citrus_mskanji.c revision 1.10
1 /* $NetBSD: citrus_mskanji.c,v 1.10 2005/10/18 06:44:28 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 * ja_JP.SJIS locale table for BSD4.4/rune 31 * version 1.0 32 * (C) Sin'ichiro MIYATANI / Phase One, Inc 33 * May 12, 1995 34 * 35 * Redistribution and use in source and binary forms, with or without 36 * modification, are permitted provided that the following conditions 37 * are met: 38 * 1. Redistributions of source code must retain the above copyright 39 * notice, this list of conditions and the following disclaimer. 40 * 2. Redistributions in binary form must reproduce the above copyright 41 * notice, this list of conditions and the following disclaimer in the 42 * documentation and/or other materials provided with the distribution. 43 * 3. All advertising materials mentioning features or use of this software 44 * must display the following acknowledgement: 45 * This product includes software developed by Phase One, Inc. 46 * 4. The name of Phase One, Inc. may be used to endorse or promote products 47 * derived from this software 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 63 #include <sys/cdefs.h> 64 #if defined(LIBC_SCCS) && !defined(lint) 65 __RCSID("$NetBSD: citrus_mskanji.c,v 1.10 2005/10/18 06:44:28 tshiozak Exp $"); 66 #endif /* LIBC_SCCS and not lint */ 67 68 #include <assert.h> 69 #include <errno.h> 70 #include <string.h> 71 #include <stdio.h> 72 #include <stdlib.h> 73 #include <stddef.h> 74 #include <locale.h> 75 #include <wchar.h> 76 #include <sys/types.h> 77 #include <limits.h> 78 79 #include "citrus_namespace.h" 80 #include "citrus_types.h" 81 #include "citrus_module.h" 82 #include "citrus_ctype.h" 83 #include "citrus_stdenc.h" 84 #include "citrus_mskanji.h" 85 86 87 /* ---------------------------------------------------------------------- 88 * private stuffs used by templates 89 */ 90 91 typedef struct _MSKanjiState { 92 char ch[2]; 93 int chlen; 94 } _MSKanjiState; 95 96 typedef struct { 97 int dummy; 98 } _MSKanjiEncodingInfo; 99 100 typedef struct { 101 _MSKanjiEncodingInfo ei; 102 struct { 103 /* for future multi-locale facility */ 104 _MSKanjiState s_mblen; 105 _MSKanjiState s_mbrlen; 106 _MSKanjiState s_mbrtowc; 107 _MSKanjiState s_mbtowc; 108 _MSKanjiState s_mbsrtowcs; 109 _MSKanjiState s_wcrtomb; 110 _MSKanjiState s_wcsrtombs; 111 _MSKanjiState s_wctomb; 112 } states; 113 } _MSKanjiCTypeInfo; 114 115 #define _CEI_TO_EI(_cei_) (&(_cei_)->ei) 116 #define _CEI_TO_STATE(_cei_, _func_) (_cei_)->states.s_##_func_ 117 118 #define _FUNCNAME(m) _citrus_MSKanji_##m 119 #define _ENCODING_INFO _MSKanjiEncodingInfo 120 #define _CTYPE_INFO _MSKanjiCTypeInfo 121 #define _ENCODING_STATE _MSKanjiState 122 #define _ENCODING_MB_CUR_MAX(_ei_) 2 123 #define _ENCODING_IS_STATE_DEPENDENT 0 124 #define _STATE_NEEDS_EXPLICIT_INIT(_ps_) 0 125 126 127 static int 128 _mskanji1(int c) 129 { 130 131 if ((c >= 0x81 && c <= 0x9f) || (c >= 0xe0 && c <= 0xfc)) 132 return 1; 133 else 134 return 0; 135 } 136 137 static int 138 _mskanji2(int c) 139 { 140 141 if ((c >= 0x40 && c <= 0x7e) || (c >= 0x80 && c <= 0xfc)) 142 return 1; 143 else 144 return 0; 145 } 146 147 static __inline void 148 /*ARGSUSED*/ 149 _citrus_MSKanji_init_state(_MSKanjiEncodingInfo * __restrict ei, 150 _MSKanjiState * __restrict s) 151 { 152 memset(s, 0, sizeof(*s)); 153 } 154 155 static __inline void 156 /*ARGSUSED*/ 157 _citrus_MSKanji_pack_state(_MSKanjiEncodingInfo * __restrict ei, 158 void * __restrict pspriv, 159 const _MSKanjiState * __restrict s) 160 { 161 memcpy(pspriv, (const void *)s, sizeof(*s)); 162 } 163 164 static __inline void 165 /*ARGSUSED*/ 166 _citrus_MSKanji_unpack_state(_MSKanjiEncodingInfo * __restrict ei, 167 _MSKanjiState * __restrict s, 168 const void * __restrict pspriv) 169 { 170 memcpy((void *)s, pspriv, sizeof(*s)); 171 } 172 173 static int 174 /*ARGSUSED*/ 175 _citrus_MSKanji_mbrtowc_priv(_MSKanjiEncodingInfo * __restrict ei, 176 wchar_t * __restrict pwc, 177 const char ** __restrict s, size_t n, 178 _MSKanjiState * __restrict psenc, 179 size_t * __restrict nresult) 180 { 181 wchar_t wchar; 182 int len; 183 int chlenbak; 184 const char *s0; 185 186 _DIAGASSERT(nresult != 0); 187 _DIAGASSERT(ei != NULL); 188 _DIAGASSERT(s != NULL); 189 _DIAGASSERT(psenc != NULL); 190 191 s0 = *s; 192 193 if (s0 == NULL) { 194 _citrus_MSKanji_init_state(ei, psenc); 195 *nresult = 0; /* state independent */ 196 return (0); 197 } 198 199 chlenbak = psenc->chlen; 200 201 /* make sure we have the first byte in the buffer */ 202 switch (psenc->chlen) { 203 case 0: 204 if (n < 1) 205 goto restart; 206 psenc->ch[0] = *s0++; 207 psenc->chlen = 1; 208 n--; 209 break; 210 case 1: 211 break; 212 default: 213 /* illegal state */ 214 goto encoding_error; 215 } 216 217 len = _mskanji1(psenc->ch[0] & 0xff) ? 2 : 1; 218 while (psenc->chlen < len) { 219 if (n < 1) 220 goto restart; 221 psenc->ch[psenc->chlen] = *s0++; 222 psenc->chlen++; 223 n--; 224 } 225 226 *s = s0; 227 228 switch (len) { 229 case 1: 230 wchar = psenc->ch[0] & 0xff; 231 break; 232 case 2: 233 if (!_mskanji2(psenc->ch[1] & 0xff)) 234 goto encoding_error; 235 wchar = ((psenc->ch[0] & 0xff) << 8) | (psenc->ch[1] & 0xff); 236 break; 237 default: 238 /* illegal state */ 239 goto encoding_error; 240 } 241 242 psenc->chlen = 0; 243 244 if (pwc) 245 *pwc = wchar; 246 247 if (!wchar) 248 *nresult = 0; 249 else 250 *nresult = len - chlenbak; 251 252 return (0); 253 254 encoding_error: 255 psenc->chlen = 0; 256 *nresult = (size_t)-1; 257 return (EILSEQ); 258 259 restart: 260 *nresult = (size_t)-2; 261 *s = s0; 262 return (0); 263 } 264 265 266 static int 267 _citrus_MSKanji_wcrtomb_priv(_MSKanjiEncodingInfo * __restrict ei, 268 char * __restrict s, size_t n, wchar_t wc, 269 _MSKanjiState * __restrict psenc, 270 size_t * __restrict nresult) 271 { 272 int ret; 273 274 _DIAGASSERT(ei != NULL); 275 _DIAGASSERT(psenc != NULL); 276 _DIAGASSERT(s != NULL); 277 278 /* check invalid sequence */ 279 if (wc & ~0xffff) { 280 ret = EILSEQ; 281 goto err; 282 } 283 284 if (wc & 0xff00) { 285 if (n < 2) { 286 ret = E2BIG; 287 goto err; 288 } 289 290 s[0] = (wc >> 8) & 0xff; 291 s[1] = wc & 0xff; 292 if (!_mskanji1(s[0] & 0xff) || !_mskanji2(s[1] & 0xff)) { 293 ret = EILSEQ; 294 goto err; 295 } 296 297 *nresult = 2; 298 return 0; 299 } else { 300 if (n < 1) { 301 ret = E2BIG; 302 goto err; 303 } 304 305 s[0] = wc & 0xff; 306 if (_mskanji1(s[0] & 0xff)) { 307 ret = EILSEQ; 308 goto err; 309 } 310 311 *nresult = 1; 312 return 0; 313 } 314 315 err: 316 *nresult = (size_t)-1; 317 return ret; 318 } 319 320 321 static __inline int 322 /*ARGSUSED*/ 323 _citrus_MSKanji_stdenc_wctocs(_MSKanjiEncodingInfo * __restrict ei, 324 _csid_t * __restrict csid, 325 _index_t * __restrict idx, wchar_t wc) 326 { 327 _index_t row, col; 328 329 _DIAGASSERT(csid != NULL && idx != NULL); 330 331 if ((_wc_t)wc < 0x80) { 332 /* ISO-646 */ 333 *csid = 0; 334 *idx = (_index_t)wc; 335 } else if ((_wc_t)wc < 0x100) { 336 /* KANA */ 337 *csid = 1; 338 *idx = (_index_t)wc & 0x7F; 339 } else if ((0x8140 <= (_wc_t)wc && (_wc_t)wc <= 0x9FFC) || 340 (0xE040 <= (_wc_t)wc && (_wc_t)wc <= 0xFCFC)) { 341 /* Kanji (containing Gaiji zone) */ 342 /* 343 * 94^2 zone (contains a part of Gaiji (0xED40 - 0xEEFC)): 344 * 0x8140 - 0x817E -> 0x2121 - 0x215F 345 * 0x8180 - 0x819E -> 0x2160 - 0x217E 346 * 0x819F - 0x81FC -> 0x2221 - 0x227E 347 * 348 * 0x8240 - 0x827E -> 0x2321 - 0x235F 349 * ... 350 * 0x9F9F - 0x9FFc -> 0x5E21 - 0x5E7E 351 * 352 * 0xE040 - 0xE07E -> 0x5F21 - 0x5F5F 353 * ... 354 * 0xEF9F - 0xEFFC -> 0x7E21 - 0x7E7E 355 * 356 * extended Gaiji zone: 357 * 0xF040 - 0xFCFC 358 */ 359 *csid = 2; 360 row = ((_wc_t)wc >> 8) - 0x81; 361 if (row >= 0x5F) 362 row -= 0x40; 363 row = row * 2 + 0x21; 364 col = (wc & 0xFF) - 0x1F; 365 if (col >= 0x61) 366 col -= 1; 367 if (col > 0x7E) { 368 row += 1; 369 col -= 0x5E; 370 } 371 *idx = ((_index_t)row << 8) | col; 372 } else 373 return EILSEQ; 374 375 return 0; 376 } 377 378 static __inline int 379 /*ARGSUSED*/ 380 _citrus_MSKanji_stdenc_cstowc(_MSKanjiEncodingInfo * __restrict ei, 381 wchar_t * __restrict wc, 382 _csid_t csid, _index_t idx) 383 { 384 u_int32_t row, col; 385 386 _DIAGASSERT(wc != NULL); 387 388 switch (csid) { 389 case 0: 390 /* ISO-646 */ 391 if (idx >= 0x80) 392 return EILSEQ; 393 *wc = (wchar_t)idx; 394 break; 395 case 1: 396 /* kana */ 397 if (idx >= 0x80) 398 return EILSEQ; 399 *wc = (wchar_t)idx + 0x80; 400 break; 401 case 2: 402 /* kanji */ 403 row = (idx >> 8); 404 col = idx & 0x7F; 405 if (row<0x21 || row>0x97 || col<0x21 || col>0x7E) 406 return EILSEQ; 407 row -= 0x21; col -= 0x21; 408 if ((row & 1)==0) { 409 col += 0x40; 410 if (col>=0x7F) 411 col += 1; 412 } else 413 col += 0x9F; 414 if (row<0x3E) 415 row = row/2 + 0x81; 416 else 417 row = row/2 + 0xc1; 418 *wc = ((wchar_t)row << 8) | col; 419 break; 420 default: 421 return EILSEQ; 422 } 423 424 return 0; 425 } 426 427 static int 428 /*ARGSUSED*/ 429 _citrus_MSKanji_encoding_module_init(_MSKanjiEncodingInfo * __restrict ei, 430 const void * __restrict var, 431 size_t lenvar) 432 { 433 434 _DIAGASSERT(ei != NULL); 435 436 return (0); 437 } 438 439 static void 440 _citrus_MSKanji_encoding_module_uninit(_MSKanjiEncodingInfo *ei) 441 { 442 } 443 444 /* ---------------------------------------------------------------------- 445 * public interface for ctype 446 */ 447 448 _CITRUS_CTYPE_DECLS(MSKanji); 449 _CITRUS_CTYPE_DEF_OPS(MSKanji); 450 451 #include "citrus_ctype_template.h" 452 453 /* ---------------------------------------------------------------------- 454 * public interface for stdenc 455 */ 456 457 _CITRUS_STDENC_DECLS(MSKanji); 458 _CITRUS_STDENC_DEF_OPS(MSKanji); 459 460 #include "citrus_stdenc_template.h" 461
Indexes created Tue Sep 30 20:09:53 GMT 2025