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: Rui Hirokawa <hirokawa@php.net>
22 *
23 */
24 /*
25 * The source code included in this files was separated from mbfilter_tw.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_big5.h"
36
37 #include "unicode_table_big5.h"
38
39 static int mbfl_filt_ident_big5(int c, mbfl_identify_filter *filter);
40
41 static const unsigned char mblen_table_big5[] = { /* 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_big5_aliases[] = {"CN-BIG5", "BIG-FIVE", "BIGFIVE", "CP950", NULL};
61
62 const mbfl_encoding mbfl_encoding_big5 = {
63 mbfl_no_encoding_big5,
64 "BIG-5",
65 "BIG5",
66 (const char *(*)[])&mbfl_encoding_big5_aliases,
67 mblen_table_big5,
68 MBFL_ENCTYPE_MBCS
69 };
70
71 const struct mbfl_identify_vtbl vtbl_identify_big5 = {
72 mbfl_no_encoding_big5,
73 mbfl_filt_ident_common_ctor,
74 mbfl_filt_ident_common_dtor,
75 mbfl_filt_ident_big5
76 };
77
78 const struct mbfl_convert_vtbl vtbl_big5_wchar = {
79 mbfl_no_encoding_big5,
80 mbfl_no_encoding_wchar,
81 mbfl_filt_conv_common_ctor,
82 mbfl_filt_conv_common_dtor,
83 mbfl_filt_conv_big5_wchar,
84 mbfl_filt_conv_common_flush
85 };
86
87 const struct mbfl_convert_vtbl vtbl_wchar_big5 = {
88 mbfl_no_encoding_wchar,
89 mbfl_no_encoding_big5,
90 mbfl_filt_conv_common_ctor,
91 mbfl_filt_conv_common_dtor,
92 mbfl_filt_conv_wchar_big5,
93 mbfl_filt_conv_common_flush
94 };
95
96 #define CK(statement) do { if ((statement) < 0) return (-1); } while (0)
97
98 /*
99 * Big5 => wchar
100 */
101 int
mbfl_filt_conv_big5_wchar(int c,mbfl_convert_filter * filter)102 mbfl_filt_conv_big5_wchar(int c, mbfl_convert_filter *filter)
103 {
104 int c1, w;
105
106 switch (filter->status) {
107 case 0:
108 if (c >= 0 && c < 0x80) { /* latin */
109 CK((*filter->output_function)(c, filter->data));
110 } else if (c > 0xa0 && c < 0xff) { /* dbcs lead byte */
111 filter->status = 1;
112 filter->cache = c;
113 } else {
114 w = c & MBFL_WCSGROUP_MASK;
115 w |= MBFL_WCSGROUP_THROUGH;
116 CK((*filter->output_function)(w, filter->data));
117 }
118 break;
119
120 case 1: /* dbcs second byte */
121 filter->status = 0;
122 c1 = filter->cache;
123 if ((c > 0x39 && c < 0x7f) | (c > 0xa0 && c < 0xff)) {
124 if (c < 0x7f){
125 w = (c1 - 0xa1)*157 + (c - 0x40);
126 } else {
127 w = (c1 - 0xa1)*157 + (c - 0xa1) + 0x3f;
128 }
129 if (w >= 0 && w < big5_ucs_table_size) {
130 w = big5_ucs_table[w];
131 } else {
132 w = 0;
133 }
134 if (w <= 0) {
135 w = (c1 << 8) | c;
136 w &= MBFL_WCSPLANE_MASK;
137 w |= MBFL_WCSPLANE_BIG5;
138 }
139 CK((*filter->output_function)(w, filter->data));
140 } else if ((c >= 0 && c < 0x21) || c == 0x7f) { /* CTLs */
141 CK((*filter->output_function)(c, filter->data));
142 } else {
143 w = (c1 << 8) | c;
144 w &= MBFL_WCSGROUP_MASK;
145 w |= MBFL_WCSGROUP_THROUGH;
146 CK((*filter->output_function)(w, filter->data));
147 }
148 break;
149
150 default:
151 filter->status = 0;
152 break;
153 }
154
155 return c;
156 }
157
158 /*
159 * wchar => Big5
160 */
161 int
mbfl_filt_conv_wchar_big5(int c,mbfl_convert_filter * filter)162 mbfl_filt_conv_wchar_big5(int c, mbfl_convert_filter *filter)
163 {
164 int c1, s;
165
166 s = 0;
167 if (c >= ucs_a1_big5_table_min && c < ucs_a1_big5_table_max) {
168 s = ucs_a1_big5_table[c - ucs_a1_big5_table_min];
169 } else if (c >= ucs_a2_big5_table_min && c < ucs_a2_big5_table_max) {
170 s = ucs_a2_big5_table[c - ucs_a2_big5_table_min];
171 } else if (c >= ucs_a3_big5_table_min && c < ucs_a3_big5_table_max) {
172 s = ucs_a3_big5_table[c - ucs_a3_big5_table_min];
173 } else if (c >= ucs_i_big5_table_min && c < ucs_i_big5_table_max) {
174 s = ucs_i_big5_table[c - ucs_i_big5_table_min];
175 } else if (c >= ucs_pua_big5_table_min && c < ucs_pua_big5_table_max) {
176 s = ucs_pua_big5_table[c - ucs_pua_big5_table_min];
177 } else if (c >= ucs_r1_big5_table_min && c < ucs_r1_big5_table_max) {
178 s = ucs_r1_big5_table[c - ucs_r1_big5_table_min];
179 } else if (c >= ucs_r2_big5_table_min && c < ucs_r2_big5_table_max) {
180 s = ucs_r2_big5_table[c - ucs_r2_big5_table_min];
181 }
182 if (s <= 0) {
183 c1 = c & ~MBFL_WCSPLANE_MASK;
184 if (c1 == MBFL_WCSPLANE_BIG5) {
185 s = c & MBFL_WCSPLANE_MASK;
186 }
187 if (c == 0) {
188 s = 0;
189 } else if (s <= 0) {
190 s = -1;
191 }
192 }
193 if (s >= 0) {
194 if (s < 0x80) { /* latin */
195 CK((*filter->output_function)(s, filter->data));
196 } else {
197 CK((*filter->output_function)((s >> 8) & 0xff, filter->data));
198 CK((*filter->output_function)(s & 0xff, filter->data));
199 }
200 } else {
201 if (filter->illegal_mode != MBFL_OUTPUTFILTER_ILLEGAL_MODE_NONE) {
202 CK(mbfl_filt_conv_illegal_output(c, filter));
203 }
204 }
205
206 return c;
207 }
208
mbfl_filt_ident_big5(int c,mbfl_identify_filter * filter)209 static int mbfl_filt_ident_big5(int c, mbfl_identify_filter *filter)
210 {
211 if (filter->status) { /* kanji second char */
212 if (c < 0x40 || (c > 0x7e && c < 0xa1) ||c > 0xfe) { /* bad */
213 filter->flag = 1;
214 }
215 filter->status = 0;
216 } else if (c >= 0 && c < 0x80) { /* latin ok */
217 ;
218 } else if (c > 0xa0 && c < 0xff) { /* DBCS lead byte */
219 filter->status = 1;
220 } else { /* bad */
221 filter->flag = 1;
222 }
223
224 return c;
225 }
226
227
228