/[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 1.70 by wakaba, Sat Mar 1 00:42:52 2008 UTC revision 1.71 by wakaba, Sun Mar 2 03:39:41 2008 UTC
# Line 8  use Error qw(:try); Line 8  use Error qw(:try);
8  ## doc.write ('');  ## doc.write ('');
9  ## alert (doc.compatMode);  ## alert (doc.compatMode);
10    
 ## ISSUE: HTML5 revision 967 says that the encoding layer MUST NOT  
 ## strip BOM and the HTML layer MUST ignore it.  Whether we can do it  
 ## is not yet clear.  
 ## "{U+FEFF}..." in UTF-16BE/UTF-16LE is three or four characters?  
 ## "{U+FEFF}..." in GB18030?  
   
11  ## TODO: Control charcters and noncharacters are not allowed (HTML5 revision 1263)  ## TODO: Control charcters and noncharacters are not allowed (HTML5 revision 1263)
12  ## TODO: 1252 parse error (revision 1264)  ## TODO: 1252 parse error (revision 1264)
13  ## TODO: 8859-11 = 874 (revision 1271)  ## TODO: 8859-11 = 874 (revision 1271)
# Line 24  my $permitted_slash_tag_name = { Line 18  my $permitted_slash_tag_name = {
18    meta => 1,    meta => 1,
19    hr => 1,    hr => 1,
20    br => 1,    br => 1,
21    img=> 1,    img => 1,
22    embed => 1,    embed => 1,
23    param => 1,    param => 1,
24    area => 1,    area => 1,
# Line 159  sub parse_byte_string ($$$$;$) { Line 153  sub parse_byte_string ($$$$;$) {
153    return $return;    return $return;
154  } # parse_byte_string  } # parse_byte_string
155    
156    ## NOTE: HTML5 spec says that the encoding layer MUST NOT strip BOM
157    ## and the HTML layer MUST ignore it.  However, we does strip BOM in
158    ## the encoding layer and the HTML layer does not ignore any U+FEFF,
159    ## because the core part of our HTML parser expects a string of character,
160    ## not a string of bytes or code units or anything which might contain a BOM.
161    ## Therefore, any parser interface that accepts a string of bytes,
162    ## such as |parse_byte_string| in this module, must ensure that it does
163    ## strip the BOM and never strip any ZWNBSP.
164    
165  *parse_char_string = \&parse_string;  *parse_char_string = \&parse_string;
166    
167  sub parse_string ($$$;$) {  sub parse_string ($$$;$) {
# Line 5464  sub set_inner_html ($$$) { Line 5467  sub set_inner_html ($$$) {
5467      $p->_initialize_tree_constructor;      $p->_initialize_tree_constructor;
5468    
5469      ## Step 2      ## Step 2
5470      my $node_ln = $node->local_name;      my $node_ln = $node->manakai_local_name;
5471      $p->{content_model} = {      $p->{content_model} = {
5472        title => RCDATA_CONTENT_MODEL,        title => RCDATA_CONTENT_MODEL,
5473        textarea => RCDATA_CONTENT_MODEL,        textarea => RCDATA_CONTENT_MODEL,
# Line 5504  sub set_inner_html ($$$) { Line 5507  sub set_inner_html ($$$) {
5507        if ($anode->node_type == 1) {        if ($anode->node_type == 1) {
5508          my $nsuri = $anode->namespace_uri;          my $nsuri = $anode->namespace_uri;
5509          if (defined $nsuri and $nsuri eq 'http://www.w3.org/1999/xhtml') {          if (defined $nsuri and $nsuri eq 'http://www.w3.org/1999/xhtml') {
5510            if ($anode->local_name eq 'form') { ## TODO: case?            if ($anode->manakai_local_name eq 'form') {
5511              $p->{form_element} = $anode;              $p->{form_element} = $anode;
5512              last AN;              last AN;
5513            }            }
Legend:
Removed from v.1.70  
changed lines
  Added in v.1.71
admin@suikawiki.org
 ViewVC Help
Powered by ViewVC 1.1.24