newlib-cygwin/newlib/libc/stdlib/mbtowc_r.c

975 lines
22 KiB
C
Raw Normal View History

#include <newlib.h>
2000-02-18 03:39:52 +08:00
#include <stdlib.h>
#include <locale.h>
#include "mbctype.h"
* libc/include/langinfo.h: New file. * libc/include/wchar.h: Likewise. * libc/include/sys/syslimits.h: Likewise. * libc/locale/fix_grouping.c: Likewise. * libc/locale/ldpart.c: Likewise. * libc/locale/ldpart.h: Likewise. * libc/locale/lmessages.c: Likewise. * libc/locale/lmessages.h: Likewise. * libc/locale/lmonetary.c: Likewise. * libc/locale/lmonetary.h: Likewise. * libc/locale/lnumeric.c: Likewise. * libc/locale/lnumeric.h: Likewise. * libc/locale/nl_langinfo.3: Likewise. * libc/locale/nl_langinfo.c: Likewise. * libc/locale/timelocal.c: Likewise. * libc/locale/timelocal.h: Likewise. * libc/stdlib/btowc.c: Likewise. * libc/stdlib/mbrlen.c: Likewise. * libc/stdlib/mbrtowc.c: Likewise. * libc/stdlib/mbsinit.c: Likewise. * libc/stdlib/mbsrtowcs.c: Likewise. * libc/stdlib/wcrtomb.c: Likewise. * libc/stdlib/wcsrtombs.c: Likewise. * libc/stdlib/wctob.c: Likewise. * libc/sys/linux/prof-freq.c: Likewise. * libc/sys/linux/profile.c: Likewise. * libc/sys/linux/machine/i386/dl-procinfo.c: Likewise. * libc/sys/linux/machine/i386/dl-procinfo.h: Likewise. * libc/include/stdlib.h: Change re-entrant functions to take mbstate_t pointers. * libc/include/sys/_types.h: Define _mbstate_t. * libc/include/sys/config.h (MB_LEN_MAX): New macro. * libc/include/sys/errno.h (EILSEQ): New error code. * libc/include/sys/reent.h: Include wchar.h. Change reentrant structure to use mbstate_t. * libc/locale/Makefile.am (LIB_SOURCES): Add new files. * libc/machine/powerpc/vfprintf.c: Use mbstate_t. * libc/machine/powerpc/vfscanf.c: Likewise. * libc/stdio/getdelim.c: Reallocate buffer only when necessary. * libc/stdio/vfprintf.c: Likewise. * libc/stdio/vfscanf.c: Likewise. * libc/stdlib/Makefile.am (LIB_SOURCES): Add new files. * libc/stdlib/mblen.c: Use mbstate_t. * libc/stdlib/mblen_r.c: Likewise. * libc/stdlib/mbstowcs.c: Likewise. * libc/stdlib/mbstowcs_r.c: Likewise. * libc/stdlib/mbtowc.c: Likewise. * libc/stdlib/mbtowc_r.c: Likewise. * libc/stdlib/wcstombs.c: Likewise. * libc/stdlib/wcstombs_r.c: Likewise. * libc/stdlib/wctomb_r.c: Likewise. * libc/sys/linux/Makefile.am (LIB_SOURCES): Add prof-freq.c and profile.c. * libc/sys/linux/machine/i386/Makefile.am (LIB_SOURCES): Add dl-procinfo.c. * libc/sys/linux/sys/errno.h (EILSEQ): New error code. * libc/sys/linux/sys/types.h (off_t): Define type. * testsuite/newlib.locale/UTF-8.c: Change locale name from UTF-8 to C-UTF-8. * testsuite/newlib.locale/UTF-8.exp: Likewise.
2002-08-23 09:56:05 +08:00
#include <wchar.h>
#include <string.h>
#include <errno.h>
* 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 18:13:27 +08:00
#include "local.h"
2000-02-18 03:39:52 +08:00
* 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 18:13:27 +08:00
int
_DEFUN (_mbtowc_r, (r, pwc, s, n, state),
struct _reent *r _AND
wchar_t *__restrict pwc _AND
const char *__restrict s _AND
* 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 18:13:27 +08:00
size_t n _AND
mbstate_t *state)
{
return __MBTOWC (r, pwc, s, n, state);
* 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 18:13:27 +08:00
}
* 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 18:13:27 +08:00
int
_DEFUN (__ascii_mbtowc, (r, pwc, s, n, state),
* 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 18:13:27 +08:00
struct _reent *r _AND
wchar_t *pwc _AND
const char *s _AND
size_t n _AND
mbstate_t *state)
{
wchar_t dummy;
unsigned char *t = (unsigned char *)s;
if (pwc == NULL)
pwc = &dummy;
if (s == NULL)
return 0;
if (n == 0)
return -2;
#ifdef __CYGWIN__
if ((wchar_t)*t >= 0x80)
{
r->_errno = EILSEQ;
return -1;
}
#endif
* 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 18:13:27 +08:00
*pwc = (wchar_t)*t;
if (*t == '\0')
return 0;
return 1;
}
#ifdef _MB_CAPABLE
typedef enum __packed { ESCAPE, DOLLAR, BRACKET, AT, B, J,
2000-02-18 03:39:52 +08:00
NUL, JIS_CHAR, OTHER, JIS_C_NUM } JIS_CHAR_TYPE;
typedef enum __packed { ASCII, JIS, A_ESC, A_ESC_DL, JIS_1, J_ESC, J_ESC_BR,
INV, JIS_S_NUM } JIS_STATE;
typedef enum __packed { COPY_A, COPY_J1, COPY_J2, MAKE_A, NOOP, EMPTY, ERROR } JIS_ACTION;
2000-02-18 03:39:52 +08:00
/**************************************************************************************
* state/action tables for processing JIS encoding
* Where possible, switches to JIS are grouped with proceding JIS characters and switches
* to ASCII are grouped with preceding JIS characters. Thus, maximum returned length
* is 2 (switch to JIS) + 2 (JIS characters) + 2 (switch back to ASCII) = 6.
*************************************************************************************/
Throughout, run newlib with -Wall -Werror option and fix bugs and compiler warnings found this way. * libc/stdio/freopen.c (_freopen_r): Fix bug setting _flags. * libc/include/stdio.h (_rename): Define when building newlib. * libc/include/sys/signal.h (_kill): Ditto. * libc/include/sys/stat.h (_mkdir): Ditto. * libc/include/sys/time.h (_gettimeofday): Ditto. * libc/include/sys/times.h (_times): Ditto. * libc/include/sys/wait.h (_wait): Ditto. * libc/locale/lmessages.c (empty): Don't define for Cygwin. * libc/locale/lmonetary.c (cnv): Ditto. * libc/locale/nl_langinfo.c (nl_langinfo): Ditto for variable s. * libc/posix/collate.c: Throughout cast to avoid compiler warning. * libc/posix/engine.c (matcher): Initialize dp to avoid compiler warning. * libc/posix/glob.c: Disable on Cygwin. Explain why. * libc/posix/regcomp.c: Fix "uninitialized" compiler warnings. (dissect): Deliberately silence gcc compiler warning. Add comment to explain why. * libc/posix/wordexp.c (wordexp): Remove num_bytes variable since result is never used. * libc/posix/popen.c (popen): Ditto for variable last. * libc/reent/mkdirr.c: Include sys/stat.h. * libc/reent/renamer.c: Include stdio.h. * libc/search/hash.c: Throughout use underscored variants of the stat function family. (init_hash): Add missing definition for the __USE_INTERNAL_STAT64 case. * libc/search/hash_bigkey.c (__big_insert): Add parenthesis to avoid compiler warning. * libc/search/hash_page.c (overflow_page): Initalize freep to NULL to avoid compiler warning. * libc/stdio/asiprintf.c (_asiprintf_r): Cast unsigned char * to char * to avoid compiler warning. (asiprintf): Ditto. * libc/stdio/asprintf.c (_asprintf_r): Ditto. (asprintf): Ditto. * libc/stdio/vasiprintf.c (_vasiprintf_r): Ditto. * libc/stdio/vasprintf.c (_vasprintf_r): Ditto. * libc/stdio/mktemp.c (_gettemp): Cast to unsigned char in call to isdigit to avoid compiler warning. * libc/stdio/vfprintf.c (_VFPRINTF_R): Initialize variables used for grouping to avoid compiler warning. Only define and set nseps and nrepeats if they are really used. * libc/stdio/vfwprintf.c (_VFWPRINTF_R): Ditto. Only define state if it is really used. * libc/stdio/vfscanf.c (u_char): Revert to be defined as unsigned char. (__SVFSCANF_R): Cast fmt in call to __mbtowc. * libc/stdlib/mbtowc_r.c (JIS_state_table): Disable when building Cygwin. (JIS_action_table): Ditto. * libc/stdlib/wctomb_r.c (__utf8_wctomb): Add parenthesis to avoid compiler warning. * libc/string/strcasestr.c: Deliberately silence gcc compiler warning. Add comment to explain why. * libc/time/strptime.c (strptime): Cast to unsigned char in calls to isspace to avoid compiler warning. * libm/math/e_atan2.c (__ieee754_atan2): Add parenthesis to avoid compiler warning. * libm/math/e_exp.c (__ieee754_exp): Initialize k to 0 to avoid compiler warning. Drop setting it to 0 later. * libm/math/ef_exp.c (__ieee754_expf): Ditto. * libm/math/e_pow.c (__ieee754_pow): Add braces to avoid compiler warning. * libm/math/ef_pow.c (__ieee754_powf): Ditto. * libm/math/er_lgamma.c (__ieee754_lgamma_r): Initialize nadj to 0 to avoid compiler warning. * libm/math/erf_lgamma.c (__ieee754_lgammaf_r): Ditto. * libm/math/e_rem_pio2.c (__ieee754_rem_pio2): Ditto for variable z. * libm/common/sf_round.c (roundf): Remove signbit variable since result is never used.
2012-08-08 19:04:18 +08:00
#ifndef __CYGWIN__
2000-02-18 03:39:52 +08:00
static JIS_STATE JIS_state_table[JIS_S_NUM][JIS_C_NUM] = {
/* ESCAPE DOLLAR BRACKET AT B J NUL JIS_CHAR OTHER */
/* ASCII */ { A_ESC, ASCII, ASCII, ASCII, ASCII, ASCII, ASCII, ASCII, ASCII },
2000-02-18 03:39:52 +08:00
/* JIS */ { J_ESC, JIS_1, JIS_1, JIS_1, JIS_1, JIS_1, INV, JIS_1, INV },
/* A_ESC */ { ASCII, A_ESC_DL, ASCII, ASCII, ASCII, ASCII, ASCII, ASCII, ASCII },
/* A_ESC_DL */{ ASCII, ASCII, ASCII, JIS, JIS, ASCII, ASCII, ASCII, ASCII },
/* JIS_1 */ { INV, JIS, JIS, JIS, JIS, JIS, INV, JIS, INV },
2000-02-18 03:39:52 +08:00
/* J_ESC */ { INV, INV, J_ESC_BR, INV, INV, INV, INV, INV, INV },
/* J_ESC_BR */{ INV, INV, INV, INV, ASCII, ASCII, INV, INV, INV },
};
static JIS_ACTION JIS_action_table[JIS_S_NUM][JIS_C_NUM] = {
/* ESCAPE DOLLAR BRACKET AT B J NUL JIS_CHAR OTHER */
/* ASCII */ { NOOP, COPY_A, COPY_A, COPY_A, COPY_A, COPY_A, EMPTY, COPY_A, COPY_A},
/* JIS */ { NOOP, COPY_J1, COPY_J1, COPY_J1, COPY_J1, COPY_J1, ERROR, COPY_J1, ERROR },
2000-02-18 03:39:52 +08:00
/* A_ESC */ { COPY_A, NOOP, COPY_A, COPY_A, COPY_A, COPY_A, COPY_A, COPY_A, COPY_A},
/* A_ESC_DL */{ COPY_A, COPY_A, COPY_A, NOOP, NOOP, COPY_A, COPY_A, COPY_A, COPY_A},
/* JIS_1 */ { ERROR, COPY_J2, COPY_J2, COPY_J2, COPY_J2, COPY_J2, ERROR, COPY_J2, ERROR },
2000-02-18 03:39:52 +08:00
/* J_ESC */ { ERROR, ERROR, NOOP, ERROR, ERROR, ERROR, ERROR, ERROR, ERROR },
/* J_ESC_BR */{ ERROR, ERROR, ERROR, ERROR, MAKE_A, MAKE_A, ERROR, ERROR, ERROR },
2000-02-18 03:39:52 +08:00
};
Throughout, run newlib with -Wall -Werror option and fix bugs and compiler warnings found this way. * libc/stdio/freopen.c (_freopen_r): Fix bug setting _flags. * libc/include/stdio.h (_rename): Define when building newlib. * libc/include/sys/signal.h (_kill): Ditto. * libc/include/sys/stat.h (_mkdir): Ditto. * libc/include/sys/time.h (_gettimeofday): Ditto. * libc/include/sys/times.h (_times): Ditto. * libc/include/sys/wait.h (_wait): Ditto. * libc/locale/lmessages.c (empty): Don't define for Cygwin. * libc/locale/lmonetary.c (cnv): Ditto. * libc/locale/nl_langinfo.c (nl_langinfo): Ditto for variable s. * libc/posix/collate.c: Throughout cast to avoid compiler warning. * libc/posix/engine.c (matcher): Initialize dp to avoid compiler warning. * libc/posix/glob.c: Disable on Cygwin. Explain why. * libc/posix/regcomp.c: Fix "uninitialized" compiler warnings. (dissect): Deliberately silence gcc compiler warning. Add comment to explain why. * libc/posix/wordexp.c (wordexp): Remove num_bytes variable since result is never used. * libc/posix/popen.c (popen): Ditto for variable last. * libc/reent/mkdirr.c: Include sys/stat.h. * libc/reent/renamer.c: Include stdio.h. * libc/search/hash.c: Throughout use underscored variants of the stat function family. (init_hash): Add missing definition for the __USE_INTERNAL_STAT64 case. * libc/search/hash_bigkey.c (__big_insert): Add parenthesis to avoid compiler warning. * libc/search/hash_page.c (overflow_page): Initalize freep to NULL to avoid compiler warning. * libc/stdio/asiprintf.c (_asiprintf_r): Cast unsigned char * to char * to avoid compiler warning. (asiprintf): Ditto. * libc/stdio/asprintf.c (_asprintf_r): Ditto. (asprintf): Ditto. * libc/stdio/vasiprintf.c (_vasiprintf_r): Ditto. * libc/stdio/vasprintf.c (_vasprintf_r): Ditto. * libc/stdio/mktemp.c (_gettemp): Cast to unsigned char in call to isdigit to avoid compiler warning. * libc/stdio/vfprintf.c (_VFPRINTF_R): Initialize variables used for grouping to avoid compiler warning. Only define and set nseps and nrepeats if they are really used. * libc/stdio/vfwprintf.c (_VFWPRINTF_R): Ditto. Only define state if it is really used. * libc/stdio/vfscanf.c (u_char): Revert to be defined as unsigned char. (__SVFSCANF_R): Cast fmt in call to __mbtowc. * libc/stdlib/mbtowc_r.c (JIS_state_table): Disable when building Cygwin. (JIS_action_table): Ditto. * libc/stdlib/wctomb_r.c (__utf8_wctomb): Add parenthesis to avoid compiler warning. * libc/string/strcasestr.c: Deliberately silence gcc compiler warning. Add comment to explain why. * libc/time/strptime.c (strptime): Cast to unsigned char in calls to isspace to avoid compiler warning. * libm/math/e_atan2.c (__ieee754_atan2): Add parenthesis to avoid compiler warning. * libm/math/e_exp.c (__ieee754_exp): Initialize k to 0 to avoid compiler warning. Drop setting it to 0 later. * libm/math/ef_exp.c (__ieee754_expf): Ditto. * libm/math/e_pow.c (__ieee754_pow): Add braces to avoid compiler warning. * libm/math/ef_pow.c (__ieee754_powf): Ditto. * libm/math/er_lgamma.c (__ieee754_lgamma_r): Initialize nadj to 0 to avoid compiler warning. * libm/math/erf_lgamma.c (__ieee754_lgammaf_r): Ditto. * libm/math/e_rem_pio2.c (__ieee754_rem_pio2): Ditto for variable z. * libm/common/sf_round.c (roundf): Remove signbit variable since result is never used.
2012-08-08 19:04:18 +08:00
#endif /* !__CYGWIN__ */
2000-02-18 03:39:52 +08:00
/* we override the mbstate_t __count field for more complex encodings and use it store a state value */
#define __state __count
* 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 18:13:27 +08:00
#ifdef _MB_EXTENDED_CHARSETS_ISO
static int
___iso_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
int iso_idx, mbstate_t *state)
2000-02-18 03:39:52 +08:00
{
wchar_t dummy;
unsigned char *t = (unsigned char *)s;
if (pwc == NULL)
pwc = &dummy;
* 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 18:13:27 +08:00
if (s == NULL)
return 0;
if (n == 0)
* libc/include/langinfo.h: New file. * libc/include/wchar.h: Likewise. * libc/include/sys/syslimits.h: Likewise. * libc/locale/fix_grouping.c: Likewise. * libc/locale/ldpart.c: Likewise. * libc/locale/ldpart.h: Likewise. * libc/locale/lmessages.c: Likewise. * libc/locale/lmessages.h: Likewise. * libc/locale/lmonetary.c: Likewise. * libc/locale/lmonetary.h: Likewise. * libc/locale/lnumeric.c: Likewise. * libc/locale/lnumeric.h: Likewise. * libc/locale/nl_langinfo.3: Likewise. * libc/locale/nl_langinfo.c: Likewise. * libc/locale/timelocal.c: Likewise. * libc/locale/timelocal.h: Likewise. * libc/stdlib/btowc.c: Likewise. * libc/stdlib/mbrlen.c: Likewise. * libc/stdlib/mbrtowc.c: Likewise. * libc/stdlib/mbsinit.c: Likewise. * libc/stdlib/mbsrtowcs.c: Likewise. * libc/stdlib/wcrtomb.c: Likewise. * libc/stdlib/wcsrtombs.c: Likewise. * libc/stdlib/wctob.c: Likewise. * libc/sys/linux/prof-freq.c: Likewise. * libc/sys/linux/profile.c: Likewise. * libc/sys/linux/machine/i386/dl-procinfo.c: Likewise. * libc/sys/linux/machine/i386/dl-procinfo.h: Likewise. * libc/include/stdlib.h: Change re-entrant functions to take mbstate_t pointers. * libc/include/sys/_types.h: Define _mbstate_t. * libc/include/sys/config.h (MB_LEN_MAX): New macro. * libc/include/sys/errno.h (EILSEQ): New error code. * libc/include/sys/reent.h: Include wchar.h. Change reentrant structure to use mbstate_t. * libc/locale/Makefile.am (LIB_SOURCES): Add new files. * libc/machine/powerpc/vfprintf.c: Use mbstate_t. * libc/machine/powerpc/vfscanf.c: Likewise. * libc/stdio/getdelim.c: Reallocate buffer only when necessary. * libc/stdio/vfprintf.c: Likewise. * libc/stdio/vfscanf.c: Likewise. * libc/stdlib/Makefile.am (LIB_SOURCES): Add new files. * libc/stdlib/mblen.c: Use mbstate_t. * libc/stdlib/mblen_r.c: Likewise. * libc/stdlib/mbstowcs.c: Likewise. * libc/stdlib/mbstowcs_r.c: Likewise. * libc/stdlib/mbtowc.c: Likewise. * libc/stdlib/mbtowc_r.c: Likewise. * libc/stdlib/wcstombs.c: Likewise. * libc/stdlib/wcstombs_r.c: Likewise. * libc/stdlib/wctomb_r.c: Likewise. * libc/sys/linux/Makefile.am (LIB_SOURCES): Add prof-freq.c and profile.c. * libc/sys/linux/machine/i386/Makefile.am (LIB_SOURCES): Add dl-procinfo.c. * libc/sys/linux/sys/errno.h (EILSEQ): New error code. * libc/sys/linux/sys/types.h (off_t): Define type. * testsuite/newlib.locale/UTF-8.c: Change locale name from UTF-8 to C-UTF-8. * testsuite/newlib.locale/UTF-8.exp: Likewise.
2002-08-23 09:56:05 +08:00
return -2;
2000-02-18 03:39:52 +08:00
* 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 18:13:27 +08:00
if (*t >= 0xa0)
{
* 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 18:13:27 +08:00
if (iso_idx >= 0)
{
* 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 18:13:27 +08:00
*pwc = __iso_8859_conv[iso_idx][*t - 0xa0];
if (*pwc == 0) /* Invalid character */
{
r->_errno = EILSEQ;
return -1;
}
* 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 18:13:27 +08:00
return 1;
}
* 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 18:13:27 +08:00
}
*pwc = (wchar_t) *t;
if (*t == '\0')
return 0;
return 1;
}
static int
__iso_8859_1_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___iso_mbtowc (r, pwc, s, n, -1, state);
}
static int
__iso_8859_2_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___iso_mbtowc (r, pwc, s, n, 0, state);
}
static int
__iso_8859_3_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___iso_mbtowc (r, pwc, s, n, 1, state);
}
static int
__iso_8859_4_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___iso_mbtowc (r, pwc, s, n, 2, state);
}
static int
__iso_8859_5_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___iso_mbtowc (r, pwc, s, n, 3, state);
}
static int
__iso_8859_6_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___iso_mbtowc (r, pwc, s, n, 4, state);
}
static int
__iso_8859_7_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___iso_mbtowc (r, pwc, s, n, 5, state);
}
static int
__iso_8859_8_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___iso_mbtowc (r, pwc, s, n, 6, state);
}
static int
__iso_8859_9_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___iso_mbtowc (r, pwc, s, n, 7, state);
}
static int
__iso_8859_10_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___iso_mbtowc (r, pwc, s, n, 8, state);
}
static int
__iso_8859_11_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___iso_mbtowc (r, pwc, s, n, 9, state);
}
static int
__iso_8859_13_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___iso_mbtowc (r, pwc, s, n, 10, state);
}
static int
__iso_8859_14_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___iso_mbtowc (r, pwc, s, n, 11, state);
}
static int
__iso_8859_15_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___iso_mbtowc (r, pwc, s, n, 12, state);
}
static int
__iso_8859_16_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___iso_mbtowc (r, pwc, s, n, 13, state);
}
static mbtowc_p __iso_8859_mbtowc[17] = {
NULL,
__iso_8859_1_mbtowc,
__iso_8859_2_mbtowc,
__iso_8859_3_mbtowc,
__iso_8859_4_mbtowc,
__iso_8859_5_mbtowc,
__iso_8859_6_mbtowc,
__iso_8859_7_mbtowc,
__iso_8859_8_mbtowc,
__iso_8859_9_mbtowc,
__iso_8859_10_mbtowc,
__iso_8859_11_mbtowc,
NULL, /* No ISO 8859-12 */
__iso_8859_13_mbtowc,
__iso_8859_14_mbtowc,
__iso_8859_15_mbtowc,
__iso_8859_16_mbtowc
};
/* val *MUST* be valid! All checks for validity are supposed to be
performed before calling this function. */
mbtowc_p
__iso_mbtowc (int val)
{
return __iso_8859_mbtowc[val];
}
* 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 18:13:27 +08:00
#endif /* _MB_EXTENDED_CHARSETS_ISO */
#ifdef _MB_EXTENDED_CHARSETS_WINDOWS
static int
___cp_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
int cp_idx, mbstate_t *state)
* 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 18:13:27 +08:00
{
wchar_t dummy;
unsigned char *t = (unsigned char *)s;
if (pwc == NULL)
pwc = &dummy;
if (s == NULL)
return 0;
if (n == 0)
return -2;
if (*t >= 0x80)
{
if (cp_idx >= 0)
{
* 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 18:13:27 +08:00
*pwc = __cp_conv[cp_idx][*t - 0x80];
if (*pwc == 0) /* Invalid character */
{
r->_errno = EILSEQ;
return -1;
}
* 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 18:13:27 +08:00
return 1;
}
* 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 18:13:27 +08:00
}
*pwc = (wchar_t)*t;
if (*t == '\0')
return 0;
return 1;
}
static int
__cp_437_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 0, state);
}
static int
__cp_720_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 1, state);
}
static int
__cp_737_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 2, state);
}
static int
__cp_775_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 3, state);
}
static int
__cp_850_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 4, state);
}
static int
__cp_852_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 5, state);
}
static int
__cp_855_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 6, state);
}
static int
__cp_857_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 7, state);
}
static int
__cp_858_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 8, state);
}
static int
__cp_862_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 9, state);
}
static int
__cp_866_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 10, state);
}
static int
__cp_874_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 11, state);
}
static int
__cp_1125_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 12, state);
}
static int
__cp_1250_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 13, state);
}
static int
__cp_1251_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 14, state);
}
static int
__cp_1252_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 15, state);
}
static int
__cp_1253_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 16, state);
}
static int
__cp_1254_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 17, state);
}
static int
__cp_1255_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 18, state);
}
static int
__cp_1256_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 19, state);
}
static int
__cp_1257_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 20, state);
}
static int
__cp_1258_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 21, state);
}
static int
__cp_20866_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 22, state);
}
static int
__cp_21866_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 23, state);
}
static int
__cp_101_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 24, state);
}
static int
__cp_102_mbtowc (struct _reent *r, wchar_t *pwc, const char *s, size_t n,
mbstate_t *state)
{
return ___cp_mbtowc (r, pwc, s, n, 25, state);
}
static mbtowc_p __cp_xxx_mbtowc[26] = {
__cp_437_mbtowc,
__cp_720_mbtowc,
__cp_737_mbtowc,
__cp_775_mbtowc,
__cp_850_mbtowc,
__cp_852_mbtowc,
__cp_855_mbtowc,
__cp_857_mbtowc,
__cp_858_mbtowc,
__cp_862_mbtowc,
__cp_866_mbtowc,
__cp_874_mbtowc,
__cp_1125_mbtowc,
__cp_1250_mbtowc,
__cp_1251_mbtowc,
__cp_1252_mbtowc,
__cp_1253_mbtowc,
__cp_1254_mbtowc,
__cp_1255_mbtowc,
__cp_1256_mbtowc,
__cp_1257_mbtowc,
__cp_1258_mbtowc,
__cp_20866_mbtowc,
__cp_21866_mbtowc,
__cp_101_mbtowc,
__cp_102_mbtowc
};
/* val *MUST* be valid! All checks for validity are supposed to be
performed before calling this function. */
mbtowc_p
__cp_mbtowc (int val)
{
return __cp_xxx_mbtowc[__cp_val_index (val)];
}
* 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 18:13:27 +08:00
#endif /* _MB_EXTENDED_CHARSETS_WINDOWS */
int
_DEFUN (__utf8_mbtowc, (r, pwc, s, n, state),
* 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 18:13:27 +08:00
struct _reent *r _AND
wchar_t *pwc _AND
const char *s _AND
size_t n _AND
mbstate_t *state)
{
wchar_t dummy;
unsigned char *t = (unsigned char *)s;
int ch;
int i = 0;
if (pwc == NULL)
pwc = &dummy;
if (s == NULL)
return 0;
if (n == 0)
return -2;
if (state->__count == 0)
ch = t[i++];
else
ch = state->__value.__wchb[0];
* 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 18:13:27 +08:00
if (ch == '\0')
{
*pwc = 0;
state->__count = 0;
return 0; /* s points to the null character */
}
if (ch <= 0x7f)
* 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 18:13:27 +08:00
{
/* single-byte sequence */
state->__count = 0;
*pwc = ch;
return 1;
}
if (ch >= 0xc0 && ch <= 0xdf)
{
/* two-byte sequence */
state->__value.__wchb[0] = ch;
if (state->__count == 0)
state->__count = 1;
else if (n < (size_t)-1)
++n;
* 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 18:13:27 +08:00
if (n < 2)
return -2;
ch = t[i++];
if (ch < 0x80 || ch > 0xbf)
{
* 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 18:13:27 +08:00
r->_errno = EILSEQ;
return -1;
}
* 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 18:13:27 +08:00
if (state->__value.__wchb[0] < 0xc2)
{
* 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 18:13:27 +08:00
/* overlong UTF-8 sequence */
r->_errno = EILSEQ;
return -1;
}
* 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 18:13:27 +08:00
state->__count = 0;
*pwc = (wchar_t)((state->__value.__wchb[0] & 0x1f) << 6)
| (wchar_t)(ch & 0x3f);
return i;
}
if (ch >= 0xe0 && ch <= 0xef)
2000-02-18 03:39:52 +08:00
{
* 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 18:13:27 +08:00
/* three-byte sequence */
wchar_t tmp;
state->__value.__wchb[0] = ch;
if (state->__count == 0)
* 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 18:13:27 +08:00
state->__count = 1;
else if (n < (size_t)-1)
++n;
if (n < 2)
return -2;
ch = (state->__count == 1) ? t[i++] : state->__value.__wchb[1];
if (state->__value.__wchb[0] == 0xe0 && ch < 0xa0)
{
* 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 18:13:27 +08:00
/* overlong UTF-8 sequence */
r->_errno = EILSEQ;
return -1;
}
* 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 18:13:27 +08:00
if (ch < 0x80 || ch > 0xbf)
{
* 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 18:13:27 +08:00
r->_errno = EILSEQ;
return -1;
}
state->__value.__wchb[1] = ch;
if (state->__count == 1)
state->__count = 2;
else if (n < (size_t)-1)
++n;
* 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 18:13:27 +08:00
if (n < 3)
return -2;
ch = t[i++];
if (ch < 0x80 || ch > 0xbf)
{
r->_errno = EILSEQ;
return -1;
}
* 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 18:13:27 +08:00
state->__count = 0;
tmp = (wchar_t)((state->__value.__wchb[0] & 0x0f) << 12)
| (wchar_t)((state->__value.__wchb[1] & 0x3f) << 6)
| (wchar_t)(ch & 0x3f);
*pwc = tmp;
return i;
2000-02-18 03:39:52 +08:00
}
if (ch >= 0xf0 && ch <= 0xf4)
2000-02-18 03:39:52 +08:00
{
* 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 18:13:27 +08:00
/* four-byte sequence */
wint_t tmp;
state->__value.__wchb[0] = ch;
if (state->__count == 0)
* 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 18:13:27 +08:00
state->__count = 1;
else if (n < (size_t)-1)
++n;
if (n < 2)
return -2;
ch = (state->__count == 1) ? t[i++] : state->__value.__wchb[1];
if ((state->__value.__wchb[0] == 0xf0 && ch < 0x90)
|| (state->__value.__wchb[0] == 0xf4 && ch >= 0x90))
{
/* overlong UTF-8 sequence or result is > 0x10ffff */
* 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 18:13:27 +08:00
r->_errno = EILSEQ;
return -1;
}
if (ch < 0x80 || ch > 0xbf)
{
r->_errno = EILSEQ;
return -1;
}
* 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 18:13:27 +08:00
state->__value.__wchb[1] = ch;
if (state->__count == 1)
* 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 18:13:27 +08:00
state->__count = 2;
else if (n < (size_t)-1)
++n;
if (n < 3)
return -2;
ch = (state->__count == 2) ? t[i++] : state->__value.__wchb[2];
if (ch < 0x80 || ch > 0xbf)
{
* 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 18:13:27 +08:00
r->_errno = EILSEQ;
return -1;
}
state->__value.__wchb[2] = ch;
if (state->__count == 2)
state->__count = 3;
else if (n < (size_t)-1)
++n;
if (state->__count == 3 && sizeof(wchar_t) == 2)
{
/* On systems which have wchar_t being UTF-16 values, the value
doesn't fit into a single wchar_t in this case. So what we
do here is to store the state with a special value of __count
and return the first half of a surrogate pair. The first
three bytes of a UTF-8 sequence are enough to generate the
first half of a UTF-16 surrogate pair. As return value we
choose to return the number of bytes actually read up to
here.
The second half of the surrogate pair is returned in case we
recognize the special __count value of four, and the next
byte is actually a valid value. See below. */
tmp = (wint_t)((state->__value.__wchb[0] & 0x07) << 18)
| (wint_t)((state->__value.__wchb[1] & 0x3f) << 12)
| (wint_t)((state->__value.__wchb[2] & 0x3f) << 6);
state->__count = 4;
*pwc = 0xd800 | ((tmp - 0x10000) >> 10);
return i;
}
* 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 18:13:27 +08:00
if (n < 4)
return -2;
ch = t[i++];
if (ch < 0x80 || ch > 0xbf)
{
r->_errno = EILSEQ;
return -1;
}
* 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 18:13:27 +08:00
tmp = (wint_t)((state->__value.__wchb[0] & 0x07) << 18)
| (wint_t)((state->__value.__wchb[1] & 0x3f) << 12)
| (wint_t)((state->__value.__wchb[2] & 0x3f) << 6)
| (wint_t)(ch & 0x3f);
if (state->__count == 4 && sizeof(wchar_t) == 2)
/* Create the second half of the surrogate pair for systems with
wchar_t == UTF-16 . */
*pwc = 0xdc00 | (tmp & 0x3ff);
else
*pwc = tmp;
* 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 18:13:27 +08:00
state->__count = 0;
return i;
2000-02-18 03:39:52 +08:00
}
* 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 18:13:27 +08:00
r->_errno = EILSEQ;
return -1;
}
2000-02-18 03:39:52 +08:00
* 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 18:13:27 +08:00
/* Cygwin defines its own doublebyte charset conversion functions
because the underlying OS requires wchar_t == UTF-16. */
#ifndef __CYGWIN__
int
_DEFUN (__sjis_mbtowc, (r, pwc, s, n, state),
* 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 18:13:27 +08:00
struct _reent *r _AND
wchar_t *pwc _AND
const char *s _AND
size_t n _AND
mbstate_t *state)
{
wchar_t dummy;
unsigned char *t = (unsigned char *)s;
int ch;
int i = 0;
2000-02-18 03:39:52 +08:00
* 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 18:13:27 +08:00
if (pwc == NULL)
pwc = &dummy;
2000-02-18 03:39:52 +08:00
if (s == NULL)
return 0; /* not state-dependent */
* 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 18:13:27 +08:00
if (n == 0)
return -2;
ch = t[i++];
if (state->__count == 0)
{
if (_issjis1 (ch))
{
state->__value.__wchb[0] = ch;
state->__count = 1;
if (n <= 1)
return -2;
ch = t[i++];
}
}
if (state->__count == 1)
{
if (_issjis2 (ch))
{
*pwc = (((wchar_t)state->__value.__wchb[0]) << 8) + (wchar_t)ch;
state->__count = 0;
return i;
}
else
{
r->_errno = EILSEQ;
return -1;
}
}
*pwc = (wchar_t)*t;
if (*t == '\0')
return 0;
return 1;
}
int
_DEFUN (__eucjp_mbtowc, (r, pwc, s, n, state),
* 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 18:13:27 +08:00
struct _reent *r _AND
wchar_t *pwc _AND
const char *s _AND
size_t n _AND
mbstate_t *state)
{
wchar_t dummy;
unsigned char *t = (unsigned char *)s;
int ch;
int i = 0;
if (pwc == NULL)
pwc = &dummy;
if (s == NULL)
return 0;
if (n == 0)
return -2;
ch = t[i++];
if (state->__count == 0)
{
if (_iseucjp1 (ch))
* 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 18:13:27 +08:00
{
state->__value.__wchb[0] = ch;
state->__count = 1;
if (n <= 1)
return -2;
ch = t[i++];
}
}
if (state->__count == 1)
{
if (_iseucjp2 (ch))
* 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 18:13:27 +08:00
{
if (state->__value.__wchb[0] == 0x8f)
{
state->__value.__wchb[1] = ch;
state->__count = 2;
if (n <= i)
return -2;
ch = t[i++];
}
else
{
*pwc = (((wchar_t)state->__value.__wchb[0]) << 8) + (wchar_t)ch;
state->__count = 0;
return i;
}
}
else
{
r->_errno = EILSEQ;
return -1;
}
}
if (state->__count == 2)
{
if (_iseucjp2 (ch))
{
*pwc = (((wchar_t)state->__value.__wchb[1]) << 8)
+ (wchar_t)(ch & 0x7f);
* 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 18:13:27 +08:00
state->__count = 0;
return i;
}
else
{
r->_errno = EILSEQ;
return -1;
}
}
2000-02-18 03:39:52 +08:00
*pwc = (wchar_t)*t;
if (*t == '\0')
return 0;
return 1;
}
* 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 18:13:27 +08:00
int
_DEFUN (__jis_mbtowc, (r, pwc, s, n, state),
* 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 18:13:27 +08:00
struct _reent *r _AND
wchar_t *pwc _AND
const char *s _AND
size_t n _AND
mbstate_t *state)
{
wchar_t dummy;
unsigned char *t = (unsigned char *)s;
JIS_STATE curr_state;
JIS_ACTION action;
JIS_CHAR_TYPE ch;
unsigned char *ptr;
unsigned int i;
int curr_ch;
if (pwc == NULL)
pwc = &dummy;
if (s == NULL)
{
state->__state = ASCII;
return 1; /* state-dependent */
}
if (n == 0)
return -2;
curr_state = state->__state;
ptr = t;
for (i = 0; i < n; ++i)
{
curr_ch = t[i];
switch (curr_ch)
{
case ESC_CHAR:
ch = ESCAPE;
break;
case '$':
ch = DOLLAR;
break;
case '@':
ch = AT;
break;
case '(':
ch = BRACKET;
break;
case 'B':
ch = B;
break;
case 'J':
ch = J;
break;
case '\0':
ch = NUL;
break;
default:
if (_isjis (curr_ch))
ch = JIS_CHAR;
else
ch = OTHER;
}
action = JIS_action_table[curr_state][ch];
curr_state = JIS_state_table[curr_state][ch];
switch (action)
{
case NOOP:
break;
case EMPTY:
state->__state = ASCII;
*pwc = (wchar_t)0;
return 0;
case COPY_A:
state->__state = ASCII;
*pwc = (wchar_t)*ptr;
return (i + 1);
case COPY_J1:
state->__value.__wchb[0] = t[i];
break;
case COPY_J2:
state->__state = JIS;
*pwc = (((wchar_t)state->__value.__wchb[0]) << 8) + (wchar_t)(t[i]);
return (i + 1);
case MAKE_A:
ptr = (unsigned char *)(t + i + 1);
break;
case ERROR:
default:
r->_errno = EILSEQ;
return -1;
}
}
state->__state = curr_state;
return -2; /* n < bytes needed */
}
#endif /* !__CYGWIN__*/
#endif /* _MB_CAPABLE */