lib/libc/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  * Copyright (c) 2011 The FreeBSD Foundation
  12  * All rights reserved.
  13  * Portions of this software were developed by David Chisnall
  14  * under sponsorship from the FreeBSD Foundation.
  15  *
  16  * Redistribution and use in source and binary forms, with or without
  17  * modification, are permitted provided that the following conditions
  18  * are met:
  19  * 1. Redistributions of source code must retain the above copyright
  20  *    notice, this list of conditions and the following disclaimer.
  21  * 2. Redistributions in binary form must reproduce the above copyright
  22  *    notice, this list of conditions and the following disclaimer in the
  23  *    documentation and/or other materials provided with the distribution.
  24  * 3. Neither the name of the University nor the names of its contributors
  25  *    may be used to endorse or promote products derived from this software
  26  *    without specific prior written permission.
  27  *
  28  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  29  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  30  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  31  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  32  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  33  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  34  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  35  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  36  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  37  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  38  * SUCH DAMAGE.
  39  */
  40
  41 #include <sys/types.h>
  42 #include <errno.h>
  43 #include <runetype.h>
  44 #include <stdlib.h>
  45 #include <string.h>
  46 #include <wchar.h>
  47 #include "mblocal.h"
  48
  49 extern int __mb_sb_limit;
  50
  51 static size_t   _GBK_mbrtowc(wchar_t * __restrict, const char * __restrict,
  52                     size_t, mbstate_t * __restrict);
  53 static int      _GBK_mbsinit(const mbstate_t *);
  54 static size_t   _GBK_wcrtomb(char * __restrict, wchar_t,
  55                     mbstate_t * __restrict);
  56 static size_t   _GBK_mbsnrtowcs(wchar_t * __restrict,
  57                     const char ** __restrict, size_t, size_t,
  58                     mbstate_t * __restrict);
  59 static size_t   _GBK_wcsnrtombs(char * __restrict,
  60                     const wchar_t ** __restrict, size_t, size_t,
  61                     mbstate_t * __restrict);
  62
  63 typedef struct {
  64         wchar_t ch;
  65 } _GBKState;
  66
  67 int
  68 _GBK_init(struct xlocale_ctype *l, _RuneLocale *rl)
  69 {
  70
  71         l->__mbrtowc = _GBK_mbrtowc;
  72         l->__wcrtomb = _GBK_wcrtomb;
  73         l->__mbsinit = _GBK_mbsinit;
  74         l->__mbsnrtowcs = _GBK_mbsnrtowcs;
  75         l->__wcsnrtombs = _GBK_wcsnrtombs;
  76         l->runes = rl;
  77         l->__mb_cur_max = 2;
  78         l->__mb_sb_limit = 128;
  79         return (0);
  80 }
  81
  82 static int
  83 _GBK_mbsinit(const mbstate_t *ps)
  84 {
  85
  86         return (ps == NULL || ((const _GBKState *)ps)->ch == 0);
  87 }
  88
  89 static int
  90 _gbk_check(u_int c)
  91 {
  92
  93         c &= 0xff;
  94         return ((c >= 0x81 && c <= 0xfe) ? 2 : 1);
  95 }
  96
  97 static size_t
  98 _GBK_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n,
  99     mbstate_t * __restrict ps)
 100 {
 101         _GBKState *gs;
 102         wchar_t wc;
 103         size_t len;
 104
 105         gs = (_GBKState *)ps;
 106
 107         if ((gs->ch & ~0xFF) != 0) {
 108                 /* Bad conversion state. */
 109                 errno = EINVAL;
 110                 return ((size_t)-1);
 111         }
 112
 113         if (s == NULL) {
 114                 s = "";
 115                 n = 1;
 116                 pwc = NULL;
 117         }
 118
 119         if (n == 0)
 120                 /* Incomplete multibyte sequence */
 121                 return ((size_t)-2);
 122
 123         if (gs->ch != 0) {
 124                 if (*s == '\0') {
 125                         errno = EILSEQ;
 126                         return ((size_t)-1);
 127                 }
 128                 wc = (gs->ch << 8) | (*s & 0xFF);
 129                 if (pwc != NULL)
 130                         *pwc = wc;
 131                 gs->ch = 0;
 132                 return (1);
 133         }
 134
 135         len = (size_t)_gbk_check(*s);
 136         wc = *s++ & 0xff;
 137         if (len == 2) {
 138                 if (n < 2) {
 139                         /* Incomplete multibyte sequence */
 140                         gs->ch = wc;
 141                         return ((size_t)-2);
 142                 }
 143                 if (*s == '\0') {
 144                         errno = EILSEQ;
 145                         return ((size_t)-1);
 146                 }
 147                 wc = (wc << 8) | (*s++ & 0xff);
 148                 if (pwc != NULL)
 149                         *pwc = wc;
 150                 return (2);
 151         } else {
 152                 if (pwc != NULL)
 153                         *pwc = wc;
 154                 return (wc == L'\0' ? 0 : 1);
 155         }
 156 }
 157
 158 static size_t
 159 _GBK_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps)
 160 {
 161         _GBKState *gs;
 162
 163         gs = (_GBKState *)ps;
 164
 165         if (gs->ch != 0) {
 166                 errno = EINVAL;
 167                 return ((size_t)-1);
 168         }
 169
 170         if (s == NULL)
 171                 /* Reset to initial shift state (no-op) */
 172                 return (1);
 173         if (wc & 0x8000) {
 174                 *s++ = (wc >> 8) & 0xff;
 175                 *s = wc & 0xff;
 176                 return (2);
 177         }
 178         *s = wc & 0xff;
 179         return (1);
 180 }
 181
 182 static size_t
 183 _GBK_mbsnrtowcs(wchar_t * __restrict dst, const char ** __restrict src,
 184     size_t nms, size_t len, mbstate_t * __restrict ps)
 185 {
 186         return (__mbsnrtowcs_std(dst, src, nms, len, ps, _GBK_mbrtowc));
 187 }
 188
 189 static size_t
 190 _GBK_wcsnrtombs(char * __restrict dst, const wchar_t ** __restrict src,
 191     size_t nwc, size_t len, mbstate_t * __restrict ps)
 192 {
 193         return (__wcsnrtombs_std(dst, src, nwc, len, ps, _GBK_wcrtomb));
 194 }