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_euc_cn.h"
36
37 #include "unicode_table_cp936.h"
38
39 static int mbfl_filt_ident_euccn(int c, mbfl_identify_filter *filter);
40
41 static const unsigned char mblen_table_euccn[] = { /* 0xA1-0xFE */
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, 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, 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_euc_cn_aliases[] = {"CN-GB", "EUC_CN", "eucCN", "x-euc-cn", "gb2312", NULL};
61
62 const mbfl_encoding mbfl_encoding_euc_cn = {
63 mbfl_no_encoding_euc_cn,
64 "EUC-CN",
65 "CN-GB",
66 (const char *(*)[])&mbfl_encoding_euc_cn_aliases,
67 mblen_table_euccn,
68 MBFL_ENCTYPE_MBCS
69 };
70
71 const struct mbfl_identify_vtbl vtbl_identify_euccn = {
72 mbfl_no_encoding_euc_cn,
73 mbfl_filt_ident_common_ctor,
74 mbfl_filt_ident_common_dtor,
75 mbfl_filt_ident_euccn
76 };
77
78 const struct mbfl_convert_vtbl vtbl_euccn_wchar = {
79 mbfl_no_encoding_euc_cn,
80 mbfl_no_encoding_wchar,
81 mbfl_filt_conv_common_ctor,
82 mbfl_filt_conv_common_dtor,
83 mbfl_filt_conv_euccn_wchar,
84 mbfl_filt_conv_common_flush
85 };
86
87 const struct mbfl_convert_vtbl vtbl_wchar_euccn = {
88 mbfl_no_encoding_wchar,
89 mbfl_no_encoding_euc_cn,
90 mbfl_filt_conv_common_ctor,
91 mbfl_filt_conv_common_dtor,
92 mbfl_filt_conv_wchar_euccn,
93 mbfl_filt_conv_common_flush
94 };
95
96 #define CK(statement) do { if ((statement) < 0) return (-1); } while (0)
97
98 /*
99 * EUC-CN => wchar
100 */
101 int
mbfl_filt_conv_euccn_wchar(int c,mbfl_convert_filter * filter)102 mbfl_filt_conv_euccn_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 (c1 > 0xa0 && c1 < 0xff && c > 0xa0 && c < 0xff) {
124 w = (c1 - 0x81)*192 + (c - 0x40);
125 if (w >= 0 && w < cp936_ucs_table_size) {
126 w = cp936_ucs_table[w];
127 } else {
128 w = 0;
129 }
130 if (w <= 0) {
131 w = (c1 << 8) | c;
132 w &= MBFL_WCSPLANE_MASK;
133 w |= MBFL_WCSPLANE_GB2312;
134 }
135 CK((*filter->output_function)(w, filter->data));
136 } else if ((c >= 0 && c < 0x21) || c == 0x7f) { /* CTLs */
137 CK((*filter->output_function)(c, filter->data));
138 } else {
139 w = (c1 << 8) | c;
140 w &= MBFL_WCSGROUP_MASK;
141 w |= MBFL_WCSGROUP_THROUGH;
142 CK((*filter->output_function)(w, filter->data));
143 }
144 break;
145
146 default:
147 filter->status = 0;
148 break;
149 }
150
151 return c;
152 }
153
154 /*
155 * wchar => EUC-CN
156 */
157 int
mbfl_filt_conv_wchar_euccn(int c,mbfl_convert_filter * filter)158 mbfl_filt_conv_wchar_euccn(int c, mbfl_convert_filter *filter)
159 {
160 int c1, c2, s;
161
162 s = 0;
163 if (c >= ucs_a1_cp936_table_min && c < ucs_a1_cp936_table_max) {
164 s = ucs_a1_cp936_table[c - ucs_a1_cp936_table_min];
165 } else if (c >= ucs_a2_cp936_table_min && c < ucs_a2_cp936_table_max) {
166 s = ucs_a2_cp936_table[c - ucs_a2_cp936_table_min];
167 } else if (c >= ucs_a3_cp936_table_min && c < ucs_a3_cp936_table_max) {
168 s = ucs_a3_cp936_table[c - ucs_a3_cp936_table_min];
169 } else if (c >= ucs_i_cp936_table_min && c < ucs_i_cp936_table_max) {
170 s = ucs_i_cp936_table[c - ucs_i_cp936_table_min];
171 } else if (c >= ucs_hff_cp936_table_min && c < ucs_hff_cp936_table_max) {
172 s = ucs_hff_cp936_table[c - ucs_hff_cp936_table_min];
173 }
174 c1 = (s >> 8) & 0xff;
175 c2 = s & 0xff;
176
177 if (c1 < 0xa1 || c2 < 0xa1) { /* exclude CP936 extension */
178 s = c;
179 }
180
181 if (s <= 0) {
182 c1 = c & ~MBFL_WCSPLANE_MASK;
183 if (c1 == MBFL_WCSPLANE_GB2312) {
184 s = c & MBFL_WCSPLANE_MASK;
185 }
186 if (c == 0) {
187 s = 0;
188 } else if (s <= 0) {
189 s = -1;
190 }
191 }
192 if (s >= 0) {
193 if (s < 0x80) { /* latin */
194 CK((*filter->output_function)(s, filter->data));
195 } else {
196 CK((*filter->output_function)((s >> 8) & 0xff, filter->data));
197 CK((*filter->output_function)(s & 0xff, filter->data));
198 }
199 } else {
200 if (filter->illegal_mode != MBFL_OUTPUTFILTER_ILLEGAL_MODE_NONE) {
201 CK(mbfl_filt_conv_illegal_output(c, filter));
202 }
203 }
204
205 return c;
206 }
207
mbfl_filt_ident_euccn(int c,mbfl_identify_filter * filter)208 static int mbfl_filt_ident_euccn(int c, mbfl_identify_filter *filter)
209 {
210 switch (filter->status) {
211 case 0: /* latin */
212 if (c >= 0 && c < 0x80) { /* ok */
213 ;
214 } else if (c > 0xa0 && c < 0xff) { /* DBCS lead byte */
215 filter->status = 1;
216 } else { /* bad */
217 filter->flag = 1;
218 }
219 break;
220
221 case 1: /* got lead byte */
222 if (c < 0xa1 || c > 0xfe) { /* bad */
223 filter->flag = 1;
224 }
225 filter->status = 0;
226 break;
227
228 default:
229 filter->status = 0;
230 break;
231 }
232
233 return c;
234 }
235
236
237