summaryrefslogtreecommitdiffstats
path: root/merge.cc
blob: 4278fc03eccedd8bbe2ca6a05467ff99aabf1b7f (plain)
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
/*  Lziprecover - Data recovery tool for lzipped files
    Copyright (C) 2009, 2010, 2011 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 3 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/>.
*/

#define _FILE_OFFSET_BITS 64

#include <cerrno>
#include <climits>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <string>
#include <vector>
#include <stdint.h>
#include <unistd.h>
#include <sys/stat.h>

#include "lzip.h"
#include "decoder.h"


namespace {

bool copy_and_diff_file( const std::vector< int > & infd_vector,
                         const int outfd, std::vector< Block > & block_vector )
  {
  const int buffer_size = 65536;
  std::vector< uint8_t * > buffer_vector( infd_vector.size() );
  for( unsigned int i = 0; i < infd_vector.size(); ++i )
    buffer_vector[i] = new uint8_t[buffer_size];
  Block b( 0, 0 );
  long long partial_pos = 0;
  int equal_bytes = 0;
  bool error = false;

  while( true )
    {
    const int rd = readblock( infd_vector[0], buffer_vector[0], buffer_size );
    if( rd != buffer_size && errno )
      { show_error( "Error reading input file", errno ); error = true; break; }
    if( rd > 0 )
      {
      for( unsigned int i = 1; i < infd_vector.size(); ++i )
        if( readblock( infd_vector[i], buffer_vector[i], rd ) != rd )
          { show_error( "Error reading input file", errno );
            error = true; break; }
      if( error ) break;
      const int wr = writeblock( outfd, buffer_vector[0], rd );
      if( wr != rd )
        { show_error( "Error writing output file", errno );
          error = true; break; }
      for( int i = 0; i < rd; ++i )
        {
        while( i < rd && b.pos() == 0 )
          {
          for( unsigned int j = 1; j < infd_vector.size(); ++j )
            if( buffer_vector[0][i] != buffer_vector[j][i] )
              { b.pos( partial_pos + i ); break; }	// begin block
          ++i;
          }
        while( i < rd && b.pos() > 0 )
          {
          ++equal_bytes;
          for( unsigned int j = 1; j < infd_vector.size(); ++j )
            if( buffer_vector[0][i] != buffer_vector[j][i] )
              { equal_bytes = 0; break; }
          if( equal_bytes >= 2 )			// end block
            {
            b.size( partial_pos + i - ( equal_bytes - 1 ) - b.pos() );
            block_vector.push_back( b );
            b.pos( 0 );
            equal_bytes = 0;
            }
          ++i;
          }
        }
      partial_pos += rd;
      }
    if( rd < buffer_size ) break;			// EOF
    }
  if( b.pos() > 0 )					// finish last block
    {
    b.size( partial_pos - b.pos() );
    block_vector.push_back( b );
    }
  for( unsigned int i = 0; i < infd_vector.size(); ++i )
    delete[] buffer_vector[i];
  return !error;
  }


int ipow( const unsigned int base, const unsigned int exponent ) throw()
  {
  int result = 1;
  for( unsigned int i = 0; i < exponent; ++i )
    {
    if( INT_MAX / base >= (unsigned int)result ) result *= base;
    else { result = INT_MAX; break; }
    }
  return result;
  }


int open_input_files( const std::vector< std::string > & filenames,
                      std::vector< int > & infd_vector, long long & isize )
  {
  bool identical = false;
  for( unsigned int i = 1; i < filenames.size(); ++i )
    if( filenames[0] == filenames[i] )
      { identical = true; break; }
  if( !identical )
    for( unsigned int i = 0; i < filenames.size(); ++i )
      {
      struct stat in_stats;
      ino_t st_ino0 = 0;
      dev_t st_dev0 = 0;
      infd_vector[i] = open_instream( filenames[i], &in_stats, true, true );
      if( infd_vector[i] < 0 ) return 1;
      if( i == 0 ) { st_ino0 = in_stats.st_ino; st_dev0 = in_stats.st_dev; }
      else if( st_ino0 == in_stats.st_ino && st_dev0 == in_stats.st_dev )
        { identical = true; break; }
      }
  if( identical ) { show_error( "Two input files are the same." ); return 1; }

  isize = 0;
  for( unsigned int i = 0; i < filenames.size(); ++i )
    {
    const long long tmp = lseek( infd_vector[i], 0, SEEK_END );
    if( tmp < 0 )
      {
      if( verbosity >= 0 )
        std::fprintf( stderr, "File `%s' is not seekable.\n", filenames[i].c_str() );
      return 1;
      }
    if( i == 0 )
      {
      isize = tmp;
      if( isize < min_member_size ) { show_error( "Input file is too short." ); return 2; }
      }
    else if( isize != tmp )
      { show_error( "Sizes of input files are different." ); return 1; }
    }

  for( unsigned int i = 0; i < filenames.size(); ++i )
    if( !verify_single_member( infd_vector[i], isize ) )
      return 2;

  for( unsigned int i = 0; i < filenames.size(); ++i )
    {
    if( lseek( infd_vector[i], 0, SEEK_SET ) < 0 )
      { show_error( "Seek error in input file", errno ); return 1; }
    if( try_decompress( infd_vector[i], isize ) )
      {
      if( verbosity >= 1 )
        std::printf( "File `%s' has no errors. Recovery is not needed.\n",
                     filenames[i].c_str() );
      return 0;
      }
    if( lseek( infd_vector[i], 0, SEEK_SET ) < 0 )
      { show_error( "Seek error in input file", errno ); return 1; }
    }
  return -1;
  }

} // end namespace


void cleanup_and_fail( const std::string & output_filename,
                       const int outfd, const int retval ) throw()
  {
  if( outfd >= 0 ) close( outfd );
  if( std::remove( output_filename.c_str() ) != 0 && errno != ENOENT )
    show_error( "WARNING: deletion of output file (apparently) failed." );
  std::exit( retval );
  }


bool copy_file( const int infd, const int outfd, const long long size )
  {
  long long rest = size;
  const int buffer_size = 65536;
  uint8_t * const buffer = new uint8_t[buffer_size];
  bool error = false;

  while( true )
    {
    const int block_size = std::min( (long long)buffer_size, rest );
    if( block_size <= 0 ) break;
    const int rd = readblock( infd, buffer, block_size );
    if( rd != block_size && errno )
      { show_error( "Error reading input file", errno ); error = true; break; }
    if( rd > 0 )
      {
      const int wr = writeblock( outfd, buffer, rd );
      if( wr != rd )
        { show_error( "Error writing output file", errno );
          error = true; break; }
      rest -= rd;
      }
    if( rd < block_size ) break;			// EOF
    }
  delete[] buffer;
  return !error;
  }


bool try_decompress( const int fd, const long long file_size,
                     long long * failure_posp )
  {
  try {
    Range_decoder rdec( fd );
    File_header header;
    rdec.reset_member_position();
    for( int i = 0; i < File_header::size; ++i )
      header.data[i] = rdec.get_byte();
    if( !rdec.finished() &&			// End Of File
        header.verify_magic() &&
        header.version() == 1 &&
        header.dictionary_size() >= min_dictionary_size &&
        header.dictionary_size() <= max_dictionary_size )
      {
      LZ_decoder decoder( header, rdec, -1 );
      Pretty_print dummy( "", -1 );

      if( decoder.decode_member( dummy ) == 0 &&
          rdec.member_position() == file_size ) return true;
      if( failure_posp ) *failure_posp = rdec.member_position();
      }
    }
  catch( std::bad_alloc )
    {
    show_error( "Not enough memory. Find a machine with more memory." );
    std::exit( 1 );
    }
  catch( Error e ) {}
  return false;
  }


bool verify_header( const File_header & header )
  {
  if( !header.verify_magic() )
    {
    show_error( "Bad magic number (file not in lzip format)." );
    return false;
    }
  if( header.version() == 0 )
    {
    show_error( "Version 0 member format can't be recovered." );
    return false;
    }
  if( header.version() != 1 )
    {
    if( verbosity >= 0 )
      std::fprintf( stderr, "Version %d member format not supported.\n",
                    header.version() );
    return false;
    }
  return true;
  }


bool verify_single_member( const int fd, const long long file_size )
  {
  File_header header;
  if( lseek( fd, 0, SEEK_SET ) < 0 ||
      readblock( fd, header.data, File_header::size ) != File_header::size )
    { show_error( "Error reading member header", errno ); return false; }
  if( !verify_header( header ) ) return false;

  File_trailer trailer;
  if( lseek( fd, -File_trailer::size(), SEEK_END ) < 0 ||
      readblock( fd, trailer.data, File_trailer::size() ) != File_trailer::size() )
    { show_error( "Error reading member trailer", errno ); return false; }
  const long long member_size = trailer.member_size();
  if( member_size != file_size )
    {
    if( member_size < file_size &&
        lseek( fd, -member_size, SEEK_END ) > 0 &&
        readblock( fd, header.data, File_header::size ) == File_header::size &&
        verify_header( header ) )
      show_error( "Input file has more than 1 member. Split it first." );
    else
      show_error( "Member size in input file trailer is corrupt." );
    return false;
    }
  return true;
  }


int merge_files( const std::vector< std::string > & filenames,
                 const std::string & output_filename, const bool force )
  {
  std::vector< int > infd_vector( filenames.size() );
  long long isize = 0;
  const int retval = open_input_files( filenames, infd_vector, isize );
  if( retval >= 0 ) return retval;

  const int outfd = open_outstream_rw( output_filename, force );
  if( outfd < 0 ) return 1;

  // vector of data blocks differing among the copies of the input file.
  std::vector< Block > block_vector;
  if( !copy_and_diff_file( infd_vector, outfd, block_vector ) )
    cleanup_and_fail( output_filename, outfd, 1 );

  if( block_vector.size() == 0 )
    { show_error( "Input files are identical. Recovery is not possible." );
      cleanup_and_fail( output_filename, outfd, 2 ); }

  const bool single_block = ( block_vector.size() == 1 );
  if( single_block && block_vector[0].size() < 2 )
    { show_error( "Input files have the same byte damaged."
                  " Try repairing one of them." );
      cleanup_and_fail( output_filename, outfd, 2 ); }

  if( ipow( filenames.size(), block_vector.size() ) >= INT_MAX ||
      ( single_block &&
        ipow( filenames.size(), 2 ) >= INT_MAX / block_vector[0].size() ) )
    { show_error( "Input files are too damaged. Recovery is not possible." );
      cleanup_and_fail( output_filename, outfd, 2 ); }

  const int shifts = ( single_block ? block_vector[0].size() - 1 : 1 );
  if( single_block )
    {
    Block b( block_vector[0].pos() + 1, block_vector[0].size() - 1 );
    block_vector[0].size( 1 );
    block_vector.push_back( b );
    }

  const int base_variations = ipow( filenames.size(), block_vector.size() );
  const int variations = ( base_variations * shifts ) - 2;
  bool done = false;
  for( int var = 1; var <= variations; ++var )
    {
    if( verbosity >= 1 )
      {
      std::printf( "Trying variation %d of %d \r", var, variations );
      std::fflush( stdout );
      }
    int tmp = var;
    for( unsigned int i = 0; i < block_vector.size(); ++i )
      {
      const int infd = infd_vector[tmp % filenames.size()];
      tmp /= filenames.size();
      if( lseek( infd, block_vector[i].pos(), SEEK_SET ) < 0 ||
          lseek( outfd, block_vector[i].pos(), SEEK_SET ) < 0 ||
          !copy_file( infd, outfd, block_vector[i].size() ) )
        { show_error( "Error reading output file", errno );
          cleanup_and_fail( output_filename, outfd, 1 ); }
      }
    if( lseek( outfd, 0, SEEK_SET ) < 0 )
      { show_error( "Seek error in output file", errno );
        cleanup_and_fail( output_filename, outfd, 1 ); }
    if( try_decompress( outfd, isize ) )
      { done = true; break; }
    if( var % base_variations == 0 ) block_vector[0].shift( block_vector[1] );
    }
  if( verbosity >= 1 ) std::printf( "\n" );

  if( close( outfd ) != 0 )
    {
    show_error( "Error closing output file", errno );
    cleanup_and_fail( output_filename, -1, 1 );
    }
  if( !done )
    {
    show_error( "Some error areas overlap. Can't recover input file." );
    cleanup_and_fail( output_filename, -1, 2 );
    }
  if( verbosity >= 1 )
    std::printf( "Input files merged successfully.\n" );
  return 0;
  }