mirror of
git://sourceware.org/git/newlib-cygwin.git
synced 2025-01-16 03:19:54 +08:00
1525d127da
* libc/ctype/Makefile.am: Add new files. * libc/ctype/Makefile.in: Regenerated. * libc/ctype/ctype.tex: Add new iswxxxx, towxxxx, wctype, and wctrans functions to documentation index. * libc/ctype/iswalnum.c: New file. * libc/ctype/iswalpha.c: Ditto. * libc/ctype/iswblank.c: Ditto. * libc/ctype/iswcntrl.c: Ditto. * libc/ctype/iswctype.c: Ditto. * libc/ctype/iswdigit.c: Ditto. * libc/ctype/iswgraph.c: Ditto. * libc/ctype/iswlower.c: Ditto. * libc/ctype/iswprint.c: Ditto. * libc/ctype/iswpunct.c: Ditto. * libc/ctype/iswspace.c: Ditto. * libc/ctype/iswupper.c: Ditto. * libc/ctype/iswxdigit.c: Ditto. * libc/ctype/jp2uc.c: Ditto. * libc/ctype/jp2uc.h: Ditto. * libc/ctype/local.h: Ditto. * libc/ctype/towctrans.c: Ditto. * libc/ctype/towlower.c: Ditto. * libc/ctype/towupper.c: Ditto. * libc/ctype/utf8alpha.h: Ditto. * libc/ctype/utf8print.h: Ditto. * libc/ctype/utf8punct.h: Ditto. * libc/ctype/wctrans.c: Ditto. * libc/ctype/wctype.c: Ditto. * libc/locale/locale.c (__lc_ctype): New external array to replace static lc_ctype array. * libc/stdlib/mbtowc_r.c: Use __lc_ctype to check current lc_ctype rather than reentrancy structure's _current_locale field. * libc/stdlib/wctomb_r.c: Ditto.
175 lines
4.7 KiB
C
175 lines
4.7 KiB
C
#include <stdlib.h>
|
|
#include <string.h>
|
|
#include <wchar.h>
|
|
#include <locale.h>
|
|
#include "mbctype.h"
|
|
|
|
/* for some conversions, we use the __count field as a place to store a state value */
|
|
#define __state __count
|
|
|
|
extern char __lc_ctype[12];
|
|
|
|
int
|
|
_DEFUN (_wctomb_r, (r, s, wchar, state),
|
|
struct _reent *r _AND
|
|
char *s _AND
|
|
wchar_t wchar _AND
|
|
mbstate_t *state)
|
|
{
|
|
if (strlen (__lc_ctype) <= 1)
|
|
{ /* fall-through */ }
|
|
else if (!strcmp (__lc_ctype, "C-UTF-8"))
|
|
{
|
|
if (s == NULL)
|
|
return 0; /* UTF-8 encoding is not state-dependent */
|
|
|
|
if (wchar <= 0x7f)
|
|
{
|
|
*s = wchar;
|
|
return 1;
|
|
}
|
|
else if (wchar >= 0x80 && wchar <= 0x7ff)
|
|
{
|
|
*s++ = 0xc0 | ((wchar & 0x7c0) >> 6);
|
|
*s = 0x80 | (wchar & 0x3f);
|
|
return 2;
|
|
}
|
|
else if (wchar >= 0x800 && wchar <= 0xffff)
|
|
{
|
|
/* UTF-16 surrogates -- must not occur in normal UCS-4 data */
|
|
if (wchar >= 0xd800 && wchar <= 0xdfff)
|
|
return -1;
|
|
|
|
*s++ = 0xe0 | ((wchar & 0xf000) >> 12);
|
|
*s++ = 0x80 | ((wchar & 0xfc0) >> 6);
|
|
*s = 0x80 | (wchar & 0x3f);
|
|
return 3;
|
|
}
|
|
else if (wchar >= 0x10000 && wchar <= 0x1fffff)
|
|
{
|
|
*s++ = 0xf0 | ((wchar & 0x1c0000) >> 18);
|
|
*s++ = 0x80 | ((wchar & 0x3f000) >> 12);
|
|
*s++ = 0x80 | ((wchar & 0xfc0) >> 6);
|
|
*s = 0x80 | (wchar & 0x3f);
|
|
return 4;
|
|
}
|
|
else if (wchar >= 0x200000 && wchar <= 0x3ffffff)
|
|
{
|
|
*s++ = 0xf8 | ((wchar & 0x3000000) >> 24);
|
|
*s++ = 0x80 | ((wchar & 0xfc0000) >> 18);
|
|
*s++ = 0x80 | ((wchar & 0x3f000) >> 12);
|
|
*s++ = 0x80 | ((wchar & 0xfc0) >> 6);
|
|
*s = 0x80 | (wchar & 0x3f);
|
|
return 5;
|
|
}
|
|
else if (wchar >= 0x4000000 && wchar <= 0x7fffffff)
|
|
{
|
|
*s++ = 0xfc | ((wchar & 0x40000000) >> 30);
|
|
*s++ = 0x80 | ((wchar & 0x3f000000) >> 24);
|
|
*s++ = 0x80 | ((wchar & 0xfc0000) >> 18);
|
|
*s++ = 0x80 | ((wchar & 0x3f000) >> 12);
|
|
*s++ = 0x80 | ((wchar & 0xfc0) >> 6);
|
|
*s = 0x80 | (wchar & 0x3f);
|
|
return 6;
|
|
}
|
|
else
|
|
return -1;
|
|
}
|
|
else if (!strcmp (__lc_ctype, "C-SJIS"))
|
|
{
|
|
unsigned char char2 = (unsigned char)wchar;
|
|
unsigned char char1 = (unsigned char)(wchar >> 8);
|
|
|
|
if (s == NULL)
|
|
return 0; /* not state-dependent */
|
|
|
|
if (char1 != 0x00)
|
|
{
|
|
/* first byte is non-zero..validate multi-byte char */
|
|
if (_issjis1(char1) && _issjis2(char2))
|
|
{
|
|
*s++ = (char)char1;
|
|
*s = (char)char2;
|
|
return 2;
|
|
}
|
|
else
|
|
return -1;
|
|
}
|
|
}
|
|
else if (!strcmp (__lc_ctype, "C-EUCJP"))
|
|
{
|
|
unsigned char char2 = (unsigned char)wchar;
|
|
unsigned char char1 = (unsigned char)(wchar >> 8);
|
|
|
|
if (s == NULL)
|
|
return 0; /* not state-dependent */
|
|
|
|
if (char1 != 0x00)
|
|
{
|
|
/* first byte is non-zero..validate multi-byte char */
|
|
if (_iseucjp (char1) && _iseucjp (char2))
|
|
{
|
|
*s++ = (char)char1;
|
|
*s = (char)char2;
|
|
return 2;
|
|
}
|
|
else
|
|
return -1;
|
|
}
|
|
}
|
|
else if (!strcmp (__lc_ctype, "C-JIS"))
|
|
{
|
|
int cnt = 0;
|
|
unsigned char char2 = (unsigned char)wchar;
|
|
unsigned char char1 = (unsigned char)(wchar >> 8);
|
|
|
|
if (s == NULL)
|
|
return 1; /* state-dependent */
|
|
|
|
if (char1 != 0x00)
|
|
{
|
|
/* first byte is non-zero..validate multi-byte char */
|
|
if (_isjis (char1) && _isjis (char2))
|
|
{
|
|
if (state->__state == 0)
|
|
{
|
|
/* must switch from ASCII to JIS state */
|
|
state->__state = 1;
|
|
*s++ = ESC_CHAR;
|
|
*s++ = '$';
|
|
*s++ = 'B';
|
|
cnt = 3;
|
|
}
|
|
*s++ = (char)char1;
|
|
*s = (char)char2;
|
|
return cnt + 2;
|
|
}
|
|
else
|
|
return -1;
|
|
}
|
|
else
|
|
{
|
|
if (state->__state != 0)
|
|
{
|
|
/* must switch from JIS to ASCII state */
|
|
state->__state = 0;
|
|
*s++ = ESC_CHAR;
|
|
*s++ = '(';
|
|
*s++ = 'B';
|
|
cnt = 3;
|
|
}
|
|
*s = (char)char2;
|
|
return cnt + 1;
|
|
}
|
|
}
|
|
|
|
if (s == NULL)
|
|
return 0;
|
|
|
|
/* otherwise we are dealing with a single byte character */
|
|
*s = (char) wchar;
|
|
return 1;
|
|
}
|
|
|
|
|