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 part: Wez Furlong <wez@thebrainroom.com>
22 *
23 */
24 /*
25 * the source code included in this files was separated from mbfilter.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_cp1252.h"
36 #include "unicode_table_cp1252.h"
37
38 static int mbfl_filt_ident_cp1252(int c, mbfl_identify_filter *filter);
39
40 static const char *mbfl_encoding_cp1252_aliases[] = {"cp1252", NULL};
41
42 const mbfl_encoding mbfl_encoding_cp1252 = {
43 mbfl_no_encoding_cp1252,
44 "Windows-1252",
45 "Windows-1252",
46 (const char *(*)[])&mbfl_encoding_cp1252_aliases,
47 NULL,
48 MBFL_ENCTYPE_SBCS,
49 &vtbl_cp1252_wchar,
50 &vtbl_wchar_cp1252
51 };
52
53 const struct mbfl_identify_vtbl vtbl_identify_cp1252 = {
54 mbfl_no_encoding_cp1252,
55 mbfl_filt_ident_common_ctor,
56 mbfl_filt_ident_common_dtor,
57 mbfl_filt_ident_cp1252
58 };
59
60 const struct mbfl_convert_vtbl vtbl_cp1252_wchar = {
61 mbfl_no_encoding_cp1252,
62 mbfl_no_encoding_wchar,
63 mbfl_filt_conv_common_ctor,
64 mbfl_filt_conv_common_dtor,
65 mbfl_filt_conv_cp1252_wchar,
66 mbfl_filt_conv_common_flush
67 };
68
69 const struct mbfl_convert_vtbl vtbl_wchar_cp1252 = {
70 mbfl_no_encoding_wchar,
71 mbfl_no_encoding_cp1252,
72 mbfl_filt_conv_common_ctor,
73 mbfl_filt_conv_common_dtor,
74 mbfl_filt_conv_wchar_cp1252,
75 mbfl_filt_conv_common_flush
76 };
77
78 #define CK(statement) do { if ((statement) < 0) return (-1); } while (0)
79
80 /*
81 * wchar => cp1252
82 */
mbfl_filt_conv_wchar_cp1252(int c,mbfl_convert_filter * filter)83 int mbfl_filt_conv_wchar_cp1252(int c, mbfl_convert_filter *filter)
84 {
85 int s=-1, n;
86
87 if (c >= 0x100) {
88 /* look it up from the cp1252 table */
89 s = -1;
90 n = 31;
91 while (n >= 0) {
92 if (c == cp1252_ucs_table[n] && c != 0xfffe) {
93 s = 0x80 + n;
94 break;
95 }
96 n--;
97 }
98 if (s <= 0 && (c & ~MBFL_WCSPLANE_MASK) == MBFL_WCSPLANE_8859_1)
99 {
100 s = c & MBFL_WCSPLANE_MASK;
101 }
102 }
103 else if (c >= 0 && c < 0x100) {
104 s = c;
105 }
106 if (s >= 0) {
107 CK((*filter->output_function)(s, filter->data));
108 } else {
109 if (filter->illegal_mode != MBFL_OUTPUTFILTER_ILLEGAL_MODE_NONE) {
110 CK(mbfl_filt_conv_illegal_output(c, filter));
111 }
112 }
113 return c;
114 }
115
116 /*
117 * cp1252 => wchar
118 */
mbfl_filt_conv_cp1252_wchar(int c,mbfl_convert_filter * filter)119 int mbfl_filt_conv_cp1252_wchar(int c, mbfl_convert_filter *filter)
120 {
121 int s;
122
123 if (c >= 0x80 && c < 0xa0) {
124 s = cp1252_ucs_table[c - 0x80];
125 } else {
126 s = c;
127 }
128
129 CK((*filter->output_function)(s, filter->data));
130
131 return c;
132 }
133
134 /* We only distinguish the MS extensions to ISO-8859-1.
135 * Actually, this is pretty much a NO-OP, since the identification
136 * system doesn't allow us to discriminate between a positive match,
137 * a possible match and a definite non-match.
138 * The problem here is that cp1252 looks like SJIS for certain chars.
139 * */
mbfl_filt_ident_cp1252(int c,mbfl_identify_filter * filter)140 static int mbfl_filt_ident_cp1252(int c, mbfl_identify_filter *filter)
141 {
142 if (c >= 0x80 && c < 0xa0)
143 filter->flag = 0;
144 else
145 filter->flag = 1; /* not it */
146 return c;
147 }
148