/src/dcmtk/oficonv/libsrc/citrus_big5.c
Line | Count | Source |
1 | | /*- |
2 | | * Copyright (c)2002, 2006 Citrus Project, |
3 | | * All rights reserved. |
4 | | * |
5 | | * Redistribution and use in source and binary forms, with or without |
6 | | * modification, are permitted provided that the following conditions |
7 | | * are met: |
8 | | * 1. Redistributions of source code must retain the above copyright |
9 | | * notice, this list of conditions and the following disclaimer. |
10 | | * 2. Redistributions in binary form must reproduce the above copyright |
11 | | * notice, this list of conditions and the following disclaimer in the |
12 | | * documentation and/or other materials provided with the distribution. |
13 | | * |
14 | | * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND |
15 | | * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE |
16 | | * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE |
17 | | * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE |
18 | | * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL |
19 | | * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS |
20 | | * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) |
21 | | * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT |
22 | | * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY |
23 | | * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF |
24 | | * SUCH DAMAGE. |
25 | | */ |
26 | | |
27 | | /*- |
28 | | * Copyright (c) 1993 |
29 | | * The Regents of the University of California. All rights reserved. |
30 | | * |
31 | | * This code is derived from software contributed to Berkeley by |
32 | | * Paul Borman at Krystal Technologies. |
33 | | * |
34 | | * Redistribution and use in source and binary forms, with or without |
35 | | * modification, are permitted provided that the following conditions |
36 | | * are met: |
37 | | * 1. Redistributions of source code must retain the above copyright |
38 | | * notice, this list of conditions and the following disclaimer. |
39 | | * 2. Redistributions in binary form must reproduce the above copyright |
40 | | * notice, this list of conditions and the following disclaimer in the |
41 | | * documentation and/or other materials provided with the distribution. |
42 | | * 3. Neither the name of the University nor the names of its contributors |
43 | | * may be used to endorse or promote products derived from this software |
44 | | * without specific prior written permission. |
45 | | * |
46 | | * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND |
47 | | * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE |
48 | | * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE |
49 | | * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE |
50 | | * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL |
51 | | * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS |
52 | | * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) |
53 | | * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT |
54 | | * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY |
55 | | * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF |
56 | | * SUCH DAMAGE. |
57 | | */ |
58 | | |
59 | | #include "dcmtk/config/osconfig.h" |
60 | | #include "citrus_big5.h" |
61 | | |
62 | | #ifdef HAVE_SYS_QUEUE_H |
63 | | #include <sys/queue.h> |
64 | | #else |
65 | | #include "dcmtk/oficonv/queue.h" |
66 | | #endif |
67 | | |
68 | | #include <sys/types.h> |
69 | | #include <errno.h> |
70 | | #include <limits.h> |
71 | | #include <stddef.h> |
72 | | #include <stdint.h> |
73 | | #include <stdio.h> |
74 | | #include <stdlib.h> |
75 | | #include <string.h> |
76 | | #include <wchar.h> |
77 | | |
78 | | #include "citrus_bcs.h" |
79 | | #include "citrus_prop.h" |
80 | | #include "citrus_types.h" |
81 | | #include "citrus_module.h" |
82 | | #include "citrus_stdenc.h" |
83 | | |
84 | | /* ---------------------------------------------------------------------- |
85 | | * private stuffs used by templates |
86 | | */ |
87 | | |
88 | | typedef struct { |
89 | | int chlen; |
90 | | char ch[2]; |
91 | | } _BIG5State; |
92 | | |
93 | | typedef struct _BIG5Exclude { |
94 | | TAILQ_ENTRY(_BIG5Exclude) entry; |
95 | | wint_t end; |
96 | | wint_t start; |
97 | | } _BIG5Exclude; |
98 | | |
99 | | typedef TAILQ_HEAD(_BIG5ExcludeList, _BIG5Exclude) _BIG5ExcludeList; |
100 | | |
101 | | typedef struct { |
102 | | _BIG5ExcludeList excludes; |
103 | | int cell[0x100]; |
104 | | } _BIG5EncodingInfo; |
105 | | |
106 | | #define _CEI_TO_EI(_cei_) (&(_cei_)->ei) |
107 | | #define _CEI_TO_STATE(_cei_, _func_) (_cei_)->states.s_##_func_ |
108 | | |
109 | 0 | #define _FUNCNAME(m) _citrus_BIG5_##m |
110 | 0 | #define _ENCODING_INFO _BIG5EncodingInfo |
111 | | #define _ENCODING_STATE _BIG5State |
112 | 0 | #define _ENCODING_MB_CUR_MAX(_ei_) 2 |
113 | | #define _ENCODING_IS_STATE_DEPENDENT 0 |
114 | | #define _STATE_NEEDS_EXPLICIT_INIT(_ps_) 0 |
115 | | |
116 | | |
117 | | static __inline void |
118 | | /*ARGSUSED*/ |
119 | | _citrus_BIG5_init_state(_BIG5EncodingInfo * ei , |
120 | | _BIG5State * s) |
121 | 0 | { |
122 | 0 | (void) ei; |
123 | 0 | memset(s, 0, sizeof(*s)); |
124 | 0 | } |
125 | | |
126 | | #if 0 |
127 | | static __inline void |
128 | | /*ARGSUSED*/ |
129 | | _citrus_BIG5_pack_state(_BIG5EncodingInfo * ei , |
130 | | void * pspriv, |
131 | | const _BIG5State * s) |
132 | | { |
133 | | (void) ei; |
134 | | memcpy(pspriv, (const void *)s, sizeof(*s)); |
135 | | } |
136 | | |
137 | | static __inline void |
138 | | /*ARGSUSED*/ |
139 | | _citrus_BIG5_unpack_state(_BIG5EncodingInfo * ei , |
140 | | _BIG5State * s, |
141 | | const void * pspriv) |
142 | | { |
143 | | (void) ei; |
144 | | memcpy((void *)s, pspriv, sizeof(*s)); |
145 | | } |
146 | | #endif |
147 | | |
148 | | static __inline int |
149 | | _citrus_BIG5_check(_BIG5EncodingInfo *ei, unsigned int c) |
150 | 0 | { |
151 | |
|
152 | 0 | return ((ei->cell[c & 0xFF] & 0x1) ? 2 : 1); |
153 | 0 | } |
154 | | |
155 | | static __inline int |
156 | | _citrus_BIG5_check2(_BIG5EncodingInfo *ei, unsigned int c) |
157 | 0 | { |
158 | |
|
159 | 0 | return ((ei->cell[c & 0xFF] & 0x2) ? 1 : 0); |
160 | 0 | } |
161 | | |
162 | | static __inline int |
163 | | _citrus_BIG5_check_excludes(_BIG5EncodingInfo *ei, wint_t c) |
164 | 0 | { |
165 | 0 | _BIG5Exclude *exclude; |
166 | |
|
167 | 0 | TAILQ_FOREACH(exclude, &ei->excludes, entry) { |
168 | 0 | if (c >= exclude->start && c <= exclude->end) |
169 | 0 | return (EILSEQ); |
170 | 0 | } |
171 | 0 | return (0); |
172 | 0 | } |
173 | | |
174 | | static int |
175 | | _citrus_BIG5_fill_rowcol(void * ctx, const char * s, |
176 | | uint64_t start, uint64_t end) |
177 | 0 | { |
178 | 0 | _BIG5EncodingInfo *ei; |
179 | 0 | uint64_t n; |
180 | 0 | int i; |
181 | |
|
182 | 0 | if (start > 0xFF || end > 0xFF) |
183 | 0 | return (EINVAL); |
184 | 0 | ei = (_BIG5EncodingInfo *)ctx; |
185 | 0 | i = strcmp("row", s) ? 1 : 0; |
186 | 0 | i = 1 << i; |
187 | 0 | for (n = start; n <= end; ++n) |
188 | 0 | ei->cell[n & 0xFF] |= i; |
189 | 0 | return (0); |
190 | 0 | } |
191 | | |
192 | | static int |
193 | | /*ARGSUSED*/ |
194 | | _citrus_BIG5_fill_excludes(void * ctx, |
195 | | const char * s , uint64_t start, uint64_t end) |
196 | 0 | { |
197 | 0 | _BIG5EncodingInfo *ei; |
198 | 0 | _BIG5Exclude *exclude; |
199 | |
|
200 | 0 | (void) s; |
201 | 0 | if (start > 0xFFFF || end > 0xFFFF) |
202 | 0 | return (EINVAL); |
203 | 0 | ei = (_BIG5EncodingInfo *)ctx; |
204 | 0 | exclude = TAILQ_LAST(&ei->excludes, _BIG5ExcludeList); |
205 | 0 | if (exclude != NULL && (wint_t)start <= exclude->end) |
206 | 0 | return (EINVAL); |
207 | 0 | exclude = (void *)malloc(sizeof(*exclude)); |
208 | 0 | if (exclude == NULL) |
209 | 0 | return (ENOMEM); |
210 | 0 | exclude->start = (wint_t)start; |
211 | 0 | exclude->end = (wint_t)end; |
212 | 0 | TAILQ_INSERT_TAIL(&ei->excludes, exclude, entry); |
213 | |
|
214 | 0 | return (0); |
215 | 0 | } |
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*/ |
226 | | _citrus_BIG5_encoding_module_uninit(_BIG5EncodingInfo *ei) |
227 | 0 | { |
228 | 0 | _BIG5Exclude *exclude; |
229 | |
|
230 | 0 | while ((exclude = TAILQ_FIRST(&ei->excludes)) != NULL) { |
231 | 0 | TAILQ_REMOVE(&ei->excludes, exclude, entry); |
232 | 0 | free(exclude); |
233 | 0 | } |
234 | 0 | } |
235 | | |
236 | | static int |
237 | | /*ARGSUSED*/ |
238 | | _citrus_BIG5_encoding_module_init(_BIG5EncodingInfo * ei, |
239 | | const void * var, size_t lenvar) |
240 | 0 | { |
241 | 0 | const char *s; |
242 | 0 | int err; |
243 | |
|
244 | 0 | memset((void *)ei, 0, sizeof(*ei)); |
245 | 0 | TAILQ_INIT(&ei->excludes); |
246 | |
|
247 | 0 | if (lenvar > 0 && var != NULL) { |
248 | 0 | s = _citrus_bcs_skip_ws_len((const char *)var, &lenvar); |
249 | 0 | if (lenvar > 0 && *s != '\0') { |
250 | 0 | err = _citrus_prop_parse_variable( |
251 | 0 | root_hints, (void *)ei, s, lenvar); |
252 | 0 | if (err == 0) |
253 | 0 | return (0); |
254 | | |
255 | 0 | _citrus_BIG5_encoding_module_uninit(ei); |
256 | 0 | memset((void *)ei, 0, sizeof(*ei)); |
257 | 0 | TAILQ_INIT(&ei->excludes); |
258 | 0 | } |
259 | 0 | } |
260 | | |
261 | | /* fallback Big5-1984, for backward compatibility. */ |
262 | 0 | _citrus_BIG5_fill_rowcol(ei, "row", 0xA1, 0xFE); |
263 | 0 | _citrus_BIG5_fill_rowcol(ei, "col", 0x40, 0x7E); |
264 | 0 | _citrus_BIG5_fill_rowcol(ei, "col", 0xA1, 0xFE); |
265 | |
|
266 | 0 | return (0); |
267 | 0 | } |
268 | | |
269 | | static int |
270 | | /*ARGSUSED*/ |
271 | | _citrus_BIG5_mbrtowc_priv(_BIG5EncodingInfo * ei, |
272 | | _citrus_wc_t * pwc, |
273 | | char ** s, size_t n, |
274 | | _BIG5State * psenc, |
275 | | size_t * nresult) |
276 | 0 | { |
277 | 0 | _citrus_wc_t wchar; |
278 | 0 | char *s0; |
279 | 0 | int c, chlenbak; |
280 | |
|
281 | 0 | s0 = *s; |
282 | |
|
283 | 0 | if (s0 == NULL) { |
284 | 0 | _citrus_BIG5_init_state(ei, psenc); |
285 | 0 | *nresult = 0; |
286 | 0 | return (0); |
287 | 0 | } |
288 | | |
289 | 0 | chlenbak = psenc->chlen; |
290 | | |
291 | | /* make sure we have the first byte in the buffer */ |
292 | 0 | switch (psenc->chlen) { |
293 | 0 | case 0: |
294 | 0 | if (n < 1) |
295 | 0 | goto restart; |
296 | 0 | psenc->ch[0] = *s0++; |
297 | 0 | psenc->chlen = 1; |
298 | 0 | n--; |
299 | 0 | break; |
300 | 0 | case 1: |
301 | 0 | break; |
302 | 0 | default: |
303 | | /* illegal state */ |
304 | 0 | goto ilseq; |
305 | 0 | } |
306 | | |
307 | 0 | c = _citrus_BIG5_check(ei, psenc->ch[0] & 0xff); |
308 | 0 | if (c == 0) |
309 | 0 | goto ilseq; |
310 | 0 | while (psenc->chlen < c) { |
311 | 0 | if (n < 1) { |
312 | 0 | goto restart; |
313 | 0 | } |
314 | 0 | psenc->ch[psenc->chlen] = *s0++; |
315 | 0 | psenc->chlen++; |
316 | 0 | n--; |
317 | 0 | } |
318 | | |
319 | 0 | switch (c) { |
320 | 0 | case 1: |
321 | 0 | wchar = psenc->ch[0] & 0xff; |
322 | 0 | break; |
323 | 0 | case 2: |
324 | 0 | if (!_citrus_BIG5_check2(ei, psenc->ch[1] & 0xff)) |
325 | 0 | goto ilseq; |
326 | 0 | wchar = ((psenc->ch[0] & 0xff) << 8) | (psenc->ch[1] & 0xff); |
327 | 0 | break; |
328 | 0 | default: |
329 | | /* illegal state */ |
330 | 0 | goto ilseq; |
331 | 0 | } |
332 | | |
333 | 0 | if (_citrus_BIG5_check_excludes(ei, (wint_t)wchar) != 0) |
334 | 0 | goto ilseq; |
335 | | |
336 | 0 | *s = s0; |
337 | 0 | psenc->chlen = 0; |
338 | 0 | if (pwc) |
339 | 0 | *pwc = wchar; |
340 | 0 | *nresult = wchar ? c - chlenbak : 0; |
341 | |
|
342 | 0 | return (0); |
343 | | |
344 | 0 | ilseq: |
345 | 0 | psenc->chlen = 0; |
346 | 0 | *nresult = (size_t)-1; |
347 | 0 | return (EILSEQ); |
348 | | |
349 | 0 | restart: |
350 | 0 | *s = s0; |
351 | 0 | *nresult = (size_t)-2; |
352 | 0 | return (0); |
353 | 0 | } |
354 | | |
355 | | static int |
356 | | /*ARGSUSED*/ |
357 | | _citrus_BIG5_wcrtomb_priv(_BIG5EncodingInfo * ei, |
358 | | char * s, |
359 | | size_t n, _citrus_wc_t wc, _BIG5State * psenc , |
360 | | size_t * nresult) |
361 | 0 | { |
362 | 0 | size_t l; |
363 | 0 | int ret; |
364 | 0 | (void) psenc; |
365 | | |
366 | | /* check invalid sequence */ |
367 | 0 | if (wc & ~0xffff || |
368 | 0 | _citrus_BIG5_check_excludes(ei, (wint_t)wc) != 0) { |
369 | 0 | ret = EILSEQ; |
370 | 0 | goto err; |
371 | 0 | } |
372 | | |
373 | 0 | if (wc & 0x8000) { |
374 | 0 | if (_citrus_BIG5_check(ei, (wc >> 8) & 0xff) != 2 || |
375 | 0 | !_citrus_BIG5_check2(ei, wc & 0xff)) { |
376 | 0 | ret = EILSEQ; |
377 | 0 | goto err; |
378 | 0 | } |
379 | 0 | l = 2; |
380 | 0 | } else { |
381 | 0 | if (wc & ~0xff || !_citrus_BIG5_check(ei, wc & 0xff)) { |
382 | 0 | ret = EILSEQ; |
383 | 0 | goto err; |
384 | 0 | } |
385 | 0 | l = 1; |
386 | 0 | } |
387 | | |
388 | 0 | if (n < l) { |
389 | | /* bound check failure */ |
390 | 0 | ret = E2BIG; |
391 | 0 | goto err; |
392 | 0 | } |
393 | | |
394 | 0 | if (l == 2) { |
395 | 0 | s[0] = (wc >> 8) & 0xff; |
396 | 0 | s[1] = wc & 0xff; |
397 | 0 | } else |
398 | 0 | s[0] = wc & 0xff; |
399 | |
|
400 | 0 | *nresult = l; |
401 | |
|
402 | 0 | return (0); |
403 | | |
404 | 0 | err: |
405 | 0 | *nresult = (size_t)-1; |
406 | 0 | return (ret); |
407 | 0 | } |
408 | | |
409 | | static __inline int |
410 | | /*ARGSUSED*/ |
411 | | _citrus_BIG5_stdenc_wctocs(_BIG5EncodingInfo * ei , |
412 | | _citrus_csid_t * csid, |
413 | | _citrus_index_t * idx, _citrus_wc_t wc) |
414 | 0 | { |
415 | 0 | (void) ei; |
416 | 0 | *csid = (wc < 0x100) ? 0 : 1; |
417 | 0 | *idx = (_citrus_index_t)wc; |
418 | |
|
419 | 0 | return (0); |
420 | 0 | } |
421 | | |
422 | | static __inline int |
423 | | /*ARGSUSED*/ |
424 | | _citrus_BIG5_stdenc_cstowc(_BIG5EncodingInfo * ei , |
425 | | _citrus_wc_t * wc, |
426 | | _citrus_csid_t csid, _citrus_index_t idx) |
427 | 0 | { |
428 | 0 | (void) ei; |
429 | 0 | switch (csid) { |
430 | 0 | case 0: |
431 | 0 | case 1: |
432 | 0 | *wc = (_citrus_wc_t)idx; |
433 | 0 | break; |
434 | 0 | default: |
435 | 0 | return (EILSEQ); |
436 | 0 | } |
437 | | |
438 | 0 | return (0); |
439 | 0 | } |
440 | | |
441 | | static __inline int |
442 | | /*ARGSUSED*/ |
443 | | _citrus_BIG5_stdenc_get_state_desc_generic(_BIG5EncodingInfo * ei , |
444 | | _BIG5State * psenc, |
445 | | int * rstate) |
446 | 0 | { |
447 | 0 | (void) ei; |
448 | 0 | *rstate = (psenc->chlen == 0) ? _CITRUS_STDENC_SDGEN_INITIAL : |
449 | 0 | _CITRUS_STDENC_SDGEN_INCOMPLETE_CHAR; |
450 | 0 | return (0); |
451 | 0 | } |
452 | | |
453 | | /* ---------------------------------------------------------------------- |
454 | | * public interface for stdenc |
455 | | */ |
456 | | |
457 | | _CITRUS_STDENC_DECLS(BIG5); |
458 | | _CITRUS_STDENC_DEF_OPS(BIG5); |
459 | | |
460 | | #include "citrus_stdenc_template.h" |