File: NoXPath.pm

package info (click to toggle)
libtest-html-content-perl 0.13-1
  • links: PTS, VCS
  • area: main
  • in suites: trixie
  • size: 328 kB
  • sloc: perl: 1,393; makefile: 2
file content (225 lines) | stat: -rwxr-xr-x 5,011 bytes parent folder | download
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
package Test::HTML::Content::NoXPath;

require 5.005_62;
use strict;
use File::Spec;
use HTML::TokeParser;

# we want to stay compatible to 5.5 and use warnings if
# we can
eval 'use warnings;' if ($] >= 5.006);
use vars qw( $HTML_PARSER_StripsTags $VERSION @exports );

$VERSION = '0.13';

BEGIN {
  # Check whether HTML::Parser is v3 and delivers the comments starting
  # with the <!--, even though that's implied :
  my $HTML = "<!--Comment-->";
  my $p = HTML::TokeParser->new(\$HTML);
  my ($type,$text) = @{$p->get_token()};
  if ($text eq "<!--Comment-->") {
    $HTML_PARSER_StripsTags = 0
  } else {
    $HTML_PARSER_StripsTags = 1
  };
};

# import what we need
{ no strict 'refs';
  *{$_} = *{"Test::HTML::Content::$_"}
    for qw( __dwim_compare __output_diag __invalid_html );
};

@exports = qw( __match_comment __count_comments __match_text __count_text
               __match __count_tags __match_declaration __count_declarations );

sub __match_comment {
  my ($text,$template) = @_;
  $text =~ s/^<!--(.*?)-->$/$1/ unless $HTML_PARSER_StripsTags;
  unless (ref $template eq "Regexp") {
    $text =~ s/^\s*(.*?)\s*$/$1/;
    $template =~ s/^\s*(.*?)\s*$/$1/;
  };
  return __dwim_compare($text, $template);
};

sub __count_comments {
  my ($HTML,$comment) = @_;
  my $result = 0;
  my $seen = [];

  my $p = HTML::TokeParser->new(\$HTML);
  my $token;
  while ($token = $p->get_token) {
    my ($type,$text) = @$token;
    if ($type eq "C") {
      push @$seen, $token->[1];
      $result++ if __match_comment($text,$comment);
    };
  };

  return ($result, $seen);
};

sub __match_text {
  my ($text,$template) = @_;
  unless (ref $template eq "Regexp") {
    $text =~ s/^\s*(.*?)\s*$/$1/;
    $template =~ s/^\s*(.*?)\s*$/$1/;
  };
  return __dwim_compare($text, $template);
};

sub __count_text {
  my ($HTML,$text) = @_;
  my $result = 0;
  my $seen = [];

  my $p = HTML::TokeParser->new(\$HTML);
  $p->unbroken_text(1);

  my $token;
  while ($token = $p->get_token) {
    my ($type,$foundtext) = @$token;
    if ($type eq "T") {
      push @$seen, $token->[1];
      $result++ if __match_text($foundtext,$text);
    };
  };

  return $result,$seen;
};

sub __match {
  my ($attrs,$currattr,$key) = @_;
  my $result = 1;

  if (exists $currattr->{$key}) {
    if (! defined $attrs->{$key}) {
      $result = 0; # We don't want to see this attribute here
    } else {
      $result = 0 unless __dwim_compare($currattr->{$key}, $attrs->{$key});
    };
  } else {
    if (! defined $attrs->{$key}) {
      $result = 0 if (exists $currattr->{$key});
    } else {
      $result = 0;
    };
  };
  return $result;
};

sub __count_tags {
  my ($HTML,$tag,$attrref) = @_;
  $attrref = {} unless defined $attrref;
  return ('skip','XML::LibXML or XML::XPath not loaded')
    if exists $attrref->{_content};

  my $result = 0;
  $tag = lc $tag;

  my $p = HTML::TokeParser->new(\$HTML);
  my $token;
  my @seen;
  while ($token = $p->get_token) {
    my ($type,$currtag,$currattr,$attrseq,$origtext) = @$token;
    if ($type eq "S" && $tag eq $currtag) {
      my (@keys) = keys %$attrref;
      my $key;
      my $complete = 1;
      foreach $key (@keys) {
        $complete = __match($attrref,$currattr,$key) if $complete;
      };
      $result += $complete;
      # Now munge the thing to resemble what the XPath variant returns :
      push @seen, $token->[4];
    };
  };

  return $result,\@seen;
};

sub __match_declaration {
  my ($text,$template) = @_;
  $text =~ s/^<!(.*?)>$/$1/ unless $HTML_PARSER_StripsTags;
  unless (ref $template eq "Regexp") {
    $text =~ s/^\s*(.*?)\s*$/$1/;
    $template =~ s/^\s*(.*?)\s*$/$1/;
  };
  return __dwim_compare($text, $template);
};

sub __count_declarations {
  my ($HTML,$doctype) = @_;
  my $result = 0;
  my $seen = [];

  my $p = HTML::TokeParser->new(\$HTML);
  my $token;
  while ($token = $p->get_token) {
    my ($type,$text) = @$token;
    if ($type eq "D") {
      push @$seen, $text;
      $result++ if __match_declaration($text,$doctype);
    };
  };

  return $result, $seen;
};

sub import {
  goto &install;
};

sub install {
  for (@exports) {
    no strict 'refs';
    *{"Test::HTML::Content::$_"} = *{"Test::HTML::Content::NoXPath::$_"};
  };
  $Test::HTML::Content::can_xpath = 0;
};

1;

__END__

=head1 NAME

Test::HTML::Content::NoXPath - HTML::TokeParser fallback for Test::HTML::Content

=head1 SYNOPSIS

=for example begin

  # This module is implicitly loaded by Test::HTML::Content
  # if XML::XPath or HTML::Tidy::Simple are unavailable.

=for example end

=head1 DESCRIPTION

This is the module that gets loaded when Test::HTML::Content
can't find its prerequisites :

    XML::XPath
    HTML::Tidy

=head2 EXPORT

Nothing. It stomps over the Test::HTML::Content namespace.

=head1 LICENSE

This code may be distributed under the same terms as Perl itself.

=head1 AUTHOR

Max Maischein, corion@cpan.org

=head1 SEE ALSO

L<Test::Builder>,L<Test::Simple>,L<HTML::TokeParser>,L<Test::HTML::Lint>,L<XML::XPath>

=cut