/src/libphdi/libuna/libuna_codepage_windows_1252.c
Line | Count | Source (jump to first uncovered line) |
1 | | /* |
2 | | * Windows 1252 codepage (Western European/Latin 1) 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_1252.h" |
26 | | #include "libuna_libcerror.h" |
27 | | #include "libuna_types.h" |
28 | | |
29 | | /* Extended ASCII to Unicode character lookup table for the Windows 1252 codepage |
30 | | * Unknown are filled with the Unicode replacement character 0xfffd |
31 | | */ |
32 | | const uint16_t libuna_codepage_windows_1252_byte_stream_to_unicode_base_0x80[ 32 ] = { |
33 | | 0x20ac, 0xfffd, 0x201a, 0x0192, 0x201e, 0x2026, 0x2020, 0x2021, |
34 | | 0x02c6, 0x2030, 0x0160, 0x2039, 0x0152, 0xfffd, 0x017d, 0xfffd, |
35 | | 0xfffd, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014, |
36 | | 0x02dc, 0x2122, 0x0161, 0x203a, 0x0153, 0xfffd, 0x017e, 0x0178 |
37 | | }; |
38 | | |
39 | | /* Unicode to ASCII character lookup tables for the Windows 1252 codepage |
40 | | * Unknown are filled with the ASCII replacement character 0x1a |
41 | | */ |
42 | | const uint8_t libuna_codepage_windows_1252_unicode_to_byte_stream_base_0x2010[ 24 ] = { |
43 | | 0x1a, 0x1a, 0x1a, 0x96, 0x97, 0x1a, 0x1a, 0x1a, |
44 | | 0x91, 0x92, 0x82, 0x1a, 0x93, 0x94, 0x84, 0x1a, |
45 | | 0x86, 0x87, 0x95, 0x1a, 0x1a, 0x1a, 0x85, 0x1a |
46 | | }; |
47 | | |
48 | | /* Copies an Unicode character from a Windows 1252 encoded byte stream |
49 | | * Returns 1 if successful or -1 on error |
50 | | */ |
51 | | int libuna_codepage_windows_1252_copy_from_byte_stream( |
52 | | libuna_unicode_character_t *unicode_character, |
53 | | const uint8_t *byte_stream, |
54 | | size_t byte_stream_size, |
55 | | size_t *byte_stream_index, |
56 | | libcerror_error_t **error ) |
57 | 90.1k | { |
58 | 90.1k | static char *function = "libuna_codepage_windows_1252_copy_from_byte_stream"; |
59 | 90.1k | libuna_unicode_character_t safe_unicode_character = 0xfffd; |
60 | 90.1k | size_t safe_byte_stream_index = 0; |
61 | 90.1k | uint8_t byte_stream_character = 0; |
62 | | |
63 | 90.1k | if( unicode_character == NULL ) |
64 | 0 | { |
65 | 0 | libcerror_error_set( |
66 | 0 | error, |
67 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
68 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
69 | 0 | "%s: invalid Unicode character.", |
70 | 0 | function ); |
71 | |
|
72 | 0 | return( -1 ); |
73 | 0 | } |
74 | 90.1k | if( byte_stream == NULL ) |
75 | 0 | { |
76 | 0 | libcerror_error_set( |
77 | 0 | error, |
78 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
79 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
80 | 0 | "%s: invalid byte stream.", |
81 | 0 | function ); |
82 | |
|
83 | 0 | return( -1 ); |
84 | 0 | } |
85 | 90.1k | if( byte_stream_size > (size_t) SSIZE_MAX ) |
86 | 0 | { |
87 | 0 | libcerror_error_set( |
88 | 0 | error, |
89 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
90 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_EXCEEDS_MAXIMUM, |
91 | 0 | "%s: invalid byte stream size value exceeds maximum.", |
92 | 0 | function ); |
93 | |
|
94 | 0 | return( -1 ); |
95 | 0 | } |
96 | 90.1k | if( byte_stream_index == 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 byte stream index.", |
103 | 0 | function ); |
104 | |
|
105 | 0 | return( -1 ); |
106 | 0 | } |
107 | 90.1k | safe_byte_stream_index = *byte_stream_index; |
108 | | |
109 | 90.1k | if( safe_byte_stream_index >= byte_stream_size ) |
110 | 0 | { |
111 | 0 | libcerror_error_set( |
112 | 0 | error, |
113 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
114 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_TOO_SMALL, |
115 | 0 | "%s: byte stream too small.", |
116 | 0 | function ); |
117 | |
|
118 | 0 | return( -1 ); |
119 | 0 | } |
120 | 90.1k | byte_stream_character = byte_stream[ safe_byte_stream_index++ ]; |
121 | | |
122 | 90.1k | if( ( byte_stream_character < 0x80 ) |
123 | 90.1k | || ( byte_stream_character >= 0xa0 ) ) |
124 | 86.6k | { |
125 | 86.6k | safe_unicode_character = byte_stream_character; |
126 | 86.6k | } |
127 | 3.48k | else |
128 | 3.48k | { |
129 | 3.48k | byte_stream_character -= 0x80; |
130 | | |
131 | 3.48k | safe_unicode_character = libuna_codepage_windows_1252_byte_stream_to_unicode_base_0x80[ byte_stream_character ]; |
132 | 3.48k | } |
133 | 90.1k | *unicode_character = safe_unicode_character; |
134 | 90.1k | *byte_stream_index = safe_byte_stream_index; |
135 | | |
136 | 90.1k | return( 1 ); |
137 | 90.1k | } |
138 | | |
139 | | /* Copies an Unicode character to a Windows 1252 encoded byte stream |
140 | | * Returns 1 if successful or -1 on error |
141 | | */ |
142 | | int libuna_codepage_windows_1252_copy_to_byte_stream( |
143 | | libuna_unicode_character_t unicode_character, |
144 | | uint8_t *byte_stream, |
145 | | size_t byte_stream_size, |
146 | | size_t *byte_stream_index, |
147 | | libcerror_error_t **error ) |
148 | 0 | { |
149 | 0 | static char *function = "libuna_codepage_windows_1252_copy_to_byte_stream"; |
150 | 0 | size_t safe_byte_stream_index = 0; |
151 | 0 | uint16_t byte_stream_value = 0x001a; |
152 | |
|
153 | 0 | if( byte_stream == NULL ) |
154 | 0 | { |
155 | 0 | libcerror_error_set( |
156 | 0 | error, |
157 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
158 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
159 | 0 | "%s: invalid byte stream.", |
160 | 0 | function ); |
161 | |
|
162 | 0 | return( -1 ); |
163 | 0 | } |
164 | 0 | if( byte_stream_size > (size_t) SSIZE_MAX ) |
165 | 0 | { |
166 | 0 | libcerror_error_set( |
167 | 0 | error, |
168 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
169 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_EXCEEDS_MAXIMUM, |
170 | 0 | "%s: invalid byte stream size value exceeds maximum.", |
171 | 0 | function ); |
172 | |
|
173 | 0 | return( -1 ); |
174 | 0 | } |
175 | 0 | if( byte_stream_index == NULL ) |
176 | 0 | { |
177 | 0 | libcerror_error_set( |
178 | 0 | error, |
179 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
180 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
181 | 0 | "%s: invalid byte stream index.", |
182 | 0 | function ); |
183 | |
|
184 | 0 | return( -1 ); |
185 | 0 | } |
186 | 0 | safe_byte_stream_index = *byte_stream_index; |
187 | |
|
188 | 0 | if( safe_byte_stream_index >= byte_stream_size ) |
189 | 0 | { |
190 | 0 | libcerror_error_set( |
191 | 0 | error, |
192 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
193 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_TOO_SMALL, |
194 | 0 | "%s: byte stream too small.", |
195 | 0 | function ); |
196 | |
|
197 | 0 | return( -1 ); |
198 | 0 | } |
199 | 0 | if( unicode_character < 0x0080 ) |
200 | 0 | { |
201 | 0 | byte_stream_value = (uint16_t) unicode_character; |
202 | 0 | } |
203 | 0 | else if( ( unicode_character >= 0x00a0 ) |
204 | 0 | && ( unicode_character < 0x0100 ) ) |
205 | 0 | { |
206 | 0 | byte_stream_value = (uint16_t) unicode_character; |
207 | 0 | } |
208 | 0 | else if( ( unicode_character >= 0x2010 ) |
209 | 0 | && ( unicode_character < 0x2028 ) ) |
210 | 0 | { |
211 | 0 | unicode_character -= 0x2010; |
212 | |
|
213 | 0 | byte_stream_value = libuna_codepage_windows_1252_unicode_to_byte_stream_base_0x2010[ unicode_character ]; |
214 | 0 | } |
215 | 0 | else switch( unicode_character ) |
216 | 0 | { |
217 | 0 | case 0x0152: |
218 | 0 | byte_stream_value = 0x8c; |
219 | 0 | break; |
220 | | |
221 | 0 | case 0x0153: |
222 | 0 | byte_stream_value = 0x9c; |
223 | 0 | break; |
224 | | |
225 | 0 | case 0x0160: |
226 | 0 | byte_stream_value = 0x8a; |
227 | 0 | break; |
228 | | |
229 | 0 | case 0x0161: |
230 | 0 | byte_stream_value = 0x9a; |
231 | 0 | break; |
232 | | |
233 | 0 | case 0x0178: |
234 | 0 | byte_stream_value = 0x9f; |
235 | 0 | break; |
236 | | |
237 | 0 | case 0x017d: |
238 | 0 | byte_stream_value = 0x8e; |
239 | 0 | break; |
240 | | |
241 | 0 | case 0x017e: |
242 | 0 | byte_stream_value = 0x9e; |
243 | 0 | break; |
244 | | |
245 | 0 | case 0x0192: |
246 | 0 | byte_stream_value = 0x83; |
247 | 0 | break; |
248 | | |
249 | 0 | case 0x02c6: |
250 | 0 | byte_stream_value = 0x88; |
251 | 0 | break; |
252 | | |
253 | 0 | case 0x02dc: |
254 | 0 | byte_stream_value = 0x98; |
255 | 0 | break; |
256 | | |
257 | 0 | case 0x2030: |
258 | 0 | byte_stream_value = 0x89; |
259 | 0 | break; |
260 | | |
261 | 0 | case 0x2039: |
262 | 0 | byte_stream_value = 0x8b; |
263 | 0 | break; |
264 | | |
265 | 0 | case 0x203a: |
266 | 0 | byte_stream_value = 0x9b; |
267 | 0 | break; |
268 | | |
269 | 0 | case 0x20ac: |
270 | 0 | byte_stream_value = 0x80; |
271 | 0 | break; |
272 | | |
273 | 0 | case 0x2122: |
274 | 0 | byte_stream_value = 0x99; |
275 | 0 | break; |
276 | | |
277 | 0 | default: |
278 | 0 | byte_stream_value = 0x1a; |
279 | 0 | break; |
280 | 0 | } |
281 | 0 | byte_stream[ safe_byte_stream_index++ ] = (uint8_t) ( byte_stream_value & 0x00ff ); |
282 | |
|
283 | 0 | *byte_stream_index = safe_byte_stream_index; |
284 | |
|
285 | 0 | return( 1 ); |
286 | 0 | } |
287 | | |