locale/FreeBSD/gb2312.c

   1 /*-
   2  * Copyright (c) 2004 Tim J. Robbins. All rights reserved.
   3  * Copyright (c) 2003 David Xu <davidxu@freebsd.org>
   4  * All rights reserved.
   5  *
   6  * Redistribution and use in source and binary forms, with or without
   7  * modification, are permitted provided that the following conditions
   8  * are met:
   9  * 1. Redistributions of source code must retain the above copyright
  10  *    notice, this list of conditions and the following disclaimer.
  11  * 2. Redistributions in binary form must reproduce the above copyright
  12  *    notice, this list of conditions and the following disclaimer in the
  13  *    documentation and/or other materials provided with the distribution.
  14  *
  15  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
  16  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  17  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  18  * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
  19  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  20  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  21  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  22  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  23  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  24  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  25  * SUCH DAMAGE.
  26  */
  27
  28 #include <sys/param.h>
  29 __FBSDID("$FreeBSD: src/lib/libc/locale/gb2312.c,v 1.10 2007/10/13 16:28:21 ache Exp $");
  30
  31 #include "xlocale_private.h"
  32
  33 #include <errno.h>
  34 #include <runetype.h>
  35 #include <stdlib.h>
  36 #include <string.h>
  37 #include <wchar.h>
  38 #include "mblocal.h"
  39
  40 #define GB2312_MB_CUR_MAX       2
  41
  42 static size_t   _GB2312_mbrtowc(wchar_t * __restrict, const char * __restrict,
  43                     size_t, mbstate_t * __restrict, locale_t);
  44 static int      _GB2312_mbsinit(const mbstate_t *, locale_t);
  45 static size_t   _GB2312_wcrtomb(char * __restrict, wchar_t,
  46                     mbstate_t * __restrict, locale_t);
  47 typedef struct {
  48         int     count;
  49         u_char  bytes[2];
  50 } _GB2312State;
  51
  52 int
  53 _GB2312_init(struct __xlocale_st_runelocale *xrl)
  54 {
  55
  56         xrl->__mbrtowc = _GB2312_mbrtowc;
  57         xrl->__wcrtomb = _GB2312_wcrtomb;
  58         xrl->__mbsinit = _GB2312_mbsinit;
  59         xrl->__mb_cur_max = GB2312_MB_CUR_MAX;
  60         xrl->__mb_sb_limit = 128;
  61         return (0);
  62 }
  63
  64 static int
  65 _GB2312_mbsinit(const mbstate_t *ps, locale_t loc __unused)
  66 {
  67
  68         return (ps == NULL || ((const _GB2312State *)ps)->count == 0);
  69 }
  70
  71 static __inline int
  72 _GB2312_check(const char *str, size_t n)
  73 {
  74         const u_char *s = (const u_char *)str;
  75
  76         if (n == 0)
  77                 /* Incomplete multibyte sequence */
  78                 return (-2);
  79         if (s[0] >= 0xa1 && s[0] <= 0xfe) {
  80                 if (n < 2)
  81                         /* Incomplete multibyte sequence */
  82                         return (-2);
  83                 if (s[1] < 0xa1 || s[1] > 0xfe)
  84                         /* Invalid multibyte sequence */
  85                         return (-1);
  86                 return (2);
  87         } else if (s[0] & 0x80) {
  88                 /* Invalid multibyte sequence */
  89                 return (-1);
  90         }
  91         return (1);
  92 }
  93
  94 static size_t
  95 _GB2312_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n,
  96     mbstate_t * __restrict ps, locale_t loc __unused)
  97 {
  98         _GB2312State *gs;
  99         wchar_t wc;
 100         int i, len, ocount;
 101         size_t ncopy;
 102
 103         gs = (_GB2312State *)ps;
 104
 105         if (gs->count < 0 || gs->count > sizeof(gs->bytes)) {
 106                 errno = EINVAL;
 107                 return ((size_t)-1);
 108         }
 109
 110         if (s == NULL) {
 111                 s = "";
 112                 n = 1;
 113                 pwc = NULL;
 114         }
 115
 116         ncopy = MIN(MIN(n, GB2312_MB_CUR_MAX), sizeof(gs->bytes) - gs->count);
 117         memcpy(gs->bytes + gs->count, s, ncopy);
 118         ocount = gs->count;
 119         gs->count += ncopy;
 120         s = (char *)gs->bytes;
 121         n = gs->count;
 122
 123         if ((len = _GB2312_check(s, n)) < 0)
 124                 return ((size_t)len);
 125         wc = 0;
 126         i = len;
 127         while (i-- > 0)
 128                 wc = (wc << 8) | (unsigned char)*s++;
 129         if (pwc != NULL)
 130                 *pwc = wc;
 131         gs->count = 0;
 132         return (wc == L'\0' ? 0 : len - ocount);
 133 }
 134
 135 static size_t
 136 _GB2312_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps, locale_t loc __unused)
 137 {
 138         _GB2312State *gs;
 139
 140         gs = (_GB2312State *)ps;
 141
 142         if (gs->count != 0) {
 143                 errno = EINVAL;
 144                 return ((size_t)-1);
 145         }
 146
 147         if (s == NULL)
 148                 /* Reset to initial shift state (no-op) */
 149                 return (1);
 150         if (wc & 0x8000) {
 151                 *s++ = (wc >> 8) & 0xff;
 152                 *s = wc & 0xff;
 153                 return (2);
 154         }
 155         *s = wc & 0xff;
 156         return (1);
 157 }