gb2312.c revision 128004
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: head/lib/libc/locale/gb2312.c 128004 2004-04-07 10:48:19Z tjr $"); 30 31#include <runetype.h> 32#include <stdlib.h> 33#include <string.h> 34#include <wchar.h> 35 36extern size_t (*__mbrtowc)(wchar_t * __restrict, const char * __restrict, 37 size_t, mbstate_t * __restrict); 38extern int (*__mbsinit)(const mbstate_t *); 39extern size_t (*__wcrtomb)(char * __restrict, wchar_t, mbstate_t * __restrict); 40 41int _GB2312_init(_RuneLocale *); 42size_t _GB2312_mbrtowc(wchar_t * __restrict, const char * __restrict, size_t, 43 mbstate_t * __restrict); 44int _GB2312_mbsinit(const mbstate_t *); 45size_t _GB2312_wcrtomb(char * __restrict, wchar_t, mbstate_t * __restrict); 46 47typedef struct { 48 int count; 49 u_char bytes[2]; 50} _GB2312State; 51 52int 53_GB2312_init(_RuneLocale *rl) 54{ 55 56 _CurrentRuneLocale = rl; 57 __mbrtowc = _GB2312_mbrtowc; 58 __wcrtomb = _GB2312_wcrtomb; 59 __mbsinit = _GB2312_mbsinit; 60 __mb_cur_max = 2; 61 return (0); 62} 63 64int 65_GB2312_mbsinit(const mbstate_t *ps) 66{ 67 68 return (ps == NULL || ((_GB2312State *)ps)->count == 0); 69} 70 71static __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 94size_t 95_GB2312_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n, 96 mbstate_t * __restrict ps) 97{ 98 _GB2312State *gs; 99 wchar_t wc; 100 int i, len, ocount; 101 size_t ncopy; 102 103 gs = (_GB2312State *)gs; 104 105 if (s == NULL) { 106 s = ""; 107 n = 1; 108 pwc = NULL; 109 } 110 111 ncopy = MIN(MIN(n, MB_CUR_MAX), sizeof(gs->bytes) - gs->count); 112 memcpy(gs->bytes + gs->count, s, ncopy); 113 ocount = gs->count; 114 gs->count += ncopy; 115 s = (char *)gs->bytes; 116 n = gs->count; 117 118 if ((len = _GB2312_check(s, n)) < 0) 119 return ((size_t)len); 120 wc = 0; 121 i = len; 122 while (i-- > 0) 123 wc = (wc << 8) | (unsigned char)*s++; 124 if (pwc != NULL) 125 *pwc = wc; 126 gs->count = 0; 127 return (wc == L'\0' ? 0 : len - ocount); 128} 129 130size_t 131_GB2312_wcrtomb(char * __restrict s, wchar_t wc, 132 mbstate_t * __restrict ps __unused) 133{ 134 135 if (s == NULL) 136 /* Reset to initial shift state (no-op) */ 137 return (1); 138 if (wc & 0x8000) { 139 *s++ = (wc >> 8) & 0xff; 140 *s = wc & 0xff; 141 return (2); 142 } 143 *s = wc & 0xff; 144 return (1); 145} 146