From c77bf91b4315efed2b61633567acc7ac3c46959c Mon Sep 17 00:00:00 2001 From: Paul Eggert Date: Fri, 10 Aug 2018 14:19:05 -0700 Subject: regex: Gnulib unibyte RRI uses bytes not chars Adjust the non-glibc code to agree with what Gawk needs for rational range interpretation (RRI) for regular expression ranges. In unibyte locales, Gawk wants ranges to use the underlying byte rather than the character code point. This change does not affect glibc proper. * posix/regcomp.c (parse_byte) [!LIBC && RE_ENABLE_I18N]: In unibyte locales, use the byte value rather than running it through btowc. --- posix/regcomp.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'posix') diff --git a/posix/regcomp.c b/posix/regcomp.c index 3b0a3c6..e81652f 100644 --- a/posix/regcomp.c +++ b/posix/regcomp.c @@ -2684,15 +2684,14 @@ parse_dup_op (bin_tree_t *elem, re_string_t *regexp, re_dfa_t *dfa, # ifdef RE_ENABLE_I18N /* Convert the byte B to the corresponding wide character. In a - unibyte locale, treat B as itself if it is an encoding error. - In a multibyte locale, return WEOF if B is an encoding error. */ + unibyte locale, treat B as itself. In a multibyte locale, return + WEOF if B is an encoding error. */ static wint_t parse_byte (unsigned char b, re_charset_t *mbcset) { - wint_t wc = __btowc (b); - return wc == WEOF && !mbcset ? b : wc; + return mbcset == NULL ? b : __btowc (b); } -#endif +# endif /* Local function for parse_bracket_exp only used in case of NOT _LIBC. Build the range expression which starts from START_ELEM, and ends -- cgit v1.1