This file is indexed.

/usr/share/perl5/HTML/WikiConverter/Markdown.pm is in libhtml-wikiconverter-markdown-perl 0.06-1.

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
package HTML::WikiConverter::Markdown;

use warnings;
use strict;

use base 'HTML::WikiConverter';
our $VERSION = '0.06';

use Params::Validate ':types';
use HTML::Entities;
use HTML::Tagset;
use URI;

=head1 NAME

HTML::WikiConverter::Markdown - Convert HTML to Markdown markup

=head1 SYNOPSIS

  use HTML::WikiConverter;
  my $wc = new HTML::WikiConverter( dialect => 'Markdown' );
  print $wc->html2wiki( $html );

=head1 DESCRIPTION

This module contains rules for converting HTML into Markdown markup.
You should not use this module directly; HTML::WikiConverter is the
entry point for html->wiki conversion (eg, see synopsis above). See
L<HTML::WikiConverter> for additional usage details.

=head1 ATTRIBUTES

In addition to the regular set of attributes recognized by the
L<HTML::WikiConverter> constructor, this dialect also accepts the
following attributes that can be passed into the C<new()>
constructor. See L<HTML::WikiConverter/ATTRIBUTES> for usage details.

=head2 header_style

Possible values: C<'setext'>, C<'atx'>. Determines how headers
C<h1>-C<h6> will be formatted. See
L<http://daringfireball.net/projects/markdown/syntax#header> for more
information. Default is C<'atx'>.

=head2 link_style

Possible values: C<'inline'>, C<'reference'>. See
L<http://daringfireball.net/projects/markdown/syntax#link> for more
information. Default is C<'reference'>.

=head2 force_inline_anchor_links

Possible values: C<0>, C<1>. If enabled, links to anchors within the
same page (eg, C<#some-anchor>) will always produce inline Markdown
links, even under reference link style. This might be useful for
building tables of contents. Default is C<0>.

=head2 image_style

Possible values: C<'inline'>, C<'reference'>. See
L<http://daringfireball.net/projects/markdown/syntax#img> for more
information. Default is C<'reference'>.

=head2 image_tag_fallback

Possible values: C<0>, C<1>. Markdown's image markup does not
support image dimensions. If C<image_tag_fallback> is enabled, image
tags containing dimensional information (ie, width or height) will not
be converted into Markdown markup. Rather, they will be roughly
preserved in their HTML form. Default is C<1>.

=head2 unordered_list_style

Possible values: C<'asterisk'>, C<'plus'>, C<'dash'>. See
L<http://daringfireball.net/projects/markdown/syntax#list> for more
information. Default is C<'asterisk'>.

=head2 ordered_list_style

Possible values: C<'sequential'>, C<'one-dot'>. Markdown supports two
different markups for ordered lists. Sequential style gives each list
element its own ordinal number (ie, C<'1.'>, C<'2.'>, C<'3.'>,
etc.). One-dot style gives each list element the same ordinal number
(ie, C<'1.'>). See
L<http://daringfireball.net/projects/markdown/syntax#list> for more
information. Default is C<'sequential'>.

=head2 md_extra

Possible values: C<0>, C<1>. Support MarkDown Extra
L<https://github.com/jmcmanus/pagedown-extra> extensions. Default is C<0>.

This support is incomplete.

    # Tables				Supported
    # Fenced Code Blocks
    # Definition Lists		Supported
    # Footnotes
    # Special Attributes
    # SmartyPants
    # Newlines
    # Strikethrough

=cut

sub attributes {
    {
        header_style              => { default => 'atx',        type => SCALAR },
        link_style                => { default => 'reference',  type => SCALAR },
        force_inline_anchor_links => { default => 0,            type => BOOLEAN },
        image_style               => { default => 'reference',  type => SCALAR },
        image_tag_fallback        => { default => 1,            type => BOOLEAN },
        unordered_list_style      => { default => 'asterisk',   type => SCALAR },
        ordered_list_style        => { default => 'sequential', type => SCALAR },

        # Requires H::WC version 0.67
        p_strict => { default => 0 },
        md_extra => { default => 0, type => BOOLEAN },
    };
}

my @common_attrs = qw/ id class lang dir title style /;

# Hack to accommodate bug #43997 - multiline code blocks
my $code_block_prefix = 'bqwegsdfbwegadfbnsdfbahwerfgkjnsdfbohqw34t927398y5jnwrteb8uq34inb';

sub rules {
    my $self = shift;

    my %rules = (
        hr => { replace  => "\n\n----\n\n" },
        br => { preserve => 1, empty => 1, end => \&_br_end },
        p => {
            block       => 1,
            trim        => 'both',
            line_format => 'multi',
            line_prefix => \&_p_prefix
        },
        blockquote => {
            block       => 1,
            trim        => 'both',
            line_format => 'blocks',
            line_prefix => '> '
        },
        ul => { block => 1,           line_format => 'multi' },
        ol => { alias => 'ul' },
        li => { start => \&_li_start, trim        => 'leading' },

        i          => { start       => '_',                end   => '_' },
        em         => { alias       => 'i' },
        b          => { start       => '**',               end   => '**' },
        strong     => { alias       => 'b' },
        code       => { start       => \&_code_delim,      end   => \&_code_delim },
        code_block => { line_prefix => $code_block_prefix, block => 1 },

        a   => { replace     => \&_link },
        img => { replace     => \&_img },
        div => { block       => 1, line_format => 'blocks' },
        pre => { line_prefix => "\t", block => 1, line_format => 'blocks' },
    );

    for ( 1 .. 6 ) {
        $rules{"h$_"} = {
            start => \&_header_start,
            end   => \&_header_end,
            trim  => 'both',
            block => 1
        };
    }

    for (qw/ table caption tr th td /) {
        $rules{$_} = {
            preserve    => 1,
            attrs       => \@common_attrs,
            start       => "\n",
            end         => "\n",
            line_format => 'multi'
        };
    }

    # MarkDown Extra https://github.com/jmcmanus/pagedown-extra
    # Tables				Supported
    # Fenced Code Blocks
    # Definition Lists		Supported
    # Footnotes
    # Special Attributes
    # SmartyPants
    # Newlines
    # Strikethrough
    if ( $self->md_extra ) {
        $rules{dt} = { start => "\n",    end => "\n", trim => 'both', };
        $rules{dd} = { start => ":    ", end => "\n", trim => 'both', };
        delete( $rules{table} );
        delete( $rules{caption} );
        $rules{tr}    = { start => "\n",    end  => "|", trim => 'both' };
        $rules{td}    = { start => "|",     trim => 'both' };
        $rules{th}    = { alias => 'td' };
        $rules{thead} = { end   => "\n|-|", trim => 'both' };
        # need an extra line here as some lists can contain complex block structures.
        $rules{ul} = { block => 1, line_format => 'blocks' };
        $rules{li} = { start => \&_li_start, blocks => 1, trim => 'leading' };
    }

    return \%rules;
}

sub _br_end {
    my ( $self, $node, $rules ) = @_;
    return "\n";
}

sub _header_start {
    my ( $self, $node, $rules ) = @_;
    return '' unless $self->header_style eq 'atx';

    ( my $level = $node->tag ) =~ s/\D//g;
    return unless $level;

    my $hr = ('#') x $level;
    return "$hr ";
}

sub _header_end {
    my ( $self, $node, $rules ) = @_;
    my $anchor = '';

    if ( $node->id() ) {
        $anchor = "\t{#" . $node->id() . "}";
    }

    return $anchor unless $self->header_style eq 'setext';
    ( my $level = $node->tag ) =~ s/\D//g;
    return $anchor unless $level;

    my $symbol = $level == 1 ? '=' : '-';
    my $len    = length $self->get_elem_contents($node);
    my $bar    = ($symbol) x $len;
    return "$anchor\n$bar\n";
}

sub _link {
    my ( $self, $node, $rules ) = @_;

    my $url   = $self->_abs2rel( $node->attr('href') || '' );
    my $text  = $self->get_elem_contents($node);
    my $title = $node->attr('title') || '';

    my $style = $self->link_style;
    $style = 'inline' if $url =~ /^\#/ and $self->force_inline_anchor_links;

    if ( $url eq $text ) {
        return sprintf "<%s>", $url;
    }
    elsif ( $style eq 'inline' ) {
        return sprintf "[%s](%s \"%s\")", $text, $url, $title if $title;
        return sprintf "[%s](%s)", $text, $url;
    }
    elsif ( $style eq 'reference' ) {
        my $id = $self->_next_link_id;
        $self->_add_link( { id => $id, url => $url, title => $title } );
        return sprintf "[%s][%s]", $text, $id;
    }
}

sub _last_link_id { shift->_attr( { internal => 1 }, _last_link_id => @_ ) }

sub _links { shift->_attr( { internal => 1 }, _links => @_ ) }

sub _next_link_id {
    my $self = shift;
    my $next_id = ( $self->_last_link_id || 0 ) + 1;
    $self->_last_link_id($next_id);
    return $next_id;
}

sub _add_link {
    my ( $self, $link ) = @_;
    $self->_links( [ @{ $self->_links || [] }, $link ] );
}

sub _img {
    my ( $self, $node, $rules ) = @_;

    my $url    = $node->attr('src')    || '';
    my $text   = $node->attr('alt')    || '';
    my $title  = $node->attr('title')  || '';
    my $width  = $node->attr('width')  || '';
    my $height = $node->attr('height') || '';

    if ( $width || $height and $self->image_tag_fallback ) {
        return "<img " . $self->get_attr_str( $node, qw/ src width height alt /, @common_attrs ) . " />";
    }
    elsif ( $self->image_style eq 'inline' ) {
        return sprintf "![%s](%s \"%s\")", $text, $url, $title if $title;
        return sprintf "![%s](%s)", $text, $url;
    }
    elsif ( $self->image_style eq 'reference' ) {
        my $id = $self->_next_link_id;
        $self->_add_link( { id => $id, url => $url, title => $title } );
        return sprintf "![%s][%s]", $text, $id;
    }
}

sub _li_start {
    my ( $self, $node, $rules ) = @_;
    my @parent_lists = $node->look_up( _tag => qr/ul|ol/ );

    my $prefix = ('  ') x ( @parent_lists - 1 );

    my $bullet = '';
    $bullet = $self->_ul_li_start if $node->parent and $node->parent->tag eq 'ul';
    $bullet = $self->_ol_li_start( $node->parent )
        if $node->parent and $node->parent->tag eq 'ol';
    return "\n$prefix$bullet ";
}

sub _ul_li_start {
    my $self  = shift;
    my $style = $self->unordered_list_style;
    return '*' if $style eq 'asterisk';
    return '+' if $style eq 'plus';
    return '-' if $style eq 'dash';
    die "no such unordered list style: '$style'";
}

my %ol_count = ();

sub _ol_li_start {
    my ( $self, $ol ) = @_;
    my $style = $self->ordered_list_style;

    if ( $style eq 'one-dot' ) {
        return '1.';
    }
    elsif ( $style eq 'sequential' ) {
        my $count = ++$ol_count{$ol};
        return "$count.";
    }
    else {
        die "no such ordered list style: $style";
    }
}

sub _p_prefix {
    my ( $wc, $node, $rules ) = @_;
    return $node->look_up( _tag => 'li' ) ? '    ' : '';
}

sub preprocess_node {
    my ( $self, $node ) = @_;
    return unless $node->tag and $node->parent and $node->parent->tag;

    if ( $node->tag eq 'blockquote' ) {
        my @non_phrasal_children = grep { !$self->_is_phrase_tag( $_->tag ) } $node->content_list;
        unless (@non_phrasal_children)
        {    # ie, we have things like <blockquote>blah blah blah</blockquote>, without a <p> or something
            $self->_envelop_children( $node, HTML::Element->new('p') );
        }
    }
    elsif ( $node->tag eq '~text' ) {
        $self->_escape_text($node);

        # bug #43998
        $self->_decode_entities_in_code($node)
            if $node->parent->tag eq 'code'
            or $node->parent->tag eq 'code_block';
    }
}

sub preprocess_tree {
    my ( $self, $root ) = @_;
    foreach my $node ( $root->descendants ) {

        # bug #43997 - multiline code blocks
        if ( $self->_text_is_within_code_pre($node) ) {
            $self->_convert_to_code_block($node);
        }
    }
}

sub _text_is_within_code_pre {
    my ( $self, $node ) = @_;
    return unless $node->parent->parent and $node->parent->parent->tag;

    # Must be <code><pre>...</pre></code> (or <pre><code>...</code></pre>)
    my $code_pre = $node->parent->tag eq 'code' && $node->parent->parent->tag eq 'pre';
    my $pre_code = $node->parent->tag eq 'pre'  && $node->parent->parent->tag eq 'code';
    return unless $code_pre or $pre_code;

    # Can't be any other nodes in a code block
    return if $node->left or $node->right;
    return if $node->parent->left or $node->parent->right;

    return 1;
}

sub _convert_to_code_block {
    my ( $self, $node ) = @_;
    $node->parent->parent->replace_with_content->delete;
    $node->parent->tag("code_block");
}

sub _envelop_children {
    my ( $self, $node, $new_child ) = @_;

    my @children = $node->detach_content;
    $node->push_content($new_child);
    $new_child->push_content(@children);
}

# special handling for: ` _ # . [ !
my @escapes = qw( \\ * { } _ ` );

my %backslash_escapes = (
    '\\' => [ '0923fjhtml2wikiescapedbackslash',  "\\\\" ],
    '*'  => [ '0923fjhtml2wikiescapedasterisk',   "\\*" ],
    '{'  => [ '0923fjhtml2wikiescapedopenbrace',  "\\{" ],
    '}'  => [ '0923fjhtml2wikiescapedclosebrace', "\\}" ],
    '_'  => [ '0923fjhtml2wikiescapedunderscore', "\\_" ],
    '`'  => [ '0923fjhtml2wikiescapedbacktick',   "\\`" ],
);

sub _escape_text {
    my ( $self, $node ) = @_;
    my $text = $node->attr('text') || '';

    #
    # (bug #43998)
    # Only backslash-escape backticks that don't occur within <code>
    # tags. Those within <code> tags are left alone and the backticks to
    # signal a <code> tag get upgraded to a double-backtick by
    # _code_delim().
    #
    # (bug #43993)
    # Likewise, only backslash-escape underscores that occur outside
    # <code> tags.
    #

    my $inside_code
        = $node->look_up( _tag => 'code' )
        || $node->look_up( _tag => 'code_block' )
        || $node->look_up( _tag => 'pre' );

    if ( not $inside_code ) {
        my $escapes = join '', @escapes;
        $text =~ s/([\Q$escapes\E])/$backslash_escapes{$1}->[0]/g;
        $text =~ s/^([\d]+)\./$1\\./;
        $text =~ s/^\#/\\#/;
        $text =~ s/\!\[/\\![/g;
        $text =~ s/\]\[/]\\[/g;

        $node->attr( text => $text );
    }
}

# bug #43998
sub _code_delim {
    my ( $self, $node, $rules ) = @_;
    my $contents = $self->get_elem_contents($node);
    return $contents =~ /\`/ ? '``' : '`';
}

# bug #43996
sub _decode_entities_in_code {
    my ( $self, $node ) = @_;
    my $text = $node->attr('text') || '';
    return unless $text;

    HTML::Entities::_decode_entities( $text, { 'amp' => '&', 'lt' => '<', 'gt' => '>' } );
    $node->attr( text => $text );
}

sub postprocess_output {
    my ( $self, $outref ) = @_;
    $$outref =~ s/\Q$code_block_prefix\E/    /gm;
    $self->_unescape_text($outref);
    $self->_add_references($outref);
}

sub _unescape_text {
    my ( $self, $outref ) = @_;
    foreach my $escape ( values %backslash_escapes ) {
        $$outref =~ s/$escape->[0]/$escape->[1]/g;
    }
}

sub _add_references {
    my ( $self, $outref ) = @_;
    my @links = @{ $self->_links || [] };
    return unless @links;

    my $links = '';
    foreach my $link (@links) {
        my $id    = $link->{id}    || '';
        my $url   = $link->{url}   || '';
        my $title = $link->{title} || '';
        if ($title) {
            $links .= sprintf "  [%s]: %s \"%s\"\n", $id, $url, $title;
        }
        else {
            $links .= sprintf "  [%s]: %s\n", $id, $url;
        }
    }

    $self->_links( [] );
    $self->_last_link_id(0);

    $$outref .= "\n\n$links";
    $$outref =~ s/\s+$//gs;
}

sub _is_phrase_tag {
    my $tag = pop || '';
    return $HTML::Tagset::isPhraseMarkup{$tag} || $tag eq '~text';
}

sub _abs2rel {
    my ( $self, $uri ) = @_;
    return $uri unless $self->base_uri;
    return URI->new($uri)->rel( $self->base_uri )->as_string;
}

=head1 AUTHOR

David J. Iberri, C<< <diberri at cpan.org> >>

=head1 BUGS

Please report any bugs or feature requests to
C<bug-html-wikiconverter-markdown at rt.cpan.org>, or through the web interface at
L<http://rt.cpan.org/NoAuth/ReportBug.html?Queue=HTML-WikiConverter-Markdown>.
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 HTML::WikiConverter::Markdown

You can also look for information at:

=over 4

=item * AnnoCPAN: Annotated CPAN documentation

L<http://annocpan.org/dist/HTML-WikiConverter-Markdown>

=item * CPAN Ratings

L<http://cpanratings.perl.org/d/HTML-WikiConverter-Markdown>

=item * RT: CPAN's request tracker

L<http://rt.cpan.org/NoAuth/Bugs.html?Dist=HTML-WikiConverter-Markdown>

=item * Search CPAN

L<http://search.cpan.org/dist/HTML-WikiConverter-Markdown>

=back

=head1 COPYRIGHT & LICENSE

Copyright 2006 David J. Iberri, all rights reserved.

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

=cut

1;