| 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', |
| 354 |
return $self->parse_byte_stream ($charset_name, $input, @_[1..$#_]); |
return $self->parse_byte_stream ($charset_name, $input, @_[1..$#_]); |
| 355 |
} # parse_byte_string |
} # parse_byte_string |
| 356 |
|
|
| 357 |
sub parse_byte_stream ($$$$;$) { |
sub parse_byte_stream ($$$$;$$) { |
| 358 |
|
# my ($self, $charset_name, $byte_stream, $doc, $onerror, $get_wrapper) = @_; |
| 359 |
my $self = ref $_[0] ? shift : shift->new; |
my $self = ref $_[0] ? shift : shift->new; |
| 360 |
my $charset_name = shift; |
my $charset_name = shift; |
| 361 |
my $byte_stream = $_[0]; |
my $byte_stream = $_[0]; |
| 366 |
}; |
}; |
| 367 |
$self->{parse_error} = $onerror; # updated later by parse_char_string |
$self->{parse_error} = $onerror; # updated later by parse_char_string |
| 368 |
|
|
| 369 |
|
my $get_wrapper = $_[3] || sub ($) { |
| 370 |
|
return $_[0]; # $_[0] = byte stream handle, returned = arg to char handle |
| 371 |
|
}; |
| 372 |
|
|
| 373 |
## HTML5 encoding sniffing algorithm |
## HTML5 encoding sniffing algorithm |
| 374 |
require Message::Charset::Info; |
require Message::Charset::Info; |
| 375 |
my $charset; |
my $charset; |
| 377 |
my ($char_stream, $e_status); |
my ($char_stream, $e_status); |
| 378 |
|
|
| 379 |
SNIFFING: { |
SNIFFING: { |
| 380 |
|
## NOTE: By setting |allow_fallback| option true when the |
| 381 |
|
## |get_decode_handle| method is invoked, we ignore what the HTML5 |
| 382 |
|
## spec requires, i.e. unsupported encoding should be ignored. |
| 383 |
|
## TODO: We should not do this unless the parser is invoked |
| 384 |
|
## in the conformance checking mode, in which this behavior |
| 385 |
|
## would be useful. |
| 386 |
|
|
| 387 |
## Step 1 |
## Step 1 |
| 388 |
if (defined $charset_name) { |
if (defined $charset_name) { |
| 389 |
$charset = Message::Charset::Info->get_by_iana_name ($charset_name); |
$charset = Message::Charset::Info->get_by_html_name ($charset_name); |
| 390 |
|
## TODO: Is this ok? Transfer protocol's parameter should be |
| 391 |
|
## interpreted in its semantics? |
| 392 |
|
|
| 393 |
## ISSUE: Unsupported encoding is not ignored according to the spec. |
## ISSUE: Unsupported encoding is not ignored according to the spec. |
| 394 |
($char_stream, $e_status) = $charset->get_decode_handle |
($char_stream, $e_status) = $charset->get_decode_handle |
| 412 |
|
|
| 413 |
## Step 3 |
## Step 3 |
| 414 |
if ($byte_buffer =~ /^\xFE\xFF/) { |
if ($byte_buffer =~ /^\xFE\xFF/) { |
| 415 |
$charset = Message::Charset::Info->get_by_iana_name ('utf-16be'); |
$charset = Message::Charset::Info->get_by_html_name ('utf-16be'); |
| 416 |
($char_stream, $e_status) = $charset->get_decode_handle |
($char_stream, $e_status) = $charset->get_decode_handle |
| 417 |
($byte_stream, allow_error_reporting => 1, |
($byte_stream, allow_error_reporting => 1, |
| 418 |
allow_fallback => 1, byte_buffer => \$byte_buffer); |
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 419 |
$self->{confident} = 1; |
$self->{confident} = 1; |
| 420 |
last SNIFFING; |
last SNIFFING; |
| 421 |
} elsif ($byte_buffer =~ /^\xFF\xFE/) { |
} elsif ($byte_buffer =~ /^\xFF\xFE/) { |
| 422 |
$charset = Message::Charset::Info->get_by_iana_name ('utf-16le'); |
$charset = Message::Charset::Info->get_by_html_name ('utf-16le'); |
| 423 |
($char_stream, $e_status) = $charset->get_decode_handle |
($char_stream, $e_status) = $charset->get_decode_handle |
| 424 |
($byte_stream, allow_error_reporting => 1, |
($byte_stream, allow_error_reporting => 1, |
| 425 |
allow_fallback => 1, byte_buffer => \$byte_buffer); |
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 426 |
$self->{confident} = 1; |
$self->{confident} = 1; |
| 427 |
last SNIFFING; |
last SNIFFING; |
| 428 |
} elsif ($byte_buffer =~ /^\xEF\xBB\xBF/) { |
} elsif ($byte_buffer =~ /^\xEF\xBB\xBF/) { |
| 429 |
$charset = Message::Charset::Info->get_by_iana_name ('utf-8'); |
$charset = Message::Charset::Info->get_by_html_name ('utf-8'); |
| 430 |
($char_stream, $e_status) = $charset->get_decode_handle |
($char_stream, $e_status) = $charset->get_decode_handle |
| 431 |
($byte_stream, allow_error_reporting => 1, |
($byte_stream, allow_error_reporting => 1, |
| 432 |
allow_fallback => 1, byte_buffer => \$byte_buffer); |
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 445 |
$charset_name = Whatpm::Charset::UniversalCharDet->detect_byte_string |
$charset_name = Whatpm::Charset::UniversalCharDet->detect_byte_string |
| 446 |
($byte_buffer); |
($byte_buffer); |
| 447 |
if (defined $charset_name) { |
if (defined $charset_name) { |
| 448 |
$charset = Message::Charset::Info->get_by_iana_name ($charset_name); |
$charset = Message::Charset::Info->get_by_html_name ($charset_name); |
| 449 |
|
|
| 450 |
## ISSUE: Unsupported encoding is not ignored according to the spec. |
## ISSUE: Unsupported encoding is not ignored according to the spec. |
| 451 |
require Whatpm::Charset::DecodeHandle; |
require Whatpm::Charset::DecodeHandle; |
| 456 |
allow_fallback => 1, byte_buffer => \$byte_buffer); |
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 457 |
if ($char_stream) { |
if ($char_stream) { |
| 458 |
$buffer->{buffer} = $byte_buffer; |
$buffer->{buffer} = $byte_buffer; |
| 459 |
!!!parse-error (type => 'sniffing:chardet', ## TODO: type name |
!!!parse-error (type => 'sniffing:chardet', |
| 460 |
value => $charset_name, |
text => $charset_name, |
| 461 |
level => $self->{info_level}, |
level => $self->{level}->{info}, |
| 462 |
|
layer => 'encode', |
| 463 |
line => 1, column => 1); |
line => 1, column => 1); |
| 464 |
$self->{confident} = 0; |
$self->{confident} = 0; |
| 465 |
last SNIFFING; |
last SNIFFING; |
| 468 |
|
|
| 469 |
## Step 7: default |
## Step 7: default |
| 470 |
## TODO: Make this configurable. |
## TODO: Make this configurable. |
| 471 |
$charset = Message::Charset::Info->get_by_iana_name ('windows-1252'); |
$charset = Message::Charset::Info->get_by_html_name ('windows-1252'); |
| 472 |
## NOTE: We choose |windows-1252| here, since |utf-8| should be |
## NOTE: We choose |windows-1252| here, since |utf-8| should be |
| 473 |
## detectable in the step 6. |
## detectable in the step 6. |
| 474 |
require Whatpm::Charset::DecodeHandle; |
require Whatpm::Charset::DecodeHandle; |
| 480 |
allow_fallback => 1, |
allow_fallback => 1, |
| 481 |
byte_buffer => \$byte_buffer); |
byte_buffer => \$byte_buffer); |
| 482 |
$buffer->{buffer} = $byte_buffer; |
$buffer->{buffer} = $byte_buffer; |
| 483 |
!!!parse-error (type => 'sniffing:default', ## TODO: type name |
!!!parse-error (type => 'sniffing:default', |
| 484 |
value => 'windows-1252', |
text => 'windows-1252', |
| 485 |
level => $self->{info_level}, |
level => $self->{level}->{info}, |
| 486 |
line => 1, column => 1); |
line => 1, column => 1, |
| 487 |
|
layer => 'encode'); |
| 488 |
$self->{confident} = 0; |
$self->{confident} = 0; |
| 489 |
} # SNIFFING |
} # SNIFFING |
| 490 |
|
|
|
$self->{input_encoding} = $charset->get_iana_name; |
|
| 491 |
if ($e_status & Message::Charset::Info::FALLBACK_ENCODING_IMPL ()) { |
if ($e_status & Message::Charset::Info::FALLBACK_ENCODING_IMPL ()) { |
| 492 |
!!!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? |
| 493 |
value => $self->{input_encoding}, |
!!!parse-error (type => 'chardecode:fallback', |
| 494 |
level => $self->{unsupported_level}, |
#text => $self->{input_encoding}, |
| 495 |
line => 1, column => 1); |
level => $self->{level}->{uncertain}, |
| 496 |
|
line => 1, column => 1, |
| 497 |
|
layer => 'encode'); |
| 498 |
} elsif (not ($e_status & |
} elsif (not ($e_status & |
| 499 |
Message::Charset::Info::ERROR_REPORTING_ENCODING_IMPL())) { |
Message::Charset::Info::ERROR_REPORTING_ENCODING_IMPL())) { |
| 500 |
!!!parse-error (type => 'chardecode:no error', ## TODO: type name |
$self->{input_encoding} = $charset->get_iana_name; |
| 501 |
value => $self->{input_encoding}, |
!!!parse-error (type => 'chardecode:no error', |
| 502 |
level => $self->{unsupported_level}, |
text => $self->{input_encoding}, |
| 503 |
line => 1, column => 1); |
level => $self->{level}->{uncertain}, |
| 504 |
|
line => 1, column => 1, |
| 505 |
|
layer => 'encode'); |
| 506 |
|
} else { |
| 507 |
|
$self->{input_encoding} = $charset->get_iana_name; |
| 508 |
} |
} |
| 509 |
|
|
| 510 |
$self->{change_encoding} = sub { |
$self->{change_encoding} = sub { |
| 512 |
$charset_name = shift; |
$charset_name = shift; |
| 513 |
my $token = shift; |
my $token = shift; |
| 514 |
|
|
| 515 |
$charset = Message::Charset::Info->get_by_iana_name ($charset_name); |
$charset = Message::Charset::Info->get_by_html_name ($charset_name); |
| 516 |
($char_stream, $e_status) = $charset->get_decode_handle |
($char_stream, $e_status) = $charset->get_decode_handle |
| 517 |
($byte_stream, allow_error_reporting => 1, allow_fallback => 1, |
($byte_stream, allow_error_reporting => 1, allow_fallback => 1, |
| 518 |
byte_buffer => \ $buffer->{buffer}); |
byte_buffer => \ $buffer->{buffer}); |
| 521 |
## "Change the encoding" algorithm: |
## "Change the encoding" algorithm: |
| 522 |
|
|
| 523 |
## Step 1 |
## Step 1 |
| 524 |
if ($charset->{iana_names}->{'utf-16'}) { ## ISSUE: UTF-16BE -> UTF-8? UTF-16LE -> UTF-8? |
if ($charset->{category} & |
| 525 |
$charset = Message::Charset::Info->get_by_iana_name ('utf-8'); |
Message::Charset::Info::CHARSET_CATEGORY_UTF16 ()) { |
| 526 |
|
$charset = Message::Charset::Info->get_by_html_name ('utf-8'); |
| 527 |
($char_stream, $e_status) = $charset->get_decode_handle |
($char_stream, $e_status) = $charset->get_decode_handle |
| 528 |
($byte_stream, |
($byte_stream, |
| 529 |
byte_buffer => \ $buffer->{buffer}); |
byte_buffer => \ $buffer->{buffer}); |
| 533 |
## Step 2 |
## Step 2 |
| 534 |
if (defined $self->{input_encoding} and |
if (defined $self->{input_encoding} and |
| 535 |
$self->{input_encoding} eq $charset_name) { |
$self->{input_encoding} eq $charset_name) { |
| 536 |
!!!parse-error (type => 'charset label:matching', ## TODO: type |
!!!parse-error (type => 'charset label:matching', |
| 537 |
value => $charset_name, |
text => $charset_name, |
| 538 |
level => $self->{info_level}); |
level => $self->{level}->{info}); |
| 539 |
$self->{confident} = 1; |
$self->{confident} = 1; |
| 540 |
return; |
return; |
| 541 |
} |
} |
| 542 |
|
|
| 543 |
!!!parse-error (type => 'charset label detected:'.$self->{input_encoding}. |
!!!parse-error (type => 'charset label detected', |
| 544 |
':'.$charset_name, level => 'w', token => $token); |
text => $self->{input_encoding}, |
| 545 |
|
value => $charset_name, |
| 546 |
|
level => $self->{level}->{warn}, |
| 547 |
|
token => $token); |
| 548 |
|
|
| 549 |
## Step 3 |
## Step 3 |
| 550 |
# if (can) { |
# if (can) { |
| 560 |
|
|
| 561 |
my $char_onerror = sub { |
my $char_onerror = sub { |
| 562 |
my (undef, $type, %opt) = @_; |
my (undef, $type, %opt) = @_; |
| 563 |
!!!parse-error (%opt, type => $type, |
!!!parse-error (layer => 'encode', |
| 564 |
|
%opt, type => $type, |
| 565 |
line => $self->{line}, column => $self->{column} + 1); |
line => $self->{line}, column => $self->{column} + 1); |
| 566 |
if ($opt{octets}) { |
if ($opt{octets}) { |
| 567 |
${$opt{octets}} = "\x{FFFD}"; # relacement character |
${$opt{octets}} = "\x{FFFD}"; # relacement character |
| 568 |
} |
} |
| 569 |
}; |
}; |
| 570 |
$char_stream->onerror ($char_onerror); |
|
| 571 |
|
my $wrapped_char_stream = $get_wrapper->($char_stream); |
| 572 |
|
$wrapped_char_stream->onerror ($char_onerror); |
| 573 |
|
|
| 574 |
my @args = @_; shift @args; # $s |
my @args = @_; shift @args; # $s |
| 575 |
my $return; |
my $return; |
| 576 |
try { |
try { |
| 577 |
$return = $self->parse_char_stream ($char_stream, @args); |
$return = $self->parse_char_stream ($wrapped_char_stream, @args); |
| 578 |
} catch Whatpm::HTML::RestartParser with { |
} catch Whatpm::HTML::RestartParser with { |
| 579 |
## NOTE: Invoked after {change_encoding}. |
## NOTE: Invoked after {change_encoding}. |
| 580 |
|
|
|
$self->{input_encoding} = $charset->get_iana_name; |
|
| 581 |
if ($e_status & Message::Charset::Info::FALLBACK_ENCODING_IMPL ()) { |
if ($e_status & Message::Charset::Info::FALLBACK_ENCODING_IMPL ()) { |
| 582 |
!!!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? |
| 583 |
value => $self->{input_encoding}, |
!!!parse-error (type => 'chardecode:fallback', |
| 584 |
level => $self->{unsupported_level}, |
level => $self->{level}->{uncertain}, |
| 585 |
line => 1, column => 1); |
#text => $self->{input_encoding}, |
| 586 |
|
line => 1, column => 1, |
| 587 |
|
layer => 'encode'); |
| 588 |
} elsif (not ($e_status & |
} elsif (not ($e_status & |
| 589 |
Message::Charset::Info::ERROR_REPORTING_ENCODING_IMPL())) { |
Message::Charset::Info::ERROR_REPORTING_ENCODING_IMPL())) { |
| 590 |
!!!parse-error (type => 'chardecode:no error', ## TODO: type name |
$self->{input_encoding} = $charset->get_iana_name; |
| 591 |
value => $self->{input_encoding}, |
!!!parse-error (type => 'chardecode:no error', |
| 592 |
level => $self->{unsupported_level}, |
text => $self->{input_encoding}, |
| 593 |
line => 1, column => 1); |
level => $self->{level}->{uncertain}, |
| 594 |
|
line => 1, column => 1, |
| 595 |
|
layer => 'encode'); |
| 596 |
|
} else { |
| 597 |
|
$self->{input_encoding} = $charset->get_iana_name; |
| 598 |
} |
} |
| 599 |
$self->{confident} = 1; |
$self->{confident} = 1; |
| 600 |
$char_stream->onerror ($char_onerror); |
|
| 601 |
$return = $self->parse_char_stream ($char_stream, @args); |
$wrapped_char_stream = $get_wrapper->($char_stream); |
| 602 |
|
$wrapped_char_stream->onerror ($char_onerror); |
| 603 |
|
|
| 604 |
|
$return = $self->parse_char_stream ($wrapped_char_stream, @args); |
| 605 |
}; |
}; |
| 606 |
return $return; |
return $return; |
| 607 |
} # parse_byte_stream |
} # parse_byte_stream |
| 615 |
## such as |parse_byte_string| in this module, must ensure that it does |
## such as |parse_byte_string| in this module, must ensure that it does |
| 616 |
## strip the BOM and never strip any ZWNBSP. |
## strip the BOM and never strip any ZWNBSP. |
| 617 |
|
|
| 618 |
sub parse_char_string ($$$;$) { |
sub parse_char_string ($$$;$$) { |
| 619 |
|
#my ($self, $s, $doc, $onerror, $get_wrapper) = @_; |
| 620 |
my $self = shift; |
my $self = shift; |
| 621 |
require utf8; |
require utf8; |
| 622 |
my $s = ref $_[0] ? $_[0] : \($_[0]); |
my $s = ref $_[0] ? $_[0] : \($_[0]); |
| 623 |
open my $input, '<' . (utf8::is_utf8 ($$s) ? ':utf8' : ''), $s; |
open my $input, '<' . (utf8::is_utf8 ($$s) ? ':utf8' : ''), $s; |
| 624 |
|
if ($_[3]) { |
| 625 |
|
$input = $_[3]->($input); |
| 626 |
|
} |
| 627 |
return $self->parse_char_stream ($input, @_[1..$#_]); |
return $self->parse_char_stream ($input, @_[1..$#_]); |
| 628 |
} # parse_char_string |
} # parse_char_string |
| 629 |
*parse_string = \&parse_char_string; |
*parse_string = \&parse_char_string; ## NOTE: Alias for backward compatibility. |
| 630 |
|
|
| 631 |
sub parse_char_stream ($$$;$) { |
sub parse_char_stream ($$$;$) { |
| 632 |
my $self = ref $_[0] ? shift : shift->new; |
my $self = ref $_[0] ? shift : shift->new; |
| 700 |
0x10FFFE => 1, 0x10FFFF => 1, |
0x10FFFE => 1, 0x10FFFF => 1, |
| 701 |
}->{$self->{next_char}}) { |
}->{$self->{next_char}}) { |
| 702 |
!!!cp ('j5'); |
!!!cp ('j5'); |
| 703 |
!!!parse-error (type => 'control char', level => $self->{must_level}); |
if ($self->{next_char} < 0x10000) { |
| 704 |
## TODO: error type documentation |
!!!parse-error (type => 'control char', |
| 705 |
|
text => (sprintf 'U+%04X', $self->{next_char})); |
| 706 |
|
} else { |
| 707 |
|
!!!parse-error (type => 'control char', |
| 708 |
|
text => (sprintf 'U-%08X', $self->{next_char})); |
| 709 |
|
} |
| 710 |
} |
} |
| 711 |
}; |
}; |
| 712 |
$self->{prev_char} = [-1, -1, -1]; |
$self->{prev_char} = [-1, -1, -1]; |
| 735 |
sub new ($) { |
sub new ($) { |
| 736 |
my $class = shift; |
my $class = shift; |
| 737 |
my $self = bless { |
my $self = bless { |
| 738 |
must_level => 'm', |
level => {must => 'm', |
| 739 |
should_level => 's', |
should => 's', |
| 740 |
good_level => 'w', |
warn => 'w', |
| 741 |
warn_level => 'w', |
info => 'i', |
| 742 |
info_level => 'i', |
uncertain => 'u'}, |
|
unsupported_level => 'u', |
|
| 743 |
}, $class; |
}, $class; |
| 744 |
$self->{set_next_char} = sub { |
$self->{set_next_char} = sub { |
| 745 |
$self->{next_char} = -1; |
$self->{next_char} = -1; |
| 804 |
sub AFTER_ATTRIBUTE_VALUE_QUOTED_STATE () { 33 } |
sub AFTER_ATTRIBUTE_VALUE_QUOTED_STATE () { 33 } |
| 805 |
sub SELF_CLOSING_START_TAG_STATE () { 34 } |
sub SELF_CLOSING_START_TAG_STATE () { 34 } |
| 806 |
sub CDATA_BLOCK_STATE () { 35 } |
sub CDATA_BLOCK_STATE () { 35 } |
| 807 |
|
sub MD_HYPHEN_STATE () { 36 } |
| 808 |
|
sub MD_DOCTYPE_STATE () { 37 } |
| 809 |
|
sub MD_CDATA_STATE () { 38 } |
| 810 |
|
|
| 811 |
sub DOCTYPE_TOKEN () { 1 } |
sub DOCTYPE_TOKEN () { 1 } |
| 812 |
sub COMMENT_TOKEN () { 2 } |
sub COMMENT_TOKEN () { 2 } |
| 859 |
sub _initialize_tokenizer ($) { |
sub _initialize_tokenizer ($) { |
| 860 |
my $self = shift; |
my $self = shift; |
| 861 |
$self->{state} = DATA_STATE; # MUST |
$self->{state} = DATA_STATE; # MUST |
| 862 |
|
#$self->{state_keyword}; # initialized when used |
| 863 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # be |
$self->{content_model} = PCDATA_CONTENT_MODEL; # be |
| 864 |
undef $self->{current_token}; # start tag, end tag, comment, or DOCTYPE |
undef $self->{current_token}; # start tag, end tag, comment, or DOCTYPE |
| 865 |
undef $self->{current_attribute}; |
undef $self->{current_attribute}; |
| 890 |
## |->{self_closing}| is used to save the value of |$self->{self_closing}| |
## |->{self_closing}| is used to save the value of |$self->{self_closing}| |
| 891 |
## while the token is pushed back to the stack. |
## while the token is pushed back to the stack. |
| 892 |
|
|
|
## 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? |
|
|
|
|
| 893 |
## Emitted token MUST immediately be handled by the tree construction state. |
## Emitted token MUST immediately be handled by the tree construction state. |
| 894 |
|
|
| 895 |
## 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 |
| 1402 |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
| 1403 |
->{$self->{current_attribute}->{name}}) { # MUST |
->{$self->{current_attribute}->{name}}) { # MUST |
| 1404 |
!!!cp (57); |
!!!cp (57); |
| 1405 |
!!!parse-error (type => 'duplicate attribute:'.$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}); |
| 1406 |
## Discard $self->{current_attribute} # MUST |
## Discard $self->{current_attribute} # MUST |
| 1407 |
} else { |
} else { |
| 1408 |
!!!cp (58); |
!!!cp (58); |
| 1573 |
|
|
| 1574 |
redo A; |
redo A; |
| 1575 |
} else { |
} else { |
| 1576 |
!!!cp (82); |
if ($self->{next_char} == 0x0022 or # " |
| 1577 |
|
$self->{next_char} == 0x0027) { # ' |
| 1578 |
|
!!!cp (78); |
| 1579 |
|
!!!parse-error (type => 'bad attribute name'); |
| 1580 |
|
} else { |
| 1581 |
|
!!!cp (82); |
| 1582 |
|
} |
| 1583 |
$self->{current_attribute} |
$self->{current_attribute} |
| 1584 |
= {name => chr ($self->{next_char}), |
= {name => chr ($self->{next_char}), |
| 1585 |
value => '', |
value => '', |
| 1614 |
!!!next-input-character; |
!!!next-input-character; |
| 1615 |
redo A; |
redo A; |
| 1616 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1617 |
|
!!!parse-error (type => 'empty unquoted attribute value'); |
| 1618 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1619 |
!!!cp (87); |
!!!cp (87); |
| 1620 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 2005 |
die "$0: _get_next_token: unexpected case [BC]"; |
die "$0: _get_next_token: unexpected case [BC]"; |
| 2006 |
} elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) { |
} elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) { |
| 2007 |
## (only happen if PCDATA state) |
## (only happen if PCDATA state) |
|
|
|
|
my ($l, $c) = ($self->{line_prev}, $self->{column_prev} - 1); |
|
|
|
|
|
my @next_char; |
|
|
push @next_char, $self->{next_char}; |
|
| 2008 |
|
|
| 2009 |
if ($self->{next_char} == 0x002D) { # - |
if ($self->{next_char} == 0x002D) { # - |
| 2010 |
|
!!!cp (133); |
| 2011 |
|
$self->{state} = MD_HYPHEN_STATE; |
| 2012 |
!!!next-input-character; |
!!!next-input-character; |
| 2013 |
push @next_char, $self->{next_char}; |
redo A; |
|
if ($self->{next_char} == 0x002D) { # - |
|
|
!!!cp (127); |
|
|
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
|
|
line => $l, column => $c, |
|
|
}; |
|
|
$self->{state} = COMMENT_START_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (128); |
|
|
} |
|
| 2014 |
} elsif ($self->{next_char} == 0x0044 or # D |
} elsif ($self->{next_char} == 0x0044 or # D |
| 2015 |
$self->{next_char} == 0x0064) { # d |
$self->{next_char} == 0x0064) { # d |
| 2016 |
|
## ASCII case-insensitive. |
| 2017 |
|
!!!cp (130); |
| 2018 |
|
$self->{state} = MD_DOCTYPE_STATE; |
| 2019 |
|
$self->{state_keyword} = chr $self->{next_char}; |
| 2020 |
!!!next-input-character; |
!!!next-input-character; |
| 2021 |
push @next_char, $self->{next_char}; |
redo A; |
|
if ($self->{next_char} == 0x004F or # O |
|
|
$self->{next_char} == 0x006F) { # o |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x0043 or # C |
|
|
$self->{next_char} == 0x0063) { # c |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x0054 or # T |
|
|
$self->{next_char} == 0x0074) { # t |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x0059 or # Y |
|
|
$self->{next_char} == 0x0079) { # y |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x0050 or # P |
|
|
$self->{next_char} == 0x0070) { # p |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x0045 or # E |
|
|
$self->{next_char} == 0x0065) { # e |
|
|
!!!cp (129); |
|
|
## TODO: What a stupid code this is! |
|
|
$self->{state} = DOCTYPE_STATE; |
|
|
$self->{current_token} = {type => DOCTYPE_TOKEN, |
|
|
quirks => 1, |
|
|
line => $l, column => $c, |
|
|
}; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (130); |
|
|
} |
|
|
} else { |
|
|
!!!cp (131); |
|
|
} |
|
|
} else { |
|
|
!!!cp (132); |
|
|
} |
|
|
} else { |
|
|
!!!cp (133); |
|
|
} |
|
|
} else { |
|
|
!!!cp (134); |
|
|
} |
|
|
} else { |
|
|
!!!cp (135); |
|
|
} |
|
| 2022 |
} elsif ($self->{insertion_mode} & IN_FOREIGN_CONTENT_IM and |
} elsif ($self->{insertion_mode} & IN_FOREIGN_CONTENT_IM and |
| 2023 |
$self->{open_elements}->[-1]->[1] & FOREIGN_EL and |
$self->{open_elements}->[-1]->[1] & FOREIGN_EL and |
| 2024 |
$self->{next_char} == 0x005B) { # [ |
$self->{next_char} == 0x005B) { # [ |
| 2025 |
|
!!!cp (135.4); |
| 2026 |
|
$self->{state} = MD_CDATA_STATE; |
| 2027 |
|
$self->{state_keyword} = '['; |
| 2028 |
!!!next-input-character; |
!!!next-input-character; |
| 2029 |
push @next_char, $self->{next_char}; |
redo A; |
|
if ($self->{next_char} == 0x0043) { # C |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x0044) { # D |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x0041) { # A |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x0054) { # T |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x0041) { # A |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x005B) { # [ |
|
|
!!!cp (135.1); |
|
|
$self->{state} = CDATA_BLOCK_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (135.2); |
|
|
} |
|
|
} else { |
|
|
!!!cp (135.3); |
|
|
} |
|
|
} else { |
|
|
!!!cp (135.4); |
|
|
} |
|
|
} else { |
|
|
!!!cp (135.5); |
|
|
} |
|
|
} else { |
|
|
!!!cp (135.6); |
|
|
} |
|
|
} else { |
|
|
!!!cp (135.7); |
|
|
} |
|
| 2030 |
} else { |
} else { |
| 2031 |
!!!cp (136); |
!!!cp (136); |
| 2032 |
} |
} |
| 2033 |
|
|
| 2034 |
!!!parse-error (type => 'bogus comment'); |
!!!parse-error (type => 'bogus comment', |
| 2035 |
$self->{next_char} = shift @next_char; |
line => $self->{line_prev}, |
| 2036 |
!!!back-next-input-character (@next_char); |
column => $self->{column_prev} - 1); |
| 2037 |
|
## Reconsume. |
| 2038 |
$self->{state} = BOGUS_COMMENT_STATE; |
$self->{state} = BOGUS_COMMENT_STATE; |
| 2039 |
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
| 2040 |
line => $l, column => $c, |
line => $self->{line_prev}, |
| 2041 |
|
column => $self->{column_prev} - 1, |
| 2042 |
}; |
}; |
| 2043 |
redo A; |
redo A; |
| 2044 |
|
} elsif ($self->{state} == MD_HYPHEN_STATE) { |
| 2045 |
## ISSUE: typos in spec: chacacters, is is a parse error |
if ($self->{next_char} == 0x002D) { # - |
| 2046 |
## ISSUE: spec is somewhat unclear on "is the first character that will be in the comment"; what is "that will be in the comment" is what the algorithm defines, isn't it? |
!!!cp (127); |
| 2047 |
|
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
| 2048 |
|
line => $self->{line_prev}, |
| 2049 |
|
column => $self->{column_prev} - 2, |
| 2050 |
|
}; |
| 2051 |
|
$self->{state} = COMMENT_START_STATE; |
| 2052 |
|
!!!next-input-character; |
| 2053 |
|
redo A; |
| 2054 |
|
} else { |
| 2055 |
|
!!!cp (128); |
| 2056 |
|
!!!parse-error (type => 'bogus comment', |
| 2057 |
|
line => $self->{line_prev}, |
| 2058 |
|
column => $self->{column_prev} - 2); |
| 2059 |
|
$self->{state} = BOGUS_COMMENT_STATE; |
| 2060 |
|
## Reconsume. |
| 2061 |
|
$self->{current_token} = {type => COMMENT_TOKEN, |
| 2062 |
|
data => '-', |
| 2063 |
|
line => $self->{line_prev}, |
| 2064 |
|
column => $self->{column_prev} - 2, |
| 2065 |
|
}; |
| 2066 |
|
redo A; |
| 2067 |
|
} |
| 2068 |
|
} elsif ($self->{state} == MD_DOCTYPE_STATE) { |
| 2069 |
|
## ASCII case-insensitive. |
| 2070 |
|
if ($self->{next_char} == [ |
| 2071 |
|
undef, |
| 2072 |
|
0x004F, # O |
| 2073 |
|
0x0043, # C |
| 2074 |
|
0x0054, # T |
| 2075 |
|
0x0059, # Y |
| 2076 |
|
0x0050, # P |
| 2077 |
|
]->[length $self->{state_keyword}] or |
| 2078 |
|
$self->{next_char} == [ |
| 2079 |
|
undef, |
| 2080 |
|
0x006F, # o |
| 2081 |
|
0x0063, # c |
| 2082 |
|
0x0074, # t |
| 2083 |
|
0x0079, # y |
| 2084 |
|
0x0070, # p |
| 2085 |
|
]->[length $self->{state_keyword}]) { |
| 2086 |
|
!!!cp (131); |
| 2087 |
|
## Stay in the state. |
| 2088 |
|
$self->{state_keyword} .= chr $self->{next_char}; |
| 2089 |
|
!!!next-input-character; |
| 2090 |
|
redo A; |
| 2091 |
|
} elsif ((length $self->{state_keyword}) == 6 and |
| 2092 |
|
($self->{next_char} == 0x0045 or # E |
| 2093 |
|
$self->{next_char} == 0x0065)) { # e |
| 2094 |
|
!!!cp (129); |
| 2095 |
|
$self->{state} = DOCTYPE_STATE; |
| 2096 |
|
$self->{current_token} = {type => DOCTYPE_TOKEN, |
| 2097 |
|
quirks => 1, |
| 2098 |
|
line => $self->{line_prev}, |
| 2099 |
|
column => $self->{column_prev} - 7, |
| 2100 |
|
}; |
| 2101 |
|
!!!next-input-character; |
| 2102 |
|
redo A; |
| 2103 |
|
} else { |
| 2104 |
|
!!!cp (132); |
| 2105 |
|
!!!parse-error (type => 'bogus comment', |
| 2106 |
|
line => $self->{line_prev}, |
| 2107 |
|
column => $self->{column_prev} - 1 - length $self->{state_keyword}); |
| 2108 |
|
$self->{state} = BOGUS_COMMENT_STATE; |
| 2109 |
|
## Reconsume. |
| 2110 |
|
$self->{current_token} = {type => COMMENT_TOKEN, |
| 2111 |
|
data => $self->{state_keyword}, |
| 2112 |
|
line => $self->{line_prev}, |
| 2113 |
|
column => $self->{column_prev} - 1 - length $self->{state_keyword}, |
| 2114 |
|
}; |
| 2115 |
|
redo A; |
| 2116 |
|
} |
| 2117 |
|
} elsif ($self->{state} == MD_CDATA_STATE) { |
| 2118 |
|
if ($self->{next_char} == { |
| 2119 |
|
'[' => 0x0043, # C |
| 2120 |
|
'[C' => 0x0044, # D |
| 2121 |
|
'[CD' => 0x0041, # A |
| 2122 |
|
'[CDA' => 0x0054, # T |
| 2123 |
|
'[CDAT' => 0x0041, # A |
| 2124 |
|
}->{$self->{state_keyword}}) { |
| 2125 |
|
!!!cp (135.1); |
| 2126 |
|
## Stay in the state. |
| 2127 |
|
$self->{state_keyword} .= chr $self->{next_char}; |
| 2128 |
|
!!!next-input-character; |
| 2129 |
|
redo A; |
| 2130 |
|
} elsif ($self->{state_keyword} eq '[CDATA' and |
| 2131 |
|
$self->{next_char} == 0x005B) { # [ |
| 2132 |
|
!!!cp (135.2); |
| 2133 |
|
$self->{state} = CDATA_BLOCK_STATE; |
| 2134 |
|
!!!next-input-character; |
| 2135 |
|
redo A; |
| 2136 |
|
} else { |
| 2137 |
|
!!!cp (135.3); |
| 2138 |
|
!!!parse-error (type => 'bogus comment', |
| 2139 |
|
line => $self->{line_prev}, |
| 2140 |
|
column => $self->{column_prev} - 1 - length $self->{state_keyword}); |
| 2141 |
|
$self->{state} = BOGUS_COMMENT_STATE; |
| 2142 |
|
## Reconsume. |
| 2143 |
|
$self->{current_token} = {type => COMMENT_TOKEN, |
| 2144 |
|
data => $self->{state_keyword}, |
| 2145 |
|
line => $self->{line_prev}, |
| 2146 |
|
column => $self->{column_prev} - 1 - length $self->{state_keyword}, |
| 2147 |
|
}; |
| 2148 |
|
redo A; |
| 2149 |
|
} |
| 2150 |
} elsif ($self->{state} == COMMENT_START_STATE) { |
} elsif ($self->{state} == COMMENT_START_STATE) { |
| 2151 |
if ($self->{next_char} == 0x002D) { # - |
if ($self->{next_char} == 0x002D) { # - |
| 2152 |
!!!cp (137); |
!!!cp (137); |
| 2731 |
redo A; |
redo A; |
| 2732 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 2733 |
!!!cp (208); |
!!!cp (208); |
| 2734 |
!!!parse-error (type => 'unclosed PUBLIC literal'); |
!!!parse-error (type => 'unclosed SYSTEM literal'); |
| 2735 |
|
|
| 2736 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 2737 |
!!!next-input-character; |
!!!next-input-character; |
| 2767 |
redo A; |
redo A; |
| 2768 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 2769 |
!!!cp (212); |
!!!cp (212); |
| 2770 |
!!!parse-error (type => 'unclosed PUBLIC literal'); |
!!!parse-error (type => 'unclosed SYSTEM literal'); |
| 2771 |
|
|
| 2772 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 2773 |
!!!next-input-character; |
!!!next-input-character; |
| 2814 |
redo A; |
redo A; |
| 2815 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 2816 |
!!!cp (217); |
!!!cp (217); |
| 2817 |
|
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 2818 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 2819 |
## reconsume |
## reconsume |
| 2820 |
|
|
| 2976 |
|
|
| 2977 |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 2978 |
!!!cp (1008); |
!!!cp (1008); |
| 2979 |
!!!parse-error (type => (sprintf 'invalid character reference:U+%04X', $code), line => $l, column => $c); |
!!!parse-error (type => 'invalid character reference', |
| 2980 |
|
text => (sprintf 'U+%04X', $code), |
| 2981 |
|
line => $l, column => $c); |
| 2982 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 2983 |
} elsif ($code > 0x10FFFF) { |
} elsif ($code > 0x10FFFF) { |
| 2984 |
!!!cp (1009); |
!!!cp (1009); |
| 2985 |
!!!parse-error (type => (sprintf 'invalid character reference:U-%08X', $code), line => $l, column => $c); |
!!!parse-error (type => 'invalid character reference', |
| 2986 |
|
text => (sprintf 'U-%08X', $code), |
| 2987 |
|
line => $l, column => $c); |
| 2988 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 2989 |
} elsif ($code == 0x000D) { |
} elsif ($code == 0x000D) { |
| 2990 |
!!!cp (1010); |
!!!cp (1010); |
| 2992 |
$code = 0x000A; |
$code = 0x000A; |
| 2993 |
} elsif (0x80 <= $code and $code <= 0x9F) { |
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 2994 |
!!!cp (1011); |
!!!cp (1011); |
| 2995 |
!!!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); |
| 2996 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 2997 |
} |
} |
| 2998 |
|
|
| 3025 |
|
|
| 3026 |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 3027 |
!!!cp (1015); |
!!!cp (1015); |
| 3028 |
!!!parse-error (type => (sprintf 'invalid character reference:U+%04X', $code), line => $l, column => $c); |
!!!parse-error (type => 'invalid character reference', |
| 3029 |
|
text => (sprintf 'U+%04X', $code), |
| 3030 |
|
line => $l, column => $c); |
| 3031 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 3032 |
} elsif ($code > 0x10FFFF) { |
} elsif ($code > 0x10FFFF) { |
| 3033 |
!!!cp (1016); |
!!!cp (1016); |
| 3034 |
!!!parse-error (type => (sprintf 'invalid character reference:U-%08X', $code), line => $l, column => $c); |
!!!parse-error (type => 'invalid character reference', |
| 3035 |
|
text => (sprintf 'U-%08X', $code), |
| 3036 |
|
line => $l, column => $c); |
| 3037 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 3038 |
} elsif ($code == 0x000D) { |
} elsif ($code == 0x000D) { |
| 3039 |
!!!cp (1017); |
!!!cp (1017); |
| 3040 |
!!!parse-error (type => 'CR character reference', line => $l, column => $c); |
!!!parse-error (type => 'CR character reference', |
| 3041 |
|
line => $l, column => $c); |
| 3042 |
$code = 0x000A; |
$code = 0x000A; |
| 3043 |
} elsif (0x80 <= $code and $code <= 0x9F) { |
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 3044 |
!!!cp (1018); |
!!!cp (1018); |
| 3045 |
!!!parse-error (type => (sprintf 'C1 character reference:U+%04X', $code), line => $l, column => $c); |
!!!parse-error (type => 'C1 character reference', |
| 3046 |
|
text => (sprintf 'U+%04X', $code), |
| 3047 |
|
line => $l, column => $c); |
| 3048 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 3049 |
} |
} |
| 3050 |
|
|
| 3142 |
## TODO: Turn mutation events off # MUST |
## TODO: Turn mutation events off # MUST |
| 3143 |
## TODO: Turn loose Document option (manakai extension) on |
## TODO: Turn loose Document option (manakai extension) on |
| 3144 |
$self->{document}->manakai_is_html (1); # MUST |
$self->{document}->manakai_is_html (1); # MUST |
| 3145 |
|
$self->{document}->set_user_data (manakai_source_line => 1); |
| 3146 |
|
$self->{document}->set_user_data (manakai_source_column => 1); |
| 3147 |
} # _initialize_tree_constructor |
} # _initialize_tree_constructor |
| 3148 |
|
|
| 3149 |
sub _terminate_tree_constructor ($) { |
sub _terminate_tree_constructor ($) { |
| 3198 |
## language. |
## language. |
| 3199 |
my $doctype_name = $token->{name}; |
my $doctype_name = $token->{name}; |
| 3200 |
$doctype_name = '' unless defined $doctype_name; |
$doctype_name = '' unless defined $doctype_name; |
| 3201 |
$doctype_name =~ tr/a-z/A-Z/; |
$doctype_name =~ tr/a-z/A-Z/; # ASCII case-insensitive |
| 3202 |
if (not defined $token->{name} or # <!DOCTYPE> |
if (not defined $token->{name} or # <!DOCTYPE> |
|
defined $token->{public_identifier} or |
|
| 3203 |
defined $token->{system_identifier}) { |
defined $token->{system_identifier}) { |
| 3204 |
!!!cp ('t1'); |
!!!cp ('t1'); |
| 3205 |
!!!parse-error (type => 'not HTML5', token => $token); |
!!!parse-error (type => 'not HTML5', token => $token); |
| 3206 |
} elsif ($doctype_name ne 'HTML') { |
} elsif ($doctype_name ne 'HTML') { |
| 3207 |
!!!cp ('t2'); |
!!!cp ('t2'); |
|
## ISSUE: ASCII case-insensitive? (in fact it does not matter) |
|
| 3208 |
!!!parse-error (type => 'not HTML5', token => $token); |
!!!parse-error (type => 'not HTML5', token => $token); |
| 3209 |
|
} elsif (defined $token->{public_identifier}) { |
| 3210 |
|
if ($token->{public_identifier} eq 'XSLT-compat') { |
| 3211 |
|
!!!cp ('t1.2'); |
| 3212 |
|
!!!parse-error (type => 'XSLT-compat', token => $token, |
| 3213 |
|
level => $self->{level}->{should}); |
| 3214 |
|
} else { |
| 3215 |
|
!!!parse-error (type => 'not HTML5', token => $token); |
| 3216 |
|
} |
| 3217 |
} else { |
} else { |
| 3218 |
!!!cp ('t3'); |
!!!cp ('t3'); |
| 3219 |
|
# |
| 3220 |
} |
} |
| 3221 |
|
|
| 3222 |
my $doctype = $self->{document}->create_document_type_definition |
my $doctype = $self->{document}->create_document_type_definition |
| 3517 |
## NOTE: Strictly spaking, the line below only applies to MathML and |
## NOTE: Strictly spaking, the line below only applies to MathML and |
| 3518 |
## SVG elements. Currently the HTML syntax supports only MathML and |
## SVG elements. Currently the HTML syntax supports only MathML and |
| 3519 |
## SVG elements as foreigners. |
## SVG elements as foreigners. |
| 3520 |
$new_mode = $self->{insertion_mode} | IN_FOREIGN_CONTENT_IM; |
$new_mode = IN_BODY_IM | IN_FOREIGN_CONTENT_IM; |
|
## ISSUE: What is set as the secondary insertion mode? |
|
| 3521 |
} elsif ($node->[1] & TABLE_CELL_EL) { |
} elsif ($node->[1] & TABLE_CELL_EL) { |
| 3522 |
if ($last) { |
if ($last) { |
| 3523 |
!!!cp ('t28.2'); |
!!!cp ('t28.2'); |
| 3718 |
## NOTE: An end-of-file token. |
## NOTE: An end-of-file token. |
| 3719 |
if ($content_model_flag == CDATA_CONTENT_MODEL) { |
if ($content_model_flag == CDATA_CONTENT_MODEL) { |
| 3720 |
!!!cp ('t43'); |
!!!cp ('t43'); |
| 3721 |
!!!parse-error (type => 'in CDATA:#'.$token->{type}, token => $token); |
!!!parse-error (type => 'in CDATA:#eof', token => $token); |
| 3722 |
} elsif ($content_model_flag == RCDATA_CONTENT_MODEL) { |
} elsif ($content_model_flag == RCDATA_CONTENT_MODEL) { |
| 3723 |
!!!cp ('t44'); |
!!!cp ('t44'); |
| 3724 |
!!!parse-error (type => 'in RCDATA:#'.$token->{type}, token => $token); |
!!!parse-error (type => 'in RCDATA:#eof', token => $token); |
| 3725 |
} else { |
} else { |
| 3726 |
die "$0: $content_model_flag in parse_rcdata"; |
die "$0: $content_model_flag in parse_rcdata"; |
| 3727 |
} |
} |
| 3758 |
## Ignore the token |
## Ignore the token |
| 3759 |
} else { |
} else { |
| 3760 |
!!!cp ('t48'); |
!!!cp ('t48'); |
| 3761 |
!!!parse-error (type => 'in CDATA:#'.$token->{type}, token => $token); |
!!!parse-error (type => 'in CDATA:#eof', token => $token); |
| 3762 |
## ISSUE: And ignore? |
## ISSUE: And ignore? |
| 3763 |
## TODO: mark as "already executed" |
## TODO: mark as "already executed" |
| 3764 |
} |
} |
| 3809 |
} # AFE |
} # AFE |
| 3810 |
unless (defined $formatting_element) { |
unless (defined $formatting_element) { |
| 3811 |
!!!cp ('t53'); |
!!!cp ('t53'); |
| 3812 |
!!!parse-error (type => 'unmatched end tag:'.$tag_name, token => $end_tag_token); |
!!!parse-error (type => 'unmatched end tag', text => $tag_name, token => $end_tag_token); |
| 3813 |
## Ignore the token |
## Ignore the token |
| 3814 |
!!!next-token; |
!!!next-token; |
| 3815 |
return; |
return; |
| 3826 |
last INSCOPE; |
last INSCOPE; |
| 3827 |
} else { # in open elements but not in scope |
} else { # in open elements but not in scope |
| 3828 |
!!!cp ('t55'); |
!!!cp ('t55'); |
| 3829 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, |
!!!parse-error (type => 'unmatched end tag', |
| 3830 |
|
text => $token->{tag_name}, |
| 3831 |
token => $end_tag_token); |
token => $end_tag_token); |
| 3832 |
## Ignore the token |
## Ignore the token |
| 3833 |
!!!next-token; |
!!!next-token; |
| 3840 |
} # INSCOPE |
} # INSCOPE |
| 3841 |
unless (defined $formatting_element_i_in_open) { |
unless (defined $formatting_element_i_in_open) { |
| 3842 |
!!!cp ('t57'); |
!!!cp ('t57'); |
| 3843 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, |
!!!parse-error (type => 'unmatched end tag', |
| 3844 |
|
text => $token->{tag_name}, |
| 3845 |
token => $end_tag_token); |
token => $end_tag_token); |
| 3846 |
pop @$active_formatting_elements; # $formatting_element |
pop @$active_formatting_elements; # $formatting_element |
| 3847 |
!!!next-token; ## TODO: ok? |
!!!next-token; ## TODO: ok? |
| 3850 |
if (not $self->{open_elements}->[-1]->[0] eq $formatting_element->[0]) { |
if (not $self->{open_elements}->[-1]->[0] eq $formatting_element->[0]) { |
| 3851 |
!!!cp ('t58'); |
!!!cp ('t58'); |
| 3852 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 3853 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 3854 |
->manakai_local_name, |
->manakai_local_name, |
| 3855 |
token => $end_tag_token); |
token => $end_tag_token); |
| 3856 |
} |
} |
| 4059 |
B: while (1) { |
B: while (1) { |
| 4060 |
if ($token->{type} == DOCTYPE_TOKEN) { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 4061 |
!!!cp ('t73'); |
!!!cp ('t73'); |
| 4062 |
!!!parse-error (type => 'DOCTYPE in the middle', token => $token); |
!!!parse-error (type => 'in html:#DOCTYPE', token => $token); |
| 4063 |
## Ignore the token |
## Ignore the token |
| 4064 |
## Stay in the phase |
## Stay in the phase |
| 4065 |
!!!next-token; |
!!!next-token; |
| 4068 |
$token->{tag_name} eq 'html') { |
$token->{tag_name} eq 'html') { |
| 4069 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 4070 |
!!!cp ('t79'); |
!!!cp ('t79'); |
| 4071 |
!!!parse-error (type => 'after html:html', token => $token); |
!!!parse-error (type => 'after html', text => 'html', token => $token); |
| 4072 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 4073 |
} elsif ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 4074 |
!!!cp ('t80'); |
!!!cp ('t80'); |
| 4075 |
!!!parse-error (type => 'after html:html', token => $token); |
!!!parse-error (type => 'after html', text => 'html', token => $token); |
| 4076 |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 4077 |
} else { |
} else { |
| 4078 |
!!!cp ('t81'); |
!!!cp ('t81'); |
| 4123 |
# |
# |
| 4124 |
} elsif ({ |
} elsif ({ |
| 4125 |
b => 1, big => 1, blockquote => 1, body => 1, br => 1, |
b => 1, big => 1, blockquote => 1, body => 1, br => 1, |
| 4126 |
center => 1, code => 1, dd => 1, div => 1, dl => 1, em => 1, |
center => 1, code => 1, dd => 1, div => 1, dl => 1, dt => 1, |
| 4127 |
embed => 1, font => 1, h1 => 1, h2 => 1, h3 => 1, ## No h4! |
em => 1, embed => 1, font => 1, h1 => 1, h2 => 1, h3 => 1, |
| 4128 |
h5 => 1, h6 => 1, head => 1, hr => 1, i => 1, img => 1, |
h4 => 1, h5 => 1, h6 => 1, head => 1, hr => 1, i => 1, |
| 4129 |
li => 1, menu => 1, meta => 1, nobr => 1, p => 1, pre => 1, |
img => 1, li => 1, listing => 1, menu => 1, meta => 1, |
| 4130 |
ruby => 1, s => 1, small => 1, span => 1, strong => 1, |
nobr => 1, ol => 1, p => 1, pre => 1, ruby => 1, s => 1, |
| 4131 |
sub => 1, sup => 1, table => 1, tt => 1, u => 1, ul => 1, |
small => 1, span => 1, strong => 1, strike => 1, sub => 1, |
| 4132 |
var => 1, |
sup => 1, table => 1, tt => 1, u => 1, ul => 1, var => 1, |
| 4133 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 4134 |
!!!cp ('t87.2'); |
!!!cp ('t87.2'); |
| 4135 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 4136 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 4137 |
->manakai_local_name, |
->manakai_local_name, |
| 4138 |
token => $token); |
token => $token); |
| 4139 |
|
|
| 4209 |
!!!cp ('t87.5'); |
!!!cp ('t87.5'); |
| 4210 |
# |
# |
| 4211 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
|
## NOTE: "using the rules for secondary insertion mode" then "continue" |
|
| 4212 |
!!!cp ('t87.6'); |
!!!cp ('t87.6'); |
| 4213 |
# |
!!!parse-error (type => 'not closed', |
| 4214 |
## TODO: ... |
text => $self->{open_elements}->[-1]->[0] |
| 4215 |
|
->manakai_local_name, |
| 4216 |
|
token => $token); |
| 4217 |
|
|
| 4218 |
|
pop @{$self->{open_elements}} |
| 4219 |
|
while $self->{open_elements}->[-1]->[1] & FOREIGN_EL; |
| 4220 |
|
|
| 4221 |
|
$self->{insertion_mode} &= ~ IN_FOREIGN_CONTENT_IM; |
| 4222 |
|
## Reprocess. |
| 4223 |
|
next B; |
| 4224 |
} else { |
} else { |
| 4225 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 4226 |
} |
} |
| 4261 |
!!!cp ('t90'); |
!!!cp ('t90'); |
| 4262 |
## As if </noscript> |
## As if </noscript> |
| 4263 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4264 |
!!!parse-error (type => 'in noscript:#character', token => $token); |
!!!parse-error (type => 'in noscript:#text', token => $token); |
| 4265 |
|
|
| 4266 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4267 |
## As if </head> |
## As if </head> |
| 4298 |
next B; |
next B; |
| 4299 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4300 |
!!!cp ('t93.2'); |
!!!cp ('t93.2'); |
| 4301 |
!!!parse-error (type => 'after head:head', token => $token); ## TODO: error type |
!!!parse-error (type => 'after head', text => 'head', |
| 4302 |
|
token => $token); |
| 4303 |
## Ignore the token |
## Ignore the token |
| 4304 |
!!!nack ('t93.3'); |
!!!nack ('t93.3'); |
| 4305 |
!!!next-token; |
!!!next-token; |
| 4306 |
next B; |
next B; |
| 4307 |
} else { |
} else { |
| 4308 |
!!!cp ('t95'); |
!!!cp ('t95'); |
| 4309 |
!!!parse-error (type => 'in head:head', token => $token); # or in head noscript |
!!!parse-error (type => 'in head:head', |
| 4310 |
|
token => $token); # or in head noscript |
| 4311 |
## Ignore the token |
## Ignore the token |
| 4312 |
!!!nack ('t95.1'); |
!!!nack ('t95.1'); |
| 4313 |
!!!next-token; |
!!!next-token; |
| 4332 |
!!!cp ('t98'); |
!!!cp ('t98'); |
| 4333 |
## As if </noscript> |
## As if </noscript> |
| 4334 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4335 |
!!!parse-error (type => 'in noscript:base', token => $token); |
!!!parse-error (type => 'in noscript', text => 'base', |
| 4336 |
|
token => $token); |
| 4337 |
|
|
| 4338 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4339 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4344 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4345 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4346 |
!!!cp ('t100'); |
!!!cp ('t100'); |
| 4347 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4348 |
|
text => $token->{tag_name}, token => $token); |
| 4349 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4350 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4351 |
} else { |
} else { |
| 4362 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4363 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4364 |
!!!cp ('t102'); |
!!!cp ('t102'); |
| 4365 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4366 |
|
text => $token->{tag_name}, token => $token); |
| 4367 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4368 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4369 |
} else { |
} else { |
| 4380 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4381 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4382 |
!!!cp ('t104'); |
!!!cp ('t104'); |
| 4383 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4384 |
|
text => $token->{tag_name}, token => $token); |
| 4385 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4386 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4387 |
} else { |
} else { |
| 4450 |
!!!cp ('t111'); |
!!!cp ('t111'); |
| 4451 |
## As if </noscript> |
## As if </noscript> |
| 4452 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4453 |
!!!parse-error (type => 'in noscript:title', token => $token); |
!!!parse-error (type => 'in noscript', text => 'title', |
| 4454 |
|
token => $token); |
| 4455 |
|
|
| 4456 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4457 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4458 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4459 |
!!!cp ('t112'); |
!!!cp ('t112'); |
| 4460 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4461 |
|
text => $token->{tag_name}, token => $token); |
| 4462 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4463 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4464 |
} else { |
} else { |
| 4472 |
pop @{$self->{open_elements}} # <head> |
pop @{$self->{open_elements}} # <head> |
| 4473 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 4474 |
next B; |
next B; |
| 4475 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($token->{tag_name} eq 'style' or |
| 4476 |
|
$token->{tag_name} eq 'noframes') { |
| 4477 |
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
| 4478 |
## insertion mode IN_HEAD_IM) |
## insertion mode IN_HEAD_IM) |
| 4479 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4480 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4481 |
!!!cp ('t114'); |
!!!cp ('t114'); |
| 4482 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4483 |
|
text => $token->{tag_name}, token => $token); |
| 4484 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4485 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4486 |
} else { |
} else { |
| 4501 |
next B; |
next B; |
| 4502 |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4503 |
!!!cp ('t117'); |
!!!cp ('t117'); |
| 4504 |
!!!parse-error (type => 'in noscript:noscript', token => $token); |
!!!parse-error (type => 'in noscript', text => 'noscript', |
| 4505 |
|
token => $token); |
| 4506 |
## Ignore the token |
## Ignore the token |
| 4507 |
!!!nack ('t117.1'); |
!!!nack ('t117.1'); |
| 4508 |
!!!next-token; |
!!!next-token; |
| 4516 |
!!!cp ('t119'); |
!!!cp ('t119'); |
| 4517 |
## As if </noscript> |
## As if </noscript> |
| 4518 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4519 |
!!!parse-error (type => 'in noscript:script', token => $token); |
!!!parse-error (type => 'in noscript', text => 'script', |
| 4520 |
|
token => $token); |
| 4521 |
|
|
| 4522 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4523 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4524 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4525 |
!!!cp ('t120'); |
!!!cp ('t120'); |
| 4526 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4527 |
|
text => $token->{tag_name}, token => $token); |
| 4528 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4529 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4530 |
} else { |
} else { |
| 4542 |
!!!cp ('t122'); |
!!!cp ('t122'); |
| 4543 |
## As if </noscript> |
## As if </noscript> |
| 4544 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4545 |
!!!parse-error (type => 'in noscript:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in noscript', |
| 4546 |
|
text => $token->{tag_name}, token => $token); |
| 4547 |
|
|
| 4548 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4549 |
## As if </head> |
## As if </head> |
| 4582 |
!!!cp ('t129'); |
!!!cp ('t129'); |
| 4583 |
## As if </noscript> |
## As if </noscript> |
| 4584 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4585 |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in noscript:/', |
| 4586 |
|
text => $token->{tag_name}, token => $token); |
| 4587 |
|
|
| 4588 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4589 |
## As if </head> |
## As if </head> |
| 4626 |
!!!cp ('t133'); |
!!!cp ('t133'); |
| 4627 |
## As if </noscript> |
## As if </noscript> |
| 4628 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4629 |
!!!parse-error (type => 'in noscript:/head', token => $token); |
!!!parse-error (type => 'in noscript:/', |
| 4630 |
|
text => 'head', token => $token); |
| 4631 |
|
|
| 4632 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4633 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4642 |
next B; |
next B; |
| 4643 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4644 |
!!!cp ('t134.1'); |
!!!cp ('t134.1'); |
| 4645 |
!!!parse-error (type => 'unmatched end tag:head', token => $token); |
!!!parse-error (type => 'unmatched end tag', text => 'head', |
| 4646 |
|
token => $token); |
| 4647 |
## Ignore the token |
## Ignore the token |
| 4648 |
!!!next-token; |
!!!next-token; |
| 4649 |
next B; |
next B; |
| 4660 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM or |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM or |
| 4661 |
$self->{insertion_mode} == AFTER_HEAD_IM) { |
$self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4662 |
!!!cp ('t137'); |
!!!cp ('t137'); |
| 4663 |
!!!parse-error (type => 'unmatched end tag:noscript', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4664 |
|
text => 'noscript', token => $token); |
| 4665 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 4666 |
!!!next-token; |
!!!next-token; |
| 4667 |
next B; |
next B; |
| 4676 |
$self->{insertion_mode} == IN_HEAD_IM or |
$self->{insertion_mode} == IN_HEAD_IM or |
| 4677 |
$self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
$self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4678 |
!!!cp ('t140'); |
!!!cp ('t140'); |
| 4679 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4680 |
|
text => $token->{tag_name}, token => $token); |
| 4681 |
## Ignore the token |
## Ignore the token |
| 4682 |
!!!next-token; |
!!!next-token; |
| 4683 |
next B; |
next B; |
| 4684 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4685 |
!!!cp ('t140.1'); |
!!!cp ('t140.1'); |
| 4686 |
!!!parse-error (type => 'unmatched end tag:' . $token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4687 |
|
text => $token->{tag_name}, token => $token); |
| 4688 |
## Ignore the token |
## Ignore the token |
| 4689 |
!!!next-token; |
!!!next-token; |
| 4690 |
next B; |
next B; |
| 4693 |
} |
} |
| 4694 |
} elsif ($token->{tag_name} eq 'p') { |
} elsif ($token->{tag_name} eq 'p') { |
| 4695 |
!!!cp ('t142'); |
!!!cp ('t142'); |
| 4696 |
!!!parse-error (type => 'unmatched end tag:p', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4697 |
|
text => $token->{tag_name}, token => $token); |
| 4698 |
## Ignore the token |
## Ignore the token |
| 4699 |
!!!next-token; |
!!!next-token; |
| 4700 |
next B; |
next B; |
| 4717 |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4718 |
!!!cp ('t143.3'); |
!!!cp ('t143.3'); |
| 4719 |
## ISSUE: Two parse errors for <head><noscript></br> |
## ISSUE: Two parse errors for <head><noscript></br> |
| 4720 |
!!!parse-error (type => 'unmatched end tag:br', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4721 |
|
text => 'br', token => $token); |
| 4722 |
## As if </noscript> |
## As if </noscript> |
| 4723 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4724 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4737 |
} |
} |
| 4738 |
|
|
| 4739 |
## ISSUE: does not agree with IE7 - it doesn't ignore </br>. |
## ISSUE: does not agree with IE7 - it doesn't ignore </br>. |
| 4740 |
!!!parse-error (type => 'unmatched end tag:br', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4741 |
|
text => 'br', token => $token); |
| 4742 |
## Ignore the token |
## Ignore the token |
| 4743 |
!!!next-token; |
!!!next-token; |
| 4744 |
next B; |
next B; |
| 4745 |
} else { |
} else { |
| 4746 |
!!!cp ('t145'); |
!!!cp ('t145'); |
| 4747 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4748 |
|
text => $token->{tag_name}, token => $token); |
| 4749 |
## Ignore the token |
## Ignore the token |
| 4750 |
!!!next-token; |
!!!next-token; |
| 4751 |
next B; |
next B; |
| 4755 |
!!!cp ('t146'); |
!!!cp ('t146'); |
| 4756 |
## As if </noscript> |
## As if </noscript> |
| 4757 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4758 |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in noscript:/', |
| 4759 |
|
text => $token->{tag_name}, token => $token); |
| 4760 |
|
|
| 4761 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4762 |
## As if </head> |
## As if </head> |
| 4772 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4773 |
## ISSUE: This case cannot be reached? |
## ISSUE: This case cannot be reached? |
| 4774 |
!!!cp ('t148'); |
!!!cp ('t148'); |
| 4775 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4776 |
|
text => $token->{tag_name}, token => $token); |
| 4777 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 4778 |
!!!next-token; |
!!!next-token; |
| 4779 |
next B; |
next B; |
| 4884 |
|
|
| 4885 |
!!!cp ('t153'); |
!!!cp ('t153'); |
| 4886 |
!!!parse-error (type => 'start tag not allowed', |
!!!parse-error (type => 'start tag not allowed', |
| 4887 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 4888 |
## Ignore the token |
## Ignore the token |
| 4889 |
!!!nack ('t153.1'); |
!!!nack ('t153.1'); |
| 4890 |
!!!next-token; |
!!!next-token; |
| 4891 |
next B; |
next B; |
| 4892 |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 4893 |
!!!parse-error (type => 'not closed:caption', token => $token); |
!!!parse-error (type => 'not closed', text => 'caption', |
| 4894 |
|
token => $token); |
| 4895 |
|
|
| 4896 |
## NOTE: As if </caption>. |
## NOTE: As if </caption>. |
| 4897 |
## have a table element in table scope |
## have a table element in table scope |
| 4911 |
|
|
| 4912 |
!!!cp ('t157'); |
!!!cp ('t157'); |
| 4913 |
!!!parse-error (type => 'start tag not allowed', |
!!!parse-error (type => 'start tag not allowed', |
| 4914 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 4915 |
## Ignore the token |
## Ignore the token |
| 4916 |
!!!nack ('t157.1'); |
!!!nack ('t157.1'); |
| 4917 |
!!!next-token; |
!!!next-token; |
| 4928 |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
| 4929 |
!!!cp ('t159'); |
!!!cp ('t159'); |
| 4930 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 4931 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 4932 |
->manakai_local_name, |
->manakai_local_name, |
| 4933 |
token => $token); |
token => $token); |
| 4934 |
} else { |
} else { |
| 4970 |
} # INSCOPE |
} # INSCOPE |
| 4971 |
unless (defined $i) { |
unless (defined $i) { |
| 4972 |
!!!cp ('t165'); |
!!!cp ('t165'); |
| 4973 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4974 |
|
text => $token->{tag_name}, |
| 4975 |
|
token => $token); |
| 4976 |
## Ignore the token |
## Ignore the token |
| 4977 |
!!!next-token; |
!!!next-token; |
| 4978 |
next B; |
next B; |
| 4989 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 4990 |
!!!cp ('t167'); |
!!!cp ('t167'); |
| 4991 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 4992 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 4993 |
->manakai_local_name, |
->manakai_local_name, |
| 4994 |
token => $token); |
token => $token); |
| 4995 |
} else { |
} else { |
| 5006 |
next B; |
next B; |
| 5007 |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 5008 |
!!!cp ('t169'); |
!!!cp ('t169'); |
| 5009 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5010 |
|
text => $token->{tag_name}, token => $token); |
| 5011 |
## Ignore the token |
## Ignore the token |
| 5012 |
!!!next-token; |
!!!next-token; |
| 5013 |
next B; |
next B; |
| 5034 |
|
|
| 5035 |
!!!cp ('t173'); |
!!!cp ('t173'); |
| 5036 |
!!!parse-error (type => 'unmatched end tag', |
!!!parse-error (type => 'unmatched end tag', |
| 5037 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 5038 |
## Ignore the token |
## Ignore the token |
| 5039 |
!!!next-token; |
!!!next-token; |
| 5040 |
next B; |
next B; |
| 5050 |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
| 5051 |
!!!cp ('t175'); |
!!!cp ('t175'); |
| 5052 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5053 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5054 |
->manakai_local_name, |
->manakai_local_name, |
| 5055 |
token => $token); |
token => $token); |
| 5056 |
} else { |
} else { |
| 5067 |
next B; |
next B; |
| 5068 |
} elsif ($self->{insertion_mode} == IN_CELL_IM) { |
} elsif ($self->{insertion_mode} == IN_CELL_IM) { |
| 5069 |
!!!cp ('t177'); |
!!!cp ('t177'); |
| 5070 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5071 |
|
text => $token->{tag_name}, token => $token); |
| 5072 |
## Ignore the token |
## Ignore the token |
| 5073 |
!!!next-token; |
!!!next-token; |
| 5074 |
next B; |
next B; |
| 5111 |
|
|
| 5112 |
!!!cp ('t182'); |
!!!cp ('t182'); |
| 5113 |
!!!parse-error (type => 'unmatched end tag', |
!!!parse-error (type => 'unmatched end tag', |
| 5114 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 5115 |
## Ignore the token |
## Ignore the token |
| 5116 |
!!!next-token; |
!!!next-token; |
| 5117 |
next B; |
next B; |
| 5118 |
} # INSCOPE |
} # INSCOPE |
| 5119 |
} elsif ($token->{tag_name} eq 'table' and |
} elsif ($token->{tag_name} eq 'table' and |
| 5120 |
$self->{insertion_mode} == IN_CAPTION_IM) { |
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 5121 |
!!!parse-error (type => 'not closed:caption', token => $token); |
!!!parse-error (type => 'not closed', text => 'caption', |
| 5122 |
|
token => $token); |
| 5123 |
|
|
| 5124 |
## As if </caption> |
## As if </caption> |
| 5125 |
## have a table element in table scope |
## have a table element in table scope |
| 5137 |
} # INSCOPE |
} # INSCOPE |
| 5138 |
unless (defined $i) { |
unless (defined $i) { |
| 5139 |
!!!cp ('t186'); |
!!!cp ('t186'); |
| 5140 |
!!!parse-error (type => 'unmatched end tag:caption', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5141 |
|
text => 'caption', token => $token); |
| 5142 |
## Ignore the token |
## Ignore the token |
| 5143 |
!!!next-token; |
!!!next-token; |
| 5144 |
next B; |
next B; |
| 5153 |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
| 5154 |
!!!cp ('t188'); |
!!!cp ('t188'); |
| 5155 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5156 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5157 |
->manakai_local_name, |
->manakai_local_name, |
| 5158 |
token => $token); |
token => $token); |
| 5159 |
} else { |
} else { |
| 5173 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5174 |
if ($self->{insertion_mode} & BODY_TABLE_IMS) { |
if ($self->{insertion_mode} & BODY_TABLE_IMS) { |
| 5175 |
!!!cp ('t190'); |
!!!cp ('t190'); |
| 5176 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5177 |
|
text => $token->{tag_name}, token => $token); |
| 5178 |
## Ignore the token |
## Ignore the token |
| 5179 |
!!!next-token; |
!!!next-token; |
| 5180 |
next B; |
next B; |
| 5188 |
}->{$token->{tag_name}} and |
}->{$token->{tag_name}} and |
| 5189 |
$self->{insertion_mode} == IN_CAPTION_IM) { |
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 5190 |
!!!cp ('t192'); |
!!!cp ('t192'); |
| 5191 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5192 |
|
text => $token->{tag_name}, token => $token); |
| 5193 |
## Ignore the token |
## Ignore the token |
| 5194 |
!!!next-token; |
!!!next-token; |
| 5195 |
next B; |
next B; |
| 5229 |
} |
} |
| 5230 |
} |
} |
| 5231 |
|
|
| 5232 |
!!!parse-error (type => 'in table:#character', token => $token); |
!!!parse-error (type => 'in table:#text', token => $token); |
| 5233 |
|
|
| 5234 |
## As if in body, but insert into foster parent element |
## As if in body, but insert into foster parent element |
| 5235 |
## ISSUE: Spec says that "whenever a node would be inserted |
## ISSUE: Spec says that "whenever a node would be inserted |
| 5280 |
!!!next-token; |
!!!next-token; |
| 5281 |
next B; |
next B; |
| 5282 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 5283 |
if ({ |
if ({ |
| 5284 |
tr => ($self->{insertion_mode} != IN_ROW_IM), |
tr => ($self->{insertion_mode} != IN_ROW_IM), |
| 5285 |
th => 1, td => 1, |
th => 1, td => 1, |
| 5286 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5287 |
if ($self->{insertion_mode} == IN_TABLE_IM) { |
if ($self->{insertion_mode} == IN_TABLE_IM) { |
| 5288 |
## Clear back to table context |
## Clear back to table context |
| 5289 |
while (not ($self->{open_elements}->[-1]->[1] |
while (not ($self->{open_elements}->[-1]->[1] |
| 5290 |
& TABLE_SCOPING_EL)) { |
& TABLE_SCOPING_EL)) { |
| 5291 |
!!!cp ('t201'); |
!!!cp ('t201'); |
| 5292 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5293 |
} |
} |
| 5294 |
|
|
| 5295 |
!!!insert-element ('tbody',, $token); |
!!!insert-element ('tbody',, $token); |
| 5296 |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 5297 |
## reprocess in the "in table body" insertion mode... |
## reprocess in the "in table body" insertion mode... |
| 5298 |
} |
} |
| 5299 |
|
|
| 5300 |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
| 5301 |
unless ($token->{tag_name} eq 'tr') { |
unless ($token->{tag_name} eq 'tr') { |
| 5302 |
!!!cp ('t202'); |
!!!cp ('t202'); |
| 5303 |
!!!parse-error (type => 'missing start tag:tr', token => $token); |
!!!parse-error (type => 'missing start tag:tr', token => $token); |
| 5304 |
} |
} |
| 5305 |
|
|
| 5306 |
## Clear back to table body context |
## Clear back to table body context |
| 5307 |
while (not ($self->{open_elements}->[-1]->[1] |
while (not ($self->{open_elements}->[-1]->[1] |
| 5308 |
& TABLE_ROWS_SCOPING_EL)) { |
& TABLE_ROWS_SCOPING_EL)) { |
| 5309 |
!!!cp ('t203'); |
!!!cp ('t203'); |
| 5310 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
| 5311 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5312 |
} |
} |
| 5313 |
|
|
| 5314 |
$self->{insertion_mode} = IN_ROW_IM; |
$self->{insertion_mode} = IN_ROW_IM; |
| 5315 |
if ($token->{tag_name} eq 'tr') { |
if ($token->{tag_name} eq 'tr') { |
| 5365 |
unless (defined $i) { |
unless (defined $i) { |
| 5366 |
!!!cp ('t210'); |
!!!cp ('t210'); |
| 5367 |
## TODO: This type is wrong. |
## TODO: This type is wrong. |
| 5368 |
!!!parse-error (type => 'unmacthed end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmacthed end tag', |
| 5369 |
|
text => $token->{tag_name}, token => $token); |
| 5370 |
## Ignore the token |
## Ignore the token |
| 5371 |
!!!nack ('t210.1'); |
!!!nack ('t210.1'); |
| 5372 |
!!!next-token; |
!!!next-token; |
| 5410 |
} # INSCOPE |
} # INSCOPE |
| 5411 |
unless (defined $i) { |
unless (defined $i) { |
| 5412 |
!!!cp ('t216'); |
!!!cp ('t216'); |
| 5413 |
## TODO: This erorr type ios wrong. |
## TODO: This erorr type is wrong. |
| 5414 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5415 |
|
text => $token->{tag_name}, token => $token); |
| 5416 |
## Ignore the token |
## Ignore the token |
| 5417 |
!!!nack ('t216.1'); |
!!!nack ('t216.1'); |
| 5418 |
!!!next-token; |
!!!next-token; |
| 5487 |
} |
} |
| 5488 |
} elsif ($token->{tag_name} eq 'table') { |
} elsif ($token->{tag_name} eq 'table') { |
| 5489 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5490 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5491 |
->manakai_local_name, |
->manakai_local_name, |
| 5492 |
token => $token); |
token => $token); |
| 5493 |
|
|
| 5508 |
unless (defined $i) { |
unless (defined $i) { |
| 5509 |
!!!cp ('t223'); |
!!!cp ('t223'); |
| 5510 |
## TODO: The following is wrong, maybe. |
## TODO: The following is wrong, maybe. |
| 5511 |
!!!parse-error (type => 'unmatched end tag:table', token => $token); |
!!!parse-error (type => 'unmatched end tag', text => 'table', |
| 5512 |
|
token => $token); |
| 5513 |
## Ignore tokens </table><table> |
## Ignore tokens </table><table> |
| 5514 |
!!!nack ('t223.1'); |
!!!nack ('t223.1'); |
| 5515 |
!!!next-token; |
!!!next-token; |
| 5516 |
next B; |
next B; |
| 5517 |
} |
} |
| 5518 |
|
|
| 5519 |
## TODO: Followings are removed from the latest spec. |
## TODO: Followings are removed from the latest spec. |
| 5520 |
## generate implied end tags |
## generate implied end tags |
| 5521 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 5522 |
!!!cp ('t224'); |
!!!cp ('t224'); |
| 5527 |
!!!cp ('t225'); |
!!!cp ('t225'); |
| 5528 |
## NOTE: |<table><tr><table>| |
## NOTE: |<table><tr><table>| |
| 5529 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5530 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5531 |
->manakai_local_name, |
->manakai_local_name, |
| 5532 |
token => $token); |
token => $token); |
| 5533 |
} else { |
} else { |
| 5568 |
my $type = lc $token->{attributes}->{type}->{value}; |
my $type = lc $token->{attributes}->{type}->{value}; |
| 5569 |
if ($type eq 'hidden') { |
if ($type eq 'hidden') { |
| 5570 |
!!!cp ('t227.3'); |
!!!cp ('t227.3'); |
| 5571 |
!!!parse-error (type => 'in table:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in table', |
| 5572 |
|
text => $token->{tag_name}, token => $token); |
| 5573 |
|
|
| 5574 |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5575 |
|
|
| 5597 |
# |
# |
| 5598 |
} |
} |
| 5599 |
|
|
| 5600 |
!!!parse-error (type => 'in table:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in table', text => $token->{tag_name}, |
| 5601 |
|
token => $token); |
| 5602 |
|
|
| 5603 |
$insert = $insert_to_foster; |
$insert = $insert_to_foster; |
| 5604 |
# |
# |
| 5620 |
} # INSCOPE |
} # INSCOPE |
| 5621 |
unless (defined $i) { |
unless (defined $i) { |
| 5622 |
!!!cp ('t230'); |
!!!cp ('t230'); |
| 5623 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5624 |
|
text => $token->{tag_name}, token => $token); |
| 5625 |
## Ignore the token |
## Ignore the token |
| 5626 |
!!!nack ('t230.1'); |
!!!nack ('t230.1'); |
| 5627 |
!!!next-token; |
!!!next-token; |
| 5662 |
unless (defined $i) { |
unless (defined $i) { |
| 5663 |
!!!cp ('t235'); |
!!!cp ('t235'); |
| 5664 |
## TODO: The following is wrong. |
## TODO: The following is wrong. |
| 5665 |
!!!parse-error (type => 'unmatched end tag:'.$token->{type}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5666 |
|
text => $token->{type}, token => $token); |
| 5667 |
## Ignore the token |
## Ignore the token |
| 5668 |
!!!nack ('t236.1'); |
!!!nack ('t236.1'); |
| 5669 |
!!!next-token; |
!!!next-token; |
| 5699 |
} # INSCOPE |
} # INSCOPE |
| 5700 |
unless (defined $i) { |
unless (defined $i) { |
| 5701 |
!!!cp ('t239'); |
!!!cp ('t239'); |
| 5702 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5703 |
|
text => $token->{tag_name}, token => $token); |
| 5704 |
## Ignore the token |
## Ignore the token |
| 5705 |
!!!nack ('t239.1'); |
!!!nack ('t239.1'); |
| 5706 |
!!!next-token; |
!!!next-token; |
| 5746 |
} # INSCOPE |
} # INSCOPE |
| 5747 |
unless (defined $i) { |
unless (defined $i) { |
| 5748 |
!!!cp ('t243'); |
!!!cp ('t243'); |
| 5749 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5750 |
|
text => $token->{tag_name}, token => $token); |
| 5751 |
## Ignore the token |
## Ignore the token |
| 5752 |
!!!nack ('t243.1'); |
!!!nack ('t243.1'); |
| 5753 |
!!!next-token; |
!!!next-token; |
| 5781 |
} # INSCOPE |
} # INSCOPE |
| 5782 |
unless (defined $i) { |
unless (defined $i) { |
| 5783 |
!!!cp ('t249'); |
!!!cp ('t249'); |
| 5784 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5785 |
|
text => $token->{tag_name}, token => $token); |
| 5786 |
## Ignore the token |
## Ignore the token |
| 5787 |
!!!nack ('t249.1'); |
!!!nack ('t249.1'); |
| 5788 |
!!!next-token; |
!!!next-token; |
| 5805 |
} # INSCOPE |
} # INSCOPE |
| 5806 |
unless (defined $i) { |
unless (defined $i) { |
| 5807 |
!!!cp ('t252'); |
!!!cp ('t252'); |
| 5808 |
!!!parse-error (type => 'unmatched end tag:tr', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5809 |
|
text => 'tr', token => $token); |
| 5810 |
## Ignore the token |
## Ignore the token |
| 5811 |
!!!nack ('t252.1'); |
!!!nack ('t252.1'); |
| 5812 |
!!!next-token; |
!!!next-token; |
| 5841 |
} # INSCOPE |
} # INSCOPE |
| 5842 |
unless (defined $i) { |
unless (defined $i) { |
| 5843 |
!!!cp ('t256'); |
!!!cp ('t256'); |
| 5844 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5845 |
|
text => $token->{tag_name}, token => $token); |
| 5846 |
## Ignore the token |
## Ignore the token |
| 5847 |
!!!nack ('t256.1'); |
!!!nack ('t256.1'); |
| 5848 |
!!!next-token; |
!!!next-token; |
| 5869 |
tbody => 1, tfoot => 1, thead => 1, # $self->{insertion_mode} == IN_TABLE_IM |
tbody => 1, tfoot => 1, thead => 1, # $self->{insertion_mode} == IN_TABLE_IM |
| 5870 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5871 |
!!!cp ('t258'); |
!!!cp ('t258'); |
| 5872 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5873 |
|
text => $token->{tag_name}, token => $token); |
| 5874 |
## Ignore the token |
## Ignore the token |
| 5875 |
!!!nack ('t258.1'); |
!!!nack ('t258.1'); |
| 5876 |
!!!next-token; |
!!!next-token; |
| 5877 |
next B; |
next B; |
| 5878 |
} else { |
} else { |
| 5879 |
!!!cp ('t259'); |
!!!cp ('t259'); |
| 5880 |
!!!parse-error (type => 'in table:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in table:/', |
| 5881 |
|
text => $token->{tag_name}, token => $token); |
| 5882 |
|
|
| 5883 |
$insert = $insert_to_foster; |
$insert = $insert_to_foster; |
| 5884 |
# |
# |
| 5928 |
if ($token->{tag_name} eq 'colgroup') { |
if ($token->{tag_name} eq 'colgroup') { |
| 5929 |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
| 5930 |
!!!cp ('t264'); |
!!!cp ('t264'); |
| 5931 |
!!!parse-error (type => 'unmatched end tag:colgroup', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5932 |
|
text => 'colgroup', token => $token); |
| 5933 |
## Ignore the token |
## Ignore the token |
| 5934 |
!!!next-token; |
!!!next-token; |
| 5935 |
next B; |
next B; |
| 5942 |
} |
} |
| 5943 |
} elsif ($token->{tag_name} eq 'col') { |
} elsif ($token->{tag_name} eq 'col') { |
| 5944 |
!!!cp ('t266'); |
!!!cp ('t266'); |
| 5945 |
!!!parse-error (type => 'unmatched end tag:col', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5946 |
|
text => 'col', token => $token); |
| 5947 |
## Ignore the token |
## Ignore the token |
| 5948 |
!!!next-token; |
!!!next-token; |
| 5949 |
next B; |
next B; |
| 5973 |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
| 5974 |
!!!cp ('t269'); |
!!!cp ('t269'); |
| 5975 |
## TODO: Wrong error type? |
## TODO: Wrong error type? |
| 5976 |
!!!parse-error (type => 'unmatched end tag:colgroup', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5977 |
|
text => 'colgroup', token => $token); |
| 5978 |
## Ignore the token |
## Ignore the token |
| 5979 |
!!!nack ('t269.1'); |
!!!nack ('t269.1'); |
| 5980 |
!!!next-token; |
!!!next-token; |
| 6028 |
!!!nack ('t277.1'); |
!!!nack ('t277.1'); |
| 6029 |
!!!next-token; |
!!!next-token; |
| 6030 |
next B; |
next B; |
| 6031 |
} elsif ($token->{tag_name} eq 'select' or |
} elsif ({ |
| 6032 |
$token->{tag_name} eq 'input' or |
select => 1, input => 1, textarea => 1, |
| 6033 |
|
}->{$token->{tag_name}} or |
| 6034 |
($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
| 6035 |
{ |
{ |
| 6036 |
caption => 1, table => 1, |
caption => 1, table => 1, |
| 6038 |
tr => 1, td => 1, th => 1, |
tr => 1, td => 1, th => 1, |
| 6039 |
}->{$token->{tag_name}})) { |
}->{$token->{tag_name}})) { |
| 6040 |
## TODO: The type below is not good - <select> is replaced by </select> |
## TODO: The type below is not good - <select> is replaced by </select> |
| 6041 |
!!!parse-error (type => 'not closed:select', token => $token); |
!!!parse-error (type => 'not closed', text => 'select', |
| 6042 |
|
token => $token); |
| 6043 |
## NOTE: As if the token were </select> (<select> case) or |
## NOTE: As if the token were </select> (<select> case) or |
| 6044 |
## as if there were </select> (otherwise). |
## as if there were </select> (otherwise). |
| 6045 |
## have an element in table scope |
## have an element in table scope |
| 6057 |
} # INSCOPE |
} # INSCOPE |
| 6058 |
unless (defined $i) { |
unless (defined $i) { |
| 6059 |
!!!cp ('t280'); |
!!!cp ('t280'); |
| 6060 |
!!!parse-error (type => 'unmatched end tag:select', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6061 |
|
text => 'select', token => $token); |
| 6062 |
## Ignore the token |
## Ignore the token |
| 6063 |
!!!nack ('t280.1'); |
!!!nack ('t280.1'); |
| 6064 |
!!!next-token; |
!!!next-token; |
| 6082 |
} |
} |
| 6083 |
} else { |
} else { |
| 6084 |
!!!cp ('t282'); |
!!!cp ('t282'); |
| 6085 |
!!!parse-error (type => 'in select:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in select', |
| 6086 |
|
text => $token->{tag_name}, token => $token); |
| 6087 |
## Ignore the token |
## Ignore the token |
| 6088 |
!!!nack ('t282.1'); |
!!!nack ('t282.1'); |
| 6089 |
!!!next-token; |
!!!next-token; |
| 6101 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 6102 |
} else { |
} else { |
| 6103 |
!!!cp ('t285'); |
!!!cp ('t285'); |
| 6104 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6105 |
|
text => $token->{tag_name}, token => $token); |
| 6106 |
## Ignore the token |
## Ignore the token |
| 6107 |
} |
} |
| 6108 |
!!!nack ('t285.1'); |
!!!nack ('t285.1'); |
| 6114 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 6115 |
} else { |
} else { |
| 6116 |
!!!cp ('t287'); |
!!!cp ('t287'); |
| 6117 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6118 |
|
text => $token->{tag_name}, token => $token); |
| 6119 |
## Ignore the token |
## Ignore the token |
| 6120 |
} |
} |
| 6121 |
!!!nack ('t287.1'); |
!!!nack ('t287.1'); |
| 6137 |
} # INSCOPE |
} # INSCOPE |
| 6138 |
unless (defined $i) { |
unless (defined $i) { |
| 6139 |
!!!cp ('t290'); |
!!!cp ('t290'); |
| 6140 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6141 |
|
text => $token->{tag_name}, token => $token); |
| 6142 |
## Ignore the token |
## Ignore the token |
| 6143 |
!!!nack ('t290.1'); |
!!!nack ('t290.1'); |
| 6144 |
!!!next-token; |
!!!next-token; |
| 6159 |
tfoot => 1, thead => 1, tr => 1, td => 1, th => 1, |
tfoot => 1, thead => 1, tr => 1, td => 1, th => 1, |
| 6160 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6161 |
## TODO: The following is wrong? |
## TODO: The following is wrong? |
| 6162 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6163 |
|
text => $token->{tag_name}, token => $token); |
| 6164 |
|
|
| 6165 |
## have an element in table scope |
## have an element in table scope |
| 6166 |
my $i; |
my $i; |
| 6201 |
unless (defined $i) { |
unless (defined $i) { |
| 6202 |
!!!cp ('t297'); |
!!!cp ('t297'); |
| 6203 |
## TODO: The following error type is correct? |
## TODO: The following error type is correct? |
| 6204 |
!!!parse-error (type => 'unmatched end tag:select', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6205 |
|
text => 'select', token => $token); |
| 6206 |
## Ignore the </select> token |
## Ignore the </select> token |
| 6207 |
!!!nack ('t297.1'); |
!!!nack ('t297.1'); |
| 6208 |
!!!next-token; ## TODO: ok? |
!!!next-token; ## TODO: ok? |
| 6219 |
next B; |
next B; |
| 6220 |
} else { |
} else { |
| 6221 |
!!!cp ('t299'); |
!!!cp ('t299'); |
| 6222 |
!!!parse-error (type => 'in select:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in select:/', |
| 6223 |
|
text => $token->{tag_name}, token => $token); |
| 6224 |
## Ignore the token |
## Ignore the token |
| 6225 |
!!!nack ('t299.3'); |
!!!nack ('t299.3'); |
| 6226 |
!!!next-token; |
!!!next-token; |
| 6258 |
|
|
| 6259 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 6260 |
!!!cp ('t301'); |
!!!cp ('t301'); |
| 6261 |
!!!parse-error (type => 'after html:#character', token => $token); |
!!!parse-error (type => 'after html:#text', token => $token); |
| 6262 |
|
|
| 6263 |
## Reprocess in the "after body" insertion mode. |
## Reprocess in the "after body" insertion mode. |
| 6264 |
} else { |
} else { |
| 6266 |
} |
} |
| 6267 |
|
|
| 6268 |
## "after body" insertion mode |
## "after body" insertion mode |
| 6269 |
!!!parse-error (type => 'after body:#character', token => $token); |
!!!parse-error (type => 'after body:#text', token => $token); |
| 6270 |
|
|
| 6271 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 6272 |
## reprocess |
## reprocess |
| 6274 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 6275 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 6276 |
!!!cp ('t303'); |
!!!cp ('t303'); |
| 6277 |
!!!parse-error (type => 'after html:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after html', |
| 6278 |
|
text => $token->{tag_name}, token => $token); |
| 6279 |
|
|
| 6280 |
## Reprocess in the "after body" insertion mode. |
## Reprocess in the "after body" insertion mode. |
| 6281 |
} else { |
} else { |
| 6283 |
} |
} |
| 6284 |
|
|
| 6285 |
## "after body" insertion mode |
## "after body" insertion mode |
| 6286 |
!!!parse-error (type => 'after body:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after body', |
| 6287 |
|
text => $token->{tag_name}, token => $token); |
| 6288 |
|
|
| 6289 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 6290 |
!!!ack-later; |
!!!ack-later; |
| 6293 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 6294 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 6295 |
!!!cp ('t305'); |
!!!cp ('t305'); |
| 6296 |
!!!parse-error (type => 'after html:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after html:/', |
| 6297 |
|
text => $token->{tag_name}, token => $token); |
| 6298 |
|
|
| 6299 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 6300 |
## Reprocess in the "after body" insertion mode. |
## Reprocess in the "after body" insertion mode. |
| 6306 |
if ($token->{tag_name} eq 'html') { |
if ($token->{tag_name} eq 'html') { |
| 6307 |
if (defined $self->{inner_html_node}) { |
if (defined $self->{inner_html_node}) { |
| 6308 |
!!!cp ('t307'); |
!!!cp ('t307'); |
| 6309 |
!!!parse-error (type => 'unmatched end tag:html', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6310 |
|
text => 'html', token => $token); |
| 6311 |
## Ignore the token |
## Ignore the token |
| 6312 |
!!!next-token; |
!!!next-token; |
| 6313 |
next B; |
next B; |
| 6319 |
} |
} |
| 6320 |
} else { |
} else { |
| 6321 |
!!!cp ('t309'); |
!!!cp ('t309'); |
| 6322 |
!!!parse-error (type => 'after body:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after body:/', |
| 6323 |
|
text => $token->{tag_name}, token => $token); |
| 6324 |
|
|
| 6325 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 6326 |
## reprocess |
## reprocess |
| 6348 |
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
| 6349 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6350 |
!!!cp ('t311'); |
!!!cp ('t311'); |
| 6351 |
!!!parse-error (type => 'in frameset:#character', token => $token); |
!!!parse-error (type => 'in frameset:#text', token => $token); |
| 6352 |
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 6353 |
!!!cp ('t312'); |
!!!cp ('t312'); |
| 6354 |
!!!parse-error (type => 'after frameset:#character', token => $token); |
!!!parse-error (type => 'after frameset:#text', token => $token); |
| 6355 |
} else { # "after html frameset" |
} else { # "after after frameset" |
| 6356 |
!!!cp ('t313'); |
!!!cp ('t313'); |
| 6357 |
!!!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); |
|
| 6358 |
} |
} |
| 6359 |
|
|
| 6360 |
## Ignore the token. |
## Ignore the token. |
| 6370 |
|
|
| 6371 |
die qq[$0: Character "$token->{data}"]; |
die qq[$0: Character "$token->{data}"]; |
| 6372 |
} 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); |
|
|
|
|
|
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
|
|
## Process in the "after frameset" insertion mode. |
|
|
} else { |
|
|
!!!cp ('t317'); |
|
|
} |
|
|
|
|
| 6373 |
if ($token->{tag_name} eq 'frameset' and |
if ($token->{tag_name} eq 'frameset' and |
| 6374 |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6375 |
!!!cp ('t318'); |
!!!cp ('t318'); |
| 6387 |
next B; |
next B; |
| 6388 |
} elsif ($token->{tag_name} eq 'noframes') { |
} elsif ($token->{tag_name} eq 'noframes') { |
| 6389 |
!!!cp ('t320'); |
!!!cp ('t320'); |
| 6390 |
## NOTE: As if in body. |
## NOTE: As if in head. |
| 6391 |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 6392 |
next B; |
next B; |
| 6393 |
|
|
| 6394 |
|
## NOTE: |<!DOCTYPE HTML><frameset></frameset></html><noframes></noframes>| |
| 6395 |
|
## has no parse error. |
| 6396 |
} else { |
} else { |
| 6397 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6398 |
!!!cp ('t321'); |
!!!cp ('t321'); |
| 6399 |
!!!parse-error (type => 'in frameset:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in frameset', |
| 6400 |
} else { |
text => $token->{tag_name}, token => $token); |
| 6401 |
|
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 6402 |
!!!cp ('t322'); |
!!!cp ('t322'); |
| 6403 |
!!!parse-error (type => 'after frameset:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after frameset', |
| 6404 |
|
text => $token->{tag_name}, token => $token); |
| 6405 |
|
} else { # "after after frameset" |
| 6406 |
|
!!!cp ('t322.2'); |
| 6407 |
|
!!!parse-error (type => 'after after frameset', |
| 6408 |
|
text => $token->{tag_name}, token => $token); |
| 6409 |
} |
} |
| 6410 |
## Ignore the token |
## Ignore the token |
| 6411 |
!!!nack ('t322.1'); |
!!!nack ('t322.1'); |
| 6413 |
next B; |
next B; |
| 6414 |
} |
} |
| 6415 |
} elsif ($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); |
|
|
|
|
|
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
|
|
## Process in the "after frameset" insertion mode. |
|
|
} else { |
|
|
!!!cp ('t324'); |
|
|
} |
|
|
|
|
| 6416 |
if ($token->{tag_name} eq 'frameset' and |
if ($token->{tag_name} eq 'frameset' and |
| 6417 |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6418 |
if ($self->{open_elements}->[-1]->[1] & HTML_EL and |
if ($self->{open_elements}->[-1]->[1] & HTML_EL and |
| 6419 |
@{$self->{open_elements}} == 1) { |
@{$self->{open_elements}} == 1) { |
| 6420 |
!!!cp ('t325'); |
!!!cp ('t325'); |
| 6421 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6422 |
|
text => $token->{tag_name}, token => $token); |
| 6423 |
## Ignore the token |
## Ignore the token |
| 6424 |
!!!next-token; |
!!!next-token; |
| 6425 |
} else { |
} else { |
| 6445 |
} else { |
} else { |
| 6446 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6447 |
!!!cp ('t330'); |
!!!cp ('t330'); |
| 6448 |
!!!parse-error (type => 'in frameset:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in frameset:/', |
| 6449 |
} else { |
text => $token->{tag_name}, token => $token); |
| 6450 |
|
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 6451 |
|
!!!cp ('t330.1'); |
| 6452 |
|
!!!parse-error (type => 'after frameset:/', |
| 6453 |
|
text => $token->{tag_name}, token => $token); |
| 6454 |
|
} else { # "after after html" |
| 6455 |
!!!cp ('t331'); |
!!!cp ('t331'); |
| 6456 |
!!!parse-error (type => 'after frameset:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after after frameset:/', |
| 6457 |
|
text => $token->{tag_name}, token => $token); |
| 6458 |
} |
} |
| 6459 |
## Ignore the token |
## Ignore the token |
| 6460 |
!!!next-token; |
!!!next-token; |
| 6562 |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
| 6563 |
next B; |
next B; |
| 6564 |
} elsif ($token->{tag_name} eq 'body') { |
} elsif ($token->{tag_name} eq 'body') { |
| 6565 |
!!!parse-error (type => 'in body:body', token => $token); |
!!!parse-error (type => 'in body', text => 'body', token => $token); |
| 6566 |
|
|
| 6567 |
if (@{$self->{open_elements}} == 1 or |
if (@{$self->{open_elements}} == 1 or |
| 6568 |
not ($self->{open_elements}->[1]->[1] & BODY_EL)) { |
not ($self->{open_elements}->[1]->[1] & BODY_EL)) { |
| 6682 |
if ($i != -1) { |
if ($i != -1) { |
| 6683 |
!!!cp ('t355'); |
!!!cp ('t355'); |
| 6684 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 6685 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 6686 |
->manakai_local_name, |
->manakai_local_name, |
| 6687 |
token => $token); |
token => $token); |
| 6688 |
} else { |
} else { |
| 6836 |
xmp => 1, |
xmp => 1, |
| 6837 |
iframe => 1, |
iframe => 1, |
| 6838 |
noembed => 1, |
noembed => 1, |
| 6839 |
noframes => 1, |
noframes => 1, ## NOTE: This is an "as if in head" code clone. |
| 6840 |
noscript => 0, ## TODO: 1 if scripting is enabled |
noscript => 0, ## TODO: 1 if scripting is enabled |
| 6841 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6842 |
if ($token->{tag_name} eq 'xmp') { |
if ($token->{tag_name} eq 'xmp') { |
| 6858 |
!!!next-token; |
!!!next-token; |
| 6859 |
next B; |
next B; |
| 6860 |
} else { |
} else { |
| 6861 |
|
!!!ack ('t391.1'); |
| 6862 |
|
|
| 6863 |
my $at = $token->{attributes}; |
my $at = $token->{attributes}; |
| 6864 |
my $form_attrs; |
my $form_attrs; |
| 6865 |
$form_attrs->{action} = $at->{action} if $at->{action}; |
$form_attrs->{action} = $at->{action} if $at->{action}; |
| 6903 |
line => $token->{line}, column => $token->{column}}, |
line => $token->{line}, column => $token->{column}}, |
| 6904 |
{type => END_TAG_TOKEN, tag_name => 'form', |
{type => END_TAG_TOKEN, tag_name => 'form', |
| 6905 |
line => $token->{line}, column => $token->{column}}; |
line => $token->{line}, column => $token->{column}}; |
|
!!!nack ('t391.1'); ## NOTE: Not acknowledged. |
|
| 6906 |
!!!back-token (@tokens); |
!!!back-token (@tokens); |
| 6907 |
!!!next-token; |
!!!next-token; |
| 6908 |
next B; |
next B; |
| 6950 |
## Ignore the token |
## Ignore the token |
| 6951 |
} else { |
} else { |
| 6952 |
!!!cp ('t398'); |
!!!cp ('t398'); |
| 6953 |
!!!parse-error (type => 'in RCDATA:#'.$token->{type}, token => $token); |
!!!parse-error (type => 'in RCDATA:#eof', token => $token); |
| 6954 |
} |
} |
| 6955 |
!!!next-token; |
!!!next-token; |
| 6956 |
next B; |
next B; |
| 6957 |
|
} elsif ($token->{tag_name} eq 'rt' or |
| 6958 |
|
$token->{tag_name} eq 'rp') { |
| 6959 |
|
## has a |ruby| element in scope |
| 6960 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 6961 |
|
my $node = $self->{open_elements}->[$_]; |
| 6962 |
|
if ($node->[1] & RUBY_EL) { |
| 6963 |
|
!!!cp ('t398.1'); |
| 6964 |
|
## generate implied end tags |
| 6965 |
|
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 6966 |
|
!!!cp ('t398.2'); |
| 6967 |
|
pop @{$self->{open_elements}}; |
| 6968 |
|
} |
| 6969 |
|
unless ($self->{open_elements}->[-1]->[1] & RUBY_EL) { |
| 6970 |
|
!!!cp ('t398.3'); |
| 6971 |
|
!!!parse-error (type => 'not closed', |
| 6972 |
|
text => $self->{open_elements}->[-1]->[0] |
| 6973 |
|
->manakai_local_name, |
| 6974 |
|
token => $token); |
| 6975 |
|
pop @{$self->{open_elements}} |
| 6976 |
|
while not $self->{open_elements}->[-1]->[1] & RUBY_EL; |
| 6977 |
|
} |
| 6978 |
|
last INSCOPE; |
| 6979 |
|
} elsif ($node->[1] & SCOPING_EL) { |
| 6980 |
|
!!!cp ('t398.4'); |
| 6981 |
|
last INSCOPE; |
| 6982 |
|
} |
| 6983 |
|
} # INSCOPE |
| 6984 |
|
|
| 6985 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 6986 |
|
|
| 6987 |
|
!!!nack ('t398.5'); |
| 6988 |
|
!!!next-token; |
| 6989 |
|
redo B; |
| 6990 |
} elsif ($token->{tag_name} eq 'math' or |
} elsif ($token->{tag_name} eq 'math' or |
| 6991 |
$token->{tag_name} eq 'svg') { |
$token->{tag_name} eq 'svg') { |
| 6992 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 6993 |
|
|
| 6994 |
|
## "Adjust MathML attributes" ('math' only) - done in insert-element-f |
| 6995 |
|
|
| 6996 |
## "adjust SVG attributes" ('svg' only) - done in insert-element-f |
## "adjust SVG attributes" ('svg' only) - done in insert-element-f |
| 6997 |
|
|
| 6998 |
## "adjust foreign attributes" - done in insert-element-f |
## "adjust foreign attributes" - done in insert-element-f |
| 7019 |
thead => 1, tr => 1, |
thead => 1, tr => 1, |
| 7020 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 7021 |
!!!cp ('t401'); |
!!!cp ('t401'); |
| 7022 |
!!!parse-error (type => 'in body:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in body', |
| 7023 |
|
text => $token->{tag_name}, token => $token); |
| 7024 |
## Ignore the token |
## Ignore the token |
| 7025 |
!!!nack ('t401.1'); ## NOTE: |<col/>| or |<frame/>| here is an error. |
!!!nack ('t401.1'); ## NOTE: |<col/>| or |<frame/>| here is an error. |
| 7026 |
!!!next-token; |
!!!next-token; |
| 7105 |
} |
} |
| 7106 |
|
|
| 7107 |
!!!parse-error (type => 'start tag not allowed', |
!!!parse-error (type => 'start tag not allowed', |
| 7108 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 7109 |
## NOTE: Ignore the token. |
## NOTE: Ignore the token. |
| 7110 |
!!!next-token; |
!!!next-token; |
| 7111 |
next B; |
next B; |
| 7115 |
unless ($_->[1] & ALL_END_TAG_OPTIONAL_EL) { |
unless ($_->[1] & ALL_END_TAG_OPTIONAL_EL) { |
| 7116 |
!!!cp ('t403'); |
!!!cp ('t403'); |
| 7117 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7118 |
value => $_->[0]->manakai_local_name, |
text => $_->[0]->manakai_local_name, |
| 7119 |
token => $token); |
token => $token); |
| 7120 |
last; |
last; |
| 7121 |
} else { |
} else { |
| 7135 |
unless ($self->{open_elements}->[-1]->[1] & BODY_EL) { |
unless ($self->{open_elements}->[-1]->[1] & BODY_EL) { |
| 7136 |
!!!cp ('t406'); |
!!!cp ('t406'); |
| 7137 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7138 |
value => $self->{open_elements}->[1]->[0] |
text => $self->{open_elements}->[1]->[0] |
| 7139 |
->manakai_local_name, |
->manakai_local_name, |
| 7140 |
token => $token); |
token => $token); |
| 7141 |
} else { |
} else { |
| 7146 |
next B; |
next B; |
| 7147 |
} else { |
} else { |
| 7148 |
!!!cp ('t408'); |
!!!cp ('t408'); |
| 7149 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7150 |
|
text => $token->{tag_name}, token => $token); |
| 7151 |
## Ignore the token |
## Ignore the token |
| 7152 |
!!!next-token; |
!!!next-token; |
| 7153 |
next B; |
next B; |
| 7175 |
|
|
| 7176 |
unless (defined $i) { # has an element in scope |
unless (defined $i) { # has an element in scope |
| 7177 |
!!!cp ('t413'); |
!!!cp ('t413'); |
| 7178 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7179 |
|
text => $token->{tag_name}, token => $token); |
| 7180 |
|
## NOTE: Ignore the token. |
| 7181 |
} else { |
} else { |
| 7182 |
## Step 1. generate implied end tags |
## Step 1. generate implied end tags |
| 7183 |
while ({ |
while ({ |
| 7184 |
|
## END_TAG_OPTIONAL_EL |
| 7185 |
dd => ($token->{tag_name} ne 'dd'), |
dd => ($token->{tag_name} ne 'dd'), |
| 7186 |
dt => ($token->{tag_name} ne 'dt'), |
dt => ($token->{tag_name} ne 'dt'), |
| 7187 |
li => ($token->{tag_name} ne 'li'), |
li => ($token->{tag_name} ne 'li'), |
| 7188 |
p => 1, |
p => 1, |
| 7189 |
|
rt => 1, |
| 7190 |
|
rp => 1, |
| 7191 |
}->{$self->{open_elements}->[-1]->[0]->manakai_local_name}) { |
}->{$self->{open_elements}->[-1]->[0]->manakai_local_name}) { |
| 7192 |
!!!cp ('t409'); |
!!!cp ('t409'); |
| 7193 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 7198 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 7199 |
!!!cp ('t412'); |
!!!cp ('t412'); |
| 7200 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7201 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 7202 |
->manakai_local_name, |
->manakai_local_name, |
| 7203 |
token => $token); |
token => $token); |
| 7204 |
} else { |
} else { |
| 7235 |
|
|
| 7236 |
unless (defined $i) { # has an element in scope |
unless (defined $i) { # has an element in scope |
| 7237 |
!!!cp ('t421'); |
!!!cp ('t421'); |
| 7238 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7239 |
|
text => $token->{tag_name}, token => $token); |
| 7240 |
|
## NOTE: Ignore the token. |
| 7241 |
} else { |
} else { |
| 7242 |
## Step 1. generate implied end tags |
## Step 1. generate implied end tags |
| 7243 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 7250 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 7251 |
!!!cp ('t417.1'); |
!!!cp ('t417.1'); |
| 7252 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7253 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 7254 |
->manakai_local_name, |
->manakai_local_name, |
| 7255 |
token => $token); |
token => $token); |
| 7256 |
} else { |
} else { |
| 7282 |
|
|
| 7283 |
unless (defined $i) { # has an element in scope |
unless (defined $i) { # has an element in scope |
| 7284 |
!!!cp ('t425.1'); |
!!!cp ('t425.1'); |
| 7285 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7286 |
|
text => $token->{tag_name}, token => $token); |
| 7287 |
|
## NOTE: Ignore the token. |
| 7288 |
} else { |
} else { |
| 7289 |
## Step 1. generate implied end tags |
## Step 1. generate implied end tags |
| 7290 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 7296 |
if ($self->{open_elements}->[-1]->[0]->manakai_local_name |
if ($self->{open_elements}->[-1]->[0]->manakai_local_name |
| 7297 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 7298 |
!!!cp ('t425'); |
!!!cp ('t425'); |
| 7299 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7300 |
|
text => $token->{tag_name}, token => $token); |
| 7301 |
} else { |
} else { |
| 7302 |
!!!cp ('t426'); |
!!!cp ('t426'); |
| 7303 |
} |
} |
| 7328 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 7329 |
!!!cp ('t412.1'); |
!!!cp ('t412.1'); |
| 7330 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7331 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 7332 |
->manakai_local_name, |
->manakai_local_name, |
| 7333 |
token => $token); |
token => $token); |
| 7334 |
} else { |
} else { |
| 7338 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 7339 |
} else { |
} else { |
| 7340 |
!!!cp ('t413.1'); |
!!!cp ('t413.1'); |
| 7341 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7342 |
|
text => $token->{tag_name}, token => $token); |
| 7343 |
|
|
| 7344 |
!!!cp ('t415.1'); |
!!!cp ('t415.1'); |
| 7345 |
## As if <p>, then reprocess the current token |
## As if <p>, then reprocess the current token |
| 7362 |
next B; |
next B; |
| 7363 |
} elsif ($token->{tag_name} eq 'br') { |
} elsif ($token->{tag_name} eq 'br') { |
| 7364 |
!!!cp ('t428'); |
!!!cp ('t428'); |
| 7365 |
!!!parse-error (type => 'unmatched end tag:br', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7366 |
|
text => 'br', token => $token); |
| 7367 |
|
|
| 7368 |
## As if <br> |
## As if <br> |
| 7369 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 7388 |
noscript => 0, ## TODO: if scripting is enabled |
noscript => 0, ## TODO: if scripting is enabled |
| 7389 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 7390 |
!!!cp ('t429'); |
!!!cp ('t429'); |
| 7391 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7392 |
|
text => $token->{tag_name}, token => $token); |
| 7393 |
## Ignore the token |
## Ignore the token |
| 7394 |
!!!next-token; |
!!!next-token; |
| 7395 |
next B; |
next B; |
| 7408 |
## generate implied end tags |
## generate implied end tags |
| 7409 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 7410 |
!!!cp ('t430'); |
!!!cp ('t430'); |
| 7411 |
## ISSUE: Can this case be reached? |
## NOTE: |<ruby><rt></ruby>|. |
| 7412 |
|
## ISSUE: <ruby><rt></rt> will also take this code path, |
| 7413 |
|
## which seems wrong. |
| 7414 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 7415 |
|
$node_i++; |
| 7416 |
} |
} |
| 7417 |
|
|
| 7418 |
## Step 2 |
## Step 2 |
| 7421 |
!!!cp ('t431'); |
!!!cp ('t431'); |
| 7422 |
## NOTE: <x><y></x> |
## NOTE: <x><y></x> |
| 7423 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7424 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 7425 |
->manakai_local_name, |
->manakai_local_name, |
| 7426 |
token => $token); |
token => $token); |
| 7427 |
} else { |
} else { |
| 7429 |
} |
} |
| 7430 |
|
|
| 7431 |
## Step 3 |
## Step 3 |
| 7432 |
splice @{$self->{open_elements}}, $node_i; |
splice @{$self->{open_elements}}, $node_i if $node_i < 0; |
| 7433 |
|
|
| 7434 |
!!!next-token; |
!!!next-token; |
| 7435 |
last S2; |
last S2; |
| 7440 |
($node->[1] & SPECIAL_EL or |
($node->[1] & SPECIAL_EL or |
| 7441 |
$node->[1] & SCOPING_EL)) { |
$node->[1] & SCOPING_EL)) { |
| 7442 |
!!!cp ('t433'); |
!!!cp ('t433'); |
| 7443 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7444 |
|
text => $token->{tag_name}, token => $token); |
| 7445 |
## Ignore the token |
## Ignore the token |
| 7446 |
!!!next-token; |
!!!next-token; |
| 7447 |
last S2; |
last S2; |
| 7487 |
## TODO: script stuffs |
## TODO: script stuffs |
| 7488 |
} # _tree_construct_main |
} # _tree_construct_main |
| 7489 |
|
|
| 7490 |
sub set_inner_html ($$$) { |
sub set_inner_html ($$$;$) { |
| 7491 |
my $class = shift; |
my $class = shift; |
| 7492 |
my $node = shift; |
my $node = shift; |
| 7493 |
my $s = \$_[0]; |
my $s = \$_[0]; |
| 7494 |
my $onerror = $_[1]; |
my $onerror = $_[1]; |
| 7495 |
|
my $get_wrapper = $_[2] || sub ($) { return $_[0] }; |
| 7496 |
|
|
| 7497 |
## ISSUE: Should {confident} be true? |
## ISSUE: Should {confident} be true? |
| 7498 |
|
|
| 7511 |
} |
} |
| 7512 |
|
|
| 7513 |
## Step 3, 4, 5 # MUST |
## Step 3, 4, 5 # MUST |
| 7514 |
$class->parse_string ($$s => $node, $onerror); |
$class->parse_char_string ($$s => $node, $onerror, $get_wrapper); |
| 7515 |
} elsif ($nt == 1) { |
} elsif ($nt == 1) { |
| 7516 |
## TODO: If non-html element |
## TODO: If non-html element |
| 7517 |
|
|
| 7518 |
## NOTE: Most of this code is copied from |parse_string| |
## NOTE: Most of this code is copied from |parse_string| |
| 7519 |
|
|
| 7520 |
|
## TODO: Support for $get_wrapper |
| 7521 |
|
|
| 7522 |
## Step 1 # MUST |
## Step 1 # MUST |
| 7523 |
my $this_doc = $node->owner_document; |
my $this_doc = $node->owner_document; |
| 7524 |
my $doc = $this_doc->implementation->create_document; |
my $doc = $this_doc->implementation->create_document; |
| 7580 |
0x10FFFE => 1, 0x10FFFF => 1, |
0x10FFFE => 1, 0x10FFFF => 1, |
| 7581 |
}->{$self->{next_char}}) { |
}->{$self->{next_char}}) { |
| 7582 |
!!!cp ('i4.1'); |
!!!cp ('i4.1'); |
| 7583 |
!!!parse-error (type => 'control char', level => $self->{must_level}); |
if ($self->{next_char} < 0x10000) { |
| 7584 |
## TODO: error type documentation |
!!!parse-error (type => 'control char', |
| 7585 |
|
text => (sprintf 'U+%04X', $self->{next_char})); |
| 7586 |
|
} else { |
| 7587 |
|
!!!parse-error (type => 'control char', |
| 7588 |
|
text => (sprintf 'U-%08X', $self->{next_char})); |
| 7589 |
|
} |
| 7590 |
} |
} |
| 7591 |
}; |
}; |
| 7592 |
$p->{prev_char} = [-1, -1, -1]; |
$p->{prev_char} = [-1, -1, -1]; |