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_euc_jp.h"
32
33 #include "unicode_table_cp932_ext.h"
34 #include "unicode_table_jis.h"
35
36 static int mbfl_filt_conv_eucjp_wchar_flush(mbfl_convert_filter *filter);
37
38 const unsigned char mblen_table_eucjp[] = { /* 0xA1-0xFE */
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 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 3,
48 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
49 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
50 2, 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, 1
55 };
56
57 static const char *mbfl_encoding_euc_jp_aliases[] = {"EUC", "EUC_JP", "eucJP", "x-euc-jp", NULL};
58
59 const mbfl_encoding mbfl_encoding_euc_jp = {
60 mbfl_no_encoding_euc_jp,
61 "EUC-JP",
62 "EUC-JP",
63 mbfl_encoding_euc_jp_aliases,
64 mblen_table_eucjp,
65 0,
66 &vtbl_eucjp_wchar,
67 &vtbl_wchar_eucjp,
68 NULL
69 };
70
71 const struct mbfl_convert_vtbl vtbl_eucjp_wchar = {
72 mbfl_no_encoding_euc_jp,
73 mbfl_no_encoding_wchar,
74 mbfl_filt_conv_common_ctor,
75 NULL,
76 mbfl_filt_conv_eucjp_wchar,
77 mbfl_filt_conv_eucjp_wchar_flush,
78 NULL,
79 };
80
81 const struct mbfl_convert_vtbl vtbl_wchar_eucjp = {
82 mbfl_no_encoding_wchar,
83 mbfl_no_encoding_euc_jp,
84 mbfl_filt_conv_common_ctor,
85 NULL,
86 mbfl_filt_conv_wchar_eucjp,
87 mbfl_filt_conv_common_flush,
88 NULL,
89 };
90
91 #define CK(statement) do { if ((statement) < 0) return (-1); } while (0)
92
93 /*
94 * EUC-JP => wchar
95 */
96 int
mbfl_filt_conv_eucjp_wchar(int c,mbfl_convert_filter * filter)97 mbfl_filt_conv_eucjp_wchar(int c, mbfl_convert_filter *filter)
98 {
99 int c1, s, w = 0;
100
101 switch (filter->status) {
102 case 0:
103 if (c >= 0 && c < 0x80) { /* latin */
104 CK((*filter->output_function)(c, filter->data));
105 } else if (c > 0xa0 && c < 0xff) { /* X 0208 first char */
106 filter->status = 1;
107 filter->cache = c;
108 } else if (c == 0x8e) { /* kana first char */
109 filter->status = 2;
110 } else if (c == 0x8f) { /* X 0212 first char */
111 filter->status = 3;
112 } else {
113 CK((*filter->output_function)(MBFL_BAD_INPUT, filter->data));
114 }
115 break;
116
117 case 1: /* got first half */
118 filter->status = 0;
119 c1 = filter->cache;
120 if (c > 0xa0 && c < 0xff) {
121 s = (c1 - 0xa1)*94 + c - 0xa1;
122 if (s >= 0 && s < jisx0208_ucs_table_size) {
123 w = jisx0208_ucs_table[s];
124 if (!w)
125 w = MBFL_BAD_INPUT;
126 } else {
127 w = MBFL_BAD_INPUT;
128 }
129
130 CK((*filter->output_function)(w, filter->data));
131 } else {
132 CK((*filter->output_function)(MBFL_BAD_INPUT, filter->data));
133 }
134 break;
135
136 case 2: /* got 0x8e */
137 filter->status = 0;
138 if (c > 0xa0 && c < 0xe0) {
139 w = 0xfec0 + c;
140 CK((*filter->output_function)(w, filter->data));
141 } else {
142 CK((*filter->output_function)(MBFL_BAD_INPUT, filter->data));
143 }
144 break;
145
146 case 3: /* got 0x8f, JIS X 0212 first byte */
147 filter->status++;
148 filter->cache = c;
149 break;
150
151 case 4: /* got 0x8f, JIS X 0212 second byte */
152 filter->status = 0;
153 c1 = filter->cache;
154 if (c > 0xA0 && c < 0xFF && c1 > 0xA0 && c1 < 0xFF) {
155 s = (c1 - 0xa1)*94 + c - 0xa1;
156 if (s >= 0 && s < jisx0212_ucs_table_size) {
157 w = jisx0212_ucs_table[s];
158 if (!w)
159 w = MBFL_BAD_INPUT;
160 } else {
161 w = MBFL_BAD_INPUT;
162 }
163
164 CK((*filter->output_function)(w, filter->data));
165 } else {
166 CK((*filter->output_function)(MBFL_BAD_INPUT, filter->data));
167 }
168 break;
169
170 default:
171 filter->status = 0;
172 break;
173 }
174
175 return 0;
176 }
177
mbfl_filt_conv_eucjp_wchar_flush(mbfl_convert_filter * filter)178 static int mbfl_filt_conv_eucjp_wchar_flush(mbfl_convert_filter *filter)
179 {
180 if (filter->status) {
181 (*filter->output_function)(MBFL_BAD_INPUT, filter->data);
182 filter->status = 0;
183 }
184
185 if (filter->flush_function) {
186 (*filter->flush_function)(filter->data);
187 }
188
189 return 0;
190 }
191
192 /*
193 * wchar => EUC-JP
194 */
195 int
mbfl_filt_conv_wchar_eucjp(int c,mbfl_convert_filter * filter)196 mbfl_filt_conv_wchar_eucjp(int c, mbfl_convert_filter *filter)
197 {
198 int s = 0;
199
200 if (c == 0xAF) { /* U+00AF is MACRON */
201 s = 0xA2B4; /* Use JIS X 0212 overline */
202 } else if (c >= ucs_a1_jis_table_min && c < ucs_a1_jis_table_max) {
203 s = ucs_a1_jis_table[c - ucs_a1_jis_table_min];
204 } else if (c >= ucs_a2_jis_table_min && c < ucs_a2_jis_table_max) {
205 s = ucs_a2_jis_table[c - ucs_a2_jis_table_min];
206 } else if (c >= ucs_i_jis_table_min && c < ucs_i_jis_table_max) {
207 s = ucs_i_jis_table[c - ucs_i_jis_table_min];
208 } else if (c >= ucs_r_jis_table_min && c < ucs_r_jis_table_max) {
209 s = ucs_r_jis_table[c - ucs_r_jis_table_min];
210 }
211 if (s <= 0) {
212 if (c == 0xff3c) { /* FULLWIDTH REVERSE SOLIDUS */
213 s = 0x2140;
214 } else if (c == 0xff5e) { /* FULLWIDTH TILDE */
215 s = 0x2141;
216 } else if (c == 0x2225) { /* PARALLEL TO */
217 s = 0x2142;
218 } else if (c == 0xff0d) { /* FULLWIDTH HYPHEN-MINUS */
219 s = 0x215d;
220 } else if (c == 0xffe0) { /* FULLWIDTH CENT SIGN */
221 s = 0x2171;
222 } else if (c == 0xffe1) { /* FULLWIDTH POUND SIGN */
223 s = 0x2172;
224 } else if (c == 0xffe2) { /* FULLWIDTH NOT SIGN */
225 s = 0x224c;
226 } else if (c == 0) {
227 s = 0;
228 } else {
229 s = -1;
230 }
231 }
232 if (s >= 0) {
233 if (s < 0x80) { /* latin */
234 CK((*filter->output_function)(s, filter->data));
235 } else if (s < 0x100) { /* kana */
236 CK((*filter->output_function)(0x8e, filter->data));
237 CK((*filter->output_function)(s, filter->data));
238 } else if (s < 0x8080) { /* X 0208 */
239 CK((*filter->output_function)(((s >> 8) & 0xff) | 0x80, filter->data));
240 CK((*filter->output_function)((s & 0xff) | 0x80, filter->data));
241 } else { /* X 0212 */
242 CK((*filter->output_function)(0x8f, filter->data));
243 CK((*filter->output_function)(((s >> 8) & 0xff) | 0x80, filter->data));
244 CK((*filter->output_function)((s & 0xff) | 0x80, filter->data));
245 }
246 } else {
247 CK(mbfl_filt_conv_illegal_output(c, filter));
248 }
249
250 return 0;
251 }
252