summaryrefslogtreecommitdiffstats
path: root/zgrep.cc
blob: 77300677051a512ef8f618c436f094423e5ba5ee (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
/*  Zgrep - search compressed files for a regular expression
    Copyright (C) 2010, 2011, 2012, 2013, 2014 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 <csignal>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <list>
#include <string>
#include <vector>
#include <dirent.h>
#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 O_BINARY
#define O_BINARY 0
#endif


namespace {

#include "recursive.cc"

void show_help()
  {
  std::printf( "Zgrep is a front end to the grep program that allows transparent search\n"
               "on any combination of compressed and uncompressed files. If any given\n"
               "file is compressed, its decompressed content is used. If a given file\n"
               "does not exist, and its name does not end with one of the known\n"
               "extensions, zgrep tries the compressed file names corresponding to the\n"
               "supported formats. If no files are specified, data is read from\n"
               "standard input, decompressed if needed, and fed to grep. Data read from\n"
               "standard input must be of the same type; all uncompressed or all\n"
               "in the same compression format.\n"
               "\nThe supported formats are bzip2, gzip, lzip and xz.\n"
               "\nUsage: zgrep [options] <pattern> [files]\n"
               "\nExit status is 0 if match, 1 if no match, 2 if trouble.\n"
               "\nOptions:\n"
               "      --help                 display this help and exit\n"
               "  -V, --version              output version information and exit\n"
               "  -a, --text                 treat all files as text\n"
               "  -A, --after-context=<n>    print <n> lines of trailing context\n"
               "  -b, --byte-offset          print the byte offset of each line\n"
               "  -B, --before-context=<n>   print <n> lines of leading context\n"
               "  -c, --count                only print a count of matching lines per file\n"
               "  -C, --context=<n>          print <n> lines of output context\n"
               "  -e, --regexp=<pattern>     use <pattern> as the pattern to match\n"
               "  -E, --extended-regexp      <pattern> is an extended regular expression\n"
               "  -f, --file=<file>          obtain patterns from <file>\n"
               "  -F, --fixed-strings        <pattern> is a set of newline-separated strings\n"
               "      --format=<fmt>         force given format (bz2, gz, lz, xz)\n"
               "  -h, --no-filename          suppress the prefixing filename on output\n"
               "  -H, --with-filename        print the filename for each match\n"
               "  -i, --ignore-case          ignore case distinctions\n"
               "  -I                         ignore binary files\n"
               "  -l, --files-with-matches   only print names of files containing matches\n"
               "  -L, --files-without-match  only print names of files containing no matches\n"
               "  -m, --max-count=<n>        stop after <n> matches\n"
               "  -n, --line-number          print the line number of each line\n"
               "  -N, --no-rcfile            don't read runtime configuration file\n"
               "  -o, --only-matching        show only the part of a line matching <pattern>\n"
               "  -q, --quiet                suppress all messages\n"
               "  -r, --recursive            operate recursively on directories\n"
               "  -s, --no-messages          suppress error messages\n"
               "  -v, --invert-match         select non-matching lines\n"
               "      --verbose              verbose mode (show error messages)\n"
               "  -w, --word-regexp          match only whole words\n"
               "  -x, --line-regexp          match only whole lines\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" );
  show_help_addr();
  }


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


int open_instream( std::string & input_filename,
                   const bool no_messages, const bool search )
  {
  int infd = open( input_filename.c_str(), O_RDONLY | O_BINARY );
  if( infd < 0 )
    {
    if( search && simple_extension_index( input_filename ) < 0 )
      {
      for( int i = 0; i < num_formats; ++i )
        {
        const std::string name( input_filename +
                                simple_extensions[format_order[i]] );
        infd = open( name.c_str(), O_RDONLY | O_BINARY );
        if( infd >= 0 ) { input_filename = name; break; }
        }
      }
    if( infd < 0 && !no_messages )
      show_error2( "Can't open input file", input_filename.c_str() );
    }
  return infd;
  }


int zgrep_stdin( int infd, const int format_index,
                 const std::vector< const char * > & grep_args )
  {
  Children children;
  if( !set_data_feeder( &infd, children, format_index ) ) return 2;
  const pid_t grep_pid = fork();
  if( grep_pid == 0 )			// child (grep)
    {
    if( dup2( infd, STDIN_FILENO ) >= 0 && close( infd ) == 0 )
      {
      const char ** const argv = new const char *[grep_args.size()+2];
      argv[0] = GREP;
      for( unsigned i = 0; i < grep_args.size(); ++i )
        argv[i+1] = grep_args[i];
      argv[grep_args.size()+1] = 0;
      execvp( argv[0], (char **)argv );
      }
    show_exec_error( GREP );
    _exit( 2 );
    }
  if( grep_pid < 0 )			// parent
    { show_fork_error( GREP ); return 2; }

  int retval = wait_for_child( grep_pid, GREP );

  if( !good_status( children, retval == 1 ) ) retval = 2;

  if( close( infd ) != 0 )
    { show_close_error(); return 2; }
  return retval;
  }


int zgrep_file( int infd, const int format_index,
                const std::string & input_filename,
                const std::vector< const char * > & grep_args,
                const int list_mode, const bool show_name )
  {
  Children children;
  if( !set_data_feeder( &infd, children, format_index ) ) return 2;
  int fda[2];				// pipe from grep
  if( pipe( fda ) < 0 )
    { show_error( "Can't create pipe", errno ); return 2; }
  const pid_t grep_pid = fork();
  if( grep_pid == 0 )			// child (grep)
    {
    if( dup2( infd, STDIN_FILENO ) >= 0 &&
        dup2( fda[1], STDOUT_FILENO ) >= 0 &&
        close( infd ) == 0 && close( fda[0] ) == 0 && close( fda[1] ) == 0 )
      {
      const char ** const argv = new const char *[grep_args.size()+2];
      argv[0] = GREP;
      for( unsigned i = 0; i < grep_args.size(); ++i )
        argv[i+1] = grep_args[i];
      argv[grep_args.size()+1] = 0;
      execvp( argv[0], (char **)argv );
      }
    show_exec_error( GREP );
    _exit( 2 );
    }
  if( grep_pid < 0 )			// parent
    { show_fork_error( GREP ); return 2; }

  close( fda[1] );
  enum { buffer_size = 256 };
  uint8_t buffer[buffer_size];
  bool line_begin = true;
  while( true )
    {
    const int size = readblock( fda[0], buffer, buffer_size );
    if( size != buffer_size && errno )
      { show_error( "Read error", errno ); return 2; }
    if( size > 0 && !list_mode )
      {
      if( show_name )
        for( int i = 0; i < size; ++i )
          {
          if( line_begin )
            { line_begin = false; std::printf( "%s:", input_filename.c_str() ); }
          if( buffer[i] == '\n' ) line_begin = true;
          putchar( buffer[i] );
          }
      else if( std::fwrite( buffer, 1, size, stdout ) != (unsigned)size )
        { show_error( "Write error", errno ); return 2; }
      }
    if( size < buffer_size ) break;
    }

  int retval = wait_for_child( grep_pid, GREP );

  if( !good_status( children, retval == 1 ) ) retval = 2;

  if( list_mode && (retval == 0) == (list_mode == 1) )
    std::printf( "%s\n", input_filename.c_str() );
  if( close( infd ) != 0 )
    { show_close_error(); return 2; }
  if( close( fda[0] ) != 0 )
    { show_close_error( GREP ); return 2; }
  return retval;
  }

} // end namespace


int main( const int argc, const char * const argv[] )
  {
  enum { format_opt = 256, help_opt, verbose_opt,
         bz2_opt, gz_opt, lz_opt, xz_opt };
  int format_index = -1;
  int infd = -1;
  int list_mode = 0;		// 1 = list matches, -1 = list non matches
  int show_name = -1;		// tri-state bool
  bool error = false;
  bool no_messages = false;
  bool recursive = false;
  std::string input_filename;
  std::list< std::string > filenames;
  std::vector< const char * > grep_args;	// args to grep, maybe empty
  invocation_name = argv[0];
  program_name = "zgrep";

  const Arg_parser::Option options[] =
    {
    { 'a', "text",                Arg_parser::no  },	// grep GNU
    { 'A', "after-context",       Arg_parser::yes },	// grep GNU
    { 'b', "byte-offset",         Arg_parser::no  },	// grep GNU
    { 'B', "before-context",      Arg_parser::yes },	// grep GNU
    { 'c', "count",               Arg_parser::no  },	// grep
    { 'C', "context",             Arg_parser::yes },	// grep GNU
    { 'e', "regexp",              Arg_parser::yes },	// grep
    { 'E', "extended-regexp",     Arg_parser::no  },	// grep
    { 'f', "file ",               Arg_parser::yes },	// grep
    { 'F', "fixed-strings",       Arg_parser::no  },	// grep
    { 'h', "no-filename",         Arg_parser::no  },	// grep GNU
    { 'H', "with-filename",       Arg_parser::no  },	// grep GNU
    { 'i', "ignore-case",         Arg_parser::no  },	// grep
    { 'I',  0,                    Arg_parser::no  },	// grep GNU
    { 'l', "files-with-matches",  Arg_parser::no  },	// grep
    { 'L', "files-without-match", Arg_parser::no  },	// grep GNU
    { 'm', "max-count",           Arg_parser::yes },	// grep GNU
    { 'n', "line-number",         Arg_parser::no  },	// grep
    { 'N', "no-rcfile",           Arg_parser::no  },
    { 'o', "only-matching",       Arg_parser::no  },	// grep
    { 'q', "quiet",               Arg_parser::no  },
    { 'r', "recursive",           Arg_parser::no  },
    { 's', "no-messages",         Arg_parser::no  },	// grep
    { 'v', "invert-match",        Arg_parser::no  },	// grep
    { 'V', "version",             Arg_parser::no  },
    { 'w', "word-regexp",         Arg_parser::no  },	// grep GNU
    { 'x', "line-regexp",         Arg_parser::no  },	// grep
    { format_opt,  "format",      Arg_parser::yes },
    { help_opt,    "help",        Arg_parser::no  },
    { verbose_opt, "verbose",     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 },
    {  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;
  bool pattern_found = false;
  for( ; argind < parser.arguments(); ++argind )
    {
    const int code = parser.code( argind );
    const char * const arg = parser.argument( argind ).c_str();
    if( !code )
      {
      if( !pattern_found )
        { grep_args.push_back( arg ); pattern_found = true; continue; }
      else break;					// no more options
      }
    switch( code )
      {
      case 'a': grep_args.push_back( "-a" ); break;
      case 'A': grep_args.push_back( "-A" ); grep_args.push_back( arg ); break;
      case 'b': grep_args.push_back( "-b" ); break;
      case 'B': grep_args.push_back( "-B" ); grep_args.push_back( arg ); break;
      case 'c': grep_args.push_back( "-c" ); break;
      case 'C': grep_args.push_back( "-C" ); grep_args.push_back( arg ); break;
      case 'e': grep_args.push_back( "-e" ); grep_args.push_back( arg );
                pattern_found = true; break;
      case 'E': grep_args.push_back( "-E" ); break;
      case 'f': grep_args.push_back( "-f" ); grep_args.push_back( arg );
                pattern_found = true; break;
      case 'F': grep_args.push_back( "-F" ); break;
      case 'h': show_name = false; break;
      case 'H': show_name = true; break;
      case 'i': grep_args.push_back( "-i" ); break;
      case 'I': grep_args.push_back( "-I" ); break;
      case 'l': grep_args.push_back( "-l" ); list_mode = 1; break;
      case 'L': grep_args.push_back( "-L" ); list_mode = -1; break;
      case 'm': grep_args.push_back( "-m" ); grep_args.push_back( arg ); break;
      case 'n': grep_args.push_back( "-n" ); break;
      case 'N': break;
      case 'o': grep_args.push_back( "-o" ); break;
      case 'q': grep_args.push_back( "-q" ); verbosity = -1; break;
      case 'r': recursive = true; break;
      case 's': grep_args.push_back( "-s" ); no_messages = true; break;
      case 'v': grep_args.push_back( "-v" ); break;
      case 'V': show_version( "Zgrep" ); return 0;
      case 'w': grep_args.push_back( "-w" ); break;
      case 'x': grep_args.push_back( "-x" ); break;
      case format_opt : format_index = parse_format_type( arg ); break;
      case help_opt   : show_help(); return 0;
      case verbose_opt: if( verbosity < 4 ) ++verbosity;
                        no_messages = false; break;
      case bz2_opt: parse_compressor( arg, fmt_bz2 ); break;
      case gz_opt: parse_compressor( arg, fmt_gz ); break;
      case lz_opt: parse_compressor( arg, fmt_lz ); break;
      case xz_opt: parse_compressor( arg, fmt_xz ); 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

  if( !pattern_found ) { show_error( "Pattern not found." ); return 2; }

  for( ; argind < parser.arguments(); ++argind )
    filenames.push_back( parser.argument( argind ) );

  if( filenames.empty() ) filenames.push_back("-");

  if( show_name < 0 ) show_name = ( filenames.size() != 1 || recursive );

  int retval = 1;
  while( next_filename( filenames, input_filename, error, recursive,
                        false, no_messages ) )
    {
    if( input_filename.empty() ) infd = STDIN_FILENO;
    else
      {
      infd = open_instream( input_filename, no_messages, format_index < 0 );
      if( infd < 0 ) { error = true; continue; }
      }

    int tmp;
    if( infd == STDIN_FILENO )
      tmp = zgrep_stdin( infd, format_index, grep_args );
    else tmp = zgrep_file( infd, format_index, input_filename, grep_args,
                           list_mode, show_name );
    if( tmp == 0 || ( tmp == 2 && retval == 1 ) ) retval = tmp;

    if( input_filename.size() ) { close( infd ); infd = -1; }
    if( retval == 0 && verbosity < 0 ) break;
    }

  if( std::fclose( stdout ) != 0 )
    {
    show_error( "Can't close stdout", errno );
    error = true;
    }
  if( error && ( retval != 0 || verbosity >= 0 ) ) retval = 2;
  return retval;
  }