lib/libc/locale/big5.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  * @(#)big5.c   8.1 (Berkeley) 6/4/93
  41  */
  42
  43 #include <sys/types.h>
  44 #include <errno.h>
  45 #include <runetype.h>
  46 #include <stdlib.h>
  47 #include <string.h>
  48 #include <wchar.h>
  49 #include "mblocal.h"
  50
  51 extern int __mb_sb_limit;
  52
  53 static size_t   _BIG5_mbrtowc(wchar_t * __restrict, const char * __restrict,
  54                     size_t, mbstate_t * __restrict);
  55 static int      _BIG5_mbsinit(const mbstate_t *);
  56 static size_t   _BIG5_wcrtomb(char * __restrict, wchar_t,
  57                     mbstate_t * __restrict);
  58 static size_t   _BIG5_mbsnrtowcs(wchar_t * __restrict,
  59                     const char ** __restrict, size_t, size_t,
  60                     mbstate_t * __restrict);
  61 static size_t   _BIG5_wcsnrtombs(char * __restrict,
  62                     const wchar_t ** __restrict, size_t, size_t,
  63                     mbstate_t * __restrict);
  64
  65 typedef struct {
  66         wchar_t ch;
  67 } _BIG5State;
  68
  69 int
  70 _BIG5_init(struct xlocale_ctype *l, _RuneLocale *rl)
  71 {
  72
  73         l->__mbrtowc = _BIG5_mbrtowc;
  74         l->__wcrtomb = _BIG5_wcrtomb;
  75         l->__mbsnrtowcs = _BIG5_mbsnrtowcs;
  76         l->__wcsnrtombs = _BIG5_wcsnrtombs;
  77         l->__mbsinit = _BIG5_mbsinit;
  78         l->runes = rl;
  79         l->__mb_cur_max = 2;
  80         l->__mb_sb_limit = 128;
  81         return (0);
  82 }
  83
  84 static int
  85 _BIG5_mbsinit(const mbstate_t *ps)
  86 {
  87
  88         return (ps == NULL || ((const _BIG5State *)ps)->ch == 0);
  89 }
  90
  91 static __inline int
  92 _big5_check(u_int c)
  93 {
  94
  95         c &= 0xff;
  96         return ((c >= 0xa1 && c <= 0xfe) ? 2 : 1);
  97 }
  98
  99 static size_t
 100 _BIG5_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n,
 101     mbstate_t * __restrict ps)
 102 {
 103         _BIG5State *bs;
 104         wchar_t wc;
 105         size_t len;
 106
 107         bs = (_BIG5State *)ps;
 108
 109         if ((bs->ch & ~0xFF) != 0) {
 110                 /* Bad conversion state. */
 111                 errno = EINVAL;
 112                 return ((size_t)-1);
 113         }
 114
 115         if (s == NULL) {
 116                 s = "";
 117                 n = 1;
 118                 pwc = NULL;
 119         }
 120
 121         if (n == 0)
 122                 /* Incomplete multibyte sequence */
 123                 return ((size_t)-2);
 124
 125         if (bs->ch != 0) {
 126                 if (*s == '\0') {
 127                         errno = EILSEQ;
 128                         return ((size_t)-1);
 129                 }
 130                 wc = (bs->ch << 8) | (*s & 0xFF);
 131                 if (pwc != NULL)
 132                         *pwc = wc;
 133                 bs->ch = 0;
 134                 return (1);
 135         }
 136
 137         len = (size_t)_big5_check(*s);
 138         wc = *s++ & 0xff;
 139         if (len == 2) {
 140                 if (n < 2) {
 141                         /* Incomplete multibyte sequence */
 142                         bs->ch = wc;
 143                         return ((size_t)-2);
 144                 }
 145                 if (*s == '\0') {
 146                         errno = EILSEQ;
 147                         return ((size_t)-1);
 148                 }
 149                 wc = (wc << 8) | (*s++ & 0xff);
 150                 if (pwc != NULL)
 151                         *pwc = wc;
 152                 return (2);
 153         } else {
 154                 if (pwc != NULL)
 155                         *pwc = wc;
 156                 return (wc == L'\0' ? 0 : 1);
 157         }
 158 }
 159
 160 static size_t
 161 _BIG5_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps)
 162 {
 163         _BIG5State *bs;
 164
 165         bs = (_BIG5State *)ps;
 166
 167         if (bs->ch != 0) {
 168                 errno = EINVAL;
 169                 return ((size_t)-1);
 170         }
 171
 172         if (s == NULL)
 173                 /* Reset to initial shift state (no-op) */
 174                 return (1);
 175         if (wc & 0x8000) {
 176                 *s++ = (wc >> 8) & 0xff;
 177                 *s = wc & 0xff;
 178                 return (2);
 179         }
 180         *s = wc & 0xff;
 181         return (1);
 182 }
 183
 184 static size_t
 185 _BIG5_mbsnrtowcs(wchar_t * __restrict dst, const char ** __restrict src,
 186     size_t nms, size_t len, mbstate_t * __restrict ps)
 187 {
 188         return (__mbsnrtowcs_std(dst, src, nms, len, ps, _BIG5_mbrtowc));
 189 }
 190
 191 static size_t
 192 _BIG5_wcsnrtombs(char * __restrict dst, const wchar_t ** __restrict src,
 193     size_t nwc, size_t len, mbstate_t * __restrict ps)
 194 {
 195         return (__wcsnrtombs_std(dst, src, nwc, len, ps, _BIG5_wcrtomb));
 196 }