1 /* $NetBSD: citrus_mskanji.c,v 1.12 2007/03/05 16:57:06 tnozaki Exp $ */
2 /* $DragonFly: src/lib/libc/citrus/modules/citrus_mskanji.c,v 1.2 2008/04/10 10:21:02 hasso Exp $ */
5 * Copyright (c)2002 Citrus Project,
8 * Redistribution and use in source and binary forms, with or without
9 * modification, are permitted provided that the following conditions
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.
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
31 * ja_JP.SJIS locale table for BSD4.4/rune
33 * (C) Sin'ichiro MIYATANI / Phase One, Inc
36 * Redistribution and use in source and binary forms, with or without
37 * modification, are permitted provided that the following conditions
39 * 1. Redistributions of source code must retain the above copyright
40 * notice, this list of conditions and the following disclaimer.
41 * 2. Redistributions in binary form must reproduce the above copyright
42 * notice, this list of conditions and the following disclaimer in the
43 * documentation and/or other materials provided with the distribution.
44 * 3. All advertising materials mentioning features or use of this software
45 * must display the following acknowledgement:
46 * This product includes software developed by Phase One, Inc.
47 * 4. The name of Phase One, Inc. may be used to endorse or promote products
48 * derived from this software without specific prior written permission.
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
64 #include <sys/types.h>
75 #include "citrus_namespace.h"
76 #include "citrus_types.h"
77 #include "citrus_bcs.h"
78 #include "citrus_module.h"
79 #include "citrus_ctype.h"
80 #include "citrus_stdenc.h"
81 #include "citrus_mskanji.h"
84 /* ----------------------------------------------------------------------
85 * private stuffs used by templates
88 typedef struct _MSKanjiState {
95 #define MODE_JIS2004 1
96 } _MSKanjiEncodingInfo;
99 _MSKanjiEncodingInfo ei;
101 /* for future multi-locale facility */
102 _MSKanjiState s_mblen;
103 _MSKanjiState s_mbrlen;
104 _MSKanjiState s_mbrtowc;
105 _MSKanjiState s_mbtowc;
106 _MSKanjiState s_mbsrtowcs;
107 _MSKanjiState s_wcrtomb;
108 _MSKanjiState s_wcsrtombs;
109 _MSKanjiState s_wctomb;
113 #define _CEI_TO_EI(_cei_) (&(_cei_)->ei)
114 #define _CEI_TO_STATE(_cei_, _func_) (_cei_)->states.s_##_func_
116 #define _FUNCNAME(m) _citrus_MSKanji_##m
117 #define _ENCODING_INFO _MSKanjiEncodingInfo
118 #define _CTYPE_INFO _MSKanjiCTypeInfo
119 #define _ENCODING_STATE _MSKanjiState
120 #define _ENCODING_MB_CUR_MAX(_ei_) 2
121 #define _ENCODING_IS_STATE_DEPENDENT 0
122 #define _STATE_NEEDS_EXPLICIT_INIT(_ps_) 0
129 if ((c >= 0x81 && c <= 0x9f) || (c >= 0xe0 && c <= 0xfc))
139 if ((c >= 0x40 && c <= 0x7e) || (c >= 0x80 && c <= 0xfc))
147 _citrus_MSKanji_init_state(_MSKanjiEncodingInfo * __restrict ei,
148 _MSKanjiState * __restrict s)
155 _citrus_MSKanji_pack_state(_MSKanjiEncodingInfo * __restrict ei,
156 void * __restrict pspriv,
157 const _MSKanjiState * __restrict s)
159 memcpy(pspriv, (const void *)s, sizeof(*s));
164 _citrus_MSKanji_unpack_state(_MSKanjiEncodingInfo * __restrict ei,
165 _MSKanjiState * __restrict s,
166 const void * __restrict pspriv)
168 memcpy((void *)s, pspriv, sizeof(*s));
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)
184 _DIAGASSERT(nresult != 0);
185 _DIAGASSERT(ei != NULL);
186 _DIAGASSERT(s != NULL);
187 _DIAGASSERT(psenc != NULL);
192 _citrus_MSKanji_init_state(ei, psenc);
193 *nresult = 0; /* state independent */
197 chlenbak = psenc->chlen;
199 /* make sure we have the first byte in the buffer */
200 switch (psenc->chlen) {
204 psenc->ch[0] = *s0++;
215 len = _mskanji1(psenc->ch[0] & 0xff) ? 2 : 1;
216 while (psenc->chlen < len) {
219 psenc->ch[psenc->chlen] = *s0++;
228 wchar = psenc->ch[0] & 0xff;
231 if (!_mskanji2(psenc->ch[1] & 0xff))
233 wchar = ((psenc->ch[0] & 0xff) << 8) | (psenc->ch[1] & 0xff);
248 *nresult = len - chlenbak;
254 *nresult = (size_t)-1;
258 *nresult = (size_t)-2;
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)
272 _DIAGASSERT(ei != NULL);
273 _DIAGASSERT(psenc != NULL);
274 _DIAGASSERT(s != NULL);
276 /* check invalid sequence */
288 s[0] = (wc >> 8) & 0xff;
290 if (!_mskanji1(s[0] & 0xff) || !_mskanji2(s[1] & 0xff)) {
304 if (_mskanji1(s[0] & 0xff)) {
314 *nresult = (size_t)-1;
321 _citrus_MSKanji_stdenc_wctocs(_MSKanjiEncodingInfo * __restrict ei,
322 _csid_t * __restrict csid,
323 _index_t * __restrict idx, wchar_t wc)
328 _DIAGASSERT(csid != NULL && idx != NULL);
330 if ((_wc_t)wc < 0x80) {
334 } else if ((_wc_t)wc < 0x100) {
337 *idx = (_index_t)wc & 0x7F;
339 /* Kanji (containing Gaiji zone) */
341 * 94^2 zone (contains a part of Gaiji (0xED40 - 0xEEFC)):
342 * 0x8140 - 0x817E -> 0x2121 - 0x215F
343 * 0x8180 - 0x819E -> 0x2160 - 0x217E
344 * 0x819F - 0x81FC -> 0x2221 - 0x227E
346 * 0x8240 - 0x827E -> 0x2321 - 0x235F
348 * 0x9F9F - 0x9FFc -> 0x5E21 - 0x5E7E
350 * 0xE040 - 0xE07E -> 0x5F21 - 0x5F5F
352 * 0xEF9F - 0xEFFC -> 0x7E21 - 0x7E7E
354 * extended Gaiji zone:
358 * 0xF040 - 0xF09E -> 0x2121 - 0x217E
359 * 0xF140 - 0xF19E -> 0x2321 - 0x237E
361 * 0xF240 - 0xF29E -> 0x2521 - 0x257E
363 * 0xF09F - 0xF0FC -> 0x2821 - 0x287E
364 * 0xF29F - 0xF2FC -> 0x2C21 - 0x2C7E
366 * 0xF44F - 0xF49E -> 0x2F21 - 0x2F7E
368 * 0xF49F - 0xF4FC -> 0x6E21 - 0x6E7E
370 * 0xFC9F - 0xFCFC -> 0x7E21 - 0x7E7E
372 row = ((_wc_t)wc >> 8) & 0xFF;
373 col = (_wc_t)wc & 0xFF;
374 if (!_mskanji1(row) || !_mskanji2(col))
376 if ((ei->mode & MODE_JIS2004) == 0 || row < 0xF0) {
381 if ((_wc_t)wc <= 0xF49E) {
382 offset = (_wc_t)wc >= 0xF29F ||
383 ((_wc_t)wc >= 0xF09F && (_wc_t)wc <= 0xF0FC)
391 row = row * 2 + 0x21;
399 *idx = ((_index_t)row << 8) | col;
407 _citrus_MSKanji_stdenc_cstowc(_MSKanjiEncodingInfo * __restrict ei,
408 wchar_t * __restrict wc,
409 _csid_t csid, _index_t idx)
414 _DIAGASSERT(wc != NULL);
427 *wc = (wchar_t)idx + 0x80;
430 if ((ei->mode & MODE_JIS2004) == 0)
440 offset = (row == 0x22 || row >= 0x26)
442 else if (row >= 0x4D && row <= 0x7E)
449 offset = (row < 0x5F) ? 0x81 : 0xC1;
452 if (col < 0x21 || col > 0x7E)
454 row -= 0x21; col -= 0x21;
455 if ((row & 1) == 0) {
461 row = row / 2 + offset;
462 *wc = ((wchar_t)row << 8) | col;
473 _citrus_MSKanji_stdenc_get_state_desc_generic(_MSKanjiEncodingInfo * __restrict ei,
474 _MSKanjiState * __restrict psenc,
475 int * __restrict rstate)
478 if (psenc->chlen == 0)
479 *rstate = _STDENC_SDGEN_INITIAL;
481 *rstate = _STDENC_SDGEN_INCOMPLETE_CHAR;
488 _citrus_MSKanji_encoding_module_init(_MSKanjiEncodingInfo * __restrict ei,
489 const void * __restrict var,
494 _DIAGASSERT(ei != NULL);
497 #define MATCH(x, act) \
499 if (lenvar >= (sizeof(#x)-1) && \
500 _bcs_strncasecmp(p, #x, sizeof(#x)-1) == 0) { \
502 lenvar -= sizeof(#x)-1; \
505 } while (/*CONSTCOND*/0)
506 memset((void *)ei, 0, sizeof(*ei));
508 switch (_bcs_toupper(*p)) {
510 MATCH(JIS2004, ei->mode |= MODE_JIS2004);
522 _citrus_MSKanji_encoding_module_uninit(_MSKanjiEncodingInfo *ei)
526 /* ----------------------------------------------------------------------
527 * public interface for ctype
530 _CITRUS_CTYPE_DECLS(MSKanji);
531 _CITRUS_CTYPE_DEF_OPS(MSKanji);
533 #include "citrus_ctype_template.h"
535 /* ----------------------------------------------------------------------
536 * public interface for stdenc
539 _CITRUS_STDENC_DECLS(MSKanji);
540 _CITRUS_STDENC_DEF_OPS(MSKanji);
542 #include "citrus_stdenc_template.h"