/[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 1.30 by wakaba, Fri Mar 7 00:31:23 2008 UTC revision 1.38 by wakaba, Sat Aug 30 13:43:50 2008 UTC
# Line 26  BEGIN { Line 26  BEGIN {
26  }  }
27    
28  use Test;  use Test;
29  BEGIN { plan tests => 472 }  BEGIN { plan tests => 1073 }
30    
31  use Data::Dumper;  use Data::Dumper;
32  $Data::Dumper::Useqq = 1;  $Data::Dumper::Useqq = 1;
33    $Data::Dumper::Sortkeys = 1;
34  sub Data::Dumper::qquote {  sub Data::Dumper::qquote {
35    my $s = shift;    my $s = shift;
36    $s =~ s/([^\x20\x21-\x26\x28-\x5B\x5D-\x7E])/sprintf '\x{%02X}', ord $1/ge;    $s =~ s/([^\x20\x21-\x26\x28-\x5B\x5D-\x7E])/sprintf '\x{%02X}', ord $1/ge;
# Line 37  sub Data::Dumper::qquote { Line 38  sub Data::Dumper::qquote {
38  } # Data::Dumper::qquote  } # Data::Dumper::qquote
39    
40  if ($DEBUG) {  if ($DEBUG) {
41    my $not_found = {%$Whatpm::HTML::Debug::cp};    my $not_found = {%{$Whatpm::HTML::Debug::cp or {}}};
42    
43    $Whatpm::HTML::Debug::cp_pass = sub {    $Whatpm::HTML::Debug::cp_pass = sub {
44      my $id = shift;      my $id = shift;
# Line 61  for my $file_name (grep {$_} split /\s+/ Line 62  for my $file_name (grep {$_} split /\s+/
62                        ${dir_name}test4.test                        ${dir_name}test4.test
63                        ${dir_name}contentModelFlags.test                        ${dir_name}contentModelFlags.test
64                        ${dir_name}escapeFlag.test                        ${dir_name}escapeFlag.test
65                          ${dir_name}entities.test
66                          ${dir_name}xmlViolation.test
67                        ${test_dir_name}tokenizer-test-1.test                        ${test_dir_name}tokenizer-test-1.test
68                       ]) {                       ]) {
69    open my $file, '<', $file_name    open my $file, '<', $file_name
# Line 80  for my $file_name (grep {$_} split /\s+/ Line 83  for my $file_name (grep {$_} split /\s+/
83      $c += ((((hex $1) & 0b1111111111) << 10) | ((hex $2) & 0b1111111111));      $c += ((((hex $1) & 0b1111111111) << 10) | ((hex $2) & 0b1111111111));
84      chr $c;      chr $c;
85    }gex;    }gex;
86    my $tests = jsonToObj ($js)->{tests};    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 121  for my $file_name (grep {$_} split /\s+/ Line 125  for my $file_name (grep {$_} split /\s+/
125          } elsif ($self->{next_char} == 0x0000) { # NULL          } elsif ($self->{next_char} == 0x0000) { # NULL
126            $self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST            $self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST
127            push @token, 'ParseError';            push @token, 'ParseError';
128            } elsif ($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];        $p->{prev_char} = [-1, -1, -1];
# Line 156  for my $file_name (grep {$_} split /\s+/ Line 181  for my $file_name (grep {$_} split /\s+/
181          $test_token->[1] = $token->{data} if defined $token->{data};          $test_token->[1] = $token->{data} if defined $token->{data};
182          if ($token->{type} == Whatpm::HTML::START_TAG_TOKEN ()) {          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              $test_token->[3] = 1 if $p->{self_closing};
185              delete $p->{self_closing};
186          } elsif ($token->{type} == Whatpm::HTML::DOCTYPE_TOKEN ()) {          } elsif ($token->{type} == Whatpm::HTML::DOCTYPE_TOKEN ()) {
187            $test_token->[1] = $token->{name};            $test_token->[1] = $token->{name};
188            $test_token->[2] = $token->{public_identifier};            $test_token->[2] = $token->{public_identifier};
Legend:
Removed from v.1.30  
changed lines
  Added in v.1.38
[email protected]
 ViewVC Help
Powered by ViewVC 1.1.24