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_cn.c
26 * by moriyoshi koizumi <moriyoshi@php.net> on 4 dec 2002.
27 *
28 */
29
30 #ifdef HAVE_CONFIG_H
31 #include "config.h"
32 #endif
33
34 #include "mbfilter.h"
35 #include "mbfilter_cp936.h"
36 #define UNICODE_TABLE_CP936_DEF
37 #include "unicode_table_cp936.h"
38
39 static int mbfl_filt_ident_cp936(int c, mbfl_identify_filter *filter);
40
41 static const unsigned char mblen_table_cp936[] = { /* 0x81-0xFE */
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 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
48 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
49 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
50 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
51 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
52 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
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 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
56 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
57 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1
58 };
59
60 static const char *mbfl_encoding_cp936_aliases[] = {"CP-936", "GBK", NULL};
61
62 const mbfl_encoding mbfl_encoding_cp936 = {
63 mbfl_no_encoding_cp936,
64 "CP936",
65 "CP936",
66 (const char *(*)[])&mbfl_encoding_cp936_aliases,
67 mblen_table_cp936,
68 MBFL_ENCTYPE_MBCS | MBFL_ENCTYPE_GL_UNSAFE
69 };
70
71 const struct mbfl_identify_vtbl vtbl_identify_cp936 = {
72 mbfl_no_encoding_cp936,
73 mbfl_filt_ident_common_ctor,
74 mbfl_filt_ident_common_dtor,
75 mbfl_filt_ident_cp936
76 };
77
78 const struct mbfl_convert_vtbl vtbl_cp936_wchar = {
79 mbfl_no_encoding_cp936,
80 mbfl_no_encoding_wchar,
81 mbfl_filt_conv_common_ctor,
82 mbfl_filt_conv_common_dtor,
83 mbfl_filt_conv_cp936_wchar,
84 mbfl_filt_conv_common_flush
85 };
86
87 const struct mbfl_convert_vtbl vtbl_wchar_cp936 = {
88 mbfl_no_encoding_wchar,
89 mbfl_no_encoding_cp936,
90 mbfl_filt_conv_common_ctor,
91 mbfl_filt_conv_common_dtor,
92 mbfl_filt_conv_wchar_cp936,
93 mbfl_filt_conv_common_flush
94 };
95
96
97 #define CK(statement) do { if ((statement) < 0) return (-1); } while (0)
98
99 /*
100 * CP936 => wchar
101 */
102 int
mbfl_filt_conv_cp936_wchar(int c,mbfl_convert_filter * filter)103 mbfl_filt_conv_cp936_wchar(int c, mbfl_convert_filter *filter)
104 {
105 int k;
106 int c1, c2, w = -1;
107
108 switch (filter->status) {
109 case 0:
110 if (c >= 0 && c < 0x80) { /* latin */
111 CK((*filter->output_function)(c, filter->data));
112 } else if (c == 0x80) { /* euro sign */
113 CK((*filter->output_function)(0x20ac, filter->data));
114 } else if (c < 0xff) { /* dbcs lead byte */
115 filter->status = 1;
116 filter->cache = c;
117 } else { /* 0xff */
118 CK((*filter->output_function)(0xf8f5, filter->data));
119 }
120 break;
121
122 case 1: /* dbcs second byte */
123 filter->status = 0;
124 c1 = filter->cache;
125
126 if (((c1 >= 0xaa && c1 <= 0xaf) || (c1 >= 0xf8 && c1 <= 0xfe)) &&
127 (c >= 0xa1 && c <= 0xfe)) {
128 /* UDA part1,2: U+E000-U+E4C5 */
129 w = 94*(c1 >= 0xf8 ? c1 - 0xf2 : c1 - 0xaa) + (c - 0xa1) + 0xe000;
130 CK((*filter->output_function)(w, filter->data));
131 } else if (c1 >= 0xa1 && c1 <= 0xa7 && c >= 0x40 && c < 0xa1 && c != 0x7f) {
132 /* UDA part3 : U+E4C6-U+E765*/
133 w = 96*(c1 - 0xa1) + c - (c >= 0x80 ? 0x41 : 0x40) + 0xe4c6;
134 CK((*filter->output_function)(w, filter->data));
135 }
136
137 c2 = (c1 << 8) | c;
138
139 if (w <= 0 &&
140 ((c2 >= 0xa2ab && c2 <= 0xa9f0 + (0xe80f-0xe801)) ||
141 (c2 >= 0xd7fa && c2 <= 0xd7fa + (0xe814-0xe810)) ||
142 (c2 >= 0xfe50 && c2 <= 0xfe80 + (0xe864-0xe844)))) {
143 for (k = 0; k < mbfl_cp936_pua_tbl_max; k++) {
144 if (c2 >= mbfl_cp936_pua_tbl[k][2] &&
145 c2 <= mbfl_cp936_pua_tbl[k][2] +
146 mbfl_cp936_pua_tbl[k][1] - mbfl_cp936_pua_tbl[k][0]) {
147 w = c2 - mbfl_cp936_pua_tbl[k][2] + mbfl_cp936_pua_tbl[k][0];
148 CK((*filter->output_function)(w, filter->data));
149 break;
150 }
151 }
152 }
153
154 if (w <= 0) {
155 if (c1 < 0xff && c1 > 0x80 && c > 0x39 && c < 0xff && c != 0x7f) {
156 w = (c1 - 0x81)*192 + (c - 0x40);
157 if (w >= 0 && w < cp936_ucs_table_size) {
158 w = cp936_ucs_table[w];
159 } else {
160 w = 0;
161 }
162 if (w <= 0) {
163 w = (c1 << 8) | c;
164 w &= MBFL_WCSPLANE_MASK;
165 w |= MBFL_WCSPLANE_WINCP936;
166 }
167 CK((*filter->output_function)(w, filter->data));
168 } else if ((c >= 0 && c < 0x21) || c == 0x7f) { /* CTLs */
169 CK((*filter->output_function)(c, filter->data));
170 } else {
171 w = (c1 << 8) | c;
172 w &= MBFL_WCSGROUP_MASK;
173 w |= MBFL_WCSGROUP_THROUGH;
174 CK((*filter->output_function)(w, filter->data));
175 }
176 }
177 break;
178
179 default:
180 filter->status = 0;
181 break;
182 }
183
184 return c;
185 }
186
187 /*
188 * wchar => CP936
189 */
190 int
mbfl_filt_conv_wchar_cp936(int c,mbfl_convert_filter * filter)191 mbfl_filt_conv_wchar_cp936(int c, mbfl_convert_filter *filter)
192 {
193 int k, k1, k2;
194 int c1, s = 0;
195
196 if (c >= ucs_a1_cp936_table_min && c < ucs_a1_cp936_table_max) {
197 /* U+0000 - U+0451 */
198 s = ucs_a1_cp936_table[c - ucs_a1_cp936_table_min];
199 } else if (c >= ucs_a2_cp936_table_min && c < ucs_a2_cp936_table_max) {
200 /* U+2000 - U+26FF */
201 if (c == 0x203e) {
202 s = 0xa3fe;
203 } else if (c == 0x2218) {
204 s = 0xa1e3;
205 } else if (c == 0x223c) {
206 s = 0xa1ab;
207 } else {
208 s = ucs_a2_cp936_table[c - ucs_a2_cp936_table_min];
209 }
210 } else if (c >= ucs_a3_cp936_table_min && c < ucs_a3_cp936_table_max) {
211 /* U+2F00 - U+33FF */
212 s = ucs_a3_cp936_table[c - ucs_a3_cp936_table_min];
213 } else if (c >= ucs_i_cp936_table_min && c < ucs_i_cp936_table_max) {
214 /* U+4D00-9FFF CJK Unified Ideographs (+ Extension A) */
215 s = ucs_i_cp936_table[c - ucs_i_cp936_table_min];
216 } else if (c >= 0xe000 && c <= 0xe864) { /* PUA */
217 if (c < 0xe766) {
218 if (c < 0xe4c6) {
219 c1 = c - 0xe000;
220 s = (c1 % 94) + 0xa1; c1 /= 94;
221 s |= (c1 < 0x06 ? c1 + 0xaa : c1 + 0xf2) << 8;
222 } else {
223 c1 = c - 0xe4c6;
224 s = ((c1 / 96) + 0xa1) << 8; c1 %= 96;
225 s |= c1 + (c1 >= 0x3f ? 0x41 : 0x40);
226 }
227 } else {
228 /* U+E766..U+E864 */
229 k1 = 0; k2 = mbfl_cp936_pua_tbl_max;
230 while (k1 < k2) {
231 k = (k1 + k2) >> 1;
232 if (c < mbfl_cp936_pua_tbl[k][0]) {
233 k2 = k;
234 } else if (c > mbfl_cp936_pua_tbl[k][1]) {
235 k1 = k + 1;
236 } else {
237 s = c - mbfl_cp936_pua_tbl[k][0] + mbfl_cp936_pua_tbl[k][2];
238 break;
239 }
240 }
241 }
242 } else if (c == 0xf8f5) {
243 s = 0xff;
244 } else if (c >= ucs_ci_cp936_table_min && c < ucs_ci_cp936_table_max) {
245 /* U+F900-FA2F CJK Compatibility Ideographs */
246 s = ucs_ci_cp936_table[c - ucs_ci_cp936_table_min];
247 } else if (c >= ucs_cf_cp936_table_min && c < ucs_cf_cp936_table_max) {
248 s = ucs_cf_cp936_table[c - ucs_cf_cp936_table_min];
249 } else if (c >= ucs_sfv_cp936_table_min && c < ucs_sfv_cp936_table_max) {
250 s = ucs_sfv_cp936_table[c - ucs_sfv_cp936_table_min]; /* U+FE50-FE6F Small Form Variants */
251 } else if (c >= ucs_hff_cp936_table_min && c < ucs_hff_cp936_table_max) {
252 /* U+FF00-FFFF HW/FW Forms */
253 if (c == 0xff04) {
254 s = 0xa1e7;
255 } else if (c == 0xff5e) {
256 s = 0xa1ab;
257 } else if (c >= 0xff01 && c <= 0xff5d) {
258 s = c - 0xff01 + 0xa3a1;
259 } else if (c >= 0xffe0 && c <= 0xffe5) {
260 s = ucs_hff_s_cp936_table[c-0xffe0];
261 }
262 }
263 if (s <= 0) {
264 c1 = c & ~MBFL_WCSPLANE_MASK;
265 if (c1 == MBFL_WCSPLANE_WINCP936) {
266 s = c & MBFL_WCSPLANE_MASK;
267 }
268 if (c == 0) {
269 s = 0;
270 } else if (s <= 0) {
271 s = -1;
272 }
273 }
274 if (s >= 0) {
275 if (s <= 0x80 || s == 0xff) { /* latin */
276 CK((*filter->output_function)(s, filter->data));
277 } else {
278 CK((*filter->output_function)((s >> 8) & 0xff, filter->data));
279 CK((*filter->output_function)(s & 0xff, filter->data));
280 }
281 } else {
282 if (filter->illegal_mode != MBFL_OUTPUTFILTER_ILLEGAL_MODE_NONE) {
283 CK(mbfl_filt_conv_illegal_output(c, filter));
284 }
285 }
286
287 return c;
288 }
289
mbfl_filt_ident_cp936(int c,mbfl_identify_filter * filter)290 static int mbfl_filt_ident_cp936(int c, mbfl_identify_filter *filter)
291 {
292 if (filter->status) { /* kanji second char */
293 if (c < 0x40 || c > 0xfe || c == 0x7f) { /* bad */
294 filter->flag = 1;
295 }
296 filter->status = 0;
297 } else if (c >= 0 && c < 0x80) { /* latin ok */
298 ;
299 } else if (c > 0x80 && c < 0xff) { /* DBCS lead byte */
300 filter->status = 1;
301 } else { /* bad */
302 filter->flag = 1;
303 }
304
305 return c;
306 }
307
