2
* "streamable kanji code filter and converter"
3
* Copyright (c) 1998-2002 HappySize, Inc. All rights reserved.
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.
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.
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
21
* The author of this file: Rui Hirokawa <hirokawa@php.net>
25
* The source code included in this files was separated from mbfilter_tw.c
26
* by moriyoshi koizumi <moriyoshi@php.net> on 4 dec 2002.
35
#include "mbfilter_big5.h"
37
#include "unicode_table_big5.h"
39
static int mbfl_filt_ident_big5(int c, mbfl_identify_filter *filter);
41
static const unsigned char mblen_table_big5[] = { /* 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
60
static const char *mbfl_encoding_big5_aliases[] = {"CN-BIG5", "BIG-FIVE", "BIGFIVE", "CP950", NULL};
62
const mbfl_encoding mbfl_encoding_big5 = {
63
mbfl_no_encoding_big5,
66
(const char *(*)[])&mbfl_encoding_big5_aliases,
71
const struct mbfl_identify_vtbl vtbl_identify_big5 = {
72
mbfl_no_encoding_big5,
73
mbfl_filt_ident_common_ctor,
74
mbfl_filt_ident_common_dtor,
78
const struct mbfl_convert_vtbl vtbl_big5_wchar = {
79
mbfl_no_encoding_big5,
80
mbfl_no_encoding_wchar,
81
mbfl_filt_conv_common_ctor,
82
mbfl_filt_conv_common_dtor,
83
mbfl_filt_conv_big5_wchar,
84
mbfl_filt_conv_common_flush
87
const struct mbfl_convert_vtbl vtbl_wchar_big5 = {
88
mbfl_no_encoding_wchar,
89
mbfl_no_encoding_big5,
90
mbfl_filt_conv_common_ctor,
91
mbfl_filt_conv_common_dtor,
92
mbfl_filt_conv_wchar_big5,
93
mbfl_filt_conv_common_flush
96
#define CK(statement) do { if ((statement) < 0) return (-1); } while (0)
102
mbfl_filt_conv_big5_wchar(int c, mbfl_convert_filter *filter)
106
switch (filter->status) {
108
if (c >= 0 && c < 0x80) { /* latin */
109
CK((*filter->output_function)(c, filter->data));
110
} else if (c > 0xa0 && c < 0xff) { /* dbcs lead byte */
114
w = c & MBFL_WCSGROUP_MASK;
115
w |= MBFL_WCSGROUP_THROUGH;
116
CK((*filter->output_function)(w, filter->data));
120
case 1: /* dbcs second byte */
123
if ((c > 0x39 && c < 0x7f) | (c > 0xa0 && c < 0xff)) {
125
w = (c1 - 0xa1)*157 + (c - 0x40);
127
w = (c1 - 0xa1)*157 + (c - 0xa1) + 0x3f;
129
if (w >= 0 && w < big5_ucs_table_size) {
130
w = big5_ucs_table[w];
136
w &= MBFL_WCSPLANE_MASK;
137
w |= MBFL_WCSPLANE_BIG5;
139
CK((*filter->output_function)(w, filter->data));
140
} else if ((c >= 0 && c < 0x21) || c == 0x7f) { /* CTLs */
141
CK((*filter->output_function)(c, filter->data));
144
w &= MBFL_WCSGROUP_MASK;
145
w |= MBFL_WCSGROUP_THROUGH;
146
CK((*filter->output_function)(w, filter->data));
162
mbfl_filt_conv_wchar_big5(int c, mbfl_convert_filter *filter)
167
if (c >= ucs_a1_big5_table_min && c < ucs_a1_big5_table_max) {
168
s = ucs_a1_big5_table[c - ucs_a1_big5_table_min];
169
} else if (c >= ucs_a2_big5_table_min && c < ucs_a2_big5_table_max) {
170
s = ucs_a2_big5_table[c - ucs_a2_big5_table_min];
171
} else if (c >= ucs_a3_big5_table_min && c < ucs_a3_big5_table_max) {
172
s = ucs_a3_big5_table[c - ucs_a3_big5_table_min];
173
} else if (c >= ucs_i_big5_table_min && c < ucs_i_big5_table_max) {
174
s = ucs_i_big5_table[c - ucs_i_big5_table_min];
175
} else if (c >= ucs_pua_big5_table_min && c < ucs_pua_big5_table_max) {
176
s = ucs_pua_big5_table[c - ucs_pua_big5_table_min];
177
} else if (c >= ucs_r1_big5_table_min && c < ucs_r1_big5_table_max) {
178
s = ucs_r1_big5_table[c - ucs_r1_big5_table_min];
179
} else if (c >= ucs_r2_big5_table_min && c < ucs_r2_big5_table_max) {
180
s = ucs_r2_big5_table[c - ucs_r2_big5_table_min];
183
c1 = c & ~MBFL_WCSPLANE_MASK;
184
if (c1 == MBFL_WCSPLANE_BIG5) {
185
s = c & MBFL_WCSPLANE_MASK;
194
if (s < 0x80) { /* latin */
195
CK((*filter->output_function)(s, filter->data));
197
CK((*filter->output_function)((s >> 8) & 0xff, filter->data));
198
CK((*filter->output_function)(s & 0xff, filter->data));
201
if (filter->illegal_mode != MBFL_OUTPUTFILTER_ILLEGAL_MODE_NONE) {
202
CK(mbfl_filt_conv_illegal_output(c, filter));
209
static int mbfl_filt_ident_big5(int c, mbfl_identify_filter *filter)
211
if (filter->status) { /* kanji second char */
212
if (c < 0x40 || (c > 0x7e && c < 0xa1) ||c > 0xfe) { /* bad */
216
} else if (c >= 0 && c < 0x80) { /* latin ok */
218
} else if (c > 0xa0 && c < 0xff) { /* DBCS lead byte */