libc/newlib/libc/ctype/jp2uc.c

167 lines
4.5 KiB
C
Raw Normal View History

/* Routine to translate from Japanese characters to Unicode */
/* Copyright (c) 2002 Red Hat Incorporated.
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
The name of Red Hat Incorporated may not be used to endorse
or promote products derived from this software without specific
prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL RED HAT INCORPORATED BE LIABLE FOR ANY
DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#include <newlib.h>
#ifdef _MB_CAPABLE
#include <_ansi.h>
#include <wctype.h>
#include "local.h"
#include "jp2uc.h"
/* Japanese encoding types supported */
#define JP_JIS 1
#define JP_SJIS 2
#define JP_EUCJP 3
wint_t
_DEFUN (__jp2uc, (c, type), wint_t c _AND int type)
{
int index, adj;
unsigned char byte1, byte2;
wint_t ret;
/* we actually use tables of EUCJP to Unicode. For JIS, we simply
note that EUCJP is essentially JIS with the top bits on in each
byte and translate to EUCJP. For SJIS, we do a translation to EUCJP before
accessing the tables. */
switch (type)
{
case JP_JIS:
byte1 = (c >> 8) + 0x80;
byte2 = (c & 0xff) + 0x80;
break;
case JP_EUCJP:
byte1 = (c >> 8);
byte2 = (c & 0xff);
break;
case JP_SJIS:
byte1 = c >> 8;
byte2 = c & 0xff;
if (byte2 <= 0x9e)
{
adj = 0xa1 - 0x22;
byte2 = (byte2 - 31) + 0xa1;
}
else
{
adj = 0xa1 - 0x21;
byte2 = (byte2 - 126) + 0xa1;
}
if (byte1 <= 0x9f)
byte1 = ((byte1 - 112) << 1) + adj;
else
byte1 = ((byte1 - 176) << 1) + adj;
break;
default:
return WEOF;
}
/* find conversion in jp2uc arrays */
/* handle larger ranges first */
if (byte1 >= 0xb0 && byte1 <= 0xcf && c <= 0xcfd3)
{
index = (byte1 - 0xb0) * 0xfe + (byte2 - 0xa1);
return b02cf[index];
}
else if (byte1 >= 0xd0 && byte1 <= 0xf4 && c <= 0xf4a6)
{
index = (byte1 - 0xd0) * 0xfe + (byte2 - 0xa1);
return d02f4[index];
}
/* handle smaller ranges here */
switch (byte1)
{
case 0xA1:
return (wint_t)a1[byte2 - 0xa1];
case 0xA2:
ret = a2[byte2 - 0xa1];
if (ret != 0)
return (wint_t)ret;
break;
case 0xA3:
if (a3[byte2 - 0xa1])
return (wint_t)(0xff00 + (byte2 - 0xa0));
break;
case 0xA4:
if (byte2 <= 0xf3)
return (wint_t)(0x3000 + (byte2 - 0x60));
break;
case 0xA5:
if (byte2 <= 0xf6)
return (wint_t)(0x3000 + byte2);
break;
case 0xA6:
ret = 0;
if (byte2 <= 0xd8)
ret = (wint_t)a6[byte2 - 0xa1];
if (ret != 0)
return ret;
break;
case 0xA7:
ret = 0;
if (byte2 <= 0xf1)
ret = (wint_t)a7[byte2 - 0xa1];
if (ret != 0)
return ret;
break;
case 0xA8:
if (byte2 <= 0xc0)
return (wint_t)a8[byte2 - 0xa1];
break;
default:
return WEOF;
}
return WEOF;
}
wint_t
_DEFUN (_jp2uc, (c), wint_t c)
{
/* Under Cygwin, the incoming wide character is already given in UTF due
to the requirements of the underlying OS. */
#ifndef __CYGWIN__
if (!strcmp (__locale_charset (), "JIS"))
c = __jp2uc (c, JP_JIS);
else if (!strcmp (__locale_charset (), "SJIS"))
c = __jp2uc (c, JP_SJIS);
else if (!strcmp (__locale_charset (), "EUCJP"))
c = __jp2uc (c, JP_EUCJP);
* libc/ctype/iswalpha.c: Handle all wchar_t as unicode on _MB_CAPABLE systems. * libc/ctype/iswblank.c: Ditto. * libc/ctype/iswcntrl.c: Ditto. * libc/ctype/iswprint.c: Ditto. * libc/ctype/iswpunct.c: Ditto. * libc/ctype/iswspace.c: Ditto. * libc/ctype/jp2uc.c (__jp2uc): On Cygwin, just return c. Explain why. * libc/ctype/towlower.c: Ditto. * libc/ctype/towupper.c: Ditto. * libc/include/sys/config.h: Define _MB_EXTENDED_CHARSETS_ISO and _MB_EXTENDED_CHARSETS_WINDOWS if _MB_EXTENDED_CHARSETS_ALL is defined. Define _MB_EXTENDED_CHARSETS_ALL on Cygwin only for now. * libc/include/sys/reent.h (struct _reent): Mark _current_category and _current_locale as unused. * libc/locale/locale.c: Add new charset support to documentation. Include ../stdio/local.h from here. (lc_ctype_charset): Set to "ASCII" by default. (lc_message_charset): Ditto. (_setlocale_r): Don't set _current_category and _current_locale. (loadlocale): Add Cygwin codepage support. On _MB_CAPABLE systems, set __mbtowc and __wctomb function pointers to function corresponding with current charset. Don't allow non-existant ISO-8859-12 charset. Add support for Windows singlebyte codepages. On Cygwin, add support for GBK, CP949, and BIG5. On Cygwin, call __set_ctype() in case the catorgy is LC_CTYPE. Don't set _current_category and _current_locale. * libc/stdlib/Makefile.am (GENERAL_SOURCES): Add sb_charsets.c. * libc/stdlib/Makefile.in: Regenerate. * libc/stdlib/local.h: Add prototype for __locale_charset. Add prototypes for __mbtowc and __wctomb pointers. Add prototypes for charset-specific _wctomb_r and _mbtowc_r functions. Declare tables and functions from sb_charsets.c. * libc/stdlib/mbtowc_r.c (__mbtowc): Define. Set to __ascii_mbtowc by default. (_mbtowc_r): Just call __mbtowc from here. (__ascii_mbtowc): New function. (__iso_mbtowc): New function. (__cp_mbtowc): New function. (__utf8_mbtowc): New function. (__sjis_mbtowc): New function. Disable on Cygwin. (__eucjp_mbtowc): New function. Disable on Cygwin. (__jis_mbtowc): New function. Disable on Cygwin. * libc/stdlib/sb_charsets.c: New file, adding singlebyte to UTF conversion tables for all ISO and CP charsets. (__iso_8859_index): New function. (__cp_index): New function. * libc/stdlib/wctomb_r.c (__wctomb): Define. Set to __ascii_wctomb by default. (_wctomb_r): Just call __wctomb from here. (__ascii_wctomb): New function. (__utf8_wctomb): New function. (__sjis_wctomb): New function. Disable on Cygwin. (__eucjp_wctomb): New function. Disable on Cygwin. (__jis_wctomb): New function. Disable on Cygwin. (__iso_wctomb): New function. (__cp_wctomb): New function.
2009-03-24 11:13:27 +01:00
#endif
return c;
}
#endif /* _MB_CAPABLE */