update to pcre 7.9

git-svn-id: http://svn.freeswitch.org/svn/freeswitch/trunk@13706 d0543943-73ff-0310-b7d9-9358b9ac24b2
This commit is contained in:
Michael Jerris
2009-06-08 23:51:30 +00:00
parent a1e5add731
commit f7efdaa901
178 changed files with 43560 additions and 11382 deletions

View File

@@ -6,7 +6,7 @@
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
Copyright (c) 1997-2009 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@@ -42,6 +42,10 @@ POSSIBILITY OF SUCH DAMAGE.
strings. */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre_internal.h"
@@ -55,6 +59,13 @@ 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.
Originally, this function checked according to RFC 2279, allowing for values in
the range 0 to 0x7fffffff, up to 6 bytes long, but ensuring that they were in
the canonical format. Once somebody had pointed out RFC 3629 to me (it
obsoletes 2279), additional restrictions were applied. The values are now
limited to be between 0 and 0x0010ffff, no more than 4 bytes long, and the
subrange 0xd000 to 0xdfff is excluded.
Arguments:
string points to the string
length length of string, or -1 if the string is zero-terminated
@@ -64,9 +75,10 @@ Returns: < 0 if the string is a valid UTF-8 string
*/
int
_pcre_valid_utf8(const uschar *string, int length)
_pcre_valid_utf8(USPTR string, int length)
{
register const uschar *p;
#ifdef SUPPORT_UTF8
register USPTR p;
if (length < 0)
{
@@ -79,32 +91,49 @@ 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;
if (c < 0xc0) return p - string;
ab = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */
if (length < ab || ab > 3) 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 */
/* Check for overlong sequences for each different length, and for the
excluded range 0xd000 to 0xdfff. */
switch (ab)
{
/* Check for xx00 000x */
/* Check for xx00 000x (overlong sequence) */
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 */
/* Check for 1110 0000, xx0x xxxx (overlong sequence) or
1110 1101, 1010 xxxx (0xd000 - 0xdfff) */
case 2:
if (c == 0xe0 && (*p & 0x20) == 0) return p - string;
if ((c == 0xe0 && (*p & 0x20) == 0) ||
(c == 0xed && *p >= 0xa0))
return p - string;
break;
/* Check for 1111 0000, xx00 xxxx */
/* Check for 1111 0000, xx00 xxxx (overlong sequence) or
greater than 0x0010ffff (f4 8f bf bf) */
case 3:
if (c == 0xf0 && (*p & 0x30) == 0) return p - string;
if ((c == 0xf0 && (*p & 0x30) == 0) ||
(c > 0xf4 ) ||
(c == 0xf4 && *p > 0x8f))
return p - string;
break;
#if 0
/* These cases can no longer occur, as we restrict to a maximum of four
bytes nowadays. Leave the code here in case we ever want to add an option
for longer sequences. */
/* Check for 1111 1000, xx00 0xxx */
case 4:
if (c == 0xf8 && (*p & 0x38) == 0) return p - string;
@@ -115,6 +144,8 @@ for (p = string; length-- > 0; p++)
if (c == 0xfe || c == 0xff ||
(c == 0xfc && (*p & 0x3c) == 0)) return p - string;
break;
#endif
}
/* Check for valid bytes after the 2nd, if any; all must start 10 */
@@ -123,6 +154,10 @@ for (p = string; length-- > 0; p++)
if ((*(++p) & 0xc0) != 0x80) return p - string;
}
}
#else
(void)(string); /* Keep picky compilers happy */
(void)(length);
#endif
return -1;
}