2 /* $NetBSD: citrus_mskanji.c,v 1.13 2008/06/14 16:01:08 tnozaki Exp $ */
5 * SPDX-License-Identifier: BSD-2-Clause
7 * Copyright (c)2002 Citrus Project,
10 * Redistribution and use in source and binary forms, with or without
11 * modification, are permitted provided that the following conditions
13 * 1. Redistributions of source code must retain the above copyright
14 * notice, this list of conditions and the following disclaimer.
15 * 2. Redistributions in binary form must reproduce the above copyright
16 * notice, this list of conditions and the following disclaimer in the
17 * documentation and/or other materials provided with the distribution.
19 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
20 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
21 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
22 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
23 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
24 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
25 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
26 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
27 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
28 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
33 * ja_JP.SJIS locale table for BSD4.4/rune
35 * (C) Sin'ichiro MIYATANI / Phase One, Inc
38 * Redistribution and use in source and binary forms, with or without
39 * modification, are permitted provided that the following conditions
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. All advertising materials mentioning features or use of this software
47 * must display the following acknowledgement:
48 * This product includes software developed by Phase One, Inc.
49 * 4. The name of Phase One, Inc. may be used to endorse or promote products
50 * derived from this software without specific prior written permission.
52 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
53 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
54 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
55 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
56 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
57 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
58 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
59 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
60 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
61 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
66 #include <sys/cdefs.h>
67 #include <sys/types.h>
79 #include "citrus_namespace.h"
80 #include "citrus_types.h"
81 #include "citrus_bcs.h"
82 #include "citrus_module.h"
83 #include "citrus_stdenc.h"
84 #include "citrus_mskanji.h"
87 /* ----------------------------------------------------------------------
88 * private stuffs used by templates
91 typedef struct _MSKanjiState {
98 #define MODE_JIS2004 1
99 } _MSKanjiEncodingInfo;
101 #define _CEI_TO_EI(_cei_) (&(_cei_)->ei)
102 #define _CEI_TO_STATE(_cei_, _func_) (_cei_)->states.s_##_func_
104 #define _FUNCNAME(m) _citrus_MSKanji_##m
105 #define _ENCODING_INFO _MSKanjiEncodingInfo
106 #define _ENCODING_STATE _MSKanjiState
107 #define _ENCODING_MB_CUR_MAX(_ei_) 2
108 #define _ENCODING_IS_STATE_DEPENDENT 0
109 #define _STATE_NEEDS_EXPLICIT_INIT(_ps_) 0
116 return ((c >= 0x81 && c <= 0x9f) || (c >= 0xe0 && c <= 0xfc));
123 return ((c >= 0x40 && c <= 0x7e) || (c >= 0x80 && c <= 0xfc));
128 _citrus_MSKanji_init_state(_MSKanjiEncodingInfo * __restrict ei __unused,
129 _MSKanjiState * __restrict s)
138 _citrus_MSKanji_pack_state(_MSKanjiEncodingInfo * __restrict ei __unused,
139 void * __restrict pspriv, const _MSKanjiState * __restrict s)
142 memcpy(pspriv, (const void *)s, sizeof(*s));
147 _citrus_MSKanji_unpack_state(_MSKanjiEncodingInfo * __restrict ei __unused,
148 _MSKanjiState * __restrict s, const void * __restrict pspriv)
151 memcpy((void *)s, pspriv, sizeof(*s));
157 _citrus_MSKanji_mbrtowc_priv(_MSKanjiEncodingInfo * __restrict ei,
158 wchar_t * __restrict pwc, char ** __restrict s, size_t n,
159 _MSKanjiState * __restrict psenc, size_t * __restrict nresult)
168 _citrus_MSKanji_init_state(ei, psenc);
169 *nresult = 0; /* state independent */
173 chlenbak = psenc->chlen;
175 /* make sure we have the first byte in the buffer */
176 switch (psenc->chlen) {
180 psenc->ch[0] = *s0++;
191 len = _mskanji1(psenc->ch[0] & 0xff) ? 2 : 1;
192 while (psenc->chlen < len) {
195 psenc->ch[psenc->chlen] = *s0++;
204 wchar = psenc->ch[0] & 0xff;
207 if (!_mskanji2(psenc->ch[1] & 0xff))
209 wchar = ((psenc->ch[0] & 0xff) << 8) | (psenc->ch[1] & 0xff);
220 *nresult = wchar ? len - chlenbak : 0;
225 *nresult = (size_t)-1;
229 *nresult = (size_t)-2;
236 _citrus_MSKanji_wcrtomb_priv(_MSKanjiEncodingInfo * __restrict ei __unused,
237 char * __restrict s, size_t n, wchar_t wc,
238 _MSKanjiState * __restrict psenc __unused, size_t * __restrict nresult)
242 /* check invalid sequence */
254 s[0] = (wc >> 8) & 0xff;
256 if (!_mskanji1(s[0] & 0xff) || !_mskanji2(s[1] & 0xff)) {
270 if (_mskanji1(s[0] & 0xff)) {
280 *nresult = (size_t)-1;
287 _citrus_MSKanji_stdenc_wctocs(_MSKanjiEncodingInfo * __restrict ei,
288 _csid_t * __restrict csid, _index_t * __restrict idx, wchar_t wc)
293 if ((_wc_t)wc < 0x80) {
297 } else if ((_wc_t)wc < 0x100) {
300 *idx = (_index_t)wc & 0x7F;
302 /* Kanji (containing Gaiji zone) */
304 * 94^2 zone (contains a part of Gaiji (0xED40 - 0xEEFC)):
305 * 0x8140 - 0x817E -> 0x2121 - 0x215F
306 * 0x8180 - 0x819E -> 0x2160 - 0x217E
307 * 0x819F - 0x81FC -> 0x2221 - 0x227E
309 * 0x8240 - 0x827E -> 0x2321 - 0x235F
311 * 0x9F9F - 0x9FFc -> 0x5E21 - 0x5E7E
313 * 0xE040 - 0xE07E -> 0x5F21 - 0x5F5F
315 * 0xEF9F - 0xEFFC -> 0x7E21 - 0x7E7E
317 * extended Gaiji zone:
321 * 0xF040 - 0xF09E -> 0x2121 - 0x217E
322 * 0xF140 - 0xF19E -> 0x2321 - 0x237E
324 * 0xF240 - 0xF29E -> 0x2521 - 0x257E
326 * 0xF09F - 0xF0FC -> 0x2821 - 0x287E
327 * 0xF29F - 0xF2FC -> 0x2C21 - 0x2C7E
329 * 0xF44F - 0xF49E -> 0x2F21 - 0x2F7E
331 * 0xF49F - 0xF4FC -> 0x6E21 - 0x6E7E
333 * 0xFC9F - 0xFCFC -> 0x7E21 - 0x7E7E
335 row = ((_wc_t)wc >> 8) & 0xFF;
336 col = (_wc_t)wc & 0xFF;
337 if (!_mskanji1(row) || !_mskanji2(col))
339 if ((ei->mode & MODE_JIS2004) == 0 || row < 0xF0) {
344 if ((_wc_t)wc <= 0xF49E) {
345 offset = (_wc_t)wc >= 0xF29F ||
346 ((_wc_t)wc >= 0xF09F &&
347 (_wc_t)wc <= 0xF0FC) ? 0xED : 0xF0;
354 row = row * 2 + 0x21;
362 *idx = ((_index_t)row << 8) | col;
370 _citrus_MSKanji_stdenc_cstowc(_MSKanjiEncodingInfo * __restrict ei,
371 wchar_t * __restrict wc, _csid_t csid, _index_t idx)
387 *wc = (wchar_t)idx + 0x80;
390 if ((ei->mode & MODE_JIS2004) == 0)
400 offset = (row == 0x22 || row >= 0x26) ?
402 else if (row >= 0x4D && row <= 0x7E)
409 offset = (row < 0x5F) ? 0x81 : 0xC1;
412 if (col < 0x21 || col > 0x7E)
414 row -= 0x21; col -= 0x21;
415 if ((row & 1) == 0) {
421 row = row / 2 + offset;
422 *wc = ((wchar_t)row << 8) | col;
433 _citrus_MSKanji_stdenc_get_state_desc_generic(_MSKanjiEncodingInfo * __restrict ei __unused,
434 _MSKanjiState * __restrict psenc, int * __restrict rstate)
437 *rstate = (psenc->chlen == 0) ? _STDENC_SDGEN_INITIAL :
438 _STDENC_SDGEN_INCOMPLETE_CHAR;
444 _citrus_MSKanji_encoding_module_init(_MSKanjiEncodingInfo * __restrict ei,
445 const void * __restrict var, size_t lenvar)
450 memset((void *)ei, 0, sizeof(*ei));
452 switch (_bcs_toupper(*p)) {
454 MATCH(JIS2004, ei->mode |= MODE_JIS2004);
465 _citrus_MSKanji_encoding_module_uninit(_MSKanjiEncodingInfo *ei __unused)
470 /* ----------------------------------------------------------------------
471 * public interface for stdenc
474 _CITRUS_STDENC_DECLS(MSKanji);
475 _CITRUS_STDENC_DEF_OPS(MSKanji);
477 #include "citrus_stdenc_template.h"