This file is indexed.

/usr/share/perl5/Parse/MediaWikiDump/Revisions.pm is in libparse-mediawikidump-perl 1.0.6-2.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  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
package Parse::MediaWikiDump::Revisions;

our $VERSION = '1.0.4';

use 5.8.0;

use strict;
use warnings;
use Carp;

use List::Util;
use Scalar::Util qw(weaken reftype);
use Data::Dumper;

sub DESTROY {
	my ($self) = @_;
	
	if (! $self->{FINISHED}) {
		$self->{EXPAT}->parse_done;
	}
}

#public methods
sub new {
	my ($class, @args) = @_;
	my $self = {};
	my $source;
	
	if (scalar(@args) == 0) {
		die "you must specify an argument to new()";
	} elsif (scalar(@args) == 1) {
		$source = $args[0];
	} else {
		my %conf = @args;
		
		if (! defined($conf{input})) {
			die "input is a required parameter to new()";
		}
		
		$source = $conf{input};
	}
	
	bless($self, $class);

	$$self{XML} = undef; #holder for XML::Accumulator
	$$self{EXPAT} = undef; #holder for expat under XML::Accumulator
	$$self{SITEINFO} = {}; #holder for the data from siteinfo
	$$self{PAGE_LIST} = []; #place to store articles as they come out of XML::Accumulator
	$$self{BYTE} = 0;
	$$self{CHUNK_SIZE} = 32768;
	$$self{FINISHED} = 0;

	$self->open($source);
	$self->init;
	
	return $self;
}

sub next {
	my ($self) = @_;
	my $case = $self->{SITEINFO}->{CASE};
	my $namespaces = $self->{SITEINFO}->{namespaces};
	
	my $page;
	
	#look for an available page and if one isn't
	#there then parse more XML
	while(1) {
		$page = shift(@{ $self->{PAGE_LIST} } );
		
		if (defined($page)) {
			
			return Parse::MediaWikiDump::page->new($page, $self->get_category_anchor, $case, $namespaces);
		}
		
		return undef unless $self->parse_more;		
	}
	
	die "should not get here";
}

sub version {
	my ($self) = @_;
	return $self->{SITEINFO}{version};
}

sub sitename {
	my ($self) = @_;
	return $$self{SITEINFO}{sitename};
}

sub base {
	my ($self) = @_;
	return $$self{SITEINFO}{base};
}

sub generator {
	my ($self) = @_;
	return $$self{SITEINFO}{generator};
}

sub case {
	my ($self) = @_;
	return $$self{SITEINFO}{case};
}

sub namespaces {
	my ($self) = @_;
	return $$self{SITEINFO}{namespaces};
}

sub namespaces_names {
	my $self = shift;
	my @result;
	
	foreach (@{ $$self{SITEINFO}{namespaces} }) {
		push(@result, $_->[1]);
	}
	
	return \@result;
}

sub current_byte {
	my ($self) = @_;
	return $$self{BYTE};
}

sub size {
	my ($self) = @_;
	
	return undef unless defined $$self{SOURCE_FILE};

	my @stat = stat($$self{SOURCE_FILE});

	return $stat[7];
}

#private functions with OO interface

sub open {
	my ($self, $source) = @_;

	if (defined(reftype($source)) && reftype($source) eq 'GLOB') {
		$$self{SOURCE} = $source;
	} else {
		if (! open($$self{SOURCE}, $source)) {
			die "could not open $source: $!";
		}

		$$self{SOURCE_FILE} = $source;
	}

	binmode($$self{SOURCE}, ':utf8');

	return 1;
}

sub init {
	my ($self) = @_;
	
	$self->{XML} = $self->new_accumulator_engine;
	my $expat_bb = $$self{XML}->parser->parse_start();
	$$self{EXPAT} = $expat_bb;
	
	#load the information from the siteinfo section so it is available before
	#someone calls ->next
	while(scalar(@{$self->{PAGE_LIST}}) < 1) {
		die "hit end of document" unless $self->parse_more;	
	}
}

sub new_accumulator_engine {
	my ($self) = @_;
	my $f = Parse::MediaWikiDump::XML::Accumulator->new;
	my $store_siteinfo = $self->{SITEINFO};
	my $store_page = $self->{PAGE_LIST};
	
	my $root = $f->root;
	my $mediawiki = $f->node('mediawiki', Start => \&handle_mediawiki_node);
	
	#stuff for siteinfo
	my $siteinfo = $f->node('siteinfo', End => sub { %$store_siteinfo = %{ $_[1] } } );
	my $sitename = $f->textcapture('sitename');
	my $base = $f->textcapture('base');
	my $generator = $f->textcapture('generator');
	my $case = $f->textcapture('case');
	my $namespaces = $f->node('namespaces', Start => sub { $_[1]->{namespaces} = []; } );
	my $namespace = $f->node('namespace', Character => \&save_namespace_node);
	
	#stuff for page entries
	my $page = $f->node('page', Start => sub { $_[0]->accumulator( {} ) } );
	my $title = $f->textcapture('title');
	my $id = $f->textcapture('id');
	my $revision = $f->node('revision', 
		Start => \&handle_revision_node_start, End => sub { push(@$store_page, { %{ $_[1] } } ) } );
	my $rev_id = $f->textcapture('id', 'revision_id');
	my $minor = $f->node('minor', Start => sub { $_[1]->{minor} = 1 } );
	my $time = $f->textcapture('timestamp');
	my $contributor = $f->node('contributor');
	my $username = $f->textcapture('username');
	my $ip = $f->textcapture('ip', 'userip');
	my $contrib_id = $f->textcapture('id', 'userid');
	my $comment = $f->textcapture('comment');
	my $text = $f->textcapture('text');
	my $restr = $f->textcapture('restrictions');
	
	#put together the tree
	$siteinfo->add_child($sitename, $base, $generator, $case, $namespaces);
	  $namespaces->add_child($namespace);
	
	$page->add_child($title, $id, $revision, $restr);
	  $revision->add_child($rev_id, $time, $contributor, $minor, $comment, $text);
	    $contributor->add_child($username, $ip, $contrib_id);
	
	$mediawiki->add_child($siteinfo, $page);
	$root->add_child($mediawiki);
	
	my $engine = $f->engine($root, {});

	return $engine;	
}

sub parse_more {
        my ($self) = @_;
        my $buf;

        my $read = read($$self{SOURCE}, $buf, $$self{CHUNK_SIZE});

        if (! defined($read)) {
                die "error during read: $!";
        } elsif ($read == 0) {
                $$self{FINISHED} = 1;
                $$self{EXPAT}->parse_done;
                
                return 0;
        }

		#expat has a bug where the current_byte
		#value overflows around 2 gigabytes
		#so we track how much data has been
		#processed ourselves
        $$self{BYTE} += $read;
        $$self{EXPAT}->parse_more($buf);
        
    	if ($self->{DIE_REQUESTED}) {
			die "$self->{DIE_REQUESTED}\n";
		}
        
        return 1;
}

sub get_category_anchor {
	my ($self) = @_;
	my $namespaces = $self->{SITEINFO}->{namespaces};

	foreach (@$namespaces) {
		my ($id, $name) = @$_;
		if ($id == 14) {
			return $name;
		}
	}	
	
	return undef;
}

#helper functions that the xml accumulator uses

sub save_namespace_node {
	my ($parser, $accum, $text, $element, $attrs) = @_;
	my $key = $attrs->{key};
	my $namespaces = $accum->{namespaces};
	
	push(@{ $accum->{namespaces} }, [$key, $text] );
}

sub handle_mediawiki_node {
	my ($engine, $a, $element, $attrs) = @_;
	my $version = $attrs->{version};

	#checking versions of the dump file removed in 1.0.6 
	#see the migration notes for why	
#	if ($version ne '0.3' && $version ne '0.4') {
#			die "Only version 0.3 and 0.4 dump files are supported";
#	}
	
	$a->{version} = $version;
}

sub handle_revision_node_start { 
	my (undef, $a) = @_;
	
	$a->{minor} = 0;
	delete($a->{username});
	delete($a->{userid});
	delete($a->{userip});
}

sub save_siteinfo {
	my ($self, $info) = @_;
	my %info = %$info;
	
	$self->{SITEINFO} = \%info;
}

1;

__END__
=head1 NAME

Parse::MediaWikiDump::Revisions - Object capable of processing dump files with multiple revisions per article

=head1 ABOUT

This object is used to access the metadata associated with a MediaWiki instance and provide an iterative interface
for extracting the indidivual article revisions out of the same. To gurantee that there is only a single
revision per article use the Parse::MediaWikiDump::Revisions object. 

=head1 SYNOPSIS
  
  $pmwd = Parse::MediaWikiDump->new;
  $revisions = $pmwd->revisions('pages-articles.xml');
  $revisions = $pmwd->revisions(\*FILEHANDLE);
  
  #print the title and id of each article inside the dump file
  while(defined($page = $revisions->next)) {
    print "title '", $page->title, "' id ", $page->id, "\n";
  }

=head1 STATUS

This software is being RETIRED - MediaWiki::DumpFile is the official successor to
Parse::MediaWikiDump and includes a compatibility library called MediaWiki::DumpFile::Compat
that is 100% API compatible and is a near perfect standin for this module. It is faster
in all instances where it counts and is actively maintained. Any undocumented deviation
of MediaWiki::DumpFile::Compat from Parse::MediaWikiDump is considered a bug and will
be fixed. 

=head1 METHODS

=over 4

=item $revisions->new

Open the specified MediaWiki dump file. If the single argument to this method
is a string it will be used as the path to the file to open. If the argument
is a reference to a filehandle the contents will be read from the filehandle as
specified. 

=item $revisions->next

Returns an instance of the next available Parse::MediaWikiDump::page object or returns undef
if there are no more articles left.

=item $revisions->version

Returns a plain text string of the dump file format revision number

=item $revisions->sitename

Returns a plain text string that is the name of the MediaWiki instance.

=item $revisions->base

Returns the URL to the instances main article in the form of a string.

=item $revisions->generator

Returns a string containing 'MediaWiki' and a version number of the instance that dumped this file.
Example: 'MediaWiki 1.14alpha'

=item $revisions->case

Returns a string describing the case sensitivity configured in the instance.

=item $revisions->namespaces

Returns a reference to an array of references. Each reference is to another array with the first
item being the unique identifier of the namespace and the second element containing a string
that is the name of the namespace.

=item $revisions->namespaces_names

Returns an array reference the array contains strings of all the namespaces each as an element. 

=item $revisions->current_byte

Returns the number of bytes that has been processed so far

=item $revisions->size

Returns the total size of the dump file in bytes. 

=back

=head1 EXAMPLE

=head2 Extract the article text of each revision of an article using a given title

  #!/usr/bin/perl
  
  use strict;
  use warnings;
  use Parse::MediaWikiDump;
  
  my $file = shift(@ARGV) or die "must specify a MediaWiki dump of the current pages";
  my $title = shift(@ARGV) or die "must specify an article title";
  my $pmwd = Parse::MediaWikiDump->new;
  my $dump = $pmwd->revisions($file);
  my $found = 0;
  
  binmode(STDOUT, ':utf8');
  binmode(STDERR, ':utf8');
  
  #this is the only currently known value but there could be more in the future
  if ($dump->case ne 'first-letter') {
    die "unable to handle any case setting besides 'first-letter'";
  }
  
  $title = case_fixer($title);
  
  while(my $revision = $dump->next) {
    if ($revision->title eq $title) {
      print STDERR "Located text for $title revision ", $revision->revision_id, "\n";
      my $text = $revision->text;
      print $$text;
      
      $found = 1;
    }
  }
  
  print STDERR "Unable to find article text for $title\n" unless $found;
  exit 1;
  
  #removes any case sensativity from the very first letter of the title
  #but not from the optional namespace name
  sub case_fixer {
    my $title = shift;
  
    #check for namespace
    if ($title =~ /^(.+?):(.+)/) {
      $title = $1 . ':' . ucfirst($2);
    } else {
      $title = ucfirst($title);
    }
  
    return $title;
  }
  
=head1 LIMITATIONS

=head2 Version 0.4

This class was updated to support version 0.4 dump files from
a MediaWiki instance but it does not currently support any of
the new information available in those files.