compiler/clib/locale/gbk.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  * 4. Neither the name of the University nor the names of its contributors
  18  *    may be used to endorse or promote products derived from this software
  19  *    without specific prior written permission.
  20  *
  21  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
  22  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  23  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  24  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
  25  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  26  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  27  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  28  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  29  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  30  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  31  * SUCH DAMAGE.
  32  */
  33
  34 #include <sys/cdefs.h>
  35 __FBSDID("$FreeBSD: src/lib/libc/locale/gbk.c,v 1.14 2007/10/13 16:28:21 ache Exp $");
  36
  37 #include <sys/types.h>
  38 #include <errno.h>
  39 #include <runetype.h>
  40 #include <stdlib.h>
  41 #include <string.h>
  42 #include <wchar.h>
  43 #include "mblocal.h"
  44
  45 extern int __mb_sb_limit;
  46
  47 static size_t   _GBK_mbrtowc(wchar_t * __restrict, const char * __restrict,
  48                     size_t, mbstate_t * __restrict);
  49 static int      _GBK_mbsinit(const mbstate_t *);
  50 static size_t   _GBK_wcrtomb(char * __restrict, wchar_t,
  51                     mbstate_t * __restrict);
  52
  53 typedef struct {
  54         wchar_t ch;
  55 } _GBKState;
  56
  57 int
  58 _GBK_init(_RuneLocale *rl)
  59 {
  60
  61         __mbrtowc = _GBK_mbrtowc;
  62         __wcrtomb = _GBK_wcrtomb;
  63         __mbsinit = _GBK_mbsinit;
  64         _CurrentRuneLocale = rl;
  65         __mb_cur_max = 2;
  66         __mb_sb_limit = 128;
  67         return (0);
  68 }
  69
  70 static int
  71 _GBK_mbsinit(const mbstate_t *ps)
  72 {
  73
  74         return (ps == NULL || ((const _GBKState *)ps)->ch == 0);
  75 }
  76
  77 static __inline int
  78 _gbk_check(u_int c)
  79 {
  80
  81         c &= 0xff;
  82         return ((c >= 0x81 && c <= 0xfe) ? 2 : 1);
  83 }
  84
  85 static size_t
  86 _GBK_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n,
  87     mbstate_t * __restrict ps)
  88 {
  89         _GBKState *gs;
  90         wchar_t wc;
  91         size_t len;
  92
  93         gs = (_GBKState *)ps;
  94
  95         if ((gs->ch & ~0xFF) != 0) {
  96                 /* Bad conversion state. */
  97                 errno = EINVAL;
  98                 return ((size_t)-1);
  99         }
 100
 101         if (s == NULL) {
 102                 s = "";
 103                 n = 1;
 104                 pwc = NULL;
 105         }
 106
 107         if (n == 0)
 108                 /* Incomplete multibyte sequence */
 109                 return ((size_t)-2);
 110
 111         if (gs->ch != 0) {
 112                 if (*s == '\0') {
 113                         errno = EILSEQ;
 114                         return ((size_t)-1);
 115                 }
 116                 wc = (gs->ch << 8) | (*s & 0xFF);
 117                 if (pwc != NULL)
 118                         *pwc = wc;
 119                 gs->ch = 0;
 120                 return (1);
 121         }
 122
 123         len = (size_t)_gbk_check(*s);
 124         wc = *s++ & 0xff;
 125         if (len == 2) {
 126                 if (n < 2) {
 127                         /* Incomplete multibyte sequence */
 128                         gs->ch = wc;
 129                         return ((size_t)-2);
 130                 }
 131                 if (*s == '\0') {
 132                         errno = EILSEQ;
 133                         return ((size_t)-1);
 134                 }
 135                 wc = (wc << 8) | (*s++ & 0xff);
 136                 if (pwc != NULL)
 137                         *pwc = wc;
 138                 return (2);
 139         } else {
 140                 if (pwc != NULL)
 141                         *pwc = wc;
 142                 return (wc == L'\0' ? 0 : 1);
 143         }
 144 }
 145
 146 static size_t
 147 _GBK_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps)
 148 {
 149         _GBKState *gs;
 150
 151         gs = (_GBKState *)ps;
 152
 153         if (gs->ch != 0) {
 154                 errno = EINVAL;
 155                 return ((size_t)-1);
 156         }
 157
 158         if (s == NULL)
 159                 /* Reset to initial shift state (no-op) */
 160                 return (1);
 161         if (wc & 0x8000) {
 162                 *s++ = (wc >> 8) & 0xff;
 163                 *s = wc & 0xff;
 164                 return (2);
 165         }
 166         *s = wc & 0xff;
 167         return (1);
 168 }