| 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 => 180 } |
| 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 |
print "# $file_name\n"; |
| 53 |
my $tests = jsonToObj ($js)->{tests}; |
| 54 |
TEST: for my $test (@$tests) { |
| 55 |
my $s = $test->{input}; |
| 56 |
|
| 57 |
my $j = 1; |
| 58 |
while ($j < @{$test->{output}}) { |
| 59 |
if (ref $test->{output}->[$j - 1] and |
| 60 |
$test->{output}->[$j - 1]->[0] eq 'Character' and |
| 61 |
ref $test->{output}->[$j] and |
| 62 |
$test->{output}->[$j]->[0] eq 'Character') { |
| 63 |
$test->{output}->[$j - 1]->[1] |
| 64 |
.= $test->{output}->[$j]->[1]; |
| 65 |
splice @{$test->{output}}, $j, 1; |
| 66 |
} |
| 67 |
$j++; |
| 68 |
} |
| 69 |
|
| 70 |
my @cm = @{$test->{contentModelFlags} || ['PCDATA']}; |
| 71 |
my $last_start_tag = $test->{lastStartTag}; |
| 72 |
for my $cm (@cm) { |
| 73 |
my $p = Whatpm::HTML->new; |
| 74 |
my $i = 0; |
| 75 |
my @token; |
| 76 |
$p->{set_next_input_character} = sub { |
| 77 |
my $self = shift; |
| 78 |
|
| 79 |
pop @{$self->{prev_input_character}}; |
| 80 |
unshift @{$self->{prev_input_character}}, $self->{next_input_character}; |
| 81 |
|
| 82 |
$self->{next_input_character} = -1 and return if $i >= length $s; |
| 83 |
$self->{next_input_character} = ord substr $s, $i++, 1; |
| 84 |
|
| 85 |
if ($self->{next_input_character} == 0x000D) { # CR |
| 86 |
if ($i >= length $s) { |
| 87 |
# |
| 88 |
} else { |
| 89 |
my $next_char = ord substr $s, $i++, 1; |
| 90 |
if ($next_char == 0x000A) { # LF |
| 91 |
# |
| 92 |
} else { |
| 93 |
push @{$self->{char}}, $next_char; |
| 94 |
} |
| 95 |
} |
| 96 |
$self->{next_input_character} = 0x000A; # LF # MUST |
| 97 |
} elsif ($self->{next_input_character} > 0x10FFFF) { |
| 98 |
$self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
| 99 |
push @token, 'ParseError'; |
| 100 |
} elsif ($self->{next_input_character} == 0x0000) { # NULL |
| 101 |
$self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
| 102 |
push @token, 'ParseError'; |
| 103 |
} |
| 104 |
}; |
| 105 |
$p->{prev_input_character} = [-1, -1, -1]; |
| 106 |
$p->{next_input_character} = -1; |
| 107 |
|
| 108 |
$p->{parse_error} = sub { |
| 109 |
push @token, 'ParseError'; |
| 110 |
}; |
| 111 |
|
| 112 |
$p->_initialize_tokenizer; |
| 113 |
$p->{content_model_flag} = $cm; |
| 114 |
$p->{last_emitted_start_tag_name} = $last_start_tag; |
| 115 |
|
| 116 |
while (1) { |
| 117 |
my $token = $p->_get_next_token; |
| 118 |
last if $token->{type} eq 'end-of-file'; |
| 119 |
|
| 120 |
my $test_token = [ |
| 121 |
{ |
| 122 |
DOCTYPE => 'DOCTYPE', |
| 123 |
'start tag' => 'StartTag', |
| 124 |
'end tag' => 'EndTag', |
| 125 |
comment => 'Comment', |
| 126 |
character => 'Character', |
| 127 |
}->{$token->{type}} || $token->{type}, |
| 128 |
]; |
| 129 |
$test_token->[1] = $token->{tag_name} if defined $token->{tag_name}; |
| 130 |
$test_token->[1] = $token->{data} if defined $token->{data}; |
| 131 |
if ($token->{type} eq 'start tag') { |
| 132 |
$test_token->[2] = {map {$_->{name} => $_->{value}} values %{$token->{attributes}}}; |
| 133 |
} elsif ($token->{type} eq 'DOCTYPE') { |
| 134 |
$test_token->[1] = $token->{name}; |
| 135 |
$test_token->[2] = $token->{public_identifier}; |
| 136 |
$test_token->[3] = $token->{system_identifier}; |
| 137 |
$test_token->[4] = $token->{correct} ? 1 : 0; |
| 138 |
} |
| 139 |
|
| 140 |
if (@token and ref $token[-1] and $token[-1]->[0] eq 'Character' and |
| 141 |
$test_token->[0] eq 'Character') { |
| 142 |
$token[-1]->[1] .= $test_token->[1]; |
| 143 |
} else { |
| 144 |
push @token, $test_token; |
| 145 |
} |
| 146 |
} |
| 147 |
|
| 148 |
my $expected_dump = Dumper ($test->{output}); |
| 149 |
my $parser_dump = Dumper (\@token); |
| 150 |
ok $parser_dump, $expected_dump, |
| 151 |
$test->{description} . ': ' . $test->{input}; |
| 152 |
} |
| 153 |
} |
| 154 |
} |
| 155 |
|
| 156 |
## $Date: 2007/06/30 13:12:33 $ |
Parent Directory
| 
Revision Log