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 #include "mbfilter.h"
31 #include "mbfilter_euc_kr.h"
32 #include "unicode_table_uhc.h"
33
34 static int mbfl_filt_conv_euckr_wchar_flush(mbfl_convert_filter *filter);
35
36 static const unsigned char mblen_table_euckr[] = { /* 0xA1-0xFE */
37 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
38 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
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, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
48 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
49 2, 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, 1
53 };
54
55 static const char *mbfl_encoding_euc_kr_aliases[] = {"EUC_KR", "eucKR", "x-euc-kr", NULL};
56
57 const mbfl_encoding mbfl_encoding_euc_kr = {
58 mbfl_no_encoding_euc_kr,
59 "EUC-KR",
60 "EUC-KR",
61 mbfl_encoding_euc_kr_aliases,
62 mblen_table_euckr,
63 0,
64 &vtbl_euckr_wchar,
65 &vtbl_wchar_euckr
66 };
67
68 const struct mbfl_convert_vtbl vtbl_euckr_wchar = {
69 mbfl_no_encoding_euc_kr,
70 mbfl_no_encoding_wchar,
71 mbfl_filt_conv_common_ctor,
72 NULL,
73 mbfl_filt_conv_euckr_wchar,
74 mbfl_filt_conv_euckr_wchar_flush,
75 NULL,
76 };
77
78 const struct mbfl_convert_vtbl vtbl_wchar_euckr = {
79 mbfl_no_encoding_wchar,
80 mbfl_no_encoding_euc_kr,
81 mbfl_filt_conv_common_ctor,
82 NULL,
83 mbfl_filt_conv_wchar_euckr,
84 mbfl_filt_conv_common_flush,
85 NULL,
86 };
87
88 #define CK(statement) do { if ((statement) < 0) return (-1); } while (0)
89
mbfl_filt_conv_euckr_wchar(int c,mbfl_convert_filter * filter)90 int mbfl_filt_conv_euckr_wchar(int c, mbfl_convert_filter *filter)
91 {
92 int c1, w, flag;
93
94 switch (filter->status) {
95 case 0:
96 if (c >= 0 && c < 0x80) { /* latin */
97 CK((*filter->output_function)(c, filter->data));
98 } else if (((c >= 0xA1 && c <= 0xAC) || (c >= 0xB0 && c <= 0xFD)) && c != 0xC9) { /* dbcs lead byte */
99 filter->status = 1;
100 filter->cache = c;
101 } else {
102 CK((*filter->output_function)(MBFL_BAD_INPUT, filter->data));
103 }
104 break;
105
106 case 1: /* dbcs second byte */
107 filter->status = 0;
108 c1 = filter->cache;
109 flag = 0;
110 if (c1 >= 0xa1 && c1 <= 0xc6) {
111 flag = 1;
112 } else if (c1 >= 0xc7 && c1 <= 0xfe && c1 != 0xc9) {
113 flag = 2;
114 }
115 if (flag > 0 && c >= 0xa1 && c <= 0xfe) {
116 if (flag == 1) { /* 1st: 0xa1..0xc6, 2nd: 0x41..0x7a, 0x81..0xfe */
117 w = (c1 - 0xa1)*190 + (c - 0x41);
118 if (w >= 0 && w < uhc2_ucs_table_size) {
119 w = uhc2_ucs_table[w];
120 } else {
121 w = 0;
122 }
123 } else { /* 1st: 0xc7..0xc8,0xca..0xfe, 2nd: 0xa1..0xfe */
124 w = (c1 - 0xc7)*94 + (c - 0xa1);
125 if (w >= 0 && w < uhc3_ucs_table_size) {
126 w = uhc3_ucs_table[w];
127 } else {
128 w = 0;
129 }
130 }
131
132 if (w <= 0) {
133 w = MBFL_BAD_INPUT;
134 }
135 CK((*filter->output_function)(w, filter->data));
136 } else {
137 CK((*filter->output_function)(MBFL_BAD_INPUT, filter->data));
138 }
139 break;
140
141 default:
142 filter->status = 0;
143 break;
144 }
145
146 return 0;
147 }
148
mbfl_filt_conv_wchar_euckr(int c,mbfl_convert_filter * filter)149 int mbfl_filt_conv_wchar_euckr(int c, mbfl_convert_filter *filter)
150 {
151 int s = 0;
152
153 if (c >= ucs_a1_uhc_table_min && c < ucs_a1_uhc_table_max) {
154 s = ucs_a1_uhc_table[c - ucs_a1_uhc_table_min];
155 } else if (c >= ucs_a2_uhc_table_min && c < ucs_a2_uhc_table_max) {
156 s = ucs_a2_uhc_table[c - ucs_a2_uhc_table_min];
157 } else if (c >= ucs_a3_uhc_table_min && c < ucs_a3_uhc_table_max) {
158 s = ucs_a3_uhc_table[c - ucs_a3_uhc_table_min];
159 } else if (c >= ucs_i_uhc_table_min && c < ucs_i_uhc_table_max) {
160 s = ucs_i_uhc_table[c - ucs_i_uhc_table_min];
161 } else if (c >= ucs_s_uhc_table_min && c < ucs_s_uhc_table_max) {
162 s = ucs_s_uhc_table[c - ucs_s_uhc_table_min];
163 } else if (c >= ucs_r1_uhc_table_min && c < ucs_r1_uhc_table_max) {
164 s = ucs_r1_uhc_table[c - ucs_r1_uhc_table_min];
165 } else if (c >= ucs_r2_uhc_table_min && c < ucs_r2_uhc_table_max) {
166 s = ucs_r2_uhc_table[c - ucs_r2_uhc_table_min];
167 }
168
169 /* exclude UHC extension area (although we are using the UHC conversion tables) */
170 if (((s >> 8) & 0xFF) < 0xA1 || (s & 0xFF) < 0xA1) {
171 s = 0;
172 }
173
174 if (s <= 0) {
175 if (c < 0x80) {
176 s = c;
177 } else {
178 s = -1;
179 }
180 }
181
182 if (s >= 0) {
183 if (s < 0x80) { /* latin */
184 CK((*filter->output_function)(s, filter->data));
185 } else {
186 CK((*filter->output_function)((s >> 8) & 0xff, filter->data));
187 CK((*filter->output_function)(s & 0xff, filter->data));
188 }
189 } else {
190 CK(mbfl_filt_conv_illegal_output(c, filter));
191 }
192
193 return 0;
194 }
195
mbfl_filt_conv_euckr_wchar_flush(mbfl_convert_filter * filter)196 static int mbfl_filt_conv_euckr_wchar_flush(mbfl_convert_filter *filter)
197 {
198 if (filter->status == 1) {
199 /* 2-byte character was truncated */
200 CK((*filter->output_function)(MBFL_BAD_INPUT, filter->data));
201 }
202
203 if (filter->flush_function) {
204 (*filter->flush_function)(filter->data);
205 }
206
207 return 0;
208 }
209