/[suikacvs]/markup/html/whatpm/Whatpm/HTML.pm.src
Suika

Diff of /markup/html/whatpm/Whatpm/HTML.pm.src

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1.213 by wakaba, Sun Jun 28 11:03:06 2009 UTC revision 1.215 by wakaba, Thu Jul 2 22:11:51 2009 UTC
# Line 525  sub parse_byte_stream ($$$$;$$) { Line 525  sub parse_byte_stream ($$$$;$$) {
525            
526      if ($char_stream) { # if supported      if ($char_stream) { # if supported
527        ## "Change the encoding" algorithm:        ## "Change the encoding" algorithm:
   
       ## Step 1      
       if ($charset->{category} &  
           Message::Charset::Info::CHARSET_CATEGORY_UTF16 ()) {  
         $charset = Message::Charset::Info->get_by_html_name ('utf-8');  
         ($char_stream, $e_status) = $charset->get_decode_handle  
             ($byte_stream,  
              byte_buffer => \ $buffer->{buffer});  
       }  
       $charset_name = $charset->get_iana_name;  
528                
529        ## Step 2        ## Step 1
530        if (defined $self->{input_encoding} and        if (defined $self->{input_encoding} and
531            $self->{input_encoding} eq $charset_name) {            $self->{input_encoding} eq $charset_name) {
532          !!!parse-error (type => 'charset label:matching',          !!!parse-error (type => 'charset label:matching',
# Line 546  sub parse_byte_stream ($$$$;$$) { Line 536  sub parse_byte_stream ($$$$;$$) {
536          return;          return;
537        }        }
538    
539          ## Step 2 (HTML5 revision 3205)
540          if (defined $self->{input_encoding} and
541              Message::Charset::Info->get_by_html_name ($self->{input_encoding})
542              ->{category} & Message::Charset::Info::CHARSET_CATEGORY_UTF16 ()) {
543            $self->{confident} = 1;
544            return;
545          }
546    
547          ## Step 3
548          if ($charset->{category} &
549              Message::Charset::Info::CHARSET_CATEGORY_UTF16 ()) {
550            $charset = Message::Charset::Info->get_by_html_name ('utf-8');
551            ($char_stream, $e_status) = $charset->get_decode_handle
552                ($byte_stream,
553                 byte_buffer => \ $buffer->{buffer});
554          }
555          $charset_name = $charset->get_iana_name;
556    
557        !!!parse-error (type => 'charset label detected',        !!!parse-error (type => 'charset label detected',
558                        text => $self->{input_encoding},                        text => $self->{input_encoding},
559                        value => $charset_name,                        value => $charset_name,
560                        level => $self->{level}->{warn},                        level => $self->{level}->{warn},
561                        token => $token);                        token => $token);
562                
563        ## Step 3        ## Step 4
564        # if (can) {        # if (can) {
565          ## change the encoding on the fly.          ## change the encoding on the fly.
566          #$self->{confident} = 1;          #$self->{confident} = 1;
567          #return;          #return;
568        # }        # }
569                
570        ## Step 4        ## Step 5
571        throw Whatpm::HTML::RestartParser ();        throw Whatpm::HTML::RestartParser ();
572      }      }
573    }; # $self->{change_encoding}    }; # $self->{change_encoding}

Legend:
Removed from v.1.213  
changed lines
  Added in v.1.215

[email protected]
ViewVC Help
Powered by ViewVC 1.1.24