This file is indexed.

/usr/share/perl5/WWW/Wikipedia/Entry.pm is in libwww-wikipedia-perl 2.04-2.

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
package WWW::Wikipedia::Entry;

use 5.006;
use strict;
use warnings;
use Text::Autoformat;
use WWW::Wikipedia;

our $VERSION = '2.04';

=head1 NAME

WWW::Wikipedia::Entry - A class for representing a Wikipedia Entry

=head1 SYNOPSIS

    my $wiki = WWW::Wikipedia->new();
    my $entry = $wiki->search( 'Perl' );
    print $entry->text();

    my $entry_es = $entry->language( 'es' );
    print $entry_es->text();

=head1 DESCRIPTION

WWW::Wikipedia::Entry objects are usually created using the search() method
on a WWW::Wikipedia object to search for a term. Once you've got an entry
object you can then extract pieces of information from the entry using 
the following methods.

=head1 METHODS

=head2 new()

You probably won't use this one, it's the constructor that is called 
behind the scenes with the correct arguments by WWW::Wikipedia::search().

=cut

sub new {
    my ( $class, $raw, $src, %ops ) = @_;
    return if length( $raw ) == 0;
    my $self = bless {
        raw         => $raw,
        src         => $src,
        text        => '',
        fulltext    => '',
        cursor      => 0,
        related     => [],
        categories  => [],
        headings    => [],
        languages   => {},
        currentlang => ''
        },
        ref( $class ) || $class;
    $self->_parse();

    # store un-"pretty"-ed version of text
    $self->{ fulltext_basic } = $self->{ fulltext };
    $self->{ text_basic }     = $self->{ text };

    if ($ops{clean_html}) {
    	$self->{ fulltext } = _clean_html( $self->{ fulltext });
    	$self->{ text } = _clean_html( $self->{ text });
    }

    $self->{ fulltext } = _pretty( $self->{ fulltext } );
    $self->{ text }     = _pretty( $self->{ text } );
    return ( $self );
}

=head2 text()

The brief text for the entry. This will provide the first paragraph of 
text; basically everything up to the first heading. Ordinarily this will
be what you want to use. When there doesn't appear to be summary text you 
will be returned the fulltext instead.

If text() returns nothing then you probably are looking at a disambiguation
entry, and should use related() to lookup more specific entries.

=cut

sub text {
    my $self = shift;
    return $self->{ text } if $self->{ text };
    return $self->fulltext();
}

=head2 text_basic()

The same as C<text()>, but not run through Text::Autoformat.

=cut

sub text_basic {
    my $self = shift;
    return $self->{ text_basic } if $self->{ text_basic };
    return $self->fulltext_basic();
}

=head2 fulltext()

Returns the full text for the entry, which can be extensive.

=cut

sub fulltext {
    my $self = shift;
    return $self->{ fulltext };
}

=head2 fulltext_basic()

The same as C<fulltext()>, but not run through Text::Autoformat.

=cut

sub fulltext_basic {
    my $self = shift;
    return $self->{ fulltext_basic };
}


=head2 title()

Returns a title of the entry.

=cut

sub title {
    my $self = shift;
    return $self->{ title };
}

=head2 related()

Returns a list of terms in the wikipedia that are mentioned in the 
entry text.

=cut

sub related {
    return ( @{ shift->{ related } } );
}

=head2 categories()

Returns a list of categories which the entry is part of. So Perl is part
of the Programming languages category.

=cut

sub categories {
    return ( @{ shift->{ categories } } );
}

=head2 headings()

Returns a list of headings used in the entry.

=cut

sub headings {
    return ( @{ shift->{ headings } } );
}

=head2 raw()

Returns the raw wikitext for the entry.

=cut

sub raw {
    my $self = shift;
    return $self->{ raw };
}

=head2 language()

With no parameters, it will return the current language of the entry. By
specifying a two-letter language code, it will return the same entry in that
language, if available.

=cut

sub language {
    my $self = shift;
    my $lang = shift;

    return $self->{ currentlang } unless defined $lang;
    return undef unless exists $self->{ languages }->{ $lang };

    my $wiki = WWW::Wikipedia->new( language => $lang );
    return $wiki->search( $self->{ languages }->{ $lang } );
}

=head2 languages()

Returns an array of two letter language codes denoting the languages in which 
this entry is available.

=cut

sub languages {
    my $self = shift;

    return keys %{ $self->{ languages } };
}

## messy internal routine for barebones parsing of wikitext

sub _parse {
    my $self = shift;
    my $raw  = $self->{ raw };
    my $src  = $self->{ src };

    # Add current language
    my ( $lang )  = ( $src =~ /http:\/\/(..)/ );
    my $title = ( split( /\//, $src ) )[ -1 ];

    if( $title =~ m{\?title=} ) {
        ( $title ) = $src =~ m{\?title=([^\&]+)};
        $title =~ s{_}{ }g;
    }

    $self->{ currentlang } = $lang;
    $self->{ languages }->{ $lang } = $title;
    $self->{ title } = $title;

    for (
        $self->{ cursor } = 0;
        $self->{ cursor } < length( $raw );
        $self->{ cursor }++
        )
    {

        pos( $raw ) = $self->{ cursor };

        ## [[ ... ]]
        if ( $raw =~ /\G\[\[ *(.*?) *\]\]/ ) {
            my $directive = $1;
            $self->{ cursor } += length( $& ) - 1;
            if ( $directive =~ /\:/ ) {
                my ( $type, $text ) = split /:/, $directive;
                if ( lc( $type ) eq 'category' ) {
                    push( @{ $self->{ categories } }, $text );
                }

                # language codes
                if ( length( $type ) == 2 and lc( $type ) eq $type ) {
                    $self->{ languages }->{ $type } = $text;
                }
            }
            elsif ( $directive =~ /\|/ ) {
                my ( $lookup, $name ) = split /\|/, $directive;
                $self->{ fulltext } .= $name;
                push( @{ $self->{ related } }, $lookup ) if $lookup !~ /^#/;
            }
            else {
                $self->{ fulltext } .= $directive;
                push( @{ $self->{ related } }, $directive );
            }
        }

        ## === heading 2 ===
        elsif ( $raw =~ /\G=== *(.*?) *===/ ) {
            ### don't bother storing these headings
            $self->{ fulltext } .= $1;
            $self->{ cursor } += length( $& ) - 1;
            next;
        }

        ## == heading 1 ==
        elsif ( $raw =~ /\G== *(.*?) *==/ ) {
            push( @{ $self->{ headings } }, $1 );
            $self->{ text } = $self->{ fulltext } if !$self->{ seenHeading };
            $self->{ seenHeading } = 1;
            $self->{ fulltext } .= $1;
            $self->{ cursor } += length( $& ) - 1;
            next;
        }

        ## '' italics ''
        elsif ( $raw =~ /\G'' *(.*?) *''/ ) {
            $self->{ fulltext } .= $1;
            $self->{ cursor } += length( $& ) - 1;
            next;
        }

        ## {{ disambig }}
        elsif ( $raw =~ /\G\{\{ *(.*?) *\}\}/ ) {
            ## ignore for now
            $self->{ cursor } += length( $& ) - 1;
            next;
        }

        else {
            $self->{ fulltext } .= substr( $raw, $self->{ cursor }, 1 );
        }
    }
}

# future versions might clean tag contents for some specific ones.
sub _clean_html {
	my $text = shift;
	# force first letter so that standalone < might be kept
	$text =~ s{<[/a-zA-Z!][^>]+>}{}g;
	return $text;
}

sub _pretty {
    my $text = shift;

    # Text::Autoformat v1.13 chokes on strings that are one or more "\n"
    return '' if $text =~ m/^\n+$/;
    return autoformat(
        $text,
        {   left    => 0,
            right   => 80,
            justify => 'left',
            all     => 1
        }
    );
}

=head1 AUTHORS

Ed Summers E<lt>ehs@pobox.comE<gt>

Brian Cassidy E<lt>bricas@cpan.orgE<gt>

=head1 COPYRIGHT AND LICENSE

Copyright 2003-2015 by Ed Summers

This library is free software; you can redistribute it and/or modify
it under the same terms as Perl itself. 

=cut

1;