Parent Directory
| 
Revision Log
| 
Patch
| revision 1.25 by wakaba, Sun Jun 24 05:12:11 2007 UTC | revision 1.38 by wakaba, Tue Jul 17 13:54:57 2007 UTC | |
|---|---|---|
| # | Line 7 our $VERSION=do{my @r=(q$Revision$=~/\d+ | Line 7 our $VERSION=do{my @r=(q$Revision$=~/\d+ |
| 7 | ## doc.write (''); | ## doc.write (''); |
| 8 | ## alert (doc.compatMode); | ## alert (doc.compatMode); |
| 9 | ||
| 10 | ## ISSUE: HTML5 revision 967 says that the encoding layer MUST NOT | |
| 11 | ## strip BOM and the HTML layer MUST ignore it. Whether we can do it | |
| 12 | ## is not yet clear. | |
| 13 | ## "{U+FEFF}..." in UTF-16BE/UTF-16LE is three or four characters? | |
| 14 | ## "{U+FEFF}..." in GB18030? | |
| 15 | ||
| 16 | my $permitted_slash_tag_name = { | my $permitted_slash_tag_name = { |
| 17 | base => 1, | base => 1, |
| 18 | link => 1, | link => 1, |
| # | Line 247 sub _get_next_token ($) { | Line 253 sub _get_next_token ($) { |
| 253 | } elsif ($self->{state} eq 'entity data') { | } elsif ($self->{state} eq 'entity data') { |
| 254 | ## (cannot happen in CDATA state) | ## (cannot happen in CDATA state) |
| 255 | ||
| 256 | my $token = $self->_tokenize_attempt_to_consume_an_entity; | my $token = $self->_tokenize_attempt_to |