summaryrefslogtreecommitdiffstats
path: root/zcmp.cc
blob: 7951046f86d1c22c58e7e37ed390e444d8f1d268 (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
/*  Zcmp - decompress and compare two files byte by byte
    Copyright (C) 2010 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 <cctype>
#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 <sys/stat.h>
#if defined(__MSVCRT__) || defined(__OS2__)
#include <io.h>
#endif

#include "arg_parser.h"
#include "zutils.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 {

#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[] = {
  { ".bz2",  ""     },
  { ".tbz",  ".tar" },
  { ".tbz2", ".tar" },
  { ".gz",   ""     },
  { ".tgz",  ".tar" },
  { ".lz",   ""     },
  { ".tlz",  ".tar" },
  { ".xz",   ""     },
  { ".txz",  ".tar" },
  { 0,       0      } };


void show_help() throw()
  {
  std::printf( "Zcmp compares two files (\"-\" means standard input), and if they\n" );
  std::printf( "differ, tells the first byte and line number where they differ. Bytes\n" );
  std::printf( "and lines are numbered starting with 1. If any given file is compressed,\n" );
  std::printf( "its uncompressed content is used. Compressed files are uncompressed on\n" );
  std::printf( "the fly; no temporary files are created.\n" );
  std::printf( "The supported compressors are bzip2, gzip, lzip and xz.\n" );
  std::printf( "\nUsage: zcmp [options] file1 [file2]\n" );
  std::printf( "\nCompares <file1> to <file2>. If <file2> is omitted zcmp tries the\n" );
  std::printf( "following:\n" );
  std::printf( "If <file1> is compressed, compares <file1> to the file with the\n" );
  std::printf( "corresponding decompressed file name (removes the extension from\n" );
  std::printf( "<file1>).\n" );
  std::printf( "If <file1> is not compressed, compares <file1> to the uncompressed\n" );
  std::printf( "contents of <file1>.[bz2|gz|lz|xz] (the first one that is found).\n" );
  std::printf( "If no suitable file is found, compares <file1> to data read from\n" );
  std::printf( "standard input.\n" );
  std::printf( "\nExit status is 0 if inputs are identical, 1 if different, 2 if trouble.\n" );
  std::printf( "\nOptions:\n" );
  std::printf( "  -h, --help                       display this help and exit\n" );
  std::printf( "  -V, --version                    output version information and exit\n" );
  std::printf( "  -b, --print-bytes                print differing bytes\n" );
  std::printf( "  -i, --ignore-initial=<n>[,<n2>]  ignore differences in the first <n> bytes\n" );
  std::printf( "  -l, --list                       list position, value of all differing bytes\n" );
  std::printf( "  -n, --bytes=<n>                  compare at most <n> bytes\n" );
  std::printf( "  -q, --quiet                      suppress all messages\n" );
  std::printf( "  -s, --silent                     (same as --quiet)\n" );
  std::printf( "  -v, --verbose                    verbose mode (same as --list)\n" );
  std::printf( "Numbers may be followed by a multiplier: k = kB = 10^3 = 1000,\n" );
  std::printf( "Ki = KiB = 2^10 = 1024, M = 10^6, Mi = 2^20, G = 10^9, Gi = 2^30, etc...\n" );
  show_help_addr();
  }


long long getnum( const char * const ptr, const char ** const tailp = 0,
                  const long long llimit = LLONG_MIN + 1,
                  const long long ulimit = LLONG_MAX ) throw()
  {
  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( 2 );
    }

  if( !errno && tail[0] && std::isalpha( tail[0] ) )
    {
    int factor = ( tail[1] == 'i' ) ? 1024 : 1000;
    int exponent = 0;
    bool bad_multiplier = false;
    switch( tail[0] )
      {
      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( 2 );
      }
    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( 2 );
    }
  if( tailp ) *tailp = tail;
  return result;
  }


int open_instream( const std::string & input_filename ) throw()
  {
  int infd = open( input_filename.c_str(), O_RDONLY | o_binary );
  if( infd < 0 )
    show_error2( "Can't open input file", input_filename.c_str() );
  return infd;
  }


int open_other_instream( std::string & name ) throw()
  {
  for( int i = 0; known_extensions[i].from; ++i )
    {					// search uncompressed version
    const std::string from( known_extensions[i].from );
    if( name.size() > from.size() &&
        name.compare( name.size() - from.size(), from.size(), from ) == 0 )
      {
      name.resize( name.size() - from.size() );
      name += known_extensions[i].to;
      return open( name.c_str(), O_RDONLY | o_binary );
      }
    }
  for( int i = 0; simple_extensions[i]; ++i )
    {					// search compressed version
    const std::string s( name + simple_extensions[i] );
    const int infd = open( s.c_str(), O_RDONLY | o_binary );
    if( infd >= 0 ) { name = s; return infd; }
    }
  return -1;
  }


bool check_identical( const char * const name1, const char * const name2 ) throw()
  {
  if( !std::strcmp( name1, name2 ) ) return true;
  struct stat stat1, stat2;
  if( stat( name1, &stat1 ) || stat( name2, &stat2 ) ) return false;
  return ( stat1.st_ino == stat2.st_ino && stat1.st_dev == stat2.st_dev );
  }


void parse_ignore_initial( const char * const arg, long long ignore_initial[2] )
  {
  const char * tail;
  ignore_initial[0] = getnum( arg, &tail, 0 );
  if( *tail == ',' || *tail == ':' )
    ignore_initial[1] = getnum( ++tail, 0, 0 );
  else ignore_initial[1] = ignore_initial[0];
  }


bool skip_ignore_initial( const long long ignore_initial, const int infd )
  {
  if( ignore_initial > 0 )
    {
    enum { buffer_size = 4096 };
    long long rest = ignore_initial;
    uint8_t buffer[buffer_size];
    while( rest > 0 )
      {
      const int size = std::min( rest, (long long)buffer_size );
      const int rd = readblock( infd, buffer, size );
      if( rd != size && errno ) return false;
      if( rd < size ) break;
      rest -= rd;
      }
    }
  return true;
  }


// Put into buf the unsigned char c, making unprintable bytes
// visible by quoting like cat -t does.
void sprintc( char * const buf, unsigned char c )
  {
  int i = 0;

  if( c < 32 || c >= 127 )
    {
    if( c >= 128 ) { c -= 128; buf[i++] = 'M'; buf[i++] = '-'; }
    if( c < 32 ) { c += 64; buf[i++] = '^'; }
    else if( c == 127 ) { c = '?'; buf[i++] = '^'; }
    }
  buf[i++] = c;
  buf[i++] = 0;
  }


int block_compare( const uint8_t * const buffer0,
                   const uint8_t * const buffer1,
                   long long * line_numberp )
  {
  const uint8_t * p0 = buffer0;
  const uint8_t * p1 = buffer1;
  if( verbosity == 0 )
    {
    int nl_count = 0;
    while( *p0 == *p1 )
      { if( *p0 == '\n' ) { ++nl_count; } ++p0; ++p1; }
    *line_numberp += nl_count;
    }
  else while( *p0 == *p1 ) { ++p0; ++p1; }
  return p0 - buffer0;
  }


int cmp( const long long max_size, const int infd[2],
         const std::string filenames[2], const bool print_bytes )
  {
  enum { buffer_size = 4096 };
  long long byte_number = 1;
  long long line_number = 1;
  long long rest = max_size;	// remaining number of bytes to compare
  // buffers with space for sentinels at the end
  uint8_t * const buffer0 = new uint8_t[2*(buffer_size+1)];
  uint8_t * const buffer1 = buffer0 + buffer_size + 1;
  uint8_t * buffer[2];
  buffer[0] = buffer0; buffer[1] = buffer1;
  int different = 0;

  while( rest > 0 )
    {
    const int size = std::min( rest, (long long)buffer_size );
    int rd[2];			// number of bytes read from each file
    for( int i = 0; i < 2; ++i )
      {
      rd[i] = readblock( infd[i], buffer[i], size );
      if( rd[i] != size && errno )
        {
        show_error2( "Error reading file", filenames[i].c_str() );
        return 2;
        }
      }
    rest -= size;

    buffer0[rd[0]] = ~buffer1[rd[0]];	// sentinels for the block compare
    buffer1[rd[1]] = ~buffer0[rd[1]];

    int first_diff = block_compare( buffer0, buffer1, &line_number );
    byte_number += first_diff;
    const int min_rd = std::min( rd[0], rd[1] );

    if( first_diff < min_rd )
      {
      if( verbosity < 0 ) return 1;		// return status only
      if( verbosity == 0 )			// show first difference
        {
        if( !print_bytes )
          std::printf( "%s %s differ: byte %lld, line %lld\n",
                       filenames[0].c_str(), filenames[1].c_str(),
                       byte_number, line_number );
        else
          {
          const unsigned char c0 = buffer0[first_diff];
          const unsigned char c1 = buffer1[first_diff];
          char buf0[5], buf1[5];
          sprintc( buf0, c0 ); sprintc( buf1, c1 );
          std::printf( "%s %s differ: byte %lld, line %lld is %3o %s %3o %s\n",
                       filenames[0].c_str(), filenames[1].c_str(),
                       byte_number, line_number, c0, buf0, c1, buf1 );
          }
        return 1;
        }
      else			// verbosity > 0 ; show all differences
        {
        different = 1;
        for( ; first_diff < min_rd; ++byte_number, ++first_diff )
          {
          const unsigned char c0 = buffer0[first_diff];
          const unsigned char c1 = buffer1[first_diff];
          if( c0 != c1 )
            {
            if( !print_bytes )
              std::printf( "%lld %3o %3o\n", byte_number, c0, c1 );
            else
              {
              char buf0[5], buf1[5];
              sprintc( buf0, c0 ); sprintc( buf1, c1 );
              std::printf( "%lld %3o %-4s %3o %s\n",
                           byte_number, c0, buf0, c1, buf1 );
              }
            }
          }
        }
      }

    if( rd[0] != rd[1] )
      {
      if( verbosity >= 0 )
        std::fprintf( stderr, "%s: EOF on %s\n",
                      util_name, filenames[rd[1]<rd[0]].c_str() );
        return 1;
      }
    if( min_rd != buffer_size ) break;
    }

  delete[] buffer0;
  return different;
  }

} // end namespace


int main( const int argc, const char * const argv[] )
  {
  // number of initial bytes ignored for each file
  long long ignore_initial[2] = { 0, 0 };
  long long max_size = LLONG_MAX;
  bool print_bytes = false;
  invocation_name = argv[0];
  util_name = "zcmp";

  const Arg_parser::Option options[] =
    {
    { 'b', "print-bytes",    Arg_parser::no  },
    { 'h', "help",           Arg_parser::no  },
    { 'i', "ignore-initial", Arg_parser::yes },
    { 'l', "list",           Arg_parser::no  },
    { 'n', "bytes",          Arg_parser::yes },
    { 'q', "quiet",          Arg_parser::no  },
    { 's', "silent",         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 2; }

  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 'b': print_bytes = true; break;
      case 'h': show_help(); return 0;
      case 'i': parse_ignore_initial( arg, ignore_initial ); break;
      case 'l': verbosity = 1; break;
      case 'n': max_size = getnum( arg, 0, 0 ); break;
      case 'q':
      case 's': verbosity = -1; break;
      case 'v': verbosity = 1; break;
      case 'V': show_version( "Zcmp" ); return 0;
      default : internal_error( "uncaught option" );
      }
    } // end process options

#if defined(__MSVCRT__) || defined(__OS2__)
  _setmode( STDIN_FILENO, O_BINARY );
  _setmode( STDOUT_FILENO, O_BINARY );
#endif

  if( argind >= parser.arguments() )
    { show_error( "No files given.", 0, true ); return 2; }
  if( argind + 2 < parser.arguments() )
    { show_error( "Too many files.", 0, true ); return 2; }

  const int files = parser.arguments() - argind;
  std::string filenames[2];		// file names of the two input files
  filenames[0] = parser.argument( argind );
  if( files == 2 ) filenames[1] = parser.argument( argind + 1 );

  int infd[2];				// file descriptors of the two files
  infd[0] = ( filenames[0] == "-" ) ?
    STDIN_FILENO : open_instream( filenames[0] );
  if( infd[0] < 0 ) return 2;

  if( ( files == 1 && filenames[0] == "-" ) ||
      ( files == 2 && check_identical( filenames[0].c_str(),
                                       filenames[1].c_str() ) ) )
    {
    if( ignore_initial[0] == ignore_initial[1] ) return 0;
    else { show_error( "Can't compare parts of same file." ); return 2; }
    }

  if( files == 2 )
    {
    infd[1] = ( filenames[1] == "-" ) ?
      STDIN_FILENO : open_instream( filenames[1] );
    if( infd[1] < 0 ) return 2;
    }
  else
    {
    filenames[1] = filenames[0];
    infd[1] = open_other_instream( filenames[1] );
    if( infd[1] < 0 ) { infd[1] = STDIN_FILENO; filenames[1] = "-"; }
    }

  int old_infd[2];		// copy of file descriptors of the two files
  old_infd[0] = infd[0]; old_infd[1] = infd[1];
  pid_t pid[2];
  if( !set_data_feeder( &infd[0], &pid[0] ) ||
      !set_data_feeder( &infd[1], &pid[1] ) )
    return 2;

  for( int i = 0; i < 2; ++i )
    if( !skip_ignore_initial( ignore_initial[i], infd[i] ) )
      {
      show_error2( "Can't skip initial bytes from file", filenames[i].c_str() );
      return 2;
      }

  int retval = cmp( max_size, infd, filenames, print_bytes );

  if( retval != 0 )
    {
    if( pid[0] ) kill( pid[0], SIGTERM );
    if( pid[1] ) kill( pid[1], SIGTERM );
    }
  else
    if( ( pid[0] && wait_for_child( pid[0], "data feeder" ) != 0 ) ||
        ( pid[1] && wait_for_child( pid[1], "data feeder" ) != 0 ) )
      retval = 2;

  for( int i = 0; i < 2; ++i )
    {
    if( close( infd[i] ) != 0 )
      { show_close_error( "data feeder" ); retval = 2; }
    if( filenames[i] != "-" && close( old_infd[i] ) != 0 )
      {
      show_error2( "Can't close input file", filenames[i].c_str() );
      retval = 2;
      }
    }
  if( std::fclose( stdout ) != 0 )
    {
    show_error( "Can't close stdout", errno );
    retval = 2;
    }

  return retval;
  }