This file is indexed.

/usr/share/perl5/HTML/Quoted.pm is in libhtml-quoted-perl 0.04-1.

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
use 5.008;
use strict;
use warnings;

package HTML::Quoted;

our $VERSION = '0.04';

=head1 NAME

HTML::Quoted - extract structure of quoted HTML mail message

=head1 SYNOPSIS

    use HTML::Quoted;
    my $html = '...';
    my $struct = HTML::Quoted->extract( $html );

=head1 DESCRIPTION

Parses and extracts quotation structure out of a HTML message.
Purpose and returned structures are very similar to
L<Text::Quoted>.

=head1 SUPPORTED FORMATS

Variouse MUAs use quite different approaches for quoting in mails.

Some use I<blockquote> tag and it's quite easy to parse.

Some wrap text into I<p> tags and add '>' in the beginning of the
paragraphs.

Things gettign messier when it's an HTML reply on plain text mail
thread.

If B<you found format> that is not supported then file a bug report
via rt.cpan.org with as short as possible example. B<Test file>
is even better. Test file with patch is the best. Not obviouse patches
without tests suck.

=head1 METHODS

=head2 extract

    my $struct = HTML::Quoted->extract( $html );

Takes a string with HTML and returns array reference. Each element
in the array either array or hash. For example:


    [
        { 'raw' => 'Hi,' },
        { 'raw' => '<div><br><div>On date X wrote:<br>' },
        [
             { 'raw' => '<blockquote>' },
             { 'raw' => 'Hello,' },
             { 'raw' => '<div>How are you?</div>' },
             { 'raw' => '</blockquote>' }
        ],
        ...
    ]

Hashes represent a part of the html. The following keys are
meaningful at the moment:

=over 4

=item * raw - raw HTML

=item * quoter_raw, quoter - raw and decoded (entities are converted) quoter if block is prefixed with quoting characters

=back

=cut

sub extract {
    my $self = shift;
    my $parser = HTML::Quoted::Parser->new(
        api_version => 3,
        handlers => {
            start_document => [handle_doc_start => 'self'],
            end_document   => [handle_doc_end => 'self'],
            start   => [handle_start   => 'self, tagname, attr, attrseq, text'],
            end     => [handle_end     => 'self, tagname, text'],
            text    => [handle_text    => 'self, text, is_cdata'],
            default => [handle_default => 'self, event, text'],
        },
    );
    $parser->empty_element_tags(1);
    $parser->parse($_[0]);
    $parser->eof;

    return $parser->{'html_quoted_parser'}{'result'};
}

=head2 combine_hunks

  my $html = HTML::Quoted->combine_hunks( $arrayref_of_hunks );

Takes the output of C<extract> and turns it back into HTML.

=cut

sub combine_hunks {
    my ($self, $hunks) = @_;

    join "",
      map {; ref $_ eq 'HASH' ? $_->{raw} : $self->combine_hunks($_) } @$hunks;
}

package HTML::Quoted::Parser;
use base "HTML::Parser";

sub handle_doc_start {
    my ($self) = @_;
    my $meta = $self->{'html_quoted_parser'} = {};
    my $res = $meta->{'result'} = [{}];
    $meta->{'current'} = $res->[0];
    $meta->{'stack'} = [$res];
    $meta->{'in'} = { quote => 0, block => [0] };
}

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

    my $meta = $self->{'html_quoted_parser'};
    pop @{ $meta->{'result'} } if ref $meta->{'result'}[-1] eq 'HASH' && !keys %{ $meta->{'result'}[-1] };
    $self->organize( $meta->{'result'} );
}

sub organize {
    my ($self, $list) = @_;

    my $prev = undef;
    foreach my $e ( splice @$list ) {
        if ( ref $e eq 'ARRAY' ) {
            push @$list, $self->organize($e);
            $prev = undef;
        }
        elsif ( $e->{'block'} ) {
            push @$list, $e;
            $prev = undef;
        }
        elsif ( defined $e->{'quoter'} ) {
            if ( !$prev || $self->combine( $prev, $e ) ) {
                push @$list, $prev = [ $e ];
            }
        } else {
            push @$list, $e;
            $prev = undef;
        }
    }
    return $list;
}

sub combine {
    my ($self, $list, $e) = @_;
    my ($last) = grep ref $_ eq 'HASH', reverse @$list;
    if ( $last->{'quoter'} eq $e->{'quoter'} ) {
        push @$list, $e;
        return ();
    }
    elsif ( rindex( $last->{'quoter'}, $e->{'quoter'}, 0) == 0 ) {
        @$list = ( [@$list], $e );
        return ();
    }
    elsif ( rindex( $e->{'quoter'}, $last->{'quoter'}, 0) == 0 ) {
        if ( ref $list->[-1] eq 'ARRAY' && !$self->combine( $list->[-1], $e ) ) {
            return ();
        }
        push @$list, [ $e ];
        return ();
    }
    else {
        return $e;
    }
}

# XXX: p is treated as inline tag as it's groupping tag that
# can not contain blocks inside, use span for groupping
my %INLINE_TAG = map {$_ => 1 } qw(
    a br span bdo map img
    tt i b big small
    em strong dfn code q
    samp kbd var cite abbr acronym sub sup
    p
);

my %ENTITIES = (
    '&gt;' => '>',
    '&#62;' => '>',
    '&#x3e;' => '>',
);

my $re_amp = join '|', map "\Q$_\E", '>', grep $ENTITIES{$_} eq '>', keys %ENTITIES;
$re_amp = qr{$re_amp};
my $re_quote_char  = qr{[!#%=|:]};
my $re_quote_chunk = qr{ $re_quote_char(?!\w) | \w*$re_amp+ }x;
my $re_quoter     = qr{ $re_quote_chunk (?:[ \\t]* $re_quote_chunk)* }x;

sub handle_start {
    my ($self, $tag, $attr, $attrseq, $text) = @_;

    my $meta = $self->{'html_quoted_parser'};
    my $stack = $meta->{'stack'};

    if ( $meta->{'in'}{'br'} ) {
        $meta->{'in'}{'br'} = 0;
        push @{ $stack->[-1] }, $meta->{'current'} = {};
    }

    if ( $tag eq 'blockquote' ) {
        my $new = [{ quote => 1, block => 1 }];
        push @{ $stack->[-1] }, $new;
        push @$stack, $new; # HACK: everything pushed into this
        $meta->{'current'} = $new->[0];
        $meta->{'in'}{'quote'}++;
        push @{ $meta->{'in'}{'block'} }, 0;
        $meta->{'current'}{'raw'} .= $text;
        push @{ $stack->[-1] }, $meta->{'current'} = {};
    }
    elsif ( $tag eq 'br' && !$meta->{'in'}{'block'}[-1] ) {
        $meta->{'current'}{'raw'} .= $text;
        my $line = $meta->{'current'}{'raw'};
        if ( $line =~ /^\n*($re_quoter)/ ) {
            $meta->{'current'}{'quoter_raw'} = $1;
            $meta->{'current'}{'quoter'} = $self->decode_entities(
                $meta->{'current'}{'quoter_raw'}
            );
        }
        $meta->{'in'}{'br'} = 1;
    }
    elsif ( !$INLINE_TAG{ $tag } ) {
        if ( !$meta->{'in'}{'block'}[-1] && keys %{ $meta->{'current'} } ) {
            push @{ $stack->[-1] }, $meta->{'current'} = { raw => '' };
        }
        $meta->{'current'}{'block'} = 1;
        $meta->{'current'}{'raw'} .= $text;

        $meta->{'in'}{'block'}[-1]++;
    }
    else {
        $meta->{'current'}{'raw'} .= $text;
    }
}

sub handle_end {
    my ($self, $tag, $text) = @_;

    my $meta = $self->{'html_quoted_parser'};
    my $stack = $meta->{'stack'};

    if ( $meta->{'in'}{'br'} && $tag ne 'br' ) {
        $meta->{'in'}{'br'} = 0;
        push @{ $stack->[-1] }, $meta->{'current'} = {}
    }

    $meta->{'current'}{'raw'} .= $text;

    if ( $tag eq 'blockquote' ) {
        pop @$stack;
        pop @{ $meta->{'in'}{'block'} };
        push @{ $stack->[-1] }, $meta->{'current'} = {};
        $meta->{'in'}{'quote'}--;
    }
    elsif ( $tag eq 'br' ) {
        $meta->{'in'}{'br'} = 0;
        push @{ $stack->[-1] }, $meta->{'current'} = {}
    }
    elsif ( $tag eq 'p' ) {
        push @{ $stack->[-1] }, $meta->{'current'} = {}
    }
    elsif ( !$INLINE_TAG{ $tag } ) {
        $meta->{'in'}{'block'}[-1]--;
        if ( $meta->{'in'}{'block'}[-1] ) {
            $meta->{'current'}{'block'} = 1;
        } else {
            push @{ $stack->[-1] }, $meta->{'current'} = {};
        }
    }
}

sub decode_entities {
    my ($self, $string) = @_;
    $string =~ s/(&(?:[a-z]+|#[0-9]|#x[0-9a-f]+);)/ $ENTITIES{$1} || $ENTITIES{lc $1} || $1 /ge;
    return $string;
}

sub handle_text {
    my ($self, $text) = @_;
    my $meta = $self->{'html_quoted_parser'};
    if ( $meta->{'in'}{'br'} ) {
        $meta->{'in'}{'br'} = 0;
        push @{ $meta->{'stack'}[-1] }, $meta->{'current'} = {};
    }
    $self->{'html_quoted_parser'}{'current'}{'raw'} .= $text;
}

sub handle_default {
    my ($self, $event, $text) = @_;
    my $meta = $self->{'html_quoted_parser'};
    if ( $meta->{'in'}{'br'} ) {
        $meta->{'in'}{'br'} = 0;
        push @{ $meta->{'stack'}[-1] }, $meta->{'current'} = {};
    }
    $self->{'html_quoted_parser'}{'current'}{'raw'} .= $text;
}

=head1 AUTHOR

Ruslan.Zakirov E<lt>ruz@bestpractical.comE<gt>

=head1 LICENSE

Under the same terms as perl itself.

=cut

1;