diff options
| author | Eli Zaretskii <eliz@gnu.org> | 2016-02-20 13:03:20 +0200 |
|---|---|---|
| committer | Eli Zaretskii <eliz@gnu.org> | 2016-02-20 13:03:20 +0200 |
| commit | 1e996cfbd0ab64e4d74d92a80ef3aefc39249462 (patch) | |
| tree | 9f184ee745d6ca7d263d62f6633ad698586ecc95 | |
| parent | 896f993dec0e7b18ed701a5dee6c224083d6e1dd (diff) | |
| download | emacs-1e996cfbd0ab64e4d74d92a80ef3aefc39249462.tar.gz | |
Fix "[:upper:]" for non-ASCII characters
* src/regex.c (re_match_2_internal): Support [:upper:] and
[:lower:] for non-ASCII characters. (Bug#18150)
| -rw-r--r-- | src/regex.c | 14 |
1 files changed, 10 insertions, 4 deletions
diff --git a/src/regex.c b/src/regex.c index dd3f2b3cd67..164eb4612ae 100644 --- a/src/regex.c +++ b/src/regex.c @@ -5444,7 +5444,7 @@ re_match_2_internal (struct re_pattern_buffer *bufp, const_re_char *string1, case charset: case charset_not: { - register unsigned int c; + register unsigned int c, corig; boolean not = (re_opcode_t) *(p - 1) == charset_not; int len; @@ -5473,7 +5473,7 @@ re_match_2_internal (struct re_pattern_buffer *bufp, const_re_char *string1, } PREFETCH (); - c = RE_STRING_CHAR_AND_LENGTH (d, len, target_multibyte); + corig = c = RE_STRING_CHAR_AND_LENGTH (d, len, target_multibyte); if (target_multibyte) { int c1; @@ -5517,11 +5517,17 @@ re_match_2_internal (struct re_pattern_buffer *bufp, const_re_char *string1, { int class_bits = CHARSET_RANGE_TABLE_BITS (&p[-1]); - if ( (class_bits & BIT_LOWER && ISLOWER (c)) + if ( (class_bits & BIT_LOWER + && (ISLOWER (c) + || (corig != c + && c == upcase (corig) && ISUPPER(c)))) | (class_bits & BIT_MULTIBYTE) | (class_bits & BIT_PUNCT && ISPUNCT (c)) | (class_bits & BIT_SPACE && ISSPACE (c)) - | (class_bits & BIT_UPPER && ISUPPER (c)) + | (class_bits & BIT_UPPER + && (ISUPPER (c) + || (corig != c + && c == downcase (corig) && ISLOWER (c)))) | (class_bits & BIT_WORD && ISWORD (c)) | (class_bits & BIT_ALPHA && ISALPHA (c)) | (class_bits & BIT_ALNUM && ISALNUM (c)) |