usr/src/lib/libc/port/locale/mskanji.c

   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. All rights reserved.
   5  *
   6  *    ja_JP.SJIS locale table for BSD4.4/rune
   7  *    version 1.0
   8  *    (C) Sin'ichiro MIYATANI / Phase One, Inc
   9  *    May 12, 1995
  10  *
  11  * Redistribution and use in source and binary forms, with or without
  12  * modification, are permitted provided that the following conditions
  13  * are met:
  14  * 1. Redistributions of source code must retain the above copyright
  15  *    notice, this list of conditions and the following disclaimer.
  16  * 2. Redistributions in binary form must reproduce the above copyright
  17  *    notice, this list of conditions and the following disclaimer in the
  18  *    documentation and/or other materials provided with the distribution.
  19  * 3. All advertising materials mentioning features or use of this software
  20  *    must display the following acknowledgement:
  21  *      This product includes software developed by Phase One, Inc.
  22  * 4. The name of Phase One, Inc. may be used to endorse or promote products
  23  *    derived from this software without specific prior written permission.
  24  *
  25  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  26  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  27  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  28  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  29  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  30  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  31  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  32  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  33  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  34  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  35  * SUCH DAMAGE.
  36  */
  37
  38 #include "lint.h"
  39 #include <sys/types.h>
  40 #include <errno.h>
  41 #include <stdlib.h>
  42 #include <string.h>
  43 #include <wchar.h>
  44 #include "mblocal.h"
  45 #include "lctype.h"
  46
  47 static size_t   _MSKanji_mbrtowc(wchar_t *_RESTRICT_KYWD,
  48                     const char *_RESTRICT_KYWD,
  49                     size_t, mbstate_t *_RESTRICT_KYWD);
  50 static int      _MSKanji_mbsinit(const mbstate_t *);
  51 static size_t   _MSKanji_wcrtomb(char *_RESTRICT_KYWD, wchar_t,
  52                     mbstate_t *_RESTRICT_KYWD);
  53 static size_t   _MSKanji_mbsnrtowcs(wchar_t *_RESTRICT_KYWD,
  54                     const char **_RESTRICT_KYWD, size_t, size_t,
  55                     mbstate_t *_RESTRICT_KYWD);
  56 static size_t   _MSKanji_wcsnrtombs(char *_RESTRICT_KYWD,
  57                     const wchar_t **_RESTRICT_KYWD, size_t, size_t,
  58                     mbstate_t *_RESTRICT_KYWD);
  59
  60 typedef struct {
  61         wchar_t ch;
  62 } _MSKanjiState;
  63
  64 void
  65 _MSKanji_init(struct lc_ctype *lct)
  66 {
  67
  68         lct->lc_mbrtowc = _MSKanji_mbrtowc;
  69         lct->lc_wcrtomb = _MSKanji_wcrtomb;
  70         lct->lc_mbsnrtowcs = _MSKanji_mbsnrtowcs;
  71         lct->lc_wcsnrtombs = _MSKanji_wcsnrtombs;
  72         lct->lc_mbsinit = _MSKanji_mbsinit;
  73         lct->lc_max_mblen = 2;
  74         lct->lc_is_ascii = 0;
  75 }
  76
  77 static int
  78 _MSKanji_mbsinit(const mbstate_t *ps)
  79 {
  80
  81         return (ps == NULL || ((const _MSKanjiState *)ps)->ch == 0);
  82 }
  83
  84 static size_t
  85 _MSKanji_mbrtowc(wchar_t *_RESTRICT_KYWD pwc, const char *_RESTRICT_KYWD s,
  86     size_t n, mbstate_t *_RESTRICT_KYWD ps)
  87 {
  88         _MSKanjiState *ms;
  89         wchar_t wc;
  90
  91         ms = (_MSKanjiState *)ps;
  92
  93         if ((ms->ch & ~0xFF) != 0) {
  94                 /* Bad conversion state. */
  95                 errno = EINVAL;
  96                 return ((size_t)-1);
  97         }
  98
  99         if (s == NULL) {
 100                 s = "";
 101                 n = 1;
 102                 pwc = NULL;
 103         }
 104
 105         if (n == 0)
 106                 /* Incomplete multibyte sequence */
 107                 return ((size_t)-2);
 108
 109         if (ms->ch != 0) {
 110                 if (*s == '\0') {
 111                         errno = EILSEQ;
 112                         return ((size_t)-1);
 113                 }
 114                 wc = (ms->ch << 8) | (*s & 0xFF);
 115                 if (pwc != NULL)
 116                         *pwc = wc;
 117                 ms->ch = 0;
 118                 return (1);
 119         }
 120         wc = *s++ & 0xff;
 121         if ((wc > 0x80 && wc < 0xa0) || (wc >= 0xe0 && wc < 0xfd)) {
 122                 if (n < 2) {
 123                         /* Incomplete multibyte sequence */
 124                         ms->ch = wc;
 125                         return ((size_t)-2);
 126                 }
 127                 if (*s == '\0') {
 128                         errno = EILSEQ;
 129                         return ((size_t)-1);
 130                 }
 131                 wc = (wc << 8) | (*s++ & 0xff);
 132                 if (pwc != NULL)
 133                         *pwc = wc;
 134                 return (2);
 135         } else {
 136                 if (pwc != NULL)
 137                         *pwc = wc;
 138                 return (wc == L'\0' ? 0 : 1);
 139         }
 140 }
 141
 142 static size_t
 143 _MSKanji_wcrtomb(char *_RESTRICT_KYWD s, wchar_t wc,
 144     mbstate_t *_RESTRICT_KYWD ps)
 145 {
 146         _MSKanjiState *ms;
 147         int len, i;
 148
 149         ms = (_MSKanjiState *)ps;
 150
 151         if (ms->ch != 0) {
 152                 errno = EINVAL;
 153                 return ((size_t)-1);
 154         }
 155
 156         if (s == NULL)
 157                 /* Reset to initial shift state (no-op) */
 158                 return (1);
 159         len = (wc > 0x100) ? 2 : 1;
 160         for (i = len; i-- > 0; )
 161                 *s++ = wc >> (i << 3);
 162         return (len);
 163 }
 164
 165 static size_t
 166 _MSKanji_mbsnrtowcs(wchar_t *_RESTRICT_KYWD dst,
 167     const char **_RESTRICT_KYWD src, size_t nms,
 168     size_t len, mbstate_t *_RESTRICT_KYWD ps)
 169 {
 170         return (__mbsnrtowcs_std(dst, src, nms, len, ps, _MSKanji_mbrtowc));
 171 }
 172
 173 static size_t
 174 _MSKanji_wcsnrtombs(char *_RESTRICT_KYWD dst,
 175     const wchar_t **_RESTRICT_KYWD src, size_t nwc,
 176     size_t len, mbstate_t *_RESTRICT_KYWD ps)
 177 {
 178         return (__wcsnrtombs_std(dst, src, nwc, len, ps, _MSKanji_wcrtomb));
 179 }