- {
- /* 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 (®ex, 0, sizeof regex);
- s = re_compile_pattern (pat, sizeof pat - 1, ®ex);
- if (s)
- result |= 1;
- else if (re_search (®ex, 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[] =
+ /* <U1000><U103B><U103D><U1014><U103A><U102F><U1015><U103A> */
+ "\xe1\x80\x80"
+ "\xe1\x80\xbb"
+ "\xe1\x80\xbd"
+ "\xe1\x80\x94"
+ "\xe1\x80\xba"
+ "\xe1\x80\xaf"
+ "\xe1\x80\x95"
+ "\xe1\x80\xba"
+ "x";
+ re_set_syntax (0);
+ memset (®ex, 0, sizeof regex);
+ s = re_compile_pattern (pat, sizeof pat - 1, ®ex);
+ if (s)
+ result |= 1;
+ else
+ {
+ i = re_search (®ex, data, sizeof data - 1,
+ 0, sizeof data - 1, 0);
+ if (i != 0 && i != 21)
+ result |= 1;
+ }
+ }