| 11 |
## TODO: 1252 parse error (revision 1264) |
## TODO: 1252 parse error (revision 1264) |
| 12 |
## TODO: 8859-11 = 874 (revision 1271) |
## TODO: 8859-11 = 874 (revision 1271) |
| 13 |
|
|
| 14 |
|
require IO::Handle; |
| 15 |
|
|
| 16 |
my $HTML_NS = q<http://www.w3.org/1999/xhtml>; |
my $HTML_NS = q<http://www.w3.org/1999/xhtml>; |
| 17 |
my $MML_NS = q<http://www.w3.org/1998/Math/MathML>; |
my $MML_NS = q<http://www.w3.org/1998/Math/MathML>; |
| 18 |
my $SVG_NS = q<http://www.w3.org/2000/svg>; |
my $SVG_NS = q<http://www.w3.org/2000/svg>; |
| 334 |
}; # $c1_entity_char |
}; # $c1_entity_char |
| 335 |
|
|
| 336 |
sub parse_byte_string ($$$$;$) { |
sub parse_byte_string ($$$$;$) { |
| 337 |
|
my $self = shift; |
| 338 |
|
my $charset_name = shift; |
| 339 |
|
open my $input, '<', ref $_[0] ? $_[0] : \($_[0]); |
| 340 |
|
return $self->parse_byte_stream ($charset_name, $input, @_[1..$#_]); |
| 341 |
|
} # parse_byte_string |
| 342 |
|
|
| 343 |
|
sub parse_byte_stream ($$$$;$) { |
| 344 |
my $self = ref $_[0] ? shift : shift->new; |
my $self = ref $_[0] ? shift : shift->new; |
| 345 |
my $charset_name = shift; |
my $charset_name = shift; |
| 346 |
open my $byte_stream, '<', ref $_[0] ? $_[0] : \($_[0]); |
my $byte_stream = $_[0]; |
| 347 |
|
|
| 348 |
my $onerror = $_[2] || sub { |
my $onerror = $_[2] || sub { |
| 349 |
my (%opt) = @_; |
my (%opt) = @_; |
| 555 |
$return = $self->parse_char_stream ($char_stream, @args); |
$return = $self->parse_char_stream ($char_stream, @args); |
| 556 |
}; |
}; |
| 557 |
return $return; |
return $return; |
| 558 |
} # parse_byte_string |
} # parse_byte_stream |
| 559 |
|
|
| 560 |
## NOTE: HTML5 spec says that the encoding layer MUST NOT strip BOM |
## NOTE: HTML5 spec says that the encoding layer MUST NOT strip BOM |
| 561 |
## and the HTML layer MUST ignore it. However, we does strip BOM in |
## and the HTML layer MUST ignore it. However, we does strip BOM in |
| 568 |
|
|
| 569 |
sub parse_char_string ($$$;$) { |
sub parse_char_string ($$$;$) { |
| 570 |
my $self = shift; |
my $self = shift; |
| 571 |
open my $input, '<:utf8', ref $_[0] ? $_[0] : \($_[0]); |
require utf8; |
| 572 |
|
my $s = ref $_[0] ? $_[0] : \($_[0]); |
| 573 |
|
open my $input, '<' . (utf8::is_utf8 ($$s) ? ':utf8' : ''), $s; |
| 574 |
return $self->parse_char_stream ($input, @_[1..$#_]); |
return $self->parse_char_stream ($input, @_[1..$#_]); |
| 575 |
} # parse_char_string |
} # parse_char_string |
| 576 |
*parse_string = \&parse_char_string; |
*parse_string = \&parse_char_string; |
| 596 |
pop @{$self->{prev_char}}; |
pop @{$self->{prev_char}}; |
| 597 |
unshift @{$self->{prev_char}}, $self->{next_char}; |
unshift @{$self->{prev_char}}, $self->{next_char}; |
| 598 |
|
|
| 599 |
my $char = $input->getc; |
my $char; |
| 600 |
|
if (defined $self->{next_next_char}) { |
| 601 |
|
$char = $self->{next_next_char}; |
| 602 |
|
delete $self->{next_next_char}; |
| 603 |
|
} else { |
| 604 |
|
$char = $input->getc; |
| 605 |
|
} |
| 606 |
$self->{next_char} = -1 and return unless defined $char; |
$self->{next_char} = -1 and return unless defined $char; |
| 607 |
$self->{next_char} = ord $char; |
$self->{next_char} = ord $char; |
| 608 |
|
|
| 617 |
} elsif ($self->{next_char} == 0x000D) { # CR |
} elsif ($self->{next_char} == 0x000D) { # CR |
| 618 |
!!!cp ('j2'); |
!!!cp ('j2'); |
| 619 |
my $next = $input->getc; |
my $next = $input->getc; |
| 620 |
if ($next ne "\x0A") { |
if (defined $next and $next ne "\x0A") { |
| 621 |
$input->ungetc ($next); |
$self->{next_next_char} = $next; |
| 622 |
} |
} |
| 623 |
$self->{next_char} = 0x000A; # LF # MUST |
$self->{next_char} = 0x000A; # LF # MUST |
| 624 |
$self->{line}++; |
$self->{line}++; |
| 1827 |
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
| 1828 |
!!!next-input-character; |
!!!next-input-character; |
| 1829 |
redo A; |
redo A; |
| 1830 |
|
} elsif ($self->{next_char} == -1) { |
| 1831 |
|
!!!parse-error (type => 'unclosed tag'); |
| 1832 |
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1833 |
|
!!!cp (122.3); |
| 1834 |
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1835 |
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1836 |
|
if ($self->{current_token}->{attributes}) { |
| 1837 |
|
!!!cp (122.1); |
| 1838 |
|
!!!parse-error (type => 'end tag attribute'); |
| 1839 |
|
} else { |
| 1840 |
|
## NOTE: This state should never be reached. |
| 1841 |
|
!!!cp (122.2); |
| 1842 |
|
} |
| 1843 |
|
} else { |
| 1844 |
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 1845 |
|
} |
| 1846 |
|
$self->{state} = DATA_STATE; |
| 1847 |
|
## Reconsume. |
| 1848 |
|
!!!emit ($self->{current_token}); # start tag or end tag |
| 1849 |
|
redo A; |
| 1850 |
} else { |
} else { |
| 1851 |
!!!cp ('124.1'); |
!!!cp ('124.1'); |
| 1852 |
!!!parse-error (type => 'no space between attributes'); |
!!!parse-error (type => 'no space between attributes'); |
| 1879 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 1880 |
|
|
| 1881 |
redo A; |
redo A; |
| 1882 |
|
} elsif ($self->{next_char} == -1) { |
| 1883 |
|
!!!parse-error (type => 'unclosed tag'); |
| 1884 |
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1885 |
|
!!!cp (124.7); |
| 1886 |
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1887 |
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1888 |
|
if ($self->{current_token}->{attributes}) { |
| 1889 |
|
!!!cp (124.5); |
| 1890 |
|
!!!parse-error (type => 'end tag attribute'); |
| 1891 |
|
} else { |
| 1892 |
|
## NOTE: This state should never be reached. |
| 1893 |
|
!!!cp (124.6); |
| 1894 |
|
} |
| 1895 |
|
} else { |
| 1896 |
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 1897 |
|
} |
| 1898 |
|
$self->{state} = DATA_STATE; |
| 1899 |
|
## Reconsume. |
| 1900 |
|
!!!emit ($self->{current_token}); # start tag or end tag |
| 1901 |
|
redo A; |
| 1902 |
} else { |
} else { |
| 1903 |
!!!cp ('124.4'); |
!!!cp ('124.4'); |
| 1904 |
!!!parse-error (type => 'nestc'); |
!!!parse-error (type => 'nestc'); |
| 3414 |
if ($self->{open_elements}->[0]->[0] eq $node->[0]) { |
if ($self->{open_elements}->[0]->[0] eq $node->[0]) { |
| 3415 |
$last = 1; |
$last = 1; |
| 3416 |
if (defined $self->{inner_html_node}) { |
if (defined $self->{inner_html_node}) { |
| 3417 |
if ($self->{inner_html_node}->[1] & TABLE_CELL_EL) { |
!!!cp ('t28'); |
| 3418 |
!!!cp ('t27'); |
$node = $self->{inner_html_node}; |
| 3419 |
# |
} else { |
| 3420 |
} else { |
die "_reset_insertion_mode: t27"; |
|
!!!cp ('t28'); |
|
|
$node = $self->{inner_html_node}; |
|
|
} |
|
| 3421 |
} |
} |
| 3422 |
} |
} |
| 3423 |
|
|
| 3424 |
## Step 4..14 |
## Step 4..14 |
| 3425 |
my $new_mode; |
my $new_mode; |
| 3426 |
if ($node->[1] & FOREIGN_EL) { |
if ($node->[1] & FOREIGN_EL) { |
| 3427 |
## NOTE: Strictly spaking, the line below only applies to MathML and |
!!!cp ('t28.1'); |
| 3428 |
## SVG elements. Currently the HTML syntax supports only MathML and |
## NOTE: Strictly spaking, the line below only applies to MathML and |
| 3429 |
## SVG elements as foreigners. |
## SVG elements. Currently the HTML syntax supports only MathML and |
| 3430 |
$new_mode = $self->{insertion_mode} | IN_FOREIGN_CONTENT_IM; |
## SVG elements as foreigners. |
| 3431 |
## ISSUE: What is set as the secondary insertion mode? |
$new_mode = $self->{insertion_mode} | IN_FOREIGN_CONTENT_IM; |
| 3432 |
} else { |
## ISSUE: What is set as the secondary insertion mode? |
| 3433 |
$new_mode = { |
} elsif ($node->[1] & TABLE_CELL_EL) { |
| 3434 |
|
if ($last) { |
| 3435 |
|
!!!cp ('t28.2'); |
| 3436 |
|
# |
| 3437 |
|
} else { |
| 3438 |
|
!!!cp ('t28.3'); |
| 3439 |
|
$new_mode = IN_CELL_IM; |
| 3440 |
|
} |
| 3441 |
|
} else { |
| 3442 |
|
!!!cp ('t28.4'); |
| 3443 |
|
$new_mode = { |
| 3444 |
select => IN_SELECT_IM, |
select => IN_SELECT_IM, |
| 3445 |
## NOTE: |option| and |optgroup| do not set |
## NOTE: |option| and |optgroup| do not set |
| 3446 |
## insertion mode to "in select" by themselves. |
## insertion mode to "in select" by themselves. |
|
td => IN_CELL_IM, |
|
|
th => IN_CELL_IM, |
|
| 3447 |
tr => IN_ROW_IM, |
tr => IN_ROW_IM, |
| 3448 |
tbody => IN_TABLE_BODY_IM, |
tbody => IN_TABLE_BODY_IM, |
| 3449 |
thead => IN_TABLE_BODY_IM, |
thead => IN_TABLE_BODY_IM, |
| 3455 |
body => IN_BODY_IM, |
body => IN_BODY_IM, |
| 3456 |
frameset => IN_FRAMESET_IM, |
frameset => IN_FRAMESET_IM, |
| 3457 |
}->{$node->[0]->manakai_local_name}; |
}->{$node->[0]->manakai_local_name}; |
| 3458 |
} |
} |
| 3459 |
$self->{insertion_mode} = $new_mode and return if defined $new_mode; |
$self->{insertion_mode} = $new_mode and return if defined $new_mode; |
| 3460 |
|
|
| 3461 |
## Step 15 |
## Step 15 |
| 3462 |
if ($node->[1] & HTML_EL) { |
if ($node->[1] & HTML_EL) { |
| 4199 |
!!!next-token; |
!!!next-token; |
| 4200 |
next B; |
next B; |
| 4201 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4202 |
!!!cp ('t94'); |
!!!cp ('t93.2'); |
| 4203 |
# |
!!!parse-error (type => 'after head:head', token => $token); ## TODO: error type |
| 4204 |
|
## Ignore the token |
| 4205 |
|
!!!nack ('t93.3'); |
| 4206 |
|
!!!next-token; |
| 4207 |
|
next B; |
| 4208 |
} else { |
} else { |
| 4209 |
!!!cp ('t95'); |
!!!cp ('t95'); |
| 4210 |
!!!parse-error (type => 'in head:head', token => $token); # or in head noscript |
!!!parse-error (type => 'in head:head', token => $token); # or in head noscript |
| 4526 |
$self->{insertion_mode} = AFTER_HEAD_IM; |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4527 |
!!!next-token; |
!!!next-token; |
| 4528 |
next B; |
next B; |
| 4529 |
|
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4530 |
|
!!!cp ('t134.1'); |
| 4531 |
|
!!!parse-error (type => 'unmatched end tag:head', token => $token); |
| 4532 |
|
## Ignore the token |
| 4533 |
|
!!!next-token; |
| 4534 |
|
next B; |
| 4535 |
} else { |
} else { |
| 4536 |
!!!cp ('t135'); |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
|
# |
|
| 4537 |
} |
} |
| 4538 |
} elsif ($token->{tag_name} eq 'noscript') { |
} elsif ($token->{tag_name} eq 'noscript') { |
| 4539 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4542 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4543 |
!!!next-token; |
!!!next-token; |
| 4544 |
next B; |
next B; |
| 4545 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM or |
| 4546 |
|
$self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4547 |
!!!cp ('t137'); |
!!!cp ('t137'); |
| 4548 |
!!!parse-error (type => 'unmatched end tag:noscript', token => $token); |
!!!parse-error (type => 'unmatched end tag:noscript', token => $token); |
| 4549 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 4556 |
} elsif ({ |
} elsif ({ |
| 4557 |
body => 1, html => 1, |
body => 1, html => 1, |
| 4558 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 4559 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM or |
| 4560 |
!!!cp ('t139'); |
$self->{insertion_mode} == IN_HEAD_IM or |
| 4561 |
## As if <head> |
$self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
|
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
|
|
push @{$self->{open_elements}}, |
|
|
[$self->{head_element}, $el_category->{head}]; |
|
|
|
|
|
$self->{insertion_mode} = IN_HEAD_IM; |
|
|
## Reprocess in the "in head" insertion mode... |
|
|
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
|
| 4562 |
!!!cp ('t140'); |
!!!cp ('t140'); |
| 4563 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4564 |
## Ignore the token |
## Ignore the token |
| 4565 |
!!!next-token; |
!!!next-token; |
| 4566 |
next B; |
next B; |
| 4567 |
|
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4568 |
|
!!!cp ('t140.1'); |
| 4569 |
|
!!!parse-error (type => 'unmatched end tag:' . $token->{tag_name}, token => $token); |
| 4570 |
|
## Ignore the token |
| 4571 |
|
!!!next-token; |
| 4572 |
|
next B; |
| 4573 |
} else { |
} else { |
| 4574 |
!!!cp ('t141'); |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
| 4575 |
} |
} |
| 4576 |
|
} elsif ($token->{tag_name} eq 'p') { |
| 4577 |
# |
!!!cp ('t142'); |
| 4578 |
} elsif ({ |
!!!parse-error (type => 'unmatched end tag:p', token => $token); |
| 4579 |
p => 1, br => 1, |
## Ignore the token |
| 4580 |
}->{$token->{tag_name}}) { |
!!!next-token; |
| 4581 |
|
next B; |
| 4582 |
|
} elsif ($token->{tag_name} eq 'br') { |
| 4583 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4584 |
!!!cp ('t142'); |
!!!cp ('t142.2'); |
| 4585 |
## As if <head> |
## (before head) as if <head>, (in head) as if </head> |
| 4586 |
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
| 4587 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 4588 |
push @{$self->{open_elements}}, |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4589 |
[$self->{head_element}, $el_category->{head}]; |
|
| 4590 |
|
## Reprocess in the "after head" insertion mode... |
| 4591 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 4592 |
|
!!!cp ('t143.2'); |
| 4593 |
|
## As if </head> |
| 4594 |
|
pop @{$self->{open_elements}}; |
| 4595 |
|
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4596 |
|
|
| 4597 |
|
## Reprocess in the "after head" insertion mode... |
| 4598 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4599 |
|
!!!cp ('t143.3'); |
| 4600 |
|
## ISSUE: Two parse errors for <head><noscript></br> |
| 4601 |
|
!!!parse-error (type => 'unmatched end tag:br', token => $token); |
| 4602 |
|
## As if </noscript> |
| 4603 |
|
pop @{$self->{open_elements}}; |
| 4604 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4605 |
|
|
| 4606 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4607 |
} else { |
## As if </head> |
| 4608 |
!!!cp ('t143'); |
pop @{$self->{open_elements}}; |
| 4609 |
} |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4610 |
|
|
| 4611 |
# |
## Reprocess in the "after head" insertion mode... |
| 4612 |
} else { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4613 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
!!!cp ('t143.4'); |
|
!!!cp ('t144'); |
|
| 4614 |
# |
# |
| 4615 |
} else { |
} else { |
| 4616 |
!!!cp ('t145'); |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
next B; |
|
| 4617 |
} |
} |
| 4618 |
|
|
| 4619 |
|
## ISSUE: does not agree with IE7 - it doesn't ignore </br>. |
| 4620 |
|
!!!parse-error (type => 'unmatched end tag:br', token => $token); |
| 4621 |
|
## Ignore the token |
| 4622 |
|
!!!next-token; |
| 4623 |
|
next B; |
| 4624 |
|
} else { |
| 4625 |
|
!!!cp ('t145'); |
| 4626 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4627 |
|
## Ignore the token |
| 4628 |
|
!!!next-token; |
| 4629 |
|
next B; |
| 4630 |
} |
} |
| 4631 |
|
|
| 4632 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |