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 /* UHC was introduced by MicroSoft in Windows 95, and is also known as CP949.
31 * It is the same as EUC-KR, but with 8,822 additional characters added to
32 * complete all the characters in the Johab charset. */
33
34 #include "mbfilter.h"
35 #include "mbfilter_uhc.h"
36 #define UNICODE_TABLE_UHC_DEF
37 #include "unicode_table_uhc.h"
38
39 static int mbfl_filt_conv_uhc_wchar_flush(mbfl_convert_filter *filter);
40
41 static const unsigned char mblen_table_uhc[] = { /* 0x81-0xFE */
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 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, 2,
57 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1
58 };
59
60 static const char *mbfl_encoding_uhc_aliases[] = {"CP949", NULL};
61
62 const mbfl_encoding mbfl_encoding_uhc = {
63 mbfl_no_encoding_uhc,
64 "UHC",
65 "UHC",
66 mbfl_encoding_uhc_aliases,
67 mblen_table_uhc,
68 0,
69 &vtbl_uhc_wchar,
70 &vtbl_wchar_uhc
71 };
72
73 const struct mbfl_convert_vtbl vtbl_uhc_wchar = {
74 mbfl_no_encoding_uhc,
75 mbfl_no_encoding_wchar,
76 mbfl_filt_conv_common_ctor,
77 NULL,
78 mbfl_filt_conv_uhc_wchar,
79 mbfl_filt_conv_uhc_wchar_flush,
80 NULL,
81 };
82
83 const struct mbfl_convert_vtbl vtbl_wchar_uhc = {
84 mbfl_no_encoding_wchar,
85 mbfl_no_encoding_uhc,
86 mbfl_filt_conv_common_ctor,
87 NULL,
88 mbfl_filt_conv_wchar_uhc,
89 mbfl_filt_conv_common_flush,
90 NULL,
91 };
92
93 #define CK(statement) do { if ((statement) < 0) return (-1); } while (0)
94
mbfl_filt_conv_uhc_wchar(int c,mbfl_convert_filter * filter)95 int mbfl_filt_conv_uhc_wchar(int c, mbfl_convert_filter *filter)
96 {
97 switch (filter->status) {
98 case 0:
99 if (c >= 0 && c < 0x80) { /* latin */
100 CK((*filter->output_function)(c, filter->data));
101 } else if (c > 0x80 && c < 0xfe && c != 0xc9) { /* dbcs lead byte */
102 filter->status = 1;
103 filter->cache = c;
104 } else {
105 CK((*filter->output_function)(MBFL_BAD_INPUT, filter->data));
106 }
107 break;
108
109 case 1: /* dbcs second byte */
110 filter->status = 0;
111 int c1 = filter->cache, w = 0;
112
113 if (c1 >= 0x81 && c1 <= 0xa0 && c >= 0x41 && c <= 0xfe) {
114 w = (c1 - 0x81)*190 + (c - 0x41);
115 if (w >= 0 && w < uhc1_ucs_table_size) {
116 w = uhc1_ucs_table[w];
117 }
118 } else if (c1 >= 0xa1 && c1 <= 0xc6 && c >= 0x41 && c <= 0xfe) {
119 w = (c1 - 0xa1)*190 + (c - 0x41);
120 if (w >= 0 && w < uhc2_ucs_table_size) {
121 w = uhc2_ucs_table[w];
122 }
123 } else if (c1 >= 0xc7 && c1 < 0xfe && c >= 0xa1 && c <= 0xfe) {
124 w = (c1 - 0xc7)*94 + (c - 0xa1);
125 if (w >= 0 && w < uhc3_ucs_table_size) {
126 w = uhc3_ucs_table[w];
127 }
128 }
129
130 if (w == 0) {
131 w = MBFL_BAD_INPUT;
132 }
133 CK((*filter->output_function)(w, filter->data));
134 break;
135
136 default:
137 filter->status = 0;
138 break;
139 }
140
141 return 0;
142 }
143
mbfl_filt_conv_uhc_wchar_flush(mbfl_convert_filter * filter)144 static int mbfl_filt_conv_uhc_wchar_flush(mbfl_convert_filter *filter)
145 {
146 if (filter->status == 1) {
147 /* 2-byte character was truncated */
148 CK((*filter->output_function)(MBFL_BAD_INPUT, filter->data));
149 }
150
151 if (filter->flush_function) {
152 (*filter->flush_function)(filter->data);
153 }
154
155 return 0;
156 }
157
mbfl_filt_conv_wchar_uhc(int c,mbfl_convert_filter * filter)158 int mbfl_filt_conv_wchar_uhc(int c, mbfl_convert_filter *filter)
159 {
160 int s = 0;
161
162 if (c >= ucs_a1_uhc_table_min && c < ucs_a1_uhc_table_max) {
163 s = ucs_a1_uhc_table[c - ucs_a1_uhc_table_min];
164 } else if (c >= ucs_a2_uhc_table_min && c < ucs_a2_uhc_table_max) {
165 s = ucs_a2_uhc_table[c - ucs_a2_uhc_table_min];
166 } else if (c >= ucs_a3_uhc_table_min && c < ucs_a3_uhc_table_max) {
167 s = ucs_a3_uhc_table[c - ucs_a3_uhc_table_min];
168 } else if (c >= ucs_i_uhc_table_min && c < ucs_i_uhc_table_max) {
169 s = ucs_i_uhc_table[c - ucs_i_uhc_table_min];
170 } else if (c >= ucs_s_uhc_table_min && c < ucs_s_uhc_table_max) {
171 s = ucs_s_uhc_table[c - ucs_s_uhc_table_min];
172 } else if (c >= ucs_r1_uhc_table_min && c < ucs_r1_uhc_table_max) {
173 s = ucs_r1_uhc_table[c - ucs_r1_uhc_table_min];
174 } else if (c >= ucs_r2_uhc_table_min && c < ucs_r2_uhc_table_max) {
175 s = ucs_r2_uhc_table[c - ucs_r2_uhc_table_min];
176 }
177
178 if (s == 0 && c != 0) {
179 s = -1;
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