citrus_mskanji.c revision 1.3
1 /* $NetBSD: citrus_mskanji.c,v 1.3 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 * 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 1.3 2002/03/27 17:54:42 yamt 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 #include "citrus_module.h" 79 #include "citrus_ctype.h" 80 #include "citrus_mskanji.h" 81 82 83 /* ---------------------------------------------------------------------- 84 * private stuffs used by templates 85 */ 86 87 typedef struct _MSKanjiState { 88 char ch[2]; 89 int chlen; 90 } _MSKanjiState; 91 92 typedef struct { 93 int dummy; 94 } _MSKanjiEncodingInfo; 95 96 typedef struct { 97 _MSKanjiEncodingInfo ei; 98 struct { 99 /* for future multi-locale facility */ 100 _MSKanjiState s_mblen; 101 _MSKanjiState s_mbrlen; 102 _MSKanjiState s_mbrtowc; 103 _MSKanjiState s_mbtowc; 104 _MSKanjiState s_mbsrtowcs; 105 _MSKanjiState s_wcrtomb; 106 _MSKanjiState s_wcsrtombs; 107 _MSKanjiState s_wctomb; 108 } states; 109 } _MSKanjiCTypeInfo; 110 111 #define _TO_EI(_cl_) ((_MSKanjiEncodingInfo *)(_cl_)) 112 #define _TO_CEI(_cl_) ((_MSKanjiCTypeInfo *)(_cl_)) 113 #define _TO_STATE(_ps_) ((_MSKanjiState *)(_ps_)) 114 #define _CEI_TO_EI(_cei_) (&(_cei_)->ei) 115 #define _CEI_TO_STATE(_cei_, _func_) (_cei_)->states.s_##_func_ 116 117 #define _FUNCNAME(m) _citrus_MSKanji_##m 118 #define _ENCODING_INFO _MSKanjiEncodingInfo 119 #define _CTYPE_INFO _MSKanjiCTypeInfo 120 #define _ENCODING_STATE _MSKanjiState 121 #define _ENCODING_MB_CUR_MAX(_ei_) 2 122 #define _ENCODING_IS_STATE_DEPENDENT 0 123 124 125 static int 126 _mskanji1(int c) 127 { 128 129 if ((c >= 0x81 && c <= 0x9f) || (c >= 0xe0 && c <= 0xef)) 130 return 1; 131 else 132 return 0; 133 } 134 135 static int 136 _mskanji2(int c) 137 { 138 139 if ((c >= 0x40 && c <= 0x7e) || (c >= 0x80 && c <= 0xfc)) 140 return 1; 141 else 142 return 0; 143 } 144 145 static __inline void 146 /*ARGSUSED*/ 147 _citrus_MSKanji_init_state(_MSKanjiEncodingInfo * __restrict ei, 148 _MSKanjiState * __restrict s) 149 { 150 memset(s, 0, sizeof(*s)); 151 } 152 153 static __inline void 154 /*ARGSUSED*/ 155 _citrus_MSKanji_pack_state(_MSKanjiEncodingInfo * __restrict ei, 156 void * __restrict pspriv, 157 const _MSKanjiState * __restrict s) 158 { 159 memcpy(pspriv, (const void *)s, sizeof(*s)); 160 } 161 162 static __inline void 163 /*ARGSUSED*/ 164 _citrus_MSKanji_unpack_state(_MSKanjiEncodingInfo * __restrict ei, 165 _MSKanjiState * __restrict s, 166 const void * __restrict pspriv) 167 { 168 memcpy((void *)s, pspriv, sizeof(*s)); 169 } 170 171 static int 172 /*ARGSUSED*/ 173 _citrus_MSKanji_mbrtowc_priv(_MSKanjiEncodingInfo * __restrict ei, 174 wchar_t * __restrict pwc, 175 const char ** __restrict s, size_t n, 176 _MSKanjiState * __restrict psenc, 177 size_t * __restrict nresult) 178 { 179 wchar_t wchar; 180 int len; 181 int chlenbak; 182 const char *s0; 183 184 _DIAGASSERT(nresult != 0); 185 _DIAGASSERT(ei != NULL); 186 _DIAGASSERT(s != NULL); 187 _DIAGASSERT(psenc != NULL); 188 189 s0 = *s; 190 191 if (s0 == NULL) { 192 _citrus_MSKanji_init_state(ei, psenc); 193 *nresult = 0; /* state independent */ 194 return (0); 195 } 196 197 chlenbak = psenc->chlen; 198 199 /* make sure we have the first byte in the buffer */ 200 switch (psenc->chlen) { 201 case 0: 202 if (n < 1) 203 goto restart; 204 psenc->ch[0] = *s0++; 205 psenc->chlen = 1; 206 n--; 207 break; 208 case 1: 209 break; 210 default: 211 /* illegal state */ 212 goto encoding_error; 213 } 214 215 len = _mskanji1(psenc->ch[0] & 0xff) ? 2 : 1; 216 while (psenc->chlen < len) { 217 if (n < 1) 218 goto restart; 219 psenc->ch[psenc->chlen] = *s0++; 220 psenc->chlen++; 221 n--; 222 } 223 224 *s = s0; 225 226 switch (len) { 227 case 1: 228 wchar = psenc->ch[0] & 0xff; 229 break; 230 case 2: 231 if (!_mskanji2(psenc->ch[1] & 0xff)) 232 goto encoding_error; 233 wchar = ((psenc->ch[0] & 0xff) << 8) | (psenc->ch[1] & 0xff); 234 break; 235 default: 236 /* illegal state */ 237 goto encoding_error; 238 } 239 240 psenc->chlen = 0; 241 242 if (pwc) 243 *pwc = wchar; 244 245 if (!wchar) 246 *nresult = 0; 247 else 248 *nresult = len - chlenbak; 249 250 return (0); 251 252 encoding_error: 253 psenc->chlen = 0; 254 *nresult = (size_t)-1; 255 return (EILSEQ); 256 257 restart: 258 *nresult = (size_t)-2; 259 *s = s0; 260 return (0); 261 } 262 263 264 static int 265 _citrus_MSKanji_wcrtomb_priv(_MSKanjiEncodingInfo * __restrict ei, 266 char * __restrict s, size_t n, wchar_t wc, 267 _MSKanjiState * __restrict psenc, 268 size_t * __restrict nresult) 269 { 270 271 _DIAGASSERT(ei != NULL); 272 _DIAGASSERT(psenc != NULL); 273 _DIAGASSERT(s != NULL); 274 275 /* check invalid sequence */ 276 if (wc & ~0xffff) 277 goto ilseq; 278 279 if (wc & 0xff00) { 280 if (n < 2) 281 goto ilseq; 282 283 s[0] = (wc >> 8) & 0xff; 284 s[1] = wc & 0xff; 285 if (!_mskanji1(s[0] & 0xff) || !_mskanji2(s[1] & 0xff)) 286 goto ilseq; 287 288 *nresult = 2; 289 return (0); 290 } else { 291 s[0] = wc & 0xff; 292 if (_mskanji1(s[0] & 0xff)) 293 goto ilseq; 294 295 *nresult = 1; 296 return (0); 297 } 298 299 ilseq: 300 *nresult = (size_t)-1; 301 return EILSEQ; 302 } 303 304 305 static int 306 /*ARGSUSED*/ 307 _citrus_MSKanji_stdencoding_init(_MSKanjiEncodingInfo * __restrict ei, 308 const void * __restrict var, size_t lenvar) 309 { 310 311 _DIAGASSERT(cl != NULL); 312 313 return (0); 314 } 315 316 static void 317 _citrus_MSKanji_stdencoding_uninit(_MSKanjiEncodingInfo *ei) 318 { 319 } 320 321 /* ---------------------------------------------------------------------- 322 * public interface for ctype 323 */ 324 325 _CITRUS_CTYPE_DECLS(MSKanji); 326 _CITRUS_CTYPE_DEF_OPS(MSKanji); 327 328 #include "citrus_ctype_template.h" 329
Indexes created Mon Oct 20 16:09:52 GMT 2025