[lib/ChangeLog]

[gnulib.git] / m4 / regex.m4

diff --git a/m4/regex.m4 b/m4/regex.m4
index d59df38..69dc326 100644 (file)
--- a/m4/regex.m4
+++ b/m4/regex.m4
@@ -1,4 +1,4 @@
-#serial 34
+#serial 40
 
 # Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2003, 2004, 2005,
 # 2006 Free Software Foundation, Inc.
@@ -14,9 +14,7 @@ AC_PREREQ([2.50])
 
 AC_DEFUN([gl_REGEX],
 [
-  AC_LIBSOURCES(
-    [regcomp.c, regex.c, regex.h,
-     regex_internal.c, regex_internal.h, regexec.c])
+  AC_CHECK_HEADERS_ONCE([locale.h])
 
   AC_ARG_WITH([included-regex],
     [AC_HELP_STRING([--without-included-regex],
@@ -24,27 +22,64 @@ AC_DEFUN([gl_REGEX],
                     systems with recent-enough versions of the GNU C
                     Library (use with caution on other systems)])])
 
-  case $with_included_regex in
+  case $with_included_regex in #(
   yes|no) ac_use_included_regex=$with_included_regex
        ;;
   '')
-    # If the system regex support is good enough that it passes the the
+    # If the system regex support is good enough that it passes the
     # following run test, then default to *not* using the included regex.c.
     # If cross compiling, assume the test would fail and use the included
     # regex.c.  The first failing regular expression is from `Spencer ere
     # test #75' in grep-2.3.
     AC_CACHE_CHECK([for working re_compile_pattern],
-                  [gl_cv_func_re_compile_pattern_broken],
+                  [gl_cv_func_re_compile_pattern_working],
       [AC_RUN_IFELSE(
        [AC_LANG_PROGRAM(
          [AC_INCLUDES_DEFAULT
-          #include <regex.h>],
+          #if HAVE_LOCALE_H
+           #include <locale.h>
+          #endif
+          #include <limits.h>
+          #include <regex.h>
+          ],
          [[static struct re_pattern_buffer regex;
+           unsigned char folded_chars[UCHAR_MAX + 1];
+           int i;
            const char *s;
            struct re_registers regs;
+
+           #if HAVE_LOCALE_H
+             /* http://sourceware.org/ml/libc-hacker/2006-09/msg00008.html
+                This test needs valgrind to catch the bug on Debian
+                GNU/Linux 3.1 x86, but it might catch the bug better
+                on other platforms and it shouldn't hurt to try the
+                test here.  */
+             if (setlocale (LC_ALL, "en_US.UTF-8"))
+               {
+                 static char const pat[] = "insert into";
+                 static char const data[] =
+                   "\xFF\0\x12\xA2\xAA\xC4\xB1,K\x12\xC4\xB1*\xACK";
+                 re_set_syntax (RE_SYNTAX_GREP | RE_HAT_LISTS_NOT_NEWLINE
+                                | RE_ICASE);
+                 memset (&regex, 0, sizeof regex);
+                 s = re_compile_pattern (pat, sizeof pat - 1, &regex);
+                 if (s)
+                   return 1;
+                 if (re_search (&regex, data, sizeof data - 1,
+                                0, sizeof data - 1, &regs)
+                     != -1)
+                   return 1;
+                 if (! setlocale (LC_ALL, "C"))
+                   return 1;
+               }
+           #endif
+
            re_set_syntax (RE_SYNTAX_POSIX_EGREP);
            memset (&regex, 0, sizeof (regex));
-           s = re_compile_pattern ("a[:@:>@:]b\n", 9, &regex);
+           for (i = 0; i <= UCHAR_MAX; i++)
+             folded_chars[i] = i;
+           regex.translate = folded_chars;
+           s = re_compile_pattern ("a[[:@:>@:]]b\n", 11, &regex);
            /* This should fail with _Invalid character class name_ error.  */
            if (!s)
              exit (1);
@@ -97,15 +132,18 @@ AC_DEFUN([gl_REGEX],
               These include glibc 2.3.5 on hosts with 64-bit ptrdiff_t
               and 32-bit int.  */
            if (sizeof (regoff_t) < sizeof (ptrdiff_t)
-               || sizeof (regoff_t) < sizeof (ssize_t))
+               || sizeof (regoff_t) < sizeof (ssize_t))
              exit (1);
 
            exit (0);]])],
-       [gl_cv_func_re_compile_pattern_broken=no],
-       [gl_cv_func_re_compile_pattern_broken=yes],
-       dnl When crosscompiling, assume it is broken.
-       [gl_cv_func_re_compile_pattern_broken=yes])])
-    ac_use_included_regex=$gl_cv_func_re_compile_pattern_broken
+       [gl_cv_func_re_compile_pattern_working=yes],
+       [gl_cv_func_re_compile_pattern_working=no],
+       dnl When crosscompiling, assume it is not working.
+       [gl_cv_func_re_compile_pattern_working=no])])
+    case $gl_cv_func_re_compile_pattern_working in #(
+    yes) ac_use_included_regex=no;; #(
+    no) ac_use_included_regex=yes;;
+    esac
     ;;
   *) AC_MSG_ERROR([Invalid value for --with-included-regex: $with_included_regex])
     ;;
@@ -153,8 +191,9 @@ AC_DEFUN([gl_REGEX],
 AC_DEFUN([gl_PREREQ_REGEX],
 [
   AC_REQUIRE([AC_GNU_SOURCE])
-  AC_REQUIRE([gl_C_RESTRICT])
+  AC_REQUIRE([AC_C_RESTRICT])
   AC_REQUIRE([AM_LANGINFO_CODESET])
-  AC_CHECK_HEADERS_ONCE([locale.h wchar.h wctype.h])
-  AC_CHECK_FUNCS_ONCE([isblank mbrtowc mempcpy wcrtomb wcscoll])
+  AC_CHECK_HEADERS_ONCE([wchar.h wctype.h])
+  AC_CHECK_FUNCS_ONCE([mbrtowc mempcpy wcrtomb wcscoll])
+  AC_CHECK_DECLS([isblank], [], [], [#include <ctype.h>])
 ])