/[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 1.1 by wakaba, Mon Apr 30 09:59:35 2007 UTC revision 1.38 by wakaba, Sat Aug 30 13:43:50 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;
7    my $test_dir_name;
8  BEGIN {  BEGIN {
9      $test_dir_name = 't/';
10      $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 ('make', 'tokenizer-files') == 0 or die           system ("cd $test_dir_name; make tokenizer-files") == 0 or die
16             unless -f 'tokenizer/test1.test';             unless -f $dir_name.'test1.test';
17           $skip = '';           $skip = '';
18          };          };
19    if ($skip) {    if ($skip) {
# Line 16  BEGIN { Line 22  BEGIN {
22      exit;      exit;
23    }    }
24    $JSON::UnMapping = 1;    $JSON::UnMapping = 1;
25      $JSON::UTF8 = 1;
26  }  }
27    
28  use Test;  use Test;
29    BEGIN { plan tests => 1073 }
30    
31  use Data::Dumper;  use Data::Dumper;
32  BEGIN { plan tests => 38 }  $Data::Dumper::Useqq = 1;
33    $Data::Dumper::Sortkeys = 1;
34    sub Data::Dumper::qquote {
35      my $s = shift;
36      $s =~ s/([^\x20\x21-\x26\x28-\x5B\x5D-\x7E])/sprintf '\x{%02X}', ord $1/ge;
37      return q<qq'> . $s . q<'>;
38    } # Data::Dumper::qquote
39    
40    if ($DEBUG) {
41      my $not_found = {%{$Whatpm::HTML::Debug::cp or {}}};
42    
43      $Whatpm::HTML::Debug::cp_pass = sub {
44        my $id = shift;
45        delete $not_found->{$id};
46      };
47    
48      END {
49        for my $id (sort {$a <=> $b || $a cmp $b} grep {!/^[ti]/}
50                    keys %$not_found) {
51          print "# checkpoint $id is not reached\n";
52        }
53      }
54    }
55    
56  use What::HTML;  use Whatpm::HTML;
57    
58  for my $file_name (qw[  for my $file_name (grep {$_} split /\s+/, qq[
59                        tokenizer/test1.test                        ${dir_name}test1.test
60                        tokenizer/test2.test                        ${dir_name}test2.test
61                        tokenizer/contentModelFlags.test                        ${dir_name}test3.test
62                          ${dir_name}test4.test
63                          ${dir_name}contentModelFlags.test
64                          ${dir_name}escapeFlag.test
65                          ${dir_name}entities.test
66                          ${dir_name}xmlViolation.test
67                          ${test_dir_name}tokenizer-test-1.test
68                       ]) {                       ]) {
69    open my $file, '<:utf8', $file_name or die "$0: $file_name: $!";    open my $file, '<', $file_name
70        or die "$0: $file_name: $!";
71    local $/ = undef;    local $/ = undef;
72    my $js = <$file>;    my $js = <$file>;
73    close $file;    close $file;
74      
75    my $tests = jsonToObj ($js)->{tests};    print "# $file_name\n";
76      $js =~ s{\\u[Dd]([89A-Fa-f][0-9A-Fa-f][0-9A-Fa-f])
77          \\u[Dd]([89A-Fa-f][0-9A-Fa-f][0-9A-Fa-f])}{
78        ## NOTE: JSON::Parser does not decode surrogate pair escapes
79        ## NOTE: In older version of JSON::Parser, utf8 string will be broken
80        ## by parsing.  Use latest version!
81        ## NOTE: Encode.pm is broken; it converts e.g. U+10FFFF to U+FFFD.
82        my $c = 0x10000;
83        $c += ((((hex $1) & 0b1111111111) << 10) | ((hex $2) & 0b1111111111));
84        chr $c;
85      }gex;
86      my $json = jsonToObj ($js);
87      my $tests = $json->{tests} || $json->{xmlViolationTests};
88    TEST: for my $test (@$tests) {    TEST: for my $test (@$tests) {
89      my $s = $test->{input};      my $s = $test->{input};
90            
# Line 51  for my $file_name (qw[ Line 101  for my $file_name (qw[
101        $j++;        $j++;
102      }      }
103    
104      my @cm = @{$test->{content_model_flags} || ['PCDATA']};      my @cm = @{$test->{contentModelFlags} || ['PCDATA']};
105        my $last_start_tag = $test->{lastStartTag};
106      for my $cm (@cm) {      for my $cm (@cm) {
107        my $p = What::HTML->new;        my $p = Whatpm::HTML->new;
108        my $i = 0;        my $i = 0;
109        $p->{set_next_input_character} = sub {        my @token;
110          $p->{set_next_char} = sub {
111          my $self = shift;          my $self = shift;
112          $self->{next_input_character} = -1 and return if $i >= length $s;  
113          $self->{next_input_character} = ord substr $s, $i++, 1;          pop @{$self->{prev_char}};
114            unshift @{$self->{prev_char}}, $self->{next_char};
115    
116            $self->{next_char} = -1 and return if $i >= length $s;
117            $self->{next_char} = ord substr $s, $i++, 1;
118    
119            if ($self->{next_char} == 0x000D) { # CR
120              $i++ if substr ($s, $i, 1) eq "\x0A";
121              $self->{next_char} = 0x000A; # LF # MUST
122            } elsif ($self->{next_char} > 0x10FFFF) {
123              $self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
124              push @token, 'ParseError';
125            } elsif ($self->{next_char} == 0x0000) { # NULL
126              $self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
127              push @token, 'ParseError';
128            } elsif ($self->{next_char} <= 0x0008 or
129                     (0x000E <= $self->{next_char} and
130                      $self->{next_char} <= 0x001F) or
131                     (0x007F <= $self->{next_char} and
132                      $self->{next_char} <= 0x009F) or
133                     (0xD800 <= $self->{next_char} and
134                      $self->{next_char} <= 0xDFFF) or
135                     (0xFDD0 <= $self->{next_char} and
136                      $self->{next_char} <= 0xFDDF) or
137                     {
138                       0xFFFE => 1, 0xFFFF => 1, 0x1FFFE => 1, 0x1FFFF => 1,
139                       0x2FFFE => 1, 0x2FFFF => 1, 0x3FFFE => 1, 0x3FFFF => 1,
140                       0x4FFFE => 1, 0x4FFFF => 1, 0x5FFFE => 1, 0x5FFFF => 1,
141                       0x6FFFE => 1, 0x6FFFF => 1, 0x7FFFE => 1, 0x7FFFF => 1,
142                       0x8FFFE => 1, 0x8FFFF => 1, 0x9FFFE => 1, 0x9FFFF => 1,
143                       0xAFFFE => 1, 0xAFFFF => 1, 0xBFFFE => 1, 0xBFFFF => 1,
144                       0xCFFFE => 1, 0xCFFFF => 1, 0xDFFFE => 1, 0xDFFFF => 1,
145                       0xEFFFE => 1, 0xEFFFF => 1, 0xFFFFE => 1, 0xFFFFF => 1,
146                       0x10FFFE => 1, 0x10FFFF => 1,
147                      }->{$self->{next_char}}) {
148              push @token, 'ParseError';
149            }
150        };        };
151          $p->{prev_char} = [-1, -1, -1];
152          $p->{next_char} = -1;
153                
       my @token;  
154        $p->{parse_error} = sub {        $p->{parse_error} = sub {
155          push @token, 'ParseError';          push @token, 'ParseError';
156        };        };
157                
158        $p->_initialize_tokenizer;        $p->_initialize_tokenizer;
159        $p->{content_model_flag} = $cm;        $p->{content_model} = {
160            CDATA => Whatpm::HTML::CDATA_CONTENT_MODEL (),
161            RCDATA => Whatpm::HTML::RCDATA_CONTENT_MODEL (),
162            PCDATA => Whatpm::HTML::PCDATA_CONTENT_MODEL (),
163            PLAINTEXT => Whatpm::HTML::PLAINTEXT_CONTENT_MODEL (),
164          }->{$cm};
165          $p->{last_emitted_start_tag_name} = $last_start_tag;
166    
167        while (1) {        while (1) {
168          my $token = $p->_get_next_token;          my $token = $p->_get_next_token;
169          last if $token->{type} eq 'end-of-file';          last if $token->{type} == Whatpm::HTML::END_OF_FILE_TOKEN ();
170                    
171          my $test_token = [          my $test_token = [
172           {           {
173            DOCTYPE => 'DOCTYPE',            Whatpm::HTML::DOCTYPE_TOKEN () => 'DOCTYPE',
174            'start tag' => 'StartTag',            Whatpm::HTML::START_TAG_TOKEN () => 'StartTag',
175            'end tag' => 'EndTag',            Whatpm::HTML::END_TAG_TOKEN () => 'EndTag',
176            comment => 'Comment',            Whatpm::HTML::COMMENT_TOKEN () => 'Comment',
177            character => 'Character',            Whatpm::HTML::CHARACTER_TOKEN () => 'Character',
178           }->{$token->{type}} || $token->{type},           }->{$token->{type}} || $token->{type},
179          ];          ];
         $test_token->[1] = $token->{name} if defined $token->{name};  
180          $test_token->[1] = $token->{tag_name} if defined $token->{tag_name};          $test_token->[1] = $token->{tag_name} if defined $token->{tag_name};
181          $test_token->[1] = $token->{data} if defined $token->{data};          $test_token->[1] = $token->{data} if defined $token->{data};
182          $test_token->[2] = $token->{error} ? 1 : 0 if $token->{type} eq 'DOCTYPE';          if ($token->{type} == Whatpm::HTML::START_TAG_TOKEN ()) {
183          $test_token->[2] = {map {$_->{name} => $_->{value}} values %{$token->{attributes}}}            $test_token->[2] = {map {$_->{name} => $_->{value}} values %{$token->{attributes}}};
184            if $token->{type} eq 'start tag';            $test_token->[3] = 1 if $p->{self_closing};
185                      delete $p->{self_closing};
186            } elsif ($token->{type} == Whatpm::HTML::DOCTYPE_TOKEN ()) {
187              $test_token->[1] = $token->{name};
188              $test_token->[2] = $token->{public_identifier};
189              $test_token->[3] = $token->{system_identifier};
190              $test_token->[4] = $token->{quirks} ? 0 : 1;
191            }
192    
193          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
194              $test_token->[0] eq 'Character') {              $test_token->[0] eq 'Character') {
195            $token[-1]->[1] .= $test_token->[1];            $token[-1]->[1] .= $test_token->[1];
# Line 99  for my $file_name (qw[ Line 200  for my $file_name (qw[
200                
201        my $expected_dump = Dumper ($test->{output});        my $expected_dump = Dumper ($test->{output});
202        my $parser_dump = Dumper (\@token);        my $parser_dump = Dumper (\@token);
203        ok $parser_dump, $expected_dump, $test->{description};        ok $parser_dump, $expected_dump,
204            $test->{description} . ': ' . Data::Dumper::qquote ($test->{input});
205      }      }
206    }    }
207  }  }
208    
209    ## License: Public Domain.
210    ## $Date$
Legend:
Removed from v.1.1  
changed lines
  Added in v.1.38
[email protected]
 ViewVC Help
Powered by ViewVC 1.1.24