/[suikacvs]/markup/html/whatpm/t/HTML-tokenizer.t
Suika

Diff of /markup/html/whatpm/t/HTML-tokenizer.t

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1.17 by wakaba, Sat Jul 21 04:55:20 2007 UTC revision 1.27 by wakaba, Mon Mar 3 10:20:19 2008 UTC
# Line 1  Line 1 
1  #!/usr/bin/perl  #!/usr/bin/perl
2  use strict;  use strict;
3    
4    my $DEBUG = $ENV{DEBUG};
5    
6  my $dir_name;  my $dir_name;
7  my $test_dir_name;  my $test_dir_name;
8  BEGIN {  BEGIN {
# Line 24  BEGIN { Line 26  BEGIN {
26  }  }
27    
28  use Test;  use Test;
29  BEGIN { plan tests => 337 }  BEGIN { plan tests => 420 }
30    
31  use Data::Dumper;  use Data::Dumper;
32  $Data::Dumper::Useqq = 1;  $Data::Dumper::Useqq = 1;
# Line 34  sub Data::Dumper::qquote { Line 36  sub Data::Dumper::qquote {
36    return q<qq'> . $s . q<'>;    return q<qq'> . $s . q<'>;
37  } # Data::Dumper::qquote  } # Data::Dumper::qquote
38    
39    if ($DEBUG) {
40      my $not_found = {%$Whatpm::HTML::Debug::cp};
41    
42      $Whatpm::HTML::Debug::cp_pass = sub {
43        my $id = shift;
44        delete $not_found->{$id};
45      };
46    
47      END {
48        for my $id (sort {$a <=> $b || $a cmp $b} keys %$not_found) {
49          print "# checkpoint $id is not passed\n";
50        }
51      }
52    }
53    
54  use Whatpm::HTML;  use Whatpm::HTML;
55    
56  for my $file_name (grep {$_} split /\s+/, qq[  for my $file_name (grep {$_} split /\s+/, qq[
# Line 85  for my $file_name (grep {$_} split /\s+/ Line 102  for my $file_name (grep {$_} split /\s+/
102        my $p = Whatpm::HTML->new;        my $p = Whatpm::HTML->new;
103        my $i = 0;        my $i = 0;
104        my @token;        my @token;
105        $p->{set_next_input_character} = sub {        $p->{set_next_char} = sub {
106          my $self = shift;          my $self = shift;
107    
108          pop @{$self->{prev_input_character}};          pop @{$self->{prev_char}};
109          unshift @{$self->{prev_input_character}}, $self->{next_input_character};          unshift @{$self->{prev_char}}, $self->{next_char};
110    
111          $self->{next_input_character} = -1 and return if $i >= length $s;          $self->{next_char} = -1 and return if $i >= length $s;
112          $self->{next_input_character} = ord substr $s, $i++, 1;          $self->{next_char} = ord substr $s, $i++, 1;
113    
114          if ($self->{next_input_character} == 0x000D) { # CR          if ($self->{next_char} == 0x000D) { # CR
115            $i++ if substr ($s, $i, 1) eq "\x0A";            $i++ if substr ($s, $i, 1) eq "\x0A";
116            $self->{next_input_character} = 0x000A; # LF # MUST            $self->{next_char} = 0x000A; # LF # MUST
117          } elsif ($self->{next_input_character} > 0x10FFFF) {          } elsif ($self->{next_char} > 0x10FFFF) {
118            $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST            $self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
119            push @token, 'ParseError';            push @token, 'ParseError';
120          } elsif ($self->{next_input_character} == 0x0000) { # NULL          } elsif ($self->{next_char} == 0x0000) { # NULL
121            $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST            $self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
122            push @token, 'ParseError';            push @token, 'ParseError';
123          }          }
124        };        };
125        $p->{prev_input_character} = [-1, -1, -1];        $p->{prev_char} = [-1, -1, -1];
126        $p->{next_input_character} = -1;        $p->{next_char} = -1;
127                
128        $p->{parse_error} = sub {        $p->{parse_error} = sub {
129          push @token, 'ParseError';          push @token, 'ParseError';
130        };        };
131                
132        $p->_initialize_tokenizer;        $p->_initialize_tokenizer;
133        $p->{content_model_flag} = $cm;        $p->{content_model} = {
134            CDATA => Whatpm::HTML::CDATA_CONTENT_MODEL (),
135            RCDATA => Whatpm::HTML::RCDATA_CONTENT_MODEL (),
136            PCDATA => Whatpm::HTML::PCDATA_CONTENT_MODEL (),
137            PLAINTEXT => Whatpm::HTML::PLAINTEXT_CONTENT_MODEL (),
138          }->{$cm};
139        $p->{last_emitted_start_tag_name} = $last_start_tag;        $p->{last_emitted_start_tag_name} = $last_start_tag;
140    
141        while (1) {        while (1) {
142          my $token = $p->_get_next_token;          my $token = $p->_get_next_token;
143          last if $token->{type} eq 'end-of-file';          last if $token->{type} == Whatpm::HTML::END_OF_FILE_TOKEN ();
144                    
145          my $test_token = [          my $test_token = [
146           {           {
147            DOCTYPE => 'DOCTYPE',            Whatpm::HTML::DOCTYPE_TOKEN () => 'DOCTYPE',
148            'start tag' => 'StartTag',            Whatpm::HTML::START_TAG_TOKEN () => 'StartTag',
149            'end tag' => 'EndTag',            Whatpm::HTML::END_TAG_TOKEN () => 'EndTag',
150            comment => 'Comment',            Whatpm::HTML::COMMENT_TOKEN () => 'Comment',
151            character => 'Character',            Whatpm::HTML::CHARACTER_TOKEN () => 'Character',
152           }->{$token->{type}} || $token->{type},           }->{$token->{type}} || $token->{type},
153          ];          ];
154          $test_token->[1] = $token->{tag_name} if defined $token->{tag_name};          $test_token->[1] = $token->{tag_name} if defined $token->{tag_name};
155          $test_token->[1] = $token->{data} if defined $token->{data};          $test_token->[1] = $token->{data} if defined $token->{data};
156          if ($token->{type} eq 'start tag') {          if ($token->{type} == Whatpm::HTML::START_TAG_TOKEN ()) {
157            $test_token->[2] = {map {$_->{name} => $_->{value}} values %{$token->{attributes}}};            $test_token->[2] = {map {$_->{name} => $_->{value}} values %{$token->{attributes}}};
158          } elsif ($token->{type} eq 'DOCTYPE') {          } elsif ($token->{type} == Whatpm::HTML::DOCTYPE_TOKEN ()) {
159            $test_token->[1] = $token->{name};            $test_token->[1] = $token->{name};
160            $test_token->[2] = $token->{public_identifier};            $test_token->[2] = $token->{public_identifier};
161            $test_token->[3] = $token->{system_identifier};            $test_token->[3] = $token->{system_identifier};
162            $test_token->[4] = $token->{correct} ? 1 : 0;            $test_token->[4] = $token->{quirks} ? 0 : 1;
163          }          }
164    
165          if (@token and ref $token[-1] and $token[-1]->[0] eq 'Character' and          if (@token and ref $token[-1] and $token[-1]->[0] eq 'Character' and
# Line 156  for my $file_name (grep {$_} split /\s+/ Line 178  for my $file_name (grep {$_} split /\s+/
178    }    }
179  }  }
180    
181    ## License: Public Domain.
182  ## $Date$  ## $Date$
Legend:
Removed from v.1.17  
changed lines
  Added in v.1.27
[email protected]
 ViewVC Help
Powered by ViewVC 1.1.24