| 8 |
## doc.write (''); |
## doc.write (''); |
| 9 |
## alert (doc.compatMode); |
## alert (doc.compatMode); |
| 10 |
|
|
|
## TODO: 1252 parse error (revision 1264) |
|
|
## TODO: 8859-11 = 874 (revision 1271) |
|
|
|
|
| 11 |
require IO::Handle; |
require IO::Handle; |
| 12 |
|
|
| 13 |
my $HTML_NS = q<http://www.w3.org/1999/xhtml>; |
my $HTML_NS = q<http://www.w3.org/1999/xhtml>; |
| 45 |
sub FOREIGN_EL () { 0b10000000000000000000000000 } |
sub FOREIGN_EL () { 0b10000000000000000000000000 } |
| 46 |
sub FOREIGN_FLOW_CONTENT_EL () { 0b100000000000000000000000000 } |
sub FOREIGN_FLOW_CONTENT_EL () { 0b100000000000000000000000000 } |
| 47 |
sub MML_AXML_EL () { 0b1000000000000000000000000000 } |
sub MML_AXML_EL () { 0b1000000000000000000000000000 } |
| 48 |
|
sub RUBY_EL () { 0b10000000000000000000000000000 } |
| 49 |
|
sub RUBY_COMPONENT_EL () { 0b100000000000000000000000000000 } |
| 50 |
|
|
| 51 |
sub TABLE_ROWS_EL () { |
sub TABLE_ROWS_EL () { |
| 52 |
TABLE_EL | |
TABLE_EL | |
| 54 |
TABLE_ROW_GROUP_EL |
TABLE_ROW_GROUP_EL |
| 55 |
} |
} |
| 56 |
|
|
| 57 |
|
## NOTE: Used in "generate implied end tags" algorithm. |
| 58 |
|
## NOTE: There is a code where a modified version of END_TAG_OPTIONAL_EL |
| 59 |
|
## is used in "generate implied end tags" implementation (search for the |
| 60 |
|
## function mae). |
| 61 |
sub END_TAG_OPTIONAL_EL () { |
sub END_TAG_OPTIONAL_EL () { |
| 62 |
DD_EL | |
DD_EL | |
| 63 |
DT_EL | |
DT_EL | |
| 64 |
LI_EL | |
LI_EL | |
| 65 |
P_EL |
P_EL | |
| 66 |
|
RUBY_COMPONENT_EL |
| 67 |
} |
} |
| 68 |
|
|
| 69 |
|
## NOTE: Used in </body> and EOF algorithms. |
| 70 |
sub ALL_END_TAG_OPTIONAL_EL () { |
sub ALL_END_TAG_OPTIONAL_EL () { |
| 71 |
END_TAG_OPTIONAL_EL | |
DD_EL | |
| 72 |
|
DT_EL | |
| 73 |
|
LI_EL | |
| 74 |
|
P_EL | |
| 75 |
|
|
| 76 |
BODY_EL | |
BODY_EL | |
| 77 |
HTML_EL | |
HTML_EL | |
| 78 |
TABLE_CELL_EL | |
TABLE_CELL_EL | |
| 108 |
ADDRESS_EL | |
ADDRESS_EL | |
| 109 |
BODY_EL | |
BODY_EL | |
| 110 |
DIV_EL | |
DIV_EL | |
| 111 |
END_TAG_OPTIONAL_EL | |
|
| 112 |
|
DD_EL | |
| 113 |
|
DT_EL | |
| 114 |
|
LI_EL | |
| 115 |
|
P_EL | |
| 116 |
|
|
| 117 |
FORM_EL | |
FORM_EL | |
| 118 |
FRAMESET_EL | |
FRAMESET_EL | |
| 119 |
HEADING_EL | |
HEADING_EL | |
| 187 |
param => MISC_SPECIAL_EL, |
param => MISC_SPECIAL_EL, |
| 188 |
plaintext => MISC_SPECIAL_EL, |
plaintext => MISC_SPECIAL_EL, |
| 189 |
pre => MISC_SPECIAL_EL, |
pre => MISC_SPECIAL_EL, |
| 190 |
|
rp => RUBY_COMPONENT_EL, |
| 191 |
|
rt => RUBY_COMPONENT_EL, |
| 192 |
|
ruby => RUBY_EL, |
| 193 |
s => FORMATTING_EL, |
s => FORMATTING_EL, |
| 194 |
script => MISC_SPECIAL_EL, |
script => MISC_SPECIAL_EL, |
| 195 |
select => SELECT_EL, |
select => SELECT_EL, |
| 231 |
}; |
}; |
| 232 |
|
|
| 233 |
my $svg_attr_name = { |
my $svg_attr_name = { |
| 234 |
|
attributename => 'attributeName', |
| 235 |
attributetype => 'attributeType', |
attributetype => 'attributeType', |
| 236 |
basefrequency => 'baseFrequency', |
basefrequency => 'baseFrequency', |
| 237 |
baseprofile => 'baseProfile', |
baseprofile => 'baseProfile', |
| 242 |
diffuseconstant => 'diffuseConstant', |
diffuseconstant => 'diffuseConstant', |
| 243 |
edgemode => 'edgeMode', |
edgemode => 'edgeMode', |
| 244 |
externalresourcesrequired => 'externalResourcesRequired', |
externalresourcesrequired => 'externalResourcesRequired', |
|
fecolormatrix => 'feColorMatrix', |
|
|
fecomposite => 'feComposite', |
|
|
fegaussianblur => 'feGaussianBlur', |
|
|
femorphology => 'feMorphology', |
|
|
fetile => 'feTile', |
|
| 245 |
filterres => 'filterRes', |
filterres => 'filterRes', |
| 246 |
filterunits => 'filterUnits', |
filterunits => 'filterUnits', |
| 247 |
glyphref => 'glyphRef', |
glyphref => 'glyphRef', |
| 275 |
repeatcount => 'repeatCount', |
repeatcount => 'repeatCount', |
| 276 |
repeatdur => 'repeatDur', |
repeatdur => 'repeatDur', |
| 277 |
requiredextensions => 'requiredExtensions', |
requiredextensions => 'requiredExtensions', |
| 278 |
|
requiredfeatures => 'requiredFeatures', |
| 279 |
specularconstant => 'specularConstant', |
specularconstant => 'specularConstant', |
| 280 |
specularexponent => 'specularExponent', |
specularexponent => 'specularExponent', |
| 281 |
spreadmethod => 'spreadMethod', |
spreadmethod => 'spreadMethod', |
| 372 |
my ($char_stream, $e_status); |
my ($char_stream, $e_status); |
| 373 |
|
|
| 374 |
SNIFFING: { |
SNIFFING: { |
| 375 |
|
## NOTE: By setting |allow_fallback| option true when the |
| 376 |
|
## |get_decode_handle| method is invoked, we ignore what the HTML5 |
| 377 |
|
## spec requires, i.e. unsupported encoding should be ignored. |
| 378 |
|
## TODO: We should not do this unless the parser is invoked |
| 379 |
|
## in the conformance checking mode, in which this behavior |
| 380 |
|
## would be useful. |
| 381 |
|
|
| 382 |
## Step 1 |
## Step 1 |
| 383 |
if (defined $charset_name) { |
if (defined $charset_name) { |
| 449 |
allow_fallback => 1, byte_buffer => \$byte_buffer); |
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 450 |
if ($char_stream) { |
if ($char_stream) { |
| 451 |
$buffer->{buffer} = $byte_buffer; |
$buffer->{buffer} = $byte_buffer; |
| 452 |
!!!parse-error (type => 'sniffing:chardet', ## TODO: type name |
!!!parse-error (type => 'sniffing:chardet', |
| 453 |
value => $charset_name, |
text => $charset_name, |
| 454 |
level => $self->{info_level}, |
level => $self->{level}->{info}, |
| 455 |
|
layer => 'encode', |
| 456 |
line => 1, column => 1); |
line => 1, column => 1); |
| 457 |
$self->{confident} = 0; |
$self->{confident} = 0; |
| 458 |
last SNIFFING; |
last SNIFFING; |
| 473 |
allow_fallback => 1, |
allow_fallback => 1, |
| 474 |
byte_buffer => \$byte_buffer); |
byte_buffer => \$byte_buffer); |
| 475 |
$buffer->{buffer} = $byte_buffer; |
$buffer->{buffer} = $byte_buffer; |
| 476 |
!!!parse-error (type => 'sniffing:default', ## TODO: type name |
!!!parse-error (type => 'sniffing:default', |
| 477 |
value => 'windows-1252', |
text => 'windows-1252', |
| 478 |
level => $self->{info_level}, |
level => $self->{level}->{info}, |
| 479 |
line => 1, column => 1); |
line => 1, column => 1, |
| 480 |
|
layer => 'encode'); |
| 481 |
$self->{confident} = 0; |
$self->{confident} = 0; |
| 482 |
} # SNIFFING |
} # SNIFFING |
| 483 |
|
|
|
$self->{input_encoding} = $charset->get_iana_name; |
|
| 484 |
if ($e_status & Message::Charset::Info::FALLBACK_ENCODING_IMPL ()) { |
if ($e_status & Message::Charset::Info::FALLBACK_ENCODING_IMPL ()) { |
| 485 |
!!!parse-error (type => 'chardecode:fallback', ## TODO: type name |
$self->{input_encoding} = $charset->get_iana_name; ## TODO: Should we set actual charset decoder's encoding name? |
| 486 |
value => $self->{input_encoding}, |
!!!parse-error (type => 'chardecode:fallback', |
| 487 |
level => $self->{unsupported_level}, |
#text => $self->{input_encoding}, |
| 488 |
line => 1, column => 1); |
level => $self->{level}->{uncertain}, |
| 489 |
|
line => 1, column => 1, |
| 490 |
|
layer => 'encode'); |
| 491 |
} elsif (not ($e_status & |
} elsif (not ($e_status & |
| 492 |
Message::Charset::Info::ERROR_REPORTING_ENCODING_IMPL())) { |
Message::Charset::Info::ERROR_REPORTING_ENCODING_IMPL())) { |
| 493 |
!!!parse-error (type => 'chardecode:no error', ## TODO: type name |
$self->{input_encoding} = $charset->get_iana_name; |
| 494 |
value => $self->{input_encoding}, |
!!!parse-error (type => 'chardecode:no error', |
| 495 |
level => $self->{unsupported_level}, |
text => $self->{input_encoding}, |
| 496 |
line => 1, column => 1); |
level => $self->{level}->{uncertain}, |
| 497 |
|
line => 1, column => 1, |
| 498 |
|
layer => 'encode'); |
| 499 |
|
} else { |
| 500 |
|
$self->{input_encoding} = $charset->get_iana_name; |
| 501 |
} |
} |
| 502 |
|
|
| 503 |
$self->{change_encoding} = sub { |
$self->{change_encoding} = sub { |
| 514 |
## "Change the encoding" algorithm: |
## "Change the encoding" algorithm: |
| 515 |
|
|
| 516 |
## Step 1 |
## Step 1 |
| 517 |
if ($charset->{iana_names}->{'utf-16'}) { ## ISSUE: UTF-16BE -> UTF-8? UTF-16LE -> UTF-8? |
if ($charset->{category} & |
| 518 |
|
Message::Charset::Info::CHARSET_CATEGORY_UTF16 ()) { |
| 519 |
$charset = Message::Charset::Info->get_by_iana_name ('utf-8'); |
$charset = Message::Charset::Info->get_by_iana_name ('utf-8'); |
| 520 |
($char_stream, $e_status) = $charset->get_decode_handle |
($char_stream, $e_status) = $charset->get_decode_handle |
| 521 |
($byte_stream, |
($byte_stream, |
| 526 |
## Step 2 |
## Step 2 |
| 527 |
if (defined $self->{input_encoding} and |
if (defined $self->{input_encoding} and |
| 528 |
$self->{input_encoding} eq $charset_name) { |
$self->{input_encoding} eq $charset_name) { |
| 529 |
!!!parse-error (type => 'charset label:matching', ## TODO: type |
!!!parse-error (type => 'charset label:matching', |
| 530 |
value => $charset_name, |
text => $charset_name, |
| 531 |
level => $self->{info_level}); |
level => $self->{level}->{info}); |
| 532 |
$self->{confident} = 1; |
$self->{confident} = 1; |
| 533 |
return; |
return; |
| 534 |
} |
} |
| 535 |
|
|
| 536 |
!!!parse-error (type => 'charset label detected:'.$self->{input_encoding}. |
!!!parse-error (type => 'charset label detected', |
| 537 |
':'.$charset_name, level => 'w', token => $token); |
text => $self->{input_encoding}, |
| 538 |
|
value => $charset_name, |
| 539 |
|
level => $self->{level}->{warn}, |
| 540 |
|
token => $token); |
| 541 |
|
|
| 542 |
## Step 3 |
## Step 3 |
| 543 |
# if (can) { |
# if (can) { |
| 553 |
|
|
| 554 |
my $char_onerror = sub { |
my $char_onerror = sub { |
| 555 |
my (undef, $type, %opt) = @_; |
my (undef, $type, %opt) = @_; |
| 556 |
!!!parse-error (%opt, type => $type, |
!!!parse-error (layer => 'encode', |
| 557 |
|
%opt, type => $type, |
| 558 |
line => $self->{line}, column => $self->{column} + 1); |
line => $self->{line}, column => $self->{column} + 1); |
| 559 |
if ($opt{octets}) { |
if ($opt{octets}) { |
| 560 |
${$opt{octets}} = "\x{FFFD}"; # relacement character |
${$opt{octets}} = "\x{FFFD}"; # relacement character |
| 569 |
} catch Whatpm::HTML::RestartParser with { |
} catch Whatpm::HTML::RestartParser with { |
| 570 |
## NOTE: Invoked after {change_encoding}. |
## NOTE: Invoked after {change_encoding}. |
| 571 |
|
|
|
$self->{input_encoding} = $charset->get_iana_name; |
|
| 572 |
if ($e_status & Message::Charset::Info::FALLBACK_ENCODING_IMPL ()) { |
if ($e_status & Message::Charset::Info::FALLBACK_ENCODING_IMPL ()) { |
| 573 |
!!!parse-error (type => 'chardecode:fallback', ## TODO: type name |
$self->{input_encoding} = $charset->get_iana_name; ## TODO: Should we set actual charset decoder's encoding name? |
| 574 |
value => $self->{input_encoding}, |
!!!parse-error (type => 'chardecode:fallback', |
| 575 |
level => $self->{unsupported_level}, |
level => $self->{level}->{uncertain}, |
| 576 |
line => 1, column => 1); |
#text => $self->{input_encoding}, |
| 577 |
|
line => 1, column => 1, |
| 578 |
|
layer => 'encode'); |
| 579 |
} elsif (not ($e_status & |
} elsif (not ($e_status & |
| 580 |
Message::Charset::Info::ERROR_REPORTING_ENCODING_IMPL())) { |
Message::Charset::Info::ERROR_REPORTING_ENCODING_IMPL())) { |
| 581 |
!!!parse-error (type => 'chardecode:no error', ## TODO: type name |
$self->{input_encoding} = $charset->get_iana_name; |
| 582 |
value => $self->{input_encoding}, |
!!!parse-error (type => 'chardecode:no error', |
| 583 |
level => $self->{unsupported_level}, |
text => $self->{input_encoding}, |
| 584 |
line => 1, column => 1); |
level => $self->{level}->{uncertain}, |
| 585 |
|
line => 1, column => 1, |
| 586 |
|
layer => 'encode'); |
| 587 |
|
} else { |
| 588 |
|
$self->{input_encoding} = $charset->get_iana_name; |
| 589 |
} |
} |
| 590 |
$self->{confident} = 1; |
$self->{confident} = 1; |
| 591 |
$char_stream->onerror ($char_onerror); |
$char_stream->onerror ($char_onerror); |
| 684 |
0x10FFFE => 1, 0x10FFFF => 1, |
0x10FFFE => 1, 0x10FFFF => 1, |
| 685 |
}->{$self->{next_char}}) { |
}->{$self->{next_char}}) { |
| 686 |
!!!cp ('j5'); |
!!!cp ('j5'); |
| 687 |
!!!parse-error (type => 'control char', level => $self->{must_level}); |
if ($self->{next_char} < 0x10000) { |
| 688 |
## TODO: error type documentation |
!!!parse-error (type => 'control char', |
| 689 |
|
text => (sprintf 'U+%04X', $self->{next_char})); |
| 690 |
|
} else { |
| 691 |
|
!!!parse-error (type => 'control char', |
| 692 |
|
text => (sprintf 'U-%08X', $self->{next_char})); |
| 693 |
|
} |
| 694 |
} |
} |
| 695 |
}; |
}; |
| 696 |
$self->{prev_char} = [-1, -1, -1]; |
$self->{prev_char} = [-1, -1, -1]; |
| 719 |
sub new ($) { |
sub new ($) { |
| 720 |
my $class = shift; |
my $class = shift; |
| 721 |
my $self = bless { |
my $self = bless { |
| 722 |
must_level => 'm', |
level => {must => 'm', |
| 723 |
should_level => 's', |
should => 's', |
| 724 |
good_level => 'w', |
warn => 'w', |
| 725 |
warn_level => 'w', |
info => 'i', |
| 726 |
info_level => 'i', |
uncertain => 'u'}, |
|
unsupported_level => 'u', |
|
| 727 |
}, $class; |
}, $class; |
| 728 |
$self->{set_next_char} = sub { |
$self->{set_next_char} = sub { |
| 729 |
$self->{next_char} = -1; |
$self->{next_char} = -1; |
| 870 |
## |->{self_closing}| is used to save the value of |$self->{self_closing}| |
## |->{self_closing}| is used to save the value of |$self->{self_closing}| |
| 871 |
## while the token is pushed back to the stack. |
## while the token is pushed back to the stack. |
| 872 |
|
|
|
## ISSUE: "When a DOCTYPE token is created, its |
|
|
## <i>self-closing flag</i> must be unset (its other state is that it |
|
|
## be set), and its attributes list must be empty.": Wrong subject? |
|
|
|
|
| 873 |
## Emitted token MUST immediately be handled by the tree construction state. |
## Emitted token MUST immediately be handled by the tree construction state. |
| 874 |
|
|
| 875 |
## Before each step, UA MAY check to see if either one of the scripts in |
## Before each step, UA MAY check to see if either one of the scripts in |
| 1382 |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
| 1383 |
->{$self->{current_attribute}->{name}}) { # MUST |
->{$self->{current_attribute}->{name}}) { # MUST |
| 1384 |
!!!cp (57); |
!!!cp (57); |
| 1385 |
!!!parse-error (type => 'duplicate attribute:'.$self->{current_attribute}->{name}, line => $self->{current_attribute}->{line}, column => $self->{current_attribute}->{column}); |
!!!parse-error (type => 'duplicate attribute', text => $self->{current_attribute}->{name}, line => $self->{current_attribute}->{line}, column => $self->{current_attribute}->{column}); |
| 1386 |
## Discard $self->{current_attribute} # MUST |
## Discard $self->{current_attribute} # MUST |
| 1387 |
} else { |
} else { |
| 1388 |
!!!cp (58); |
!!!cp (58); |
| 1553 |
|
|
| 1554 |
redo A; |
redo A; |
| 1555 |
} else { |
} else { |
| 1556 |
!!!cp (82); |
if ($self->{next_char} == 0x0022 or # " |
| 1557 |
|
$self->{next_char} == 0x0027) { # ' |
| 1558 |
|
!!!cp (78); |
| 1559 |
|
!!!parse-error (type => 'bad attribute name'); |
| 1560 |
|
} else { |
| 1561 |
|
!!!cp (82); |
| 1562 |
|
} |
| 1563 |
$self->{current_attribute} |
$self->{current_attribute} |
| 1564 |
= {name => chr ($self->{next_char}), |
= {name => chr ($self->{next_char}), |
| 1565 |
value => '', |
value => '', |
| 1594 |
!!!next-input-character; |
!!!next-input-character; |
| 1595 |
redo A; |
redo A; |
| 1596 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1597 |
|
!!!parse-error (type => 'empty unquoted attribute value'); |
| 1598 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1599 |
!!!cp (87); |
!!!cp (87); |
| 1600 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1871 |
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
| 1872 |
!!!next-input-character; |
!!!next-input-character; |
| 1873 |
redo A; |
redo A; |
| 1874 |
|
} elsif ($self->{next_char} == -1) { |
| 1875 |
|
!!!parse-error (type => 'unclosed tag'); |
| 1876 |
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1877 |
|
!!!cp (122.3); |
| 1878 |
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1879 |
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1880 |
|
if ($self->{current_token}->{attributes}) { |
| 1881 |
|
!!!cp (122.1); |
| 1882 |
|
!!!parse-error (type => 'end tag attribute'); |
| 1883 |
|
} else { |
| 1884 |
|
## NOTE: This state should never be reached. |
| 1885 |
|
!!!cp (122.2); |
| 1886 |
|
} |
| 1887 |
|
} else { |
| 1888 |
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 1889 |
|
} |
| 1890 |
|
$self->{state} = DATA_STATE; |
| 1891 |
|
## Reconsume. |
| 1892 |
|
!!!emit ($self->{current_token}); # start tag or end tag |
| 1893 |
|
redo A; |
| 1894 |
} else { |
} else { |
| 1895 |
!!!cp ('124.1'); |
!!!cp ('124.1'); |
| 1896 |
!!!parse-error (type => 'no space between attributes'); |
!!!parse-error (type => 'no space between attributes'); |
| 1923 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 1924 |
|
|
| 1925 |
redo A; |
redo A; |
| 1926 |
|
} elsif ($self->{next_char} == -1) { |
| 1927 |
|
!!!parse-error (type => 'unclosed tag'); |
| 1928 |
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1929 |
|
!!!cp (124.7); |
| 1930 |
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1931 |
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1932 |
|
if ($self->{current_token}->{attributes}) { |
| 1933 |
|
!!!cp (124.5); |
| 1934 |
|
!!!parse-error (type => 'end tag attribute'); |
| 1935 |
|
} else { |
| 1936 |
|
## NOTE: This state should never be reached. |
| 1937 |
|
!!!cp (124.6); |
| 1938 |
|
} |
| 1939 |
|
} else { |
| 1940 |
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 1941 |
|
} |
| 1942 |
|
$self->{state} = DATA_STATE; |
| 1943 |
|
## Reconsume. |
| 1944 |
|
!!!emit ($self->{current_token}); # start tag or end tag |
| 1945 |
|
redo A; |
| 1946 |
} else { |
} else { |
| 1947 |
!!!cp ('124.4'); |
!!!cp ('124.4'); |
| 1948 |
!!!parse-error (type => 'nestc'); |
!!!parse-error (type => 'nestc'); |
| 2700 |
redo A; |
redo A; |
| 2701 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 2702 |
!!!cp (208); |
!!!cp (208); |
| 2703 |
!!!parse-error (type => 'unclosed PUBLIC literal'); |
!!!parse-error (type => 'unclosed SYSTEM literal'); |
| 2704 |
|
|
| 2705 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 2706 |
!!!next-input-character; |
!!!next-input-character; |
| 2736 |
redo A; |
redo A; |
| 2737 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 2738 |
!!!cp (212); |
!!!cp (212); |
| 2739 |
!!!parse-error (type => 'unclosed PUBLIC literal'); |
!!!parse-error (type => 'unclosed SYSTEM literal'); |
| 2740 |
|
|
| 2741 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 2742 |
!!!next-input-character; |
!!!next-input-character; |
| 2784 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 2785 |
!!!cp (217); |
!!!cp (217); |
| 2786 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
|
|
|
| 2787 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 2788 |
## reconsume |
## reconsume |
| 2789 |
|
|
| 2945 |
|
|
| 2946 |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 2947 |
!!!cp (1008); |
!!!cp (1008); |
| 2948 |
!!!parse-error (type => (sprintf 'invalid character reference:U+%04X', $code), line => $l, column => $c); |
!!!parse-error (type => 'invalid character reference', |
| 2949 |
|
text => (sprintf 'U+%04X', $code), |
| 2950 |
|
line => $l, column => $c); |
| 2951 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 2952 |
} elsif ($code > 0x10FFFF) { |
} elsif ($code > 0x10FFFF) { |
| 2953 |
!!!cp (1009); |
!!!cp (1009); |
| 2954 |
!!!parse-error (type => (sprintf 'invalid character reference:U-%08X', $code), line => $l, column => $c); |
!!!parse-error (type => 'invalid character reference', |
| 2955 |
|
text => (sprintf 'U-%08X', $code), |
| 2956 |
|
line => $l, column => $c); |
| 2957 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 2958 |
} elsif ($code == 0x000D) { |
} elsif ($code == 0x000D) { |
| 2959 |
!!!cp (1010); |
!!!cp (1010); |
| 2961 |
$code = 0x000A; |
$code = 0x000A; |
| 2962 |
} elsif (0x80 <= $code and $code <= 0x9F) { |
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 2963 |
!!!cp (1011); |
!!!cp (1011); |
| 2964 |
!!!parse-error (type => (sprintf 'C1 character reference:U+%04X', $code), line => $l, column => $c); |
!!!parse-error (type => 'C1 character reference', text => (sprintf 'U+%04X', $code), line => $l, column => $c); |
| 2965 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 2966 |
} |
} |
| 2967 |
|
|
| 2994 |
|
|
| 2995 |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 2996 |
!!!cp (1015); |
!!!cp (1015); |
| 2997 |
!!!parse-error (type => (sprintf 'invalid character reference:U+%04X', $code), line => $l, column => $c); |
!!!parse-error (type => 'invalid character reference', |
| 2998 |
|
text => (sprintf 'U+%04X', $code), |
| 2999 |
|
line => $l, column => $c); |
| 3000 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 3001 |
} elsif ($code > 0x10FFFF) { |
} elsif ($code > 0x10FFFF) { |
| 3002 |
!!!cp (1016); |
!!!cp (1016); |
| 3003 |
!!!parse-error (type => (sprintf 'invalid character reference:U-%08X', $code), line => $l, column => $c); |
!!!parse-error (type => 'invalid character reference', |
| 3004 |
|
text => (sprintf 'U-%08X', $code), |
| 3005 |
|
line => $l, column => $c); |
| 3006 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 3007 |
} elsif ($code == 0x000D) { |
} elsif ($code == 0x000D) { |
| 3008 |
!!!cp (1017); |
!!!cp (1017); |
| 3009 |
!!!parse-error (type => 'CR character reference', line => $l, column => $c); |
!!!parse-error (type => 'CR character reference', |
| 3010 |
|
line => $l, column => $c); |
| 3011 |
$code = 0x000A; |
$code = 0x000A; |
| 3012 |
} elsif (0x80 <= $code and $code <= 0x9F) { |
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 3013 |
!!!cp (1018); |
!!!cp (1018); |
| 3014 |
!!!parse-error (type => (sprintf 'C1 character reference:U+%04X', $code), line => $l, column => $c); |
!!!parse-error (type => 'C1 character reference', |
| 3015 |
|
text => (sprintf 'U+%04X', $code), |
| 3016 |
|
line => $l, column => $c); |
| 3017 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 3018 |
} |
} |
| 3019 |
|
|
| 3111 |
## TODO: Turn mutation events off # MUST |
## TODO: Turn mutation events off # MUST |
| 3112 |
## TODO: Turn loose Document option (manakai extension) on |
## TODO: Turn loose Document option (manakai extension) on |
| 3113 |
$self->{document}->manakai_is_html (1); # MUST |
$self->{document}->manakai_is_html (1); # MUST |
| 3114 |
|
$self->{document}->set_user_data (manakai_source_line => 1); |
| 3115 |
|
$self->{document}->set_user_data (manakai_source_column => 1); |
| 3116 |
} # _initialize_tree_constructor |
} # _initialize_tree_constructor |
| 3117 |
|
|
| 3118 |
sub _terminate_tree_constructor ($) { |
sub _terminate_tree_constructor ($) { |
| 3167 |
## language. |
## language. |
| 3168 |
my $doctype_name = $token->{name}; |
my $doctype_name = $token->{name}; |
| 3169 |
$doctype_name = '' unless defined $doctype_name; |
$doctype_name = '' unless defined $doctype_name; |
| 3170 |
$doctype_name =~ tr/a-z/A-Z/; |
$doctype_name =~ tr/a-z/A-Z/; # ASCII case-insensitive |
| 3171 |
if (not defined $token->{name} or # <!DOCTYPE> |
if (not defined $token->{name} or # <!DOCTYPE> |
|
defined $token->{public_identifier} or |
|
| 3172 |
defined $token->{system_identifier}) { |
defined $token->{system_identifier}) { |
| 3173 |
!!!cp ('t1'); |
!!!cp ('t1'); |
| 3174 |
!!!parse-error (type => 'not HTML5', token => $token); |
!!!parse-error (type => 'not HTML5', token => $token); |
| 3175 |
} elsif ($doctype_name ne 'HTML') { |
} elsif ($doctype_name ne 'HTML') { |
| 3176 |
!!!cp ('t2'); |
!!!cp ('t2'); |
|
## ISSUE: ASCII case-insensitive? (in fact it does not matter) |
|
| 3177 |
!!!parse-error (type => 'not HTML5', token => $token); |
!!!parse-error (type => 'not HTML5', token => $token); |
| 3178 |
|
} elsif (defined $token->{public_identifier}) { |
| 3179 |
|
if ($token->{public_identifier} eq 'XSLT-compat') { |
| 3180 |
|
!!!cp ('t1.2'); |
| 3181 |
|
!!!parse-error (type => 'XSLT-compat', token => $token, |
| 3182 |
|
level => $self->{level}->{should}); |
| 3183 |
|
} else { |
| 3184 |
|
!!!parse-error (type => 'not HTML5', token => $token); |
| 3185 |
|
} |
| 3186 |
} else { |
} else { |
| 3187 |
!!!cp ('t3'); |
!!!cp ('t3'); |
| 3188 |
|
# |
| 3189 |
} |
} |
| 3190 |
|
|
| 3191 |
my $doctype = $self->{document}->create_document_type_definition |
my $doctype = $self->{document}->create_document_type_definition |
| 3206 |
} elsif (defined $token->{public_identifier}) { |
} elsif (defined $token->{public_identifier}) { |
| 3207 |
my $pubid = $token->{public_identifier}; |
my $pubid = $token->{public_identifier}; |
| 3208 |
$pubid =~ tr/a-z/A-z/; |
$pubid =~ tr/a-z/A-z/; |
| 3209 |
if ({ |
my $prefix = [ |
| 3210 |
"+//SILMARIL//DTD HTML PRO V0R11 19970101//EN" => 1, |
"+//SILMARIL//DTD HTML PRO V0R11 19970101//", |
| 3211 |
"-//ADVASOFT LTD//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1, |
"-//ADVASOFT LTD//DTD HTML 3.0 ASWEDIT + EXTENSIONS//", |
| 3212 |
"-//AS//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1, |
"-//AS//DTD HTML 3.0 ASWEDIT + EXTENSIONS//", |
| 3213 |
"-//IETF//DTD HTML 2.0 LEVEL 1//EN" => 1, |
"-//IETF//DTD HTML 2.0 LEVEL 1//", |
| 3214 |
"-//IETF//DTD HTML 2.0 LEVEL 2//EN" => 1, |
"-//IETF//DTD HTML 2.0 LEVEL 2//", |
| 3215 |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 1//EN" => 1, |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 1//", |
| 3216 |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 2//EN" => 1, |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 2//", |
| 3217 |
"-//IETF//DTD HTML 2.0 STRICT//EN" => 1, |
"-//IETF//DTD HTML 2.0 STRICT//", |
| 3218 |
"-//IETF//DTD HTML 2.0//EN" => 1, |
"-//IETF//DTD HTML 2.0//", |
| 3219 |
"-//IETF//DTD HTML 2.1E//EN" => 1, |
"-//IETF//DTD HTML 2.1E//", |
| 3220 |
"-//IETF//DTD HTML 3.0//EN" => 1, |
"-//IETF//DTD HTML 3.0//", |
| 3221 |
"-//IETF//DTD HTML 3.0//EN//" => 1, |
"-//IETF//DTD HTML 3.2 FINAL//", |
| 3222 |
"-//IETF//DTD HTML 3.2 FINAL//EN" => 1, |
"-//IETF//DTD HTML 3.2//", |
| 3223 |
"-//IETF//DTD HTML 3.2//EN" => 1, |
"-//IETF//DTD HTML 3//", |
| 3224 |
"-//IETF//DTD HTML 3//EN" => 1, |
"-//IETF//DTD HTML LEVEL 0//", |
| 3225 |
"-//IETF//DTD HTML LEVEL 0//EN" => 1, |
"-//IETF//DTD HTML LEVEL 1//", |
| 3226 |
"-//IETF//DTD HTML LEVEL 0//EN//2.0" => 1, |
"-//IETF//DTD HTML LEVEL 2//", |
| 3227 |
"-//IETF//DTD HTML LEVEL 1//EN" => 1, |
"-//IETF//DTD HTML LEVEL 3//", |
| 3228 |
"-//IETF//DTD HTML LEVEL 1//EN//2.0" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 0//", |
| 3229 |
"-//IETF//DTD HTML LEVEL 2//EN" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 1//", |
| 3230 |
"-//IETF//DTD HTML LEVEL 2//EN//2.0" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 2//", |
| 3231 |
"-//IETF//DTD HTML LEVEL 3//EN" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 3//", |
| 3232 |
"-//IETF//DTD HTML LEVEL 3//EN//3.0" => 1, |
"-//IETF//DTD HTML STRICT//", |
| 3233 |
"-//IETF//DTD HTML STRICT LEVEL 0//EN" => 1, |
"-//IETF//DTD HTML//", |
| 3234 |
"-//IETF//DTD HTML STRICT LEVEL 0//EN//2.0" => 1, |
"-//METRIUS//DTD METRIUS PRESENTATIONAL//", |
| 3235 |
"-//IETF//DTD HTML STRICT LEVEL 1//EN" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML STRICT//", |
| 3236 |
"-//IETF//DTD HTML STRICT LEVEL 1//EN//2.0" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML//", |
| 3237 |
"-//IETF//DTD HTML STRICT LEVEL 2//EN" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 TABLES//", |
| 3238 |
"-//IETF//DTD HTML STRICT LEVEL 2//EN//2.0" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML STRICT//", |
| 3239 |
"-//IETF//DTD HTML STRICT LEVEL 3//EN" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML//", |
| 3240 |
"-//IETF//DTD HTML STRICT LEVEL 3//EN//3.0" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 TABLES//", |
| 3241 |
"-//IETF//DTD HTML STRICT//EN" => 1, |
"-//NETSCAPE COMM. CORP.//DTD HTML//", |
| 3242 |
"-//IETF//DTD HTML STRICT//EN//2.0" => 1, |
"-//NETSCAPE COMM. CORP.//DTD STRICT HTML//", |
| 3243 |
"-//IETF//DTD HTML STRICT//EN//3.0" => 1, |
"-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//", |
| 3244 |
"-//IETF//DTD HTML//EN" => 1, |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//", |
| 3245 |
"-//IETF//DTD HTML//EN//2.0" => 1, |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED RELAXED 1.0//", |
| 3246 |
"-//IETF//DTD HTML//EN//3.0" => 1, |
"-//SOFTQUAD SOFTWARE//DTD HOTMETAL PRO 6.0::19990601::EXTENSIONS TO HTML 4.0//", |
| 3247 |
"-//METRIUS//DTD METRIUS PRESENTATIONAL//EN" => 1, |
"-//SOFTQUAD//DTD HOTMETAL PRO 4.0::19971010::EXTENSIONS TO HTML 4.0//", |
| 3248 |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML STRICT//EN" => 1, |
"-//SPYGLASS//DTD HTML 2.0 EXTENDED//", |
| 3249 |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML//EN" => 1, |
"-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//", |
| 3250 |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 TABLES//EN" => 1, |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//", |
| 3251 |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML STRICT//EN" => 1, |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA STRICT HTML//", |
| 3252 |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML//EN" => 1, |
"-//W3C//DTD HTML 3 1995-03-24//", |
| 3253 |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 TABLES//EN" => 1, |
"-//W3C//DTD HTML 3.2 DRAFT//", |
| 3254 |
"-//NETSCAPE COMM. CORP.//DTD HTML//EN" => 1, |
"-//W3C//DTD HTML 3.2 FINAL//", |
| 3255 |
"-//NETSCAPE COMM. CORP.//DTD STRICT HTML//EN" => 1, |
"-//W3C//DTD HTML 3.2//", |
| 3256 |
"-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//EN" => 1, |
"-//W3C//DTD HTML 3.2S DRAFT//", |
| 3257 |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//EN" => 1, |
"-//W3C//DTD HTML 4.0 FRAMESET//", |
| 3258 |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED RELAXED 1.0//EN" => 1, |
"-//W3C//DTD HTML 4.0 TRANSITIONAL//", |
| 3259 |
"-//SOFTQUAD SOFTWARE//DTD HOTMETAL PRO 6.0::19990601::EXTENSIONS TO HTML 4.0//EN" => 1, |
"-//W3C//DTD HTML EXPERIMETNAL 19960712//", |
| 3260 |
"-//SOFTQUAD//DTD HOTMETAL PRO 4.0::19971010::EXTENSIONS TO HTML 4.0//EN" => 1, |
"-//W3C//DTD HTML EXPERIMENTAL 970421//", |
| 3261 |
"-//SPYGLASS//DTD HTML 2.0 EXTENDED//EN" => 1, |
"-//W3C//DTD W3 HTML//", |
| 3262 |
"-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//EN" => 1, |
"-//W3O//DTD W3 HTML 3.0//", |
| 3263 |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//EN" => 1, |
"-//WEBTECHS//DTD MOZILLA HTML 2.0//", |
| 3264 |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA STRICT HTML//EN" => 1, |
"-//WEBTECHS//DTD MOZILLA HTML//", |
| 3265 |
"-//W3C//DTD HTML 3 1995-03-24//EN" => 1, |
]; # $prefix |
| 3266 |
"-//W3C//DTD HTML 3.2 DRAFT//EN" => 1, |
my $match; |
| 3267 |
"-//W3C//DTD HTML 3.2 FINAL//EN" => 1, |
for (@$prefix) { |
| 3268 |
"-//W3C//DTD HTML 3.2//EN" => 1, |
if (substr ($prefix, 0, length $_) eq $_) { |
| 3269 |
"-//W3C//DTD HTML 3.2S DRAFT//EN" => 1, |
$match = 1; |
| 3270 |
"-//W3C//DTD HTML 4.0 FRAMESET//EN" => 1, |
last; |
| 3271 |
"-//W3C//DTD HTML 4.0 TRANSITIONAL//EN" => 1, |
} |
| 3272 |
"-//W3C//DTD HTML EXPERIMETNAL 19960712//EN" => 1, |
} |
| 3273 |
"-//W3C//DTD HTML EXPERIMENTAL 970421//EN" => 1, |
if ($match or |
| 3274 |
"-//W3C//DTD W3 HTML//EN" => 1, |
$pubid eq "-//W3O//DTD W3 HTML STRICT 3.0//EN//" or |
| 3275 |
"-//W3O//DTD W3 HTML 3.0//EN" => 1, |
$pubid eq "-/W3C/DTD HTML 4.0 TRANSITIONAL/EN" or |
| 3276 |
"-//W3O//DTD W3 HTML 3.0//EN//" => 1, |
$pubid eq "HTML") { |
|
"-//W3O//DTD W3 HTML STRICT 3.0//EN//" => 1, |
|
|
"-//WEBTECHS//DTD MOZILLA HTML 2.0//EN" => 1, |
|
|
"-//WEBTECHS//DTD MOZILLA HTML//EN" => 1, |
|
|
"-/W3C/DTD HTML 4.0 TRANSITIONAL/EN" => 1, |
|
|
"HTML" => 1, |
|
|
}->{$pubid}) { |
|
| 3277 |
!!!cp ('t5'); |
!!!cp ('t5'); |
| 3278 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 3279 |
} elsif ($pubid eq "-//W3C//DTD HTML 4.01 FRAMESET//EN" or |
} elsif ($pubid =~ m[^-//W3C//DTD HTML 4.01 FRAMESET//] or |
| 3280 |
$pubid eq "-//W3C//DTD HTML 4.01 TRANSITIONAL//EN") { |
$pubid =~ m[^-//W3C//DTD HTML 4.01 TRANSITIONAL//]) { |
| 3281 |
if (defined $token->{system_identifier}) { |
if (defined $token->{system_identifier}) { |
| 3282 |
!!!cp ('t6'); |
!!!cp ('t6'); |
| 3283 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 3285 |
!!!cp ('t7'); |
!!!cp ('t7'); |
| 3286 |
$self->{document}->manakai_compat_mode ('limited quirks'); |
$self->{document}->manakai_compat_mode ('limited quirks'); |
| 3287 |
} |
} |
| 3288 |
} elsif ($pubid eq "-//W3C//DTD XHTML 1.0 FRAMESET//EN" or |
} elsif ($pubid =~ m[^-//W3C//DTD XHTML 1.0 FRAMESET//] or |
| 3289 |
$pubid eq "-//W3C//DTD XHTML 1.0 TRANSITIONAL//EN") { |
$pubid =~ m[^-//W3C//DTD XHTML 1.0 TRANSITIONAL//]) { |
| 3290 |
!!!cp ('t8'); |
!!!cp ('t8'); |
| 3291 |
$self->{document}->manakai_compat_mode ('limited quirks'); |
$self->{document}->manakai_compat_mode ('limited quirks'); |
| 3292 |
} else { |
} else { |
| 3299 |
my $sysid = $token->{system_identifier}; |
my $sysid = $token->{system_identifier}; |
| 3300 |
$sysid =~ tr/A-Z/a-z/; |
$sysid =~ tr/A-Z/a-z/; |
| 3301 |
if ($sysid eq "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd") { |
if ($sysid eq "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd") { |
| 3302 |
## TODO: Check the spec: PUBLIC "(limited quirks)" "(quirks)" |
## NOTE: Ensure that |PUBLIC "(limited quirks)" "(quirks)"| is |
| 3303 |
|
## marked as quirks. |
| 3304 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 3305 |
!!!cp ('t11'); |
!!!cp ('t11'); |
| 3306 |
} else { |
} else { |
| 3486 |
## NOTE: Strictly spaking, the line below only applies to MathML and |
## NOTE: Strictly spaking, the line below only applies to MathML and |
| 3487 |
## SVG elements. Currently the HTML syntax supports only MathML and |
## SVG elements. Currently the HTML syntax supports only MathML and |
| 3488 |
## SVG elements as foreigners. |
## SVG elements as foreigners. |
| 3489 |
$new_mode = $self->{insertion_mode} | IN_FOREIGN_CONTENT_IM; |
$new_mode = IN_BODY_IM | IN_FOREIGN_CONTENT_IM; |
|
## ISSUE: What is set as the secondary insertion mode? |
|
| 3490 |
} elsif ($node->[1] & TABLE_CELL_EL) { |
} elsif ($node->[1] & TABLE_CELL_EL) { |
| 3491 |
if ($last) { |
if ($last) { |
| 3492 |
!!!cp ('t28.2'); |
!!!cp ('t28.2'); |
| 3687 |
## NOTE: An end-of-file token. |
## NOTE: An end-of-file token. |
| 3688 |
if ($content_model_flag == CDATA_CONTENT_MODEL) { |
if ($content_model_flag == CDATA_CONTENT_MODEL) { |
| 3689 |
!!!cp ('t43'); |
!!!cp ('t43'); |
| 3690 |
!!!parse-error (type => 'in CDATA:#'.$token->{type}, token => $token); |
!!!parse-error (type => 'in CDATA:#eof', token => $token); |
| 3691 |
} elsif ($content_model_flag == RCDATA_CONTENT_MODEL) { |
} elsif ($content_model_flag == RCDATA_CONTENT_MODEL) { |
| 3692 |
!!!cp ('t44'); |
!!!cp ('t44'); |
| 3693 |
!!!parse-error (type => 'in RCDATA:#'.$token->{type}, token => $token); |
!!!parse-error (type => 'in RCDATA:#eof', token => $token); |
| 3694 |
} else { |
} else { |
| 3695 |
die "$0: $content_model_flag in parse_rcdata"; |
die "$0: $content_model_flag in parse_rcdata"; |
| 3696 |
} |
} |
| 3727 |
## Ignore the token |
## Ignore the token |
| 3728 |
} else { |
} else { |
| 3729 |
!!!cp ('t48'); |
!!!cp ('t48'); |
| 3730 |
!!!parse-error (type => 'in CDATA:#'.$token->{type}, token => $token); |
!!!parse-error (type => 'in CDATA:#eof', token => $token); |
| 3731 |
## ISSUE: And ignore? |
## ISSUE: And ignore? |
| 3732 |
## TODO: mark as "already executed" |
## TODO: mark as "already executed" |
| 3733 |
} |
} |
| 3778 |
} # AFE |
} # AFE |
| 3779 |
unless (defined $formatting_element) { |
unless (defined $formatting_element) { |
| 3780 |
!!!cp ('t53'); |
!!!cp ('t53'); |
| 3781 |
!!!parse-error (type => 'unmatched end tag:'.$tag_name, token => $end_tag_token); |
!!!parse-error (type => 'unmatched end tag', text => $tag_name, token => $end_tag_token); |
| 3782 |
## Ignore the token |
## Ignore the token |
| 3783 |
!!!next-token; |
!!!next-token; |
| 3784 |
return; |
return; |
| 3795 |
last INSCOPE; |
last INSCOPE; |
| 3796 |
} else { # in open elements but not in scope |
} else { # in open elements but not in scope |
| 3797 |
!!!cp ('t55'); |
!!!cp ('t55'); |
| 3798 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, |
!!!parse-error (type => 'unmatched end tag', |
| 3799 |
|
text => $token->{tag_name}, |
| 3800 |
token => $end_tag_token); |
token => $end_tag_token); |
| 3801 |
## Ignore the token |
## Ignore the token |
| 3802 |
!!!next-token; |
!!!next-token; |
| 3809 |
} # INSCOPE |
} # INSCOPE |
| 3810 |
unless (defined $formatting_element_i_in_open) { |
unless (defined $formatting_element_i_in_open) { |
| 3811 |
!!!cp ('t57'); |
!!!cp ('t57'); |
| 3812 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, |
!!!parse-error (type => 'unmatched end tag', |
| 3813 |
|
text => $token->{tag_name}, |
| 3814 |
token => $end_tag_token); |
token => $end_tag_token); |
| 3815 |
pop @$active_formatting_elements; # $formatting_element |
pop @$active_formatting_elements; # $formatting_element |
| 3816 |
!!!next-token; ## TODO: ok? |
!!!next-token; ## TODO: ok? |
| 3819 |
if (not $self->{open_elements}->[-1]->[0] eq $formatting_element->[0]) { |
if (not $self->{open_elements}->[-1]->[0] eq $formatting_element->[0]) { |
| 3820 |
!!!cp ('t58'); |
!!!cp ('t58'); |
| 3821 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 3822 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 3823 |
->manakai_local_name, |
->manakai_local_name, |
| 3824 |
token => $end_tag_token); |
token => $end_tag_token); |
| 3825 |
} |
} |
| 4028 |
B: while (1) { |
B: while (1) { |
| 4029 |
if ($token->{type} == DOCTYPE_TOKEN) { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 4030 |
!!!cp ('t73'); |
!!!cp ('t73'); |
| 4031 |
!!!parse-error (type => 'DOCTYPE in the middle', token => $token); |
!!!parse-error (type => 'in html:#DOCTYPE', token => $token); |
| 4032 |
## Ignore the token |
## Ignore the token |
| 4033 |
## Stay in the phase |
## Stay in the phase |
| 4034 |
!!!next-token; |
!!!next-token; |
| 4037 |
$token->{tag_name} eq 'html') { |
$token->{tag_name} eq 'html') { |
| 4038 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 4039 |
!!!cp ('t79'); |
!!!cp ('t79'); |
| 4040 |
!!!parse-error (type => 'after html:html', token => $token); |
!!!parse-error (type => 'after html', text => 'html', token => $token); |
| 4041 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 4042 |
} elsif ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 4043 |
!!!cp ('t80'); |
!!!cp ('t80'); |
| 4044 |
!!!parse-error (type => 'after html:html', token => $token); |
!!!parse-error (type => 'after html', text => 'html', token => $token); |
| 4045 |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 4046 |
} else { |
} else { |
| 4047 |
!!!cp ('t81'); |
!!!cp ('t81'); |
| 4092 |
# |
# |
| 4093 |
} elsif ({ |
} elsif ({ |
| 4094 |
b => 1, big => 1, blockquote => 1, body => 1, br => 1, |
b => 1, big => 1, blockquote => 1, body => 1, br => 1, |
| 4095 |
center => 1, code => 1, dd => 1, div => 1, dl => 1, em => 1, |
center => 1, code => 1, dd => 1, div => 1, dl => 1, dt => 1, |
| 4096 |
embed => 1, font => 1, h1 => 1, h2 => 1, h3 => 1, ## No h4! |
em => 1, embed => 1, font => 1, h1 => 1, h2 => 1, h3 => 1, |
| 4097 |
h5 => 1, h6 => 1, head => 1, hr => 1, i => 1, img => 1, |
h4 => 1, h5 => 1, h6 => 1, head => 1, hr => 1, i => 1, |
| 4098 |
li => 1, menu => 1, meta => 1, nobr => 1, p => 1, pre => 1, |
img => 1, li => 1, listing => 1, menu => 1, meta => 1, |
| 4099 |
ruby => 1, s => 1, small => 1, span => 1, strong => 1, |
nobr => 1, ol => 1, p => 1, pre => 1, ruby => 1, s => 1, |
| 4100 |
sub => 1, sup => 1, table => 1, tt => 1, u => 1, ul => 1, |
small => 1, span => 1, strong => 1, strike => 1, sub => 1, |
| 4101 |
var => 1, |
sup => 1, table => 1, tt => 1, u => 1, ul => 1, var => 1, |
| 4102 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 4103 |
!!!cp ('t87.2'); |
!!!cp ('t87.2'); |
| 4104 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 4105 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 4106 |
->manakai_local_name, |
->manakai_local_name, |
| 4107 |
token => $token); |
token => $token); |
| 4108 |
|
|
| 4178 |
!!!cp ('t87.5'); |
!!!cp ('t87.5'); |
| 4179 |
# |
# |
| 4180 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
|
## NOTE: "using the rules for secondary insertion mode" then "continue" |
|
| 4181 |
!!!cp ('t87.6'); |
!!!cp ('t87.6'); |
| 4182 |
# |
!!!parse-error (type => 'not closed', |
| 4183 |
## TODO: ... |
text => $self->{open_elements}->[-1]->[0] |
| 4184 |
|
->manakai_local_name, |
| 4185 |
|
token => $token); |
| 4186 |
|
|
| 4187 |
|
pop @{$self->{open_elements}} |
| 4188 |
|
while $self->{open_elements}->[-1]->[1] & FOREIGN_EL; |
| 4189 |
|
|
| 4190 |
|
$self->{insertion_mode} &= ~ IN_FOREIGN_CONTENT_IM; |
| 4191 |
|
## Reprocess. |
| 4192 |
|
next B; |
| 4193 |
} else { |
} else { |
| 4194 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 4195 |
} |
} |
| 4230 |
!!!cp ('t90'); |
!!!cp ('t90'); |
| 4231 |
## As if </noscript> |
## As if </noscript> |
| 4232 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4233 |
!!!parse-error (type => 'in noscript:#character', token => $token); |
!!!parse-error (type => 'in noscript:#text', token => $token); |
| 4234 |
|
|
| 4235 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4236 |
## As if </head> |
## As if </head> |
| 4267 |
next B; |
next B; |
| 4268 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4269 |
!!!cp ('t93.2'); |
!!!cp ('t93.2'); |
| 4270 |
!!!parse-error (type => 'after head:head', token => $token); ## TODO: error type |
!!!parse-error (type => 'after head', text => 'head', |
| 4271 |
|
token => $token); |
| 4272 |
## Ignore the token |
## Ignore the token |
| 4273 |
!!!nack ('t93.3'); |
!!!nack ('t93.3'); |
| 4274 |
!!!next-token; |
!!!next-token; |
| 4275 |
next B; |
next B; |
| 4276 |
} else { |
} else { |
| 4277 |
!!!cp ('t95'); |
!!!cp ('t95'); |
| 4278 |
!!!parse-error (type => 'in head:head', token => $token); # or in head noscript |
!!!parse-error (type => 'in head:head', |
| 4279 |
|
token => $token); # or in head noscript |
| 4280 |
## Ignore the token |
## Ignore the token |
| 4281 |
!!!nack ('t95.1'); |
!!!nack ('t95.1'); |
| 4282 |
!!!next-token; |
!!!next-token; |
| 4301 |
!!!cp ('t98'); |
!!!cp ('t98'); |
| 4302 |
## As if </noscript> |
## As if </noscript> |
| 4303 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4304 |
!!!parse-error (type => 'in noscript:base', token => $token); |
!!!parse-error (type => 'in noscript', text => 'base', |
| 4305 |
|
token => $token); |
| 4306 |
|
|
| 4307 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4308 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4313 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4314 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4315 |
!!!cp ('t100'); |
!!!cp ('t100'); |
| 4316 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4317 |
|
text => $token->{tag_name}, token => $token); |
| 4318 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4319 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4320 |
} else { |
} else { |
| 4331 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4332 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4333 |
!!!cp ('t102'); |
!!!cp ('t102'); |
| 4334 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4335 |
|
text => $token->{tag_name}, token => $token); |
| 4336 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4337 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4338 |
} else { |
} else { |
| 4349 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4350 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4351 |
!!!cp ('t104'); |
!!!cp ('t104'); |
| 4352 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4353 |
|
text => $token->{tag_name}, token => $token); |
| 4354 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4355 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4356 |
} else { |
} else { |
| 4374 |
->{has_reference}); |
->{has_reference}); |
| 4375 |
} elsif ($token->{attributes}->{content}) { |
} elsif ($token->{attributes}->{content}) { |
| 4376 |
if ($token->{attributes}->{content}->{value} |
if ($token->{attributes}->{content}->{value} |
| 4377 |
=~ /\A[^;]*;[\x09-\x0D\x20]*[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
=~ /[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
| 4378 |
[\x09-\x0D\x20]*= |
[\x09-\x0D\x20]*= |
| 4379 |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
| 4380 |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20\x3B]*))/x) { |
| 4381 |
!!!cp ('t107'); |
!!!cp ('t107'); |
| 4382 |
## NOTE: Whether the encoding is supported or not is handled |
## NOTE: Whether the encoding is supported or not is handled |
| 4383 |
## in the {change_encoding} callback. |
## in the {change_encoding} callback. |
| 4419 |
!!!cp ('t111'); |
!!!cp ('t111'); |
| 4420 |
## As if </noscript> |
## As if </noscript> |
| 4421 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4422 |
!!!parse-error (type => 'in noscript:title', token => $token); |
!!!parse-error (type => 'in noscript', text => 'title', |
| 4423 |
|
token => $token); |
| 4424 |
|
|
| 4425 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4426 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4427 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4428 |
!!!cp ('t112'); |
!!!cp ('t112'); |
| 4429 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4430 |
|
text => $token->{tag_name}, token => $token); |
| 4431 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4432 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4433 |
} else { |
} else { |
| 4441 |
pop @{$self->{open_elements}} # <head> |
pop @{$self->{open_elements}} # <head> |
| 4442 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 4443 |
next B; |
next B; |
| 4444 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($token->{tag_name} eq 'style' or |
| 4445 |
|
$token->{tag_name} eq 'noframes') { |
| 4446 |
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
| 4447 |
## insertion mode IN_HEAD_IM) |
## insertion mode IN_HEAD_IM) |
| 4448 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4449 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4450 |
!!!cp ('t114'); |
!!!cp ('t114'); |
| 4451 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4452 |
|
text => $token->{tag_name}, token => $token); |
| 4453 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4454 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4455 |
} else { |
} else { |
| 4470 |
next B; |
next B; |
| 4471 |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4472 |
!!!cp ('t117'); |
!!!cp ('t117'); |
| 4473 |
!!!parse-error (type => 'in noscript:noscript', token => $token); |
!!!parse-error (type => 'in noscript', text => 'noscript', |
| 4474 |
|
token => $token); |
| 4475 |
## Ignore the token |
## Ignore the token |
| 4476 |
!!!nack ('t117.1'); |
!!!nack ('t117.1'); |
| 4477 |
!!!next-token; |
!!!next-token; |
| 4485 |
!!!cp ('t119'); |
!!!cp ('t119'); |
| 4486 |
## As if </noscript> |
## As if </noscript> |
| 4487 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4488 |
!!!parse-error (type => 'in noscript:script', token => $token); |
!!!parse-error (type => 'in noscript', text => 'script', |
| 4489 |
|
token => $token); |
| 4490 |
|
|
| 4491 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4492 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4493 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4494 |
!!!cp ('t120'); |
!!!cp ('t120'); |
| 4495 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4496 |
|
text => $token->{tag_name}, token => $token); |
| 4497 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4498 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4499 |
} else { |
} else { |
| 4511 |
!!!cp ('t122'); |
!!!cp ('t122'); |
| 4512 |
## As if </noscript> |
## As if </noscript> |
| 4513 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4514 |
!!!parse-error (type => 'in noscript:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in noscript', |
| 4515 |
|
text => $token->{tag_name}, token => $token); |
| 4516 |
|
|
| 4517 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4518 |
## As if </head> |
## As if </head> |
| 4551 |
!!!cp ('t129'); |
!!!cp ('t129'); |
| 4552 |
## As if </noscript> |
## As if </noscript> |
| 4553 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4554 |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in noscript:/', |
| 4555 |
|
text => $token->{tag_name}, token => $token); |
| 4556 |
|
|
| 4557 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4558 |
## As if </head> |
## As if </head> |
| 4595 |
!!!cp ('t133'); |
!!!cp ('t133'); |
| 4596 |
## As if </noscript> |
## As if </noscript> |
| 4597 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4598 |
!!!parse-error (type => 'in noscript:/head', token => $token); |
!!!parse-error (type => 'in noscript:/', |
| 4599 |
|
text => 'head', token => $token); |
| 4600 |
|
|
| 4601 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4602 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4611 |
next B; |
next B; |
| 4612 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4613 |
!!!cp ('t134.1'); |
!!!cp ('t134.1'); |
| 4614 |
!!!parse-error (type => 'unmatched end tag:head', token => $token); |
!!!parse-error (type => 'unmatched end tag', text => 'head', |
| 4615 |
|
token => $token); |
| 4616 |
## Ignore the token |
## Ignore the token |
| 4617 |
!!!next-token; |
!!!next-token; |
| 4618 |
next B; |
next B; |
| 4629 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM or |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM or |
| 4630 |
$self->{insertion_mode} == AFTER_HEAD_IM) { |
$self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4631 |
!!!cp ('t137'); |
!!!cp ('t137'); |
| 4632 |
!!!parse-error (type => 'unmatched end tag:noscript', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4633 |
|
text => 'noscript', token => $token); |
| 4634 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 4635 |
!!!next-token; |
!!!next-token; |
| 4636 |
next B; |
next B; |
| 4645 |
$self->{insertion_mode} == IN_HEAD_IM or |
$self->{insertion_mode} == IN_HEAD_IM or |
| 4646 |
$self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
$self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4647 |
!!!cp ('t140'); |
!!!cp ('t140'); |
| 4648 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4649 |
|
text => $token->{tag_name}, token => $token); |
| 4650 |
## Ignore the token |
## Ignore the token |
| 4651 |
!!!next-token; |
!!!next-token; |
| 4652 |
next B; |
next B; |
| 4653 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4654 |
!!!cp ('t140.1'); |
!!!cp ('t140.1'); |
| 4655 |
!!!parse-error (type => 'unmatched end tag:' . $token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4656 |
|
text => $token->{tag_name}, token => $token); |
| 4657 |
## Ignore the token |
## Ignore the token |
| 4658 |
!!!next-token; |
!!!next-token; |
| 4659 |
next B; |
next B; |
| 4662 |
} |
} |
| 4663 |
} elsif ($token->{tag_name} eq 'p') { |
} elsif ($token->{tag_name} eq 'p') { |
| 4664 |
!!!cp ('t142'); |
!!!cp ('t142'); |
| 4665 |
!!!parse-error (type => 'unmatched end tag:p', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4666 |
|
text => $token->{tag_name}, token => $token); |
| 4667 |
## Ignore the token |
## Ignore the token |
| 4668 |
!!!next-token; |
!!!next-token; |
| 4669 |
next B; |
next B; |
| 4686 |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4687 |
!!!cp ('t143.3'); |
!!!cp ('t143.3'); |
| 4688 |
## ISSUE: Two parse errors for <head><noscript></br> |
## ISSUE: Two parse errors for <head><noscript></br> |
| 4689 |
!!!parse-error (type => 'unmatched end tag:br', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4690 |
|
text => 'br', token => $token); |
| 4691 |
## As if </noscript> |
## As if </noscript> |
| 4692 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4693 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4706 |
} |
} |
| 4707 |
|
|
| 4708 |
## ISSUE: does not agree with IE7 - it doesn't ignore </br>. |
## ISSUE: does not agree with IE7 - it doesn't ignore </br>. |
| 4709 |
!!!parse-error (type => 'unmatched end tag:br', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4710 |
|
text => 'br', token => $token); |
| 4711 |
## Ignore the token |
## Ignore the token |
| 4712 |
!!!next-token; |
!!!next-token; |
| 4713 |
next B; |
next B; |
| 4714 |
} else { |
} else { |
| 4715 |
!!!cp ('t145'); |
!!!cp ('t145'); |
| 4716 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4717 |
|
text => $token->{tag_name}, token => $token); |
| 4718 |
## Ignore the token |
## Ignore the token |
| 4719 |
!!!next-token; |
!!!next-token; |
| 4720 |
next B; |
next B; |
| 4724 |
!!!cp ('t146'); |
!!!cp ('t146'); |
| 4725 |
## As if </noscript> |
## As if </noscript> |
| 4726 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4727 |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in noscript:/', |
| 4728 |
|
text => $token->{tag_name}, token => $token); |
| 4729 |
|
|
| 4730 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4731 |
## As if </head> |
## As if </head> |
| 4741 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4742 |
## ISSUE: This case cannot be reached? |
## ISSUE: This case cannot be reached? |
| 4743 |
!!!cp ('t148'); |
!!!cp ('t148'); |
| 4744 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4745 |
|
text => $token->{tag_name}, token => $token); |
| 4746 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 4747 |
!!!next-token; |
!!!next-token; |
| 4748 |
next B; |
next B; |
| 4853 |
|
|
| 4854 |
!!!cp ('t153'); |
!!!cp ('t153'); |
| 4855 |
!!!parse-error (type => 'start tag not allowed', |
!!!parse-error (type => 'start tag not allowed', |
| 4856 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 4857 |
## Ignore the token |
## Ignore the token |
| 4858 |
!!!nack ('t153.1'); |
!!!nack ('t153.1'); |
| 4859 |
!!!next-token; |
!!!next-token; |
| 4860 |
next B; |
next B; |
| 4861 |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 4862 |
!!!parse-error (type => 'not closed:caption', token => $token); |
!!!parse-error (type => 'not closed', text => 'caption', |
| 4863 |
|
token => $token); |
| 4864 |
|
|
| 4865 |
## NOTE: As if </caption>. |
## NOTE: As if </caption>. |
| 4866 |
## have a table element in table scope |
## have a table element in table scope |
| 4880 |
|
|
| 4881 |
!!!cp ('t157'); |
!!!cp ('t157'); |
| 4882 |
!!!parse-error (type => 'start tag not allowed', |
!!!parse-error (type => 'start tag not allowed', |
| 4883 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 4884 |
## Ignore the token |
## Ignore the token |
| 4885 |
!!!nack ('t157.1'); |
!!!nack ('t157.1'); |
| 4886 |
!!!next-token; |
!!!next-token; |
| 4897 |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
| 4898 |
!!!cp ('t159'); |
!!!cp ('t159'); |
| 4899 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 4900 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 4901 |
->manakai_local_name, |
->manakai_local_name, |
| 4902 |
token => $token); |
token => $token); |
| 4903 |
} else { |
} else { |
| 4939 |
} # INSCOPE |
} # INSCOPE |
| 4940 |
unless (defined $i) { |
unless (defined $i) { |
| 4941 |
!!!cp ('t165'); |
!!!cp ('t165'); |
| 4942 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4943 |
|
text => $token->{tag_name}, |
| 4944 |
|
token => $token); |
| 4945 |
## Ignore the token |
## Ignore the token |
| 4946 |
!!!next-token; |
!!!next-token; |
| 4947 |
next B; |
next B; |
| 4958 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 4959 |
!!!cp ('t167'); |
!!!cp ('t167'); |
| 4960 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 4961 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 4962 |
->manakai_local_name, |
->manakai_local_name, |
| 4963 |
token => $token); |
token => $token); |
| 4964 |
} else { |
} else { |
| 4975 |
next B; |
next B; |
| 4976 |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 4977 |
!!!cp ('t169'); |
!!!cp ('t169'); |
| 4978 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4979 |
|
text => $token->{tag_name}, token => $token); |
| 4980 |
## Ignore the token |
## Ignore the token |
| 4981 |
!!!next-token; |
!!!next-token; |
| 4982 |
next B; |
next B; |
| 5003 |
|
|
| 5004 |
!!!cp ('t173'); |
!!!cp ('t173'); |
| 5005 |
!!!parse-error (type => 'unmatched end tag', |
!!!parse-error (type => 'unmatched end tag', |
| 5006 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 5007 |
## Ignore the token |
## Ignore the token |
| 5008 |
!!!next-token; |
!!!next-token; |
| 5009 |
next B; |
next B; |
| 5019 |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
| 5020 |
!!!cp ('t175'); |
!!!cp ('t175'); |
| 5021 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5022 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5023 |
->manakai_local_name, |
->manakai_local_name, |
| 5024 |
token => $token); |
token => $token); |
| 5025 |
} else { |
} else { |
| 5036 |
next B; |
next B; |
| 5037 |
} elsif ($self->{insertion_mode} == IN_CELL_IM) { |
} elsif ($self->{insertion_mode} == IN_CELL_IM) { |
| 5038 |
!!!cp ('t177'); |
!!!cp ('t177'); |
| 5039 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5040 |
|
text => $token->{tag_name}, token => $token); |
| 5041 |
## Ignore the token |
## Ignore the token |
| 5042 |
!!!next-token; |
!!!next-token; |
| 5043 |
next B; |
next B; |
| 5080 |
|
|
| 5081 |
!!!cp ('t182'); |
!!!cp ('t182'); |
| 5082 |
!!!parse-error (type => 'unmatched end tag', |
!!!parse-error (type => 'unmatched end tag', |
| 5083 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 5084 |
## Ignore the token |
## Ignore the token |
| 5085 |
!!!next-token; |
!!!next-token; |
| 5086 |
next B; |
next B; |
| 5087 |
} # INSCOPE |
} # INSCOPE |
| 5088 |
} elsif ($token->{tag_name} eq 'table' and |
} elsif ($token->{tag_name} eq 'table' and |
| 5089 |
$self->{insertion_mode} == IN_CAPTION_IM) { |
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 5090 |
!!!parse-error (type => 'not closed:caption', token => $token); |
!!!parse-error (type => 'not closed', text => 'caption', |
| 5091 |
|
token => $token); |
| 5092 |
|
|
| 5093 |
## As if </caption> |
## As if </caption> |
| 5094 |
## have a table element in table scope |
## have a table element in table scope |
| 5106 |
} # INSCOPE |
} # INSCOPE |
| 5107 |
unless (defined $i) { |
unless (defined $i) { |
| 5108 |
!!!cp ('t186'); |
!!!cp ('t186'); |
| 5109 |
!!!parse-error (type => 'unmatched end tag:caption', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5110 |
|
text => 'caption', token => $token); |
| 5111 |
## Ignore the token |
## Ignore the token |
| 5112 |
!!!next-token; |
!!!next-token; |
| 5113 |
next B; |
next B; |
| 5122 |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
| 5123 |
!!!cp ('t188'); |
!!!cp ('t188'); |
| 5124 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5125 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5126 |
->manakai_local_name, |
->manakai_local_name, |
| 5127 |
token => $token); |
token => $token); |
| 5128 |
} else { |
} else { |
| 5142 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5143 |
if ($self->{insertion_mode} & BODY_TABLE_IMS) { |
if ($self->{insertion_mode} & BODY_TABLE_IMS) { |
| 5144 |
!!!cp ('t190'); |
!!!cp ('t190'); |
| 5145 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5146 |
|
text => $token->{tag_name}, token => $token); |
| 5147 |
## Ignore the token |
## Ignore the token |
| 5148 |
!!!next-token; |
!!!next-token; |
| 5149 |
next B; |
next B; |
| 5157 |
}->{$token->{tag_name}} and |
}->{$token->{tag_name}} and |
| 5158 |
$self->{insertion_mode} == IN_CAPTION_IM) { |
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 5159 |
!!!cp ('t192'); |
!!!cp ('t192'); |
| 5160 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5161 |
|
text => $token->{tag_name}, token => $token); |
| 5162 |
## Ignore the token |
## Ignore the token |
| 5163 |
!!!next-token; |
!!!next-token; |
| 5164 |
next B; |
next B; |
| 5198 |
} |
} |
| 5199 |
} |
} |
| 5200 |
|
|
| 5201 |
!!!parse-error (type => 'in table:#character', token => $token); |
!!!parse-error (type => 'in table:#text', token => $token); |
| 5202 |
|
|
| 5203 |
## As if in body, but insert into foster parent element |
## As if in body, but insert into foster parent element |
| 5204 |
## ISSUE: Spec says that "whenever a node would be inserted |
## ISSUE: Spec says that "whenever a node would be inserted |
| 5249 |
!!!next-token; |
!!!next-token; |
| 5250 |
next B; |
next B; |
| 5251 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 5252 |
if ({ |
if ({ |
| 5253 |
tr => ($self->{insertion_mode} != IN_ROW_IM), |
tr => ($self->{insertion_mode} != IN_ROW_IM), |
| 5254 |
th => 1, td => 1, |
th => 1, td => 1, |
| 5255 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5256 |
if ($self->{insertion_mode} == IN_TABLE_IM) { |
if ($self->{insertion_mode} == IN_TABLE_IM) { |
| 5257 |
## Clear back to table context |
## Clear back to table context |
| 5258 |
while (not ($self->{open_elements}->[-1]->[1] |
while (not ($self->{open_elements}->[-1]->[1] |
| 5259 |
& TABLE_SCOPING_EL)) { |
& TABLE_SCOPING_EL)) { |
| 5260 |
!!!cp ('t201'); |
!!!cp ('t201'); |
| 5261 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5262 |
} |
} |
| 5263 |
|
|
| 5264 |
!!!insert-element ('tbody',, $token); |
!!!insert-element ('tbody',, $token); |
| 5265 |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 5266 |
## reprocess in the "in table body" insertion mode... |
## reprocess in the "in table body" insertion mode... |
| 5267 |
} |
} |
| 5268 |
|
|
| 5269 |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
| 5270 |
unless ($token->{tag_name} eq 'tr') { |
unless ($token->{tag_name} eq 'tr') { |
| 5271 |
!!!cp ('t202'); |
!!!cp ('t202'); |
| 5272 |
!!!parse-error (type => 'missing start tag:tr', token => $token); |
!!!parse-error (type => 'missing start tag:tr', token => $token); |
| 5273 |
} |
} |
| 5274 |
|
|
| 5275 |
## Clear back to table body context |
## Clear back to table body context |
| 5276 |
while (not ($self->{open_elements}->[-1]->[1] |
while (not ($self->{open_elements}->[-1]->[1] |
| 5277 |
& TABLE_ROWS_SCOPING_EL)) { |
& TABLE_ROWS_SCOPING_EL)) { |
| 5278 |
!!!cp ('t203'); |
!!!cp ('t203'); |
| 5279 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
| 5280 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5281 |
} |
} |
| 5282 |
|
|
| 5283 |
$self->{insertion_mode} = IN_ROW_IM; |
$self->{insertion_mode} = IN_ROW_IM; |
| 5284 |
if ($token->{tag_name} eq 'tr') { |
if ($token->{tag_name} eq 'tr') { |
| 5334 |
unless (defined $i) { |
unless (defined $i) { |
| 5335 |
!!!cp ('t210'); |
!!!cp ('t210'); |
| 5336 |
## TODO: This type is wrong. |
## TODO: This type is wrong. |
| 5337 |
!!!parse-error (type => 'unmacthed end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmacthed end tag', |
| 5338 |
|
text => $token->{tag_name}, token => $token); |
| 5339 |
## Ignore the token |
## Ignore the token |
| 5340 |
!!!nack ('t210.1'); |
!!!nack ('t210.1'); |
| 5341 |
!!!next-token; |
!!!next-token; |
| 5379 |
} # INSCOPE |
} # INSCOPE |
| 5380 |
unless (defined $i) { |
unless (defined $i) { |
| 5381 |
!!!cp ('t216'); |
!!!cp ('t216'); |
| 5382 |
## TODO: This erorr type ios wrong. |
## TODO: This erorr type is wrong. |
| 5383 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5384 |
|
text => $token->{tag_name}, token => $token); |
| 5385 |
## Ignore the token |
## Ignore the token |
| 5386 |
!!!nack ('t216.1'); |
!!!nack ('t216.1'); |
| 5387 |
!!!next-token; |
!!!next-token; |
| 5456 |
} |
} |
| 5457 |
} elsif ($token->{tag_name} eq 'table') { |
} elsif ($token->{tag_name} eq 'table') { |
| 5458 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5459 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5460 |
->manakai_local_name, |
->manakai_local_name, |
| 5461 |
token => $token); |
token => $token); |
| 5462 |
|
|
| 5477 |
unless (defined $i) { |
unless (defined $i) { |
| 5478 |
!!!cp ('t223'); |
!!!cp ('t223'); |
| 5479 |
## TODO: The following is wrong, maybe. |
## TODO: The following is wrong, maybe. |
| 5480 |
!!!parse-error (type => 'unmatched end tag:table', token => $token); |
!!!parse-error (type => 'unmatched end tag', text => 'table', |
| 5481 |
|
token => $token); |
| 5482 |
## Ignore tokens </table><table> |
## Ignore tokens </table><table> |
| 5483 |
!!!nack ('t223.1'); |
!!!nack ('t223.1'); |
| 5484 |
!!!next-token; |
!!!next-token; |
| 5485 |
next B; |
next B; |
| 5486 |
} |
} |
| 5487 |
|
|
| 5488 |
## TODO: Followings are removed from the latest spec. |
## TODO: Followings are removed from the latest spec. |
| 5489 |
## generate implied end tags |
## generate implied end tags |
| 5490 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 5491 |
!!!cp ('t224'); |
!!!cp ('t224'); |
| 5496 |
!!!cp ('t225'); |
!!!cp ('t225'); |
| 5497 |
## NOTE: |<table><tr><table>| |
## NOTE: |<table><tr><table>| |
| 5498 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5499 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5500 |
->manakai_local_name, |
->manakai_local_name, |
| 5501 |
token => $token); |
token => $token); |
| 5502 |
} else { |
} else { |
| 5537 |
my $type = lc $token->{attributes}->{type}->{value}; |
my $type = lc $token->{attributes}->{type}->{value}; |
| 5538 |
if ($type eq 'hidden') { |
if ($type eq 'hidden') { |
| 5539 |
!!!cp ('t227.3'); |
!!!cp ('t227.3'); |
| 5540 |
!!!parse-error (type => 'in table:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in table', |
| 5541 |
|
text => $token->{tag_name}, token => $token); |
| 5542 |
|
|
| 5543 |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5544 |
|
|
| 5566 |
# |
# |
| 5567 |
} |
} |
| 5568 |
|
|
| 5569 |
!!!parse-error (type => 'in table:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in table', text => $token->{tag_name}, |
| 5570 |
|
token => $token); |
| 5571 |
|
|
| 5572 |
$insert = $insert_to_foster; |
$insert = $insert_to_foster; |
| 5573 |
# |
# |
| 5589 |
} # INSCOPE |
} # INSCOPE |
| 5590 |
unless (defined $i) { |
unless (defined $i) { |
| 5591 |
!!!cp ('t230'); |
!!!cp ('t230'); |
| 5592 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5593 |
|
text => $token->{tag_name}, token => $token); |
| 5594 |
## Ignore the token |
## Ignore the token |
| 5595 |
!!!nack ('t230.1'); |
!!!nack ('t230.1'); |
| 5596 |
!!!next-token; |
!!!next-token; |
| 5631 |
unless (defined $i) { |
unless (defined $i) { |
| 5632 |
!!!cp ('t235'); |
!!!cp ('t235'); |
| 5633 |
## TODO: The following is wrong. |
## TODO: The following is wrong. |
| 5634 |
!!!parse-error (type => 'unmatched end tag:'.$token->{type}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5635 |
|
text => $token->{type}, token => $token); |
| 5636 |
## Ignore the token |
## Ignore the token |
| 5637 |
!!!nack ('t236.1'); |
!!!nack ('t236.1'); |
| 5638 |
!!!next-token; |
!!!next-token; |
| 5668 |
} # INSCOPE |
} # INSCOPE |
| 5669 |
unless (defined $i) { |
unless (defined $i) { |
| 5670 |
!!!cp ('t239'); |
!!!cp ('t239'); |
| 5671 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5672 |
|
text => $token->{tag_name}, token => $token); |
| 5673 |
## Ignore the token |
## Ignore the token |
| 5674 |
!!!nack ('t239.1'); |
!!!nack ('t239.1'); |
| 5675 |
!!!next-token; |
!!!next-token; |
| 5715 |
} # INSCOPE |
} # INSCOPE |
| 5716 |
unless (defined $i) { |
unless (defined $i) { |
| 5717 |
!!!cp ('t243'); |
!!!cp ('t243'); |
| 5718 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5719 |
|
text => $token->{tag_name}, token => $token); |
| 5720 |
## Ignore the token |
## Ignore the token |
| 5721 |
!!!nack ('t243.1'); |
!!!nack ('t243.1'); |
| 5722 |
!!!next-token; |
!!!next-token; |
| 5750 |
} # INSCOPE |
} # INSCOPE |
| 5751 |
unless (defined $i) { |
unless (defined $i) { |
| 5752 |
!!!cp ('t249'); |
!!!cp ('t249'); |
| 5753 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5754 |
|
text => $token->{tag_name}, token => $token); |
| 5755 |
## Ignore the token |
## Ignore the token |
| 5756 |
!!!nack ('t249.1'); |
!!!nack ('t249.1'); |
| 5757 |
!!!next-token; |
!!!next-token; |
| 5774 |
} # INSCOPE |
} # INSCOPE |
| 5775 |
unless (defined $i) { |
unless (defined $i) { |
| 5776 |
!!!cp ('t252'); |
!!!cp ('t252'); |
| 5777 |
!!!parse-error (type => 'unmatched end tag:tr', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5778 |
|
text => 'tr', token => $token); |
| 5779 |
## Ignore the token |
## Ignore the token |
| 5780 |
!!!nack ('t252.1'); |
!!!nack ('t252.1'); |
| 5781 |
!!!next-token; |
!!!next-token; |
| 5810 |
} # INSCOPE |
} # INSCOPE |
| 5811 |
unless (defined $i) { |
unless (defined $i) { |
| 5812 |
!!!cp ('t256'); |
!!!cp ('t256'); |
| 5813 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5814 |
|
text => $token->{tag_name}, token => $token); |
| 5815 |
## Ignore the token |
## Ignore the token |
| 5816 |
!!!nack ('t256.1'); |
!!!nack ('t256.1'); |
| 5817 |
!!!next-token; |
!!!next-token; |
| 5838 |
tbody => 1, tfoot => 1, thead => 1, # $self->{insertion_mode} == IN_TABLE_IM |
tbody => 1, tfoot => 1, thead => 1, # $self->{insertion_mode} == IN_TABLE_IM |
| 5839 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5840 |
!!!cp ('t258'); |
!!!cp ('t258'); |
| 5841 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5842 |
|
text => $token->{tag_name}, token => $token); |
| 5843 |
## Ignore the token |
## Ignore the token |
| 5844 |
!!!nack ('t258.1'); |
!!!nack ('t258.1'); |
| 5845 |
!!!next-token; |
!!!next-token; |
| 5846 |
next B; |
next B; |
| 5847 |
} else { |
} else { |
| 5848 |
!!!cp ('t259'); |
!!!cp ('t259'); |
| 5849 |
!!!parse-error (type => 'in table:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in table:/', |
| 5850 |
|
text => $token->{tag_name}, token => $token); |
| 5851 |
|
|
| 5852 |
$insert = $insert_to_foster; |
$insert = $insert_to_foster; |
| 5853 |
# |
# |
| 5897 |
if ($token->{tag_name} eq 'colgroup') { |
if ($token->{tag_name} eq 'colgroup') { |
| 5898 |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
| 5899 |
!!!cp ('t264'); |
!!!cp ('t264'); |
| 5900 |
!!!parse-error (type => 'unmatched end tag:colgroup', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5901 |
|
text => 'colgroup', token => $token); |
| 5902 |
## Ignore the token |
## Ignore the token |
| 5903 |
!!!next-token; |
!!!next-token; |
| 5904 |
next B; |
next B; |
| 5911 |
} |
} |
| 5912 |
} elsif ($token->{tag_name} eq 'col') { |
} elsif ($token->{tag_name} eq 'col') { |
| 5913 |
!!!cp ('t266'); |
!!!cp ('t266'); |
| 5914 |
!!!parse-error (type => 'unmatched end tag:col', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5915 |
|
text => 'col', token => $token); |
| 5916 |
## Ignore the token |
## Ignore the token |
| 5917 |
!!!next-token; |
!!!next-token; |
| 5918 |
next B; |
next B; |
| 5942 |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
| 5943 |
!!!cp ('t269'); |
!!!cp ('t269'); |
| 5944 |
## TODO: Wrong error type? |
## TODO: Wrong error type? |
| 5945 |
!!!parse-error (type => 'unmatched end tag:colgroup', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5946 |
|
text => 'colgroup', token => $token); |
| 5947 |
## Ignore the token |
## Ignore the token |
| 5948 |
!!!nack ('t269.1'); |
!!!nack ('t269.1'); |
| 5949 |
!!!next-token; |
!!!next-token; |
| 5997 |
!!!nack ('t277.1'); |
!!!nack ('t277.1'); |
| 5998 |
!!!next-token; |
!!!next-token; |
| 5999 |
next B; |
next B; |
| 6000 |
} elsif ($token->{tag_name} eq 'select' or |
} elsif ({ |
| 6001 |
$token->{tag_name} eq 'input' or |
select => 1, input => 1, textarea => 1, |
| 6002 |
|
}->{$token->{tag_name}} or |
| 6003 |
($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
| 6004 |
{ |
{ |
| 6005 |
caption => 1, table => 1, |
caption => 1, table => 1, |
| 6007 |
tr => 1, td => 1, th => 1, |
tr => 1, td => 1, th => 1, |
| 6008 |
}->{$token->{tag_name}})) { |
}->{$token->{tag_name}})) { |
| 6009 |
## TODO: The type below is not good - <select> is replaced by </select> |
## TODO: The type below is not good - <select> is replaced by </select> |
| 6010 |
!!!parse-error (type => 'not closed:select', token => $token); |
!!!parse-error (type => 'not closed', text => 'select', |
| 6011 |
|
token => $token); |
| 6012 |
## NOTE: As if the token were </select> (<select> case) or |
## NOTE: As if the token were </select> (<select> case) or |
| 6013 |
## as if there were </select> (otherwise). |
## as if there were </select> (otherwise). |
| 6014 |
## have an element in table scope |
## have an element in table scope |
| 6026 |
} # INSCOPE |
} # INSCOPE |
| 6027 |
unless (defined $i) { |
unless (defined $i) { |
| 6028 |
!!!cp ('t280'); |
!!!cp ('t280'); |
| 6029 |
!!!parse-error (type => 'unmatched end tag:select', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6030 |
|
text => 'select', token => $token); |
| 6031 |
## Ignore the token |
## Ignore the token |
| 6032 |
!!!nack ('t280.1'); |
!!!nack ('t280.1'); |
| 6033 |
!!!next-token; |
!!!next-token; |
| 6051 |
} |
} |
| 6052 |
} else { |
} else { |
| 6053 |
!!!cp ('t282'); |
!!!cp ('t282'); |
| 6054 |
!!!parse-error (type => 'in select:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in select', |
| 6055 |
|
text => $token->{tag_name}, token => $token); |
| 6056 |
## Ignore the token |
## Ignore the token |
| 6057 |
!!!nack ('t282.1'); |
!!!nack ('t282.1'); |
| 6058 |
!!!next-token; |
!!!next-token; |
| 6070 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 6071 |
} else { |
} else { |
| 6072 |
!!!cp ('t285'); |
!!!cp ('t285'); |
| 6073 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6074 |
|
text => $token->{tag_name}, token => $token); |
| 6075 |
## Ignore the token |
## Ignore the token |
| 6076 |
} |
} |
| 6077 |
!!!nack ('t285.1'); |
!!!nack ('t285.1'); |
| 6083 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 6084 |
} else { |
} else { |
| 6085 |
!!!cp ('t287'); |
!!!cp ('t287'); |
| 6086 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6087 |
|
text => $token->{tag_name}, token => $token); |
| 6088 |
## Ignore the token |
## Ignore the token |
| 6089 |
} |
} |
| 6090 |
!!!nack ('t287.1'); |
!!!nack ('t287.1'); |
| 6106 |
} # INSCOPE |
} # INSCOPE |
| 6107 |
unless (defined $i) { |
unless (defined $i) { |
| 6108 |
!!!cp ('t290'); |
!!!cp ('t290'); |
| 6109 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6110 |
|
text => $token->{tag_name}, token => $token); |
| 6111 |
## Ignore the token |
## Ignore the token |
| 6112 |
!!!nack ('t290.1'); |
!!!nack ('t290.1'); |
| 6113 |
!!!next-token; |
!!!next-token; |
| 6128 |
tfoot => 1, thead => 1, tr => 1, td => 1, th => 1, |
tfoot => 1, thead => 1, tr => 1, td => 1, th => 1, |
| 6129 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6130 |
## TODO: The following is wrong? |
## TODO: The following is wrong? |
| 6131 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6132 |
|
text => $token->{tag_name}, token => $token); |
| 6133 |
|
|
| 6134 |
## have an element in table scope |
## have an element in table scope |
| 6135 |
my $i; |
my $i; |
| 6170 |
unless (defined $i) { |
unless (defined $i) { |
| 6171 |
!!!cp ('t297'); |
!!!cp ('t297'); |
| 6172 |
## TODO: The following error type is correct? |
## TODO: The following error type is correct? |
| 6173 |
!!!parse-error (type => 'unmatched end tag:select', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6174 |
|
text => 'select', token => $token); |
| 6175 |
## Ignore the </select> token |
## Ignore the </select> token |
| 6176 |
!!!nack ('t297.1'); |
!!!nack ('t297.1'); |
| 6177 |
!!!next-token; ## TODO: ok? |
!!!next-token; ## TODO: ok? |
| 6188 |
next B; |
next B; |
| 6189 |
} else { |
} else { |
| 6190 |
!!!cp ('t299'); |
!!!cp ('t299'); |
| 6191 |
!!!parse-error (type => 'in select:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in select:/', |
| 6192 |
|
text => $token->{tag_name}, token => $token); |
| 6193 |
## Ignore the token |
## Ignore the token |
| 6194 |
!!!nack ('t299.3'); |
!!!nack ('t299.3'); |
| 6195 |
!!!next-token; |
!!!next-token; |
| 6227 |
|
|
| 6228 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 6229 |
!!!cp ('t301'); |
!!!cp ('t301'); |
| 6230 |
!!!parse-error (type => 'after html:#character', token => $token); |
!!!parse-error (type => 'after html:#text', token => $token); |
| 6231 |
|
|
| 6232 |
## Reprocess in the "after body" insertion mode. |
## Reprocess in the "after body" insertion mode. |
| 6233 |
} else { |
} else { |
| 6235 |
} |
} |
| 6236 |
|
|
| 6237 |
## "after body" insertion mode |
## "after body" insertion mode |
| 6238 |
!!!parse-error (type => 'after body:#character', token => $token); |
!!!parse-error (type => 'after body:#text', token => $token); |
| 6239 |
|
|
| 6240 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 6241 |
## reprocess |
## reprocess |
| 6243 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 6244 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 6245 |
!!!cp ('t303'); |
!!!cp ('t303'); |
| 6246 |
!!!parse-error (type => 'after html:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after html', |
| 6247 |
|
text => $token->{tag_name}, token => $token); |
| 6248 |
|
|
| 6249 |
## Reprocess in the "after body" insertion mode. |
## Reprocess in the "after body" insertion mode. |
| 6250 |
} else { |
} else { |
| 6252 |
} |
} |
| 6253 |
|
|
| 6254 |
## "after body" insertion mode |
## "after body" insertion mode |
| 6255 |
!!!parse-error (type => 'after body:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after body', |
| 6256 |
|
text => $token->{tag_name}, token => $token); |
| 6257 |
|
|
| 6258 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 6259 |
!!!ack-later; |
!!!ack-later; |
| 6262 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 6263 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 6264 |
!!!cp ('t305'); |
!!!cp ('t305'); |
| 6265 |
!!!parse-error (type => 'after html:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after html:/', |
| 6266 |
|
text => $token->{tag_name}, token => $token); |
| 6267 |
|
|
| 6268 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 6269 |
## Reprocess in the "after body" insertion mode. |
## Reprocess in the "after body" insertion mode. |
| 6275 |
if ($token->{tag_name} eq 'html') { |
if ($token->{tag_name} eq 'html') { |
| 6276 |
if (defined $self->{inner_html_node}) { |
if (defined $self->{inner_html_node}) { |
| 6277 |
!!!cp ('t307'); |
!!!cp ('t307'); |
| 6278 |
!!!parse-error (type => 'unmatched end tag:html', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6279 |
|
text => 'html', token => $token); |
| 6280 |
## Ignore the token |
## Ignore the token |
| 6281 |
!!!next-token; |
!!!next-token; |
| 6282 |
next B; |
next B; |
| 6288 |
} |
} |
| 6289 |
} else { |
} else { |
| 6290 |
!!!cp ('t309'); |
!!!cp ('t309'); |
| 6291 |
!!!parse-error (type => 'after body:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after body:/', |
| 6292 |
|
text => $token->{tag_name}, token => $token); |
| 6293 |
|
|
| 6294 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 6295 |
## reprocess |
## reprocess |
| 6317 |
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
| 6318 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6319 |
!!!cp ('t311'); |
!!!cp ('t311'); |
| 6320 |
!!!parse-error (type => 'in frameset:#character', token => $token); |
!!!parse-error (type => 'in frameset:#text', token => $token); |
| 6321 |
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 6322 |
!!!cp ('t312'); |
!!!cp ('t312'); |
| 6323 |
!!!parse-error (type => 'after frameset:#character', token => $token); |
!!!parse-error (type => 'after frameset:#text', token => $token); |
| 6324 |
} else { # "after html frameset" |
} else { # "after after frameset" |
| 6325 |
!!!cp ('t313'); |
!!!cp ('t313'); |
| 6326 |
!!!parse-error (type => 'after html:#character', token => $token); |
!!!parse-error (type => 'after html:#text', token => $token); |
|
|
|
|
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
|
|
## Reprocess in the "after frameset" insertion mode. |
|
|
!!!parse-error (type => 'after frameset:#character', token => $token); |
|
| 6327 |
} |
} |
| 6328 |
|
|
| 6329 |
## Ignore the token. |
## Ignore the token. |
| 6339 |
|
|
| 6340 |
die qq[$0: Character "$token->{data}"]; |
die qq[$0: Character "$token->{data}"]; |
| 6341 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
|
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
|
|
!!!cp ('t316'); |
|
|
!!!parse-error (type => 'after html:'.$token->{tag_name}, token => $token); |
|
|
|
|
|
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
|
|
## Process in the "after frameset" insertion mode. |
|
|
} else { |
|
|
!!!cp ('t317'); |
|
|
} |
|
|
|
|
| 6342 |
if ($token->{tag_name} eq 'frameset' and |
if ($token->{tag_name} eq 'frameset' and |
| 6343 |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6344 |
!!!cp ('t318'); |
!!!cp ('t318'); |
| 6356 |
next B; |
next B; |
| 6357 |
} elsif ($token->{tag_name} eq 'noframes') { |
} elsif ($token->{tag_name} eq 'noframes') { |
| 6358 |
!!!cp ('t320'); |
!!!cp ('t320'); |
| 6359 |
## NOTE: As if in body. |
## NOTE: As if in head. |
| 6360 |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 6361 |
next B; |
next B; |
| 6362 |
|
|
| 6363 |
|
## NOTE: |<!DOCTYPE HTML><frameset></frameset></html><noframes></noframes>| |
| 6364 |
|
## has no parse error. |
| 6365 |
} else { |
} else { |
| 6366 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6367 |
!!!cp ('t321'); |
!!!cp ('t321'); |
| 6368 |
!!!parse-error (type => 'in frameset:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in frameset', |
| 6369 |
} else { |
text => $token->{tag_name}, token => $token); |
| 6370 |
|
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 6371 |
!!!cp ('t322'); |
!!!cp ('t322'); |
| 6372 |
!!!parse-error (type => 'after frameset:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after frameset', |
| 6373 |
|
text => $token->{tag_name}, token => $token); |
| 6374 |
|
} else { # "after after frameset" |
| 6375 |
|
!!!cp ('t322.2'); |
| 6376 |
|
!!!parse-error (type => 'after after frameset', |
| 6377 |
|
text => $token->{tag_name}, token => $token); |
| 6378 |
} |
} |
| 6379 |
## Ignore the token |
## Ignore the token |
| 6380 |
!!!nack ('t322.1'); |
!!!nack ('t322.1'); |
| 6382 |
next B; |
next B; |
| 6383 |
} |
} |
| 6384 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
|
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
|
|
!!!cp ('t323'); |
|
|
!!!parse-error (type => 'after html:/'.$token->{tag_name}, token => $token); |
|
|
|
|
|
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
|
|
## Process in the "after frameset" insertion mode. |
|
|
} else { |
|
|
!!!cp ('t324'); |
|
|
} |
|
|
|
|
| 6385 |
if ($token->{tag_name} eq 'frameset' and |
if ($token->{tag_name} eq 'frameset' and |
| 6386 |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6387 |
if ($self->{open_elements}->[-1]->[1] & HTML_EL and |
if ($self->{open_elements}->[-1]->[1] & HTML_EL and |
| 6388 |
@{$self->{open_elements}} == 1) { |
@{$self->{open_elements}} == 1) { |
| 6389 |
!!!cp ('t325'); |
!!!cp ('t325'); |
| 6390 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6391 |
|
text => $token->{tag_name}, token => $token); |
| 6392 |
## Ignore the token |
## Ignore the token |
| 6393 |
!!!next-token; |
!!!next-token; |
| 6394 |
} else { |
} else { |
| 6414 |
} else { |
} else { |
| 6415 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6416 |
!!!cp ('t330'); |
!!!cp ('t330'); |
| 6417 |
!!!parse-error (type => 'in frameset:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in frameset:/', |
| 6418 |
} else { |
text => $token->{tag_name}, token => $token); |
| 6419 |
|
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 6420 |
|
!!!cp ('t330.1'); |
| 6421 |
|
!!!parse-error (type => 'after frameset:/', |
| 6422 |
|
text => $token->{tag_name}, token => $token); |
| 6423 |
|
} else { # "after after html" |
| 6424 |
!!!cp ('t331'); |
!!!cp ('t331'); |
| 6425 |
!!!parse-error (type => 'after frameset:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after after frameset:/', |
| 6426 |
|
text => $token->{tag_name}, token => $token); |
| 6427 |
} |
} |
| 6428 |
## Ignore the token |
## Ignore the token |
| 6429 |
!!!next-token; |
!!!next-token; |
| 6490 |
->{has_reference}); |
->{has_reference}); |
| 6491 |
} elsif ($token->{attributes}->{content}) { |
} elsif ($token->{attributes}->{content}) { |
| 6492 |
if ($token->{attributes}->{content}->{value} |
if ($token->{attributes}->{content}->{value} |
| 6493 |
=~ /\A[^;]*;[\x09-\x0D\x20]*[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
=~ /[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
| 6494 |
[\x09-\x0D\x20]*= |
[\x09-\x0D\x20]*= |
| 6495 |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
| 6496 |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20\x3B]*))/x) { |
| 6497 |
!!!cp ('t336'); |
!!!cp ('t336'); |
| 6498 |
## NOTE: Whether the encoding is supported or not is handled |
## NOTE: Whether the encoding is supported or not is handled |
| 6499 |
## in the {change_encoding} callback. |
## in the {change_encoding} callback. |
| 6531 |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
| 6532 |
next B; |
next B; |
| 6533 |
} elsif ($token->{tag_name} eq 'body') { |
} elsif ($token->{tag_name} eq 'body') { |
| 6534 |
!!!parse-error (type => 'in body:body', token => $token); |
!!!parse-error (type => 'in body', text => 'body', token => $token); |
| 6535 |
|
|
| 6536 |
if (@{$self->{open_elements}} == 1 or |
if (@{$self->{open_elements}} == 1 or |
| 6537 |
not ($self->{open_elements}->[1]->[1] & BODY_EL)) { |
not ($self->{open_elements}->[1]->[1] & BODY_EL)) { |
| 6651 |
if ($i != -1) { |
if ($i != -1) { |
| 6652 |
!!!cp ('t355'); |
!!!cp ('t355'); |
| 6653 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 6654 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 6655 |
->manakai_local_name, |
->manakai_local_name, |
| 6656 |
token => $token); |
token => $token); |
| 6657 |
} else { |
} else { |
| 6805 |
xmp => 1, |
xmp => 1, |
| 6806 |
iframe => 1, |
iframe => 1, |
| 6807 |
noembed => 1, |
noembed => 1, |
| 6808 |
noframes => 1, |
noframes => 1, ## NOTE: This is an "as if in head" code clone. |
| 6809 |
noscript => 0, ## TODO: 1 if scripting is enabled |
noscript => 0, ## TODO: 1 if scripting is enabled |
| 6810 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6811 |
if ($token->{tag_name} eq 'xmp') { |
if ($token->{tag_name} eq 'xmp') { |
| 6827 |
!!!next-token; |
!!!next-token; |
| 6828 |
next B; |
next B; |
| 6829 |
} else { |
} else { |
| 6830 |
|
!!!ack ('t391.1'); |
| 6831 |
|
|
| 6832 |
my $at = $token->{attributes}; |
my $at = $token->{attributes}; |
| 6833 |
my $form_attrs; |
my $form_attrs; |
| 6834 |
$form_attrs->{action} = $at->{action} if $at->{action}; |
$form_attrs->{action} = $at->{action} if $at->{action}; |
| 6872 |
line => $token->{line}, column => $token->{column}}, |
line => $token->{line}, column => $token->{column}}, |
| 6873 |
{type => END_TAG_TOKEN, tag_name => 'form', |
{type => END_TAG_TOKEN, tag_name => 'form', |
| 6874 |
line => $token->{line}, column => $token->{column}}; |
line => $token->{line}, column => $token->{column}}; |
|
!!!nack ('t391.1'); ## NOTE: Not acknowledged. |
|
| 6875 |
!!!back-token (@tokens); |
!!!back-token (@tokens); |
| 6876 |
!!!next-token; |
!!!next-token; |
| 6877 |
next B; |
next B; |
| 6919 |
## Ignore the token |
## Ignore the token |
| 6920 |
} else { |
} else { |
| 6921 |
!!!cp ('t398'); |
!!!cp ('t398'); |
| 6922 |
!!!parse-error (type => 'in RCDATA:#'.$token->{type}, token => $token); |
!!!parse-error (type => 'in RCDATA:#eof', token => $token); |
| 6923 |
} |
} |
| 6924 |
!!!next-token; |
!!!next-token; |
| 6925 |
next B; |
next B; |
| 6926 |
|
} elsif ($token->{tag_name} eq 'rt' or |
| 6927 |
|
$token->{tag_name} eq 'rp') { |
| 6928 |
|
## has a |ruby| element in scope |
| 6929 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 6930 |
|
my $node = $self->{open_elements}->[$_]; |
| 6931 |
|
if ($node->[1] & RUBY_EL) { |
| 6932 |
|
!!!cp ('t398.1'); |
| 6933 |
|
## generate implied end tags |
| 6934 |
|
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 6935 |
|
!!!cp ('t398.2'); |
| 6936 |
|
pop @{$self->{open_elements}}; |
| 6937 |
|
} |
| 6938 |
|
unless ($self->{open_elements}->[-1]->[1] & RUBY_EL) { |
| 6939 |
|
!!!cp ('t398.3'); |
| 6940 |
|
!!!parse-error (type => 'not closed', |
| 6941 |
|
text => $self->{open_elements}->[-1]->[0] |
| 6942 |
|
->manakai_local_name, |
| 6943 |
|
token => $token); |
| 6944 |
|
pop @{$self->{open_elements}} |
| 6945 |
|
while not $self->{open_elements}->[-1]->[1] & RUBY_EL; |
| 6946 |
|
} |
| 6947 |
|
last INSCOPE; |
| 6948 |
|
} elsif ($node->[1] & SCOPING_EL) { |
| 6949 |
|
!!!cp ('t398.4'); |
| 6950 |
|
last INSCOPE; |
| 6951 |
|
} |
| 6952 |
|
} # INSCOPE |
| 6953 |
|
|
| 6954 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 6955 |
|
|
| 6956 |
|
!!!nack ('t398.5'); |
| 6957 |
|
!!!next-token; |
| 6958 |
|
redo B; |
| 6959 |
} elsif ($token->{tag_name} eq 'math' or |
} elsif ($token->{tag_name} eq 'math' or |
| 6960 |
$token->{tag_name} eq 'svg') { |
$token->{tag_name} eq 'svg') { |
| 6961 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 6962 |
|
|
| 6963 |
|
## "Adjust MathML attributes" ('math' only) - done in insert-element-f |
| 6964 |
|
|
| 6965 |
## "adjust SVG attributes" ('svg' only) - done in insert-element-f |
## "adjust SVG attributes" ('svg' only) - done in insert-element-f |
| 6966 |
|
|
| 6967 |
## "adjust foreign attributes" - done in insert-element-f |
## "adjust foreign attributes" - done in insert-element-f |
| 6988 |
thead => 1, tr => 1, |
thead => 1, tr => 1, |
| 6989 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6990 |
!!!cp ('t401'); |
!!!cp ('t401'); |
| 6991 |
!!!parse-error (type => 'in body:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in body', |
| 6992 |
|
text => $token->{tag_name}, token => $token); |
| 6993 |
## Ignore the token |
## Ignore the token |
| 6994 |
!!!nack ('t401.1'); ## NOTE: |<col/>| or |<frame/>| here is an error. |
!!!nack ('t401.1'); ## NOTE: |<col/>| or |<frame/>| here is an error. |
| 6995 |
!!!next-token; |
!!!next-token; |
| 7074 |
} |
} |
| 7075 |
|
|
| 7076 |
!!!parse-error (type => 'start tag not allowed', |
!!!parse-error (type => 'start tag not allowed', |
| 7077 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 7078 |
## NOTE: Ignore the token. |
## NOTE: Ignore the token. |
| 7079 |
!!!next-token; |
!!!next-token; |
| 7080 |
next B; |
next B; |
| 7084 |
unless ($_->[1] & ALL_END_TAG_OPTIONAL_EL) { |
unless ($_->[1] & ALL_END_TAG_OPTIONAL_EL) { |
| 7085 |
!!!cp ('t403'); |
!!!cp ('t403'); |
| 7086 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7087 |
value => $_->[0]->manakai_local_name, |
text => $_->[0]->manakai_local_name, |
| 7088 |
token => $token); |
token => $token); |
| 7089 |
last; |
last; |
| 7090 |
} else { |
} else { |
| 7104 |
unless ($self->{open_elements}->[-1]->[1] & BODY_EL) { |
unless ($self->{open_elements}->[-1]->[1] & BODY_EL) { |
| 7105 |
!!!cp ('t406'); |
!!!cp ('t406'); |
| 7106 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7107 |
value => $self->{open_elements}->[1]->[0] |
text => $self->{open_elements}->[1]->[0] |
| 7108 |
->manakai_local_name, |
->manakai_local_name, |
| 7109 |
token => $token); |
token => $token); |
| 7110 |
} else { |
} else { |
| 7115 |
next B; |
next B; |
| 7116 |
} else { |
} else { |
| 7117 |
!!!cp ('t408'); |
!!!cp ('t408'); |
| 7118 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7119 |
|
text => $token->{tag_name}, token => $token); |
| 7120 |
## Ignore the token |
## Ignore the token |
| 7121 |
!!!next-token; |
!!!next-token; |
| 7122 |
next B; |
next B; |
| 7144 |
|
|
| 7145 |
unless (defined $i) { # has an element in scope |
unless (defined $i) { # has an element in scope |
| 7146 |
!!!cp ('t413'); |
!!!cp ('t413'); |
| 7147 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7148 |
|
text => $token->{tag_name}, token => $token); |
| 7149 |
|
## NOTE: Ignore the token. |
| 7150 |
} else { |
} else { |
| 7151 |
## Step 1. generate implied end tags |
## Step 1. generate implied end tags |
| 7152 |
while ({ |
while ({ |
| 7153 |
|
## END_TAG_OPTIONAL_EL |
| 7154 |
dd => ($token->{tag_name} ne 'dd'), |
dd => ($token->{tag_name} ne 'dd'), |
| 7155 |
dt => ($token->{tag_name} ne 'dt'), |
dt => ($token->{tag_name} ne 'dt'), |
| 7156 |
li => ($token->{tag_name} ne 'li'), |
li => ($token->{tag_name} ne 'li'), |
| 7157 |
p => 1, |
p => 1, |
| 7158 |
|
rt => 1, |
| 7159 |
|
rp => 1, |
| 7160 |
}->{$self->{open_elements}->[-1]->[0]->manakai_local_name}) { |
}->{$self->{open_elements}->[-1]->[0]->manakai_local_name}) { |
| 7161 |
!!!cp ('t409'); |
!!!cp ('t409'); |
| 7162 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 7167 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 7168 |
!!!cp ('t412'); |
!!!cp ('t412'); |
| 7169 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7170 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 7171 |
->manakai_local_name, |
->manakai_local_name, |
| 7172 |
token => $token); |
token => $token); |
| 7173 |
} else { |
} else { |
| 7204 |
|
|
| 7205 |
unless (defined $i) { # has an element in scope |
unless (defined $i) { # has an element in scope |
| 7206 |
!!!cp ('t421'); |
!!!cp ('t421'); |
| 7207 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7208 |
|
text => $token->{tag_name}, token => $token); |
| 7209 |
|
## NOTE: Ignore the token. |
| 7210 |
} else { |
} else { |
| 7211 |
## Step 1. generate implied end tags |
## Step 1. generate implied end tags |
| 7212 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 7219 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 7220 |
!!!cp ('t417.1'); |
!!!cp ('t417.1'); |
| 7221 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7222 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 7223 |
->manakai_local_name, |
->manakai_local_name, |
| 7224 |
token => $token); |
token => $token); |
| 7225 |
} else { |
} else { |
| 7251 |
|
|
| 7252 |
unless (defined $i) { # has an element in scope |
unless (defined $i) { # has an element in scope |
| 7253 |
!!!cp ('t425.1'); |
!!!cp ('t425.1'); |
| 7254 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7255 |
|
text => $token->{tag_name}, token => $token); |
| 7256 |
|
## NOTE: Ignore the token. |
| 7257 |
} else { |
} else { |
| 7258 |
## Step 1. generate implied end tags |
## Step 1. generate implied end tags |
| 7259 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 7265 |
if ($self->{open_elements}->[-1]->[0]->manakai_local_name |
if ($self->{open_elements}->[-1]->[0]->manakai_local_name |
| 7266 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 7267 |
!!!cp ('t425'); |
!!!cp ('t425'); |
| 7268 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7269 |
|
text => $token->{tag_name}, token => $token); |
| 7270 |
} else { |
} else { |
| 7271 |
!!!cp ('t426'); |
!!!cp ('t426'); |
| 7272 |
} |
} |
| 7297 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 7298 |
!!!cp ('t412.1'); |
!!!cp ('t412.1'); |
| 7299 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7300 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 7301 |
->manakai_local_name, |
->manakai_local_name, |
| 7302 |
token => $token); |
token => $token); |
| 7303 |
} else { |
} else { |
| 7307 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 7308 |
} else { |
} else { |
| 7309 |
!!!cp ('t413.1'); |
!!!cp ('t413.1'); |
| 7310 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7311 |
|
text => $token->{tag_name}, token => $token); |
| 7312 |
|
|
| 7313 |
!!!cp ('t415.1'); |
!!!cp ('t415.1'); |
| 7314 |
## As if <p>, then reprocess the current token |
## As if <p>, then reprocess the current token |
| 7331 |
next B; |
next B; |
| 7332 |
} elsif ($token->{tag_name} eq 'br') { |
} elsif ($token->{tag_name} eq 'br') { |
| 7333 |
!!!cp ('t428'); |
!!!cp ('t428'); |
| 7334 |
!!!parse-error (type => 'unmatched end tag:br', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7335 |
|
text => 'br', token => $token); |
| 7336 |
|
|
| 7337 |
## As if <br> |
## As if <br> |
| 7338 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 7357 |
noscript => 0, ## TODO: if scripting is enabled |
noscript => 0, ## TODO: if scripting is enabled |
| 7358 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 7359 |
!!!cp ('t429'); |
!!!cp ('t429'); |
| 7360 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7361 |
|
text => $token->{tag_name}, token => $token); |
| 7362 |
## Ignore the token |
## Ignore the token |
| 7363 |
!!!next-token; |
!!!next-token; |
| 7364 |
next B; |
next B; |
| 7377 |
## generate implied end tags |
## generate implied end tags |
| 7378 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 7379 |
!!!cp ('t430'); |
!!!cp ('t430'); |
| 7380 |
## ISSUE: Can this case be reached? |
## NOTE: |<ruby><rt></ruby>|. |
| 7381 |
|
## ISSUE: <ruby><rt></rt> will also take this code path, |
| 7382 |
|
## which seems wrong. |
| 7383 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 7384 |
|
$node_i++; |
| 7385 |
} |
} |
| 7386 |
|
|
| 7387 |
## Step 2 |
## Step 2 |
| 7390 |
!!!cp ('t431'); |
!!!cp ('t431'); |
| 7391 |
## NOTE: <x><y></x> |
## NOTE: <x><y></x> |
| 7392 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7393 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 7394 |
->manakai_local_name, |
->manakai_local_name, |
| 7395 |
token => $token); |
token => $token); |
| 7396 |
} else { |
} else { |
| 7398 |
} |
} |
| 7399 |
|
|
| 7400 |
## Step 3 |
## Step 3 |
| 7401 |
splice @{$self->{open_elements}}, $node_i; |
splice @{$self->{open_elements}}, $node_i if $node_i < 0; |
| 7402 |
|
|
| 7403 |
!!!next-token; |
!!!next-token; |
| 7404 |
last S2; |
last S2; |
| 7409 |
($node->[1] & SPECIAL_EL or |
($node->[1] & SPECIAL_EL or |
| 7410 |
$node->[1] & SCOPING_EL)) { |
$node->[1] & SCOPING_EL)) { |
| 7411 |
!!!cp ('t433'); |
!!!cp ('t433'); |
| 7412 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7413 |
|
text => $token->{tag_name}, token => $token); |
| 7414 |
## Ignore the token |
## Ignore the token |
| 7415 |
!!!next-token; |
!!!next-token; |
| 7416 |
last S2; |
last S2; |
| 7546 |
0x10FFFE => 1, 0x10FFFF => 1, |
0x10FFFE => 1, 0x10FFFF => 1, |
| 7547 |
}->{$self->{next_char}}) { |
}->{$self->{next_char}}) { |
| 7548 |
!!!cp ('i4.1'); |
!!!cp ('i4.1'); |
| 7549 |
!!!parse-error (type => 'control char', level => $self->{must_level}); |
if ($self->{next_char} < 0x10000) { |
| 7550 |
## TODO: error type documentation |
!!!parse-error (type => 'control char', |
| 7551 |
|
text => (sprintf 'U+%04X', $self->{next_char})); |
| 7552 |
|
} else { |
| 7553 |
|
!!!parse-error (type => 'control char', |
| 7554 |
|
text => (sprintf 'U-%08X', $self->{next_char})); |
| 7555 |
|
} |
| 7556 |
} |
} |
| 7557 |
}; |
}; |
| 7558 |
$p->{prev_char} = [-1, -1, -1]; |
$p->{prev_char} = [-1, -1, -1]; |