Parent Directory
| 
Revision Log
| 
Patch
| revision 1.95 by wakaba, Sat Mar 8 05:09:25 2008 UTC | revision 1.239 by wakaba, Sun Sep 6 10:17:38 2009 UTC | |
|---|---|---|
| # | Line 3 use strict; | Line 3 use strict; |
| 3 | our $VERSION=do{my @r=(q$Revision$=~/\d+/g);sprintf "%d."."%02d" x $#r,@r}; | our $VERSION=do{my @r=(q$Revision$=~/\d+/g);sprintf "%d."."%02d" x $#r,@r}; |
| 4 | use Error qw(:try); | use Error qw(:try); |
| 5 | ||
| 6 | use Whatpm::HTML::Tokenizer; | |
| 7 | ||
| 8 | ## NOTE: This module don't check all HTML5 parse errors; character | |
| 9 | ## encoding related parse errors are expected to be handled by relevant | |
| 10 | ## modules. | |
| 11 | ## Parse errors for control characters that are not allowed in HTML5 | |
| 12 | ## documents, for surrogate code points, and for noncharacter code | |
| 13 | ## points, as well as U+FFFD substitions for characters whose code points | |
| 14 | ## is higher than U+10FFFF may be detected by combining the parser with | |
| 15 | ## the checker implemented by Whatpm::Charset::UnicodeChecker (for its | |
| 16 | ## usage example, see |t/HTML-tree.t| in the Whatpm package or the | |
| 17 | ## WebHACC::Language::HTML module in the WebHACC package). | |
| 18 | ||
| 19 | ## ISSUE: | ## ISSUE: |
| 20 | ## var doc = implementation.createDocument (null, null, null); | ## var doc = implementation.createDocument (null, null, null); |
| 21 | ## doc.write (''); | ## doc.write (''); |
| 22 | ## alert (doc.compatMode); | ## alert (doc.compatMode); |
| 23 | ||
| 24 | ## TODO: Control charcters and noncharacters are not allowed (HTML5 revision 1263) | require IO::Handle; |
| 25 | ## TODO: 1252 parse error (revision 1264) | |
| 26 | ## TODO: 8859-11 = 874 (revision 1271) | ## Namespace URLs |
| 27 | ||
| 28 | my $permitted_slash_tag_name = { | my $HTML_NS = q<http://www.w3.org/1999/xhtml>; |
| 29 | base => 1, | my $MML_NS = q<http://www.w3.org/1998/Math/MathML>; |
| 30 | link => 1, | my $SVG_NS = q<http://www.w3.org/2000/svg>; |
| 31 | meta => 1, | my $XLINK_NS = q<http://www.w3.org/1999/xlink>; |
| 32 | hr => 1, | my $XML_NS = q<http://www.w3.org/XML/1998/namespace>; |
| 33 | br => 1, | my $XMLNS_NS = q<http://www.w3.org/2000/xmlns/>; |
| 34 | img => 1, | |
| 35 | embed => 1, | ## Element categories |
| 36 | param => 1, | |
| 37 | area => 1, | ## Bits 12-15 |
| 38 | col => 1, | sub SPECIAL_EL () { 0b1_000000000000000 } |
| 39 | input => 1, | sub SCOPING_EL () { 0b1_00000000000000 } |
| 40 | sub FORMATTING_EL () { 0b1_0000000000000 } | |
| 41 | sub PHRASING_EL () { 0b1_000000000000 } | |
| 42 | ||
| 43 | ## Bits 10-11 | |
| 44 | #sub FOREIGN_EL () { 0b1_00000000000 } # see Whatpm::HTML::Tokenizer | |
| 45 | sub FOREIGN_FLOW_CONTENT_EL () { 0b1_0000000000 } | |
| 46 | ||
| 47 | ## Bits 6-9 | |