File: StripWhitespace.pm

package info (click to toggle)
libhtml-formfu-perl 2.07000-2
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 4,396 kB
  • sloc: perl: 12,777; makefile: 9; sql: 5
file content (223 lines) | stat: -rw-r--r-- 4,678 bytes parent folder | download | duplicates (2)
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
use strict;

package HTML::FormFu::OutputProcessor::StripWhitespace;
$HTML::FormFu::OutputProcessor::StripWhitespace::VERSION = '2.07';
# ABSTRACT: Strip shitespace from HTML output

use Moose;
use MooseX::Attribute::Chained;
extends 'HTML::FormFu::OutputProcessor';

use HTML::FormFu::Constants qw( $EMPTY_STR );
use HTML::TokeParser::Simple;
use List::Util 1.33 qw( any );

has collapse_tags => (
    is      => 'rw',
    default => sub {
        [ qw(
                fieldset
                form
                hr
                legend
                optgroup
                option
                table
                td
                th
                tr
                ) ];
    },
    lazy   => 1,
    traits => ['Chained'],
);

has collapse_consecutive_tags => (
    is      => 'rw',
    default => sub {
        [ qw(
                span
                div
                ) ];
    },
    lazy   => 1,
    traits => ['Chained'],
);

sub process {
    my ( $self, $input ) = @_;

    my $parser = HTML::TokeParser::Simple->new( \$input );
    my @tokens;

    while ( my $token = $parser->get_token ) {
        push @tokens, $token;
    }

    my $iter
        = HTML::FormFu::OutputProcessor::StripWhitespace::_iter->new(@tokens);

    my @collapse    = @{ $self->collapse_tags };
    my @consecutive = @{ $self->collapse_consecutive_tags };
    my $output      = $EMPTY_STR;

    while ( defined( my $token = $iter->next ) ) {

        if ( $token->is_start_tag ) {
            my $tag      = $token->get_tag;
            my $prev_tag = $iter->prev_tag_name;

            if ( any { $tag eq $_ } @collapse ) {

                # strip \s from before us
                $output =~ s/ \s+ \z //x;
            }
            elsif ( defined $prev_tag ) {

                # strip \s between <start> <start>
                for my $consec (@consecutive) {
                    if ( $tag eq $consec && $tag eq $prev_tag ) {
                        $output =~ s/ \s+ \z //x;
                    }
                }
            }
        }
        elsif ( $token->is_end_tag ) {
            my $tag      = $token->get_tag;
            my $prev_tag = $iter->prev_tag_name;

            if ( any { $tag eq $_ } @collapse ) {

                # strip \s from before us
                $output =~ s/ \s+ \z //x;
            }
            elsif ( defined $prev_tag ) {

                # strip \s between </end> </end>
                for my $consec (@consecutive) {
                    if ( $tag eq $consec && $tag eq $prev_tag ) {
                        $output =~ s/ \s+ \z //x;
                    }
                }
            }
        }

        my $prev_tag = $iter->prev_tag_name;

        if ( defined $prev_tag && any { $prev_tag eq $_ } @collapse ) {
            $output =~ s/ \s+ \z //x;

            my $part = $token->as_is;

            $part =~ s/ ^ \s+ //x;

            $output .= $part;
        }
        else {
            $output .= $token->as_is;
        }
    }

    return $output;
}

__PACKAGE__->meta->make_immutable;

use strict;

package HTML::FormFu::OutputProcessor::StripWhitespace::_iter;
$HTML::FormFu::OutputProcessor::StripWhitespace::_iter::VERSION = '2.07';
use Moose;
use MooseX::Attribute::Chained;

sub new {
    my ( $class, @tags ) = @_;

    my %self = (
        tags => \@tags,
        i    => 0,
    );

    return bless \%self, $class;
}

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

    return $self->{tags}[ $self->{i}++ ];
}

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

    my $i = $self->{i} - 2;

    while ( $i >= 0 ) {

        if ( $self->{tags}[$i]->is_tag ) {
            return if !$self->{tags}[$i]->is_tag;

            return $self->{tags}[$i]->get_tag;
        }

        --$i;
    }
}

__PACKAGE__->meta->make_immutable( inline_constructor => 0 );

1;

__END__

=pod

=encoding UTF-8

=head1 NAME

HTML::FormFu::OutputProcessor::StripWhitespace - Strip shitespace from HTML output

=head1 VERSION

version 2.07

=head1 SYNOPSIS

    ---
    output_processors:
      - StripWhitespace

=head1 METHODS

=head2 collapse_tags

=head2 collapse_consecutive_tags

=head1 SEE ALSO

Is a sub-class of, and inherits methods from L<HTML::FormFu::OutputProcessor>

L<HTML::FormFu>

=head1 AUTHOR

Carl Franks C<cfranks@cpan.org>

=head1 LICENSE

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

=head1 AUTHOR

Carl Franks <cpan@fireartist.com>

=head1 COPYRIGHT AND LICENSE

This software is copyright (c) 2018 by Carl Franks.

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