This file is indexed.

/usr/share/perl5/XML/RSS/Feed.pm is in libxml-rss-feed-perl 2.212-1.

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
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
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
package XML::RSS::Feed;

use strict;
use warnings;

use XML::RSS;
use XML::RSS::Headline;
use Time::HiRes;
use Storable qw(store retrieve);

=head1 NAME

XML::RSS::Feed - Persistant XML RSS Encapsulation

=head1 VERSION

2.212

=cut

our $VERSION = 2.212;

=head1 SYNOPSIS

A quick and dirty non-POE example that uses a blocking B<sleep>.  The
magic is in the B<late_breaking_news> method that returns only 
headlines it hasn't seen.

    use XML::RSS::Feed;
    use LWP::Simple qw(get);

    my $feed = XML::RSS::Feed->new(
	url    => "http://www.jbisbee.com/rdf/",
	name   => "jbisbee",
	delay  => 10,
	debug  => 1,
	tmpdir => "/tmp", # optional caching
    );

    while (1) {
	$feed->parse(get($feed->url));
	print $_->headline . "\n" for $feed->late_breaking_news;
	sleep($feed->delay); 
    }

ATTENTION! - If you want a non-blocking way to watch multiple RSS sources 
with one process use L<POE::Component::RSSAggregator>.

=head1 CONSTRUCTOR

=head2 XML::RSS::Feed->new( url => $url, name => $name )

=over 4

=item B<Required Params>

=over 4

=item * B<name> 

Identifier and hash lookup key for the RSS feed. 

=item * B<url> 

The URL of the RSS feed

=back

=item B<Optional Params>

=over 4

=item * B<delay> 

Number of seconds between updates (defaults to 600)

=item * B<tmpdir> 

Directory to keep a cached feed (using Storable) to keep persistance between instances.

=item * B<debug>

Turn debuging on.

=item * B<headline_as_id>

Boolean value to use the headline as the id when URL isn't unique within a feed.

=item * B<hlobj>

A class name sublcassed from L<XML::RSS::Headline>

=item * B<max_headlines>

The max number of headlines to keep.  (default is unlimited)

=back

=back

=cut 

sub new {
    my $class = shift;

    my $self = bless {
        process_count    => 0,
        rss_headlines    => [],
        rss_headline_ids => {},
        max_headlines    => 0,
    }, $class;

    my %args = @_;
    foreach my $method ( keys %args ) {
        if ( $self->can($method) ) {
            $self->$method( $args{$method} );
        }
        else {
            warn "Invalid argument '$method'";
        }
    }
    $self->_load_cached_headlines if $self->{tmpdir};
    $self->delay(3600) unless $self->delay;
    return $self;
}

sub _load_cached_headlines {
    my ($self)       = @_;
    my $filename_sto = $self->{tmpdir} . '/' . $self->name . '.sto';
    my $filename_xml = $self->{tmpdir} . '/' . $self->name;
    if ( -s $filename_sto ) {
        my $cached = retrieve($filename_sto);
        my $title = $self->title || $cached->{title} || "";
        $self->set_last_updated( $cached->{last_updated} );
        $self->{process_count}++;
        $self->process( $cached->{items}, $title, $cached->{link} );
        warn "[$self->{name}] Loaded Cached RSS Storable\n" if $self->{debug};
    }
    elsif ( -T $filename_xml ) {    # legacy XML caching
        open( my $fh, $filename_xml );
        my $xml = do { local $/, <$fh> };
        close $fh;
        warn "[$self->{name}] Loaded Cached RSS XML\n" if $self->{debug};
        $self->{process_count}++;
        $self->parse($xml);
    }
    else {
        warn "[$self->{name}] No Cache File Found\n" if $self->{debug};
    }
}

sub _strip_whitespace {
    my ($string) = @_;
    $string =~ s/^\s+//;
    $string =~ s/\s+$//;
    return $string;
}

sub _mark_all_headlines_seen {
    my ($self) = @_;
    return unless $self->{process_count};
    $self->{rss_headline_ids}{ $_->id } = 1 for $self->late_breaking_news;
}

=head1 METHODS

=head2 $feed->parse( $xml_string )

Pass in a xml string to parse with XML::RSS and then call 
process to process the results.

=cut

sub parse {
    my ( $self, $xml ) = @_;
    my $rss = XML::RSS->new();
    eval { $rss->parse($xml) };
    if ($@) {
        warn "[$self->{name}] [!!] Failed to parse RSS XML: $@\n";
        return 0;
    }
    else {
        warn "[$self->{name}] Parsed RSS XML\n" if $self->{debug};
        my $items = [ map { { item => $_ } } @{ $rss->{items} } ];

        $self->process(
            $items,
            ( $self->title || $rss->{channel}{title} ),
            $rss->{channel}{link}
        );
        return 1;
    }
}

=head2 $feed->process( $items, $title, $link )

=head2 $feed->process( $items, $title )

=head2 $feed->process( $items )

Calls B<pre_process>, B<process_items>, B<post_process>, B<title>, and B<link>
methods to process the parsed results of an RSS XML feed.

=over 4

=item * B<$items>

An array of hash refs which will eventually become L<XML::RSS::Headline> objects.  Look
at XML::RSS::Headline->new() for acceptable arguments.

=item * B<$title>

The title of the RSS feed.

=item * B<$link>

The RSS channel link (normally a URL back to the homepage) of the RSS feed.

=back

=cut

sub process {
    my ( $self, $items, $title, $link ) = @_;
    if ($items) {
        $self->pre_process;
        $self->process_items($items);
        $self->title($title) if $title;
        $self->link($link)   if $link;
        $self->post_process;
        return 1;
    }
    return 0;
}

=head2 $feed->pre_process

Mark all headlines from previous run as seen.

=cut

sub pre_process {
    my ($self) = @_;
    $self->_mark_all_headlines_seen;
}

=head2 $feed->process_items( $items )

Turn an array refs of hash refs into L<XML::RSS::Headline> objects and 
added to the internal list of headlines.

=cut

sub process_items {
    my ( $self, $items ) = @_;
    if ($items) {

        # used 'reverse' so order seen is preserved
        for my $item ( reverse @$items ) {
            $self->create_headline(%$item);
        }
        return 1;
    }
    return 0;
}

=head2 $feed->post_process

Post process cleanup, cache headlines (if tmpdir), and debug messages.

=cut

sub post_process {
    my ($self) = @_;
    if ( $self->init ) {
        warn "[$self->{name}] "
            . $self->late_breaking_news
            . " New Headlines Found\n"
            if $self->{debug};
    }
    else {
        $self->_mark_all_headlines_seen;
        $self->init(1);
        warn "[$self->{name}] "
            . $self->num_headlines
            . " Headlines Initialized\n"
            if $self->{debug};
    }
    $self->{process_count}++;
    $self->cache;
    $self->set_last_updated;
}

=head2 $feed->create_headline( %args)

Create a new L<XML::RSS::Headline> object and add it to the interal list.  
Check B<< XML::RSS::Headline->new() >> for acceptable values for B<< %args >>.

=cut

sub create_headline {
    my ( $self, %args ) = @_;
    my $hlobj = $self->{hlobj} || "XML::RSS::Headline";
    $args{headline_as_id} = $self->{headline_as_id};
    my $headline = $hlobj->new(%args);
    return unless $headline;

    unshift( @{ $self->{rss_headlines} }, $headline )
        unless $self->seen_headline( $headline->id );

    # remove the oldest if the new headline put us over the max_headlines limit
    if ( $self->max_headlines ) {
        while ( $self->num_headlines > $self->max_headlines ) {
            my $garbage = pop @{ $self->{rss_headlines} };

            # just in case max_headlines < number of headlines in the feed
            $self->{rss_headline_ids}{ $garbage->id } = 1;
            warn "[$self->{name}] Exceeded maximum headlines, removing "
                . "oldest headline\n"
                if $self->{debug};
        }
    }
}

=head2 $feed->num_headlines

Returns the number of headlines for the feed.

=cut

sub num_headlines {
    my ($self) = @_;
    return scalar @{ $self->{rss_headlines} };
}

=head2 $feed->seen_headline( $id )

Just a boolean test to see if we've seen a headline or not.

=cut

sub seen_headline {
    my ( $self, $id ) = @_;
    return 1 if exists $self->{rss_headline_ids}{$id};
    return 0;
}

=head2 $feed->headlines

Returns an array or array reference (based on context) of 
L<XML::RSS::Headline> objects

=cut

sub headlines {
    my ($self) = @_;
    return wantarray ? @{ $self->{rss_headlines} } : $self->{rss_headlines};
}

=head2 $feed->late_breaking_news

Returns an array or the number of elements (based on context) of the 
B<latest> L<XML::RSS::Headline> objects.

=cut

sub late_breaking_news {
    my ($self) = @_;
    my @list = grep { !$self->seen_headline( $_->id ); }
        @{ $self->{rss_headlines} };
    return wantarray ? @list : scalar @list;
}


=head2 $feed->cache

If tmpdir is defined the rss info is cached.

=cut

sub cache {
    my ($self) = @_;
    return unless $self->tmpdir;
    if ( -d $self->tmpdir && $self->num_headlines ) {
        my $tmp_filename = $self->tmpdir . '/' . $self->{name} . ".sto";
        eval { store( $self->_build_dump_structure, $tmp_filename ) };
        if ($@) {
            warn "[$self->{name}] Could not cache RSS XML to $tmp_filename\n";
            return;
        }
        else {
            warn "[$self->{name}] Cached RSS Storable to $tmp_filename\n"
                if $self->{debug};
            return 1;
        }
    }
    return;
}

sub _build_dump_structure {
    my ($self) = @_;
    my $cached = {};
    $cached->{title}        = $self->title;
    $cached->{link}         = $self->link;
    $cached->{last_updated} = $self->{timestamp_hires};
    $cached->{items}        = [];
    for my $headline ( $self->headlines ) {
        push @{ $cached->{items} },
            {
            headline    => $headline->headline,
            url         => $headline->url,
            description => $headline->description,
            first_seen  => $headline->first_seen_hires,
            };
    }
    return $cached;
}

=head2 $feed->set_last_updated

=head2 $feed->set_last_updated( Time::HiRes::time )

Set the time of when the feed was last processed.  If you pass in a value
it will be used otherwise calls Time::HiRes::time.

=cut

sub set_last_updated {
    my ( $self, $hires_time ) = @_;
    $self->{hires_timestamp} = $hires_time if $hires_time;
    $self->{hires_timestamp} = Time::HiRes::time()
        unless $self->{hires_timestamp};
}

=head2 $feed->last_updated

The time (in epoch seconds) of when the feed was last processed.

=cut

sub last_updated {
    my ($self) = @_;
    return int $self->{hires_timestamp};
}

=head2 $feed->last_updated_hires

The time (in epoch seconds and milliseconds) of when the feed was last 
processed.

=cut

sub last_updated_hires {
    my ($self) = @_;
    return $self->{hires_timestamp};
}

=head1 SET/GET ACCESSOR METHODS

=head2 $feed->title

=head2 $feed->title( $title )

The title of the RSS feed.

=cut

sub title {
    my ( $self, $title ) = @_;
    if ($title) {
        $title = _strip_whitespace($title);
        $self->{title} = $title if $title;
    }
    $self->{title};
}

=head2 $feed->debug

=head2 $feed->debug( $bool )

Turn on debugging messages

=cut

sub debug {
    my $self = shift @_;
    $self->{debug} = shift if @_;
    $self->{debug};
}

=head2 $feed->init

=head2 $feed->init( $bool )

init is used so that we just load the current headlines and don't return all 
headlines.  in other words we initialize them.  Takes a boolean argument.

=cut

sub init {
    my $self = shift @_;
    $self->{init} = shift if @_;
    $self->{init};
}

=head2 $feed->name

=head2 $feed->name( $name )

The identifier of an RSS feed.

=cut

sub name {
    my $self = shift;
    $self->{name} = shift if @_;
    $self->{name};
}

=head2 $feed->delay

=head2 $feed->delay( $seconds )

Number of seconds between updates.

=cut

sub delay {
    my $self = shift @_;
    $self->{delay} = shift if @_;
    $self->{delay};
}

=head2 $feed->link

=head2 $feed->link( $rss_channel_url )

The url in the RSS feed with a link back to the site where the RSS feed 
came from.

=cut

sub link {
    my $self = shift @_;
    $self->{link} = shift if @_;
    $self->{link};
}

=head2 $feed->url

=head2 $feed->url( $url )

The url in the RSS feed with a link back to the site where the RSS feed 
came from.

=cut

sub url {
    my $self = shift @_;
    $self->{url} = shift if @_;
    $self->{url};
}

=head2 $feed->headline_as_id

=head2 $feed->headline_as_id( $bool )

Within some RSS feeds the URL may not always be unique, in these cases
you can use the headline as the unique id.  The id is used to check whether
or not a feed is new or has already been seen.

=cut

sub headline_as_id {
    my ( $self, $bool ) = @_;
    if ( defined $bool ) {
        $self->{headline_as_id} = $bool;
        $_->headline_as_id($bool) for $self->headlines;
    }
    $self->{headline_as_id};
}

=head2 $feed->hlobj

=head2 $feed->hlobj( $class )

Ablity to use a subclass of L<XML::RSS::Headline>.  (See Perl Jobs example in 
L<XML::RSS::Headline::PerlJobs>).  This should just be the name of the subclass.

=cut

sub hlobj {
    my ( $self, $hlobj ) = @_;
    $self->{hlobj} = $hlobj if defined $hlobj;
    $self->{hlobj};
}

=head2 $feed->tmpdir

=head2 $feed->tmpdir( $tmpdir )

Temporay directory to store cached RSS XML between instances for persistance.

=cut

sub tmpdir {
    my $self = shift @_;
    $self->{tmpdir} = shift if @_;
    $self->{tmpdir};
}

=head2 $feed->max_headlines

=head2 $feed->max_headlines( $integer )

The maximum number of headlines you'd like to keep track of.  
(0 means infinate)

=cut

sub max_headlines {
    my $self = shift @_;
    $self->{max_headlines} = shift if @_;
    $self->{max_headlines};
}

=head1 DEPRECATED METHODS

=head2 $feed->failed_to_fetch

This should was deprecated because, the object shouldn't really know
anything about fetching, it just processes the results.  This method 
currently will always return false

=cut

sub failed_to_fetch {
    warn __PACKAGE__ . "::failed_to_fetch has been deprecated";
    return;
}

=head2 $feed->failed_to_parse

This method was deprecated because, $feed->parse now returns a bool value.
This method will always return false

=cut

sub failed_to_parse {
    warn __PACKAGE__ . "::failed_to_parse has been deprecated";
    return;
}

=head1 AUTHOR

Jeff Bisbee, C<< <jbisbee at cpan.org> >>

=head1 BUGS

Please report any bugs or feature requests to
C<bug-xml-rss-feed at rt.cpan.org>, or through the web interface at
L<http://rt.cpan.org/NoAuth/ReportBug.html?Queue=XML-RSS-Feed>.
I will be notified, and then you'll automatically be notified of progress on
your bug as I make changes.

=head1 SUPPORT

You can find documentation for this module with the perldoc command.

    perldoc XML::RSS::Feed

You can also look for information at:

=over 4

=item * AnnoCPAN: Annotated CPAN documentation

L<http://annocpan.org/dist/XML-RSS-Feed>

=item * CPAN Ratings

L<http://cpanratings.perl.org/d/XML-RSS-Feed>

=item * RT: CPAN's request tracker

L<http://rt.cpan.org/NoAuth/Bugs.html?Dist=XML-RSS-Feed>

=item * Search CPAN

L<http://search.cpan.org/dist/XML-RSS-Feed>

=back

=head1 ACKNOWLEDGEMENTS

Special thanks to Rocco Caputo, Martijn van Beers, Sean Burke, Prakash Kailasa
and Randal Schwartz for their help, guidance, patience, and bug reports. Guys 
thanks for actually taking time to use the code and give good, honest feedback.

=head1 COPYRIGHT & LICENSE

Copyright 2006 Jeff Bisbee, all rights reserved.

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

=head1 SEE ALSO

L<XML::RSS::Headline>, L<XML::RSS::Headline::PerlJobs>, L<XML::RSS::Headline::Fark>, L<XML::RSS::Headline::UsePerlJournals>, L<POE::Component::RSSAggregator>

=cut

1;