* regex/regcomp.c (xwcrtomb): New function to convert wide chars

outside of the base plane to UTF-8.  Call throughout instead of
	wcrtomb.
	(wgetnext): Handle surrogate pairs on UTF-16 systems.
	* regex/regexec.c (xmbrtowc): Ditto.
This commit is contained in:
Corinna Vinschen
2010-02-12 17:46:39 +00:00
parent e122c47112
commit 7bd2296c83
3 changed files with 62 additions and 5 deletions

View File

@@ -84,8 +84,24 @@ xmbrtowc(wint_t *wi, const char *s, size_t n, mbstate_t *mbs, wint_t dummy)
if (wi != NULL)
*wi = dummy;
return (1);
} else
} else {
if (sizeof (wchar_t) == 2 && wc >= 0xd800 && wc <= 0xdbff) {
/* UTF-16 surrogate pair. Fetch second half and
compute UTF-32 value */
int n2 = mbrtowc(&wc, s + nr, n - nr, mbs);
if (n2 == 0 || n2 == (size_t)-1 || n2 == (size_t)-2) {
memset(mbs, 0, sizeof(*mbs));
if (wi != NULL)
*wi = dummy;
return (1);
}
if (wi != NULL)
*wi = (((*wi & 0x3ff) << 10) | (wc & 0x3ff))
+ 0x10000;
nr += n2;
}
return (nr);
}
}
static __inline size_t