citrus_big5.c revision 267829
1/* $FreeBSD: releng/10.0/lib/libiconv_modules/BIG5/citrus_big5.c 267829 2014-06-24 19:05:08Z delphij $ */ 2/* $NetBSD: citrus_big5.c,v 1.12 2008/06/14 16:01:07 tnozaki Exp $ */ 3 4/*- 5 * Copyright (c)2002, 2006 Citrus Project, 6 * All rights reserved. 7 * 8 * Redistribution and use in source and binary forms, with or without 9 * modification, are permitted provided that the following conditions 10 * are met: 11 * 1. Redistributions of source code must retain the above copyright 12 * notice, this list of conditions and the following disclaimer. 13 * 2. Redistributions in binary form must reproduce the above copyright 14 * notice, this list of conditions and the following disclaimer in the 15 * documentation and/or other materials provided with the distribution. 16 * 17 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND 18 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 19 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 20 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE 21 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 22 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 23 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 24 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 25 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 26 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 27 * SUCH DAMAGE. 28 */ 29 30/*- 31 * Copyright (c) 1993 32 * The Regents of the University of California. All rights reserved. 33 * 34 * This code is derived from software contributed to Berkeley by 35 * Paul Borman at Krystal Technologies. 36 * 37 * Redistribution and use in source and binary forms, with or without 38 * modification, are permitted provided that the following conditions 39 * are met: 40 * 1. Redistributions of source code must retain the above copyright 41 * notice, this list of conditions and the following disclaimer. 42 * 2. Redistributions in binary form must reproduce the above copyright 43 * notice, this list of conditions and the following disclaimer in the 44 * documentation and/or other materials provided with the distribution. 45 * 3. Neither the name of the University nor the names of its contributors 46 * may be used to endorse or promote products derived from this software 47 * without specific prior written permission. 48 * 49 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 50 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 51 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 52 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 53 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 54 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 55 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 56 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 57 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 58 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 59 * SUCH DAMAGE. 60 */ 61 62#include <sys/cdefs.h> 63#include <sys/queue.h> 64#include <sys/types.h> 65 66#include <assert.h> 67#include <errno.h> 68#include <limits.h> 69#include <stddef.h> 70#include <stdint.h> 71#include <stdio.h> 72#include <stdlib.h> 73#include <string.h> 74#include <wchar.h> 75 76#include "citrus_namespace.h" 77#include "citrus_prop.h" 78#include "citrus_types.h" 79#include "citrus_bcs.h" 80#include "citrus_module.h" 81#include "citrus_stdenc.h" 82#include "citrus_big5.h" 83 84/* ---------------------------------------------------------------------- 85 * private stuffs used by templates 86 */ 87 88typedef struct { 89 int chlen; 90 char ch[2]; 91} _BIG5State; 92 93typedef struct _BIG5Exclude { 94 TAILQ_ENTRY(_BIG5Exclude) entry; 95 wint_t end; 96 wint_t start; 97} _BIG5Exclude; 98 99typedef TAILQ_HEAD(_BIG5ExcludeList, _BIG5Exclude) _BIG5ExcludeList; 100 101typedef struct { 102 _BIG5ExcludeList excludes; 103 int cell[0x100]; 104} _BIG5EncodingInfo; 105 106#define _CEI_TO_EI(_cei_) (&(_cei_)->ei) 107#define _CEI_TO_STATE(_cei_, _func_) (_cei_)->states.s_##_func_ 108 109#define _FUNCNAME(m) _citrus_BIG5_##m 110#define _ENCODING_INFO _BIG5EncodingInfo 111#define _ENCODING_STATE _BIG5State 112#define _ENCODING_MB_CUR_MAX(_ei_) 2 113#define _ENCODING_IS_STATE_DEPENDENT 0 114#define _STATE_NEEDS_EXPLICIT_INIT(_ps_) 0 115 116 117static __inline void 118/*ARGSUSED*/ 119_citrus_BIG5_init_state(_BIG5EncodingInfo * __restrict ei __unused, 120 _BIG5State * __restrict s) 121{ 122 123 memset(s, 0, sizeof(*s)); 124} 125 126static __inline void 127/*ARGSUSED*/ 128_citrus_BIG5_pack_state(_BIG5EncodingInfo * __restrict ei __unused, 129 void * __restrict pspriv, 130 const _BIG5State * __restrict s) 131{ 132 133 memcpy(pspriv, (const void *)s, sizeof(*s)); 134} 135 136static __inline void 137/*ARGSUSED*/ 138_citrus_BIG5_unpack_state(_BIG5EncodingInfo * __restrict ei __unused, 139 _BIG5State * __restrict s, 140 const void * __restrict pspriv) 141{ 142 143 memcpy((void *)s, pspriv, sizeof(*s)); 144} 145 146static __inline int 147_citrus_BIG5_check(_BIG5EncodingInfo *ei, unsigned int c) 148{ 149 150 return ((ei->cell[c & 0xFF] & 0x1) ? 2 : 1); 151} 152 153static __inline int 154_citrus_BIG5_check2(_BIG5EncodingInfo *ei, unsigned int c) 155{ 156 157 return ((ei->cell[c & 0xFF] & 0x2) ? 1 : 0); 158} 159 160static __inline int 161_citrus_BIG5_check_excludes(_BIG5EncodingInfo *ei, wint_t c) 162{ 163 _BIG5Exclude *exclude; 164 165 TAILQ_FOREACH(exclude, &ei->excludes, entry) { 166 if (c >= exclude->start && c <= exclude->end) 167 return (EILSEQ); 168 } 169 return (0); 170} 171 172static int 173_citrus_BIG5_fill_rowcol(void * __restrict ctx, const char * __restrict s, 174 uint64_t start, uint64_t end) 175{ 176 _BIG5EncodingInfo *ei; 177 uint64_t n; 178 int i; 179 180 if (start > 0xFF || end > 0xFF) 181 return (EINVAL); 182 ei = (_BIG5EncodingInfo *)ctx; 183 i = strcmp("row", s) ? 1 : 0; 184 i = 1 << i; 185 for (n = start; n <= end; ++n) 186 ei->cell[n & 0xFF] |= i; 187 return (0); 188} 189 190static int 191/*ARGSUSED*/ 192_citrus_BIG5_fill_excludes(void * __restrict ctx, 193 const char * __restrict s __unused, uint64_t start, uint64_t end) 194{ 195 _BIG5EncodingInfo *ei; 196 _BIG5Exclude *exclude; 197 198 if (start > 0xFFFF || end > 0xFFFF) 199 return (EINVAL); 200 ei = (_BIG5EncodingInfo *)ctx; 201 exclude = TAILQ_LAST(&ei->excludes, _BIG5ExcludeList); 202 if (exclude != NULL && (wint_t)start <= exclude->end) 203 return (EINVAL); 204 exclude = (void *)malloc(sizeof(*exclude)); 205 if (exclude == NULL) 206 return (ENOMEM); 207 exclude->start = (wint_t)start; 208 exclude->end = (wint_t)end; 209 TAILQ_INSERT_TAIL(&ei->excludes, exclude, entry); 210 211 return (0); 212} 213 214static const _citrus_prop_hint_t root_hints[] = { 215 _CITRUS_PROP_HINT_NUM("row", &_citrus_BIG5_fill_rowcol), 216 _CITRUS_PROP_HINT_NUM("col", &_citrus_BIG5_fill_rowcol), 217 _CITRUS_PROP_HINT_NUM("excludes", &_citrus_BIG5_fill_excludes), 218 _CITRUS_PROP_HINT_END 219}; 220 221static void 222/*ARGSUSED*/ 223_citrus_BIG5_encoding_module_uninit(_BIG5EncodingInfo *ei) 224{ 225 _BIG5Exclude *exclude; 226 227 while ((exclude = TAILQ_FIRST(&ei->excludes)) != NULL) { 228 TAILQ_REMOVE(&ei->excludes, exclude, entry); 229 free(exclude); 230 } 231} 232 233static int 234/*ARGSUSED*/ 235_citrus_BIG5_encoding_module_init(_BIG5EncodingInfo * __restrict ei, 236 const void * __restrict var, size_t lenvar) 237{ 238 const char *s; 239 int err; 240 241 memset((void *)ei, 0, sizeof(*ei)); 242 TAILQ_INIT(&ei->excludes); 243 244 if (lenvar > 0 && var != NULL) { 245 s = _bcs_skip_ws_len((const char *)var, &lenvar); 246 if (lenvar > 0 && *s != '\0') { 247 err = _citrus_prop_parse_variable( 248 root_hints, (void *)ei, s, lenvar); 249 if (err == 0) 250 return (0); 251 252 _citrus_BIG5_encoding_module_uninit(ei); 253 memset((void *)ei, 0, sizeof(*ei)); 254 TAILQ_INIT(&ei->excludes); 255 } 256 } 257 258 /* fallback Big5-1984, for backward compatibility. */ 259 _citrus_BIG5_fill_rowcol(ei, "row", 0xA1, 0xFE); 260 _citrus_BIG5_fill_rowcol(ei, "col", 0x40, 0x7E); 261 _citrus_BIG5_fill_rowcol(ei, "col", 0xA1, 0xFE); 262 263 return (0); 264} 265 266static int 267/*ARGSUSED*/ 268_citrus_BIG5_mbrtowc_priv(_BIG5EncodingInfo * __restrict ei, 269 wchar_t * __restrict pwc, 270 const char ** __restrict s, size_t n, 271 _BIG5State * __restrict psenc, 272 size_t * __restrict nresult) 273{ 274 wchar_t wchar; 275 const char *s0; 276 int c, chlenbak; 277 278 s0 = *s; 279 280 if (s0 == NULL) { 281 _citrus_BIG5_init_state(ei, psenc); 282 *nresult = 0; 283 return (0); 284 } 285 286 chlenbak = psenc->chlen; 287 288 /* make sure we have the first byte in the buffer */ 289 switch (psenc->chlen) { 290 case 0: 291 if (n < 1) 292 goto restart; 293 psenc->ch[0] = *s0++; 294 psenc->chlen = 1; 295 n--; 296 break; 297 case 1: 298 break; 299 default: 300 /* illegal state */ 301 goto ilseq; 302 } 303 304 c = _citrus_BIG5_check(ei, psenc->ch[0] & 0xff); 305 if (c == 0) 306 goto ilseq; 307 while (psenc->chlen < c) { 308 if (n < 1) { 309 goto restart; 310 } 311 psenc->ch[psenc->chlen] = *s0++; 312 psenc->chlen++; 313 n--; 314 } 315 316 switch (c) { 317 case 1: 318 wchar = psenc->ch[0] & 0xff; 319 break; 320 case 2: 321 if (!_citrus_BIG5_check2(ei, psenc->ch[1] & 0xff)) 322 goto ilseq; 323 wchar = ((psenc->ch[0] & 0xff) << 8) | (psenc->ch[1] & 0xff); 324 break; 325 default: 326 /* illegal state */ 327 goto ilseq; 328 } 329 330 if (_citrus_BIG5_check_excludes(ei, (wint_t)wchar) != 0) 331 goto ilseq; 332 333 *s = s0; 334 psenc->chlen = 0; 335 if (pwc) 336 *pwc = wchar; 337 *nresult = wchar ? c - chlenbak : 0; 338 339 return (0); 340 341ilseq: 342 psenc->chlen = 0; 343 *nresult = (size_t)-1; 344 return (EILSEQ); 345 346restart: 347 *s = s0; 348 *nresult = (size_t)-2; 349 return (0); 350} 351 352static int 353/*ARGSUSED*/ 354_citrus_BIG5_wcrtomb_priv(_BIG5EncodingInfo * __restrict ei, 355 char * __restrict s, 356 size_t n, wchar_t wc, _BIG5State * __restrict psenc __unused, 357 size_t * __restrict nresult) 358{ 359 unsigned char l; 360 int ret; 361 362 /* check invalid sequence */ 363 if (wc & ~0xffff || 364 _citrus_BIG5_check_excludes(ei, (wint_t)wc) != 0) { 365 ret = EILSEQ; 366 goto err; 367 } 368 369 if (wc & 0x8000) { 370 if (_citrus_BIG5_check(ei, (wc >> 8) & 0xff) != 2 || 371 !_citrus_BIG5_check2(ei, wc & 0xff)) { 372 ret = EILSEQ; 373 goto err; 374 } 375 l = 2; 376 } else { 377 if (wc & ~0xff || !_citrus_BIG5_check(ei, wc & 0xff)) { 378 ret = EILSEQ; 379 goto err; 380 } 381 l = 1; 382 } 383 384 if (n < l) { 385 /* bound check failure */ 386 ret = E2BIG; 387 goto err; 388 } 389 390 if (l == 2) { 391 s[0] = (wc >> 8) & 0xff; 392 s[1] = wc & 0xff; 393 } else 394 s[0] = wc & 0xff; 395 396 *nresult = l; 397 398 return (0); 399 400err: 401 *nresult = (size_t)-1; 402 return (ret); 403} 404 405static __inline int 406/*ARGSUSED*/ 407_citrus_BIG5_stdenc_wctocs(_BIG5EncodingInfo * __restrict ei __unused, 408 _csid_t * __restrict csid, 409 _index_t * __restrict idx, wchar_t wc) 410{ 411 412 *csid = (wc < 0x100) ? 0 : 1; 413 *idx = (_index_t)wc; 414 415 return (0); 416} 417 418static __inline int 419/*ARGSUSED*/ 420_citrus_BIG5_stdenc_cstowc(_BIG5EncodingInfo * __restrict ei __unused, 421 wchar_t * __restrict wc, 422 _csid_t csid, _index_t idx) 423{ 424 425 switch (csid) { 426 case 0: 427 case 1: 428 *wc = (wchar_t)idx; 429 break; 430 default: 431 return (EILSEQ); 432 } 433 434 return (0); 435} 436 437static __inline int 438/*ARGSUSED*/ 439_citrus_BIG5_stdenc_get_state_desc_generic(_BIG5EncodingInfo * __restrict ei __unused, 440 _BIG5State * __restrict psenc, 441 int * __restrict rstate) 442{ 443 444 *rstate = (psenc->chlen == 0) ? _STDENC_SDGEN_INITIAL : 445 _STDENC_SDGEN_INCOMPLETE_CHAR; 446 return (0); 447} 448 449/* ---------------------------------------------------------------------- 450 * public interface for stdenc 451 */ 452 453_CITRUS_STDENC_DECLS(BIG5); 454_CITRUS_STDENC_DEF_OPS(BIG5); 455 456#include "citrus_stdenc_template.h" 457