remove strcasecmp from regex code; use localcharset instead

[Paul Eggert]

I installed this.  It adds a dependency of regex on localcharset,
which I'd rather avoid, but the alternatives seemed worse to me.

2007-02-14  Paul Eggert  <address@hidden>

        Fix regex code so it doesn't rely on strcasecmp.
        * lib/regex_internal.h: Include <langinfo.h> only if _LIBC is defined.
        Otherwise, include gnulib's langinfo.h.
        * lib/regcomp.c (init_dfa): Don't use strcasecmp, as it can have
        undesirable behavior in non-C locales.  Instead, rely on localecharset.
        * m4/regex.m4 (gl_PREREQ_REGEX): Don't require AM_LANGINFO_CODESET.
        * modules/regex (FILES): Remove m4/codeset.m4.
        (Depends-on): Add localcharset.  Remove strcase.

Index: lib/regex_internal.h
===================================================================
RCS file: /cvsroot/gnulib/gnulib/lib/regex_internal.h,v
retrieving revision 1.31
diff -u -p -r1.31 regex_internal.h
--- lib/regex_internal.h        2 Feb 2007 22:15:44 -0000       1.31
+++ lib/regex_internal.h        15 Feb 2007 00:16:51 -0000
@@ -27,8 +27,10 @@
 #include <stdlib.h>
 #include <string.h>

-#if defined HAVE_LANGINFO_H || defined HAVE_LANGINFO_CODESET || defined _LIBC
+#ifdef _LIBC
 # include <langinfo.h>
+#else
+# include "localcharset.h"
 #endif
 #if defined HAVE_LOCALE_H || defined _LIBC
 # include <locale.h>
Index: lib/regcomp.c
===================================================================
RCS file: /cvsroot/gnulib/gnulib/lib/regcomp.c,v
retrieving revision 1.26
diff -u -p -r1.26 regcomp.c
--- lib/regcomp.c       5 Feb 2007 15:38:59 -0000       1.26
+++ lib/regcomp.c       15 Feb 2007 00:16:52 -0000
@@ -829,9 +829,6 @@ static reg_errcode_t
 init_dfa (re_dfa_t *dfa, size_t pat_len)
 {
   __re_size_t table_size;
-#ifndef _LIBC
-  char *codeset_name;
-#endif
 #ifdef RE_ENABLE_I18N
   size_t max_i18n_object_size = MAX (sizeof (wchar_t), sizeof (wctype_t));
 #else
@@ -875,22 +872,7 @@ 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
-
-  if (strcasecmp (codeset_name, "UTF-8") == 0
-      || strcasecmp (codeset_name, "UTF8") == 0)
+  if (strcmp (locale_charset (), "UTF-8") == 0)
     dfa->is_utf8 = 1;

   /* We check exhaustively in the loop below if this charset is a
Index: m4/regex.m4
===================================================================
RCS file: /cvsroot/gnulib/gnulib/m4/regex.m4,v
retrieving revision 1.62
diff -u -p -r1.62 regex.m4
--- m4/regex.m4 6 Feb 2007 07:02:59 -0000       1.62
+++ m4/regex.m4 15 Feb 2007 00:16:52 -0000
@@ -1,4 +1,4 @@
-#serial 44
+#serial 45

 # Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2003, 2004, 2005,
 # 2006, 2007 Free Software Foundation, Inc.
@@ -203,7 +203,6 @@ AC_DEFUN([gl_PREREQ_REGEX],
 [
   AC_REQUIRE([AC_GNU_SOURCE])
   AC_REQUIRE([AC_C_RESTRICT])
-  AC_REQUIRE([AM_LANGINFO_CODESET])
   AC_CHECK_FUNCS_ONCE([iswctype mbrtowc wcrtomb wcscoll])
   AC_CHECK_DECLS([isblank], [], [], [#include <ctype.h>])
 ])
Index: modules/regex
===================================================================
RCS file: /cvsroot/gnulib/gnulib/modules/regex,v
retrieving revision 1.23
diff -u -p -r1.23 regex
--- modules/regex       8 Feb 2007 23:34:28 -0000       1.23
+++ modules/regex       15 Feb 2007 00:16:52 -0000
@@ -8,17 +8,16 @@ lib/regex_internal.c
 lib/regex_internal.h
 lib/regexec.c
 lib/regcomp.c
-m4/codeset.m4
 m4/regex.m4

 Depends-on:
 alloca
 extensions
 gettext-h
+localcharset
 malloc
 stdbool
 stdint
-strcase
 ssize_t
 wchar
 wctype