/src/libesedb/libuna/libuna_utf8_stream.c
Line | Count | Source (jump to first uncovered line) |
1 | | /* |
2 | | * UTF-8 stream 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 <memory.h> |
24 | | #include <types.h> |
25 | | |
26 | | #include "libuna_definitions.h" |
27 | | #include "libuna_libcerror.h" |
28 | | #include "libuna_types.h" |
29 | | #include "libuna_unicode_character.h" |
30 | | #include "libuna_utf8_stream.h" |
31 | | |
32 | | /* Copies an UTF-8 stream byte order mark (BOM) |
33 | | * Returns 1 if successful or -1 on error |
34 | | */ |
35 | | int libuna_utf8_stream_copy_byte_order_mark( |
36 | | uint8_t *utf8_stream, |
37 | | size_t utf8_stream_size, |
38 | | size_t *utf8_stream_index, |
39 | | libcerror_error_t **error ) |
40 | 0 | { |
41 | 0 | static char *function = "libuna_utf8_stream_copy_byte_order_mark"; |
42 | |
|
43 | 0 | if( utf8_stream == NULL ) |
44 | 0 | { |
45 | 0 | libcerror_error_set( |
46 | 0 | error, |
47 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
48 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
49 | 0 | "%s: invalid UTF-8 stream.", |
50 | 0 | function ); |
51 | |
|
52 | 0 | return( -1 ); |
53 | 0 | } |
54 | 0 | if( utf8_stream_size > (size_t) SSIZE_MAX ) |
55 | 0 | { |
56 | 0 | libcerror_error_set( |
57 | 0 | error, |
58 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
59 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_EXCEEDS_MAXIMUM, |
60 | 0 | "%s: invalid UTF-8 stream size value exceeds maximum.", |
61 | 0 | function ); |
62 | |
|
63 | 0 | return( -1 ); |
64 | 0 | } |
65 | 0 | if( utf8_stream_index == NULL ) |
66 | 0 | { |
67 | 0 | libcerror_error_set( |
68 | 0 | error, |
69 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
70 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
71 | 0 | "%s: invalid UTF-8 stream index.", |
72 | 0 | function ); |
73 | |
|
74 | 0 | return( -1 ); |
75 | 0 | } |
76 | 0 | if( ( *utf8_stream_index + 3 ) > utf8_stream_size ) |
77 | 0 | { |
78 | 0 | libcerror_error_set( |
79 | 0 | error, |
80 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
81 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_TOO_SMALL, |
82 | 0 | "%s: UTF-8 stream too small.", |
83 | 0 | function ); |
84 | |
|
85 | 0 | return( -1 ); |
86 | 0 | } |
87 | 0 | utf8_stream[ *utf8_stream_index ] = 0xef; |
88 | 0 | utf8_stream[ *utf8_stream_index + 1 ] = 0xbb; |
89 | 0 | utf8_stream[ *utf8_stream_index + 2 ] = 0xbf; |
90 | |
|
91 | 0 | *utf8_stream_index += 3; |
92 | |
|
93 | 0 | return( 1 ); |
94 | 0 | } |
95 | | |
96 | | /* Determines the size of an UTF-8 stream from an UTF-8 string |
97 | | * Returns 1 if successful or -1 on error |
98 | | */ |
99 | | int libuna_utf8_stream_size_from_utf8( |
100 | | const libuna_utf8_character_t *utf8_string, |
101 | | size_t utf8_string_size, |
102 | | size_t *utf8_stream_size, |
103 | | libcerror_error_t **error ) |
104 | 0 | { |
105 | 0 | static char *function = "libuna_utf8_stream_size_from_utf8"; |
106 | 0 | libuna_unicode_character_t unicode_character = 0; |
107 | 0 | size_t utf8_string_index = 0; |
108 | |
|
109 | 0 | if( utf8_string == NULL ) |
110 | 0 | { |
111 | 0 | libcerror_error_set( |
112 | 0 | error, |
113 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
114 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
115 | 0 | "%s: invalid UTF-8 string.", |
116 | 0 | function ); |
117 | |
|
118 | 0 | return( -1 ); |
119 | 0 | } |
120 | 0 | if( utf8_string_size > (size_t) SSIZE_MAX ) |
121 | 0 | { |
122 | 0 | libcerror_error_set( |
123 | 0 | error, |
124 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
125 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_EXCEEDS_MAXIMUM, |
126 | 0 | "%s: invalid UTF-8 string size value exceeds maximum.", |
127 | 0 | function ); |
128 | |
|
129 | 0 | return( -1 ); |
130 | 0 | } |
131 | 0 | if( utf8_stream_size == NULL ) |
132 | 0 | { |
133 | 0 | libcerror_error_set( |
134 | 0 | error, |
135 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
136 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
137 | 0 | "%s: invalid UTF-8 stream size.", |
138 | 0 | function ); |
139 | |
|
140 | 0 | return( -1 ); |
141 | 0 | } |
142 | | /* Add the byte order mark |
143 | | */ |
144 | 0 | *utf8_stream_size = 3; |
145 | |
|
146 | 0 | while( utf8_string_index < utf8_string_size ) |
147 | 0 | { |
148 | | /* Convert the UTF-8 character bytes into an Unicode character |
149 | | */ |
150 | 0 | if( libuna_unicode_character_copy_from_utf8( |
151 | 0 | &unicode_character, |
152 | 0 | utf8_string, |
153 | 0 | utf8_string_size, |
154 | 0 | &utf8_string_index, |
155 | 0 | error ) != 1 ) |
156 | 0 | { |
157 | 0 | libcerror_error_set( |
158 | 0 | error, |
159 | 0 | LIBCERROR_ERROR_DOMAIN_CONVERSION, |
160 | 0 | LIBCERROR_CONVERSION_ERROR_INPUT_FAILED, |
161 | 0 | "%s: unable to copy Unicode character from UTF-8.", |
162 | 0 | function ); |
163 | |
|
164 | 0 | return( -1 ); |
165 | 0 | } |
166 | | /* Determine how many UTF-8 character bytes are required |
167 | | */ |
168 | 0 | if( libuna_unicode_character_size_to_utf8( |
169 | 0 | unicode_character, |
170 | 0 | utf8_stream_size, |
171 | 0 | error ) != 1 ) |
172 | 0 | { |
173 | 0 | libcerror_error_set( |
174 | 0 | error, |
175 | 0 | LIBCERROR_ERROR_DOMAIN_CONVERSION, |
176 | 0 | LIBCERROR_CONVERSION_ERROR_OUTPUT_FAILED, |
177 | 0 | "%s: unable to determine size of Unicode character in UTF-8.", |
178 | 0 | function ); |
179 | |
|
180 | 0 | return( -1 ); |
181 | 0 | } |
182 | 0 | if( unicode_character == 0 ) |
183 | 0 | { |
184 | 0 | break; |
185 | 0 | } |
186 | 0 | } |
187 | 0 | return( 1 ); |
188 | 0 | } |
189 | | |
190 | | /* Copies an UTF-8 stream from an UTF-8 string |
191 | | * Returns 1 if successful or -1 on error |
192 | | */ |
193 | | int libuna_utf8_stream_copy_from_utf8( |
194 | | uint8_t *utf8_stream, |
195 | | size_t utf8_stream_size, |
196 | | const libuna_utf8_character_t *utf8_string, |
197 | | size_t utf8_string_size, |
198 | | libcerror_error_t **error ) |
199 | 0 | { |
200 | 0 | static char *function = "libuna_utf8_stream_copy_from_utf8"; |
201 | 0 | libuna_unicode_character_t unicode_character = 0; |
202 | 0 | size_t utf8_stream_index = 0; |
203 | 0 | size_t utf8_string_index = 0; |
204 | |
|
205 | 0 | if( utf8_stream == NULL ) |
206 | 0 | { |
207 | 0 | libcerror_error_set( |
208 | 0 | error, |
209 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
210 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
211 | 0 | "%s: invalid UTF-8 stream.", |
212 | 0 | function ); |
213 | |
|
214 | 0 | return( -1 ); |
215 | 0 | } |
216 | 0 | if( utf8_stream_size > (size_t) SSIZE_MAX ) |
217 | 0 | { |
218 | 0 | libcerror_error_set( |
219 | 0 | error, |
220 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
221 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_EXCEEDS_MAXIMUM, |
222 | 0 | "%s: invalid UTF-8 stream size value exceeds maximum.", |
223 | 0 | function ); |
224 | |
|
225 | 0 | return( -1 ); |
226 | 0 | } |
227 | 0 | if( utf8_string == NULL ) |
228 | 0 | { |
229 | 0 | libcerror_error_set( |
230 | 0 | error, |
231 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
232 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
233 | 0 | "%s: invalid UTF-8 string.", |
234 | 0 | function ); |
235 | |
|
236 | 0 | return( -1 ); |
237 | 0 | } |
238 | 0 | if( utf8_string_size > (size_t) SSIZE_MAX ) |
239 | 0 | { |
240 | 0 | libcerror_error_set( |
241 | 0 | error, |
242 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
243 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_EXCEEDS_MAXIMUM, |
244 | 0 | "%s: invalid UTF-8 string size value exceeds maximum.", |
245 | 0 | function ); |
246 | |
|
247 | 0 | return( -1 ); |
248 | 0 | } |
249 | 0 | if( utf8_stream_size < utf8_string_size ) |
250 | 0 | { |
251 | 0 | libcerror_error_set( |
252 | 0 | error, |
253 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
254 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_TOO_SMALL, |
255 | 0 | "%s: UTF-8 stream is too small.", |
256 | 0 | function ); |
257 | |
|
258 | 0 | return( -1 ); |
259 | 0 | } |
260 | 0 | if( libuna_utf8_stream_copy_byte_order_mark( |
261 | 0 | utf8_stream, |
262 | 0 | utf8_stream_size, |
263 | 0 | &utf8_stream_index, |
264 | 0 | error ) != 1 ) |
265 | 0 | { |
266 | 0 | libcerror_error_set( |
267 | 0 | error, |
268 | 0 | LIBCERROR_ERROR_DOMAIN_CONVERSION, |
269 | 0 | LIBCERROR_CONVERSION_ERROR_OUTPUT_FAILED, |
270 | 0 | "%s: unable to copy UTF-8 byte order mark.", |
271 | 0 | function ); |
272 | |
|
273 | 0 | return( -1 ); |
274 | 0 | } |
275 | 0 | while( utf8_string_index < utf8_string_size ) |
276 | 0 | { |
277 | | /* Convert the UTF-8 string bytes into an Unicode character |
278 | | */ |
279 | 0 | if( libuna_unicode_character_copy_from_utf8( |
280 | 0 | &unicode_character, |
281 | 0 | utf8_string, |
282 | 0 | utf8_string_size, |
283 | 0 | &utf8_string_index, |
284 | 0 | error ) != 1 ) |
285 | 0 | { |
286 | 0 | libcerror_error_set( |
287 | 0 | error, |
288 | 0 | LIBCERROR_ERROR_DOMAIN_CONVERSION, |
289 | 0 | LIBCERROR_CONVERSION_ERROR_INPUT_FAILED, |
290 | 0 | "%s: unable to copy Unicode character from UTF-8 string.", |
291 | 0 | function ); |
292 | |
|
293 | 0 | return( -1 ); |
294 | 0 | } |
295 | | /* Convert the Unicode character into UTF-8 stream bytes |
296 | | */ |
297 | 0 | if( libuna_unicode_character_copy_to_utf8( |
298 | 0 | unicode_character, |
299 | 0 | utf8_stream, |
300 | 0 | utf8_stream_size, |
301 | 0 | &utf8_stream_index, |
302 | 0 | error ) != 1 ) |
303 | 0 | { |
304 | 0 | libcerror_error_set( |
305 | 0 | error, |
306 | 0 | LIBCERROR_ERROR_DOMAIN_CONVERSION, |
307 | 0 | LIBCERROR_CONVERSION_ERROR_OUTPUT_FAILED, |
308 | 0 | "%s: unable to copy Unicode character to UTF-8 stream.", |
309 | 0 | function ); |
310 | |
|
311 | 0 | return( -1 ); |
312 | 0 | } |
313 | 0 | if( unicode_character == 0 ) |
314 | 0 | { |
315 | 0 | break; |
316 | 0 | } |
317 | 0 | } |
318 | 0 | return( 1 ); |
319 | 0 | } |
320 | | |
321 | | /* Determines the size of an UTF-8 stream from an UTF-16 string |
322 | | * Returns 1 if successful or -1 on error |
323 | | */ |
324 | | int libuna_utf8_stream_size_from_utf16( |
325 | | const libuna_utf16_character_t *utf16_string, |
326 | | size_t utf16_string_size, |
327 | | size_t *utf8_stream_size, |
328 | | libcerror_error_t **error ) |
329 | 0 | { |
330 | 0 | static char *function = "libuna_utf8_stream_size_from_utf16"; |
331 | 0 | libuna_unicode_character_t unicode_character = 0; |
332 | 0 | size_t utf16_string_index = 0; |
333 | |
|
334 | 0 | if( utf16_string == NULL ) |
335 | 0 | { |
336 | 0 | libcerror_error_set( |
337 | 0 | error, |
338 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
339 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
340 | 0 | "%s: invalid UTF-16 string.", |
341 | 0 | function ); |
342 | |
|
343 | 0 | return( -1 ); |
344 | 0 | } |
345 | 0 | if( utf16_string_size > (size_t) SSIZE_MAX ) |
346 | 0 | { |
347 | 0 | libcerror_error_set( |
348 | 0 | error, |
349 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
350 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_EXCEEDS_MAXIMUM, |
351 | 0 | "%s: invalid UTF-16 string size value exceeds maximum.", |
352 | 0 | function ); |
353 | |
|
354 | 0 | return( -1 ); |
355 | 0 | } |
356 | 0 | if( utf8_stream_size == NULL ) |
357 | 0 | { |
358 | 0 | libcerror_error_set( |
359 | 0 | error, |
360 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
361 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
362 | 0 | "%s: invalid UTF-8 stream size.", |
363 | 0 | function ); |
364 | |
|
365 | 0 | return( -1 ); |
366 | 0 | } |
367 | | /* Add the byte order mark |
368 | | */ |
369 | 0 | *utf8_stream_size = 3; |
370 | |
|
371 | 0 | while( utf16_string_index < utf16_string_size ) |
372 | 0 | { |
373 | | /* Convert the UTF-16 character bytes into an Unicode character |
374 | | */ |
375 | 0 | if( libuna_unicode_character_copy_from_utf16( |
376 | 0 | &unicode_character, |
377 | 0 | utf16_string, |
378 | 0 | utf16_string_size, |
379 | 0 | &utf16_string_index, |
380 | 0 | error ) != 1 ) |
381 | 0 | { |
382 | 0 | libcerror_error_set( |
383 | 0 | error, |
384 | 0 | LIBCERROR_ERROR_DOMAIN_CONVERSION, |
385 | 0 | LIBCERROR_CONVERSION_ERROR_INPUT_FAILED, |
386 | 0 | "%s: unable to copy Unicode character from UTF-16.", |
387 | 0 | function ); |
388 | |
|
389 | 0 | return( -1 ); |
390 | 0 | } |
391 | | /* Determine how many UTF-8 character bytes are required |
392 | | */ |
393 | 0 | if( libuna_unicode_character_size_to_utf8( |
394 | 0 | unicode_character, |
395 | 0 | utf8_stream_size, |
396 | 0 | error ) != 1 ) |
397 | 0 | { |
398 | 0 | libcerror_error_set( |
399 | 0 | error, |
400 | 0 | LIBCERROR_ERROR_DOMAIN_CONVERSION, |
401 | 0 | LIBCERROR_CONVERSION_ERROR_OUTPUT_FAILED, |
402 | 0 | "%s: unable to determine size of Unicode character in UTF-8.", |
403 | 0 | function ); |
404 | |
|
405 | 0 | return( -1 ); |
406 | 0 | } |
407 | 0 | if( unicode_character == 0 ) |
408 | 0 | { |
409 | 0 | break; |
410 | 0 | } |
411 | 0 | } |
412 | 0 | return( 1 ); |
413 | 0 | } |
414 | | |
415 | | /* Copies an UTF-8 stream from an UTF-16 string |
416 | | * Returns 1 if successful or -1 on error |
417 | | */ |
418 | | int libuna_utf8_stream_copy_from_utf16( |
419 | | uint8_t *utf8_stream, |
420 | | size_t utf8_stream_size, |
421 | | const libuna_utf16_character_t *utf16_string, |
422 | | size_t utf16_string_size, |
423 | | libcerror_error_t **error ) |
424 | 0 | { |
425 | 0 | static char *function = "libuna_utf8_stream_copy_from_utf16"; |
426 | 0 | libuna_unicode_character_t unicode_character = 0; |
427 | 0 | size_t utf16_string_index = 0; |
428 | 0 | size_t utf8_stream_index = 0; |
429 | |
|
430 | 0 | if( utf8_stream == NULL ) |
431 | 0 | { |
432 | 0 | libcerror_error_set( |
433 | 0 | error, |
434 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
435 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
436 | 0 | "%s: invalid UTF-8 stream.", |
437 | 0 | function ); |
438 | |
|
439 | 0 | return( -1 ); |
440 | 0 | } |
441 | 0 | if( utf8_stream_size > (size_t) SSIZE_MAX ) |
442 | 0 | { |
443 | 0 | libcerror_error_set( |
444 | 0 | error, |
445 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
446 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_EXCEEDS_MAXIMUM, |
447 | 0 | "%s: invalid UTF-8 stream size value exceeds maximum.", |
448 | 0 | function ); |
449 | |
|
450 | 0 | return( -1 ); |
451 | 0 | } |
452 | 0 | if( utf16_string == NULL ) |
453 | 0 | { |
454 | 0 | libcerror_error_set( |
455 | 0 | error, |
456 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
457 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
458 | 0 | "%s: invalid UTF-16 string.", |
459 | 0 | function ); |
460 | |
|
461 | 0 | return( -1 ); |
462 | 0 | } |
463 | 0 | if( utf16_string_size > (size_t) SSIZE_MAX ) |
464 | 0 | { |
465 | 0 | libcerror_error_set( |
466 | 0 | error, |
467 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
468 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_EXCEEDS_MAXIMUM, |
469 | 0 | "%s: invalid UTF-16 string size value exceeds maximum.", |
470 | 0 | function ); |
471 | |
|
472 | 0 | return( -1 ); |
473 | 0 | } |
474 | 0 | if( libuna_utf8_stream_copy_byte_order_mark( |
475 | 0 | utf8_stream, |
476 | 0 | utf8_stream_size, |
477 | 0 | &utf8_stream_index, |
478 | 0 | error ) != 1 ) |
479 | 0 | { |
480 | 0 | libcerror_error_set( |
481 | 0 | error, |
482 | 0 | LIBCERROR_ERROR_DOMAIN_CONVERSION, |
483 | 0 | LIBCERROR_CONVERSION_ERROR_OUTPUT_FAILED, |
484 | 0 | "%s: unable to copy UTF-8 byte order mark.", |
485 | 0 | function ); |
486 | |
|
487 | 0 | return( -1 ); |
488 | 0 | } |
489 | 0 | while( utf16_string_index < utf16_string_size ) |
490 | 0 | { |
491 | | /* Convert the UTF-16 string bytes into an Unicode character |
492 | | */ |
493 | 0 | if( libuna_unicode_character_copy_from_utf16( |
494 | 0 | &unicode_character, |
495 | 0 | utf16_string, |
496 | 0 | utf16_string_size, |
497 | 0 | &utf16_string_index, |
498 | 0 | error ) != 1 ) |
499 | 0 | { |
500 | 0 | libcerror_error_set( |
501 | 0 | error, |
502 | 0 | LIBCERROR_ERROR_DOMAIN_CONVERSION, |
503 | 0 | LIBCERROR_CONVERSION_ERROR_INPUT_FAILED, |
504 | 0 | "%s: unable to copy Unicode character from UTF-16 string.", |
505 | 0 | function ); |
506 | |
|
507 | 0 | return( -1 ); |
508 | 0 | } |
509 | | /* Convert the Unicode character into UTF-8 stream bytes |
510 | | */ |
511 | 0 | if( libuna_unicode_character_copy_to_utf8( |
512 | 0 | unicode_character, |
513 | 0 | utf8_stream, |
514 | 0 | utf8_stream_size, |
515 | 0 | &utf8_stream_index, |
516 | 0 | error ) != 1 ) |
517 | 0 | { |
518 | 0 | libcerror_error_set( |
519 | 0 | error, |
520 | 0 | LIBCERROR_ERROR_DOMAIN_CONVERSION, |
521 | 0 | LIBCERROR_CONVERSION_ERROR_OUTPUT_FAILED, |
522 | 0 | "%s: unable to copy Unicode character to UTF-8 stream.", |
523 | 0 | function ); |
524 | |
|
525 | 0 | return( -1 ); |
526 | 0 | } |
527 | 0 | if( unicode_character == 0 ) |
528 | 0 | { |
529 | 0 | break; |
530 | 0 | } |
531 | 0 | } |
532 | 0 | return( 1 ); |
533 | 0 | } |
534 | | |
535 | | /* Determines the size of an UTF-8 stream from an UTF-32 string |
536 | | * Returns 1 if successful or -1 on error |
537 | | */ |
538 | | int libuna_utf8_stream_size_from_utf32( |
539 | | const libuna_utf32_character_t *utf32_string, |
540 | | size_t utf32_string_size, |
541 | | size_t *utf8_stream_size, |
542 | | libcerror_error_t **error ) |
543 | 0 | { |
544 | 0 | static char *function = "libuna_utf8_stream_size_from_utf32"; |
545 | 0 | libuna_unicode_character_t unicode_character = 0; |
546 | 0 | size_t utf32_string_index = 0; |
547 | |
|
548 | 0 | if( utf32_string == NULL ) |
549 | 0 | { |
550 | 0 | libcerror_error_set( |
551 | 0 | error, |
552 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
553 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
554 | 0 | "%s: invalid UTF-32 string.", |
555 | 0 | function ); |
556 | |
|
557 | 0 | return( -1 ); |
558 | 0 | } |
559 | 0 | if( utf32_string_size > (size_t) SSIZE_MAX ) |
560 | 0 | { |
561 | 0 | libcerror_error_set( |
562 | 0 | error, |
563 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
564 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_EXCEEDS_MAXIMUM, |
565 | 0 | "%s: invalid UTF-32 string size value exceeds maximum.", |
566 | 0 | function ); |
567 | |
|
568 | 0 | return( -1 ); |
569 | 0 | } |
570 | 0 | if( utf8_stream_size == NULL ) |
571 | 0 | { |
572 | 0 | libcerror_error_set( |
573 | 0 | error, |
574 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
575 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
576 | 0 | "%s: invalid UTF-8 stream size.", |
577 | 0 | function ); |
578 | |
|
579 | 0 | return( -1 ); |
580 | 0 | } |
581 | | /* Add the byte order mark |
582 | | */ |
583 | 0 | *utf8_stream_size = 3; |
584 | |
|
585 | 0 | while( utf32_string_index < utf32_string_size ) |
586 | 0 | { |
587 | | /* Convert the UTF-32 character bytes into an Unicode character |
588 | | */ |
589 | 0 | if( libuna_unicode_character_copy_from_utf32( |
590 | 0 | &unicode_character, |
591 | 0 | utf32_string, |
592 | 0 | utf32_string_size, |
593 | 0 | &utf32_string_index, |
594 | 0 | error ) != 1 ) |
595 | 0 | { |
596 | 0 | libcerror_error_set( |
597 | 0 | error, |
598 | 0 | LIBCERROR_ERROR_DOMAIN_CONVERSION, |
599 | 0 | LIBCERROR_CONVERSION_ERROR_INPUT_FAILED, |
600 | 0 | "%s: unable to copy Unicode character from UTF-32.", |
601 | 0 | function ); |
602 | |
|
603 | 0 | return( -1 ); |
604 | 0 | } |
605 | | /* Determine how many UTF-8 character bytes are required |
606 | | */ |
607 | 0 | if( libuna_unicode_character_size_to_utf8( |
608 | 0 | unicode_character, |
609 | 0 | utf8_stream_size, |
610 | 0 | error ) != 1 ) |
611 | 0 | { |
612 | 0 | libcerror_error_set( |
613 | 0 | error, |
614 | 0 | LIBCERROR_ERROR_DOMAIN_CONVERSION, |
615 | 0 | LIBCERROR_CONVERSION_ERROR_OUTPUT_FAILED, |
616 | 0 | "%s: unable to determine size of Unicode character in UTF-8.", |
617 | 0 | function ); |
618 | |
|
619 | 0 | return( -1 ); |
620 | 0 | } |
621 | 0 | if( unicode_character == 0 ) |
622 | 0 | { |
623 | 0 | break; |
624 | 0 | } |
625 | 0 | } |
626 | 0 | return( 1 ); |
627 | 0 | } |
628 | | |
629 | | /* Copies an UTF-8 stream from an UTF-32 string |
630 | | * Returns 1 if successful or -1 on error |
631 | | */ |
632 | | int libuna_utf8_stream_copy_from_utf32( |
633 | | uint8_t *utf8_stream, |
634 | | size_t utf8_stream_size, |
635 | | const libuna_utf32_character_t *utf32_string, |
636 | | size_t utf32_string_size, |
637 | | libcerror_error_t **error ) |
638 | 0 | { |
639 | 0 | static char *function = "libuna_utf8_stream_copy_from_utf32"; |
640 | 0 | libuna_unicode_character_t unicode_character = 0; |
641 | 0 | size_t utf32_string_index = 0; |
642 | 0 | size_t utf8_stream_index = 0; |
643 | |
|
644 | 0 | if( utf8_stream == NULL ) |
645 | 0 | { |
646 | 0 | libcerror_error_set( |
647 | 0 | error, |
648 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
649 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
650 | 0 | "%s: invalid UTF-8 stream.", |
651 | 0 | function ); |
652 | |
|
653 | 0 | return( -1 ); |
654 | 0 | } |
655 | 0 | if( utf8_stream_size > (size_t) SSIZE_MAX ) |
656 | 0 | { |
657 | 0 | libcerror_error_set( |
658 | 0 | error, |
659 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
660 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_EXCEEDS_MAXIMUM, |
661 | 0 | "%s: invalid UTF-8 stream size value exceeds maximum.", |
662 | 0 | function ); |
663 | |
|
664 | 0 | return( -1 ); |
665 | 0 | } |
666 | 0 | if( utf32_string == NULL ) |
667 | 0 | { |
668 | 0 | libcerror_error_set( |
669 | 0 | error, |
670 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
671 | 0 | LIBCERROR_ARGUMENT_ERROR_INVALID_VALUE, |
672 | 0 | "%s: invalid UTF-32 string.", |
673 | 0 | function ); |
674 | |
|
675 | 0 | return( -1 ); |
676 | 0 | } |
677 | 0 | if( utf32_string_size > (size_t) SSIZE_MAX ) |
678 | 0 | { |
679 | 0 | libcerror_error_set( |
680 | 0 | error, |
681 | 0 | LIBCERROR_ERROR_DOMAIN_ARGUMENTS, |
682 | 0 | LIBCERROR_ARGUMENT_ERROR_VALUE_EXCEEDS_MAXIMUM, |
683 | 0 | "%s: invalid UTF-32 string size value exceeds maximum.", |
684 | 0 | function ); |
685 | |
|
686 | 0 | return( -1 ); |
687 | 0 | } |
688 | 0 | if( libuna_utf8_stream_copy_byte_order_mark( |
689 | 0 | utf8_stream, |
690 | 0 | utf8_stream_size, |
691 | 0 | &utf8_stream_index, |
692 | 0 | error ) != 1 ) |
693 | 0 | { |
694 | 0 | libcerror_error_set( |
695 | 0 | error, |
696 | 0 | LIBCERROR_ERROR_DOMAIN_CONVERSION, |
697 | 0 | LIBCERROR_CONVERSION_ERROR_OUTPUT_FAILED, |
698 | 0 | "%s: unable to copy UTF-8 byte order mark.", |
699 | 0 | function ); |
700 | |
|
701 | 0 | return( -1 ); |
702 | 0 | } |
703 | 0 | while( utf32_string_index < utf32_string_size ) |
704 | 0 | { |
705 | | /* Convert the UTF-32 character bytes into an Unicode character |
706 | | */ |
707 | 0 | if( libuna_unicode_character_copy_from_utf32( |
708 | 0 | &unicode_character, |
709 | 0 | utf32_string, |
710 | 0 | utf32_string_size, |
711 | 0 | &utf32_string_index, |
712 | 0 | error ) != 1 ) |
713 | 0 | { |
714 | 0 | libcerror_error_set( |
715 | 0 | error, |
716 | 0 | LIBCERROR_ERROR_DOMAIN_CONVERSION, |
717 | 0 | LIBCERROR_CONVERSION_ERROR_INPUT_FAILED, |
718 | 0 | "%s: unable to copy Unicode character from UTF-32.", |
719 | 0 | function ); |
720 | |
|
721 | 0 | return( -1 ); |
722 | 0 | } |
723 | | /* Convert the Unicode character into UTF-8 character bytes |
724 | | */ |
725 | 0 | if( libuna_unicode_character_copy_to_utf8( |
726 | 0 | unicode_character, |
727 | 0 | utf8_stream, |
728 | 0 | utf8_stream_size, |
729 | 0 | &utf8_stream_index, |
730 | 0 | error ) != 1 ) |
731 | 0 | { |
732 | 0 | libcerror_error_set( |
733 | 0 | error, |
734 | 0 | LIBCERROR_ERROR_DOMAIN_CONVERSION, |
735 | 0 | LIBCERROR_CONVERSION_ERROR_OUTPUT_FAILED, |
736 | 0 | "%s: unable to copy Unicode character to UTF-8 stream.", |
737 | 0 | function ); |
738 | |
|
739 | 0 | return( -1 ); |
740 | 0 | } |
741 | 0 | if( unicode_character == 0 ) |
742 | 0 | { |
743 | 0 | break; |
744 | 0 | } |
745 | 0 | } |
746 | 0 | return( 1 ); |
747 | 0 | } |
748 | | |