mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-30 00:31:08 +00:00
466f2be6c0
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>
85 lines
1.6 KiB
C
85 lines
1.6 KiB
C
#include <locale.h>
|
|
#include <stdio.h>
|
|
#include <string.h>
|
|
#include <regex.h>
|
|
#include <wchar.h>
|
|
|
|
int
|
|
main (void)
|
|
{
|
|
struct re_pattern_buffer regex;
|
|
struct re_registers regs;
|
|
const char *s;
|
|
int match;
|
|
int result = 0;
|
|
|
|
memset (®ex, '\0', sizeof (regex));
|
|
|
|
setlocale (LC_ALL, "de_DE.ISO-8859-1");
|
|
fwide (stdout, -1);
|
|
|
|
re_set_syntax (RE_SYNTAX_POSIX_EGREP | RE_DEBUG);
|
|
|
|
puts ("in C locale");
|
|
setlocale (LC_ALL, "C");
|
|
s = re_compile_pattern ("[an\371]*n", 7, ®ex);
|
|
if (s != NULL)
|
|
{
|
|
puts ("re_compile_pattern return non-NULL value");
|
|
result = 1;
|
|
}
|
|
else
|
|
{
|
|
match = re_match (®ex, "an", 2, 0, ®s);
|
|
if (match != 2)
|
|
{
|
|
printf ("re_match returned %d, expected 2\n", match);
|
|
result = 1;
|
|
}
|
|
else
|
|
puts (" -> OK");
|
|
}
|
|
|
|
puts ("in C.UTF-8 locale");
|
|
setlocale (LC_ALL, "C.UTF-8");
|
|
s = re_compile_pattern ("[an\371]*n", 7, ®ex);
|
|
if (s != NULL)
|
|
{
|
|
puts ("re_compile_pattern return non-NULL value");
|
|
result = 1;
|
|
}
|
|
else
|
|
{
|
|
match = re_match (®ex, "an", 2, 0, ®s);
|
|
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, ®ex);
|
|
if (s != NULL)
|
|
{
|
|
puts ("re_compile_pattern return non-NULL value");
|
|
result = 1;
|
|
}
|
|
else
|
|
{
|
|
match = re_match (®ex, "an", 2, 0, ®s);
|
|
if (match != 2)
|
|
{
|
|
printf ("re_match returned %d, expected 2\n", match);
|
|
result = 1;
|
|
}
|
|
else
|
|
puts (" -> OK");
|
|
}
|
|
|
|
return result;
|
|
}
|