Print this page
2964 need POSIX 2008 locale object support
Reviewed by: Robert Mustacchi <rm@joyent.com>
Reviewed by: Gordon Ross <gordon.ross@nexenta.com>
Approved by: TBD
   1 /*

   2  * Copyright 2010 Nexenta Systems, Inc.  All rights reserved.
   3  * Copyright (c) 2002-2004 Tim J. Robbins
   4  * All rights reserved.
   5  *
   6  * Redistribution and use in source and binary forms, with or without
   7  * modification, are permitted provided that the following conditions
   8  * are met:
   9  * 1. Redistributions of source code must retain the above copyright
  10  *    notice, this list of conditions and the following disclaimer.
  11  * 2. Redistributions in binary form must reproduce the above copyright
  12  *    notice, this list of conditions and the following disclaimer in the
  13  *    documentation and/or other materials provided with the distribution.
  14  *
  15  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
  16  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  17  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  18  * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
  19  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  20  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  21  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  22  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  23  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  24  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  25  * SUCH DAMAGE.
  26  */
  27 
  28 /*
  29  * PRC National Standard GB 18030-2000 encoding of Chinese text.
  30  *
  31  * See gb18030(5) for details.
  32  */
  33 
  34 #include "lint.h"
  35 #include <sys/types.h>
  36 #include <errno.h>
  37 #include "runetype.h"
  38 #include <stdlib.h>
  39 #include <string.h>
  40 #include <wchar.h>
  41 #include "mblocal.h"

  42 
  43 
  44 static size_t   _GB18030_mbrtowc(wchar_t *_RESTRICT_KYWD,
  45                     const char *_RESTRICT_KYWD,
  46                     size_t, mbstate_t *_RESTRICT_KYWD);
  47 static int      _GB18030_mbsinit(const mbstate_t *);
  48 static size_t   _GB18030_wcrtomb(char *_RESTRICT_KYWD, wchar_t,
  49                     mbstate_t *_RESTRICT_KYWD);






  50 

  51 typedef struct {
  52         int     count;
  53         uchar_t bytes[4];
  54 } _GB18030State;
  55 
  56 int
  57 _GB18030_init(_RuneLocale *rl)
  58 {
  59 
  60         __mbrtowc = _GB18030_mbrtowc;
  61         __wcrtomb = _GB18030_wcrtomb;
  62         __mbsinit = _GB18030_mbsinit;
  63         _CurrentRuneLocale = rl;
  64         __ctype[520] = 4;
  65         charset_is_ascii = 0;
  66 
  67         return (0);
  68 }
  69 
  70 static int
  71 _GB18030_mbsinit(const mbstate_t *ps)
  72 {
  73 
  74         return (ps == NULL || ((const _GB18030State *)ps)->count == 0);
  75 }
  76 
  77 static size_t
  78 _GB18030_mbrtowc(wchar_t *_RESTRICT_KYWD pwc, const char *_RESTRICT_KYWD s,
  79     size_t n, mbstate_t *_RESTRICT_KYWD ps)
  80 {
  81         _GB18030State *gs;
  82         wchar_t wch;
  83         int ch, len, ocount;
  84         size_t ncopy;
  85 
  86         gs = (_GB18030State *)ps;
  87 


 203         else if (wc & 0x0000ff00) {
 204                 c = (wc >> 8) & 0xff;
 205                 if (c < 0x81 || c > 0xfe)
 206                         goto ilseq;
 207                 *s++ = c;
 208                 c = wc & 0xff;
 209                 if (c < 0x40 || c == 0x7f || c == 0xff)
 210                         goto ilseq;
 211                 *s++ = c;
 212                 len = 2;
 213         } else if (wc <= 0x7f) {
 214                 *s++ = wc;
 215                 len = 1;
 216         } else
 217                 goto ilseq;
 218 
 219         return (len);
 220 ilseq:
 221         errno = EILSEQ;
 222         return ((size_t)-1);
















 223 }
   1 /*
   2  * Copyright 2013 Garrett D'Amore <garrett@damore.org>
   3  * Copyright 2010 Nexenta Systems, Inc.  All rights reserved.
   4  * Copyright (c) 2002-2004 Tim J. Robbins
   5  * All rights reserved.
   6  *
   7  * Redistribution and use in source and binary forms, with or without
   8  * modification, are permitted provided that the following conditions
   9  * are met:
  10  * 1. Redistributions of source code must retain the above copyright
  11  *    notice, this list of conditions and the following disclaimer.
  12  * 2. Redistributions in binary form must reproduce the above copyright
  13  *    notice, this list of conditions and the following disclaimer in the
  14  *    documentation and/or other materials provided with the distribution.
  15  *
  16  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
  17  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  18  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  19  * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
  20  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  21  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  22  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  23  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  24  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  25  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  26  * SUCH DAMAGE.
  27  */
  28 
  29 /*
  30  * PRC National Standard GB 18030-2000 encoding of Chinese text.
  31  *
  32  * See gb18030(5) for details.
  33  */
  34 
  35 #include "lint.h"
  36 #include <sys/types.h>
  37 #include <errno.h>

  38 #include <stdlib.h>
  39 #include <string.h>
  40 #include <wchar.h>
  41 #include "mblocal.h"
  42 #include "lctype.h"
  43 
  44 
  45 static size_t   _GB18030_mbrtowc(wchar_t *_RESTRICT_KYWD,
  46                     const char *_RESTRICT_KYWD,
  47                     size_t, mbstate_t *_RESTRICT_KYWD);
  48 static int      _GB18030_mbsinit(const mbstate_t *);
  49 static size_t   _GB18030_wcrtomb(char *_RESTRICT_KYWD, wchar_t,
  50                     mbstate_t *_RESTRICT_KYWD);
  51 static size_t   _GB18030_mbsnrtowcs(wchar_t *_RESTRICT_KYWD,
  52                     const char **_RESTRICT_KYWD, size_t, size_t,
  53                     mbstate_t *_RESTRICT_KYWD);
  54 static size_t   _GB18030_wcsnrtombs(char *_RESTRICT_KYWD,
  55                     const wchar_t **_RESTRICT_KYWD, size_t, size_t,
  56                     mbstate_t *_RESTRICT_KYWD);
  57 
  58 
  59 typedef struct {
  60         int     count;
  61         uchar_t bytes[4];
  62 } _GB18030State;
  63 
  64 void
  65 _GB18030_init(struct lc_ctype *lct)
  66 {
  67 
  68         lct->lc_mbrtowc = _GB18030_mbrtowc;
  69         lct->lc_wcrtomb = _GB18030_wcrtomb;
  70         lct->lc_mbsinit = _GB18030_mbsinit;
  71         lct->lc_mbsnrtowcs = _GB18030_mbsnrtowcs;
  72         lct->lc_wcsnrtombs = _GB18030_wcsnrtombs;
  73         lct->lc_max_mblen = 4;
  74         lct->lc_is_ascii = 0;

  75 }
  76 
  77 static int
  78 _GB18030_mbsinit(const mbstate_t *ps)
  79 {
  80 
  81         return (ps == NULL || ((const _GB18030State *)ps)->count == 0);
  82 }
  83 
  84 static size_t
  85 _GB18030_mbrtowc(wchar_t *_RESTRICT_KYWD pwc, const char *_RESTRICT_KYWD s,
  86     size_t n, mbstate_t *_RESTRICT_KYWD ps)
  87 {
  88         _GB18030State *gs;
  89         wchar_t wch;
  90         int ch, len, ocount;
  91         size_t ncopy;
  92 
  93         gs = (_GB18030State *)ps;
  94 


 210         else if (wc & 0x0000ff00) {
 211                 c = (wc >> 8) & 0xff;
 212                 if (c < 0x81 || c > 0xfe)
 213                         goto ilseq;
 214                 *s++ = c;
 215                 c = wc & 0xff;
 216                 if (c < 0x40 || c == 0x7f || c == 0xff)
 217                         goto ilseq;
 218                 *s++ = c;
 219                 len = 2;
 220         } else if (wc <= 0x7f) {
 221                 *s++ = wc;
 222                 len = 1;
 223         } else
 224                 goto ilseq;
 225 
 226         return (len);
 227 ilseq:
 228         errno = EILSEQ;
 229         return ((size_t)-1);
 230 }
 231 
 232 static size_t
 233 _GB18030_mbsnrtowcs(wchar_t *_RESTRICT_KYWD dst,
 234     const char **_RESTRICT_KYWD src, size_t nms, size_t len,
 235     mbstate_t *_RESTRICT_KYWD ps)
 236 {
 237         return (__mbsnrtowcs_std(dst, src, nms, len, ps, _GB18030_mbrtowc));
 238 }
 239 
 240 static size_t
 241 _GB18030_wcsnrtombs(char *_RESTRICT_KYWD dst,
 242     const wchar_t **_RESTRICT_KYWD src, size_t nwc, size_t len,
 243     mbstate_t *_RESTRICT_KYWD ps)
 244 {
 245         return (__wcsnrtombs_std(dst, src, nwc, len, ps, _GB18030_wcrtomb));
 246 }