/[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 1.25 by wakaba, Mon Mar 3 00:13:22 2008 UTC revision 1.28 by wakaba, Mon Mar 3 11:56:18 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 => 420 }  BEGIN { plan tests => 471 }
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 reached\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';
Legend:
Removed from v.1.25  
changed lines
  Added in v.1.28
[email protected]
 ViewVC Help
Powered by ViewVC 1.1.24