lib/libc/citrus/modules/citrus_utf8.c

   1 /* $NetBSD: citrus_utf8.c,v 1.16 2007/03/06 16:13:58 tnozaki Exp $ */
   2 /* $DragonFly: src/lib/libc/citrus/modules/citrus_utf8.c,v 1.3 2008/05/20 21:13:39 hasso 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/types.h>
  63 #include <assert.h>
  64 #include <errno.h>
  65 #include <limits.h>
  66 #include <locale.h>
  67 #include <stddef.h>
  68 #include <stdio.h>
  69 #include <stdlib.h>
  70 #include <string.h>
  71 #include <wchar.h>
  72
  73 #include "citrus_namespace.h"
  74 #include "citrus_types.h"
  75 #include "citrus_module.h"
  76 #include "citrus_ctype.h"
  77 #include "citrus_stdenc.h"
  78 #include "citrus_utf8.h"
  79
  80
  81 /* ----------------------------------------------------------------------
  82  * private stuffs used by templates
  83  */
  84
  85 static int _UTF8_count_array[256];
  86 static int const *_UTF8_count = NULL;
  87
  88 static const u_int32_t _UTF8_range[] = {
  89         0,      /*dummy*/
  90         0x00000000, 0x00000080, 0x00000800, 0x00010000,
  91         0x00200000, 0x04000000, 0x80000000,
  92 };
  93
  94 typedef struct {
  95         char ch[6];
  96         int chlen;
  97 } _UTF8State;
  98
  99 typedef struct {
 100 } _UTF8EncodingInfo;
 101
 102 typedef struct {
 103         _UTF8EncodingInfo       ei;
 104         struct {
 105                 /* for future multi-locale facility */
 106                 _UTF8State      s_mblen;
 107                 _UTF8State      s_mbrlen;
 108                 _UTF8State      s_mbrtowc;
 109                 _UTF8State      s_mbtowc;
 110                 _UTF8State      s_mbsrtowcs;
 111                 _UTF8State      s_wcrtomb;
 112                 _UTF8State      s_wcsrtombs;
 113                 _UTF8State      s_wctomb;
 114         } states;
 115 } _UTF8CTypeInfo;
 116
 117 #define _CEI_TO_EI(_cei_)               (&(_cei_)->ei)
 118 #define _CEI_TO_STATE(_ei_, _func_)     (_ei_)->states.s_##_func_
 119
 120 #define _FUNCNAME(m)                    _citrus_UTF8_##m
 121 #define _ENCODING_INFO                  _UTF8EncodingInfo
 122 #define _CTYPE_INFO                     _UTF8CTypeInfo
 123 #define _ENCODING_STATE                 _UTF8State
 124 #define _ENCODING_MB_CUR_MAX(_ei_)      6
 125 #define _ENCODING_IS_STATE_DEPENDENT    0
 126 #define _STATE_NEEDS_EXPLICIT_INIT(_ps_)        0
 127
 128
 129 static __inline void
 130 _UTF8_init_count(void)
 131 {
 132         int i;
 133         if (!_UTF8_count) {
 134                 memset(_UTF8_count_array, 0, sizeof(_UTF8_count_array));
 135                 for (i = 0; i <= 0x7f; i++)
 136                         _UTF8_count_array[i] = 1;
 137                 for (i = 0xc0; i <= 0xdf; i++)
 138                         _UTF8_count_array[i] = 2;
 139                 for (i = 0xe0; i <= 0xef; i++)
 140                         _UTF8_count_array[i] = 3;
 141                 for (i = 0xf0; i <= 0xf7; i++)
 142                         _UTF8_count_array[i] = 4;
 143                 for (i = 0xf8; i <= 0xfb; i++)
 144                         _UTF8_count_array[i] = 5;
 145                 for (i = 0xfc; i <= 0xfd; i++)
 146                         _UTF8_count_array[i] = 6;
 147                 _UTF8_count = _UTF8_count_array;
 148         }
 149 }
 150
 151 static int
 152 _UTF8_findlen(wchar_t v)
 153 {
 154         int i;
 155         u_int32_t c;
 156
 157         c = (u_int32_t)v;       /*XXX*/
 158         for (i = 1; i < sizeof(_UTF8_range) / sizeof(_UTF8_range[0]) - 1; i++)
 159                 if (c >= _UTF8_range[i] && c < _UTF8_range[i + 1])
 160                         return i;
 161
 162         return -1;      /*out of range*/
 163 }
 164
 165 static __inline int
 166 _UTF8_surrogate(wchar_t wc)
 167 {
 168         return wc >= 0xd800 && wc <= 0xdfff;
 169 }
 170
 171 static __inline void
 172 /*ARGSUSED*/
 173 _citrus_UTF8_init_state(_UTF8EncodingInfo *ei, _UTF8State *s)
 174 {
 175         s->chlen = 0;
 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
 203         _DIAGASSERT(nresult != 0);
 204         _DIAGASSERT(s != NULL);
 205         _DIAGASSERT(psenc != NULL);
 206
 207         s0 = *s;
 208
 209         if (s0 == NULL) {
 210                 _citrus_UTF8_init_state(ei, psenc);
 211                 *nresult = 0; /* state independent */
 212                 return 0;
 213         }
 214
 215         /* make sure we have the first byte in the buffer */
 216         if (psenc->chlen == 0) {
 217                 if (n-- < 1)
 218                         goto restart;
 219                 psenc->ch[psenc->chlen++] = *s0++;
 220         }
 221
 222         c = _UTF8_count[psenc->ch[0] & 0xff];
 223         if (c < 1 || c < psenc->chlen)
 224                 goto ilseq;
 225
 226         if (c == 1)
 227                 wchar = psenc->ch[0] & 0xff;
 228         else {
 229                 while (psenc->chlen < c) {
 230                         if (n-- < 1)
 231                                 goto restart;
 232                         psenc->ch[psenc->chlen++] = *s0++;
 233                 }
 234                 wchar = psenc->ch[0] & (0x7f >> c);
 235                 for (i = 1; i < c; i++) {
 236                         if ((psenc->ch[i] & 0xc0) != 0x80)
 237                                 goto ilseq;
 238                         wchar <<= 6;
 239                         wchar |= (psenc->ch[i] & 0x3f);
 240                 }
 241                 if (_UTF8_surrogate(wchar) || _UTF8_findlen(wchar) != c)
 242                         goto ilseq;
 243         }
 244         if (pwc != NULL)
 245                 *pwc = wchar;
 246         *nresult = (wchar == 0) ? 0 : s0 - *s;
 247         *s = s0;
 248         psenc->chlen = 0;
 249
 250         return 0;
 251
 252 ilseq:
 253         *nresult = (size_t)-1;
 254         return EILSEQ;
 255
 256 restart:
 257         *s = s0;
 258         *nresult = (size_t)-2;
 259         return 0;
 260 }
 261
 262 static int
 263 _citrus_UTF8_wcrtomb_priv(_UTF8EncodingInfo *ei, char *s, size_t n, wchar_t wc,
 264                           _UTF8State *psenc, size_t *nresult)
 265 {
 266         int cnt, i, ret;
 267         wchar_t c;
 268
 269         _DIAGASSERT(nresult != 0);
 270         _DIAGASSERT(s != NULL);
 271
 272         if (_UTF8_surrogate(wc)) {
 273                 ret = EILSEQ;
 274                 goto err;
 275         }
 276         cnt = _UTF8_findlen(wc);
 277         if (cnt <= 0 || cnt > 6) {
 278                 /* invalid UCS4 value */
 279                 ret = EILSEQ;
 280                 goto err;
 281         }
 282         if (n < cnt) {
 283                 /* bound check failure */
 284                 ret = E2BIG;
 285                 goto err;
 286         }
 287
 288         c = wc;
 289         if (s) {
 290                 for (i = cnt - 1; i > 0; i--) {
 291                         s[i] = 0x80 | (c & 0x3f);
 292                         c >>= 6;
 293                 }
 294                 s[0] = c;
 295                 if (cnt == 1)
 296                         s[0] &= 0x7f;
 297                 else {
 298                         s[0] &= (0x7f >> cnt);
 299                         s[0] |= ((0xff00 >> cnt) & 0xff);
 300                 }
 301         }
 302
 303         *nresult = (size_t)cnt;
 304         return 0;
 305
 306 err:
 307         *nresult = (size_t)-1;
 308         return ret;
 309 }
 310
 311 static __inline int
 312 /*ARGSUSED*/
 313 _citrus_UTF8_stdenc_wctocs(_UTF8EncodingInfo * __restrict ei,
 314                            _csid_t * __restrict csid,
 315                            _index_t * __restrict idx,
 316                            wchar_t wc)
 317 {
 318
 319         _DIAGASSERT(csid != NULL && idx != NULL);
 320
 321         *csid = 0;
 322         *idx = (_citrus_index_t)wc;
 323
 324         return (0);
 325 }
 326
 327 static __inline int
 328 /*ARGSUSED*/
 329 _citrus_UTF8_stdenc_cstowc(_UTF8EncodingInfo * __restrict ei,
 330                            wchar_t * __restrict wc,
 331                            _csid_t csid, _index_t idx)
 332 {
 333
 334         _DIAGASSERT(wc != NULL);
 335
 336         if (csid != 0)
 337                 return (EILSEQ);
 338
 339         *wc = (wchar_t)idx;
 340
 341         return (0);
 342 }
 343
 344 static __inline int
 345 /*ARGSUSED*/
 346 _citrus_UTF8_stdenc_get_state_desc_generic(_UTF8EncodingInfo * __restrict ei,
 347                                            _UTF8State * __restrict psenc,
 348                                            int * __restrict rstate)
 349 {
 350
 351         if (psenc->chlen == 0)
 352                 *rstate = _STDENC_SDGEN_INITIAL;
 353         else
 354                 *rstate = _STDENC_SDGEN_INCOMPLETE_CHAR;
 355
 356         return 0;
 357 }
 358
 359 static int
 360 /*ARGSUSED*/
 361 _citrus_UTF8_encoding_module_init(_UTF8EncodingInfo * __restrict ei,
 362                                   const void * __restrict var, size_t lenvar)
 363 {
 364         _UTF8_init_count();
 365
 366         return 0;
 367 }
 368
 369 static void
 370 /*ARGSUSED*/
 371 _citrus_UTF8_encoding_module_uninit(_UTF8EncodingInfo *ei)
 372 {
 373 }
 374
 375
 376 /* ----------------------------------------------------------------------
 377  * public interface for ctype
 378  */
 379
 380 _CITRUS_CTYPE_DECLS(UTF8);
 381 _CITRUS_CTYPE_DEF_OPS(UTF8);
 382
 383 #include "citrus_ctype_template.h"
 384
 385 /* ----------------------------------------------------------------------
 386  * public interface for stdenc
 387  */
 388
 389 _CITRUS_STDENC_DECLS(UTF8);
 390 _CITRUS_STDENC_DEF_OPS(UTF8);
 391
 392 #include "citrus_stdenc_template.h"