summaryrefslogtreecommitdiffstats
path: root/main.cc
blob: 276fe3092e2ed341b5a80428ab24b313ca1f8746 (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
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
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
/*  Lzip - Data compressor based on the LZMA algorithm
    Copyright (C) 2008, 2009, 2010, 2011, 2012 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/>.
*/
/*
    Return values: 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 lzip to panic.
*/

#define _FILE_OFFSET_BITS 64

#include <algorithm>
#include <cerrno>
#include <climits>
#include <csignal>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <string>
#include <vector>
#include <fcntl.h>
#include <stdint.h>
#include <unistd.h>
#include <utime.h>
#include <sys/stat.h>
#if defined(__MSVCRT__)
#include <io.h>
#define fchmod(x,y) 0
#define fchown(x,y,z) 0
#define SIGHUP SIGTERM
#define S_ISSOCK(x) 0
#define S_IRGRP 0
#define S_IWGRP 0
#define S_IROTH 0
#define S_IWOTH 0
#endif
#if defined(__OS2__)
#include <io.h>
#endif

#include "arg_parser.h"
#include "lzip.h"
#include "decoder.h"
#include "encoder.h"
#include "fast_encoder.h"

#if CHAR_BIT != 8
#error "Environments where CHAR_BIT != 8 are not supported."
#endif

#ifndef LLONG_MAX
#define LLONG_MAX  0x7FFFFFFFFFFFFFFFLL
#endif
#ifndef LLONG_MIN
#define LLONG_MIN  (-LLONG_MAX - 1LL)
#endif
#ifndef ULLONG_MAX
#define ULLONG_MAX 0xFFFFFFFFFFFFFFFFULL
#endif


namespace {

const char * const Program_name = "Lzip";
const char * const program_name = "lzip";
const char * const program_year = "2012";
const char * invocation_name = 0;

#ifdef O_BINARY
const int o_binary = O_BINARY;
#else
const int o_binary = 0;
#endif

struct { const char * from; const char * to; } const known_extensions[] = {
  { ".lz",  ""     },
  { ".tlz", ".tar" },
  { 0,      0      } };

struct Lzma_options
  {
  int dictionary_size;		// 4KiB..512MiB
  int match_len_limit;		// 5..273
  };

enum Mode { m_compress, m_decompress, m_test };

std::string output_filename;
int outfd = -1;
int verbosity = 0;
const mode_t usr_rw = S_IRUSR | S_IWUSR;
const mode_t all_rw = usr_rw | S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH;
mode_t outfd_mode = usr_rw;
bool delete_output_on_interrupt = false;


void show_help()
  {
  std::printf( "%s - Data compressor based on the LZMA algorithm.\n", Program_name );
  std::printf( "\nUsage: %s [options] [files]\n", invocation_name );
  std::printf( "\nOptions:\n"
               "  -h, --help                     display this help and exit\n"
               "  -V, --version                  output version information and exit\n"
               "  -b, --member-size=<bytes>      set member size limit in bytes\n"
               "  -c, --stdout                   send output to standard output\n"
               "  -d, --decompress               decompress\n"
               "  -f, --force                    overwrite existing output files\n"
               "  -F, --recompress               force recompression of compressed files\n"
               "  -k, --keep                     keep (don't delete) input files\n"
               "  -m, --match-length=<bytes>     set match length limit in bytes [36]\n"
               "  -o, --output=<file>            if reading stdin, place the output into <file>\n"
               "  -q, --quiet                    suppress all messages\n"
               "  -s, --dictionary-size=<bytes>  set dictionary size limit in bytes [8MiB]\n"
               "  -S, --volume-size=<bytes>      set volume size limit in bytes\n"
               "  -t, --test                     test compressed file integrity\n"
               "  -v, --verbose                  be verbose (a 2nd -v gives more)\n"
               "  -0 .. -9                       set compression level [default 6]\n"
               "      --fast                     alias for -0\n"
               "      --best                     alias for -9\n"
               "If no file names are given, lzip compresses or decompresses\n"
               "from standard input to standard output.\n"
               "Numbers may be followed by a multiplier: k = kB = 10^3 = 1000,\n"
               "Ki = KiB = 2^10 = 1024, M = 10^6, Mi = 2^20, G = 10^9, Gi = 2^30, etc...\n"
               "The bidimensional parameter space of LZMA can't be mapped to a linear\n"
               "scale optimal for all files. If your files are large, very repetitive,\n"
               "etc, you may need to use the --match-length and --dictionary-size\n"
               "options directly to achieve optimal performance.\n"
               "\nReport bugs to lzip-bug@nongnu.org\n"
               "Lzip home page: http://www.nongnu.org/lzip/lzip.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 GPLv3+: GNU GPL version 3 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" );
  }


const char * format_num( long long num )
  {
  const char * const prefix[8] =
    { "Ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi", "Yi" };
  enum { buf_size = 16, factor = 1024 };
  static char buf[buf_size];
  const char *p = "";
  bool exact = ( num % factor == 0 );

  for( int i = 0; i < 8 && ( llabs( num ) > 9999 ||
                             ( exact && llabs( num ) >= factor ) ); ++i )
    { num /= factor; if( num % factor != 0 ) exact = false; p = prefix[i]; }
  snprintf( buf, buf_size, "%lld %s", num, p );
  return buf;
  }


long long getnum( const char * const ptr,
                  const long long llimit = LLONG_MIN + 1,
                  const long long ulimit = LLONG_MAX )
  {
  errno = 0;
  char *tail;
  long long result = strtoll( ptr, &tail, 0 );
  if( tail == ptr )
    {
    show_error( "Bad or missing numerical argument.", 0, true );
    std::exit( 1 );
    }

  if( !errno && tail[0] )
    {
    int factor = ( tail[1] == 'i' ) ? 1024 : 1000;
    int exponent = 0;
    bool bad_multiplier = false;
    switch( tail[0] )
      {
      case ' ': 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; else bad_multiplier = true;
                break;
      case 'k': if( factor == 1000 ) exponent = 1; else bad_multiplier = true;
                break;
      default : bad_multiplier = true;
      }
    if( bad_multiplier )
      {
      show_error( "Bad multiplier in numerical argument.", 0, true );
      std::exit( 1 );
      }
    for( int i = 0; i < exponent; ++i )
      {
      if( LLONG_MAX / factor >= llabs( 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;
  }


int get_dict_size( const char * const arg )
  {
  char *tail;
  int bits = std::strtol( arg, &tail, 0 );
  if( bits >= min_dictionary_bits &&
      bits <= max_dictionary_bits && *tail == 0 )
    return ( 1 << bits );
  return getnum( arg, min_dictionary_size, max_dictionary_size );
  }


int extension_index( const std::string & name )
  {
  for( int i = 0; known_extensions[i].from; ++i )
    {
    const std::string ext( known_extensions[i].from );
    if( name.size() > ext.size() &&
        name.compare( name.size() - ext.size(), ext.size(), ext ) == 0 )
      return i;
    }
  return -1;
  }


int open_instream( const std::string & name, struct stat * const in_statsp,
                   const Mode program_mode, const int eindex,
                   const bool recompress, const bool to_stdout )
  {
  int infd = -1;
  if( program_mode == m_compress && !recompress && eindex >= 0 )
    {
    if( verbosity >= 0 )
      std::fprintf( stderr, "%s: Input file '%s' already has '%s' suffix.\n",
                    program_name, name.c_str(),
                    known_extensions[eindex].from );
    }
  else
    {
    infd = open( name.c_str(), O_RDONLY | o_binary );
    if( infd < 0 )
      {
      if( verbosity >= 0 )
        std::fprintf( stderr, "%s: Can't open input file '%s': %s.\n",
                      program_name, name.c_str(), std::strerror( errno ) );
      }
    else
      {
      const int i = fstat( infd, in_statsp );
      const mode_t & mode = in_statsp->st_mode;
      const bool can_read = ( i == 0 &&
                              ( S_ISBLK( mode ) || S_ISCHR( mode ) ||
                                S_ISFIFO( mode ) || S_ISSOCK( mode ) ) );
      if( i != 0 || ( !S_ISREG( mode ) && ( !to_stdout || !can_read ) ) )
        {
        if( verbosity >= 0 )
          std::fprintf( stderr, "%s: Input file '%s' is not a regular file%s.\n",
                        program_name, name.c_str(),
                        ( can_read && !to_stdout ) ?
                        " and '--stdout' was not specified" : "" );
        close( infd );
        infd = -1;
        }
      }
    }
  return infd;
  }


void set_c_outname( const std::string & name, const bool multifile )
  {
  output_filename = name;
  if( multifile ) output_filename += "00001";
  output_filename += known_extensions[0].from;
  }


void set_d_outname( const std::string & name, const int i )
  {
  if( i >= 0 )
    {
    const std::string from( known_extensions[i].from );
    if( name.size() > from.size() )
      {
      output_filename.assign( name, 0, name.size() - from.size() );
      output_filename += known_extensions[i].to;
      return;
      }
    }
  output_filename = name; output_filename += ".out";
  if( verbosity >= 1 )
    std::fprintf( stderr, "%s: Can't guess original name for '%s' -- using '%s'.\n",
                  program_name, name.c_str(), output_filename.c_str() );
  }


bool open_outstream( const bool force )
  {
  int flags = O_CREAT | O_WRONLY | o_binary;
  if( force ) flags |= O_TRUNC; else flags |= O_EXCL;

  outfd = open( output_filename.c_str(), flags, outfd_mode );
  if( outfd < 0 && verbosity >= 0 )
    {
    if( errno == EEXIST )
      std::fprintf( stderr, "%s: Output file '%s' already exists, skipping.\n",
                    program_name, output_filename.c_str() );
    else
      std::fprintf( stderr, "%s: Can't create output file '%s': %s.\n",
                    program_name, output_filename.c_str(), std::strerror( errno ) );
    }
  return ( outfd >= 0 );
  }


bool check_tty( const int infd, const Mode program_mode )
  {
  if( program_mode == m_compress && outfd >= 0 && isatty( outfd ) )
    {
    show_error( "I won't write compressed data to a terminal.", 0, true );
    return false;
    }
  if( ( program_mode == m_decompress || program_mode == m_test ) &&
      isatty( infd ) )
    {
    show_error( "I won't read compressed data from a terminal.", 0, true );
    return false;
    }
  return true;
  }


void cleanup_and_fail( const int retval )
  {
  if( delete_output_on_interrupt )
    {
    delete_output_on_interrupt = false;
    if( verbosity >= 0 )
      std::fprintf( stderr, "%s: Deleting output file '%s', if it exists.\n",
                    program_name, output_filename.c_str() );
    if( outfd >= 0 ) { close( outfd ); outfd = -1; }
    if( std::remove( output_filename.c_str() ) != 0 && errno != ENOENT )
      show_error( "WARNING: deletion of output file (apparently) failed." );
    }
  std::exit( retval );
  }


     // Set permissions, owner and times.
void close_and_set_permissions( const struct stat * const in_statsp )
  {
  bool warning = false;
  if( in_statsp )
    {
    // fchown will in many cases return with EPERM, which can be safely ignored.
    if( ( fchown( outfd, in_statsp->st_uid, in_statsp->st_gid ) != 0 &&
          errno != EPERM ) ||
        fchmod( outfd, in_statsp->st_mode ) != 0 ) warning = true;
    }
  if( close( outfd ) != 0 ) cleanup_and_fail( 1 );
  outfd = -1;
  delete_output_on_interrupt = false;
  if( in_statsp )
    {
    struct utimbuf t;
    t.actime = in_statsp->st_atime;
    t.modtime = in_statsp->st_mtime;
    if( utime( output_filename.c_str(), &t ) != 0 ) warning = true;
    }
  if( warning && verbosity >= 1 )
    show_error( "Can't change output file attributes." );
  }


bool next_filename()
  {
  const unsigned int len = std::strlen( known_extensions[0].from );
  if( output_filename.size() >= len + 5 )		// "*00001.lz"
    for( int i = output_filename.size() - len - 1, j = 0; j < 5; --i, ++j )
      {
      if( output_filename[i] < '9' ) { ++output_filename[i]; return true; }
      else output_filename[i] = '0';
      }
  return false;
  }


int compress( const long long member_size, const long long volume_size,
              const Lzma_options & encoder_options, const int infd,
              const Pretty_print & pp, const struct stat * const in_statsp )
  {
  int retval = 0;
  File_header header;
  header.set_magic();
  if( verbosity >= 1 ) pp();
  if( !header.dictionary_size( encoder_options.dictionary_size ) ||
      encoder_options.match_len_limit < min_match_len_limit ||
      encoder_options.match_len_limit > max_match_len )
    internal_error( "invalid argument to encoder" );

  try {
    Matchfinder matchfinder( header.dictionary_size(),
                             encoder_options.match_len_limit, infd );
    header.dictionary_size( matchfinder.dictionary_size() );

    long long in_size = 0, out_size = 0, partial_volume_size = 0;
    while( true )		// encode one member per iteration
      {
      LZ_encoder encoder( matchfinder, header, outfd );
      const long long size =
        std::min( member_size, volume_size - partial_volume_size );
      if( !encoder.encode_member( size ) )
        { pp( "Encoder error" ); retval = 1; break; }
      in_size += matchfinder.data_position();
      out_size += encoder.member_position();
      if( matchfinder.finished() ) break;
      partial_volume_size += encoder.member_position();
      if( partial_volume_size >= volume_size - min_dictionary_size )
        {
        partial_volume_size = 0;
        if( delete_output_on_interrupt )
          {
          close_and_set_permissions( in_statsp );
          if( !next_filename() )
            { pp( "Too many volume files" ); retval = 1; break; }
          if( !open_outstream( true ) ) { retval = 1; break; }
          delete_output_on_interrupt = true;
          }
        }
      matchfinder.reset();
      }

    if( retval == 0 && verbosity >= 1 )
      {
      if( in_size <= 0 || out_size <= 0 )
        std::fprintf( stderr, " no data compressed.\n" );
      else
        std::fprintf( stderr, "%6.3f:1, %6.3f bits/byte, "
                              "%5.2f%% saved, %lld in, %lld out.\n",
                      (double)in_size / out_size,
                      ( 8.0 * out_size ) / in_size,
                      100.0 * ( 1.0 - ( (double)out_size / in_size ) ),
                      in_size, out_size );
      }
    }
  catch( std::bad_alloc )
    {
    pp( "Not enough memory. Try a smaller dictionary size" );
    retval = 1;
    }
  catch( Error e ) { pp(); show_error( e.msg, errno ); retval = 1; }
  return retval;
  }


int fcompress( const long long member_size, const long long volume_size,
               const int infd,
               const Pretty_print & pp, const struct stat * const in_statsp )
  {
  int retval = 0;
  File_header header;
  header.set_magic();
  if( verbosity >= 1 ) pp();

  try {
    Fmatchfinder fmatchfinder( infd );
    header.dictionary_size( fmatchfinder.dictionary_size() );

    long long in_size = 0, out_size = 0, partial_volume_size = 0;
    while( true )		// encode one member per iteration
      {
      FLZ_encoder encoder( fmatchfinder, header, outfd );
      const long long size =
        std::min( member_size, volume_size - partial_volume_size );
      if( !encoder.encode_member( size ) )
        { pp( "Encoder error" ); retval = 1; break; }
      in_size += fmatchfinder.data_position();
      out_size += encoder.member_position();
      if( fmatchfinder.finished() ) break;
      partial_volume_size += encoder.member_position();
      if( partial_volume_size >= volume_size - min_dictionary_size )
        {
        partial_volume_size = 0;
        if( delete_output_on_interrupt )
          {
          close_and_set_permissions( in_statsp );
          if( !next_filename() )
            { pp( "Too many volume files" ); retval = 1; break; }
          if( !open_outstream( true ) ) { retval = 1; break; }
          delete_output_on_interrupt = true;
          }
        }
      fmatchfinder.reset();
      }

    if( retval == 0 && verbosity >= 1 )
      {
      if( in_size <= 0 || out_size <= 0 )
        std::fprintf( stderr, " no data compressed.\n" );
      else
        std::fprintf( stderr, "%6.3f:1, %6.3f bits/byte, "
                              "%5.2f%% saved, %lld in, %lld out.\n",
                      (double)in_size / out_size,
                      ( 8.0 * out_size ) / in_size,
                      100.0 * ( 1.0 - ( (double)out_size / in_size ) ),
                      in_size, out_size );
      }
    }
  catch( std::bad_alloc )
    {
    pp( "Not enough memory. Try a smaller dictionary size" );
    retval = 1;
    }
  catch( Error e ) { pp(); show_error( e.msg, errno ); retval = 1; }
  return retval;
  }


unsigned char xdigit( const int value )
  {
  if( value >= 0 && value <= 9 ) return '0' + value;
  if( value >= 10 && value <= 15 ) return 'A' + value - 10;
  return 0;
  }


void show_trailing_garbage( const uint8_t * const data, const int size,
                            const Pretty_print & pp, const bool all )
  {
  std::string garbage_msg;
  if( !all ) garbage_msg = "first bytes of ";
  garbage_msg += "trailing garbage found = ";
  bool text = true;
  for( int i = 0; i < size; ++i )
    if( !std::isprint( data[i] ) ) { text = false; break; }
  if( text )
    {
    garbage_msg += '\'';
    garbage_msg.append( (const char *)data, size );
    garbage_msg += '\'';
    }
  else
    {
    for( int i = 0; i < size; ++i )
      {
      if( i > 0 ) garbage_msg += ' ';
      garbage_msg += xdigit( data[i] >> 4 );
      garbage_msg += xdigit( data[i] & 0x0F );
      }
    }
  pp( garbage_msg.c_str() );
  }


int decompress( const int infd, const Pretty_print & pp, const bool testing )
  {
  int retval = 0;

  try {
    Range_decoder rdec( infd );
    long long partial_file_pos = 0;
    for( bool first_member = true; ; first_member = false, pp.reset() )
      {
      File_header header;
      rdec.reset_member_position();
      const int size = rdec.read_data( header.data, File_header::size );
      if( rdec.finished() )			// End Of File
        {
        if( first_member )
          { pp( "Error reading member header" ); retval = 1; }
        else if( verbosity >= 4 && size > 0 )
          show_trailing_garbage( header.data, size, pp, true );
        break;
        }
      if( !header.verify_magic() )
        {
        if( first_member )
          { pp( "Bad magic number (file not in lzip format)" ); retval = 2; }
        else if( verbosity >= 4 )
          show_trailing_garbage( header.data, size, pp, false );
        break;
        }
      if( !header.verify_version() )
        {
        if( verbosity >= 0 )
          { pp();
            std::fprintf( stderr, "Version %d member format not supported.\n",
                          header.version() ); }
        retval = 2; break;
        }
      if( header.dictionary_size() < min_dictionary_size ||
          header.dictionary_size() > max_dictionary_size )
        { pp( "Invalid dictionary size in member header" ); retval = 2; break; }

      if( verbosity >= 2 || ( verbosity == 1 && first_member ) )
        {
        pp();
        if( verbosity >= 2 )
          std::fprintf( stderr, "version %d, dictionary size %7sB.  ",
                        header.version(),
                        format_num( header.dictionary_size() ) );
        }

      LZ_decoder decoder( header, rdec, outfd );
      const int result = decoder.decode_member( pp );
      partial_file_pos += rdec.member_position();
      if( result != 0 )
        {
        if( verbosity >= 0 && result <= 2 )
          {
          pp();
          if( result == 2 )
            std::fprintf( stderr, "File ends unexpectedly at pos %lld\n",
                          partial_file_pos );
          else
            std::fprintf( stderr, "Decoder error at pos %lld\n",
                          partial_file_pos );
          }
        retval = 2; break;
        }
      if( verbosity >= 2 )
        { if( testing ) std::fprintf( stderr, "ok\n" );
          else std::fprintf( stderr, "done\n" ); }
      }
    }
  catch( std::bad_alloc )
    {
    pp( "Not enough memory. Find a machine with more memory" );
    retval = 1;
    }
  catch( Error e ) { pp(); show_error( e.msg, errno ); retval = 1; }
  if( verbosity == 1 && retval == 0 )
    { if( testing ) std::fprintf( stderr, "ok\n" );
      else std::fprintf( stderr, "done\n" ); }
  return retval;
  }


extern "C" void signal_handler( int )
  {
  show_error( "Control-C or similar caught, quitting." );
  cleanup_and_fail( 1 );
  }


void set_signals()
  {
  std::signal( SIGHUP, signal_handler );
  std::signal( SIGINT, signal_handler );
  std::signal( SIGTERM, signal_handler );
  }

} // end namespace


void show_error( const char * const msg, const int errcode, const bool help )
  {
  if( verbosity >= 0 )
    {
    if( msg && msg[0] )
      {
      std::fprintf( stderr, "%s: %s", program_name, msg );
      if( errcode > 0 )
        std::fprintf( stderr, ": %s", std::strerror( errcode ) );
      std::fprintf( stderr, "\n" );
      }
    if( help && invocation_name && invocation_name[0] )
      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 );
  }


int main( const int argc, const char * const argv[] )
  {
  // Mapping from gzip/bzip2 style 1..9 compression modes
  // to the corresponding LZMA compression modes.
  const Lzma_options option_mapping[] =
    {
    { 1 << 16,  16 },		// -0 entry values not used
    { 1 << 20,   5 },		// -1
    { 3 << 19,   6 },		// -2
    { 1 << 21,   8 },		// -3
    { 3 << 20,  12 },		// -4
    { 1 << 22,  20 },		// -5
    { 1 << 23,  36 },		// -6
    { 1 << 24,  68 },		// -7
    { 3 << 23, 132 },		// -8
    { 1 << 25, 273 } };		// -9
  Lzma_options encoder_options = option_mapping[6];	// default = "-6"
  long long member_size = LLONG_MAX;
  long long volume_size = LLONG_MAX;
  int infd = -1;
  Mode program_mode = m_compress;
  bool force = false;
  bool keep_input_files = false;
  bool recompress = false;
  bool to_stdout = false;
  bool zero = false;
  std::string input_filename;
  std::string default_output_filename;
  std::vector< std::string > filenames;
  invocation_name = argv[0];

  const Arg_parser::Option options[] =
    {
    { '0', "fast",            Arg_parser::no  },
    { '1',  0,                Arg_parser::no  },
    { '2',  0,                Arg_parser::no  },
    { '3',  0,                Arg_parser::no  },
    { '4',  0,                Arg_parser::no  },
    { '5',  0,                Arg_parser::no  },
    { '6',  0,                Arg_parser::no  },
    { '7',  0,                Arg_parser::no  },
    { '8',  0,                Arg_parser::no  },
    { '9', "best",            Arg_parser::no  },
    { 'b', "member-size",     Arg_parser::yes },
    { 'c', "stdout",          Arg_parser::no  },
    { 'd', "decompress",      Arg_parser::no  },
    { 'f', "force",           Arg_parser::no  },
    { 'F', "recompress",      Arg_parser::no  },
    { 'h', "help",            Arg_parser::no  },
    { 'k', "keep",            Arg_parser::no  },
    { 'm', "match-length",    Arg_parser::yes },
    { 'o', "output",          Arg_parser::yes },
    { 'q', "quiet",           Arg_parser::no  },
    { 's', "dictionary-size", Arg_parser::yes },
    { 'S', "volume-size",     Arg_parser::yes },
    { 't', "test",            Arg_parser::no  },
    { 'v', "verbose",         Arg_parser::no  },
    { 'V', "version",         Arg_parser::no  },
    {  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 '0': zero = true; break;
      case '1': case '2': case '3': case '4':
      case '5': case '6': case '7': case '8': case '9':
                zero = false;
                encoder_options = option_mapping[code-'0']; break;
      case 'b': member_size = getnum( arg, 100000, LLONG_MAX / 2 ); break;
      case 'c': to_stdout = true; break;
      case 'd': program_mode = m_decompress; break;
      case 'f': force = true; break;
      case 'F': recompress = true; break;
      case 'h': show_help(); return 0;
      case 'k': keep_input_files = true; break;
      case 'm': encoder_options.match_len_limit =
                  getnum( arg, min_match_len_limit, max_match_len );
                zero = false; break;
      case 'o': default_output_filename = arg; break;
      case 'q': verbosity = -1; break;
      case 's': encoder_options.dictionary_size = get_dict_size( arg );
                zero = false; break;
      case 'S': volume_size = getnum( arg, 100000, LLONG_MAX / 2 ); break;
      case 't': program_mode = m_test; break;
      case 'v': if( verbosity < 4 ) ++verbosity; break;
      case 'V': show_version(); return 0;
      default : internal_error( "uncaught option" );
      }
    } // end process options

#if defined(__MSVCRT__) || defined(__OS2__)
  _fsetmode( stdin, "b" );
  _fsetmode( stdout, "b" );
#endif

  if( program_mode == m_test )
    outfd = -1;
  else if( program_mode == m_compress )
    {
    dis_slots.init();
    prob_prices.init();
    }

  bool filenames_given = false;
  for( ; argind < parser.arguments(); ++argind )
    {
    if( parser.argument( argind ) != "-" ) filenames_given = true;
    filenames.push_back( parser.argument( argind ) );
    }

  if( filenames.empty() ) filenames.push_back("-");
  if( !to_stdout && program_mode != m_test &&
      ( filenames_given || default_output_filename.size() ) )
    set_signals();

  Pretty_print pp( filenames, verbosity );

  int retval = 0;
  for( unsigned int i = 0; i < filenames.size(); ++i )
    {
    struct stat in_stats;
    output_filename.clear();

    if( !filenames[i].size() || filenames[i] == "-" )
      {
      input_filename.clear();
      infd = STDIN_FILENO;
      if( program_mode != m_test )
        {
        if( to_stdout || !default_output_filename.size() )
          outfd = STDOUT_FILENO;
        else
          {
          if( program_mode == m_compress )
            set_c_outname( default_output_filename, volume_size != LLONG_MAX );
          else output_filename = default_output_filename;
          outfd_mode = all_rw;
          if( !open_outstream( force ) )
            {
            if( outfd == -1 && retval < 1 ) retval = 1;
            close( infd ); infd = -1;
            continue;
            }
          }
        }
      }
    else
      {
      input_filename = filenames[i];
      const int eindex = extension_index( input_filename );
      infd = open_instream( input_filename, &in_stats, program_mode,
                            eindex, recompress, to_stdout );
      if( infd < 0 ) { if( retval < 1 ) retval = 1; continue; }
      if( program_mode != m_test )
        {
        if( to_stdout ) outfd = STDOUT_FILENO;
        else
          {
          if( program_mode == m_compress )
            set_c_outname( input_filename, volume_size != LLONG_MAX );
          else set_d_outname( input_filename, eindex );
          outfd_mode = usr_rw;
          if( !open_outstream( force ) )
            {
            if( outfd == -1 && retval < 1 ) retval = 1;
            close( infd ); infd = -1;
            continue;
            }
          }
        }
      }

    if( !check_tty( infd, program_mode ) ) return 1;

    if( output_filename.size() && !to_stdout && program_mode != m_test )
      delete_output_on_interrupt = true;
    const struct stat * const in_statsp = input_filename.size() ? &in_stats : 0;
    pp.set_name( input_filename );
    int tmp = 0;
    if( program_mode == m_compress )
      {
      if( zero )
        tmp = fcompress( member_size, volume_size, infd, pp, in_statsp );
      else
        tmp = compress( member_size, volume_size, encoder_options, infd,
                        pp, in_statsp );
      }
    else
      tmp = decompress( infd, pp, program_mode == m_test );
    if( tmp > retval ) retval = tmp;
    if( tmp && program_mode != m_test ) cleanup_and_fail( retval );

    if( delete_output_on_interrupt )
      close_and_set_permissions( in_statsp );
    if( input_filename.size() )
      {
      close( infd ); infd = -1;
      if( !keep_input_files && !to_stdout && program_mode != m_test )
        std::remove( input_filename.c_str() );
      }
    }
  if( outfd >= 0 && close( outfd ) != 0 )
    {
    show_error( "Can't close stdout", errno );
    if( retval < 1 ) retval = 1;
    }
  return retval;
  }