summaryrefslogtreecommitdiffstats
path: root/zcmp.cc
blob: 5336a13a8bc45b3e11d9622579ef6e15fa1e1abf (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
/* Zcmp - decompress and compare two files byte by byte
   Copyright (C) 2010-2024 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/>.
*/

#define _FILE_OFFSET_BITS 64

#include <algorithm>
#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 "rc.h"
#include "zutils.h"

#ifndef LLONG_MAX
#define LLONG_MAX 0x7FFFFFFFFFFFFFFFLL
#endif


namespace {

#include "zcmpdiff.cc"

void show_help()
  {
  std::printf( "zcmp compares two files and, if they differ, writes to standard output the\n"
               "first byte and line number where they differ. Bytes and lines are numbered\n"
               "starting with 1. A hyphen '-' used as a file argument means standard input.\n"
               "If any file given is compressed, its decompressed content is used. Compressed\n"
               "files are decompressed on the fly; no temporary files are created.\n"
               "\nThe formats supported are bzip2, gzip, lzip, xz, and zstd.\n"
               "\nUsage: zcmp [options] file1 [file2]\n"
               "\nzcmp compares file1 to file2. The standard input is used only if file1 or\n"
               "file2 refers to standard input. If file2 is omitted zcmp tries to compare\n"
               "file1 with the corresponding uncompressed file (if file1 is compressed), and\n"
               "then with the corresponding compressed files of the remaining formats until\n"
               "one is found.\n"
               "\nExit status is 0 if inputs are identical, 1 if different, 2 if trouble.\n"
               "\nOptions:\n"
               "  -h, --help                        display this help and exit\n"
               "  -V, --version                     output version information and exit\n"
               "  -b, --print-bytes                 print differing bytes\n"
               "  -H, --hexadecimal                 print hexadecimal values instead of octal\n"
               "  -i, --ignore-initial=<n>[:<n2>]   ignore differences in the first <n> bytes\n"
               "  -l, --list                        list position, value of all differing bytes\n"
               "  -M, --format=<list>               process only the formats in <list>\n"
               "  -n, --bytes=<n>                   compare at most <n> bytes\n"
               "  -N, --no-rcfile                   don't read runtime configuration file\n"
               "  -O, --force-format=[<f1>][,<f2>]  force one or both input formats\n"
               "  -q, --quiet, --silent             suppress diagnostics written to stderr\n"
               "  -s, --script                      suppress messages about file differences\n"
               "  -v, --verbose                     verbose mode (opposite of --quiet)\n"
               "      --bz2=<command>               set compressor and options for bzip2 format\n"
               "      --gz=<command>                set compressor and options for gzip format\n"
               "      --lz=<command>                set compressor and options for lzip format\n"
               "      --xz=<command>                set compressor and options for xz format\n"
               "      --zst=<command>               set compressor and options for zstd format\n"
               "\nValid formats for options '-M' and '-O' are 'bz2', 'gz', 'lz', 'xz', 'zst',\n"
               "and 'un' for uncompressed.\n"
               "\nByte counts given as arguments to options may be expressed in decimal,\n"
               "hexadecimal, or octal (using the same syntax as integer constants in C++),\n"
               "and 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" );
  show_help_addr();
  }


// separate numbers of 5 or more digits in groups of 3 digits using '_'
const char * format_num3( long long num )
  {
  enum { buffers = 8, bufsize = 4 * sizeof num, n = 10 };
  const char * const si_prefix = "kMGTPEZYRQ";
  const char * const binary_prefix = "KMGTPEZYRQ";
  static char buffer[buffers][bufsize];	// circle of static buffers for printf
  static int current = 0;

  char * const buf = buffer[current++]; current %= buffers;
  char * p = buf + bufsize - 1;		// fill the buffer backwards
  *p = 0;	// terminator
  const bool negative = num < 0;
  if( num > 1024 || num < -1024 )
    {
    char prefix = 0;			// try binary first, then si
    for( int i = 0; i < n && num != 0 && num % 1024 == 0; ++i )
      { num /= 1024; prefix = binary_prefix[i]; }
    if( prefix ) *(--p) = 'i';
    else
      for( int i = 0; i < n && num != 0 && num % 1000 == 0; ++i )
        { num /= 1000; prefix = si_prefix[i]; }
    if( prefix ) *(--p) = prefix;
    }
  const bool split = num >= 10000 || num <= -10000;

  for( int i = 0; ; )
    {
    const long long onum = num; num /= 10;
    *(--p) = llabs( onum - ( 10 * num ) ) + '0'; if( num == 0 ) break;
    if( split && ++i >= 3 ) { i = 0; *(--p) = '_'; }
    }
  if( negative ) *(--p) = '-';
  return p;
  }


// Recognized formats: <num>k[B], <num>Ki[B], <num>[MGTPEZYRQ][i][B]
long long getnum( const char * const arg, const char * const option_name,
                  const char ** const tailp = 0,
                  const long long llimit = 0,
                  const long long ulimit = LLONG_MAX )
  {
  char * tail;
  errno = 0;
  long long result = strtoll( arg, &tail, 0 );
  if( tail == arg )
    { show_option_error( arg, "Bad or missing numerical argument in",
                         option_name ); std::exit( 2 ); }
  if( result < 0 ) errno = ERANGE;

  if( !errno && tail[0] && std::isalpha( tail[0] ) )
    {
    const unsigned char ch = *tail++;
    int factor;
    bool bsuf;					// 'B' suffix is present
    if( tail[0] == 'i' ) { ++tail; factor = 1024; } else factor = 1000;
    if( tail[0] == 'B' ) { ++tail; bsuf = true; } else bsuf = false;
    int exponent = -1;				// -1 = bad multiplier
    switch( ch )
      {
      case 'Q': exponent = 10; break;
      case 'R': exponent = 9; 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;
      case 'B': if( factor == 1000 && !bsuf ) exponent = 0; break;
      }
    if( exponent < 0 )
      { show_option_error( arg, "Bad multiplier in numerical argument of",
                           option_name ); std::exit( 2 ); }
    for( int i = 0; i < exponent; ++i )
      {
      if( ulimit / factor >= result ) result *= factor;
      else { errno = ERANGE; break; }
      }
    }
  if( !errno && ( result < llimit || result > ulimit ) ) errno = ERANGE;
  if( errno )
    {
    if( verbosity >= 0 )
      std::fprintf( stderr, "%s: '%s': Value out of limits [%s,%s] in "
                    "option '%s'.\n", program_name, arg, format_num3( llimit ),
                    format_num3( ulimit ), option_name );
    std::exit( 2 );
    }
  if( tailp ) *tailp = tail;
  return result;
  }


void parse_ignore_initial( const char * const arg, const char * const pn,
                           long long ignore_initial[2] )
  {
  const char * tail;
  ignore_initial[0] = getnum( arg, pn, &tail );
  if( *tail == ':' || *tail == ',' )
    ignore_initial[1] = getnum( ++tail, pn );
  else if( *tail == 0 ) ignore_initial[1] = ignore_initial[0];
  else { show_option_error( arg, "Missing colon in", pn ); std::exit( 2 ); }
  }


bool skip_ignore_initial( const long long ignore_initial, const int infd )
  {
  if( ignore_initial > 0 )
    {
    const int 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;			// EOF
      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,
                   unsigned long long * const line_numberp )
  {
  const uint8_t * p0 = buffer0;
  const uint8_t * p1 = buffer1;

  if( line_numberp )
    {
    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], bool finished[2],
         const bool hexadecimal, const bool list, const bool print_bytes,
         const bool scripted )
  {
  const int buffer_size = 4096;
  unsigned long long byte_number = 1;
  unsigned long long line_number = 1;
  // remaining number of bytes to compare
  long long rest = ( max_size >= 0 ) ? max_size : buffer_size;
  // 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 retval = 0;
  bool empty[2] = { true, true };

  while( rest > 0 )
    {
    const int size = std::min( (long long)buffer_size, rest );
    if( max_size >= 0 ) rest -= 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_file_error( filenames[i].c_str(), "Read error", errno );
          retval = 2; goto done; }
      if( rd[i] > 0 ) empty[i] = false;
      }
    for( int i = 0; i < 2; ++i )
      if( rd[i] < size ) finished[i] = true;

    const int min_rd = std::min( rd[0], rd[1] );
    buffer0[min_rd] = 0;		// sentinels for the block compare
    buffer1[min_rd] = 1;

    int first_diff = block_compare( buffer0, buffer1, list ? 0 : &line_number );
    byte_number += first_diff;

    if( first_diff < min_rd )
      {
      retval = 1;				// difference found
      if( scripted ) break;			// status only
      if( !list )				// show first difference
        {
        if( !print_bytes )
          std::printf( "%s %s differ: byte %llu, line %llu\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( hexadecimal ?
                       "%s %s differ: byte %llu, line %llu is %02X %s %02X %s\n" :
                       "%s %s differ: byte %llu, line %llu is %3o %s %3o %s\n",
                       filenames[0].c_str(), filenames[1].c_str(),
                       byte_number, line_number, c0, buf0, c1, buf1 );
          }
        std::fflush( stdout );
        break;
        }
      else			// list ; show all differences
        {
        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( hexadecimal ? "%llu %02X %02X\n" : "%llu %3o %3o\n",
                           byte_number, c0, c1 );
            else
              {
              char buf0[5], buf1[5];
              sprintc( buf0, c0 ); sprintc( buf1, c1 );
              std::printf( hexadecimal ? "%llu %02X %-4s %02X %s\n" :
                           "%llu %3o %-4s %3o %s\n",
                           byte_number, c0, buf0, c1, buf1 );
              }
            }
          }
        std::fflush( stdout );
        }
      }

    if( rd[0] != rd[1] )
      {
      const int i = rd[1] < rd[0];
      if( verbosity >= 0 )
        std::fprintf( stderr, empty[i] ?
                      "%s: EOF on %s which is empty\n" : list ?
                      "%s: EOF on %s after byte %llu\n" :
                      "%s: EOF on %s after byte %llu, in line %llu\n",
                      program_name, filenames[i].c_str(),
                      byte_number - 1, line_number );
      retval = 1; break;
      }
    if( min_rd != buffer_size ) break;
    }
done:
  delete[] buffer0;
  return retval;
  }

} // end namespace


int main( const int argc, const char * const argv[] )
  {
  enum { bz2_opt = 256, gz_opt, lz_opt, xz_opt, zst_opt };
  // number of initial bytes ignored for each file
  long long ignore_initial[2] = { 0, 0 };
  long long max_size = -1;			// < 0 means unlimited size
  int format_types[2] = { -1, -1 };		// < 0 means undefined
  bool hexadecimal = false;
  bool list = false;		// list position, value of all differing bytes
  bool print_bytes = false;	// print differing bytes
  bool scripted = false;	// suppress messages about file differences
  program_name = "zcmp";
  invocation_name = ( argc > 0 ) ? argv[0] : program_name;

  const Arg_parser::Option options[] =
    {
    { 'b', "print-bytes",    Arg_parser::no  },
    { 'h', "help",           Arg_parser::no  },
    { 'H', "hexadecimal",    Arg_parser::no  },
    { 'i', "ignore-initial", Arg_parser::yes },
    { 'l', "list",           Arg_parser::no  },
    { 'M', "format",         Arg_parser::yes },
    { 'n', "bytes",          Arg_parser::yes },
    { 'N', "no-rcfile",      Arg_parser::no  },
    { 'O', "force-format",   Arg_parser::yes },
    { 'q', "quiet",          Arg_parser::no  },
    { 'q', "silent",         Arg_parser::no  },
    { 's', "script",         Arg_parser::no  },
    { 'v', "verbose",        Arg_parser::no  },
    { 'V', "version",        Arg_parser::no  },
    { bz2_opt, "bz2",        Arg_parser::yes },
    { gz_opt,  "gz",         Arg_parser::yes },
    { lz_opt,  "lz",         Arg_parser::yes },
    { xz_opt,  "xz",         Arg_parser::yes },
    { zst_opt, "zst",        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 2; }

  maybe_process_config_file( parser );

  int argind = 0;
  for( ; argind < parser.arguments(); ++argind )
    {
    const int code = parser.code( argind );
    if( !code ) break;					// no more options
    const char * const pn = parser.parsed_name( argind ).c_str();
    const std::string & sarg = parser.argument( argind );
    const char * const arg = sarg.c_str();
    switch( code )
      {
      case 'b': print_bytes = true; break;
      case 'h': show_help(); return 0;
      case 'H': hexadecimal = true; break;
      case 'i': parse_ignore_initial( arg, pn, ignore_initial ); break;
      case 'l': list = true; break;
      case 'M': parse_format_list( sarg, pn ); break;
      case 'n': max_size = getnum( arg, pn ); break;
      case 'N': break;
      case 'O': parse_format_types2( sarg, pn, format_types ); break;
      case 'q': verbosity = -1; break;
      case 's': scripted = true; break;
      case 'v': if( verbosity < 4 ) ++verbosity; break;
      case 'V': show_version(); return 0;
      case bz2_opt: parse_compressor( sarg, pn, fmt_bz2 ); break;
      case gz_opt: parse_compressor( sarg, pn, fmt_gz ); break;
      case lz_opt: parse_compressor( sarg, pn, fmt_lz ); break;
      case xz_opt: parse_compressor( sarg, pn, fmt_xz ); break;
      case zst_opt: parse_compressor( sarg, pn, fmt_zst ); break;
      default: internal_error( "uncaught option." );
      }
    } // end process options

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

  const int files = parser.arguments() - argind;
  if( files < 1 ) { show_error( "No files given.", 0, true ); return 2; }
  if( files > 2 ) { show_error( "Too many files.", 0, true ); return 2; }

  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 == 2 )
    {
    if( 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; }
      }
    infd[1] = ( filenames[1] == "-" ) ?
      STDIN_FILENO : open_instream( filenames[1] );
    if( infd[1] < 0 ) return 2;
    }
  else
    {
    if( filenames[0] == "-" )
      { show_error( "Missing operand after '-'.", 0, true ); return 2; }
    if( format_types[0] >= 0 || format_types[1] >= 0 )
      { show_error( "Two files must be given when format is specified.", 0, true );
        return 2; }
    filenames[1] = filenames[0];
    infd[1] = open_other_instream( filenames[1] );
    if( infd[1] < 0 )
      {
      if( verbosity >= 0 )
        std::fprintf( stderr, "%s: Can't find file to compare with '%s'.\n",
                      program_name, filenames[0].c_str() );
      show_error( 0, 0, true ); return 2;
      }
    }

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

  for( int i = 0; i < 2; ++i )
    if( !skip_ignore_initial( ignore_initial[i], infd[i] ) )
      {
      show_file_error( filenames[i].c_str(),
                       "Read error skipping initial bytes", errno );
      return 2;
      }

  bool finished[2] = { false, false };
  int retval = cmp( max_size, infd, filenames, finished, hexadecimal, list,
                    print_bytes, scripted );

  for( int i = 0; i < 2; ++i )
    if( !good_status( children[i], finished[i] ) ) retval = 2;

  for( int i = 0; i < 2; ++i )
    {
    if( close( infd[i] ) != 0 )
      { show_close_error(); retval = 2; }
    if( filenames[i] != "-" && close( old_infd[i] ) != 0 )
      {
      show_file_error( filenames[i].c_str(), "Error closing input file", errno );
      retval = 2;
      }
    }
  if( std::fclose( stdout ) != 0 )
    {
    show_error( "Error closing stdout", errno );
    retval = 2;
    }

  return retval;
  }