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.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_ucs4.h"
36 
37 static const char *mbfl_encoding_ucs4_aliases[] = {"ISO-10646-UCS-4", "UCS4", NULL};
38 
39 const mbfl_encoding mbfl_encoding_ucs4 = {
40 	mbfl_no_encoding_ucs4,
41 	"UCS-4",
42 	"UCS-4",
43 	(const char *(*)[])&mbfl_encoding_ucs4_aliases,
44 	NULL,
45 	MBFL_ENCTYPE_WCS4BE,
46 	&vtbl_ucs4_wchar,
47 	&vtbl_wchar_ucs4
48 };
49 
50 const mbfl_encoding mbfl_encoding_ucs4be = {
51 	mbfl_no_encoding_ucs4be,
52 	"UCS-4BE",
53 	"UCS-4BE",
54 	NULL,
55 	NULL,
56 	MBFL_ENCTYPE_WCS4BE,
57 	&vtbl_ucs4be_wchar,
58 	&vtbl_wchar_ucs4be
59 };
60 
61 const mbfl_encoding mbfl_encoding_ucs4le = {
62 	mbfl_no_encoding_ucs4le,
63 	"UCS-4LE",
64 	"UCS-4LE",
65 	NULL,
66 	NULL,
67 	MBFL_ENCTYPE_WCS4LE,
68 	&vtbl_ucs4le_wchar,
69 	&vtbl_wchar_ucs4le
70 };
71 
72 const struct mbfl_convert_vtbl vtbl_ucs4_wchar = {
73 	mbfl_no_encoding_ucs4,
74 	mbfl_no_encoding_wchar,
75 	mbfl_filt_conv_common_ctor,
76 	mbfl_filt_conv_common_dtor,
77 	mbfl_filt_conv_ucs4_wchar,
78 	mbfl_filt_conv_common_flush
79 };
80 
81 const struct mbfl_convert_vtbl vtbl_wchar_ucs4 = {
82 	mbfl_no_encoding_wchar,
83 	mbfl_no_encoding_ucs4,
84 	mbfl_filt_conv_common_ctor,
85 	mbfl_filt_conv_common_dtor,
86 	mbfl_filt_conv_wchar_ucs4be,
87 	mbfl_filt_conv_common_flush
88 };
89 
90 const struct mbfl_convert_vtbl vtbl_ucs4be_wchar = {
91 	mbfl_no_encoding_ucs4be,
92 	mbfl_no_encoding_wchar,
93 	mbfl_filt_conv_common_ctor,
94 	mbfl_filt_conv_common_dtor,
95 	mbfl_filt_conv_ucs4be_wchar,
96 	mbfl_filt_conv_common_flush
97 };
98 
99 const struct mbfl_convert_vtbl vtbl_wchar_ucs4be = {
100 	mbfl_no_encoding_wchar,
101 	mbfl_no_encoding_ucs4be,
102 	mbfl_filt_conv_common_ctor,
103 	mbfl_filt_conv_common_dtor,
104 	mbfl_filt_conv_wchar_ucs4be,
105 	mbfl_filt_conv_common_flush
106 };
107 
108 const struct mbfl_convert_vtbl vtbl_ucs4le_wchar = {
109 	mbfl_no_encoding_ucs4le,
110 	mbfl_no_encoding_wchar,
111 	mbfl_filt_conv_common_ctor,
112 	mbfl_filt_conv_common_dtor,
113 	mbfl_filt_conv_ucs4le_wchar,
114 	mbfl_filt_conv_common_flush
115 };
116 
117 const struct mbfl_convert_vtbl vtbl_wchar_ucs4le = {
118 	mbfl_no_encoding_wchar,
119 	mbfl_no_encoding_ucs4le,
120 	mbfl_filt_conv_common_ctor,
121 	mbfl_filt_conv_common_dtor,
122 	mbfl_filt_conv_wchar_ucs4le,
123 	mbfl_filt_conv_common_flush
124 };
125 
126 
127 #define CK(statement)	do { if ((statement) < 0) return (-1); } while (0)
128 
129 /*
130  * UCS-4 => wchar
131  */
mbfl_filt_conv_ucs4_wchar(int c,mbfl_convert_filter * filter)132 int mbfl_filt_conv_ucs4_wchar(int c, mbfl_convert_filter *filter)
133 {
134 	int n, endian;
135 
136 	endian = filter->status & 0xff00;
137 	switch (filter->status & 0xff) {
138 	case 0:
139 		if (endian) {
140 			n = c & 0xff;
141 		} else {
142 			n = (c & 0xff) << 24;
143 		}
144 		filter->cache = n;
145 		filter->status++;
146 		break;
147 	case 1:
148 		if (endian) {
149 			n = (c & 0xff) << 8;
150 		} else {
151 			n = (c & 0xff) << 16;
152 		}
153 		filter->cache |= n;
154 		filter->status++;
155 		break;
156 	case 2:
157 		if (endian) {
158 			n = (c & 0xff) << 16;
159 		} else {
160 			n = (c & 0xff) << 8;
161 		}
162 		filter->cache |= n;
163 		filter->status++;
164 		break;
165 	default:
166 		if (endian) {
167 			n = (c & 0xff) << 24;
168 		} else {
169 			n = c & 0xff;
170 		}
171 		n |= filter->cache;
172 		if ((n & 0xffff) == 0 && ((n >> 16) & 0xffff) == 0xfffe) {
173 			if (endian) {
174 				filter->status = 0;		/* big-endian */
175 			} else {
176 				filter->status = 0x100;		/* little-endian */
177 			}
178 			CK((*filter->output_function)(0xfeff, filter->data));
179 		} else {
180 			filter->status &= ~0xff;
181 			CK((*filter->output_function)(n, filter->data));
182 		}
183 		break;
184 	}
185 
186 	return c;
187 }
188 
189 /*
190  * UCS-4BE => wchar
191  */
mbfl_filt_conv_ucs4be_wchar(int c,mbfl_convert_filter * filter)192 int mbfl_filt_conv_ucs4be_wchar(int c, mbfl_convert_filter *filter)
193 {
194 	int n;
195 
196 	if (filter->status == 0) {
197 		filter->status = 1;
198 		n = (c & 0xff) << 24;
199 		filter->cache = n;
200 	} else if (filter->status == 1) {
201 		filter->status = 2;
202 		n = (c & 0xff) << 16;
203 		filter->cache |= n;
204 	} else if (filter->status == 2) {
205 		filter->status = 3;
206 		n = (c & 0xff) << 8;
207 		filter->cache |= n;
208 	} else {
209 		filter->status = 0;
210 		n = (c & 0xff) | filter->cache;
211 		CK((*filter->output_function)(n, filter->data));
212 	}
213 	return c;
214 }
215 
216 /*
217  * wchar => UCS-4BE
218  */
mbfl_filt_conv_wchar_ucs4be(int c,mbfl_convert_filter * filter)219 int mbfl_filt_conv_wchar_ucs4be(int c, mbfl_convert_filter *filter)
220 {
221 	if (c >= 0 && c < MBFL_WCSGROUP_UCS4MAX) {
222 		CK((*filter->output_function)((c >> 24) & 0xff, filter->data));
223 		CK((*filter->output_function)((c >> 16) & 0xff, filter->data));
224 		CK((*filter->output_function)((c >> 8) & 0xff, filter->data));
225 		CK((*filter->output_function)(c & 0xff, filter->data));
226 	} else {
227 		if (filter->illegal_mode != MBFL_OUTPUTFILTER_ILLEGAL_MODE_NONE) {
228 			CK(mbfl_filt_conv_illegal_output(c, filter));
229 		}
230 	}
231 
232 	return c;
233 }
234 
235 /*
236  * UCS-4LE => wchar
237  */
mbfl_filt_conv_ucs4le_wchar(int c,mbfl_convert_filter * filter)238 int mbfl_filt_conv_ucs4le_wchar(int c, mbfl_convert_filter *filter)
239 {
240 	int n;
241 
242 	if (filter->status == 0) {
243 		filter->status = 1;
244 		n = (c & 0xff);
245 		filter->cache = n;
246 	} else if (filter->status == 1) {
247 		filter->status = 2;
248 		n = (c & 0xff) << 8;
249 		filter->cache |= n;
250 	} else if (filter->status == 2) {
251 		filter->status = 3;
252 		n = (c & 0xff) << 16;
253 		filter->cache |= n;
254 	} else {
255 		filter->status = 0;
256 		n = ((c & 0xff) << 24) | filter->cache;
257 		CK((*filter->output_function)(n, filter->data));
258 	}
259 	return c;
260 }
261 
262 /*
263  * wchar => UCS-4LE
264  */
mbfl_filt_conv_wchar_ucs4le(int c,mbfl_convert_filter * filter)265 int mbfl_filt_conv_wchar_ucs4le(int c, mbfl_convert_filter *filter)
266 {
267 	if (c >= 0 && c < MBFL_WCSGROUP_UCS4MAX) {
268 		CK((*filter->output_function)(c & 0xff, filter->data));
269 		CK((*filter->output_function)((c >> 8) & 0xff, filter->data));
270 		CK((*filter->output_function)((c >> 16) & 0xff, filter->data));
271 		CK((*filter->output_function)((c >> 24) & 0xff, filter->data));
272 	} else {
273 		if (filter->illegal_mode != MBFL_OUTPUTFILTER_ILLEGAL_MODE_NONE) {
274 			CK(mbfl_filt_conv_illegal_output(c, filter));
275 		}
276 	}
277 
278 	return c;
279 }
280