Cygwin: __collate_range_cmp: handle Unicode values >= 0x10000

So far the input to __collate_range_cmp was handled as a wchar_t.
Change that to handle it as wint_t holding a UTF-32 value and
add creating surrogate pairs for the call to wcscoll.

Signed-off-by: Corinna Vinschen <corinna@vinschen.de>
This commit is contained in:
Corinna Vinschen 2023-02-14 12:22:36 +01:00
parent 60c25da90d
commit eac830e0fe
1 changed files with 14 additions and 2 deletions

View File

@ -1176,8 +1176,20 @@ strcoll (const char *__restrict s1, const char *__restrict s2)
extern "C" int extern "C" int
__collate_range_cmp (int c1, int c2) __collate_range_cmp (int c1, int c2)
{ {
wchar_t s1[2] = { (wchar_t) c1, L'\0' }; wchar_t s1[3] = { (wchar_t) c1, L'\0', L'\0' };
wchar_t s2[2] = { (wchar_t) c2, L'\0' }; wchar_t s2[3] = { (wchar_t) c2, L'\0', L'\0' };
/* Handle Unicode values >= 0x10000, convert to surrogate pair */
if (c1 > 0xffff)
{
s1[0] = ((c1 - 0x10000) >> 10) + 0xd800;
s1[1] = ((c1 - 0x10000) & 0x3ff) + 0xdc00;
}
if (c2 > 0xffff)
{
s2[0] = ((c2 - 0x10000) >> 10) + 0xd800;
s2[1] = ((c2 - 0x10000) & 0x3ff) + 0xdc00;
}
return wcscoll (s1, s2); return wcscoll (s1, s2);
} }