1 /* $FreeBSD$ */ 2 /* $NetBSD: citrus_euc.c,v 1.14 2009/01/11 02:46:24 christos Exp $ */ 3 4 /*- 5 * Copyright (c)2002 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/types.h> 64 65 #include <assert.h> 66 #include <errno.h> 67 #include <limits.h> 68 #include <stddef.h> 69 #include <stdio.h> 70 #include <stdlib.h> 71 #include <string.h> 72 #include <wchar.h> 73 74 #include "citrus_namespace.h" 75 #include "citrus_bcs.h" 76 #include "citrus_types.h" 77 #include "citrus_module.h" 78 #include "citrus_stdenc.h" 79 #include "citrus_euc.h" 80 81 82 /* ---------------------------------------------------------------------- 83 * private stuffs used by templates 84 */ 85 86 typedef struct { 87 int chlen; 88 char ch[3]; 89 } _EUCState; 90 91 typedef struct { 92 wchar_t bits[4]; 93 wchar_t mask; 94 unsigned count[4]; 95 unsigned mb_cur_max; 96 } _EUCEncodingInfo; 97 98 #define _SS2 0x008e 99 #define _SS3 0x008f 100 101 #define _CEI_TO_EI(_cei_) (&(_cei_)->ei) 102 #define _CEI_TO_STATE(_cei_, _func_) (_cei_)->states.s_##_func_ 103 104 #define _FUNCNAME(m) _citrus_EUC_##m 105 #define _ENCODING_INFO _EUCEncodingInfo 106 #define _ENCODING_STATE _EUCState 107 #define _ENCODING_MB_CUR_MAX(_ei_) (_ei_)->mb_cur_max 108 #define _ENCODING_IS_STATE_DEPENDENT 0 109 #define _STATE_NEEDS_EXPLICIT_INIT(_ps_) 0 110 111 112 static __inline int 113 _citrus_EUC_cs(unsigned int c) 114 { 115 116 c &= 0xff; 117 118 return ((c & 0x80) ? c == _SS3 ? 3 : c == _SS2 ? 2 : 1 : 0); 119 } 120 121 static __inline int 122 _citrus_EUC_parse_variable(_EUCEncodingInfo *ei, const void *var, 123 size_t lenvar __unused) 124 { 125 char *e; 126 const char *v; 127 int x; 128 129 /* parse variable string */ 130 if (!var) 131 return (EFTYPE); 132 133 v = (const char *)var; 134 135 while (*v == ' ' || *v == '\t') 136 ++v; 137 138 ei->mb_cur_max = 1; 139 for (x = 0; x < 4; ++x) { 140 ei->count[x] = (int)_bcs_strtol(v, (char **)&e, 0); 141 if (v == e || !(v = e) || ei->count[x] < 1 || ei->count[x] > 4) { 142 return (EFTYPE); 143 } 144 if (ei->mb_cur_max < ei->count[x]) 145 ei->mb_cur_max = ei->count[x]; 146 while (*v == ' ' || *v == '\t') 147 ++v; 148 ei->bits[x] = (int)_bcs_strtol(v, (char **)&e, 0); 149 if (v == e || !(v = e)) { 150 return (EFTYPE); 151 } 152 while (*v == ' ' || *v == '\t') 153 ++v; 154 } 155 ei->mask = (int)_bcs_strtol(v, (char **)&e, 0); 156 if (v == e || !(v = e)) { 157 return (EFTYPE); 158 } 159 160 return (0); 161 } 162 163 164 static __inline void 165 /*ARGSUSED*/ 166 _citrus_EUC_init_state(_EUCEncodingInfo *ei __unused, _EUCState *s) 167 { 168 169 memset(s, 0, sizeof(*s)); 170 } 171 172 static __inline void 173 /*ARGSUSED*/ 174 _citrus_EUC_pack_state(_EUCEncodingInfo *ei __unused, void *pspriv, 175 const _EUCState *s) 176 { 177 178 memcpy(pspriv, (const void *)s, sizeof(*s)); 179 } 180 181 static __inline void 182 /*ARGSUSED*/ 183 _citrus_EUC_unpack_state(_EUCEncodingInfo *ei __unused, _EUCState *s, 184 const void *pspriv) 185 { 186 187 memcpy((void *)s, pspriv, sizeof(*s)); 188 } 189 190 static int 191 _citrus_EUC_mbrtowc_priv(_EUCEncodingInfo *ei, wchar_t *pwc, const char **s, 192 size_t n, _EUCState *psenc, size_t *nresult) 193 { 194 wchar_t wchar; 195 int c, chlenbak, cs, len; 196 const char *s0, *s1 = NULL; 197 198 s0 = *s; 199 200 if (s0 == NULL) { 201 _citrus_EUC_init_state(ei, psenc); 202 *nresult = 0; /* state independent */ 203 return (0); 204 } 205 206 chlenbak = psenc->chlen; 207 208 /* make sure we have the first byte in the buffer */ 209 switch (psenc->chlen) { 210 case 0: 211 if (n < 1) 212 goto restart; 213 psenc->ch[0] = *s0++; 214 psenc->chlen = 1; 215 n--; 216 break; 217 case 1: 218 case 2: 219 break; 220 default: 221 /* illgeal state */ 222 goto encoding_error; 223 } 224 225 c = ei->count[cs = _citrus_EUC_cs(psenc->ch[0] & 0xff)]; 226 if (c == 0) 227 goto encoding_error; 228 while (psenc->chlen < c) { 229 if (n < 1) 230 goto restart; 231 psenc->ch[psenc->chlen] = *s0++; 232 psenc->chlen++; 233 n--; 234 } 235 *s = s0; 236 237 switch (cs) { 238 case 3: 239 case 2: 240 /* skip SS2/SS3 */ 241 len = c - 1; 242 s1 = &psenc->ch[1]; 243 break; 244 case 1: 245 case 0: 246 len = c; 247 s1 = &psenc->ch[0]; 248 break; 249 default: 250 goto encoding_error; 251 } 252 wchar = 0; 253 while (len-- > 0) 254 wchar = (wchar << 8) | (*s1++ & 0xff); 255 wchar = (wchar & ~ei->mask) | ei->bits[cs]; 256 257 psenc->chlen = 0; 258 if (pwc) 259 *pwc = wchar; 260 *nresult = wchar ? (size_t)(c - chlenbak) : 0; 261 return (0); 262 263 encoding_error: 264 psenc->chlen = 0; 265 *nresult = (size_t)-1; 266 return (EILSEQ); 267 268 restart: 269 *nresult = (size_t)-2; 270 *s = s0; 271 return (0); 272 } 273 274 static int 275 _citrus_EUC_wcrtomb_priv(_EUCEncodingInfo *ei, char *s, size_t n, wchar_t wc, 276 _EUCState *psenc __unused, size_t *nresult) 277 { 278 wchar_t m, nm; 279 unsigned int cs; 280 int ret; 281 short i; 282 283 m = wc & ei->mask; 284 nm = wc & ~m; 285 286 for (cs = 0; cs < sizeof(ei->count) / sizeof(ei->count[0]); cs++) 287 if (m == ei->bits[cs]) 288 break; 289 /* fallback case - not sure if it is necessary */ 290 if (cs == sizeof(ei->count) / sizeof(ei->count[0])) 291 cs = 1; 292 293 i = ei->count[cs]; 294 if (n < (unsigned)i) { 295 ret = E2BIG; 296 goto err; 297 } 298 m = (cs) ? 0x80 : 0x00; 299 switch (cs) { 300 case 2: 301 *s++ = _SS2; 302 i--; 303 break; 304 case 3: 305 *s++ = _SS3; 306 i--; 307 break; 308 } 309 310 while (i-- > 0) 311 *s++ = ((nm >> (i << 3)) & 0xff) | m; 312 313 *nresult = (size_t)ei->count[cs]; 314 return (0); 315 316 err: 317 *nresult = (size_t)-1; 318 return (ret); 319 } 320 321 static __inline int 322 /*ARGSUSED*/ 323 _citrus_EUC_stdenc_wctocs(_EUCEncodingInfo * __restrict ei, 324 _csid_t * __restrict csid, _index_t * __restrict idx, wchar_t wc) 325 { 326 wchar_t m, nm; 327 328 m = wc & ei->mask; 329 nm = wc & ~m; 330 331 *csid = (_citrus_csid_t)m; 332 *idx = (_citrus_index_t)nm; 333 334 return (0); 335 } 336 337 static __inline int 338 /*ARGSUSED*/ 339 _citrus_EUC_stdenc_cstowc(_EUCEncodingInfo * __restrict ei, 340 wchar_t * __restrict wc, _csid_t csid, _index_t idx) 341 { 342 343 if ((csid & ~ei->mask) != 0 || (idx & ei->mask) != 0) 344 return (EINVAL); 345 346 *wc = (wchar_t)csid | (wchar_t)idx; 347 348 return (0); 349 } 350 351 static __inline int 352 /*ARGSUSED*/ 353 _citrus_EUC_stdenc_get_state_desc_generic(_EUCEncodingInfo * __restrict ei __unused, 354 _EUCState * __restrict psenc, int * __restrict rstate) 355 { 356 357 *rstate = (psenc->chlen == 0) ? _STDENC_SDGEN_INITIAL : 358 _STDENC_SDGEN_INCOMPLETE_CHAR; 359 return (0); 360 } 361 362 static int 363 /*ARGSUSED*/ 364 _citrus_EUC_encoding_module_init(_EUCEncodingInfo * __restrict ei, 365 const void * __restrict var, size_t lenvar) 366 { 367 368 return (_citrus_EUC_parse_variable(ei, var, lenvar)); 369 } 370 371 static void 372 /*ARGSUSED*/ 373 _citrus_EUC_encoding_module_uninit(_EUCEncodingInfo * __restrict ei __unused) 374 { 375 376 } 377 378 /* ---------------------------------------------------------------------- 379 * public interface for stdenc 380 */ 381 382 _CITRUS_STDENC_DECLS(EUC); 383 _CITRUS_STDENC_DEF_OPS(EUC); 384 385 #include "citrus_stdenc_template.h" 386