diff options
| author | Corinna Vinschen <corinna@vinschen.de> | 2013-07-21 23:28:45 +0400 |
|---|---|---|
| committer | Corinna Vinschen <corinna@vinschen.de> | 2013-07-21 23:28:45 +0400 |
| commit | e6ff6a18d4949dd49acc9be04bd522ebdd207900 (patch) | |
| tree | 74f77f2cad7a72dad83a3353eff05499472ccee8 /winsup/cygwin/regex | |
| parent | ca5eb1cba534d77159fedad70a10d5f05787cf4b (diff) | |
* regex/regcomp.c (wgetnext): Add a kludge to be more glibc compatible.
Add comment to explain.
Diffstat (limited to 'winsup/cygwin/regex')
| -rw-r--r-- | winsup/cygwin/regex/regcomp.c | 12 |
1 files changed, 12 insertions, 0 deletions
diff --git a/winsup/cygwin/regex/regcomp.c b/winsup/cygwin/regex/regcomp.c index 881c16099..b68db99c7 100644 --- a/winsup/cygwin/regex/regcomp.c +++ b/winsup/cygwin/regex/regcomp.c @@ -1128,6 +1128,18 @@ wgetnext(struct parse *p) wint_t ret; size_t n; +#ifdef __CYGWIN__ + /* Kludge for more glibc compatibility. On Cygwin as well as on + Linux, mbrtowc returns -1 if the current local's codeset is ASCII + and the character is >= 0x80. Nevertheless, glibc's regcomp allows + any char value, even stuff like [\xc0-\xff], if the locale's codeset + is ASCII, so in regcomp it ignores the fact that chars >= 0x80 are + invalid ASCII chars. To be more Linux-compatible, we align the + behaviour to glibc here. Allow any character value if the current + local's codeset is ASCII. */ + if (*__locale_charset () == 'A') /* SCII */ + return (wint_t) (unsigned char) *p->next++; +#endif memset(&mbs, 0, sizeof(mbs)); n = mbrtowc(&wc, p->next, p->end - p->next, &mbs); if (n == (size_t)-1 || n == (size_t)-2) { |