nameentrysize; + } + } + + /* The NOPARTIAL bit is a private bit in the options, so we have + to fish it out via out back door */ + + all_options = ((real_pcre *)re)->options; + if (do_flip) + { + all_options = byteflip(all_options, sizeof(all_options)); + } + + if ((all_options & PCRE_NOPARTIAL) != 0) + fprintf(outfile, "Partial matching not supported\n"); + + if (get_options == 0) fprintf(outfile, "No options\n"); + else fprintf(outfile, "Options:%s%s%s%s%s%s%s%s%s%s%s%s%s\n", + ((get_options & PCRE_ANCHORED) != 0)? " anchored" : "", + ((get_options & PCRE_CASELESS) != 0)? " caseless" : "", + ((get_options & PCRE_EXTENDED) != 0)? " extended" : "", + ((get_options & PCRE_MULTILINE) != 0)? " multiline" : "", + ((get_options & PCRE_FIRSTLINE) != 0)? " firstline" : "", + ((get_options & PCRE_DOTALL) != 0)? " dotall" : "", + ((get_options & PCRE_DOLLAR_ENDONLY) != 0)? " dollar_endonly" : "", + ((get_options & PCRE_EXTRA) != 0)? " extra" : "", + ((get_options & PCRE_UNGREEDY) != 0)? " ungreedy" : "", + ((get_options & PCRE_NO_AUTO_CAPTURE) != 0)? " no_auto_capture" : "", + ((get_options & PCRE_UTF8) != 0)? " utf8" : "", + ((get_options & PCRE_NO_UTF8_CHECK) != 0)? " no_utf8_check" : "", + ((get_options & PCRE_DUPNAMES) != 0)? " dupnames" : ""); + + switch (get_options & PCRE_NEWLINE_CRLF) + { + case PCRE_NEWLINE_CR: + fprintf(outfile, "Forced newline sequence: CR\n"); + break; + + case PCRE_NEWLINE_LF: + fprintf(outfile, "Forced newline sequence: LF\n"); + break; + + case PCRE_NEWLINE_CRLF: + fprintf(outfile, "Forced newline sequence: CRLF\n"); + break; + + default: + break; + } + + if (first_char == -1) + { + fprintf(outfile, "First char at start or follows newline\n"); + } + else if (first_char < 0) + { + fprintf(outfile, "No first char\n"); + } + else + { + int ch = first_char & 255; + const char *caseless = ((first_char & REQ_CASELESS) == 0)? + "" : " (caseless)"; + if (isprint(ch)) + fprintf(outfile, "First char = \'%c\'%s\n", ch, caseless); + else + fprintf(outfile, "First char = %d%s\n", ch, caseless); + } + + if (need_char < 0) + { + fprintf(outfile, "No need char\n"); + } + else + { + int ch = need_char & 255; + const char *caseless = ((need_char & REQ_CASELESS) == 0)? + "" : " (caseless)"; + if (isprint(ch)) + fprintf(outfile, "Need char = \'%c\'%s\n", ch, caseless); + else + fprintf(outfile, "Need char = %d%s\n", ch, caseless); + } + + /* Don't output study size; at present it is in any case a fixed + value, but it varies, depending on the computer architecture, and + so messes up the test suite. (And with the /F option, it might be + flipped.) */ + + if (do_study) + { + if (extra == NULL) + fprintf(outfile, "Study returned NULL\n"); + else + { + uschar *start_bits = NULL; + new_info(re, extra, PCRE_INFO_FIRSTTABLE, &start_bits); + + if (start_bits == NULL) + fprintf(outfile, "No starting byte set\n"); + else + { + int i; + int c = 24; + fprintf(outfile, "Starting byte set: "); + for (i = 0; i < 256; i++) + { + if ((start_bits[i/8] & (1<<(i&7))) != 0) + { + if (c > 75) + { + fprintf(outfile, "\n "); + c = 2; + } + if (isprint(i) && i != ' ') + { + fprintf(outfile, "%c ", i); + c += 2; + } + else + { + fprintf(outfile, "\\x%02x ", i); + c += 5; + } + } + } + fprintf(outfile, "\n"); + } + } + } + } + + /* If the '>' option was present, we write out the regex to a file, and + that is all. The first 8 bytes of the file are the regex length and then + the study length, in big-endian order. */ + + if (to_file != NULL) + { + FILE *f = fopen((char *)to_file, "wb"); + if (f == NULL) + { + fprintf(outfile, "Unable to open %s: %s\n", to_file, strerror(errno)); + } + else + { + uschar sbuf[8]; + sbuf[0] = (true_size >> 24) & 255; + sbuf[1] = (true_size >> 16) & 255; + sbuf[2] = (true_size >> 8) & 255; + sbuf[3] = (true_size) & 255; + + sbuf[4] = (true_study_size >> 24) & 255; + sbuf[5] = (true_study_size >> 16) & 255; + sbuf[6] = (true_study_size >> 8) & 255; + sbuf[7] = (true_study_size) & 255; + + if (fwrite(sbuf, 1, 8, f) < 8 || + fwrite(re, 1, true_size, f) < true_size) + { + fprintf(outfile, "Write error on %s: %s\n", to_file, strerror(errno)); + } + else + { + fprintf(outfile, "Compiled regex written to %s\n", to_file); + if (extra != NULL) + { + if (fwrite(extra->study_data, 1, true_study_size, f) < + true_study_size) + { + fprintf(outfile, "Write error on %s: %s\n", to_file, + strerror(errno)); + } + else fprintf(outfile, "Study data written to %s\n", to_file); + } + } + fclose(f); + } + + new_free(re); + if (extra != NULL) new_free(extra); + if (tables != NULL) new_free((void *)tables); + continue; /* With next regex */ + } + } /* End of non-POSIX compile */ + + /* Read data lines and test them */ + + for (;;) + { + uschar *q; + uschar *bptr = dbuffer; + int *use_offsets = offsets; + int use_size_offsets = size_offsets; + int callout_data = 0; + int callout_data_set = 0; + int count, c; + int copystrings = 0; + int find_match_limit = 0; + int getstrings = 0; + int getlist = 0; + int gmatched = 0; + int start_offset = 0; + int g_notempty = 0; + int use_dfa = 0; + + options = 0; + + *copynames = 0; + *getnames = 0; + + copynamesptr = copynames; + getnamesptr = getnames; + + pcre_callout = callout; + first_callout = 1; + callout_extra = 0; + callout_count = 0; + callout_fail_count = 999999; + callout_fail_id = -1; + show_malloc = 0; + + if (extra != NULL) extra->flags &= + ~(PCRE_EXTRA_MATCH_LIMIT|PCRE_EXTRA_MATCH_LIMIT_RECURSION); + + len = 0; + for (;;) + { + if (infile == stdin) printf("data> "); + if (extend_inputline(infile, buffer + len) == NULL) + { + if (len > 0) break; + done = 1; + goto CONTINUE; + } + if (infile != stdin) fprintf(outfile, "%s", (char *)buffer); + len = (int)strlen((char *)buffer); + if (buffer[len-1] == '\n') break; + } + + while (len > 0 && isspace(buffer[len-1])) len--; + buffer[len] = 0; + if (len == 0) break; + + p = buffer; + while (isspace(*p)) p++; + + q = dbuffer; + while ((c = *p++) != 0) + { + int i = 0; + int n = 0; + + if (c == '\\') switch ((c = *p++)) + { + case 'a': c = 7; break; + case 'b': c = '\b'; break; + case 'e': c = 27; break; + case 'f': c = '\f'; break; + case 'n': c = '\n'; break; + case 'r': c = '\r'; break; + case 't': c = '\t'; break; + case 'v': c = '\v'; break; + + case '0': case '1': case '2': case '3': + case '4': case '5': case '6': case '7': + c -= '0'; + while (i++ < 2 && isdigit(*p) && *p != '8' && *p != '9') + c = c * 8 + *p++ - '0'; + +#if !defined NOUTF8 + if (use_utf8 && c > 255) + { + unsigned char buff8[8]; + int ii, utn; + utn = ord2utf8(c, buff8); + for (ii = 0; ii < utn - 1; ii++) *q++ = buff8[ii]; + c = buff8[ii]; /* Last byte */ + } +#endif + break; + + case 'x': + + /* Handle \x{..} specially - new Perl thing for utf8 */ + +#if !defined NOUTF8 + if (*p == '{') + { + unsigned char *pt = p; + c = 0; + while (isxdigit(*(++pt))) + c = c * 16 + tolower(*pt) - ((isdigit(*pt))? '0' : 'W'); + if (*pt == '}') + { + unsigned char buff8[8]; + int ii, utn; + utn = ord2utf8(c, buff8); + for (ii = 0; ii < utn - 1; ii++) *q++ = buff8[ii]; + c = buff8[ii]; /* Last byte */ + p = pt + 1; + break; + } + /* Not correct form; fall through */ + } +#endif + + /* Ordinary \x */ + + c = 0; + while (i++ < 2 && isxdigit(*p)) + { + c = c * 16 + tolower(*p) - ((isdigit(*p))? '0' : 'W'); + p++; + } + break; + + case 0: /* \ followed by EOF allows for an empty line */ + p--; + continue; + + case '>': + while(isdigit(*p)) start_offset = start_offset * 10 + *p++ - '0'; + continue; + + case 'A': /* Option setting */ + options |= PCRE_ANCHORED; + continue; + + case 'B': + options |= PCRE_NOTBOL; + continue; + + case 'C': + if (isdigit(*p)) /* Set copy string */ + { + while(isdigit(*p)) n = n * 10 + *p++ - '0'; + copystrings |= 1 << n; + } + else if (isalnum(*p)) + { + uschar *npp = copynamesptr; + while (isalnum(*p)) *npp++ = *p++; + *npp++ = 0; + *npp = 0; + n = pcre_get_stringnumber(re, (char *)copynamesptr); + if (n < 0) + fprintf(outfile, "no parentheses with name \"%s\"\n", copynamesptr); + copynamesptr = npp; + } + else if (*p == '+') + { + callout_extra = 1; + p++; + } + else if (*p == '-') + { + pcre_callout = NULL; + p++; + } + else if (*p == '!') + { + callout_fail_id = 0; + p++; + while(isdigit(*p)) + callout_fail_id = callout_fail_id * 10 + *p++ - '0'; + callout_fail_count = 0; + if (*p == '!') + { + p++; + while(isdigit(*p)) + callout_fail_count = callout_fail_count * 10 + *p++ - '0'; + } + } + else if (*p == '*') + { + int sign = 1; + callout_data = 0; + if (*(++p) == '-') { sign = -1; p++; } + while(isdigit(*p)) + callout_data = callout_data * 10 + *p++ - '0'; + callout_data *= sign; + callout_data_set = 1; + } + continue; + +#if !defined NODFA + case 'D': +#if !defined NOPOSIX + if (posix || do_posix) + printf("** Can't use dfa matching in POSIX mode: \\D ignored\n"); + else +#endif + use_dfa = 1; + continue; + + case 'F': + options |= PCRE_DFA_SHORTEST; + continue; +#endif + + case 'G': + if (isdigit(*p)) + { + while(isdigit(*p)) n = n * 10 + *p++ - '0'; + getstrings |= 1 << n; + } + else if (isalnum(*p)) + { + uschar *npp = getnamesptr; + while (isalnum(*p)) *npp++ = *p++; + *npp++ = 0; + *npp = 0; + n = pcre_get_stringnumber(re, (char *)getnamesptr); + if (n < 0) + fprintf(outfile, "no parentheses with name \"%s\"\n", getnamesptr); + getnamesptr = npp; + } + continue; + + case 'L': + getlist = 1; + continue; + + case 'M': + find_match_limit = 1; + continue; + + case 'N': + options |= PCRE_NOTEMPTY; + continue; + + case 'O': + while(isdigit(*p)) n = n * 10 + *p++ - '0'; + if (n > size_offsets_max) + { + size_offsets_max = n; + free(offsets); + use_offsets = offsets = (int *)malloc(size_offsets_max * sizeof(int)); + if (offsets == NULL) + { + printf("** Failed to get %d bytes of memory for offsets vector\n", + size_offsets_max * sizeof(int)); + yield = 1; + goto EXIT; + } + } + use_size_offsets = n; + if (n == 0) use_offsets = NULL; /* Ensures it can't write to it */ + continue; + + case 'P': + options |= PCRE_PARTIAL; + continue; + + case 'Q': + while(isdigit(*p)) n = n * 10 + *p++ - '0'; + if (extra == NULL) + { + extra = (pcre_extra *)malloc(sizeof(pcre_extra)); + extra->flags = 0; + } + extra->flags |= PCRE_EXTRA_MATCH_LIMIT_RECURSION; + extra->match_limit_recursion = n; + continue; + + case 'q': + while(isdigit(*p)) n = n * 10 + *p++ - '0'; + if (extra == NULL) + { + extra = (pcre_extra *)malloc(sizeof(pcre_extra)); + extra->flags = 0; + } + extra->flags |= PCRE_EXTRA_MATCH_LIMIT; + extra->match_limit = n; + continue; + +#if !defined NODFA + case 'R': + options |= PCRE_DFA_RESTART; + continue; +#endif + + case 'S': + show_malloc = 1; + continue; + + case 'Z': + options |= PCRE_NOTEOL; + continue; + + case '?': + options |= PCRE_NO_UTF8_CHECK; + continue; + + case '<': + { + int x = check_newline(p, outfile); + if (x == 0) goto NEXT_DATA; + options |= x; + while (*p++ != '>'); + } + continue; + } + *q++ = c; + } + *q = 0; + len = q - dbuffer; + + if ((all_use_dfa || use_dfa) && find_match_limit) + { + printf("**Match limit not relevant for DFA matching: ignored\n"); + find_match_limit = 0; + } + + /* Handle matching via the POSIX interface, which does not + support timing or playing with the match limit or callout data. */ + +#if !defined NOPOSIX + if (posix || do_posix) + { + int rc; + int eflags = 0; + regmatch_t *pmatch = NULL; + if (use_size_offsets > 0) + pmatch = (regmatch_t *)malloc(sizeof(regmatch_t) * use_size_offsets); + if ((options & PCRE_NOTBOL) != 0) eflags |= REG_NOTBOL; + if ((options & PCRE_NOTEOL) != 0) eflags |= REG_NOTEOL; + + rc = regexec(&preg, (const char *)bptr, use_size_offsets, pmatch, eflags); + + if (rc != 0) + { + (void)regerror(rc, &preg, (char *)buffer, buffer_size); + fprintf(outfile, "No match: POSIX code %d: %s\n", rc, buffer); + } + else if ((((const pcre *)preg.re_pcre)->options & PCRE_NO_AUTO_CAPTURE) + != 0) + { + fprintf(outfile, "Matched with REG_NOSUB\n"); + } + else + { + size_t i; + for (i = 0; i < (size_t)use_size_offsets; i++) + { + if (pmatch[i].rm_so >= 0) + { + fprintf(outfile, "%2d: ", (int)i); + (void)pchars(dbuffer + pmatch[i].rm_so, + pmatch[i].rm_eo - pmatch[i].rm_so, outfile); + fprintf(outfile, "\n"); + if (i == 0 && do_showrest) + { + fprintf(outfile, " 0+ "); + (void)pchars(dbuffer + pmatch[i].rm_eo, len - pmatch[i].rm_eo, + outfile); + fprintf(outfile, "\n"); + } + } + } + } + free(pmatch); + } + + /* Handle matching via the native interface - repeats for /g and /G */ + + else +#endif /* !defined NOPOSIX */ + + for (;; gmatched++) /* Loop for /g or /G */ + { + if (timeit) + { + register int i; + clock_t time_taken; + clock_t start_time = clock(); + +#if !defined NODFA + if (all_use_dfa || use_dfa) + { + int workspace[1000]; + for (i = 0; i < LOOPREPEAT; i++) + count = pcre_dfa_exec(re, NULL, (char *)bptr, len, start_offset, + options | g_notempty, use_offsets, use_size_offsets, workspace, + sizeof(workspace)/sizeof(int)); + } + else +#endif + + for (i = 0; i < LOOPREPEAT; i++) + count = pcre_exec(re, extra, (char *)bptr, len, + start_offset, options | g_notempty, use_offsets, use_size_offsets); + + time_taken = clock() - start_time; + fprintf(outfile, "Execute time %.3f milliseconds\n", + (((double)time_taken * 1000.0) / (double)LOOPREPEAT) / + (double)CLOCKS_PER_SEC); + } + + /* If find_match_limit is set, we want to do repeated matches with + varying limits in order to find the minimum value for the match limit and + for the recursion limit. */ + + if (find_match_limit) + { + if (extra == NULL) + { + extra = (pcre_extra *)malloc(sizeof(pcre_extra)); + extra->flags = 0; + } + + (void)check_match_limit(re, extra, bptr, len, start_offset, + options|g_notempty, use_offsets, use_size_offsets, + PCRE_EXTRA_MATCH_LIMIT, &(extra->match_limit), + PCRE_ERROR_MATCHLIMIT, "match()"); + + count = check_match_limit(re, extra, bptr, len, start_offset, + options|g_notempty, use_offsets, use_size_offsets, + PCRE_EXTRA_MATCH_LIMIT_RECURSION, &(extra->match_limit_recursion), + PCRE_ERROR_RECURSIONLIMIT, "match() recursion"); + } + + /* If callout_data is set, use the interface with additional data */ + + else if (callout_data_set) + { + if (extra == NULL) + { + extra = (pcre_extra *)malloc(sizeof(pcre_extra)); + extra->flags = 0; + } + extra->flags |= PCRE_EXTRA_CALLOUT_DATA; + extra->callout_data = &callout_data; + count = pcre_exec(re, extra, (char *)bptr, len, start_offset, + options | g_notempty, use_offsets, use_size_offsets); + extra->flags &= ~PCRE_EXTRA_CALLOUT_DATA; + } + + /* The normal case is just to do the match once, with the default + value of match_limit. */ + +#if !defined NODFA + else if (all_use_dfa || use_dfa) + { + int workspace[1000]; + count = pcre_dfa_exec(re, NULL, (char *)bptr, len, start_offset, + options | g_notempty, use_offsets, use_size_offsets, workspace, + sizeof(workspace)/sizeof(int)); + if (count == 0) + { + fprintf(outfile, "Matched, but too many subsidiary matches\n"); + count = use_size_offsets/2; + } + } +#endif + + else + { + count = pcre_exec(re, extra, (char *)bptr, len, + start_offset, options | g_notempty, use_offsets, use_size_offsets); + if (count == 0) + { + fprintf(outfile, "Matched, but too many substrings\n"); + count = use_size_offsets/3; + } + } + + /* Matched */ + + if (count >= 0) + { + int i; + for (i = 0; i < count * 2; i += 2) + { + if (use_offsets[i] < 0) + fprintf(outfile, "%2d: \n", i/2); + else + { + fprintf(outfile, "%2d: ", i/2); + (void)pchars(bptr + use_offsets[i], + use_offsets[i+1] - use_offsets[i], outfile); + fprintf(outfile, "\n"); + if (i == 0) + { + if (do_showrest) + { + fprintf(outfile, " 0+ "); + (void)pchars(bptr + use_offsets[i+1], len - use_offsets[i+1], + outfile); + fprintf(outfile, "\n"); + } + } + } + } + + for (i = 0; i < 32; i++) + { + if ((copystrings & (1 << i)) != 0) + { + char copybuffer[256]; + int rc = pcre_copy_substring((char *)bptr, use_offsets, count, + i, copybuffer, sizeof(copybuffer)); + if (rc < 0) + fprintf(outfile, "copy substring %d failed %d\n", i, rc); + else + fprintf(outfile, "%2dC %s (%d)\n", i, copybuffer, rc); + } + } + + for (copynamesptr = copynames; + *copynamesptr != 0; + copynamesptr += (int)strlen((char*)copynamesptr) + 1) + { + char copybuffer[256]; + int rc = pcre_copy_named_substring(re, (char *)bptr, use_offsets, + count, (char *)copynamesptr, copybuffer, sizeof(copybuffer)); + if (rc < 0) + fprintf(outfile, "copy substring %s failed %d\n", copynamesptr, rc); + else + fprintf(outfile, " C %s (%d) %s\n", copybuffer, rc, copynamesptr); + } + + for (i = 0; i < 32; i++) + { + if ((getstrings & (1 << i)) != 0) + { + const char *substring; + int rc = pcre_get_substring((char *)bptr, use_offsets, count, + i, &substring); + if (rc < 0) + fprintf(outfile, "get substring %d failed %d\n", i, rc); + else + { + fprintf(outfile, "%2dG %s (%d)\n", i, substring, rc); + pcre_free_substring(substring); + } + } + } + + for (getnamesptr = getnames; + *getnamesptr != 0; + getnamesptr += (int)strlen((char*)getnamesptr) + 1) + { + const char *substring; + int rc = pcre_get_named_substring(re, (char *)bptr, use_offsets, + count, (char *)getnamesptr, &substring); + if (rc < 0) + fprintf(outfile, "copy substring %s failed %d\n", getnamesptr, rc); + else + { + fprintf(outfile, " G %s (%d) %s\n", substring, rc, getnamesptr); + pcre_free_substring(substring); + } + } + + if (getlist) + { + const char **stringlist; + int rc = pcre_get_substring_list((char *)bptr, use_offsets, count, + &stringlist); + if (rc < 0) + fprintf(outfile, "get substring list failed %d\n", rc); + else + { + for (i = 0; i < count; i++) + fprintf(outfile, "%2dL %s\n", i, stringlist[i]); + if (stringlist[i] != NULL) + fprintf(outfile, "string list not terminated by NULL\n"); + /* free((void *)stringlist); */ + pcre_free_substring_list(stringlist); + } + } + } + + /* There was a partial match */ + + else if (count == PCRE_ERROR_PARTIAL) + { + fprintf(outfile, "Partial match"); +#if !defined NODFA + if ((all_use_dfa || use_dfa) && use_size_offsets > 2) + fprintf(outfile, ": %.*s", use_offsets[1] - use_offsets[0], + bptr + use_offsets[0]); +#endif + fprintf(outfile, "\n"); + break; /* Out of the /g loop */ + } + + /* Failed to match. If this is a /g or /G loop and we previously set + g_notempty after a null match, this is not necessarily the end. + We want to advance the start offset, and continue. In the case of UTF-8 + matching, the advance must be one character, not one byte. Fudge the + offset values to achieve this. We won't be at the end of the string - + that was checked before setting g_notempty. */ + + else + { + if (g_notempty != 0) + { + int onechar = 1; + use_offsets[0] = start_offset; + if (use_utf8) + { + while (start_offset + onechar < len) + { + int tb = bptr[start_offset+onechar]; + if (tb <= 127) break; + tb &= 0xc0; + if (tb != 0 && tb != 0xc0) onechar++; + } + } + use_offsets[1] = start_offset + onechar; + } + else + { + if (count == PCRE_ERROR_NOMATCH) + { + if (gmatched == 0) fprintf(outfile, "No match\n"); + } + else fprintf(outfile, "Error %d\n", count); + break; /* Out of the /g loop */ + } + } + + /* If not /g or /G we are done */ + + if (!do_g && !do_G) break; + + /* If we have matched an empty string, first check to see if we are at + the end of the subject. If so, the /g loop is over. Otherwise, mimic + what Perl's /g options does. This turns out to be rather cunning. First + we set PCRE_NOTEMPTY and PCRE_ANCHORED and try the match again at the + same point. If this fails (picked up above) we advance to the next + character. */ + + g_notempty = 0; + if (use_offsets[0] == use_offsets[1]) + { + if (use_offsets[0] == len) break; + g_notempty = PCRE_NOTEMPTY | PCRE_ANCHORED; + } + + /* For /g, update the start offset, leaving the rest alone */ + + if (do_g) start_offset = use_offsets[1]; + + /* For /G, update the pointer and length */ + + else + { + bptr += use_offsets[1]; + len -= use_offsets[1]; + } + } /* End of loop for /g and /G */ + + NEXT_DATA: continue; + } /* End of loop for data lines */ + + CONTINUE: + +#if !defined NOPOSIX + if (posix || do_posix) regfree(&preg); +#endif + + if (re != NULL) new_free(re); + if (extra != NULL) new_free(extra); + if (tables != NULL) + { + new_free((void *)tables); + setlocale(LC_CTYPE, "C"); + } + } + +if (infile == stdin) fprintf(outfile, "\n"); + +EXIT: + +if (infile != NULL && infile != stdin) fclose(infile); +if (outfile != NULL && outfile != stdout) fclose(outfile); + +free(buffer); +free(dbuffer); +free(pbuffer); +free(offsets); + +return yield; +} + +/* End of pcretest.c */ diff --git a/libs/pcre/perltest b/libs/pcre/perltest new file mode 100755 index 0000000000..9f511656a5 --- /dev/null +++ b/libs/pcre/perltest @@ -0,0 +1,191 @@ +#! /usr/bin/perl + +# Program for testing regular expressions with perl to check that PCRE handles +# them the same. This is the version that supports /8 for UTF-8 testing. As it +# stands, it requires at least Perl 5.8 for UTF-8 support. However, it needs to +# have "use utf8" at the start for running the UTF-8 tests, but *not* for the +# other tests. The only way I've found for doing this is to cat this line in +# explicitly in the RunPerlTest script. + +# use locale; # With this included, \x0b matches \s! + +# Function for turning a string into a string of printing chars. There are +# currently problems with UTF-8 strings; this fudges round them. + +sub pchars { +my($t) = ""; + +if ($utf8) + { + @p = unpack('U*', $_[0]); + foreach $c (@p) + { + if ($c >= 32 && $c < 127) { $t .= chr $c; } + else { $t .= sprintf("\\x{%02x}", $c); } + } + } + +else + { + foreach $c (split(//, $_[0])) + { + if (ord $c >= 32 && ord $c < 127) { $t .= $c; } + else { $t .= sprintf("\\x%02x", ord $c); } + } + } + +$t; +} + + +# Read lines from named file or stdin and write to named file or stdout; lines +# consist of a regular expression, in delimiters and optionally followed by +# options, followed by a set of test data, terminated by an empty line. + +# Sort out the input and output files + +if (@ARGV > 0) + { + open(INFILE, "<$ARGV[0]") || die "Failed to open $ARGV[0]\n"; + $infile = "INFILE"; + } +else { $infile = "STDIN"; } + +if (@ARGV > 1) + { + open(OUTFILE, ">$ARGV[1]") || die "Failed to open $ARGV[1]\n"; + $outfile = "OUTFILE"; + } +else { $outfile = "STDOUT"; } + +printf($outfile "Perl $] Regular Expressions\n\n"); + +# Main loop + +NEXT_RE: +for (;;) + { + printf " re> " if $infile eq "STDIN"; + last if ! ($_ = <$infile>); + printf $outfile "$_" if $infile ne "STDIN"; + next if ($_ eq ""); + + $pattern = $_; + + while ($pattern !~ /^\s*(.).*\1/s) + { + printf " > " if $infile eq "STDIN"; + last if ! ($_ = <$infile>); + printf $outfile "$_" if $infile ne "STDIN"; + $pattern .= $_; + } + + chomp($pattern); + $pattern =~ s/\s+$//; + + # The private /+ modifier means "print $' afterwards". + + $showrest = ($pattern =~ s/\+(?=[a-z]*$)//); + + # Remove /8 from a UTF-8 pattern. + + $utf8 = $pattern =~ s/8(?=[a-z]*$)//; + + # Check that the pattern is valid + + eval "\$_ =~ ${pattern}"; + if ($@) + { + printf $outfile "Error: $@"; + next NEXT_RE; + } + + # If the /g modifier is present, we want to put a loop round the matching; + # otherwise just a single "if". + + $cmd = ($pattern =~ /g[a-z]*$/)? "while" : "if"; + + # If the pattern is actually the null string, Perl uses the most recently + # executed (and successfully compiled) regex is used instead. This is a + # nasty trap for the unwary! The PCRE test suite does contain null strings + # in places - if they are allowed through here all sorts of weird and + # unexpected effects happen. To avoid this, we replace such patterns with + # a non-null pattern that has the same effect. + + $pattern = "/(?#)/$2" if ($pattern =~ /^(.)\1(.*)$/); + + # Read data lines and test them + + for (;;) + { + printf "data> " if $infile eq "STDIN"; + last NEXT_RE if ! ($_ = <$infile>); + chomp; + printf $outfile "$_\n" if $infile ne "STDIN"; + + s/\s+$//; + s/^\s+//; + + last if ($_ eq ""); + $x = eval "\"$_\""; # To get escapes processed + + # Empty array for holding results, then do the matching. + + @subs = (); + + $pushes = "push \@subs,\$&;" . + "push \@subs,\$1;" . + "push \@subs,\$2;" . + "push \@subs,\$3;" . + "push \@subs,\$4;" . + "push \@subs,\$5;" . + "push \@subs,\$6;" . + "push \@subs,\$7;" . + "push \@subs,\$8;" . + "push \@subs,\$9;" . + "push \@subs,\$10;" . + "push \@subs,\$11;" . + "push \@subs,\$12;" . + "push \@subs,\$13;" . + "push \@subs,\$14;" . + "push \@subs,\$15;" . + "push \@subs,\$16;" . + "push \@subs,\$'; }"; + + eval "${cmd} (\$x =~ ${pattern}) {" . $pushes; + + if ($@) + { + printf $outfile "Error: $@\n"; + next NEXT_RE; + } + elsif (scalar(@subs) == 0) + { + printf $outfile "No match\n"; + } + else + { + while (scalar(@subs) != 0) + { + printf $outfile (" 0: %s\n", &pchars($subs[0])); + printf $outfile (" 0+ %s\n", &pchars($subs[17])) if $showrest; + $last_printed = 0; + for ($i = 1; $i <= 16; $i++) + { + if (defined $subs[$i]) + { + while ($last_printed++ < $i-1) + { printf $outfile ("%2d: \n", $last_printed); } + printf $outfile ("%2d: %s\n", $i, &pchars($subs[$i])); + $last_printed = $i; + } + } + splice(@subs, 0, 18); + } + } + } + } + +# printf $outfile "\n"; + +# End diff --git a/libs/pcre/testdata/grepinput b/libs/pcre/testdata/grepinput new file mode 100644 index 0000000000..ed33f86d4a --- /dev/null +++ b/libs/pcre/testdata/grepinput @@ -0,0 +1,609 @@ +This is a file of miscellaneous text that is used as test data for checking +that the pcregrep command is working correctly. The file must be more than 24K +long so that it needs more than a single read() call to process it. New +features should be added at the end, because some of the tests involve the +output of line numbers, and we don't want these to change. + +PATTERN at the start of a line. +In the middle of a line, PATTERN appears. + +This pattern is in lower case. + +Here follows a whole lot of stuff that makes the file over 24K long. + +------------------------------------------------------------------------------- +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. + +The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the +lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox +jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick +brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. +------------------------------------------------------------------------------- + +aaaaa0 +aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +bbbbbb +cccccccccccccccccccccccccccccccccccccccccc +aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +eeeee +aaaaa2 +ffffffffff + +This is a line before the binary zero. +This line contains a binary zero here >< for testing. +This is a line after the binary zero. + +ABOVE the elephant +ABOVE +ABOVE theatre +AB.VE +AB.VE the turtle + +PUT NEW DATA ABOVE THIS LINE. +============================= + +Check up on PATTERN near the end. +This is the last line of this file. diff --git a/libs/pcre/testdata/grepinputx b/libs/pcre/testdata/grepinputx new file mode 100644 index 0000000000..296ed4cef2 --- /dev/null +++ b/libs/pcre/testdata/grepinputx @@ -0,0 +1,48 @@ +This is a second file of input for the pcregrep tests. + +Here is the pattern again. + +Pattern +That time it was on a line by itself. + +To pat or not to pat, that is the question. + +complete pair +of lines + +That was a complete pair +of lines all by themselves. + +complete pair +of lines + +And there they were again, to check line numbers. + +one +two +three +four +five +six +seven +eight +nine +ten +eleven +twelve +thirteen +fourteen +fifteen +sixteen +seventeen +eighteen +nineteen +twenty + +Here follows some CR/LF/CRLF test data. + +abc def +ghi +jkl + +This is the last line of this file. diff --git a/libs/pcre/testdata/greplist b/libs/pcre/testdata/greplist new file mode 100644 index 0000000000..1434ae96f6 --- /dev/null +++ b/libs/pcre/testdata/greplist @@ -0,0 +1,7 @@ +This is a file of patterns for testing the -f option. Don't include any blank +lines because they will match everything! This is no longer true, so have one. + +pattern +line by itself + +End of the list of patterns. diff --git a/libs/pcre/testdata/grepoutput b/libs/pcre/testdata/grepoutput new file mode 100644 index 0000000000..99b81bd994 --- /dev/null +++ b/libs/pcre/testdata/grepoutput @@ -0,0 +1,417 @@ +---------------------------- Test 1 ------------------------------ +PATTERN at the start of a line. +In the middle of a line, PATTERN appears. +Check up on PATTERN near the end. +---------------------------- Test 2 ------------------------------ +PATTERN at the start of a line. +---------------------------- Test 3 ------------------------------ +7:PATTERN at the start of a line. +8:In the middle of a line, PATTERN appears. +10:This pattern is in lower case. +608:Check up on PATTERN near the end. +---------------------------- Test 4 ------------------------------ +4 +---------------------------- Test 5 ------------------------------ +./testdata/grepinput:7:PATTERN at the start of a line. +./testdata/grepinput:8:In the middle of a line, PATTERN appears. +./testdata/grepinput:10:This pattern is in lower case. +./testdata/grepinput:608:Check up on PATTERN near the end. +./testdata/grepinputx:3:Here is the pattern again. +./testdata/grepinputx:5:Pattern +---------------------------- Test 6 ------------------------------ +7:PATTERN at the start of a line. +8:In the middle of a line, PATTERN appears. +10:This pattern is in lower case. +608:Check up on PATTERN near the end. +3:Here is the pattern again. +5:Pattern +---------------------------- Test 7 ------------------------------ +./testdata/grepinput +./testdata/grepinputx +---------------------------- Test 8 ------------------------------ +./testdata/grepinput +---------------------------- Test 9 ------------------------------ +RC=0 +---------------------------- Test 10 ----------------------------- +RC=1 +---------------------------- Test 11 ----------------------------- +1:This is a second file of input for the pcregrep tests. +2: +4: +5:Pattern +6:That time it was on a line by itself. +7: +8:To pat or not to pat, that is the question. +9: +10:complete pair +11:of lines +12: +13:That was a complete pair +14:of lines all by themselves. +15: +16:complete pair +17:of lines +18: +19:And there they were again, to check line numbers. +20: +21:one +22:two +23:three +24:four +25:five +26:six +27:seven +28:eight +29:nine +30:ten +31:eleven +32:twelve +33:thirteen +34:fourteen +35:fifteen +36:sixteen +37:seventeen +38:eighteen +39:nineteen +40:twenty +41: +42:Here follows some CR/LF/CRLF test data. +43: +44:abc def +45:ghi +46:jkl +47: +48:This is the last line of this file. +---------------------------- Test 12 ----------------------------- +Pattern +---------------------------- Test 13 ----------------------------- +Here is the pattern again. +That time it was on a line by itself. +---------------------------- Test 14 ----------------------------- +./testdata/grepinputx:To pat or not to pat, that is the question. +---------------------------- Test 15 ----------------------------- +pcregrep: Error in command-line regex at offset 4: nothing to repeat +---------------------------- Test 16 ----------------------------- +pcregrep: Failed to open ./testdata/nonexistfile: No such file or directory +---------------------------- Test 17 ----------------------------- +features should be added at the end, because some of the tests involve the +output of line numbers, and we don't want these to change. +---------------------------- Test 18 ----------------------------- +4:features should be added at the end, because some of the tests involve the +output of line numbers, and we don't want these to change. +583:brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. +------------------------------------------------------------------------------- +---------------------------- Test 19 ----------------------------- +Pattern +---------------------------- Test 20 ----------------------------- +10:complete pair +of lines +16:complete pair +of lines +---------------------------- Test 21 ----------------------------- +24:four +25-five +26-six +27-seven +-- +34:fourteen +35-fifteen +36-sixteen +37-seventeen +---------------------------- Test 22 ----------------------------- +21-one +22-two +23-three +24:four +-- +31-eleven +32-twelve +33-thirteen +34:fourteen +---------------------------- Test 23 ----------------------------- +one +two +three +four +five +six +seven +-- +eleven +twelve +thirteen +fourteen +fifteen +sixteen +seventeen +---------------------------- Test 24 ----------------------------- +four +five +six +seven +eight +nine +ten +eleven +twelve +thirteen +fourteen +fifteen +sixteen +seventeen +eighteen +nineteen +twenty + +Here follows some CR/LF/CRLF test data. + +---------------------------- Test 25 ----------------------------- +15- +16-complete pair +17-of lines +18- +19-And there they were again, to check line numbers. +20- +21-one +22-two +23-three +24:four +25-five +26-six +27-seven +28-eight +29-nine +30-ten +31-eleven +32-twelve +33-thirteen +34:fourteen +---------------------------- Test 26 ----------------------------- + +complete pair +of lines + +And there they were again, to check line numbers. + +one +two +three +four +five +six +seven +eight +nine +ten +eleven +twelve +thirteen +fourteen +fifteen +sixteen +seventeen +eighteen +nineteen +twenty + +Here follows some CR/LF/CRLF test data. + +---------------------------- Test 27 ----------------------------- +four +five +six +seven +eight +nine +ten +eleven +twelve +thirteen +fourteen +fifteen +sixteen +seventeen +eighteen +nineteen +twenty + +Here follows some CR/LF/CRLF test data. + +abc def +---------------------------- Test 28 ----------------------------- +14-of lines all by themselves. +15- +16-complete pair +17-of lines +18- +19-And there they were again, to check line numbers. +20- +21-one +22-two +23-three +24:four +25-five +26-six +27-seven +28-eight +29-nine +30-ten +31-eleven +32-twelve +33-thirteen +34:fourteen +---------------------------- Test 29 ----------------------------- +of lines all by themselves. + +complete pair +of lines + +And there they were again, to check line numbers. + +one +two +three +four +five +six +seven +eight +nine +ten +eleven +twelve +thirteen +fourteen +fifteen +sixteen +seventeen +eighteen +nineteen +twenty + +Here follows some CR/LF/CRLF test data. + +abc def +ghi +jkl +---------------------------- Test 30 ----------------------------- +./testdata/grepinput-4-features should be added at the end, because some of the tests involve the +./testdata/grepinput-5-output of line numbers, and we don't want these to change. +./testdata/grepinput-6- +./testdata/grepinput:7:PATTERN at the start of a line. +./testdata/grepinput:8:In the middle of a line, PATTERN appears. +./testdata/grepinput-9- +./testdata/grepinput:10:This pattern is in lower case. +-- +./testdata/grepinput-605-PUT NEW DATA ABOVE THIS LINE. +./testdata/grepinput-606-============================= +./testdata/grepinput-607- +./testdata/grepinput:608:Check up on PATTERN near the end. +-- +./testdata/grepinputx-1-This is a second file of input for the pcregrep tests. +./testdata/grepinputx-2- +./testdata/grepinputx:3:Here is the pattern again. +./testdata/grepinputx-4- +./testdata/grepinputx:5:Pattern +---------------------------- Test 31 ----------------------------- +./testdata/grepinput:7:PATTERN at the start of a line. +./testdata/grepinput:8:In the middle of a line, PATTERN appears. +./testdata/grepinput-9- +./testdata/grepinput:10:This pattern is in lower case. +./testdata/grepinput-11- +./testdata/grepinput-12-Here follows a whole lot of stuff that makes the file over 24K long. +./testdata/grepinput-13- +-- +./testdata/grepinput:608:Check up on PATTERN near the end. +./testdata/grepinput-609-This is the last line of this file. +-- +./testdata/grepinputx:3:Here is the pattern again. +./testdata/grepinputx-4- +./testdata/grepinputx:5:Pattern +./testdata/grepinputx-6-That time it was on a line by itself. +./testdata/grepinputx-7- +./testdata/grepinputx-8-To pat or not to pat, that is the question. +---------------------------- Test 32 ----------------------------- +./testdata/grepinputx +---------------------------- Test 33 ----------------------------- +pcregrep: Failed to open ./testdata/grepnonexist: No such file or directory +RC=2 +---------------------------- Test 34 ----------------------------- +RC=2 +---------------------------- Test 35 ----------------------------- +./testdata/grepinputx +RC=0 +---------------------------- Test 36 ----------------------------- +./testdata/grepinputx +RC=0 +---------------------------- Test 37 ----------------------------- +aaaaa0 +aaaaa2 +RC=0 +======== STDERR ======== +pcregrep: pcre_exec() error -8 while matching this line: +aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +pcregrep: error -8 means that a resource limit was exceeded +pcregrep: check your regex for nested unlimited loops +pcregrep: pcre_exec() error -8 while matching this line: +aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +---------------------------- Test 38 ------------------------------ +This line contains a binary zero here >< for testing. +---------------------------- Test 39 ------------------------------ +This is a line before the binary zero. +This line contains a binary zero here >< for testing. +---------------------------- Test 40 ------------------------------ +This line contains a binary zero here >< for testing. +This is a line after the binary zero. +---------------------------- Test 41 ------------------------------ +before the binary zero +after the binary zero +---------------------------- Test 41 ------------------------------ +./testdata/grepinput:595:before the binary zero +./testdata/grepinput:597:after the binary zero +---------------------------- Test 42 ------------------------------ +595:before +596:zero +597:after +---------------------------- Test 43 ------------------------------ +595:before +596:zero +597:zero +---------------------------- Test 44 ------------------------------ +10:pattern +595:binary +596:binary +597:binary +---------------------------- Test 45 ------------------------------ +pcregrep: Error in 2nd command-line regex at offset 9: missing ) +---------------------------- Test 46 ------------------------------ +AB.VE +---------------------------- Test 47 ------------------------------ +ABOVE the elephant +AB.VE +AB.VE the turtle +---------------------------- Test 48 ------------------------------ +ABOVE the elephant +AB.VE +AB.VE the turtle +PUT NEW DATA ABOVE THIS LINE. +---------------------------- Test 49 ------------------------------ +abc def +ghi +jkl +---------------------------- Test 50 ------------------------------ +def +---------------------------- Test 51 ------------------------------ +abc def +ghi +jkl +---------------------------- Test 52 ------------------------------ +def + +ghi +jkl + +This is the last line of this file. + +---------------------------- Test 53 ------------------------------ +jkl diff --git a/libs/pcre/testdata/testinput1 b/libs/pcre/testdata/testinput1 new file mode 100644 index 0000000000..042db24e6d --- /dev/null +++ b/libs/pcre/testdata/testinput1 @@ -0,0 +1,3886 @@ +/the quick brown fox/ + the quick brown fox + The quick brown FOX + What do you know about the quick brown fox? + What do you know about THE QUICK BROWN FOX? + +/The quick brown fox/i + the quick brown fox + The quick brown FOX + What do you know about the quick brown fox? + What do you know about THE QUICK BROWN FOX? + +/abcd\t\n\r\f\a\e\071\x3b\$\\\?caxyz/ + abcd\t\n\r\f\a\e9;\$\\?caxyz + +/a*abc?xyz+pqr{3}ab{2,}xy{4,5}pq{0,6}AB{0,}zz/ + abxyzpqrrrabbxyyyypqAzz + abxyzpqrrrabbxyyyypqAzz + aabxyzpqrrrabbxyyyypqAzz + aaabxyzpqrrrabbxyyyypqAzz + aaaabxyzpqrrrabbxyyyypqAzz + abcxyzpqrrrabbxyyyypqAzz + aabcxyzpqrrrabbxyyyypqAzz + aaabcxyzpqrrrabbxyyyypAzz + aaabcxyzpqrrrabbxyyyypqAzz + aaabcxyzpqrrrabbxyyyypqqAzz + aaabcxyzpqrrrabbxyyyypqqqAzz + aaabcxyzpqrrrabbxyyyypqqqqAzz + aaabcxyzpqrrrabbxyyyypqqqqqAzz + aaabcxyzpqrrrabbxyyyypqqqqqqAzz + aaaabcxyzpqrrrabbxyyyypqAzz + abxyzzpqrrrabbxyyyypqAzz + aabxyzzzpqrrrabbxyyyypqAzz + aaabxyzzzzpqrrrabbxyyyypqAzz + aaaabxyzzzzpqrrrabbxyyyypqAzz + abcxyzzpqrrrabbxyyyypqAzz + aabcxyzzzpqrrrabbxyyyypqAzz + aaabcxyzzzzpqrrrabbxyyyypqAzz + aaaabcxyzzzzpqrrrabbxyyyypqAzz + aaaabcxyzzzzpqrrrabbbxyyyypqAzz + aaaabcxyzzzzpqrrrabbbxyyyyypqAzz + aaabcxyzpqrrrabbxyyyypABzz + aaabcxyzpqrrrabbxyyyypABBzz + >>>aaabxyzpqrrrabbxyyyypqAzz + >aaaabxyzpqrrrabbxyyyypqAzz + >>>>abcxyzpqrrrabbxyyyypqAzz + *** Failers + abxyzpqrrabbxyyyypqAzz + abxyzpqrrrrabbxyyyypqAzz + abxyzpqrrrabxyyyypqAzz + aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz + aaaabcxyzzzzpqrrrabbbxyyypqAzz + aaabcxyzpqrrrabbxyyyypqqqqqqqAzz + +/^(abc){1,2}zz/ + abczz + abcabczz + *** Failers + zz + abcabcabczz + >>abczz + +/^(b+?|a){1,2}?c/ + bc + bbc + bbbc + bac + bbac + aac + abbbbbbbbbbbc + bbbbbbbbbbbac + *** Failers + aaac + abbbbbbbbbbbac + +/^(b+|a){1,2}c/ + bc + bbc + bbbc + bac + bbac + aac + abbbbbbbbbbbc + bbbbbbbbbbbac + *** Failers + aaac + abbbbbbbbbbbac + +/^(b+|a){1,2}?bc/ + bbc + +/^(b*|ba){1,2}?bc/ + babc + bbabc + bababc + *** Failers + bababbc + babababc + +/^(ba|b*){1,2}?bc/ + babc + bbabc + bababc + *** Failers + bababbc + babababc + +/^\ca\cA\c[\c{\c:/ + \x01\x01\e;z + +/^[ab\]cde]/ + athing + bthing + ]thing + cthing + dthing + ething + *** Failers + fthing + [thing + \\thing + +/^[]cde]/ + ]thing + cthing + dthing + ething + *** Failers + athing + fthing + +/^[^ab\]cde]/ + fthing + [thing + \\thing + *** Failers + athing + bthing + ]thing + cthing + dthing + ething + +/^[^]cde]/ + athing + fthing + *** Failers + ]thing + cthing + dthing + ething + +/^\/ + + +/^ÿ/ + ÿ + +/^[0-9]+$/ + 0 + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8 + 9 + 10 + 100 + *** Failers + abc + +/^.*nter/ + enter + inter + uponter + +/^xxx[0-9]+$/ + xxx0 + xxx1234 + *** Failers + xxx + +/^.+[0-9][0-9][0-9]$/ + x123 + xx123 + 123456 + *** Failers + 123 + x1234 + +/^.+?[0-9][0-9][0-9]$/ + x123 + xx123 + 123456 + *** Failers + 123 + x1234 + +/^([^!]+)!(.+)=apquxz\.ixr\.zzz\.ac\.uk$/ + abc!pqr=apquxz.ixr.zzz.ac.uk + *** Failers + !pqr=apquxz.ixr.zzz.ac.uk + abc!=apquxz.ixr.zzz.ac.uk + abc!pqr=apquxz:ixr.zzz.ac.uk + abc!pqr=apquxz.ixr.zzz.ac.ukk + +/:/ + Well, we need a colon: somewhere + *** Fail if we don't + +/([\da-f:]+)$/i + 0abc + abc + fed + E + :: + 5f03:12C0::932e + fed def + Any old stuff + *** Failers + 0zzz + gzzz + fed\x20 + Any old rubbish + +/^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/ + .1.2.3 + A.12.123.0 + *** Failers + .1.2.3333 + 1.2.3 + 1234.2.3 + +/^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/ + 1 IN SOA non-sp1 non-sp2( + 1 IN SOA non-sp1 non-sp2 ( + *** Failers + 1IN SOA non-sp1 non-sp2( + +/^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/ + a. + Z. + 2. + ab-c.pq-r. + sxk.zzz.ac.uk. + x-.y-. + *** Failers + -abc.peq. + +/^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/ + *.a + *.b0-a + *.c3-b.c + *.c-a.b-c + *** Failers + *.0 + *.a- + *.a-b.c- + *.c-a.0-c + +/^(?=ab(de))(abd)(e)/ + abde + +/^(?!(ab)de|x)(abd)(f)/ + abdf + +/^(?=(ab(cd)))(ab)/ + abcd + +/^[\da-f](\.[\da-f])*$/i + a.b.c.d + A.B.C.D + a.b.c.1.2.3.C + +/^\".*\"\s*(;.*)?$/ + \"1234\" + \"abcd\" ; + \"\" ; rhubarb + *** Failers + \"1234\" : things + +/^$/ + \ + *** Failers + +/ ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/x + ab c + *** Failers + abc + ab cde + +/(?x) ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/ + ab c + *** Failers + abc + ab cde + +/^ a\ b[c ]d $/x + a bcd + a b d + *** Failers + abcd + ab d + +/^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/ + abcdefhijklm + +/^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/ + abcdefhijklm + +/^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/ + a+ Z0+\x08\n\x1d\x12 + +/^[.^$|()*+?{,}]+/ + .^\$(*+)|{?,?} + +/^a*\w/ + z + az + aaaz + a + aa + aaaa + a+ + aa+ + +/^a*?\w/ + z + az + aaaz + a + aa + aaaa + a+ + aa+ + +/^a+\w/ + az + aaaz + aa + aaaa + aa+ + +/^a+?\w/ + az + aaaz + aa + aaaa + aa+ + +/^\d{8}\w{2,}/ + 1234567890 + 12345678ab + 12345678__ + *** Failers + 1234567 + +/^[aeiou\d]{4,5}$/ + uoie + 1234 + 12345 + aaaaa + *** Failers + 123456 + +/^[aeiou\d]{4,5}?/ + uoie + 1234 + 12345 + aaaaa + 123456 + +/\A(abc|def)=(\1){2,3}\Z/ + abc=abcabc + def=defdefdef + *** Failers + abc=defdef + +/^(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\11*(\3\4)\1(?#)2$/ + abcdefghijkcda2 + abcdefghijkkkkcda2 + +/(cat(a(ract|tonic)|erpillar)) \1()2(3)/ + cataract cataract23 + catatonic catatonic23 + caterpillar caterpillar23 + + +/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/ + From abcd Mon Sep 01 12:33:02 1997 + +/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/ + From abcd Mon Sep 01 12:33:02 1997 + From abcd Mon Sep 1 12:33:02 1997 + *** Failers + From abcd Sep 01 12:33:02 1997 + +/^12.34/s + 12\n34 + 12\r34 + +/\w+(?=\t)/ + the quick brown\t fox + +/foo(?!bar)(.*)/ + foobar is foolish see? + +/(?:(?!foo)...|^.{0,2})bar(.*)/ + foobar crowbar etc + barrel + 2barrel + A barrel + +/^(\D*)(?=\d)(?!123)/ + abc456 + *** Failers + abc123 + +/^1234(?# test newlines + inside)/ + 1234 + +/^1234 #comment in extended re + /x + 1234 + +/#rhubarb + abcd/x + abcd + +/^abcd#rhubarb/x + abcd + +/^(a)\1{2,3}(.)/ + aaab + aaaab + aaaaab + aaaaaab + +/(?!^)abc/ + the abc + *** Failers + abc + +/(?=^)abc/ + abc + *** Failers + the abc + +/^[ab]{1,3}(ab*|b)/ + aabbbbb + +/^[ab]{1,3}?(ab*|b)/ + aabbbbb + +/^[ab]{1,3}?(ab*?|b)/ + aabbbbb + +/^[ab]{1,3}(ab*?|b)/ + aabbbbb + +/ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # optional leading comment +(?: (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # initial word +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) )* # further okay, if led by a period +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +# address +| # or +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # one word, optionally followed by.... +(?: +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] | # atom and space parts, or... +\( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) | # comments, or... + +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +# quoted strings +)* +< (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # leading < +(?: @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* + +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* , (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +)* # further okay, if led by comma +: # closing colon +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* )? # optional route +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # initial word +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) )* # further okay, if led by a period +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +# address spec +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* > # trailing > +# name and address +) (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # optional trailing comment +/x + Alan Other + + user\@dom.ain + \"A. Other\" (a comment) + A. Other (a comment) + \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay + A missing angle @,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# additional words +)* +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +# address +| # or +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +# leading word +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # "normal" atoms and or spaces +(?: +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +| +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +) # "special" comment or quoted string +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # more "normal" +)* +< +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# < +(?: +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +(?: , +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +)* # additional domains +: +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)? # optional route +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# additional words +)* +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +# address spec +> # > +# name and address +) +/x + Alan Other + + user\@dom.ain + \"A. Other\" (a comment) + A. Other (a comment) + \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay + A missing angle ]{0,})>]{0,})>([\d]{0,}\.)(.*)((
([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is + 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide + +/a[^a]b/ + acb + a\nb + +/a.b/ + acb + *** Failers + a\nb + +/a[^a]b/s + acb + a\nb + +/a.b/s + acb + a\nb + +/^(b+?|a){1,2}?c/ + bac + bbac + bbbac + bbbbac + bbbbbac + +/^(b+|a){1,2}?c/ + bac + bbac + bbbac + bbbbac + bbbbbac + +/(?!\A)x/m + x\nb\n + a\bx\n + +/\x0{ab}/ + \0{ab} + +/(A|B)*?CD/ + CD + +/(A|B)*CD/ + CD + +/(AB)*?\1/ + ABABAB + +/(AB)*\1/ + ABABAB + +/(?.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/ + +"(?>.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo + +/(?>(\.\d\d[1-9]?))\d+/ + 1.230003938 + 1.875000282 + *** Failers + 1.235 + +/^((?>\w+)|(?>\s+))*$/ + now is the time for all good men to come to the aid of the party + *** Failers + this is not a line with only words and spaces! + +/(\d+)(\w)/ + 12345a + 12345+ + +/((?>\d+))(\w)/ + 12345a + *** Failers + 12345+ + +/(?>a+)b/ + aaab + +/((?>a+)b)/ + aaab + +/(?>(a+))b/ + aaab + +/(?>b)+/ + aaabbbccc + +/(?>a+|b+|c+)*c/ + aaabbbbccccd + +/((?>[^()]+)|\([^()]*\))+/ + ((abc(ade)ufh()()x + +/\(((?>[^()]+)|\([^()]+\))+\)/ + (abc) + (abc(def)xyz) + *** Failers + ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/a(?-i)b/i + ab + Ab + *** Failers + aB + AB + +/(a (?x)b c)d e/ + a bcd e + *** Failers + a b cd e + abcd e + a bcde + +/(a b(?x)c d (?-x)e f)/ + a bcde f + *** Failers + abcdef + +/(a(?i)b)c/ + abc + aBc + *** Failers + abC + aBC + Abc + ABc + ABC + AbC + +/a(?i:b)c/ + abc + aBc + *** Failers + ABC + abC + aBC + +/a(?i:b)*c/ + aBc + aBBc + *** Failers + aBC + aBBC + +/a(?=b(?i)c)\w\wd/ + abcd + abCd + *** Failers + aBCd + abcD + +/(?s-i:more.*than).*million/i + more than million + more than MILLION + more \n than Million + *** Failers + MORE THAN MILLION + more \n than \n million + +/(?:(?s-i)more.*than).*million/i + more than million + more than MILLION + more \n than Million + *** Failers + MORE THAN MILLION + more \n than \n million + +/(?>a(?i)b+)+c/ + abc + aBbc + aBBc + *** Failers + Abc + abAb + abbC + +/(?=a(?i)b)\w\wc/ + abc + aBc + *** Failers + Ab + abC + aBC + +/(?<=a(?i)b)(\w\w)c/ + abxxc + aBxxc + *** Failers + Abxxc + ABxxc + abxxC + +/(?:(a)|b)(?(1)A|B)/ + aA + bB + *** Failers + aB + bA + +/^(a)?(?(1)a|b)+$/ + aa + b + bb + *** Failers + ab + +/^(?(?=abc)\w{3}:|\d\d)$/ + abc: + 12 + *** Failers + 123 + xyz + +/^(?(?!abc)\d\d|\w{3}:)$/ + abc: + 12 + *** Failers + 123 + xyz + +/(?(?<=foo)bar|cat)/ + foobar + cat + fcat + focat + *** Failers + foocat + +/(?(?a*)*/ + a + aa + aaaa + +/(abc|)+/ + abc + abcabc + abcabcabc + xyz + +/([a]*)*/ + a + aaaaa + +/([ab]*)*/ + a + b + ababab + aaaabcde + bbbb + +/([^a]*)*/ + b + bbbb + aaa + +/([^ab]*)*/ + cccc + abab + +/([a]*?)*/ + a + aaaa + +/([ab]*?)*/ + a + b + abab + baba + +/([^a]*?)*/ + b + bbbb + aaa + +/([^ab]*?)*/ + c + cccc + baba + +/(?>a*)*/ + a + aaabcde + +/((?>a*))*/ + aaaaa + aabbaa + +/((?>a*?))*/ + aaaaa + aabbaa + +/(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /x + 12-sep-98 + 12-09-98 + *** Failers + sep-12-98 + +/(?<=(foo))bar\1/ + foobarfoo + foobarfootling + *** Failers + foobar + barfoo + +/(?i:saturday|sunday)/ + saturday + sunday + Saturday + Sunday + SATURDAY + SUNDAY + SunDay + +/(a(?i)bc|BB)x/ + abcx + aBCx + bbx + BBx + *** Failers + abcX + aBCX + bbX + BBX + +/^([ab](?i)[cd]|[ef])/ + ac + aC + bD + elephant + Europe + frog + France + *** Failers + Africa + +/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/ + ab + aBd + xy + xY + zebra + Zambesi + *** Failers + aCD + XY + +/(?<=foo\n)^bar/m + foo\nbar + *** Failers + bar + baz\nbar + +/(?<=(?]&/ + <&OUT + +/^(a\1?){4}$/ + aaaaaaaaaa + *** Failers + AB + aaaaaaaaa + aaaaaaaaaaa + +/^(a(?(1)\1)){4}$/ + aaaaaaaaaa + *** Failers + aaaaaaaaa + aaaaaaaaaaa + +/(?:(f)(o)(o)|(b)(a)(r))*/ + foobar + +/(?<=a)b/ + ab + *** Failers + cb + b + +/(?a+)ab/ + +/(?>a+)b/ + aaab + +/([[:]+)/ + a:[b]: + +/([[=]+)/ + a=[b]= + +/([[.]+)/ + a.[b]. + +/((?>a+)b)/ + aaab + +/(?>(a+))b/ + aaab + +/((?>[^()]+)|\([^()]*\))+/ + ((abc(ade)ufh()()x + +/a\Z/ + *** Failers + aaab + a\nb\n + +/b\Z/ + a\nb\n + +/b\z/ + +/b\Z/ + a\nb + +/b\z/ + a\nb + *** Failers + +/^(?>(?(1)\.|())[^\W_](?>[a-z0-9-]*[^\W_])?)+$/ + a + abc + a-b + 0-9 + a.b + 5.6.7 + the.quick.brown.fox + a100.b200.300c + 12-ab.1245 + *** Failers + \ + .a + -a + a- + a. + a_b + a.- + a.. + ab..bc + the.quick.brown.fox- + the.quick.brown.fox. + the.quick.brown.fox_ + the.quick.brown.fox+ + +/(?>.*)(?<=(abcd|wxyz))/ + alphabetabcd + endingwxyz + *** Failers + a rather long string that doesn't end with one of them + +/word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark otherword + word cat dog elephant mussel cow horse canary baboon snake shark + +/word (?>[a-zA-Z0-9]+ ){0,30}otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope + +/(?<=\d{3}(?!999))foo/ + 999foo + 123999foo + *** Failers + 123abcfoo + +/(?<=(?!...999)\d{3})foo/ + 999foo + 123999foo + *** Failers + 123abcfoo + +/(?<=\d{3}(?!999)...)foo/ + 123abcfoo + 123456foo + *** Failers + 123999foo + +/(?<=\d{3}...)(?\s*)=(?>\s*) # find Z)+|A)*/ + ZABCDEFG + +/((?>)+|A)*/ + ZABCDEFG + +/a*/g + abbab + +/^[a-\d]/ + abcde + -things + 0digit + *** Failers + bcdef + +/^[\d-a]/ + abcde + -things + 0digit + *** Failers + bcdef + +/[[:space:]]+/ + > \x09\x0a\x0c\x0d\x0b< + +/[[:blank:]]+/ + > \x09\x0a\x0c\x0d\x0b< + +/[\s]+/ + > \x09\x0a\x0c\x0d\x0b< + +/\s+/ + > \x09\x0a\x0c\x0d\x0b< + +/a b/x + ab + +/(?!\A)x/m + a\nxb\n + +/(?!^)x/m + a\nxb\n + +/abc\Qabc\Eabc/ + abcabcabc + +/abc\Q(*+|\Eabc/ + abc(*+|abc + +/ abc\Q abc\Eabc/x + abc abcabc + *** Failers + abcabcabc + +/abc#comment + \Q#not comment + literal\E/x + abc#not comment\n literal + +/abc#comment + \Q#not comment + literal/x + abc#not comment\n literal + +/abc#comment + \Q#not comment + literal\E #more comment + /x + abc#not comment\n literal + +/abc#comment + \Q#not comment + literal\E #more comment/x + abc#not comment\n literal + +/\Qabc\$xyz\E/ + abc\\\$xyz + +/\Qabc\E\$\Qxyz\E/ + abc\$xyz + +/\Gabc/ + abc + *** Failers + xyzabc + +/\Gabc./g + abc1abc2xyzabc3 + +/abc./g + abc1abc2xyzabc3 + +/a(?x: b c )d/ + XabcdY + *** Failers + Xa b c d Y + +/((?x)x y z | a b c)/ + XabcY + AxyzB + +/(?i)AB(?-i)C/ + XabCY + *** Failers + XabcY + +/((?i)AB(?-i)C|D)E/ + abCE + DE + *** Failers + abcE + abCe + dE + De + +/(.*)\d+\1/ + abc123abc + abc123bc + +/(.*)\d+\1/s + abc123abc + abc123bc + +/((.*))\d+\1/ + abc123abc + abc123bc + +/-- This tests for an IPv6 address in the form where it can have up to --/ +/-- eight components, one and only one of which is empty. This must be --/ +/-- an internal component. --/ + +/^(?!:) # colon disallowed at start + (?: # start of item + (?: [0-9a-f]{1,4} | # 1-4 hex digits or + (?(1)0 | () ) ) # if null previously matched, fail; else null + : # followed by colon + ){1,7} # end item; 1-7 of them required + [0-9a-f]{1,4} $ # final hex number at end of string + (?(1)|.) # check that there was an empty component + /xi + a123::a123 + a123:b342::abcd + a123:b342::324e:abcd + a123:ddde:b342::324e:abcd + a123:ddde:b342::324e:dcba:abcd + a123:ddde:9999:b342::324e:dcba:abcd + *** Failers + 1:2:3:4:5:6:7:8 + a123:bce:ddde:9999:b342::324e:dcba:abcd + a123::9999:b342::324e:dcba:abcd + abcde:2:3:4:5:6:7:8 + ::1 + abcd:fee0:123:: + :1 + 1: + +/[z\Qa-d]\E]/ + z + a + - + d + ] + *** Failers + b + +/[\z\C]/ + z + C + +/\M/ + M + +/(a+)*b/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/(?i)reg(?:ul(?:[aä]|ae)r|ex)/ + REGular + regulaer + Regex + regulär + +/Åæåä[à-ÿÀ-ß]+/ + Åæåäà + Åæåäÿ + ÅæåäÀ + Åæåäß + +/(?<=Z)X./ + \x84XAZXB + +/ab cd (?x) de fg/ + ab cd defg + +/ab cd(?x) de fg/ + ab cddefg + ** Failers + abcddefg + +/(?/ + abcghinop + +/<.*?>/ + abcghinop + +/<.*>/U + abcghinop + +/(?U)<.*>/ + abcghinop + +/<.*?>/U + abcghinop + +/={3,}/U + abc========def + +/(?U)={3,}?/ + abc========def + +/(?^abc)/m + abc + def\nabc + *** Failers + defabc + +/(?<=ab(c+)d)ef/ + +/(?<=ab(?<=c+)d)ef/ + +/(?<=ab(c|de)f)g/ + +/The next three are in testinput2 because they have variable length branches/ + +/(?<=bullock|donkey)-cart/ + the bullock-cart + a donkey-cart race + *** Failers + cart + horse-and-cart + +/(?<=ab(?i)x|y|z)/ + +/(?>.*)(?<=(abcd)|(xyz))/ + alphabetabcd + endingxyz + +/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/ + abxyZZ + abXyZZ + ZZZ + zZZ + bZZ + BZZ + *** Failers + ZZ + abXYZZ + zzz + bzz + +/(?[^()]+) # Either a sequence of non-brackets (no backtracking) + | # Or + (?R) # Recurse - i.e. nested bracketed string + )* # Zero or more contents + \) # Closing ) + /x + (abcd) + (abcd)xyz + xyz(abcd) + (ab(xy)cd)pqr + (ab(xycd)pqr + () abc () + 12(abcde(fsh)xyz(foo(bar))lmno)89 + *** Failers + abcd + abcd) + (abcd + +/\( ( (?>[^()]+) | (?R) )* \) /xg + (ab(xy)cd)pqr + 1(abcd)(x(y)z)pqr + +/\( (?: (?>[^()]+) | (?R) ) \) /x + (abcd) + (ab(xy)cd) + (a(b(c)d)e) + ((ab)) + *** Failers + () + +/\( (?: (?>[^()]+) | (?R) )? \) /x + () + 12(abcde(fsh)xyz(foo(bar))lmno)89 + +/\( ( (?>[^()]+) | (?R) )* \) /x + (ab(xy)cd) + +/\( ( ( (?>[^()]+) | (?R) )* ) \) /x + (ab(xy)cd) + +/\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /x + (ab(xy)cd) + (123ab(xy)cd) + +/\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /x + (ab(xy)cd) + (123ab(xy)cd) + +/\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /x + (ab(xy)cd) + +/\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /x + (abcd(xyz

qrs)123) + +/\( ( ( (?>[^()]+) | ((?R)) )* ) \) /x + (ab(cd)ef) + (ab(cd(ef)gh)ij) + +/^[[:alnum:]]/D + +/^[[:^alnum:]]/D + +/^[[:alpha:]]/D + +/^[[:^alpha:]]/D + +/[_[:alpha:]]/IS + +/^[[:ascii:]]/D + +/^[[:^ascii:]]/D + +/^[[:blank:]]/D + +/^[[:^blank:]]/D + +/[\n\x0b\x0c\x0d[:blank:]]/IS + +/^[[:cntrl:]]/D + +/^[[:digit:]]/D + +/^[[:graph:]]/D + +/^[[:lower:]]/D + +/^[[:print:]]/D + +/^[[:punct:]]/D + +/^[[:space:]]/D + +/^[[:upper:]]/D + +/^[[:xdigit:]]/D + +/^[[:word:]]/D + +/^[[:^cntrl:]]/D + +/^[12[:^digit:]]/D + +/^[[:^blank:]]/D + +/[01[:alpha:]%]/D + +/[[.ch.]]/ + +/[[=ch=]]/ + +/[[:rhubarb:]]/ + +/[[:upper:]]/i + A + a + +/[[:lower:]]/i + A + a + +/((?-i)[[:lower:]])[[:lower:]]/i + ab + aB + *** Failers + Ab + AB + +/[\200-\110]/ + +/^(?(0)f|b)oo/ + +/This one's here because of the large output vector needed/ + +/(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\w+)\s+(\270)/ + \O900 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 ABC ABC + +/This one's here because Perl does this differently and PCRE can't at present/ + +/(main(O)?)+/ + mainmain + mainOmain + +/These are all cases where Perl does it differently (nested captures)/ + +/^(a(b)?)+$/ + aba + +/^(aa(bb)?)+$/ + aabbaa + +/^(aa|aa(bb))+$/ + aabbaa + +/^(aa(bb)??)+$/ + aabbaa + +/^(?:aa(bb)?)+$/ + aabbaa + +/^(aa(b(b))?)+$/ + aabbaa + +/^(?:aa(b(b))?)+$/ + aabbaa + +/^(?:aa(b(?:b))?)+$/ + aabbaa + +/^(?:aa(bb(?:b))?)+$/ + aabbbaa + +/^(?:aa(b(?:bb))?)+$/ + aabbbaa + +/^(?:aa(?:b(b))?)+$/ + aabbaa + +/^(?:aa(?:b(bb))?)+$/ + aabbbaa + +/^(aa(b(bb))?)+$/ + aabbbaa + +/^(aa(bb(bb))?)+$/ + aabbbbaa + +/--------------------------------------------------------------------/ + +/#/xMD + +/a#/xMD + +/[\s]/D + +/[\S]/D + +/a(?i)b/D + ab + aB + *** Failers + AB + +/(a(?i)b)/D + ab + aB + *** Failers + AB + +/ (?i)abc/xD + +/#this is a comment + (?i)abc/xD + +/123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/D + +/\Q123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/D + +/\Q\E/D + \ + +/\Q\Ex/D + +/ \Q\E/D + +/a\Q\E/D + abc + bca + bac + +/a\Q\Eb/D + abc + +/\Q\Eabc/D + +/x*+\w/D + *** Failers + xxxxx + +/x?+/D + +/x++/D + +/x{1,3}+/D + +/(x)*+/D + +/^(\w++|\s++)*$/ + now is the time for all good men to come to the aid of the party + *** Failers + this is not a line with only words and spaces! + +/(\d++)(\w)/ + 12345a + *** Failers + 12345+ + +/a++b/ + aaab + +/(a++b)/ + aaab + +/(a++)b/ + aaab + +/([^()]++|\([^()]*\))+/ + ((abc(ade)ufh()()x + +/\(([^()]++|\([^()]+\))+\)/ + (abc) + (abc(def)xyz) + *** Failers + ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/(abc){1,3}+/D + +/a+?+/ + +/a{2,3}?+b/ + +/(?U)a+?+/ + +/a{2,3}?+b/U + +/x(?U)a++b/D + xaaaab + +/(?U)xa++b/D + xaaaab + +/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/D + +/^x(?U)a+b/D + +/^x(?U)(a+)b/D + +/[.x.]/ + +/[=x=]/ + +/[:x:]/ + +/\l/ + +/\L/ + +/\N{name}/ + +/\u/ + +/\U/ + +/[/ + +/[a-/ + +/[[:space:]/ + +/[\s]/DM + +/[[:space:]]/DM + +/[[:space:]abcde]/DM + +/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/x + <> + + hij> + hij> + def> + + *** Failers + iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|DM + +|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|DM + +/(.*)\d+\1/I + +/(.*)\d+/I + +/(.*)\d+\1/Is + +/(.*)\d+/Is + +/(.*(xyz))\d+\2/I + +/((.*))\d+\1/I + abc123bc + +/a[b]/I + +/(?=a).*/I + +/(?=abc).xyz/iI + +/(?=abc)(?i).xyz/I + +/(?=a)(?=b)/I + +/(?=.)a/I + +/((?=abcda)a)/I + +/((?=abcda)ab)/I + +/()a/I + +/(?(1)ab|ac)/I + +/(?(1)abz|acz)/I + +/(?(1)abz)/I + +/(?(1)abz)123/I + +/(a)+/I + +/(a){2,3}/I + +/(a)*/I + +/[a]/I + +/[ab]/I + +/[ab]/IS + +/[^a]/I + +/\d456/I + +/\d456/IS + +/a^b/I + +/^a/mI + abcde + xy\nabc + *** Failers + xyabc + +/c|abc/I + +/(?i)[ab]/IS + +/[ab](?i)cd/IS + +/abc(?C)def/ + abcdef + 1234abcdef + *** Failers + abcxyz + abcxyzf + +/abc(?C)de(?C1)f/ + 123abcdef + +/(?C1)\dabc(?C2)def/ + 1234abcdef + *** Failers + abcdef + +/(?C255)ab/ + +/(?C256)ab/ + +/(?Cab)xx/ + +/(?C12vr)x/ + +/abc(?C)def/ + *** Failers + \x83\x0\x61bcdef + +/(abc)(?C)de(?C1)f/ + 123abcdef + 123abcdef\C+ + 123abcdef\C- + *** Failers + 123abcdef\C!1 + +/(?C0)(abc(?C1))*/ + abcabcabc + abcabc\C!1!3 + *** Failers + abcabcabc\C!1!3 + +/(\d{3}(?C))*/ + 123\C+ + 123456\C+ + 123456789\C+ + +/((xyz)(?C)p|(?C1)xyzabc)/ + xyzabc\C+ + +/(X)((xyz)(?C)p|(?C1)xyzabc)/ + Xxyzabc\C+ + +/(?=(abc))(?C)abcdef/ + abcdef\C+ + +/(?!(abc)(?C1)d)(?C2)abcxyz/ + abcxyz\C+ + +/(?<=(abc)(?C))xyz/ + abcxyz\C+ + +/a(b+)(c*)(?C1)/ + abbbbbccc\C*1 + +/a(b+?)(c*?)(?C1)/ + abbbbbccc\C*1 + +/(?C)abc/ + +/(?C)^abc/ + +/(?C)a|b/S + +/(?R)/ + +/(a|(?R))/ + +/(ab|(bc|(de|(?R))))/ + +/x(ab|(bc|(de|(?R))))/ + xab + xbc + xde + xxab + xxxab + *** Failers + xyab + +/(ab|(bc|(de|(?1))))/ + +/x(ab|(bc|(de|(?1)x)x)x)/ + +/^([^()]|\((?1)*\))*$/ + abc + a(b)c + a(b(c))d + *** Failers) + a(b(c)d + +/^>abc>([^()]|\((?1)*\))*abc>123abc>1(2)3abc>(1(2)3)]*+) | (?2)) * >))/x + <> + + hij> + hij> + def> + + *** Failers + b|c)d(?Pe)/D + abde + acde + +/(?:a(?Pc(?Pd)))(?Pa)/D + +/(?Pa)...(?P=a)bbb(?P>a)d/D + +/^\W*(?:(?P(?P.)\W*(?P>one)\W*(?P=two)|)|(?P(?P.)\W*(?P>three)\W*(?P=four)|\W*.\W*))\W*$/i + 1221 + Satan, oscillate my metallic sonatas! + A man, a plan, a canal: Panama! + Able was I ere I saw Elba. + *** Failers + The quick brown fox + +/((?(R)a|b))\1(?1)?/ + bb + bbaa + +/(.*)a/sI + +/(.*)a\1/sI + +/(.*)a(b)\2/sI + +/((.*)a|(.*)b)z/sI + +/((.*)a|(.*)b)z\1/sI + +/((.*)a|(.*)b)z\2/sI + +/((.*)a|(.*)b)z\3/sI + +/((.*)a|^(.*)b)z\3/sI + +/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a/sI + +/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\31/sI + +/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\32/sI + +/(a)(bc)/ND + abc + +/(?Pa)(bc)/ND + abc + +/(a)(?Pbc)/ND + +/(a+)*zz/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazzbbbbbb\M + aaaaaaaaaaaaaz\M + +/(aaa(?C1)bbb|ab)/ + aaabbb + aaabbb\C*0 + aaabbb\C*1 + aaabbb\C*-1 + +/ab(?Pcd)ef(?Pgh)/ + abcdefgh + abcdefgh\C1\Gtwo + abcdefgh\Cone\Ctwo + abcdefgh\Cthree + +/(?P)(?P)/D + +/(?P)(?P)/D + +/(?Pzz)(?Paa)/ + zzaa\CZ + zzaa\CA + +/(?Peks)(?Peccs)/ + +/(?Pabc(?Pdef)(?Pxyz))/ + +"\[((?P\d+)(,(?P>elem))*)\]" + [10,20,30,5,5,4,4,2,43,23,4234] + *** Failers + [] + +"\[((?P\d+)(,(?P>elem))*)?\]" + [10,20,30,5,5,4,4,2,43,23,4234] + [] + +/(a(b(?2)c))?/D + +/(a(b(?2)c))*/D + +/(a(b(?2)c)){0,2}/D + +/[ab]{1}+/D + +/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/i + Baby Bjorn Active Carrier - With free SHIPPING!! + +/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/iS + Baby Bjorn Active Carrier - With free SHIPPING!! + +/a*.*b/SD + +/(a|b)*.?c/SD + +/abc(?C255)de(?C)f/D + +/abcde/CD + abcde + abcdfe + +/a*b/CD + ab + aaaab + aaaacb + +/a+b/CD + ab + aaaab + aaaacb + +/(abc|def)x/CD + abcx + defx + abcdefzx + +/(ab|cd){3,4}/C + ababab + abcdabcd + abcdcdcdcdcd + +/([ab]{,4}c|xy)/CD + Note: that { does NOT introduce a quantifier + +/([ab]{1,4}c|xy){4,5}?123/CD + aacaacaacaacaac123 + +/\b.*/I + ab cd\>1 + +/\b.*/Is + ab cd\>1 + +/(?!.bcd).*/I + Xbcd12345 + +/abcde/ + ab\P + abc\P + abcd\P + abcde\P + the quick brown abc\P + ** Failers\P + the quick brown abxyz fox\P + +"^(0?[1-9]|[12][0-9]|3[01])/(0?[1-9]|1[012])/(20)?\d\d$" + 13/05/04\P + 13/5/2004\P + 02/05/09\P + 1\P + 1/2\P + 1/2/0\P + 1/2/04\P + 0\P + 02/\P + 02/0\P + 02/1\P + ** Failers\P + \P + 123\P + 33/4/04\P + 3/13/04\P + 0/1/2003\P + 0/\P + 02/0/\P + 02/13\P + +/0{0,2}ABC/I + +/\d{3,}ABC/I + +/\d*ABC/I + +/[abc]+DE/I + +/[abc]?123/ + 123\P + a\P + b\P + c\P + c12\P + c123\P + +/^(?:\d){3,5}X/ + 1\P + 123\P + 123X + 1234\P + 1234X + 12345\P + 12345X + *** Failers + 1X + 123456\P + +/abc/>testsavedregex +testsavedregex +testsavedregex +testsavedregex +(.)*~smg + \n\n\nPartner der LCO\nde\nPartner der LINEAS Consulting\nGmbH\nLINEAS Consulting GmbH Hamburg\nPartnerfirmen\n30 days\nindex,follow\n\nja\n3\nPartner\n\n\nLCO\nLINEAS Consulting\n15.10.2003\n\n\n\n\nDie Partnerfirmen der LINEAS Consulting\nGmbH\n\n\n \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n + +/^a/IF + +/line\nbreak/ + this is a line\nbreak + line one\nthis is a line\nbreak in the second line + +/line\nbreak/f + this is a line\nbreak + ** Failers + line one\nthis is a line\nbreak in the second line + +/line\nbreak/mf + this is a line\nbreak + ** Failers + line one\nthis is a line\nbreak in the second line + +/ab.cd/P + ab-cd + ab=cd + ** Failers + ab\ncd + +/ab.cd/Ps + ab-cd + ab=cd + ab\ncd + +/(?i)(?-i)AbCd/ + AbCd + ** Failers + abcd + +/a{11111111111111111111}/ + +/(){64294967295}/ + +/(){2,4294967295}/ + +"(?i:a)(?i:b)(?i:c)(?i:d)(?i:e)(?i:f)(?i:g)(?i:h)(?i:i)(?i:j)(k)(?i:l)A\1B" + abcdefghijklAkB + +"(?Pa)(?Pb)(?Pc)(?Pd)(?Pe)(?Pf)(?Pg)(?Ph)(?Pi)(?Pj)(?Pk)(?Pl)A\11B" + abcdefghijklAkB + +"(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)A\11B" + abcdefghijklAkB + +"(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)" + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +"(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)" + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/[^()]*(?:\((?R)\)[^()]*)*/ + (this(and)that + (this(and)that) + (this(and)that)stuff + +/[^()]*(?:\((?>(?R))\)[^()]*)*/ + (this(and)that + (this(and)that) + +/[^()]*(?:\((?R)\))*[^()]*/ + (this(and)that + (this(and)that) + +/(?:\((?R)\))*[^()]*/ + (this(and)that + (this(and)that) + ((this)) + +/(?:\((?R)\))|[^()]*/ + (this(and)that + (this(and)that) + (this) + ((this)) + +/a(b)c/PN + abc + +/a(?Pb)c/PN + abc + +/\x{100}/ + +/\x{0000ff}/ + +/^((?Pa1)|(?Pa2)b)/ + +/^((?Pa1)|(?Pa2)b)/J + a1b\CA + a2b\CA + ** Failers + a1b\CZ\CA + +/^(?Pa)(?Pb)/J + ab\CA + +/^(?Pa)(?Pb)|cd/J + ab\CA + cd\CA + +/^(?Pa)(?Pb)|cd(?Pef)(?Pgh)/J + cdefgh\CA + +/^((?Pa1)|(?Pa2)b)/J + a1b\GA + a2b\GA + ** Failers + a1b\GZ\GA + +/^(?Pa)(?Pb)/J + ab\GA + +/^(?Pa)(?Pb)|cd/J + ab\GA + cd\GA + +/^(?Pa)(?Pb)|cd(?Pef)(?Pgh)/J + cdefgh\GA + +/(?J)^((?Pa1)|(?Pa2)b)/ + a1b\CA + a2b\CA + +/^(?Pa) (?J:(?Pb)(?Pc)) (?Pd)/ + +/ In this next test, J is not set at the outer level; consequently it isn't +set in the pattern's options; consequently pcre_get_named_substring() produces +a random value. /x + +/^(?Pa) (?J:(?Pb)(?Pc)) (?Pd)/ + a bc d\CA\CB\CC + +/^(?Pa)?(?(A)a|b)/ + aabc + bc + ** Failers + abc + +/(?:(?(ZZ)a|b)(?PX))+/ + bXaX + +/(?:(?(2y)a|b)(X))+/ + +/(?:(?(ZA)a|b)(?PX))+/ + +/(?:(?(ZZ)a|b)(?(ZZ)a|b)(?PX))+/ + bbXaaX + +/(?:(?(ZZ)a|\(b\))\\(?PX))+/ + (b)\\Xa\\X + +/(?PX|Y))+/ + bXXaYYaY + bXYaXXaX + +/()()()()()()()()()(?:(?(A)(?P=A)a|b)(?PX|Y))+/ + bXXaYYaY + +/\777/ + +/\s*,\s*/S + \x0b,\x0b + \x0c,\x0d + +/^abc/m + xyz\nabc + xyz\nabc\ + xyz\r\nabc\ + xyz\rabc\ + xyz\r\nabc\ + ** Failers + xyz\nabc\ + xyz\r\nabc\ + xyz\nabc\ + xyz\rabc\ + xyz\rabc\ + +/abc$/m + xyzabc + xyzabc\n + xyzabc\npqr + xyzabc\r\ + xyzabc\rpqr\ + xyzabc\r\n\ + xyzabc\r\npqr\ + ** Failers + xyzabc\r + xyzabc\rpqr + xyzabc\r\n + xyzabc\r\npqr + +/^abc/m + xyz\rabcdef + xyz\nabcdef\ + ** Failers + xyz\nabcdef + +/^abc/m + xyz\nabcdef + xyz\rabcdef\ + ** Failers + xyz\rabcdef + +/^abc/m + xyz\r\nabcdef + xyz\rabcdef\ + ** Failers + xyz\rabcdef + +/^abc/m + +/abc/ + xyz\rabc\ + abc + +/.*/ + abc\ndef + abc\rdef + abc\r\ndef + \abc\ndef + \abc\rdef + \abc\r\ndef + \abc\ndef + \abc\rdef + \abc\r\ndef + +/\w+(.)(.)?def/s + abc\ndef + abc\rdef + abc\r\ndef + ++((?:\s|//.*\\n|/[*](?:\\n|.)*?[*]/)*)+ + /* this is a C style comment */\M + +/(?P25[0-5]|2[0-4]\d|[01]?\d?\d)(?:\.(?P>B)){3}/ + +/ End of testinput2 / diff --git a/libs/pcre/testdata/testinput3 b/libs/pcre/testdata/testinput3 new file mode 100644 index 0000000000..e6ac826f77 --- /dev/null +++ b/libs/pcre/testdata/testinput3 @@ -0,0 +1,91 @@ +/^[\w]+/ + *** Failers + École + +/^[\w]+/Lfr_FR + École + +/^[\w]+/ + *** Failers + École + +/^[\W]+/ + École + +/^[\W]+/Lfr_FR + *** Failers + École + +/[\b]/ + \b + *** Failers + a + +/[\b]/Lfr_FR + \b + *** Failers + a + +/^\w+/ + *** Failers + École + +/^\w+/Lfr_FR + École + +/(.+)\b(.+)/ + École + +/(.+)\b(.+)/Lfr_FR + *** Failers + École + +/École/i + École + *** Failers + école + +/École/iLfr_FR + École + école + +/\w/IS + +/\w/ISLfr_FR + +/^[\xc8-\xc9]/iLfr_FR + École + école + +/^[\xc8-\xc9]/Lfr_FR + École + *** Failers + école + +/\W+/Lfr_FR + >>>\xaa<<< + >>>\xba<<< + +/[\W]+/Lfr_FR + >>>\xaa<<< + >>>\xba<<< + +/[^[:alpha:]]+/Lfr_FR + >>>\xaa<<< + >>>\xba<<< + +/\w+/Lfr_FR + >>>\xaa<<< + >>>\xba<<< + +/[\w]+/Lfr_FR + >>>\xaa<<< + >>>\xba<<< + +/[[:alpha:]]+/Lfr_FR + >>>\xaa<<< + >>>\xba<<< + +/[[:alpha:]][[:lower:]][[:upper:]]/DLfr_FR + +/ End of testinput3 / diff --git a/libs/pcre/testdata/testinput4 b/libs/pcre/testdata/testinput4 new file mode 100644 index 0000000000..9ff0fc7a64 --- /dev/null +++ b/libs/pcre/testdata/testinput4 @@ -0,0 +1,523 @@ +/-- Do not use the \x{} construct except with patterns that have the --/ +/-- /8 option set, because PCRE doesn't recognize them as UTF-8 unless --/ +/-- that option is set. However, the latest Perls recognize them always. --/ + +/a.b/8 + acb + a\x7fb + a\x{100}b + *** Failers + a\nb + +/a(.{3})b/8 + a\x{4000}xyb + a\x{4000}\x7fyb + a\x{4000}\x{100}yb + *** Failers + a\x{4000}b + ac\ncb + +/a(.*?)(.)/ + a\xc0\x88b + +/a(.*?)(.)/8 + a\x{100}b + +/a(.*)(.)/ + a\xc0\x88b + +/a(.*)(.)/8 + a\x{100}b + +/a(.)(.)/ + a\xc0\x92bcd + +/a(.)(.)/8 + a\x{240}bcd + +/a(.?)(.)/ + a\xc0\x92bcd + +/a(.?)(.)/8 + a\x{240}bcd + +/a(.??)(.)/ + a\xc0\x92bcd + +/a(.??)(.)/8 + a\x{240}bcd + +/a(.{3})b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + *** Failers + a\x{1234}b + ac\ncb + +/a(.{3,})b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + *** Failers + a\x{1234}b + +/a(.{3,}?)b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + *** Failers + a\x{1234}b + +/a(.{3,5})b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + axbxxbcdefghijb + axxxxxbcdefghijb + *** Failers + a\x{1234}b + axxxxxxbcdefghijb + +/a(.{3,5}?)b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + axbxxbcdefghijb + axxxxxbcdefghijb + *** Failers + a\x{1234}b + axxxxxxbcdefghijb + +/^[a\x{c0}]/8 + *** Failers + \x{100} + +/(?<=aXb)cd/8 + aXbcd + +/(?<=a\x{100}b)cd/8 + a\x{100}bcd + +/(?<=a\x{100000}b)cd/8 + a\x{100000}bcd + +/(?:\x{100}){3}b/8 + \x{100}\x{100}\x{100}b + *** Failers + \x{100}\x{100}b + +/\x{ab}/8 + \x{ab} + \xc2\xab + *** Failers + \x00{ab} + +/(?<=(.))X/8 + WXYZ + \x{256}XYZ + *** Failers + XYZ + +/X(\C{3})/8 + X\x{1234} + +/X(\C{4})/8 + X\x{1234}YZ + +/X\C*/8 + XYZabcdce + +/X\C*?/8 + XYZabcde + +/X\C{3,5}/8 + Xabcdefg + X\x{1234} + X\x{1234}YZ + X\x{1234}\x{512} + X\x{1234}\x{512}YZ + +/X\C{3,5}?/8 + Xabcdefg + X\x{1234} + X\x{1234}YZ + X\x{1234}\x{512} + +/[^a]+/8g + bcd + \x{100}aY\x{256}Z + +/^[^a]{2}/8 + \x{100}bc + +/^[^a]{2,}/8 + \x{100}bcAa + +/^[^a]{2,}?/8 + \x{100}bca + +/[^a]+/8ig + bcd + \x{100}aY\x{256}Z + +/^[^a]{2}/8i + \x{100}bc + +/^[^a]{2,}/8i + \x{100}bcAa + +/^[^a]{2,}?/8i + \x{100}bca + +/\x{100}{0,0}/8 + abcd + +/\x{100}?/8 + abcd + \x{100}\x{100} + +/\x{100}{0,3}/8 + \x{100}\x{100} + \x{100}\x{100}\x{100}\x{100} + +/\x{100}*/8 + abce + \x{100}\x{100}\x{100}\x{100} + +/\x{100}{1,1}/8 + abcd\x{100}\x{100}\x{100}\x{100} + +/\x{100}{1,3}/8 + abcd\x{100}\x{100}\x{100}\x{100} + +/\x{100}+/8 + abcd\x{100}\x{100}\x{100}\x{100} + +/\x{100}{3}/8 + abcd\x{100}\x{100}\x{100}XX + +/\x{100}{3,5}/8 + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + +/\x{100}{3,}/8 + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + +/(?<=a\x{100}{2}b)X/8+ + Xyyya\x{100}\x{100}bXzzz + +/\D*/8 + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/\D*/8 + \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + +/\D/8 + 1X2 + 1\x{100}2 + +/>\S/8 + > >X Y + > >\x{100} Y + +/\d/8 + \x{100}3 + +/\s/8 + \x{100} X + +/\D+/8 + 12abcd34 + *** Failers + 1234 + +/\D{2,3}/8 + 12abcd34 + 12ab34 + *** Failers + 1234 + 12a34 + +/\D{2,3}?/8 + 12abcd34 + 12ab34 + *** Failers + 1234 + 12a34 + +/\d+/8 + 12abcd34 + *** Failers + +/\d{2,3}/8 + 12abcd34 + 1234abcd + *** Failers + 1.4 + +/\d{2,3}?/8 + 12abcd34 + 1234abcd + *** Failers + 1.4 + +/\S+/8 + 12abcd34 + *** Failers + \ \ + +/\S{2,3}/8 + 12abcd34 + 1234abcd + *** Failers + \ \ + +/\S{2,3}?/8 + 12abcd34 + 1234abcd + *** Failers + \ \ + +/>\s+ <34 + *** Failers + +/>\s{2,3} \s{2,3}? \xff< + +/[\xff]/8 + >\x{ff}< + +/[^\xFF]/ + XYZ + +/[^\xff]/8 + XYZ + \x{123} + +/^[ac]*b/8 + xb + +/^[ac\x{100}]*b/8 + xb + +/^[^x]*b/8i + xb + +/^[^x]*b/8 + xb + +/^\d*b/8 + xb + +/(|a)/g8 + catac + a\x{256}a + +/^\x{85}$/8i + \x{85} + +/^ሴ/8 + ሴ + +/^\ሴ/8 + ሴ + +"(?s)(.{1,5})"8 + abcdefg + ab + +/ End of testinput4 / diff --git a/libs/pcre/testdata/testinput5 b/libs/pcre/testdata/testinput5 new file mode 100644 index 0000000000..54643f6516 --- /dev/null +++ b/libs/pcre/testdata/testinput5 @@ -0,0 +1,274 @@ +/\x{100}/8DM + +/\x{1000}/8DM + +/\x{10000}/8DM + +/\x{100000}/8DM + +/\x{1000000}/8DM + +/\x{4000000}/8DM + +/\x{7fffFFFF}/8DM + +/[\x{ff}]/8DM + +/[\x{100}]/8DM + +/\x{ffffffff}/8 + +/\x{100000000}/8 + +/^\x{100}a\x{1234}/8 + \x{100}a\x{1234}bcd + +/\x80/8D + +/\xff/8D + +/\x{0041}\x{2262}\x{0391}\x{002e}/D8 + \x{0041}\x{2262}\x{0391}\x{002e} + +/\x{D55c}\x{ad6d}\x{C5B4}/D8 + \x{D55c}\x{ad6d}\x{C5B4} + +/\x{65e5}\x{672c}\x{8a9e}/D8 + \x{65e5}\x{672c}\x{8a9e} + +/\x{80}/D8 + +/\x{084}/D8 + +/\x{104}/D8 + +/\x{861}/D8 + +/\x{212ab}/D8 + +/.{3,5}X/D8 + \x{212ab}\x{212ab}\x{212ab}\x{861}X + + +/.{3,5}?/D8 + \x{212ab}\x{212ab}\x{212ab}\x{861} + +/-- These tests are here rather than in testinput4 because Perl 5.6 has --/ +/-- some problems with UTF-8 support, in the area of \x{..} where the --/ +/-- value is < 255. It grumbles about invalid UTF-8 strings. --/ + +/^[a\x{c0}]b/8 + \x{c0}b + +/^([a\x{c0}]*?)aa/8 + a\x{c0}aaaa/ + +/^([a\x{c0}]*?)aa/8 + a\x{c0}aaaa/ + a\x{c0}a\x{c0}aaa/ + +/^([a\x{c0}]*)aa/8 + a\x{c0}aaaa/ + a\x{c0}a\x{c0}aaa/ + +/^([a\x{c0}]*)a\x{c0}/8 + a\x{c0}aaaa/ + a\x{c0}a\x{c0}aaa/ + +/-- --/ + +/(?<=\C)X/8 + Should produce an error diagnostic + +/-- This one is here not because it's different to Perl, but because the --/ +/-- way the captured single-byte is displayed. (In Perl it becomes a --/ +/-- character, and you can't tell the difference.) --/ + +/X(\C)(.*)/8 + X\x{1234} + X\nabc + +/^[ab]/8D + bar + *** Failers + c + \x{ff} + \x{100} + +/^[^ab]/8D + c + \x{ff} + \x{100} + *** Failers + aaa + +/[^ab\xC0-\xF0]/8SD + \x{f1} + \x{bf} + \x{100} + \x{1000} + *** Failers + \x{c0} + \x{f0} + +/Ä€{3,4}/8SD + \x{100}\x{100}\x{100}\x{100\x{100} + +/(\x{100}+|x)/8SD + +/(\x{100}*a|x)/8SD + +/(\x{100}{0,2}a|x)/8SD + +/(\x{100}{1,2}a|x)/8SD + +/\x{100}*(\d+|"(?1)")/8 + 1234 + "1234" + \x{100}1234 + "\x{100}1234" + \x{100}\x{100}12ab + \x{100}\x{100}"12" + *** Failers + \x{100}\x{100}abcd + +/\x{100}/8D + +/\x{100}*/8D + +/a\x{100}*/8D + +/ab\x{100}*/8D + +/a\x{100}\x{101}*/8D + +/a\x{100}\x{101}+/8D + +/\x{100}*A/8D + A + +/\x{100}*\d(?R)/8D + +/[^\x{c4}]/D + +/[^\x{c4}]/8D + +/[\x{100}]/8DM + \x{100} + Z\x{100} + \x{100}Z + *** Failers + +/[Z\x{100}]/8DM + Z\x{100} + \x{100} + \x{100}Z + *** Failers + +/[\x{200}-\x{100}]/8 + +/[Ä€-Ä„]/8 + \x{100} + \x{104} + *** Failers + \x{105} + \x{ff} + +/[z-\x{100}]/8D + +/[z\Qa-d]Ä€\E]/8D + \x{100} + Ä€ + +/[\xFF]/D + >\xff< + +/[\xff]/D8 + >\x{ff}< + +/[^\xFF]/D + +/[^\xff]/8D + +/[Ä-Ãœ]/8 + Ö # Matches without Study + \x{d6} + +/[Ä-Ãœ]/8S + Ö <-- Same with Study + \x{d6} + +/[\x{c4}-\x{dc}]/8 + Ö # Matches without Study + \x{d6} + +/[\x{c4}-\x{dc}]/8S + Ö <-- Same with Study + \x{d6} + +/[Ã]/8 + +/Ã/8 + +/ÃÃÃxxx/8 + +/ÃÃÃxxx/8?D + +/abc/8 + Ã] + à + ÃÃà + ÃÃÃ\? + +/anything/8 + \xc0\x80 + \xc1\x8f + \xe0\x9f\x80 + \xf0\x8f\x80\x80 + \xf8\x87\x80\x80\x80 + \xfc\x83\x80\x80\x80\x80 + \xfe\x80\x80\x80\x80\x80 + \xff\x80\x80\x80\x80\x80 + \xc3\x8f + \xe0\xaf\x80 + \xe1\x80\x80 + \xf0\x9f\x80\x80 + \xf1\x8f\x80\x80 + \xf8\x88\x80\x80\x80 + \xf9\x87\x80\x80\x80 + \xfc\x84\x80\x80\x80\x80 + \xfd\x83\x80\x80\x80\x80 + +/\x{100}abc(xyz(?1))/8D + +/[^\x{100}]abc(xyz(?1))/8D + +/[ab\x{100}]abc(xyz(?1))/8D + +/(\x{100}(b(?2)c))?/D8 + +/(\x{100}(b(?2)c)){0,2}/D8 + +/(\x{100}(b(?1)c))?/D8 + +/(\x{100}(b(?1)c)){0,2}/D8 + +/\W/8 + A.B + A\x{100}B + +/\w/8 + \x{100}X + +/a\x{1234}b/P8 + a\x{1234}b + +/^\ሴ/8D + +/\777/I + +/\777/8I + \x{1ff} + \777 + +/ End of testinput5 / diff --git a/libs/pcre/testdata/testinput6 b/libs/pcre/testdata/testinput6 new file mode 100644 index 0000000000..da5b9ca236 --- /dev/null +++ b/libs/pcre/testdata/testinput6 @@ -0,0 +1,750 @@ +/^\pC\pL\pM\pN\pP\pS\pZ3 + *** Failers + xyzabc + xyzabc\>2 + +/x\dy\Dz/ + x9yzz + x0y+z + *** Failers + xyz + xxy0z + +/x\sy\Sz/ + x yzz + x y+z + *** Failers + xyz + xxyyz + +/x\wy\Wz/ + xxy+z + *** Failers + xxy0z + x+y+z + +/x.y/ + x+y + x-y + *** Failers + x\ny + +/x.y/s + x+y + x-y + x\ny + +/(a.b(?s)c.d|x.y)p.q/ + a+bc+dp+q + a+bc\ndp+q + x\nyp+q + *** Failers + a\nbc\ndp+q + a+bc\ndp\nq + x\nyp\nq + +/a\d\z/ + ba0 + *** Failers + ba0\n + ba0\ncd + +/a\d\z/m + ba0 + *** Failers + ba0\n + ba0\ncd + +/a\d\Z/ + ba0 + ba0\n + *** Failers + ba0\ncd + +/a\d\Z/m + ba0 + ba0\n + *** Failers + ba0\ncd + +/a\d$/ + ba0 + ba0\n + *** Failers + ba0\ncd + +/a\d$/m + ba0 + ba0\n + ba0\ncd + *** Failers + +/abc/i + abc + aBc + ABC + +/[^a]/ + abcd + +/ab?\w/ + abz + abbz + azz + +/x{0,3}yz/ + ayzq + axyzq + axxyz + axxxyzq + axxxxyzq + *** Failers + ax + axx + +/x{3}yz/ + axxxyzq + axxxxyzq + *** Failers + ax + axx + ayzq + axyzq + axxyz + +/x{2,3}yz/ + axxyz + axxxyzq + axxxxyzq + *** Failers + ax + axx + ayzq + axyzq + +/[^a]+/ + bac + bcdefax + *** Failers + aaaaa + +/[^a]*/ + bac + bcdefax + *** Failers + aaaaa + +/[^a]{3,5}/ + xyz + awxyza + abcdefa + abcdefghijk + *** Failers + axya + axa + aaaaa + +/\d*/ + 1234b567 + xyz + +/\D*/ + a1234b567 + xyz + +/\d+/ + ab1234c56 + *** Failers + xyz + +/\D+/ + ab123c56 + *** Failers + 789 + +/\d?A/ + 045ABC + ABC + *** Failers + XYZ + +/\D?A/ + ABC + BAC + 9ABC + *** Failers + +/a+/ + aaaa + +/^.*xyz/ + xyz + ggggggggxyz + +/^.+xyz/ + abcdxyz + axyz + *** Failers + xyz + +/^.?xyz/ + xyz + cxyz + +/^\d{2,3}X/ + 12X + 123X + *** Failers + X + 1X + 1234X + +/^[abcd]\d/ + a45 + b93 + c99z + d04 + *** Failers + e45 + abcd + abcd1234 + 1234 + +/^[abcd]*\d/ + a45 + b93 + c99z + d04 + abcd1234 + 1234 + *** Failers + e45 + abcd + +/^[abcd]+\d/ + a45 + b93 + c99z + d04 + abcd1234 + *** Failers + 1234 + e45 + abcd + +/^a+X/ + aX + aaX + +/^[abcd]?\d/ + a45 + b93 + c99z + d04 + 1234 + *** Failers + abcd1234 + e45 + +/^[abcd]{2,3}\d/ + ab45 + bcd93 + *** Failers + 1234 + a36 + abcd1234 + ee45 + +/^(abc)*\d/ + abc45 + abcabcabc45 + 42xyz + *** Failers + +/^(abc)+\d/ + abc45 + abcabcabc45 + *** Failers + 42xyz + +/^(abc)?\d/ + abc45 + 42xyz + *** Failers + abcabcabc45 + +/^(abc){2,3}\d/ + abcabc45 + abcabcabc45 + *** Failers + abcabcabcabc45 + abc45 + 42xyz + +/1(abc|xyz)2(?1)3/ + 1abc2abc3456 + 1abc2xyz3456 + +/^(a*\w|ab)=(a*\w|ab)/ + ab=ab + +/^(a*\w|ab)=(?1)/ + ab=ab + +/^([^()]|\((?1)*\))*$/ + abc + a(b)c + a(b(c))d + *** Failers) + a(b(c)d + +/^>abc>([^()]|\((?1)*\))*abc>123abc>1(2)3abc>(1(2)3)a*)\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa9876 + *** Failers + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/x + <> + + hij> + hij> + def> + + *** Failers + 3 + *** Failers + defabcxyz + +/^abcdef/ + ab\P + abcde\P + abcdef\P + *** Failers + abx\P + +/^a{2,4}\d+z/ + a\P + aa\P + aa2\P + aaa\P + aaa23\P + aaaa12345\P + aa0z\P + aaaa4444444444444z\P + *** Failers + az\P + aaaaa\P + a56\P + +/^abcdef/ + abc\P + def\R + +/(?<=foo)bar/ + xyzfo\P + foob\P\>2 + foobar...\R\P\>4 + xyzfo\P + foobar\>2 + *** Failers + xyzfo\P + obar\R + +/(ab*(cd|ef))+X/ + adfadadaklhlkalkajhlkjahdfasdfasdfladsfjkj\P\Z + lkjhlkjhlkjhlkjhabbbbbbcdaefabbbbbbbefa\P\B\Z + cdabbbbbbbb\P\R\B\Z + efabbbbbbbbbbbbbbbb\P\R\B\Z + bbbbbbbbbbbbcdXyasdfadf\P\R\B\Z + +/(a|b)/SF>testsavedregex +>>aaabxyzpqrrrabbxyyyypqAzz + >aaaabxyzpqrrrabbxyyyypqAzz + >>>>abcxyzpqrrrabbxyyyypqAzz + *** Failers + abxyzpqrrabbxyyyypqAzz + abxyzpqrrrrabbxyyyypqAzz + abxyzpqrrrabxyyyypqAzz + aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz + aaaabcxyzzzzpqrrrabbbxyyypqAzz + aaabcxyzpqrrrabbxyyyypqqqqqqqAzz + +/^(abc){1,2}zz/ + abczz + abcabczz + *** Failers + zz + abcabcabczz + >>abczz + +/^(b+?|a){1,2}?c/ + bc + bbc + bbbc + bac + bbac + aac + abbbbbbbbbbbc + bbbbbbbbbbbac + *** Failers + aaac + abbbbbbbbbbbac + +/^(b+|a){1,2}c/ + bc + bbc + bbbc + bac + bbac + aac + abbbbbbbbbbbc + bbbbbbbbbbbac + *** Failers + aaac + abbbbbbbbbbbac + +/^(b+|a){1,2}?bc/ + bbc + +/^(b*|ba){1,2}?bc/ + babc + bbabc + bababc + *** Failers + bababbc + babababc + +/^(ba|b*){1,2}?bc/ + babc + bbabc + bababc + *** Failers + bababbc + babababc + +/^\ca\cA\c[\c{\c:/ + \x01\x01\e;z + +/^[ab\]cde]/ + athing + bthing + ]thing + cthing + dthing + ething + *** Failers + fthing + [thing + \\thing + +/^[]cde]/ + ]thing + cthing + dthing + ething + *** Failers + athing + fthing + +/^[^ab\]cde]/ + fthing + [thing + \\thing + *** Failers + athing + bthing + ]thing + cthing + dthing + ething + +/^[^]cde]/ + athing + fthing + *** Failers + ]thing + cthing + dthing + ething + +/^\/ + + +/^ÿ/ + ÿ + +/^[0-9]+$/ + 0 + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8 + 9 + 10 + 100 + *** Failers + abc + +/^.*nter/ + enter + inter + uponter + +/^xxx[0-9]+$/ + xxx0 + xxx1234 + *** Failers + xxx + +/^.+[0-9][0-9][0-9]$/ + x123 + xx123 + 123456 + *** Failers + 123 + x1234 + +/^.+?[0-9][0-9][0-9]$/ + x123 + xx123 + 123456 + *** Failers + 123 + x1234 + +/^([^!]+)!(.+)=apquxz\.ixr\.zzz\.ac\.uk$/ + abc!pqr=apquxz.ixr.zzz.ac.uk + *** Failers + !pqr=apquxz.ixr.zzz.ac.uk + abc!=apquxz.ixr.zzz.ac.uk + abc!pqr=apquxz:ixr.zzz.ac.uk + abc!pqr=apquxz.ixr.zzz.ac.ukk + +/:/ + Well, we need a colon: somewhere + *** Fail if we don't + +/([\da-f:]+)$/i + 0abc + abc + fed + E + :: + 5f03:12C0::932e + fed def + Any old stuff + *** Failers + 0zzz + gzzz + fed\x20 + Any old rubbish + +/^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/ + .1.2.3 + A.12.123.0 + *** Failers + .1.2.3333 + 1.2.3 + 1234.2.3 + +/^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/ + 1 IN SOA non-sp1 non-sp2( + 1 IN SOA non-sp1 non-sp2 ( + *** Failers + 1IN SOA non-sp1 non-sp2( + +/^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/ + a. + Z. + 2. + ab-c.pq-r. + sxk.zzz.ac.uk. + x-.y-. + *** Failers + -abc.peq. + +/^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/ + *.a + *.b0-a + *.c3-b.c + *.c-a.b-c + *** Failers + *.0 + *.a- + *.a-b.c- + *.c-a.0-c + +/^(?=ab(de))(abd)(e)/ + abde + +/^(?!(ab)de|x)(abd)(f)/ + abdf + +/^(?=(ab(cd)))(ab)/ + abcd + +/^[\da-f](\.[\da-f])*$/i + a.b.c.d + A.B.C.D + a.b.c.1.2.3.C + +/^\".*\"\s*(;.*)?$/ + \"1234\" + \"abcd\" ; + \"\" ; rhubarb + *** Failers + \"1234\" : things + +/^$/ + \ + *** Failers + +/ ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/x + ab c + *** Failers + abc + ab cde + +/(?x) ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/ + ab c + *** Failers + abc + ab cde + +/^ a\ b[c ]d $/x + a bcd + a b d + *** Failers + abcd + ab d + +/^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/ + abcdefhijklm + +/^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/ + abcdefhijklm + +/^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/ + a+ Z0+\x08\n\x1d\x12 + +/^[.^$|()*+?{,}]+/ + .^\$(*+)|{?,?} + +/^a*\w/ + z + az + aaaz + a + aa + aaaa + a+ + aa+ + +/^a*?\w/ + z + az + aaaz + a + aa + aaaa + a+ + aa+ + +/^a+\w/ + az + aaaz + aa + aaaa + aa+ + +/^a+?\w/ + az + aaaz + aa + aaaa + aa+ + +/^\d{8}\w{2,}/ + 1234567890 + 12345678ab + 12345678__ + *** Failers + 1234567 + +/^[aeiou\d]{4,5}$/ + uoie + 1234 + 12345 + aaaaa + *** Failers + 123456 + +/^[aeiou\d]{4,5}?/ + uoie + 1234 + 12345 + aaaaa + 123456 + +/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/ + From abcd Mon Sep 01 12:33:02 1997 + +/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/ + From abcd Mon Sep 01 12:33:02 1997 + From abcd Mon Sep 1 12:33:02 1997 + *** Failers + From abcd Sep 01 12:33:02 1997 + +/^12.34/s + 12\n34 + 12\r34 + +/\w+(?=\t)/ + the quick brown\t fox + +/foo(?!bar)(.*)/ + foobar is foolish see? + +/(?:(?!foo)...|^.{0,2})bar(.*)/ + foobar crowbar etc + barrel + 2barrel + A barrel + +/^(\D*)(?=\d)(?!123)/ + abc456 + *** Failers + abc123 + +/^1234(?# test newlines + inside)/ + 1234 + +/^1234 #comment in extended re + /x + 1234 + +/#rhubarb + abcd/x + abcd + +/^abcd#rhubarb/x + abcd + +/(?!^)abc/ + the abc + *** Failers + abc + +/(?=^)abc/ + abc + *** Failers + the abc + +/^[ab]{1,3}(ab*|b)/ + aabbbbb + +/^[ab]{1,3}?(ab*|b)/ + aabbbbb + +/^[ab]{1,3}?(ab*?|b)/ + aabbbbb + +/^[ab]{1,3}(ab*?|b)/ + aabbbbb + +/ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # optional leading comment +(?: (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # initial word +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) )* # further okay, if led by a period +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +# address +| # or +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # one word, optionally followed by.... +(?: +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] | # atom and space parts, or... +\( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) | # comments, or... + +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +# quoted strings +)* +< (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # leading < +(?: @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* + +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* , (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +)* # further okay, if led by comma +: # closing colon +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* )? # optional route +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # initial word +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) )* # further okay, if led by a period +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +# address spec +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* > # trailing > +# name and address +) (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # optional trailing comment +/x + Alan Other + + user\@dom.ain + \"A. Other\" (a comment) + A. Other (a comment) + \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay + A missing angle @,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# additional words +)* +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +# address +| # or +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +# leading word +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # "normal" atoms and or spaces +(?: +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +| +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +) # "special" comment or quoted string +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # more "normal" +)* +< +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# < +(?: +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +(?: , +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +)* # additional domains +: +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)? # optional route +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# additional words +)* +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +# address spec +> # > +# name and address +) +/x + Alan Other + + user\@dom.ain + \"A. Other\" (a comment) + A. Other (a comment) + \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay + A missing angle ]{0,})>]{0,})>([\d]{0,}\.)(.*)((
([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is + 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide + +/a[^a]b/ + acb + a\nb + +/a.b/ + acb + *** Failers + a\nb + +/a[^a]b/s + acb + a\nb + +/a.b/s + acb + a\nb + +/^(b+?|a){1,2}?c/ + bac + bbac + bbbac + bbbbac + bbbbbac + +/^(b+|a){1,2}?c/ + bac + bbac + bbbac + bbbbac + bbbbbac + +/(?!\A)x/m + x\nb\n + a\bx\n + +/\x0{ab}/ + \0{ab} + +/(A|B)*?CD/ + CD + +/(A|B)*CD/ + CD + +/(?.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/ + +"(?>.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo + +/(?>(\.\d\d[1-9]?))\d+/ + 1.230003938 + 1.875000282 + *** Failers + 1.235 + +/^((?>\w+)|(?>\s+))*$/ + now is the time for all good men to come to the aid of the party + *** Failers + this is not a line with only words and spaces! + +/(\d+)(\w)/ + 12345a + 12345+ + +/((?>\d+))(\w)/ + 12345a + *** Failers + 12345+ + +/(?>a+)b/ + aaab + +/((?>a+)b)/ + aaab + +/(?>(a+))b/ + aaab + +/(?>b)+/ + aaabbbccc + +/(?>a+|b+|c+)*c/ + aaabbbbccccd + +/(a+|b+|c+)*c/ + aaabbbbccccd + +/((?>[^()]+)|\([^()]*\))+/ + ((abc(ade)ufh()()x + +/\(((?>[^()]+)|\([^()]+\))+\)/ + (abc) + (abc(def)xyz) + *** Failers + ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/a(?-i)b/i + ab + Ab + *** Failers + aB + AB + +/(a (?x)b c)d e/ + a bcd e + *** Failers + a b cd e + abcd e + a bcde + +/(a b(?x)c d (?-x)e f)/ + a bcde f + *** Failers + abcdef + +/(a(?i)b)c/ + abc + aBc + *** Failers + abC + aBC + Abc + ABc + ABC + AbC + +/a(?i:b)c/ + abc + aBc + *** Failers + ABC + abC + aBC + +/a(?i:b)*c/ + aBc + aBBc + *** Failers + aBC + aBBC + +/a(?=b(?i)c)\w\wd/ + abcd + abCd + *** Failers + aBCd + abcD + +/(?s-i:more.*than).*million/i + more than million + more than MILLION + more \n than Million + *** Failers + MORE THAN MILLION + more \n than \n million + +/(?:(?s-i)more.*than).*million/i + more than million + more than MILLION + more \n than Million + *** Failers + MORE THAN MILLION + more \n than \n million + +/(?>a(?i)b+)+c/ + abc + aBbc + aBBc + *** Failers + Abc + abAb + abbC + +/(?=a(?i)b)\w\wc/ + abc + aBc + *** Failers + Ab + abC + aBC + +/(?<=a(?i)b)(\w\w)c/ + abxxc + aBxxc + *** Failers + Abxxc + ABxxc + abxxC + +/^(?(?=abc)\w{3}:|\d\d)$/ + abc: + 12 + *** Failers + 123 + xyz + +/^(?(?!abc)\d\d|\w{3}:)$/ + abc: + 12 + *** Failers + 123 + xyz + +/(?(?<=foo)bar|cat)/ + foobar + cat + fcat + focat + *** Failers + foocat + +/(?(?a*)*/ + a + aa + aaaa + +/(abc|)+/ + abc + abcabc + abcabcabc + xyz + +/([a]*)*/ + a + aaaaa + +/([ab]*)*/ + a + b + ababab + aaaabcde + bbbb + +/([^a]*)*/ + b + bbbb + aaa + +/([^ab]*)*/ + cccc + abab + +/([a]*?)*/ + a + aaaa + +/([ab]*?)*/ + a + b + abab + baba + +/([^a]*?)*/ + b + bbbb + aaa + +/([^ab]*?)*/ + c + cccc + baba + +/(?>a*)*/ + a + aaabcde + +/((?>a*))*/ + aaaaa + aabbaa + +/((?>a*?))*/ + aaaaa + aabbaa + +/(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /x + 12-sep-98 + 12-09-98 + *** Failers + sep-12-98 + +/(?i:saturday|sunday)/ + saturday + sunday + Saturday + Sunday + SATURDAY + SUNDAY + SunDay + +/(a(?i)bc|BB)x/ + abcx + aBCx + bbx + BBx + *** Failers + abcX + aBCX + bbX + BBX + +/^([ab](?i)[cd]|[ef])/ + ac + aC + bD + elephant + Europe + frog + France + *** Failers + Africa + +/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/ + ab + aBd + xy + xY + zebra + Zambesi + *** Failers + aCD + XY + +/(?<=foo\n)^bar/m + foo\nbar + *** Failers + bar + baz\nbar + +/(?<=(?]&/ + <&OUT + +/(?:(f)(o)(o)|(b)(a)(r))*/ + foobar + +/(?<=a)b/ + ab + *** Failers + cb + b + +/(?a+)ab/ + +/(?>a+)b/ + aaab + +/([[:]+)/ + a:[b]: + +/([[=]+)/ + a=[b]= + +/([[.]+)/ + a.[b]. + +/((?>a+)b)/ + aaab + +/(?>(a+))b/ + aaab + +/((?>[^()]+)|\([^()]*\))+/ + ((abc(ade)ufh()()x + +/a\Z/ + *** Failers + aaab + a\nb\n + +/b\Z/ + a\nb\n + +/b\z/ + +/b\Z/ + a\nb + +/b\z/ + a\nb + *** Failers + +/(?>.*)(?<=(abcd|wxyz))/ + alphabetabcd + endingwxyz + *** Failers + a rather long string that doesn't end with one of them + +/word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark otherword + word cat dog elephant mussel cow horse canary baboon snake shark + +/word (?>[a-zA-Z0-9]+ ){0,30}otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope + +/(?<=\d{3}(?!999))foo/ + 999foo + 123999foo + *** Failers + 123abcfoo + +/(?<=(?!...999)\d{3})foo/ + 999foo + 123999foo + *** Failers + 123abcfoo + +/(?<=\d{3}(?!999)...)foo/ + 123abcfoo + 123456foo + *** Failers + 123999foo + +/(?<=\d{3}...)(?Z)+|A)*/ + ZABCDEFG + +/((?>)+|A)*/ + ZABCDEFG + +/a*/g + abbab + +/^[a-\d]/ + abcde + -things + 0digit + *** Failers + bcdef + +/^[\d-a]/ + abcde + -things + 0digit + *** Failers + bcdef + +/[[:space:]]+/ + > \x09\x0a\x0c\x0d\x0b< + +/[[:blank:]]+/ + > \x09\x0a\x0c\x0d\x0b< + +/[\s]+/ + > \x09\x0a\x0c\x0d\x0b< + +/\s+/ + > \x09\x0a\x0c\x0d\x0b< + +/a b/x + ab + +/(?!\A)x/m + a\nxb\n + +/(?!^)x/m + a\nxb\n + +/abc\Qabc\Eabc/ + abcabcabc + +/abc\Q(*+|\Eabc/ + abc(*+|abc + +/ abc\Q abc\Eabc/x + abc abcabc + *** Failers + abcabcabc + +/abc#comment + \Q#not comment + literal\E/x + abc#not comment\n literal + +/abc#comment + \Q#not comment + literal/x + abc#not comment\n literal + +/abc#comment + \Q#not comment + literal\E #more comment + /x + abc#not comment\n literal + +/abc#comment + \Q#not comment + literal\E #more comment/x + abc#not comment\n literal + +/\Qabc\$xyz\E/ + abc\\\$xyz + +/\Qabc\E\$\Qxyz\E/ + abc\$xyz + +/\Gabc/ + abc + *** Failers + xyzabc + +/\Gabc./g + abc1abc2xyzabc3 + +/abc./g + abc1abc2xyzabc3 + +/a(?x: b c )d/ + XabcdY + *** Failers + Xa b c d Y + +/((?x)x y z | a b c)/ + XabcY + AxyzB + +/(?i)AB(?-i)C/ + XabCY + *** Failers + XabcY + +/((?i)AB(?-i)C|D)E/ + abCE + DE + *** Failers + abcE + abCe + dE + De + +/[z\Qa-d]\E]/ + z + a + - + d + ] + *** Failers + b + +/[\z\C]/ + z + C + +/\M/ + M + +/(a+)*b/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/(?i)reg(?:ul(?:[aä]|ae)r|ex)/ + REGular + regulaer + Regex + regulär + +/Åæåä[à-ÿÀ-ß]+/ + Åæåäà + Åæåäÿ + ÅæåäÀ + Åæåäß + +/(?<=Z)X./ + \x84XAZXB + +/^(?(2)a|(1)(2))+$/ + 123a + +/(?<=a|bbbb)c/ + ac + bbbbc + +/abc/>testsavedregex +testsavedregex +testsavedregex +testsavedregex + + xyz\r\nabc\ + xyz\rabc\ + xyz\r\nabc\ + ** Failers + xyz\nabc\ + xyz\r\nabc\ + xyz\nabc\ + xyz\rabc\ + xyz\rabc\ + +/abc$/m + xyzabc + xyzabc\n + xyzabc\npqr + xyzabc\r\ + xyzabc\rpqr\ + xyzabc\r\n\ + xyzabc\r\npqr\ + ** Failers + xyzabc\r + xyzabc\rpqr + xyzabc\r\n + xyzabc\r\npqr + +/^abc/m + xyz\rabcdef + xyz\nabcdef\ + ** Failers + xyz\nabcdef + +/^abc/m + xyz\nabcdef + xyz\rabcdef\ + ** Failers + xyz\rabcdef + +/^abc/m + xyz\r\nabcdef + xyz\rabcdef\ + ** Failers + xyz\rabcdef + +/.*/ + abc\ndef + abc\rdef + abc\r\ndef + \abc\ndef + \abc\rdef + \abc\r\ndef + \abc\ndef + \abc\rdef + \abc\r\ndef + +/\w+(.)(.)?def/s + abc\ndef + abc\rdef + abc\r\ndef + +/ End of testinput7 / diff --git a/libs/pcre/testdata/testinput8 b/libs/pcre/testdata/testinput8 new file mode 100644 index 0000000000..36db2433e4 --- /dev/null +++ b/libs/pcre/testdata/testinput8 @@ -0,0 +1,540 @@ +/-- Do not use the \x{} construct except with patterns that have the --/ +/-- /8 option set, because PCRE doesn't recognize them as UTF-8 unless --/ +/-- that option is set. However, the latest Perls recognize them always. --/ + +/\x{100}ab/8 + \x{100}ab + +/a\x{100}*b/8 + ab + a\x{100}b + a\x{100}\x{100}b + +/a\x{100}+b/8 + a\x{100}b + a\x{100}\x{100}b + *** Failers + ab + +/\bX/8 + Xoanon + +Xoanon + \x{300}Xoanon + *** Failers + YXoanon + +/\BX/8 + YXoanon + *** Failers + Xoanon + +Xoanon + \x{300}Xoanon + +/X\b/8 + X+oanon + ZX\x{300}oanon + FAX + *** Failers + Xoanon + +/X\B/8 + Xoanon + *** Failers + X+oanon + ZX\x{300}oanon + FAX + +/[^a]/8 + abcd + a\x{100} + +/^[abc\x{123}\x{400}-\x{402}]{2,3}\d/8 + ab99 + \x{123}\x{123}45 + \x{400}\x{401}\x{402}6 + *** Failers + d99 + \x{123}\x{122}4 + \x{400}\x{403}6 + \x{400}\x{401}\x{402}\x{402}6 + +/abc/8 + Ã] + à + ÃÃà + ÃÃÃ\? + +/a.b/8 + acb + a\x7fb + a\x{100}b + *** Failers + a\nb + +/a(.{3})b/8 + a\x{4000}xyb + a\x{4000}\x7fyb + a\x{4000}\x{100}yb + *** Failers + a\x{4000}b + ac\ncb + +/a(.*?)(.)/ + a\xc0\x88b + +/a(.*?)(.)/8 + a\x{100}b + +/a(.*)(.)/ + a\xc0\x88b + +/a(.*)(.)/8 + a\x{100}b + +/a(.)(.)/ + a\xc0\x92bcd + +/a(.)(.)/8 + a\x{240}bcd + +/a(.?)(.)/ + a\xc0\x92bcd + +/a(.?)(.)/8 + a\x{240}bcd + +/a(.??)(.)/ + a\xc0\x92bcd + +/a(.??)(.)/8 + a\x{240}bcd + +/a(.{3})b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + *** Failers + a\x{1234}b + ac\ncb + +/a(.{3,})b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + *** Failers + a\x{1234}b + +/a(.{3,}?)b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + *** Failers + a\x{1234}b + +/a(.{3,5})b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + axbxxbcdefghijb + axxxxxbcdefghijb + *** Failers + a\x{1234}b + axxxxxxbcdefghijb + +/a(.{3,5}?)b/8 + a\x{1234}xyb + a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + a\x{1234}\x{4321}\x{3412}\x{3421}b + axbxxbcdefghijb + axxxxxbcdefghijb + *** Failers + a\x{1234}b + axxxxxxbcdefghijb + +/^[a\x{c0}]/8 + *** Failers + \x{100} + +/(?<=aXb)cd/8 + aXbcd + +/(?<=a\x{100}b)cd/8 + a\x{100}bcd + +/(?<=a\x{100000}b)cd/8 + a\x{100000}bcd + +/(?:\x{100}){3}b/8 + \x{100}\x{100}\x{100}b + *** Failers + \x{100}\x{100}b + +/\x{ab}/8 + \x{ab} + \xc2\xab + *** Failers + \x00{ab} + +/(?<=(.))X/8 + WXYZ + \x{256}XYZ + *** Failers + XYZ + +/[^a]+/8g + bcd + \x{100}aY\x{256}Z + +/^[^a]{2}/8 + \x{100}bc + +/^[^a]{2,}/8 + \x{100}bcAa + +/^[^a]{2,}?/8 + \x{100}bca + +/[^a]+/8ig + bcd + \x{100}aY\x{256}Z + +/^[^a]{2}/8i + \x{100}bc + +/^[^a]{2,}/8i + \x{100}bcAa + +/^[^a]{2,}?/8i + \x{100}bca + +/\x{100}{0,0}/8 + abcd + +/\x{100}?/8 + abcd + \x{100}\x{100} + +/\x{100}{0,3}/8 + \x{100}\x{100} + \x{100}\x{100}\x{100}\x{100} + +/\x{100}*/8 + abce + \x{100}\x{100}\x{100}\x{100} + +/\x{100}{1,1}/8 + abcd\x{100}\x{100}\x{100}\x{100} + +/\x{100}{1,3}/8 + abcd\x{100}\x{100}\x{100}\x{100} + +/\x{100}+/8 + abcd\x{100}\x{100}\x{100}\x{100} + +/\x{100}{3}/8 + abcd\x{100}\x{100}\x{100}XX + +/\x{100}{3,5}/8 + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + +/\x{100}{3,}/8 + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + +/(?<=a\x{100}{2}b)X/8 + Xyyya\x{100}\x{100}bXzzz + +/\D*/8 + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/\D*/8 + \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + +/\D/8 + 1X2 + 1\x{100}2 + +/>\S/8 + > >X Y + > >\x{100} Y + +/\d/8 + \x{100}3 + +/\s/8 + \x{100} X + +/\D+/8 + 12abcd34 + *** Failers + 1234 + +/\D{2,3}/8 + 12abcd34 + 12ab34 + *** Failers + 1234 + 12a34 + +/\D{2,3}?/8 + 12abcd34 + 12ab34 + *** Failers + 1234 + 12a34 + +/\d+/8 + 12abcd34 + *** Failers + +/\d{2,3}/8 + 12abcd34 + 1234abcd + *** Failers + 1.4 + +/\d{2,3}?/8 + 12abcd34 + 1234abcd + *** Failers + 1.4 + +/\S+/8 + 12abcd34 + *** Failers + \ \ + +/\S{2,3}/8 + 12abcd34 + 1234abcd + *** Failers + \ \ + +/\S{2,3}?/8 + 12abcd34 + 1234abcd + *** Failers + \ \ + +/>\s+ <34 + *** Failers + +/>\s{2,3} \s{2,3}? \xff< + +/[\xff]/8 + >\x{ff}< + +/[^\xFF]/ + XYZ + +/[^\xff]/8 + XYZ + \x{123} + +/^[ac]*b/8 + xb + +/^[ac\x{100}]*b/8 + xb + +/^[^x]*b/8i + xb + +/^[^x]*b/8 + xb + +/^\d*b/8 + xb + +/(|a)/g8 + catac + a\x{256}a + +/^\x{85}$/8i + \x{85} + +/ End of testinput 8 / diff --git a/libs/pcre/testdata/testinput9 b/libs/pcre/testdata/testinput9 new file mode 100644 index 0000000000..23d3d3e434 --- /dev/null +++ b/libs/pcre/testdata/testinput9 @@ -0,0 +1,816 @@ +/\pL\P{Nd}/8 + AB + *** Failers + A0 + 00 + +/\X./8 + AB + A\x{300}BC + A\x{300}\x{301}\x{302}BC + *** Failers + \x{300} + +/\X\X/8 + ABC + A\x{300}B\x{300}\x{301}C + A\x{300}\x{301}\x{302}BC + *** Failers + \x{300} + +/^\pL+/8 + abcd + a + *** Failers + +/^\PL+/8 + 1234 + = + *** Failers + abcd + +/^\X+/8 + abcdA\x{300}\x{301}\x{302} + A\x{300}\x{301}\x{302} + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302} + a + *** Failers + \x{300}\x{301}\x{302} + +/\X?abc/8 + abc + A\x{300}abc + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + \x{300}abc + *** Failers + +/^\X?abc/8 + abc + A\x{300}abc + *** Failers + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + \x{300}abc + +/\X*abc/8 + abc + A\x{300}abc + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + \x{300}abc + *** Failers + +/^\X*abc/8 + abc + A\x{300}abc + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + *** Failers + \x{300}abc + +/^\pL?=./8 + A=b + =c + *** Failers + 1=2 + AAAA=b + +/^\pL*=./8 + AAAA=b + =c + *** Failers + 1=2 + +/^\X{2,3}X/8 + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + *** Failers + X + A\x{300}\x{301}\x{302}X + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + +/^\pC\pL\pM\pN\pP\pS\pZ>>aaabxyzpqrrrabbxyyyypqAzz + 0: aaabxyzpqrrrabbxyyyypqAzz + >aaaabxyzpqrrrabbxyyyypqAzz + 0: aaaabxyzpqrrrabbxyyyypqAzz + >>>>abcxyzpqrrrabbxyyyypqAzz + 0: abcxyzpqrrrabbxyyyypqAzz + *** Failers +No match + abxyzpqrrabbxyyyypqAzz +No match + abxyzpqrrrrabbxyyyypqAzz +No match + abxyzpqrrrabxyyyypqAzz +No match + aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz +No match + aaaabcxyzzzzpqrrrabbbxyyypqAzz +No match + aaabcxyzpqrrrabbxyyyypqqqqqqqAzz +No match + +/^(abc){1,2}zz/ + abczz + 0: abczz + 1: abc + abcabczz + 0: abcabczz + 1: abc + *** Failers +No match + zz +No match + abcabcabczz +No match + >>abczz +No match + +/^(b+?|a){1,2}?c/ + bc + 0: bc + 1: b + bbc + 0: bbc + 1: b + bbbc + 0: bbbc + 1: bb + bac + 0: bac + 1: a + bbac + 0: bbac + 1: a + aac + 0: aac + 1: a + abbbbbbbbbbbc + 0: abbbbbbbbbbbc + 1: bbbbbbbbbbb + bbbbbbbbbbbac + 0: bbbbbbbbbbbac + 1: a + *** Failers +No match + aaac +No match + abbbbbbbbbbbac +No match + +/^(b+|a){1,2}c/ + bc + 0: bc + 1: b + bbc + 0: bbc + 1: bb + bbbc + 0: bbbc + 1: bbb + bac + 0: bac + 1: a + bbac + 0: bbac + 1: a + aac + 0: aac + 1: a + abbbbbbbbbbbc + 0: abbbbbbbbbbbc + 1: bbbbbbbbbbb + bbbbbbbbbbbac + 0: bbbbbbbbbbbac + 1: a + *** Failers +No match + aaac +No match + abbbbbbbbbbbac +No match + +/^(b+|a){1,2}?bc/ + bbc + 0: bbc + 1: b + +/^(b*|ba){1,2}?bc/ + babc + 0: babc + 1: ba + bbabc + 0: bbabc + 1: ba + bababc + 0: bababc + 1: ba + *** Failers +No match + bababbc +No match + babababc +No match + +/^(ba|b*){1,2}?bc/ + babc + 0: babc + 1: ba + bbabc + 0: bbabc + 1: ba + bababc + 0: bababc + 1: ba + *** Failers +No match + bababbc +No match + babababc +No match + +/^\ca\cA\c[\c{\c:/ + \x01\x01\e;z + 0: \x01\x01\x1b;z + +/^[ab\]cde]/ + athing + 0: a + bthing + 0: b + ]thing + 0: ] + cthing + 0: c + dthing + 0: d + ething + 0: e + *** Failers +No match + fthing +No match + [thing +No match + \\thing +No match + +/^[]cde]/ + ]thing + 0: ] + cthing + 0: c + dthing + 0: d + ething + 0: e + *** Failers +No match + athing +No match + fthing +No match + +/^[^ab\]cde]/ + fthing + 0: f + [thing + 0: [ + \\thing + 0: \ + *** Failers + 0: * + athing +No match + bthing +No match + ]thing +No match + cthing +No match + dthing +No match + ething +No match + +/^[^]cde]/ + athing + 0: a + fthing + 0: f + *** Failers + 0: * + ]thing +No match + cthing +No match + dthing +No match + ething +No match + +/^\/ + + 0: \x81 + +/^ÿ/ + ÿ + 0: \xff + +/^[0-9]+$/ + 0 + 0: 0 + 1 + 0: 1 + 2 + 0: 2 + 3 + 0: 3 + 4 + 0: 4 + 5 + 0: 5 + 6 + 0: 6 + 7 + 0: 7 + 8 + 0: 8 + 9 + 0: 9 + 10 + 0: 10 + 100 + 0: 100 + *** Failers +No match + abc +No match + +/^.*nter/ + enter + 0: enter + inter + 0: inter + uponter + 0: uponter + +/^xxx[0-9]+$/ + xxx0 + 0: xxx0 + xxx1234 + 0: xxx1234 + *** Failers +No match + xxx +No match + +/^.+[0-9][0-9][0-9]$/ + x123 + 0: x123 + xx123 + 0: xx123 + 123456 + 0: 123456 + *** Failers +No match + 123 +No match + x1234 + 0: x1234 + +/^.+?[0-9][0-9][0-9]$/ + x123 + 0: x123 + xx123 + 0: xx123 + 123456 + 0: 123456 + *** Failers +No match + 123 +No match + x1234 + 0: x1234 + +/^([^!]+)!(.+)=apquxz\.ixr\.zzz\.ac\.uk$/ + abc!pqr=apquxz.ixr.zzz.ac.uk + 0: abc!pqr=apquxz.ixr.zzz.ac.uk + 1: abc + 2: pqr + *** Failers +No match + !pqr=apquxz.ixr.zzz.ac.uk +No match + abc!=apquxz.ixr.zzz.ac.uk +No match + abc!pqr=apquxz:ixr.zzz.ac.uk +No match + abc!pqr=apquxz.ixr.zzz.ac.ukk +No match + +/:/ + Well, we need a colon: somewhere + 0: : + *** Fail if we don't +No match + +/([\da-f:]+)$/i + 0abc + 0: 0abc + 1: 0abc + abc + 0: abc + 1: abc + fed + 0: fed + 1: fed + E + 0: E + 1: E + :: + 0: :: + 1: :: + 5f03:12C0::932e + 0: 5f03:12C0::932e + 1: 5f03:12C0::932e + fed def + 0: def + 1: def + Any old stuff + 0: ff + 1: ff + *** Failers +No match + 0zzz +No match + gzzz +No match + fed\x20 +No match + Any old rubbish +No match + +/^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/ + .1.2.3 + 0: .1.2.3 + 1: 1 + 2: 2 + 3: 3 + A.12.123.0 + 0: A.12.123.0 + 1: 12 + 2: 123 + 3: 0 + *** Failers +No match + .1.2.3333 +No match + 1.2.3 +No match + 1234.2.3 +No match + +/^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/ + 1 IN SOA non-sp1 non-sp2( + 0: 1 IN SOA non-sp1 non-sp2( + 1: 1 + 2: non-sp1 + 3: non-sp2 + 1 IN SOA non-sp1 non-sp2 ( + 0: 1 IN SOA non-sp1 non-sp2 ( + 1: 1 + 2: non-sp1 + 3: non-sp2 + *** Failers +No match + 1IN SOA non-sp1 non-sp2( +No match + +/^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/ + a. + 0: a. + Z. + 0: Z. + 2. + 0: 2. + ab-c.pq-r. + 0: ab-c.pq-r. + 1: .pq-r + sxk.zzz.ac.uk. + 0: sxk.zzz.ac.uk. + 1: .uk + x-.y-. + 0: x-.y-. + 1: .y- + *** Failers +No match + -abc.peq. +No match + +/^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/ + *.a + 0: *.a + *.b0-a + 0: *.b0-a + 1: 0-a + *.c3-b.c + 0: *.c3-b.c + 1: 3-b + 2: .c + *.c-a.b-c + 0: *.c-a.b-c + 1: -a + 2: .b-c + 3: -c + *** Failers +No match + *.0 +No match + *.a- +No match + *.a-b.c- +No match + *.c-a.0-c +No match + +/^(?=ab(de))(abd)(e)/ + abde + 0: abde + 1: de + 2: abd + 3: e + +/^(?!(ab)de|x)(abd)(f)/ + abdf + 0: abdf + 1: + 2: abd + 3: f + +/^(?=(ab(cd)))(ab)/ + abcd + 0: ab + 1: abcd + 2: cd + 3: ab + +/^[\da-f](\.[\da-f])*$/i + a.b.c.d + 0: a.b.c.d + 1: .d + A.B.C.D + 0: A.B.C.D + 1: .D + a.b.c.1.2.3.C + 0: a.b.c.1.2.3.C + 1: .C + +/^\".*\"\s*(;.*)?$/ + \"1234\" + 0: "1234" + \"abcd\" ; + 0: "abcd" ; + 1: ; + \"\" ; rhubarb + 0: "" ; rhubarb + 1: ; rhubarb + *** Failers +No match + \"1234\" : things +No match + +/^$/ + \ + 0: + *** Failers +No match + +/ ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/x + ab c + 0: ab c + *** Failers +No match + abc +No match + ab cde +No match + +/(?x) ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/ + ab c + 0: ab c + *** Failers +No match + abc +No match + ab cde +No match + +/^ a\ b[c ]d $/x + a bcd + 0: a bcd + a b d + 0: a b d + *** Failers +No match + abcd +No match + ab d +No match + +/^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/ + abcdefhijklm + 0: abcdefhijklm + 1: abc + 2: bc + 3: c + 4: def + 5: ef + 6: f + 7: hij + 8: ij + 9: j +10: klm +11: lm +12: m + +/^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/ + abcdefhijklm + 0: abcdefhijklm + 1: bc + 2: c + 3: ef + 4: f + 5: ij + 6: j + 7: lm + 8: m + +/^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/ + a+ Z0+\x08\n\x1d\x12 + 0: a+ Z0+\x08\x0a\x1d\x12 + +/^[.^$|()*+?{,}]+/ + .^\$(*+)|{?,?} + 0: .^$(*+)|{?,?} + +/^a*\w/ + z + 0: z + az + 0: az + aaaz + 0: aaaz + a + 0: a + aa + 0: aa + aaaa + 0: aaaa + a+ + 0: a + aa+ + 0: aa + +/^a*?\w/ + z + 0: z + az + 0: a + aaaz + 0: a + a + 0: a + aa + 0: a + aaaa + 0: a + a+ + 0: a + aa+ + 0: a + +/^a+\w/ + az + 0: az + aaaz + 0: aaaz + aa + 0: aa + aaaa + 0: aaaa + aa+ + 0: aa + +/^a+?\w/ + az + 0: az + aaaz + 0: aa + aa + 0: aa + aaaa + 0: aa + aa+ + 0: aa + +/^\d{8}\w{2,}/ + 1234567890 + 0: 1234567890 + 12345678ab + 0: 12345678ab + 12345678__ + 0: 12345678__ + *** Failers +No match + 1234567 +No match + +/^[aeiou\d]{4,5}$/ + uoie + 0: uoie + 1234 + 0: 1234 + 12345 + 0: 12345 + aaaaa + 0: aaaaa + *** Failers +No match + 123456 +No match + +/^[aeiou\d]{4,5}?/ + uoie + 0: uoie + 1234 + 0: 1234 + 12345 + 0: 1234 + aaaaa + 0: aaaa + 123456 + 0: 1234 + +/\A(abc|def)=(\1){2,3}\Z/ + abc=abcabc + 0: abc=abcabc + 1: abc + 2: abc + def=defdefdef + 0: def=defdefdef + 1: def + 2: def + *** Failers +No match + abc=defdef +No match + +/^(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\11*(\3\4)\1(?#)2$/ + abcdefghijkcda2 + 0: abcdefghijkcda2 + 1: a + 2: b + 3: c + 4: d + 5: e + 6: f + 7: g + 8: h + 9: i +10: j +11: k +12: cd + abcdefghijkkkkcda2 + 0: abcdefghijkkkkcda2 + 1: a + 2: b + 3: c + 4: d + 5: e + 6: f + 7: g + 8: h + 9: i +10: j +11: k +12: cd + +/(cat(a(ract|tonic)|erpillar)) \1()2(3)/ + cataract cataract23 + 0: cataract cataract23 + 1: cataract + 2: aract + 3: ract + 4: + 5: 3 + catatonic catatonic23 + 0: catatonic catatonic23 + 1: catatonic + 2: atonic + 3: tonic + 4: + 5: 3 + caterpillar caterpillar23 + 0: caterpillar caterpillar23 + 1: caterpillar + 2: erpillar + 3: + 4: + 5: 3 + + +/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/ + From abcd Mon Sep 01 12:33:02 1997 + 0: From abcd Mon Sep 01 12:33 + 1: abcd + +/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/ + From abcd Mon Sep 01 12:33:02 1997 + 0: From abcd Mon Sep 01 12:33 + 1: Sep + From abcd Mon Sep 1 12:33:02 1997 + 0: From abcd Mon Sep 1 12:33 + 1: Sep + *** Failers +No match + From abcd Sep 01 12:33:02 1997 +No match + +/^12.34/s + 12\n34 + 0: 12\x0a34 + 12\r34 + 0: 12\x0d34 + +/\w+(?=\t)/ + the quick brown\t fox + 0: brown + +/foo(?!bar)(.*)/ + foobar is foolish see? + 0: foolish see? + 1: lish see? + +/(?:(?!foo)...|^.{0,2})bar(.*)/ + foobar crowbar etc + 0: rowbar etc + 1: etc + barrel + 0: barrel + 1: rel + 2barrel + 0: 2barrel + 1: rel + A barrel + 0: A barrel + 1: rel + +/^(\D*)(?=\d)(?!123)/ + abc456 + 0: abc + 1: abc + *** Failers +No match + abc123 +No match + +/^1234(?# test newlines + inside)/ + 1234 + 0: 1234 + +/^1234 #comment in extended re + /x + 1234 + 0: 1234 + +/#rhubarb + abcd/x + abcd + 0: abcd + +/^abcd#rhubarb/x + abcd + 0: abcd + +/^(a)\1{2,3}(.)/ + aaab + 0: aaab + 1: a + 2: b + aaaab + 0: aaaab + 1: a + 2: b + aaaaab + 0: aaaaa + 1: a + 2: a + aaaaaab + 0: aaaaa + 1: a + 2: a + +/(?!^)abc/ + the abc + 0: abc + *** Failers +No match + abc +No match + +/(?=^)abc/ + abc + 0: abc + *** Failers +No match + the abc +No match + +/^[ab]{1,3}(ab*|b)/ + aabbbbb + 0: aabb + 1: b + +/^[ab]{1,3}?(ab*|b)/ + aabbbbb + 0: aabbbbb + 1: abbbbb + +/^[ab]{1,3}?(ab*?|b)/ + aabbbbb + 0: aa + 1: a + +/^[ab]{1,3}(ab*?|b)/ + aabbbbb + 0: aabb + 1: b + +/ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # optional leading comment +(?: (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # initial word +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) )* # further okay, if led by a period +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +# address +| # or +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # one word, optionally followed by.... +(?: +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] | # atom and space parts, or... +\( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) | # comments, or... + +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +# quoted strings +)* +< (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # leading < +(?: @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* + +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* , (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +)* # further okay, if led by comma +: # closing colon +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* )? # optional route +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # initial word +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) )* # further okay, if led by a period +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +# address spec +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* > # trailing > +# name and address +) (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # optional trailing comment +/x + Alan Other + 0: Alan Other + + 0: user@dom.ain + user\@dom.ain + 0: user@dom.ain + \"A. Other\" (a comment) + 0: "A. Other" (a comment) + A. Other (a comment) + 0: Other (a comment) + \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay + 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay + A missing angle @,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# additional words +)* +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +# address +| # or +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +# leading word +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # "normal" atoms and or spaces +(?: +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +| +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +) # "special" comment or quoted string +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # more "normal" +)* +< +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# < +(?: +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +(?: , +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +)* # additional domains +: +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)? # optional route +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# additional words +)* +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +# address spec +> # > +# name and address +) +/x + Alan Other + 0: Alan Other + + 0: user@dom.ain + user\@dom.ain + 0: user@dom.ain + \"A. Other\" (a comment) + 0: "A. Other" + A. Other (a comment) + 0: Other + \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay + 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay + A missing angle ?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff + +/P[^*]TAIRE[^*]{1,6}?LL/ + xxxxxxxxxxxPSTAIREISLLxxxxxxxxx + 0: PSTAIREISLL + +/P[^*]TAIRE[^*]{1,}?LL/ + xxxxxxxxxxxPSTAIREISLLxxxxxxxxx + 0: PSTAIREISLL + +/(\.\d\d[1-9]?)\d+/ + 1.230003938 + 0: .230003938 + 1: .23 + 1.875000282 + 0: .875000282 + 1: .875 + 1.235 + 0: .235 + 1: .23 + +/(\.\d\d((?=0)|\d(?=\d)))/ + 1.230003938 + 0: .23 + 1: .23 + 2: + 1.875000282 + 0: .875 + 1: .875 + 2: 5 + *** Failers +No match + 1.235 +No match + +/a(?)b/ + ab + 0: ab + +/\b(foo)\s+(\w+)/i + Food is on the foo table + 0: foo table + 1: foo + 2: table + +/foo(.*)bar/ + The food is under the bar in the barn. + 0: food is under the bar in the bar + 1: d is under the bar in the + +/foo(.*?)bar/ + The food is under the bar in the barn. + 0: food is under the bar + 1: d is under the + +/(.*)(\d*)/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: 53147 + 2: + +/(.*)(\d+)/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: 5314 + 2: 7 + +/(.*?)(\d*)/ + I have 2 numbers: 53147 + 0: + 1: + 2: + +/(.*?)(\d+)/ + I have 2 numbers: 53147 + 0: I have 2 + 1: I have + 2: 2 + +/(.*)(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: 5314 + 2: 7 + +/(.*?)(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: + 2: 53147 + +/(.*)\b(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: + 2: 53147 + +/(.*\D)(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: + 2: 53147 + +/^\D*(?!123)/ + ABC123 + 0: AB + +/^(\D*)(?=\d)(?!123)/ + ABC445 + 0: ABC + 1: ABC + *** Failers +No match + ABC123 +No match + +/^[W-]46]/ + W46]789 + 0: W46] + -46]789 + 0: -46] + *** Failers +No match + Wall +No match + Zebra +No match + 42 +No match + [abcd] +No match + ]abcd[ +No match + +/^[W-\]46]/ + W46]789 + 0: W + Wall + 0: W + Zebra + 0: Z + Xylophone + 0: X + 42 + 0: 4 + [abcd] + 0: [ + ]abcd[ + 0: ] + \\backslash + 0: \ + *** Failers +No match + -46]789 +No match + well +No match + +/\d\d\/\d\d\/\d\d\d\d/ + 01/01/2000 + 0: 01/01/2000 + +/word (?:[a-zA-Z0-9]+ ){0,10}otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark otherword + 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword + word cat dog elephant mussel cow horse canary baboon snake shark +No match + +/word (?:[a-zA-Z0-9]+ ){0,300}otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope +No match + +/^(a){0,0}/ + bcd + 0: + abc + 0: + aab + 0: + +/^(a){0,1}/ + bcd + 0: + abc + 0: a + 1: a + aab + 0: a + 1: a + +/^(a){0,2}/ + bcd + 0: + abc + 0: a + 1: a + aab + 0: aa + 1: a + +/^(a){0,3}/ + bcd + 0: + abc + 0: a + 1: a + aab + 0: aa + 1: a + aaa + 0: aaa + 1: a + +/^(a){0,}/ + bcd + 0: + abc + 0: a + 1: a + aab + 0: aa + 1: a + aaa + 0: aaa + 1: a + aaaaaaaa + 0: aaaaaaaa + 1: a + +/^(a){1,1}/ + bcd +No match + abc + 0: a + 1: a + aab + 0: a + 1: a + +/^(a){1,2}/ + bcd +No match + abc + 0: a + 1: a + aab + 0: aa + 1: a + +/^(a){1,3}/ + bcd +No match + abc + 0: a + 1: a + aab + 0: aa + 1: a + aaa + 0: aaa + 1: a + +/^(a){1,}/ + bcd +No match + abc + 0: a + 1: a + aab + 0: aa + 1: a + aaa + 0: aaa + 1: a + aaaaaaaa + 0: aaaaaaaa + 1: a + +/.*\.gif/ + borfle\nbib.gif\nno + 0: bib.gif + +/.{0,}\.gif/ + borfle\nbib.gif\nno + 0: bib.gif + +/.*\.gif/m + borfle\nbib.gif\nno + 0: bib.gif + +/.*\.gif/s + borfle\nbib.gif\nno + 0: borfle\x0abib.gif + +/.*\.gif/ms + borfle\nbib.gif\nno + 0: borfle\x0abib.gif + +/.*$/ + borfle\nbib.gif\nno + 0: no + +/.*$/m + borfle\nbib.gif\nno + 0: borfle + +/.*$/s + borfle\nbib.gif\nno + 0: borfle\x0abib.gif\x0ano + +/.*$/ms + borfle\nbib.gif\nno + 0: borfle\x0abib.gif\x0ano + +/.*$/ + borfle\nbib.gif\nno\n + 0: no + +/.*$/m + borfle\nbib.gif\nno\n + 0: borfle + +/.*$/s + borfle\nbib.gif\nno\n + 0: borfle\x0abib.gif\x0ano\x0a + +/.*$/ms + borfle\nbib.gif\nno\n + 0: borfle\x0abib.gif\x0ano\x0a + +/(.*X|^B)/ + abcde\n1234Xyz + 0: 1234X + 1: 1234X + BarFoo + 0: B + 1: B + *** Failers +No match + abcde\nBar +No match + +/(.*X|^B)/m + abcde\n1234Xyz + 0: 1234X + 1: 1234X + BarFoo + 0: B + 1: B + abcde\nBar + 0: B + 1: B + +/(.*X|^B)/s + abcde\n1234Xyz + 0: abcde\x0a1234X + 1: abcde\x0a1234X + BarFoo + 0: B + 1: B + *** Failers +No match + abcde\nBar +No match + +/(.*X|^B)/ms + abcde\n1234Xyz + 0: abcde\x0a1234X + 1: abcde\x0a1234X + BarFoo + 0: B + 1: B + abcde\nBar + 0: B + 1: B + +/(?s)(.*X|^B)/ + abcde\n1234Xyz + 0: abcde\x0a1234X + 1: abcde\x0a1234X + BarFoo + 0: B + 1: B + *** Failers +No match + abcde\nBar +No match + +/(?s:.*X|^B)/ + abcde\n1234Xyz + 0: abcde\x0a1234X + BarFoo + 0: B + *** Failers +No match + abcde\nBar +No match + +/^.*B/ + **** Failers +No match + abc\nB +No match + +/(?s)^.*B/ + abc\nB + 0: abc\x0aB + +/(?m)^.*B/ + abc\nB + 0: B + +/(?ms)^.*B/ + abc\nB + 0: abc\x0aB + +/(?ms)^B/ + abc\nB + 0: B + +/(?s)B$/ + B\n + 0: B + +/^[0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9]/ + 123456654321 + 0: 123456654321 + +/^\d\d\d\d\d\d\d\d\d\d\d\d/ + 123456654321 + 0: 123456654321 + +/^[\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d]/ + 123456654321 + 0: 123456654321 + +/^[abc]{12}/ + abcabcabcabc + 0: abcabcabcabc + +/^[a-c]{12}/ + abcabcabcabc + 0: abcabcabcabc + +/^(a|b|c){12}/ + abcabcabcabc + 0: abcabcabcabc + 1: c + +/^[abcdefghijklmnopqrstuvwxy0123456789]/ + n + 0: n + *** Failers +No match + z +No match + +/abcde{0,0}/ + abcd + 0: abcd + *** Failers +No match + abce +No match + +/ab[cd]{0,0}e/ + abe + 0: abe + *** Failers +No match + abcde +No match + +/ab(c){0,0}d/ + abd + 0: abd + *** Failers +No match + abcd +No match + +/a(b*)/ + a + 0: a + 1: + ab + 0: ab + 1: b + abbbb + 0: abbbb + 1: bbbb + *** Failers + 0: a + 1: + bbbbb +No match + +/ab\d{0}e/ + abe + 0: abe + *** Failers +No match + ab1e +No match + +/"([^\\"]+|\\.)*"/ + the \"quick\" brown fox + 0: "quick" + 1: quick + \"the \\\"quick\\\" brown fox\" + 0: "the \"quick\" brown fox" + 1: brown fox + +/.*?/g+ + abc + 0: + 0+ abc + 0: a + 0+ bc + 0: + 0+ bc + 0: b + 0+ c + 0: + 0+ c + 0: c + 0+ + 0: + 0+ + +/\b/g+ + abc + 0: + 0+ abc + 0: + 0+ + +/\b/+g + abc + 0: + 0+ abc + 0: + 0+ + +//g + abc + 0: + 0: + 0: + 0: + +/]{0,})>]{0,})>([\d]{0,}\.)(.*)((
([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is + 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide + 0: 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide + 1: BGCOLOR='#DBE9E9' + 2: align=left valign=top + 3: 43. + 4: Word Processor
(N-1286) + 5: + 6: + 7: + 8: align=left valign=top + 9: Lega lstaff.com +10: align=left valign=top +11: CA - Statewide + +/a[^a]b/ + acb + 0: acb + a\nb + 0: a\x0ab + +/a.b/ + acb + 0: acb + *** Failers +No match + a\nb +No match + +/a[^a]b/s + acb + 0: acb + a\nb + 0: a\x0ab + +/a.b/s + acb + 0: acb + a\nb + 0: a\x0ab + +/^(b+?|a){1,2}?c/ + bac + 0: bac + 1: a + bbac + 0: bbac + 1: a + bbbac + 0: bbbac + 1: a + bbbbac + 0: bbbbac + 1: a + bbbbbac + 0: bbbbbac + 1: a + +/^(b+|a){1,2}?c/ + bac + 0: bac + 1: a + bbac + 0: bbac + 1: a + bbbac + 0: bbbac + 1: a + bbbbac + 0: bbbbac + 1: a + bbbbbac + 0: bbbbbac + 1: a + +/(?!\A)x/m + x\nb\n +No match + a\bx\n + 0: x + +/\x0{ab}/ + \0{ab} + 0: \x00{ab} + +/(A|B)*?CD/ + CD + 0: CD + +/(A|B)*CD/ + CD + 0: CD + +/(AB)*?\1/ + ABABAB + 0: ABAB + 1: AB + +/(AB)*\1/ + ABABAB + 0: ABABAB + 1: AB + +/(?.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/ +No match + +"(?>.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo + 0: /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo + +/(?>(\.\d\d[1-9]?))\d+/ + 1.230003938 + 0: .230003938 + 1: .23 + 1.875000282 + 0: .875000282 + 1: .875 + *** Failers +No match + 1.235 +No match + +/^((?>\w+)|(?>\s+))*$/ + now is the time for all good men to come to the aid of the party + 0: now is the time for all good men to come to the aid of the party + 1: party + *** Failers +No match + this is not a line with only words and spaces! +No match + +/(\d+)(\w)/ + 12345a + 0: 12345a + 1: 12345 + 2: a + 12345+ + 0: 12345 + 1: 1234 + 2: 5 + +/((?>\d+))(\w)/ + 12345a + 0: 12345a + 1: 12345 + 2: a + *** Failers +No match + 12345+ +No match + +/(?>a+)b/ + aaab + 0: aaab + +/((?>a+)b)/ + aaab + 0: aaab + 1: aaab + +/(?>(a+))b/ + aaab + 0: aaab + 1: aaa + +/(?>b)+/ + aaabbbccc + 0: bbb + +/(?>a+|b+|c+)*c/ + aaabbbbccccd + 0: aaabbbbc + +/((?>[^()]+)|\([^()]*\))+/ + ((abc(ade)ufh()()x + 0: abc(ade)ufh()()x + 1: x + +/\(((?>[^()]+)|\([^()]+\))+\)/ + (abc) + 0: (abc) + 1: abc + (abc(def)xyz) + 0: (abc(def)xyz) + 1: xyz + *** Failers +No match + ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + +/a(?-i)b/i + ab + 0: ab + Ab + 0: Ab + *** Failers +No match + aB +No match + AB +No match + +/(a (?x)b c)d e/ + a bcd e + 0: a bcd e + 1: a bc + *** Failers +No match + a b cd e +No match + abcd e +No match + a bcde +No match + +/(a b(?x)c d (?-x)e f)/ + a bcde f + 0: a bcde f + 1: a bcde f + *** Failers +No match + abcdef +No match + +/(a(?i)b)c/ + abc + 0: abc + 1: ab + aBc + 0: aBc + 1: aB + *** Failers +No match + abC +No match + aBC +No match + Abc +No match + ABc +No match + ABC +No match + AbC +No match + +/a(?i:b)c/ + abc + 0: abc + aBc + 0: aBc + *** Failers +No match + ABC +No match + abC +No match + aBC +No match + +/a(?i:b)*c/ + aBc + 0: aBc + aBBc + 0: aBBc + *** Failers +No match + aBC +No match + aBBC +No match + +/a(?=b(?i)c)\w\wd/ + abcd + 0: abcd + abCd + 0: abCd + *** Failers +No match + aBCd +No match + abcD +No match + +/(?s-i:more.*than).*million/i + more than million + 0: more than million + more than MILLION + 0: more than MILLION + more \n than Million + 0: more \x0a than Million + *** Failers +No match + MORE THAN MILLION +No match + more \n than \n million +No match + +/(?:(?s-i)more.*than).*million/i + more than million + 0: more than million + more than MILLION + 0: more than MILLION + more \n than Million + 0: more \x0a than Million + *** Failers +No match + MORE THAN MILLION +No match + more \n than \n million +No match + +/(?>a(?i)b+)+c/ + abc + 0: abc + aBbc + 0: aBbc + aBBc + 0: aBBc + *** Failers +No match + Abc +No match + abAb +No match + abbC +No match + +/(?=a(?i)b)\w\wc/ + abc + 0: abc + aBc + 0: aBc + *** Failers +No match + Ab +No match + abC +No match + aBC +No match + +/(?<=a(?i)b)(\w\w)c/ + abxxc + 0: xxc + 1: xx + aBxxc + 0: xxc + 1: xx + *** Failers +No match + Abxxc +No match + ABxxc +No match + abxxC +No match + +/(?:(a)|b)(?(1)A|B)/ + aA + 0: aA + 1: a + bB + 0: bB + *** Failers +No match + aB +No match + bA +No match + +/^(a)?(?(1)a|b)+$/ + aa + 0: aa + 1: a + b + 0: b + bb + 0: bb + *** Failers +No match + ab +No match + +/^(?(?=abc)\w{3}:|\d\d)$/ + abc: + 0: abc: + 12 + 0: 12 + *** Failers +No match + 123 +No match + xyz +No match + +/^(?(?!abc)\d\d|\w{3}:)$/ + abc: + 0: abc: + 12 + 0: 12 + *** Failers +No match + 123 +No match + xyz +No match + +/(?(?<=foo)bar|cat)/ + foobar + 0: bar + cat + 0: cat + fcat + 0: cat + focat + 0: cat + *** Failers +No match + foocat +No match + +/(?(?a*)*/ + a + 0: a + aa + 0: aa + aaaa + 0: aaaa + +/(abc|)+/ + abc + 0: abc + 1: + abcabc + 0: abcabc + 1: + abcabcabc + 0: abcabcabc + 1: + xyz + 0: + 1: + +/([a]*)*/ + a + 0: a + 1: + aaaaa + 0: aaaaa + 1: + +/([ab]*)*/ + a + 0: a + 1: + b + 0: b + 1: + ababab + 0: ababab + 1: + aaaabcde + 0: aaaab + 1: + bbbb + 0: bbbb + 1: + +/([^a]*)*/ + b + 0: b + 1: + bbbb + 0: bbbb + 1: + aaa + 0: + 1: + +/([^ab]*)*/ + cccc + 0: cccc + 1: + abab + 0: + 1: + +/([a]*?)*/ + a + 0: + 1: + aaaa + 0: + 1: + +/([ab]*?)*/ + a + 0: + 1: + b + 0: + 1: + abab + 0: + 1: + baba + 0: + 1: + +/([^a]*?)*/ + b + 0: + 1: + bbbb + 0: + 1: + aaa + 0: + 1: + +/([^ab]*?)*/ + c + 0: + 1: + cccc + 0: + 1: + baba + 0: + 1: + +/(?>a*)*/ + a + 0: a + aaabcde + 0: aaa + +/((?>a*))*/ + aaaaa + 0: aaaaa + 1: + aabbaa + 0: aa + 1: + +/((?>a*?))*/ + aaaaa + 0: + 1: + aabbaa + 0: + 1: + +/(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /x + 12-sep-98 + 0: 12-sep-98 + 12-09-98 + 0: 12-09-98 + *** Failers +No match + sep-12-98 +No match + +/(?<=(foo))bar\1/ + foobarfoo + 0: barfoo + 1: foo + foobarfootling + 0: barfoo + 1: foo + *** Failers +No match + foobar +No match + barfoo +No match + +/(?i:saturday|sunday)/ + saturday + 0: saturday + sunday + 0: sunday + Saturday + 0: Saturday + Sunday + 0: Sunday + SATURDAY + 0: SATURDAY + SUNDAY + 0: SUNDAY + SunDay + 0: SunDay + +/(a(?i)bc|BB)x/ + abcx + 0: abcx + 1: abc + aBCx + 0: aBCx + 1: aBC + bbx + 0: bbx + 1: bb + BBx + 0: BBx + 1: BB + *** Failers +No match + abcX +No match + aBCX +No match + bbX +No match + BBX +No match + +/^([ab](?i)[cd]|[ef])/ + ac + 0: ac + 1: ac + aC + 0: aC + 1: aC + bD + 0: bD + 1: bD + elephant + 0: e + 1: e + Europe + 0: E + 1: E + frog + 0: f + 1: f + France + 0: F + 1: F + *** Failers +No match + Africa +No match + +/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/ + ab + 0: ab + 1: ab + aBd + 0: aBd + 1: aBd + xy + 0: xy + 1: xy + xY + 0: xY + 1: xY + zebra + 0: z + 1: z + Zambesi + 0: Z + 1: Z + *** Failers +No match + aCD +No match + XY +No match + +/(?<=foo\n)^bar/m + foo\nbar + 0: bar + *** Failers +No match + bar +No match + baz\nbar +No match + +/(?<=(?]&/ + <&OUT + 0: <& + +/^(a\1?){4}$/ + aaaaaaaaaa + 0: aaaaaaaaaa + 1: aaaa + *** Failers +No match + AB +No match + aaaaaaaaa +No match + aaaaaaaaaaa +No match + +/^(a(?(1)\1)){4}$/ + aaaaaaaaaa + 0: aaaaaaaaaa + 1: aaaa + *** Failers +No match + aaaaaaaaa +No match + aaaaaaaaaaa +No match + +/(?:(f)(o)(o)|(b)(a)(r))*/ + foobar + 0: foobar + 1: f + 2: o + 3: o + 4: b + 5: a + 6: r + +/(?<=a)b/ + ab + 0: b + *** Failers +No match + cb +No match + b +No match + +/(? + 2: abcd + xy:z:::abcd + 0: xy:z:::abcd + 1: xy:z::: + 2: abcd + +/^[^bcd]*(c+)/ + aexycd + 0: aexyc + 1: c + +/(a*)b+/ + caab + 0: aab + 1: aa + +/([\w:]+::)?(\w+)$/ + abcd + 0: abcd + 1: + 2: abcd + xy:z:::abcd + 0: xy:z:::abcd + 1: xy:z::: + 2: abcd + *** Failers + 0: Failers + 1: + 2: Failers + abcd: +No match + abcd: +No match + +/^[^bcd]*(c+)/ + aexycd + 0: aexyc + 1: c + +/(>a+)ab/ + +/(?>a+)b/ + aaab + 0: aaab + +/([[:]+)/ + a:[b]: + 0: :[ + 1: :[ + +/([[=]+)/ + a=[b]= + 0: =[ + 1: =[ + +/([[.]+)/ + a.[b]. + 0: .[ + 1: .[ + +/((?>a+)b)/ + aaab + 0: aaab + 1: aaab + +/(?>(a+))b/ + aaab + 0: aaab + 1: aaa + +/((?>[^()]+)|\([^()]*\))+/ + ((abc(ade)ufh()()x + 0: abc(ade)ufh()()x + 1: x + +/a\Z/ + *** Failers +No match + aaab +No match + a\nb\n +No match + +/b\Z/ + a\nb\n + 0: b + +/b\z/ + +/b\Z/ + a\nb + 0: b + +/b\z/ + a\nb + 0: b + *** Failers +No match + +/^(?>(?(1)\.|())[^\W_](?>[a-z0-9-]*[^\W_])?)+$/ + a + 0: a + 1: + abc + 0: abc + 1: + a-b + 0: a-b + 1: + 0-9 + 0: 0-9 + 1: + a.b + 0: a.b + 1: + 5.6.7 + 0: 5.6.7 + 1: + the.quick.brown.fox + 0: the.quick.brown.fox + 1: + a100.b200.300c + 0: a100.b200.300c + 1: + 12-ab.1245 + 0: 12-ab.1245 + 1: + *** Failers +No match + \ +No match + .a +No match + -a +No match + a- +No match + a. +No match + a_b +No match + a.- +No match + a.. +No match + ab..bc +No match + the.quick.brown.fox- +No match + the.quick.brown.fox. +No match + the.quick.brown.fox_ +No match + the.quick.brown.fox+ +No match + +/(?>.*)(?<=(abcd|wxyz))/ + alphabetabcd + 0: alphabetabcd + 1: abcd + endingwxyz + 0: endingwxyz + 1: wxyz + *** Failers +No match + a rather long string that doesn't end with one of them +No match + +/word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark otherword + 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword + word cat dog elephant mussel cow horse canary baboon snake shark +No match + +/word (?>[a-zA-Z0-9]+ ){0,30}otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope +No match + +/(?<=\d{3}(?!999))foo/ + 999foo + 0: foo + 123999foo + 0: foo + *** Failers +No match + 123abcfoo +No match + +/(?<=(?!...999)\d{3})foo/ + 999foo + 0: foo + 123999foo + 0: foo + *** Failers +No match + 123abcfoo +No match + +/(?<=\d{3}(?!999)...)foo/ + 123abcfoo + 0: foo + 123456foo + 0: foo + *** Failers +No match + 123999foo +No match + +/(?<=\d{3}...)(? + 2: + 3: abcd + + 2: + 3: abcd + \s*)=(?>\s*) # find + 2: + 3: abcd + Z)+|A)*/ + ZABCDEFG + 0: ZA + 1: A + +/((?>)+|A)*/ + ZABCDEFG + 0: + 1: + +/a*/g + abbab + 0: a + 0: + 0: + 0: a + 0: + 0: + +/^[a-\d]/ + abcde + 0: a + -things + 0: - + 0digit + 0: 0 + *** Failers +No match + bcdef +No match + +/^[\d-a]/ + abcde + 0: a + -things + 0: - + 0digit + 0: 0 + *** Failers +No match + bcdef +No match + +/[[:space:]]+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09\x0a\x0c\x0d\x0b + +/[[:blank:]]+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09 + +/[\s]+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09\x0a\x0c\x0d + +/\s+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09\x0a\x0c\x0d + +/a b/x + ab +No match + +/(?!\A)x/m + a\nxb\n + 0: x + +/(?!^)x/m + a\nxb\n +No match + +/abc\Qabc\Eabc/ + abcabcabc + 0: abcabcabc + +/abc\Q(*+|\Eabc/ + abc(*+|abc + 0: abc(*+|abc + +/ abc\Q abc\Eabc/x + abc abcabc + 0: abc abcabc + *** Failers +No match + abcabcabc +No match + +/abc#comment + \Q#not comment + literal\E/x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/abc#comment + \Q#not comment + literal/x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/abc#comment + \Q#not comment + literal\E #more comment + /x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/abc#comment + \Q#not comment + literal\E #more comment/x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/\Qabc\$xyz\E/ + abc\\\$xyz + 0: abc\$xyz + +/\Qabc\E\$\Qxyz\E/ + abc\$xyz + 0: abc$xyz + +/\Gabc/ + abc + 0: abc + *** Failers +No match + xyzabc +No match + +/\Gabc./g + abc1abc2xyzabc3 + 0: abc1 + 0: abc2 + +/abc./g + abc1abc2xyzabc3 + 0: abc1 + 0: abc2 + 0: abc3 + +/a(?x: b c )d/ + XabcdY + 0: abcd + *** Failers +No match + Xa b c d Y +No match + +/((?x)x y z | a b c)/ + XabcY + 0: abc + 1: abc + AxyzB + 0: xyz + 1: xyz + +/(?i)AB(?-i)C/ + XabCY + 0: abC + *** Failers +No match + XabcY +No match + +/((?i)AB(?-i)C|D)E/ + abCE + 0: abCE + 1: abC + DE + 0: DE + 1: D + *** Failers +No match + abcE +No match + abCe +No match + dE +No match + De +No match + +/(.*)\d+\1/ + abc123abc + 0: abc123abc + 1: abc + abc123bc + 0: bc123bc + 1: bc + +/(.*)\d+\1/s + abc123abc + 0: abc123abc + 1: abc + abc123bc + 0: bc123bc + 1: bc + +/((.*))\d+\1/ + abc123abc + 0: abc123abc + 1: abc + 2: abc + abc123bc + 0: bc123bc + 1: bc + 2: bc + +/-- This tests for an IPv6 address in the form where it can have up to --/ +/-- eight components, one and only one of which is empty. This must be --/ +No match +/-- an internal component. --/ +No match + +/^(?!:) # colon disallowed at start + (?: # start of item + (?: [0-9a-f]{1,4} | # 1-4 hex digits or + (?(1)0 | () ) ) # if null previously matched, fail; else null + : # followed by colon + ){1,7} # end item; 1-7 of them required + [0-9a-f]{1,4} $ # final hex number at end of string + (?(1)|.) # check that there was an empty component + /xi + a123::a123 + 0: a123::a123 + 1: + a123:b342::abcd + 0: a123:b342::abcd + 1: + a123:b342::324e:abcd + 0: a123:b342::324e:abcd + 1: + a123:ddde:b342::324e:abcd + 0: a123:ddde:b342::324e:abcd + 1: + a123:ddde:b342::324e:dcba:abcd + 0: a123:ddde:b342::324e:dcba:abcd + 1: + a123:ddde:9999:b342::324e:dcba:abcd + 0: a123:ddde:9999:b342::324e:dcba:abcd + 1: + *** Failers +No match + 1:2:3:4:5:6:7:8 +No match + a123:bce:ddde:9999:b342::324e:dcba:abcd +No match + a123::9999:b342::324e:dcba:abcd +No match + abcde:2:3:4:5:6:7:8 +No match + ::1 +No match + abcd:fee0:123:: +No match + :1 +No match + 1: +No match + +/[z\Qa-d]\E]/ + z + 0: z + a + 0: a + - + 0: - + d + 0: d + ] + 0: ] + *** Failers + 0: a + b +No match + +/[\z\C]/ + z + 0: z + C + 0: C + +/\M/ + M + 0: M + +/(a+)*b/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + +/(?i)reg(?:ul(?:[aä]|ae)r|ex)/ + REGular + 0: REGular + regulaer + 0: regulaer + Regex + 0: Regex + regulär + 0: regul\xe4r + +/Åæåä[à-ÿÀ-ß]+/ + Åæåäà + 0: \xc5\xe6\xe5\xe4\xe0 + Åæåäÿ + 0: \xc5\xe6\xe5\xe4\xff + ÅæåäÀ + 0: \xc5\xe6\xe5\xe4\xc0 + Åæåäß + 0: \xc5\xe6\xe5\xe4\xdf + +/(?<=Z)X./ + \x84XAZXB + 0: XB + +/ab cd (?x) de fg/ + ab cd defg + 0: ab cd defg + +/ab cd(?x) de fg/ + ab cddefg + 0: ab cddefg + ** Failers +No match + abcddefg +No match + +/(? + ? @ A B C D E F G H I J K L M N O P Q R S T U V W X Y [ \ ] ^ _ ` a b c d + e f g h i j k l m n o p q r s t u v w x y z { | } ~ \x7f \x80 \x81 \x82 \x83 + \x84 \x85 \x86 \x87 \x88 \x89 \x8a \x8b \x8c \x8d \x8e \x8f \x90 \x91 \x92 + \x93 \x94 \x95 \x96 \x97 \x98 \x99 \x9a \x9b \x9c \x9d \x9e \x9f \xa0 \xa1 + \xa2 \xa3 \xa4 \xa5 \xa6 \xa7 \xa8 \xa9 \xaa \xab \xac \xad \xae \xaf \xb0 + \xb1 \xb2 \xb3 \xb4 \xb5 \xb6 \xb7 \xb8 \xb9 \xba \xbb \xbc \xbd \xbe \xbf + \xc0 \xc1 \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd \xce + \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc \xdd + \xde \xdf \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb \xec + \xed \xee \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa \xfb + \xfc \xfd \xfe \xff + +/(a|b)*[\s]/S +Capturing subpattern count = 1 +No options +No first char +No need char +Starting byte set: \x09 \x0a \x0c \x0d \x20 a b + +/(ab\2)/ +Failed: reference to non-existent subpattern at offset 6 + +/{4,5}abc/ +Failed: nothing to repeat at offset 4 + +/(a)(b)(c)\2/ +Capturing subpattern count = 3 +Max back reference = 2 +No options +First char = 'a' +Need char = 'c' + abcb + 0: abcb + 1: a + 2: b + 3: c + \O0abcb +Matched, but too many substrings + \O3abcb +Matched, but too many substrings + 0: abcb + \O6abcb +Matched, but too many substrings + 0: abcb + 1: a + \O9abcb +Matched, but too many substrings + 0: abcb + 1: a + 2: b + \O12abcb + 0: abcb + 1: a + 2: b + 3: c + +/(a)bc|(a)(b)\2/ +Capturing subpattern count = 3 +Max back reference = 2 +No options +First char = 'a' +No need char + abc + 0: abc + 1: a + \O0abc +Matched, but too many substrings + \O3abc +Matched, but too many substrings + 0: abc + \O6abc + 0: abc + 1: a + aba + 0: aba + 1: + 2: a + 3: b + \O0aba +Matched, but too many substrings + \O3aba +Matched, but too many substrings + 0: aba + \O6aba +Matched, but too many substrings + 0: aba + 1: + \O9aba +Matched, but too many substrings + 0: aba + 1: + 2: a + \O12aba + 0: aba + 1: + 2: a + 3: b + +/abc$/E +Capturing subpattern count = 0 +Options: dollar_endonly +First char = 'a' +Need char = 'c' + abc + 0: abc + *** Failers +No match + abc\n +No match + abc\ndef +No match + +/(a)(b)(c)(d)(e)\6/ +Failed: reference to non-existent subpattern at offset 17 + +/the quick brown fox/ +Capturing subpattern count = 0 +No options +First char = 't' +Need char = 'x' + the quick brown fox + 0: the quick brown fox + this is a line with the quick brown fox + 0: the quick brown fox + +/the quick brown fox/A +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + the quick brown fox + 0: the quick brown fox + *** Failers +No match + this is a line with the quick brown fox +No match + +/ab(?z)cd/ +Failed: unrecognized character after (? at offset 4 + +/^abc|def/ +Capturing subpattern count = 0 +No options +No first char +No need char + abcdef + 0: abc + abcdef\B + 0: def + +/.*((abc)$|(def))/ +Capturing subpattern count = 3 +Partial matching not supported +No options +First char at start or follows newline +No need char + defabc + 0: defabc + 1: abc + 2: abc + \Zdefabc + 0: def + 1: def + 2: + 3: def + +/abc/P + abc + 0: abc + *** Failers +No match: POSIX code 17: match failed + +/^abc|def/P + abcdef + 0: abc + abcdef\B + 0: def + +/.*((abc)$|(def))/P + defabc + 0: defabc + 1: abc + 2: abc + \Zdefabc + 0: def + 1: def + 3: def + +/the quick brown fox/P + the quick brown fox + 0: the quick brown fox + *** Failers +No match: POSIX code 17: match failed + The Quick Brown Fox +No match: POSIX code 17: match failed + +/the quick brown fox/Pi + the quick brown fox + 0: the quick brown fox + The Quick Brown Fox + 0: The Quick Brown Fox + +/abc.def/P + *** Failers +No match: POSIX code 17: match failed + abc\ndef +No match: POSIX code 17: match failed + +/abc$/P + abc + 0: abc + abc\n + 0: abc + +/(abc)\2/P +Failed: POSIX code 15: bad back reference at offset 7 + +/(abc\1)/P + abc +No match: POSIX code 17: match failed + +/)/ +Failed: unmatched parentheses at offset 0 + +/a[]b/ +Failed: missing terminating ] for character class at offset 4 + +/[^aeiou ]{3,}/ +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + co-processors, and for + 0: -pr + +/<.*>/ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = '<' +Need char = '>' + abcghinop + 0: ghi + +/<.*?>/ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = '<' +Need char = '>' + abcghinop + 0: + +/<.*>/U +Capturing subpattern count = 0 +Partial matching not supported +Options: ungreedy +First char = '<' +Need char = '>' + abcghinop + 0: + +/(?U)<.*>/ +Capturing subpattern count = 0 +Partial matching not supported +Options: ungreedy +First char = '<' +Need char = '>' + abcghinop + 0: + +/<.*?>/U +Capturing subpattern count = 0 +Partial matching not supported +Options: ungreedy +First char = '<' +Need char = '>' + abcghinop + 0: ghi + +/={3,}/U +Capturing subpattern count = 0 +Partial matching not supported +Options: ungreedy +First char = '=' +Need char = '=' + abc========def + 0: === + +/(?U)={3,}?/ +Capturing subpattern count = 0 +Partial matching not supported +Options: ungreedy +First char = '=' +Need char = '=' + abc========def + 0: ======== + +/(?^abc)/m +Capturing subpattern count = 0 +Options: multiline +First char at start or follows newline +Need char = 'c' + abc + 0: abc + def\nabc + 0: abc + *** Failers +No match + defabc +No match + +/(?<=ab(c+)d)ef/ +Failed: lookbehind assertion is not fixed length at offset 11 + +/(?<=ab(?<=c+)d)ef/ +Failed: lookbehind assertion is not fixed length at offset 12 + +/(?<=ab(c|de)f)g/ +Failed: lookbehind assertion is not fixed length at offset 13 + +/The next three are in testinput2 because they have variable length branches/ +Capturing subpattern count = 0 +No options +First char = 'T' +Need char = 's' + +/(?<=bullock|donkey)-cart/ +Capturing subpattern count = 0 +No options +First char = '-' +Need char = 't' + the bullock-cart + 0: -cart + a donkey-cart race + 0: -cart + *** Failers +No match + cart +No match + horse-and-cart +No match + +/(?<=ab(?i)x|y|z)/ +Capturing subpattern count = 0 +No options +No first char +No need char + +/(?>.*)(?<=(abcd)|(xyz))/ +Capturing subpattern count = 2 +Partial matching not supported +No options +First char at start or follows newline +No need char + alphabetabcd + 0: alphabetabcd + 1: abcd + endingxyz + 0: endingxyz + 1: + 2: xyz + +/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/ +Capturing subpattern count = 0 +No options +First char = 'Z' +Need char = 'Z' + abxyZZ + 0: ZZ + abXyZZ + 0: ZZ + ZZZ + 0: ZZ + zZZ + 0: ZZ + bZZ + 0: ZZ + BZZ + 0: ZZ + *** Failers +No match + ZZ +No match + abXYZZ +No match + zzz +No match + bzz +No match + +/(? + 3: f + 1G a (1) + 2G (0) + 3G f (1) +get substring 4 failed -7 + 0L adef + 1L a + 2L + 3L f + bcdef\G1\G2\G3\G4\L + 0: bcdef + 1: bc + 2: bc + 3: f + 1G bc (2) + 2G bc (2) + 3G f (1) +get substring 4 failed -7 + 0L bcdef + 1L bc + 2L bc + 3L f + adefghijk\C0 + 0: adef + 1: a + 2: + 3: f + 0C adef (4) + +/^abc\00def/ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + abc\00def\L\C0 + 0: abc\x00def + 0C abc (7) + 0L abc + +/word ((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ +)((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ +)?)?)?)?)?)?)?)?)?otherword/M +Memory allocation (code space): 432 +Capturing subpattern count = 8 +Partial matching not supported +No options +First char = 'w' +Need char = 'd' + +/.*X/D +------------------------------------------------------------------ + 0 7 Bra 0 + 3 Any* + 5 X + 7 7 Ket + 10 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char at start or follows newline +Need char = 'X' + +/.*X/Ds +------------------------------------------------------------------ + 0 7 Bra 0 + 3 Any* + 5 X + 7 7 Ket + 10 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: anchored dotall +No first char +Need char = 'X' + +/(.*X|^B)/D +------------------------------------------------------------------ + 0 19 Bra 0 + 3 7 Bra 1 + 6 Any* + 8 X + 10 6 Alt + 13 ^ + 14 B + 16 13 Ket + 19 19 Ket + 22 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Partial matching not supported +No options +First char at start or follows newline +No need char + +/(.*X|^B)/Ds +------------------------------------------------------------------ + 0 19 Bra 0 + 3 7 Bra 1 + 6 Any* + 8 X + 10 6 Alt + 13 ^ + 14 B + 16 13 Ket + 19 19 Ket + 22 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Partial matching not supported +Options: anchored dotall +No first char +No need char + +/(?s)(.*X|^B)/D +------------------------------------------------------------------ + 0 19 Bra 0 + 3 7 Bra 1 + 6 Any* + 8 X + 10 6 Alt + 13 ^ + 14 B + 16 13 Ket + 19 19 Ket + 22 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Partial matching not supported +Options: anchored dotall +No first char +No need char + +/(?s:.*X|^B)/D +------------------------------------------------------------------ + 0 25 Bra 0 + 3 9 Bra 0 + 6 04 Opt + 8 Any* + 10 X + 12 8 Alt + 15 04 Opt + 17 ^ + 18 B + 20 17 Ket + 23 00 Opt + 25 25 Ket + 28 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char at start or follows newline +No need char + +/\Biss\B/+ +Capturing subpattern count = 0 +No options +First char = 'i' +Need char = 's' + Mississippi + 0: iss + 0+ issippi + +/\Biss\B/+P + Mississippi + 0: iss + 0+ issippi + +/iss/G+ +Capturing subpattern count = 0 +No options +First char = 'i' +Need char = 's' + Mississippi + 0: iss + 0+ issippi + 0: iss + 0+ ippi + +/\Biss\B/G+ +Capturing subpattern count = 0 +No options +First char = 'i' +Need char = 's' + Mississippi + 0: iss + 0+ issippi + +/\Biss\B/g+ +Capturing subpattern count = 0 +No options +First char = 'i' +Need char = 's' + Mississippi + 0: iss + 0+ issippi + 0: iss + 0+ ippi + *** Failers +No match + Mississippi\A +No match + +/(?<=[Ms])iss/g+ +Capturing subpattern count = 0 +No options +First char = 'i' +Need char = 's' + Mississippi + 0: iss + 0+ issippi + 0: iss + 0+ ippi + +/(?<=[Ms])iss/G+ +Capturing subpattern count = 0 +No options +First char = 'i' +Need char = 's' + Mississippi + 0: iss + 0+ issippi + +/^iss/g+ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + ississippi + 0: iss + 0+ issippi + +/.*iss/g+ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char at start or follows newline +Need char = 's' + abciss\nxyzisspqr + 0: abciss + 0+ \x0axyzisspqr + 0: xyziss + 0+ pqr + +/.i./+g +Capturing subpattern count = 0 +No options +No first char +Need char = 'i' + Mississippi + 0: Mis + 0+ sissippi + 0: sis + 0+ sippi + 0: sip + 0+ pi + Mississippi\A + 0: Mis + 0+ sissippi + 0: sis + 0+ sippi + 0: sip + 0+ pi + Missouri river + 0: Mis + 0+ souri river + 0: ri + 0+ river + 0: riv + 0+ er + Missouri river\A + 0: Mis + 0+ souri river + +/^.is/+g +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + Mississippi + 0: Mis + 0+ sissippi + +/^ab\n/g+ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + ab\nab\ncd + 0: ab\x0a + 0+ ab\x0acd + +/^ab\n/mg+ +Capturing subpattern count = 0 +Options: multiline +First char at start or follows newline +Need char = 10 + ab\nab\ncd + 0: ab\x0a + 0+ ab\x0acd + 0: ab\x0a + 0+ cd + +/abc/ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'c' + +/abc|bac/ +Capturing subpattern count = 0 +No options +No first char +Need char = 'c' + +/(abc|bac)/ +Capturing subpattern count = 1 +No options +No first char +Need char = 'c' + +/(abc|(c|dc))/ +Capturing subpattern count = 2 +No options +No first char +Need char = 'c' + +/(abc|(d|de)c)/ +Capturing subpattern count = 2 +No options +No first char +Need char = 'c' + +/a*/ +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + +/a+/ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +No need char + +/(baa|a+)/ +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +Need char = 'a' + +/a{0,3}/ +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + +/baa{3,}/ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'b' +Need char = 'a' + +/"([^\\"]+|\\.)*"/ +Capturing subpattern count = 1 +Partial matching not supported +No options +First char = '"' +Need char = '"' + +/(abc|ab[cd])/ +Capturing subpattern count = 1 +No options +First char = 'a' +No need char + +/(a|.)/ +Capturing subpattern count = 1 +No options +No first char +No need char + +/a|ba|\w/ +Capturing subpattern count = 0 +No options +No first char +No need char + +/abc(?=pqr)/ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'r' + +/...(?<=abc)/ +Capturing subpattern count = 0 +No options +No first char +No need char + +/abc(?!pqr)/ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'c' + +/ab./ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'b' + +/ab[xyz]/ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'b' + +/abc*/ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +Need char = 'b' + +/ab.c*/ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +Need char = 'b' + +/a.c*/ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +No need char + +/.c*/ +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + +/ac*/ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +No need char + +/(a.c*|b.c*)/ +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +No need char + +/a.c*|aba/ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +No need char + +/.+a/ +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +Need char = 'a' + +/(?=abcda)a.*/ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +Need char = 'a' + +/(?=a)a.*/ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +No need char + +/a(b)*/ +Capturing subpattern count = 1 +No options +First char = 'a' +No need char + +/a\d*/ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +No need char + +/ab\d*/ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +Need char = 'b' + +/a(\d)*/ +Capturing subpattern count = 1 +No options +First char = 'a' +No need char + +/abcde{0,0}/ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'd' + +/ab\d+/ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +Need char = 'b' + +/a(?(1)b)/ +Capturing subpattern count = 0 +No options +First char = 'a' +No need char + +/a(?(1)bag|big)/ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'g' + +/a(?(1)bag|big)*/ +Capturing subpattern count = 0 +No options +First char = 'a' +No need char + +/a(?(1)bag|big)+/ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'g' + +/a(?(1)b..|b..)/ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'b' + +/ab\d{0}e/ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'e' + +/a?b?/ +Capturing subpattern count = 0 +No options +No first char +No need char + a + 0: a + b + 0: b + ab + 0: ab + \ + 0: + *** Failers + 0: + \N +No match + +/|-/ +Capturing subpattern count = 0 +No options +No first char +No need char + abcd + 0: + -abc + 0: + \Nab-c + 0: - + *** Failers + 0: + \Nabc +No match + +/a*(b+)(z)(z)/P + aaaabbbbzzzz + 0: aaaabbbbzz + 1: bbbb + 2: z + 3: z + aaaabbbbzzzz\O0 + aaaabbbbzzzz\O1 + 0: aaaabbbbzz + aaaabbbbzzzz\O2 + 0: aaaabbbbzz + 1: bbbb + aaaabbbbzzzz\O3 + 0: aaaabbbbzz + 1: bbbb + 2: z + aaaabbbbzzzz\O4 + 0: aaaabbbbzz + 1: bbbb + 2: z + 3: z + aaaabbbbzzzz\O5 + 0: aaaabbbbzz + 1: bbbb + 2: z + 3: z + +/^.?abcd/S +Capturing subpattern count = 0 +Options: anchored +No first char +Need char = 'd' +Study returned NULL + +/\( # ( at start + (?: # Non-capturing bracket + (?>[^()]+) # Either a sequence of non-brackets (no backtracking) + | # Or + (?R) # Recurse - i.e. nested bracketed string + )* # Zero or more contents + \) # Closing ) + /x +Capturing subpattern count = 0 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (abcd) + 0: (abcd) + (abcd)xyz + 0: (abcd) + xyz(abcd) + 0: (abcd) + (ab(xy)cd)pqr + 0: (ab(xy)cd) + (ab(xycd)pqr + 0: (xycd) + () abc () + 0: () + 12(abcde(fsh)xyz(foo(bar))lmno)89 + 0: (abcde(fsh)xyz(foo(bar))lmno) + *** Failers +No match + abcd +No match + abcd) +No match + (abcd +No match + +/\( ( (?>[^()]+) | (?R) )* \) /xg +Capturing subpattern count = 1 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (ab(xy)cd)pqr + 0: (ab(xy)cd) + 1: cd + 1(abcd)(x(y)z)pqr + 0: (abcd) + 1: abcd + 0: (x(y)z) + 1: z + +/\( (?: (?>[^()]+) | (?R) ) \) /x +Capturing subpattern count = 0 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (abcd) + 0: (abcd) + (ab(xy)cd) + 0: (xy) + (a(b(c)d)e) + 0: (c) + ((ab)) + 0: ((ab)) + *** Failers +No match + () +No match + +/\( (?: (?>[^()]+) | (?R) )? \) /x +Capturing subpattern count = 0 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + () + 0: () + 12(abcde(fsh)xyz(foo(bar))lmno)89 + 0: (fsh) + +/\( ( (?>[^()]+) | (?R) )* \) /x +Capturing subpattern count = 1 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (ab(xy)cd) + 0: (ab(xy)cd) + 1: cd + +/\( ( ( (?>[^()]+) | (?R) )* ) \) /x +Capturing subpattern count = 2 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (ab(xy)cd) + 0: (ab(xy)cd) + 1: ab(xy)cd + 2: cd + +/\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /x +Capturing subpattern count = 3 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (ab(xy)cd) + 0: (ab(xy)cd) + 1: + 2: ab(xy)cd + 3: cd + (123ab(xy)cd) + 0: (123ab(xy)cd) + 1: 123 + 2: ab(xy)cd + 3: cd + +/\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /x +Capturing subpattern count = 3 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (ab(xy)cd) + 0: (ab(xy)cd) + 1: ab(xy)cd + 2: + 3: cd + (123ab(xy)cd) + 0: (123ab(xy)cd) + 1: 123ab(xy)cd + 2: 123 + 3: cd + +/\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /x +Capturing subpattern count = 11 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (ab(xy)cd) + 0: (ab(xy)cd) + 1: ab(xy)cd + 2: ab(xy)cd + 3: ab(xy)cd + 4: ab(xy)cd + 5: ab(xy)cd + 6: ab(xy)cd + 7: ab(xy)cd + 8: ab(xy)cd + 9: ab(xy)cd +10: ab(xy)cd +11: cd + +/\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /x +Capturing subpattern count = 3 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (abcd(xyz

qrs)123) + 0: (abcd(xyz

qrs)123) + 1: abcd(xyz

qrs)123 + 2: 123 + 3: + +/\( ( ( (?>[^()]+) | ((?R)) )* ) \) /x +Capturing subpattern count = 3 +Partial matching not supported +Options: extended +First char = '(' +Need char = ')' + (ab(cd)ef) + 0: (ab(cd)ef) + 1: ab(cd)ef + 2: ef + 3: (cd) + (ab(cd(ef)gh)ij) + 0: (ab(cd(ef)gh)ij) + 1: ab(cd(ef)gh)ij + 2: ij + 3: (cd(ef)gh) + +/^[[:alnum:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [0-9A-Za-z] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:^alnum:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [\x00-/:-@[-`{-\xff] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:alpha:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [A-Za-z] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:^alpha:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [\x00-@[-`{-\xff] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/[_[:alpha:]]/IS +Capturing subpattern count = 0 +No options +No first char +No need char +Starting byte set: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z + _ a b c d e f g h i j k l m n o p q r s t u v w x y z + +/^[[:ascii:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [\x00-\x7f] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:^ascii:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [\x80-\xff] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:blank:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [\x09 ] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:^blank:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [\x00-\x08\x0a-\x1f!-\xff] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/[\n\x0b\x0c\x0d[:blank:]]/IS +Capturing subpattern count = 0 +No options +No first char +No need char +Starting byte set: \x09 \x0a \x0b \x0c \x0d \x20 + +/^[[:cntrl:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [\x00-\x1f\x7f] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:digit:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [0-9] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:graph:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [!-~] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:lower:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [a-z] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:print:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [ -~] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:punct:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [!-/:-@[-`{-~] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:space:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [\x09-\x0d ] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:upper:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [A-Z] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:xdigit:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [0-9A-Fa-f] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:word:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [0-9A-Z_a-z] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:^cntrl:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [ -~\x80-\xff] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[12[:^digit:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [\x00-/12:-\xff] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/^[[:^blank:]]/D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [\x00-\x08\x0a-\x1f!-\xff] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/[01[:alpha:]%]/D +------------------------------------------------------------------ + 0 36 Bra 0 + 3 [%01A-Za-z] + 36 36 Ket + 39 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/[[.ch.]]/ +Failed: POSIX collating elements are not supported at offset 1 + +/[[=ch=]]/ +Failed: POSIX collating elements are not supported at offset 1 + +/[[:rhubarb:]]/ +Failed: unknown POSIX class name at offset 3 + +/[[:upper:]]/i +Capturing subpattern count = 0 +Options: caseless +No first char +No need char + A + 0: A + a + 0: a + +/[[:lower:]]/i +Capturing subpattern count = 0 +Options: caseless +No first char +No need char + A + 0: A + a + 0: a + +/((?-i)[[:lower:]])[[:lower:]]/i +Capturing subpattern count = 1 +Options: caseless +No first char +No need char + ab + 0: ab + 1: a + aB + 0: aB + 1: a + *** Failers + 0: ai + 1: a + Ab +No match + AB +No match + +/[\200-\110]/ +Failed: range out of order in character class at offset 9 + +/^(?(0)f|b)oo/ +Failed: invalid condition (?(0) at offset 6 + +/This one's here because of the large output vector needed/ +Capturing subpattern count = 0 +No options +First char = 'T' +Need char = 'd' + +/(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\w+)\s+(\270)/ +Capturing subpattern count = 271 +Max back reference = 270 +Partial matching not supported +No options +No first char +No need char + \O900 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 ABC ABC + 0: 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 ABC ABC + 1: 1 + 2: 2 + 3: 3 + 4: 4 + 5: 5 + 6: 6 + 7: 7 + 8: 8 + 9: 9 +10: 10 +11: 11 +12: 12 +13: 13 +14: 14 +15: 15 +16: 16 +17: 17 +18: 18 +19: 19 +20: 20 +21: 21 +22: 22 +23: 23 +24: 24 +25: 25 +26: 26 +27: 27 +28: 28 +29: 29 +30: 30 +31: 31 +32: 32 +33: 33 +34: 34 +35: 35 +36: 36 +37: 37 +38: 38 +39: 39 +40: 40 +41: 41 +42: 42 +43: 43 +44: 44 +45: 45 +46: 46 +47: 47 +48: 48 +49: 49 +50: 50 +51: 51 +52: 52 +53: 53 +54: 54 +55: 55 +56: 56 +57: 57 +58: 58 +59: 59 +60: 60 +61: 61 +62: 62 +63: 63 +64: 64 +65: 65 +66: 66 +67: 67 +68: 68 +69: 69 +70: 70 +71: 71 +72: 72 +73: 73 +74: 74 +75: 75 +76: 76 +77: 77 +78: 78 +79: 79 +80: 80 +81: 81 +82: 82 +83: 83 +84: 84 +85: 85 +86: 86 +87: 87 +88: 88 +89: 89 +90: 90 +91: 91 +92: 92 +93: 93 +94: 94 +95: 95 +96: 96 +97: 97 +98: 98 +99: 99 +100: 100 +101: 101 +102: 102 +103: 103 +104: 104 +105: 105 +106: 106 +107: 107 +108: 108 +109: 109 +110: 110 +111: 111 +112: 112 +113: 113 +114: 114 +115: 115 +116: 116 +117: 117 +118: 118 +119: 119 +120: 120 +121: 121 +122: 122 +123: 123 +124: 124 +125: 125 +126: 126 +127: 127 +128: 128 +129: 129 +130: 130 +131: 131 +132: 132 +133: 133 +134: 134 +135: 135 +136: 136 +137: 137 +138: 138 +139: 139 +140: 140 +141: 141 +142: 142 +143: 143 +144: 144 +145: 145 +146: 146 +147: 147 +148: 148 +149: 149 +150: 150 +151: 151 +152: 152 +153: 153 +154: 154 +155: 155 +156: 156 +157: 157 +158: 158 +159: 159 +160: 160 +161: 161 +162: 162 +163: 163 +164: 164 +165: 165 +166: 166 +167: 167 +168: 168 +169: 169 +170: 170 +171: 171 +172: 172 +173: 173 +174: 174 +175: 175 +176: 176 +177: 177 +178: 178 +179: 179 +180: 180 +181: 181 +182: 182 +183: 183 +184: 184 +185: 185 +186: 186 +187: 187 +188: 188 +189: 189 +190: 190 +191: 191 +192: 192 +193: 193 +194: 194 +195: 195 +196: 196 +197: 197 +198: 198 +199: 199 +200: 200 +201: 201 +202: 202 +203: 203 +204: 204 +205: 205 +206: 206 +207: 207 +208: 208 +209: 209 +210: 210 +211: 211 +212: 212 +213: 213 +214: 214 +215: 215 +216: 216 +217: 217 +218: 218 +219: 219 +220: 220 +221: 221 +222: 222 +223: 223 +224: 224 +225: 225 +226: 226 +227: 227 +228: 228 +229: 229 +230: 230 +231: 231 +232: 232 +233: 233 +234: 234 +235: 235 +236: 236 +237: 237 +238: 238 +239: 239 +240: 240 +241: 241 +242: 242 +243: 243 +244: 244 +245: 245 +246: 246 +247: 247 +248: 248 +249: 249 +250: 250 +251: 251 +252: 252 +253: 253 +254: 254 +255: 255 +256: 256 +257: 257 +258: 258 +259: 259 +260: 260 +261: 261 +262: 262 +263: 263 +264: 264 +265: 265 +266: 266 +267: 267 +268: 268 +269: 269 +270: ABC +271: ABC + +/This one's here because Perl does this differently and PCRE can't at present/ +Capturing subpattern count = 0 +No options +First char = 'T' +Need char = 't' + +/(main(O)?)+/ +Capturing subpattern count = 2 +No options +First char = 'm' +Need char = 'n' + mainmain + 0: mainmain + 1: main + mainOmain + 0: mainOmain + 1: main + 2: O + +/These are all cases where Perl does it differently (nested captures)/ +Capturing subpattern count = 1 +No options +First char = 'T' +Need char = 's' + +/^(a(b)?)+$/ +Capturing subpattern count = 2 +Options: anchored +No first char +No need char + aba + 0: aba + 1: a + 2: b + +/^(aa(bb)?)+$/ +Capturing subpattern count = 2 +Options: anchored +No first char +No need char + aabbaa + 0: aabbaa + 1: aa + 2: bb + +/^(aa|aa(bb))+$/ +Capturing subpattern count = 2 +Options: anchored +No first char +No need char + aabbaa + 0: aabbaa + 1: aa + 2: bb + +/^(aa(bb)??)+$/ +Capturing subpattern count = 2 +Options: anchored +No first char +No need char + aabbaa + 0: aabbaa + 1: aa + 2: bb + +/^(?:aa(bb)?)+$/ +Capturing subpattern count = 1 +Options: anchored +No first char +No need char + aabbaa + 0: aabbaa + 1: bb + +/^(aa(b(b))?)+$/ +Capturing subpattern count = 3 +Options: anchored +No first char +No need char + aabbaa + 0: aabbaa + 1: aa + 2: bb + 3: b + +/^(?:aa(b(b))?)+$/ +Capturing subpattern count = 2 +Options: anchored +No first char +No need char + aabbaa + 0: aabbaa + 1: bb + 2: b + +/^(?:aa(b(?:b))?)+$/ +Capturing subpattern count = 1 +Options: anchored +No first char +No need char + aabbaa + 0: aabbaa + 1: bb + +/^(?:aa(bb(?:b))?)+$/ +Capturing subpattern count = 1 +Options: anchored +No first char +No need char + aabbbaa + 0: aabbbaa + 1: bbb + +/^(?:aa(b(?:bb))?)+$/ +Capturing subpattern count = 1 +Options: anchored +No first char +No need char + aabbbaa + 0: aabbbaa + 1: bbb + +/^(?:aa(?:b(b))?)+$/ +Capturing subpattern count = 1 +Options: anchored +No first char +No need char + aabbaa + 0: aabbaa + 1: b + +/^(?:aa(?:b(bb))?)+$/ +Capturing subpattern count = 1 +Options: anchored +No first char +No need char + aabbbaa + 0: aabbbaa + 1: bb + +/^(aa(b(bb))?)+$/ +Capturing subpattern count = 3 +Options: anchored +No first char +No need char + aabbbaa + 0: aabbbaa + 1: aa + 2: bbb + 3: bb + +/^(aa(bb(bb))?)+$/ +Capturing subpattern count = 3 +Options: anchored +No first char +No need char + aabbbbaa + 0: aabbbbaa + 1: aa + 2: bbbb + 3: bb + +/--------------------------------------------------------------------/ +Capturing subpattern count = 0 +No options +First char = '-' +Need char = '-' + +/#/xMD +Memory allocation (code space): 7 +------------------------------------------------------------------ + 0 3 Bra 0 + 3 3 Ket + 6 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: extended +No first char +No need char + +/a#/xMD +Memory allocation (code space): 9 +------------------------------------------------------------------ + 0 5 Bra 0 + 3 a + 5 5 Ket + 8 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: extended +First char = 'a' +No need char + +/[\s]/D +------------------------------------------------------------------ + 0 36 Bra 0 + 3 [\x09\x0a\x0c\x0d ] + 36 36 Ket + 39 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/[\S]/D +------------------------------------------------------------------ + 0 36 Bra 0 + 3 [\x00-\x08\x0b\x0e-\x1f!-\xff] + 36 36 Ket + 39 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/a(?i)b/D +------------------------------------------------------------------ + 0 9 Bra 0 + 3 a + 5 01 Opt + 7 NC b + 9 9 Ket + 12 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'b' (caseless) + ab + 0: ab + aB + 0: aB + *** Failers +No match + AB +No match + +/(a(?i)b)/D +------------------------------------------------------------------ + 0 17 Bra 0 + 3 9 Bra 1 + 6 a + 8 01 Opt + 10 NC b + 12 9 Ket + 15 00 Opt + 17 17 Ket + 20 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'b' (caseless) + ab + 0: ab + 1: ab + aB + 0: aB + 1: aB + *** Failers +No match + AB +No match + +/ (?i)abc/xD +------------------------------------------------------------------ + 0 9 Bra 0 + 3 NC abc + 9 9 Ket + 12 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: caseless extended +First char = 'a' (caseless) +Need char = 'c' (caseless) + +/#this is a comment + (?i)abc/xD +------------------------------------------------------------------ + 0 9 Bra 0 + 3 NC abc + 9 9 Ket + 12 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: caseless extended +First char = 'a' (caseless) +Need char = 'c' (caseless) + +/123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/D +------------------------------------------------------------------ + 0 603 Bra 0 + 3 123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890 +603 603 Ket +606 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = '1' +Need char = '0' + +/\Q123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/D +------------------------------------------------------------------ + 0 603 Bra 0 + 3 123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890 +603 603 Ket +606 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = '1' +Need char = '0' + +/\Q\E/D +------------------------------------------------------------------ + 0 3 Bra 0 + 3 3 Ket + 6 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + \ + 0: + +/\Q\Ex/D +------------------------------------------------------------------ + 0 5 Bra 0 + 3 x + 5 5 Ket + 8 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = 'x' +No need char + +/ \Q\E/D +------------------------------------------------------------------ + 0 5 Bra 0 + 3 + 5 5 Ket + 8 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = ' ' +No need char + +/a\Q\E/D +------------------------------------------------------------------ + 0 5 Bra 0 + 3 a + 5 5 Ket + 8 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = 'a' +No need char + abc + 0: a + bca + 0: a + bac + 0: a + +/a\Q\Eb/D +------------------------------------------------------------------ + 0 7 Bra 0 + 3 ab + 7 7 Ket + 10 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'b' + abc + 0: ab + +/\Q\Eabc/D +------------------------------------------------------------------ + 0 9 Bra 0 + 3 abc + 9 9 Ket + 12 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'c' + +/x*+\w/D +------------------------------------------------------------------ + 0 12 Bra 0 + 3 5 Once + 6 x* + 8 5 Ket + 11 \w + 12 12 Ket + 15 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + *** Failers + 0: F + xxxxx +No match + +/x?+/D +------------------------------------------------------------------ + 0 11 Bra 0 + 3 5 Once + 6 x? + 8 5 Ket + 11 11 Ket + 14 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/x++/D +------------------------------------------------------------------ + 0 11 Bra 0 + 3 5 Once + 6 x+ + 8 5 Ket + 11 11 Ket + 14 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'x' +No need char + +/x{1,3}+/D +------------------------------------------------------------------ + 0 15 Bra 0 + 3 9 Once + 6 x + 8 x{,2} + 12 9 Ket + 15 15 Ket + 18 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'x' +No need char + +/(x)*+/D +------------------------------------------------------------------ + 0 18 Bra 0 + 3 12 Once + 6 Brazero + 7 5 Bra 1 + 10 x + 12 5 KetRmax + 15 12 Ket + 18 18 Ket + 21 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +No options +No first char +No need char + +/^(\w++|\s++)*$/ +Capturing subpattern count = 1 +Partial matching not supported +Options: anchored +No first char +No need char + now is the time for all good men to come to the aid of the party + 0: now is the time for all good men to come to the aid of the party + 1: party + *** Failers +No match + this is not a line with only words and spaces! +No match + +/(\d++)(\w)/ +Capturing subpattern count = 2 +Partial matching not supported +No options +No first char +No need char + 12345a + 0: 12345a + 1: 12345 + 2: a + *** Failers +No match + 12345+ +No match + +/a++b/ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +Need char = 'b' + aaab + 0: aaab + +/(a++b)/ +Capturing subpattern count = 1 +Partial matching not supported +No options +First char = 'a' +Need char = 'b' + aaab + 0: aaab + 1: aaab + +/(a++)b/ +Capturing subpattern count = 1 +Partial matching not supported +No options +First char = 'a' +Need char = 'b' + aaab + 0: aaab + 1: aaa + +/([^()]++|\([^()]*\))+/ +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +No need char + ((abc(ade)ufh()()x + 0: abc(ade)ufh()()x + 1: x + +/\(([^()]++|\([^()]+\))+\)/ +Capturing subpattern count = 1 +Partial matching not supported +No options +First char = '(' +Need char = ')' + (abc) + 0: (abc) + 1: abc + (abc(def)xyz) + 0: (abc(def)xyz) + 1: xyz + *** Failers +No match + ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + +/(abc){1,3}+/D +------------------------------------------------------------------ + 0 53 Bra 0 + 3 47 Once + 6 9 Bra 1 + 9 abc + 15 9 Ket + 18 Brazero + 19 28 Bra 0 + 22 9 Bra 1 + 25 abc + 31 9 Ket + 34 Brazero + 35 9 Bra 1 + 38 abc + 44 9 Ket + 47 28 Ket + 50 47 Ket + 53 53 Ket + 56 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'c' + +/a+?+/ +Failed: nothing to repeat at offset 3 + +/a{2,3}?+b/ +Failed: nothing to repeat at offset 7 + +/(?U)a+?+/ +Failed: nothing to repeat at offset 7 + +/a{2,3}?+b/U +Failed: nothing to repeat at offset 7 + +/x(?U)a++b/D +------------------------------------------------------------------ + 0 15 Bra 0 + 3 x + 5 5 Once + 8 a+ + 10 5 Ket + 13 b + 15 15 Ket + 18 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'x' +Need char = 'b' + xaaaab + 0: xaaaab + +/(?U)xa++b/D +------------------------------------------------------------------ + 0 15 Bra 0 + 3 x + 5 5 Once + 8 a+ + 10 5 Ket + 13 b + 15 15 Ket + 18 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: ungreedy +First char = 'x' +Need char = 'b' + xaaaab + 0: xaaaab + +/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/D +------------------------------------------------------------------ + 0 106 Bra 0 + 3 ^ + 4 99 Bra 1 + 7 5 Bra 2 + 10 a+ + 12 5 Ket + 15 37 Bra 3 + 18 [ab]+? + 52 37 Ket + 55 37 Bra 4 + 58 [bc]+ + 92 37 Ket + 95 5 Bra 5 + 98 \w* +100 5 Ket +103 99 Ket +106 106 Ket +109 End +------------------------------------------------------------------ +Capturing subpattern count = 5 +Partial matching not supported +Options: anchored +No first char +No need char + +/^x(?U)a+b/D +------------------------------------------------------------------ + 0 10 Bra 0 + 3 ^ + 4 x + 6 a+? + 8 b + 10 10 Ket + 13 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: anchored +No first char +Need char = 'b' + +/^x(?U)(a+)b/D +------------------------------------------------------------------ + 0 16 Bra 0 + 3 ^ + 4 x + 6 5 Bra 1 + 9 a+? + 11 5 Ket + 14 b + 16 16 Ket + 19 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Partial matching not supported +Options: anchored +No first char +Need char = 'b' + +/[.x.]/ +Failed: POSIX collating elements are not supported at offset 0 + +/[=x=]/ +Failed: POSIX collating elements are not supported at offset 0 + +/[:x:]/ +Failed: POSIX named classes are supported only within a class at offset 0 + +/\l/ +Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 + +/\L/ +Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 + +/\N{name}/ +Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 + +/\u/ +Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 + +/\U/ +Failed: PCRE does not support \L, \l, \N, \U, or \u at offset 1 + +/[/ +Failed: missing terminating ] for character class at offset 1 + +/[a-/ +Failed: missing terminating ] for character class at offset 3 + +/[[:space:]/ +Failed: missing terminating ] for character class at offset 10 + +/[\s]/DM +Memory allocation (code space): 40 +------------------------------------------------------------------ + 0 36 Bra 0 + 3 [\x09\x0a\x0c\x0d ] + 36 36 Ket + 39 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/[[:space:]]/DM +Memory allocation (code space): 40 +------------------------------------------------------------------ + 0 36 Bra 0 + 3 [\x09-\x0d ] + 36 36 Ket + 39 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/[[:space:]abcde]/DM +Memory allocation (code space): 40 +------------------------------------------------------------------ + 0 36 Bra 0 + 3 [\x09-\x0d a-e] + 36 36 Ket + 39 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/x +Capturing subpattern count = 0 +Partial matching not supported +Options: extended +First char = '<' +Need char = '>' + <> + 0: <> + + 0: + hij> + 0: hij> + hij> + 0: + def> + 0: def> + + 0: <> + *** Failers +No match + iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|DM +Memory allocation (code space): 826 +------------------------------------------------------------------ + 0 822 Bra 0 + 3 8J$WE<.rX+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDDqmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X +821 \b +822 822 Ket +825 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = '8' +Need char = 'X' + +|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|DM +Memory allocation (code space): 816 +------------------------------------------------------------------ + 0 812 Bra 0 + 3 $<.X+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDDqmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X +811 \b +812 812 Ket +815 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = '$' +Need char = 'X' + +/(.*)\d+\1/I +Capturing subpattern count = 1 +Max back reference = 1 +Partial matching not supported +No options +No first char +No need char + +/(.*)\d+/I +Capturing subpattern count = 1 +Partial matching not supported +No options +First char at start or follows newline +No need char + +/(.*)\d+\1/Is +Capturing subpattern count = 1 +Max back reference = 1 +Partial matching not supported +Options: dotall +No first char +No need char + +/(.*)\d+/Is +Capturing subpattern count = 1 +Partial matching not supported +Options: anchored dotall +No first char +No need char + +/(.*(xyz))\d+\2/I +Capturing subpattern count = 2 +Max back reference = 2 +Partial matching not supported +No options +First char at start or follows newline +Need char = 'z' + +/((.*))\d+\1/I +Capturing subpattern count = 2 +Max back reference = 1 +Partial matching not supported +No options +No first char +No need char + abc123bc + 0: bc123bc + 1: bc + 2: bc + +/a[b]/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'b' + +/(?=a).*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +First char = 'a' +No need char + +/(?=abc).xyz/iI +Capturing subpattern count = 0 +Options: caseless +First char = 'a' (caseless) +Need char = 'z' (caseless) + +/(?=abc)(?i).xyz/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'z' (caseless) + +/(?=a)(?=b)/I +Capturing subpattern count = 0 +No options +First char = 'a' +No need char + +/(?=.)a/I +Capturing subpattern count = 0 +No options +First char = 'a' +No need char + +/((?=abcda)a)/I +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'a' + +/((?=abcda)ab)/I +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'b' + +/()a/I +Capturing subpattern count = 1 +No options +No first char +Need char = 'a' + +/(?(1)ab|ac)/I +Capturing subpattern count = 0 +No options +First char = 'a' +No need char + +/(?(1)abz|acz)/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'z' + +/(?(1)abz)/I +Capturing subpattern count = 0 +No options +No first char +No need char + +/(?(1)abz)123/I +Capturing subpattern count = 0 +No options +No first char +Need char = '3' + +/(a)+/I +Capturing subpattern count = 1 +No options +First char = 'a' +No need char + +/(a){2,3}/I +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'a' + +/(a)*/I +Capturing subpattern count = 1 +No options +No first char +No need char + +/[a]/I +Capturing subpattern count = 0 +No options +First char = 'a' +No need char + +/[ab]/I +Capturing subpattern count = 0 +No options +No first char +No need char + +/[ab]/IS +Capturing subpattern count = 0 +No options +No first char +No need char +Starting byte set: a b + +/[^a]/I +Capturing subpattern count = 0 +No options +No first char +No need char + +/\d456/I +Capturing subpattern count = 0 +No options +No first char +Need char = '6' + +/\d456/IS +Capturing subpattern count = 0 +No options +No first char +Need char = '6' +Starting byte set: 0 1 2 3 4 5 6 7 8 9 + +/a^b/I +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'b' + +/^a/mI +Capturing subpattern count = 0 +Options: multiline +First char at start or follows newline +Need char = 'a' + abcde + 0: a + xy\nabc + 0: a + *** Failers +No match + xyabc +No match + +/c|abc/I +Capturing subpattern count = 0 +No options +No first char +Need char = 'c' + +/(?i)[ab]/IS +Capturing subpattern count = 0 +Options: caseless +No first char +No need char +Starting byte set: A B a b + +/[ab](?i)cd/IS +Capturing subpattern count = 0 +No options +No first char +Need char = 'd' (caseless) +Starting byte set: a b + +/abc(?C)def/ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'f' + abcdef +--->abcdef + 0 ^ ^ d + 0: abcdef + 1234abcdef +--->1234abcdef + 0 ^ ^ d + 0: abcdef + *** Failers +No match + abcxyz +No match + abcxyzf +--->abcxyzf + 0 ^ ^ d +No match + +/abc(?C)de(?C1)f/ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'f' + 123abcdef +--->123abcdef + 0 ^ ^ d + 1 ^ ^ f + 0: abcdef + +/(?C1)\dabc(?C2)def/ +Capturing subpattern count = 0 +No options +No first char +Need char = 'f' + 1234abcdef +--->1234abcdef + 1 ^ \d + 1 ^ \d + 1 ^ \d + 1 ^ \d + 2 ^ ^ d + 0: 4abcdef + *** Failers +No match + abcdef +--->abcdef + 1 ^ \d + 1 ^ \d + 1 ^ \d + 1 ^ \d + 1 ^ \d + 1 ^ \d +No match + +/(?C255)ab/ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'b' + +/(?C256)ab/ +Failed: number after (?C is > 255 at offset 6 + +/(?Cab)xx/ +Failed: closing ) for (?C expected at offset 3 + +/(?C12vr)x/ +Failed: closing ) for (?C expected at offset 5 + +/abc(?C)def/ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'f' + *** Failers +No match + \x83\x0\x61bcdef +--->\x83\x00abcdef + 0 ^ ^ d + 0: abcdef + +/(abc)(?C)de(?C1)f/ +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'f' + 123abcdef +--->123abcdef + 0 ^ ^ d + 1 ^ ^ f + 0: abcdef + 1: abc + 123abcdef\C+ +Callout 0: last capture = 1 + 0: + 1: abc +--->123abcdef + ^ ^ d +Callout 1: last capture = 1 + 0: + 1: abc +--->123abcdef + ^ ^ f + 0: abcdef + 1: abc + 123abcdef\C- + 0: abcdef + 1: abc + *** Failers +No match + 123abcdef\C!1 +--->123abcdef + 0 ^ ^ d + 1 ^ ^ f +No match + +/(?C0)(abc(?C1))*/ +Capturing subpattern count = 1 +No options +No first char +No need char + abcabcabc +--->abcabcabc + 0 ^ (abc(?C1))* + 1 ^ ^ ) + 1 ^ ^ ) + 1 ^ ^ ) + 0: abcabcabc + 1: abc + abcabc\C!1!3 +--->abcabc + 0 ^ (abc(?C1))* + 1 ^ ^ ) + 1 ^ ^ ) + 0: abcabc + 1: abc + *** Failers +--->*** Failers + 0 ^ (abc(?C1))* + 0: + abcabcabc\C!1!3 +--->abcabcabc + 0 ^ (abc(?C1))* + 1 ^ ^ ) + 1 ^ ^ ) + 1 ^ ^ ) + 0: abcabc + 1: abc + +/(\d{3}(?C))*/ +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +No need char + 123\C+ +Callout 0: last capture = -1 + 0: +--->123 + ^ ^ ) + 0: 123 + 1: 123 + 123456\C+ +Callout 0: last capture = -1 + 0: +--->123456 + ^ ^ ) +Callout 0: last capture = 1 + 0: + 1: 123 +--->123456 + ^ ^ ) + 0: 123456 + 1: 456 + 123456789\C+ +Callout 0: last capture = -1 + 0: +--->123456789 + ^ ^ ) +Callout 0: last capture = 1 + 0: + 1: 123 +--->123456789 + ^ ^ ) +Callout 0: last capture = 1 + 0: + 1: 456 +--->123456789 + ^ ^ ) + 0: 123456789 + 1: 789 + +/((xyz)(?C)p|(?C1)xyzabc)/ +Capturing subpattern count = 2 +No options +First char = 'x' +No need char + xyzabc\C+ +Callout 0: last capture = 2 + 0: + 1: + 2: xyz +--->xyzabc + ^ ^ p +Callout 1: last capture = -1 + 0: +--->xyzabc + ^ x + 0: xyzabc + 1: xyzabc + +/(X)((xyz)(?C)p|(?C1)xyzabc)/ +Capturing subpattern count = 3 +No options +First char = 'X' +Need char = 'x' + Xxyzabc\C+ +Callout 0: last capture = 3 + 0: + 1: X + 2: + 3: xyz +--->Xxyzabc + ^ ^ p +Callout 1: last capture = 1 + 0: + 1: X +--->Xxyzabc + ^^ x + 0: Xxyzabc + 1: X + 2: xyzabc + +/(?=(abc))(?C)abcdef/ +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'f' + abcdef\C+ +Callout 0: last capture = 1 + 0: + 1: abc +--->abcdef + ^ a + 0: abcdef + 1: abc + +/(?!(abc)(?C1)d)(?C2)abcxyz/ +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'z' + abcxyz\C+ +Callout 1: last capture = 1 + 0: + 1: abc +--->abcxyz + ^ ^ d +Callout 2: last capture = -1 + 0: +--->abcxyz + ^ a + 0: abcxyz + +/(?<=(abc)(?C))xyz/ +Capturing subpattern count = 1 +No options +First char = 'x' +Need char = 'z' + abcxyz\C+ +Callout 0: last capture = 1 + 0: + 1: abc +--->abcxyz + ^ ) + 0: xyz + 1: abc + +/a(b+)(c*)(?C1)/ +Capturing subpattern count = 2 +Partial matching not supported +No options +First char = 'a' +Need char = 'b' + abbbbbccc\C*1 +--->abbbbbccc + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 +No match + +/a(b+?)(c*?)(?C1)/ +Capturing subpattern count = 2 +Partial matching not supported +No options +First char = 'a' +Need char = 'b' + abbbbbccc\C*1 +--->abbbbbccc + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 + 1 ^ ^ +Callout data = 1 +No match + +/(?C)abc/ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'c' + +/(?C)^abc/ +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/(?C)a|b/S +Capturing subpattern count = 0 +No options +No first char +No need char +Starting byte set: a b + +/(?R)/ +Failed: recursive call could loop indefinitely at offset 3 + +/(a|(?R))/ +Failed: recursive call could loop indefinitely at offset 6 + +/(ab|(bc|(de|(?R))))/ +Failed: recursive call could loop indefinitely at offset 15 + +/x(ab|(bc|(de|(?R))))/ +Capturing subpattern count = 3 +No options +First char = 'x' +No need char + xab + 0: xab + 1: ab + xbc + 0: xbc + 1: bc + 2: bc + xde + 0: xde + 1: de + 2: de + 3: de + xxab + 0: xxab + 1: xab + 2: xab + 3: xab + xxxab + 0: xxxab + 1: xxab + 2: xxab + 3: xxab + *** Failers +No match + xyab +No match + +/(ab|(bc|(de|(?1))))/ +Failed: recursive call could loop indefinitely at offset 15 + +/x(ab|(bc|(de|(?1)x)x)x)/ +Failed: recursive call could loop indefinitely at offset 16 + +/^([^()]|\((?1)*\))*$/ +Capturing subpattern count = 1 +Options: anchored +No first char +No need char + abc + 0: abc + 1: c + a(b)c + 0: a(b)c + 1: c + a(b(c))d + 0: a(b(c))d + 1: d + *** Failers) +No match + a(b(c)d +No match + +/^>abc>([^()]|\((?1)*\))*abc>123abc>123abc>1(2)3abc>1(2)3abc>(1(2)3)abc>(1(2)3) + 2: + 3: Satan, oscillate my metallic sonatas + 4: S + A man, a plan, a canal: Panama! + 0: A man, a plan, a canal: Panama! + 1: + 2: + 3: A man, a plan, a canal: Panama + 4: A + Able was I ere I saw Elba. + 0: Able was I ere I saw Elba. + 1: + 2: + 3: Able was I ere I saw Elba + 4: A + *** Failers +No match + The quick brown fox +No match + +/^(\d+|\((?1)([+*-])(?1)\)|-(?1))$/ +Capturing subpattern count = 2 +Partial matching not supported +Options: anchored +No first char +No need char + 12 + 0: 12 + 1: 12 + (((2+2)*-3)-7) + 0: (((2+2)*-3)-7) + 1: (((2+2)*-3)-7) + 2: - + -12 + 0: -12 + 1: -12 + *** Failers +No match + ((2+2)*-3)-7) +No match + +/^(x(y|(?1){2})z)/ +Capturing subpattern count = 2 +Options: anchored +No first char +No need char + xyz + 0: xyz + 1: xyz + 2: y + xxyzxyzz + 0: xxyzxyzz + 1: xxyzxyzz + 2: xyzxyz + *** Failers +No match + xxyzz +No match + xxyzxyzxyzz +No match + +/((< (?: (?(R) \d++ | [^<>]*+) | (?2)) * >))/x +Capturing subpattern count = 2 +Partial matching not supported +Options: extended +First char = '<' +Need char = '>' + <> + 0: <> + 1: <> + 2: <> + + 0: + 1: + 2: + hij> + 0: hij> + 1: hij> + 2: hij> + hij> + 0: + 1: + 2: + def> + 0: def> + 1: def> + 2: def> + + 0: <> + 1: <> + 2: <> + *** Failers +No match + b|c)d(?Pe)/D +------------------------------------------------------------------ + 0 28 Bra 0 + 3 a + 5 5 Bra 1 + 8 b + 10 5 Alt + 13 c + 15 10 Ket + 18 d + 20 5 Bra 2 + 23 e + 25 5 Ket + 28 28 Ket + 31 End +------------------------------------------------------------------ +Capturing subpattern count = 2 +Named capturing subpatterns: + longername2 2 + name1 1 +No options +First char = 'a' +Need char = 'e' + abde + 0: abde + 1: b + 2: e + acde + 0: acde + 1: c + 2: e + +/(?:a(?Pc(?Pd)))(?Pa)/D +------------------------------------------------------------------ + 0 35 Bra 0 + 3 21 Bra 0 + 6 a + 8 13 Bra 1 + 11 c + 13 5 Bra 2 + 16 d + 18 5 Ket + 21 13 Ket + 24 21 Ket + 27 5 Bra 3 + 30 a + 32 5 Ket + 35 35 Ket + 38 End +------------------------------------------------------------------ +Capturing subpattern count = 3 +Named capturing subpatterns: + a 3 + c 1 + d 2 +No options +First char = 'a' +Need char = 'a' + +/(?Pa)...(?P=a)bbb(?P>a)d/D +------------------------------------------------------------------ + 0 34 Bra 0 + 3 5 Bra 1 + 6 a + 8 5 Ket + 11 Any + 12 Any + 13 Any + 14 \1 + 17 bbb + 23 6 Once + 26 3 Recurse + 29 6 Ket + 32 d + 34 34 Ket + 37 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Max back reference = 1 +Named capturing subpatterns: + a 1 +No options +First char = 'a' +Need char = 'd' + +/^\W*(?:(?P(?P.)\W*(?P>one)\W*(?P=two)|)|(?P(?P.)\W*(?P>three)\W*(?P=four)|\W*.\W*))\W*$/i +Capturing subpattern count = 4 +Max back reference = 4 +Named capturing subpatterns: + four 4 + one 1 + three 3 + two 2 +Partial matching not supported +Options: anchored caseless +No first char +No need char + 1221 + 0: 1221 + 1: 1221 + 2: 1 + Satan, oscillate my metallic sonatas! + 0: Satan, oscillate my metallic sonatas! + 1: + 2: + 3: Satan, oscillate my metallic sonatas + 4: S + A man, a plan, a canal: Panama! + 0: A man, a plan, a canal: Panama! + 1: + 2: + 3: A man, a plan, a canal: Panama + 4: A + Able was I ere I saw Elba. + 0: Able was I ere I saw Elba. + 1: + 2: + 3: Able was I ere I saw Elba + 4: A + *** Failers +No match + The quick brown fox +No match + +/((?(R)a|b))\1(?1)?/ +Capturing subpattern count = 1 +Max back reference = 1 +No options +No first char +No need char + bb + 0: bb + 1: b + bbaa + 0: bba + 1: b + +/(.*)a/sI +Capturing subpattern count = 1 +Partial matching not supported +Options: anchored dotall +No first char +Need char = 'a' + +/(.*)a\1/sI +Capturing subpattern count = 1 +Max back reference = 1 +Partial matching not supported +Options: dotall +No first char +Need char = 'a' + +/(.*)a(b)\2/sI +Capturing subpattern count = 2 +Max back reference = 2 +Partial matching not supported +Options: anchored dotall +No first char +Need char = 'b' + +/((.*)a|(.*)b)z/sI +Capturing subpattern count = 3 +Partial matching not supported +Options: anchored dotall +No first char +Need char = 'z' + +/((.*)a|(.*)b)z\1/sI +Capturing subpattern count = 3 +Max back reference = 1 +Partial matching not supported +Options: dotall +No first char +Need char = 'z' + +/((.*)a|(.*)b)z\2/sI +Capturing subpattern count = 3 +Max back reference = 2 +Partial matching not supported +Options: dotall +No first char +Need char = 'z' + +/((.*)a|(.*)b)z\3/sI +Capturing subpattern count = 3 +Max back reference = 3 +Partial matching not supported +Options: dotall +No first char +Need char = 'z' + +/((.*)a|^(.*)b)z\3/sI +Capturing subpattern count = 3 +Max back reference = 3 +Partial matching not supported +Options: anchored dotall +No first char +Need char = 'z' + +/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a/sI +Capturing subpattern count = 31 +Partial matching not supported +Options: anchored dotall +No first char +No need char + +/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\31/sI +Capturing subpattern count = 31 +Max back reference = 31 +Partial matching not supported +Options: dotall +No first char +No need char + +/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\32/sI +Capturing subpattern count = 32 +Max back reference = 32 +Partial matching not supported +Options: dotall +No first char +No need char + +/(a)(bc)/ND +------------------------------------------------------------------ + 0 21 Bra 0 + 3 5 Bra 0 + 6 a + 8 5 Ket + 11 7 Bra 0 + 14 bc + 18 7 Ket + 21 21 Ket + 24 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: no_auto_capture +First char = 'a' +Need char = 'c' + abc + 0: abc + +/(?Pa)(bc)/ND +------------------------------------------------------------------ + 0 21 Bra 0 + 3 5 Bra 1 + 6 a + 8 5 Ket + 11 7 Bra 0 + 14 bc + 18 7 Ket + 21 21 Ket + 24 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Named capturing subpatterns: + one 1 +Options: no_auto_capture +First char = 'a' +Need char = 'c' + abc + 0: abc + 1: a + +/(a)(?Pbc)/ND +------------------------------------------------------------------ + 0 21 Bra 0 + 3 5 Bra 0 + 6 a + 8 5 Ket + 11 7 Bra 1 + 14 bc + 18 7 Ket + 21 21 Ket + 24 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Named capturing subpatterns: + named 1 +Options: no_auto_capture +First char = 'a' +Need char = 'c' + +/(a+)*zz/ +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +Need char = 'z' + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazzbbbbbb\M +Minimum match() limit = 8 +Minimum match() recursion limit = 6 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazz + 1: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + aaaaaaaaaaaaaz\M +Minimum match() limit = 32768 +Minimum match() recursion limit = 42 +No match + +/(aaa(?C1)bbb|ab)/ +Capturing subpattern count = 1 +No options +First char = 'a' +Need char = 'b' + aaabbb +--->aaabbb + 1 ^ ^ b + 0: aaabbb + 1: aaabbb + aaabbb\C*0 +--->aaabbb + 1 ^ ^ b + 0: aaabbb + 1: aaabbb + aaabbb\C*1 +--->aaabbb + 1 ^ ^ b +Callout data = 1 + 0: ab + 1: ab + aaabbb\C*-1 +--->aaabbb + 1 ^ ^ b +Callout data = -1 +No match + +/ab(?Pcd)ef(?Pgh)/ +Capturing subpattern count = 2 +Named capturing subpatterns: + one 1 + two 2 +No options +First char = 'a' +Need char = 'h' + abcdefgh + 0: abcdefgh + 1: cd + 2: gh + abcdefgh\C1\Gtwo + 0: abcdefgh + 1: cd + 2: gh + 1C cd (2) + G gh (2) two + abcdefgh\Cone\Ctwo + 0: abcdefgh + 1: cd + 2: gh + C cd (2) one + C gh (2) two + abcdefgh\Cthree +no parentheses with name "three" + 0: abcdefgh + 1: cd + 2: gh +copy substring three failed -7 + +/(?P)(?P)/D +------------------------------------------------------------------ + 0 15 Bra 0 + 3 3 Bra 1 + 6 3 Ket + 9 3 Bra 2 + 12 3 Ket + 15 15 Ket + 18 End +------------------------------------------------------------------ +Capturing subpattern count = 2 +Named capturing subpatterns: + Tes 1 + Test 2 +No options +No first char +No need char + +/(?P)(?P)/D +------------------------------------------------------------------ + 0 15 Bra 0 + 3 3 Bra 1 + 6 3 Ket + 9 3 Bra 2 + 12 3 Ket + 15 15 Ket + 18 End +------------------------------------------------------------------ +Capturing subpattern count = 2 +Named capturing subpatterns: + Tes 2 + Test 1 +No options +No first char +No need char + +/(?Pzz)(?Paa)/ +Capturing subpattern count = 2 +Named capturing subpatterns: + A 2 + Z 1 +No options +First char = 'z' +Need char = 'a' + zzaa\CZ + 0: zzaa + 1: zz + 2: aa + C zz (2) Z + zzaa\CA + 0: zzaa + 1: zz + 2: aa + C aa (2) A + +/(?Peks)(?Peccs)/ +Failed: two named subpatterns have the same name at offset 16 + +/(?Pabc(?Pdef)(?Pxyz))/ +Failed: two named subpatterns have the same name at offset 31 + +"\[((?P\d+)(,(?P>elem))*)\]" +Capturing subpattern count = 3 +Named capturing subpatterns: + elem 2 +Partial matching not supported +No options +First char = '[' +Need char = ']' + [10,20,30,5,5,4,4,2,43,23,4234] + 0: [10,20,30,5,5,4,4,2,43,23,4234] + 1: 10,20,30,5,5,4,4,2,43,23,4234 + 2: 10 + 3: ,4234 + *** Failers +No match + [] +No match + +"\[((?P\d+)(,(?P>elem))*)?\]" +Capturing subpattern count = 3 +Named capturing subpatterns: + elem 2 +Partial matching not supported +No options +First char = '[' +Need char = ']' + [10,20,30,5,5,4,4,2,43,23,4234] + 0: [10,20,30,5,5,4,4,2,43,23,4234] + 1: 10,20,30,5,5,4,4,2,43,23,4234 + 2: 10 + 3: ,4234 + [] + 0: [] + +/(a(b(?2)c))?/D +------------------------------------------------------------------ + 0 31 Bra 0 + 3 Brazero + 4 24 Bra 1 + 7 a + 9 16 Bra 2 + 12 b + 14 6 Once + 17 9 Recurse + 20 6 Ket + 23 c + 25 16 Ket + 28 24 Ket + 31 31 Ket + 34 End +------------------------------------------------------------------ +Capturing subpattern count = 2 +No options +No first char +No need char + +/(a(b(?2)c))*/D +------------------------------------------------------------------ + 0 31 Bra 0 + 3 Brazero + 4 24 Bra 1 + 7 a + 9 16 Bra 2 + 12 b + 14 6 Once + 17 9 Recurse + 20 6 Ket + 23 c + 25 16 Ket + 28 24 KetRmax + 31 31 Ket + 34 End +------------------------------------------------------------------ +Capturing subpattern count = 2 +No options +No first char +No need char + +/(a(b(?2)c)){0,2}/D +------------------------------------------------------------------ + 0 65 Bra 0 + 3 Brazero + 4 58 Bra 0 + 7 24 Bra 1 + 10 a + 12 16 Bra 2 + 15 b + 17 6 Once + 20 12 Recurse + 23 6 Ket + 26 c + 28 16 Ket + 31 24 Ket + 34 Brazero + 35 24 Bra 1 + 38 a + 40 16 Bra 2 + 43 b + 45 6 Once + 48 12 Recurse + 51 6 Ket + 54 c + 56 16 Ket + 59 24 Ket + 62 58 Ket + 65 65 Ket + 68 End +------------------------------------------------------------------ +Capturing subpattern count = 2 +No options +No first char +No need char + +/[ab]{1}+/D +------------------------------------------------------------------ + 0 47 Bra 0 + 3 41 Once + 6 [ab]{1,1} + 44 41 Ket + 47 47 Ket + 50 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/i +Capturing subpattern count = 3 +Partial matching not supported +Options: caseless +No first char +Need char = 'g' (caseless) + Baby Bjorn Active Carrier - With free SHIPPING!! + 0: Baby Bjorn Active Carrier - With free SHIPPING!! + 1: Baby Bjorn Active Carrier - With free SHIPPING!! + +/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/iS +Capturing subpattern count = 3 +Partial matching not supported +Options: caseless +No first char +Need char = 'g' (caseless) +Study returned NULL + Baby Bjorn Active Carrier - With free SHIPPING!! + 0: Baby Bjorn Active Carrier - With free SHIPPING!! + 1: Baby Bjorn Active Carrier - With free SHIPPING!! + +/a*.*b/SD +------------------------------------------------------------------ + 0 9 Bra 0 + 3 a* + 5 Any* + 7 b + 9 9 Ket + 12 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +Need char = 'b' +Study returned NULL + +/(a|b)*.?c/SD +------------------------------------------------------------------ + 0 21 Bra 0 + 3 Brazero + 4 5 Bra 1 + 7 a + 9 5 Alt + 12 b + 14 10 KetRmax + 17 Any? + 19 c + 21 21 Ket + 24 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +No options +No first char +Need char = 'c' +Study returned NULL + +/abc(?C255)de(?C)f/D +------------------------------------------------------------------ + 0 27 Bra 0 + 3 abc + 9 Callout 255 10 1 + 15 de + 19 Callout 0 16 1 + 25 f + 27 27 Ket + 30 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'f' + +/abcde/CD +------------------------------------------------------------------ + 0 49 Bra 0 + 3 Callout 255 0 1 + 9 a + 11 Callout 255 1 1 + 17 b + 19 Callout 255 2 1 + 25 c + 27 Callout 255 3 1 + 33 d + 35 Callout 255 4 1 + 41 e + 43 Callout 255 5 0 + 49 49 Ket + 52 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: +First char = 'a' +Need char = 'e' + abcde +--->abcde + +0 ^ a + +1 ^^ b + +2 ^ ^ c + +3 ^ ^ d + +4 ^ ^ e + +5 ^ ^ + 0: abcde + abcdfe +--->abcdfe + +0 ^ a + +1 ^^ b + +2 ^ ^ c + +3 ^ ^ d + +4 ^ ^ e +No match + +/a*b/CD +------------------------------------------------------------------ + 0 25 Bra 0 + 3 Callout 255 0 2 + 9 a* + 11 Callout 255 2 1 + 17 b + 19 Callout 255 3 0 + 25 25 Ket + 28 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: +No first char +Need char = 'b' + ab +--->ab + +0 ^ a* + +2 ^^ b + +3 ^ ^ + 0: ab + aaaab +--->aaaab + +0 ^ a* + +2 ^ ^ b + +3 ^ ^ + 0: aaaab + aaaacb +--->aaaacb + +0 ^ a* + +2 ^ ^ b + +2 ^ ^ b + +2 ^ ^ b + +2 ^^ b + +2 ^ b + +0 ^ a* + +2 ^ ^ b + +2 ^ ^ b + +2 ^^ b + +2 ^ b + +0 ^ a* + +2 ^ ^ b + +2 ^^ b + +2 ^ b + +0 ^ a* + +2 ^^ b + +2 ^ b + +0 ^ a* + +2 ^ b + +0 ^ a* + +2 ^ b + +3 ^^ + 0: b + +/a+b/CD +------------------------------------------------------------------ + 0 25 Bra 0 + 3 Callout 255 0 2 + 9 a+ + 11 Callout 255 2 1 + 17 b + 19 Callout 255 3 0 + 25 25 Ket + 28 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: +First char = 'a' +Need char = 'b' + ab +--->ab + +0 ^ a+ + +2 ^^ b + +3 ^ ^ + 0: ab + aaaab +--->aaaab + +0 ^ a+ + +2 ^ ^ b + +3 ^ ^ + 0: aaaab + aaaacb +--->aaaacb + +0 ^ a+ + +2 ^ ^ b + +2 ^ ^ b + +2 ^ ^ b + +2 ^^ b + +0 ^ a+ + +2 ^ ^ b + +2 ^ ^ b + +2 ^^ b + +0 ^ a+ + +2 ^ ^ b + +2 ^^ b + +0 ^ a+ + +2 ^^ b +No match + +/(abc|def)x/CD +------------------------------------------------------------------ + 0 92 Bra 0 + 3 Callout 255 0 9 + 9 33 Bra 1 + 12 Callout 255 1 1 + 18 a + 20 Callout 255 2 1 + 26 b + 28 Callout 255 3 1 + 34 c + 36 Callout 255 4 0 + 42 33 Alt + 45 Callout 255 5 1 + 51 d + 53 Callout 255 6 1 + 59 e + 61 Callout 255 7 1 + 67 f + 69 Callout 255 8 0 + 75 66 Ket + 78 Callout 255 9 1 + 84 x + 86 Callout 255 10 0 + 92 92 Ket + 95 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Options: +No first char +Need char = 'x' + abcx +--->abcx + +0 ^ (abc|def) + +1 ^ a + +2 ^^ b + +3 ^ ^ c + +4 ^ ^ | + +9 ^ ^ x ++10 ^ ^ + 0: abcx + 1: abc + defx +--->defx + +0 ^ (abc|def) + +1 ^ a + +5 ^ d + +6 ^^ e + +7 ^ ^ f + +8 ^ ^ ) + +9 ^ ^ x ++10 ^ ^ + 0: defx + 1: def + abcdefzx +--->abcdefzx + +0 ^ (abc|def) + +1 ^ a + +2 ^^ b + +3 ^ ^ c + +4 ^ ^ | + +9 ^ ^ x + +5 ^ d + +0 ^ (abc|def) + +1 ^ a + +5 ^ d + +0 ^ (abc|def) + +1 ^ a + +5 ^ d + +0 ^ (abc|def) + +1 ^ a + +5 ^ d + +6 ^^ e + +7 ^ ^ f + +8 ^ ^ ) + +9 ^ ^ x + +0 ^ (abc|def) + +1 ^ a + +5 ^ d + +0 ^ (abc|def) + +1 ^ a + +5 ^ d + +0 ^ (abc|def) + +1 ^ a + +5 ^ d + +0 ^ (abc|def) + +1 ^ a + +5 ^ d +No match + +/(ab|cd){3,4}/C +Capturing subpattern count = 1 +Options: +No first char +No need char + ababab +--->ababab + +0 ^ (ab|cd){3,4} + +1 ^ a + +2 ^^ b + +3 ^ ^ | + +1 ^ ^ a + +2 ^ ^ b + +3 ^ ^ | + +1 ^ ^ a + +2 ^ ^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c ++12 ^ ^ + 0: ababab + 1: ab + abcdabcd +--->abcdabcd + +0 ^ (ab|cd){3,4} + +1 ^ a + +2 ^^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) + +1 ^ ^ a + +2 ^ ^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) ++12 ^ ^ + 0: abcdabcd + 1: cd + abcdcdcdcdcd +--->abcdcdcdcdcd + +0 ^ (ab|cd){3,4} + +1 ^ a + +2 ^^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) ++12 ^ ^ + 0: abcdcdcd + 1: cd + +/([ab]{,4}c|xy)/CD +------------------------------------------------------------------ + 0 131 Bra 0 + 3 Callout 255 0 14 + 9 88 Bra 1 + 12 Callout 255 1 4 + 18 [ab] + 51 Callout 255 5 1 + 57 { + 59 Callout 255 6 1 + 65 , + 67 Callout 255 7 1 + 73 4 + 75 Callout 255 8 1 + 81 } + 83 Callout 255 9 1 + 89 c + 91 Callout 255 10 0 + 97 25 Alt +100 Callout 255 11 1 +106 x +108 Callout 255 12 1 +114 y +116 Callout 255 13 0 +122 113 Ket +125 Callout 255 14 0 +131 131 Ket +134 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Options: +No first char +No need char + Note: that { does NOT introduce a quantifier +--->Note: that { does NOT introduce a quantifier + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] + +5 ^^ { ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] + +5 ^^ { ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] + +5 ^^ { ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x + +0 ^ ([ab]{,4}c|xy) + +1 ^ [ab] ++11 ^ x +No match + +/([ab]{1,4}c|xy){4,5}?123/CD +------------------------------------------------------------------ + 0 485 Bra 0 + 3 Callout 255 0 21 + 9 61 Bra 1 + 12 Callout 255 1 9 + 18 [ab]{1,4} + 56 Callout 255 10 1 + 62 c + 64 Callout 255 11 0 + 70 25 Alt + 73 Callout 255 12 1 + 79 x + 81 Callout 255 13 1 + 87 y + 89 Callout 255 14 0 + 95 86 Ket + 98 61 Bra 1 +101 Callout 255 1 9 +107 [ab]{1,4} +145 Callout 255 10 1 +151 c +153 Callout 255 11 0 +159 25 Alt +162 Callout 255 12 1 +168 x +170 Callout 255 13 1 +176 y +178 Callout 255 14 0 +184 86 Ket +187 61 Bra 1 +190 Callout 255 1 9 +196 [ab]{1,4} +234 Callout 255 10 1 +240 c +242 Callout 255 11 0 +248 25 Alt +251 Callout 255 12 1 +257 x +259 Callout 255 13 1 +265 y +267 Callout 255 14 0 +273 86 Ket +276 61 Bra 1 +279 Callout 255 1 9 +285 [ab]{1,4} +323 Callout 255 10 1 +329 c +331 Callout 255 11 0 +337 25 Alt +340 Callout 255 12 1 +346 x +348 Callout 255 13 1 +354 y +356 Callout 255 14 0 +362 86 Ket +365 Braminzero +366 61 Bra 1 +369 Callout 255 1 9 +375 [ab]{1,4} +413 Callout 255 10 1 +419 c +421 Callout 255 11 0 +427 25 Alt +430 Callout 255 12 1 +436 x +438 Callout 255 13 1 +444 y +446 Callout 255 14 0 +452 86 Ket +455 Callout 255 21 1 +461 1 +463 Callout 255 22 1 +469 2 +471 Callout 255 23 1 +477 3 +479 Callout 255 24 0 +485 485 Ket +488 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Partial matching not supported +Options: +No first char +Need char = '3' + aacaacaacaacaac123 +--->aacaacaacaacaac123 + +0 ^ ([ab]{1,4}c|xy){4,5}? + +1 ^ [ab]{1,4} ++10 ^ ^ c ++11 ^ ^ | + +1 ^ ^ [ab]{1,4} ++10 ^ ^ c ++11 ^ ^ | + +1 ^ ^ [ab]{1,4} ++10 ^ ^ c ++11 ^ ^ | + +1 ^ ^ [ab]{1,4} ++10 ^ ^ c ++11 ^ ^ | ++21 ^ ^ 1 + +1 ^ ^ [ab]{1,4} ++10 ^ ^ c ++11 ^ ^ | ++21 ^ ^ 1 ++22 ^ ^ 2 ++23 ^ ^ 3 ++24 ^ ^ + 0: aacaacaacaacaac123 + 1: aac + +/\b.*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + ab cd\>1 + 0: cd + +/\b.*/Is +Capturing subpattern count = 0 +Partial matching not supported +Options: dotall +No first char +No need char + ab cd\>1 + 0: cd + +/(?!.bcd).*/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + Xbcd12345 + 0: bcd12345 + +/abcde/ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'e' + ab\P +Partial match + abc\P +Partial match + abcd\P +Partial match + abcde\P + 0: abcde + the quick brown abc\P +Partial match + ** Failers\P +No match + the quick brown abxyz fox\P +No match + +"^(0?[1-9]|[12][0-9]|3[01])/(0?[1-9]|1[012])/(20)?\d\d$" +Capturing subpattern count = 3 +Options: anchored +No first char +Need char = '/' + 13/05/04\P + 0: 13/05/04 + 1: 13 + 2: 05 + 13/5/2004\P + 0: 13/5/2004 + 1: 13 + 2: 5 + 3: 20 + 02/05/09\P + 0: 02/05/09 + 1: 02 + 2: 05 + 1\P +Partial match + 1/2\P +Partial match + 1/2/0\P +Partial match + 1/2/04\P + 0: 1/2/04 + 1: 1 + 2: 2 + 0\P +Partial match + 02/\P +Partial match + 02/0\P +Partial match + 02/1\P +Partial match + ** Failers\P +No match + \P +No match + 123\P +No match + 33/4/04\P +No match + 3/13/04\P +No match + 0/1/2003\P +No match + 0/\P +No match + 02/0/\P +No match + 02/13\P +No match + +/0{0,2}ABC/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +Need char = 'C' + +/\d{3,}ABC/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +Need char = 'C' + +/\d*ABC/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +Need char = 'C' + +/[abc]+DE/I +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +Need char = 'E' + +/[abc]?123/ +Capturing subpattern count = 0 +No options +No first char +Need char = '3' + 123\P + 0: 123 + a\P +Partial match + b\P +Partial match + c\P +Partial match + c12\P +Partial match + c123\P + 0: c123 + +/^(?:\d){3,5}X/ +Capturing subpattern count = 0 +Options: anchored +No first char +Need char = 'X' + 1\P +Partial match + 123\P +Partial match + 123X + 0: 123X + 1234\P +Partial match + 1234X + 0: 1234X + 12345\P +Partial match + 12345X + 0: 12345X + *** Failers +No match + 1X +No match + 123456\P +No match + +/abc/>testsavedregex +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'c' +Compiled regex written to testsavedregex +testsavedregex +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'c' +Compiled regex written to testsavedregex +testsavedregex +Capturing subpattern count = 1 +No options +No first char +No need char +Starting byte set: a b +Compiled regex written to testsavedregex +Study data written to testsavedregex +testsavedregex +Capturing subpattern count = 1 +No options +No first char +No need char +Starting byte set: a b +Compiled regex written to testsavedregex +Study data written to testsavedregex +(.)*~smg +Capturing subpattern count = 3 +Max back reference = 1 +Partial matching not supported +Options: multiline dotall +First char = '<' +Need char = '>' + \n\n\nPartner der LCO\nde\nPartner der LINEAS Consulting\nGmbH\nLINEAS Consulting GmbH Hamburg\nPartnerfirmen\n30 days\nindex,follow\n\nja\n3\nPartner\n\n\nLCO\nLINEAS Consulting\n15.10.2003\n\n\n\n\nDie Partnerfirmen der LINEAS Consulting\nGmbH\n\n\n \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n + 0: \x0a\x0aPartner der LCO\x0ade\x0aPartner der LINEAS Consulting\x0aGmbH\x0aLINEAS Consulting GmbH Hamburg\x0aPartnerfirmen\x0a30 days\x0aindex,follow\x0a\x0aja\x0a3\x0aPartner\x0a\x0a\x0aLCO\x0aLINEAS Consulting\x0a15.10.2003\x0a\x0a\x0a\x0a\x0aDie Partnerfirmen der LINEAS Consulting\x0aGmbH\x0a\x0a\x0a \x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a\x0a + 1: seite + 2: \x0a + 3: seite + +/^a/IF +Capturing subpattern count = 0 +Options: anchored +No first char +No need char + +/line\nbreak/ +Capturing subpattern count = 0 +No options +First char = 'l' +Need char = 'k' + this is a line\nbreak + 0: line\x0abreak + line one\nthis is a line\nbreak in the second line + 0: line\x0abreak + +/line\nbreak/f +Capturing subpattern count = 0 +Options: firstline +First char = 'l' +Need char = 'k' + this is a line\nbreak + 0: line\x0abreak + ** Failers +No match + line one\nthis is a line\nbreak in the second line +No match + +/line\nbreak/mf +Capturing subpattern count = 0 +Options: multiline firstline +First char = 'l' +Need char = 'k' + this is a line\nbreak + 0: line\x0abreak + ** Failers +No match + line one\nthis is a line\nbreak in the second line +No match + +/ab.cd/P + ab-cd + 0: ab-cd + ab=cd + 0: ab=cd + ** Failers +No match: POSIX code 17: match failed + ab\ncd +No match: POSIX code 17: match failed + +/ab.cd/Ps + ab-cd + 0: ab-cd + ab=cd + 0: ab=cd + ab\ncd + 0: ab\x0acd + +/(?i)(?-i)AbCd/ +Capturing subpattern count = 0 +No options +First char = 'A' +Need char = 'd' + AbCd + 0: AbCd + ** Failers +No match + abcd +No match + +/a{11111111111111111111}/ +Failed: number too big in {} quantifier at offset 22 + +/(){64294967295}/ +Failed: number too big in {} quantifier at offset 14 + +/(){2,4294967295}/ +Failed: number too big in {} quantifier at offset 15 + +"(?i:a)(?i:b)(?i:c)(?i:d)(?i:e)(?i:f)(?i:g)(?i:h)(?i:i)(?i:j)(k)(?i:l)A\1B" +Capturing subpattern count = 1 +Max back reference = 1 +No options +First char = 'a' (caseless) +Need char = 'B' + abcdefghijklAkB + 0: abcdefghijklAkB + 1: k + +"(?Pa)(?Pb)(?Pc)(?Pd)(?Pe)(?Pf)(?Pg)(?Ph)(?Pi)(?Pj)(?Pk)(?Pl)A\11B" +Capturing subpattern count = 12 +Max back reference = 11 +Named capturing subpatterns: + n0 1 + n1 2 + n10 11 + n11 12 + n2 3 + n3 4 + n4 5 + n5 6 + n6 7 + n7 8 + n8 9 + n9 10 +No options +First char = 'a' +Need char = 'B' + abcdefghijklAkB + 0: abcdefghijklAkB + 1: a + 2: b + 3: c + 4: d + 5: e + 6: f + 7: g + 8: h + 9: i +10: j +11: k +12: l + +"(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)A\11B" +Capturing subpattern count = 12 +Max back reference = 11 +No options +First char = 'a' +Need char = 'B' + abcdefghijklAkB + 0: abcdefghijklAkB + 1: a + 2: b + 3: c + 4: d + 5: e + 6: f + 7: g + 8: h + 9: i +10: j +11: k +12: l + +"(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)(?Pa)" +Capturing subpattern count = 101 +Named capturing subpatterns: + name0 1 + name1 2 + name10 11 + name100 101 + name11 12 + name12 13 + name13 14 + name14 15 + name15 16 + name16 17 + name17 18 + name18 19 + name19 20 + name2 3 + name20 21 + name21 22 + name22 23 + name23 24 + name24 25 + name25 26 + name26 27 + name27 28 + name28 29 + name29 30 + name3 4 + name30 31 + name31 32 + name32 33 + name33 34 + name34 35 + name35 36 + name36 37 + name37 38 + name38 39 + name39 40 + name4 5 + name40 41 + name41 42 + name42 43 + name43 44 + name44 45 + name45 46 + name46 47 + name47 48 + name48 49 + name49 50 + name5 6 + name50 51 + name51 52 + name52 53 + name53 54 + name54 55 + name55 56 + name56 57 + name57 58 + name58 59 + name59 60 + name6 7 + name60 61 + name61 62 + name62 63 + name63 64 + name64 65 + name65 66 + name66 67 + name67 68 + name68 69 + name69 70 + name7 8 + name70 71 + name71 72 + name72 73 + name73 74 + name74 75 + name75 76 + name76 77 + name77 78 + name78 79 + name79 80 + name8 9 + name80 81 + name81 82 + name82 83 + name83 84 + name84 85 + name85 86 + name86 87 + name87 88 + name88 89 + name89 90 + name9 10 + name90 91 + name91 92 + name92 93 + name93 94 + name94 95 + name95 96 + name96 97 + name97 98 + name98 99 + name99 100 +No options +First char = 'a' +Need char = 'a' + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +Matched, but too many substrings + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 1: a + 2: a + 3: a + 4: a + 5: a + 6: a + 7: a + 8: a + 9: a +10: a +11: a +12: a +13: a +14: a + +"(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)" +Capturing subpattern count = 101 +No options +First char = 'a' +Need char = 'a' + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +Matched, but too many substrings + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 1: a + 2: a + 3: a + 4: a + 5: a + 6: a + 7: a + 8: a + 9: a +10: a +11: a +12: a +13: a +14: a + +/[^()]*(?:\((?R)\)[^()]*)*/ +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + (this(and)that + 0: + (this(and)that) + 0: (this(and)that) + (this(and)that)stuff + 0: (this(and)that)stuff + +/[^()]*(?:\((?>(?R))\)[^()]*)*/ +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + (this(and)that + 0: + (this(and)that) + 0: (this(and)that) + +/[^()]*(?:\((?R)\))*[^()]*/ +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + (this(and)that + 0: + (this(and)that) + 0: (this(and)that) + +/(?:\((?R)\))*[^()]*/ +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + (this(and)that + 0: + (this(and)that) + 0: + ((this)) + 0: ((this)) + +/(?:\((?R)\))|[^()]*/ +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +No need char + (this(and)that + 0: + (this(and)that) + 0: + (this) + 0: (this) + ((this)) + 0: ((this)) + +/a(b)c/PN + abc +Matched with REG_NOSUB + +/a(?Pb)c/PN + abc +Matched with REG_NOSUB + +/\x{100}/ +Failed: character value in \x{...} sequence is too large at offset 6 + +/\x{0000ff}/ +Capturing subpattern count = 0 +No options +First char = 255 +No need char + +/^((?Pa1)|(?Pa2)b)/ +Failed: two named subpatterns have the same name at offset 18 + +/^((?Pa1)|(?Pa2)b)/J +Capturing subpattern count = 3 +Named capturing subpatterns: + A 2 + A 3 +Options: anchored dupnames +No first char +No need char + a1b\CA + 0: a1 + 1: a1 + 2: a1 + C a1 (2) A + a2b\CA + 0: a2b + 1: a2b + 2: + 3: a2 + C a2 (2) A + ** Failers +No match + a1b\CZ\CA +no parentheses with name "Z" + 0: a1 + 1: a1 + 2: a1 +copy substring Z failed -7 + C a1 (2) A + +/^(?Pa)(?Pb)/J +Capturing subpattern count = 2 +Named capturing subpatterns: + A 1 + A 2 +Options: anchored dupnames +No first char +No need char + ab\CA + 0: ab + 1: a + 2: b + C a (1) A + +/^(?Pa)(?Pb)|cd/J +Capturing subpattern count = 2 +Named capturing subpatterns: + A 1 + A 2 +Options: dupnames +No first char +No need char + ab\CA + 0: ab + 1: a + 2: b + C a (1) A + cd\CA + 0: cd +copy substring A failed -7 + +/^(?Pa)(?Pb)|cd(?Pef)(?Pgh)/J +Capturing subpattern count = 4 +Named capturing subpatterns: + A 1 + A 2 + A 3 + A 4 +Options: dupnames +No first char +No need char + cdefgh\CA + 0: cdefgh + 1: + 2: + 3: ef + 4: gh + C ef (2) A + +/^((?Pa1)|(?Pa2)b)/J +Capturing subpattern count = 3 +Named capturing subpatterns: + A 2 + A 3 +Options: anchored dupnames +No first char +No need char + a1b\GA + 0: a1 + 1: a1 + 2: a1 + G a1 (2) A + a2b\GA + 0: a2b + 1: a2b + 2: + 3: a2 + G a2 (2) A + ** Failers +No match + a1b\GZ\GA +no parentheses with name "Z" + 0: a1 + 1: a1 + 2: a1 +copy substring Z failed -7 + G a1 (2) A + +/^(?Pa)(?Pb)/J +Capturing subpattern count = 2 +Named capturing subpatterns: + A 1 + A 2 +Options: anchored dupnames +No first char +No need char + ab\GA + 0: ab + 1: a + 2: b + G a (1) A + +/^(?Pa)(?Pb)|cd/J +Capturing subpattern count = 2 +Named capturing subpatterns: + A 1 + A 2 +Options: dupnames +No first char +No need char + ab\GA + 0: ab + 1: a + 2: b + G a (1) A + cd\GA + 0: cd +copy substring A failed -7 + +/^(?Pa)(?Pb)|cd(?Pef)(?Pgh)/J +Capturing subpattern count = 4 +Named capturing subpatterns: + A 1 + A 2 + A 3 + A 4 +Options: dupnames +No first char +No need char + cdefgh\GA + 0: cdefgh + 1: + 2: + 3: ef + 4: gh + G ef (2) A + +/(?J)^((?Pa1)|(?Pa2)b)/ +Capturing subpattern count = 3 +Named capturing subpatterns: + A 2 + A 3 +Options: anchored dupnames +No first char +No need char + a1b\CA + 0: a1 + 1: a1 + 2: a1 + C a1 (2) A + a2b\CA + 0: a2b + 1: a2b + 2: + 3: a2 + C a2 (2) A + +/^(?Pa) (?J:(?Pb)(?Pc)) (?Pd)/ +Failed: two named subpatterns have the same name at offset 38 + +/ In this next test, J is not set at the outer level; consequently it isn't +set in the pattern's options; consequently pcre_get_named_substring() produces +a random value. /x +Capturing subpattern count = 1 +Options: extended +First char = 'I' +Need char = 'e' + +/^(?Pa) (?J:(?Pb)(?Pc)) (?Pd)/ +Capturing subpattern count = 4 +Named capturing subpatterns: + A 1 + B 2 + B 3 + C 4 +Options: anchored +No first char +No need char + a bc d\CA\CB\CC + 0: a bc d + 1: a + 2: b + 3: c + 4: d + C a (1) A + C b (1) B + C d (1) C + +/^(?Pa)?(?(A)a|b)/ +Capturing subpattern count = 1 +Named capturing subpatterns: + A 1 +Options: anchored +No first char +No need char + aabc + 0: aa + 1: a + bc + 0: b + ** Failers +No match + abc +No match + +/(?:(?(ZZ)a|b)(?PX))+/ +Capturing subpattern count = 1 +Named capturing subpatterns: + ZZ 1 +No options +No first char +Need char = 'X' + bXaX + 0: bXaX + 1: X + +/(?:(?(2y)a|b)(X))+/ +Failed: reference to non-existent subpattern at offset 9 + +/(?:(?(ZA)a|b)(?PX))+/ +Failed: reference to non-existent subpattern at offset 9 + +/(?:(?(ZZ)a|b)(?(ZZ)a|b)(?PX))+/ +Capturing subpattern count = 1 +Named capturing subpatterns: + ZZ 1 +No options +No first char +Need char = 'X' + bbXaaX + 0: bbXaaX + 1: X + +/(?:(?(ZZ)a|\(b\))\\(?PX))+/ +Capturing subpattern count = 1 +Named capturing subpatterns: + ZZ 1 +No options +No first char +Need char = 'X' + (b)\\Xa\\X + 0: (b)\Xa\X + 1: X + +/(?PX|Y))+/ +Capturing subpattern count = 1 +Max back reference = 1 +Named capturing subpatterns: + A 1 +No options +No first char +No need char + bXXaYYaY + 0: bXXaYYaY + 1: Y + bXYaXXaX + 0: bX + 1: X + +/()()()()()()()()()(?:(?(A)(?P=A)a|b)(?PX|Y))+/ +Capturing subpattern count = 10 +Max back reference = 10 +Named capturing subpatterns: + A 10 +No options +No first char +No need char + bXXaYYaY + 0: bXXaYYaY + 1: + 2: + 3: + 4: + 5: + 6: + 7: + 8: + 9: +10: Y + +/\777/ +Failed: octal value is greater than \377 (not in UTF-8 mode) at offset 3 + +/\s*,\s*/S +Capturing subpattern count = 0 +Partial matching not supported +No options +No first char +Need char = ',' +Starting byte set: \x09 \x0a \x0c \x0d \x20 , + \x0b,\x0b + 0: , + \x0c,\x0d + 0: \x0c,\x0d + +/^abc/m +Capturing subpattern count = 0 +Options: multiline +First char at start or follows newline +Need char = 'c' + xyz\nabc + 0: abc + xyz\nabc\ + 0: abc + xyz\r\nabc\ + 0: abc + xyz\rabc\ + 0: abc + xyz\r\nabc\ + 0: abc + ** Failers +No match + xyz\nabc\ +No match + xyz\r\nabc\ +No match + xyz\nabc\ +No match + xyz\rabc\ +No match + xyz\rabc\ +No match + +/abc$/m +Capturing subpattern count = 0 +Options: multiline +First char = 'a' +Need char = 'c' + xyzabc + 0: abc + xyzabc\n + 0: abc + xyzabc\npqr + 0: abc + xyzabc\r\ + 0: abc + xyzabc\rpqr\ + 0: abc + xyzabc\r\n\ + 0: abc + xyzabc\r\npqr\ + 0: abc + ** Failers +No match + xyzabc\r +No match + xyzabc\rpqr +No match + xyzabc\r\n +No match + xyzabc\r\npqr +No match + +/^abc/m +Capturing subpattern count = 0 +Options: multiline +Forced newline sequence: CR +First char at start or follows newline +Need char = 'c' + xyz\rabcdef + 0: abc + xyz\nabcdef\ + 0: abc + ** Failers +No match + xyz\nabcdef +No match + +/^abc/m +Capturing subpattern count = 0 +Options: multiline +Forced newline sequence: LF +First char at start or follows newline +Need char = 'c' + xyz\nabcdef + 0: abc + xyz\rabcdef\ + 0: abc + ** Failers +No match + xyz\rabcdef +No match + +/^abc/m +Capturing subpattern count = 0 +Options: multiline +Forced newline sequence: CRLF +First char at start or follows newline +Need char = 'c' + xyz\r\nabcdef + 0: abc + xyz\rabcdef\ + 0: abc + ** Failers +No match + xyz\rabcdef +No match + +/^abc/m +Unknown newline type at: + + +/abc/ +Capturing subpattern count = 0 +No options +First char = 'a' +Need char = 'c' + xyz\rabc\ +Unknown newline type at: + abc + 0: abc + +/.*/ +Capturing subpattern count = 0 +Partial matching not supported +No options +First char at start or follows newline +No need char + abc\ndef + 0: abc + abc\rdef + 0: abc\x0ddef + abc\r\ndef + 0: abc\x0d + \abc\ndef + 0: abc\x0adef + \abc\rdef + 0: abc + \abc\r\ndef + 0: abc + \abc\ndef + 0: abc\x0adef + \abc\rdef + 0: abc\x0ddef + \abc\r\ndef + 0: abc + +/\w+(.)(.)?def/s +Capturing subpattern count = 2 +Partial matching not supported +Options: dotall +No first char +Need char = 'f' + abc\ndef + 0: abc\x0adef + 1: \x0a + abc\rdef + 0: abc\x0ddef + 1: \x0d + abc\r\ndef + 0: abc\x0d\x0adef + 1: \x0d + 2: \x0a + ++((?:\s|//.*\\n|/[*](?:\\n|.)*?[*]/)*)+ +Capturing subpattern count = 1 +Partial matching not supported +No options +No first char +No need char + /* this is a C style comment */\M +Minimum match() limit = 120 +Minimum match() recursion limit = 6 + 0: /* this is a C style comment */ + 1: /* this is a C style comment */ + +/(?P25[0-5]|2[0-4]\d|[01]?\d?\d)(?:\.(?P>B)){3}/ +Capturing subpattern count = 1 +Named capturing subpatterns: + B 1 +No options +No first char +Need char = '.' + +/ End of testinput2 / +Capturing subpattern count = 0 +No options +First char = ' ' +Need char = ' ' diff --git a/libs/pcre/testdata/testoutput3 b/libs/pcre/testdata/testoutput3 new file mode 100644 index 0000000000..06e2888d91 --- /dev/null +++ b/libs/pcre/testdata/testoutput3 @@ -0,0 +1,163 @@ +/^[\w]+/ + *** Failers +No match + École +No match + +/^[\w]+/Lfr_FR + École + 0: École + +/^[\w]+/ + *** Failers +No match + École +No match + +/^[\W]+/ + École + 0: \xc9 + +/^[\W]+/Lfr_FR + *** Failers + 0: *** + École +No match + +/[\b]/ + \b + 0: \x08 + *** Failers +No match + a +No match + +/[\b]/Lfr_FR + \b + 0: \x08 + *** Failers +No match + a +No match + +/^\w+/ + *** Failers +No match + École +No match + +/^\w+/Lfr_FR + École + 0: École + +/(.+)\b(.+)/ + École + 0: \xc9cole + 1: \xc9 + 2: cole + +/(.+)\b(.+)/Lfr_FR + *** Failers + 0: *** Failers + 1: *** + 2: Failers + École +No match + +/École/i + École + 0: \xc9cole + *** Failers +No match + école +No match + +/École/iLfr_FR + École + 0: École + école + 0: école + +/\w/IS +Capturing subpattern count = 0 +No options +No first char +No need char +Starting byte set: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P + Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z + +/\w/ISLfr_FR +Capturing subpattern count = 0 +No options +No first char +No need char +Starting byte set: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P + Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z + ª µ º À Á Â Ã Ä Å Æ Ç È É Ê Ë Ì Í Î Ï Ð Ñ Ò Ó Ô Õ Ö Ø Ù Ú Û Ü Ý Þ ß à á â + ã ä å æ ç è é ê ë ì í î ï ð ñ ò ó ô õ ö ø ù ú û ü ý þ ÿ + +/^[\xc8-\xc9]/iLfr_FR + École + 0: É + école + 0: é + +/^[\xc8-\xc9]/Lfr_FR + École + 0: É + *** Failers +No match + école +No match + +/\W+/Lfr_FR + >>>\xaa<<< + 0: >>> + >>>\xba<<< + 0: >>> + +/[\W]+/Lfr_FR + >>>\xaa<<< + 0: >>> + >>>\xba<<< + 0: >>> + +/[^[:alpha:]]+/Lfr_FR + >>>\xaa<<< + 0: >>> + >>>\xba<<< + 0: >>> + +/\w+/Lfr_FR + >>>\xaa<<< + 0: ª + >>>\xba<<< + 0: º + +/[\w]+/Lfr_FR + >>>\xaa<<< + 0: ª + >>>\xba<<< + 0: º + +/[[:alpha:]]+/Lfr_FR + >>>\xaa<<< + 0: ª + >>>\xba<<< + 0: º + +/[[:alpha:]][[:lower:]][[:upper:]]/DLfr_FR +------------------------------------------------------------------ + 0 102 Bra 0 + 3 [A-Za-zªµºÀ-ÖØ-öø-ÿ] + 36 [a-zµß-öø-ÿ] + 69 [A-ZÀ-ÖØ-Þ] +102 102 Ket +105 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/ End of testinput3 / diff --git a/libs/pcre/testdata/testoutput4 b/libs/pcre/testdata/testoutput4 new file mode 100644 index 0000000000..3b49455075 --- /dev/null +++ b/libs/pcre/testdata/testoutput4 @@ -0,0 +1,917 @@ +/-- Do not use the \x{} construct except with patterns that have the --/ +/-- /8 option set, because PCRE doesn't recognize them as UTF-8 unless --/ +No match +/-- that option is set. However, the latest Perls recognize them always. --/ +No match + +/a.b/8 + acb + 0: acb + a\x7fb + 0: a\x{7f}b + a\x{100}b + 0: a\x{100}b + *** Failers +No match + a\nb +No match + +/a(.{3})b/8 + a\x{4000}xyb + 0: a\x{4000}xyb + 1: \x{4000}xy + a\x{4000}\x7fyb + 0: a\x{4000}\x{7f}yb + 1: \x{4000}\x{7f}y + a\x{4000}\x{100}yb + 0: a\x{4000}\x{100}yb + 1: \x{4000}\x{100}y + *** Failers +No match + a\x{4000}b +No match + ac\ncb +No match + +/a(.*?)(.)/ + a\xc0\x88b + 0: a\xc0 + 1: + 2: \xc0 + +/a(.*?)(.)/8 + a\x{100}b + 0: a\x{100} + 1: + 2: \x{100} + +/a(.*)(.)/ + a\xc0\x88b + 0: a\xc0\x88b + 1: \xc0\x88 + 2: b + +/a(.*)(.)/8 + a\x{100}b + 0: a\x{100}b + 1: \x{100} + 2: b + +/a(.)(.)/ + a\xc0\x92bcd + 0: a\xc0\x92 + 1: \xc0 + 2: \x92 + +/a(.)(.)/8 + a\x{240}bcd + 0: a\x{240}b + 1: \x{240} + 2: b + +/a(.?)(.)/ + a\xc0\x92bcd + 0: a\xc0\x92 + 1: \xc0 + 2: \x92 + +/a(.?)(.)/8 + a\x{240}bcd + 0: a\x{240}b + 1: \x{240} + 2: b + +/a(.??)(.)/ + a\xc0\x92bcd + 0: a\xc0 + 1: + 2: \xc0 + +/a(.??)(.)/8 + a\x{240}bcd + 0: a\x{240} + 1: + 2: \x{240} + +/a(.{3})b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + 1: \x{1234}xy + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + 1: \x{1234}\x{4321}y + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + 1: \x{1234}\x{4321}\x{3412} + *** Failers +No match + a\x{1234}b +No match + ac\ncb +No match + +/a(.{3,})b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + 1: \x{1234}xy + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + 1: \x{1234}\x{4321}y + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + 1: \x{1234}\x{4321}\x{3412} + axxxxbcdefghijb + 0: axxxxbcdefghijb + 1: xxxxbcdefghij + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + 1: \x{1234}\x{4321}\x{3412}\x{3421} + *** Failers +No match + a\x{1234}b +No match + +/a(.{3,}?)b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + 1: \x{1234}xy + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + 1: \x{1234}\x{4321}y + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + 1: \x{1234}\x{4321}\x{3412} + axxxxbcdefghijb + 0: axxxxb + 1: xxxx + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + 1: \x{1234}\x{4321}\x{3412}\x{3421} + *** Failers +No match + a\x{1234}b +No match + +/a(.{3,5})b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + 1: \x{1234}xy + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + 1: \x{1234}\x{4321}y + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + 1: \x{1234}\x{4321}\x{3412} + axxxxbcdefghijb + 0: axxxxb + 1: xxxx + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + 1: \x{1234}\x{4321}\x{3412}\x{3421} + axbxxbcdefghijb + 0: axbxxb + 1: xbxx + axxxxxbcdefghijb + 0: axxxxxb + 1: xxxxx + *** Failers +No match + a\x{1234}b +No match + axxxxxxbcdefghijb +No match + +/a(.{3,5}?)b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + 1: \x{1234}xy + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + 1: \x{1234}\x{4321}y + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + 1: \x{1234}\x{4321}\x{3412} + axxxxbcdefghijb + 0: axxxxb + 1: xxxx + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + 1: \x{1234}\x{4321}\x{3412}\x{3421} + axbxxbcdefghijb + 0: axbxxb + 1: xbxx + axxxxxbcdefghijb + 0: axxxxxb + 1: xxxxx + *** Failers +No match + a\x{1234}b +No match + axxxxxxbcdefghijb +No match + +/^[a\x{c0}]/8 + *** Failers +No match + \x{100} +No match + +/(?<=aXb)cd/8 + aXbcd + 0: cd + +/(?<=a\x{100}b)cd/8 + a\x{100}bcd + 0: cd + +/(?<=a\x{100000}b)cd/8 + a\x{100000}bcd + 0: cd + +/(?:\x{100}){3}b/8 + \x{100}\x{100}\x{100}b + 0: \x{100}\x{100}\x{100}b + *** Failers +No match + \x{100}\x{100}b +No match + +/\x{ab}/8 + \x{ab} + 0: \x{ab} + \xc2\xab + 0: \x{ab} + *** Failers +No match + \x00{ab} +No match + +/(?<=(.))X/8 + WXYZ + 0: X + 1: W + \x{256}XYZ + 0: X + 1: \x{256} + *** Failers +No match + XYZ +No match + +/X(\C{3})/8 + X\x{1234} + 0: X\x{1234} + 1: \x{1234} + +/X(\C{4})/8 + X\x{1234}YZ + 0: X\x{1234}Y + 1: \x{1234}Y + +/X\C*/8 + XYZabcdce + 0: XYZabcdce + +/X\C*?/8 + XYZabcde + 0: X + +/X\C{3,5}/8 + Xabcdefg + 0: Xabcde + X\x{1234} + 0: X\x{1234} + X\x{1234}YZ + 0: X\x{1234}YZ + X\x{1234}\x{512} + 0: X\x{1234}\x{512} + X\x{1234}\x{512}YZ + 0: X\x{1234}\x{512} + +/X\C{3,5}?/8 + Xabcdefg + 0: Xabc + X\x{1234} + 0: X\x{1234} + X\x{1234}YZ + 0: X\x{1234} + X\x{1234}\x{512} + 0: X\x{1234} + +/[^a]+/8g + bcd + 0: bcd + \x{100}aY\x{256}Z + 0: \x{100} + 0: Y\x{256}Z + +/^[^a]{2}/8 + \x{100}bc + 0: \x{100}b + +/^[^a]{2,}/8 + \x{100}bcAa + 0: \x{100}bcA + +/^[^a]{2,}?/8 + \x{100}bca + 0: \x{100}b + +/[^a]+/8ig + bcd + 0: bcd + \x{100}aY\x{256}Z + 0: \x{100} + 0: Y\x{256}Z + +/^[^a]{2}/8i + \x{100}bc + 0: \x{100}b + +/^[^a]{2,}/8i + \x{100}bcAa + 0: \x{100}bc + +/^[^a]{2,}?/8i + \x{100}bca + 0: \x{100}b + +/\x{100}{0,0}/8 + abcd + 0: + +/\x{100}?/8 + abcd + 0: + \x{100}\x{100} + 0: \x{100} + +/\x{100}{0,3}/8 + \x{100}\x{100} + 0: \x{100}\x{100} + \x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100} + +/\x{100}*/8 + abce + 0: + \x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100}\x{100} + +/\x{100}{1,1}/8 + abcd\x{100}\x{100}\x{100}\x{100} + 0: \x{100} + +/\x{100}{1,3}/8 + abcd\x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100} + +/\x{100}+/8 + abcd\x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100}\x{100} + +/\x{100}{3}/8 + abcd\x{100}\x{100}\x{100}XX + 0: \x{100}\x{100}\x{100} + +/\x{100}{3,5}/8 + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + 0: \x{100}\x{100}\x{100}\x{100}\x{100} + +/\x{100}{3,}/8 + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + +/(?<=a\x{100}{2}b)X/8+ + Xyyya\x{100}\x{100}bXzzz + 0: X + 0+ zzz + +/\D*/8 + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/\D*/8 + \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + +/\D/8 + 1X2 + 0: X + 1\x{100}2 + 0: \x{100} + +/>\S/8 + > >X Y + 0: >X + > >\x{100} Y + 0: >\x{100} + +/\d/8 + \x{100}3 + 0: 3 + +/\s/8 + \x{100} X + 0: + +/\D+/8 + 12abcd34 + 0: abcd + *** Failers + 0: *** Failers + 1234 +No match + +/\D{2,3}/8 + 12abcd34 + 0: abc + 12ab34 + 0: ab + *** Failers + 0: *** + 1234 +No match + 12a34 +No match + +/\D{2,3}?/8 + 12abcd34 + 0: ab + 12ab34 + 0: ab + *** Failers + 0: ** + 1234 +No match + 12a34 +No match + +/\d+/8 + 12abcd34 + 0: 12 + *** Failers +No match + +/\d{2,3}/8 + 12abcd34 + 0: 12 + 1234abcd + 0: 123 + *** Failers +No match + 1.4 +No match + +/\d{2,3}?/8 + 12abcd34 + 0: 12 + 1234abcd + 0: 12 + *** Failers +No match + 1.4 +No match + +/\S+/8 + 12abcd34 + 0: 12abcd34 + *** Failers + 0: *** + \ \ +No match + +/\S{2,3}/8 + 12abcd34 + 0: 12a + 1234abcd + 0: 123 + *** Failers + 0: *** + \ \ +No match + +/\S{2,3}?/8 + 12abcd34 + 0: 12 + 1234abcd + 0: 12 + *** Failers + 0: ** + \ \ +No match + +/>\s+ <34 + 0: > < + 0+ 34 + *** Failers +No match + +/>\s{2,3} < + 0+ cd + ab> < + 0+ ce + *** Failers +No match + ab> \s{2,3}? < + 0+ cd + ab> < + 0+ ce + *** Failers +No match + ab> \xff< + 0: \xff + +/[\xff]/8 + >\x{ff}< + 0: \x{ff} + +/[^\xFF]/ + XYZ + 0: X + +/[^\xff]/8 + XYZ + 0: X + \x{123} + 0: \x{123} + +/^[ac]*b/8 + xb +No match + +/^[ac\x{100}]*b/8 + xb +No match + +/^[^x]*b/8i + xb +No match + +/^[^x]*b/8 + xb +No match + +/^\d*b/8 + xb +No match + +/(|a)/g8 + catac + 0: + 1: + 0: + 1: + 0: a + 1: a + 0: + 1: + 0: + 1: + 0: a + 1: a + 0: + 1: + 0: + 1: + a\x{256}a + 0: + 1: + 0: a + 1: a + 0: + 1: + 0: + 1: + 0: a + 1: a + 0: + 1: + +/^\x{85}$/8i + \x{85} + 0: \x{85} + +/^ሴ/8 + ሴ + 0: \x{1234} + +/^\ሴ/8 + ሴ + 0: \x{1234} + +"(?s)(.{1,5})"8 + abcdefg + 0: abcde + 1: abcde + ab + 0: ab + 1: ab + +/ End of testinput4 / diff --git a/libs/pcre/testdata/testoutput5 b/libs/pcre/testdata/testoutput5 new file mode 100644 index 0000000000..2c5e3c09cd --- /dev/null +++ b/libs/pcre/testdata/testoutput5 @@ -0,0 +1,1123 @@ +/\x{100}/8DM +Memory allocation (code space): 10 +------------------------------------------------------------------ + 0 6 Bra 0 + 3 \x{100} + 6 6 Ket + 9 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 196 +Need char = 128 + +/\x{1000}/8DM +Memory allocation (code space): 11 +------------------------------------------------------------------ + 0 7 Bra 0 + 3 \x{1000} + 7 7 Ket + 10 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 225 +Need char = 128 + +/\x{10000}/8DM +Memory allocation (code space): 12 +------------------------------------------------------------------ + 0 8 Bra 0 + 3 \x{10000} + 8 8 Ket + 11 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 240 +Need char = 128 + +/\x{100000}/8DM +Memory allocation (code space): 12 +------------------------------------------------------------------ + 0 8 Bra 0 + 3 \x{100000} + 8 8 Ket + 11 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 244 +Need char = 128 + +/\x{1000000}/8DM +Memory allocation (code space): 13 +------------------------------------------------------------------ + 0 9 Bra 0 + 3 \x{1000000} + 9 9 Ket + 12 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 249 +Need char = 128 + +/\x{4000000}/8DM +Memory allocation (code space): 14 +------------------------------------------------------------------ + 0 10 Bra 0 + 3 \x{4000000} + 10 10 Ket + 13 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 252 +Need char = 128 + +/\x{7fffFFFF}/8DM +Memory allocation (code space): 14 +------------------------------------------------------------------ + 0 10 Bra 0 + 3 \x{7fffffff} + 10 10 Ket + 13 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 253 +Need char = 191 + +/[\x{ff}]/8DM +Memory allocation (code space): 10 +------------------------------------------------------------------ + 0 6 Bra 0 + 3 \x{ff} + 6 6 Ket + 9 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 195 +Need char = 191 + +/[\x{100}]/8DM +Memory allocation (code space): 47 +------------------------------------------------------------------ + 0 11 Bra 0 + 3 [\x{100}] + 11 11 Ket + 14 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +No first char +No need char + +/\x{ffffffff}/8 +Failed: character value in \x{...} sequence is too large at offset 11 + +/\x{100000000}/8 +Failed: character value in \x{...} sequence is too large at offset 12 + +/^\x{100}a\x{1234}/8 + \x{100}a\x{1234}bcd + 0: \x{100}a\x{1234} + +/\x80/8D +------------------------------------------------------------------ + 0 6 Bra 0 + 3 \x{80} + 6 6 Ket + 9 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 194 +Need char = 128 + +/\xff/8D +------------------------------------------------------------------ + 0 6 Bra 0 + 3 \x{ff} + 6 6 Ket + 9 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 195 +Need char = 191 + +/\x{0041}\x{2262}\x{0391}\x{002e}/D8 +------------------------------------------------------------------ + 0 14 Bra 0 + 3 A\x{2262}\x{391}. + 14 14 Ket + 17 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 'A' +Need char = '.' + \x{0041}\x{2262}\x{0391}\x{002e} + 0: A\x{2262}\x{391}. + +/\x{D55c}\x{ad6d}\x{C5B4}/D8 +------------------------------------------------------------------ + 0 15 Bra 0 + 3 \x{d55c}\x{ad6d}\x{c5b4} + 15 15 Ket + 18 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 237 +Need char = 180 + \x{D55c}\x{ad6d}\x{C5B4} + 0: \x{d55c}\x{ad6d}\x{c5b4} + +/\x{65e5}\x{672c}\x{8a9e}/D8 +------------------------------------------------------------------ + 0 15 Bra 0 + 3 \x{65e5}\x{672c}\x{8a9e} + 15 15 Ket + 18 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 230 +Need char = 158 + \x{65e5}\x{672c}\x{8a9e} + 0: \x{65e5}\x{672c}\x{8a9e} + +/\x{80}/D8 +------------------------------------------------------------------ + 0 6 Bra 0 + 3 \x{80} + 6 6 Ket + 9 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 194 +Need char = 128 + +/\x{084}/D8 +------------------------------------------------------------------ + 0 6 Bra 0 + 3 \x{84} + 6 6 Ket + 9 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 194 +Need char = 132 + +/\x{104}/D8 +------------------------------------------------------------------ + 0 6 Bra 0 + 3 \x{104} + 6 6 Ket + 9 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 196 +Need char = 132 + +/\x{861}/D8 +------------------------------------------------------------------ + 0 7 Bra 0 + 3 \x{861} + 7 7 Ket + 10 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 224 +Need char = 161 + +/\x{212ab}/D8 +------------------------------------------------------------------ + 0 8 Bra 0 + 3 \x{212ab} + 8 8 Ket + 11 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 240 +Need char = 171 + +/.{3,5}X/D8 +------------------------------------------------------------------ + 0 13 Bra 0 + 3 Any{3} + 7 Any{0,2} + 11 X + 13 13 Ket + 16 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +Need char = 'X' + \x{212ab}\x{212ab}\x{212ab}\x{861}X + 0: \x{212ab}\x{212ab}\x{212ab}\x{861}X + + +/.{3,5}?/D8 +------------------------------------------------------------------ + 0 11 Bra 0 + 3 Any{3} + 7 Any{0,2}? + 11 11 Ket + 14 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +No need char + \x{212ab}\x{212ab}\x{212ab}\x{861} + 0: \x{212ab}\x{212ab}\x{212ab} + +/-- These tests are here rather than in testinput4 because Perl 5.6 has --/ +/-- some problems with UTF-8 support, in the area of \x{..} where the --/ +No match +/-- value is < 255. It grumbles about invalid UTF-8 strings. --/ +No match + +/^[a\x{c0}]b/8 + \x{c0}b + 0: \x{c0}b + +/^([a\x{c0}]*?)aa/8 + a\x{c0}aaaa/ + 0: a\x{c0}aa + 1: a\x{c0} + +/^([a\x{c0}]*?)aa/8 + a\x{c0}aaaa/ + 0: a\x{c0}aa + 1: a\x{c0} + a\x{c0}a\x{c0}aaa/ + 0: a\x{c0}a\x{c0}aa + 1: a\x{c0}a\x{c0} + +/^([a\x{c0}]*)aa/8 + a\x{c0}aaaa/ + 0: a\x{c0}aaaa + 1: a\x{c0}aa + a\x{c0}a\x{c0}aaa/ + 0: a\x{c0}a\x{c0}aaa + 1: a\x{c0}a\x{c0}a + +/^([a\x{c0}]*)a\x{c0}/8 + a\x{c0}aaaa/ + 0: a\x{c0} + 1: + a\x{c0}a\x{c0}aaa/ + 0: a\x{c0}a\x{c0} + 1: a\x{c0} + +/-- --/ + +/(?<=\C)X/8 +Failed: \C not allowed in lookbehind assertion at offset 6 + +/-- This one is here not because it's different to Perl, but because the --/ +/-- way the captured single-byte is displayed. (In Perl it becomes a --/ +No match +/-- character, and you can't tell the difference.) --/ +No match + +/X(\C)(.*)/8 + X\x{1234} + 0: X\x{1234} + 1: \xe1 + 2: \x88\xb4 + X\nabc + 0: X\x{0a}abc + 1: \x{0a} + 2: abc + +/^[ab]/8D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [ab] + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored utf8 +No first char +No need char + bar + 0: b + *** Failers +No match + c +No match + \x{ff} +No match + \x{100} +No match + +/^[^ab]/8D +------------------------------------------------------------------ + 0 37 Bra 0 + 3 ^ + 4 [\x00-`c-\xff] (neg) + 37 37 Ket + 40 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored utf8 +No first char +No need char + c + 0: c + \x{ff} + 0: \x{ff} + \x{100} + 0: \x{100} + *** Failers + 0: * + aaa +No match + +/[^ab\xC0-\xF0]/8SD +------------------------------------------------------------------ + 0 36 Bra 0 + 3 [\x00-`c-\xbf\xf1-\xff] (neg) + 36 36 Ket + 39 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +No first char +No need char +Starting byte set: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a + \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 + \x1a \x1b \x1c \x1d \x1e \x1f \x20 ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 + 5 6 7 8 9 : ; < = > ? @ A B C D E F G H I J K L M N O P Q R S T U V W X Y + Z [ \ ] ^ _ ` c d e f g h i j k l m n o p q r s t u v w x y z { | } ~ \x7f + \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd \xce \xcf \xd0 + \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc \xdd \xde \xdf + \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb \xec \xed \xee + \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa \xfb \xfc \xfd + \xfe \xff + \x{f1} + 0: \x{f1} + \x{bf} + 0: \x{bf} + \x{100} + 0: \x{100} + \x{1000} + 0: \x{1000} + *** Failers + 0: * + \x{c0} +No match + \x{f0} +No match + +/Ä€{3,4}/8SD +------------------------------------------------------------------ + 0 13 Bra 0 + 3 \x{100}{3} + 8 \x{100}{,1} + 13 13 Ket + 16 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +First char = 196 +Need char = 128 +Study returned NULL + \x{100}\x{100}\x{100}\x{100\x{100} + 0: \x{100}\x{100}\x{100} + +/(\x{100}+|x)/8SD +------------------------------------------------------------------ + 0 17 Bra 0 + 3 6 Bra 1 + 6 \x{100}+ + 9 5 Alt + 12 x + 14 11 Ket + 17 17 Ket + 20 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Partial matching not supported +Options: utf8 +No first char +No need char +Starting byte set: x \xc4 + +/(\x{100}*a|x)/8SD +------------------------------------------------------------------ + 0 19 Bra 0 + 3 8 Bra 1 + 6 \x{100}* + 9 a + 11 5 Alt + 14 x + 16 13 Ket + 19 19 Ket + 22 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Partial matching not supported +Options: utf8 +No first char +No need char +Starting byte set: a x \xc4 + +/(\x{100}{0,2}a|x)/8SD +------------------------------------------------------------------ + 0 21 Bra 0 + 3 10 Bra 1 + 6 \x{100}{,2} + 11 a + 13 5 Alt + 16 x + 18 15 Ket + 21 21 Ket + 24 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Partial matching not supported +Options: utf8 +No first char +No need char +Starting byte set: a x \xc4 + +/(\x{100}{1,2}a|x)/8SD +------------------------------------------------------------------ + 0 24 Bra 0 + 3 13 Bra 1 + 6 \x{100} + 9 \x{100}{,1} + 14 a + 16 5 Alt + 19 x + 21 18 Ket + 24 24 Ket + 27 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Partial matching not supported +Options: utf8 +No first char +No need char +Starting byte set: x \xc4 + +/\x{100}*(\d+|"(?1)")/8 + 1234 + 0: 1234 + 1: 1234 + "1234" + 0: "1234" + 1: "1234" + \x{100}1234 + 0: \x{100}1234 + 1: 1234 + "\x{100}1234" + 0: \x{100}1234 + 1: 1234 + \x{100}\x{100}12ab + 0: \x{100}\x{100}12 + 1: 12 + \x{100}\x{100}"12" + 0: \x{100}\x{100}"12" + 1: "12" + *** Failers +No match + \x{100}\x{100}abcd +No match + +/\x{100}/8D +------------------------------------------------------------------ + 0 6 Bra 0 + 3 \x{100} + 6 6 Ket + 9 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 196 +Need char = 128 + +/\x{100}*/8D +------------------------------------------------------------------ + 0 6 Bra 0 + 3 \x{100}* + 6 6 Ket + 9 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +No need char + +/a\x{100}*/8D +------------------------------------------------------------------ + 0 8 Bra 0 + 3 a + 5 \x{100}* + 8 8 Ket + 11 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +First char = 'a' +No need char + +/ab\x{100}*/8D +------------------------------------------------------------------ + 0 10 Bra 0 + 3 ab + 7 \x{100}* + 10 10 Ket + 13 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +First char = 'a' +Need char = 'b' + +/a\x{100}\x{101}*/8D +------------------------------------------------------------------ + 0 11 Bra 0 + 3 a\x{100} + 8 \x{101}* + 11 11 Ket + 14 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +First char = 'a' +Need char = 128 + +/a\x{100}\x{101}+/8D +------------------------------------------------------------------ + 0 11 Bra 0 + 3 a\x{100} + 8 \x{101}+ + 11 11 Ket + 14 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +First char = 'a' +Need char = 129 + +/\x{100}*A/8D +------------------------------------------------------------------ + 0 8 Bra 0 + 3 \x{100}* + 6 A + 8 8 Ket + 11 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +Need char = 'A' + A + 0: A + +/\x{100}*\d(?R)/8D +------------------------------------------------------------------ + 0 16 Bra 0 + 3 \x{100}* + 6 \d + 7 6 Once + 10 0 Recurse + 13 6 Ket + 16 16 Ket + 19 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Partial matching not supported +Options: utf8 +No first char +No need char + +/[^\x{c4}]/D +------------------------------------------------------------------ + 0 5 Bra 0 + 3 [^\xc4] + 5 5 Ket + 8 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/[^\x{c4}]/8D +------------------------------------------------------------------ + 0 36 Bra 0 + 3 [\x00-\xc3\xc5-\xff] (neg) + 36 36 Ket + 39 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +No first char +No need char + +/[\x{100}]/8DM +Memory allocation (code space): 47 +------------------------------------------------------------------ + 0 11 Bra 0 + 3 [\x{100}] + 11 11 Ket + 14 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +No first char +No need char + \x{100} + 0: \x{100} + Z\x{100} + 0: \x{100} + \x{100}Z + 0: \x{100} + *** Failers +No match + +/[Z\x{100}]/8DM +Memory allocation (code space): 47 +------------------------------------------------------------------ + 0 43 Bra 0 + 3 [Z\x{100}] + 43 43 Ket + 46 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +No first char +No need char + Z\x{100} + 0: Z + \x{100} + 0: \x{100} + \x{100}Z + 0: \x{100} + *** Failers +No match + +/[\x{200}-\x{100}]/8 +Failed: range out of order in character class at offset 15 + +/[Ä€-Ä„]/8 + \x{100} + 0: \x{100} + \x{104} + 0: \x{104} + *** Failers +No match + \x{105} +No match + \x{ff} +No match + +/[z-\x{100}]/8D +------------------------------------------------------------------ + 0 12 Bra 0 + 3 [z-\x{100}] + 12 12 Ket + 15 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +No first char +No need char + +/[z\Qa-d]Ä€\E]/8D +------------------------------------------------------------------ + 0 43 Bra 0 + 3 [\-\]adz\x{100}] + 43 43 Ket + 46 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +No first char +No need char + \x{100} + 0: \x{100} + Ä€ + 0: \x{100} + +/[\xFF]/D +------------------------------------------------------------------ + 0 5 Bra 0 + 3 \xff + 5 5 Ket + 8 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +First char = 255 +No need char + >\xff< + 0: \xff + +/[\xff]/D8 +------------------------------------------------------------------ + 0 6 Bra 0 + 3 \x{ff} + 6 6 Ket + 9 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +First char = 195 +Need char = 191 + >\x{ff}< + 0: \x{ff} + +/[^\xFF]/D +------------------------------------------------------------------ + 0 5 Bra 0 + 3 [^\xff] + 5 5 Ket + 8 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +No options +No first char +No need char + +/[^\xff]/8D +------------------------------------------------------------------ + 0 36 Bra 0 + 3 [\x00-\xfe] (neg) + 36 36 Ket + 39 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 +No first char +No need char + +/[Ä-Ãœ]/8 + Ö # Matches without Study + 0: \x{d6} + \x{d6} + 0: \x{d6} + +/[Ä-Ãœ]/8S + Ö <-- Same with Study + 0: \x{d6} + \x{d6} + 0: \x{d6} + +/[\x{c4}-\x{dc}]/8 + Ö # Matches without Study + 0: \x{d6} + \x{d6} + 0: \x{d6} + +/[\x{c4}-\x{dc}]/8S + Ö <-- Same with Study + 0: \x{d6} + \x{d6} + 0: \x{d6} + +/[Ã]/8 +Failed: invalid UTF-8 string at offset 2 + +/Ã/8 +Failed: invalid UTF-8 string at offset 0 + +/ÃÃÃxxx/8 +Failed: invalid UTF-8 string at offset 1 + +/ÃÃÃxxx/8?D +------------------------------------------------------------------ + 0 15 Bra 0 + 3 \X{c0}\X{c0}\X{c0}xxx + 15 15 Ket + 18 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: utf8 no_utf8_check +First char = 195 +Need char = 'x' + +/abc/8 + Ã] +Error -10 + à +Error -10 + ÃÃà +Error -10 + ÃÃÃ\? +No match + +/anything/8 + \xc0\x80 +Error -10 + \xc1\x8f +Error -10 + \xe0\x9f\x80 +Error -10 + \xf0\x8f\x80\x80 +Error -10 + \xf8\x87\x80\x80\x80 +Error -10 + \xfc\x83\x80\x80\x80\x80 +Error -10 + \xfe\x80\x80\x80\x80\x80 +Error -10 + \xff\x80\x80\x80\x80\x80 +Error -10 + \xc3\x8f +No match + \xe0\xaf\x80 +No match + \xe1\x80\x80 +No match + \xf0\x9f\x80\x80 +No match + \xf1\x8f\x80\x80 +No match + \xf8\x88\x80\x80\x80 +No match + \xf9\x87\x80\x80\x80 +No match + \xfc\x84\x80\x80\x80\x80 +No match + \xfd\x83\x80\x80\x80\x80 +No match + +/\x{100}abc(xyz(?1))/8D +------------------------------------------------------------------ + 0 33 Bra 0 + 3 \x{100}abc + 12 18 Bra 1 + 15 xyz + 21 6 Once + 24 12 Recurse + 27 6 Ket + 30 18 Ket + 33 33 Ket + 36 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Options: utf8 +First char = 196 +Need char = 'z' + +/[^\x{100}]abc(xyz(?1))/8D +------------------------------------------------------------------ + 0 38 Bra 0 + 3 [^\x{100}] + 11 abc + 17 18 Bra 1 + 20 xyz + 26 6 Once + 29 17 Recurse + 32 6 Ket + 35 18 Ket + 38 38 Ket + 41 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Options: utf8 +No first char +Need char = 'z' + +/[ab\x{100}]abc(xyz(?1))/8D +------------------------------------------------------------------ + 0 70 Bra 0 + 3 [ab\x{100}] + 43 abc + 49 18 Bra 1 + 52 xyz + 58 6 Once + 61 49 Recurse + 64 6 Ket + 67 18 Ket + 70 70 Ket + 73 End +------------------------------------------------------------------ +Capturing subpattern count = 1 +Options: utf8 +No first char +Need char = 'z' + +/(\x{100}(b(?2)c))?/D8 +------------------------------------------------------------------ + 0 32 Bra 0 + 3 Brazero + 4 25 Bra 1 + 7 \x{100} + 10 16 Bra 2 + 13 b + 15 6 Once + 18 10 Recurse + 21 6 Ket + 24 c + 26 16 Ket + 29 25 Ket + 32 32 Ket + 35 End +------------------------------------------------------------------ +Capturing subpattern count = 2 +Options: utf8 +No first char +No need char + +/(\x{100}(b(?2)c)){0,2}/D8 +------------------------------------------------------------------ + 0 67 Bra 0 + 3 Brazero + 4 60 Bra 0 + 7 25 Bra 1 + 10 \x{100} + 13 16 Bra 2 + 16 b + 18 6 Once + 21 13 Recurse + 24 6 Ket + 27 c + 29 16 Ket + 32 25 Ket + 35 Brazero + 36 25 Bra 1 + 39 \x{100} + 42 16 Bra 2 + 45 b + 47 6 Once + 50 13 Recurse + 53 6 Ket + 56 c + 58 16 Ket + 61 25 Ket + 64 60 Ket + 67 67 Ket + 70 End +------------------------------------------------------------------ +Capturing subpattern count = 2 +Options: utf8 +No first char +No need char + +/(\x{100}(b(?1)c))?/D8 +------------------------------------------------------------------ + 0 32 Bra 0 + 3 Brazero + 4 25 Bra 1 + 7 \x{100} + 10 16 Bra 2 + 13 b + 15 6 Once + 18 4 Recurse + 21 6 Ket + 24 c + 26 16 Ket + 29 25 Ket + 32 32 Ket + 35 End +------------------------------------------------------------------ +Capturing subpattern count = 2 +Options: utf8 +No first char +No need char + +/(\x{100}(b(?1)c)){0,2}/D8 +------------------------------------------------------------------ + 0 67 Bra 0 + 3 Brazero + 4 60 Bra 0 + 7 25 Bra 1 + 10 \x{100} + 13 16 Bra 2 + 16 b + 18 6 Once + 21 7 Recurse + 24 6 Ket + 27 c + 29 16 Ket + 32 25 Ket + 35 Brazero + 36 25 Bra 1 + 39 \x{100} + 42 16 Bra 2 + 45 b + 47 6 Once + 50 7 Recurse + 53 6 Ket + 56 c + 58 16 Ket + 61 25 Ket + 64 60 Ket + 67 67 Ket + 70 End +------------------------------------------------------------------ +Capturing subpattern count = 2 +Options: utf8 +No first char +No need char + +/\W/8 + A.B + 0: . + A\x{100}B + 0: \x{100} + +/\w/8 + \x{100}X + 0: X + +/a\x{1234}b/P8 + a\x{1234}b + 0: a\x{1234}b + +/^\ሴ/8D +------------------------------------------------------------------ + 0 8 Bra 0 + 3 ^ + 4 \x{1234} + 8 8 Ket + 11 End +------------------------------------------------------------------ +Capturing subpattern count = 0 +Options: anchored utf8 +No first char +No need char + +/\777/I +Failed: octal value is greater than \377 (not in UTF-8 mode) at offset 3 + +/\777/8I +Capturing subpattern count = 0 +Options: utf8 +First char = 199 +Need char = 191 + \x{1ff} + 0: \x{1ff} + \777 + 0: \x{1ff} + +/ End of testinput5 / diff --git a/libs/pcre/testdata/testoutput6 b/libs/pcre/testdata/testoutput6 new file mode 100644 index 0000000000..ee174a6b01 --- /dev/null +++ b/libs/pcre/testdata/testoutput6 @@ -0,0 +1,1413 @@ +/^\pC\pL\pM\pN\pP\pS\pZ3 + 0: abc + *** Failers +No match + xyzabc +No match + xyzabc\>2 +No match + +/x\dy\Dz/ + x9yzz + 0: x9yzz + x0y+z + 0: x0y+z + *** Failers +No match + xyz +No match + xxy0z +No match + +/x\sy\Sz/ + x yzz + 0: x yzz + x y+z + 0: x y+z + *** Failers +No match + xyz +No match + xxyyz +No match + +/x\wy\Wz/ + xxy+z + 0: xxy+z + *** Failers +No match + xxy0z +No match + x+y+z +No match + +/x.y/ + x+y + 0: x+y + x-y + 0: x-y + *** Failers +No match + x\ny +No match + +/x.y/s + x+y + 0: x+y + x-y + 0: x-y + x\ny + 0: x\x0ay + +/(a.b(?s)c.d|x.y)p.q/ + a+bc+dp+q + 0: a+bc+dp+q + a+bc\ndp+q + 0: a+bc\x0adp+q + x\nyp+q + 0: x\x0ayp+q + *** Failers +No match + a\nbc\ndp+q +No match + a+bc\ndp\nq +No match + x\nyp\nq +No match + +/a\d\z/ + ba0 + 0: a0 + *** Failers +No match + ba0\n +No match + ba0\ncd +No match + +/a\d\z/m + ba0 + 0: a0 + *** Failers +No match + ba0\n +No match + ba0\ncd +No match + +/a\d\Z/ + ba0 + 0: a0 + ba0\n + 0: a0 + *** Failers +No match + ba0\ncd +No match + +/a\d\Z/m + ba0 + 0: a0 + ba0\n + 0: a0 + *** Failers +No match + ba0\ncd +No match + +/a\d$/ + ba0 + 0: a0 + ba0\n + 0: a0 + *** Failers +No match + ba0\ncd +No match + +/a\d$/m + ba0 + 0: a0 + ba0\n + 0: a0 + ba0\ncd + 0: a0 + *** Failers +No match + +/abc/i + abc + 0: abc + aBc + 0: aBc + ABC + 0: ABC + +/[^a]/ + abcd + 0: b + +/ab?\w/ + abz + 0: abz + 1: ab + abbz + 0: abb + 1: ab + azz + 0: az + +/x{0,3}yz/ + ayzq + 0: yz + axyzq + 0: xyz + axxyz + 0: xxyz + axxxyzq + 0: xxxyz + axxxxyzq + 0: xxxyz + *** Failers +No match + ax +No match + axx +No match + +/x{3}yz/ + axxxyzq + 0: xxxyz + axxxxyzq + 0: xxxyz + *** Failers +No match + ax +No match + axx +No match + ayzq +No match + axyzq +No match + axxyz +No match + +/x{2,3}yz/ + axxyz + 0: xxyz + axxxyzq + 0: xxxyz + axxxxyzq + 0: xxxyz + *** Failers +No match + ax +No match + axx +No match + ayzq +No match + axyzq +No match + +/[^a]+/ + bac + 0: b + bcdefax + 0: bcdef + 1: bcde + 2: bcd + 3: bc + 4: b + *** Failers + 0: *** F + 1: *** + 2: *** + 3: ** + 4: * + aaaaa +No match + +/[^a]*/ + bac + 0: b + 1: + bcdefax + 0: bcdef + 1: bcde + 2: bcd + 3: bc + 4: b + 5: + *** Failers + 0: *** F + 1: *** + 2: *** + 3: ** + 4: * + 5: + aaaaa + 0: + +/[^a]{3,5}/ + xyz + 0: xyz + awxyza + 0: wxyz + 1: wxy + abcdefa + 0: bcdef + 1: bcde + 2: bcd + abcdefghijk + 0: bcdef + 1: bcde + 2: bcd + *** Failers + 0: *** F + 1: *** + 2: *** + axya +No match + axa +No match + aaaaa +No match + +/\d*/ + 1234b567 + 0: 1234 + 1: 123 + 2: 12 + 3: 1 + 4: + xyz + 0: + +/\D*/ + a1234b567 + 0: a + 1: + xyz + 0: xyz + 1: xy + 2: x + 3: + +/\d+/ + ab1234c56 + 0: 1234 + 1: 123 + 2: 12 + 3: 1 + *** Failers +No match + xyz +No match + +/\D+/ + ab123c56 + 0: ab + 1: a + *** Failers + 0: *** Failers + 1: *** Failer + 2: *** Faile + 3: *** Fail + 4: *** Fai + 5: *** Fa + 6: *** F + 7: *** + 8: *** + 9: ** +10: * + 789 +No match + +/\d?A/ + 045ABC + 0: 5A + ABC + 0: A + *** Failers +No match + XYZ +No match + +/\D?A/ + ABC + 0: A + BAC + 0: BA + 9ABC + 0: A + *** Failers +No match + +/a+/ + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + +/^.*xyz/ + xyz + 0: xyz + ggggggggxyz + 0: ggggggggxyz + +/^.+xyz/ + abcdxyz + 0: abcdxyz + axyz + 0: axyz + *** Failers +No match + xyz +No match + +/^.?xyz/ + xyz + 0: xyz + cxyz + 0: cxyz + +/^\d{2,3}X/ + 12X + 0: 12X + 123X + 0: 123X + *** Failers +No match + X +No match + 1X +No match + 1234X +No match + +/^[abcd]\d/ + a45 + 0: a4 + b93 + 0: b9 + c99z + 0: c9 + d04 + 0: d0 + *** Failers +No match + e45 +No match + abcd +No match + abcd1234 +No match + 1234 +No match + +/^[abcd]*\d/ + a45 + 0: a4 + b93 + 0: b9 + c99z + 0: c9 + d04 + 0: d0 + abcd1234 + 0: abcd1 + 1234 + 0: 1 + *** Failers +No match + e45 +No match + abcd +No match + +/^[abcd]+\d/ + a45 + 0: a4 + b93 + 0: b9 + c99z + 0: c9 + d04 + 0: d0 + abcd1234 + 0: abcd1 + *** Failers +No match + 1234 +No match + e45 +No match + abcd +No match + +/^a+X/ + aX + 0: aX + aaX + 0: aaX + +/^[abcd]?\d/ + a45 + 0: a4 + b93 + 0: b9 + c99z + 0: c9 + d04 + 0: d0 + 1234 + 0: 1 + *** Failers +No match + abcd1234 +No match + e45 +No match + +/^[abcd]{2,3}\d/ + ab45 + 0: ab4 + bcd93 + 0: bcd9 + *** Failers +No match + 1234 +No match + a36 +No match + abcd1234 +No match + ee45 +No match + +/^(abc)*\d/ + abc45 + 0: abc4 + abcabcabc45 + 0: abcabcabc4 + 42xyz + 0: 4 + *** Failers +No match + +/^(abc)+\d/ + abc45 + 0: abc4 + abcabcabc45 + 0: abcabcabc4 + *** Failers +No match + 42xyz +No match + +/^(abc)?\d/ + abc45 + 0: abc4 + 42xyz + 0: 4 + *** Failers +No match + abcabcabc45 +No match + +/^(abc){2,3}\d/ + abcabc45 + 0: abcabc4 + abcabcabc45 + 0: abcabcabc4 + *** Failers +No match + abcabcabcabc45 +No match + abc45 +No match + 42xyz +No match + +/1(abc|xyz)2(?1)3/ + 1abc2abc3456 + 0: 1abc2abc3 + 1abc2xyz3456 + 0: 1abc2xyz3 + +/^(a*\w|ab)=(a*\w|ab)/ + ab=ab + 0: ab=ab + 1: ab=a + +/^(a*\w|ab)=(?1)/ + ab=ab + 0: ab=ab + +/^([^()]|\((?1)*\))*$/ + abc + 0: abc + a(b)c + 0: a(b)c + a(b(c))d + 0: a(b(c))d + *** Failers) +No match + a(b(c)d +No match + +/^>abc>([^()]|\((?1)*\))*abc>123abc>123abc>1(2)3abc>1(2)3abc>(1(2)3)abc>(1(2)3)a*)\d/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa9876 + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa9 + *** Failers +No match + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + +/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/x + <> + 0: <> + + 0: + hij> + 0: hij> + hij> + 0: + def> + 0: def> + + 0: <> + *** Failers +No match + abcxyz + 1 ^ ^ x + 0: abcxyz + 123abcxyz999 +--->123abcxyz999 + 1 ^ ^ x + 0: abcxyz + +/(ab|cd){3,4}/C + ababab +--->ababab + +0 ^ (ab|cd){3,4} + +1 ^ a + +4 ^ c + +2 ^^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c + +2 ^ ^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c + +2 ^ ^ b + +3 ^ ^ | ++12 ^ ^ + +1 ^ ^ a + +4 ^ ^ c + 0: ababab + abcdabcd +--->abcdabcd + +0 ^ (ab|cd){3,4} + +1 ^ a + +4 ^ c + +2 ^^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) + +1 ^ ^ a + +4 ^ ^ c + +2 ^ ^ b + +3 ^ ^ | ++12 ^ ^ + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) ++12 ^ ^ + 0: abcdabcd + 1: abcdab + abcdcdcdcdcd +--->abcdcdcdcdcd + +0 ^ (ab|cd){3,4} + +1 ^ a + +4 ^ c + +2 ^^ b + +3 ^ ^ | + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) ++12 ^ ^ + +1 ^ ^ a + +4 ^ ^ c + +5 ^ ^ d + +6 ^ ^ ) ++12 ^ ^ + 0: abcdcdcd + 1: abcdcd + +/^abc/ + abcdef + 0: abc + *** Failers +No match + abcdef\B +No match + +/^(a*|xyz)/ + bcd + 0: + aaabcd + 0: aaa + 1: aa + 2: a + 3: + xyz + 0: xyz + 1: + xyz\N + 0: xyz + *** Failers + 0: + bcd\N +No match + +/xyz$/ + xyz + 0: xyz + xyz\n + 0: xyz + *** Failers +No match + xyz\Z +No match + xyz\n\Z +No match + +/xyz$/m + xyz + 0: xyz + xyz\n + 0: xyz + abcxyz\npqr + 0: xyz + abcxyz\npqr\Z + 0: xyz + xyz\n\Z + 0: xyz + *** Failers +No match + xyz\Z +No match + +/\Gabc/ + abcdef + 0: abc + defabcxyz\>3 + 0: abc + *** Failers +No match + defabcxyz +No match + +/^abcdef/ + ab\P +Partial match: ab + abcde\P +Partial match: abcde + abcdef\P + 0: abcdef + *** Failers +No match + abx\P +No match + +/^a{2,4}\d+z/ + a\P +Partial match: a + aa\P +Partial match: aa + aa2\P +Partial match: aa2 + aaa\P +Partial match: aaa + aaa23\P +Partial match: aaa23 + aaaa12345\P +Partial match: aaaa12345 + aa0z\P + 0: aa0z + aaaa4444444444444z\P + 0: aaaa4444444444444z + *** Failers +No match + az\P +No match + aaaaa\P +No match + a56\P +No match + +/^abcdef/ + abc\P +Partial match: abc + def\R + 0: def + +/(?<=foo)bar/ + xyzfo\P +No match + foob\P\>2 +Partial match: b + foobar...\R\P\>4 + 0: ar + xyzfo\P +No match + foobar\>2 + 0: bar + *** Failers +No match + xyzfo\P +No match + obar\R +No match + +/(ab*(cd|ef))+X/ + adfadadaklhlkalkajhlkjahdfasdfasdfladsfjkj\P\Z +No match + lkjhlkjhlkjhlkjhabbbbbbcdaefabbbbbbbefa\P\B\Z +Partial match: abbbbbbcdaefabbbbbbbefa + cdabbbbbbbb\P\R\B\Z +Partial match: cdabbbbbbbb + efabbbbbbbbbbbbbbbb\P\R\B\Z +Partial match: efabbbbbbbbbbbbbbbb + bbbbbbbbbbbbcdXyasdfadf\P\R\B\Z + 0: bbbbbbbbbbbbcdX + +/(a|b)/SF>testsavedregex +Compiled regex written to testsavedregex +Study data written to testsavedregex +>>aaabxyzpqrrrabbxyyyypqAzz + 0: aaabxyzpqrrrabbxyyyypqAzz + >aaaabxyzpqrrrabbxyyyypqAzz + 0: aaaabxyzpqrrrabbxyyyypqAzz + >>>>abcxyzpqrrrabbxyyyypqAzz + 0: abcxyzpqrrrabbxyyyypqAzz + *** Failers +No match + abxyzpqrrabbxyyyypqAzz +No match + abxyzpqrrrrabbxyyyypqAzz +No match + abxyzpqrrrabxyyyypqAzz +No match + aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz +No match + aaaabcxyzzzzpqrrrabbbxyyypqAzz +No match + aaabcxyzpqrrrabbxyyyypqqqqqqqAzz +No match + +/^(abc){1,2}zz/ + abczz + 0: abczz + abcabczz + 0: abcabczz + *** Failers +No match + zz +No match + abcabcabczz +No match + >>abczz +No match + +/^(b+?|a){1,2}?c/ + bc + 0: bc + bbc + 0: bbc + bbbc + 0: bbbc + bac + 0: bac + bbac + 0: bbac + aac + 0: aac + abbbbbbbbbbbc + 0: abbbbbbbbbbbc + bbbbbbbbbbbac + 0: bbbbbbbbbbbac + *** Failers +No match + aaac +No match + abbbbbbbbbbbac +No match + +/^(b+|a){1,2}c/ + bc + 0: bc + bbc + 0: bbc + bbbc + 0: bbbc + bac + 0: bac + bbac + 0: bbac + aac + 0: aac + abbbbbbbbbbbc + 0: abbbbbbbbbbbc + bbbbbbbbbbbac + 0: bbbbbbbbbbbac + *** Failers +No match + aaac +No match + abbbbbbbbbbbac +No match + +/^(b+|a){1,2}?bc/ + bbc + 0: bbc + +/^(b*|ba){1,2}?bc/ + babc + 0: babc + bbabc + 0: bbabc + bababc + 0: bababc + *** Failers +No match + bababbc +No match + babababc +No match + +/^(ba|b*){1,2}?bc/ + babc + 0: babc + bbabc + 0: bbabc + bababc + 0: bababc + *** Failers +No match + bababbc +No match + babababc +No match + +/^\ca\cA\c[\c{\c:/ + \x01\x01\e;z + 0: \x01\x01\x1b;z + +/^[ab\]cde]/ + athing + 0: a + bthing + 0: b + ]thing + 0: ] + cthing + 0: c + dthing + 0: d + ething + 0: e + *** Failers +No match + fthing +No match + [thing +No match + \\thing +No match + +/^[]cde]/ + ]thing + 0: ] + cthing + 0: c + dthing + 0: d + ething + 0: e + *** Failers +No match + athing +No match + fthing +No match + +/^[^ab\]cde]/ + fthing + 0: f + [thing + 0: [ + \\thing + 0: \ + *** Failers + 0: * + athing +No match + bthing +No match + ]thing +No match + cthing +No match + dthing +No match + ething +No match + +/^[^]cde]/ + athing + 0: a + fthing + 0: f + *** Failers + 0: * + ]thing +No match + cthing +No match + dthing +No match + ething +No match + +/^\/ + + 0: \x81 + +/^ÿ/ + ÿ + 0: \xff + +/^[0-9]+$/ + 0 + 0: 0 + 1 + 0: 1 + 2 + 0: 2 + 3 + 0: 3 + 4 + 0: 4 + 5 + 0: 5 + 6 + 0: 6 + 7 + 0: 7 + 8 + 0: 8 + 9 + 0: 9 + 10 + 0: 10 + 100 + 0: 100 + *** Failers +No match + abc +No match + +/^.*nter/ + enter + 0: enter + inter + 0: inter + uponter + 0: uponter + +/^xxx[0-9]+$/ + xxx0 + 0: xxx0 + xxx1234 + 0: xxx1234 + *** Failers +No match + xxx +No match + +/^.+[0-9][0-9][0-9]$/ + x123 + 0: x123 + xx123 + 0: xx123 + 123456 + 0: 123456 + *** Failers +No match + 123 +No match + x1234 + 0: x1234 + +/^.+?[0-9][0-9][0-9]$/ + x123 + 0: x123 + xx123 + 0: xx123 + 123456 + 0: 123456 + *** Failers +No match + 123 +No match + x1234 + 0: x1234 + +/^([^!]+)!(.+)=apquxz\.ixr\.zzz\.ac\.uk$/ + abc!pqr=apquxz.ixr.zzz.ac.uk + 0: abc!pqr=apquxz.ixr.zzz.ac.uk + *** Failers +No match + !pqr=apquxz.ixr.zzz.ac.uk +No match + abc!=apquxz.ixr.zzz.ac.uk +No match + abc!pqr=apquxz:ixr.zzz.ac.uk +No match + abc!pqr=apquxz.ixr.zzz.ac.ukk +No match + +/:/ + Well, we need a colon: somewhere + 0: : + *** Fail if we don't +No match + +/([\da-f:]+)$/i + 0abc + 0: 0abc + abc + 0: abc + fed + 0: fed + E + 0: E + :: + 0: :: + 5f03:12C0::932e + 0: 5f03:12C0::932e + fed def + 0: def + Any old stuff + 0: ff + *** Failers +No match + 0zzz +No match + gzzz +No match + fed\x20 +No match + Any old rubbish +No match + +/^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/ + .1.2.3 + 0: .1.2.3 + A.12.123.0 + 0: A.12.123.0 + *** Failers +No match + .1.2.3333 +No match + 1.2.3 +No match + 1234.2.3 +No match + +/^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/ + 1 IN SOA non-sp1 non-sp2( + 0: 1 IN SOA non-sp1 non-sp2( + 1 IN SOA non-sp1 non-sp2 ( + 0: 1 IN SOA non-sp1 non-sp2 ( + *** Failers +No match + 1IN SOA non-sp1 non-sp2( +No match + +/^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/ + a. + 0: a. + Z. + 0: Z. + 2. + 0: 2. + ab-c.pq-r. + 0: ab-c.pq-r. + sxk.zzz.ac.uk. + 0: sxk.zzz.ac.uk. + x-.y-. + 0: x-.y-. + *** Failers +No match + -abc.peq. +No match + +/^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/ + *.a + 0: *.a + *.b0-a + 0: *.b0-a + *.c3-b.c + 0: *.c3-b.c + *.c-a.b-c + 0: *.c-a.b-c + *** Failers +No match + *.0 +No match + *.a- +No match + *.a-b.c- +No match + *.c-a.0-c +No match + +/^(?=ab(de))(abd)(e)/ + abde + 0: abde + +/^(?!(ab)de|x)(abd)(f)/ + abdf + 0: abdf + +/^(?=(ab(cd)))(ab)/ + abcd + 0: ab + +/^[\da-f](\.[\da-f])*$/i + a.b.c.d + 0: a.b.c.d + A.B.C.D + 0: A.B.C.D + a.b.c.1.2.3.C + 0: a.b.c.1.2.3.C + +/^\".*\"\s*(;.*)?$/ + \"1234\" + 0: "1234" + \"abcd\" ; + 0: "abcd" ; + \"\" ; rhubarb + 0: "" ; rhubarb + *** Failers +No match + \"1234\" : things +No match + +/^$/ + \ + 0: + *** Failers +No match + +/ ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/x + ab c + 0: ab c + *** Failers +No match + abc +No match + ab cde +No match + +/(?x) ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/ + ab c + 0: ab c + *** Failers +No match + abc +No match + ab cde +No match + +/^ a\ b[c ]d $/x + a bcd + 0: a bcd + a b d + 0: a b d + *** Failers +No match + abcd +No match + ab d +No match + +/^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/ + abcdefhijklm + 0: abcdefhijklm + +/^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/ + abcdefhijklm + 0: abcdefhijklm + +/^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/ + a+ Z0+\x08\n\x1d\x12 + 0: a+ Z0+\x08\x0a\x1d\x12 + +/^[.^$|()*+?{,}]+/ + .^\$(*+)|{?,?} + 0: .^$(*+)|{?,?} + 1: .^$(*+)|{?,? + 2: .^$(*+)|{?, + 3: .^$(*+)|{? + 4: .^$(*+)|{ + 5: .^$(*+)| + 6: .^$(*+) + 7: .^$(*+ + 8: .^$(* + 9: .^$( +10: .^$ +11: .^ +12: . + +/^a*\w/ + z + 0: z + az + 0: az + 1: a + aaaz + 0: aaaz + 1: aaa + 2: aa + 3: a + a + 0: a + aa + 0: aa + 1: a + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + a+ + 0: a + aa+ + 0: aa + 1: a + +/^a*?\w/ + z + 0: z + az + 0: az + 1: a + aaaz + 0: aaaz + 1: aaa + 2: aa + 3: a + a + 0: a + aa + 0: aa + 1: a + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + a+ + 0: a + aa+ + 0: aa + 1: a + +/^a+\w/ + az + 0: az + aaaz + 0: aaaz + 1: aaa + 2: aa + aa + 0: aa + aaaa + 0: aaaa + 1: aaa + 2: aa + aa+ + 0: aa + +/^a+?\w/ + az + 0: az + aaaz + 0: aaaz + 1: aaa + 2: aa + aa + 0: aa + aaaa + 0: aaaa + 1: aaa + 2: aa + aa+ + 0: aa + +/^\d{8}\w{2,}/ + 1234567890 + 0: 1234567890 + 12345678ab + 0: 12345678ab + 12345678__ + 0: 12345678__ + *** Failers +No match + 1234567 +No match + +/^[aeiou\d]{4,5}$/ + uoie + 0: uoie + 1234 + 0: 1234 + 12345 + 0: 12345 + aaaaa + 0: aaaaa + *** Failers +No match + 123456 +No match + +/^[aeiou\d]{4,5}?/ + uoie + 0: uoie + 1234 + 0: 1234 + 12345 + 0: 12345 + 1: 1234 + aaaaa + 0: aaaaa + 1: aaaa + 123456 + 0: 12345 + 1: 1234 + +/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/ + From abcd Mon Sep 01 12:33:02 1997 + 0: From abcd Mon Sep 01 12:33 + +/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/ + From abcd Mon Sep 01 12:33:02 1997 + 0: From abcd Mon Sep 01 12:33 + From abcd Mon Sep 1 12:33:02 1997 + 0: From abcd Mon Sep 1 12:33 + *** Failers +No match + From abcd Sep 01 12:33:02 1997 +No match + +/^12.34/s + 12\n34 + 0: 12\x0a34 + 12\r34 + 0: 12\x0d34 + +/\w+(?=\t)/ + the quick brown\t fox + 0: brown + +/foo(?!bar)(.*)/ + foobar is foolish see? + 0: foolish see? + 1: foolish see + 2: foolish se + 3: foolish s + 4: foolish + 5: foolish + 6: foolis + 7: fooli + 8: fool + 9: foo + +/(?:(?!foo)...|^.{0,2})bar(.*)/ + foobar crowbar etc + 0: rowbar etc + 1: rowbar et + 2: rowbar e + 3: rowbar + 4: rowbar + barrel + 0: barrel + 1: barre + 2: barr + 3: bar + 2barrel + 0: 2barrel + 1: 2barre + 2: 2barr + 3: 2bar + A barrel + 0: A barrel + 1: A barre + 2: A barr + 3: A bar + +/^(\D*)(?=\d)(?!123)/ + abc456 + 0: abc + *** Failers +No match + abc123 +No match + +/^1234(?# test newlines + inside)/ + 1234 + 0: 1234 + +/^1234 #comment in extended re + /x + 1234 + 0: 1234 + +/#rhubarb + abcd/x + abcd + 0: abcd + +/^abcd#rhubarb/x + abcd + 0: abcd + +/(?!^)abc/ + the abc + 0: abc + *** Failers +No match + abc +No match + +/(?=^)abc/ + abc + 0: abc + *** Failers +No match + the abc +No match + +/^[ab]{1,3}(ab*|b)/ + aabbbbb + 0: aabbbbb + 1: aabbbb + 2: aabbb + 3: aabb + 4: aab + 5: aa + +/^[ab]{1,3}?(ab*|b)/ + aabbbbb + 0: aabbbbb + 1: aabbbb + 2: aabbb + 3: aabb + 4: aab + 5: aa + +/^[ab]{1,3}?(ab*?|b)/ + aabbbbb + 0: aabbbbb + 1: aabbbb + 2: aabbb + 3: aabb + 4: aab + 5: aa + +/^[ab]{1,3}(ab*?|b)/ + aabbbbb + 0: aabbbbb + 1: aabbbb + 2: aabbb + 3: aabb + 4: aab + 5: aa + +/ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # optional leading comment +(?: (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # initial word +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) )* # further okay, if led by a period +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +# address +| # or +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # one word, optionally followed by.... +(?: +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] | # atom and space parts, or... +\( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) | # comments, or... + +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +# quoted strings +)* +< (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # leading < +(?: @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* + +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* , (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +)* # further okay, if led by comma +: # closing colon +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* )? # optional route +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) # initial word +(?: (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +" (?: # opening quote... +[^\\\x80-\xff\n\015"] # Anything except backslash and quote +| # or +\\ [^\x80-\xff] # Escaped something (something != CR) +)* " # closing quote +) )* # further okay, if led by a period +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* @ (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # initial subdomain +(?: # +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* \. # if led by a period... +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* (?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| \[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) # ...further okay +)* +# address spec +(?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* > # trailing > +# name and address +) (?: [\040\t] | \( +(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* +\) )* # optional trailing comment +/x + Alan Other + 0: Alan Other + + 0: user@dom.ain + 1: user@dom + user\@dom.ain + 0: user@dom.ain + 1: user@dom + \"A. Other\" (a comment) + 0: "A. Other" (a comment) + 1: "A. Other" + 2: "A. Other" + A. Other (a comment) + 0: Other (a comment) + 1: Other + 2: Other + \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay + 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay + 1: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re + A missing angle @,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# additional words +)* +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +# address +| # or +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +# leading word +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # "normal" atoms and or spaces +(?: +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +| +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +) # "special" comment or quoted string +[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # more "normal" +)* +< +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# < +(?: +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +(?: , +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +)* # additional domains +: +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)? # optional route +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +# Atom +| # or +" # " +[^\\\x80-\xff\n\015"] * # normal +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* +" # " +# Quoted string +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# additional words +)* +@ +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +(?: +\. +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +(?: +[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... +(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom +| +\[ # [ +(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff +\] # ] +) +[\040\t]* # Nab whitespace. +(?: +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: # ( +(?: \\ [^\x80-\xff] | +\( # ( +[^\\\x80-\xff\n\015()] * # normal* +(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* +\) # ) +) # special +[^\\\x80-\xff\n\015()] * # normal* +)* # )* +\) # ) +[\040\t]* )* # If comment found, allow more spaces. +# optional trailing comments +)* +# address spec +> # > +# name and address +) +/x + Alan Other + 0: Alan Other + + 0: user@dom.ain + 1: user@dom + user\@dom.ain + 0: user@dom.ain + 1: user@dom + \"A. Other\" (a comment) + 0: "A. Other" + A. Other (a comment) + 0: Other + \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay + 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay + 1: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re + A missing angle ?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff + +/P[^*]TAIRE[^*]{1,6}?LL/ + xxxxxxxxxxxPSTAIREISLLxxxxxxxxx + 0: PSTAIREISLL + +/P[^*]TAIRE[^*]{1,}?LL/ + xxxxxxxxxxxPSTAIREISLLxxxxxxxxx + 0: PSTAIREISLL + +/(\.\d\d[1-9]?)\d+/ + 1.230003938 + 0: .230003938 + 1: .23000393 + 2: .2300039 + 3: .230003 + 4: .23000 + 5: .2300 + 6: .230 + 1.875000282 + 0: .875000282 + 1: .87500028 + 2: .8750002 + 3: .875000 + 4: .87500 + 5: .8750 + 6: .875 + 1.235 + 0: .235 + +/(\.\d\d((?=0)|\d(?=\d)))/ + 1.230003938 + 0: .230 + 1: .23 + 1.875000282 + 0: .875 + *** Failers +No match + 1.235 +No match + +/a(?)b/ + ab + 0: ab + +/\b(foo)\s+(\w+)/i + Food is on the foo table + 0: foo table + 1: foo tabl + 2: foo tab + 3: foo ta + 4: foo t + +/foo(.*)bar/ + The food is under the bar in the barn. + 0: food is under the bar in the bar + 1: food is under the bar + +/foo(.*?)bar/ + The food is under the bar in the barn. + 0: food is under the bar in the bar + 1: food is under the bar + +/(.*)(\d*)/ + I have 2 numbers: 53147 +Matched, but too many subsidiary matches + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: 5314 + 2: I have 2 numbers: 531 + 3: I have 2 numbers: 53 + 4: I have 2 numbers: 5 + 5: I have 2 numbers: + 6: I have 2 numbers: + 7: I have 2 numbers + 8: I have 2 number + 9: I have 2 numbe +10: I have 2 numb +11: I have 2 num +12: I have 2 nu +13: I have 2 n +14: I have 2 +15: I have 2 +16: I have +17: I have +18: I hav +19: I ha +20: I h +21: I + +/(.*)(\d+)/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: 5314 + 2: I have 2 numbers: 531 + 3: I have 2 numbers: 53 + 4: I have 2 numbers: 5 + 5: I have 2 + +/(.*?)(\d*)/ + I have 2 numbers: 53147 +Matched, but too many subsidiary matches + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: 5314 + 2: I have 2 numbers: 531 + 3: I have 2 numbers: 53 + 4: I have 2 numbers: 5 + 5: I have 2 numbers: + 6: I have 2 numbers: + 7: I have 2 numbers + 8: I have 2 number + 9: I have 2 numbe +10: I have 2 numb +11: I have 2 num +12: I have 2 nu +13: I have 2 n +14: I have 2 +15: I have 2 +16: I have +17: I have +18: I hav +19: I ha +20: I h +21: I + +/(.*?)(\d+)/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + 1: I have 2 numbers: 5314 + 2: I have 2 numbers: 531 + 3: I have 2 numbers: 53 + 4: I have 2 numbers: 5 + 5: I have 2 + +/(.*)(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + +/(.*?)(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + +/(.*)\b(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + +/(.*\D)(\d+)$/ + I have 2 numbers: 53147 + 0: I have 2 numbers: 53147 + +/^\D*(?!123)/ + ABC123 + 0: AB + 1: A + 2: + +/^(\D*)(?=\d)(?!123)/ + ABC445 + 0: ABC + *** Failers +No match + ABC123 +No match + +/^[W-]46]/ + W46]789 + 0: W46] + -46]789 + 0: -46] + *** Failers +No match + Wall +No match + Zebra +No match + 42 +No match + [abcd] +No match + ]abcd[ +No match + +/^[W-\]46]/ + W46]789 + 0: W + Wall + 0: W + Zebra + 0: Z + Xylophone + 0: X + 42 + 0: 4 + [abcd] + 0: [ + ]abcd[ + 0: ] + \\backslash + 0: \ + *** Failers +No match + -46]789 +No match + well +No match + +/\d\d\/\d\d\/\d\d\d\d/ + 01/01/2000 + 0: 01/01/2000 + +/word (?:[a-zA-Z0-9]+ ){0,10}otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark otherword + 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword + word cat dog elephant mussel cow horse canary baboon snake shark +No match + +/word (?:[a-zA-Z0-9]+ ){0,300}otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope +No match + +/^(a){0,0}/ + bcd + 0: + abc + 0: + aab + 0: + +/^(a){0,1}/ + bcd + 0: + abc + 0: a + 1: + aab + 0: a + 1: + +/^(a){0,2}/ + bcd + 0: + abc + 0: a + 1: + aab + 0: aa + 1: a + 2: + +/^(a){0,3}/ + bcd + 0: + abc + 0: a + 1: + aab + 0: aa + 1: a + 2: + aaa + 0: aaa + 1: aa + 2: a + 3: + +/^(a){0,}/ + bcd + 0: + abc + 0: a + 1: + aab + 0: aa + 1: a + 2: + aaa + 0: aaa + 1: aa + 2: a + 3: + aaaaaaaa + 0: aaaaaaaa + 1: aaaaaaa + 2: aaaaaa + 3: aaaaa + 4: aaaa + 5: aaa + 6: aa + 7: a + 8: + +/^(a){1,1}/ + bcd +No match + abc + 0: a + aab + 0: a + +/^(a){1,2}/ + bcd +No match + abc + 0: a + aab + 0: aa + 1: a + +/^(a){1,3}/ + bcd +No match + abc + 0: a + aab + 0: aa + 1: a + aaa + 0: aaa + 1: aa + 2: a + +/^(a){1,}/ + bcd +No match + abc + 0: a + aab + 0: aa + 1: a + aaa + 0: aaa + 1: aa + 2: a + aaaaaaaa + 0: aaaaaaaa + 1: aaaaaaa + 2: aaaaaa + 3: aaaaa + 4: aaaa + 5: aaa + 6: aa + 7: a + +/.*\.gif/ + borfle\nbib.gif\nno + 0: bib.gif + +/.{0,}\.gif/ + borfle\nbib.gif\nno + 0: bib.gif + +/.*\.gif/m + borfle\nbib.gif\nno + 0: bib.gif + +/.*\.gif/s + borfle\nbib.gif\nno + 0: borfle\x0abib.gif + +/.*\.gif/ms + borfle\nbib.gif\nno + 0: borfle\x0abib.gif + +/.*$/ + borfle\nbib.gif\nno + 0: no + +/.*$/m + borfle\nbib.gif\nno + 0: borfle + +/.*$/s + borfle\nbib.gif\nno + 0: borfle\x0abib.gif\x0ano + +/.*$/ms + borfle\nbib.gif\nno + 0: borfle\x0abib.gif\x0ano + 1: borfle\x0abib.gif + 2: borfle + +/.*$/ + borfle\nbib.gif\nno\n + 0: no + +/.*$/m + borfle\nbib.gif\nno\n + 0: borfle + +/.*$/s + borfle\nbib.gif\nno\n + 0: borfle\x0abib.gif\x0ano\x0a + 1: borfle\x0abib.gif\x0ano + +/.*$/ms + borfle\nbib.gif\nno\n + 0: borfle\x0abib.gif\x0ano\x0a + 1: borfle\x0abib.gif\x0ano + 2: borfle\x0abib.gif + 3: borfle + +/(.*X|^B)/ + abcde\n1234Xyz + 0: 1234X + BarFoo + 0: B + *** Failers +No match + abcde\nBar +No match + +/(.*X|^B)/m + abcde\n1234Xyz + 0: 1234X + BarFoo + 0: B + abcde\nBar + 0: B + +/(.*X|^B)/s + abcde\n1234Xyz + 0: abcde\x0a1234X + BarFoo + 0: B + *** Failers +No match + abcde\nBar +No match + +/(.*X|^B)/ms + abcde\n1234Xyz + 0: abcde\x0a1234X + BarFoo + 0: B + abcde\nBar + 0: B + +/(?s)(.*X|^B)/ + abcde\n1234Xyz + 0: abcde\x0a1234X + BarFoo + 0: B + *** Failers +No match + abcde\nBar +No match + +/(?s:.*X|^B)/ + abcde\n1234Xyz + 0: abcde\x0a1234X + BarFoo + 0: B + *** Failers +No match + abcde\nBar +No match + +/^.*B/ + **** Failers +No match + abc\nB +No match + +/(?s)^.*B/ + abc\nB + 0: abc\x0aB + +/(?m)^.*B/ + abc\nB + 0: B + +/(?ms)^.*B/ + abc\nB + 0: abc\x0aB + +/(?ms)^B/ + abc\nB + 0: B + +/(?s)B$/ + B\n + 0: B + +/^[0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9]/ + 123456654321 + 0: 123456654321 + +/^\d\d\d\d\d\d\d\d\d\d\d\d/ + 123456654321 + 0: 123456654321 + +/^[\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d]/ + 123456654321 + 0: 123456654321 + +/^[abc]{12}/ + abcabcabcabc + 0: abcabcabcabc + +/^[a-c]{12}/ + abcabcabcabc + 0: abcabcabcabc + +/^(a|b|c){12}/ + abcabcabcabc + 0: abcabcabcabc + +/^[abcdefghijklmnopqrstuvwxy0123456789]/ + n + 0: n + *** Failers +No match + z +No match + +/abcde{0,0}/ + abcd + 0: abcd + *** Failers +No match + abce +No match + +/ab[cd]{0,0}e/ + abe + 0: abe + *** Failers +No match + abcde +No match + +/ab(c){0,0}d/ + abd + 0: abd + *** Failers +No match + abcd +No match + +/a(b*)/ + a + 0: a + ab + 0: ab + 1: a + abbbb + 0: abbbb + 1: abbb + 2: abb + 3: ab + 4: a + *** Failers + 0: a + bbbbb +No match + +/ab\d{0}e/ + abe + 0: abe + *** Failers +No match + ab1e +No match + +/"([^\\"]+|\\.)*"/ + the \"quick\" brown fox + 0: "quick" + \"the \\\"quick\\\" brown fox\" + 0: "the \"quick\" brown fox" + +/.*?/g+ + abc + 0: abc + 0+ + 1: ab + 2: a + 3: + 0: + 0+ + +/\b/g+ + abc + 0: + 0+ abc + 0: + 0+ + +/\b/+g + abc + 0: + 0+ abc + 0: + 0+ + +//g + abc + 0: + 0: + 0: + 0: + +/]{0,})>]{0,})>([\d]{0,}\.)(.*)((
([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is + 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide + 0: 43.Word Processor
(N-1286)Lega lstaff.comCA - Statewide + +/a[^a]b/ + acb + 0: acb + a\nb + 0: a\x0ab + +/a.b/ + acb + 0: acb + *** Failers +No match + a\nb +No match + +/a[^a]b/s + acb + 0: acb + a\nb + 0: a\x0ab + +/a.b/s + acb + 0: acb + a\nb + 0: a\x0ab + +/^(b+?|a){1,2}?c/ + bac + 0: bac + bbac + 0: bbac + bbbac + 0: bbbac + bbbbac + 0: bbbbac + bbbbbac + 0: bbbbbac + +/^(b+|a){1,2}?c/ + bac + 0: bac + bbac + 0: bbac + bbbac + 0: bbbac + bbbbac + 0: bbbbac + bbbbbac + 0: bbbbbac + +/(?!\A)x/m + x\nb\n +No match + a\bx\n + 0: x + +/\x0{ab}/ + \0{ab} + 0: \x00{ab} + +/(A|B)*?CD/ + CD + 0: CD + +/(A|B)*CD/ + CD + 0: CD + +/(?.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/ +No match + +"(?>.*/)foo" + /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo + 0: /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo + +/(?>(\.\d\d[1-9]?))\d+/ + 1.230003938 + 0: .230003938 + 1: .23000393 + 2: .2300039 + 3: .230003 + 4: .23000 + 5: .2300 + 6: .230 + 1.875000282 + 0: .875000282 + 1: .87500028 + 2: .8750002 + 3: .875000 + 4: .87500 + 5: .8750 + *** Failers +No match + 1.235 +No match + +/^((?>\w+)|(?>\s+))*$/ + now is the time for all good men to come to the aid of the party + 0: now is the time for all good men to come to the aid of the party + *** Failers +No match + this is not a line with only words and spaces! +No match + +/(\d+)(\w)/ + 12345a + 0: 12345a + 1: 12345 + 2: 1234 + 3: 123 + 4: 12 + 12345+ + 0: 12345 + 1: 1234 + 2: 123 + 3: 12 + +/((?>\d+))(\w)/ + 12345a + 0: 12345a + *** Failers +No match + 12345+ +No match + +/(?>a+)b/ + aaab + 0: aaab + +/((?>a+)b)/ + aaab + 0: aaab + +/(?>(a+))b/ + aaab + 0: aaab + +/(?>b)+/ + aaabbbccc + 0: bbb + 1: bb + 2: b + +/(?>a+|b+|c+)*c/ + aaabbbbccccd + 0: aaabbbbcccc + 1: aaabbbbc + +/(a+|b+|c+)*c/ + aaabbbbccccd + 0: aaabbbbcccc + 1: aaabbbbccc + 2: aaabbbbcc + 3: aaabbbbc + +/((?>[^()]+)|\([^()]*\))+/ + ((abc(ade)ufh()()x + 0: abc(ade)ufh()()x + 1: abc(ade)ufh()() + 2: abc(ade)ufh() + 3: abc(ade)ufh + 4: abc(ade) + 5: abc + +/\(((?>[^()]+)|\([^()]+\))+\)/ + (abc) + 0: (abc) + (abc(def)xyz) + 0: (abc(def)xyz) + *** Failers +No match + ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + +/a(?-i)b/i + ab + 0: ab + Ab + 0: Ab + *** Failers +No match + aB +No match + AB +No match + +/(a (?x)b c)d e/ + a bcd e + 0: a bcd e + *** Failers +No match + a b cd e +No match + abcd e +No match + a bcde +No match + +/(a b(?x)c d (?-x)e f)/ + a bcde f + 0: a bcde f + *** Failers +No match + abcdef +No match + +/(a(?i)b)c/ + abc + 0: abc + aBc + 0: aBc + *** Failers +No match + abC +No match + aBC +No match + Abc +No match + ABc +No match + ABC +No match + AbC +No match + +/a(?i:b)c/ + abc + 0: abc + aBc + 0: aBc + *** Failers +No match + ABC +No match + abC +No match + aBC +No match + +/a(?i:b)*c/ + aBc + 0: aBc + aBBc + 0: aBBc + *** Failers +No match + aBC +No match + aBBC +No match + +/a(?=b(?i)c)\w\wd/ + abcd + 0: abcd + abCd + 0: abCd + *** Failers +No match + aBCd +No match + abcD +No match + +/(?s-i:more.*than).*million/i + more than million + 0: more than million + more than MILLION + 0: more than MILLION + more \n than Million + 0: more \x0a than Million + *** Failers +No match + MORE THAN MILLION +No match + more \n than \n million +No match + +/(?:(?s-i)more.*than).*million/i + more than million + 0: more than million + more than MILLION + 0: more than MILLION + more \n than Million + 0: more \x0a than Million + *** Failers +No match + MORE THAN MILLION +No match + more \n than \n million +No match + +/(?>a(?i)b+)+c/ + abc + 0: abc + aBbc + 0: aBbc + aBBc + 0: aBBc + *** Failers +No match + Abc +No match + abAb +No match + abbC +No match + +/(?=a(?i)b)\w\wc/ + abc + 0: abc + aBc + 0: aBc + *** Failers +No match + Ab +No match + abC +No match + aBC +No match + +/(?<=a(?i)b)(\w\w)c/ + abxxc + 0: xxc + aBxxc + 0: xxc + *** Failers +No match + Abxxc +No match + ABxxc +No match + abxxC +No match + +/^(?(?=abc)\w{3}:|\d\d)$/ + abc: + 0: abc: + 12 + 0: 12 + *** Failers +No match + 123 +No match + xyz +No match + +/^(?(?!abc)\d\d|\w{3}:)$/ + abc: + 0: abc: + 12 + 0: 12 + *** Failers +No match + 123 +No match + xyz +No match + +/(?(?<=foo)bar|cat)/ + foobar + 0: bar + cat + 0: cat + fcat + 0: cat + focat + 0: cat + *** Failers +No match + foocat +No match + +/(?(?a*)*/ + a + 0: a + 1: + aa + 0: aa + 1: + aaaa + 0: aaaa + 1: + +/(abc|)+/ + abc + 0: abc + 1: + abcabc + 0: abcabc + 1: abc + 2: + abcabcabc + 0: abcabcabc + 1: abcabc + 2: abc + 3: + xyz + 0: + +/([a]*)*/ + a + 0: a + 1: + aaaaa + 0: aaaaa + 1: aaaa + 2: aaa + 3: aa + 4: a + 5: + +/([ab]*)*/ + a + 0: a + 1: + b + 0: b + 1: + ababab + 0: ababab + 1: ababa + 2: abab + 3: aba + 4: ab + 5: a + 6: + aaaabcde + 0: aaaab + 1: aaaa + 2: aaa + 3: aa + 4: a + 5: + bbbb + 0: bbbb + 1: bbb + 2: bb + 3: b + 4: + +/([^a]*)*/ + b + 0: b + 1: + bbbb + 0: bbbb + 1: bbb + 2: bb + 3: b + 4: + aaa + 0: + +/([^ab]*)*/ + cccc + 0: cccc + 1: ccc + 2: cc + 3: c + 4: + abab + 0: + +/([a]*?)*/ + a + 0: a + 1: + aaaa + 0: aaaa + 1: aaa + 2: aa + 3: a + 4: + +/([ab]*?)*/ + a + 0: a + 1: + b + 0: b + 1: + abab + 0: abab + 1: aba + 2: ab + 3: a + 4: + baba + 0: baba + 1: bab + 2: ba + 3: b + 4: + +/([^a]*?)*/ + b + 0: b + 1: + bbbb + 0: bbbb + 1: bbb + 2: bb + 3: b + 4: + aaa + 0: + +/([^ab]*?)*/ + c + 0: c + 1: + cccc + 0: cccc + 1: ccc + 2: cc + 3: c + 4: + baba + 0: + +/(?>a*)*/ + a + 0: a + 1: + aaabcde + 0: aaa + 1: + +/((?>a*))*/ + aaaaa + 0: aaaaa + 1: + aabbaa + 0: aa + 1: + +/((?>a*?))*/ + aaaaa + 0: aaaaa + 1: + aabbaa + 0: aa + 1: + +/(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /x + 12-sep-98 + 0: 12-sep-98 + 12-09-98 + 0: 12-09-98 + *** Failers +No match + sep-12-98 +No match + +/(?i:saturday|sunday)/ + saturday + 0: saturday + sunday + 0: sunday + Saturday + 0: Saturday + Sunday + 0: Sunday + SATURDAY + 0: SATURDAY + SUNDAY + 0: SUNDAY + SunDay + 0: SunDay + +/(a(?i)bc|BB)x/ + abcx + 0: abcx + aBCx + 0: aBCx + bbx + 0: bbx + BBx + 0: BBx + *** Failers +No match + abcX +No match + aBCX +No match + bbX +No match + BBX +No match + +/^([ab](?i)[cd]|[ef])/ + ac + 0: ac + aC + 0: aC + bD + 0: bD + elephant + 0: e + Europe + 0: E + frog + 0: f + France + 0: F + *** Failers +No match + Africa +No match + +/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/ + ab + 0: ab + aBd + 0: aBd + xy + 0: xy + xY + 0: xY + zebra + 0: z + Zambesi + 0: Z + *** Failers +No match + aCD +No match + XY +No match + +/(?<=foo\n)^bar/m + foo\nbar + 0: bar + *** Failers +No match + bar +No match + baz\nbar +No match + +/(?<=(?]&/ + <&OUT + 0: <& + +/(?:(f)(o)(o)|(b)(a)(r))*/ + foobar + 0: foobar + 1: foo + 2: + +/(?<=a)b/ + ab + 0: b + *** Failers +No match + cb +No match + b +No match + +/(?a+)ab/ + +/(?>a+)b/ + aaab + 0: aaab + +/([[:]+)/ + a:[b]: + 0: :[ + 1: : + +/([[=]+)/ + a=[b]= + 0: =[ + 1: = + +/([[.]+)/ + a.[b]. + 0: .[ + 1: . + +/((?>a+)b)/ + aaab + 0: aaab + +/(?>(a+))b/ + aaab + 0: aaab + +/((?>[^()]+)|\([^()]*\))+/ + ((abc(ade)ufh()()x + 0: abc(ade)ufh()()x + 1: abc(ade)ufh()() + 2: abc(ade)ufh() + 3: abc(ade)ufh + 4: abc(ade) + 5: abc + +/a\Z/ + *** Failers +No match + aaab +No match + a\nb\n +No match + +/b\Z/ + a\nb\n + 0: b + +/b\z/ + +/b\Z/ + a\nb + 0: b + +/b\z/ + a\nb + 0: b + *** Failers +No match + +/(?>.*)(?<=(abcd|wxyz))/ + alphabetabcd + 0: alphabetabcd + endingwxyz + 0: endingwxyz + *** Failers +No match + a rather long string that doesn't end with one of them +No match + +/word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark otherword + 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword + word cat dog elephant mussel cow horse canary baboon snake shark +No match + +/word (?>[a-zA-Z0-9]+ ){0,30}otherword/ + word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope +No match + +/(?<=\d{3}(?!999))foo/ + 999foo + 0: foo + 123999foo + 0: foo + *** Failers +No match + 123abcfoo +No match + +/(?<=(?!...999)\d{3})foo/ + 999foo + 0: foo + 123999foo + 0: foo + *** Failers +No match + 123abcfoo +No match + +/(?<=\d{3}(?!999)...)foo/ + 123abcfoo + 0: foo + 123456foo + 0: foo + *** Failers +No match + 123999foo +No match + +/(?<=\d{3}...)(?Z)+|A)*/ + ZABCDEFG + 0: ZA + 1: Z + 2: + +/((?>)+|A)*/ + ZABCDEFG + 0: + +/a*/g + abbab + 0: a + 1: + 0: + 0: + 0: a + 1: + 0: + 0: + +/^[a-\d]/ + abcde + 0: a + -things + 0: - + 0digit + 0: 0 + *** Failers +No match + bcdef +No match + +/^[\d-a]/ + abcde + 0: a + -things + 0: - + 0digit + 0: 0 + *** Failers +No match + bcdef +No match + +/[[:space:]]+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09\x0a\x0c\x0d\x0b + 1: \x09\x0a\x0c\x0d + 2: \x09\x0a\x0c + 3: \x09\x0a + 4: \x09 + 5: + +/[[:blank:]]+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09 + 1: + +/[\s]+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09\x0a\x0c\x0d + 1: \x09\x0a\x0c + 2: \x09\x0a + 3: \x09 + 4: + +/\s+/ + > \x09\x0a\x0c\x0d\x0b< + 0: \x09\x0a\x0c\x0d + 1: \x09\x0a\x0c + 2: \x09\x0a + 3: \x09 + 4: + +/a b/x + ab +No match + +/(?!\A)x/m + a\nxb\n + 0: x + +/(?!^)x/m + a\nxb\n +No match + +/abc\Qabc\Eabc/ + abcabcabc + 0: abcabcabc + +/abc\Q(*+|\Eabc/ + abc(*+|abc + 0: abc(*+|abc + +/ abc\Q abc\Eabc/x + abc abcabc + 0: abc abcabc + *** Failers +No match + abcabcabc +No match + +/abc#comment + \Q#not comment + literal\E/x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/abc#comment + \Q#not comment + literal/x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/abc#comment + \Q#not comment + literal\E #more comment + /x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/abc#comment + \Q#not comment + literal\E #more comment/x + abc#not comment\n literal + 0: abc#not comment\x0a literal + +/\Qabc\$xyz\E/ + abc\\\$xyz + 0: abc\$xyz + +/\Qabc\E\$\Qxyz\E/ + abc\$xyz + 0: abc$xyz + +/\Gabc/ + abc + 0: abc + *** Failers +No match + xyzabc +No match + +/\Gabc./g + abc1abc2xyzabc3 + 0: abc1 + 0: abc2 + +/abc./g + abc1abc2xyzabc3 + 0: abc1 + 0: abc2 + 0: abc3 + +/a(?x: b c )d/ + XabcdY + 0: abcd + *** Failers +No match + Xa b c d Y +No match + +/((?x)x y z | a b c)/ + XabcY + 0: abc + AxyzB + 0: xyz + +/(?i)AB(?-i)C/ + XabCY + 0: abC + *** Failers +No match + XabcY +No match + +/((?i)AB(?-i)C|D)E/ + abCE + 0: abCE + DE + 0: DE + *** Failers +No match + abcE +No match + abCe +No match + dE +No match + De +No match + +/[z\Qa-d]\E]/ + z + 0: z + a + 0: a + - + 0: - + d + 0: d + ] + 0: ] + *** Failers + 0: a + b +No match + +/[\z\C]/ + z + 0: z + C + 0: C + +/\M/ + M + 0: M + +/(a+)*b/ + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +No match + +/(?i)reg(?:ul(?:[aä]|ae)r|ex)/ + REGular + 0: REGular + regulaer + 0: regulaer + Regex + 0: Regex + regulär + 0: regul\xe4r + +/Åæåä[à-ÿÀ-ß]+/ + Åæåäà + 0: \xc5\xe6\xe5\xe4\xe0 + Åæåäÿ + 0: \xc5\xe6\xe5\xe4\xff + ÅæåäÀ + 0: \xc5\xe6\xe5\xe4\xc0 + Åæåäß + 0: \xc5\xe6\xe5\xe4\xdf + +/(?<=Z)X./ + \x84XAZXB + 0: XB + +/^(?(2)a|(1)(2))+$/ + 123a +Error -17 + +/(?<=a|bbbb)c/ + ac + 0: c + bbbbc + 0: c + +/abc/>testsavedregex +Compiled regex written to testsavedregex +testsavedregex +Compiled regex written to testsavedregex +testsavedregex +Compiled regex written to testsavedregex +Study data written to testsavedregex +testsavedregex +Compiled regex written to testsavedregex +Study data written to testsavedregex + + 0: abc + xyz\r\nabc\ + 0: abc + xyz\rabc\ + 0: abc + xyz\r\nabc\ + 0: abc + ** Failers +No match + xyz\nabc\ +No match + xyz\r\nabc\ +No match + xyz\nabc\ +No match + xyz\rabc\ +No match + xyz\rabc\ +No match + +/abc$/m + xyzabc + 0: abc + xyzabc\n + 0: abc + xyzabc\npqr + 0: abc + xyzabc\r\ + 0: abc + xyzabc\rpqr\ + 0: abc + xyzabc\r\n\ + 0: abc + xyzabc\r\npqr\ + 0: abc + ** Failers +No match + xyzabc\r +No match + xyzabc\rpqr +No match + xyzabc\r\n +No match + xyzabc\r\npqr +No match + +/^abc/m + xyz\rabcdef + 0: abc + xyz\nabcdef\ + 0: abc + ** Failers +No match + xyz\nabcdef +No match + +/^abc/m + xyz\nabcdef + 0: abc + xyz\rabcdef\ + 0: abc + ** Failers +No match + xyz\rabcdef +No match + +/^abc/m + xyz\r\nabcdef + 0: abc + xyz\rabcdef\ + 0: abc + ** Failers +No match + xyz\rabcdef +No match + +/.*/ + abc\ndef + 0: abc + 1: ab + 2: a + 3: + abc\rdef + 0: abc\x0ddef + 1: abc\x0dde + 2: abc\x0dd + 3: abc\x0d + 4: abc + 5: ab + 6: a + 7: + abc\r\ndef + 0: abc\x0d + 1: abc + 2: ab + 3: a + 4: + \abc\ndef + 0: abc\x0adef + 1: abc\x0ade + 2: abc\x0ad + 3: abc\x0a + 4: abc + 5: ab + 6: a + 7: + \abc\rdef + 0: abc + 1: ab + 2: a + 3: + \abc\r\ndef + 0: abc + 1: ab + 2: a + 3: + \abc\ndef + 0: abc\x0adef + 1: abc\x0ade + 2: abc\x0ad + 3: abc\x0a + 4: abc + 5: ab + 6: a + 7: + \abc\rdef + 0: abc\x0ddef + 1: abc\x0dde + 2: abc\x0dd + 3: abc\x0d + 4: abc + 5: ab + 6: a + 7: + \abc\r\ndef + 0: abc + 1: ab + 2: a + 3: + +/\w+(.)(.)?def/s + abc\ndef + 0: abc\x0adef + abc\rdef + 0: abc\x0ddef + abc\r\ndef + 0: abc\x0d\x0adef + +/ End of testinput7 / diff --git a/libs/pcre/testdata/testoutput8 b/libs/pcre/testdata/testoutput8 new file mode 100644 index 0000000000..72e7673f56 --- /dev/null +++ b/libs/pcre/testdata/testoutput8 @@ -0,0 +1,1031 @@ +/-- Do not use the \x{} construct except with patterns that have the --/ +/-- /8 option set, because PCRE doesn't recognize them as UTF-8 unless --/ +No match +/-- that option is set. However, the latest Perls recognize them always. --/ +No match + +/\x{100}ab/8 + \x{100}ab + 0: \x{100}ab + +/a\x{100}*b/8 + ab + 0: ab + a\x{100}b + 0: a\x{100}b + a\x{100}\x{100}b + 0: a\x{100}\x{100}b + +/a\x{100}+b/8 + a\x{100}b + 0: a\x{100}b + a\x{100}\x{100}b + 0: a\x{100}\x{100}b + *** Failers +No match + ab +No match + +/\bX/8 + Xoanon + 0: X + +Xoanon + 0: X + \x{300}Xoanon + 0: X + *** Failers +No match + YXoanon +No match + +/\BX/8 + YXoanon + 0: X + *** Failers +No match + Xoanon +No match + +Xoanon +No match + \x{300}Xoanon +No match + +/X\b/8 + X+oanon + 0: X + ZX\x{300}oanon + 0: X + FAX + 0: X + *** Failers +No match + Xoanon +No match + +/X\B/8 + Xoanon + 0: X + *** Failers +No match + X+oanon +No match + ZX\x{300}oanon +No match + FAX +No match + +/[^a]/8 + abcd + 0: b + a\x{100} + 0: \x{100} + +/^[abc\x{123}\x{400}-\x{402}]{2,3}\d/8 + ab99 + 0: ab9 + \x{123}\x{123}45 + 0: \x{123}\x{123}4 + \x{400}\x{401}\x{402}6 + 0: \x{400}\x{401}\x{402}6 + *** Failers +No match + d99 +No match + \x{123}\x{122}4 +No match + \x{400}\x{403}6 +No match + \x{400}\x{401}\x{402}\x{402}6 +No match + +/abc/8 + Ã] +Error -10 + à +Error -10 + ÃÃà +Error -10 + ÃÃÃ\? +No match + +/a.b/8 + acb + 0: acb + a\x7fb + 0: a\x{7f}b + a\x{100}b + 0: a\x{100}b + *** Failers +No match + a\nb +No match + +/a(.{3})b/8 + a\x{4000}xyb + 0: a\x{4000}xyb + a\x{4000}\x7fyb + 0: a\x{4000}\x{7f}yb + a\x{4000}\x{100}yb + 0: a\x{4000}\x{100}yb + *** Failers +No match + a\x{4000}b +No match + ac\ncb +No match + +/a(.*?)(.)/ + a\xc0\x88b + 0: a\xc0\x88b + 1: a\xc0\x88 + 2: a\xc0 + +/a(.*?)(.)/8 + a\x{100}b + 0: a\x{100}b + 1: a\x{100} + +/a(.*)(.)/ + a\xc0\x88b + 0: a\xc0\x88b + 1: a\xc0\x88 + 2: a\xc0 + +/a(.*)(.)/8 + a\x{100}b + 0: a\x{100}b + 1: a\x{100} + +/a(.)(.)/ + a\xc0\x92bcd + 0: a\xc0\x92 + +/a(.)(.)/8 + a\x{240}bcd + 0: a\x{240}b + +/a(.?)(.)/ + a\xc0\x92bcd + 0: a\xc0\x92 + 1: a\xc0 + +/a(.?)(.)/8 + a\x{240}bcd + 0: a\x{240}b + 1: a\x{240} + +/a(.??)(.)/ + a\xc0\x92bcd + 0: a\xc0\x92 + 1: a\xc0 + +/a(.??)(.)/8 + a\x{240}bcd + 0: a\x{240}b + 1: a\x{240} + +/a(.{3})b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + *** Failers +No match + a\x{1234}b +No match + ac\ncb +No match + +/a(.{3,})b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + 0: axxxxbcdefghijb + 1: axxxxb + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + *** Failers +No match + a\x{1234}b +No match + +/a(.{3,}?)b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + 0: axxxxbcdefghijb + 1: axxxxb + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + *** Failers +No match + a\x{1234}b +No match + +/a(.{3,5})b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + 0: axxxxb + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + axbxxbcdefghijb + 0: axbxxb + axxxxxbcdefghijb + 0: axxxxxb + *** Failers +No match + a\x{1234}b +No match + axxxxxxbcdefghijb +No match + +/a(.{3,5}?)b/8 + a\x{1234}xyb + 0: a\x{1234}xyb + a\x{1234}\x{4321}yb + 0: a\x{1234}\x{4321}yb + a\x{1234}\x{4321}\x{3412}b + 0: a\x{1234}\x{4321}\x{3412}b + axxxxbcdefghijb + 0: axxxxb + a\x{1234}\x{4321}\x{3412}\x{3421}b + 0: a\x{1234}\x{4321}\x{3412}\x{3421}b + axbxxbcdefghijb + 0: axbxxb + axxxxxbcdefghijb + 0: axxxxxb + *** Failers +No match + a\x{1234}b +No match + axxxxxxbcdefghijb +No match + +/^[a\x{c0}]/8 + *** Failers +No match + \x{100} +No match + +/(?<=aXb)cd/8 + aXbcd + 0: cd + +/(?<=a\x{100}b)cd/8 + a\x{100}bcd + 0: cd + +/(?<=a\x{100000}b)cd/8 + a\x{100000}bcd + 0: cd + +/(?:\x{100}){3}b/8 + \x{100}\x{100}\x{100}b + 0: \x{100}\x{100}\x{100}b + *** Failers +No match + \x{100}\x{100}b +No match + +/\x{ab}/8 + \x{ab} + 0: \x{ab} + \xc2\xab + 0: \x{ab} + *** Failers +No match + \x00{ab} +No match + +/(?<=(.))X/8 + WXYZ + 0: X + \x{256}XYZ + 0: X + *** Failers +No match + XYZ +No match + +/[^a]+/8g + bcd + 0: bcd + 1: bc + 2: b + \x{100}aY\x{256}Z + 0: \x{100} + 0: Y\x{256}Z + 1: Y\x{256} + 2: Y + +/^[^a]{2}/8 + \x{100}bc + 0: \x{100}b + +/^[^a]{2,}/8 + \x{100}bcAa + 0: \x{100}bcA + 1: \x{100}bc + 2: \x{100}b + +/^[^a]{2,}?/8 + \x{100}bca + 0: \x{100}bc + 1: \x{100}b + +/[^a]+/8ig + bcd + 0: bcd + 1: bc + 2: b + \x{100}aY\x{256}Z + 0: \x{100} + 0: Y\x{256}Z + 1: Y\x{256} + 2: Y + +/^[^a]{2}/8i + \x{100}bc + 0: \x{100}b + +/^[^a]{2,}/8i + \x{100}bcAa + 0: \x{100}bc + 1: \x{100}b + +/^[^a]{2,}?/8i + \x{100}bca + 0: \x{100}bc + 1: \x{100}b + +/\x{100}{0,0}/8 + abcd + 0: + +/\x{100}?/8 + abcd + 0: + \x{100}\x{100} + 0: \x{100} + 1: + +/\x{100}{0,3}/8 + \x{100}\x{100} + 0: \x{100}\x{100} + 1: \x{100} + 2: + \x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100} + 1: \x{100}\x{100} + 2: \x{100} + 3: + +/\x{100}*/8 + abce + 0: + \x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100}\x{100} + 1: \x{100}\x{100}\x{100} + 2: \x{100}\x{100} + 3: \x{100} + 4: + +/\x{100}{1,1}/8 + abcd\x{100}\x{100}\x{100}\x{100} + 0: \x{100} + +/\x{100}{1,3}/8 + abcd\x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100} + 1: \x{100}\x{100} + 2: \x{100} + +/\x{100}+/8 + abcd\x{100}\x{100}\x{100}\x{100} + 0: \x{100}\x{100}\x{100}\x{100} + 1: \x{100}\x{100}\x{100} + 2: \x{100}\x{100} + 3: \x{100} + +/\x{100}{3}/8 + abcd\x{100}\x{100}\x{100}XX + 0: \x{100}\x{100}\x{100} + +/\x{100}{3,5}/8 + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + 0: \x{100}\x{100}\x{100}\x{100}\x{100} + 1: \x{100}\x{100}\x{100}\x{100} + 2: \x{100}\x{100}\x{100} + +/\x{100}{3,}/8 + abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX + 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 1: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 2: \x{100}\x{100}\x{100}\x{100}\x{100} + 3: \x{100}\x{100}\x{100}\x{100} + 4: \x{100}\x{100}\x{100} + +/(?<=a\x{100}{2}b)X/8 + Xyyya\x{100}\x{100}bXzzz + 0: X + +/\D*/8 + aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +Matched, but too many subsidiary matches + 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 1: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 2: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 3: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 4: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 5: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 6: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 7: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 8: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + 9: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +10: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +11: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +12: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +13: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +14: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +15: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +16: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +17: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +18: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +19: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +20: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa +21: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa + +/\D*/8 + \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +Matched, but too many subsidiary matches + 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 1: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 2: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 3: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 4: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 5: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 6: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 7: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 8: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + 9: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +10: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +11: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +12: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +13: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +14: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +15: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +16: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +17: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +18: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +19: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +20: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} +21: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} + +/\D/8 + 1X2 + 0: X + 1\x{100}2 + 0: \x{100} + +/>\S/8 + > >X Y + 0: >X + > >\x{100} Y + 0: >\x{100} + +/\d/8 + \x{100}3 + 0: 3 + +/\s/8 + \x{100} X + 0: + +/\D+/8 + 12abcd34 + 0: abcd + 1: abc + 2: ab + 3: a + *** Failers + 0: *** Failers + 1: *** Failer + 2: *** Faile + 3: *** Fail + 4: *** Fai + 5: *** Fa + 6: *** F + 7: *** + 8: *** + 9: ** +10: * + 1234 +No match + +/\D{2,3}/8 + 12abcd34 + 0: abc + 1: ab + 12ab34 + 0: ab + *** Failers + 0: *** + 1: ** + 1234 +No match + 12a34 +No match + +/\D{2,3}?/8 + 12abcd34 + 0: abc + 1: ab + 12ab34 + 0: ab + *** Failers + 0: *** + 1: ** + 1234 +No match + 12a34 +No match + +/\d+/8 + 12abcd34 + 0: 12 + 1: 1 + *** Failers +No match + +/\d{2,3}/8 + 12abcd34 + 0: 12 + 1234abcd + 0: 123 + 1: 12 + *** Failers +No match + 1.4 +No match + +/\d{2,3}?/8 + 12abcd34 + 0: 12 + 1234abcd + 0: 123 + 1: 12 + *** Failers +No match + 1.4 +No match + +/\S+/8 + 12abcd34 + 0: 12abcd34 + 1: 12abcd3 + 2: 12abcd + 3: 12abc + 4: 12ab + 5: 12a + 6: 12 + 7: 1 + *** Failers + 0: *** + 1: ** + 2: * + \ \ +No match + +/\S{2,3}/8 + 12abcd34 + 0: 12a + 1: 12 + 1234abcd + 0: 123 + 1: 12 + *** Failers + 0: *** + 1: ** + \ \ +No match + +/\S{2,3}?/8 + 12abcd34 + 0: 12a + 1: 12 + 1234abcd + 0: 123 + 1: 12 + *** Failers + 0: *** + 1: ** + \ \ +No match + +/>\s+ <34 + 0: > < + *** Failers +No match + +/>\s{2,3} < + ab> < + *** Failers +No match + ab> \s{2,3}? < + ab> < + *** Failers +No match + ab> \xff< + 0: \xff + +/[\xff]/8 + >\x{ff}< + 0: \x{ff} + +/[^\xFF]/ + XYZ + 0: X + +/[^\xff]/8 + XYZ + 0: X + \x{123} + 0: \x{123} + +/^[ac]*b/8 + xb +No match + +/^[ac\x{100}]*b/8 + xb +No match + +/^[^x]*b/8i + xb +No match + +/^[^x]*b/8 + xb +No match + +/^\d*b/8 + xb +No match + +/(|a)/g8 + catac + 0: + 0: a + 1: + 0: + 0: a + 1: + 0: + 0: + a\x{256}a + 0: a + 1: + 0: + 0: a + 1: + 0: + +/^\x{85}$/8i + \x{85} + 0: \x{85} + +/ End of testinput 8 / diff --git a/libs/pcre/testdata/testoutput9 b/libs/pcre/testdata/testoutput9 new file mode 100644 index 0000000000..000e2b9882 --- /dev/null +++ b/libs/pcre/testdata/testoutput9 @@ -0,0 +1,1627 @@ +/\pL\P{Nd}/8 + AB + 0: AB + *** Failers + 0: Fa + A0 +No match + 00 +No match + +/\X./8 + AB + 0: AB + A\x{300}BC + 0: A\x{300}B + A\x{300}\x{301}\x{302}BC + 0: A\x{300}\x{301}\x{302}B + *** Failers + 0: ** + \x{300} +No match + +/\X\X/8 + ABC + 0: AB + A\x{300}B\x{300}\x{301}C + 0: A\x{300}B\x{300}\x{301} + A\x{300}\x{301}\x{302}BC + 0: A\x{300}\x{301}\x{302}B + *** Failers + 0: ** + \x{300} +No match + +/^\pL+/8 + abcd + 0: abcd + 1: abc + 2: ab + 3: a + a + 0: a + *** Failers +No match + +/^\PL+/8 + 1234 + 0: 1234 + 1: 123 + 2: 12 + 3: 1 + = + 0: = + *** Failers + 0: *** + 1: *** + 2: ** + 3: * + abcd +No match + +/^\X+/8 + abcdA\x{300}\x{301}\x{302} + 0: abcdA\x{300}\x{301}\x{302} + 1: abcd + 2: abc + 3: ab + 4: a + A\x{300}\x{301}\x{302} + 0: A\x{300}\x{301}\x{302} + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302} + 0: A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302} + 1: A\x{300}\x{301}\x{302} + a + 0: a + *** Failers + 0: *** Failers + 1: *** Failer + 2: *** Faile + 3: *** Fail + 4: *** Fai + 5: *** Fa + 6: *** F + 7: *** + 8: *** + 9: ** +10: * + \x{300}\x{301}\x{302} +No match + +/\X?abc/8 + abc + 0: abc + A\x{300}abc + 0: A\x{300}abc + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + 0: A\x{300}abc + \x{300}abc + 0: abc + *** Failers +No match + +/^\X?abc/8 + abc + 0: abc + A\x{300}abc + 0: A\x{300}abc + *** Failers +No match + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz +No match + \x{300}abc +No match + +/\X*abc/8 + abc + 0: abc + A\x{300}abc + 0: A\x{300}abc + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + 0: A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abc + \x{300}abc + 0: abc + *** Failers +No match + +/^\X*abc/8 + abc + 0: abc + A\x{300}abc + 0: A\x{300}abc + A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abcxyz + 0: A\x{300}\x{301}\x{302}A\x{300}A\x{300}A\x{300}abc + *** Failers +No match + \x{300}abc +No match + +/^\pL?=./8 + A=b + 0: A=b + =c + 0: =c + *** Failers +No match + 1=2 +No match + AAAA=b +No match + +/^\pL*=./8 + AAAA=b + 0: AAAA=b + =c + 0: =c + *** Failers +No match + 1=2 +No match + +/^\X{2,3}X/8 + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + 0: A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + 0: A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X + *** Failers +No match + X +No match + A\x{300}\x{301}\x{302}X +No match + A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}A\x{300}\x{301}\x{302}X +No match + +/^\pC\pL\pM\pN\pP\pS\pZ spare | |-> spare + | | | + | |-> spare |-> spare + | + |-> range flag + +The upper/lower casing information is set only for characters that come in +pairs. The non-one-to-one mappings in the Unicode data are ignored. + +When searching the data, proceed as follows: + +(1) Set up for a binary chop search. + +(2) If the top is not greater than the bottom, the character is not in the + table. Its type must therefore be "Cn" ("Undefined"). + +(3) Find the middle vector element. + +(4) Extract the code point and compare. If equal, we are done. + +(5) If the test character is smaller, set the top to the current point, and + goto (2). + +(6) If the current entry defines a range, compute the last character by adding + the offset, and see if the test character is within the range. If it is, + we are done. + +(7) Otherwise, set the bottom to one element past the current point and goto + (2). +*/ + +/* End of ucpinternal.h */ diff --git a/libs/pcre/ucptable.c b/libs/pcre/ucptable.c new file mode 100644 index 0000000000..ae665b3760 --- /dev/null +++ b/libs/pcre/ucptable.c @@ -0,0 +1,2968 @@ +/* This source module is automatically generated from the Unicode +property table. See ucpinternal.h for a description of the layout. */ + +static cnode ucp_table[] = { + { 0x09800000, 0x0000001f }, + { 0x09000020, 0x74000000 }, + { 0x09800021, 0x54000002 }, + { 0x09000024, 0x5c000000 }, + { 0x09800025, 0x54000002 }, + { 0x09000028, 0x58000000 }, + { 0x09000029, 0x48000000 }, + { 0x0900002a, 0x54000000 }, + { 0x0900002b, 0x64000000 }, + { 0x0900002c, 0x54000000 }, + { 0x0900002d, 0x44000000 }, + { 0x0980002e, 0x54000001 }, + { 0x09800030, 0x34000009 }, + { 0x0980003a, 0x54000001 }, + { 0x0980003c, 0x64000002 }, + { 0x0980003f, 0x54000001 }, + { 0x21000041, 0x24000020 }, + { 0x21000042, 0x24000020 }, + { 0x21000043, 0x24000020 }, + { 0x21000044, 0x24000020 }, + { 0x21000045, 0x24000020 }, + { 0x21000046, 0x24000020 }, + { 0x21000047, 0x24000020 }, + { 0x21000048, 0x24000020 }, + { 0x21000049, 0x24000020 }, + { 0x2100004a, 0x24000020 }, + { 0x2100004b, 0x24000020 }, + { 0x2100004c, 0x24000020 }, + { 0x2100004d, 0x24000020 }, + { 0x2100004e, 0x24000020 }, + { 0x2100004f, 0x24000020 }, + { 0x21000050, 0x24000020 }, + { 0x21000051, 0x24000020 }, + { 0x21000052, 0x24000020 }, + { 0x21000053, 0x24000020 }, + { 0x21000054, 0x24000020 }, + { 0x21000055, 0x24000020 }, + { 0x21000056, 0x24000020 }, + { 0x21000057, 0x24000020 }, + { 0x21000058, 0x24000020 }, + { 0x21000059, 0x24000020 }, + { 0x2100005a, 0x24000020 }, + { 0x0900005b, 0x58000000 }, + { 0x0900005c, 0x54000000 }, + { 0x0900005d, 0x48000000 }, + { 0x0900005e, 0x60000000 }, + { 0x0900005f, 0x40000000 }, + { 0x09000060, 0x60000000 }, + { 0x21000061, 0x1400ffe0 }, + { 0x21000062, 0x1400ffe0 }, + { 0x21000063, 0x1400ffe0 }, + { 0x21000064, 0x1400ffe0 }, + { 0x21000065, 0x1400ffe0 }, + { 0x21000066, 0x1400ffe0 }, + { 0x21000067, 0x1400ffe0 }, + { 0x21000068, 0x1400ffe0 }, + { 0x21000069, 0x1400ffe0 }, + { 0x2100006a, 0x1400ffe0 }, + { 0x2100006b, 0x1400ffe0 }, + { 0x2100006c, 0x1400ffe0 }, + { 0x2100006d, 0x1400ffe0 }, + { 0x2100006e, 0x1400ffe0 }, + { 0x2100006f, 0x1400ffe0 }, + { 0x21000070, 0x1400ffe0 }, + { 0x21000071, 0x1400ffe0 }, + { 0x21000072, 0x1400ffe0 }, + { 0x21000073, 0x1400ffe0 }, + { 0x21000074, 0x1400ffe0 }, + { 0x21000075, 0x1400ffe0 }, + { 0x21000076, 0x1400ffe0 }, + { 0x21000077, 0x1400ffe0 }, + { 0x21000078, 0x1400ffe0 }, + { 0x21000079, 0x1400ffe0 }, + { 0x2100007a, 0x1400ffe0 }, + { 0x0900007b, 0x58000000 }, + { 0x0900007c, 0x64000000 }, + { 0x0900007d, 0x48000000 }, + { 0x0900007e, 0x64000000 }, + { 0x0980007f, 0x00000020 }, + { 0x090000a0, 0x74000000 }, + { 0x090000a1, 0x54000000 }, + { 0x098000a2, 0x5c000003 }, + { 0x098000a6, 0x68000001 }, + { 0x090000a8, 0x60000000 }, + { 0x090000a9, 0x68000000 }, + { 0x210000aa, 0x14000000 }, + { 0x090000ab, 0x50000000 }, + { 0x090000ac, 0x64000000 }, + { 0x090000ad, 0x04000000 }, + { 0x090000ae, 0x68000000 }, + { 0x090000af, 0x60000000 }, + { 0x090000b0, 0x68000000 }, + { 0x090000b1, 0x64000000 }, + { 0x098000b2, 0x3c000001 }, + { 0x090000b4, 0x60000000 }, + { 0x090000b5, 0x140002e7 }, + { 0x090000b6, 0x68000000 }, + { 0x090000b7, 0x54000000 }, + { 0x090000b8, 0x60000000 }, + { 0x090000b9, 0x3c000000 }, + { 0x210000ba, 0x14000000 }, + { 0x090000bb, 0x4c000000 }, + { 0x098000bc, 0x3c000002 }, + { 0x090000bf, 0x54000000 }, + { 0x210000c0, 0x24000020 }, + { 0x210000c1, 0x24000020 }, + { 0x210000c2, 0x24000020 }, + { 0x210000c3, 0x24000020 }, + { 0x210000c4, 0x24000020 }, + { 0x210000c5, 0x24000020 }, + { 0x210000c6, 0x24000020 }, + { 0x210000c7, 0x24000020 }, + { 0x210000c8, 0x24000020 }, + { 0x210000c9, 0x24000020 }, + { 0x210000ca, 0x24000020 }, + { 0x210000cb, 0x24000020 }, + { 0x210000cc, 0x24000020 }, + { 0x210000cd, 0x24000020 }, + { 0x210000ce, 0x24000020 }, + { 0x210000cf, 0x24000020 }, + { 0x210000d0, 0x24000020 }, + { 0x210000d1, 0x24000020 }, + { 0x210000d2, 0x24000020 }, + { 0x210000d3, 0x24000020 }, + { 0x210000d4, 0x24000020 }, + { 0x210000d5, 0x24000020 }, + { 0x210000d6, 0x24000020 }, + { 0x090000d7, 0x64000000 }, + { 0x210000d8, 0x24000020 }, + { 0x210000d9, 0x24000020 }, + { 0x210000da, 0x24000020 }, + { 0x210000db, 0x24000020 }, + { 0x210000dc, 0x24000020 }, + { 0x210000dd, 0x24000020 }, + { 0x210000de, 0x24000020 }, + { 0x210000df, 0x14000000 }, + { 0x210000e0, 0x1400ffe0 }, + { 0x210000e1, 0x1400ffe0 }, + { 0x210000e2, 0x1400ffe0 }, + { 0x210000e3, 0x1400ffe0 }, + { 0x210000e4, 0x1400ffe0 }, + { 0x210000e5, 0x1400ffe0 }, + { 0x210000e6, 0x1400ffe0 }, + { 0x210000e7, 0x1400ffe0 }, + { 0x210000e8, 0x1400ffe0 }, + { 0x210000e9, 0x1400ffe0 }, + { 0x210000ea, 0x1400ffe0 }, + { 0x210000eb, 0x1400ffe0 }, + { 0x210000ec, 0x1400ffe0 }, + { 0x210000ed, 0x1400ffe0 }, + { 0x210000ee, 0x1400ffe0 }, + { 0x210000ef, 0x1400ffe0 }, + { 0x210000f0, 0x1400ffe0 }, + { 0x210000f1, 0x1400ffe0 }, + { 0x210000f2, 0x1400ffe0 }, + { 0x210000f3, 0x1400ffe0 }, + { 0x210000f4, 0x1400ffe0 }, + { 0x210000f5, 0x1400ffe0 }, + { 0x210000f6, 0x1400ffe0 }, + { 0x090000f7, 0x64000000 }, + { 0x210000f8, 0x1400ffe0 }, + { 0x210000f9, 0x1400ffe0 }, + { 0x210000fa, 0x1400ffe0 }, + { 0x210000fb, 0x1400ffe0 }, + { 0x210000fc, 0x1400ffe0 }, + { 0x210000fd, 0x1400ffe0 }, + { 0x210000fe, 0x1400ffe0 }, + { 0x210000ff, 0x14000079 }, + { 0x21000100, 0x24000001 }, + { 0x21000101, 0x1400ffff }, + { 0x21000102, 0x24000001 }, + { 0x21000103, 0x1400ffff }, + { 0x21000104, 0x24000001 }, + { 0x21000105, 0x1400ffff }, + { 0x21000106, 0x24000001 }, + { 0x21000107, 0x1400ffff }, + { 0x21000108, 0x24000001 }, + { 0x21000109, 0x1400ffff }, + { 0x2100010a, 0x24000001 }, + { 0x2100010b, 0x1400ffff }, + { 0x2100010c, 0x24000001 }, + { 0x2100010d, 0x1400ffff }, + { 0x2100010e, 0x24000001 }, + { 0x2100010f, 0x1400ffff }, + { 0x21000110, 0x24000001 }, + { 0x21000111, 0x1400ffff }, + { 0x21000112, 0x24000001 }, + { 0x21000113, 0x1400ffff }, + { 0x21000114, 0x24000001 }, + { 0x21000115, 0x1400ffff }, + { 0x21000116, 0x24000001 }, + { 0x21000117, 0x1400ffff }, + { 0x21000118, 0x24000001 }, + { 0x21000119, 0x1400ffff }, + { 0x2100011a, 0x24000001 }, + { 0x2100011b, 0x1400ffff }, + { 0x2100011c, 0x24000001 }, + { 0x2100011d, 0x1400ffff }, + { 0x2100011e, 0x24000001 }, + { 0x2100011f, 0x1400ffff }, + { 0x21000120, 0x24000001 }, + { 0x21000121, 0x1400ffff }, + { 0x21000122, 0x24000001 }, + { 0x21000123, 0x1400ffff }, + { 0x21000124, 0x24000001 }, + { 0x21000125, 0x1400ffff }, + { 0x21000126, 0x24000001 }, + { 0x21000127, 0x1400ffff }, + { 0x21000128, 0x24000001 }, + { 0x21000129, 0x1400ffff }, + { 0x2100012a, 0x24000001 }, + { 0x2100012b, 0x1400ffff }, + { 0x2100012c, 0x24000001 }, + { 0x2100012d, 0x1400ffff }, + { 0x2100012e, 0x24000001 }, + { 0x2100012f, 0x1400ffff }, + { 0x21000130, 0x2400ff39 }, + { 0x21000131, 0x1400ff18 }, + { 0x21000132, 0x24000001 }, + { 0x21000133, 0x1400ffff }, + { 0x21000134, 0x24000001 }, + { 0x21000135, 0x1400ffff }, + { 0x21000136, 0x24000001 }, + { 0x21000137, 0x1400ffff }, + { 0x21000138, 0x14000000 }, + { 0x21000139, 0x24000001 }, + { 0x2100013a, 0x1400ffff }, + { 0x2100013b, 0x24000001 }, + { 0x2100013c, 0x1400ffff }, + { 0x2100013d, 0x24000001 }, + { 0x2100013e, 0x1400ffff }, + { 0x2100013f, 0x24000001 }, + { 0x21000140, 0x1400ffff }, + { 0x21000141, 0x24000001 }, + { 0x21000142, 0x1400ffff }, + { 0x21000143, 0x24000001 }, + { 0x21000144, 0x1400ffff }, + { 0x21000145, 0x24000001 }, + { 0x21000146, 0x1400ffff }, + { 0x21000147, 0x24000001 }, + { 0x21000148, 0x1400ffff }, + { 0x21000149, 0x14000000 }, + { 0x2100014a, 0x24000001 }, + { 0x2100014b, 0x1400ffff }, + { 0x2100014c, 0x24000001 }, + { 0x2100014d, 0x1400ffff }, + { 0x2100014e, 0x24000001 }, + { 0x2100014f, 0x1400ffff }, + { 0x21000150, 0x24000001 }, + { 0x21000151, 0x1400ffff }, + { 0x21000152, 0x24000001 }, + { 0x21000153, 0x1400ffff }, + { 0x21000154, 0x24000001 }, + { 0x21000155, 0x1400ffff }, + { 0x21000156, 0x24000001 }, + { 0x21000157, 0x1400ffff }, + { 0x21000158, 0x24000001 }, + { 0x21000159, 0x1400ffff }, + { 0x2100015a, 0x24000001 }, + { 0x2100015b, 0x1400ffff }, + { 0x2100015c, 0x24000001 }, + { 0x2100015d, 0x1400ffff }, + { 0x2100015e, 0x24000001 }, + { 0x2100015f, 0x1400ffff }, + { 0x21000160, 0x24000001 }, + { 0x21000161, 0x1400ffff }, + { 0x21000162, 0x24000001 }, + { 0x21000163, 0x1400ffff }, + { 0x21000164, 0x24000001 }, + { 0x21000165, 0x1400ffff }, + { 0x21000166, 0x24000001 }, + { 0x21000167, 0x1400ffff }, + { 0x21000168, 0x24000001 }, + { 0x21000169, 0x1400ffff }, + { 0x2100016a, 0x24000001 }, + { 0x2100016b, 0x1400ffff }, + { 0x2100016c, 0x24000001 }, + { 0x2100016d, 0x1400ffff }, + { 0x2100016e, 0x24000001 }, + { 0x2100016f, 0x1400ffff }, + { 0x21000170, 0x24000001 }, + { 0x21000171, 0x1400ffff }, + { 0x21000172, 0x24000001 }, + { 0x21000173, 0x1400ffff }, + { 0x21000174, 0x24000001 }, + { 0x21000175, 0x1400ffff }, + { 0x21000176, 0x24000001 }, + { 0x21000177, 0x1400ffff }, + { 0x21000178, 0x2400ff87 }, + { 0x21000179, 0x24000001 }, + { 0x2100017a, 0x1400ffff }, + { 0x2100017b, 0x24000001 }, + { 0x2100017c, 0x1400ffff }, + { 0x2100017d, 0x24000001 }, + { 0x2100017e, 0x1400ffff }, + { 0x2100017f, 0x1400fed4 }, + { 0x21000180, 0x14000000 }, + { 0x21000181, 0x240000d2 }, + { 0x21000182, 0x24000001 }, + { 0x21000183, 0x1400ffff }, + { 0x21000184, 0x24000001 }, + { 0x21000185, 0x1400ffff }, + { 0x21000186, 0x240000ce }, + { 0x21000187, 0x24000001 }, + { 0x21000188, 0x1400ffff }, + { 0x21000189, 0x240000cd }, + { 0x2100018a, 0x240000cd }, + { 0x2100018b, 0x24000001 }, + { 0x2100018c, 0x1400ffff }, + { 0x2100018d, 0x14000000 }, + { 0x2100018e, 0x2400004f }, + { 0x2100018f, 0x240000ca }, + { 0x21000190, 0x240000cb }, + { 0x21000191, 0x24000001 }, + { 0x21000192, 0x1400ffff }, + { 0x21000193, 0x240000cd }, + { 0x21000194, 0x240000cf }, + { 0x21000195, 0x14000061 }, + { 0x21000196, 0x240000d3 }, + { 0x21000197, 0x240000d1 }, + { 0x21000198, 0x24000001 }, + { 0x21000199, 0x1400ffff }, + { 0x2100019a, 0x140000a3 }, + { 0x2100019b, 0x14000000 }, + { 0x2100019c, 0x240000d3 }, + { 0x2100019d, 0x240000d5 }, + { 0x2100019e, 0x14000082 }, + { 0x2100019f, 0x240000d6 }, + { 0x210001a0, 0x24000001 }, + { 0x210001a1, 0x1400ffff }, + { 0x210001a2, 0x24000001 }, + { 0x210001a3, 0x1400ffff }, + { 0x210001a4, 0x24000001 }, + { 0x210001a5, 0x1400ffff }, + { 0x210001a6, 0x240000da }, + { 0x210001a7, 0x24000001 }, + { 0x210001a8, 0x1400ffff }, + { 0x210001a9, 0x240000da }, + { 0x218001aa, 0x14000001 }, + { 0x210001ac, 0x24000001 }, + { 0x210001ad, 0x1400ffff }, + { 0x210001ae, 0x240000da }, + { 0x210001af, 0x24000001 }, + { 0x210001b0, 0x1400ffff }, + { 0x210001b1, 0x240000d9 }, + { 0x210001b2, 0x240000d9 }, + { 0x210001b3, 0x24000001 }, + { 0x210001b4, 0x1400ffff }, + { 0x210001b5, 0x24000001 }, + { 0x210001b6, 0x1400ffff }, + { 0x210001b7, 0x240000db }, + { 0x210001b8, 0x24000001 }, + { 0x210001b9, 0x1400ffff }, + { 0x210001ba, 0x14000000 }, + { 0x210001bb, 0x1c000000 }, + { 0x210001bc, 0x24000001 }, + { 0x210001bd, 0x1400ffff }, + { 0x210001be, 0x14000000 }, + { 0x210001bf, 0x14000038 }, + { 0x218001c0, 0x1c000003 }, + { 0x210001c4, 0x24000002 }, + { 0x210001c5, 0x2000ffff }, + { 0x210001c6, 0x1400fffe }, + { 0x210001c7, 0x24000002 }, + { 0x210001c8, 0x2000ffff }, + { 0x210001c9, 0x1400fffe }, + { 0x210001ca, 0x24000002 }, + { 0x210001cb, 0x2000ffff }, + { 0x210001cc, 0x1400fffe }, + { 0x210001cd, 0x24000001 }, + { 0x210001ce, 0x1400ffff }, + { 0x210001cf, 0x24000001 }, + { 0x210001d0, 0x1400ffff }, + { 0x210001d1, 0x24000001 }, + { 0x210001d2, 0x1400ffff }, + { 0x210001d3, 0x24000001 }, + { 0x210001d4, 0x1400ffff }, + { 0x210001d5, 0x24000001 }, + { 0x210001d6, 0x1400ffff }, + { 0x210001d7, 0x24000001 }, + { 0x210001d8, 0x1400ffff }, + { 0x210001d9, 0x24000001 }, + { 0x210001da, 0x1400ffff }, + { 0x210001db, 0x24000001 }, + { 0x210001dc, 0x1400ffff }, + { 0x210001dd, 0x1400ffb1 }, + { 0x210001de, 0x24000001 }, + { 0x210001df, 0x1400ffff }, + { 0x210001e0, 0x24000001 }, + { 0x210001e1, 0x1400ffff }, + { 0x210001e2, 0x24000001 }, + { 0x210001e3, 0x1400ffff }, + { 0x210001e4, 0x24000001 }, + { 0x210001e5, 0x1400ffff }, + { 0x210001e6, 0x24000001 }, + { 0x210001e7, 0x1400ffff }, + { 0x210001e8, 0x24000001 }, + { 0x210001e9, 0x1400ffff }, + { 0x210001ea, 0x24000001 }, + { 0x210001eb, 0x1400ffff }, + { 0x210001ec, 0x24000001 }, + { 0x210001ed, 0x1400ffff }, + { 0x210001ee, 0x24000001 }, + { 0x210001ef, 0x1400ffff }, + { 0x210001f0, 0x14000000 }, + { 0x210001f1, 0x24000002 }, + { 0x210001f2, 0x2000ffff }, + { 0x210001f3, 0x1400fffe }, + { 0x210001f4, 0x24000001 }, + { 0x210001f5, 0x1400ffff }, + { 0x210001f6, 0x2400ff9f }, + { 0x210001f7, 0x2400ffc8 }, + { 0x210001f8, 0x24000001 }, + { 0x210001f9, 0x1400ffff }, + { 0x210001fa, 0x24000001 }, + { 0x210001fb, 0x1400ffff }, + { 0x210001fc, 0x24000001 }, + { 0x210001fd, 0x1400ffff }, + { 0x210001fe, 0x24000001 }, + { 0x210001ff, 0x1400ffff }, + { 0x21000200, 0x24000001 }, + { 0x21000201, 0x1400ffff }, + { 0x21000202, 0x24000001 }, + { 0x21000203, 0x1400ffff }, + { 0x21000204, 0x24000001 }, + { 0x21000205, 0x1400ffff }, + { 0x21000206, 0x24000001 }, + { 0x21000207, 0x1400ffff }, + { 0x21000208, 0x24000001 }, + { 0x21000209, 0x1400ffff }, + { 0x2100020a, 0x24000001 }, + { 0x2100020b, 0x1400ffff }, + { 0x2100020c, 0x24000001 }, + { 0x2100020d, 0x1400ffff }, + { 0x2100020e, 0x24000001 }, + { 0x2100020f, 0x1400ffff }, + { 0x21000210, 0x24000001 }, + { 0x21000211, 0x1400ffff }, + { 0x21000212, 0x24000001 }, + { 0x21000213, 0x1400ffff }, + { 0x21000214, 0x24000001 }, + { 0x21000215, 0x1400ffff }, + { 0x21000216, 0x24000001 }, + { 0x21000217, 0x1400ffff }, + { 0x21000218, 0x24000001 }, + { 0x21000219, 0x1400ffff }, + { 0x2100021a, 0x24000001 }, + { 0x2100021b, 0x1400ffff }, + { 0x2100021c, 0x24000001 }, + { 0x2100021d, 0x1400ffff }, + { 0x2100021e, 0x24000001 }, + { 0x2100021f, 0x1400ffff }, + { 0x21000220, 0x2400ff7e }, + { 0x21000221, 0x14000000 }, + { 0x21000222, 0x24000001 }, + { 0x21000223, 0x1400ffff }, + { 0x21000224, 0x24000001 }, + { 0x21000225, 0x1400ffff }, + { 0x21000226, 0x24000001 }, + { 0x21000227, 0x1400ffff }, + { 0x21000228, 0x24000001 }, + { 0x21000229, 0x1400ffff }, + { 0x2100022a, 0x24000001 }, + { 0x2100022b, 0x1400ffff }, + { 0x2100022c, 0x24000001 }, + { 0x2100022d, 0x1400ffff }, + { 0x2100022e, 0x24000001 }, + { 0x2100022f, 0x1400ffff }, + { 0x21000230, 0x24000001 }, + { 0x21000231, 0x1400ffff }, + { 0x21000232, 0x24000001 }, + { 0x21000233, 0x1400ffff }, + { 0x21800234, 0x14000005 }, + { 0x2100023a, 0x24000000 }, + { 0x2100023b, 0x24000001 }, + { 0x2100023c, 0x1400ffff }, + { 0x2100023d, 0x2400ff5d }, + { 0x2100023e, 0x24000000 }, + { 0x2180023f, 0x14000001 }, + { 0x21000241, 0x24000053 }, + { 0x21800250, 0x14000002 }, + { 0x21000253, 0x1400ff2e }, + { 0x21000254, 0x1400ff32 }, + { 0x21000255, 0x14000000 }, + { 0x21000256, 0x1400ff33 }, + { 0x21000257, 0x1400ff33 }, + { 0x21000258, 0x14000000 }, + { 0x21000259, 0x1400ff36 }, + { 0x2100025a, 0x14000000 }, + { 0x2100025b, 0x1400ff35 }, + { 0x2180025c, 0x14000003 }, + { 0x21000260, 0x1400ff33 }, + { 0x21800261, 0x14000001 }, + { 0x21000263, 0x1400ff31 }, + { 0x21800264, 0x14000003 }, + { 0x21000268, 0x1400ff2f }, + { 0x21000269, 0x1400ff2d }, + { 0x2180026a, 0x14000004 }, + { 0x2100026f, 0x1400ff2d }, + { 0x21800270, 0x14000001 }, + { 0x21000272, 0x1400ff2b }, + { 0x21800273, 0x14000001 }, + { 0x21000275, 0x1400ff2a }, + { 0x21800276, 0x14000009 }, + { 0x21000280, 0x1400ff26 }, + { 0x21800281, 0x14000001 }, + { 0x21000283, 0x1400ff26 }, + { 0x21800284, 0x14000003 }, + { 0x21000288, 0x1400ff26 }, + { 0x21000289, 0x14000000 }, + { 0x2100028a, 0x1400ff27 }, + { 0x2100028b, 0x1400ff27 }, + { 0x2180028c, 0x14000005 }, + { 0x21000292, 0x1400ff25 }, + { 0x21000293, 0x14000000 }, + { 0x21000294, 0x1400ffad }, + { 0x21800295, 0x1400001a }, + { 0x218002b0, 0x18000011 }, + { 0x098002c2, 0x60000003 }, + { 0x098002c6, 0x1800000b }, + { 0x098002d2, 0x6000000d }, + { 0x218002e0, 0x18000004 }, + { 0x098002e5, 0x60000008 }, + { 0x090002ee, 0x18000000 }, + { 0x098002ef, 0x60000010 }, + { 0x1b800300, 0x30000044 }, + { 0x1b000345, 0x30000054 }, + { 0x1b800346, 0x30000029 }, + { 0x13800374, 0x60000001 }, + { 0x1300037a, 0x18000000 }, + { 0x0900037e, 0x54000000 }, + { 0x13800384, 0x60000001 }, + { 0x13000386, 0x24000026 }, + { 0x09000387, 0x54000000 }, + { 0x13000388, 0x24000025 }, + { 0x13000389, 0x24000025 }, + { 0x1300038a, 0x24000025 }, + { 0x1300038c, 0x24000040 }, + { 0x1300038e, 0x2400003f }, + { 0x1300038f, 0x2400003f }, + { 0x13000390, 0x14000000 }, + { 0x13000391, 0x24000020 }, + { 0x13000392, 0x24000020 }, + { 0x13000393, 0x24000020 }, + { 0x13000394, 0x24000020 }, + { 0x13000395, 0x24000020 }, + { 0x13000396, 0x24000020 }, + { 0x13000397, 0x24000020 }, + { 0x13000398, 0x24000020 }, + { 0x13000399, 0x24000020 }, + { 0x1300039a, 0x24000020 }, + { 0x1300039b, 0x24000020 }, + { 0x1300039c, 0x24000020 }, + { 0x1300039d, 0x24000020 }, + { 0x1300039e, 0x24000020 }, + { 0x1300039f, 0x24000020 }, + { 0x130003a0, 0x24000020 }, + { 0x130003a1, 0x24000020 }, + { 0x130003a3, 0x24000020 }, + { 0x130003a4, 0x24000020 }, + { 0x130003a5, 0x24000020 }, + { 0x130003a6, 0x24000020 }, + { 0x130003a7, 0x24000020 }, + { 0x130003a8, 0x24000020 }, + { 0x130003a9, 0x24000020 }, + { 0x130003aa, 0x24000020 }, + { 0x130003ab, 0x24000020 }, + { 0x130003ac, 0x1400ffda }, + { 0x130003ad, 0x1400ffdb }, + { 0x130003ae, 0x1400ffdb }, + { 0x130003af, 0x1400ffdb }, + { 0x130003b0, 0x14000000 }, + { 0x130003b1, 0x1400ffe0 }, + { 0x130003b2, 0x1400ffe0 }, + { 0x130003b3, 0x1400ffe0 }, + { 0x130003b4, 0x1400ffe0 }, + { 0x130003b5, 0x1400ffe0 }, + { 0x130003b6, 0x1400ffe0 }, + { 0x130003b7, 0x1400ffe0 }, + { 0x130003b8, 0x1400ffe0 }, + { 0x130003b9, 0x1400ffe0 }, + { 0x130003ba, 0x1400ffe0 }, + { 0x130003bb, 0x1400ffe0 }, + { 0x130003bc, 0x1400ffe0 }, + { 0x130003bd, 0x1400ffe0 }, + { 0x130003be, 0x1400ffe0 }, + { 0x130003bf, 0x1400ffe0 }, + { 0x130003c0, 0x1400ffe0 }, + { 0x130003c1, 0x1400ffe0 }, + { 0x130003c2, 0x1400ffe1 }, + { 0x130003c3, 0x1400ffe0 }, + { 0x130003c4, 0x1400ffe0 }, + { 0x130003c5, 0x1400ffe0 }, + { 0x130003c6, 0x1400ffe0 }, + { 0x130003c7, 0x1400ffe0 }, + { 0x130003c8, 0x1400ffe0 }, + { 0x130003c9, 0x1400ffe0 }, + { 0x130003ca, 0x1400ffe0 }, + { 0x130003cb, 0x1400ffe0 }, + { 0x130003cc, 0x1400ffc0 }, + { 0x130003cd, 0x1400ffc1 }, + { 0x130003ce, 0x1400ffc1 }, + { 0x130003d0, 0x1400ffc2 }, + { 0x130003d1, 0x1400ffc7 }, + { 0x138003d2, 0x24000002 }, + { 0x130003d5, 0x1400ffd1 }, + { 0x130003d6, 0x1400ffca }, + { 0x130003d7, 0x14000000 }, + { 0x130003d8, 0x24000001 }, + { 0x130003d9, 0x1400ffff }, + { 0x130003da, 0x24000001 }, + { 0x130003db, 0x1400ffff }, + { 0x130003dc, 0x24000001 }, + { 0x130003dd, 0x1400ffff }, + { 0x130003de, 0x24000001 }, + { 0x130003df, 0x1400ffff }, + { 0x130003e0, 0x24000001 }, + { 0x130003e1, 0x1400ffff }, + { 0x0a0003e2, 0x24000001 }, + { 0x0a0003e3, 0x1400ffff }, + { 0x0a0003e4, 0x24000001 }, + { 0x0a0003e5, 0x1400ffff }, + { 0x0a0003e6, 0x24000001 }, + { 0x0a0003e7, 0x1400ffff }, + { 0x0a0003e8, 0x24000001 }, + { 0x0a0003e9, 0x1400ffff }, + { 0x0a0003ea, 0x24000001 }, + { 0x0a0003eb, 0x1400ffff }, + { 0x0a0003ec, 0x24000001 }, + { 0x0a0003ed, 0x1400ffff }, + { 0x0a0003ee, 0x24000001 }, + { 0x0a0003ef, 0x1400ffff }, + { 0x130003f0, 0x1400ffaa }, + { 0x130003f1, 0x1400ffb0 }, + { 0x130003f2, 0x14000007 }, + { 0x130003f3, 0x14000000 }, + { 0x130003f4, 0x2400ffc4 }, + { 0x130003f5, 0x1400ffa0 }, + { 0x130003f6, 0x64000000 }, + { 0x130003f7, 0x24000001 }, + { 0x130003f8, 0x1400ffff }, + { 0x130003f9, 0x2400fff9 }, + { 0x130003fa, 0x24000001 }, + { 0x130003fb, 0x1400ffff }, + { 0x130003fc, 0x14000000 }, + { 0x138003fd, 0x24000002 }, + { 0x0c000400, 0x24000050 }, + { 0x0c000401, 0x24000050 }, + { 0x0c000402, 0x24000050 }, + { 0x0c000403, 0x24000050 }, + { 0x0c000404, 0x24000050 }, + { 0x0c000405, 0x24000050 }, + { 0x0c000406, 0x24000050 }, + { 0x0c000407, 0x24000050 }, + { 0x0c000408, 0x24000050 }, + { 0x0c000409, 0x24000050 }, + { 0x0c00040a, 0x24000050 }, + { 0x0c00040b, 0x24000050 }, + { 0x0c00040c, 0x24000050 }, + { 0x0c00040d, 0x24000050 }, + { 0x0c00040e, 0x24000050 }, + { 0x0c00040f, 0x24000050 }, + { 0x0c000410, 0x24000020 }, + { 0x0c000411, 0x24000020 }, + { 0x0c000412, 0x24000020 }, + { 0x0c000413, 0x24000020 }, + { 0x0c000414, 0x24000020 }, + { 0x0c000415, 0x24000020 }, + { 0x0c000416, 0x24000020 }, + { 0x0c000417, 0x24000020 }, + { 0x0c000418, 0x24000020 }, + { 0x0c000419, 0x24000020 }, + { 0x0c00041a, 0x24000020 }, + { 0x0c00041b, 0x24000020 }, + { 0x0c00041c, 0x24000020 }, + { 0x0c00041d, 0x24000020 }, + { 0x0c00041e, 0x24000020 }, + { 0x0c00041f, 0x24000020 }, + { 0x0c000420, 0x24000020 }, + { 0x0c000421, 0x24000020 }, + { 0x0c000422, 0x24000020 }, + { 0x0c000423, 0x24000020 }, + { 0x0c000424, 0x24000020 }, + { 0x0c000425, 0x24000020 }, + { 0x0c000426, 0x24000020 }, + { 0x0c000427, 0x24000020 }, + { 0x0c000428, 0x24000020 }, + { 0x0c000429, 0x24000020 }, + { 0x0c00042a, 0x24000020 }, + { 0x0c00042b, 0x24000020 }, + { 0x0c00042c, 0x24000020 }, + { 0x0c00042d, 0x24000020 }, + { 0x0c00042e, 0x24000020 }, + { 0x0c00042f, 0x24000020 }, + { 0x0c000430, 0x1400ffe0 }, + { 0x0c000431, 0x1400ffe0 }, + { 0x0c000432, 0x1400ffe0 }, + { 0x0c000433, 0x1400ffe0 }, + { 0x0c000434, 0x1400ffe0 }, + { 0x0c000435, 0x1400ffe0 }, + { 0x0c000436, 0x1400ffe0 }, + { 0x0c000437, 0x1400ffe0 }, + { 0x0c000438, 0x1400ffe0 }, + { 0x0c000439, 0x1400ffe0 }, + { 0x0c00043a, 0x1400ffe0 }, + { 0x0c00043b, 0x1400ffe0 }, + { 0x0c00043c, 0x1400ffe0 }, + { 0x0c00043d, 0x1400ffe0 }, + { 0x0c00043e, 0x1400ffe0 }, + { 0x0c00043f, 0x1400ffe0 }, + { 0x0c000440, 0x1400ffe0 }, + { 0x0c000441, 0x1400ffe0 }, + { 0x0c000442, 0x1400ffe0 }, + { 0x0c000443, 0x1400ffe0 }, + { 0x0c000444, 0x1400ffe0 }, + { 0x0c000445, 0x1400ffe0 }, + { 0x0c000446, 0x1400ffe0 }, + { 0x0c000447, 0x1400ffe0 }, + { 0x0c000448, 0x1400ffe0 }, + { 0x0c000449, 0x1400ffe0 }, + { 0x0c00044a, 0x1400ffe0 }, + { 0x0c00044b, 0x1400ffe0 }, + { 0x0c00044c, 0x1400ffe0 }, + { 0x0c00044d, 0x1400ffe0 }, + { 0x0c00044e, 0x1400ffe0 }, + { 0x0c00044f, 0x1400ffe0 }, + { 0x0c000450, 0x1400ffb0 }, + { 0x0c000451, 0x1400ffb0 }, + { 0x0c000452, 0x1400ffb0 }, + { 0x0c000453, 0x1400ffb0 }, + { 0x0c000454, 0x1400ffb0 }, + { 0x0c000455, 0x1400ffb0 }, + { 0x0c000456, 0x1400ffb0 }, + { 0x0c000457, 0x1400ffb0 }, + { 0x0c000458, 0x1400ffb0 }, + { 0x0c000459, 0x1400ffb0 }, + { 0x0c00045a, 0x1400ffb0 }, + { 0x0c00045b, 0x1400ffb0 }, + { 0x0c00045c, 0x1400ffb0 }, + { 0x0c00045d, 0x1400ffb0 }, + { 0x0c00045e, 0x1400ffb0 }, + { 0x0c00045f, 0x1400ffb0 }, + { 0x0c000460, 0x24000001 }, + { 0x0c000461, 0x1400ffff }, + { 0x0c000462, 0x24000001 }, + { 0x0c000463, 0x1400ffff }, + { 0x0c000464, 0x24000001 }, + { 0x0c000465, 0x1400ffff }, + { 0x0c000466, 0x24000001 }, + { 0x0c000467, 0x1400ffff }, + { 0x0c000468, 0x24000001 }, + { 0x0c000469, 0x1400ffff }, + { 0x0c00046a, 0x24000001 }, + { 0x0c00046b, 0x1400ffff }, + { 0x0c00046c, 0x24000001 }, + { 0x0c00046d, 0x1400ffff }, + { 0x0c00046e, 0x24000001 }, + { 0x0c00046f, 0x1400ffff }, + { 0x0c000470, 0x24000001 }, + { 0x0c000471, 0x1400ffff }, + { 0x0c000472, 0x24000001 }, + { 0x0c000473, 0x1400ffff }, + { 0x0c000474, 0x24000001 }, + { 0x0c000475, 0x1400ffff }, + { 0x0c000476, 0x24000001 }, + { 0x0c000477, 0x1400ffff }, + { 0x0c000478, 0x24000001 }, + { 0x0c000479, 0x1400ffff }, + { 0x0c00047a, 0x24000001 }, + { 0x0c00047b, 0x1400ffff }, + { 0x0c00047c, 0x24000001 }, + { 0x0c00047d, 0x1400ffff }, + { 0x0c00047e, 0x24000001 }, + { 0x0c00047f, 0x1400ffff }, + { 0x0c000480, 0x24000001 }, + { 0x0c000481, 0x1400ffff }, + { 0x0c000482, 0x68000000 }, + { 0x0c800483, 0x30000003 }, + { 0x0c800488, 0x2c000001 }, + { 0x0c00048a, 0x24000001 }, + { 0x0c00048b, 0x1400ffff }, + { 0x0c00048c, 0x24000001 }, + { 0x0c00048d, 0x1400ffff }, + { 0x0c00048e, 0x24000001 }, + { 0x0c00048f, 0x1400ffff }, + { 0x0c000490, 0x24000001 }, + { 0x0c000491, 0x1400ffff }, + { 0x0c000492, 0x24000001 }, + { 0x0c000493, 0x1400ffff }, + { 0x0c000494, 0x24000001 }, + { 0x0c000495, 0x1400ffff }, + { 0x0c000496, 0x24000001 }, + { 0x0c000497, 0x1400ffff }, + { 0x0c000498, 0x24000001 }, + { 0x0c000499, 0x1400ffff }, + { 0x0c00049a, 0x24000001 }, + { 0x0c00049b, 0x1400ffff }, + { 0x0c00049c, 0x24000001 }, + { 0x0c00049d, 0x1400ffff }, + { 0x0c00049e, 0x24000001 }, + { 0x0c00049f, 0x1400ffff }, + { 0x0c0004a0, 0x24000001 }, + { 0x0c0004a1, 0x1400ffff }, + { 0x0c0004a2, 0x24000001 }, + { 0x0c0004a3, 0x1400ffff }, + { 0x0c0004a4, 0x24000001 }, + { 0x0c0004a5, 0x1400ffff }, + { 0x0c0004a6, 0x24000001 }, + { 0x0c0004a7, 0x1400ffff }, + { 0x0c0004a8, 0x24000001 }, + { 0x0c0004a9, 0x1400ffff }, + { 0x0c0004aa, 0x24000001 }, + { 0x0c0004ab, 0x1400ffff }, + { 0x0c0004ac, 0x24000001 }, + { 0x0c0004ad, 0x1400ffff }, + { 0x0c0004ae, 0x24000001 }, + { 0x0c0004af, 0x1400ffff }, + { 0x0c0004b0, 0x24000001 }, + { 0x0c0004b1, 0x1400ffff }, + { 0x0c0004b2, 0x24000001 }, + { 0x0c0004b3, 0x1400ffff }, + { 0x0c0004b4, 0x24000001 }, + { 0x0c0004b5, 0x1400ffff }, + { 0x0c0004b6, 0x24000001 }, + { 0x0c0004b7, 0x1400ffff }, + { 0x0c0004b8, 0x24000001 }, + { 0x0c0004b9, 0x1400ffff }, + { 0x0c0004ba, 0x24000001 }, + { 0x0c0004bb, 0x1400ffff }, + { 0x0c0004bc, 0x24000001 }, + { 0x0c0004bd, 0x1400ffff }, + { 0x0c0004be, 0x24000001 }, + { 0x0c0004bf, 0x1400ffff }, + { 0x0c0004c0, 0x24000000 }, + { 0x0c0004c1, 0x24000001 }, + { 0x0c0004c2, 0x1400ffff }, + { 0x0c0004c3, 0x24000001 }, + { 0x0c0004c4, 0x1400ffff }, + { 0x0c0004c5, 0x24000001 }, + { 0x0c0004c6, 0x1400ffff }, + { 0x0c0004c7, 0x24000001 }, + { 0x0c0004c8, 0x1400ffff }, + { 0x0c0004c9, 0x24000001 }, + { 0x0c0004ca, 0x1400ffff }, + { 0x0c0004cb, 0x24000001 }, + { 0x0c0004cc, 0x1400ffff }, + { 0x0c0004cd, 0x24000001 }, + { 0x0c0004ce, 0x1400ffff }, + { 0x0c0004d0, 0x24000001 }, + { 0x0c0004d1, 0x1400ffff }, + { 0x0c0004d2, 0x24000001 }, + { 0x0c0004d3, 0x1400ffff }, + { 0x0c0004d4, 0x24000001 }, + { 0x0c0004d5, 0x1400ffff }, + { 0x0c0004d6, 0x24000001 }, + { 0x0c0004d7, 0x1400ffff }, + { 0x0c0004d8, 0x24000001 }, + { 0x0c0004d9, 0x1400ffff }, + { 0x0c0004da, 0x24000001 }, + { 0x0c0004db, 0x1400ffff }, + { 0x0c0004dc, 0x24000001 }, + { 0x0c0004dd, 0x1400ffff }, + { 0x0c0004de, 0x24000001 }, + { 0x0c0004df, 0x1400ffff }, + { 0x0c0004e0, 0x24000001 }, + { 0x0c0004e1, 0x1400ffff }, + { 0x0c0004e2, 0x24000001 }, + { 0x0c0004e3, 0x1400ffff }, + { 0x0c0004e4, 0x24000001 }, + { 0x0c0004e5, 0x1400ffff }, + { 0x0c0004e6, 0x24000001 }, + { 0x0c0004e7, 0x1400ffff }, + { 0x0c0004e8, 0x24000001 }, + { 0x0c0004e9, 0x1400ffff }, + { 0x0c0004ea, 0x24000001 }, + { 0x0c0004eb, 0x1400ffff }, + { 0x0c0004ec, 0x24000001 }, + { 0x0c0004ed, 0x1400ffff }, + { 0x0c0004ee, 0x24000001 }, + { 0x0c0004ef, 0x1400ffff }, + { 0x0c0004f0, 0x24000001 }, + { 0x0c0004f1, 0x1400ffff }, + { 0x0c0004f2, 0x24000001 }, + { 0x0c0004f3, 0x1400ffff }, + { 0x0c0004f4, 0x24000001 }, + { 0x0c0004f5, 0x1400ffff }, + { 0x0c0004f6, 0x24000001 }, + { 0x0c0004f7, 0x1400ffff }, + { 0x0c0004f8, 0x24000001 }, + { 0x0c0004f9, 0x1400ffff }, + { 0x0c000500, 0x24000001 }, + { 0x0c000501, 0x1400ffff }, + { 0x0c000502, 0x24000001 }, + { 0x0c000503, 0x1400ffff }, + { 0x0c000504, 0x24000001 }, + { 0x0c000505, 0x1400ffff }, + { 0x0c000506, 0x24000001 }, + { 0x0c000507, 0x1400ffff }, + { 0x0c000508, 0x24000001 }, + { 0x0c000509, 0x1400ffff }, + { 0x0c00050a, 0x24000001 }, + { 0x0c00050b, 0x1400ffff }, + { 0x0c00050c, 0x24000001 }, + { 0x0c00050d, 0x1400ffff }, + { 0x0c00050e, 0x24000001 }, + { 0x0c00050f, 0x1400ffff }, + { 0x01000531, 0x24000030 }, + { 0x01000532, 0x24000030 }, + { 0x01000533, 0x24000030 }, + { 0x01000534, 0x24000030 }, + { 0x01000535, 0x24000030 }, + { 0x01000536, 0x24000030 }, + { 0x01000537, 0x24000030 }, + { 0x01000538, 0x24000030 }, + { 0x01000539, 0x24000030 }, + { 0x0100053a, 0x24000030 }, + { 0x0100053b, 0x24000030 }, + { 0x0100053c, 0x24000030 }, + { 0x0100053d, 0x24000030 }, + { 0x0100053e, 0x24000030 }, + { 0x0100053f, 0x24000030 }, + { 0x01000540, 0x24000030 }, + { 0x01000541, 0x24000030 }, + { 0x01000542, 0x24000030 }, + { 0x01000543, 0x24000030 }, + { 0x01000544, 0x24000030 }, + { 0x01000545, 0x24000030 }, + { 0x01000546, 0x24000030 }, + { 0x01000547, 0x24000030 }, + { 0x01000548, 0x24000030 }, + { 0x01000549, 0x24000030 }, + { 0x0100054a, 0x24000030 }, + { 0x0100054b, 0x24000030 }, + { 0x0100054c, 0x24000030 }, + { 0x0100054d, 0x24000030 }, + { 0x0100054e, 0x24000030 }, + { 0x0100054f, 0x24000030 }, + { 0x01000550, 0x24000030 }, + { 0x01000551, 0x24000030 }, + { 0x01000552, 0x24000030 }, + { 0x01000553, 0x24000030 }, + { 0x01000554, 0x24000030 }, + { 0x01000555, 0x24000030 }, + { 0x01000556, 0x24000030 }, + { 0x01000559, 0x18000000 }, + { 0x0180055a, 0x54000005 }, + { 0x01000561, 0x1400ffd0 }, + { 0x01000562, 0x1400ffd0 }, + { 0x01000563, 0x1400ffd0 }, + { 0x01000564, 0x1400ffd0 }, + { 0x01000565, 0x1400ffd0 }, + { 0x01000566, 0x1400ffd0 }, + { 0x01000567, 0x1400ffd0 }, + { 0x01000568, 0x1400ffd0 }, + { 0x01000569, 0x1400ffd0 }, + { 0x0100056a, 0x1400ffd0 }, + { 0x0100056b, 0x1400ffd0 }, + { 0x0100056c, 0x1400ffd0 }, + { 0x0100056d, 0x1400ffd0 }, + { 0x0100056e, 0x1400ffd0 }, + { 0x0100056f, 0x1400ffd0 }, + { 0x01000570, 0x1400ffd0 }, + { 0x01000571, 0x1400ffd0 }, + { 0x01000572, 0x1400ffd0 }, + { 0x01000573, 0x1400ffd0 }, + { 0x01000574, 0x1400ffd0 }, + { 0x01000575, 0x1400ffd0 }, + { 0x01000576, 0x1400ffd0 }, + { 0x01000577, 0x1400ffd0 }, + { 0x01000578, 0x1400ffd0 }, + { 0x01000579, 0x1400ffd0 }, + { 0x0100057a, 0x1400ffd0 }, + { 0x0100057b, 0x1400ffd0 }, + { 0x0100057c, 0x1400ffd0 }, + { 0x0100057d, 0x1400ffd0 }, + { 0x0100057e, 0x1400ffd0 }, + { 0x0100057f, 0x1400ffd0 }, + { 0x01000580, 0x1400ffd0 }, + { 0x01000581, 0x1400ffd0 }, + { 0x01000582, 0x1400ffd0 }, + { 0x01000583, 0x1400ffd0 }, + { 0x01000584, 0x1400ffd0 }, + { 0x01000585, 0x1400ffd0 }, + { 0x01000586, 0x1400ffd0 }, + { 0x01000587, 0x14000000 }, + { 0x09000589, 0x54000000 }, + { 0x0100058a, 0x44000000 }, + { 0x19800591, 0x30000028 }, + { 0x198005bb, 0x30000002 }, + { 0x190005be, 0x54000000 }, + { 0x190005bf, 0x30000000 }, + { 0x190005c0, 0x54000000 }, + { 0x198005c1, 0x30000001 }, + { 0x190005c3, 0x54000000 }, + { 0x198005c4, 0x30000001 }, + { 0x190005c6, 0x54000000 }, + { 0x190005c7, 0x30000000 }, + { 0x198005d0, 0x1c00001a }, + { 0x198005f0, 0x1c000002 }, + { 0x198005f3, 0x54000001 }, + { 0x09800600, 0x04000003 }, + { 0x0000060b, 0x5c000000 }, + { 0x0980060c, 0x54000001 }, + { 0x0080060e, 0x68000001 }, + { 0x00800610, 0x30000005 }, + { 0x0900061b, 0x54000000 }, + { 0x0080061e, 0x54000001 }, + { 0x00800621, 0x1c000019 }, + { 0x09000640, 0x18000000 }, + { 0x00800641, 0x1c000009 }, + { 0x1b80064b, 0x30000013 }, + { 0x09800660, 0x34000009 }, + { 0x0080066a, 0x54000003 }, + { 0x0080066e, 0x1c000001 }, + { 0x1b000670, 0x30000000 }, + { 0x00800671, 0x1c000062 }, + { 0x000006d4, 0x54000000 }, + { 0x000006d5, 0x1c000000 }, + { 0x008006d6, 0x30000006 }, + { 0x090006dd, 0x04000000 }, + { 0x000006de, 0x2c000000 }, + { 0x008006df, 0x30000005 }, + { 0x008006e5, 0x18000001 }, + { 0x008006e7, 0x30000001 }, + { 0x000006e9, 0x68000000 }, + { 0x008006ea, 0x30000003 }, + { 0x008006ee, 0x1c000001 }, + { 0x008006f0, 0x34000009 }, + { 0x008006fa, 0x1c000002 }, + { 0x008006fd, 0x68000001 }, + { 0x000006ff, 0x1c000000 }, + { 0x31800700, 0x5400000d }, + { 0x3100070f, 0x04000000 }, + { 0x31000710, 0x1c000000 }, + { 0x31000711, 0x30000000 }, + { 0x31800712, 0x1c00001d }, + { 0x31800730, 0x3000001a }, + { 0x3180074d, 0x1c000020 }, + { 0x37800780, 0x1c000025 }, + { 0x378007a6, 0x3000000a }, + { 0x370007b1, 0x1c000000 }, + { 0x0e800901, 0x30000001 }, + { 0x0e000903, 0x28000000 }, + { 0x0e800904, 0x1c000035 }, + { 0x0e00093c, 0x30000000 }, + { 0x0e00093d, 0x1c000000 }, + { 0x0e80093e, 0x28000002 }, + { 0x0e800941, 0x30000007 }, + { 0x0e800949, 0x28000003 }, + { 0x0e00094d, 0x30000000 }, + { 0x0e000950, 0x1c000000 }, + { 0x0e800951, 0x30000003 }, + { 0x0e800958, 0x1c000009 }, + { 0x0e800962, 0x30000001 }, + { 0x09800964, 0x54000001 }, + { 0x0e800966, 0x34000009 }, + { 0x09000970, 0x54000000 }, + { 0x0e00097d, 0x1c000000 }, + { 0x02000981, 0x30000000 }, + { 0x02800982, 0x28000001 }, + { 0x02800985, 0x1c000007 }, + { 0x0280098f, 0x1c000001 }, + { 0x02800993, 0x1c000015 }, + { 0x028009aa, 0x1c000006 }, + { 0x020009b2, 0x1c000000 }, + { 0x028009b6, 0x1c000003 }, + { 0x020009bc, 0x30000000 }, + { 0x020009bd, 0x1c000000 }, + { 0x028009be, 0x28000002 }, + { 0x028009c1, 0x30000003 }, + { 0x028009c7, 0x28000001 }, + { 0x028009cb, 0x28000001 }, + { 0x020009cd, 0x30000000 }, + { 0x020009ce, 0x1c000000 }, + { 0x020009d7, 0x28000000 }, + { 0x028009dc, 0x1c000001 }, + { 0x028009df, 0x1c000002 }, + { 0x028009e2, 0x30000001 }, + { 0x028009e6, 0x34000009 }, + { 0x028009f0, 0x1c000001 }, + { 0x028009f2, 0x5c000001 }, + { 0x028009f4, 0x3c000005 }, + { 0x020009fa, 0x68000000 }, + { 0x15800a01, 0x30000001 }, + { 0x15000a03, 0x28000000 }, + { 0x15800a05, 0x1c000005 }, + { 0x15800a0f, 0x1c000001 }, + { 0x15800a13, 0x1c000015 }, + { 0x15800a2a, 0x1c000006 }, + { 0x15800a32, 0x1c000001 }, + { 0x15800a35, 0x1c000001 }, + { 0x15800a38, 0x1c000001 }, + { 0x15000a3c, 0x30000000 }, + { 0x15800a3e, 0x28000002 }, + { 0x15800a41, 0x30000001 }, + { 0x15800a47, 0x30000001 }, + { 0x15800a4b, 0x30000002 }, + { 0x15800a59, 0x1c000003 }, + { 0x15000a5e, 0x1c000000 }, + { 0x15800a66, 0x34000009 }, + { 0x15800a70, 0x30000001 }, + { 0x15800a72, 0x1c000002 }, + { 0x14800a81, 0x30000001 }, + { 0x14000a83, 0x28000000 }, + { 0x14800a85, 0x1c000008 }, + { 0x14800a8f, 0x1c000002 }, + { 0x14800a93, 0x1c000015 }, + { 0x14800aaa, 0x1c000006 }, + { 0x14800ab2, 0x1c000001 }, + { 0x14800ab5, 0x1c000004 }, + { 0x14000abc, 0x30000000 }, + { 0x14000abd, 0x1c000000 }, + { 0x14800abe, 0x28000002 }, + { 0x14800ac1, 0x30000004 }, + { 0x14800ac7, 0x30000001 }, + { 0x14000ac9, 0x28000000 }, + { 0x14800acb, 0x28000001 }, + { 0x14000acd, 0x30000000 }, + { 0x14000ad0, 0x1c000000 }, + { 0x14800ae0, 0x1c000001 }, + { 0x14800ae2, 0x30000001 }, + { 0x14800ae6, 0x34000009 }, + { 0x14000af1, 0x5c000000 }, + { 0x2b000b01, 0x30000000 }, + { 0x2b800b02, 0x28000001 }, + { 0x2b800b05, 0x1c000007 }, + { 0x2b800b0f, 0x1c000001 }, + { 0x2b800b13, 0x1c000015 }, + { 0x2b800b2a, 0x1c000006 }, + { 0x2b800b32, 0x1c000001 }, + { 0x2b800b35, 0x1c000004 }, + { 0x2b000b3c, 0x30000000 }, + { 0x2b000b3d, 0x1c000000 }, + { 0x2b000b3e, 0x28000000 }, + { 0x2b000b3f, 0x30000000 }, + { 0x2b000b40, 0x28000000 }, + { 0x2b800b41, 0x30000002 }, + { 0x2b800b47, 0x28000001 }, + { 0x2b800b4b, 0x28000001 }, + { 0x2b000b4d, 0x30000000 }, + { 0x2b000b56, 0x30000000 }, + { 0x2b000b57, 0x28000000 }, + { 0x2b800b5c, 0x1c000001 }, + { 0x2b800b5f, 0x1c000002 }, + { 0x2b800b66, 0x34000009 }, + { 0x2b000b70, 0x68000000 }, + { 0x2b000b71, 0x1c000000 }, + { 0x35000b82, 0x30000000 }, + { 0x35000b83, 0x1c000000 }, + { 0x35800b85, 0x1c000005 }, + { 0x35800b8e, 0x1c000002 }, + { 0x35800b92, 0x1c000003 }, + { 0x35800b99, 0x1c000001 }, + { 0x35000b9c, 0x1c000000 }, + { 0x35800b9e, 0x1c000001 }, + { 0x35800ba3, 0x1c000001 }, + { 0x35800ba8, 0x1c000002 }, + { 0x35800bae, 0x1c00000b }, + { 0x35800bbe, 0x28000001 }, + { 0x35000bc0, 0x30000000 }, + { 0x35800bc1, 0x28000001 }, + { 0x35800bc6, 0x28000002 }, + { 0x35800bca, 0x28000002 }, + { 0x35000bcd, 0x30000000 }, + { 0x35000bd7, 0x28000000 }, + { 0x35800be6, 0x34000009 }, + { 0x35800bf0, 0x3c000002 }, + { 0x35800bf3, 0x68000005 }, + { 0x35000bf9, 0x5c000000 }, + { 0x35000bfa, 0x68000000 }, + { 0x36800c01, 0x28000002 }, + { 0x36800c05, 0x1c000007 }, + { 0x36800c0e, 0x1c000002 }, + { 0x36800c12, 0x1c000016 }, + { 0x36800c2a, 0x1c000009 }, + { 0x36800c35, 0x1c000004 }, + { 0x36800c3e, 0x30000002 }, + { 0x36800c41, 0x28000003 }, + { 0x36800c46, 0x30000002 }, + { 0x36800c4a, 0x30000003 }, + { 0x36800c55, 0x30000001 }, + { 0x36800c60, 0x1c000001 }, + { 0x36800c66, 0x34000009 }, + { 0x1c800c82, 0x28000001 }, + { 0x1c800c85, 0x1c000007 }, + { 0x1c800c8e, 0x1c000002 }, + { 0x1c800c92, 0x1c000016 }, + { 0x1c800caa, 0x1c000009 }, + { 0x1c800cb5, 0x1c000004 }, + { 0x1c000cbc, 0x30000000 }, + { 0x1c000cbd, 0x1c000000 }, + { 0x1c000cbe, 0x28000000 }, + { 0x1c000cbf, 0x30000000 }, + { 0x1c800cc0, 0x28000004 }, + { 0x1c000cc6, 0x30000000 }, + { 0x1c800cc7, 0x28000001 }, + { 0x1c800cca, 0x28000001 }, + { 0x1c800ccc, 0x30000001 }, + { 0x1c800cd5, 0x28000001 }, + { 0x1c000cde, 0x1c000000 }, + { 0x1c800ce0, 0x1c000001 }, + { 0x1c800ce6, 0x34000009 }, + { 0x24800d02, 0x28000001 }, + { 0x24800d05, 0x1c000007 }, + { 0x24800d0e, 0x1c000002 }, + { 0x24800d12, 0x1c000016 }, + { 0x24800d2a, 0x1c00000f }, + { 0x24800d3e, 0x28000002 }, + { 0x24800d41, 0x30000002 }, + { 0x24800d46, 0x28000002 }, + { 0x24800d4a, 0x28000002 }, + { 0x24000d4d, 0x30000000 }, + { 0x24000d57, 0x28000000 }, + { 0x24800d60, 0x1c000001 }, + { 0x24800d66, 0x34000009 }, + { 0x2f800d82, 0x28000001 }, + { 0x2f800d85, 0x1c000011 }, + { 0x2f800d9a, 0x1c000017 }, + { 0x2f800db3, 0x1c000008 }, + { 0x2f000dbd, 0x1c000000 }, + { 0x2f800dc0, 0x1c000006 }, + { 0x2f000dca, 0x30000000 }, + { 0x2f800dcf, 0x28000002 }, + { 0x2f800dd2, 0x30000002 }, + { 0x2f000dd6, 0x30000000 }, + { 0x2f800dd8, 0x28000007 }, + { 0x2f800df2, 0x28000001 }, + { 0x2f000df4, 0x54000000 }, + { 0x38800e01, 0x1c00002f }, + { 0x38000e31, 0x30000000 }, + { 0x38800e32, 0x1c000001 }, + { 0x38800e34, 0x30000006 }, + { 0x09000e3f, 0x5c000000 }, + { 0x38800e40, 0x1c000005 }, + { 0x38000e46, 0x18000000 }, + { 0x38800e47, 0x30000007 }, + { 0x38000e4f, 0x54000000 }, + { 0x38800e50, 0x34000009 }, + { 0x38800e5a, 0x54000001 }, + { 0x20800e81, 0x1c000001 }, + { 0x20000e84, 0x1c000000 }, + { 0x20800e87, 0x1c000001 }, + { 0x20000e8a, 0x1c000000 }, + { 0x20000e8d, 0x1c000000 }, + { 0x20800e94, 0x1c000003 }, + { 0x20800e99, 0x1c000006 }, + { 0x20800ea1, 0x1c000002 }, + { 0x20000ea5, 0x1c000000 }, + { 0x20000ea7, 0x1c000000 }, + { 0x20800eaa, 0x1c000001 }, + { 0x20800ead, 0x1c000003 }, + { 0x20000eb1, 0x30000000 }, + { 0x20800eb2, 0x1c000001 }, + { 0x20800eb4, 0x30000005 }, + { 0x20800ebb, 0x30000001 }, + { 0x20000ebd, 0x1c000000 }, + { 0x20800ec0, 0x1c000004 }, + { 0x20000ec6, 0x18000000 }, + { 0x20800ec8, 0x30000005 }, + { 0x20800ed0, 0x34000009 }, + { 0x20800edc, 0x1c000001 }, + { 0x39000f00, 0x1c000000 }, + { 0x39800f01, 0x68000002 }, + { 0x39800f04, 0x5400000e }, + { 0x39800f13, 0x68000004 }, + { 0x39800f18, 0x30000001 }, + { 0x39800f1a, 0x68000005 }, + { 0x39800f20, 0x34000009 }, + { 0x39800f2a, 0x3c000009 }, + { 0x39000f34, 0x68000000 }, + { 0x39000f35, 0x30000000 }, + { 0x39000f36, 0x68000000 }, + { 0x39000f37, 0x30000000 }, + { 0x39000f38, 0x68000000 }, + { 0x39000f39, 0x30000000 }, + { 0x39000f3a, 0x58000000 }, + { 0x39000f3b, 0x48000000 }, + { 0x39000f3c, 0x58000000 }, + { 0x39000f3d, 0x48000000 }, + { 0x39800f3e, 0x28000001 }, + { 0x39800f40, 0x1c000007 }, + { 0x39800f49, 0x1c000021 }, + { 0x39800f71, 0x3000000d }, + { 0x39000f7f, 0x28000000 }, + { 0x39800f80, 0x30000004 }, + { 0x39000f85, 0x54000000 }, + { 0x39800f86, 0x30000001 }, + { 0x39800f88, 0x1c000003 }, + { 0x39800f90, 0x30000007 }, + { 0x39800f99, 0x30000023 }, + { 0x39800fbe, 0x68000007 }, + { 0x39000fc6, 0x30000000 }, + { 0x39800fc7, 0x68000005 }, + { 0x39000fcf, 0x68000000 }, + { 0x39800fd0, 0x54000001 }, + { 0x26801000, 0x1c000021 }, + { 0x26801023, 0x1c000004 }, + { 0x26801029, 0x1c000001 }, + { 0x2600102c, 0x28000000 }, + { 0x2680102d, 0x30000003 }, + { 0x26001031, 0x28000000 }, + { 0x26001032, 0x30000000 }, + { 0x26801036, 0x30000001 }, + { 0x26001038, 0x28000000 }, + { 0x26001039, 0x30000000 }, + { 0x26801040, 0x34000009 }, + { 0x2680104a, 0x54000005 }, + { 0x26801050, 0x1c000005 }, + { 0x26801056, 0x28000001 }, + { 0x26801058, 0x30000001 }, + { 0x100010a0, 0x24001c60 }, + { 0x100010a1, 0x24001c60 }, + { 0x100010a2, 0x24001c60 }, + { 0x100010a3, 0x24001c60 }, + { 0x100010a4, 0x24001c60 }, + { 0x100010a5, 0x24001c60 }, + { 0x100010a6, 0x24001c60 }, + { 0x100010a7, 0x24001c60 }, + { 0x100010a8, 0x24001c60 }, + { 0x100010a9, 0x24001c60 }, + { 0x100010aa, 0x24001c60 }, + { 0x100010ab, 0x24001c60 }, + { 0x100010ac, 0x24001c60 }, + { 0x100010ad, 0x24001c60 }, + { 0x100010ae, 0x24001c60 }, + { 0x100010af, 0x24001c60 }, + { 0x100010b0, 0x24001c60 }, + { 0x100010b1, 0x24001c60 }, + { 0x100010b2, 0x24001c60 }, + { 0x100010b3, 0x24001c60 }, + { 0x100010b4, 0x24001c60 }, + { 0x100010b5, 0x24001c60 }, + { 0x100010b6, 0x24001c60 }, + { 0x100010b7, 0x24001c60 }, + { 0x100010b8, 0x24001c60 }, + { 0x100010b9, 0x24001c60 }, + { 0x100010ba, 0x24001c60 }, + { 0x100010bb, 0x24001c60 }, + { 0x100010bc, 0x24001c60 }, + { 0x100010bd, 0x24001c60 }, + { 0x100010be, 0x24001c60 }, + { 0x100010bf, 0x24001c60 }, + { 0x100010c0, 0x24001c60 }, + { 0x100010c1, 0x24001c60 }, + { 0x100010c2, 0x24001c60 }, + { 0x100010c3, 0x24001c60 }, + { 0x100010c4, 0x24001c60 }, + { 0x100010c5, 0x24001c60 }, + { 0x108010d0, 0x1c00002a }, + { 0x090010fb, 0x54000000 }, + { 0x100010fc, 0x18000000 }, + { 0x17801100, 0x1c000059 }, + { 0x1780115f, 0x1c000043 }, + { 0x178011a8, 0x1c000051 }, + { 0x0f801200, 0x1c000048 }, + { 0x0f80124a, 0x1c000003 }, + { 0x0f801250, 0x1c000006 }, + { 0x0f001258, 0x1c000000 }, + { 0x0f80125a, 0x1c000003 }, + { 0x0f801260, 0x1c000028 }, + { 0x0f80128a, 0x1c000003 }, + { 0x0f801290, 0x1c000020 }, + { 0x0f8012b2, 0x1c000003 }, + { 0x0f8012b8, 0x1c000006 }, + { 0x0f0012c0, 0x1c000000 }, + { 0x0f8012c2, 0x1c000003 }, + { 0x0f8012c8, 0x1c00000e }, + { 0x0f8012d8, 0x1c000038 }, + { 0x0f801312, 0x1c000003 }, + { 0x0f801318, 0x1c000042 }, + { 0x0f00135f, 0x30000000 }, + { 0x0f001360, 0x68000000 }, + { 0x0f801361, 0x54000007 }, + { 0x0f801369, 0x3c000013 }, + { 0x0f801380, 0x1c00000f }, + { 0x0f801390, 0x68000009 }, + { 0x088013a0, 0x1c000054 }, + { 0x07801401, 0x1c00026b }, + { 0x0780166d, 0x54000001 }, + { 0x0780166f, 0x1c000007 }, + { 0x28001680, 0x74000000 }, + { 0x28801681, 0x1c000019 }, + { 0x2800169b, 0x58000000 }, + { 0x2800169c, 0x48000000 }, + { 0x2d8016a0, 0x1c00004a }, + { 0x098016eb, 0x54000002 }, + { 0x2d8016ee, 0x38000002 }, + { 0x32801700, 0x1c00000c }, + { 0x3280170e, 0x1c000003 }, + { 0x32801712, 0x30000002 }, + { 0x18801720, 0x1c000011 }, + { 0x18801732, 0x30000002 }, + { 0x09801735, 0x54000001 }, + { 0x06801740, 0x1c000011 }, + { 0x06801752, 0x30000001 }, + { 0x33801760, 0x1c00000c }, + { 0x3380176e, 0x1c000002 }, + { 0x33801772, 0x30000001 }, + { 0x1f801780, 0x1c000033 }, + { 0x1f8017b4, 0x04000001 }, + { 0x1f0017b6, 0x28000000 }, + { 0x1f8017b7, 0x30000006 }, + { 0x1f8017be, 0x28000007 }, + { 0x1f0017c6, 0x30000000 }, + { 0x1f8017c7, 0x28000001 }, + { 0x1f8017c9, 0x3000000a }, + { 0x1f8017d4, 0x54000002 }, + { 0x1f0017d7, 0x18000000 }, + { 0x1f8017d8, 0x54000002 }, + { 0x1f0017db, 0x5c000000 }, + { 0x1f0017dc, 0x1c000000 }, + { 0x1f0017dd, 0x30000000 }, + { 0x1f8017e0, 0x34000009 }, + { 0x1f8017f0, 0x3c000009 }, + { 0x25801800, 0x54000005 }, + { 0x25001806, 0x44000000 }, + { 0x25801807, 0x54000003 }, + { 0x2580180b, 0x30000002 }, + { 0x2500180e, 0x74000000 }, + { 0x25801810, 0x34000009 }, + { 0x25801820, 0x1c000022 }, + { 0x25001843, 0x18000000 }, + { 0x25801844, 0x1c000033 }, + { 0x25801880, 0x1c000028 }, + { 0x250018a9, 0x30000000 }, + { 0x22801900, 0x1c00001c }, + { 0x22801920, 0x30000002 }, + { 0x22801923, 0x28000003 }, + { 0x22801927, 0x30000001 }, + { 0x22801929, 0x28000002 }, + { 0x22801930, 0x28000001 }, + { 0x22001932, 0x30000000 }, + { 0x22801933, 0x28000005 }, + { 0x22801939, 0x30000002 }, + { 0x22001940, 0x68000000 }, + { 0x22801944, 0x54000001 }, + { 0x22801946, 0x34000009 }, + { 0x34801950, 0x1c00001d }, + { 0x34801970, 0x1c000004 }, + { 0x27801980, 0x1c000029 }, + { 0x278019b0, 0x28000010 }, + { 0x278019c1, 0x1c000006 }, + { 0x278019c8, 0x28000001 }, + { 0x278019d0, 0x34000009 }, + { 0x278019de, 0x54000001 }, + { 0x1f8019e0, 0x6800001f }, + { 0x05801a00, 0x1c000016 }, + { 0x05801a17, 0x30000001 }, + { 0x05801a19, 0x28000002 }, + { 0x05801a1e, 0x54000001 }, + { 0x21801d00, 0x1400002b }, + { 0x21801d2c, 0x18000035 }, + { 0x21801d62, 0x14000015 }, + { 0x0c001d78, 0x18000000 }, + { 0x21801d79, 0x14000021 }, + { 0x21801d9b, 0x18000024 }, + { 0x1b801dc0, 0x30000003 }, + { 0x21001e00, 0x24000001 }, + { 0x21001e01, 0x1400ffff }, + { 0x21001e02, 0x24000001 }, + { 0x21001e03, 0x1400ffff }, + { 0x21001e04, 0x24000001 }, + { 0x21001e05, 0x1400ffff }, + { 0x21001e06, 0x24000001 }, + { 0x21001e07, 0x1400ffff }, + { 0x21001e08, 0x24000001 }, + { 0x21001e09, 0x1400ffff }, + { 0x21001e0a, 0x24000001 }, + { 0x21001e0b, 0x1400ffff }, + { 0x21001e0c, 0x24000001 }, + { 0x21001e0d, 0x1400ffff }, + { 0x21001e0e, 0x24000001 }, + { 0x21001e0f, 0x1400ffff }, + { 0x21001e10, 0x24000001 }, + { 0x21001e11, 0x1400ffff }, + { 0x21001e12, 0x24000001 }, + { 0x21001e13, 0x1400ffff }, + { 0x21001e14, 0x24000001 }, + { 0x21001e15, 0x1400ffff }, + { 0x21001e16, 0x24000001 }, + { 0x21001e17, 0x1400ffff }, + { 0x21001e18, 0x24000001 }, + { 0x21001e19, 0x1400ffff }, + { 0x21001e1a, 0x24000001 }, + { 0x21001e1b, 0x1400ffff }, + { 0x21001e1c, 0x24000001 }, + { 0x21001e1d, 0x1400ffff }, + { 0x21001e1e, 0x24000001 }, + { 0x21001e1f, 0x1400ffff }, + { 0x21001e20, 0x24000001 }, + { 0x21001e21, 0x1400ffff }, + { 0x21001e22, 0x24000001 }, + { 0x21001e23, 0x1400ffff }, + { 0x21001e24, 0x24000001 }, + { 0x21001e25, 0x1400ffff }, + { 0x21001e26, 0x24000001 }, + { 0x21001e27, 0x1400ffff }, + { 0x21001e28, 0x24000001 }, + { 0x21001e29, 0x1400ffff }, + { 0x21001e2a, 0x24000001 }, + { 0x21001e2b, 0x1400ffff }, + { 0x21001e2c, 0x24000001 }, + { 0x21001e2d, 0x1400ffff }, + { 0x21001e2e, 0x24000001 }, + { 0x21001e2f, 0x1400ffff }, + { 0x21001e30, 0x24000001 }, + { 0x21001e31, 0x1400ffff }, + { 0x21001e32, 0x24000001 }, + { 0x21001e33, 0x1400ffff }, + { 0x21001e34, 0x24000001 }, + { 0x21001e35, 0x1400ffff }, + { 0x21001e36, 0x24000001 }, + { 0x21001e37, 0x1400ffff }, + { 0x21001e38, 0x24000001 }, + { 0x21001e39, 0x1400ffff }, + { 0x21001e3a, 0x24000001 }, + { 0x21001e3b, 0x1400ffff }, + { 0x21001e3c, 0x24000001 }, + { 0x21001e3d, 0x1400ffff }, + { 0x21001e3e, 0x24000001 }, + { 0x21001e3f, 0x1400ffff }, + { 0x21001e40, 0x24000001 }, + { 0x21001e41, 0x1400ffff }, + { 0x21001e42, 0x24000001 }, + { 0x21001e43, 0x1400ffff }, + { 0x21001e44, 0x24000001 }, + { 0x21001e45, 0x1400ffff }, + { 0x21001e46, 0x24000001 }, + { 0x21001e47, 0x1400ffff }, + { 0x21001e48, 0x24000001 }, + { 0x21001e49, 0x1400ffff }, + { 0x21001e4a, 0x24000001 }, + { 0x21001e4b, 0x1400ffff }, + { 0x21001e4c, 0x24000001 }, + { 0x21001e4d, 0x1400ffff }, + { 0x21001e4e, 0x24000001 }, + { 0x21001e4f, 0x1400ffff }, + { 0x21001e50, 0x24000001 }, + { 0x21001e51, 0x1400ffff }, + { 0x21001e52, 0x24000001 }, + { 0x21001e53, 0x1400ffff }, + { 0x21001e54, 0x24000001 }, + { 0x21001e55, 0x1400ffff }, + { 0x21001e56, 0x24000001 }, + { 0x21001e57, 0x1400ffff }, + { 0x21001e58, 0x24000001 }, + { 0x21001e59, 0x1400ffff }, + { 0x21001e5a, 0x24000001 }, + { 0x21001e5b, 0x1400ffff }, + { 0x21001e5c, 0x24000001 }, + { 0x21001e5d, 0x1400ffff }, + { 0x21001e5e, 0x24000001 }, + { 0x21001e5f, 0x1400ffff }, + { 0x21001e60, 0x24000001 }, + { 0x21001e61, 0x1400ffff }, + { 0x21001e62, 0x24000001 }, + { 0x21001e63, 0x1400ffff }, + { 0x21001e64, 0x24000001 }, + { 0x21001e65, 0x1400ffff }, + { 0x21001e66, 0x24000001 }, + { 0x21001e67, 0x1400ffff }, + { 0x21001e68, 0x24000001 }, + { 0x21001e69, 0x1400ffff }, + { 0x21001e6a, 0x24000001 }, + { 0x21001e6b, 0x1400ffff }, + { 0x21001e6c, 0x24000001 }, + { 0x21001e6d, 0x1400ffff }, + { 0x21001e6e, 0x24000001 }, + { 0x21001e6f, 0x1400ffff }, + { 0x21001e70, 0x24000001 }, + { 0x21001e71, 0x1400ffff }, + { 0x21001e72, 0x24000001 }, + { 0x21001e73, 0x1400ffff }, + { 0x21001e74, 0x24000001 }, + { 0x21001e75, 0x1400ffff }, + { 0x21001e76, 0x24000001 }, + { 0x21001e77, 0x1400ffff }, + { 0x21001e78, 0x24000001 }, + { 0x21001e79, 0x1400ffff }, + { 0x21001e7a, 0x24000001 }, + { 0x21001e7b, 0x1400ffff }, + { 0x21001e7c, 0x24000001 }, + { 0x21001e7d, 0x1400ffff }, + { 0x21001e7e, 0x24000001 }, + { 0x21001e7f, 0x1400ffff }, + { 0x21001e80, 0x24000001 }, + { 0x21001e81, 0x1400ffff }, + { 0x21001e82, 0x24000001 }, + { 0x21001e83, 0x1400ffff }, + { 0x21001e84, 0x24000001 }, + { 0x21001e85, 0x1400ffff }, + { 0x21001e86, 0x24000001 }, + { 0x21001e87, 0x1400ffff }, + { 0x21001e88, 0x24000001 }, + { 0x21001e89, 0x1400ffff }, + { 0x21001e8a, 0x24000001 }, + { 0x21001e8b, 0x1400ffff }, + { 0x21001e8c, 0x24000001 }, + { 0x21001e8d, 0x1400ffff }, + { 0x21001e8e, 0x24000001 }, + { 0x21001e8f, 0x1400ffff }, + { 0x21001e90, 0x24000001 }, + { 0x21001e91, 0x1400ffff }, + { 0x21001e92, 0x24000001 }, + { 0x21001e93, 0x1400ffff }, + { 0x21001e94, 0x24000001 }, + { 0x21001e95, 0x1400ffff }, + { 0x21801e96, 0x14000004 }, + { 0x21001e9b, 0x1400ffc5 }, + { 0x21001ea0, 0x24000001 }, + { 0x21001ea1, 0x1400ffff }, + { 0x21001ea2, 0x24000001 }, + { 0x21001ea3, 0x1400ffff }, + { 0x21001ea4, 0x24000001 }, + { 0x21001ea5, 0x1400ffff }, + { 0x21001ea6, 0x24000001 }, + { 0x21001ea7, 0x1400ffff }, + { 0x21001ea8, 0x24000001 }, + { 0x21001ea9, 0x1400ffff }, + { 0x21001eaa, 0x24000001 }, + { 0x21001eab, 0x1400ffff }, + { 0x21001eac, 0x24000001 }, + { 0x21001ead, 0x1400ffff }, + { 0x21001eae, 0x24000001 }, + { 0x21001eaf, 0x1400ffff }, + { 0x21001eb0, 0x24000001 }, + { 0x21001eb1, 0x1400ffff }, + { 0x21001eb2, 0x24000001 }, + { 0x21001eb3, 0x1400ffff }, + { 0x21001eb4, 0x24000001 }, + { 0x21001eb5, 0x1400ffff }, + { 0x21001eb6, 0x24000001 }, + { 0x21001eb7, 0x1400ffff }, + { 0x21001eb8, 0x24000001 }, + { 0x21001eb9, 0x1400ffff }, + { 0x21001eba, 0x24000001 }, + { 0x21001ebb, 0x1400ffff }, + { 0x21001ebc, 0x24000001 }, + { 0x21001ebd, 0x1400ffff }, + { 0x21001ebe, 0x24000001 }, + { 0x21001ebf, 0x1400ffff }, + { 0x21001ec0, 0x24000001 }, + { 0x21001ec1, 0x1400ffff }, + { 0x21001ec2, 0x24000001 }, + { 0x21001ec3, 0x1400ffff }, + { 0x21001ec4, 0x24000001 }, + { 0x21001ec5, 0x1400ffff }, + { 0x21001ec6, 0x24000001 }, + { 0x21001ec7, 0x1400ffff }, + { 0x21001ec8, 0x24000001 }, + { 0x21001ec9, 0x1400ffff }, + { 0x21001eca, 0x24000001 }, + { 0x21001ecb, 0x1400ffff }, + { 0x21001ecc, 0x24000001 }, + { 0x21001ecd, 0x1400ffff }, + { 0x21001ece, 0x24000001 }, + { 0x21001ecf, 0x1400ffff }, + { 0x21001ed0, 0x24000001 }, + { 0x21001ed1, 0x1400ffff }, + { 0x21001ed2, 0x24000001 }, + { 0x21001ed3, 0x1400ffff }, + { 0x21001ed4, 0x24000001 }, + { 0x21001ed5, 0x1400ffff }, + { 0x21001ed6, 0x24000001 }, + { 0x21001ed7, 0x1400ffff }, + { 0x21001ed8, 0x24000001 }, + { 0x21001ed9, 0x1400ffff }, + { 0x21001eda, 0x24000001 }, + { 0x21001edb, 0x1400ffff }, + { 0x21001edc, 0x24000001 }, + { 0x21001edd, 0x1400ffff }, + { 0x21001ede, 0x24000001 }, + { 0x21001edf, 0x1400ffff }, + { 0x21001ee0, 0x24000001 }, + { 0x21001ee1, 0x1400ffff }, + { 0x21001ee2, 0x24000001 }, + { 0x21001ee3, 0x1400ffff }, + { 0x21001ee4, 0x24000001 }, + { 0x21001ee5, 0x1400ffff }, + { 0x21001ee6, 0x24000001 }, + { 0x21001ee7, 0x1400ffff }, + { 0x21001ee8, 0x24000001 }, + { 0x21001ee9, 0x1400ffff }, + { 0x21001eea, 0x24000001 }, + { 0x21001eeb, 0x1400ffff }, + { 0x21001eec, 0x24000001 }, + { 0x21001eed, 0x1400ffff }, + { 0x21001eee, 0x24000001 }, + { 0x21001eef, 0x1400ffff }, + { 0x21001ef0, 0x24000001 }, + { 0x21001ef1, 0x1400ffff }, + { 0x21001ef2, 0x24000001 }, + { 0x21001ef3, 0x1400ffff }, + { 0x21001ef4, 0x24000001 }, + { 0x21001ef5, 0x1400ffff }, + { 0x21001ef6, 0x24000001 }, + { 0x21001ef7, 0x1400ffff }, + { 0x21001ef8, 0x24000001 }, + { 0x21001ef9, 0x1400ffff }, + { 0x13001f00, 0x14000008 }, + { 0x13001f01, 0x14000008 }, + { 0x13001f02, 0x14000008 }, + { 0x13001f03, 0x14000008 }, + { 0x13001f04, 0x14000008 }, + { 0x13001f05, 0x14000008 }, + { 0x13001f06, 0x14000008 }, + { 0x13001f07, 0x14000008 }, + { 0x13001f08, 0x2400fff8 }, + { 0x13001f09, 0x2400fff8 }, + { 0x13001f0a, 0x2400fff8 }, + { 0x13001f0b, 0x2400fff8 }, + { 0x13001f0c, 0x2400fff8 }, + { 0x13001f0d, 0x2400fff8 }, + { 0x13001f0e, 0x2400fff8 }, + { 0x13001f0f, 0x2400fff8 }, + { 0x13001f10, 0x14000008 }, + { 0x13001f11, 0x14000008 }, + { 0x13001f12, 0x14000008 }, + { 0x13001f13, 0x14000008 }, + { 0x13001f14, 0x14000008 }, + { 0x13001f15, 0x14000008 }, + { 0x13001f18, 0x2400fff8 }, + { 0x13001f19, 0x2400fff8 }, + { 0x13001f1a, 0x2400fff8 }, + { 0x13001f1b, 0x2400fff8 }, + { 0x13001f1c, 0x2400fff8 }, + { 0x13001f1d, 0x2400fff8 }, + { 0x13001f20, 0x14000008 }, + { 0x13001f21, 0x14000008 }, + { 0x13001f22, 0x14000008 }, + { 0x13001f23, 0x14000008 }, + { 0x13001f24, 0x14000008 }, + { 0x13001f25, 0x14000008 }, + { 0x13001f26, 0x14000008 }, + { 0x13001f27, 0x14000008 }, + { 0x13001f28, 0x2400fff8 }, + { 0x13001f29, 0x2400fff8 }, + { 0x13001f2a, 0x2400fff8 }, + { 0x13001f2b, 0x2400fff8 }, + { 0x13001f2c, 0x2400fff8 }, + { 0x13001f2d, 0x2400fff8 }, + { 0x13001f2e, 0x2400fff8 }, + { 0x13001f2f, 0x2400fff8 }, + { 0x13001f30, 0x14000008 }, + { 0x13001f31, 0x14000008 }, + { 0x13001f32, 0x14000008 }, + { 0x13001f33, 0x14000008 }, + { 0x13001f34, 0x14000008 }, + { 0x13001f35, 0x14000008 }, + { 0x13001f36, 0x14000008 }, + { 0x13001f37, 0x14000008 }, + { 0x13001f38, 0x2400fff8 }, + { 0x13001f39, 0x2400fff8 }, + { 0x13001f3a, 0x2400fff8 }, + { 0x13001f3b, 0x2400fff8 }, + { 0x13001f3c, 0x2400fff8 }, + { 0x13001f3d, 0x2400fff8 }, + { 0x13001f3e, 0x2400fff8 }, + { 0x13001f3f, 0x2400fff8 }, + { 0x13001f40, 0x14000008 }, + { 0x13001f41, 0x14000008 }, + { 0x13001f42, 0x14000008 }, + { 0x13001f43, 0x14000008 }, + { 0x13001f44, 0x14000008 }, + { 0x13001f45, 0x14000008 }, + { 0x13001f48, 0x2400fff8 }, + { 0x13001f49, 0x2400fff8 }, + { 0x13001f4a, 0x2400fff8 }, + { 0x13001f4b, 0x2400fff8 }, + { 0x13001f4c, 0x2400fff8 }, + { 0x13001f4d, 0x2400fff8 }, + { 0x13001f50, 0x14000000 }, + { 0x13001f51, 0x14000008 }, + { 0x13001f52, 0x14000000 }, + { 0x13001f53, 0x14000008 }, + { 0x13001f54, 0x14000000 }, + { 0x13001f55, 0x14000008 }, + { 0x13001f56, 0x14000000 }, + { 0x13001f57, 0x14000008 }, + { 0x13001f59, 0x2400fff8 }, + { 0x13001f5b, 0x2400fff8 }, + { 0x13001f5d, 0x2400fff8 }, + { 0x13001f5f, 0x2400fff8 }, + { 0x13001f60, 0x14000008 }, + { 0x13001f61, 0x14000008 }, + { 0x13001f62, 0x14000008 }, + { 0x13001f63, 0x14000008 }, + { 0x13001f64, 0x14000008 }, + { 0x13001f65, 0x14000008 }, + { 0x13001f66, 0x14000008 }, + { 0x13001f67, 0x14000008 }, + { 0x13001f68, 0x2400fff8 }, + { 0x13001f69, 0x2400fff8 }, + { 0x13001f6a, 0x2400fff8 }, + { 0x13001f6b, 0x2400fff8 }, + { 0x13001f6c, 0x2400fff8 }, + { 0x13001f6d, 0x2400fff8 }, + { 0x13001f6e, 0x2400fff8 }, + { 0x13001f6f, 0x2400fff8 }, + { 0x13001f70, 0x1400004a }, + { 0x13001f71, 0x1400004a }, + { 0x13001f72, 0x14000056 }, + { 0x13001f73, 0x14000056 }, + { 0x13001f74, 0x14000056 }, + { 0x13001f75, 0x14000056 }, + { 0x13001f76, 0x14000064 }, + { 0x13001f77, 0x14000064 }, + { 0x13001f78, 0x14000080 }, + { 0x13001f79, 0x14000080 }, + { 0x13001f7a, 0x14000070 }, + { 0x13001f7b, 0x14000070 }, + { 0x13001f7c, 0x1400007e }, + { 0x13001f7d, 0x1400007e }, + { 0x13001f80, 0x14000008 }, + { 0x13001f81, 0x14000008 }, + { 0x13001f82, 0x14000008 }, + { 0x13001f83, 0x14000008 }, + { 0x13001f84, 0x14000008 }, + { 0x13001f85, 0x14000008 }, + { 0x13001f86, 0x14000008 }, + { 0x13001f87, 0x14000008 }, + { 0x13001f88, 0x2000fff8 }, + { 0x13001f89, 0x2000fff8 }, + { 0x13001f8a, 0x2000fff8 }, + { 0x13001f8b, 0x2000fff8 }, + { 0x13001f8c, 0x2000fff8 }, + { 0x13001f8d, 0x2000fff8 }, + { 0x13001f8e, 0x2000fff8 }, + { 0x13001f8f, 0x2000fff8 }, + { 0x13001f90, 0x14000008 }, + { 0x13001f91, 0x14000008 }, + { 0x13001f92, 0x14000008 }, + { 0x13001f93, 0x14000008 }, + { 0x13001f94, 0x14000008 }, + { 0x13001f95, 0x14000008 }, + { 0x13001f96, 0x14000008 }, + { 0x13001f97, 0x14000008 }, + { 0x13001f98, 0x2000fff8 }, + { 0x13001f99, 0x2000fff8 }, + { 0x13001f9a, 0x2000fff8 }, + { 0x13001f9b, 0x2000fff8 }, + { 0x13001f9c, 0x2000fff8 }, + { 0x13001f9d, 0x2000fff8 }, + { 0x13001f9e, 0x2000fff8 }, + { 0x13001f9f, 0x2000fff8 }, + { 0x13001fa0, 0x14000008 }, + { 0x13001fa1, 0x14000008 }, + { 0x13001fa2, 0x14000008 }, + { 0x13001fa3, 0x14000008 }, + { 0x13001fa4, 0x14000008 }, + { 0x13001fa5, 0x14000008 }, + { 0x13001fa6, 0x14000008 }, + { 0x13001fa7, 0x14000008 }, + { 0x13001fa8, 0x2000fff8 }, + { 0x13001fa9, 0x2000fff8 }, + { 0x13001faa, 0x2000fff8 }, + { 0x13001fab, 0x2000fff8 }, + { 0x13001fac, 0x2000fff8 }, + { 0x13001fad, 0x2000fff8 }, + { 0x13001fae, 0x2000fff8 }, + { 0x13001faf, 0x2000fff8 }, + { 0x13001fb0, 0x14000008 }, + { 0x13001fb1, 0x14000008 }, + { 0x13001fb2, 0x14000000 }, + { 0x13001fb3, 0x14000009 }, + { 0x13001fb4, 0x14000000 }, + { 0x13801fb6, 0x14000001 }, + { 0x13001fb8, 0x2400fff8 }, + { 0x13001fb9, 0x2400fff8 }, + { 0x13001fba, 0x2400ffb6 }, + { 0x13001fbb, 0x2400ffb6 }, + { 0x13001fbc, 0x2000fff7 }, + { 0x13001fbd, 0x60000000 }, + { 0x13001fbe, 0x1400e3db }, + { 0x13801fbf, 0x60000002 }, + { 0x13001fc2, 0x14000000 }, + { 0x13001fc3, 0x14000009 }, + { 0x13001fc4, 0x14000000 }, + { 0x13801fc6, 0x14000001 }, + { 0x13001fc8, 0x2400ffaa }, + { 0x13001fc9, 0x2400ffaa }, + { 0x13001fca, 0x2400ffaa }, + { 0x13001fcb, 0x2400ffaa }, + { 0x13001fcc, 0x2000fff7 }, + { 0x13801fcd, 0x60000002 }, + { 0x13001fd0, 0x14000008 }, + { 0x13001fd1, 0x14000008 }, + { 0x13801fd2, 0x14000001 }, + { 0x13801fd6, 0x14000001 }, + { 0x13001fd8, 0x2400fff8 }, + { 0x13001fd9, 0x2400fff8 }, + { 0x13001fda, 0x2400ff9c }, + { 0x13001fdb, 0x2400ff9c }, + { 0x13801fdd, 0x60000002 }, + { 0x13001fe0, 0x14000008 }, + { 0x13001fe1, 0x14000008 }, + { 0x13801fe2, 0x14000002 }, + { 0x13001fe5, 0x14000007 }, + { 0x13801fe6, 0x14000001 }, + { 0x13001fe8, 0x2400fff8 }, + { 0x13001fe9, 0x2400fff8 }, + { 0x13001fea, 0x2400ff90 }, + { 0x13001feb, 0x2400ff90 }, + { 0x13001fec, 0x2400fff9 }, + { 0x13801fed, 0x60000002 }, + { 0x13001ff2, 0x14000000 }, + { 0x13001ff3, 0x14000009 }, + { 0x13001ff4, 0x14000000 }, + { 0x13801ff6, 0x14000001 }, + { 0x13001ff8, 0x2400ff80 }, + { 0x13001ff9, 0x2400ff80 }, + { 0x13001ffa, 0x2400ff82 }, + { 0x13001ffb, 0x2400ff82 }, + { 0x13001ffc, 0x2000fff7 }, + { 0x13801ffd, 0x60000001 }, + { 0x09802000, 0x7400000a }, + { 0x0980200b, 0x04000004 }, + { 0x09802010, 0x44000005 }, + { 0x09802016, 0x54000001 }, + { 0x09002018, 0x50000000 }, + { 0x09002019, 0x4c000000 }, + { 0x0900201a, 0x58000000 }, + { 0x0980201b, 0x50000001 }, + { 0x0900201d, 0x4c000000 }, + { 0x0900201e, 0x58000000 }, + { 0x0900201f, 0x50000000 }, + { 0x09802020, 0x54000007 }, + { 0x09002028, 0x6c000000 }, + { 0x09002029, 0x70000000 }, + { 0x0980202a, 0x04000004 }, + { 0x0900202f, 0x74000000 }, + { 0x09802030, 0x54000008 }, + { 0x09002039, 0x50000000 }, + { 0x0900203a, 0x4c000000 }, + { 0x0980203b, 0x54000003 }, + { 0x0980203f, 0x40000001 }, + { 0x09802041, 0x54000002 }, + { 0x09002044, 0x64000000 }, + { 0x09002045, 0x58000000 }, + { 0x09002046, 0x48000000 }, + { 0x09802047, 0x5400000a }, + { 0x09002052, 0x64000000 }, + { 0x09002053, 0x54000000 }, + { 0x09002054, 0x40000000 }, + { 0x09802055, 0x54000009 }, + { 0x0900205f, 0x74000000 }, + { 0x09802060, 0x04000003 }, + { 0x0980206a, 0x04000005 }, + { 0x09002070, 0x3c000000 }, + { 0x21002071, 0x14000000 }, + { 0x09802074, 0x3c000005 }, + { 0x0980207a, 0x64000002 }, + { 0x0900207d, 0x58000000 }, + { 0x0900207e, 0x48000000 }, + { 0x2100207f, 0x14000000 }, + { 0x09802080, 0x3c000009 }, + { 0x0980208a, 0x64000002 }, + { 0x0900208d, 0x58000000 }, + { 0x0900208e, 0x48000000 }, + { 0x21802090, 0x18000004 }, + { 0x098020a0, 0x5c000015 }, + { 0x1b8020d0, 0x3000000c }, + { 0x1b8020dd, 0x2c000003 }, + { 0x1b0020e1, 0x30000000 }, + { 0x1b8020e2, 0x2c000002 }, + { 0x1b8020e5, 0x30000006 }, + { 0x09802100, 0x68000001 }, + { 0x09002102, 0x24000000 }, + { 0x09802103, 0x68000003 }, + { 0x09002107, 0x24000000 }, + { 0x09802108, 0x68000001 }, + { 0x0900210a, 0x14000000 }, + { 0x0980210b, 0x24000002 }, + { 0x0980210e, 0x14000001 }, + { 0x09802110, 0x24000002 }, + { 0x09002113, 0x14000000 }, + { 0x09002114, 0x68000000 }, + { 0x09002115, 0x24000000 }, + { 0x09802116, 0x68000002 }, + { 0x09802119, 0x24000004 }, + { 0x0980211e, 0x68000005 }, + { 0x09002124, 0x24000000 }, + { 0x09002125, 0x68000000 }, + { 0x13002126, 0x2400e2a3 }, + { 0x09002127, 0x68000000 }, + { 0x09002128, 0x24000000 }, + { 0x09002129, 0x68000000 }, + { 0x2100212a, 0x2400df41 }, + { 0x2100212b, 0x2400dfba }, + { 0x0980212c, 0x24000001 }, + { 0x0900212e, 0x68000000 }, + { 0x0900212f, 0x14000000 }, + { 0x09802130, 0x24000001 }, + { 0x09002132, 0x68000000 }, + { 0x09002133, 0x24000000 }, + { 0x09002134, 0x14000000 }, + { 0x09802135, 0x1c000003 }, + { 0x09002139, 0x14000000 }, + { 0x0980213a, 0x68000001 }, + { 0x0980213c, 0x14000001 }, + { 0x0980213e, 0x24000001 }, + { 0x09802140, 0x64000004 }, + { 0x09002145, 0x24000000 }, + { 0x09802146, 0x14000003 }, + { 0x0900214a, 0x68000000 }, + { 0x0900214b, 0x64000000 }, + { 0x0900214c, 0x68000000 }, + { 0x09802153, 0x3c00000c }, + { 0x09002160, 0x38000010 }, + { 0x09002161, 0x38000010 }, + { 0x09002162, 0x38000010 }, + { 0x09002163, 0x38000010 }, + { 0x09002164, 0x38000010 }, + { 0x09002165, 0x38000010 }, + { 0x09002166, 0x38000010 }, + { 0x09002167, 0x38000010 }, + { 0x09002168, 0x38000010 }, + { 0x09002169, 0x38000010 }, + { 0x0900216a, 0x38000010 }, + { 0x0900216b, 0x38000010 }, + { 0x0900216c, 0x38000010 }, + { 0x0900216d, 0x38000010 }, + { 0x0900216e, 0x38000010 }, + { 0x0900216f, 0x38000010 }, + { 0x09002170, 0x3800fff0 }, + { 0x09002171, 0x3800fff0 }, + { 0x09002172, 0x3800fff0 }, + { 0x09002173, 0x3800fff0 }, + { 0x09002174, 0x3800fff0 }, + { 0x09002175, 0x3800fff0 }, + { 0x09002176, 0x3800fff0 }, + { 0x09002177, 0x3800fff0 }, + { 0x09002178, 0x3800fff0 }, + { 0x09002179, 0x3800fff0 }, + { 0x0900217a, 0x3800fff0 }, + { 0x0900217b, 0x3800fff0 }, + { 0x0900217c, 0x3800fff0 }, + { 0x0900217d, 0x3800fff0 }, + { 0x0900217e, 0x3800fff0 }, + { 0x0900217f, 0x3800fff0 }, + { 0x09802180, 0x38000003 }, + { 0x09802190, 0x64000004 }, + { 0x09802195, 0x68000004 }, + { 0x0980219a, 0x64000001 }, + { 0x0980219c, 0x68000003 }, + { 0x090021a0, 0x64000000 }, + { 0x098021a1, 0x68000001 }, + { 0x090021a3, 0x64000000 }, + { 0x098021a4, 0x68000001 }, + { 0x090021a6, 0x64000000 }, + { 0x098021a7, 0x68000006 }, + { 0x090021ae, 0x64000000 }, + { 0x098021af, 0x6800001e }, + { 0x098021ce, 0x64000001 }, + { 0x098021d0, 0x68000001 }, + { 0x090021d2, 0x64000000 }, + { 0x090021d3, 0x68000000 }, + { 0x090021d4, 0x64000000 }, + { 0x098021d5, 0x6800001e }, + { 0x098021f4, 0x6400010b }, + { 0x09802300, 0x68000007 }, + { 0x09802308, 0x64000003 }, + { 0x0980230c, 0x68000013 }, + { 0x09802320, 0x64000001 }, + { 0x09802322, 0x68000006 }, + { 0x09002329, 0x58000000 }, + { 0x0900232a, 0x48000000 }, + { 0x0980232b, 0x68000050 }, + { 0x0900237c, 0x64000000 }, + { 0x0980237d, 0x6800001d }, + { 0x0980239b, 0x64000018 }, + { 0x090023b4, 0x58000000 }, + { 0x090023b5, 0x48000000 }, + { 0x090023b6, 0x54000000 }, + { 0x098023b7, 0x68000024 }, + { 0x09802400, 0x68000026 }, + { 0x09802440, 0x6800000a }, + { 0x09802460, 0x3c00003b }, + { 0x0980249c, 0x68000019 }, + { 0x090024b6, 0x6800001a }, + { 0x090024b7, 0x6800001a }, + { 0x090024b8, 0x6800001a }, + { 0x090024b9, 0x6800001a }, + { 0x090024ba, 0x6800001a }, + { 0x090024bb, 0x6800001a }, + { 0x090024bc, 0x6800001a }, + { 0x090024bd, 0x6800001a }, + { 0x090024be, 0x6800001a }, + { 0x090024bf, 0x6800001a }, + { 0x090024c0, 0x6800001a }, + { 0x090024c1, 0x6800001a }, + { 0x090024c2, 0x6800001a }, + { 0x090024c3, 0x6800001a }, + { 0x090024c4, 0x6800001a }, + { 0x090024c5, 0x6800001a }, + { 0x090024c6, 0x6800001a }, + { 0x090024c7, 0x6800001a }, + { 0x090024c8, 0x6800001a }, + { 0x090024c9, 0x6800001a }, + { 0x090024ca, 0x6800001a }, + { 0x090024cb, 0x6800001a }, + { 0x090024cc, 0x6800001a }, + { 0x090024cd, 0x6800001a }, + { 0x090024ce, 0x6800001a }, + { 0x090024cf, 0x6800001a }, + { 0x090024d0, 0x6800ffe6 }, + { 0x090024d1, 0x6800ffe6 }, + { 0x090024d2, 0x6800ffe6 }, + { 0x090024d3, 0x6800ffe6 }, + { 0x090024d4, 0x6800ffe6 }, + { 0x090024d5, 0x6800ffe6 }, + { 0x090024d6, 0x6800ffe6 }, + { 0x090024d7, 0x6800ffe6 }, + { 0x090024d8, 0x6800ffe6 }, + { 0x090024d9, 0x6800ffe6 }, + { 0x090024da, 0x6800ffe6 }, + { 0x090024db, 0x6800ffe6 }, + { 0x090024dc, 0x6800ffe6 }, + { 0x090024dd, 0x6800ffe6 }, + { 0x090024de, 0x6800ffe6 }, + { 0x090024df, 0x6800ffe6 }, + { 0x090024e0, 0x6800ffe6 }, + { 0x090024e1, 0x6800ffe6 }, + { 0x090024e2, 0x6800ffe6 }, + { 0x090024e3, 0x6800ffe6 }, + { 0x090024e4, 0x6800ffe6 }, + { 0x090024e5, 0x6800ffe6 }, + { 0x090024e6, 0x6800ffe6 }, + { 0x090024e7, 0x6800ffe6 }, + { 0x090024e8, 0x6800ffe6 }, + { 0x090024e9, 0x6800ffe6 }, + { 0x098024ea, 0x3c000015 }, + { 0x09802500, 0x680000b6 }, + { 0x090025b7, 0x64000000 }, + { 0x098025b8, 0x68000008 }, + { 0x090025c1, 0x64000000 }, + { 0x098025c2, 0x68000035 }, + { 0x098025f8, 0x64000007 }, + { 0x09802600, 0x6800006e }, + { 0x0900266f, 0x64000000 }, + { 0x09802670, 0x6800002c }, + { 0x098026a0, 0x68000011 }, + { 0x09802701, 0x68000003 }, + { 0x09802706, 0x68000003 }, + { 0x0980270c, 0x6800001b }, + { 0x09802729, 0x68000022 }, + { 0x0900274d, 0x68000000 }, + { 0x0980274f, 0x68000003 }, + { 0x09002756, 0x68000000 }, + { 0x09802758, 0x68000006 }, + { 0x09802761, 0x68000006 }, + { 0x09002768, 0x58000000 }, + { 0x09002769, 0x48000000 }, + { 0x0900276a, 0x58000000 }, + { 0x0900276b, 0x48000000 }, + { 0x0900276c, 0x58000000 }, + { 0x0900276d, 0x48000000 }, + { 0x0900276e, 0x58000000 }, + { 0x0900276f, 0x48000000 }, + { 0x09002770, 0x58000000 }, + { 0x09002771, 0x48000000 }, + { 0x09002772, 0x58000000 }, + { 0x09002773, 0x48000000 }, + { 0x09002774, 0x58000000 }, + { 0x09002775, 0x48000000 }, + { 0x09802776, 0x3c00001d }, + { 0x09002794, 0x68000000 }, + { 0x09802798, 0x68000017 }, + { 0x098027b1, 0x6800000d }, + { 0x098027c0, 0x64000004 }, + { 0x090027c5, 0x58000000 }, + { 0x090027c6, 0x48000000 }, + { 0x098027d0, 0x64000015 }, + { 0x090027e6, 0x58000000 }, + { 0x090027e7, 0x48000000 }, + { 0x090027e8, 0x58000000 }, + { 0x090027e9, 0x48000000 }, + { 0x090027ea, 0x58000000 }, + { 0x090027eb, 0x48000000 }, + { 0x098027f0, 0x6400000f }, + { 0x04802800, 0x680000ff }, + { 0x09802900, 0x64000082 }, + { 0x09002983, 0x58000000 }, + { 0x09002984, 0x48000000 }, + { 0x09002985, 0x58000000 }, + { 0x09002986, 0x48000000 }, + { 0x09002987, 0x58000000 }, + { 0x09002988, 0x48000000 }, + { 0x09002989, 0x58000000 }, + { 0x0900298a, 0x48000000 }, + { 0x0900298b, 0x58000000 }, + { 0x0900298c, 0x48000000 }, + { 0x0900298d, 0x58000000 }, + { 0x0900298e, 0x48000000 }, + { 0x0900298f, 0x58000000 }, + { 0x09002990, 0x48000000 }, + { 0x09002991, 0x58000000 }, + { 0x09002992, 0x48000000 }, + { 0x09002993, 0x58000000 }, + { 0x09002994, 0x48000000 }, + { 0x09002995, 0x58000000 }, + { 0x09002996, 0x48000000 }, + { 0x09002997, 0x58000000 }, + { 0x09002998, 0x48000000 }, + { 0x09802999, 0x6400003e }, + { 0x090029d8, 0x58000000 }, + { 0x090029d9, 0x48000000 }, + { 0x090029da, 0x58000000 }, + { 0x090029db, 0x48000000 }, + { 0x098029dc, 0x6400001f }, + { 0x090029fc, 0x58000000 }, + { 0x090029fd, 0x48000000 }, + { 0x098029fe, 0x64000101 }, + { 0x09802b00, 0x68000013 }, + { 0x11002c00, 0x24000030 }, + { 0x11002c01, 0x24000030 }, + { 0x11002c02, 0x24000030 }, + { 0x11002c03, 0x24000030 }, + { 0x11002c04, 0x24000030 }, + { 0x11002c05, 0x24000030 }, + { 0x11002c06, 0x24000030 }, + { 0x11002c07, 0x24000030 }, + { 0x11002c08, 0x24000030 }, + { 0x11002c09, 0x24000030 }, + { 0x11002c0a, 0x24000030 }, + { 0x11002c0b, 0x24000030 }, + { 0x11002c0c, 0x24000030 }, + { 0x11002c0d, 0x24000030 }, + { 0x11002c0e, 0x24000030 }, + { 0x11002c0f, 0x24000030 }, + { 0x11002c10, 0x24000030 }, + { 0x11002c11, 0x24000030 }, + { 0x11002c12, 0x24000030 }, + { 0x11002c13, 0x24000030 }, + { 0x11002c14, 0x24000030 }, + { 0x11002c15, 0x24000030 }, + { 0x11002c16, 0x24000030 }, + { 0x11002c17, 0x24000030 }, + { 0x11002c18, 0x24000030 }, + { 0x11002c19, 0x24000030 }, + { 0x11002c1a, 0x24000030 }, + { 0x11002c1b, 0x24000030 }, + { 0x11002c1c, 0x24000030 }, + { 0x11002c1d, 0x24000030 }, + { 0x11002c1e, 0x24000030 }, + { 0x11002c1f, 0x24000030 }, + { 0x11002c20, 0x24000030 }, + { 0x11002c21, 0x24000030 }, + { 0x11002c22, 0x24000030 }, + { 0x11002c23, 0x24000030 }, + { 0x11002c24, 0x24000030 }, + { 0x11002c25, 0x24000030 }, + { 0x11002c26, 0x24000030 }, + { 0x11002c27, 0x24000030 }, + { 0x11002c28, 0x24000030 }, + { 0x11002c29, 0x24000030 }, + { 0x11002c2a, 0x24000030 }, + { 0x11002c2b, 0x24000030 }, + { 0x11002c2c, 0x24000030 }, + { 0x11002c2d, 0x24000030 }, + { 0x11002c2e, 0x24000030 }, + { 0x11002c30, 0x1400ffd0 }, + { 0x11002c31, 0x1400ffd0 }, + { 0x11002c32, 0x1400ffd0 }, + { 0x11002c33, 0x1400ffd0 }, + { 0x11002c34, 0x1400ffd0 }, + { 0x11002c35, 0x1400ffd0 }, + { 0x11002c36, 0x1400ffd0 }, + { 0x11002c37, 0x1400ffd0 }, + { 0x11002c38, 0x1400ffd0 }, + { 0x11002c39, 0x1400ffd0 }, + { 0x11002c3a, 0x1400ffd0 }, + { 0x11002c3b, 0x1400ffd0 }, + { 0x11002c3c, 0x1400ffd0 }, + { 0x11002c3d, 0x1400ffd0 }, + { 0x11002c3e, 0x1400ffd0 }, + { 0x11002c3f, 0x1400ffd0 }, + { 0x11002c40, 0x1400ffd0 }, + { 0x11002c41, 0x1400ffd0 }, + { 0x11002c42, 0x1400ffd0 }, + { 0x11002c43, 0x1400ffd0 }, + { 0x11002c44, 0x1400ffd0 }, + { 0x11002c45, 0x1400ffd0 }, + { 0x11002c46, 0x1400ffd0 }, + { 0x11002c47, 0x1400ffd0 }, + { 0x11002c48, 0x1400ffd0 }, + { 0x11002c49, 0x1400ffd0 }, + { 0x11002c4a, 0x1400ffd0 }, + { 0x11002c4b, 0x1400ffd0 }, + { 0x11002c4c, 0x1400ffd0 }, + { 0x11002c4d, 0x1400ffd0 }, + { 0x11002c4e, 0x1400ffd0 }, + { 0x11002c4f, 0x1400ffd0 }, + { 0x11002c50, 0x1400ffd0 }, + { 0x11002c51, 0x1400ffd0 }, + { 0x11002c52, 0x1400ffd0 }, + { 0x11002c53, 0x1400ffd0 }, + { 0x11002c54, 0x1400ffd0 }, + { 0x11002c55, 0x1400ffd0 }, + { 0x11002c56, 0x1400ffd0 }, + { 0x11002c57, 0x1400ffd0 }, + { 0x11002c58, 0x1400ffd0 }, + { 0x11002c59, 0x1400ffd0 }, + { 0x11002c5a, 0x1400ffd0 }, + { 0x11002c5b, 0x1400ffd0 }, + { 0x11002c5c, 0x1400ffd0 }, + { 0x11002c5d, 0x1400ffd0 }, + { 0x11002c5e, 0x1400ffd0 }, + { 0x0a002c80, 0x24000001 }, + { 0x0a002c81, 0x1400ffff }, + { 0x0a002c82, 0x24000001 }, + { 0x0a002c83, 0x1400ffff }, + { 0x0a002c84, 0x24000001 }, + { 0x0a002c85, 0x1400ffff }, + { 0x0a002c86, 0x24000001 }, + { 0x0a002c87, 0x1400ffff }, + { 0x0a002c88, 0x24000001 }, + { 0x0a002c89, 0x1400ffff }, + { 0x0a002c8a, 0x24000001 }, + { 0x0a002c8b, 0x1400ffff }, + { 0x0a002c8c, 0x24000001 }, + { 0x0a002c8d, 0x1400ffff }, + { 0x0a002c8e, 0x24000001 }, + { 0x0a002c8f, 0x1400ffff }, + { 0x0a002c90, 0x24000001 }, + { 0x0a002c91, 0x1400ffff }, + { 0x0a002c92, 0x24000001 }, + { 0x0a002c93, 0x1400ffff }, + { 0x0a002c94, 0x24000001 }, + { 0x0a002c95, 0x1400ffff }, + { 0x0a002c96, 0x24000001 }, + { 0x0a002c97, 0x1400ffff }, + { 0x0a002c98, 0x24000001 }, + { 0x0a002c99, 0x1400ffff }, + { 0x0a002c9a, 0x24000001 }, + { 0x0a002c9b, 0x1400ffff }, + { 0x0a002c9c, 0x24000001 }, + { 0x0a002c9d, 0x1400ffff }, + { 0x0a002c9e, 0x24000001 }, + { 0x0a002c9f, 0x1400ffff }, + { 0x0a002ca0, 0x24000001 }, + { 0x0a002ca1, 0x1400ffff }, + { 0x0a002ca2, 0x24000001 }, + { 0x0a002ca3, 0x1400ffff }, + { 0x0a002ca4, 0x24000001 }, + { 0x0a002ca5, 0x1400ffff }, + { 0x0a002ca6, 0x24000001 }, + { 0x0a002ca7, 0x1400ffff }, + { 0x0a002ca8, 0x24000001 }, + { 0x0a002ca9, 0x1400ffff }, + { 0x0a002caa, 0x24000001 }, + { 0x0a002cab, 0x1400ffff }, + { 0x0a002cac, 0x24000001 }, + { 0x0a002cad, 0x1400ffff }, + { 0x0a002cae, 0x24000001 }, + { 0x0a002caf, 0x1400ffff }, + { 0x0a002cb0, 0x24000001 }, + { 0x0a002cb1, 0x1400ffff }, + { 0x0a002cb2, 0x24000001 }, + { 0x0a002cb3, 0x1400ffff }, + { 0x0a002cb4, 0x24000001 }, + { 0x0a002cb5, 0x1400ffff }, + { 0x0a002cb6, 0x24000001 }, + { 0x0a002cb7, 0x1400ffff }, + { 0x0a002cb8, 0x24000001 }, + { 0x0a002cb9, 0x1400ffff }, + { 0x0a002cba, 0x24000001 }, + { 0x0a002cbb, 0x1400ffff }, + { 0x0a002cbc, 0x24000001 }, + { 0x0a002cbd, 0x1400ffff }, + { 0x0a002cbe, 0x24000001 }, + { 0x0a002cbf, 0x1400ffff }, + { 0x0a002cc0, 0x24000001 }, + { 0x0a002cc1, 0x1400ffff }, + { 0x0a002cc2, 0x24000001 }, + { 0x0a002cc3, 0x1400ffff }, + { 0x0a002cc4, 0x24000001 }, + { 0x0a002cc5, 0x1400ffff }, + { 0x0a002cc6, 0x24000001 }, + { 0x0a002cc7, 0x1400ffff }, + { 0x0a002cc8, 0x24000001 }, + { 0x0a002cc9, 0x1400ffff }, + { 0x0a002cca, 0x24000001 }, + { 0x0a002ccb, 0x1400ffff }, + { 0x0a002ccc, 0x24000001 }, + { 0x0a002ccd, 0x1400ffff }, + { 0x0a002cce, 0x24000001 }, + { 0x0a002ccf, 0x1400ffff }, + { 0x0a002cd0, 0x24000001 }, + { 0x0a002cd1, 0x1400ffff }, + { 0x0a002cd2, 0x24000001 }, + { 0x0a002cd3, 0x1400ffff }, + { 0x0a002cd4, 0x24000001 }, + { 0x0a002cd5, 0x1400ffff }, + { 0x0a002cd6, 0x24000001 }, + { 0x0a002cd7, 0x1400ffff }, + { 0x0a002cd8, 0x24000001 }, + { 0x0a002cd9, 0x1400ffff }, + { 0x0a002cda, 0x24000001 }, + { 0x0a002cdb, 0x1400ffff }, + { 0x0a002cdc, 0x24000001 }, + { 0x0a002cdd, 0x1400ffff }, + { 0x0a002cde, 0x24000001 }, + { 0x0a002cdf, 0x1400ffff }, + { 0x0a002ce0, 0x24000001 }, + { 0x0a002ce1, 0x1400ffff }, + { 0x0a002ce2, 0x24000001 }, + { 0x0a002ce3, 0x1400ffff }, + { 0x0a002ce4, 0x14000000 }, + { 0x0a802ce5, 0x68000005 }, + { 0x0a802cf9, 0x54000003 }, + { 0x0a002cfd, 0x3c000000 }, + { 0x0a802cfe, 0x54000001 }, + { 0x10002d00, 0x1400e3a0 }, + { 0x10002d01, 0x1400e3a0 }, + { 0x10002d02, 0x1400e3a0 }, + { 0x10002d03, 0x1400e3a0 }, + { 0x10002d04, 0x1400e3a0 }, + { 0x10002d05, 0x1400e3a0 }, + { 0x10002d06, 0x1400e3a0 }, + { 0x10002d07, 0x1400e3a0 }, + { 0x10002d08, 0x1400e3a0 }, + { 0x10002d09, 0x1400e3a0 }, + { 0x10002d0a, 0x1400e3a0 }, + { 0x10002d0b, 0x1400e3a0 }, + { 0x10002d0c, 0x1400e3a0 }, + { 0x10002d0d, 0x1400e3a0 }, + { 0x10002d0e, 0x1400e3a0 }, + { 0x10002d0f, 0x1400e3a0 }, + { 0x10002d10, 0x1400e3a0 }, + { 0x10002d11, 0x1400e3a0 }, + { 0x10002d12, 0x1400e3a0 }, + { 0x10002d13, 0x1400e3a0 }, + { 0x10002d14, 0x1400e3a0 }, + { 0x10002d15, 0x1400e3a0 }, + { 0x10002d16, 0x1400e3a0 }, + { 0x10002d17, 0x1400e3a0 }, + { 0x10002d18, 0x1400e3a0 }, + { 0x10002d19, 0x1400e3a0 }, + { 0x10002d1a, 0x1400e3a0 }, + { 0x10002d1b, 0x1400e3a0 }, + { 0x10002d1c, 0x1400e3a0 }, + { 0x10002d1d, 0x1400e3a0 }, + { 0x10002d1e, 0x1400e3a0 }, + { 0x10002d1f, 0x1400e3a0 }, + { 0x10002d20, 0x1400e3a0 }, + { 0x10002d21, 0x1400e3a0 }, + { 0x10002d22, 0x1400e3a0 }, + { 0x10002d23, 0x1400e3a0 }, + { 0x10002d24, 0x1400e3a0 }, + { 0x10002d25, 0x1400e3a0 }, + { 0x3a802d30, 0x1c000035 }, + { 0x3a002d6f, 0x18000000 }, + { 0x0f802d80, 0x1c000016 }, + { 0x0f802da0, 0x1c000006 }, + { 0x0f802da8, 0x1c000006 }, + { 0x0f802db0, 0x1c000006 }, + { 0x0f802db8, 0x1c000006 }, + { 0x0f802dc0, 0x1c000006 }, + { 0x0f802dc8, 0x1c000006 }, + { 0x0f802dd0, 0x1c000006 }, + { 0x0f802dd8, 0x1c000006 }, + { 0x09802e00, 0x54000001 }, + { 0x09002e02, 0x50000000 }, + { 0x09002e03, 0x4c000000 }, + { 0x09002e04, 0x50000000 }, + { 0x09002e05, 0x4c000000 }, + { 0x09802e06, 0x54000002 }, + { 0x09002e09, 0x50000000 }, + { 0x09002e0a, 0x4c000000 }, + { 0x09002e0b, 0x54000000 }, + { 0x09002e0c, 0x50000000 }, + { 0x09002e0d, 0x4c000000 }, + { 0x09802e0e, 0x54000008 }, + { 0x09002e17, 0x44000000 }, + { 0x09002e1c, 0x50000000 }, + { 0x09002e1d, 0x4c000000 }, + { 0x16802e80, 0x68000019 }, + { 0x16802e9b, 0x68000058 }, + { 0x16802f00, 0x680000d5 }, + { 0x09802ff0, 0x6800000b }, + { 0x09003000, 0x74000000 }, + { 0x09803001, 0x54000002 }, + { 0x09003004, 0x68000000 }, + { 0x16003005, 0x18000000 }, + { 0x09003006, 0x1c000000 }, + { 0x16003007, 0x38000000 }, + { 0x09003008, 0x58000000 }, + { 0x09003009, 0x48000000 }, + { 0x0900300a, 0x58000000 }, + { 0x0900300b, 0x48000000 }, + { 0x0900300c, 0x58000000 }, + { 0x0900300d, 0x48000000 }, + { 0x0900300e, 0x58000000 }, + { 0x0900300f, 0x48000000 }, + { 0x09003010, 0x58000000 }, + { 0x09003011, 0x48000000 }, + { 0x09803012, 0x68000001 }, + { 0x09003014, 0x58000000 }, + { 0x09003015, 0x48000000 }, + { 0x09003016, 0x58000000 }, + { 0x09003017, 0x48000000 }, + { 0x09003018, 0x58000000 }, + { 0x09003019, 0x48000000 }, + { 0x0900301a, 0x58000000 }, + { 0x0900301b, 0x48000000 }, + { 0x0900301c, 0x44000000 }, + { 0x0900301d, 0x58000000 }, + { 0x0980301e, 0x48000001 }, + { 0x09003020, 0x68000000 }, + { 0x16803021, 0x38000008 }, + { 0x1b80302a, 0x30000005 }, + { 0x09003030, 0x44000000 }, + { 0x09803031, 0x18000004 }, + { 0x09803036, 0x68000001 }, + { 0x16803038, 0x38000002 }, + { 0x1600303b, 0x18000000 }, + { 0x0900303c, 0x1c000000 }, + { 0x0900303d, 0x54000000 }, + { 0x0980303e, 0x68000001 }, + { 0x1a803041, 0x1c000055 }, + { 0x1b803099, 0x30000001 }, + { 0x0980309b, 0x60000001 }, + { 0x1a80309d, 0x18000001 }, + { 0x1a00309f, 0x1c000000 }, + { 0x090030a0, 0x44000000 }, + { 0x1d8030a1, 0x1c000059 }, + { 0x090030fb, 0x54000000 }, + { 0x098030fc, 0x18000002 }, + { 0x1d0030ff, 0x1c000000 }, + { 0x03803105, 0x1c000027 }, + { 0x17803131, 0x1c00005d }, + { 0x09803190, 0x68000001 }, + { 0x09803192, 0x3c000003 }, + { 0x09803196, 0x68000009 }, + { 0x038031a0, 0x1c000017 }, + { 0x098031c0, 0x6800000f }, + { 0x1d8031f0, 0x1c00000f }, + { 0x17803200, 0x6800001e }, + { 0x09803220, 0x3c000009 }, + { 0x0980322a, 0x68000019 }, + { 0x09003250, 0x68000000 }, + { 0x09803251, 0x3c00000e }, + { 0x17803260, 0x6800001f }, + { 0x09803280, 0x3c000009 }, + { 0x0980328a, 0x68000026 }, + { 0x098032b1, 0x3c00000e }, + { 0x098032c0, 0x6800003e }, + { 0x09803300, 0x680000ff }, + { 0x16803400, 0x1c0019b5 }, + { 0x09804dc0, 0x6800003f }, + { 0x16804e00, 0x1c0051bb }, + { 0x3c80a000, 0x1c000014 }, + { 0x3c00a015, 0x18000000 }, + { 0x3c80a016, 0x1c000476 }, + { 0x3c80a490, 0x68000036 }, + { 0x0980a700, 0x60000016 }, + { 0x3080a800, 0x1c000001 }, + { 0x3000a802, 0x28000000 }, + { 0x3080a803, 0x1c000002 }, + { 0x3000a806, 0x30000000 }, + { 0x3080a807, 0x1c000003 }, + { 0x3000a80b, 0x30000000 }, + { 0x3080a80c, 0x1c000016 }, + { 0x3080a823, 0x28000001 }, + { 0x3080a825, 0x30000001 }, + { 0x3000a827, 0x28000000 }, + { 0x3080a828, 0x68000003 }, + { 0x1780ac00, 0x1c002ba3 }, + { 0x0980d800, 0x1000037f }, + { 0x0980db80, 0x1000007f }, + { 0x0980dc00, 0x100003ff }, + { 0x0980e000, 0x0c0018ff }, + { 0x1680f900, 0x1c00012d }, + { 0x1680fa30, 0x1c00003a }, + { 0x1680fa70, 0x1c000069 }, + { 0x2180fb00, 0x14000006 }, + { 0x0180fb13, 0x14000004 }, + { 0x1900fb1d, 0x1c000000 }, + { 0x1900fb1e, 0x30000000 }, + { 0x1980fb1f, 0x1c000009 }, + { 0x1900fb29, 0x64000000 }, + { 0x1980fb2a, 0x1c00000c }, + { 0x1980fb38, 0x1c000004 }, + { 0x1900fb3e, 0x1c000000 }, + { 0x1980fb40, 0x1c000001 }, + { 0x1980fb43, 0x1c000001 }, + { 0x1980fb46, 0x1c00006b }, + { 0x0080fbd3, 0x1c00016a }, + { 0x0900fd3e, 0x58000000 }, + { 0x0900fd3f, 0x48000000 }, + { 0x0080fd50, 0x1c00003f }, + { 0x0080fd92, 0x1c000035 }, + { 0x0080fdf0, 0x1c00000b }, + { 0x0000fdfc, 0x5c000000 }, + { 0x0900fdfd, 0x68000000 }, + { 0x1b80fe00, 0x3000000f }, + { 0x0980fe10, 0x54000006 }, + { 0x0900fe17, 0x58000000 }, + { 0x0900fe18, 0x48000000 }, + { 0x0900fe19, 0x54000000 }, + { 0x1b80fe20, 0x30000003 }, + { 0x0900fe30, 0x54000000 }, + { 0x0980fe31, 0x44000001 }, + { 0x0980fe33, 0x40000001 }, + { 0x0900fe35, 0x58000000 }, + { 0x0900fe36, 0x48000000 }, + { 0x0900fe37, 0x58000000 }, + { 0x0900fe38, 0x48000000 }, + { 0x0900fe39, 0x58000000 }, + { 0x0900fe3a, 0x48000000 }, + { 0x0900fe3b, 0x58000000 }, + { 0x0900fe3c, 0x48000000 }, + { 0x0900fe3d, 0x58000000 }, + { 0x0900fe3e, 0x48000000 }, + { 0x0900fe3f, 0x58000000 }, + { 0x0900fe40, 0x48000000 }, + { 0x0900fe41, 0x58000000 }, + { 0x0900fe42, 0x48000000 }, + { 0x0900fe43, 0x58000000 }, + { 0x0900fe44, 0x48000000 }, + { 0x0980fe45, 0x54000001 }, + { 0x0900fe47, 0x58000000 }, + { 0x0900fe48, 0x48000000 }, + { 0x0980fe49, 0x54000003 }, + { 0x0980fe4d, 0x40000002 }, + { 0x0980fe50, 0x54000002 }, + { 0x0980fe54, 0x54000003 }, + { 0x0900fe58, 0x44000000 }, + { 0x0900fe59, 0x58000000 }, + { 0x0900fe5a, 0x48000000 }, + { 0x0900fe5b, 0x58000000 }, + { 0x0900fe5c, 0x48000000 }, + { 0x0900fe5d, 0x58000000 }, + { 0x0900fe5e, 0x48000000 }, + { 0x0980fe5f, 0x54000002 }, + { 0x0900fe62, 0x64000000 }, + { 0x0900fe63, 0x44000000 }, + { 0x0980fe64, 0x64000002 }, + { 0x0900fe68, 0x54000000 }, + { 0x0900fe69, 0x5c000000 }, + { 0x0980fe6a, 0x54000001 }, + { 0x0080fe70, 0x1c000004 }, + { 0x0080fe76, 0x1c000086 }, + { 0x0900feff, 0x04000000 }, + { 0x0980ff01, 0x54000002 }, + { 0x0900ff04, 0x5c000000 }, + { 0x0980ff05, 0x54000002 }, + { 0x0900ff08, 0x58000000 }, + { 0x0900ff09, 0x48000000 }, + { 0x0900ff0a, 0x54000000 }, + { 0x0900ff0b, 0x64000000 }, + { 0x0900ff0c, 0x54000000 }, + { 0x0900ff0d, 0x44000000 }, + { 0x0980ff0e, 0x54000001 }, + { 0x0980ff10, 0x34000009 }, + { 0x0980ff1a, 0x54000001 }, + { 0x0980ff1c, 0x64000002 }, + { 0x0980ff1f, 0x54000001 }, + { 0x2100ff21, 0x24000020 }, + { 0x2100ff22, 0x24000020 }, + { 0x2100ff23, 0x24000020 }, + { 0x2100ff24, 0x24000020 }, + { 0x2100ff25, 0x24000020 }, + { 0x2100ff26, 0x24000020 }, + { 0x2100ff27, 0x24000020 }, + { 0x2100ff28, 0x24000020 }, + { 0x2100ff29, 0x24000020 }, + { 0x2100ff2a, 0x24000020 }, + { 0x2100ff2b, 0x24000020 }, + { 0x2100ff2c, 0x24000020 }, + { 0x2100ff2d, 0x24000020 }, + { 0x2100ff2e, 0x24000020 }, + { 0x2100ff2f, 0x24000020 }, + { 0x2100ff30, 0x24000020 }, + { 0x2100ff31, 0x24000020 }, + { 0x2100ff32, 0x24000020 }, + { 0x2100ff33, 0x24000020 }, + { 0x2100ff34, 0x24000020 }, + { 0x2100ff35, 0x24000020 }, + { 0x2100ff36, 0x24000020 }, + { 0x2100ff37, 0x24000020 }, + { 0x2100ff38, 0x24000020 }, + { 0x2100ff39, 0x24000020 }, + { 0x2100ff3a, 0x24000020 }, + { 0x0900ff3b, 0x58000000 }, + { 0x0900ff3c, 0x54000000 }, + { 0x0900ff3d, 0x48000000 }, + { 0x0900ff3e, 0x60000000 }, + { 0x0900ff3f, 0x40000000 }, + { 0x0900ff40, 0x60000000 }, + { 0x2100ff41, 0x1400ffe0 }, + { 0x2100ff42, 0x1400ffe0 }, + { 0x2100ff43, 0x1400ffe0 }, + { 0x2100ff44, 0x1400ffe0 }, + { 0x2100ff45, 0x1400ffe0 }, + { 0x2100ff46, 0x1400ffe0 }, + { 0x2100ff47, 0x1400ffe0 }, + { 0x2100ff48, 0x1400ffe0 }, + { 0x2100ff49, 0x1400ffe0 }, + { 0x2100ff4a, 0x1400ffe0 }, + { 0x2100ff4b, 0x1400ffe0 }, + { 0x2100ff4c, 0x1400ffe0 }, + { 0x2100ff4d, 0x1400ffe0 }, + { 0x2100ff4e, 0x1400ffe0 }, + { 0x2100ff4f, 0x1400ffe0 }, + { 0x2100ff50, 0x1400ffe0 }, + { 0x2100ff51, 0x1400ffe0 }, + { 0x2100ff52, 0x1400ffe0 }, + { 0x2100ff53, 0x1400ffe0 }, + { 0x2100ff54, 0x1400ffe0 }, + { 0x2100ff55, 0x1400ffe0 }, + { 0x2100ff56, 0x1400ffe0 }, + { 0x2100ff57, 0x1400ffe0 }, + { 0x2100ff58, 0x1400ffe0 }, + { 0x2100ff59, 0x1400ffe0 }, + { 0x2100ff5a, 0x1400ffe0 }, + { 0x0900ff5b, 0x58000000 }, + { 0x0900ff5c, 0x64000000 }, + { 0x0900ff5d, 0x48000000 }, + { 0x0900ff5e, 0x64000000 }, + { 0x0900ff5f, 0x58000000 }, + { 0x0900ff60, 0x48000000 }, + { 0x0900ff61, 0x54000000 }, + { 0x0900ff62, 0x58000000 }, + { 0x0900ff63, 0x48000000 }, + { 0x0980ff64, 0x54000001 }, + { 0x1d80ff66, 0x1c000009 }, + { 0x0900ff70, 0x18000000 }, + { 0x1d80ff71, 0x1c00002c }, + { 0x0980ff9e, 0x18000001 }, + { 0x1780ffa0, 0x1c00001e }, + { 0x1780ffc2, 0x1c000005 }, + { 0x1780ffca, 0x1c000005 }, + { 0x1780ffd2, 0x1c000005 }, + { 0x1780ffda, 0x1c000002 }, + { 0x0980ffe0, 0x5c000001 }, + { 0x0900ffe2, 0x64000000 }, + { 0x0900ffe3, 0x60000000 }, + { 0x0900ffe4, 0x68000000 }, + { 0x0980ffe5, 0x5c000001 }, + { 0x0900ffe8, 0x68000000 }, + { 0x0980ffe9, 0x64000003 }, + { 0x0980ffed, 0x68000001 }, + { 0x0980fff9, 0x04000002 }, + { 0x0980fffc, 0x68000001 }, + { 0x23810000, 0x1c00000b }, + { 0x2381000d, 0x1c000019 }, + { 0x23810028, 0x1c000012 }, + { 0x2381003c, 0x1c000001 }, + { 0x2381003f, 0x1c00000e }, + { 0x23810050, 0x1c00000d }, + { 0x23810080, 0x1c00007a }, + { 0x09810100, 0x54000001 }, + { 0x09010102, 0x68000000 }, + { 0x09810107, 0x3c00002c }, + { 0x09810137, 0x68000008 }, + { 0x13810140, 0x38000034 }, + { 0x13810175, 0x3c000003 }, + { 0x13810179, 0x68000010 }, + { 0x1301018a, 0x3c000000 }, + { 0x29810300, 0x1c00001e }, + { 0x29810320, 0x3c000003 }, + { 0x12810330, 0x1c000019 }, + { 0x1201034a, 0x38000000 }, + { 0x3b810380, 0x1c00001d }, + { 0x3b01039f, 0x54000000 }, + { 0x2a8103a0, 0x1c000023 }, + { 0x2a8103c8, 0x1c000007 }, + { 0x2a0103d0, 0x68000000 }, + { 0x2a8103d1, 0x38000004 }, + { 0x0d010400, 0x24000028 }, + { 0x0d010401, 0x24000028 }, + { 0x0d010402, 0x24000028 }, + { 0x0d010403, 0x24000028 }, + { 0x0d010404, 0x24000028 }, + { 0x0d010405, 0x24000028 }, + { 0x0d010406, 0x24000028 }, + { 0x0d010407, 0x24000028 }, + { 0x0d010408, 0x24000028 }, + { 0x0d010409, 0x24000028 }, + { 0x0d01040a, 0x24000028 }, + { 0x0d01040b, 0x24000028 }, + { 0x0d01040c, 0x24000028 }, + { 0x0d01040d, 0x24000028 }, + { 0x0d01040e, 0x24000028 }, + { 0x0d01040f, 0x24000028 }, + { 0x0d010410, 0x24000028 }, + { 0x0d010411, 0x24000028 }, + { 0x0d010412, 0x24000028 }, + { 0x0d010413, 0x24000028 }, + { 0x0d010414, 0x24000028 }, + { 0x0d010415, 0x24000028 }, + { 0x0d010416, 0x24000028 }, + { 0x0d010417, 0x24000028 }, + { 0x0d010418, 0x24000028 }, + { 0x0d010419, 0x24000028 }, + { 0x0d01041a, 0x24000028 }, + { 0x0d01041b, 0x24000028 }, + { 0x0d01041c, 0x24000028 }, + { 0x0d01041d, 0x24000028 }, + { 0x0d01041e, 0x24000028 }, + { 0x0d01041f, 0x24000028 }, + { 0x0d010420, 0x24000028 }, + { 0x0d010421, 0x24000028 }, + { 0x0d010422, 0x24000028 }, + { 0x0d010423, 0x24000028 }, + { 0x0d010424, 0x24000028 }, + { 0x0d010425, 0x24000028 }, + { 0x0d010426, 0x24000028 }, + { 0x0d010427, 0x24000028 }, + { 0x0d010428, 0x1400ffd8 }, + { 0x0d010429, 0x1400ffd8 }, + { 0x0d01042a, 0x1400ffd8 }, + { 0x0d01042b, 0x1400ffd8 }, + { 0x0d01042c, 0x1400ffd8 }, + { 0x0d01042d, 0x1400ffd8 }, + { 0x0d01042e, 0x1400ffd8 }, + { 0x0d01042f, 0x1400ffd8 }, + { 0x0d010430, 0x1400ffd8 }, + { 0x0d010431, 0x1400ffd8 }, + { 0x0d010432, 0x1400ffd8 }, + { 0x0d010433, 0x1400ffd8 }, + { 0x0d010434, 0x1400ffd8 }, + { 0x0d010435, 0x1400ffd8 }, + { 0x0d010436, 0x1400ffd8 }, + { 0x0d010437, 0x1400ffd8 }, + { 0x0d010438, 0x1400ffd8 }, + { 0x0d010439, 0x1400ffd8 }, + { 0x0d01043a, 0x1400ffd8 }, + { 0x0d01043b, 0x1400ffd8 }, + { 0x0d01043c, 0x1400ffd8 }, + { 0x0d01043d, 0x1400ffd8 }, + { 0x0d01043e, 0x1400ffd8 }, + { 0x0d01043f, 0x1400ffd8 }, + { 0x0d010440, 0x1400ffd8 }, + { 0x0d010441, 0x1400ffd8 }, + { 0x0d010442, 0x1400ffd8 }, + { 0x0d010443, 0x1400ffd8 }, + { 0x0d010444, 0x1400ffd8 }, + { 0x0d010445, 0x1400ffd8 }, + { 0x0d010446, 0x1400ffd8 }, + { 0x0d010447, 0x1400ffd8 }, + { 0x0d010448, 0x1400ffd8 }, + { 0x0d010449, 0x1400ffd8 }, + { 0x0d01044a, 0x1400ffd8 }, + { 0x0d01044b, 0x1400ffd8 }, + { 0x0d01044c, 0x1400ffd8 }, + { 0x0d01044d, 0x1400ffd8 }, + { 0x0d01044e, 0x1400ffd8 }, + { 0x0d01044f, 0x1400ffd8 }, + { 0x2e810450, 0x1c00004d }, + { 0x2c8104a0, 0x34000009 }, + { 0x0b810800, 0x1c000005 }, + { 0x0b010808, 0x1c000000 }, + { 0x0b81080a, 0x1c00002b }, + { 0x0b810837, 0x1c000001 }, + { 0x0b01083c, 0x1c000000 }, + { 0x0b01083f, 0x1c000000 }, + { 0x1e010a00, 0x1c000000 }, + { 0x1e810a01, 0x30000002 }, + { 0x1e810a05, 0x30000001 }, + { 0x1e810a0c, 0x30000003 }, + { 0x1e810a10, 0x1c000003 }, + { 0x1e810a15, 0x1c000002 }, + { 0x1e810a19, 0x1c00001a }, + { 0x1e810a38, 0x30000002 }, + { 0x1e010a3f, 0x30000000 }, + { 0x1e810a40, 0x3c000007 }, + { 0x1e810a50, 0x54000008 }, + { 0x0981d000, 0x680000f5 }, + { 0x0981d100, 0x68000026 }, + { 0x0981d12a, 0x6800003a }, + { 0x0981d165, 0x28000001 }, + { 0x1b81d167, 0x30000002 }, + { 0x0981d16a, 0x68000002 }, + { 0x0981d16d, 0x28000005 }, + { 0x0981d173, 0x04000007 }, + { 0x1b81d17b, 0x30000007 }, + { 0x0981d183, 0x68000001 }, + { 0x1b81d185, 0x30000006 }, + { 0x0981d18c, 0x6800001d }, + { 0x1b81d1aa, 0x30000003 }, + { 0x0981d1ae, 0x6800002f }, + { 0x1381d200, 0x68000041 }, + { 0x1381d242, 0x30000002 }, + { 0x1301d245, 0x68000000 }, + { 0x0981d300, 0x68000056 }, + { 0x0981d400, 0x24000019 }, + { 0x0981d41a, 0x14000019 }, + { 0x0981d434, 0x24000019 }, + { 0x0981d44e, 0x14000006 }, + { 0x0981d456, 0x14000011 }, + { 0x0981d468, 0x24000019 }, + { 0x0981d482, 0x14000019 }, + { 0x0901d49c, 0x24000000 }, + { 0x0981d49e, 0x24000001 }, + { 0x0901d4a2, 0x24000000 }, + { 0x0981d4a5, 0x24000001 }, + { 0x0981d4a9, 0x24000003 }, + { 0x0981d4ae, 0x24000007 }, + { 0x0981d4b6, 0x14000003 }, + { 0x0901d4bb, 0x14000000 }, + { 0x0981d4bd, 0x14000006 }, + { 0x0981d4c5, 0x1400000a }, + { 0x0981d4d0, 0x24000019 }, + { 0x0981d4ea, 0x14000019 }, + { 0x0981d504, 0x24000001 }, + { 0x0981d507, 0x24000003 }, + { 0x0981d50d, 0x24000007 }, + { 0x0981d516, 0x24000006 }, + { 0x0981d51e, 0x14000019 }, + { 0x0981d538, 0x24000001 }, + { 0x0981d53b, 0x24000003 }, + { 0x0981d540, 0x24000004 }, + { 0x0901d546, 0x24000000 }, + { 0x0981d54a, 0x24000006 }, + { 0x0981d552, 0x14000019 }, + { 0x0981d56c, 0x24000019 }, + { 0x0981d586, 0x14000019 }, + { 0x0981d5a0, 0x24000019 }, + { 0x0981d5ba, 0x14000019 }, + { 0x0981d5d4, 0x24000019 }, + { 0x0981d5ee, 0x14000019 }, + { 0x0981d608, 0x24000019 }, + { 0x0981d622, 0x14000019 }, + { 0x0981d63c, 0x24000019 }, + { 0x0981d656, 0x14000019 }, + { 0x0981d670, 0x24000019 }, + { 0x0981d68a, 0x1400001b }, + { 0x0981d6a8, 0x24000018 }, + { 0x0901d6c1, 0x64000000 }, + { 0x0981d6c2, 0x14000018 }, + { 0x0901d6db, 0x64000000 }, + { 0x0981d6dc, 0x14000005 }, + { 0x0981d6e2, 0x24000018 }, + { 0x0901d6fb, 0x64000000 }, + { 0x0981d6fc, 0x14000018 }, + { 0x0901d715, 0x64000000 }, + { 0x0981d716, 0x14000005 }, + { 0x0981d71c, 0x24000018 }, + { 0x0901d735, 0x64000000 }, + { 0x0981d736, 0x14000018 }, + { 0x0901d74f, 0x64000000 }, + { 0x0981d750, 0x14000005 }, + { 0x0981d756, 0x24000018 }, + { 0x0901d76f, 0x64000000 }, + { 0x0981d770, 0x14000018 }, + { 0x0901d789, 0x64000000 }, + { 0x0981d78a, 0x14000005 }, + { 0x0981d790, 0x24000018 }, + { 0x0901d7a9, 0x64000000 }, + { 0x0981d7aa, 0x14000018 }, + { 0x0901d7c3, 0x64000000 }, + { 0x0981d7c4, 0x14000005 }, + { 0x0981d7ce, 0x34000031 }, + { 0x16820000, 0x1c00a6d6 }, + { 0x1682f800, 0x1c00021d }, + { 0x090e0001, 0x04000000 }, + { 0x098e0020, 0x0400005f }, + { 0x1b8e0100, 0x300000ef }, + { 0x098f0000, 0x0c00fffd }, + { 0x09900000, 0x0c00fffd }, +};