Add generic C.UTF-8 locale (Bug 17318)

We add a new C.UTF-8 locale. This locale is not builtin to glibc, but
is provided as a distinct locale. The locale provides full support for
UTF-8 and this includes full code point sorting via STRCMP-based
collation (strcmp or wcscmp).

The collation uses a new keyword 'codepoint_collation' which drops all
collation rules and generates an empty zero rules collation to enable
STRCMP usage in collation. This ensures that we get full code point
sorting for C.UTF-8 with a minimal 1406 bytes of overhead (LC_COLLATE
structure information and ASCII collating tables).

The new locale is added to SUPPORTED. Minimal test data for specific
code points (minus those not supported by collate-test) is provided in
C.UTF-8.in, and this verifies code point sorting is working reasonably
across the range. The locale was tested manually with the full set of
code points without failure.

The locale is harmonized with locales already shipping in various
downstream distributions. A new tst-iconv9 test is added which verifies
the C.UTF-8 locale is generally usable.

Testing for fnmatch, regexec, and recomp is provided by extending
bug-regex1, bugregex19, bug-regex4, bug-regex6, transbug, tst-fnmatch,
tst-regcomp-truncated, and tst-regex to use C.UTF-8.

Tested on x86_64 or i686 without regression.

Reviewed-by: Florian Weimer <fweimer@redhat.com>

9 files changed, 662 insertions, 30 deletions

diff --git a/posix/Makefile b/posix/Makefile
index 059efb3..a522977 100644
--- a/posix/Makefile
+++ b/posix/Makefile
@@ -190,9 +190,19 @@ $(objpfx)wordexp-tst.out: wordexp-tst.sh $(objpfx)wordexp-test
 	$(evaluate-test)
 endif
 
-LOCALES := cs_CZ.UTF-8 da_DK.ISO-8859-1 de_DE.ISO-8859-1 de_DE.UTF-8 \
-	   en_US.UTF-8 es_US.ISO-8859-1 es_US.UTF-8 ja_JP.EUC-JP tr_TR.UTF-8 \
-	   cs_CZ.ISO-8859-2
+LOCALES := \
+	cs_CZ.ISO-8859-2 \
+	cs_CZ.UTF-8 \
+	C.UTF-8 \
+	da_DK.ISO-8859-1 \
+	de_DE.ISO-8859-1 \
+	de_DE.UTF-8 \
+	en_US.UTF-8 \
+	es_US.ISO-8859-1 \
+	es_US.UTF-8 \
+	ja_JP.EUC-JP \
+	tr_TR.UTF-8 \
+	# LOCALES
 include ../gen-locales.mk
 
 $(objpfx)bug-regex1.out: $(gen-locales)
diff --git a/posix/bug-regex1.c b/posix/bug-regex1.c
index b8cf97c..99357e3 100644
--- a/posix/bug-regex1.c
+++ b/posix/bug-regex1.c
@@ -40,6 +40,26 @@ main (void)
 	puts (" -> OK");
     }
 
+  puts ("in C.UTF-8 locale");
+  setlocale (LC_ALL, "C.UTF-8");
+  s = re_compile_pattern ("[an\371]*n", 7, &regex);
+  if (s != NULL)
+    {
+      puts ("re_compile_pattern return non-NULL value");
+      result = 1;
+    }
+  else
+    {
+      match = re_match (&regex, "an", 2, 0, &regs);
+      if (match != 2)
+	{
+	  printf ("re_match returned %d, expected 2\n", match);
+	  result = 1;
+	}
+      else
+	puts (" -> OK");
+    }
+
   puts ("in de_DE.ISO-8859-1 locale");
   setlocale (LC_ALL, "de_DE.ISO-8859-1");
   s = re_compile_pattern ("[an\371]*n", 7, &regex);
diff --git a/posix/bug-regex19.c b/posix/bug-regex19.c
index 001827c..44f6ab6 100644
--- a/posix/bug-regex19.c
+++ b/posix/bug-regex19.c
@@ -24,6 +24,7 @@
 #include <string.h>
 #include <locale.h>
 #include <libc-diag.h>
+#include <support/support.h>
 
 #define BRE RE_SYNTAX_POSIX_BASIC
 #define ERE RE_SYNTAX_POSIX_EXTENDED
@@ -406,8 +407,8 @@ do_mb_tests (const struct test_s *test)
   return 0;
 }
 
-int
-main (void)
+static int
+do_test (void)
 {
   size_t i;
   int ret = 0;
@@ -416,20 +417,17 @@ main (void)
 
   for (i = 0; i < sizeof (tests) / sizeof (tests[0]); ++i)
     {
-      if (setlocale (LC_ALL, "de_DE.ISO-8859-1") == NULL)
-	{
-	  puts ("setlocale de_DE.ISO-8859-1 failed");
-	  ret = 1;
-	}
+      xsetlocale (LC_ALL, "de_DE.ISO-8859-1");
       ret |= do_one_test (&tests[i], "");
-      if (setlocale (LC_ALL, "de_DE.UTF-8") == NULL)
-	{
-	  puts ("setlocale de_DE.UTF-8 failed");
-	  ret = 1;
-	}
+      xsetlocale (LC_ALL, "de_DE.UTF-8");
+      ret |= do_one_test (&tests[i], "UTF-8 ");
+      ret |= do_mb_tests (&tests[i]);
+      xsetlocale (LC_ALL, "C.UTF-8");
       ret |= do_one_test (&tests[i], "UTF-8 ");
       ret |= do_mb_tests (&tests[i]);
     }
 
   return ret;
 }
+
+#include <support/test-driver.c>
diff --git a/posix/bug-regex4.c b/posix/bug-regex4.c
index 86901ec..3b63d7d 100644
--- a/posix/bug-regex4.c
+++ b/posix/bug-regex4.c
@@ -31,6 +31,7 @@ main (void)
 
   memset (&regex, '\0', sizeof (regex));
 
+  printf ("INFO: Checking C.\n");
   setlocale (LC_ALL, "C");
 
   s = re_compile_pattern ("ab[cde]", 7, &regex);
@@ -54,5 +55,29 @@ main (void)
 	puts (" -> OK");
     }
 
+  printf ("INFO: Checking C.UTF-8.\n");
+  setlocale (LC_ALL, "C.UTF-8");
+
+  s = re_compile_pattern ("ab[cde]", 7, &regex);
+  if (s != NULL)
+    {
+      puts ("re_compile_pattern returned non-NULL value");
+      result = 1;
+    }
+  else
+    {
+      match[0] = re_search_2 (&regex, "xyabez", 6, "", 0, 1, 5, NULL, 6);
+      match[1] = re_search_2 (&regex, NULL, 0, "abc", 3, 0, 3, NULL, 3);
+      match[2] = re_search_2 (&regex, "xya", 3, "bd", 2, 2, 3, NULL, 5);
+      if (match[0] != 2 || match[1] != 0 || match[2] != 2)
+	{
+	  printf ("re_search_2 returned %d,%d,%d, expected 2,0,2\n",
+		  match[0], match[1], match[2]);
+	  result = 1;
+	}
+      else
+	puts (" -> OK");
+    }
+
   return result;
 }
diff --git a/posix/bug-regex6.c b/posix/bug-regex6.c
index 324bd51..145f007 100644
--- a/posix/bug-regex6.c
+++ b/posix/bug-regex6.c
@@ -29,7 +29,7 @@ main (int argc, char *argv[])
   regex_t re;
   regmatch_t mat[10];
   int i, j, ret = 0;
-  const char *locales[] = { "C", "de_DE.UTF-8" };
+  const char *locales[] = { "C", "C.UTF-8", "de_DE.UTF-8" };
   const char *string = "http://www.regex.com/pattern/matching.html#intro";
   regmatch_t expect[10] = {
     { 0, 48 }, { 0, 5 }, { 0, 4 }, { 5, 20 }, { 7, 20 }, { 20, 42 },
diff --git a/posix/transbug.c b/posix/transbug.c
index d0983b4..b240177 100644
--- a/posix/transbug.c
+++ b/posix/transbug.c
@@ -116,16 +116,32 @@ do_test (void)
   static const char lower[] = "[[:lower:]]+";
   static const char upper[] = "[[:upper:]]+";
   struct re_registers regs[4];
+  int result = 0;
 
+#define CHECK(exp) \
+  if (exp) { puts (#exp); result = 1; }
+
+  printf ("INFO: Checking C.\n");
   setlocale (LC_ALL, "C");
 
   (void) re_set_syntax (RE_SYNTAX_GNU_AWK);
 
-  int result;
-#define CHECK(exp) \
-  if (exp) { puts (#exp); result = 1; }
+  result |= run_test (lower, regs);
+  result |= run_test (upper, &regs[2]);
+  if (! result)
+    {
+      CHECK (regs[0].start[0] != regs[2].start[0]);
+      CHECK (regs[0].end[0] != regs[2].end[0]);
+      CHECK (regs[1].start[0] != regs[3].start[0]);
+      CHECK (regs[1].end[0] != regs[3].end[0]);
+    }
+
+  printf ("INFO: Checking C.UTF-8.\n");
+  setlocale (LC_ALL, "C.UTF-8");
+
+  (void) re_set_syntax (RE_SYNTAX_GNU_AWK);
 
-  result = run_test (lower, regs);
+  result |= run_test (lower, regs);
   result |= run_test (upper, &regs[2]);
   if (! result)
     {
diff --git a/posix/tst-fnmatch.input b/posix/tst-fnmatch.input
index 9d07168..837fa2c 100644
--- a/posix/tst-fnmatch.input
+++ b/posix/tst-fnmatch.input
@@ -472,6 +472,397 @@ C		"\\"			"[Z-\\]]"	       0
 C		"]"			"[Z-\\]]"	       0
 C		"-"			"[Z-\\]]"	       NOMATCH
 
+# B.6 004(C)
+C.UTF-8		 "!#%+,-./01234567889"	"!#%+,-./01234567889"  0
+C.UTF-8		 ":;=@ABCDEFGHIJKLMNO"	":;=@ABCDEFGHIJKLMNO"  0
+C.UTF-8		 "PQRSTUVWXYZ]abcdefg"	"PQRSTUVWXYZ]abcdefg"  0
+C.UTF-8		 "hijklmnopqrstuvwxyz"	"hijklmnopqrstuvwxyz"  0
+C.UTF-8		 "^_{}~"		"^_{}~"		       0
+
+# B.6 005(C)
+C.UTF-8		 "\"$&'()"		"\\\"\\$\\&\\'\\(\\)"  0
+C.UTF-8		 "*?[\\`|"		"\\*\\?\\[\\\\\\`\\|"  0
+C.UTF-8		 "<>"			"\\<\\>"	       0
+
+# B.6 006(C)
+C.UTF-8		 "?*["			"[?*[][?*[][?*[]"      0
+C.UTF-8		 "a/b"			"?/b"		       0
+
+# B.6 007(C)
+C.UTF-8		 "a/b"			"a?b"		       0
+C.UTF-8		 "a/b"			"a/?"		       0
+C.UTF-8		 "aa/b"			"?/b"		       NOMATCH
+C.UTF-8		 "aa/b"			"a?b"		       NOMATCH
+C.UTF-8		 "a/bb"			"a/?"		       NOMATCH
+
+# B.6 009(C)
+C.UTF-8		 "abc"			"[abc]"		       NOMATCH
+C.UTF-8		 "x"			"[abc]"		       NOMATCH
+C.UTF-8		 "a"			"[abc]"		       0
+C.UTF-8		 "["			"[[abc]"	       0
+C.UTF-8		 "a"			"[][abc]"	       0
+C.UTF-8		 "a]"			"[]a]]"		       0
+
+# B.6 010(C)
+C.UTF-8		 "xyz"			"[!abc]"	       NOMATCH
+C.UTF-8		 "x"			"[!abc]"	       0
+C.UTF-8		 "a"			"[!abc]"	       NOMATCH
+
+# B.6 011(C)
+C.UTF-8		 "]"			"[][abc]"	       0
+C.UTF-8		 "abc]"			"[][abc]"	       NOMATCH
+C.UTF-8		 "[]abc"		"[][]abc"	       NOMATCH
+C.UTF-8		 "]"			"[!]]"		       NOMATCH
+C.UTF-8		 "aa]"			"[!]a]"		       NOMATCH
+C.UTF-8		 "]"			"[!a]"		       0
+C.UTF-8		 "]]"			"[!a]]"		       0
+
+# B.6 012(C)
+C.UTF-8		 "a"			"[[.a.]]"	       0
+C.UTF-8		 "-"			"[[.-.]]"	       0
+C.UTF-8		 "-"			"[[.-.][.].]]"	       0
+C.UTF-8		 "-"			"[[.].][.-.]]"	       0
+C.UTF-8		 "-"			"[[.-.][=u=]]"	       0
+C.UTF-8		 "-"			"[[.-.][:alpha:]]"     0
+C.UTF-8		 "a"			"[![.a.]]"	       NOMATCH
+
+# B.6 013(C)
+C.UTF-8		 "a"			"[[.b.]]"	       NOMATCH
+C.UTF-8		 "a"			"[[.b.][.c.]]"	       NOMATCH
+C.UTF-8		 "a"			"[[.b.][=b=]]"	       NOMATCH
+
+
+# B.6 015(C)
+C.UTF-8		 "a"			"[[=a=]]"	       0
+C.UTF-8		 "b"			"[[=a=]b]"	       0
+C.UTF-8		 "b"			"[[=a=][=b=]]"	       0
+C.UTF-8		 "a"			"[[=a=][=b=]]"	       0
+C.UTF-8		 "a"			"[[=a=][.b.]]"	       0
+C.UTF-8		 "a"			"[[=a=][:digit:]]"     0
+
+# B.6 016(C)
+C.UTF-8		 "="			"[[=a=]b]"	       NOMATCH
+C.UTF-8		 "]"			"[[=a=]b]"	       NOMATCH
+C.UTF-8		 "a"			"[[=b=][=c=]]"	       NOMATCH
+C.UTF-8		 "a"			"[[=b=][.].]]"	       NOMATCH
+C.UTF-8		 "a"			"[[=b=][:digit:]]"     NOMATCH
+
+# B.6 017(C)
+C.UTF-8		 "a"			"[[:alnum:]]"	       0
+C.UTF-8		 "a"			"[![:alnum:]]"	       NOMATCH
+C.UTF-8		 "-"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "a]a"			"[[:alnum:]]a"	       NOMATCH
+C.UTF-8		 "-"			"[[:alnum:]-]"	       0
+C.UTF-8		 "aa"			"[[:alnum:]]a"	       0
+C.UTF-8		 "-"			"[![:alnum:]]"	       0
+C.UTF-8		 "]"			"[!][:alnum:]]"	       NOMATCH
+C.UTF-8		 "["			"[![:alnum:][]"	       NOMATCH
+C.UTF-8		 "a"			"[[:alnum:]]"	       0
+C.UTF-8		 "b"			"[[:alnum:]]"	       0
+C.UTF-8		 "c"			"[[:alnum:]]"	       0
+C.UTF-8		 "d"			"[[:alnum:]]"	       0
+C.UTF-8		 "e"			"[[:alnum:]]"	       0
+C.UTF-8		 "f"			"[[:alnum:]]"	       0
+C.UTF-8		 "g"			"[[:alnum:]]"	       0
+C.UTF-8		 "h"			"[[:alnum:]]"	       0
+C.UTF-8		 "i"			"[[:alnum:]]"	       0
+C.UTF-8		 "j"			"[[:alnum:]]"	       0
+C.UTF-8		 "k"			"[[:alnum:]]"	       0
+C.UTF-8		 "l"			"[[:alnum:]]"	       0
+C.UTF-8		 "m"			"[[:alnum:]]"	       0
+C.UTF-8		 "n"			"[[:alnum:]]"	       0
+C.UTF-8		 "o"			"[[:alnum:]]"	       0
+C.UTF-8		 "p"			"[[:alnum:]]"	       0
+C.UTF-8		 "q"			"[[:alnum:]]"	       0
+C.UTF-8		 "r"			"[[:alnum:]]"	       0
+C.UTF-8		 "s"			"[[:alnum:]]"	       0
+C.UTF-8		 "t"			"[[:alnum:]]"	       0
+C.UTF-8		 "u"			"[[:alnum:]]"	       0
+C.UTF-8		 "v"			"[[:alnum:]]"	       0
+C.UTF-8		 "w"			"[[:alnum:]]"	       0
+C.UTF-8		 "x"			"[[:alnum:]]"	       0
+C.UTF-8		 "y"			"[[:alnum:]]"	       0
+C.UTF-8		 "z"			"[[:alnum:]]"	       0
+C.UTF-8		 "A"			"[[:alnum:]]"	       0
+C.UTF-8		 "B"			"[[:alnum:]]"	       0
+C.UTF-8		 "C"			"[[:alnum:]]"	       0
+C.UTF-8		 "D"			"[[:alnum:]]"	       0
+C.UTF-8		 "E"			"[[:alnum:]]"	       0
+C.UTF-8		 "F"			"[[:alnum:]]"	       0
+C.UTF-8		 "G"			"[[:alnum:]]"	       0
+C.UTF-8		 "H"			"[[:alnum:]]"	       0
+C.UTF-8		 "I"			"[[:alnum:]]"	       0
+C.UTF-8		 "J"			"[[:alnum:]]"	       0
+C.UTF-8		 "K"			"[[:alnum:]]"	       0
+C.UTF-8		 "L"			"[[:alnum:]]"	       0
+C.UTF-8		 "M"			"[[:alnum:]]"	       0
+C.UTF-8		 "N"			"[[:alnum:]]"	       0
+C.UTF-8		 "O"			"[[:alnum:]]"	       0
+C.UTF-8		 "P"			"[[:alnum:]]"	       0
+C.UTF-8		 "Q"			"[[:alnum:]]"	       0
+C.UTF-8		 "R"			"[[:alnum:]]"	       0
+C.UTF-8		 "S"			"[[:alnum:]]"	       0
+C.UTF-8		 "T"			"[[:alnum:]]"	       0
+C.UTF-8		 "U"			"[[:alnum:]]"	       0
+C.UTF-8		 "V"			"[[:alnum:]]"	       0
+C.UTF-8		 "W"			"[[:alnum:]]"	       0
+C.UTF-8		 "X"			"[[:alnum:]]"	       0
+C.UTF-8		 "Y"			"[[:alnum:]]"	       0
+C.UTF-8		 "Z"			"[[:alnum:]]"	       0
+C.UTF-8		 "0"			"[[:alnum:]]"	       0
+C.UTF-8		 "1"			"[[:alnum:]]"	       0
+C.UTF-8		 "2"			"[[:alnum:]]"	       0
+C.UTF-8		 "3"			"[[:alnum:]]"	       0
+C.UTF-8		 "4"			"[[:alnum:]]"	       0
+C.UTF-8		 "5"			"[[:alnum:]]"	       0
+C.UTF-8		 "6"			"[[:alnum:]]"	       0
+C.UTF-8		 "7"			"[[:alnum:]]"	       0
+C.UTF-8		 "8"			"[[:alnum:]]"	       0
+C.UTF-8		 "9"			"[[:alnum:]]"	       0
+C.UTF-8		 "!"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "#"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "%"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "+"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 ","			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "-"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "."			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "/"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 ":"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 ";"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "="			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "@"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "["			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "\\"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "]"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "^"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "_"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "{"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "}"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "~"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "\""			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "$"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "&"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "'"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "("			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 ")"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "*"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "?"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "`"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "|"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "<"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 ">"			"[[:alnum:]]"	       NOMATCH
+C.UTF-8		 "\t"			"[[:cntrl:]]"	       0
+C.UTF-8		 "t"			"[[:cntrl:]]"	       NOMATCH
+C.UTF-8		 "t"			"[[:lower:]]"	       0
+C.UTF-8		 "\t"			"[[:lower:]]"	       NOMATCH
+C.UTF-8		 "T"			"[[:lower:]]"	       NOMATCH
+C.UTF-8		 "\t"			"[[:space:]]"	       0
+C.UTF-8		 "t"			"[[:space:]]"	       NOMATCH
+C.UTF-8		 "t"			"[[:alpha:]]"	       0
+C.UTF-8		 "\t"			"[[:alpha:]]"	       NOMATCH
+C.UTF-8		 "0"			"[[:digit:]]"	       0
+C.UTF-8		 "\t"			"[[:digit:]]"	       NOMATCH
+C.UTF-8		 "t"			"[[:digit:]]"	       NOMATCH
+C.UTF-8		 "\t"			"[[:print:]]"	       NOMATCH
+C.UTF-8		 "t"			"[[:print:]]"	       0
+C.UTF-8		 "T"			"[[:upper:]]"	       0
+C.UTF-8		 "\t"			"[[:upper:]]"	       NOMATCH
+C.UTF-8		 "t"			"[[:upper:]]"	       NOMATCH
+C.UTF-8		 "\t"			"[[:blank:]]"	       0
+C.UTF-8		 "t"			"[[:blank:]]"	       NOMATCH
+C.UTF-8		 "\t"			"[[:graph:]]"	       NOMATCH
+C.UTF-8		 "t"			"[[:graph:]]"	       0
+C.UTF-8		 "."			"[[:punct:]]"	       0
+C.UTF-8		 "t"			"[[:punct:]]"	       NOMATCH
+C.UTF-8		 "\t"			"[[:punct:]]"	       NOMATCH
+C.UTF-8		 "0"			"[[:xdigit:]]"	       0
+C.UTF-8		 "\t"			"[[:xdigit:]]"	       NOMATCH
+C.UTF-8		 "a"			"[[:xdigit:]]"	       0
+C.UTF-8		 "A"			"[[:xdigit:]]"	       0
+C.UTF-8		 "t"			"[[:xdigit:]]"	       NOMATCH
+C.UTF-8		 "a"			"[[alpha]]"	       NOMATCH
+C.UTF-8		 "a"			"[[alpha:]]"	       NOMATCH
+C.UTF-8		 "a]"			"[[alpha]]"	       0
+C.UTF-8		 "a]"			"[[alpha:]]"	       0
+C.UTF-8		 "a"			"[[:alpha:][.b.]]"     0
+C.UTF-8		 "a"			"[[:alpha:][=b=]]"     0
+C.UTF-8		 "a"			"[[:alpha:][:digit:]]" 0
+C.UTF-8		 "a"			"[[:digit:][:alpha:]]" 0
+
+# B.6 018(C)
+C.UTF-8		 "a"			"[a-c]"		       0
+C.UTF-8		 "b"			"[a-c]"		       0
+C.UTF-8		 "c"			"[a-c]"		       0
+C.UTF-8		 "a"			"[b-c]"		       NOMATCH
+C.UTF-8		 "d"			"[b-c]"		       NOMATCH
+C.UTF-8		 "B"			"[a-c]"		       NOMATCH
+C.UTF-8		 "b"			"[A-C]"		       NOMATCH
+C.UTF-8		 ""			"[a-c]"		       NOMATCH
+C.UTF-8		 "as"			"[a-ca-z]"	       NOMATCH
+C.UTF-8		 "a"			"[[.a.]-c]"	       0
+C.UTF-8		 "a"			"[a-[.c.]]"	       0
+C.UTF-8		 "a"			"[[.a.]-[.c.]]"	       0
+C.UTF-8		 "b"			"[[.a.]-c]"	       0
+C.UTF-8		 "b"			"[a-[.c.]]"	       0
+C.UTF-8		 "b"			"[[.a.]-[.c.]]"	       0
+C.UTF-8		 "c"			"[[.a.]-c]"	       0
+C.UTF-8		 "c"			"[a-[.c.]]"	       0
+C.UTF-8		 "c"			"[[.a.]-[.c.]]"	       0
+C.UTF-8		 "d"			"[[.a.]-c]"	       NOMATCH
+C.UTF-8		 "d"			"[a-[.c.]]"	       NOMATCH
+C.UTF-8		 "d"			"[[.a.]-[.c.]]"	       NOMATCH
+
+# B.6 019(C)
+C.UTF-8		 "a"			"[c-a]"		       NOMATCH
+C.UTF-8		 "a"			"[[.c.]-a]"	       NOMATCH
+C.UTF-8		 "a"			"[c-[.a.]]"	       NOMATCH
+C.UTF-8		 "a"			"[[.c.]-[.a.]]"	       NOMATCH
+C.UTF-8		 "c"			"[c-a]"		       NOMATCH
+C.UTF-8		 "c"			"[[.c.]-a]"	       NOMATCH
+C.UTF-8		 "c"			"[c-[.a.]]"	       NOMATCH
+C.UTF-8		 "c"			"[[.c.]-[.a.]]"	       NOMATCH
+
+# B.6 020(C)
+C.UTF-8		 "a"			"[a-c0-9]"	       0
+C.UTF-8		 "d"			"[a-c0-9]"	       NOMATCH
+C.UTF-8		 "B"			"[a-c0-9]"	       NOMATCH
+
+# B.6 021(C)
+C.UTF-8		 "-"			"[-a]"		       0
+C.UTF-8		 "a"			"[-b]"		       NOMATCH
+C.UTF-8		 "-"			"[!-a]"		       NOMATCH
+C.UTF-8		 "a"			"[!-b]"		       0
+C.UTF-8		 "-"			"[a-c-0-9]"	       0
+C.UTF-8		 "b"			"[a-c-0-9]"	       0
+C.UTF-8		 "a:"			"a[0-9-a]"	       NOMATCH
+C.UTF-8		 "a:"			"a[09-a]"	       0
+
+# B.6 024(C)
+C.UTF-8		 ""			"*"		       0
+C.UTF-8		 "asd/sdf"		"*"		       0
+
+# B.6 025(C)
+C.UTF-8		 "as"			"[a-c][a-z]"	       0
+C.UTF-8		 "as"			"??"		       0
+
+# B.6 026(C)
+C.UTF-8		 "asd/sdf"		"as*df"		       0
+C.UTF-8		 "asd/sdf"		"as*"		       0
+C.UTF-8		 "asd/sdf"		"*df"		       0
+C.UTF-8		 "asd/sdf"		"as*dg"		       NOMATCH
+C.UTF-8		 "asdf"			"as*df"		       0
+C.UTF-8		 "asdf"			"as*df?"	       NOMATCH
+C.UTF-8		 "asdf"			"as*??"		       0
+C.UTF-8		 "asdf"			"a*???"		       0
+C.UTF-8		 "asdf"			"*????"		       0
+C.UTF-8		 "asdf"			"????*"		       0
+C.UTF-8		 "asdf"			"??*?"		       0
+
+# B.6 027(C)
+C.UTF-8		 "/"			"/"		       0
+C.UTF-8		 "/"			"/*"		       0
+C.UTF-8		 "/"			"*/"		       0
+C.UTF-8		 "/"			"/?"		       NOMATCH
+C.UTF-8		 "/"			"?/"		       NOMATCH
+C.UTF-8		 "/"			"?"		       0
+C.UTF-8		 "."			"?"		       0
+C.UTF-8		 "/."			"??"		       0
+C.UTF-8		 "/"			"[!a-c]"	       0
+C.UTF-8		 "."			"[!a-c]"	       0
+
+# B.6 029(C)
+C.UTF-8		 "/"			"/"		       0       PATHNAME
+C.UTF-8		 "//"			"//"		       0       PATHNAME
+C.UTF-8		 "/.a"			"/*"		       0       PATHNAME
+C.UTF-8		 "/.a"			"/?a"		       0       PATHNAME
+C.UTF-8		 "/.a"			"/[!a-z]a"	       0       PATHNAME
+C.UTF-8		 "/.a/.b"		"/*/?b"		       0       PATHNAME
+
+# B.6 030(C)
+C.UTF-8		 "/"			"?"		       NOMATCH PATHNAME
+C.UTF-8		 "/"			"*"		       NOMATCH PATHNAME
+C.UTF-8		 "a/b"			"a?b"		       NOMATCH PATHNAME
+C.UTF-8		 "/.a/.b"		"/*b"		       NOMATCH PATHNAME
+
+# B.6 031(C)
+C.UTF-8		 "/$"			"\\/\\$"	       0
+C.UTF-8		 "/["			"\\/\\["	       0
+C.UTF-8		 "/["			"\\/["		       0
+C.UTF-8		 "/[]"			"\\/\\[]"	       0
+
+# B.6 032(C)
+C.UTF-8		 "/$"			"\\/\\$"	       NOMATCH NOESCAPE
+C.UTF-8		 "/\\$"			"\\/\\$"	       NOMATCH NOESCAPE
+C.UTF-8		 "\\/\\$"		"\\/\\$"	       0       NOESCAPE
+
+# B.6 033(C)
+C.UTF-8		 ".asd"			".*"		       0       PERIOD
+C.UTF-8		 "/.asd"		"*"		       0       PERIOD
+C.UTF-8		 "/as/.df"		"*/?*f"		       0       PERIOD
+C.UTF-8		 "..asd"		".[!a-z]*"	       0       PERIOD
+
+# B.6 034(C)
+C.UTF-8		 ".asd"			"*"		       NOMATCH PERIOD
+C.UTF-8		 ".asd"			"?asd"		       NOMATCH PERIOD
+C.UTF-8		 ".asd"			"[!a-z]*"	       NOMATCH PERIOD
+
+# B.6 035(C)
+C.UTF-8		 "/."			"/."		       0       PATHNAME|PERIOD
+C.UTF-8		 "/.a./.b."		"/.*/.*"	       0       PATHNAME|PERIOD
+C.UTF-8		 "/.a./.b."		"/.??/.??"	       0       PATHNAME|PERIOD
+
+# B.6 036(C)
+C.UTF-8		 "/."			"*"		       NOMATCH PATHNAME|PERIOD
+C.UTF-8		 "/."			"/*"		       NOMATCH PATHNAME|PERIOD
+C.UTF-8		 "/."			"/?"		       NOMATCH PATHNAME|PERIOD
+C.UTF-8		 "/."			"/[!a-z]"	       NOMATCH PATHNAME|PERIOD
+C.UTF-8		 "/a./.b."		"/*/*"		       NOMATCH PATHNAME|PERIOD
+C.UTF-8		 "/a./.b."		"/??/???"	       NOMATCH PATHNAME|PERIOD
+
+# Some home-grown tests.
+C.UTF-8		"foobar"		"foo*[abc]z"	       NOMATCH
+C.UTF-8		"foobaz"		"foo*[abc][xyz]"       0
+C.UTF-8		"foobaz"		"foo?*[abc][xyz]"      0
+C.UTF-8		"foobaz"		"foo?*[abc][x/yz]"     0
+C.UTF-8		"foobaz"		"foo?*[abc]/[xyz]"     NOMATCH PATHNAME
+C.UTF-8		"a"			"a/"                   NOMATCH PATHNAME
+C.UTF-8		"a/"			"a"		       NOMATCH PATHNAME
+C.UTF-8		"//a"			"/a"		       NOMATCH PATHNAME
+C.UTF-8		"/a"			"//a"		       NOMATCH PATHNAME
+C.UTF-8		"az"			"[a-]z"		       0
+C.UTF-8		"bz"			"[ab-]z"	       0
+C.UTF-8		"cz"			"[ab-]z"	       NOMATCH
+C.UTF-8		"-z"			"[ab-]z"	       0
+C.UTF-8		"az"			"[-a]z"		       0
+C.UTF-8		"bz"			"[-ab]z"	       0
+C.UTF-8		"cz"			"[-ab]z"	       NOMATCH
+C.UTF-8		"-z"			"[-ab]z"	       0
+C.UTF-8		"\\"			"[\\\\-a]"	       0
+C.UTF-8		"_"			"[\\\\-a]"	       0
+C.UTF-8		"a"			"[\\\\-a]"	       0
+C.UTF-8		"-"			"[\\\\-a]"	       NOMATCH
+C.UTF-8		"\\"			"[\\]-a]"	       NOMATCH
+C.UTF-8		"_"			"[\\]-a]"	       0
+C.UTF-8		"a"			"[\\]-a]"	       0
+C.UTF-8		"]"			"[\\]-a]"	       0
+C.UTF-8		"-"			"[\\]-a]"	       NOMATCH
+C.UTF-8		"\\"			"[!\\\\-a]"	       NOMATCH
+C.UTF-8		"_"			"[!\\\\-a]"	       NOMATCH
+C.UTF-8		"a"			"[!\\\\-a]"	       NOMATCH
+C.UTF-8		"-"			"[!\\\\-a]"	       0
+C.UTF-8		"!"			"[\\!-]"	       0
+C.UTF-8		"-"			"[\\!-]"	       0
+C.UTF-8		"\\"			"[\\!-]"	       NOMATCH
+C.UTF-8		"Z"			"[Z-\\\\]"	       0
+C.UTF-8		"["			"[Z-\\\\]"	       0
+C.UTF-8		"\\"			"[Z-\\\\]"	       0
+C.UTF-8		"-"			"[Z-\\\\]"	       NOMATCH
+C.UTF-8		"Z"			"[Z-\\]]"	       0
+C.UTF-8		"["			"[Z-\\]]"	       0
+C.UTF-8		"\\"			"[Z-\\]]"	       0
+C.UTF-8		"]"			"[Z-\\]]"	       0
+C.UTF-8		"-"			"[Z-\\]]"	       NOMATCH
+
 # Following are tests outside the scope of IEEE 2003.2 since they are using
 # locales other than the C locale.  The main focus of the tests is on the
 # handling of ranges and the recognition of character (vs bytes).
@@ -677,7 +1068,6 @@ C		 "x/y"			"*"		       0       PATHNAME|LEADING_DIR
 C		 "x/y/z"		"*"		       0       PATHNAME|LEADING_DIR
 C		 "x"			"*x"		       0       PATHNAME|LEADING_DIR
 
-en_US.UTF-8	 "\366.csv"		"*.csv"                0
 C		 "x/y"			"*x"		       0       PATHNAME|LEADING_DIR
 C		 "x/y/z"		"*x"		       0       PATHNAME|LEADING_DIR
 C		 "x"			"x*"		       0       PATHNAME|LEADING_DIR
@@ -693,6 +1083,33 @@ C		 "x"			"x?y"		       NOMATCH PATHNAME|LEADING_DIR
 C		 "x/y"			"x?y"		       NOMATCH PATHNAME|LEADING_DIR
 C		 "x/y/z"		"x?y"		       NOMATCH PATHNAME|LEADING_DIR
 
+# Duplicate the "Test of GNU extensions." tests but for C.UTF-8.
+C.UTF-8		 "x"			"x"		       0       PATHNAME|LEADING_DIR
+C.UTF-8		 "x/y"			"x"		       0       PATHNAME|LEADING_DIR
+C.UTF-8		 "x/y/z"		"x"		       0       PATHNAME|LEADING_DIR
+C.UTF-8		 "x"			"*"		       0       PATHNAME|LEADING_DIR
+C.UTF-8		 "x/y"			"*"		       0       PATHNAME|LEADING_DIR
+C.UTF-8		 "x/y/z"		"*"		       0       PATHNAME|LEADING_DIR
+C.UTF-8		 "x"			"*x"		       0       PATHNAME|LEADING_DIR
+
+C.UTF-8		 "x/y"			"*x"		       0       PATHNAME|LEADING_DIR
+C.UTF-8		 "x/y/z"		"*x"		       0       PATHNAME|LEADING_DIR
+C.UTF-8		 "x"			"x*"		       0       PATHNAME|LEADING_DIR
+C.UTF-8		 "x/y"			"x*"		       0       PATHNAME|LEADING_DIR
+C.UTF-8		 "x/y/z"		"x*"		       0       PATHNAME|LEADING_DIR
+C.UTF-8		 "x"			"a"		       NOMATCH PATHNAME|LEADING_DIR
+C.UTF-8		 "x/y"			"a"		       NOMATCH PATHNAME|LEADING_DIR
+C.UTF-8		 "x/y/z"		"a"		       NOMATCH PATHNAME|LEADING_DIR
+C.UTF-8		 "x"			"x/y"		       NOMATCH PATHNAME|LEADING_DIR
+C.UTF-8		 "x/y"			"x/y"		       0       PATHNAME|LEADING_DIR
+C.UTF-8		 "x/y/z"		"x/y"		       0       PATHNAME|LEADING_DIR
+C.UTF-8		 "x"			"x?y"		       NOMATCH PATHNAME|LEADING_DIR
+C.UTF-8		 "x/y"			"x?y"		       NOMATCH PATHNAME|LEADING_DIR
+C.UTF-8		 "x/y/z"		"x?y"		       NOMATCH PATHNAME|LEADING_DIR
+
+# Bug 14185
+en_US.UTF-8	 "\366.csv"		"*.csv"                0
+
 # ksh style matching.
 C		"abcd"			"?@(a|b)*@(c)d"	       0       EXTMATCH
 C		"/dev/udp/129.22.8.102/45" "/dev/@(tcp|udp)/*/*" 0     PATHNAME|EXTMATCH
@@ -822,3 +1239,133 @@ C		""			""		       0
 C		""			""		       0       EXTMATCH
 C		""			"*([abc])"	       0       EXTMATCH
 C		""			"?([abc])"	       0       EXTMATCH
+
+# Duplicate the "ksh style matching." for C.UTF-8.
+C.UTF-8		"abcd"			"?@(a|b)*@(c)d"	       0       EXTMATCH
+C.UTF-8		"/dev/udp/129.22.8.102/45" "/dev/@(tcp|udp)/*/*" 0     PATHNAME|EXTMATCH
+C.UTF-8		"12"			"[1-9]*([0-9])"        0       EXTMATCH
+C.UTF-8		"12abc"			"[1-9]*([0-9])"        NOMATCH EXTMATCH
+C.UTF-8		"1"			"[1-9]*([0-9])"	       0       EXTMATCH
+C.UTF-8		"07"			"+([0-7])"	       0       EXTMATCH
+C.UTF-8		"0377"			"+([0-7])"	       0       EXTMATCH
+C.UTF-8		"09"			"+([0-7])"	       NOMATCH EXTMATCH
+C.UTF-8		"paragraph"		"para@(chute|graph)"   0       EXTMATCH
+C.UTF-8		"paramour"		"para@(chute|graph)"   NOMATCH EXTMATCH
+C.UTF-8		"para991"		"para?([345]|99)1"     0       EXTMATCH
+C.UTF-8		"para381"		"para?([345]|99)1"     NOMATCH EXTMATCH
+C.UTF-8		"paragraph"		"para*([0-9])"	       NOMATCH EXTMATCH
+C.UTF-8		"para"			"para*([0-9])"	       0       EXTMATCH
+C.UTF-8		"para13829383746592"	"para*([0-9])"	       0       EXTMATCH
+C.UTF-8		"paragraph"		"para+([0-9])"	       NOMATCH EXTMATCH
+C.UTF-8		"para"			"para+([0-9])"	       NOMATCH EXTMATCH
+C.UTF-8		"para987346523"		"para+([0-9])"	       0       EXTMATCH
+C.UTF-8		"paragraph"		"para!(*.[0-9])"       0       EXTMATCH
+C.UTF-8		"para.38"		"para!(*.[0-9])"       0       EXTMATCH
+C.UTF-8		"para.graph"		"para!(*.[0-9])"       0       EXTMATCH
+C.UTF-8		"para39"		"para!(*.[0-9])"       0       EXTMATCH
+C.UTF-8		""			"*(0|1|3|5|7|9)"       0       EXTMATCH
+C.UTF-8		"137577991"		"*(0|1|3|5|7|9)"       0       EXTMATCH
+C.UTF-8		"2468"			"*(0|1|3|5|7|9)"       NOMATCH EXTMATCH
+C.UTF-8		"1358"			"*(0|1|3|5|7|9)"       NOMATCH EXTMATCH
+C.UTF-8		"file.c"		"*.c?(c)"	       0       EXTMATCH
+C.UTF-8		"file.C"		"*.c?(c)"	       NOMATCH EXTMATCH
+C.UTF-8		"file.cc"		"*.c?(c)"	       0       EXTMATCH
+C.UTF-8		"file.ccc"		"*.c?(c)"	       NOMATCH EXTMATCH
+C.UTF-8		"parse.y"		"!(*.c|*.h|Makefile.in|config*|README)" 0 EXTMATCH
+C.UTF-8		"shell.c"		"!(*.c|*.h|Makefile.in|config*|README)" NOMATCH EXTMATCH
+C.UTF-8		"Makefile"		"!(*.c|*.h|Makefile.in|config*|README)" 0 EXTMATCH
+C.UTF-8		"VMS.FILE;1"		"*\;[1-9]*([0-9])"     0       EXTMATCH
+C.UTF-8		"VMS.FILE;0"		"*\;[1-9]*([0-9])"     NOMATCH EXTMATCH
+C.UTF-8		"VMS.FILE;"		"*\;[1-9]*([0-9])"     NOMATCH EXTMATCH
+C.UTF-8		"VMS.FILE;139"		"*\;[1-9]*([0-9])"     0       EXTMATCH
+C.UTF-8		"VMS.FILE;1N"		"*\;[1-9]*([0-9])"     NOMATCH EXTMATCH
+C.UTF-8		"abcfefg"		"ab**(e|f)"	       0       EXTMATCH
+C.UTF-8		"abcfefg"		"ab**(e|f)g"	       0       EXTMATCH
+C.UTF-8		"ab"			"ab*+(e|f)"	       NOMATCH EXTMATCH
+C.UTF-8		"abef"			"ab***ef"	       0       EXTMATCH
+C.UTF-8		"abef"			"ab**"		       0       EXTMATCH
+C.UTF-8		"fofo"			"*(f*(o))"	       0       EXTMATCH
+C.UTF-8		"ffo"			"*(f*(o))"	       0       EXTMATCH
+C.UTF-8		"foooofo"		"*(f*(o))"	       0       EXTMATCH
+C.UTF-8		"foooofof"		"*(f*(o))"	       0       EXTMATCH
+C.UTF-8		"fooofoofofooo"		"*(f*(o))"	       0       EXTMATCH
+C.UTF-8		"foooofof"		"*(f+(o))"	       NOMATCH EXTMATCH
+C.UTF-8		"xfoooofof"		"*(f*(o))"	       NOMATCH EXTMATCH
+C.UTF-8		"foooofofx"		"*(f*(o))"	       NOMATCH EXTMATCH
+C.UTF-8		"ofxoofxo"		"*(*(of*(o)x)o)"       0       EXTMATCH
+C.UTF-8		"ofooofoofofooo"	"*(f*(o))"	       NOMATCH EXTMATCH
+C.UTF-8		"foooxfooxfoxfooox"	"*(f*(o)x)"	       0       EXTMATCH
+C.UTF-8		"foooxfooxofoxfooox"	"*(f*(o)x)"	       NOMATCH EXTMATCH
+C.UTF-8		"foooxfooxfxfooox"	"*(f*(o)x)"	       0       EXTMATCH
+C.UTF-8		"ofxoofxo"		"*(*(of*(o)x)o)"       0       EXTMATCH
+C.UTF-8		"ofoooxoofxo"		"*(*(of*(o)x)o)"       0       EXTMATCH
+C.UTF-8		"ofoooxoofxoofoooxoofxo" "*(*(of*(o)x)o)"      0       EXTMATCH
+C.UTF-8		"ofoooxoofxoofoooxoofxoo" "*(*(of*(o)x)o)"     0       EXTMATCH
+C.UTF-8		"ofoooxoofxoofoooxoofxofo" "*(*(of*(o)x)o)"    NOMATCH EXTMATCH
+C.UTF-8		"ofoooxoofxoofoooxoofxooofxofxo" "*(*(of*(o)x)o)" 0    EXTMATCH
+C.UTF-8		"aac"			"*(@(a))a@(c)"	       0       EXTMATCH
+C.UTF-8		"ac"			"*(@(a))a@(c)"	       0       EXTMATCH
+C.UTF-8		"c"			"*(@(a))a@(c)"	       NOMATCH EXTMATCH
+C.UTF-8		"aaac"			"*(@(a))a@(c)"	       0       EXTMATCH
+C.UTF-8		"baaac"			"*(@(a))a@(c)"	       NOMATCH EXTMATCH
+C.UTF-8		"abcd"			"?@(a|b)*@(c)d"	       0       EXTMATCH
+C.UTF-8		"abcd"			"@(ab|a*@(b))*(c)d"    0       EXTMATCH
+C.UTF-8		"acd"			"@(ab|a*(b))*(c)d"     0       EXTMATCH
+C.UTF-8		"abbcd"			"@(ab|a*(b))*(c)d"     0       EXTMATCH
+C.UTF-8		"effgz"			"@(b+(c)d|e*(f)g?|?(h)i@(j|k))" 0 EXTMATCH
+C.UTF-8		"efgz"			"@(b+(c)d|e*(f)g?|?(h)i@(j|k))" 0 EXTMATCH
+C.UTF-8		"egz"			"@(b+(c)d|e*(f)g?|?(h)i@(j|k))" 0 EXTMATCH
+C.UTF-8		"egzefffgzbcdij"	"*(b+(c)d|e*(f)g?|?(h)i@(j|k))" 0 EXTMATCH
+C.UTF-8		"egz"			"@(b+(c)d|e+(f)g?|?(h)i@(j|k))" NOMATCH EXTMATCH
+C.UTF-8		"ofoofo"		"*(of+(o))"	       0       EXTMATCH
+C.UTF-8		"oxfoxoxfox"		"*(oxf+(ox))"	       0       EXTMATCH
+C.UTF-8		"oxfoxfox"		"*(oxf+(ox))"	       NOMATCH EXTMATCH
+C.UTF-8		"ofoofo"		"*(of+(o)|f)"	       0       EXTMATCH
+C.UTF-8		"foofoofo"		"@(foo|f|fo)*(f|of+(o))" 0     EXTMATCH
+C.UTF-8		"oofooofo"		"*(of|oof+(o))"	       0       EXTMATCH
+C.UTF-8		"fffooofoooooffoofffooofff" "*(*(f)*(o))"      0       EXTMATCH
+C.UTF-8		"fofoofoofofoo"		"*(fo|foo)"	       0       EXTMATCH
+C.UTF-8		"foo"			"!(x)"		       0       EXTMATCH
+C.UTF-8		"foo"			"!(x)*"		       0       EXTMATCH
+C.UTF-8		"foo"			"!(foo)"	       NOMATCH EXTMATCH
+C.UTF-8		"foo"			"!(foo)*"	       0       EXTMATCH
+C.UTF-8		"foobar"		"!(foo)"	       0       EXTMATCH
+C.UTF-8		"foobar"		"!(foo)*"	       0       EXTMATCH
+C.UTF-8		"moo.cow"		"!(*.*).!(*.*)"	       0       EXTMATCH
+C.UTF-8		"mad.moo.cow"		"!(*.*).!(*.*)"	       NOMATCH EXTMATCH
+C.UTF-8		"mucca.pazza"		"mu!(*(c))?.pa!(*(z))?" NOMATCH EXTMATCH
+C.UTF-8		"fff"			"!(f)"		       0       EXTMATCH
+C.UTF-8		"fff"			"*(!(f))"	       0       EXTMATCH
+C.UTF-8		"fff"			"+(!(f))"	       0       EXTMATCH
+C.UTF-8		"ooo"			"!(f)"		       0       EXTMATCH
+C.UTF-8		"ooo"			"*(!(f))"	       0       EXTMATCH
+C.UTF-8		"ooo"			"+(!(f))"	       0       EXTMATCH
+C.UTF-8		"foo"			"!(f)"		       0       EXTMATCH
+C.UTF-8		"foo"			"*(!(f))"	       0       EXTMATCH
+C.UTF-8		"foo"			"+(!(f))"	       0       EXTMATCH
+C.UTF-8		"f"			"!(f)"		       NOMATCH EXTMATCH
+C.UTF-8		"f"			"*(!(f))"	       NOMATCH EXTMATCH
+C.UTF-8		"f"			"+(!(f))"	       NOMATCH EXTMATCH
+C.UTF-8		"foot"			"@(!(z*)|*x)"	       0       EXTMATCH
+C.UTF-8		"zoot"			"@(!(z*)|*x)"	       NOMATCH EXTMATCH
+C.UTF-8		"foox"			"@(!(z*)|*x)"	       0       EXTMATCH
+C.UTF-8		"zoox"			"@(!(z*)|*x)"	       0       EXTMATCH
+C.UTF-8		"foo"			"*(!(foo))"	       0       EXTMATCH
+C.UTF-8		"foob"			"!(foo)b*"	       NOMATCH EXTMATCH
+C.UTF-8		"foobb"			"!(foo)b*"	       0       EXTMATCH
+C.UTF-8		"["			"*([a[])"	       0       EXTMATCH
+C.UTF-8		"]"			"*([]a[])"	       0       EXTMATCH
+C.UTF-8		"a"			"*([]a[])"	       0       EXTMATCH
+C.UTF-8		"b"			"*([!]a[])"	       0       EXTMATCH
+C.UTF-8		"["			"*([!]a[]|[[])"	       0       EXTMATCH
+C.UTF-8		"]"			"*([!]a[]|[]])"	       0       EXTMATCH
+C.UTF-8		"["			"!([!]a[])"	       0       EXTMATCH
+C.UTF-8		"]"			"!([!]a[])"	       0       EXTMATCH
+C.UTF-8		")"			"*([)])"	       0       EXTMATCH
+C.UTF-8		"*"			"*([*(])"	       0       EXTMATCH
+C.UTF-8		"abcd"			"*!(|a)cd"	       0       EXTMATCH
+C.UTF-8		"ab/.a"			"+([abc])/*"	       NOMATCH EXTMATCH|PATHNAME|PERIOD
+C.UTF-8		""			""		       0
+C.UTF-8		""			""		       0       EXTMATCH
+C.UTF-8		""			"*([abc])"	       0       EXTMATCH
+C.UTF-8		""			"?([abc])"	       0       EXTMATCH
diff --git a/posix/tst-regcomp-truncated.c b/posix/tst-regcomp-truncated.c
index 84195fc..da3f977 100644
--- a/posix/tst-regcomp-truncated.c
+++ b/posix/tst-regcomp-truncated.c
@@ -37,6 +37,7 @@
 static const char locales[][17] =
   {
     "C",
+    "C.UTF-8",
     "en_US.UTF-8",
     "de_DE.ISO-8859-1",
   };
diff --git a/posix/tst-regex.c b/posix/tst-regex.c
index e7c2b05..531128d 100644
--- a/posix/tst-regex.c
+++ b/posix/tst-regex.c
@@ -32,6 +32,7 @@
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <regex.h>
+#include <support/support.h>
 
 
 #if defined _POSIX_CPUTIME && _POSIX_CPUTIME >= 0
@@ -58,7 +59,7 @@ do_test (void)
   const char *file;
   int fd;
   struct stat st;
-  int result;
+  int result = 0;
   char *inmem;
   char *outmem;
   size_t inlen;
@@ -123,7 +124,7 @@ do_test (void)
 
   /* Run the actual tests.  All tests are run in a single-byte and a
      multi-byte locale.  */
-  result = test_expr ("[äáàâéèêíìîñöóòôüúùû]", 4, 4);
+  result |= test_expr ("[äáàâéèêíìîñöóòôüúùû]", 4, 4);
   result |= test_expr ("G.ran", 2, 3);
   result |= test_expr ("G.\\{1\\}ran", 2, 3);
   result |= test_expr ("G.*ran", 3, 44);
@@ -143,19 +144,33 @@ do_test (void)
 static int
 test_expr (const char *expr, int expected, int expectedicase)
 {
-  int result;
+  int result = 0;
   char *inmem;
   char *outmem;
   size_t inlen;
   size_t outlen;
   char *uexpr;
 
-  /* First test: search with an UTF-8 locale.  */
-  if (setlocale (LC_ALL, "de_DE.UTF-8") == NULL)
-    error (EXIT_FAILURE, 0, "cannot set locale de_DE.UTF-8");
+  /* First test: search with basic C.UTF-8 locale.  */
+  printf ("INFO: Testing C.UTF-8.\n");
+  xsetlocale (LC_ALL, "C.UTF-8");
 
   printf ("\nTest \"%s\" with multi-byte locale\n", expr);
-  result = run_test (expr, mem, memlen, 0, expected);
+  result |= run_test (expr, mem, memlen, 0, expected);
+  printf ("\nTest \"%s\" with multi-byte locale, case insensitive\n", expr);
+  result |= run_test (expr, mem, memlen, 1, expectedicase);
+  printf ("\nTest \"%s\" backwards with multi-byte locale\n", expr);
+  result |= run_test_backwards (expr, mem, memlen, 0, expected);
+  printf ("\nTest \"%s\" backwards with multi-byte locale, case insensitive\n",
+	  expr);
+  result |= run_test_backwards (expr, mem, memlen, 1, expectedicase);
+
+  /* Second test: search with an UTF-8 locale.  */
+  printf ("INFO: Testing de_DE.UTF-8.\n");
+  xsetlocale (LC_ALL, "de_DE.UTF-8");
+
+  printf ("\nTest \"%s\" with multi-byte locale\n", expr);
+  result |= run_test (expr, mem, memlen, 0, expected);
   printf ("\nTest \"%s\" with multi-byte locale, case insensitive\n", expr);
   result |= run_test (expr, mem, memlen, 1, expectedicase);
   printf ("\nTest \"%s\" backwards with multi-byte locale\n", expr);
@@ -165,8 +180,8 @@ test_expr (const char *expr, int expected, int expectedicase)
   result |= run_test_backwards (expr, mem, memlen, 1, expectedicase);
 
   /* Second test: search with an ISO-8859-1 locale.  */
-  if (setlocale (LC_ALL, "de_DE.ISO-8859-1") == NULL)
-    error (EXIT_FAILURE, 0, "cannot set locale de_DE.ISO-8859-1");
+  printf ("INFO: Testing de_DE.ISO-8859-1.\n");
+  xsetlocale (LC_ALL, "de_DE.ISO-8859-1");
 
   inmem = (char *) expr;
   inlen = strlen (expr);