1 /* $NetBSD: citrus_mskanji.c,v 1.13 2008/06/14 16:01:08 tnozaki Exp $ */
2
3 /*-
4 * SPDX-License-Identifier: BSD-2-Clause
5 *
6 * Copyright (c)2002 Citrus Project,
7 * All rights reserved.
8 *
9 * Redistribution and use in source and binary forms, with or without
10 * modification, are permitted provided that the following conditions
11 * are met:
12 * 1. Redistributions of source code must retain the above copyright
13 * notice, this list of conditions and the following disclaimer.
14 * 2. Redistributions in binary form must reproduce the above copyright
15 * notice, this list of conditions and the following disclaimer in the
16 * documentation and/or other materials provided with the distribution.
17 *
18 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
19 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
20 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
21 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
22 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
23 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
24 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
25 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
26 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
27 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
28 * SUCH DAMAGE.
29 */
30
31 /*
32 * ja_JP.SJIS locale table for BSD4.4/rune
33 * version 1.0
34 * (C) Sin'ichiro MIYATANI / Phase One, Inc
35 * May 12, 1995
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. All advertising materials mentioning features or use of this software
46 * must display the following acknowledgement:
47 * This product includes software developed by Phase One, Inc.
48 * 4. The name of Phase One, Inc. may be used to endorse or promote products
49 * derived from this software without specific prior written permission.
50 *
51 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
52 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
53 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
54 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
55 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
56 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
57 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
58 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
59 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
60 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
61 * SUCH DAMAGE.
62 */
63
64
65 #include <sys/cdefs.h>
66 #include <sys/types.h>
67
68 #include <assert.h>
69 #include <errno.h>
70 #include <limits.h>
71 #include <stdbool.h>
72 #include <stddef.h>
73 #include <stdio.h>
74 #include <stdlib.h>
75 #include <string.h>
76 #include <wchar.h>
77
78 #include "citrus_namespace.h"
79 #include "citrus_types.h"
80 #include "citrus_bcs.h"
81 #include "citrus_module.h"
82 #include "citrus_stdenc.h"
83 #include "citrus_mskanji.h"
84
85
86 /* ----------------------------------------------------------------------
87 * private stuffs used by templates
88 */
89
90 typedef struct _MSKanjiState {
91 int chlen;
92 char ch[2];
93 } _MSKanjiState;
94
95 typedef struct {
96 int mode;
97 #define MODE_JIS2004 1
98 } _MSKanjiEncodingInfo;
99
100 #define _CEI_TO_EI(_cei_) (&(_cei_)->ei)
101 #define _CEI_TO_STATE(_cei_, _func_) (_cei_)->states.s_##_func_
102
103 #define _FUNCNAME(m) _citrus_MSKanji_##m
104 #define _ENCODING_INFO _MSKanjiEncodingInfo
105 #define _ENCODING_STATE _MSKanjiState
106 #define _ENCODING_MB_CUR_MAX(_ei_) 2
107 #define _ENCODING_IS_STATE_DEPENDENT 0
108 #define _STATE_NEEDS_EXPLICIT_INIT(_ps_) 0
109
110
111 static bool
_mskanji1(int c)112 _mskanji1(int c)
113 {
114
115 return ((c >= 0x81 && c <= 0x9f) || (c >= 0xe0 && c <= 0xfc));
116 }
117
118 static bool
_mskanji2(int c)119 _mskanji2(int c)
120 {
121
122 return ((c >= 0x40 && c <= 0x7e) || (c >= 0x80 && c <= 0xfc));
123 }
124
125 static __inline void
126 /*ARGSUSED*/
_citrus_MSKanji_init_state(_MSKanjiEncodingInfo * __restrict ei __unused,_MSKanjiState * __restrict s)127 _citrus_MSKanji_init_state(_MSKanjiEncodingInfo * __restrict ei __unused,
128 _MSKanjiState * __restrict s)
129 {
130
131 s->chlen = 0;
132 }
133
134 #if 0
135 static __inline void
136 /*ARGSUSED*/
137 _citrus_MSKanji_pack_state(_MSKanjiEncodingInfo * __restrict ei __unused,
138 void * __restrict pspriv, const _MSKanjiState * __restrict s)
139 {
140
141 memcpy(pspriv, (const void *)s, sizeof(*s));
142 }
143
144 static __inline void
145 /*ARGSUSED*/
146 _citrus_MSKanji_unpack_state(_MSKanjiEncodingInfo * __restrict ei __unused,
147 _MSKanjiState * __restrict s, const void * __restrict pspriv)
148 {
149
150 memcpy((void *)s, pspriv, sizeof(*s));
151 }
152 #endif
153
154 static int
155 /*ARGSUSED*/
_citrus_MSKanji_mbrtowc_priv(_MSKanjiEncodingInfo * __restrict ei,wchar_t * __restrict pwc,char ** __restrict s,size_t n,_MSKanjiState * __restrict psenc,size_t * __restrict nresult)156 _citrus_MSKanji_mbrtowc_priv(_MSKanjiEncodingInfo * __restrict ei,
157 wchar_t * __restrict pwc, char ** __restrict s, size_t n,
158 _MSKanjiState * __restrict psenc, size_t * __restrict nresult)
159 {
160 char *s0;
161 wchar_t wchar;
162 int chlenbak, len;
163
164 s0 = *s;
165
166 if (s0 == NULL) {
167 _citrus_MSKanji_init_state(ei, psenc);
168 *nresult = 0; /* state independent */
169 return (0);
170 }
171
172 chlenbak = psenc->chlen;
173
174 /* make sure we have the first byte in the buffer */
175 switch (psenc->chlen) {
176 case 0:
177 if (n < 1)
178 goto restart;
179 psenc->ch[0] = *s0++;
180 psenc->chlen = 1;
181 n--;
182 break;
183 case 1:
184 break;
185 default:
186 /* illegal state */
187 goto encoding_error;
188 }
189
190 len = _mskanji1(psenc->ch[0] & 0xff) ? 2 : 1;
191 while (psenc->chlen < len) {
192 if (n < 1)
193 goto restart;
194 psenc->ch[psenc->chlen] = *s0++;
195 psenc->chlen++;
196 n--;
197 }
198
199 *s = s0;
200
201 switch (len) {
202 case 1:
203 wchar = psenc->ch[0] & 0xff;
204 break;
205 case 2:
206 if (!_mskanji2(psenc->ch[1] & 0xff))
207 goto encoding_error;
208 wchar = ((psenc->ch[0] & 0xff) << 8) | (psenc->ch[1] & 0xff);
209 break;
210 default:
211 /* illegal state */
212 goto encoding_error;
213 }
214
215 psenc->chlen = 0;
216
217 if (pwc)
218 *pwc = wchar;
219 *nresult = wchar ? len - chlenbak : 0;
220 return (0);
221
222 encoding_error:
223 psenc->chlen = 0;
224 *nresult = (size_t)-1;
225 return (EILSEQ);
226
227 restart:
228 *nresult = (size_t)-2;
229 *s = s0;
230 return (0);
231 }
232
233
234 static int
_citrus_MSKanji_wcrtomb_priv(_MSKanjiEncodingInfo * __restrict ei __unused,char * __restrict s,size_t n,wchar_t wc,_MSKanjiState * __restrict psenc __unused,size_t * __restrict nresult)235 _citrus_MSKanji_wcrtomb_priv(_MSKanjiEncodingInfo * __restrict ei __unused,
236 char * __restrict s, size_t n, wchar_t wc,
237 _MSKanjiState * __restrict psenc __unused, size_t * __restrict nresult)
238 {
239 int ret;
240
241 /* check invalid sequence */
242 if (wc & ~0xffff) {
243 ret = EILSEQ;
244 goto err;
245 }
246
247 if (wc & 0xff00) {
248 if (n < 2) {
249 ret = E2BIG;
250 goto err;
251 }
252
253 s[0] = (wc >> 8) & 0xff;
254 s[1] = wc & 0xff;
255 if (!_mskanji1(s[0] & 0xff) || !_mskanji2(s[1] & 0xff)) {
256 ret = EILSEQ;
257 goto err;
258 }
259
260 *nresult = 2;
261 return (0);
262 } else {
263 if (n < 1) {
264 ret = E2BIG;
265 goto err;
266 }
267
268 s[0] = wc & 0xff;
269 if (_mskanji1(s[0] & 0xff)) {
270 ret = EILSEQ;
271 goto err;
272 }
273
274 *nresult = 1;
275 return (0);
276 }
277
278 err:
279 *nresult = (size_t)-1;
280 return (ret);
281 }
282
283
284 static __inline int
285 /*ARGSUSED*/
_citrus_MSKanji_stdenc_wctocs(_MSKanjiEncodingInfo * __restrict ei,_csid_t * __restrict csid,_index_t * __restrict idx,wchar_t wc)286 _citrus_MSKanji_stdenc_wctocs(_MSKanjiEncodingInfo * __restrict ei,
287 _csid_t * __restrict csid, _index_t * __restrict idx, wchar_t wc)
288 {
289 _index_t col, row;
290 int offset;
291
292 if ((_wc_t)wc < 0x80) {
293 /* ISO-646 */
294 *csid = 0;
295 *idx = (_index_t)wc;
296 } else if ((_wc_t)wc < 0x100) {
297 /* KANA */
298 *csid = 1;
299 *idx = (_index_t)wc & 0x7F;
300 } else {
301 /* Kanji (containing Gaiji zone) */
302 /*
303 * 94^2 zone (contains a part of Gaiji (0xED40 - 0xEEFC)):
304 * 0x8140 - 0x817E -> 0x2121 - 0x215F
305 * 0x8180 - 0x819E -> 0x2160 - 0x217E
306 * 0x819F - 0x81FC -> 0x2221 - 0x227E
307 *
308 * 0x8240 - 0x827E -> 0x2321 - 0x235F
309 * ...
310 * 0x9F9F - 0x9FFc -> 0x5E21 - 0x5E7E
311 *
312 * 0xE040 - 0xE07E -> 0x5F21 - 0x5F5F
313 * ...
314 * 0xEF9F - 0xEFFC -> 0x7E21 - 0x7E7E
315 *
316 * extended Gaiji zone:
317 * 0xF040 - 0xFCFC
318 *
319 * JIS X0213-plane2:
320 * 0xF040 - 0xF09E -> 0x2121 - 0x217E
321 * 0xF140 - 0xF19E -> 0x2321 - 0x237E
322 * ...
323 * 0xF240 - 0xF29E -> 0x2521 - 0x257E
324 *
325 * 0xF09F - 0xF0FC -> 0x2821 - 0x287E
326 * 0xF29F - 0xF2FC -> 0x2C21 - 0x2C7E
327 * ...
328 * 0xF44F - 0xF49E -> 0x2F21 - 0x2F7E
329 *
330 * 0xF49F - 0xF4FC -> 0x6E21 - 0x6E7E
331 * ...
332 * 0xFC9F - 0xFCFC -> 0x7E21 - 0x7E7E
333 */
334 row = ((_wc_t)wc >> 8) & 0xFF;
335 col = (_wc_t)wc & 0xFF;
336 if (!_mskanji1(row) || !_mskanji2(col))
337 return (EILSEQ);
338 if ((ei->mode & MODE_JIS2004) == 0 || row < 0xF0) {
339 *csid = 2;
340 offset = 0x81;
341 } else {
342 *csid = 3;
343 if ((_wc_t)wc <= 0xF49E) {
344 offset = (_wc_t)wc >= 0xF29F ||
345 ((_wc_t)wc >= 0xF09F &&
346 (_wc_t)wc <= 0xF0FC) ? 0xED : 0xF0;
347 } else
348 offset = 0xCE;
349 }
350 row -= offset;
351 if (row >= 0x5F)
352 row -= 0x40;
353 row = row * 2 + 0x21;
354 col -= 0x1F;
355 if (col >= 0x61)
356 col -= 1;
357 if (col > 0x7E) {
358 row += 1;
359 col -= 0x5E;
360 }
361 *idx = ((_index_t)row << 8) | col;
362 }
363
364 return (0);
365 }
366
367 static __inline int
368 /*ARGSUSED*/
_citrus_MSKanji_stdenc_cstowc(_MSKanjiEncodingInfo * __restrict ei,wchar_t * __restrict wc,_csid_t csid,_index_t idx)369 _citrus_MSKanji_stdenc_cstowc(_MSKanjiEncodingInfo * __restrict ei,
370 wchar_t * __restrict wc, _csid_t csid, _index_t idx)
371 {
372 uint32_t col, row;
373 int offset;
374
375 switch (csid) {
376 case 0:
377 /* ISO-646 */
378 if (idx >= 0x80)
379 return (EILSEQ);
380 *wc = (wchar_t)idx;
381 break;
382 case 1:
383 /* kana */
384 if (idx >= 0x80)
385 return (EILSEQ);
386 *wc = (wchar_t)idx + 0x80;
387 break;
388 case 3:
389 if ((ei->mode & MODE_JIS2004) == 0)
390 return (EILSEQ);
391 /*FALLTHROUGH*/
392 case 2:
393 /* kanji */
394 row = (idx >> 8);
395 if (row < 0x21)
396 return (EILSEQ);
397 if (csid == 3) {
398 if (row <= 0x2F)
399 offset = (row == 0x22 || row >= 0x26) ?
400 0xED : 0xF0;
401 else if (row >= 0x4D && row <= 0x7E)
402 offset = 0xCE;
403 else
404 return (EILSEQ);
405 } else {
406 if (row > 0x97)
407 return (EILSEQ);
408 offset = (row < 0x5F) ? 0x81 : 0xC1;
409 }
410 col = idx & 0xFF;
411 if (col < 0x21 || col > 0x7E)
412 return (EILSEQ);
413 row -= 0x21; col -= 0x21;
414 if ((row & 1) == 0) {
415 col += 0x40;
416 if (col >= 0x7F)
417 col += 1;
418 } else
419 col += 0x9F;
420 row = row / 2 + offset;
421 *wc = ((wchar_t)row << 8) | col;
422 break;
423 default:
424 return (EILSEQ);
425 }
426
427 return (0);
428 }
429
430 static __inline int
431 /*ARGSUSED*/
_citrus_MSKanji_stdenc_get_state_desc_generic(_MSKanjiEncodingInfo * __restrict ei __unused,_MSKanjiState * __restrict psenc,int * __restrict rstate)432 _citrus_MSKanji_stdenc_get_state_desc_generic(_MSKanjiEncodingInfo * __restrict ei __unused,
433 _MSKanjiState * __restrict psenc, int * __restrict rstate)
434 {
435
436 *rstate = (psenc->chlen == 0) ? _STDENC_SDGEN_INITIAL :
437 _STDENC_SDGEN_INCOMPLETE_CHAR;
438 return (0);
439 }
440
441 static int
442 /*ARGSUSED*/
_citrus_MSKanji_encoding_module_init(_MSKanjiEncodingInfo * __restrict ei,const void * __restrict var,size_t lenvar)443 _citrus_MSKanji_encoding_module_init(_MSKanjiEncodingInfo * __restrict ei,
444 const void * __restrict var, size_t lenvar)
445 {
446 const char *p;
447
448 p = var;
449 memset((void *)ei, 0, sizeof(*ei));
450 while (lenvar > 0) {
451 switch (_bcs_toupper(*p)) {
452 case 'J':
453 MATCH(JIS2004, ei->mode |= MODE_JIS2004);
454 break;
455 }
456 ++p;
457 --lenvar;
458 }
459
460 return (0);
461 }
462
463 static void
_citrus_MSKanji_encoding_module_uninit(_MSKanjiEncodingInfo * ei __unused)464 _citrus_MSKanji_encoding_module_uninit(_MSKanjiEncodingInfo *ei __unused)
465 {
466
467 }
468
469 /* ----------------------------------------------------------------------
470 * public interface for stdenc
471 */
472
473 _CITRUS_STDENC_DECLS(MSKanji);
474 _CITRUS_STDENC_DEF_OPS(MSKanji);
475
476 #include "citrus_stdenc_template.h"
477