citrus_utf8.c revision 1.4
1 /* $NetBSD: citrus_utf8.c,v 1.4 2002/03/27 17:54:42 yamt 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 1.4 2002/03/27 17:54:42 yamt 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 _TO_EI(_cl_) ((_UTF8EncodingInfo *)(_cl_)) 121 #define _TO_CEI(_cl_) ((_UTF8CTypeInfo *)(_cl_)) 122 #define _TO_STATE(_ps_) ((_UTF8State *)(_ps_)) 123 #define _CEI_TO_EI(_cei_) (&(_cei_)->ei) 124 #define _CEI_TO_STATE(_ei_, _func_) (_ei_)->states.s_##_func_ 125 126 #define _FUNCNAME(m) _citrus_UTF8_##m 127 #define _ENCODING_INFO _UTF8EncodingInfo 128 #define _CTYPE_INFO _UTF8CTypeInfo 129 #define _ENCODING_STATE _UTF8State 130 #define _ENCODING_MB_CUR_MAX(_ei_) 6 131 #define _ENCODING_IS_STATE_DEPENDENT 0 132 133 134 static __inline void 135 _UTF8_init_count(void) 136 { 137 int i; 138 if (!_UTF8_count) { 139 memset(_UTF8_count_array, 0, sizeof(_UTF8_count_array)); 140 for (i = 0; i <= 0x7f; i++) 141 _UTF8_count_array[i] = 1; 142 for (i = 0xc0; i <= 0xdf; i++) 143 _UTF8_count_array[i] = 2; 144 for (i = 0xe0; i <= 0xef; i++) 145 _UTF8_count_array[i] = 3; 146 for (i = 0xf0; i <= 0xf7; i++) 147 _UTF8_count_array[i] = 4; 148 for (i = 0xf8; i <= 0xfb; i++) 149 _UTF8_count_array[i] = 5; 150 for (i = 0xfc; i <= 0xfd; i++) 151 _UTF8_count_array[i] = 6; 152 _UTF8_count = _UTF8_count_array; 153 } 154 } 155 156 static int 157 _UTF8_findlen(wchar_t v) 158 { 159 int i; 160 u_int32_t c; 161 162 c = (u_int32_t)v; /*XXX*/ 163 for (i = 1; i < sizeof(_UTF8_range) / sizeof(_UTF8_range[0]); i++) 164 if (c >= _UTF8_range[i] && c < _UTF8_range[i + 1]) 165 return i; 166 167 return -1; /*out of range*/ 168 } 169 170 static __inline void 171 /*ARGSUSED*/ 172 _citrus_UTF8_init_state(_UTF8EncodingInfo *ei, _UTF8State *s) 173 { 174 memset(s, 0, sizeof(*s)); 175 } 176 177 static __inline void 178 /*ARGSUSED*/ 179 _citrus_UTF8_pack_state(_UTF8EncodingInfo *ei, void *pspriv, 180 const _UTF8State *s) 181 { 182 memcpy(pspriv, (const void *)s, sizeof(*s)); 183 } 184 185 static __inline void 186 /*ARGSUSED*/ 187 _citrus_UTF8_unpack_state(_UTF8EncodingInfo *ei, _UTF8State *s, 188 const void *pspriv) 189 { 190 memcpy((void *)s, pspriv, sizeof(*s)); 191 } 192 193 static int 194 _citrus_UTF8_mbrtowc_priv(_UTF8EncodingInfo *ei, wchar_t *pwc, const char **s, 195 size_t n, _UTF8State *psenc, size_t *nresult) 196 { 197 wchar_t wchar; 198 const char *s0; 199 int c; 200 int i; 201 int chlenbak; 202 203 _DIAGASSERT(nresult != 0); 204 _DIAGASSERT(ei != NULL); 205 _DIAGASSERT(s != NULL); 206 _DIAGASSERT(psenc != NULL); 207 208 s0 = *s; 209 210 if (s0 == NULL) { 211 _citrus_UTF8_init_state(ei, psenc); 212 *nresult = 0; /* state independent */ 213 return (0); 214 } 215 216 chlenbak = psenc->chlen; 217 218 /* make sure we have the first byte in the buffer */ 219 switch (psenc->chlen) { 220 case 0: 221 if (n < 1) { 222 goto restart; 223 } 224 psenc->ch[0] = *s0++; 225 psenc->chlen = 1; 226 n--; 227 break; 228 case 1: case 2: case 3: case 4: case 5: 229 break; 230 default: 231 /* illegal state */ 232 goto ilseq; 233 } 234 235 c = _UTF8_count[psenc->ch[0] & 0xff]; 236 if (c == 0) 237 goto ilseq; 238 while (psenc->chlen < c) { 239 if (n < 1) { 240 goto restart; 241 } 242 psenc->ch[psenc->chlen] = *s0++; 243 psenc->chlen++; 244 n--; 245 } 246 247 switch (c) { 248 case 1: 249 wchar = psenc->ch[0] & 0xff; 250 break; 251 case 2: case 3: case 4: case 5: case 6: 252 wchar = psenc->ch[0] & (0x7f >> c); 253 for (i = 1; i < c; i++) { 254 if ((psenc->ch[i] & 0xc0) != 0x80) 255 goto ilseq; 256 wchar <<= 6; 257 wchar |= (psenc->ch[i] & 0x3f); 258 } 259 260 _DIAGASSERT(findlen(wchar) == c); 261 262 break; 263 } 264 265 *s = s0; 266 267 psenc->chlen = 0; 268 269 if (pwc) 270 *pwc = wchar; 271 272 if (!wchar) 273 *nresult = 0; 274 else 275 *nresult = c - chlenbak; 276 277 return (0); 278 279 ilseq: 280 psenc->chlen = 0; 281 return (EILSEQ); 282 283 restart: 284 *nresult = (size_t)-2; 285 *s = s0; 286 return (0); 287 } 288 289 static int 290 _citrus_UTF8_wcrtomb_priv(_UTF8EncodingInfo *ei, char *s, size_t n, wchar_t wc, 291 _UTF8State *psenc, size_t *nresult) 292 { 293 int cnt, i; 294 wchar_t c; 295 296 _DIAGASSERT(ei != NULL); 297 _DIAGASSERT(nresult != 0); 298 _DIAGASSERT(s != NULL); 299 300 cnt = _UTF8_findlen(wc); 301 if (cnt <= 0 || cnt > 6) { 302 /* invalid UCS4 value */ 303 goto ilseq; 304 } 305 if (n < cnt) { 306 /* bound check failure */ 307 goto ilseq; 308 } 309 310 c = wc; 311 if (s) { 312 for (i = cnt - 1; i > 0; i--) { 313 s[i] = 0x80 | (c & 0x3f); 314 c >>= 6; 315 } 316 s[0] = c; 317 if (cnt == 1) 318 s[0] &= 0x7f; 319 else { 320 s[0] &= (0x7f >> cnt); 321 s[0] |= ((0xff00 >> cnt) & 0xff); 322 } 323 } 324 325 *nresult = (size_t)cnt; 326 return (0); 327 328 ilseq: 329 *nresult = (size_t)-1; 330 return (EILSEQ); 331 } 332 333 334 static int 335 /*ARGSUSED*/ 336 _citrus_UTF8_stdencoding_init(_UTF8EncodingInfo * __restrict ei, 337 const void * __restrict var, size_t lenvar) 338 { 339 _DIAGASSERT(ei != NULL); 340 341 _UTF8_init_count(); 342 memset((void *)ei, 0, sizeof(*ei)); 343 344 return (0); 345 } 346 347 static void 348 /*ARGSUSED*/ 349 _citrus_UTF8_stdencoding_uninit(_UTF8EncodingInfo *ei) 350 { 351 } 352 353 354 /* ---------------------------------------------------------------------- 355 * public interface for ctype 356 */ 357 358 _CITRUS_CTYPE_DECLS(UTF8); 359 _CITRUS_CTYPE_DEF_OPS(UTF8); 360 361 #include "citrus_ctype_template.h" 362
Indexes created Tue Oct 21 12:09:54 GMT 2025