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_kr.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_kr.h"
36 #include "unicode_table_uhc.h"
37
38 static int mbfl_filt_ident_euckr(int c, mbfl_identify_filter *filter);
39
40 static const unsigned char mblen_table_euckr[] = { /* 0xA1-0xFE */
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, 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, 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, 1
57 };
58
59 static const char *mbfl_encoding_euc_kr_aliases[] = {"EUC_KR", "eucKR", "x-euc-kr", NULL};
60
61 const mbfl_encoding mbfl_encoding_euc_kr = {
62 mbfl_no_encoding_euc_kr,
63 "EUC-KR",
64 "EUC-KR",
65 (const char *(*)[])&mbfl_encoding_euc_kr_aliases,
66 mblen_table_euckr,
67 MBFL_ENCTYPE_MBCS
68 };
69
70 const struct mbfl_identify_vtbl vtbl_identify_euckr = {
71 mbfl_no_encoding_euc_kr,
72 mbfl_filt_ident_common_ctor,
73 mbfl_filt_ident_common_dtor,
74 mbfl_filt_ident_euckr
75 };
76
77 const struct mbfl_convert_vtbl vtbl_euckr_wchar = {
78 mbfl_no_encoding_euc_kr,
79 mbfl_no_encoding_wchar,
80 mbfl_filt_conv_common_ctor,
81 mbfl_filt_conv_common_dtor,
82 mbfl_filt_conv_euckr_wchar,
83 mbfl_filt_conv_common_flush
84 };
85
86 const struct mbfl_convert_vtbl vtbl_wchar_euckr = {
87 mbfl_no_encoding_wchar,
88 mbfl_no_encoding_euc_kr,
89 mbfl_filt_conv_common_ctor,
90 mbfl_filt_conv_common_dtor,
91 mbfl_filt_conv_wchar_euckr,
92 mbfl_filt_conv_common_flush
93 };
94
95
96 #define CK(statement) do { if ((statement) < 0) return (-1); } while (0)
97
98 /*
99 * EUC-KR => wchar
100 */
101 int
mbfl_filt_conv_euckr_wchar(int c,mbfl_convert_filter * filter)102 mbfl_filt_conv_euckr_wchar(int c, mbfl_convert_filter *filter)
103 {
104 int c1, w, flag;
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 && c != 0xc9) { /* 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 flag = 0;
124 if (c1 >= 0xa1 && c1 <= 0xc6) {
125 flag = 1;
126 } else if (c1 >= 0xc7 && c1 <= 0xfe && c1 != 0xc9) {
127 flag = 2;
128 }
129 if (flag > 0 && c >= 0xa1 && c <= 0xfe) {
130 if (flag == 1){ /* 1st: 0xa1..0xc6, 2nd: 0x41..0x7a, 0x81..0xfe */
131 w = (c1 - 0xa1)*190 + (c - 0x41);
132 if (w >= 0 && w < uhc2_ucs_table_size) {
133 w = uhc2_ucs_table[w];
134 } else {
135 w = 0;
136 }
137 } else { /* 1st: 0xc7..0xc8,0xca..0xfe, 2nd: 0xa1..0xfe */
138 w = (c1 - 0xc7)*94 + (c - 0xa1);
139 if (w >= 0 && w < uhc3_ucs_table_size) {
140 w = uhc3_ucs_table[w];
141 } else {
142 w = 0;
143 }
144 }
145
146 if (w <= 0) {
147 w = (c1 << 8) | c;
148 w &= MBFL_WCSPLANE_MASK;
149 w |= MBFL_WCSPLANE_KSC5601;
150 }
151 CK((*filter->output_function)(w, filter->data));
152 } else if ((c >= 0 && c < 0x21) || c == 0x7f) { /* CTLs */
153 CK((*filter->output_function)(c, filter->data));
154 } else {
155 w = (c1 << 8) | c;
156 w &= MBFL_WCSGROUP_MASK;
157 w |= MBFL_WCSGROUP_THROUGH;
158 CK((*filter->output_function)(w, filter->data));
159 }
160 break;
161
162 default:
163 filter->status = 0;
164 break;
165 }
166
167 return c;
168 }
169
170 /*
171 * wchar => EUC-KR
172 */
173 int
mbfl_filt_conv_wchar_euckr(int c,mbfl_convert_filter * filter)174 mbfl_filt_conv_wchar_euckr(int c, mbfl_convert_filter *filter)
175 {
176 int c1, c2, s;
177
178 s = 0;
179
180 if (c >= ucs_a1_uhc_table_min && c < ucs_a1_uhc_table_max) {
181 s = ucs_a1_uhc_table[c - ucs_a1_uhc_table_min];
182 } else if (c >= ucs_a2_uhc_table_min && c < ucs_a2_uhc_table_max) {
183 s = ucs_a2_uhc_table[c - ucs_a2_uhc_table_min];
184 } else if (c >= ucs_a3_uhc_table_min && c < ucs_a3_uhc_table_max) {
185 s = ucs_a3_uhc_table[c - ucs_a3_uhc_table_min];
186 } else if (c >= ucs_i_uhc_table_min && c < ucs_i_uhc_table_max) {
187 s = ucs_i_uhc_table[c - ucs_i_uhc_table_min];
188 } else if (c >= ucs_s_uhc_table_min && c < ucs_s_uhc_table_max) {
189 s = ucs_s_uhc_table[c - ucs_s_uhc_table_min];
190 } else if (c >= ucs_r1_uhc_table_min && c < ucs_r1_uhc_table_max) {
191 s = ucs_r1_uhc_table[c - ucs_r1_uhc_table_min];
192 } else if (c >= ucs_r2_uhc_table_min && c < ucs_r2_uhc_table_max) {
193 s = ucs_r2_uhc_table[c - ucs_r2_uhc_table_min];
194 }
195
196 c1 = (s >> 8) & 0xff;
197 c2 = s & 0xff;
198 /* exclude UHC extension area */
199 if (c1 < 0xa1 || c2 < 0xa1){
200 s = c;
201 }
202
203 if (s <= 0) {
204 c1 = c & ~MBFL_WCSPLANE_MASK;
205 if (c1 == MBFL_WCSPLANE_KSC5601) {
206 s = c & MBFL_WCSPLANE_MASK;
207 }
208 if (c == 0) {
209 s = 0;
210 } else if (s <= 0) {
211 s = -1;
212 }
213 }
214 if (s >= 0) {
215 if (s < 0x80) { /* latin */
216 CK((*filter->output_function)(s, filter->data));
217 } else {
218 CK((*filter->output_function)((s >> 8) & 0xff, filter->data));
219 CK((*filter->output_function)(s & 0xff, filter->data));
220 }
221 } else {
222 if (filter->illegal_mode != MBFL_OUTPUTFILTER_ILLEGAL_MODE_NONE) {
223 CK(mbfl_filt_conv_illegal_output(c, filter));
224 }
225 }
226
227 return c;
228 }
229
mbfl_filt_ident_euckr(int c,mbfl_identify_filter * filter)230 static int mbfl_filt_ident_euckr(int c, mbfl_identify_filter *filter)
231 {
232 switch (filter->status) {
233 case 0: /* latin */
234 if (c >= 0 && c < 0x80) { /* ok */
235 ;
236 } else if (c > 0xa0 && c < 0xff) { /* DBCS lead byte */
237 filter->status = 1;
238 } else { /* bad */
239 filter->flag = 1;
240 }
241 break;
242
243 case 1: /* got lead byte */
244 if (c < 0xa1 || c > 0xfe) { /* bad */
245 filter->flag = 1;
246 }
247 filter->status = 0;
248 break;
249
250 default:
251 filter->status = 0;
252 break;
253 }
254
255 return c;
256 }
257