1 /* $NetBSD: citrus_big5.c,v 1.13 2011/05/23 14:53:46 joerg Exp $ */
2
3 /*-
4 * Copyright (c)2002, 2006 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 * SPDX-License-Identifier: BSD-3-Clause
31 *
32 * Copyright (c) 1993
33 * The Regents of the University of California. All rights reserved.
34 *
35 * This code is derived from software contributed to Berkeley by
36 * Paul Borman at Krystal Technologies.
37 *
38 * Redistribution and use in source and binary forms, with or without
39 * modification, are permitted provided that the following conditions
40 * are met:
41 * 1. Redistributions of source code must retain the above copyright
42 * notice, this list of conditions and the following disclaimer.
43 * 2. Redistributions in binary form must reproduce the above copyright
44 * notice, this list of conditions and the following disclaimer in the
45 * documentation and/or other materials provided with the distribution.
46 * 3. Neither the name of the University nor the names of its contributors
47 * may be used to endorse or promote products derived from this software
48 * without specific prior written permission.
49 *
50 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
51 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
52 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
53 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
54 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
55 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
56 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
57 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
58 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
59 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
60 * SUCH DAMAGE.
61 */
62
63 #include <sys/cdefs.h>
64 #include <sys/queue.h>
65 #include <sys/types.h>
66
67 #include <assert.h>
68 #include <errno.h>
69 #include <limits.h>
70 #include <stddef.h>
71 #include <stdint.h>
72 #include <stdio.h>
73 #include <stdlib.h>
74 #include <string.h>
75 #include <wchar.h>
76
77 #include "citrus_namespace.h"
78 #include "citrus_prop.h"
79 #include "citrus_types.h"
80 #include "citrus_bcs.h"
81 #include "citrus_module.h"
82 #include "citrus_stdenc.h"
83 #include "citrus_big5.h"
84
85 /* ----------------------------------------------------------------------
86 * private stuffs used by templates
87 */
88
89 typedef struct {
90 int chlen;
91 char ch[2];
92 } _BIG5State;
93
94 typedef struct _BIG5Exclude {
95 TAILQ_ENTRY(_BIG5Exclude) entry;
96 wint_t start;
97 wint_t end;
98 } _BIG5Exclude;
99
100 typedef TAILQ_HEAD(_BIG5ExcludeList, _BIG5Exclude) _BIG5ExcludeList;
101
102 typedef struct {
103 _BIG5ExcludeList excludes;
104 int cell[0x100];
105 } _BIG5EncodingInfo;
106
107 #define _CEI_TO_EI(_cei_) (&(_cei_)->ei)
108 #define _CEI_TO_STATE(_cei_, _func_) (_cei_)->states.s_##_func_
109
110 #define _FUNCNAME(m) _citrus_BIG5_##m
111 #define _ENCODING_INFO _BIG5EncodingInfo
112 #define _ENCODING_STATE _BIG5State
113 #define _ENCODING_MB_CUR_MAX(_ei_) 2
114 #define _ENCODING_IS_STATE_DEPENDENT 0
115 #define _STATE_NEEDS_EXPLICIT_INIT(_ps_) 0
116
117
118 static __inline void
119 /*ARGSUSED*/
_citrus_BIG5_init_state(_BIG5EncodingInfo * __restrict ei __unused,_BIG5State * __restrict s)120 _citrus_BIG5_init_state(_BIG5EncodingInfo * __restrict ei __unused,
121 _BIG5State * __restrict s)
122 {
123
124 memset(s, 0, sizeof(*s));
125 }
126
127 #if 0
128 static __inline void
129 /*ARGSUSED*/
130 _citrus_BIG5_pack_state(_BIG5EncodingInfo * __restrict ei __unused,
131 void * __restrict pspriv,
132 const _BIG5State * __restrict s)
133 {
134
135 memcpy(pspriv, (const void *)s, sizeof(*s));
136 }
137
138 static __inline void
139 /*ARGSUSED*/
140 _citrus_BIG5_unpack_state(_BIG5EncodingInfo * __restrict ei __unused,
141 _BIG5State * __restrict s,
142 const void * __restrict pspriv)
143 {
144
145 memcpy((void *)s, pspriv, sizeof(*s));
146 }
147 #endif
148
149 static __inline int
_citrus_BIG5_check(_BIG5EncodingInfo * ei,unsigned int c)150 _citrus_BIG5_check(_BIG5EncodingInfo *ei, unsigned int c)
151 {
152
153 return ((ei->cell[c & 0xFF] & 0x1) ? 2 : 1);
154 }
155
156 static __inline int
_citrus_BIG5_check2(_BIG5EncodingInfo * ei,unsigned int c)157 _citrus_BIG5_check2(_BIG5EncodingInfo *ei, unsigned int c)
158 {
159
160 return ((ei->cell[c & 0xFF] & 0x2) ? 1 : 0);
161 }
162
163 static __inline int
_citrus_BIG5_check_excludes(_BIG5EncodingInfo * ei,wint_t c)164 _citrus_BIG5_check_excludes(_BIG5EncodingInfo *ei, wint_t c)
165 {
166 _BIG5Exclude *exclude;
167
168 TAILQ_FOREACH(exclude, &ei->excludes, entry) {
169 if (c >= exclude->start && c <= exclude->end)
170 return (EILSEQ);
171 }
172 return (0);
173 }
174
175 static int
_citrus_BIG5_fill_rowcol(void * __restrict ctx,const char * __restrict s,uint64_t start,uint64_t end)176 _citrus_BIG5_fill_rowcol(void * __restrict ctx, const char * __restrict s,
177 uint64_t start, uint64_t end)
178 {
179 _BIG5EncodingInfo *ei;
180 uint64_t n;
181 int i;
182
183 if (start > 0xFF || end > 0xFF)
184 return (EINVAL);
185 ei = (_BIG5EncodingInfo *)ctx;
186 i = strcmp("row", s) ? 1 : 0;
187 i = 1 << i;
188 for (n = start; n <= end; ++n)
189 ei->cell[n & 0xFF] |= i;
190 return (0);
191 }
192
193 static int
194 /*ARGSUSED*/
_citrus_BIG5_fill_excludes(void * __restrict ctx,const char * __restrict s __unused,uint64_t start,uint64_t end)195 _citrus_BIG5_fill_excludes(void * __restrict ctx,
196 const char * __restrict s __unused, uint64_t start, uint64_t end)
197 {
198 _BIG5EncodingInfo *ei;
199 _BIG5Exclude *exclude;
200
201 if (start > 0xFFFF || end > 0xFFFF)
202 return (EINVAL);
203 ei = (_BIG5EncodingInfo *)ctx;
204 exclude = TAILQ_LAST(&ei->excludes, _BIG5ExcludeList);
205 if (exclude != NULL && (wint_t)start <= exclude->end)
206 return (EINVAL);
207 exclude = (void *)malloc(sizeof(*exclude));
208 if (exclude == NULL)
209 return (ENOMEM);
210 exclude->start = (wint_t)start;
211 exclude->end = (wint_t)end;
212 TAILQ_INSERT_TAIL(&ei->excludes, exclude, entry);
213
214 return (0);
215 }
216
217 static const _citrus_prop_hint_t root_hints[] = {
218 _CITRUS_PROP_HINT_NUM("row", &_citrus_BIG5_fill_rowcol),
219 _CITRUS_PROP_HINT_NUM("col", &_citrus_BIG5_fill_rowcol),
220 _CITRUS_PROP_HINT_NUM("excludes", &_citrus_BIG5_fill_excludes),
221 _CITRUS_PROP_HINT_END
222 };
223
224 static void
225 /*ARGSUSED*/
_citrus_BIG5_encoding_module_uninit(_BIG5EncodingInfo * ei)226 _citrus_BIG5_encoding_module_uninit(_BIG5EncodingInfo *ei)
227 {
228 _BIG5Exclude *exclude;
229
230 while ((exclude = TAILQ_FIRST(&ei->excludes)) != NULL) {
231 TAILQ_REMOVE(&ei->excludes, exclude, entry);
232 free(exclude);
233 }
234 }
235
236 static int
237 /*ARGSUSED*/
_citrus_BIG5_encoding_module_init(_BIG5EncodingInfo * __restrict ei,const void * __restrict var,size_t lenvar)238 _citrus_BIG5_encoding_module_init(_BIG5EncodingInfo * __restrict ei,
239 const void * __restrict var, size_t lenvar)
240 {
241 const char *s;
242 int err;
243
244 memset((void *)ei, 0, sizeof(*ei));
245 TAILQ_INIT(&ei->excludes);
246
247 if (lenvar > 0 && var != NULL) {
248 s = _bcs_skip_ws_len((const char *)var, &lenvar);
249 if (lenvar > 0 && *s != '\0') {
250 err = _citrus_prop_parse_variable(
251 root_hints, (void *)ei, s, lenvar);
252 if (err == 0)
253 return (0);
254
255 _citrus_BIG5_encoding_module_uninit(ei);
256 memset((void *)ei, 0, sizeof(*ei));
257 TAILQ_INIT(&ei->excludes);
258 }
259 }
260
261 /* fallback Big5-1984, for backward compatibility. */
262 _citrus_BIG5_fill_rowcol(ei, "row", 0xA1, 0xFE);
263 _citrus_BIG5_fill_rowcol(ei, "col", 0x40, 0x7E);
264 _citrus_BIG5_fill_rowcol(ei, "col", 0xA1, 0xFE);
265
266 return (0);
267 }
268
269 static int
270 /*ARGSUSED*/
_citrus_BIG5_mbrtowc_priv(_BIG5EncodingInfo * __restrict ei,wchar_t * __restrict pwc,char ** __restrict s,size_t n,_BIG5State * __restrict psenc,size_t * __restrict nresult)271 _citrus_BIG5_mbrtowc_priv(_BIG5EncodingInfo * __restrict ei,
272 wchar_t * __restrict pwc,
273 char ** __restrict s, size_t n,
274 _BIG5State * __restrict psenc,
275 size_t * __restrict nresult)
276 {
277 wchar_t wchar;
278 char *s0;
279 int c, chlenbak;
280
281 s0 = *s;
282
283 if (s0 == NULL) {
284 _citrus_BIG5_init_state(ei, psenc);
285 *nresult = 0;
286 return (0);
287 }
288
289 chlenbak = psenc->chlen;
290
291 /* make sure we have the first byte in the buffer */
292 switch (psenc->chlen) {
293 case 0:
294 if (n < 1)
295 goto restart;
296 psenc->ch[0] = *s0++;
297 psenc->chlen = 1;
298 n--;
299 break;
300 case 1:
301 break;
302 default:
303 /* illegal state */
304 goto ilseq;
305 }
306
307 c = _citrus_BIG5_check(ei, psenc->ch[0] & 0xff);
308 if (c == 0)
309 goto ilseq;
310 while (psenc->chlen < c) {
311 if (n < 1) {
312 goto restart;
313 }
314 psenc->ch[psenc->chlen] = *s0++;
315 psenc->chlen++;
316 n--;
317 }
318
319 switch (c) {
320 case 1:
321 wchar = psenc->ch[0] & 0xff;
322 break;
323 case 2:
324 if (!_citrus_BIG5_check2(ei, psenc->ch[1] & 0xff))
325 goto ilseq;
326 wchar = ((psenc->ch[0] & 0xff) << 8) | (psenc->ch[1] & 0xff);
327 break;
328 default:
329 /* illegal state */
330 goto ilseq;
331 }
332
333 if (_citrus_BIG5_check_excludes(ei, (wint_t)wchar) != 0)
334 goto ilseq;
335
336 *s = s0;
337 psenc->chlen = 0;
338 if (pwc)
339 *pwc = wchar;
340 *nresult = wchar ? c - chlenbak : 0;
341
342 return (0);
343
344 ilseq:
345 psenc->chlen = 0;
346 *nresult = (size_t)-1;
347 return (EILSEQ);
348
349 restart:
350 *s = s0;
351 *nresult = (size_t)-2;
352 return (0);
353 }
354
355 static int
356 /*ARGSUSED*/
_citrus_BIG5_wcrtomb_priv(_BIG5EncodingInfo * __restrict ei,char * __restrict s,size_t n,wchar_t wc,_BIG5State * __restrict psenc __unused,size_t * __restrict nresult)357 _citrus_BIG5_wcrtomb_priv(_BIG5EncodingInfo * __restrict ei,
358 char * __restrict s,
359 size_t n, wchar_t wc, _BIG5State * __restrict psenc __unused,
360 size_t * __restrict nresult)
361 {
362 size_t l;
363 int ret;
364
365 /* check invalid sequence */
366 if (wc & ~0xffff ||
367 _citrus_BIG5_check_excludes(ei, (wint_t)wc) != 0) {
368 ret = EILSEQ;
369 goto err;
370 }
371
372 if (wc & 0x8000) {
373 if (_citrus_BIG5_check(ei, (wc >> 8) & 0xff) != 2 ||
374 !_citrus_BIG5_check2(ei, wc & 0xff)) {
375 ret = EILSEQ;
376 goto err;
377 }
378 l = 2;
379 } else {
380 if (wc & ~0xff || !_citrus_BIG5_check(ei, wc & 0xff)) {
381 ret = EILSEQ;
382 goto err;
383 }
384 l = 1;
385 }
386
387 if (n < l) {
388 /* bound check failure */
389 ret = E2BIG;
390 goto err;
391 }
392
393 if (l == 2) {
394 s[0] = (wc >> 8) & 0xff;
395 s[1] = wc & 0xff;
396 } else
397 s[0] = wc & 0xff;
398
399 *nresult = l;
400
401 return (0);
402
403 err:
404 *nresult = (size_t)-1;
405 return (ret);
406 }
407
408 static __inline int
409 /*ARGSUSED*/
_citrus_BIG5_stdenc_wctocs(_BIG5EncodingInfo * __restrict ei __unused,_csid_t * __restrict csid,_index_t * __restrict idx,wchar_t wc)410 _citrus_BIG5_stdenc_wctocs(_BIG5EncodingInfo * __restrict ei __unused,
411 _csid_t * __restrict csid,
412 _index_t * __restrict idx, wchar_t wc)
413 {
414
415 *csid = (wc < 0x100) ? 0 : 1;
416 *idx = (_index_t)wc;
417
418 return (0);
419 }
420
421 static __inline int
422 /*ARGSUSED*/
_citrus_BIG5_stdenc_cstowc(_BIG5EncodingInfo * __restrict ei __unused,wchar_t * __restrict wc,_csid_t csid,_index_t idx)423 _citrus_BIG5_stdenc_cstowc(_BIG5EncodingInfo * __restrict ei __unused,
424 wchar_t * __restrict wc,
425 _csid_t csid, _index_t idx)
426 {
427
428 switch (csid) {
429 case 0:
430 case 1:
431 *wc = (wchar_t)idx;
432 break;
433 default:
434 return (EILSEQ);
435 }
436
437 return (0);
438 }
439
440 static __inline int
441 /*ARGSUSED*/
_citrus_BIG5_stdenc_get_state_desc_generic(_BIG5EncodingInfo * __restrict ei __unused,_BIG5State * __restrict psenc,int * __restrict rstate)442 _citrus_BIG5_stdenc_get_state_desc_generic(_BIG5EncodingInfo * __restrict ei __unused,
443 _BIG5State * __restrict psenc,
444 int * __restrict rstate)
445 {
446
447 *rstate = (psenc->chlen == 0) ? _STDENC_SDGEN_INITIAL :
448 _STDENC_SDGEN_INCOMPLETE_CHAR;
449 return (0);
450 }
451
452 /* ----------------------------------------------------------------------
453 * public interface for stdenc
454 */
455
456 _CITRUS_STDENC_DECLS(BIG5);
457 _CITRUS_STDENC_DEF_OPS(BIG5);
458
459 #include "citrus_stdenc_template.h"
460