1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
|
/* Unzcrash - Tests robustness of decompressors to corrupted data.
Inspired by unzcrash.c from Julian Seward's bzip2.
Copyright (C) 2008-2016 Antonio Diaz Diaz.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
/*
Exit status: 0 for a normal exit, 1 for environmental problems
(file not found, invalid flags, I/O errors, etc), 2 to indicate a
corrupt or invalid input file, 3 for an internal consistency error
(eg, bug) which caused unzcrash to panic.
*/
#include <algorithm>
#include <cerrno>
#include <climits>
#include <csignal>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <string>
#include <vector>
#include <stdint.h>
#include <unistd.h>
#include "arg_parser.h"
#if CHAR_BIT != 8
#error "Environments where CHAR_BIT != 8 are not supported."
#endif
namespace {
const char * const Program_name = "Unzcrash";
const char * const program_name = "unzcrash";
const char * const program_year = "2016";
const char * invocation_name = 0;
int verbosity = 0;
void show_help()
{
std::printf( "%s - Tests robustness of decompressors to corrupted data.\n", Program_name );
std::printf( "\nUsage: %s [options] \"lzip -tv\" filename.lz\n", invocation_name );
std::printf( "\nThis program reads the specified file and then repeatedly decompresses\n"
"it, increasing 256 times each byte of the compressed data, so as to test\n"
"all possible one-byte errors. This should not cause any invalid memory\n"
"accesses. If it does, please, report it as a bug.\n"
"\nIf the decompressor returns with zero status, unzcrash compares the\n"
"output of the decompressor for the original and corrupt files. If the\n"
"outputs differ, it means that the decompressor failed to recognize the\n"
"corruption and produced garbage output. Please, report it as a bug.\n"
"\nIn order to compare the outputs, unzcrash needs a zcmp program able to\n"
"understand the format being tested. For example the one provided by zutils.\n"
"Use '--zcmp=false' to disable comparisons.\n"
"\nOptions:\n"
" -h, --help display this help and exit\n"
" -V, --version output version information and exit\n"
" -b, --bits=<range> test N-bit errors instead of full byte\n"
" -B, --block[=<size>][,<val>] test blocks of given size [512,0]\n"
" -d, --delta=<n> test one of every n bytes/blocks/truncations\n"
" -p, --position=<bytes> first byte position to test [default 0]\n"
" -q, --quiet suppress all messages\n"
" -s, --size=<bytes> number of byte positions to test [all]\n"
" -t, --truncate test decompression of truncated file\n"
" -v, --verbose be verbose (a 2nd -v gives more)\n"
" -z, --zcmp=<command> set zcmp command name and options [zcmp]\n"
"Examples of <range>: 1 1,2,3 1-4 1,3-5,8 1-3,5-8\n"
"A negative position is relative to the end of file.\n"
"A negative size is relative to the rest of the file.\n"
"\nExit status: 0 for a normal exit, 1 for environmental problems (file\n"
"not found, invalid flags, I/O errors, etc), 2 to indicate a corrupt or\n"
"invalid input file, 3 for an internal consistency error (eg, bug) which\n"
"caused unzcrash to panic.\n"
"\nReport bugs to lzip-bug@nongnu.org\n"
"Lziprecover home page: http://www.nongnu.org/lzip/lziprecover.html\n" );
}
void show_version()
{
std::printf( "%s %s\n", program_name, PROGVERSION );
std::printf( "Copyright (C) %s Antonio Diaz Diaz.\n", program_year );
std::printf( "License GPLv2+: GNU GPL version 2 or later <http://gnu.org/licenses/gpl.html>\n"
"This is free software: you are free to change and redistribute it.\n"
"There is NO WARRANTY, to the extent permitted by law.\n" );
}
void show_error( const char * const msg, const int errcode = 0,
const bool help = false )
{
if( verbosity < 0 ) return;
if( msg && msg[0] )
{
std::fprintf( stderr, "%s: %s", program_name, msg );
if( errcode > 0 ) std::fprintf( stderr, ": %s", std::strerror( errcode ) );
std::fputc( '\n', stderr );
}
if( help )
std::fprintf( stderr, "Try '%s --help' for more information.\n",
invocation_name );
}
void internal_error( const char * const msg )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: internal error: %s\n", program_name, msg );
std::exit( 3 );
}
long getnum( const char * const ptr, const long llimit, const long ulimit,
const bool comma = false )
{
char * tail;
errno = 0;
long result = strtol( ptr, &tail, 0 );
if( tail == ptr )
{
show_error( "Bad or missing numerical argument.", 0, true );
std::exit( 1 );
}
if( !errno && tail[0] )
{
const int factor = ( tail[1] == 'i' ) ? 1024 : 1000;
int exponent = -1; // -1 = bad multiplier
switch( tail[0] )
{
case ',': if( comma ) exponent = 0; break;
case 'Y': exponent = 8; break;
case 'Z': exponent = 7; break;
case 'E': exponent = 6; break;
case 'P': exponent = 5; break;
case 'T': exponent = 4; break;
case 'G': exponent = 3; break;
case 'M': exponent = 2; break;
case 'K': if( factor == 1024 ) exponent = 1; break;
case 'k': if( factor == 1000 ) exponent = 1; break;
}
if( exponent < 0 )
{
show_error( "Bad multiplier in numerical argument.", 0, true );
std::exit( 1 );
}
for( int i = 0; i < exponent; ++i )
{
if( LONG_MAX / factor >= std::labs( result ) ) result *= factor;
else { errno = ERANGE; break; }
}
}
if( !errno && ( result < llimit || result > ulimit ) ) errno = ERANGE;
if( errno )
{
show_error( "Numerical argument out of limits." );
std::exit( 1 );
}
return result;
}
void parse_block( const char * const ptr, long & size, uint8_t & value )
{
const char * const ptr2 = std::strchr( ptr, ',' );
if( !ptr2 || ptr2 != ptr )
size = getnum( ptr, 1, INT_MAX, true );
if( ptr2 )
value = getnum( ptr2 + 1, 0, 255 );
}
/* Returns the address of a malloc'd buffer containing the file data and
its size in '*size'.
In case of error, returns 0 and does not modify '*size'.
*/
uint8_t * read_file( const char * const name, long * const size )
{
FILE * const f = std::fopen( name, "rb" );
if( !f )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Can't open input file '%s': %s\n",
program_name, name, std::strerror( errno ) );
return 0;
}
long buffer_size = 1 << 20;
uint8_t * buffer = (uint8_t *)std::malloc( buffer_size );
if( !buffer ) { show_error( "Not enough memory." ); return 0; }
long file_size = std::fread( buffer, 1, buffer_size, f );
while( file_size >= buffer_size )
{
if( buffer_size >= LONG_MAX )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Input file '%s' is too large.\n",
program_name, name );
std::free( buffer ); return 0;
}
buffer_size = ( buffer_size <= LONG_MAX / 2 ) ? 2 * buffer_size : LONG_MAX;
uint8_t * const tmp = (uint8_t *)std::realloc( buffer, buffer_size );
if( !tmp )
{ show_error( "Not enough memory." ); std::free( buffer ); return 0; }
buffer = tmp;
file_size += std::fread( buffer + file_size, 1, buffer_size - file_size, f );
}
if( std::ferror( f ) || !std::feof( f ) )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Error reading file '%s': %s\n",
program_name, name, std::strerror( errno ) );
std::free( buffer ); return 0;
}
std::fclose( f );
*size = file_size;
return buffer;
}
class Bitset8 // 8 value bitset (1 to 8)
{
bool data[8];
static bool valid_digit( const unsigned char ch )
{ return ( ch >= '1' && ch <= '8' ); }
public:
Bitset8() { for( int i = 0; i < 8; ++i ) data[i] = true; }
bool includes( const int i ) const
{ return ( i >= 1 && i <= 8 && data[i-1] ); }
// Recognized formats: 1 1,2,3 1-4 1,3-5,8 1-3,5-8
bool parse( const char * p )
{
for( int i = 0; i < 8; ++i ) data[i] = false;
while( true )
{
const unsigned char ch1 = *p++;
if( !valid_digit( ch1 ) ) break;
if( *p != '-' ) data[ch1-'1'] = true;
else
{
++p;
if( !valid_digit( *p ) || ch1 > *p ) break;
for( int c = ch1; c <= *p; ++c ) data[c-'1'] = true;
++p;
}
if( *p == 0 ) return true;
if( *p == ',' ) ++p; else break;
}
show_error( "Invalid value or range." );
return false;
}
// number of N-bit errors per byte (N=0 to 8): 1 8 28 56 70 56 28 8 1
void print() const
{
std::fflush( stderr );
int c = 0;
for( int i = 0; i < 8; ++i ) if( data[i] ) ++c;
if( c == 8 ) std::fputs( "Testing full byte.\n", stdout );
else if( c == 0 ) std::fputs( "Nothing to test.\n", stdout );
else
{
std::fputs( "Testing ", stdout );
for( int i = 0; i < 8; ++i )
if( data[i] )
{
std::printf( "%d", i + 1 );
if( --c ) std::fputs( ",", stdout );
}
std::fputs( " bit errors.\n", stdout );
}
std::fflush( stdout );
}
};
int differing_bits( const uint8_t byte1, const uint8_t byte2 )
{
int count = 0;
uint8_t dif = byte1 ^ byte2;
while( dif )
{ count += ( dif & 1 ); dif >>= 1; }
return count;
}
} // end namespace
int main( const int argc, const char * const argv[] )
{
enum Mode { m_block, m_byte, m_truncate };
const char * mode_str[3] = { "block", "byte", "size" };
Bitset8 bits; // if Bitset8::parse not called test full byte
const char * zcmp_program = "zcmp";
long pos = 0;
long max_size = LONG_MAX;
long delta = 1;
long block_size = 512;
Mode program_mode = m_byte;
uint8_t block_value = 0;
invocation_name = argv[0];
const Arg_parser::Option options[] =
{
{ 'h', "help", Arg_parser::no },
{ 'b', "bits", Arg_parser::yes },
{ 'B', "block", Arg_parser::maybe },
{ 'd', "delta", Arg_parser::yes },
{ 'p', "position", Arg_parser::yes },
{ 'q', "quiet", Arg_parser::no },
{ 's', "size", Arg_parser::yes },
{ 't', "truncate", Arg_parser::no },
{ 'v', "verbose", Arg_parser::no },
{ 'V', "version", Arg_parser::no },
{ 'z', "zcmp", Arg_parser::yes },
{ 0 , 0, Arg_parser::no } };
const Arg_parser parser( argc, argv, options );
if( parser.error().size() ) // bad option
{ show_error( parser.error().c_str(), 0, true ); return 1; }
int argind = 0;
for( ; argind < parser.arguments(); ++argind )
{
const int code = parser.code( argind );
if( !code ) break; // no more options
const char * const arg = parser.argument( argind ).c_str();
switch( code )
{
case 'h': show_help(); return 0;
case 'b': if( !bits.parse( arg ) ) return 1; program_mode = m_byte; break;
case 'B': if( arg[0] ) parse_block( arg, block_size, block_value );
program_mode = m_block; break;
case 'd': delta = getnum( arg, 1, INT_MAX ); break;
case 'p': pos = getnum( arg, -LONG_MAX, LONG_MAX ); break;
case 'q': verbosity = -1; break;
case 's': max_size = getnum( arg, -LONG_MAX, LONG_MAX ); break;
case 't': program_mode = m_truncate; break;
case 'v': if( verbosity < 4 ) ++verbosity; break;
case 'V': show_version(); return 0;
case 'z': zcmp_program = arg; break;
default : internal_error( "uncaught option." );
}
} // end process options
if( argind + 2 != parser.arguments() )
{
if( verbosity >= 0 )
std::fprintf( stderr, "Usage: %s \"lzip -tv\" filename.lz\n",
invocation_name );
return 1;
}
const char * const filename = parser.argument( argind + 1 ).c_str();
long file_size = 0;
uint8_t * const buffer = read_file( filename, &file_size );
if( !buffer ) return 1;
const char * const command = parser.argument( argind ).c_str();
char zcmp_command[1024] = { 0 };
if( std::strcmp( zcmp_program, "false" ) != 0 )
snprintf( zcmp_command, sizeof zcmp_command, "%s '%s' -",
zcmp_program, filename );
// verify original file
if( verbosity >= 1 ) fprintf( stderr, "Testing file '%s'\n", filename );
FILE * f = popen( command, "w" );
if( !f )
{ show_error( "Can't open pipe to decompressor", errno ); return 1; }
if( (long)std::fwrite( buffer, 1, file_size, f ) != file_size )
{ show_error( "Can't write to decompressor", errno ); return 1; }
if( pclose( f ) != 0 )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Can't run '%s'.\n", program_name, command );
return 1;
}
if( zcmp_command[0] )
{
f = popen( zcmp_command, "w" );
if( !f )
{ show_error( "Can't open pipe to zcmp command", errno ); return 1; }
if( (long)std::fwrite( buffer, 1, file_size, f ) != file_size )
{ show_error( "Can't write to zcmp command", errno ); return 1; }
if( pclose( f ) != 0 )
{
show_error( "zcmp command failed. Skipping comparison" );
zcmp_command[0] = 0;
}
}
std::signal( SIGPIPE, SIG_IGN );
if( pos < 0 ) pos = std::max( 0L, file_size + pos );
if( pos >= file_size || max_size == 0 ||
( max_size < 0 && -max_size >= file_size - pos ) )
{ show_error( "Nothing to do; domain is empty." ); return 0; }
if( max_size < 0 ) max_size += file_size - pos;
const long end = ( ( max_size < file_size - pos ) ? pos + max_size : file_size );
long positions = 0, decompressions = 0, successes = 0, failed_comparisons = 0;
if( program_mode == m_truncate )
for( long i = pos; i < end; i += std::min( delta, end - i ) )
{
if( verbosity >= 0 )
std::fprintf( stderr, "length %ld\n", i );
++positions; ++decompressions;
f = popen( command, "w" );
if( !f ) { show_error( "Can't open pipe", errno ); return 1; }
std::fwrite( buffer, 1, i, f );
if( pclose( f ) == 0 )
{
++successes;
if( verbosity >= 0 )
std::fputs( "passed the test\n", stderr );
if( zcmp_command[0] )
{
f = popen( zcmp_command, "w" );
if( !f ) { show_error( "Can't open pipe", errno ); return 1; }
std::fwrite( buffer, 1, i, f );
if( pclose( f ) != 0 )
{
++failed_comparisons;
if( verbosity >= 0 )
std::fprintf( stderr, "byte %ld comparison failed\n", i );
}
}
}
}
else if( program_mode == m_block )
{
uint8_t * block = (uint8_t *)std::malloc( block_size );
if( !block ) { show_error( "Not enough memory." ); return 1; }
for( long i = pos; i < end; i += std::min( block_size * delta, end - i ) )
{
const long size = std::min( block_size, file_size - i );
if( verbosity >= 0 )
std::fprintf( stderr, "block %ld,%ld\n", i, size );
++positions; ++decompressions;
f = popen( command, "w" );
if( !f ) { show_error( "Can't open pipe", errno ); return 1; }
std::memcpy( block , buffer + i, size );
std::memset( buffer + i, block_value, size );
std::fwrite( buffer, 1, file_size, f );
if( pclose( f ) == 0 )
{
++successes;
if( verbosity >= 0 )
std::fputs( "passed the test\n", stderr );
if( zcmp_command[0] )
{
f = popen( zcmp_command, "w" );
if( !f ) { show_error( "Can't open pipe", errno ); return 1; }
std::fwrite( buffer, 1, file_size, f );
if( pclose( f ) != 0 )
{
++failed_comparisons;
if( verbosity >= 0 )
std::fprintf( stderr, "block %ld,%ld comparison failed\n", i, size );
}
}
}
std::memcpy( buffer + i, block, size );
}
std::free( block );
}
else
{
if( verbosity >= 1 ) bits.print();
for( long i = pos; i < end; i += std::min( delta, end - i ) )
{
if( verbosity >= 0 )
std::fprintf( stderr, "byte %ld\n", i );
++positions;
const uint8_t byte = buffer[i];
for( int j = 1; j < 256; ++j )
{
++buffer[i];
if( bits.includes( differing_bits( byte, buffer[i] ) ) )
{
++decompressions;
if( verbosity >= 2 )
std::fprintf( stderr, "0x%02X (0x%02X+0x%02X) ",
buffer[i], byte, j );
f = popen( command, "w" );
if( !f ) { show_error( "Can't open pipe", errno ); return 1; }
std::fwrite( buffer, 1, file_size, f );
if( pclose( f ) == 0 )
{
++successes;
if( verbosity >= 0 )
std::fprintf( stderr, "0x%02X (0x%02X+0x%02X) passed the test\n",
buffer[i], byte, j );
if( zcmp_command[0] )
{
f = popen( zcmp_command, "w" );
if( !f ) { show_error( "Can't open pipe", errno ); return 1; }
std::fwrite( buffer, 1, file_size, f );
if( pclose( f ) != 0 )
{
++failed_comparisons;
if( verbosity >= 0 )
std::fprintf( stderr, "byte %ld comparison failed\n", i );
}
}
}
}
}
buffer[i] = byte;
}
}
if( verbosity >= 0 )
{
std::fprintf( stderr, "\n%8ld %ss tested\n%8ld total decompressions"
"\n%8ld decompressions returned with zero status",
positions, mode_str[program_mode], decompressions, successes );
if( successes > 0 )
{
if( zcmp_command[0] )
std::fprintf( stderr, ", of which\n%8ld comparisons failed\n",
failed_comparisons );
else std::fprintf( stderr, "\n comparisons disabled\n" );
}
else std::fputc( '\n', stderr );
}
std::free( buffer );
return 0;
}
|