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#include <sys/param.h>
|
28__FBSDID("$FreeBSD: head/lib/libc/locale/utf8.c 128081 2004-04-10 00:27:52Z tjr $");
|
28__FBSDID("$FreeBSD: head/lib/libc/locale/utf8.c 128155 2004-04-12 13:09:18Z tjr $"); |
29 30#include <errno.h> 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 41size_t _UTF8_mbrtowc(wchar_t * __restrict, const char * __restrict, size_t, 42 mbstate_t * __restrict); 43int _UTF8_mbsinit(const mbstate_t *); 44size_t _UTF8_wcrtomb(char * __restrict, wchar_t, mbstate_t * __restrict); 45 46typedef struct { 47 int count; 48 u_char bytes[6]; 49} _UTF8State; 50 51int 52_UTF8_init(_RuneLocale *rl) 53{ 54 55 __mbrtowc = _UTF8_mbrtowc; 56 __wcrtomb = _UTF8_wcrtomb; 57 __mbsinit = _UTF8_mbsinit; 58 _CurrentRuneLocale = rl; 59 __mb_cur_max = 6; 60 61 return (0); 62} 63 64int 65_UTF8_mbsinit(const mbstate_t *ps) 66{ 67 68 return (ps == NULL || ((const _UTF8State *)ps)->count == 0); 69} 70 71size_t 72_UTF8_mbrtowc(wchar_t * __restrict pwc, const char * __restrict s, size_t n, 73 mbstate_t * __restrict ps) 74{ 75 _UTF8State *us; 76 int ch, i, len, mask, ocount; 77 wchar_t lbound, wch; 78 size_t ncopy; 79 80 us = (_UTF8State *)ps; 81
|
82 if (us->count < 0 || us->count > sizeof(us->bytes)) { 83 errno = EINVAL; 84 return ((size_t)-1); 85 } 86 |
87 if (s == NULL) { 88 s = ""; 89 n = 1; 90 pwc = NULL; 91 } 92 93 ncopy = MIN(MIN(n, MB_CUR_MAX), sizeof(us->bytes) - us->count); 94 memcpy(us->bytes + us->count, s, ncopy); 95 ocount = us->count; 96 us->count += ncopy; 97 s = (char *)us->bytes; 98 n = us->count; 99 100 if (n == 0) 101 /* Incomplete multibyte sequence */ 102 return ((size_t)-2); 103 104 /* 105 * Determine the number of octets that make up this character from 106 * the first octet, and a mask that extracts the interesting bits of 107 * the first octet. 108 * 109 * We also specify a lower bound for the character code to detect 110 * redundant, non-"shortest form" encodings. For example, the 111 * sequence C0 80 is _not_ a legal representation of the null 112 * character. This enforces a 1-to-1 mapping between character 113 * codes and their multibyte representations. 114 */ 115 ch = (unsigned char)*s; 116 if ((ch & 0x80) == 0) { 117 mask = 0x7f; 118 len = 1; 119 lbound = 0; 120 } else if ((ch & 0xe0) == 0xc0) { 121 mask = 0x1f; 122 len = 2; 123 lbound = 0x80; 124 } else if ((ch & 0xf0) == 0xe0) { 125 mask = 0x0f; 126 len = 3; 127 lbound = 0x800; 128 } else if ((ch & 0xf8) == 0xf0) { 129 mask = 0x07; 130 len = 4; 131 lbound = 0x10000; 132 } else if ((ch & 0xfc) == 0xf8) { 133 mask = 0x03; 134 len = 5; 135 lbound = 0x200000; 136 } else if ((ch & 0xfc) == 0xfc) { 137 mask = 0x01; 138 len = 6; 139 lbound = 0x4000000; 140 } else { 141 /* 142 * Malformed input; input is not UTF-8. 143 */ 144 errno = EILSEQ; 145 return ((size_t)-1); 146 } 147 148 if (n < (size_t)len) 149 /* Incomplete multibyte sequence */ 150 return ((size_t)-2); 151 152 /* 153 * Decode the octet sequence representing the character in chunks 154 * of 6 bits, most significant first. 155 */ 156 wch = (unsigned char)*s++ & mask; 157 i = len; 158 while (--i != 0) { 159 if ((*s & 0xc0) != 0x80) { 160 /* 161 * Malformed input; bad characters in the middle 162 * of a character. 163 */ 164 errno = EILSEQ; 165 return ((size_t)-1); 166 } 167 wch <<= 6; 168 wch |= *s++ & 0x3f; 169 } 170 if (wch < lbound) { 171 /* 172 * Malformed input; redundant encoding. 173 */ 174 errno = EILSEQ; 175 return ((size_t)-1); 176 } 177 if (pwc != NULL) 178 *pwc = wch; 179 us->count = 0; 180 return (wch == L'\0' ? 0 : len - ocount); 181} 182 183size_t
|
179_UTF8_wcrtomb(char * __restrict s, wchar_t wc,
180 mbstate_t * __restrict ps __unused)
|
184_UTF8_wcrtomb(char * __restrict s, wchar_t wc, mbstate_t * __restrict ps) |
185{
|
186 _UTF8State *us; |
187 unsigned char lead; 188 int i, len; 189
|
190 us = (_UTF8State *)ps; 191 192 if (us->count < 0 || us->count > sizeof(us->bytes)) { 193 errno = EINVAL; 194 return ((size_t)-1); 195 } 196 |
197 if (s == NULL) 198 /* Reset to initial shift state (no-op) */ 199 return (1); 200 201 /* 202 * Determine the number of octets needed to represent this character. 203 * We always output the shortest sequence possible. Also specify the 204 * first few bits of the first octet, which contains the information 205 * about the sequence length. 206 */ 207 if ((wc & ~0x7f) == 0) { 208 lead = 0; 209 len = 1; 210 } else if ((wc & ~0x7ff) == 0) { 211 lead = 0xc0; 212 len = 2; 213 } else if ((wc & ~0xffff) == 0) { 214 lead = 0xe0; 215 len = 3; 216 } else if ((wc & ~0x1fffff) == 0) { 217 lead = 0xf0; 218 len = 4; 219 } else if ((wc & ~0x3ffffff) == 0) { 220 lead = 0xf8; 221 len = 5; 222 } else if ((wc & ~0x7fffffff) == 0) { 223 lead = 0xfc; 224 len = 6; 225 } else { 226 errno = EILSEQ; 227 return ((size_t)-1); 228 } 229 230 /* 231 * Output the octets representing the character in chunks 232 * of 6 bits, least significant last. The first octet is 233 * a special case because it contains the sequence length 234 * information. 235 */ 236 for (i = len - 1; i > 0; i--) { 237 s[i] = (wc & 0x3f) | 0x80; 238 wc >>= 6; 239 } 240 *s = (wc & 0xff) | lead; 241 242 return (len); 243}
|