/src/libfvde/libuna/libuna_codepage_windows_1255.c
Line | Count | Source (jump to first uncovered line) |
1 | | /* |
2 | | * Windows 1255 codepage (Hebrew) functions |
3 | | * |
4 | | * Copyright (C) 2008-2024, Joachim Metz <joachim.metz@gmail.com> |
5 | | * |
6 | | * Refer to AUTHORS for acknowledgements. |
7 | | * |
8 | | * This program is free software: you can redistribute it and/or modify |
9 | | * it under the terms of the GNU Lesser General Public License as published by |
10 | | * the Free Software Foundation, either version 3 of the License, or |
11 | | * (at your option) any later version. |
12 | | * |
13 | | * This program is distributed in the hope that it will be useful, |
14 | | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
15 | | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
16 | | * GNU General Public License for more details. |
17 | | * |
18 | | * You should have received a copy of the GNU Lesser General Public License |
19 | | * along with this program. If not, see <https://www.gnu.org/licenses/>. |
20 | | */ |
21 | | |
22 | | #include <common.h> |
23 | | #include <types.h> |
24 | | |
25 | | #include "libuna_codepage_windows_1255.h" |
26 | | #include "libuna_libcerror.h" |
27 | | #include "libuna_types.h" |
28 | | |
29 | | /* Extended ASCII to Unicode character lookup table for the Windows 1255 codepage |
30 | | * Unknown are filled with the Unicode replacement character 0xfffd |
31 | | */ |
32 | | const uint16_t libuna_codepage_windows_1255_byte_stream_to_unicode_base_0x80[ 128 ] = { |
33 | | 0x20ac, 0xfffd, 0x201a, 0x0192, 0x201e, 0x2026, 0x2020, 0x2021, |
34 | | 0x02c6, 0x2030, 0xfffd, 0x2039, 0xfffd, 0xfffd, 0xfffd, 0xfffd, |
35 | | 0xfffd, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014, |
36 | | 0x02dc, 0x2122, 0xfffd, 0x203a, 0xfffd, 0xfffd, 0xfffd, 0xfffd, |
37 | | 0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x20aa, 0x00a5, 0x00a6, 0x00a7, |
38 | | 0x00a8, 0x00a9, 0x00d7, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af, |
39 | | 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7, |
40 | | 0x00b8, 0x00b9, 0x00f7, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf, |
41 | | 0x05b0, 0x05b1, 0x05b2, 0x05b3, 0x05b4, 0x05b5, 0x05b6, 0x05b7, |
42 | | 0x05b8, 0x05b9, 0xfffd, 0x05bb, 0x05bc, 0x05bd, 0x05be, 0x05bf, |
43 | | 0x05c0, 0x05c1, 0x05c2, 0x05c3, 0x05f0, 0x05f1, 0x05f2, 0x05f3, |
44 | | 0x05f4, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd, |
45 | | 0x05d0, 0x05d1, 0x05d2, 0x05d3, 0x05d4, 0x05d5, 0x05d6, 0x05d7, |
46 | | 0x05d8, 0x05d9, 0x05da, 0x05db, 0x05dc, 0x05dd, 0x05de, 0x05df, |
47 | | 0x05e0, 0x05e1, 0x05e2, 0x05e3, 0x05e4, 0x05e5, 0x05e6, 0x05e7, |
48 | | 0x05e8, 0x05e9, 0x05ea, 0xfffd, 0xfffd, 0x200e, 0x200f, 0xfffd |
49 | | }; |
50 | | |
51 | | /* Unicode to ASCII character lookup tables for the Windows 1255 codepage |
52 | | * Unknown are filled with the ASCII replacement character 0x1a |
53 | | */ |
54 | | const uint8_t libuna_codepage_windows_1255_unicode_to_byte_stream_base_0x00a0[ 32 ] = { |
55 | | 0xa0, 0xa1, 0xa2, 0xa3, 0x1a, 0xa5, 0xa6, 0xa7, |
56 | | 0xa8, 0xa9, 0x1a, 0xab, 0xac, 0xad, 0xae, 0xaf, |
57 | | 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, |
58 | | 0xb8, 0xb9, 0x1a, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf |
59 | | }; |
60 | | |
61 | | const uint8_t libuna_codepage_windows_1255_unicode_to_byte_stream_base_0x05b0[ 24 ] = { |
62 | | 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, |
63 | | 0xc8, 0xc9, 0x1a, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, |
64 | | 0xd0, 0xd1, 0xd2, 0xd3, 0x1a, 0x1a, 0x1a, 0x1a |
65 | | }; |
66 | | |
67 | | const uint8_t libuna_codepage_windows_1255_unicode_to_byte_stream_base_0x05d0[ 40 ] = { |
68 | | 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, |
69 | | 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, |
70 | | 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, |
71 | | 0xf8, 0xf9, 0xfa, 0x1a, 0x1a, 0x1a, 0x1a, 0x1a, |
72 | | 0xd4, 0xd5, 0xd6, 0xd7, 0xd8, 0x1a, 0x1a, 0x1a |
73 | | }; |
74 | | |
75 | | const uint8_t libuna_codepage_windows_1255_unicode_to_byte_stream_base_0x2010[ 24 ] = { |
76 | | 0x1a, 0x1a, 0x1a, 0x96, 0x97, 0x1a, 0x1a, 0x1a, |
77 | | 0x91, 0x92, 0x82, 0x1a, 0x93, 0x94, 0x84, 0x1a, |
78 | | 0x86, 0x87, 0x95, 0x1a, 0x1a, 0x1a, 0x85, 0x1a |
79 | | }; |
80 | | |
81 | | /* Copies an Unicode character from a Windows 1255 encoded byte stream |
82 | | * Returns 1 if successful or -1 on error |
83 | | */ |
84 | | int libuna_codepage_windows_1255_copy_from_byte_stream( |
85 | | libuna_unicode_character_t *unicode_character, |
86 | | const uint8_t *byte_stream, |
87 | | size_t byte_stream_size, |
88 | | size_t *byte_stream_index, |
89 | | libcerror_error_t **error ) |
90 | 0 | { |
91 | 0 | static char *function = "libuna_codepage_windows_1255_copy_from_byte_stream"; |
92 | 0 | libuna_unicode_character_t safe_unicode_character = 0xfffd; |
93 | 0 | size_t safe_byte_stream_index = 0; |
94 | 0 | uint8_t byte_stream_character = 0; |
95 | |
|
96 | 0 | if( unicode_character == NULL ) |
97 | 0 | { |
98 | 0 | libcerror_error_set( |
99 | 0 | error, |
100 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
101 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
102 | 0 | "%s: invalid Unicode character.", |
103 | 0 | function ); |
104 | |
|
105 | 0 | return( -1 ); |
106 | 0 | } |
107 | 0 | if( byte_stream == NULL ) |
108 | 0 | { |
109 | 0 | libcerror_error_set( |
110 | 0 | error, |
111 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
112 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
113 | 0 | "%s: invalid byte stream.", |
114 | 0 | function ); |
115 | |
|
116 | 0 | return( -1 ); |
117 | 0 | } |
118 | 0 | if( byte_stream_size > (size_t) SSIZE_MAX ) |
119 | 0 | { |
120 | 0 | libcerror_error_set( |
121 | 0 | error, |
122 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
123 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_EXCEEDS_MAXIMUM, |
124 | 0 | "%s: invalid byte stream size value exceeds maximum.", |
125 | 0 | function ); |
126 | |
|
127 | 0 | return( -1 ); |
128 | 0 | } |
129 | 0 | if( byte_stream_index == NULL ) |
130 | 0 | { |
131 | 0 | libcerror_error_set( |
132 | 0 | error, |
133 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
134 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
135 | 0 | "%s: invalid byte stream index.", |
136 | 0 | function ); |
137 | |
|
138 | 0 | return( -1 ); |
139 | 0 | } |
140 | 0 | safe_byte_stream_index = *byte_stream_index; |
141 | |
|
142 | 0 | if( safe_byte_stream_index >= byte_stream_size ) |
143 | 0 | { |
144 | 0 | libcerror_error_set( |
145 | 0 | error, |
146 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
147 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_TOO_SMALL, |
148 | 0 | "%s: byte stream too small.", |
149 | 0 | function ); |
150 | |
|
151 | 0 | return( -1 ); |
152 | 0 | } |
153 | 0 | byte_stream_character = byte_stream[ safe_byte_stream_index++ ]; |
154 | |
|
155 | 0 | if( byte_stream_character < 0x80 ) |
156 | 0 | { |
157 | 0 | safe_unicode_character = byte_stream_character; |
158 | 0 | } |
159 | 0 | else |
160 | 0 | { |
161 | 0 | byte_stream_character -= 0x80; |
162 | |
|
163 | 0 | safe_unicode_character = libuna_codepage_windows_1255_byte_stream_to_unicode_base_0x80[ byte_stream_character ]; |
164 | 0 | } |
165 | 0 | *unicode_character = safe_unicode_character; |
166 | 0 | *byte_stream_index = safe_byte_stream_index; |
167 | |
|
168 | 0 | return( 1 ); |
169 | 0 | } |
170 | | |
171 | | /* Copies an Unicode character to a Windows 1255 encoded byte stream |
172 | | * Returns 1 if successful or -1 on error |
173 | | */ |
174 | | int libuna_codepage_windows_1255_copy_to_byte_stream( |
175 | | libuna_unicode_character_t unicode_character, |
176 | | uint8_t *byte_stream, |
177 | | size_t byte_stream_size, |
178 | | size_t *byte_stream_index, |
179 | | libcerror_error_t **error ) |
180 | 0 | { |
181 | 0 | static char *function = "libuna_codepage_windows_1255_copy_to_byte_stream"; |
182 | 0 | size_t safe_byte_stream_index = 0; |
183 | 0 | uint16_t byte_stream_value = 0x001a; |
184 | |
|
185 | 0 | if( byte_stream == NULL ) |
186 | 0 | { |
187 | 0 | libcerror_error_set( |
188 | 0 | error, |
189 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
190 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
191 | 0 | "%s: invalid byte stream.", |
192 | 0 | function ); |
193 | |
|
194 | 0 | return( -1 ); |
195 | 0 | } |
196 | 0 | if( byte_stream_size > (size_t) SSIZE_MAX ) |
197 | 0 | { |
198 | 0 | libcerror_error_set( |
199 | 0 | error, |
200 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
201 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_EXCEEDS_MAXIMUM, |
202 | 0 | "%s: invalid byte stream size value exceeds maximum.", |
203 | 0 | function ); |
204 | |
|
205 | 0 | return( -1 ); |
206 | 0 | } |
207 | 0 | if( byte_stream_index == NULL ) |
208 | 0 | { |
209 | 0 | libcerror_error_set( |
210 | 0 | error, |
211 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
212 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
213 | 0 | "%s: invalid byte stream index.", |
214 | 0 | function ); |
215 | |
|
216 | 0 | return( -1 ); |
217 | 0 | } |
218 | 0 | safe_byte_stream_index = *byte_stream_index; |
219 | |
|
220 | 0 | if( safe_byte_stream_index >= byte_stream_size ) |
221 | 0 | { |
222 | 0 | libcerror_error_set( |
223 | 0 | error, |
224 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
225 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_TOO_SMALL, |
226 | 0 | "%s: byte stream too small.", |
227 | 0 | function ); |
228 | |
|
229 | 0 | return( -1 ); |
230 | 0 | } |
231 | 0 | if( unicode_character < 0x0080 ) |
232 | 0 | { |
233 | 0 | byte_stream_value = (uint16_t) unicode_character; |
234 | 0 | } |
235 | 0 | else if( ( unicode_character >= 0x00a0 ) |
236 | 0 | && ( unicode_character < 0x00c0 ) ) |
237 | 0 | { |
238 | 0 | unicode_character -= 0x00a0; |
239 | |
|
240 | 0 | byte_stream_value = libuna_codepage_windows_1255_unicode_to_byte_stream_base_0x00a0[ unicode_character ]; |
241 | 0 | } |
242 | 0 | else if( ( unicode_character >= 0x05b0 ) |
243 | 0 | && ( unicode_character < 0x05c8 ) ) |
244 | 0 | { |
245 | 0 | unicode_character -= 0x05b0; |
246 | |
|
247 | 0 | byte_stream_value = libuna_codepage_windows_1255_unicode_to_byte_stream_base_0x05b0[ unicode_character ]; |
248 | 0 | } |
249 | 0 | else if( ( unicode_character >= 0x05d0 ) |
250 | 0 | && ( unicode_character < 0x05f8 ) ) |
251 | 0 | { |
252 | 0 | unicode_character -= 0x05d0; |
253 | |
|
254 | 0 | byte_stream_value = libuna_codepage_windows_1255_unicode_to_byte_stream_base_0x05d0[ unicode_character ]; |
255 | 0 | } |
256 | 0 | else if( ( unicode_character >= 0x2010 ) |
257 | 0 | && ( unicode_character < 0x2028 ) ) |
258 | 0 | { |
259 | 0 | unicode_character -= 0x2010; |
260 | |
|
261 | 0 | byte_stream_value = libuna_codepage_windows_1255_unicode_to_byte_stream_base_0x2010[ unicode_character ]; |
262 | 0 | } |
263 | 0 | else switch( unicode_character ) |
264 | 0 | { |
265 | 0 | case 0x00d7: |
266 | 0 | byte_stream_value = 0xaa; |
267 | 0 | break; |
268 | | |
269 | 0 | case 0x00f7: |
270 | 0 | byte_stream_value = 0xba; |
271 | 0 | break; |
272 | | |
273 | 0 | case 0x0192: |
274 | 0 | byte_stream_value = 0x83; |
275 | 0 | break; |
276 | | |
277 | 0 | case 0x02c6: |
278 | 0 | byte_stream_value = 0x88; |
279 | 0 | break; |
280 | | |
281 | 0 | case 0x02dc: |
282 | 0 | byte_stream_value = 0x98; |
283 | 0 | break; |
284 | | |
285 | 0 | case 0x200e: |
286 | 0 | byte_stream_value = 0xfd; |
287 | 0 | break; |
288 | | |
289 | 0 | case 0x200f: |
290 | 0 | byte_stream_value = 0xfe; |
291 | 0 | break; |
292 | | |
293 | 0 | case 0x2030: |
294 | 0 | byte_stream_value = 0x89; |
295 | 0 | break; |
296 | | |
297 | 0 | case 0x2039: |
298 | 0 | byte_stream_value = 0x8b; |
299 | 0 | break; |
300 | | |
301 | 0 | case 0x203a: |
302 | 0 | byte_stream_value = 0x9b; |
303 | 0 | break; |
304 | | |
305 | 0 | case 0x20aa: |
306 | 0 | byte_stream_value = 0xa4; |
307 | 0 | break; |
308 | | |
309 | 0 | case 0x20ac: |
310 | 0 | byte_stream_value = 0x80; |
311 | 0 | break; |
312 | | |
313 | 0 | case 0x2122: |
314 | 0 | byte_stream_value = 0x99; |
315 | 0 | break; |
316 | | |
317 | 0 | default: |
318 | 0 | byte_stream_value = 0x1a; |
319 | 0 | break; |
320 | 0 | } |
321 | 0 | byte_stream[ safe_byte_stream_index++ ] = (uint8_t) ( byte_stream_value & 0x00ff ); |
322 | |
|
323 | 0 | *byte_stream_index = safe_byte_stream_index; |
324 | |
|
325 | 0 | return( 1 ); |
326 | 0 | } |
327 | | |
328 | | |