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 NULL
67 };
68
69 const struct mbfl_convert_vtbl vtbl_euckr_wchar = {
70 mbfl_no_encoding_euc_kr,
71 mbfl_no_encoding_wchar,
72 mbfl_filt_conv_common_ctor,
73 NULL,
74 mbfl_filt_conv_euckr_wchar,
75 mbfl_filt_conv_euckr_wchar_flush,
76 NULL,
77 };
78
79 const struct mbfl_convert_vtbl vtbl_wchar_euckr = {
80 mbfl_no_encoding_wchar,
81 mbfl_no_encoding_euc_kr,
82 mbfl_filt_conv_common_ctor,
83 NULL,
84 mbfl_filt_conv_wchar_euckr,
85 mbfl_filt_conv_common_flush,
86 NULL,
87 };
88
89 #define CK(statement) do { if ((statement) < 0) return (-1); } while (0)
90
mbfl_filt_conv_euckr_wchar(int c,mbfl_convert_filter * filter)91 int mbfl_filt_conv_euckr_wchar(int c, mbfl_convert_filter *filter)
92 {
93 int c1, w, flag;
94
95 switch (filter->status) {
96 case 0:
97 if (c >= 0 && c < 0x80) { /* latin */
98 CK((*filter->output_function)(c, filter->data));
99 } else if (((c >= 0xA1 && c <= 0xAC) || (c >= 0xB0 && c <= 0xFD)) && c != 0xC9) { /* dbcs lead byte */
100 filter->status = 1;
101 filter->cache = c;
102 } else {
103 CK((*filter->output_function)(MBFL_BAD_INPUT, filter->data));
104 }
105 break;
106
107 case 1: /* dbcs second byte */
108 filter->status = 0;
109 c1 = filter->cache;
110 flag = 0;
111 if (c1 >= 0xa1 && c1 <= 0xc6) {
112 flag = 1;
113 } else if (c1 >= 0xc7 && c1 <= 0xfe && c1 != 0xc9) {
114 flag = 2;
115 }
116 if (flag > 0 && c >= 0xa1 && c <= 0xfe) {
117 if (flag == 1) { /* 1st: 0xa1..0xc6, 2nd: 0x41..0x7a, 0x81..0xfe */
118 w = (c1 - 0xa1)*190 + (c - 0x41);
119 if (w >= 0 && w < uhc2_ucs_table_size) {
120 w = uhc2_ucs_table[w];
121 } else {
122 w = 0;
123 }
124 } else { /* 1st: 0xc7..0xc8,0xca..0xfe, 2nd: 0xa1..0xfe */
125 w = (c1 - 0xc7)*94 + (c - 0xa1);
126 if (w >= 0 && w < uhc3_ucs_table_size) {
127 w = uhc3_ucs_table[w];
128 } else {
129 w = 0;
130 }
131 }
132
133 if (w <= 0) {
134 w = MBFL_BAD_INPUT;
135 }
136 CK((*filter->output_function)(w, filter->data));
137 } else {
138 CK((*filter->output_function)(MBFL_BAD_INPUT, filter->data));
139 }
140 break;
141
142 default:
143 filter->status = 0;
144 break;
145 }
146
147 return 0;
148 }
149
mbfl_filt_conv_wchar_euckr(int c,mbfl_convert_filter * filter)150 int mbfl_filt_conv_wchar_euckr(int c, mbfl_convert_filter *filter)
151 {
152 int s = 0;
153
154 if (c >= ucs_a1_uhc_table_min && c < ucs_a1_uhc_table_max) {
155 s = ucs_a1_uhc_table[c - ucs_a1_uhc_table_min];
156 } else if (c >= ucs_a2_uhc_table_min && c < ucs_a2_uhc_table_max) {
157 s = ucs_a2_uhc_table[c - ucs_a2_uhc_table_min];
158 } else if (c >= ucs_a3_uhc_table_min && c < ucs_a3_uhc_table_max) {
159 s = ucs_a3_uhc_table[c - ucs_a3_uhc_table_min];
160 } else if (c >= ucs_i_uhc_table_min && c < ucs_i_uhc_table_max) {
161 s = ucs_i_uhc_table[c - ucs_i_uhc_table_min];
162 } else if (c >= ucs_s_uhc_table_min && c < ucs_s_uhc_table_max) {
163 s = ucs_s_uhc_table[c - ucs_s_uhc_table_min];
164 } else if (c >= ucs_r1_uhc_table_min && c < ucs_r1_uhc_table_max) {
165 s = ucs_r1_uhc_table[c - ucs_r1_uhc_table_min];
166 } else if (c >= ucs_r2_uhc_table_min && c < ucs_r2_uhc_table_max) {
167 s = ucs_r2_uhc_table[c - ucs_r2_uhc_table_min];
168 }
169
170 /* exclude UHC extension area (although we are using the UHC conversion tables) */
171 if (((s >> 8) & 0xFF) < 0xA1 || (s & 0xFF) < 0xA1) {
172 s = 0;
173 }
174
175 if (s <= 0) {
176 if (c < 0x80) {
177 s = c;
178 } else {
179 s = -1;
180 }
181 }
182
183 if (s >= 0) {
184 if (s < 0x80) { /* latin */
185 CK((*filter->output_function)(s, filter->data));
186 } else {
187 CK((*filter->output_function)((s >> 8) & 0xff, filter->data));
188 CK((*filter->output_function)(s & 0xff, filter->data));
189 }
190 } else {
191 CK(mbfl_filt_conv_illegal_output(c, filter));
192 }
193
194 return 0;
195 }
196
mbfl_filt_conv_euckr_wchar_flush(mbfl_convert_filter * filter)197 static int mbfl_filt_conv_euckr_wchar_flush(mbfl_convert_filter *filter)
198 {
199 if (filter->status == 1) {
200 /* 2-byte character was truncated */
201 filter->status = 0;
202 CK((*filter->output_function)(MBFL_BAD_INPUT, filter->data));
203 }
204
205 if (filter->flush_function) {
206 (*filter->flush_function)(filter->data);
207 }
208
209 return 0;
210 }
211