locale/gbk-fbsd.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 #include <sys/param.h>
  39 __FBSDID("$FreeBSD: src/lib/libc/locale/gbk.c,v 1.11 2004/05/17 11:16:14 tjr Exp $");
  40
  41 #include "xlocale_private.h"
  42
  43 #include <errno.h>
  44 #include <runetype.h>
  45 #include <stdlib.h>
  46 #include <string.h>
  47 #include <wchar.h>
  48 #include "mblocal.h"
  49
  50 __private_extern__ int  _GBK_init(struct __xlocale_st_runelocale *);
  51 static size_t   _GBK_mbrtowc(wchar_t * __restrict, const char * __restrict, size_t,
  52             mbstate_t * __restrict, locale_t);
  53 static int      _GBK_mbsinit(const mbstate_t *, locale_t);
  54 static size_t   _GBK_wcrtomb(char * __restrict, wchar_t, mbstate_t * __restrict, locale_t);
  55
  56 typedef struct {
  57         wchar_t ch;
  58 } _GBKState;
  59
  60 __private_extern__ int
  61 _GBK_init(struct __xlocale_st_runelocale *xrl)
  62 {
  63
  64         xrl->__mbrtowc = _GBK_mbrtowc;
  65         xrl->__wcrtomb = _GBK_wcrtomb;
  66         xrl->__mbsinit = _GBK_mbsinit;
  67         xrl->__mb_cur_max = 2;
  68         return (0);
  69 }
  70
  71 static int
  72 _GBK_mbsinit(const mbstate_t *ps, locale_t loc)
  73 {
  74
  75         return (ps == NULL || ((const _GBKState *)ps)->ch == 0);
  76 }
  77
  78 static __inline int
  79 _gbk_check(u_int c)
  80 {
  81
  82         c &= 0xff;
  83         return ((c >= 0x81 && c <= 0xfe) ? 2 : 1);
  84 }
  85
  86 static size_t
  87 _GBK_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n,
  88     mbstate_t * __restrict ps, locale_t loc)
  89 {
  90         _GBKState *gs;
  91         wchar_t wc;
  92         size_t len;
  93
  94         gs = (_GBKState *)ps;
  95
  96         if ((gs->ch & ~0xFF) != 0) {
  97                 /* Bad conversion state. */
  98                 errno = EINVAL;
  99                 return ((size_t)-1);
 100         }
 101
 102         if (s == NULL) {
 103                 s = "";
 104                 n = 1;
 105                 pwc = NULL;
 106         }
 107
 108         if (n == 0)
 109                 /* Incomplete multibyte sequence */
 110                 return ((size_t)-2);
 111
 112         if (gs->ch != 0) {
 113                 if (*s == '\0') {
 114                         errno = EILSEQ;
 115                         return ((size_t)-1);
 116                 }
 117                 wc = (gs->ch << 8) | (*s & 0xFF);
 118                 if (pwc != NULL)
 119                         *pwc = wc;
 120                 gs->ch = 0;
 121                 return (1);
 122         }
 123
 124         len = (size_t)_gbk_check(*s);
 125         wc = *s++ & 0xff;
 126         if (len == 2) {
 127                 if (n < 2) {
 128                         /* Incomplete multibyte sequence */
 129                         gs->ch = wc;
 130                         return ((size_t)-2);
 131                 }
 132                 if (*s == '\0') {
 133                         errno = EILSEQ;
 134                         return ((size_t)-1);
 135                 }
 136                 wc = (wc << 8) | (*s++ & 0xff);
 137                 if (pwc != NULL)
 138                         *pwc = wc;
 139                 return (2);
 140         } else {
 141                 if (pwc != NULL)
 142                         *pwc = wc;
 143                 return (wc == L'\0' ? 0 : 1);
 144         }
 145 }
 146
 147 static size_t
 148 _GBK_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps, locale_t loc)
 149 {
 150         _GBKState *gs;
 151
 152         gs = (_GBKState *)ps;
 153
 154         if (gs->ch != 0) {
 155                 errno = EINVAL;
 156                 return ((size_t)-1);
 157         }
 158
 159         if (s == NULL)
 160                 /* Reset to initial shift state (no-op) */
 161                 return (1);
 162         if (wc & 0x8000) {
 163                 *s++ = (wc >> 8) & 0xff;
 164                 *s = wc & 0xff;
 165                 return (2);
 166         }
 167         *s = wc & 0xff;
 168         return (1);
 169 }