/src/libcreg/libuna/libuna_codepage_windows_1251.c
Line  | Count  | Source (jump to first uncovered line)  | 
1  |  | /*  | 
2  |  |  * Windows 1251 codepage (Cyrillic) 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_1251.h"  | 
26  |  | #include "libuna_libcerror.h"  | 
27  |  | #include "libuna_types.h"  | 
28  |  |  | 
29  |  | /* Extended ASCII to Unicode character lookup table for the Windows 1251 codepage  | 
30  |  |  * Unknown are filled with the Unicode replacement character 0xfffd  | 
31  |  |  */  | 
32  |  | const uint16_t libuna_codepage_windows_1251_byte_stream_to_unicode_base_0x80[ 128 ] = { | 
33  |  |   0x0402, 0x0403, 0x201a, 0x0453, 0x201e, 0x2026, 0x2020, 0x2021,  | 
34  |  |   0x20ac, 0x2030, 0x0409, 0x2039, 0x040a, 0x040c, 0x040b, 0x040f,  | 
35  |  |   0x0452, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014,  | 
36  |  |   0xfffd, 0x2122, 0x0459, 0x203a, 0x045a, 0x045c, 0x045b, 0x045f,  | 
37  |  |   0x00a0, 0x040e, 0x045e, 0x0408, 0x00a4, 0x0490, 0x00a6, 0x00a7,  | 
38  |  |   0x0401, 0x00a9, 0x0404, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x0407,  | 
39  |  |   0x00b0, 0x00b1, 0x0406, 0x0456, 0x0491, 0x00b5, 0x00b6, 0x00b7,  | 
40  |  |   0x0451, 0x2116, 0x0454, 0x00bb, 0x0458, 0x0405, 0x0455, 0x0457,  | 
41  |  |   0x0410, 0x0411, 0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417,  | 
42  |  |   0x0418, 0x0419, 0x041a, 0x041b, 0x041c, 0x041d, 0x041e, 0x041f,  | 
43  |  |   0x0420, 0x0421, 0x0422, 0x0423, 0x0424, 0x0425, 0x0426, 0x0427,  | 
44  |  |   0x0428, 0x0429, 0x042a, 0x042b, 0x042c, 0x042d, 0x042e, 0x042f,  | 
45  |  |   0x0430, 0x0431, 0x0432, 0x0433, 0x0434, 0x0435, 0x0436, 0x0437,  | 
46  |  |   0x0438, 0x0439, 0x043a, 0x043b, 0x043c, 0x043d, 0x043e, 0x043f,  | 
47  |  |   0x0440, 0x0441, 0x0442, 0x0443, 0x0444, 0x0445, 0x0446, 0x0447,  | 
48  |  |   0x0448, 0x0449, 0x044a, 0x044b, 0x044c, 0x044d, 0x044e, 0x044f  | 
49  |  | };  | 
50  |  |  | 
51  |  | /* Unicode to ASCII character lookup tables for the Windows 1251 codepage  | 
52  |  |  * Unknown are filled with the ASCII replacement character 0x1a  | 
53  |  |  */  | 
54  |  | const uint8_t libuna_codepage_windows_1251_unicode_to_byte_stream_base_0x00a0[ 32 ] = { | 
55  |  |   0xa0, 0x1a, 0x1a, 0x1a, 0xa4, 0x1a, 0xa6, 0xa7,  | 
56  |  |   0x1a, 0xa9, 0x1a, 0xab, 0xac, 0xad, 0xae, 0x1a,  | 
57  |  |   0xb0, 0xb1, 0x1a, 0x1a, 0x1a, 0xb5, 0xb6, 0xb7,  | 
58  |  |   0x1a, 0x1a, 0x1a, 0xbb, 0x1a, 0x1a, 0x1a, 0x1a  | 
59  |  | };  | 
60  |  |  | 
61  |  | const uint8_t libuna_codepage_windows_1251_unicode_to_byte_stream_base_0x0400[ 96 ] = { | 
62  |  |   0x1a, 0xa8, 0x80, 0x81, 0xaa, 0xbd, 0xb2, 0xaf,  | 
63  |  |   0xa3, 0x8a, 0x8c, 0x8e, 0x8d, 0x1a, 0xa1, 0x8f,  | 
64  |  |   0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7,  | 
65  |  |   0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf,  | 
66  |  |   0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7,  | 
67  |  |   0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf,  | 
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, 0xfb, 0xfc, 0xfd, 0xfe, 0xff,  | 
72  |  |   0x1a, 0xb8, 0x90, 0x83, 0xba, 0xbe, 0xb3, 0xbf,  | 
73  |  |   0xbc, 0x9a, 0x9c, 0x9e, 0x9d, 0x1a, 0xa2, 0x9f  | 
74  |  | };  | 
75  |  |  | 
76  |  | const uint8_t libuna_codepage_windows_1251_unicode_to_byte_stream_base_0x2010[ 24 ] = { | 
77  |  |   0x1a, 0x1a, 0x1a, 0x96, 0x97, 0x1a, 0x1a, 0x1a,  | 
78  |  |   0x91, 0x92, 0x82, 0x1a, 0x93, 0x94, 0x84, 0x1a,  | 
79  |  |   0x86, 0x87, 0x95, 0x1a, 0x1a, 0x1a, 0x85, 0x1a  | 
80  |  | };  | 
81  |  |  | 
82  |  | /* Copies an Unicode character from a Windows 1251 encoded byte stream  | 
83  |  |  * Returns 1 if successful or -1 on error  | 
84  |  |  */  | 
85  |  | int libuna_codepage_windows_1251_copy_from_byte_stream(  | 
86  |  |      libuna_unicode_character_t *unicode_character,  | 
87  |  |      const uint8_t *byte_stream,  | 
88  |  |      size_t byte_stream_size,  | 
89  |  |      size_t *byte_stream_index,  | 
90  |  |      libcerror_error_t **error )  | 
91  | 0  | { | 
92  | 0  |   static char *function                             = "libuna_codepage_windows_1251_copy_from_byte_stream";  | 
93  | 0  |   libuna_unicode_character_t safe_unicode_character = 0xfffd;  | 
94  | 0  |   size_t safe_byte_stream_index                     = 0;  | 
95  | 0  |   uint8_t byte_stream_character                     = 0;  | 
96  |  | 
  | 
97  | 0  |   if( unicode_character == NULL )  | 
98  | 0  |   { | 
99  | 0  |     libcerror_error_set(  | 
100  | 0  |      error,  | 
101  | 0  |      LIBCERROR_ERROR_DOMAIN_ARGUMENTS,  | 
102  | 0  |      LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE,  | 
103  | 0  |      "%s: invalid Unicode character.",  | 
104  | 0  |      function );  | 
105  |  | 
  | 
106  | 0  |     return( -1 );  | 
107  | 0  |   }  | 
108  | 0  |   if( byte_stream == NULL )  | 
109  | 0  |   { | 
110  | 0  |     libcerror_error_set(  | 
111  | 0  |      error,  | 
112  | 0  |      LIBCERROR_ERROR_DOMAIN_ARGUMENTS,  | 
113  | 0  |      LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE,  | 
114  | 0  |      "%s: invalid byte stream.",  | 
115  | 0  |      function );  | 
116  |  | 
  | 
117  | 0  |     return( -1 );  | 
118  | 0  |   }  | 
119  | 0  |   if( byte_stream_size > (size_t) SSIZE_MAX )  | 
120  | 0  |   { | 
121  | 0  |     libcerror_error_set(  | 
122  | 0  |      error,  | 
123  | 0  |      LIBCERROR_ERROR_DOMAIN_ARGUMENTS,  | 
124  | 0  |      LIBCERROR_ARGUMENT_ERROR_VALUE_EXCEEDS_MAXIMUM,  | 
125  | 0  |      "%s: invalid byte stream size value exceeds maximum.",  | 
126  | 0  |      function );  | 
127  |  | 
  | 
128  | 0  |     return( -1 );  | 
129  | 0  |   }  | 
130  | 0  |   if( byte_stream_index == NULL )  | 
131  | 0  |   { | 
132  | 0  |     libcerror_error_set(  | 
133  | 0  |      error,  | 
134  | 0  |      LIBCERROR_ERROR_DOMAIN_ARGUMENTS,  | 
135  | 0  |      LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE,  | 
136  | 0  |      "%s: invalid byte stream index.",  | 
137  | 0  |      function );  | 
138  |  | 
  | 
139  | 0  |     return( -1 );  | 
140  | 0  |   }  | 
141  | 0  |   safe_byte_stream_index = *byte_stream_index;  | 
142  |  | 
  | 
143  | 0  |   if( safe_byte_stream_index >= byte_stream_size )  | 
144  | 0  |   { | 
145  | 0  |     libcerror_error_set(  | 
146  | 0  |      error,  | 
147  | 0  |      LIBCERROR_ERROR_DOMAIN_ARGUMENTS,  | 
148  | 0  |      LIBCERROR_ARGUMENT_ERROR_VALUE_TOO_SMALL,  | 
149  | 0  |      "%s: byte stream too small.",  | 
150  | 0  |      function );  | 
151  |  | 
  | 
152  | 0  |     return( -1 );  | 
153  | 0  |   }  | 
154  | 0  |   byte_stream_character = byte_stream[ safe_byte_stream_index++ ];  | 
155  |  | 
  | 
156  | 0  |   if( byte_stream_character < 0x80 )  | 
157  | 0  |   { | 
158  | 0  |     safe_unicode_character = byte_stream_character;  | 
159  | 0  |   }  | 
160  | 0  |   else  | 
161  | 0  |   { | 
162  | 0  |     byte_stream_character -= 0x80;  | 
163  |  | 
  | 
164  | 0  |     safe_unicode_character = libuna_codepage_windows_1251_byte_stream_to_unicode_base_0x80[ byte_stream_character ];  | 
165  | 0  |   }  | 
166  | 0  |   *unicode_character = safe_unicode_character;  | 
167  | 0  |   *byte_stream_index = safe_byte_stream_index;  | 
168  |  | 
  | 
169  | 0  |   return( 1 );  | 
170  | 0  | }  | 
171  |  |  | 
172  |  | /* Copies an Unicode character to a Windows 1251 encoded byte stream  | 
173  |  |  * Returns 1 if successful or -1 on error  | 
174  |  |  */  | 
175  |  | int libuna_codepage_windows_1251_copy_to_byte_stream(  | 
176  |  |      libuna_unicode_character_t unicode_character,  | 
177  |  |      uint8_t *byte_stream,  | 
178  |  |      size_t byte_stream_size,  | 
179  |  |      size_t *byte_stream_index,  | 
180  |  |      libcerror_error_t **error )  | 
181  | 0  | { | 
182  | 0  |   static char *function         = "libuna_codepage_windows_1251_copy_to_byte_stream";  | 
183  | 0  |   size_t safe_byte_stream_index = 0;  | 
184  | 0  |   uint16_t byte_stream_value    = 0x001a;  | 
185  |  | 
  | 
186  | 0  |   if( byte_stream == NULL )  | 
187  | 0  |   { | 
188  | 0  |     libcerror_error_set(  | 
189  | 0  |      error,  | 
190  | 0  |      LIBCERROR_ERROR_DOMAIN_ARGUMENTS,  | 
191  | 0  |      LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE,  | 
192  | 0  |      "%s: invalid byte stream.",  | 
193  | 0  |      function );  | 
194  |  | 
  | 
195  | 0  |     return( -1 );  | 
196  | 0  |   }  | 
197  | 0  |   if( byte_stream_size > (size_t) SSIZE_MAX )  | 
198  | 0  |   { | 
199  | 0  |     libcerror_error_set(  | 
200  | 0  |      error,  | 
201  | 0  |      LIBCERROR_ERROR_DOMAIN_ARGUMENTS,  | 
202  | 0  |      LIBCERROR_ARGUMENT_ERROR_VALUE_EXCEEDS_MAXIMUM,  | 
203  | 0  |      "%s: invalid byte stream size value exceeds maximum.",  | 
204  | 0  |      function );  | 
205  |  | 
  | 
206  | 0  |     return( -1 );  | 
207  | 0  |   }  | 
208  | 0  |   if( byte_stream_index == NULL )  | 
209  | 0  |   { | 
210  | 0  |     libcerror_error_set(  | 
211  | 0  |      error,  | 
212  | 0  |      LIBCERROR_ERROR_DOMAIN_ARGUMENTS,  | 
213  | 0  |      LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE,  | 
214  | 0  |      "%s: invalid byte stream index.",  | 
215  | 0  |      function );  | 
216  |  | 
  | 
217  | 0  |     return( -1 );  | 
218  | 0  |   }  | 
219  | 0  |   safe_byte_stream_index = *byte_stream_index;  | 
220  |  | 
  | 
221  | 0  |   if( safe_byte_stream_index >= byte_stream_size )  | 
222  | 0  |   { | 
223  | 0  |     libcerror_error_set(  | 
224  | 0  |      error,  | 
225  | 0  |      LIBCERROR_ERROR_DOMAIN_ARGUMENTS,  | 
226  | 0  |      LIBCERROR_ARGUMENT_ERROR_VALUE_TOO_SMALL,  | 
227  | 0  |      "%s: byte stream too small.",  | 
228  | 0  |      function );  | 
229  |  | 
  | 
230  | 0  |     return( -1 );  | 
231  | 0  |   }  | 
232  | 0  |   if( unicode_character < 0x0080 )  | 
233  | 0  |   { | 
234  | 0  |     byte_stream_value = (uint16_t) unicode_character;  | 
235  | 0  |   }  | 
236  | 0  |   else if( ( unicode_character >= 0x00a0 )  | 
237  | 0  |         && ( unicode_character < 0x00c0 ) )  | 
238  | 0  |   { | 
239  | 0  |     unicode_character -= 0x00a0;  | 
240  |  | 
  | 
241  | 0  |     byte_stream_value = libuna_codepage_windows_1251_unicode_to_byte_stream_base_0x00a0[ unicode_character ];  | 
242  | 0  |   }  | 
243  | 0  |   else if( ( unicode_character >= 0x0400 )  | 
244  | 0  |         && ( unicode_character < 0x0460 ) )  | 
245  | 0  |   { | 
246  | 0  |     unicode_character -= 0x0400;  | 
247  |  | 
  | 
248  | 0  |     byte_stream_value = libuna_codepage_windows_1251_unicode_to_byte_stream_base_0x0400[ unicode_character ];  | 
249  | 0  |   }  | 
250  | 0  |   else if( ( unicode_character >= 0x2010 )  | 
251  | 0  |         && ( unicode_character < 0x2028 ) )  | 
252  | 0  |   { | 
253  | 0  |     unicode_character -= 0x2010;  | 
254  |  | 
  | 
255  | 0  |     byte_stream_value = libuna_codepage_windows_1251_unicode_to_byte_stream_base_0x2010[ unicode_character ];  | 
256  | 0  |   }  | 
257  | 0  |   else switch( unicode_character )  | 
258  | 0  |   { | 
259  | 0  |     case 0x0490:  | 
260  | 0  |       byte_stream_value = 0xa5;  | 
261  | 0  |       break;  | 
262  |  |  | 
263  | 0  |     case 0x0491:  | 
264  | 0  |       byte_stream_value = 0xb4;  | 
265  | 0  |       break;  | 
266  |  |  | 
267  | 0  |     case 0x2030:  | 
268  | 0  |       byte_stream_value = 0x89;  | 
269  | 0  |       break;  | 
270  |  |  | 
271  | 0  |     case 0x2039:  | 
272  | 0  |       byte_stream_value = 0x8b;  | 
273  | 0  |       break;  | 
274  |  |  | 
275  | 0  |     case 0x203a:  | 
276  | 0  |       byte_stream_value = 0x9b;  | 
277  | 0  |       break;  | 
278  |  |  | 
279  | 0  |     case 0x20ac:  | 
280  | 0  |       byte_stream_value = 0x88;  | 
281  | 0  |       break;  | 
282  |  |  | 
283  | 0  |     case 0x2116:  | 
284  | 0  |       byte_stream_value = 0xb9;  | 
285  | 0  |       break;  | 
286  |  |  | 
287  | 0  |     case 0x2122:  | 
288  | 0  |       byte_stream_value = 0x99;  | 
289  | 0  |       break;  | 
290  |  |  | 
291  | 0  |     default:  | 
292  | 0  |       byte_stream_value = 0x1a;  | 
293  | 0  |       break;  | 
294  | 0  |   }  | 
295  | 0  |   byte_stream[ safe_byte_stream_index++ ] = (uint8_t) ( byte_stream_value & 0x00ff );  | 
296  |  | 
  | 
297  | 0  |   *byte_stream_index = safe_byte_stream_index;  | 
298  |  | 
  | 
299  | 0  |   return( 1 );  | 
300  | 0  | }  | 
301  |  |  |