1 /*- 2 * Copyright (c) 2002-2004 Tim J. Robbins 3 * All rights reserved. 4 * 5 * Redistribution and use in source and binary forms, with or without 6 * modification, are permitted provided that the following conditions 7 * are met: 8 * 1. Redistributions of source code must retain the above copyright 9 * notice, this list of conditions and the following disclaimer. 10 * 2. Redistributions in binary form must reproduce the above copyright 11 * notice, this list of conditions and the following disclaimer in the 12 * documentation and/or other materials provided with the distribution. 13 * 14 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND 15 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 16 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 17 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE 18 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 19 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 20 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 21 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 22 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 23 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 24 * SUCH DAMAGE. 25 */ 26 /* 27 * PRC National Standard GB 18030-2000 encoding of Chinese text. 28 * 29 * See gb18030(5) for details. 30 */ 31 32 #include <sys/param.h> 33 __FBSDID("$FreeBSD$"); 34 35 #include <errno.h> 36 #include <runetype.h> 37 #include <stdlib.h> 38 #include <string.h> 39 #include <wchar.h> 40 41 extern size_t (*__mbrtowc)(wchar_t * __restrict, const char * __restrict, 42 size_t, mbstate_t * __restrict); 43 extern int (*__mbsinit)(const mbstate_t *); 44 extern size_t (*__wcrtomb)(char * __restrict, wchar_t, mbstate_t * __restrict); 45 46 int _GB18030_init(_RuneLocale *); 47 size_t _GB18030_mbrtowc(wchar_t * __restrict, const char * __restrict, size_t, 48 mbstate_t * __restrict); 49 int _GB18030_mbsinit(const mbstate_t *); 50 size_t _GB18030_wcrtomb(char * __restrict, wchar_t, mbstate_t * __restrict); 51 52 typedef struct { 53 int count; 54 u_char bytes[4]; 55 } _GB18030State; 56 57 int 58 _GB18030_init(_RuneLocale *rl) 59 { 60 61 __mbrtowc = _GB18030_mbrtowc; 62 __wcrtomb = _GB18030_wcrtomb; 63 __mbsinit = _GB18030_mbsinit; 64 _CurrentRuneLocale = rl; 65 __mb_cur_max = 4; 66 67 return (0); 68 } 69 70 int 71 _GB18030_mbsinit(const mbstate_t *ps) 72 { 73 74 return (ps == NULL || ((_GB18030State *)ps)->count == 0); 75 } 76 77 size_t 78 _GB18030_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, 79 size_t n, mbstate_t * __restrict ps) 80 { 81 _GB18030State *gs; 82 wchar_t wch; 83 int ch, len, ocount; 84 size_t ncopy; 85 86 gs = (_GB18030State *)ps; 87 88 if (s == NULL) { 89 s = ""; 90 n = 1; 91 pwc = NULL; 92 } 93 94 ncopy = MIN(MIN(n, MB_CUR_MAX), sizeof(gs->bytes) - gs->count); 95 memcpy(gs->bytes + gs->count, s, ncopy); 96 ocount = gs->count; 97 gs->count += ncopy; 98 s = (char *)gs->bytes; 99 n = gs->count; 100 101 if (n == 0) 102 /* Incomplete multibyte sequence */ 103 return ((size_t)-2); 104 105 /* 106 * Single byte: [00-7f] 107 * Two byte: [81-fe][40-7e,80-fe] 108 * Four byte: [81-fe][30-39][81-fe][30-39] 109 */ 110 ch = (unsigned char)*s++; 111 if (ch <= 0x7f) { 112 len = 1; 113 wch = ch; 114 } else if (ch >= 0x81 && ch <= 0xfe) { 115 wch = ch; 116 if (n < 2) 117 return ((size_t)-2); 118 ch = (unsigned char)*s++; 119 if ((ch >= 0x40 && ch <= 0x7e) || (ch >= 0x80 && ch <= 0xfe)) { 120 wch = (wch << 8) | ch; 121 len = 2; 122 } else if (ch >= 0x30 && ch <= 0x39) { 123 /* 124 * Strip high bit off the wide character we will 125 * eventually output so that it is positive when 126 * cast to wint_t on 32-bit twos-complement machines. 127 */ 128 wch = ((wch & 0x7f) << 8) | ch; 129 if (n < 3) 130 return ((size_t)-2); 131 ch = (unsigned char)*s++; 132 if (ch < 0x81 || ch > 0xfe) 133 goto ilseq; 134 wch = (wch << 8) | ch; 135 if (n < 4) 136 return ((size_t)-2); 137 ch = (unsigned char)*s++; 138 if (ch < 0x30 || ch > 0x39) 139 goto ilseq; 140 wch = (wch << 8) | ch; 141 len = 4; 142 } else 143 goto ilseq; 144 } else 145 goto ilseq; 146 147 if (pwc != NULL) 148 *pwc = wch; 149 gs->count = 0; 150 return (wch == L'\0' ? 0 : len - ocount); 151 ilseq: 152 errno = EILSEQ; 153 return ((size_t)-1); 154 } 155 156 size_t 157 _GB18030_wcrtomb(char * __restrict s, wchar_t wc, 158 mbstate_t * __restrict ps __unused) 159 { 160 size_t len; 161 int c; 162 163 if (s == NULL) 164 /* Reset to initial shift state (no-op) */ 165 return (1); 166 if ((wc & ~0x7fffffff) != 0) 167 goto ilseq; 168 if (wc & 0x7f000000) { 169 /* Replace high bit that mbrtowc() removed. */ 170 wc |= 0x80000000; 171 c = (wc >> 24) & 0xff; 172 if (c < 0x81 || c > 0xfe) 173 goto ilseq; 174 *s++ = c; 175 c = (wc >> 16) & 0xff; 176 if (c < 0x30 || c > 0x39) 177 goto ilseq; 178 *s++ = c; 179 c = (wc >> 8) & 0xff; 180 if (c < 0x81 || c > 0xfe) 181 goto ilseq; 182 *s++ = c; 183 c = wc & 0xff; 184 if (c < 0x30 || c > 0x39) 185 goto ilseq; 186 *s++ = c; 187 len = 4; 188 } else if (wc & 0x00ff0000) 189 goto ilseq; 190 else if (wc & 0x0000ff00) { 191 c = (wc >> 8) & 0xff; 192 if (c < 0x81 || c > 0xfe) 193 goto ilseq; 194 *s++ = c; 195 c = wc & 0xff; 196 if (c < 0x40 || c == 0x7f || c == 0xff) 197 goto ilseq; 198 *s++ = c; 199 len = 2; 200 } else if (wc <= 0x7f) { 201 *s++ = wc; 202 len = 1; 203 } else 204 goto ilseq; 205 206 return (len); 207 ilseq: 208 errno = EILSEQ; 209 return ((size_t)-1); 210 } 211