usr/src/lib/libc/port/locale/gbk.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  * Copyright (c) 1993
   6  *      The Regents of the University of California.  All rights reserved.
   7  *
   8  * This code is derived from software contributed to Berkeley by
   9  * Paul Borman at Krystal Technologies.
  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  * 4. Neither the name of the University nor the names of its contributors
  20  *    may be used to endorse or promote products derived from this software
  21  *    without specific prior written permission.
  22  *
  23  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  24  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  25  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  26  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  27  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  28  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  29  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  30  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  31  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  32  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  33  * SUCH DAMAGE.
  34  */
  35
  36 #include "lint.h"
  37 #include <sys/types.h>
  38 #include <errno.h>
  39 #include <stdlib.h>
  40 #include <string.h>
  41 #include <wchar.h>
  42 #include "mblocal.h"
  43 #include "lctype.h"
  44
  45 static size_t   _GBK_mbrtowc(wchar_t *_RESTRICT_KYWD,
  46                     const char *_RESTRICT_KYWD,
  47                     size_t, mbstate_t *_RESTRICT_KYWD);
  48 static int      _GBK_mbsinit(const mbstate_t *);
  49 static size_t   _GBK_wcrtomb(char *_RESTRICT_KYWD, wchar_t,
  50                     mbstate_t *_RESTRICT_KYWD);
  51 static size_t   _GBK_mbsnrtowcs(wchar_t *_RESTRICT_KYWD,
  52                     const char **_RESTRICT_KYWD, size_t, size_t,
  53                     mbstate_t *_RESTRICT_KYWD);
  54 static size_t   _GBK_wcsnrtombs(char *_RESTRICT_KYWD,
  55                     const wchar_t **_RESTRICT_KYWD, size_t, size_t,
  56                     mbstate_t *_RESTRICT_KYWD);
  57
  58 typedef struct {
  59         wchar_t ch;
  60 } _GBKState;
  61
  62 void
  63 _GBK_init(struct lc_ctype *lct)
  64 {
  65         lct->lc_mbrtowc = _GBK_mbrtowc;
  66         lct->lc_wcrtomb = _GBK_wcrtomb;
  67         lct->lc_mbsinit = _GBK_mbsinit;
  68         lct->lc_mbsnrtowcs = _GBK_mbsnrtowcs;
  69         lct->lc_wcsnrtombs = _GBK_wcsnrtombs;
  70         lct->lc_max_mblen = 2;
  71         lct->lc_is_ascii = 0;
  72 }
  73
  74 static int
  75 _GBK_mbsinit(const mbstate_t *ps)
  76 {
  77
  78         return (ps == NULL || ((const _GBKState *)ps)->ch == 0);
  79 }
  80
  81 static int
  82 _gbk_check(uint_t c)
  83 {
  84
  85         c &= 0xff;
  86         return ((c >= 0x81 && c <= 0xfe) ? 2 : 1);
  87 }
  88
  89 static size_t
  90 _GBK_mbrtowc(wchar_t *_RESTRICT_KYWD pwc, const char *_RESTRICT_KYWD s,
  91     size_t n, mbstate_t *_RESTRICT_KYWD ps)
  92 {
  93         _GBKState *gs;
  94         wchar_t wc;
  95         size_t len;
  96
  97         gs = (_GBKState *)ps;
  98
  99         if ((gs->ch & ~0xFF) != 0) {
 100                 /* Bad conversion state. */
 101                 errno = EINVAL;
 102                 return ((size_t)-1);
 103         }
 104
 105         if (s == NULL) {
 106                 s = "";
 107                 n = 1;
 108                 pwc = NULL;
 109         }
 110
 111         if (n == 0)
 112                 /* Incomplete multibyte sequence */
 113                 return ((size_t)-2);
 114
 115         if (gs->ch != 0) {
 116                 if (*s == '\0') {
 117                         errno = EILSEQ;
 118                         return ((size_t)-1);
 119                 }
 120                 wc = (gs->ch << 8) | (*s & 0xFF);
 121                 if (pwc != NULL)
 122                         *pwc = wc;
 123                 gs->ch = 0;
 124                 return (1);
 125         }
 126
 127         len = (size_t)_gbk_check(*s);
 128         wc = *s++ & 0xff;
 129         if (len == 2) {
 130                 if (n < 2) {
 131                         /* Incomplete multibyte sequence */
 132                         gs->ch = wc;
 133                         return ((size_t)-2);
 134                 }
 135                 if (*s == '\0') {
 136                         errno = EILSEQ;
 137                         return ((size_t)-1);
 138                 }
 139                 wc = (wc << 8) | (*s++ & 0xff);
 140                 if (pwc != NULL)
 141                         *pwc = wc;
 142                 return (2);
 143         } else {
 144                 if (pwc != NULL)
 145                         *pwc = wc;
 146                 return (wc == L'\0' ? 0 : 1);
 147         }
 148 }
 149
 150 static size_t
 151 _GBK_wcrtomb(char *_RESTRICT_KYWD s, wchar_t wc, mbstate_t *_RESTRICT_KYWD ps)
 152 {
 153         _GBKState *gs;
 154
 155         gs = (_GBKState *)ps;
 156
 157         if (gs->ch != 0) {
 158                 errno = EINVAL;
 159                 return ((size_t)-1);
 160         }
 161
 162         if (s == NULL)
 163                 /* Reset to initial shift state (no-op) */
 164                 return (1);
 165         if (wc & 0x8000) {
 166                 *s++ = (wc >> 8) & 0xff;
 167                 *s = wc & 0xff;
 168                 return (2);
 169         }
 170         *s = wc & 0xff;
 171         return (1);
 172 }
 173
 174 static size_t
 175 _GBK_mbsnrtowcs(wchar_t *_RESTRICT_KYWD dst, const char **_RESTRICT_KYWD src,
 176     size_t nms, size_t len, mbstate_t *_RESTRICT_KYWD ps)
 177 {
 178         return (__mbsnrtowcs_std(dst, src, nms, len, ps, _GBK_mbrtowc));
 179 }
 180
 181 static size_t
 182 _GBK_wcsnrtombs(char *_RESTRICT_KYWD dst, const wchar_t **_RESTRICT_KYWD src,
 183     size_t nwc, size_t len, mbstate_t *_RESTRICT_KYWD ps)
 184 {
 185         return (__wcsnrtombs_std(dst, src, nwc, len, ps, _GBK_wcrtomb));
 186 }