From 1eaecf2f18d57718a98f3d4054ac414df3069cf2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Carlos=20Mart=C3=ADn=20Nieto?= Date: Sat, 18 Feb 2012 01:01:48 +0100 Subject: regex: The world uses utf-8 --- deps/regex/regcomp.c | 33 +-------------------------------- 1 file changed, 1 insertion(+), 32 deletions(-) (limited to 'deps/regex') diff --git a/deps/regex/regcomp.c b/deps/regex/regcomp.c index 8c96ed94..200415ec 100644 --- a/deps/regex/regcomp.c +++ b/deps/regex/regcomp.c @@ -840,9 +840,6 @@ static reg_errcode_t init_dfa (re_dfa_t *dfa, size_t pat_len) { unsigned int table_size; -#ifndef _LIBC - char *codeset_name; -#endif memset (dfa, '\0', sizeof (re_dfa_t)); @@ -872,35 +869,7 @@ init_dfa (re_dfa_t *dfa, size_t pat_len) dfa->map_notascii = (_NL_CURRENT_WORD (LC_CTYPE, _NL_CTYPE_MAP_TO_NONASCII) != 0); #else -# ifdef HAVE_LANGINFO_CODESET - codeset_name = nl_langinfo (CODESET); -# else - codeset_name = getenv ("LC_ALL"); - if (codeset_name == NULL || codeset_name[0] == '\0') - codeset_name = getenv ("LC_CTYPE"); - if (codeset_name == NULL || codeset_name[0] == '\0') - codeset_name = getenv ("LANG"); - if (codeset_name == NULL) - codeset_name = ""; - else if (strchr (codeset_name, '.') != NULL) - codeset_name = strchr (codeset_name, '.') + 1; -# endif - - /* strcasecmp isn't a standard interface. brute force check */ -#if 0 - if (strcasecmp (codeset_name, "UTF-8") == 0 - || strcasecmp (codeset_name, "UTF8") == 0) - dfa->is_utf8 = 1; -#else - if ( (codeset_name[0] == 'U' || codeset_name[0] == 'u') - && (codeset_name[1] == 'T' || codeset_name[1] == 't') - && (codeset_name[2] == 'F' || codeset_name[2] == 'f') - && (codeset_name[3] == '-' - ? codeset_name[4] == '8' && codeset_name[5] == '\0' - : codeset_name[3] == '8' && codeset_name[4] == '\0')) - dfa->is_utf8 = 1; -#endif - + dfa->is_utf8 = 1; /* We check exhaustively in the loop below if this charset is a superset of ASCII. */ dfa->map_notascii = 0; -- cgit v1.2.1