diff options
| author | ph10 <ph10@2f5784b3-3f2a-0410-8824-cb99058d5e15> | 2013-02-27 16:27:01 +0000 |
|---|---|---|
| committer | ph10 <ph10@2f5784b3-3f2a-0410-8824-cb99058d5e15> | 2013-02-27 16:27:01 +0000 |
| commit | fddeb9c5b24e4d2799afbf6367980c5d982df4d2 (patch) | |
| tree | 37ac15a4f72dbb78f889d770cfd1c26137889785 /pcre_valid_utf8.c | |
| parent | dba7b5b11ce2b26cc1747f58910da27dd15a72b3 (diff) | |
| download | pcre-fddeb9c5b24e4d2799afbf6367980c5d982df4d2.tar.gz | |
Correct Unicode string checking in the light of corrigendum #9.
git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1261 2f5784b3-3f2a-0410-8824-cb99058d5e15
Diffstat (limited to 'pcre_valid_utf8.c')
| -rw-r--r-- | pcre_valid_utf8.c | 15 |
1 files changed, 2 insertions, 13 deletions
diff --git a/pcre_valid_utf8.c b/pcre_valid_utf8.c index a415927..3b0f646 100644 --- a/pcre_valid_utf8.c +++ b/pcre_valid_utf8.c @@ -6,7 +6,7 @@ and semantics are as close as possible to those of the Perl 5 language. Written by Philip Hazel - Copyright (c) 1997-2012 University of Cambridge + Copyright (c) 1997-2013 University of Cambridge ----------------------------------------------------------------------------- Redistribution and use in source and binary forms, with or without @@ -92,7 +92,7 @@ PCRE_UTF8_ERR18 Overlong 5-byte sequence (won't ever occur) PCRE_UTF8_ERR19 Overlong 6-byte sequence (won't ever occur) PCRE_UTF8_ERR20 Isolated 0x80 byte (not within UTF-8 character) PCRE_UTF8_ERR21 Byte with the illegal value 0xfe or 0xff -PCRE_UTF8_ERR22 Non-character +PCRE_UTF8_ERR22 Unused (was non-character) Arguments: string points to the string @@ -118,7 +118,6 @@ if (length < 0) for (p = string; length-- > 0; p++) { register pcre_uchar ab, c, d; - pcre_uint32 v = 0; c = *p; if (c < 128) continue; /* ASCII character */ @@ -187,7 +186,6 @@ for (p = string; length-- > 0; p++) *erroroffset = (int)(p - string) - 2; return PCRE_UTF8_ERR14; } - v = ((c & 0x0f) << 12) | ((d & 0x3f) << 6) | (*p & 0x3f); break; /* 4-byte character. Check 3rd and 4th bytes for 0x80. Then check first 2 @@ -215,7 +213,6 @@ for (p = string; length-- > 0; p++) *erroroffset = (int)(p - string) - 3; return PCRE_UTF8_ERR13; } - v = ((c & 0x07) << 18) | ((d & 0x3f) << 12) | ((p[-1] & 0x3f) << 6) | (*p & 0x3f); break; /* 5-byte and 6-byte characters are not allowed by RFC 3629, and will be @@ -290,14 +287,6 @@ for (p = string; length-- > 0; p++) *erroroffset = (int)(p - string) - ab; return (ab == 4)? PCRE_UTF8_ERR11 : PCRE_UTF8_ERR12; } - - /* Reject non-characters. The pointer p is currently at the last byte of the - character. */ - if ((v & 0xfffeu) == 0xfffeu || (v >= 0xfdd0 && v <= 0xfdef)) - { - *erroroffset = (int)(p - string) - ab; - return PCRE_UTF8_ERR22; - } } #else /* Not SUPPORT_UTF */ |