whatpm/t/HTML-tokenizer.t

#!/usr/bin/perl
use strict;

my $dir_name;
my $test_dir_name;
BEGIN {
  $test_dir_name = 't/';
  $dir_name = 't/tokenizer/';
  my $skip = "You don't have JSON module";
  eval q{
         use JSON 1.00;
         $skip = "You don't have make command";
         system ("cd $test_dir_name; make tokenizer-files") == 0 or die
           unless -f $dir_name.'test1.test';
         $skip = '';
        };
  if ($skip) {
    print "1..1\n";
    print "ok 1 # $skip\n";
    exit;
  }
  $JSON::UnMapping = 1;
  $JSON::UTF8 = 1;
}

use Test;
BEGIN { plan tests => 94 }

use Data::Dumper;
$Data::Dumper::Useqq = 1;
sub Data::Dumper::qquote {
  my $s = shift;
  $s =~ s/([^\x20\x21-\x26\x28-\x5B\x5D-\x7E])/sprintf '\x{%02X}', ord $1/ge;
  return q<qq'> . $s . q<'>;
} # Data::Dumper::qquote

use Whatpm::HTML;

for my $file_name (grep {$_} split /\s+/, qq[
                      ${dir_name}test1.test
                      ${dir_name}test2.test
                      ${dir_name}contentModelFlags.test
                      ${dir_name}escapeFlag.test
                      ${test_dir_name}tokenizer-test-1.test
                     ]) {
  open my $file, '<', $file_name
    or die "$0: $file_name: $!";
  local $/ = undef;
  my $js = <$file>;
  close $file;
  
  my $tests = jsonToObj ($js)->{tests};
  TEST: for my $test (@$tests) {
    my $s = $test->{input};
    
    my $j = 1;
    while ($j < @{$test->{output}}) {
      if (ref $test->{output}->[$j - 1] and
          $test->{output}->[$j - 1]->[0] eq 'Character' and
          ref $test->{output}->[$j] and 
          $test->{output}->[$j]->[0] eq 'Character') {
        $test->{output}->[$j - 1]->[1]
          .= $test->{output}->[$j]->[1];
        splice @{$test->{output}}, $j, 1;
      }
      $j++;
    }

    my @cm = @{$test->{contentModelFlags} || ['PCDATA']};
    my $last_start_tag = $test->{lastStartTag};
    for my $cm (@cm) {
      my $p = Whatpm::HTML->new;
      my $i = 0;
      $p->{set_next_input_character} = sub {
        my $self = shift;
        $self->{next_input_character} = -1 and return if $i >= length $s;
        $self->{next_input_character} = ord substr $s, $i++, 1;

        if ($self->{next_input_character} == 0x000D) { # CR
          if ($i >= length $s) {
            #
          } else {
            my $next_char = ord substr $s, $i++, 1;
            if ($next_char == 0x000A) { # LF
              #
            } else {
              push @{$self->{char}}, $next_char;
            }
          }
          $self->{next_input_character} = 0x000A; # LF # MUST
        } elsif ($self->{next_input_character} > 0x10FFFF) {
          $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
        } elsif ($self->{next_input_character} == 0x0000) { # NULL
          $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
        }
      };
      
      my @token;
      $p->{parse_error} = sub {
        push @token, 'ParseError';
      };
      
      $p->_initialize_tokenizer;
      $p->{content_model_flag} = $cm;
      $p->{last_emitted_start_tag_name} = $last_start_tag;

      while (1) {
        my $token = $p->_get_next_token;
        last if $token->{type} eq 'end-of-file';
        
        my $test_token = [
         {
          DOCTYPE => 'DOCTYPE',
          'start tag' => 'StartTag',
          'end tag' => 'EndTag',
          comment => 'Comment',
          character => 'Character',
         }->{$token->{type}} || $token->{type},
        ];
        $test_token->[1] = $token->{name} if defined $token->{name};
        $test_token->[1] = $token->{tag_name} if defined $token->{tag_name};
        $test_token->[1] = $token->{data} if defined $token->{data};
        $test_token->[2] = $token->{error} ? 1 : 0 if $token->{type} eq 'DOCTYPE';
        $test_token->[2] = {map {$_->{name} => $_->{value}} values %{$token->{attributes}}}
          if $token->{type} eq 'start tag';
        
        if (@token and ref $token[-1] and $token[-1]->[0] eq 'Character' and
            $test_token->[0] eq 'Character') {
          $token[-1]->[1] .= $test_token->[1];
        } else {
          push @token, $test_token;
        }
      }
      
      my $expected_dump = Dumper ($test->{output});
      my $parser_dump = Dumper (\@token);
      ok $parser_dump, $expected_dump,
        $test->{description} . ': ' . $test->{input};
    }
  }
}

## $Date: 2007/05/20 11:12:25 $
1	#!/usr/bin/perl
2	use strict;
3
4	my $dir_name;
5	my $test_dir_name;
6	BEGIN {
7	$test_dir_name = 't/';
8	$dir_name = 't/tokenizer/';
9	my $skip = "You don't have JSON module";
10	eval q{
11	use JSON 1.00;
12	$skip = "You don't have make command";
13	system ("cd $test_dir_name; make tokenizer-files") == 0 or die
14	unless -f $dir_name.'test1.test';
15	$skip = '';
16	};
17	if ($skip) {
18	print "1..1\n";
19	print "ok 1 # $skip\n";
20	exit;
21	}
22	$JSON::UnMapping = 1;
23	$JSON::UTF8 = 1;
24	}
25
26	use Test;
27	BEGIN { plan tests => 94 }
28
29	use Data::Dumper;
30	$Data::Dumper::Useqq = 1;
31	sub Data::Dumper::qquote {
32	my $s = shift;
33	$s =~ s/([^\x20\x21-\x26\x28-\x5B\x5D-\x7E])/sprintf '\x{%02X}', ord $1/ge;
34	return q<qq'> . $s . q<'>;
35	} # Data::Dumper::qquote
36
37	use Whatpm::HTML;
38
39	for my $file_name (grep {$_} split /\s+/, qq[
40	${dir_name}test1.test
41	${dir_name}test2.test
42	${dir_name}contentModelFlags.test
43	${dir_name}escapeFlag.test
44	${test_dir_name}tokenizer-test-1.test
45	]) {
46	open my $file, '<', $file_name
47	or die "$0: $file_name: $!";
48	local $/ = undef;
49	my $js = <$file>;
50	close $file;
51
52	my $tests = jsonToObj ($js)->{tests};
53	TEST: for my $test (@$tests) {
54	my $s = $test->{input};
55
56	my $j = 1;
57	while ($j < @{$test->{output}}) {
58	if (ref $test->{output}->[$j - 1] and
59	$test->{output}->[$j - 1]->[0] eq 'Character' and
60	ref $test->{output}->[$j] and
61	$test->{output}->[$j]->[0] eq 'Character') {
62	$test->{output}->[$j - 1]->[1]
63	.= $test->{output}->[$j]->[1];
64	splice @{$test->{output}}, $j, 1;
65	}
66	$j++;
67	}
68
69	my @cm = @{$test->{contentModelFlags} \|\| ['PCDATA']};
70	my $last_start_tag = $test->{lastStartTag};
71	for my $cm (@cm) {
72	my $p = Whatpm::HTML->new;
73	my $i = 0;
74	$p->{set_next_input_character} = sub {
75	my $self = shift;
76	$self->{next_input_character} = -1 and return if $i >= length $s;
77	$self->{next_input_character} = ord substr $s, $i++, 1;
78
79	if ($self->{next_input_character} == 0x000D) { # CR
80	if ($i >= length $s) {
81	#
82	} else {
83	my $next_char = ord substr $s, $i++, 1;
84	if ($next_char == 0x000A) { # LF
85	#
86	} else {
87	push @{$self->{char}}, $next_char;
88	}
89	}
90	$self->{next_input_character} = 0x000A; # LF # MUST
91	} elsif ($self->{next_input_character} > 0x10FFFF) {
92	$self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
93	} elsif ($self->{next_input_character} == 0x0000) { # NULL
94	$self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
95	}
96	};
97
98	my @token;
99	$p->{parse_error} = sub {
100	push @token, 'ParseError';
101	};
102
103	$p->_initialize_tokenizer;
104	$p->{content_model_flag} = $cm;
105	$p->{last_emitted_start_tag_name} = $last_start_tag;
106
107	while (1) {
108	my $token = $p->_get_next_token;
109	last if $token->{type} eq 'end-of-file';
110
111	my $test_token = [
112	{
113	DOCTYPE => 'DOCTYPE',
114	'start tag' => 'StartTag',
115	'end tag' => 'EndTag',
116	comment => 'Comment',
117	character => 'Character',
118	}->{$token->{type}} \|\| $token->{type},
119	];
120	$test_token->[1] = $token->{name} if defined $token->{name};
121	$test_token->[1] = $token->{tag_name} if defined $token->{tag_name};
122	$test_token->[1] = $token->{data} if defined $token->{data};
123	$test_token->[2] = $token->{error} ? 1 : 0 if $token->{type} eq 'DOCTYPE';
124	$test_token->[2] = {map {$_->{name} => $_->{value}} values %{$token->{attributes}}}
125	if $token->{type} eq 'start tag';
126
127	if (@token and ref $token[-1] and $token[-1]->[0] eq 'Character' and
128	$test_token->[0] eq 'Character') {
129	$token[-1]->[1] .= $test_token->[1];
130	} else {
131	push @token, $test_token;
132	}
133	}
134
135	my $expected_dump = Dumper ($test->{output});
136	my $parser_dump = Dumper (\@token);
137	ok $parser_dump, $expected_dump,
138	$test->{description} . ': ' . $test->{input};
139	}
140	}
141	}
142
143	## $Date: 2007/05/20 11:12:25 $