citrus_utf8.c revision 1.2
1 /* $NetBSD: citrus_utf8.c,v 1.2 2002/03/18 08:56:32 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 1.2 2002/03/18 08:56:32 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_wcstombs; 117 _UTF8State s_wctomb; 118 } states; 119 } _UTF8CTypeInfo; 120 121 #define _TO_EI(_cl_) ((_UTF8EncodingInfo *)(_cl_)) 122 #define _TO_CEI(_cl_) ((_UTF8CTypeInfo *)(_cl_)) 123 #define _TO_STATE(_ps_) ((_UTF8State *)(_ps_)) 124 #define _CEI_TO_EI(_cei_) (&(_cei_)->ei) 125 #define _CEI_TO_STATE(_ei_, _func_) (_ei_)->states.s_##_func_ 126 127 #define _FUNCNAME(m) _citrus_UTF8_##m 128 #define _ENCODING_INFO _UTF8EncodingInfo 129 #define _CTYPE_INFO _UTF8CTypeInfo 130 #define _ENCODING_STATE _UTF8State 131 #define _ENCODING_MB_CUR_MAX(_cl_) 6 132 #define _ENCODING_IS_STATE_DEPENDENT 0 133 134 135 static __inline void 136 _UTF8_init_count(void) 137 { 138 int i; 139 if (!_UTF8_count) { 140 memset(_UTF8_count_array, 0, sizeof(_UTF8_count_array)); 141 for (i = 0; i <= 0x7f; i++) 142 _UTF8_count_array[i] = 1; 143 for (i = 0xc0; i <= 0xdf; i++) 144 _UTF8_count_array[i] = 2; 145 for (i = 0xe0; i <= 0xef; i++) 146 _UTF8_count_array[i] = 3; 147 for (i = 0xf0; i <= 0xf7; i++) 148 _UTF8_count_array[i] = 4; 149 for (i = 0xf8; i <= 0xfb; i++) 150 _UTF8_count_array[i] = 5; 151 for (i = 0xfc; i <= 0xfd; i++) 152 _UTF8_count_array[i] = 6; 153 _UTF8_count = _UTF8_count_array; 154 } 155 } 156 157 static int 158 _UTF8_findlen(wchar_t v) 159 { 160 int i; 161 u_int32_t c; 162 163 c = (u_int32_t)v; /*XXX*/ 164 for (i = 1; i < sizeof(_UTF8_range) / sizeof(_UTF8_range[0]); i++) 165 if (c >= _UTF8_range[i] && c < _UTF8_range[i + 1]) 166 return i; 167 168 return -1; /*out of range*/ 169 } 170 171 static __inline void 172 /*ARGSUSED*/ 173 _citrus_UTF8_init_state(_UTF8EncodingInfo *ei, _UTF8State *s) 174 { 175 memset(s, 0, sizeof(*s)); 176 } 177 178 static __inline void 179 /*ARGSUSED*/ 180 _citrus_UTF8_pack_state(_UTF8EncodingInfo *ei, void *pspriv, 181 const _UTF8State *s) 182 { 183 memcpy(pspriv, (const void *)s, sizeof(*s)); 184 } 185 186 static __inline void 187 /*ARGSUSED*/ 188 _citrus_UTF8_unpack_state(_UTF8EncodingInfo *ei, _UTF8State *s, 189 const void *pspriv) 190 { 191 memcpy((void *)s, pspriv, sizeof(*s)); 192 } 193 194 static int 195 _citrus_UTF8_mbrtowc_priv(_UTF8EncodingInfo *ei, wchar_t *pwc, const char **s, 196 size_t n, _UTF8State *psenc, size_t *nresult) 197 { 198 wchar_t wchar; 199 const char *s0; 200 int c; 201 int i; 202 int chlenbak; 203 204 _DIAGASSERT(nresult != 0); 205 _DIAGASSERT(ei != NULL); 206 _DIAGASSERT(s != NULL); 207 _DIAGASSERT(psenc != NULL); 208 209 s0 = *s; 210 211 if (s0 == NULL) { 212 _citrus_UTF8_init_state(ei, psenc); 213 *nresult = 0; /* state independent */ 214 return (0); 215 } 216 217 chlenbak = psenc->chlen; 218 219 /* make sure we have the first byte in the buffer */ 220 switch (psenc->chlen) { 221 case 0: 222 if (n < 1) { 223 goto restart; 224 } 225 psenc->ch[0] = *s0++; 226 psenc->chlen = 1; 227 n--; 228 break; 229 case 1: case 2: case 3: case 4: case 5: 230 break; 231 default: 232 /* illegal state */ 233 goto ilseq; 234 } 235 236 c = _UTF8_count[psenc->ch[0] & 0xff]; 237 if (c == 0) 238 goto ilseq; 239 while (psenc->chlen < c) { 240 if (n < 1) { 241 goto restart; 242 } 243 psenc->ch[psenc->chlen] = *s0++; 244 psenc->chlen++; 245 n--; 246 } 247 248 switch (c) { 249 case 1: 250 wchar = psenc->ch[0] & 0xff; 251 break; 252 case 2: case 3: case 4: case 5: case 6: 253 wchar = psenc->ch[0] & (0x7f >> c); 254 for (i = 1; i < c; i++) { 255 if ((psenc->ch[i] & 0xc0) != 0x80) 256 goto ilseq; 257 wchar <<= 6; 258 wchar |= (psenc->ch[i] & 0x3f); 259 } 260 261 _DIAGASSERT(findlen(wchar) == c); 262 263 break; 264 } 265 266 *s = s0; 267 268 psenc->chlen = 0; 269 270 if (pwc) 271 *pwc = wchar; 272 273 if (!wchar) 274 *nresult = 0; 275 else 276 *nresult = c - chlenbak; 277 278 return (0); 279 280 ilseq: 281 psenc->chlen = 0; 282 return (EILSEQ); 283 284 restart: 285 *nresult = (size_t)-2; 286 *s = s0; 287 return (0); 288 } 289 290 static int 291 _citrus_UTF8_wcrtomb_priv(_UTF8EncodingInfo *ei, char *s, size_t n, wchar_t wc, 292 _UTF8State *psenc, size_t *nresult) 293 { 294 int cnt, i; 295 wchar_t c; 296 297 _DIAGASSERT(ei != NULL); 298 _DIAGASSERT(nresult != 0); 299 _DIAGASSERT(s != NULL); 300 301 cnt = _UTF8_findlen(wc); 302 if (cnt <= 0 || cnt > 6) { 303 /* invalid UCS4 value */ 304 goto ilseq; 305 } 306 if (n < cnt) { 307 /* bound check failure */ 308 goto ilseq; 309 } 310 311 c = wc; 312 if (s) { 313 for (i = cnt - 1; i > 0; i--) { 314 s[i] = 0x80 | (c & 0x3f); 315 c >>= 6; 316 } 317 s[0] = c; 318 if (cnt == 1) 319 s[0] &= 0x7f; 320 else { 321 s[0] &= (0x7f >> cnt); 322 s[0] |= ((0xff00 >> cnt) & 0xff); 323 } 324 } 325 326 *nresult = (size_t)cnt; 327 return (0); 328 329 ilseq: 330 *nresult = (size_t)-1; 331 return (EILSEQ); 332 } 333 334 335 static int 336 /*ARGSUSED*/ 337 _citrus_UTF8_stdencoding_init(_UTF8EncodingInfo * __restrict ei, 338 const void * __restrict var, size_t lenvar) 339 { 340 _DIAGASSERT(ei != NULL); 341 342 _UTF8_init_count(); 343 memset((void *)ei, 0, sizeof(*ei)); 344 345 return (0); 346 } 347 348 static void 349 /*ARGSUSED*/ 350 _citrus_UTF8_stdencoding_uninit(_UTF8EncodingInfo *ei) 351 { 352 } 353 354 355 /* ---------------------------------------------------------------------- 356 * public interface for ctype 357 */ 358 359 _CITRUS_CTYPE_DECLS(UTF8); 360 _CITRUS_CTYPE_DEF_OPS(UTF8); 361 362 #include "citrus_ctype_template.h" 363
Indexes created Tue Oct 21 19:09:51 GMT 2025