/[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 1.160 by wakaba, Wed Sep 10 10:27:08 2008 UTC revision 1.162 by wakaba, Thu Sep 11 09:12:27 2008 UTC
# Line 354  sub parse_byte_string ($$$$;$) { Line 354  sub parse_byte_string ($$$$;$) {
354    return $self->parse_byte_stream ($charset_name, $input, @_[1..$#_]);    return $self->parse_byte_stream ($charset_name, $input, @_[1..$#_]);
355  } # parse_byte_string  } # parse_byte_string
356    
357  sub parse_byte_stream ($$$$;$) {  sub parse_byte_stream ($$$$;$$) {
358      # my ($self, $charset_name, $byte_stream, $doc, $onerror, $get_wrapper) = @_;
359    my $self = ref $_[0] ? shift : shift->new;    my $self = ref $_[0] ? shift : shift->new;
360    my $charset_name = shift;    my $charset_name = shift;
361    my $byte_stream = $_[0];    my $byte_stream = $_[0];
# Line 365  sub parse_byte_stream ($$$$;$) { Line 366  sub parse_byte_stream ($$$$;$) {
366    };    };
367    $self->{parse_error} = $onerror; # updated later by parse_char_string    $self->{parse_error} = $onerror; # updated later by parse_char_string
368    
369      my $get_wrapper = $_[3] || sub ($) {
370        return $_[0]; # $_[0] = byte stream handle, returned = arg to char handle
371      };
372    
373    ## HTML5 encoding sniffing algorithm    ## HTML5 encoding sniffing algorithm
374    require Message::Charset::Info;    require Message::Charset::Info;
375    my $charset;    my $charset;
# Line 381  sub parse_byte_stream ($$$$;$) { Line 386  sub parse_byte_stream ($$$$;$) {
386    
387      ## Step 1      ## Step 1
388      if (defined $charset_name) {      if (defined $charset_name) {
389        $charset = Message::Charset::Info->get_by_iana_name ($charset_name);        $charset = Message::Charset::Info->get_by_html_name ($charset_name);
390              ## TODO: Is this ok?  Transfer protocol's parameter should be
391              ## interpreted in its semantics?
392    
393        ## ISSUE: Unsupported encoding is not ignored according to the spec.        ## ISSUE: Unsupported encoding is not ignored according to the spec.
394        ($char_stream, $e_status) = $charset->get_decode_handle        ($char_stream, $e_status) = $charset->get_decode_handle
# Line 405  sub parse_byte_stream ($$$$;$) { Line 412  sub parse_byte_stream ($$$$;$) {
412    
413      ## Step 3      ## Step 3
414      if ($byte_buffer =~ /^\xFE\xFF/) {      if ($byte_buffer =~ /^\xFE\xFF/) {
415        $charset = Message::Charset::Info->get_by_iana_name ('utf-16be');        $charset = Message::Charset::Info->get_by_html_name ('utf-16be');
416        ($char_stream, $e_status) = $charset->get_decode_handle        ($char_stream, $e_status) = $charset->get_decode_handle
417            ($byte_stream, allow_error_reporting => 1,            ($byte_stream, allow_error_reporting => 1,
418             allow_fallback => 1, byte_buffer => \$byte_buffer);             allow_fallback => 1, byte_buffer => \$byte_buffer);
419        $self->{confident} = 1;        $self->{confident} = 1;
420        last SNIFFING;        last SNIFFING;
421      } elsif ($byte_buffer =~ /^\xFF\xFE/) {      } elsif ($byte_buffer =~ /^\xFF\xFE/) {
422        $charset = Message::Charset::Info->get_by_iana_name ('utf-16le');        $charset = Message::Charset::Info->get_by_html_name ('utf-16le');
423        ($char_stream, $e_status) = $charset->get_decode_handle        ($char_stream, $e_status) = $charset->get_decode_handle
424            ($byte_stream, allow_error_reporting => 1,            ($byte_stream, allow_error_reporting => 1,
425             allow_fallback => 1, byte_buffer => \$byte_buffer);             allow_fallback => 1, byte_buffer => \$byte_buffer);
426        $self->{confident} = 1;        $self->{confident} = 1;
427        last SNIFFING;        last SNIFFING;
428      } elsif ($byte_buffer =~ /^\xEF\xBB\xBF/) {      } elsif ($byte_buffer =~ /^\xEF\xBB\xBF/) {
429        $charset = Message::Charset::Info->get_by_iana_name ('utf-8');        $charset = Message::Charset::Info->get_by_html_name ('utf-8');
430        ($char_stream, $e_status) = $charset->get_decode_handle        ($char_stream, $e_status) = $charset->get_decode_handle
431            ($byte_stream, allow_error_reporting => 1,            ($byte_stream, allow_error_reporting => 1,
432             allow_fallback => 1, byte_buffer => \$byte_buffer);             allow_fallback => 1, byte_buffer => \$byte_buffer);
# Line 438  sub parse_byte_stream ($$$$;$) { Line 445  sub parse_byte_stream ($$$$;$) {
445      $charset_name = Whatpm::Charset::UniversalCharDet->detect_byte_string      $charset_name = Whatpm::Charset::UniversalCharDet->detect_byte_string
446          ($byte_buffer);          ($byte_buffer);
447      if (defined $charset_name) {      if (defined $charset_name) {
448        $charset = Message::Charset::Info->get_by_iana_name ($charset_name);        $charset = Message::Charset::Info->get_by_html_name ($charset_name);
449    
450        ## ISSUE: Unsupported encoding is not ignored according to the spec.        ## ISSUE: Unsupported encoding is not ignored according to the spec.
451        require Whatpm::Charset::DecodeHandle;        require Whatpm::Charset::DecodeHandle;
# Line 461  sub parse_byte_stream ($$$$;$) { Line 468  sub parse_byte_stream ($$$$;$) {
468    
469      ## Step 7: default      ## Step 7: default
470      ## TODO: Make this configurable.      ## TODO: Make this configurable.
471      $charset = Message::Charset::Info->get_by_iana_name ('windows-1252');      $charset = Message::Charset::Info->get_by_html_name ('windows-1252');
472          ## NOTE: We choose |windows-1252| here, since |utf-8| should be          ## NOTE: We choose |windows-1252| here, since |utf-8| should be
473          ## detectable in the step 6.          ## detectable in the step 6.
474      require Whatpm::Charset::DecodeHandle;      require Whatpm::Charset::DecodeHandle;
# Line 505  sub parse_byte_stream ($$$$;$) { Line 512  sub parse_byte_stream ($$$$;$) {
512      $charset_name = shift;      $charset_name = shift;
513      my $token = shift;      my $token = shift;
514    
515      $charset = Message::Charset::Info->get_by_iana_name ($charset_name);      $charset = Message::Charset::Info->get_by_html_name ($charset_name);
516      ($char_stream, $e_status) = $charset->get_decode_handle      ($char_stream, $e_status) = $charset->get_decode_handle
517          ($byte_stream, allow_error_reporting => 1, allow_fallback => 1,          ($byte_stream, allow_error_reporting => 1, allow_fallback => 1,
518           byte_buffer => \ $buffer->{buffer});           byte_buffer => \ $buffer->{buffer});
# Line 516  sub parse_byte_stream ($$$$;$) { Line 523  sub parse_byte_stream ($$$$;$) {
523        ## Step 1            ## Step 1    
524        if ($charset->{category} &        if ($charset->{category} &
525            Message::Charset::Info::CHARSET_CATEGORY_UTF16 ()) {            Message::Charset::Info::CHARSET_CATEGORY_UTF16 ()) {
526          $charset = Message::Charset::Info->get_by_iana_name ('utf-8');          $charset = Message::Charset::Info->get_by_html_name ('utf-8');
527          ($char_stream, $e_status) = $charset->get_decode_handle          ($char_stream, $e_status) = $charset->get_decode_handle
528              ($byte_stream,              ($byte_stream,
529               byte_buffer => \ $buffer->{buffer});               byte_buffer => \ $buffer->{buffer});
# Line 560  sub parse_byte_stream ($$$$;$) { Line 567  sub parse_byte_stream ($$$$;$) {
567        ${$opt{octets}} = "\x{FFFD}"; # relacement character        ${$opt{octets}} = "\x{FFFD}"; # relacement character
568      }      }
569    };    };
570    $char_stream->onerror ($char_onerror);  
571      my $wrapped_char_stream = $get_wrapper->($char_stream);
572      $wrapped_char_stream->onerror ($char_onerror);
573    
574    my @args = @_; shift @args; # $s    my @args = @_; shift @args; # $s
575    my $return;    my $return;
576    try {    try {
577      $return = $self->parse_char_stream ($char_stream, @args);        $return = $self->parse_char_stream ($wrapped_char_stream, @args);  
578    } catch Whatpm::HTML::RestartParser with {    } catch Whatpm::HTML::RestartParser with {
579      ## NOTE: Invoked after {change_encoding}.      ## NOTE: Invoked after {change_encoding}.
580    
# Line 588  sub parse_byte_stream ($$$$;$) { Line 597  sub parse_byte_stream ($$$$;$) {
597        $self->{input_encoding} = $charset->get_iana_name;        $self->{input_encoding} = $charset->get_iana_name;
598      }      }
599      $self->{confident} = 1;      $self->{confident} = 1;
600      $char_stream->onerror ($char_onerror);  
601      $return = $self->parse_char_stream ($char_stream, @args);      $wrapped_char_stream = $get_wrapper->($char_stream);
602        $wrapped_char_stream->onerror ($char_onerror);
603    
604        $return = $self->parse_char_stream ($wrapped_char_stream, @args);
605    };    };
606    return $return;    return $return;
607  } # parse_byte_stream  } # parse_byte_stream
# Line 603  sub parse_byte_stream ($$$$;$) { Line 615  sub parse_byte_stream ($$$$;$) {
615  ## such as |parse_byte_string| in this module, must ensure that it does  ## such as |parse_byte_string| in this module, must ensure that it does
616  ## strip the BOM and never strip any ZWNBSP.  ## strip the BOM and never strip any ZWNBSP.
617    
618  sub parse_char_string ($$$;$) {  sub parse_char_string ($$$;$$) {
619      #my ($self, $s, $doc, $onerror, $get_wrapper) = @_;
620    my $self = shift;    my $self = shift;
621    require utf8;    require utf8;
622    my $s = ref $_[0] ? $_[0] : \($_[0]);    my $s = ref $_[0] ? $_[0] : \($_[0]);
623    open my $input, '<' . (utf8::is_utf8 ($$s) ? ':utf8' : ''), $s;    open my $input, '<' . (utf8::is_utf8 ($$s) ? ':utf8' : ''), $s;
624      if ($_[3]) {
625        $input = $_[3]->($input);
626      }
627    return $self->parse_char_stream ($input, @_[1..$#_]);    return $self->parse_char_stream ($input, @_[1..$#_]);
628  } # parse_char_string  } # parse_char_string
629  *parse_string = \&parse_char_string;  *parse_string = \&parse_char_string; ## NOTE: Alias for backward compatibility.
630    
631  sub parse_char_stream ($$$;$) {  sub parse_char_stream ($$$;$) {
632    my $self = ref $_[0] ? shift : shift->new;    my $self = ref $_[0] ? shift : shift->new;
# Line 7456  sub _tree_construction_main ($) { Line 7472  sub _tree_construction_main ($) {
7472    ## TODO: script stuffs    ## TODO: script stuffs
7473  } # _tree_construct_main  } # _tree_construct_main
7474    
7475  sub set_inner_html ($$$) {  sub set_inner_html ($$$;$) {
7476    my $class = shift;    my $class = shift;
7477    my $node = shift;    my $node = shift;
7478    my $s = \$_[0];    my $s = \$_[0];
7479    my $onerror = $_[1];    my $onerror = $_[1];
7480      my $get_wrapper = $_[2] || sub ($) { return $_[0] };
7481    
7482    ## ISSUE: Should {confident} be true?    ## ISSUE: Should {confident} be true?
7483    
# Line 7479  sub set_inner_html ($$$) { Line 7496  sub set_inner_html ($$$) {
7496      }      }
7497    
7498      ## Step 3, 4, 5 # MUST      ## Step 3, 4, 5 # MUST
7499      $class->parse_string ($$s => $node, $onerror);      $class->parse_char_string ($$s => $node, $onerror, $get_wrapper);
7500    } elsif ($nt == 1) {    } elsif ($nt == 1) {
7501      ## TODO: If non-html element      ## TODO: If non-html element
7502    
7503      ## NOTE: Most of this code is copied from |parse_string|      ## NOTE: Most of this code is copied from |parse_string|
7504    
7505    ## TODO: Support for $get_wrapper
7506    
7507      ## Step 1 # MUST      ## Step 1 # MUST
7508      my $this_doc = $node->owner_document;      my $this_doc = $node->owner_document;
7509      my $doc = $this_doc->implementation->create_document;      my $doc = $this_doc->implementation->create_document;
Legend:
Removed from v.1.160  
changed lines
  Added in v.1.162
[email protected]
 ViewVC Help
Powered by ViewVC 1.1.24