citrus_utf8.c revision 1.7
1 /* $NetBSD: citrus_utf8.c,v 1.7 2003/03/25 17:35:36 tshiozak Exp $ */ 2 3 /*- 4 * Copyright (c)2002 Citrus Project, 5 * All rights reserved. 6 * 7 * Redistribution and use in source and binary forms, with or without 8 * modification, are permitted provided that the following conditions 9 * are met: 10 * 1. Redistributions of source code must retain the above copyright 11 * notice, this list of conditions and the following disclaimer. 12 * 2. Redistributions in binary form must reproduce the above copyright 13 * notice, this list of conditions and the following disclaimer in the 14 * documentation and/or other materials provided with the distribution. 15 * 16 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND 17 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 18 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 19 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE 20 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 21 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 22 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 23 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 24 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 25 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 26 * SUCH DAMAGE. 27 */ 28 29 /*- 30 * Copyright (c) 1993 31 * The Regents of the University of California. All rights reserved. 32 * 33 * This code is derived from software contributed to Berkeley by 34 * Paul Borman at Krystal Technologies. 35 * 36 * Redistribution and use in source and binary forms, with or without 37 * modification, are permitted provided that the following conditions 38 * are met: 39 * 1. Redistributions of source code must retain the above copyright 40 * notice, this list of conditions and the following disclaimer. 41 * 2. Redistributions in binary form must reproduce the above copyright 42 * notice, this list of conditions and the following disclaimer in the 43 * documentation and/or other materials provided with the distribution. 44 * 3. All advertising materials mentioning features or use of this software 45 * must display the following acknowledgement: 46 * This product includes software developed by the University of 47 * California, Berkeley and its contributors. 48 * 4. Neither the name of the University nor the names of its contributors 49 * may be used to endorse or promote products derived from this software 50 * without specific prior written permission. 51 * 52 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 53 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 54 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 55 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 56 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 57 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 58 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 59 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 60 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 61 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 62 * SUCH DAMAGE. 63 */ 64 65 #include <sys/cdefs.h> 66 #if defined(LIBC_SCCS) && !defined(lint) 67 __RCSID("$NetBSD: citrus_utf8.c,v 1.7 2003/03/25 17:35:36 tshiozak Exp $"); 68 #endif /* LIBC_SCCS and not lint */ 69 70 #include <assert.h> 71 #include <errno.h> 72 #include <string.h> 73 #include <stdio.h> 74 #include <stdlib.h> 75 #include <stddef.h> 76 #include <locale.h> 77 #include <wchar.h> 78 #include <sys/types.h> 79 #include <limits.h> 80 #include "citrus_module.h" 81 #include "citrus_ctype.h" 82 #include "citrus_utf8.h" 83 84 85 /* ---------------------------------------------------------------------- 86 * private stuffs used by templates 87 */ 88 89 static int _UTF8_count_array[256]; 90 static int const *_UTF8_count = NULL; 91 92 static u_int32_t _UTF8_range[] = { 93 0, /*dummy*/ 94 0x00000000, 0x00000080, 0x00000800, 0x00010000, 95 0x00200000, 0x04000000, 0x80000000, 96 }; 97 98 typedef struct { 99 char ch[6]; 100 int chlen; 101 } _UTF8State; 102 103 typedef struct { 104 } _UTF8EncodingInfo; 105 typedef struct { 106 _UTF8EncodingInfo ei; 107 struct { 108 /* for future multi-locale facility */ 109 _UTF8State s_mblen; 110 _UTF8State s_mbrlen; 111 _UTF8State s_mbrtowc; 112 _UTF8State s_mbtowc; 113 _UTF8State s_mbsrtowcs; 114 _UTF8State s_wcrtomb; 115 _UTF8State s_wcsrtombs; 116 _UTF8State s_wctomb; 117 } states; 118 } _UTF8CTypeInfo; 119 120 #define _CEI_TO_EI(_cei_) (&(_cei_)->ei) 121 #define _CEI_TO_STATE(_ei_, _func_) (_ei_)->states.s_##_func_ 122 123 #define _FUNCNAME(m) _citrus_UTF8_##m 124 #define _ENCODING_INFO _UTF8EncodingInfo 125 #define _CTYPE_INFO _UTF8CTypeInfo 126 #define _ENCODING_STATE _UTF8State 127 #define _ENCODING_MB_CUR_MAX(_ei_) 6 128 #define _ENCODING_IS_STATE_DEPENDENT 0 129 #define _STATE_NEEDS_EXPLICIT_INIT(_ps_) 0 130 131 132 static __inline void 133 _UTF8_init_count(void) 134 { 135 int i; 136 if (!_UTF8_count) { 137 memset(_UTF8_count_array, 0, sizeof(_UTF8_count_array)); 138 for (i = 0; i <= 0x7f; i++) 139 _UTF8_count_array[i] = 1; 140 for (i = 0xc0; i <= 0xdf; i++) 141 _UTF8_count_array[i] = 2; 142 for (i = 0xe0; i <= 0xef; i++) 143 _UTF8_count_array[i] = 3; 144 for (i = 0xf0; i <= 0xf7; i++) 145 _UTF8_count_array[i] = 4; 146 for (i = 0xf8; i <= 0xfb; i++) 147 _UTF8_count_array[i] = 5; 148 for (i = 0xfc; i <= 0xfd; i++) 149 _UTF8_count_array[i] = 6; 150 _UTF8_count = _UTF8_count_array; 151 } 152 } 153 154 static int 155 _UTF8_findlen(wchar_t v) 156 { 157 int i; 158 u_int32_t c; 159 160 c = (u_int32_t)v; /*XXX*/ 161 for (i = 1; i < sizeof(_UTF8_range) / sizeof(_UTF8_range[0]); i++) 162 if (c >= _UTF8_range[i] && c < _UTF8_range[i + 1]) 163 return i; 164 165 return -1; /*out of range*/ 166 } 167 168 static __inline void 169 /*ARGSUSED*/ 170 _citrus_UTF8_init_state(_UTF8EncodingInfo *ei, _UTF8State *s) 171 { 172 memset(s, 0, sizeof(*s)); 173 } 174 175 static __inline void 176 /*ARGSUSED*/ 177 _citrus_UTF8_pack_state(_UTF8EncodingInfo *ei, void *pspriv, 178 const _UTF8State *s) 179 { 180 memcpy(pspriv, (const void *)s, sizeof(*s)); 181 } 182 183 static __inline void 184 /*ARGSUSED*/ 185 _citrus_UTF8_unpack_state(_UTF8EncodingInfo *ei, _UTF8State *s, 186 const void *pspriv) 187 { 188 memcpy((void *)s, pspriv, sizeof(*s)); 189 } 190 191 static int 192 _citrus_UTF8_mbrtowc_priv(_UTF8EncodingInfo *ei, wchar_t *pwc, const char **s, 193 size_t n, _UTF8State *psenc, size_t *nresult) 194 { 195 wchar_t wchar; 196 const char *s0; 197 int c; 198 int i; 199 int chlenbak; 200 201 _DIAGASSERT(nresult != 0); 202 _DIAGASSERT(ei != NULL); 203 _DIAGASSERT(s != NULL); 204 _DIAGASSERT(psenc != NULL); 205 206 s0 = *s; 207 208 if (s0 == NULL) { 209 _citrus_UTF8_init_state(ei, psenc); 210 *nresult = 0; /* state independent */ 211 return (0); 212 } 213 214 chlenbak = psenc->chlen; 215 216 /* make sure we have the first byte in the buffer */ 217 switch (psenc->chlen) { 218 case 0: 219 if (n < 1) { 220 goto restart; 221 } 222 psenc->ch[0] = *s0++; 223 psenc->chlen = 1; 224 n--; 225 break; 226 case 1: case 2: case 3: case 4: case 5: 227 break; 228 default: 229 /* illegal state */ 230 goto ilseq; 231 } 232 233 c = _UTF8_count[psenc->ch[0] & 0xff]; 234 if (c == 0) 235 goto ilseq; 236 while (psenc->chlen < c) { 237 if (n < 1) { 238 goto restart; 239 } 240 psenc->ch[psenc->chlen] = *s0++; 241 psenc->chlen++; 242 n--; 243 } 244 245 switch (c) { 246 case 1: 247 wchar = psenc->ch[0] & 0xff; 248 break; 249 case 2: case 3: case 4: case 5: case 6: 250 wchar = psenc->ch[0] & (0x7f >> c); 251 for (i = 1; i < c; i++) { 252 if ((psenc->ch[i] & 0xc0) != 0x80) 253 goto ilseq; 254 wchar <<= 6; 255 wchar |= (psenc->ch[i] & 0x3f); 256 } 257 258 _DIAGASSERT(findlen(wchar) == c); 259 260 break; 261 } 262 263 *s = s0; 264 265 psenc->chlen = 0; 266 267 if (pwc) 268 *pwc = wchar; 269 270 if (!wchar) 271 *nresult = 0; 272 else 273 *nresult = c - chlenbak; 274 275 return (0); 276 277 ilseq: 278 psenc->chlen = 0; 279 *nresult = (size_t)-1; 280 return (EILSEQ); 281 282 restart: 283 *s = s0; 284 *nresult = (size_t)-2; 285 return (0); 286 } 287 288 static int 289 _citrus_UTF8_wcrtomb_priv(_UTF8EncodingInfo *ei, char *s, size_t n, wchar_t wc, 290 _UTF8State *psenc, size_t *nresult) 291 { 292 int cnt, i; 293 wchar_t c; 294 295 _DIAGASSERT(ei != NULL); 296 _DIAGASSERT(nresult != 0); 297 _DIAGASSERT(s != NULL); 298 299 cnt = _UTF8_findlen(wc); 300 if (cnt <= 0 || cnt > 6) { 301 /* invalid UCS4 value */ 302 goto ilseq; 303 } 304 if (n < cnt) { 305 /* bound check failure */ 306 goto ilseq; 307 } 308 309 c = wc; 310 if (s) { 311 for (i = cnt - 1; i > 0; i--) { 312 s[i] = 0x80 | (c & 0x3f); 313 c >>= 6; 314 } 315 s[0] = c; 316 if (cnt == 1) 317 s[0] &= 0x7f; 318 else { 319 s[0] &= (0x7f >> cnt); 320 s[0] |= ((0xff00 >> cnt) & 0xff); 321 } 322 } 323 324 *nresult = (size_t)cnt; 325 return (0); 326 327 ilseq: 328 *nresult = (size_t)-1; 329 return (EILSEQ); 330 } 331 332 333 static int 334 /*ARGSUSED*/ 335 _citrus_UTF8_stdencoding_init(_UTF8EncodingInfo * __restrict ei, 336 const void * __restrict var, size_t lenvar) 337 { 338 _DIAGASSERT(ei != NULL); 339 340 _UTF8_init_count(); 341 memset((void *)ei, 0, sizeof(*ei)); 342 343 return (0); 344 } 345 346 static void 347 /*ARGSUSED*/ 348 _citrus_UTF8_stdencoding_uninit(_UTF8EncodingInfo *ei) 349 { 350 } 351 352 353 /* ---------------------------------------------------------------------- 354 * public interface for ctype 355 */ 356 357 _CITRUS_CTYPE_DECLS(UTF8); 358 _CITRUS_CTYPE_DEF_OPS(UTF8); 359 360 #include "citrus_ctype_template.h" 361
Indexes created Tue Oct 21 16:10:11 GMT 2025