compiler/clib/locale/big5.c

   1 /*-
   2  * Copyright (c) 2002-2004 Tim J. Robbins. All rights reserved.
   3  * Copyright (c) 1993
   4  *      The Regents of the University of California.  All rights reserved.
   5  *
   6  * This code is derived from software contributed to Berkeley by
   7  * Paul Borman at Krystal Technologies.
   8  *
   9  * Redistribution and use in source and binary forms, with or without
  10  * modification, are permitted provided that the following conditions
  11  * are met:
  12  * 1. Redistributions of source code must retain the above copyright
  13  *    notice, this list of conditions and the following disclaimer.
  14  * 2. Redistributions in binary form must reproduce the above copyright
  15  *    notice, this list of conditions and the following disclaimer in the
  16  *    documentation and/or other materials provided with the distribution.
  17  * 3. All advertising materials mentioning features or use of this software
  18  *    must display the following acknowledgement:
  19  *      This product includes software developed by the University of
  20  *      California, Berkeley and its contributors.
  21  * 4. Neither the name of the University nor the names of its contributors
  22  *    may be used to endorse or promote products derived from this software
  23  *    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 #if defined(LIBC_SCCS) && !defined(lint)
  39 static char sccsid[] = "@(#)big5.c      8.1 (Berkeley) 6/4/93";
  40 #endif /* LIBC_SCCS and not lint */
  41 #include <sys/cdefs.h>
  42 __FBSDID("$FreeBSD: src/lib/libc/locale/big5.c,v 1.18 2007/10/13 16:28:21 ache Exp $");
  43
  44 #include <sys/types.h>
  45 #include <errno.h>
  46 #include <runetype.h>
  47 #include <stdlib.h>
  48 #include <string.h>
  49 #include <wchar.h>
  50 #include "mblocal.h"
  51
  52 extern int __mb_sb_limit;
  53
  54 static size_t   _BIG5_mbrtowc(wchar_t * __restrict, const char * __restrict,
  55                     size_t, mbstate_t * __restrict);
  56 static int      _BIG5_mbsinit(const mbstate_t *);
  57 static size_t   _BIG5_wcrtomb(char * __restrict, wchar_t,
  58                     mbstate_t * __restrict);
  59
  60 typedef struct {
  61         wchar_t ch;
  62 } _BIG5State;
  63
  64 int
  65 _BIG5_init(_RuneLocale *rl)
  66 {
  67
  68         __mbrtowc = _BIG5_mbrtowc;
  69         __wcrtomb = _BIG5_wcrtomb;
  70         __mbsinit = _BIG5_mbsinit;
  71         _CurrentRuneLocale = rl;
  72         __mb_cur_max = 2;
  73         __mb_sb_limit = 128;
  74         return (0);
  75 }
  76
  77 static int
  78 _BIG5_mbsinit(const mbstate_t *ps)
  79 {
  80
  81         return (ps == NULL || ((const _BIG5State *)ps)->ch == 0);
  82 }
  83
  84 static __inline int
  85 _big5_check(u_int c)
  86 {
  87
  88         c &= 0xff;
  89         return ((c >= 0xa1 && c <= 0xfe) ? 2 : 1);
  90 }
  91
  92 static size_t
  93 _BIG5_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n,
  94     mbstate_t * __restrict ps)
  95 {
  96         _BIG5State *bs;
  97         wchar_t wc;
  98         size_t len;
  99
 100         bs = (_BIG5State *)ps;
 101
 102         if ((bs->ch & ~0xFF) != 0) {
 103                 /* Bad conversion state. */
 104                 errno = EINVAL;
 105                 return ((size_t)-1);
 106         }
 107
 108         if (s == NULL) {
 109                 s = "";
 110                 n = 1;
 111                 pwc = NULL;
 112         }
 113
 114         if (n == 0)
 115                 /* Incomplete multibyte sequence */
 116                 return ((size_t)-2);
 117
 118         if (bs->ch != 0) {
 119                 if (*s == '\0') {
 120                         errno = EILSEQ;
 121                         return ((size_t)-1);
 122                 }
 123                 wc = (bs->ch << 8) | (*s & 0xFF);
 124                 if (pwc != NULL)
 125                         *pwc = wc;
 126                 bs->ch = 0;
 127                 return (1);
 128         }
 129
 130         len = (size_t)_big5_check(*s);
 131         wc = *s++ & 0xff;
 132         if (len == 2) {
 133                 if (n < 2) {
 134                         /* Incomplete multibyte sequence */
 135                         bs->ch = wc;
 136                         return ((size_t)-2);
 137                 }
 138                 if (*s == '\0') {
 139                         errno = EILSEQ;
 140                         return ((size_t)-1);
 141                 }
 142                 wc = (wc << 8) | (*s++ & 0xff);
 143                 if (pwc != NULL)
 144                         *pwc = wc;
 145                 return (2);
 146         } else {
 147                 if (pwc != NULL)
 148                         *pwc = wc;
 149                 return (wc == L'\0' ? 0 : 1);
 150         }
 151 }
 152
 153 static size_t
 154 _BIG5_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps)
 155 {
 156         _BIG5State *bs;
 157
 158         bs = (_BIG5State *)ps;
 159
 160         if (bs->ch != 0) {
 161                 errno = EINVAL;
 162                 return ((size_t)-1);
 163         }
 164
 165         if (s == NULL)
 166                 /* Reset to initial shift state (no-op) */
 167                 return (1);
 168         if (wc & 0x8000) {
 169                 *s++ = (wc >> 8) & 0xff;
 170                 *s = wc & 0xff;
 171                 return (2);
 172         }
 173         *s = wc & 0xff;
 174         return (1);
 175 }