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: Den V. Tsopa <tdv@edisoft.ru>
22  *
23  */
24 /*
25  * The source code included in this files was separated from mbfilter_ru.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_cp1251.h"
36 #include "unicode_table_cp1251.h"
37 
38 static int mbfl_filt_ident_cp1251(int c, mbfl_identify_filter *filter);
39 
40 static const char *mbfl_encoding_cp1251_aliases[] = {"CP1251", "CP-1251", "WINDOWS-1251", NULL};
41 
42 const mbfl_encoding mbfl_encoding_cp1251 = {
43 	mbfl_no_encoding_cp1251,
44 	"Windows-1251",
45 	"Windows-1251",
46 	(const char *(*)[])&mbfl_encoding_cp1251_aliases,
47 	NULL,
48 	MBFL_ENCTYPE_SBCS
49 };
50 
51 const struct mbfl_identify_vtbl vtbl_identify_cp1251 = {
52 	mbfl_no_encoding_cp1251,
53 	mbfl_filt_ident_common_ctor,
54 	mbfl_filt_ident_common_dtor,
55 	mbfl_filt_ident_cp1251
56 };
57 
58 const struct mbfl_convert_vtbl vtbl_wchar_cp1251 = {
59 	mbfl_no_encoding_wchar,
60 	mbfl_no_encoding_cp1251,
61 	mbfl_filt_conv_common_ctor,
62 	mbfl_filt_conv_common_dtor,
63 	mbfl_filt_conv_wchar_cp1251,
64 	mbfl_filt_conv_common_flush
65 };
66 
67 const struct mbfl_convert_vtbl vtbl_cp1251_wchar = {
68 	mbfl_no_encoding_cp1251,
69 	mbfl_no_encoding_wchar,
70 	mbfl_filt_conv_common_ctor,
71 	mbfl_filt_conv_common_dtor,
72 	mbfl_filt_conv_cp1251_wchar,
73 	mbfl_filt_conv_common_flush
74 };
75 
76 #define CK(statement)	do { if ((statement) < 0) return (-1); } while (0)
77 
78 /*
79  * cp1251 => wchar
80  */
81 int
mbfl_filt_conv_cp1251_wchar(int c,mbfl_convert_filter * filter)82 mbfl_filt_conv_cp1251_wchar(int c, mbfl_convert_filter *filter)
83 {
84 	int s;
85 
86 	if (c >= 0 && c < cp1251_ucs_table_min) {
87 		s = c;
88 	} else if (c >= cp1251_ucs_table_min && c < 0x100) {
89 		s = cp1251_ucs_table[c - cp1251_ucs_table_min];
90 		if (s <= 0) {
91 			s = c;
92 			s &= MBFL_WCSPLANE_MASK;
93 			s |= MBFL_WCSPLANE_CP1251;
94 		}
95 	} else {
96 		s = c;
97 		s &= MBFL_WCSGROUP_MASK;
98 		s |= MBFL_WCSGROUP_THROUGH;
99 	}
100 
101 	CK((*filter->output_function)(s, filter->data));
102 
103 	return c;
104 }
105 
106 /*
107  * wchar => cp1251
108  */
109 int
mbfl_filt_conv_wchar_cp1251(int c,mbfl_convert_filter * filter)110 mbfl_filt_conv_wchar_cp1251(int c, mbfl_convert_filter *filter)
111 {
112 	int s, n;
113 
114 	if (c < 0x80) {
115 		s = c;
116 	} else {
117 		s = -1;
118 		n = cp1251_ucs_table_len-1;
119 		while (n >= 0) {
120 			if (c == cp1251_ucs_table[n]) {
121 				s = cp1251_ucs_table_min + n;
122 				break;
123 			}
124 			n--;
125 		}
126 		if (s <= 0 && (c & ~MBFL_WCSPLANE_MASK) == MBFL_WCSPLANE_CP1251) {
127 			s = c & MBFL_WCSPLANE_MASK;
128 		}
129 	}
130 
131 	if (s >= 0) {
132 		CK((*filter->output_function)(s, filter->data));
133 	} else {
134 		if (filter->illegal_mode != MBFL_OUTPUTFILTER_ILLEGAL_MODE_NONE) {
135 			CK(mbfl_filt_conv_illegal_output(c, filter));
136 		}
137 	}
138 
139 	return c;
140 }
141 
142 /* all of this is so ugly now! */
mbfl_filt_ident_cp1251(int c,mbfl_identify_filter * filter)143 static int mbfl_filt_ident_cp1251(int c, mbfl_identify_filter *filter)
144 {
145 	if (c >= 0x80 && c < 0xff)
146 		filter->flag = 0;
147 	else
148 		filter->flag = 1; /* not it */
149 	return c;
150 }
151 
152 
153