This file is indexed.

/usr/share/perl5/HTML/Scrubber.pm is in libhtml-scrubber-perl 0.11-1.

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
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
package HTML::Scrubber;

# ABSTRACT: Perl extension for scrubbing/sanitizing html


use strict;
use warnings;
use HTML::Parser 3.47 ();
use HTML::Entities;
our( @_scrub, @_scrub_fh );

our $VERSION = '0.11'; # VERSION
our $AUTHORITY = 'cpan:NIGELM'; # AUTHORITY

# my my my my, these here to prevent foolishness like
# http://perlmonks.org/index.pl?node_id=251127#Stealing+Lexicals
(@_scrub    )= ( \&_scrub, "self, event, tagname, attr, attrseq, text");
(@_scrub_fh )= ( \&_scrub_fh, "self, event, tagname, attr, attrseq, text");

sub new {
    my $package = shift;
    my $p = HTML::Parser->new(
        api_version     => 3,
        default_h       => \@_scrub,
        marked_sections => 0,
        strict_comment  => 0,
        unbroken_text   => 1,
        case_sensitive  => 0,
        boolean_attribute_value => undef,
        empty_element_tags => 1,
    );

    my $self = {
        _p => $p,
        _rules => {
            '*' => 0,
        },
        _comment => 0,
        _process => 0,
        _r => "",
        _optimize => 1,
        _script => 0,
        _style  => 0,
    };

    $p->{"\0_s"} = bless $self, $package;

    return $self unless @_;

    my(%args)= @_;

    for my $f( qw[ default allow deny rules process comment ] ) {
        next unless exists $args{$f};
        if( ref $args{$f} ) {
            $self->$f( @{ $args{$f} } ) ;
        } else {
            $self->$f( $args{$f} ) ;
        }
    }

    return $self;
}


sub comment {
    return
        $_[0]->{_comment}
            if @_ == 1;
    $_[0]->{_comment} = $_[1];
    return;
}



sub process {
    return
        $_[0]->{_process}
            if @_ == 1;
    $_[0]->{_process} = $_[1];
    return;
}



sub script {
    return
        $_[0]->{_script}
            if @_ == 1;
    $_[0]->{_script} = $_[1];
    return;
}


sub style {
    return
        $_[0]->{_style}
            if @_ == 1;
    $_[0]->{_style} = $_[1];
    return;
}


sub allow {
    my $self = shift;
    for my $k(@_){
        $self->{_rules}{lc $k}=1;
    }
    $self->{_optimize} = 1; # each time a rule changes, reoptimize when parse

    return;
}



sub deny {
    my $self = shift;

    for my $k(@_){
        $self->{_rules}{lc $k} = 0;
    }

    $self->{_optimize} = 1; # each time a rule changes, reoptimize when parse

    return;
}


sub rules{
    my $self = shift;
    my(%rules)= @_;
    for my $k(keys %rules) {
        $self->{_rules}{lc $k} = $rules{$k};
    }

    $self->{_optimize} = 1; # each time a rule changes, reoptimize when parse

    return;
}


sub default {
    return
        $_[0]->{_rules}{'*'}
            if @_ == 1;

    $_[0]->{_rules}{'*'} = $_[1] if defined $_[1];
    $_[0]->{_rules}{'_'} = $_[2] if defined $_[2] and ref $_[2];
    $_[0]->{_optimize} = 1; # each time a rule changes, reoptimize when parse

    return;
}


sub scrub_file {
    if(@_ > 2){
        return unless defined $_[0]->_out($_[2]);
    } else {
        $_[0]->{_p}->handler( default => @_scrub );
    }

    $_[0]->_optimize() ;#if $_[0]->{_optimize};

    $_[0]->{_p}->parse_file($_[1]);

    return delete $_[0]->{_r} unless exists $_[0]->{_out};
    print { $_[0]->{_out} } $_[0]->{_r} if length $_[0]->{_r};
    delete $_[0]->{_out};
    return 1;
}


sub scrub {
    if(@_ > 2){
        return unless defined $_[0]->_out($_[2]);
    } else {
        $_[0]->{_p}->handler( default => @_scrub );
    }

    $_[0]->_optimize();# if $_[0]->{_optimize};

    $_[0]->{_p}->parse($_[1]);
    $_[0]->{_p}->eof();

    return delete $_[0]->{_r} unless exists $_[0]->{_out};
    delete $_[0]->{_out};
    return 1;
}



sub _out {
    my($self, $o ) = @_;

    unless( ref $o and ref \$o ne 'GLOB') {
        open my $F, '>', $o or return;
        binmode $F;
        $self->{_out} = $F;
    } else {
        $self->{_out} = $o;
    }

    $self->{_p}->handler( default => @_scrub_fh );

    return 1;
}



sub _validate {
    my($s, $t, $r, $a, $as) = @_;
    return "<$t>" unless %$a;

    $r = $s->{_rules}->{$r};
    my %f;

    for my $k( keys %$a ) {
        my $check = exists $r->{$k}? $r->{$k} : exists $r->{'*'}? $r->{'*'} : next;

        if( ref $check eq 'CODE' ) {
            my @v = $check->( $s, $t, $k, $a->{$k}, $a, \%f );
            next unless @v;
            $f{$k} = shift @v;
        } elsif( ref $check || length($check) > 1 ) {
            $f{$k} = $a->{$k} if $a->{$k} =~ m{$check};
        } elsif( $check ) {
            $f{$k} = $a->{$k};
        }
    }

    if( %f ){
        my %seen;
        return "<$t $r>"
            if $r = join ' ',
                    map {
                        defined $f{$_}
                        ? qq[$_="].encode_entities($f{$_}).q["]
                        : $_; # boolean attribute (TODO?)
                    } grep {
                        exists $f{$_} and !$seen{$_}++;
                    } @$as;
    }

    return "<$t>";
}


sub _scrub_str {
    my ( $p, $e, $t, $a, $as, $text ) = @_;

    my $s      = $p->{"\0_s"};
    my $outstr = '';

    if ( $e eq 'start' ) {
        if ( exists $s->{_rules}->{$t} )    # is there a specific rule
        {
            if ( ref $s->{_rules}->{$t} )    # is it complicated?(not simple;)
            {
                $outstr .= $s->_validate( $t, $t, $a, $as );
            }
            elsif ( $s->{_rules}->{$t} )     # validate using default attribute rule
            {
                $outstr .= $s->_validate( $t, '_', $a, $as );
            }
        }
        elsif ( $s->{_rules}->{'*'} )        # default allow tags
        {
            $outstr .= $s->_validate( $t, '_', $a, $as );
        }
    }
    elsif ( $e eq 'end' ) {
        my $place = 0;
        if ( exists $s->{_rules}->{$t} ) {
            $place = 1 if $s->{_rules}->{$t};
        }
        elsif ( $s->{_rules}->{'*'} ) {
            $place = 1;
        }
        if ( $place ) {
            if ( length $text ) {
                $outstr .= "</$t>";
            } else {
                substr $s->{_r}, -1, 0, ' /';
            }
        }
    }
    elsif ( $e eq 'comment' ) {
        $outstr .= $text if $s->{_comment};
    }
    elsif ( $e eq 'process' ) {
        $outstr .= $text if $s->{_process};
    }
    elsif ( $e eq 'text' or $e eq 'default' ) {
        $text =~ s/</&lt;/g;    #https://rt.cpan.org/Ticket/Attachment/8716/10332/scrubber.patch
        $text =~ s/>/&gt;/g;

        $outstr .= $text;
    }
    elsif ( $e eq 'start_document' ) {
        $outstr = "";
    }

    return $outstr;
}


sub _scrub_fh {
    my $self =  $_[0]->{"\0_s"};
    print { $self->{_out} } $self->{'_r'} if length $self->{_r};
    $self->{'_r'} = _scrub_str(@_);
}


sub _scrub {

    $_[0]->{"\0_s"}->{_r} .= _scrub_str(@_);
}

sub _optimize {
    my($self) = @_;

    my( @ignore_elements ) = grep { not $self->{"_$_"} } qw(script style);
    $self->{_p}->ignore_elements(@ignore_elements); # if @ is empty, we reset ;)

    return unless $self->{_optimize};
#sub allow
#    return unless $self->{_optimize}; # till I figure it out (huh)

    if( $self->{_rules}{'*'} ){       # default allow
        $self->{_p}->report_tags();   # so clear it
    } else {

        my(@reports) =
            grep {                # report only tags we want
                $self->{_rules}{$_}
            } keys %{
                $self->{_rules}
            };

        $self->{_p}->report_tags( # default deny, so optimize
            @reports
        ) if @reports;
    }

# sub deny
#    return unless $self->{_optimize}; # till I figure it out (huh)
    my(@ignores)=
        grep {
            not $self->{_rules}{$_}
        } grep {
            $_ ne '*'
        } keys %{
            $self->{_rules}
        };

    $self->{_p}->ignore_tags( # always ignore stuff we don't want
        @ignores
    ) if @ignores;

    $self->{_optimize}=0;
    return;
}


sub DESTROY {
    delete $_[0]->{_p}->{"\0_s"}; # break circular reference
}
1;

#print sprintf q[ '%-12s => %s,], "$_'", $h{$_} for sort keys %h;# perl!
#perl -ne"chomp;print $_;print qq'\t\t# test ', ++$a if /ok\(/;print $/" test.pl >test2.pl
#perl -ne"chomp;print $_;if( /ok\(/ ){s/\#test \d+$//;print qq'\t\t# test ', ++$a }print $/" test.pl >test2.pl
#perl -ne"chomp;if(/ok\(/){s/# test .*$//;print$_,qq'\t\t# test ',++$a}else{print$_}print$/" test.pl >test2.pl

__END__

=pod

=for stopwords html cpan callback homepage

=head1 NAME

HTML::Scrubber - Perl extension for scrubbing/sanitizing html

=head1 VERSION

version 0.11

=head1 SYNOPSIS

    use HTML::Scrubber;

    my $scrubber = HTML::Scrubber->new( allow => [ qw[ p b i u hr br ] ] );
    print $scrubber->scrub('<p><b>bold</b> <em>missing</em></p>');
    # output is: <p><b>bold</b> </p>

    # more complex input
    my $html = q[
    <style type="text/css"> BAD { background: #666; color: #666;} </style>
    <script language="javascript"> alert("Hello, I am EVIL!");    </script>
    <HR>
        a   => <a href=1>link </a>
        br  => <br>
        b   => <B> bold </B>
        u   => <U> UNDERLINE </U>
    ];

    print $scrubber->scrub($html);

    $scrubber->deny( qw[ p b i u hr br ] );

    print $scrubber->scrub($html);

=head1 DESCRIPTION

If you want to "scrub" or "sanitize" html input in a reliable and
flexible fashion, then this module is for you.

I wasn't satisfied with HTML::Sanitizer because it is based on
HTML::TreeBuilder, so I thought I'd write something similar that
works directly with HTML::Parser.

=head1 METHODS

First a note on documentation: just study the L<EXAMPLE|"EXAMPLE"> below.
It's all the documentation you could need

Also, be sure to read all the comments as well as
L<How does it work?|"How does it work?">.

If you're new to perl, good luck to you.

=head2 comment

    warn "comments are  ", $p->comment ? 'allowed' : 'not allowed';
    $p->comment(0);  # off by default

=head2 process

    warn "process instructions are  ", $p->process ? 'allowed' : 'not allowed';
    $p->process(0);  # off by default

=head2 script

    warn "script tags (and everything in between) are supressed"
        if $p->script;      # off by default
    $p->script( 0 || 1 );

B<**> Please note that this is implemented
using HTML::Parser's ignore_elements function,
so if C<script> is set to true,
all script tags encountered will be validated like all other tags.

=head2 style

    warn "style tags (and everything in between) are supressed"
        if $p->style;       # off by default
    $p->style( 0 || 1 );

B<**> Please note that this is implemented
using HTML::Parser's ignore_elements function,
so if C<style> is set to true,
all style tags encountered will be validated like all other tags.

=head2 allow

    $p->allow(qw[ t a g s ]);

=head2 deny

    $p->deny(qw[ t a g s ]);

=head2 rules

    $p->rules(
        img => {
            src => qr{^(?!http://)}i, # only relative image links allowed
            alt => 1,                 # alt attribute allowed
            '*' => 0,                 # deny all other attributes
        },
        a => {
            href => sub { ... },      # check or adjust with a callback
        },
        b => 1,
        ...
    );

Updates set of attribute rules. Each rule can be 1/0, regular expression
or a callback. Values longer than 1 char are treated as regexps. Callback
is called with the following arguments: this object, tag name, attribute
name and attribute value, should return empty list to drop attribute,
C<undef> to keep it without value or a new scalar value.

=head2 default

    print "default is ", $p->default();
    $p->default(1);      # allow tags by default
    $p->default(
        undef,           # don't change
        {                # default attribute rules
            '*' => 1,    # allow attributes by default
        }
    );

=head2 scrub_file

    $html = $scrubber->scrub_file('foo.html');   ## returns giant string
    die "Eeek $!" unless defined $html;  ## opening foo.html may have failed
    $scrubber->scrub_file('foo.html', 'new.html') or die "Eeek $!";
    $scrubber->scrub_file('foo.html', *STDOUT)
        or die "Eeek $!"
            if fileno STDOUT;

=head2 scrub

    print $scrubber->scrub($html);  ## returns giant string
    $scrubber->scrub($html, 'new.html') or die "Eeek $!";
    $scrubber->scrub($html', *STDOUT)
        or die "Eeek $!"
            if fileno STDOUT;

=for comment _out
    $scrubber->_out(*STDOUT) if fileno STDOUT;
    $scrubber->_out('foo.html') or die "eeek $!";

=for comment _validate
Uses $self->{_rules} to do attribute validation.
Takes tag, rule('_' || $tag), attrref.

=for comment _scrub_str

I<default> handler, used by both _scrub and _scrub_fh
Moved all the common code (basically all of it) into a single routine for
ease of maintenance

=for comment _scrub_fh

I<default> handler, does the scrubbing if we're scrubbing out to a file.
Now calls _scrub_str and pushes that out to a file.

=for comment _scrub

I<default> handler, does the scrubbing if we're returning a giant string.
Now calls _scrub_str and appends that to the output string.

=head1 How does it work?

When a tag is encountered, HTML::Scrubber
allows/denies the tag using the explicit rule if one exists.

If no explicit rule exists, Scrubber applies the default rule.

If an explicit rule exists,
but it's a simple rule(1),
the default attribute rule is applied.

=head2 EXAMPLE

=for example begin

    #!/usr/bin/perl -w
    use HTML::Scrubber;
    use strict;

    my @allow = qw[ br hr b a ];

    my @rules = (
        script => 0,
        img => {
            src => qr{^(?!http://)}i, # only relative image links allowed
            alt => 1,                 # alt attribute allowed
            '*' => 0,                 # deny all other attributes
        },
    );

    my @default = (
        0   =>    # default rule, deny all tags
        {
            '*'           => 1, # default rule, allow all attributes
            'href'        => qr{^(?:http|https|ftp)://}i,
            'src'         => qr{^(?:http|https|ftp)://}i,
    #   If your perl doesn't have qr
    #   just use a string with length greater than 1
            'cite'        => '(?i-xsm:^(?:http|https|ftp):)',
            'language'    => 0,
            'name'        => 1, # could be sneaky, but hey ;)
            'onblur'      => 0,
            'onchange'    => 0,
            'onclick'     => 0,
            'ondblclick'  => 0,
            'onerror'     => 0,
            'onfocus'     => 0,
            'onkeydown'   => 0,
            'onkeypress'  => 0,
            'onkeyup'     => 0,
            'onload'      => 0,
            'onmousedown' => 0,
            'onmousemove' => 0,
            'onmouseout'  => 0,
            'onmouseover' => 0,
            'onmouseup'   => 0,
            'onreset'     => 0,
            'onselect'    => 0,
            'onsubmit'    => 0,
            'onunload'    => 0,
            'src'         => 0,
            'type'        => 0,
        }
    );

    my $scrubber = HTML::Scrubber->new();
    $scrubber->allow( @allow );
    $scrubber->rules( @rules ); # key/value pairs
    $scrubber->default( @default );
    $scrubber->comment(1); # 1 allow, 0 deny

    ## preferred way to create the same object
    $scrubber = HTML::Scrubber->new(
        allow   => \@allow,
        rules   => \@rules,
        default => \@default,
        comment => 1,
        process => 0,
    );

    require Data::Dumper,die Data::Dumper::Dumper($scrubber) if @ARGV;

    my $it = q[
        <?php   echo(" EVIL EVIL EVIL "); ?>    <!-- asdf -->
        <hr>
        <I FAKE="attribute" > IN ITALICS WITH FAKE="attribute" </I><br>
        <B> IN BOLD </B><br>
        <A NAME="evil">
            <A HREF="javascript:alert('die die die');">HREF=JAVA &lt;!&gt;</A>
            <br>
            <A HREF="image/bigone.jpg" ONMOUSEOVER="alert('die die die');">
                <IMG SRC="image/smallone.jpg" ALT="ONMOUSEOVER JAVASCRIPT">
            </A>
        </A> <br>
    ];

    print "#original text",$/, $it, $/;
    print
        "#scrubbed text (default ",
        $scrubber->default(), # no arguments returns the current value
        " comment ",
        $scrubber->comment(),
        " process ",
        $scrubber->process(),
        " )",
        $/,
        $scrubber->scrub($it),
        $/;

    $scrubber->default(1); # allow all tags by default
    $scrubber->comment(0); # deny comments

    print
        "#scrubbed text (default ",
        $scrubber->default(),
        " comment ",
        $scrubber->comment(),
        " process ",
        $scrubber->process(),
        " )",
        $/,
        $scrubber->scrub($it),
        $/;

    $scrubber->process(1);        # allow process instructions (dangerous)
    $default[0] = 1;              # allow all tags by default
    $default[1]->{'*'} = 0;       # deny all attributes by default
    $scrubber->default(@default); # set the default again

    print
        "#scrubbed text (default ",
        $scrubber->default(),
        " comment ",
        $scrubber->comment(),
        " process ",
        $scrubber->process(),
        " )",
        $/,
        $scrubber->scrub($it),
        $/;

=for example end

=head2 FUN

If you have Test::Inline (and you've installed HTML::Scrubber), try

    pod2test Scrubber.pm >scrubber.t
    perl scrubber.t

=head1 SEE ALSO

L<HTML::Parser>, L<Test::Inline>, L<HTML::Sanitizer>.

=head1 INSTALLATION

See perlmodinstall for information and options on installing Perl modules.

=head1 BUGS AND LIMITATIONS

You can make new bug reports, and view existing ones, through the
web interface at L<http://rt.cpan.org/Public/Dist/Display.html?Name=HTML-Scrubber>.

=head1 AVAILABILITY

The project homepage is L<https://metacpan.org/release/HTML-Scrubber>.

The latest version of this module is available from the Comprehensive Perl
Archive Network (CPAN). Visit L<http://www.perl.com/CPAN/> to find a CPAN
site near you, or see L<https://metacpan.org/module/HTML::Scrubber/>.

=head1 AUTHORS

=over 4

=item *

Ruslan Zakirov <Ruslan.Zakirov@gmail.com>

=item *

Nigel Metheringham <nigelm@cpan.org>

=item *

D. H. <podmaster@cpan.org>

=back

=head1 COPYRIGHT AND LICENSE

This software is copyright (c) 2013 by Ruslan Zakirov, Nigel Metheringham, 2003-2004 D. H..

This is free software; you can redistribute it and/or modify it under
the same terms as the Perl 5 programming language system itself.

=cut