From: Eric Blake <eblake@redhat.com>
Date: Tue, 12 Mar 2013 21:15:01 +0000 (-0600)
Subject: regex-tests: skip UTF-8 test on mingw
X-Git-Tag: v0.1~172
X-Git-Url: http://erislabs.org.uk/gitweb/?a=commitdiff_plain;h=d69a4209386e256b60ece4407c16c272ff4e45ae;p=gnulib.git

regex-tests: skip UTF-8 test on mingw

test-regex failed on mingw; and I traced it in gdb to an instance
of init_dfa() setting dfa->is_utf8 to 0 in spite of setlocale()
claiming success for "en_US.UTF-8".  test-wcwidth already has
precedent for skipping utf-8 tests where the system (or gnulib
setlocale replacement, in this case) lies about utf-8 support.

* modules/regex-tests (Depends-on): Add localcharset.
* tests/test-regex.c (main): Use it to skip test on mingw.

Signed-off-by: Eric Blake <eblake@redhat.com>
---

diff --git a/ChangeLog b/ChangeLog
index a60836218..7dac78471 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,9 @@
+2013-03-12  Eric Blake  <eblake@redhat.com>
+
+	regex-tests: skip UTF-8 test on mingw
+	* modules/regex-tests (Depends-on): Add localcharset.
+	* tests/test-regex.c (main): Use it to skip test on mingw.
+
 2013-03-11  Eric Blake  <eblake@redhat.com>
 
 	tests: make it easier to bypass alarm time in debugger
diff --git a/modules/regex-tests b/modules/regex-tests
index eb1b1d317..cfff7bfd0 100644
--- a/modules/regex-tests
+++ b/modules/regex-tests
@@ -3,6 +3,7 @@ tests/test-regex.c
 tests/macros.h
 
 Depends-on:
+localcharset
 
 configure.ac:
 
diff --git a/tests/test-regex.c b/tests/test-regex.c
index 682903557..5a94c14f0 100644
--- a/tests/test-regex.c
+++ b/tests/test-regex.c
@@ -26,6 +26,8 @@
 # include <signal.h>
 #endif
 
+#include "localcharset.h"
+
 int
 main (void)
 {
@@ -65,25 +67,30 @@ main (void)
           result |= 1;
       }
 
-      {
-        /* This test is from glibc bug 15078.
-           The test case is from Andreas Schwab in
-           <http://www.sourceware.org/ml/libc-alpha/2013-01/msg00967.html>.
-           */
-        static char const pat[] = "[^x]x";
-        static char const data[] =
-          "\xe1\x80\x80\xe1\x80\xbb\xe1\x80\xbd\xe1\x80\x94\xe1\x80"
-          "\xba\xe1\x80\xaf\xe1\x80\x95\xe1\x80\xbax";
-        re_set_syntax (0);
-        memset (&regex, 0, sizeof regex);
-        s = re_compile_pattern (pat, sizeof pat - 1, &regex);
-        if (s)
-          result |= 1;
-        else if (re_search (&regex, data, sizeof data - 1,
-                            0, sizeof data - 1, 0)
-                 != 21)
-          result |= 1;
-      }
+      /* Check whether it's really a UTF-8 locale.
+         On mingw, the setlocale call succeeds but returns
+         "English_United States.1252", with locale_charset() returning
+         "CP1252".  */
+      if (strcmp (locale_charset (), "UTF-8") == 0)
+        {
+          /* This test is from glibc bug 15078.
+             The test case is from Andreas Schwab in
+             <http://www.sourceware.org/ml/libc-alpha/2013-01/msg00967.html>.
+          */
+          static char const pat[] = "[^x]x";
+          static char const data[] =
+            "\xe1\x80\x80\xe1\x80\xbb\xe1\x80\xbd\xe1\x80\x94\xe1\x80"
+            "\xba\xe1\x80\xaf\xe1\x80\x95\xe1\x80\xbax";
+          re_set_syntax (0);
+          memset (&regex, 0, sizeof regex);
+          s = re_compile_pattern (pat, sizeof pat - 1, &regex);
+          if (s)
+            result |= 1;
+          else if (re_search (&regex, data, sizeof data - 1,
+                              0, sizeof data - 1, 0)
+                   != 21)
+            result |= 1;
+        }
 
       if (! setlocale (LC_ALL, "C"))
         return 1;