/[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 1.2 by wakaba, Mon Apr 30 11:45:24 2007 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;
8  BEGIN {  BEGIN {
9      $test_dir_name = 't/';
10    $dir_name = 't/tokenizer/';    $dir_name = 't/tokenizer/';
11    my $skip = "You don't have JSON module";    my $skip = "You don't have JSON module";
12    eval q{    eval q{
13           use JSON 1.00;           use JSON 1.07;
14           $skip = "You don't have make command";           $skip = "You don't have make command";
15           system ('cd $dir_name; cd ..; make tokenizer-files') == 0 or die           system ("cd $test_dir_name; make tokenizer-files") == 0 or die
16             unless -f $dir_name.'test1.test';             unless -f $dir_name.'test1.test';
17           $skip = '';           $skip = '';
18          };          };
# Line 22  BEGIN { Line 26  BEGIN {
26  }  }
27    
28  use Test;  use Test;
29  BEGIN { plan tests => 38 }  BEGIN { plan tests => 471 }
30    
31  use Data::Dumper;  use Data::Dumper;
32  $Data::Dumper::Useqq = 1;  $Data::Dumper::Useqq = 1;
# Line 32  sub Data::Dumper::qquote { Line 36  sub Data::Dumper::qquote {
36    return q<qq'> . $s . q<'>;    return q<qq'> . $s . q<'>;
37  } # Data::Dumper::qquote  } # Data::Dumper::qquote
38    
39  use What::HTML;  if ($DEBUG) {
40  use Encode;    my $not_found = {%$Whatpm::HTML::Debug::cp};
41    
42  for my $file_name (qw[    $Whatpm::HTML::Debug::cp_pass = sub {
43                        test1.test      my $id = shift;
44                        test2.test      delete $not_found->{$id};
45                        contentModelFlags.test    };
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;
55    
56    for my $file_name (grep {$_} split /\s+/, qq[
57                          ${dir_name}test1.test
58                          ${dir_name}test2.test
59                          ${dir_name}test3.test
60                          ${dir_name}test4.test
61                          ${dir_name}contentModelFlags.test
62                          ${dir_name}escapeFlag.test
63                          ${test_dir_name}tokenizer-test-1.test
64                       ]) {                       ]) {
65    open my $file, '<', $dir_name.$file_name    open my $file, '<', $file_name
66      or die "$0: $dir_name$file_name: $!";      or die "$0: $file_name: $!";
67    local $/ = undef;    local $/ = undef;
68    my $js = <$file>;    my $js = <$file>;
69    close $file;    close $file;
70      
71      print "# $file_name\n";
72      $js =~ s{\\u[Dd]([89A-Fa-f][0-9A-Fa-f][0-9A-Fa-f])
73          \\u[Dd]([89A-Fa-f][0-9A-Fa-f][0-9A-Fa-f])}{
74        ## NOTE: JSON::Parser does not decode surrogate pair escapes
75        ## NOTE: In older version of JSON::Parser, utf8 string will be broken
76        ## by parsing.  Use latest version!
77        ## NOTE: Encode.pm is broken; it converts e.g. U+10FFFF to U+FFFD.
78        my $c = 0x10000;
79        $c += ((((hex $1) & 0b1111111111) << 10) | ((hex $2) & 0b1111111111));
80        chr $c;
81      }gex;
82    my $tests = jsonToObj ($js)->{tests};    my $tests = jsonToObj ($js)->{tests};
83    TEST: for my $test (@$tests) {    TEST: for my $test (@$tests) {
84      my $s = $test->{input};      my $s = $test->{input};
# Line 66  for my $file_name (qw[ Line 99  for my $file_name (qw[
99      my @cm = @{$test->{contentModelFlags} || ['PCDATA']};      my @cm = @{$test->{contentModelFlags} || ['PCDATA']};
100      my $last_start_tag = $test->{lastStartTag};      my $last_start_tag = $test->{lastStartTag};
101      for my $cm (@cm) {      for my $cm (@cm) {
102        my $p = What::HTML->new;        my $p = Whatpm::HTML->new;
103        my $i = 0;        my $i = 0;
104        $p->{set_next_input_character} = sub {        my @token;
105          $p->{set_next_char} = sub {
106          my $self = shift;          my $self = shift;
         $self->{next_input_character} = -1 and return if $i >= length $s;  
         $self->{next_input_character} = ord substr $s, $i++, 1;  
107    
108          if ($self->{next_input_character} == 0x000D) { # CR          pop @{$self->{prev_char}};
109            if ($i >= length $s) {          unshift @{$self->{prev_char}}, $self->{next_char};
110              #  
111            } else {          $self->{next_char} = -1 and return if $i >= length $s;
112              my $next_char = ord substr $s, $i++, 1;          $self->{next_char} = ord substr $s, $i++, 1;
113              if ($next_char == 0x000A) { # LF  
114                #          if ($self->{next_char} == 0x000D) { # CR
115              } else {            $i++ if substr ($s, $i, 1) eq "\x0A";
116                push @{$self->{char}}, $next_char;            $self->{next_char} = 0x000A; # LF # MUST
117              }          } elsif ($self->{next_char} > 0x10FFFF) {
118            }            $self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
119            $self->{next_input_character} = 0x000A; # LF # MUST            push @token, 'ParseError';
120          } elsif ($self->{next_input_character} > 0x10FFFF) {          } elsif ($self->{next_char} == 0x0000) { # NULL
121            $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST            $self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
122          } elsif ($self->{next_input_character} == 0x0000) { # NULL            push @token, 'ParseError';
           $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST  
123          }          }
124        };        };
125          $p->{prev_char} = [-1, -1, -1];
126          $p->{next_char} = -1;
127                
       my @token;  
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          ];          ];
         $test_token->[1] = $token->{name} if defined $token->{name};  
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          $test_token->[2] = $token->{error} ? 1 : 0 if $token->{type} eq 'DOCTYPE';          if ($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            if $token->{type} eq 'start tag';          } elsif ($token->{type} == Whatpm::HTML::DOCTYPE_TOKEN ()) {
159                      $test_token->[1] = $token->{name};
160              $test_token->[2] = $token->{public_identifier};
161              $test_token->[3] = $token->{system_identifier};
162              $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
166              $test_token->[0] eq 'Character') {              $test_token->[0] eq 'Character') {
167            $token[-1]->[1] .= $test_token->[1];            $token[-1]->[1] .= $test_token->[1];
# Line 132  for my $file_name (qw[ Line 173  for my $file_name (qw[
173        my $expected_dump = Dumper ($test->{output});        my $expected_dump = Dumper ($test->{output});
174        my $parser_dump = Dumper (\@token);        my $parser_dump = Dumper (\@token);
175        ok $parser_dump, $expected_dump,        ok $parser_dump, $expected_dump,
176          $test->{description} . ': ' . $test->{input};          $test->{description} . ': ' . Data::Dumper::qquote ($test->{input});
177      }      }
178    }    }
179  }  }
180    
181    ## License: Public Domain.
182  ## $Date$  ## $Date$
Legend:
Removed from v.1.2  
changed lines
  Added in v.1.28
[email protected]
 ViewVC Help
Powered by ViewVC 1.1.24