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_sjis.h"
32
33 #define UNICODE_TABLE_CP932_DEF
34 #define UNICODE_TABLE_JIS_DEF
35
36 #include "unicode_table_cp932_ext.h"
37 #include "unicode_table_jis.h"
38
39 static int mbfl_filt_conv_sjis_wchar_flush(mbfl_convert_filter *filter);
40
41 const unsigned char mblen_table_sjis[] = { /* 0x81-0x9F,0xE0-0xEF */
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 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
53 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
54 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
55 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
56 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
57 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1
58 };
59
60 static const char *mbfl_encoding_sjis_aliases[] = {"x-sjis", "SHIFT-JIS", NULL};
61
62 const mbfl_encoding mbfl_encoding_sjis = {
63 mbfl_no_encoding_sjis,
64 "SJIS",
65 "Shift_JIS",
66 mbfl_encoding_sjis_aliases,
67 mblen_table_sjis,
68 MBFL_ENCTYPE_GL_UNSAFE,
69 &vtbl_sjis_wchar,
70 &vtbl_wchar_sjis,
71 NULL
72 };
73
74 const struct mbfl_convert_vtbl vtbl_sjis_wchar = {
75 mbfl_no_encoding_sjis,
76 mbfl_no_encoding_wchar,
77 mbfl_filt_conv_common_ctor,
78 NULL,
79 mbfl_filt_conv_sjis_wchar,
80 mbfl_filt_conv_sjis_wchar_flush,
81 NULL
82 };
83
84 const struct mbfl_convert_vtbl vtbl_wchar_sjis = {
85 mbfl_no_encoding_wchar,
86 mbfl_no_encoding_sjis,
87 mbfl_filt_conv_common_ctor,
88 NULL,
89 mbfl_filt_conv_wchar_sjis,
90 mbfl_filt_conv_common_flush,
91 NULL
92 };
93
94 #define CK(statement) do { if ((statement) < 0) return (-1); } while (0)
95
96 #define SJIS_ENCODE(c1,c2,s1,s2) \
97 do { \
98 s1 = c1; \
99 s1--; \
100 s1 >>= 1; \
101 if ((c1) < 0x5f) { \
102 s1 += 0x71; \
103 } else { \
104 s1 += 0xb1; \
105 } \
106 s2 = c2; \
107 if ((c1) & 1) { \
108 if ((c2) < 0x60) { \
109 s2--; \
110 } \
111 s2 += 0x20; \
112 } else { \
113 s2 += 0x7e; \
114 } \
115 } while (0)
116
117 #define SJIS_DECODE(c1,c2,s1,s2) \
118 do { \
119 s1 = c1; \
120 if (s1 < 0xa0) { \
121 s1 -= 0x81; \
122 } else { \
123 s1 -= 0xc1; \
124 } \
125 s1 <<= 1; \
126 s1 += 0x21; \
127 s2 = c2; \
128 if (s2 < 0x9f) { \
129 if (s2 < 0x7f) { \
130 s2++; \
131 } \
132 s2 -= 0x20; \
133 } else { \
134 s1++; \
135 s2 -= 0x7e; \
136 } \
137 } while (0)
138
mbfl_filt_conv_sjis_wchar(int c,mbfl_convert_filter * filter)139 int mbfl_filt_conv_sjis_wchar(int c, mbfl_convert_filter *filter)
140 {
141 int s1, s2, w;
142
143 switch (filter->status) {
144 case 0:
145 if (c >= 0 && c < 0x80) { /* ASCII */
146 CK((*filter->output_function)(c, filter->data));
147 } else if (c > 0xA0 && c < 0xE0) { /* Kana */
148 CK((*filter->output_function)(0xFEC0 + c, filter->data));
149 } else if (c > 0x80 && c < 0xF0 && c != 0xA0) { /* Kanji, first byte */
150 filter->status = 1;
151 filter->cache = c;
152 } else {
153 CK((*filter->output_function)(MBFL_BAD_INPUT, filter->data));
154 }
155 break;
156
157 case 1: /* Kanji, second byte */
158 filter->status = 0;
159 int c1 = filter->cache;
160 if (c >= 0x40 && c <= 0xFC && c != 0x7F) {
161 SJIS_DECODE(c1, c, s1, s2);
162 w = (s1 - 0x21)*94 + s2 - 0x21;
163 if (w >= 0 && w < jisx0208_ucs_table_size) {
164 w = jisx0208_ucs_table[w];
165 if (!w)
166 w = MBFL_BAD_INPUT;
167 } else {
168 w = MBFL_BAD_INPUT;
169 }
170 CK((*filter->output_function)(w, filter->data));
171 } else {
172 CK((*filter->output_function)(MBFL_BAD_INPUT, filter->data));
173 }
174 }
175
176 return 0;
177 }
178
mbfl_filt_conv_sjis_wchar_flush(mbfl_convert_filter * filter)179 static int mbfl_filt_conv_sjis_wchar_flush(mbfl_convert_filter *filter)
180 {
181 if (filter->status) {
182 (*filter->output_function)(MBFL_BAD_INPUT, filter->data);
183 filter->status = 0;
184 }
185
186 if (filter->flush_function) {
187 (*filter->flush_function)(filter->data);
188 }
189
190 return 0;
191 }
192
mbfl_filt_conv_wchar_sjis(int c,mbfl_convert_filter * filter)193 int mbfl_filt_conv_wchar_sjis(int c, mbfl_convert_filter *filter)
194 {
195 int c1, c2, s1, s2;
196
197 s1 = 0;
198 if (c >= ucs_a1_jis_table_min && c < ucs_a1_jis_table_max) {
199 s1 = ucs_a1_jis_table[c - ucs_a1_jis_table_min];
200 } else if (c >= ucs_a2_jis_table_min && c < ucs_a2_jis_table_max) {
201 s1 = ucs_a2_jis_table[c - ucs_a2_jis_table_min];
202 } else if (c >= ucs_i_jis_table_min && c < ucs_i_jis_table_max) {
203 s1 = ucs_i_jis_table[c - ucs_i_jis_table_min];
204 } else if (c >= ucs_r_jis_table_min && c < ucs_r_jis_table_max) {
205 s1 = ucs_r_jis_table[c - ucs_r_jis_table_min];
206 }
207 if (s1 <= 0) {
208 if (c == 0xA5) { /* YEN SIGN */
209 s1 = 0x216F; /* FULLWIDTH YEN SIGN */
210 } else if (c == 0xAF || c == 0x203E) { /* U+00AF is MACRON, U+203E is OVERLINE */
211 s1 = 0x2131; /* FULLWIDTH MACRON */
212 } else if (c == 0xFF3C) { /* FULLWIDTH REVERSE SOLIDUS */
213 s1 = 0x2140;
214 } else if (c == 0xFF5E) { /* FULLWIDTH TILDE */
215 s1 = 0x2141;
216 } else if (c == 0x2225) { /* PARALLEL TO */
217 s1 = 0x2142;
218 } else if (c == 0xFF0D) { /* FULLWIDTH HYPHEN-MINUS */
219 s1 = 0x215D;
220 } else if (c == 0xFFE0) { /* FULLWIDTH CENT SIGN */
221 s1 = 0x2171;
222 } else if (c == 0xFFE1) { /* FULLWIDTH POUND SIGN */
223 s1 = 0x2172;
224 } else if (c == 0xFFE2) { /* FULLWIDTH NOT SIGN */
225 s1 = 0x224C;
226 } else if (c == 0) {
227 s1 = 0;
228 } else {
229 s1 = -1;
230 }
231 } else if (s1 >= 0x8080) { /* JIS X 0212; not supported */
232 s1 = -1;
233 }
234
235 if (s1 >= 0) {
236 if (s1 < 0x100) { /* Latin/Kana */
237 CK((*filter->output_function)(s1, filter->data));
238 } else { /* Kanji */
239 c1 = (s1 >> 8) & 0xFF;
240 c2 = s1 & 0xFF;
241 SJIS_ENCODE(c1, c2, s1, s2);
242 CK((*filter->output_function)(s1, filter->data));
243 CK((*filter->output_function)(s2, filter->data));
244 }
245 } else {
246 CK(mbfl_filt_conv_illegal_output(c, filter));
247 }
248
249 return 0;
250 }
251
