1 /*
2 * "streamable kanji code filter and converter"
3 * Copyright (c) 1998-2002 HappySize, Inc. All rights reserved.
4 *
5 * LICENSE NOTICES
6 *
7 * This file is part of "streamable kanji code filter and converter",
8 * which is distributed under the terms of GNU Lesser General Public
9 * License (version 2) as published by the Free Software Foundation.
10 *
11 * This software is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 * GNU Lesser General Public License for more details.
15 *
16 * You should have received a copy of the GNU Lesser General Public
17 * License along with "streamable kanji code filter and converter";
18 * if not, write to the Free Software Foundation, Inc., 59 Temple Place,
19 * Suite 330, Boston, MA 02111-1307 USA
20 *
21 * The author of this file:
22 *
23 */
24 /*
25 * the source code included in this files was separated from mbfilter_ja.c
26 * by moriyoshi koizumi <moriyoshi@php.net> on 4 dec 2002.
27 *
28 */
29
30 #include "mbfilter.h"
31 #include "mbfilter_cp932.h"
32
33 #include "unicode_table_cp932_ext.h"
34 #include "unicode_table_jis.h"
35
36 static int mbfl_filt_conv_cp932_wchar_flush(mbfl_convert_filter *filter);
37
38 static const unsigned char mblen_table_sjis[] = { /* 0x80-0x9f,0xE0-0xFF */
39 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
40 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
41 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
42 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
43 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
44 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
45 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
46 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
47 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
48 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
49 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
50 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
51 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
52 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
53 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
54 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2
55 };
56
57 static const char *mbfl_encoding_cp932_aliases[] = {"MS932", "Windows-31J", "MS_Kanji", "SJIS-win", "SJIS-ms", "SJIS-open", NULL};
58
59 const mbfl_encoding mbfl_encoding_cp932 = {
60 mbfl_no_encoding_cp932,
61 "CP932",
62 "Shift_JIS",
63 mbfl_encoding_cp932_aliases,
64 mblen_table_sjis,
65 MBFL_ENCTYPE_GL_UNSAFE,
66 &vtbl_cp932_wchar,
67 &vtbl_wchar_cp932
68 };
69
70 const struct mbfl_convert_vtbl vtbl_cp932_wchar = {
71 mbfl_no_encoding_cp932,
72 mbfl_no_encoding_wchar,
73 mbfl_filt_conv_common_ctor,
74 NULL,
75 mbfl_filt_conv_cp932_wchar,
76 mbfl_filt_conv_cp932_wchar_flush,
77 NULL,
78 };
79
80 const struct mbfl_convert_vtbl vtbl_wchar_cp932 = {
81 mbfl_no_encoding_wchar,
82 mbfl_no_encoding_cp932,
83 mbfl_filt_conv_common_ctor,
84 NULL,
85 mbfl_filt_conv_wchar_cp932,
86 mbfl_filt_conv_common_flush,
87 NULL,
88 };
89
90 #define CK(statement) do { if ((statement) < 0) return (-1); } while (0)
91
92 #define SJIS_ENCODE(c1,c2,s1,s2) \
93 do { \
94 s1 = c1; \
95 s1--; \
96 s1 >>= 1; \
97 if ((c1) < 0x5f) { \
98 s1 += 0x71; \
99 } else { \
100 s1 += 0xb1; \
101 } \
102 s2 = c2; \
103 if ((c1) & 1) { \
104 if ((c2) < 0x60) { \
105 s2--; \
106 } \
107 s2 += 0x20; \
108 } else { \
109 s2 += 0x7e; \
110 } \
111 } while (0)
112
113 #define SJIS_DECODE(c1,c2,s1,s2) \
114 do { \
115 s1 = c1; \
116 if (s1 < 0xa0) { \
117 s1 -= 0x81; \
118 } else { \
119 s1 -= 0xc1; \
120 } \
121 s1 <<= 1; \
122 s1 += 0x21; \
123 s2 = c2; \
124 if (s2 < 0x9f) { \
125 if (s2 < 0x7f) { \
126 s2++; \
127 } \
128 s2 -= 0x20; \
129 } else { \
130 s1++; \
131 s2 -= 0x7e; \
132 } \
133 } while (0)
134
135
136 /*
137 * SJIS-win => wchar
138 */
139 int
mbfl_filt_conv_cp932_wchar(int c,mbfl_convert_filter * filter)140 mbfl_filt_conv_cp932_wchar(int c, mbfl_convert_filter *filter)
141 {
142 int c1, s, s1, s2, w;
143
144 switch (filter->status) {
145 case 0:
146 if (c >= 0 && c < 0x80) { /* latin */
147 CK((*filter->output_function)(c, filter->data));
148 } else if (c > 0xa0 && c < 0xe0) { /* kana */
149 CK((*filter->output_function)(0xfec0 + c, filter->data));
150 } else if (c > 0x80 && c < 0xfd && c != 0xa0) { /* kanji first char */
151 filter->status = 1;
152 filter->cache = c;
153 } else {
154 CK((*filter->output_function)(MBFL_BAD_INPUT, filter->data));
155 }
156 break;
157
158 case 1: /* kanji second char */
159 filter->status = 0;
160 c1 = filter->cache;
161 if (c >= 0x40 && c <= 0xfc && c != 0x7f) {
162 w = 0;
163 SJIS_DECODE(c1, c, s1, s2);
164 s = (s1 - 0x21)*94 + s2 - 0x21;
165 if (s <= 137) {
166 if (s == 31) {
167 w = 0xff3c; /* FULLWIDTH REVERSE SOLIDUS */
168 } else if (s == 32) {
169 w = 0xff5e; /* FULLWIDTH TILDE */
170 } else if (s == 33) {
171 w = 0x2225; /* PARALLEL TO */
172 } else if (s == 60) {
173 w = 0xff0d; /* FULLWIDTH HYPHEN-MINUS */
174 } else if (s == 80) {
175 w = 0xffe0; /* FULLWIDTH CENT SIGN */
176 } else if (s == 81) {
177 w = 0xffe1; /* FULLWIDTH POUND SIGN */
178 } else if (s == 137) {
179 w = 0xffe2; /* FULLWIDTH NOT SIGN */
180 }
181 }
182 if (w == 0) {
183 if (s >= cp932ext1_ucs_table_min && s < cp932ext1_ucs_table_max) { /* vendor ext1 (13ku) */
184 w = cp932ext1_ucs_table[s - cp932ext1_ucs_table_min];
185 } else if (s >= 0 && s < jisx0208_ucs_table_size) { /* X 0208 */
186 w = jisx0208_ucs_table[s];
187 } else if (s >= cp932ext2_ucs_table_min && s < cp932ext2_ucs_table_max) { /* vendor ext2 (89ku - 92ku) */
188 w = cp932ext2_ucs_table[s - cp932ext2_ucs_table_min];
189 } else if (s >= cp932ext3_ucs_table_min && s < cp932ext3_ucs_table_max) { /* vendor ext3 (115ku - 119ku) */
190 w = cp932ext3_ucs_table[s - cp932ext3_ucs_table_min];
191 } else if (s >= (94*94) && s < (114*94)) { /* user (95ku - 114ku) */
192 w = s - (94*94) + 0xe000;
193 }
194 }
195
196 if (w <= 0) {
197 w = MBFL_BAD_INPUT;
198 }
199
200 CK((*filter->output_function)(w, filter->data));
201 } else {
202 CK((*filter->output_function)(MBFL_BAD_INPUT, filter->data));
203 }
204 break;
205
206 default:
207 filter->status = 0;
208 break;
209 }
210
211 return 0;
212 }
213
mbfl_filt_conv_cp932_wchar_flush(mbfl_convert_filter * filter)214 static int mbfl_filt_conv_cp932_wchar_flush(mbfl_convert_filter *filter)
215 {
216 if (filter->status) {
217 (*filter->output_function)(MBFL_BAD_INPUT, filter->data);
218 }
219
220 if (filter->flush_function) {
221 (*filter->flush_function)(filter->data);
222 }
223
224 return 0;
225 }
226
227 /*
228 * wchar => SJIS-win
229 */
230 int
mbfl_filt_conv_wchar_cp932(int c,mbfl_convert_filter * filter)231 mbfl_filt_conv_wchar_cp932(int c, mbfl_convert_filter *filter)
232 {
233 int c1, c2, s1, s2;
234
235 s1 = 0;
236 s2 = 0;
237 if (c >= ucs_a1_jis_table_min && c < ucs_a1_jis_table_max) {
238 s1 = ucs_a1_jis_table[c - ucs_a1_jis_table_min];
239 } else if (c >= ucs_a2_jis_table_min && c < ucs_a2_jis_table_max) {
240 s1 = ucs_a2_jis_table[c - ucs_a2_jis_table_min];
241 } else if (c >= ucs_i_jis_table_min && c < ucs_i_jis_table_max) {
242 s1 = ucs_i_jis_table[c - ucs_i_jis_table_min];
243 } else if (c >= ucs_r_jis_table_min && c < ucs_r_jis_table_max) {
244 s1 = ucs_r_jis_table[c - ucs_r_jis_table_min];
245 } else if (c >= 0xe000 && c < (0xe000 + 20*94)) { /* user (95ku - 114ku) */
246 s1 = c - 0xe000;
247 c1 = s1/94 + 0x7f;
248 c2 = s1%94 + 0x21;
249 s1 = (c1 << 8) | c2;
250 s2 = 1;
251 }
252 if (s1 <= 0) {
253 if (c == 0xa5) { /* YEN SIGN */
254 s1 = 0x216F; /* FULLWIDTH YEN SIGN */
255 } else if (c == 0xff3c) { /* FULLWIDTH REVERSE SOLIDUS */
256 s1 = 0x2140;
257 } else if (c == 0x2225) { /* PARALLEL TO */
258 s1 = 0x2142;
259 } else if (c == 0xff0d) { /* FULLWIDTH HYPHEN-MINUS */
260 s1 = 0x215d;
261 } else if (c == 0xffe0) { /* FULLWIDTH CENT SIGN */
262 s1 = 0x2171;
263 } else if (c == 0xffe1) { /* FULLWIDTH POUND SIGN */
264 s1 = 0x2172;
265 } else if (c == 0xffe2) { /* FULLWIDTH NOT SIGN */
266 s1 = 0x224c;
267 }
268 }
269 if ((s1 <= 0) || (s1 >= 0x8080 && s2 == 0)) { /* not found or X 0212 */
270 s1 = -1;
271 c1 = 0;
272 c2 = cp932ext1_ucs_table_max - cp932ext1_ucs_table_min;
273 while (c1 < c2) { /* CP932 vendor ext1 (13ku) */
274 if (c == cp932ext1_ucs_table[c1]) {
275 s1 = ((c1/94 + 0x2d) << 8) + (c1%94 + 0x21);
276 break;
277 }
278 c1++;
279 }
280 if (s1 <= 0) {
281 c1 = 0;
282 c2 = cp932ext3_ucs_table_max - cp932ext3_ucs_table_min;
283 while (c1 < c2) { /* CP932 vendor ext3 (115ku - 119ku) */
284 if (c == cp932ext3_ucs_table[c1]) {
285 s1 = ((c1/94 + 0x93) << 8) + (c1%94 + 0x21);
286 break;
287 }
288 c1++;
289 }
290 }
291 if (c == 0) {
292 s1 = 0;
293 } else if (s1 <= 0) {
294 s1 = -1;
295 }
296 }
297 if (s1 >= 0) {
298 if (s1 < 0x100) { /* latin or kana */
299 CK((*filter->output_function)(s1, filter->data));
300 } else { /* kanji */
301 c1 = (s1 >> 8) & 0xff;
302 c2 = s1 & 0xff;
303 SJIS_ENCODE(c1, c2, s1, s2);
304 CK((*filter->output_function)(s1, filter->data));
305 CK((*filter->output_function)(s2, filter->data));
306 }
307 } else {
308 CK(mbfl_filt_conv_illegal_output(c, filter));
309 }
310
311 return 0;
312 }
313