| 8 |
## doc.write (''); |
## doc.write (''); |
| 9 |
## alert (doc.compatMode); |
## alert (doc.compatMode); |
| 10 |
|
|
| 11 |
## TODO: 1252 parse error (revision 1264) |
require IO::Handle; |
|
## TODO: 8859-11 = 874 (revision 1271) |
|
| 12 |
|
|
| 13 |
my $HTML_NS = q<http://www.w3.org/1999/xhtml>; |
my $HTML_NS = q<http://www.w3.org/1999/xhtml>; |
| 14 |
my $MML_NS = q<http://www.w3.org/1998/Math/MathML>; |
my $MML_NS = q<http://www.w3.org/1998/Math/MathML>; |
| 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', |
| 348 |
}; # $c1_entity_char |
}; # $c1_entity_char |
| 349 |
|
|
| 350 |
sub parse_byte_string ($$$$;$) { |
sub parse_byte_string ($$$$;$) { |
| 351 |
|
my $self = shift; |
| 352 |
|
my $charset_name = shift; |
| 353 |
|
open my $input, '<', ref $_[0] ? $_[0] : \($_[0]); |
| 354 |
|
return $self->parse_byte_stream ($charset_name, $input, @_[1..$#_]); |
| 355 |
|
} # parse_byte_string |
| 356 |
|
|
| 357 |
|
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 $bytes_s = ref $_[0] ? $_[0] : \($_[0]); |
my $byte_stream = $_[0]; |
|
my $s; |
|
| 362 |
|
|
| 363 |
my $onerror = $_[2] || sub { |
my $onerror = $_[2] || sub { |
| 364 |
my (%opt) = @_; |
my (%opt) = @_; |
| 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 $charset; |
| 376 |
my ($e, $e_status); |
my $buffer; |
| 377 |
|
my ($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 |
($e, $e_status) = $charset->get_perl_encoding |
($char_stream, $e_status) = $charset->get_decode_handle |
| 395 |
(allow_error_reporting => 1, |
($byte_stream, allow_error_reporting => 1, |
| 396 |
allow_fallback => 1); |
allow_fallback => 1); |
| 397 |
if ($e) { |
if ($char_stream) { |
| 398 |
$self->{confident} = 1; |
$self->{confident} = 1; |
| 399 |
last SNIFFING; |
last SNIFFING; |
| 400 |
|
} else { |
| 401 |
|
## TODO: unsupported error |
| 402 |
} |
} |
| 403 |
} |
} |
| 404 |
|
|
| 405 |
## Step 2 |
## Step 2 |
| 406 |
# wait |
my $byte_buffer = ''; |
| 407 |
|
for (1..1024) { |
| 408 |
|
my $char = $byte_stream->getc; |
| 409 |
|
last unless defined $char; |
| 410 |
|
$byte_buffer .= $char; |
| 411 |
|
} ## TODO: timeout |
| 412 |
|
|
| 413 |
## Step 3 |
## Step 3 |
| 414 |
my $head = substr ($$bytes_s, 0, 3); |
if ($byte_buffer =~ /^\xFE\xFF/) { |
| 415 |
if ($head =~ /^\xFE\xFF/) { |
$charset = Message::Charset::Info->get_by_html_name ('utf-16be'); |
| 416 |
$charset = Message::Charset::Info->get_by_iana_name ('utf-16be'); |
($char_stream, $e_status) = $charset->get_decode_handle |
| 417 |
($e, $e_status) = $charset->get_perl_encoding |
($byte_stream, allow_error_reporting => 1, |
| 418 |
(allow_error_reporting => 1, |
allow_fallback => 1, byte_buffer => \$byte_buffer); |
|
allow_fallback => 1); |
|
| 419 |
$self->{confident} = 1; |
$self->{confident} = 1; |
| 420 |
last SNIFFING; |
last SNIFFING; |
| 421 |
} elsif ($head =~ /^\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 |
($e, $e_status) = $charset->get_perl_encoding |
($char_stream, $e_status) = $charset->get_decode_handle |
| 424 |
(allow_error_reporting => 1, |
($byte_stream, allow_error_reporting => 1, |
| 425 |
allow_fallback => 1); |
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 426 |
$self->{confident} = 1; |
$self->{confident} = 1; |
| 427 |
last SNIFFING; |
last SNIFFING; |
| 428 |
} elsif ($head eq "\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 |
($e, $e_status) = $charset->get_perl_encoding |
($char_stream, $e_status) = $charset->get_decode_handle |
| 431 |
(allow_error_reporting => 1, |
($byte_stream, allow_error_reporting => 1, |
| 432 |
allow_fallback => 1); |
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 433 |
$self->{confident} = 1; |
$self->{confident} = 1; |
| 434 |
last SNIFFING; |
last SNIFFING; |
| 435 |
} |
} |
| 443 |
## Step 6 |
## Step 6 |
| 444 |
require Whatpm::Charset::UniversalCharDet; |
require Whatpm::Charset::UniversalCharDet; |
| 445 |
$charset_name = Whatpm::Charset::UniversalCharDet->detect_byte_string |
$charset_name = Whatpm::Charset::UniversalCharDet->detect_byte_string |
| 446 |
(substr ($$bytes_s, 0, 1024)); |
($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 |
($e, $e_status) = $charset->get_perl_encoding |
require Whatpm::Charset::DecodeHandle; |
| 452 |
(allow_error_reporting => 1, |
$buffer = Whatpm::Charset::DecodeHandle::ByteBuffer->new |
| 453 |
allow_fallback => 1); |
($byte_stream); |
| 454 |
if ($e) { |
($char_stream, $e_status) = $charset->get_decode_handle |
| 455 |
!!!parse-error (type => 'sniffing:chardet', ## TODO: type name |
($buffer, allow_error_reporting => 1, |
| 456 |
value => $charset_name, |
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 457 |
level => $self->{info_level}, |
if ($char_stream) { |
| 458 |
|
$buffer->{buffer} = $byte_buffer; |
| 459 |
|
!!!parse-error (type => 'sniffing:chardet', |
| 460 |
|
text => $charset_name, |
| 461 |
|
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'); |
$charset = Message::Charset::Info->get_by_html_name ('windows-1252'); |
| 472 |
## NOTE: We choose |windows-1252| here, since |utf-8| should be |
## NOTE: We choose |windows-1252| here, since |utf-8| should be |
| 473 |
## detectable in the step 6. |
## detectable in the step 6. |
| 474 |
($e, $e_status) = $charset->get_perl_encoding (allow_error_reporting => 1, |
require Whatpm::Charset::DecodeHandle; |
| 475 |
allow_fallback => 1); |
$buffer = Whatpm::Charset::DecodeHandle::ByteBuffer->new |
| 476 |
!!!parse-error (type => 'sniffing:default', ## TODO: type name |
($byte_stream); |
| 477 |
value => 'windows-1252', |
($char_stream, $e_status) |
| 478 |
level => $self->{info_level}, |
= $charset->get_decode_handle ($buffer, |
| 479 |
line => 1, column => 1); |
allow_error_reporting => 1, |
| 480 |
|
allow_fallback => 1, |
| 481 |
|
byte_buffer => \$byte_buffer); |
| 482 |
|
$buffer->{buffer} = $byte_buffer; |
| 483 |
|
!!!parse-error (type => 'sniffing:default', |
| 484 |
|
text => 'windows-1252', |
| 485 |
|
level => $self->{level}->{info}, |
| 486 |
|
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 => $e->name, |
!!!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 |
} |
} |
|
$s = \ $e->decode ($$bytes_s); |
|
| 509 |
|
|
| 510 |
$self->{change_encoding} = sub { |
$self->{change_encoding} = sub { |
| 511 |
my $self = shift; |
my $self = shift; |
| 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 |
($e, $e_status) = $charset->get_perl_encoding |
($char_stream, $e_status) = $charset->get_decode_handle |
| 517 |
(allow_error_reporting => 1, allow_fallback => 1); |
($byte_stream, allow_error_reporting => 1, allow_fallback => 1, |
| 518 |
|
byte_buffer => \ $buffer->{buffer}); |
| 519 |
|
|
| 520 |
if ($e) { # if supported |
if ($char_stream) { # if supported |
| 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 |
($e, $e_status) = $charset->get_perl_encoding; |
$charset = Message::Charset::Info->get_by_html_name ('utf-8'); |
| 527 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 528 |
|
($byte_stream, |
| 529 |
|
byte_buffer => \ $buffer->{buffer}); |
| 530 |
} |
} |
| 531 |
$charset_name = $charset->get_iana_name; |
$charset_name = $charset->get_iana_name; |
| 532 |
|
|
| 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) { |
| 558 |
} |
} |
| 559 |
}; # $self->{change_encoding} |
}; # $self->{change_encoding} |
| 560 |
|
|
| 561 |
|
my $char_onerror = sub { |
| 562 |
|
my (undef, $type, %opt) = @_; |
| 563 |
|
!!!parse-error (layer => 'encode', |
| 564 |
|
%opt, type => $type, |
| 565 |
|
line => $self->{line}, column => $self->{column} + 1); |
| 566 |
|
if ($opt{octets}) { |
| 567 |
|
${$opt{octets}} = "\x{FFFD}"; # relacement character |
| 568 |
|
} |
| 569 |
|
}; |
| 570 |
|
|
| 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_string ($s, @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 => $e->name, |
!!!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 |
} |
} |
|
$s = \ $e->decode ($$bytes_s); |
|
| 599 |
$self->{confident} = 1; |
$self->{confident} = 1; |
| 600 |
$return = $self->parse_char_string ($s, @args); |
|
| 601 |
|
$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_string |
} # parse_byte_stream |
| 608 |
|
|
| 609 |
## NOTE: HTML5 spec says that the encoding layer MUST NOT strip BOM |
## NOTE: HTML5 spec says that the encoding layer MUST NOT strip BOM |
| 610 |
## and the HTML layer MUST ignore it. However, we does strip BOM in |
## and the HTML layer MUST ignore it. However, we does strip BOM in |
| 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 |
*parse_char_string = \&parse_string; |
sub parse_char_string ($$$;$$) { |
| 619 |
|
#my ($self, $s, $doc, $onerror, $get_wrapper) = @_; |
| 620 |
|
my $self = shift; |
| 621 |
|
require utf8; |
| 622 |
|
my $s = ref $_[0] ? $_[0] : \($_[0]); |
| 623 |
|
open my $input, '<' . (utf8::is_utf8 ($$s) ? ':utf8' : ''), $s; |
| 624 |
|
if ($_[3]) { |
| 625 |
|
$input = $_[3]->($input); |
| 626 |
|
} |
| 627 |
|
return $self->parse_char_stream ($input, @_[1..$#_]); |
| 628 |
|
} # parse_char_string |
| 629 |
|
*parse_string = \&parse_char_string; ## NOTE: Alias for backward compatibility. |
| 630 |
|
|
| 631 |
sub parse_string ($$$;$) { |
sub parse_char_stream ($$$;$) { |
| 632 |
my $self = ref $_[0] ? shift : shift->new; |
my $self = ref $_[0] ? shift : shift->new; |
| 633 |
my $s = ref $_[0] ? $_[0] : \($_[0]); |
my $input = $_[0]; |
| 634 |
$self->{document} = $_[1]; |
$self->{document} = $_[1]; |
| 635 |
@{$self->{document}->child_nodes} = (); |
@{$self->{document}->child_nodes} = (); |
| 636 |
|
|
| 649 |
pop @{$self->{prev_char}}; |
pop @{$self->{prev_char}}; |
| 650 |
unshift @{$self->{prev_char}}, $self->{next_char}; |
unshift @{$self->{prev_char}}, $self->{next_char}; |
| 651 |
|
|
| 652 |
$self->{next_char} = -1 and return if $i >= length $$s; |
my $char; |
| 653 |
$self->{next_char} = ord substr $$s, $i++, 1; |
if (defined $self->{next_next_char}) { |
| 654 |
|
$char = $self->{next_next_char}; |
| 655 |
|
delete $self->{next_next_char}; |
| 656 |
|
} else { |
| 657 |
|
$char = $input->getc; |
| 658 |
|
} |
| 659 |
|
$self->{next_char} = -1 and return unless defined $char; |
| 660 |
|
$self->{next_char} = ord $char; |
| 661 |
|
|
| 662 |
($self->{line_prev}, $self->{column_prev}) |
($self->{line_prev}, $self->{column_prev}) |
| 663 |
= ($self->{line}, $self->{column}); |
= ($self->{line}, $self->{column}); |
| 669 |
$self->{column} = 0; |
$self->{column} = 0; |
| 670 |
} elsif ($self->{next_char} == 0x000D) { # CR |
} elsif ($self->{next_char} == 0x000D) { # CR |
| 671 |
!!!cp ('j2'); |
!!!cp ('j2'); |
| 672 |
$i++ if substr ($$s, $i, 1) eq "\x0A"; |
my $next = $input->getc; |
| 673 |
|
if (defined $next and $next ne "\x0A") { |
| 674 |
|
$self->{next_next_char} = $next; |
| 675 |
|
} |
| 676 |
$self->{next_char} = 0x000A; # LF # MUST |
$self->{next_char} = 0x000A; # LF # MUST |
| 677 |
$self->{line}++; |
$self->{line}++; |
| 678 |
$self->{column} = 0; |
$self->{column} = 0; |
| 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]; |
| 730 |
delete $self->{parse_error}; # remove loop |
delete $self->{parse_error}; # remove loop |
| 731 |
|
|
| 732 |
return $self->{document}; |
return $self->{document}; |
| 733 |
} # parse_string |
} # parse_char_stream |
| 734 |
|
|
| 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; |
| 803 |
sub BOGUS_DOCTYPE_STATE () { 32 } |
sub BOGUS_DOCTYPE_STATE () { 32 } |
| 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_SECTION_STATE () { 35 } |
| 807 |
|
sub MD_HYPHEN_STATE () { 36 } # "markup declaration open state" in the spec |
| 808 |
|
sub MD_DOCTYPE_STATE () { 37 } # "markup declaration open state" in the spec |
| 809 |
|
sub MD_CDATA_STATE () { 38 } # "markup declaration open state" in the spec |
| 810 |
|
sub CDATA_PCDATA_CLOSE_TAG_STATE () { 39 } # "close tag open state" in the spec |
| 811 |
|
sub CDATA_SECTION_MSE1_STATE () { 40 } # "CDATA section state" in the spec |
| 812 |
|
sub CDATA_SECTION_MSE2_STATE () { 41 } # "CDATA section state" in the spec |
| 813 |
|
sub PUBLIC_STATE () { 42 } # "after DOCTYPE name state" in the spec |
| 814 |
|
sub SYSTEM_STATE () { 43 } # "after DOCTYPE name state" in the spec |
| 815 |
|
|
| 816 |
sub DOCTYPE_TOKEN () { 1 } |
sub DOCTYPE_TOKEN () { 1 } |
| 817 |
sub COMMENT_TOKEN () { 2 } |
sub COMMENT_TOKEN () { 2 } |
| 864 |
sub _initialize_tokenizer ($) { |
sub _initialize_tokenizer ($) { |
| 865 |
my $self = shift; |
my $self = shift; |
| 866 |
$self->{state} = DATA_STATE; # MUST |
$self->{state} = DATA_STATE; # MUST |
| 867 |
|
#$self->{state_keyword}; # initialized when used |
| 868 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # be |
$self->{content_model} = PCDATA_CONTENT_MODEL; # be |
| 869 |
undef $self->{current_token}; # start tag, end tag, comment, or DOCTYPE |
undef $self->{current_token}; |
| 870 |
undef $self->{current_attribute}; |
undef $self->{current_attribute}; |
| 871 |
undef $self->{last_emitted_start_tag_name}; |
undef $self->{last_emitted_start_tag_name}; |
| 872 |
undef $self->{last_attribute_value_state}; |
undef $self->{last_attribute_value_state}; |
| 895 |
## |->{self_closing}| is used to save the value of |$self->{self_closing}| |
## |->{self_closing}| is used to save the value of |$self->{self_closing}| |
| 896 |
## while the token is pushed back to the stack. |
## while the token is pushed back to the stack. |
| 897 |
|
|
|
## 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? |
|
|
|
|
| 898 |
## Emitted token MUST immediately be handled by the tree construction state. |
## Emitted token MUST immediately be handled by the tree construction state. |
| 899 |
|
|
| 900 |
## 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 |
| 1110 |
redo A; |
redo A; |
| 1111 |
} else { |
} else { |
| 1112 |
!!!cp (23); |
!!!cp (23); |
| 1113 |
!!!parse-error (type => 'bare stago'); |
!!!parse-error (type => 'bare stago', |
| 1114 |
|
line => $self->{line_prev}, |
| 1115 |
|
column => $self->{column_prev}); |
| 1116 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1117 |
## reconsume |
## reconsume |
| 1118 |
|
|
| 1127 |
die "$0: $self->{content_model} in tag open"; |
die "$0: $self->{content_model} in tag open"; |
| 1128 |
} |
} |
| 1129 |
} elsif ($self->{state} == CLOSE_TAG_OPEN_STATE) { |
} elsif ($self->{state} == CLOSE_TAG_OPEN_STATE) { |
| 1130 |
|
## NOTE: The "close tag open state" in the spec is implemented as |
| 1131 |
|
## |CLOSE_TAG_OPEN_STATE| and |CDATA_PCDATA_CLOSE_TAG_STATE|. |
| 1132 |
|
|
| 1133 |
my ($l, $c) = ($self->{line_prev}, $self->{column_prev} - 1); # "<"of"</" |
my ($l, $c) = ($self->{line_prev}, $self->{column_prev} - 1); # "<"of"</" |
| 1134 |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
| 1135 |
if (defined $self->{last_emitted_start_tag_name}) { |
if (defined $self->{last_emitted_start_tag_name}) { |
| 1136 |
|
$self->{state} = CDATA_PCDATA_CLOSE_TAG_STATE; |
| 1137 |
## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564> |
$self->{state_keyword} = ''; |
| 1138 |
my @next_char; |
## Reconsume. |
| 1139 |
TAGNAME: for (my $i = 0; $i < length $self->{last_emitted_start_tag_name}; $i++) { |
redo A; |
|
push @next_char, $self->{next_char}; |
|
|
my $c = ord substr ($self->{last_emitted_start_tag_name}, $i, 1); |
|
|
my $C = 0x0061 <= $c && $c <= 0x007A ? $c - 0x0020 : $c; |
|
|
if ($self->{next_char} == $c or $self->{next_char} == $C) { |
|
|
!!!cp (24); |
|
|
!!!next-input-character; |
|
|
next TAGNAME; |
|
|
} else { |
|
|
!!!cp (25); |
|
|
$self->{next_char} = shift @next_char; # reconsume |
|
|
!!!back-next-input-character (@next_char); |
|
|
$self->{state} = DATA_STATE; |
|
|
|
|
|
!!!emit ({type => CHARACTER_TOKEN, data => '</', |
|
|
line => $l, column => $c, |
|
|
}); |
|
|
|
|
|
redo A; |
|
|
} |
|
|
} |
|
|
push @next_char, $self->{next_char}; |
|
|
|
|
|
unless ($self->{next_char} == 0x0009 or # HT |
|
|
$self->{next_char} == 0x000A or # LF |
|
|
$self->{next_char} == 0x000B or # VT |
|
|
$self->{next_char} == 0x000C or # FF |
|
|
$self->{next_char} == 0x0020 or # SP |
|
|
$self->{next_char} == 0x003E or # > |
|
|
$self->{next_char} == 0x002F or # / |
|
|
$self->{next_char} == -1) { |
|
|
!!!cp (26); |
|
|
$self->{next_char} = shift @next_char; # reconsume |
|
|
!!!back-next-input-character (@next_char); |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!emit ({type => CHARACTER_TOKEN, data => '</', |
|
|
line => $l, column => $c, |
|
|
}); |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (27); |
|
|
$self->{next_char} = shift @next_char; |
|
|
!!!back-next-input-character (@next_char); |
|
|
# and consume... |
|
|
} |
|
| 1140 |
} else { |
} else { |
| 1141 |
## No start tag token has ever been emitted |
## No start tag token has ever been emitted |
| 1142 |
|
## NOTE: See <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564>. |
| 1143 |
!!!cp (28); |
!!!cp (28); |
|
# next-input-character is already done |
|
| 1144 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1145 |
|
## Reconsume. |
| 1146 |
!!!emit ({type => CHARACTER_TOKEN, data => '</', |
!!!emit ({type => CHARACTER_TOKEN, data => '</', |
| 1147 |
line => $l, column => $c, |
line => $l, column => $c, |
| 1148 |
}); |
}); |
| 1149 |
redo A; |
redo A; |
| 1150 |
} |
} |
| 1151 |
} |
} |
| 1152 |
|
|
| 1153 |
if (0x0041 <= $self->{next_char} and |
if (0x0041 <= $self->{next_char} and |
| 1154 |
$self->{next_char} <= 0x005A) { # A..Z |
$self->{next_char} <= 0x005A) { # A..Z |
| 1155 |
!!!cp (29); |
!!!cp (29); |
| 1196 |
line => $self->{line_prev}, # "<" of "</" |
line => $self->{line_prev}, # "<" of "</" |
| 1197 |
column => $self->{column_prev} - 1, |
column => $self->{column_prev} - 1, |
| 1198 |
}; |
}; |
| 1199 |
## $self->{next_char} is intentionally left as is |
## NOTE: $self->{next_char} is intentionally left as is. |
| 1200 |
redo A; |
## Although the "anything else" case of the spec not explicitly |
| 1201 |
|
## states that the next input character is to be reconsumed, |
| 1202 |
|
## it will be included to the |data| of the comment token |
| 1203 |
|
## generated from the bogus end tag, as defined in the |
| 1204 |
|
## "bogus comment state" entry. |
| 1205 |
|
redo A; |
| 1206 |
|
} |
| 1207 |
|
} elsif ($self->{state} == CDATA_PCDATA_CLOSE_TAG_STATE) { |
| 1208 |
|
my $ch = substr $self->{last_emitted_start_tag_name}, length $self->{state_keyword}, 1; |
| 1209 |
|
if (length $ch) { |
| 1210 |
|
my $CH = $ch; |
| 1211 |
|
$ch =~ tr/a-z/A-Z/; |
| 1212 |
|
my $nch = chr $self->{next_char}; |
| 1213 |
|
if ($nch eq $ch or $nch eq $CH) { |
| 1214 |
|
!!!cp (24); |
| 1215 |
|
## Stay in the state. |
| 1216 |
|
$self->{state_keyword} .= $nch; |
| 1217 |
|
!!!next-input-character; |
| 1218 |
|
redo A; |
| 1219 |
|
} else { |
| 1220 |
|
!!!cp (25); |
| 1221 |
|
$self->{state} = DATA_STATE; |
| 1222 |
|
## Reconsume. |
| 1223 |
|
!!!emit ({type => CHARACTER_TOKEN, |
| 1224 |
|
data => '</' . $self->{state_keyword}, |
| 1225 |
|
line => $self->{line_prev}, |
| 1226 |
|
column => $self->{column_prev} - 1 - length $self->{state_keyword}, |
| 1227 |
|
}); |
| 1228 |
|
redo A; |
| 1229 |
|
} |
| 1230 |
|
} else { # after "<{tag-name}" |
| 1231 |
|
unless ({ |
| 1232 |
|
0x0009 => 1, # HT |
| 1233 |
|
0x000A => 1, # LF |
| 1234 |
|
0x000B => 1, # VT |
| 1235 |
|
0x000C => 1, # FF |
| 1236 |
|
0x0020 => 1, # SP |
| 1237 |
|
0x003E => 1, # > |
| 1238 |
|
0x002F => 1, # / |
| 1239 |
|
-1 => 1, # EOF |
| 1240 |
|
}->{$self->{next_char}}) { |
| 1241 |
|
!!!cp (26); |
| 1242 |
|
## Reconsume. |
| 1243 |
|
$self->{state} = DATA_STATE; |
| 1244 |
|
!!!emit ({type => CHARACTER_TOKEN, |
| 1245 |
|
data => '</' . $self->{state_keyword}, |
| 1246 |
|
line => $self->{line_prev}, |
| 1247 |
|
column => $self->{column_prev} - 1 - length $self->{state_keyword}, |
| 1248 |
|
}); |
| 1249 |
|
redo A; |
| 1250 |
|
} else { |
| 1251 |
|
!!!cp (27); |
| 1252 |
|
$self->{current_token} |
| 1253 |
|
= {type => END_TAG_TOKEN, |
| 1254 |
|
tag_name => $self->{last_emitted_start_tag_name}, |
| 1255 |
|
line => $self->{line_prev}, |
| 1256 |
|
column => $self->{column_prev} - 1 - length $self->{state_keyword}}; |
| 1257 |
|
$self->{state} = TAG_NAME_STATE; |
| 1258 |
|
## Reconsume. |
| 1259 |
|
redo A; |
| 1260 |
|
} |
| 1261 |
} |
} |
| 1262 |
} elsif ($self->{state} == TAG_NAME_STATE) { |
} elsif ($self->{state} == TAG_NAME_STATE) { |
| 1263 |
if ($self->{next_char} == 0x0009 or # HT |
if ($self->{next_char} == 0x0009 or # HT |
| 1427 |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
| 1428 |
->{$self->{current_attribute}->{name}}) { # MUST |
->{$self->{current_attribute}->{name}}) { # MUST |
| 1429 |
!!!cp (57); |
!!!cp (57); |
| 1430 |
!!!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}); |
| 1431 |
## Discard $self->{current_attribute} # MUST |
## Discard $self->{current_attribute} # MUST |
| 1432 |
} else { |
} else { |
| 1433 |
!!!cp (58); |
!!!cp (58); |
| 1598 |
|
|
| 1599 |
redo A; |
redo A; |
| 1600 |
} else { |
} else { |
| 1601 |
!!!cp (82); |
if ($self->{next_char} == 0x0022 or # " |
| 1602 |
|
$self->{next_char} == 0x0027) { # ' |
| 1603 |
|
!!!cp (78); |
| 1604 |
|
!!!parse-error (type => 'bad attribute name'); |
| 1605 |
|
} else { |
| 1606 |
|
!!!cp (82); |
| 1607 |
|
} |
| 1608 |
$self->{current_attribute} |
$self->{current_attribute} |
| 1609 |
= {name => chr ($self->{next_char}), |
= {name => chr ($self->{next_char}), |
| 1610 |
value => '', |
value => '', |
| 1639 |
!!!next-input-character; |
!!!next-input-character; |
| 1640 |
redo A; |
redo A; |
| 1641 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1642 |
|
!!!parse-error (type => 'empty unquoted attribute value'); |
| 1643 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1644 |
!!!cp (87); |
!!!cp (87); |
| 1645 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1916 |
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
| 1917 |
!!!next-input-character; |
!!!next-input-character; |
| 1918 |
redo A; |
redo A; |
| 1919 |
|
} elsif ($self->{next_char} == -1) { |
| 1920 |
|
!!!parse-error (type => 'unclosed tag'); |
| 1921 |
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1922 |
|
!!!cp (122.3); |
| 1923 |
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1924 |
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1925 |
|
if ($self->{current_token}->{attributes}) { |
| 1926 |
|
!!!cp (122.1); |
| 1927 |
|
!!!parse-error (type => 'end tag attribute'); |
| 1928 |
|
} else { |
| 1929 |
|
## NOTE: This state should never be reached. |
| 1930 |
|
!!!cp (122.2); |
| 1931 |
|
} |
| 1932 |
|
} else { |
| 1933 |
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 1934 |
|
} |
| 1935 |
|
$self->{state} = DATA_STATE; |
| 1936 |
|
## Reconsume. |
| 1937 |
|
!!!emit ($self->{current_token}); # start tag or end tag |
| 1938 |
|
redo A; |
| 1939 |
} else { |
} else { |
| 1940 |
!!!cp ('124.1'); |
!!!cp ('124.1'); |
| 1941 |
!!!parse-error (type => 'no space between attributes'); |
!!!parse-error (type => 'no space between attributes'); |
| 1968 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 1969 |
|
|
| 1970 |
redo A; |
redo A; |
| 1971 |
|
} elsif ($self->{next_char} == -1) { |
| 1972 |
|
!!!parse-error (type => 'unclosed tag'); |
| 1973 |
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1974 |
|
!!!cp (124.7); |
| 1975 |
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1976 |
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1977 |
|
if ($self->{current_token}->{attributes}) { |
| 1978 |
|
!!!cp (124.5); |
| 1979 |
|
!!!parse-error (type => 'end tag attribute'); |
| 1980 |
|
} else { |
| 1981 |
|
## NOTE: This state should never be reached. |
| 1982 |
|
!!!cp (124.6); |
| 1983 |
|
} |
| 1984 |
|
} else { |
| 1985 |
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 1986 |
|
} |
| 1987 |
|
$self->{state} = DATA_STATE; |
| 1988 |
|
## Reconsume. |
| 1989 |
|
!!!emit ($self->{current_token}); # start tag or end tag |
| 1990 |
|
redo A; |
| 1991 |
} else { |
} else { |
| 1992 |
!!!cp ('124.4'); |
!!!cp ('124.4'); |
| 1993 |
!!!parse-error (type => 'nestc'); |
!!!parse-error (type => 'nestc'); |
| 2030 |
die "$0: _get_next_token: unexpected case [BC]"; |
die "$0: _get_next_token: unexpected case [BC]"; |
| 2031 |
} elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) { |
} elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) { |
| 2032 |
## (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}; |
|
| 2033 |
|
|
| 2034 |
if ($self->{next_char} == 0x002D) { # - |
if ($self->{next_char} == 0x002D) { # - |
| 2035 |
|
!!!cp (133); |
| 2036 |
|
$self->{state} = MD_HYPHEN_STATE; |
| 2037 |
!!!next-input-character; |
!!!next-input-character; |
| 2038 |
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); |
|
|
} |
|
| 2039 |
} elsif ($self->{next_char} == 0x0044 or # D |
} elsif ($self->{next_char} == 0x0044 or # D |
| 2040 |
$self->{next_char} == 0x0064) { # d |
$self->{next_char} == 0x0064) { # d |
| 2041 |
|
## ASCII case-insensitive. |
| 2042 |
|
!!!cp (130); |
| 2043 |
|
$self->{state} = MD_DOCTYPE_STATE; |
| 2044 |
|
$self->{state_keyword} = chr $self->{next_char}; |
| 2045 |
!!!next-input-character; |
!!!next-input-character; |
| 2046 |
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); |
|
|
} |
|
| 2047 |
} elsif ($self->{insertion_mode} & IN_FOREIGN_CONTENT_IM and |
} elsif ($self->{insertion_mode} & IN_FOREIGN_CONTENT_IM and |
| 2048 |
$self->{open_elements}->[-1]->[1] & FOREIGN_EL and |
$self->{open_elements}->[-1]->[1] & FOREIGN_EL and |
| 2049 |
$self->{next_char} == 0x005B) { # [ |
$self->{next_char} == 0x005B) { # [ |
| 2050 |
|
!!!cp (135.4); |
| 2051 |
|
$self->{state} = MD_CDATA_STATE; |
| 2052 |
|
$self->{state_keyword} = '['; |
| 2053 |
!!!next-input-character; |
!!!next-input-character; |
| 2054 |
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); |
|
|
} |
|
| 2055 |
} else { |
} else { |
| 2056 |
!!!cp (136); |
!!!cp (136); |
| 2057 |
} |
} |
| 2058 |
|
|
| 2059 |
!!!parse-error (type => 'bogus comment'); |
!!!parse-error (type => 'bogus comment', |
| 2060 |
$self->{next_char} = shift @next_char; |
line => $self->{line_prev}, |
| 2061 |
!!!back-next-input-character (@next_char); |
column => $self->{column_prev} - 1); |
| 2062 |
|
## Reconsume. |
| 2063 |
$self->{state} = BOGUS_COMMENT_STATE; |
$self->{state} = BOGUS_COMMENT_STATE; |
| 2064 |
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
| 2065 |
line => $l, column => $c, |
line => $self->{line_prev}, |
| 2066 |
|
column => $self->{column_prev} - 1, |
| 2067 |
}; |
}; |
| 2068 |
redo A; |
redo A; |
| 2069 |
|
} elsif ($self->{state} == MD_HYPHEN_STATE) { |
| 2070 |
## ISSUE: typos in spec: chacacters, is is a parse error |
if ($self->{next_char} == 0x002D) { # - |
| 2071 |
## 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); |
| 2072 |
|
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
| 2073 |
|
line => $self->{line_prev}, |
| 2074 |
|
column => $self->{column_prev} - 2, |
| 2075 |
|
}; |
| 2076 |
|
$self->{state} = COMMENT_START_STATE; |
| 2077 |
|
!!!next-input-character; |
| 2078 |
|
redo A; |
| 2079 |
|
} else { |
| 2080 |
|
!!!cp (128); |
| 2081 |
|
!!!parse-error (type => 'bogus comment', |
| 2082 |
|
line => $self->{line_prev}, |
| 2083 |
|
column => $self->{column_prev} - 2); |
| 2084 |
|
$self->{state} = BOGUS_COMMENT_STATE; |
| 2085 |
|
## Reconsume. |
| 2086 |
|
$self->{current_token} = {type => COMMENT_TOKEN, |
| 2087 |
|
data => '-', |
| 2088 |
|
line => $self->{line_prev}, |
| 2089 |
|
column => $self->{column_prev} - 2, |
| 2090 |
|
}; |
| 2091 |
|
redo A; |
| 2092 |
|
} |
| 2093 |
|
} elsif ($self->{state} == MD_DOCTYPE_STATE) { |
| 2094 |
|
## ASCII case-insensitive. |
| 2095 |
|
if ($self->{next_char} == [ |
| 2096 |
|
undef, |
| 2097 |
|
0x004F, # O |
| 2098 |
|
0x0043, # C |
| 2099 |
|
0x0054, # T |
| 2100 |
|
0x0059, # Y |
| 2101 |
|
0x0050, # P |
| 2102 |
|
]->[length $self->{state_keyword}] or |
| 2103 |
|
$self->{next_char} == [ |
| 2104 |
|
undef, |
| 2105 |
|
0x006F, # o |
| 2106 |
|
0x0063, # c |
| 2107 |
|
0x0074, # t |
| 2108 |
|
0x0079, # y |
| 2109 |
|
0x0070, # p |
| 2110 |
|
]->[length $self->{state_keyword}]) { |
| 2111 |
|
!!!cp (131); |
| 2112 |
|
## Stay in the state. |
| 2113 |
|
$self->{state_keyword} .= chr $self->{next_char}; |
| 2114 |
|
!!!next-input-character; |
| 2115 |
|
redo A; |
| 2116 |
|
} elsif ((length $self->{state_keyword}) == 6 and |
| 2117 |
|
($self->{next_char} == 0x0045 or # E |
| 2118 |
|
$self->{next_char} == 0x0065)) { # e |
| 2119 |
|
!!!cp (129); |
| 2120 |
|
$self->{state} = DOCTYPE_STATE; |
| 2121 |
|
$self->{current_token} = {type => DOCTYPE_TOKEN, |
| 2122 |
|
quirks => 1, |
| 2123 |
|
line => $self->{line_prev}, |
| 2124 |
|
column => $self->{column_prev} - 7, |
| 2125 |
|
}; |
| 2126 |
|
!!!next-input-character; |
| 2127 |
|
redo A; |
| 2128 |
|
} else { |
| 2129 |
|
!!!cp (132); |
| 2130 |
|
!!!parse-error (type => 'bogus comment', |
| 2131 |
|
line => $self->{line_prev}, |
| 2132 |
|
column => $self->{column_prev} - 1 - length $self->{state_keyword}); |
| 2133 |
|
$self->{state} = BOGUS_COMMENT_STATE; |
| 2134 |
|
## Reconsume. |
| 2135 |
|
$self->{current_token} = {type => COMMENT_TOKEN, |
| 2136 |
|
data => $self->{state_keyword}, |
| 2137 |
|
line => $self->{line_prev}, |
| 2138 |
|
column => $self->{column_prev} - 1 - length $self->{state_keyword}, |
| 2139 |
|
}; |
| 2140 |
|
redo A; |
| 2141 |
|
} |
| 2142 |
|
} elsif ($self->{state} == MD_CDATA_STATE) { |
| 2143 |
|
if ($self->{next_char} == { |
| 2144 |
|
'[' => 0x0043, # C |
| 2145 |
|
'[C' => 0x0044, # D |
| 2146 |
|
'[CD' => 0x0041, # A |
| 2147 |
|
'[CDA' => 0x0054, # T |
| 2148 |
|
'[CDAT' => 0x0041, # A |
| 2149 |
|
}->{$self->{state_keyword}}) { |
| 2150 |
|
!!!cp (135.1); |
| 2151 |
|
## Stay in the state. |
| 2152 |
|
$self->{state_keyword} .= chr $self->{next_char}; |
| 2153 |
|
!!!next-input-character; |
| 2154 |
|
redo A; |
| 2155 |
|
} elsif ($self->{state_keyword} eq '[CDATA' and |
| 2156 |
|
$self->{next_char} == 0x005B) { # [ |
| 2157 |
|
!!!cp (135.2); |
| 2158 |
|
$self->{current_token} = {type => CHARACTER_TOKEN, |
| 2159 |
|
data => '', |
| 2160 |
|
line => $self->{line_prev}, |
| 2161 |
|
column => $self->{column_prev} - 7}; |
| 2162 |
|
$self->{state} = CDATA_SECTION_STATE; |
| 2163 |
|
!!!next-input-character; |
| 2164 |
|
redo A; |
| 2165 |
|
} else { |
| 2166 |
|
!!!cp (135.3); |
| 2167 |
|
!!!parse-error (type => 'bogus comment', |
| 2168 |
|
line => $self->{line_prev}, |
| 2169 |
|
column => $self->{column_prev} - 1 - length $self->{state_keyword}); |
| 2170 |
|
$self->{state} = BOGUS_COMMENT_STATE; |
| 2171 |
|
## Reconsume. |
| 2172 |
|
$self->{current_token} = {type => COMMENT_TOKEN, |
| 2173 |
|
data => $self->{state_keyword}, |
| 2174 |
|
line => $self->{line_prev}, |
| 2175 |
|
column => $self->{column_prev} - 1 - length $self->{state_keyword}, |
| 2176 |
|
}; |
| 2177 |
|
redo A; |
| 2178 |
|
} |
| 2179 |
} elsif ($self->{state} == COMMENT_START_STATE) { |
} elsif ($self->{state} == COMMENT_START_STATE) { |
| 2180 |
if ($self->{next_char} == 0x002D) { # - |
if ($self->{next_char} == 0x002D) { # - |
| 2181 |
!!!cp (137); |
!!!cp (137); |
| 2442 |
redo A; |
redo A; |
| 2443 |
} elsif ($self->{next_char} == 0x0050 or # P |
} elsif ($self->{next_char} == 0x0050 or # P |
| 2444 |
$self->{next_char} == 0x0070) { # p |
$self->{next_char} == 0x0070) { # p |
| 2445 |
|
$self->{state} = PUBLIC_STATE; |
| 2446 |
|
$self->{state_keyword} = chr $self->{next_char}; |
| 2447 |
!!!next-input-character; |
!!!next-input-character; |
| 2448 |
if ($self->{next_char} == 0x0055 or # U |
redo A; |
|
$self->{next_char} == 0x0075) { # u |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x0042 or # B |
|
|
$self->{next_char} == 0x0062) { # b |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x004C or # L |
|
|
$self->{next_char} == 0x006C) { # l |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x0049 or # I |
|
|
$self->{next_char} == 0x0069) { # i |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x0043 or # C |
|
|
$self->{next_char} == 0x0063) { # c |
|
|
!!!cp (168); |
|
|
$self->{state} = BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (169); |
|
|
} |
|
|
} else { |
|
|
!!!cp (170); |
|
|
} |
|
|
} else { |
|
|
!!!cp (171); |
|
|
} |
|
|
} else { |
|
|
!!!cp (172); |
|
|
} |
|
|
} else { |
|
|
!!!cp (173); |
|
|
} |
|
|
|
|
|
# |
|
| 2449 |
} elsif ($self->{next_char} == 0x0053 or # S |
} elsif ($self->{next_char} == 0x0053 or # S |
| 2450 |
$self->{next_char} == 0x0073) { # s |
$self->{next_char} == 0x0073) { # s |
| 2451 |
|
$self->{state} = SYSTEM_STATE; |
| 2452 |
|
$self->{state_keyword} = chr $self->{next_char}; |
| 2453 |
!!!next-input-character; |
!!!next-input-character; |
| 2454 |
if ($self->{next_char} == 0x0059 or # Y |
redo A; |
|
$self->{next_char} == 0x0079) { # y |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x0053 or # S |
|
|
$self->{next_char} == 0x0073) { # s |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x0054 or # T |
|
|
$self->{next_char} == 0x0074) { # t |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x0045 or # E |
|
|
$self->{next_char} == 0x0065) { # e |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x004D or # M |
|
|
$self->{next_char} == 0x006D) { # m |
|
|
!!!cp (174); |
|
|
$self->{state} = BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (175); |
|
|
} |
|
|
} else { |
|
|
!!!cp (176); |
|
|
} |
|
|
} else { |
|
|
!!!cp (177); |
|
|
} |
|
|
} else { |
|
|
!!!cp (178); |
|
|
} |
|
|
} else { |
|
|
!!!cp (179); |
|
|
} |
|
|
|
|
|
# |
|
| 2455 |
} else { |
} else { |
| 2456 |
!!!cp (180); |
!!!cp (180); |
| 2457 |
|
!!!parse-error (type => 'string after DOCTYPE name'); |
| 2458 |
|
$self->{current_token}->{quirks} = 1; |
| 2459 |
|
|
| 2460 |
|
$self->{state} = BOGUS_DOCTYPE_STATE; |
| 2461 |
!!!next-input-character; |
!!!next-input-character; |
| 2462 |
# |
redo A; |
| 2463 |
} |
} |
| 2464 |
|
} elsif ($self->{state} == PUBLIC_STATE) { |
| 2465 |
|
## ASCII case-insensitive |
| 2466 |
|
if ($self->{next_char} == [ |
| 2467 |
|
undef, |
| 2468 |
|
0x0055, # U |
| 2469 |
|
0x0042, # B |
| 2470 |
|
0x004C, # L |
| 2471 |
|
0x0049, # I |
| 2472 |
|
]->[length $self->{state_keyword}] or |
| 2473 |
|
$self->{next_char} == [ |
| 2474 |
|
undef, |
| 2475 |
|
0x0075, # u |
| 2476 |
|
0x0062, # b |
| 2477 |
|
0x006C, # l |
| 2478 |
|
0x0069, # i |
| 2479 |
|
]->[length $self->{state_keyword}]) { |
| 2480 |
|
!!!cp (175); |
| 2481 |
|
## Stay in the state. |
| 2482 |
|
$self->{state_keyword} .= chr $self->{next_char}; |
| 2483 |
|
!!!next-input-character; |
| 2484 |
|
redo A; |
| 2485 |
|
} elsif ((length $self->{state_keyword}) == 5 and |
| 2486 |
|
($self->{next_char} == 0x0043 or # C |
| 2487 |
|
$self->{next_char} == 0x0063)) { # c |
| 2488 |
|
!!!cp (168); |
| 2489 |
|
$self->{state} = BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE; |
| 2490 |
|
!!!next-input-character; |
| 2491 |
|
redo A; |
| 2492 |
|
} else { |
| 2493 |
|
!!!cp (169); |
| 2494 |
|
!!!parse-error (type => 'string after DOCTYPE name', |
| 2495 |
|
line => $self->{line_prev}, |
| 2496 |
|
column => $self->{column_prev} + 1 - length $self->{state_keyword}); |
| 2497 |
|
$self->{current_token}->{quirks} = 1; |
| 2498 |
|
|
| 2499 |
!!!parse-error (type => 'string after DOCTYPE name'); |
$self->{state} = BOGUS_DOCTYPE_STATE; |
| 2500 |
$self->{current_token}->{quirks} = 1; |
## Reconsume. |
| 2501 |
|
redo A; |
| 2502 |
|
} |
| 2503 |
|
} elsif ($self->{state} == SYSTEM_STATE) { |
| 2504 |
|
## ASCII case-insensitive |
| 2505 |
|
if ($self->{next_char} == [ |
| 2506 |
|
undef, |
| 2507 |
|
0x0059, # Y |
| 2508 |
|
0x0053, # S |
| 2509 |
|
0x0054, # T |
| 2510 |
|
0x0045, # E |
| 2511 |
|
]->[length $self->{state_keyword}] or |
| 2512 |
|
$self->{next_char} == [ |
| 2513 |
|
undef, |
| 2514 |
|
0x0079, # y |
| 2515 |
|
0x0073, # s |
| 2516 |
|
0x0074, # t |
| 2517 |
|
0x0065, # e |
| 2518 |
|
]->[length $self->{state_keyword}]) { |
| 2519 |
|
!!!cp (170); |
| 2520 |
|
## Stay in the state. |
| 2521 |
|
$self->{state_keyword} .= chr $self->{next_char}; |
| 2522 |
|
!!!next-input-character; |
| 2523 |
|
redo A; |
| 2524 |
|
} elsif ((length $self->{state_keyword}) == 5 and |
| 2525 |
|
($self->{next_char} == 0x004D or # M |
| 2526 |
|
$self->{next_char} == 0x006D)) { # m |
| 2527 |
|
!!!cp (171); |
| 2528 |
|
$self->{state} = BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE; |
| 2529 |
|
!!!next-input-character; |
| 2530 |
|
redo A; |
| 2531 |
|
} else { |
| 2532 |
|
!!!cp (172); |
| 2533 |
|
!!!parse-error (type => 'string after DOCTYPE name', |
| 2534 |
|
line => $self->{line_prev}, |
| 2535 |
|
column => $self->{column_prev} + 1 - length $self->{state_keyword}); |
| 2536 |
|
$self->{current_token}->{quirks} = 1; |
| 2537 |
|
|
| 2538 |
$self->{state} = BOGUS_DOCTYPE_STATE; |
$self->{state} = BOGUS_DOCTYPE_STATE; |
| 2539 |
# next-input-character is already done |
## Reconsume. |
| 2540 |
redo A; |
redo A; |
| 2541 |
|
} |
| 2542 |
} elsif ($self->{state} == BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE) { |
} elsif ($self->{state} == BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE) { |
| 2543 |
if ({ |
if ({ |
| 2544 |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
| 2771 |
redo A; |
redo A; |
| 2772 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 2773 |
!!!cp (208); |
!!!cp (208); |
| 2774 |
!!!parse-error (type => 'unclosed PUBLIC literal'); |
!!!parse-error (type => 'unclosed SYSTEM literal'); |
| 2775 |
|
|
| 2776 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 2777 |
!!!next-input-character; |
!!!next-input-character; |
| 2807 |
redo A; |
redo A; |
| 2808 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 2809 |
!!!cp (212); |
!!!cp (212); |
| 2810 |
!!!parse-error (type => 'unclosed PUBLIC literal'); |
!!!parse-error (type => 'unclosed SYSTEM literal'); |
| 2811 |
|
|
| 2812 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 2813 |
!!!next-input-character; |
!!!next-input-character; |
| 2855 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 2856 |
!!!cp (217); |
!!!cp (217); |
| 2857 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
|
|
|
| 2858 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 2859 |
## reconsume |
## reconsume |
| 2860 |
|
|
| 2895 |
!!!next-input-character; |
!!!next-input-character; |
| 2896 |
redo A; |
redo A; |
| 2897 |
} |
} |
| 2898 |
} elsif ($self->{state} == CDATA_BLOCK_STATE) { |
} elsif ($self->{state} == CDATA_SECTION_STATE) { |
| 2899 |
my $s = ''; |
## NOTE: "CDATA section state" in the state is jointly implemented |
| 2900 |
|
## by three states, |CDATA_SECTION_STATE|, |CDATA_SECTION_MSE1_STATE|, |
| 2901 |
|
## and |CDATA_SECTION_MSE2_STATE|. |
| 2902 |
|
|
| 2903 |
my ($l, $c) = ($self->{line}, $self->{column}); |
if ($self->{next_char} == 0x005D) { # ] |
| 2904 |
|
!!!cp (221.1); |
| 2905 |
|
$self->{state} = CDATA_SECTION_MSE1_STATE; |
| 2906 |
|
!!!next-input-character; |
| 2907 |
|
redo A; |
| 2908 |
|
} elsif ($self->{next_char} == -1) { |
| 2909 |
|
$self->{state} = DATA_STATE; |
| 2910 |
|
!!!next-input-character; |
| 2911 |
|
if (length $self->{current_token}->{data}) { # character |
| 2912 |
|
!!!cp (221.2); |
| 2913 |
|
!!!emit ($self->{current_token}); # character |
| 2914 |
|
} else { |
| 2915 |
|
!!!cp (221.3); |
| 2916 |
|
## No token to emit. $self->{current_token} is discarded. |
| 2917 |
|
} |
| 2918 |
|
redo A; |
| 2919 |
|
} else { |
| 2920 |
|
!!!cp (221.4); |
| 2921 |
|
$self->{current_token}->{data} .= chr $self->{next_char}; |
| 2922 |
|
## Stay in the state. |
| 2923 |
|
!!!next-input-character; |
| 2924 |
|
redo A; |
| 2925 |
|
} |
| 2926 |
|
|
| 2927 |
CS: while ($self->{next_char} != -1) { |
## ISSUE: "text tokens" in spec. |
| 2928 |
if ($self->{next_char} == 0x005D) { # ] |
} elsif ($self->{state} == CDATA_SECTION_MSE1_STATE) { |
| 2929 |
!!!next-input-character; |
if ($self->{next_char} == 0x005D) { # ] |
| 2930 |
if ($self->{next_char} == 0x005D) { # ] |
!!!cp (221.5); |
| 2931 |
!!!next-input-character; |
$self->{state} = CDATA_SECTION_MSE2_STATE; |
| 2932 |
MDC: { |
!!!next-input-character; |
| 2933 |
if ($self->{next_char} == 0x003E) { # > |
redo A; |
| 2934 |
!!!cp (221.1); |
} else { |
| 2935 |
!!!next-input-character; |
!!!cp (221.6); |
| 2936 |
last CS; |
$self->{current_token}->{data} .= ']'; |
| 2937 |
} elsif ($self->{next_char} == 0x005D) { # ] |
$self->{state} = CDATA_SECTION_STATE; |
| 2938 |
!!!cp (221.2); |
## Reconsume. |
| 2939 |
$s .= ']'; |
redo A; |
| 2940 |
!!!next-input-character; |
} |
| 2941 |
redo MDC; |
} elsif ($self->{state} == CDATA_SECTION_MSE2_STATE) { |
| 2942 |
} else { |
if ($self->{next_char} == 0x003E) { # > |
| 2943 |
!!!cp (221.3); |
$self->{state} = DATA_STATE; |
| 2944 |
$s .= ']]'; |
!!!next-input-character; |
| 2945 |
# |
if (length $self->{current_token}->{data}) { # character |
| 2946 |
} |
!!!cp (221.7); |
| 2947 |
} # MDC |
!!!emit ($self->{current_token}); # character |
|
} else { |
|
|
!!!cp (221.4); |
|
|
$s .= ']'; |
|
|
# |
|
|
} |
|
| 2948 |
} else { |
} else { |
| 2949 |
!!!cp (221.5); |
!!!cp (221.8); |
| 2950 |
# |
## No token to emit. $self->{current_token} is discarded. |
| 2951 |
} |
} |
| 2952 |
$s .= chr $self->{next_char}; |
redo A; |
| 2953 |
|
} elsif ($self->{next_char} == 0x005D) { # ] |
| 2954 |
|
!!!cp (221.9); # character |
| 2955 |
|
$self->{current_token}->{data} .= ']'; ## Add first "]" of "]]]". |
| 2956 |
|
## Stay in the state. |
| 2957 |
!!!next-input-character; |
!!!next-input-character; |
| 2958 |
} # CS |
redo A; |
|
|
|
|
$self->{state} = DATA_STATE; |
|
|
## next-input-character done or EOF, which is reconsumed. |
|
|
|
|
|
if (length $s) { |
|
|
!!!cp (221.6); |
|
|
!!!emit ({type => CHARACTER_TOKEN, data => $s, |
|
|
line => $l, column => $c}); |
|
| 2959 |
} else { |
} else { |
| 2960 |
!!!cp (221.7); |
!!!cp (221.11); |
| 2961 |
|
$self->{current_token}->{data} .= ']]'; # character |
| 2962 |
|
$self->{state} = CDATA_SECTION_STATE; |
| 2963 |
|
## Reconsume. |
| 2964 |
|
redo A; |
| 2965 |
} |
} |
|
|
|
|
redo A; |
|
|
|
|
|
## ISSUE: "text tokens" in spec. |
|
|
## TODO: Streaming support |
|
| 2966 |
} else { |
} else { |
| 2967 |
die "$0: $self->{state}: Unknown state"; |
die "$0: $self->{state}: Unknown state"; |
| 2968 |
} |
} |
| 3030 |
|
|
| 3031 |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 3032 |
!!!cp (1008); |
!!!cp (1008); |
| 3033 |
!!!parse-error (type => (sprintf 'invalid character reference:U+%04X', $code), line => $l, column => $c); |
!!!parse-error (type => 'invalid character reference', |
| 3034 |
|
text => (sprintf 'U+%04X', $code), |
| 3035 |
|
line => $l, column => $c); |
| 3036 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 3037 |
} elsif ($code > 0x10FFFF) { |
} elsif ($code > 0x10FFFF) { |
| 3038 |
!!!cp (1009); |
!!!cp (1009); |
| 3039 |
!!!parse-error (type => (sprintf 'invalid character reference:U-%08X', $code), line => $l, column => $c); |
!!!parse-error (type => 'invalid character reference', |
| 3040 |
|
text => (sprintf 'U-%08X', $code), |
| 3041 |
|
line => $l, column => $c); |
| 3042 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 3043 |
} elsif ($code == 0x000D) { |
} elsif ($code == 0x000D) { |
| 3044 |
!!!cp (1010); |
!!!cp (1010); |
| 3046 |
$code = 0x000A; |
$code = 0x000A; |
| 3047 |
} elsif (0x80 <= $code and $code <= 0x9F) { |
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 3048 |
!!!cp (1011); |
!!!cp (1011); |
| 3049 |
!!!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); |
| 3050 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 3051 |
} |
} |
| 3052 |
|
|
| 3079 |
|
|
| 3080 |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 3081 |
!!!cp (1015); |
!!!cp (1015); |
| 3082 |
!!!parse-error (type => (sprintf 'invalid character reference:U+%04X', $code), line => $l, column => $c); |
!!!parse-error (type => 'invalid character reference', |
| 3083 |
|
text => (sprintf 'U+%04X', $code), |
| 3084 |
|
line => $l, column => $c); |
| 3085 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 3086 |
} elsif ($code > 0x10FFFF) { |
} elsif ($code > 0x10FFFF) { |
| 3087 |
!!!cp (1016); |
!!!cp (1016); |
| 3088 |
!!!parse-error (type => (sprintf 'invalid character reference:U-%08X', $code), line => $l, column => $c); |
!!!parse-error (type => 'invalid character reference', |
| 3089 |
|
text => (sprintf 'U-%08X', $code), |
| 3090 |
|
line => $l, column => $c); |
| 3091 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 3092 |
} elsif ($code == 0x000D) { |
} elsif ($code == 0x000D) { |
| 3093 |
!!!cp (1017); |
!!!cp (1017); |
| 3094 |
!!!parse-error (type => 'CR character reference', line => $l, column => $c); |
!!!parse-error (type => 'CR character reference', |
| 3095 |
|
line => $l, column => $c); |
| 3096 |
$code = 0x000A; |
$code = 0x000A; |
| 3097 |
} elsif (0x80 <= $code and $code <= 0x9F) { |
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 3098 |
!!!cp (1018); |
!!!cp (1018); |
| 3099 |
!!!parse-error (type => (sprintf 'C1 character reference:U+%04X', $code), line => $l, column => $c); |
!!!parse-error (type => 'C1 character reference', |
| 3100 |
|
text => (sprintf 'U+%04X', $code), |
| 3101 |
|
line => $l, column => $c); |
| 3102 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 3103 |
} |
} |
| 3104 |
|
|
| 3196 |
## TODO: Turn mutation events off # MUST |
## TODO: Turn mutation events off # MUST |
| 3197 |
## TODO: Turn loose Document option (manakai extension) on |
## TODO: Turn loose Document option (manakai extension) on |
| 3198 |
$self->{document}->manakai_is_html (1); # MUST |
$self->{document}->manakai_is_html (1); # MUST |
| 3199 |
|
$self->{document}->set_user_data (manakai_source_line => 1); |
| 3200 |
|
$self->{document}->set_user_data (manakai_source_column => 1); |
| 3201 |
} # _initialize_tree_constructor |
} # _initialize_tree_constructor |
| 3202 |
|
|
| 3203 |
sub _terminate_tree_constructor ($) { |
sub _terminate_tree_constructor ($) { |
| 3252 |
## language. |
## language. |
| 3253 |
my $doctype_name = $token->{name}; |
my $doctype_name = $token->{name}; |
| 3254 |
$doctype_name = '' unless defined $doctype_name; |
$doctype_name = '' unless defined $doctype_name; |
| 3255 |
$doctype_name =~ tr/a-z/A-Z/; |
$doctype_name =~ tr/a-z/A-Z/; # ASCII case-insensitive |
| 3256 |
if (not defined $token->{name} or # <!DOCTYPE> |
if (not defined $token->{name} or # <!DOCTYPE> |
|
defined $token->{public_identifier} or |
|
| 3257 |
defined $token->{system_identifier}) { |
defined $token->{system_identifier}) { |
| 3258 |
!!!cp ('t1'); |
!!!cp ('t1'); |
| 3259 |
!!!parse-error (type => 'not HTML5', token => $token); |
!!!parse-error (type => 'not HTML5', token => $token); |
| 3260 |
} elsif ($doctype_name ne 'HTML') { |
} elsif ($doctype_name ne 'HTML') { |
| 3261 |
!!!cp ('t2'); |
!!!cp ('t2'); |
|
## ISSUE: ASCII case-insensitive? (in fact it does not matter) |
|
| 3262 |
!!!parse-error (type => 'not HTML5', token => $token); |
!!!parse-error (type => 'not HTML5', token => $token); |
| 3263 |
|
} elsif (defined $token->{public_identifier}) { |
| 3264 |
|
if ($token->{public_identifier} eq 'XSLT-compat') { |
| 3265 |
|
!!!cp ('t1.2'); |
| 3266 |
|
!!!parse-error (type => 'XSLT-compat', token => $token, |
| 3267 |
|
level => $self->{level}->{should}); |
| 3268 |
|
} else { |
| 3269 |
|
!!!parse-error (type => 'not HTML5', token => $token); |
| 3270 |
|
} |
| 3271 |
} else { |
} else { |
| 3272 |
!!!cp ('t3'); |
!!!cp ('t3'); |
| 3273 |
|
# |
| 3274 |
} |
} |
| 3275 |
|
|
| 3276 |
my $doctype = $self->{document}->create_document_type_definition |
my $doctype = $self->{document}->create_document_type_definition |
| 3291 |
} elsif (defined $token->{public_identifier}) { |
} elsif (defined $token->{public_identifier}) { |
| 3292 |
my $pubid = $token->{public_identifier}; |
my $pubid = $token->{public_identifier}; |
| 3293 |
$pubid =~ tr/a-z/A-z/; |
$pubid =~ tr/a-z/A-z/; |
| 3294 |
if ({ |
my $prefix = [ |
| 3295 |
"+//SILMARIL//DTD HTML PRO V0R11 19970101//EN" => 1, |
"+//SILMARIL//DTD HTML PRO V0R11 19970101//", |
| 3296 |
"-//ADVASOFT LTD//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1, |
"-//ADVASOFT LTD//DTD HTML 3.0 ASWEDIT + EXTENSIONS//", |
| 3297 |
"-//AS//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1, |
"-//AS//DTD HTML 3.0 ASWEDIT + EXTENSIONS//", |
| 3298 |
"-//IETF//DTD HTML 2.0 LEVEL 1//EN" => 1, |
"-//IETF//DTD HTML 2.0 LEVEL 1//", |
| 3299 |
"-//IETF//DTD HTML 2.0 LEVEL 2//EN" => 1, |
"-//IETF//DTD HTML 2.0 LEVEL 2//", |
| 3300 |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 1//EN" => 1, |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 1//", |
| 3301 |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 2//EN" => 1, |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 2//", |
| 3302 |
"-//IETF//DTD HTML 2.0 STRICT//EN" => 1, |
"-//IETF//DTD HTML 2.0 STRICT//", |
| 3303 |
"-//IETF//DTD HTML 2.0//EN" => 1, |
"-//IETF//DTD HTML 2.0//", |
| 3304 |
"-//IETF//DTD HTML 2.1E//EN" => 1, |
"-//IETF//DTD HTML 2.1E//", |
| 3305 |
"-//IETF//DTD HTML 3.0//EN" => 1, |
"-//IETF//DTD HTML 3.0//", |
| 3306 |
"-//IETF//DTD HTML 3.0//EN//" => 1, |
"-//IETF//DTD HTML 3.2 FINAL//", |
| 3307 |
"-//IETF//DTD HTML 3.2 FINAL//EN" => 1, |
"-//IETF//DTD HTML 3.2//", |
| 3308 |
"-//IETF//DTD HTML 3.2//EN" => 1, |
"-//IETF//DTD HTML 3//", |
| 3309 |
"-//IETF//DTD HTML 3//EN" => 1, |
"-//IETF//DTD HTML LEVEL 0//", |
| 3310 |
"-//IETF//DTD HTML LEVEL 0//EN" => 1, |
"-//IETF//DTD HTML LEVEL 1//", |
| 3311 |
"-//IETF//DTD HTML LEVEL 0//EN//2.0" => 1, |
"-//IETF//DTD HTML LEVEL 2//", |
| 3312 |
"-//IETF//DTD HTML LEVEL 1//EN" => 1, |
"-//IETF//DTD HTML LEVEL 3//", |
| 3313 |
"-//IETF//DTD HTML LEVEL 1//EN//2.0" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 0//", |
| 3314 |
"-//IETF//DTD HTML LEVEL 2//EN" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 1//", |
| 3315 |
"-//IETF//DTD HTML LEVEL 2//EN//2.0" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 2//", |
| 3316 |
"-//IETF//DTD HTML LEVEL 3//EN" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 3//", |
| 3317 |
"-//IETF//DTD HTML LEVEL 3//EN//3.0" => 1, |
"-//IETF//DTD HTML STRICT//", |
| 3318 |
"-//IETF//DTD HTML STRICT LEVEL 0//EN" => 1, |
"-//IETF//DTD HTML//", |
| 3319 |
"-//IETF//DTD HTML STRICT LEVEL 0//EN//2.0" => 1, |
"-//METRIUS//DTD METRIUS PRESENTATIONAL//", |
| 3320 |
"-//IETF//DTD HTML STRICT LEVEL 1//EN" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML STRICT//", |
| 3321 |
"-//IETF//DTD HTML STRICT LEVEL 1//EN//2.0" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML//", |
| 3322 |
"-//IETF//DTD HTML STRICT LEVEL 2//EN" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 TABLES//", |
| 3323 |
"-//IETF//DTD HTML STRICT LEVEL 2//EN//2.0" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML STRICT//", |
| 3324 |
"-//IETF//DTD HTML STRICT LEVEL 3//EN" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML//", |
| 3325 |
"-//IETF//DTD HTML STRICT LEVEL 3//EN//3.0" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 TABLES//", |
| 3326 |
"-//IETF//DTD HTML STRICT//EN" => 1, |
"-//NETSCAPE COMM. CORP.//DTD HTML//", |
| 3327 |
"-//IETF//DTD HTML STRICT//EN//2.0" => 1, |
"-//NETSCAPE COMM. CORP.//DTD STRICT HTML//", |
| 3328 |
"-//IETF//DTD HTML STRICT//EN//3.0" => 1, |
"-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//", |
| 3329 |
"-//IETF//DTD HTML//EN" => 1, |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//", |
| 3330 |
"-//IETF//DTD HTML//EN//2.0" => 1, |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED RELAXED 1.0//", |
| 3331 |
"-//IETF//DTD HTML//EN//3.0" => 1, |
"-//SOFTQUAD SOFTWARE//DTD HOTMETAL PRO 6.0::19990601::EXTENSIONS TO HTML 4.0//", |
| 3332 |
"-//METRIUS//DTD METRIUS PRESENTATIONAL//EN" => 1, |
"-//SOFTQUAD//DTD HOTMETAL PRO 4.0::19971010::EXTENSIONS TO HTML 4.0//", |
| 3333 |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML STRICT//EN" => 1, |
"-//SPYGLASS//DTD HTML 2.0 EXTENDED//", |
| 3334 |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML//EN" => 1, |
"-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//", |
| 3335 |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 TABLES//EN" => 1, |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//", |
| 3336 |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML STRICT//EN" => 1, |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA STRICT HTML//", |
| 3337 |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML//EN" => 1, |
"-//W3C//DTD HTML 3 1995-03-24//", |
| 3338 |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 TABLES//EN" => 1, |
"-//W3C//DTD HTML 3.2 DRAFT//", |
| 3339 |
"-//NETSCAPE COMM. CORP.//DTD HTML//EN" => 1, |
"-//W3C//DTD HTML 3.2 FINAL//", |
| 3340 |
"-//NETSCAPE COMM. CORP.//DTD STRICT HTML//EN" => 1, |
"-//W3C//DTD HTML 3.2//", |
| 3341 |
"-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//EN" => 1, |
"-//W3C//DTD HTML 3.2S DRAFT//", |
| 3342 |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//EN" => 1, |
"-//W3C//DTD HTML 4.0 FRAMESET//", |
| 3343 |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED RELAXED 1.0//EN" => 1, |
"-//W3C//DTD HTML 4.0 TRANSITIONAL//", |
| 3344 |
"-//SOFTQUAD SOFTWARE//DTD HOTMETAL PRO 6.0::19990601::EXTENSIONS TO HTML 4.0//EN" => 1, |
"-//W3C//DTD HTML EXPERIMETNAL 19960712//", |
| 3345 |
"-//SOFTQUAD//DTD HOTMETAL PRO 4.0::19971010::EXTENSIONS TO HTML 4.0//EN" => 1, |
"-//W3C//DTD HTML EXPERIMENTAL 970421//", |
| 3346 |
"-//SPYGLASS//DTD HTML 2.0 EXTENDED//EN" => 1, |
"-//W3C//DTD W3 HTML//", |
| 3347 |
"-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//EN" => 1, |
"-//W3O//DTD W3 HTML 3.0//", |
| 3348 |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//EN" => 1, |
"-//WEBTECHS//DTD MOZILLA HTML 2.0//", |
| 3349 |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA STRICT HTML//EN" => 1, |
"-//WEBTECHS//DTD MOZILLA HTML//", |
| 3350 |
"-//W3C//DTD HTML 3 1995-03-24//EN" => 1, |
]; # $prefix |
| 3351 |
"-//W3C//DTD HTML 3.2 DRAFT//EN" => 1, |
my $match; |
| 3352 |
"-//W3C//DTD HTML 3.2 FINAL//EN" => 1, |
for (@$prefix) { |
| 3353 |
"-//W3C//DTD HTML 3.2//EN" => 1, |
if (substr ($prefix, 0, length $_) eq $_) { |
| 3354 |
"-//W3C//DTD HTML 3.2S DRAFT//EN" => 1, |
$match = 1; |
| 3355 |
"-//W3C//DTD HTML 4.0 FRAMESET//EN" => 1, |
last; |
| 3356 |
"-//W3C//DTD HTML 4.0 TRANSITIONAL//EN" => 1, |
} |
| 3357 |
"-//W3C//DTD HTML EXPERIMETNAL 19960712//EN" => 1, |
} |
| 3358 |
"-//W3C//DTD HTML EXPERIMENTAL 970421//EN" => 1, |
if ($match or |
| 3359 |
"-//W3C//DTD W3 HTML//EN" => 1, |
$pubid eq "-//W3O//DTD W3 HTML STRICT 3.0//EN//" or |
| 3360 |
"-//W3O//DTD W3 HTML 3.0//EN" => 1, |
$pubid eq "-/W3C/DTD HTML 4.0 TRANSITIONAL/EN" or |
| 3361 |
"-//W3O//DTD W3 HTML 3.0//EN//" => 1, |
$pubid eq "HTML") { |
|
"-//W3O//DTD W3 HTML STRICT 3.0//EN//" => 1, |
|
|
"-//WEBTECHS//DTD MOZILLA HTML 2.0//EN" => 1, |
|
|
"-//WEBTECHS//DTD MOZILLA HTML//EN" => 1, |
|
|
"-/W3C/DTD HTML 4.0 TRANSITIONAL/EN" => 1, |
|
|
"HTML" => 1, |
|
|
}->{$pubid}) { |
|
| 3362 |
!!!cp ('t5'); |
!!!cp ('t5'); |
| 3363 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 3364 |
} elsif ($pubid eq "-//W3C//DTD HTML 4.01 FRAMESET//EN" or |
} elsif ($pubid =~ m[^-//W3C//DTD HTML 4.01 FRAMESET//] or |
| 3365 |
$pubid eq "-//W3C//DTD HTML 4.01 TRANSITIONAL//EN") { |
$pubid =~ m[^-//W3C//DTD HTML 4.01 TRANSITIONAL//]) { |
| 3366 |
if (defined $token->{system_identifier}) { |
if (defined $token->{system_identifier}) { |
| 3367 |
!!!cp ('t6'); |
!!!cp ('t6'); |
| 3368 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 3370 |
!!!cp ('t7'); |
!!!cp ('t7'); |
| 3371 |
$self->{document}->manakai_compat_mode ('limited quirks'); |
$self->{document}->manakai_compat_mode ('limited quirks'); |
| 3372 |
} |
} |
| 3373 |
} elsif ($pubid eq "-//W3C//DTD XHTML 1.0 FRAMESET//EN" or |
} elsif ($pubid =~ m[^-//W3C//DTD XHTML 1.0 FRAMESET//] or |
| 3374 |
$pubid eq "-//W3C//DTD XHTML 1.0 TRANSITIONAL//EN") { |
$pubid =~ m[^-//W3C//DTD XHTML 1.0 TRANSITIONAL//]) { |
| 3375 |
!!!cp ('t8'); |
!!!cp ('t8'); |
| 3376 |
$self->{document}->manakai_compat_mode ('limited quirks'); |
$self->{document}->manakai_compat_mode ('limited quirks'); |
| 3377 |
} else { |
} else { |
| 3384 |
my $sysid = $token->{system_identifier}; |
my $sysid = $token->{system_identifier}; |
| 3385 |
$sysid =~ tr/A-Z/a-z/; |
$sysid =~ tr/A-Z/a-z/; |
| 3386 |
if ($sysid eq "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd") { |
if ($sysid eq "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd") { |
| 3387 |
## TODO: Check the spec: PUBLIC "(limited quirks)" "(quirks)" |
## NOTE: Ensure that |PUBLIC "(limited quirks)" "(quirks)"| is |
| 3388 |
|
## marked as quirks. |
| 3389 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 3390 |
!!!cp ('t11'); |
!!!cp ('t11'); |
| 3391 |
} else { |
} else { |
| 3557 |
if ($self->{open_elements}->[0]->[0] eq $node->[0]) { |
if ($self->{open_elements}->[0]->[0] eq $node->[0]) { |
| 3558 |
$last = 1; |
$last = 1; |
| 3559 |
if (defined $self->{inner_html_node}) { |
if (defined $self->{inner_html_node}) { |
| 3560 |
if ($self->{inner_html_node}->[1] & TABLE_CELL_EL) { |
!!!cp ('t28'); |
| 3561 |
!!!cp ('t27'); |
$node = $self->{inner_html_node}; |
| 3562 |
# |
} else { |
| 3563 |
} else { |
die "_reset_insertion_mode: t27"; |
|
!!!cp ('t28'); |
|
|
$node = $self->{inner_html_node}; |
|
|
} |
|
| 3564 |
} |
} |
| 3565 |
} |
} |
| 3566 |
|
|
| 3567 |
## Step 4..14 |
## Step 4..14 |
| 3568 |
my $new_mode; |
my $new_mode; |
| 3569 |
if ($node->[1] & FOREIGN_EL) { |
if ($node->[1] & FOREIGN_EL) { |
| 3570 |
## NOTE: Strictly spaking, the line below only applies to MathML and |
!!!cp ('t28.1'); |
| 3571 |
## SVG elements. Currently the HTML syntax supports only MathML and |
## NOTE: Strictly spaking, the line below only applies to MathML and |
| 3572 |
## SVG elements as foreigners. |
## SVG elements. Currently the HTML syntax supports only MathML and |
| 3573 |
$new_mode = $self->{insertion_mode} | IN_FOREIGN_CONTENT_IM; |
## SVG elements as foreigners. |
| 3574 |
## ISSUE: What is set as the secondary insertion mode? |
$new_mode = IN_BODY_IM | IN_FOREIGN_CONTENT_IM; |
| 3575 |
} else { |
} elsif ($node->[1] & TABLE_CELL_EL) { |
| 3576 |
$new_mode = { |
if ($last) { |
| 3577 |
|
!!!cp ('t28.2'); |
| 3578 |
|
# |
| 3579 |
|
} else { |
| 3580 |
|
!!!cp ('t28.3'); |
| 3581 |
|
$new_mode = IN_CELL_IM; |
| 3582 |
|
} |
| 3583 |
|
} else { |
| 3584 |
|
!!!cp ('t28.4'); |
| 3585 |
|
$new_mode = { |
| 3586 |
select => IN_SELECT_IM, |
select => IN_SELECT_IM, |
| 3587 |
## NOTE: |option| and |optgroup| do not set |
## NOTE: |option| and |optgroup| do not set |
| 3588 |
## insertion mode to "in select" by themselves. |
## insertion mode to "in select" by themselves. |
|
td => IN_CELL_IM, |
|
|
th => IN_CELL_IM, |
|
| 3589 |
tr => IN_ROW_IM, |
tr => IN_ROW_IM, |
| 3590 |
tbody => IN_TABLE_BODY_IM, |
tbody => IN_TABLE_BODY_IM, |
| 3591 |
thead => IN_TABLE_BODY_IM, |
thead => IN_TABLE_BODY_IM, |
| 3597 |
body => IN_BODY_IM, |
body => IN_BODY_IM, |
| 3598 |
frameset => IN_FRAMESET_IM, |
frameset => IN_FRAMESET_IM, |
| 3599 |
}->{$node->[0]->manakai_local_name}; |
}->{$node->[0]->manakai_local_name}; |
| 3600 |
} |
} |
| 3601 |
$self->{insertion_mode} = $new_mode and return if defined $new_mode; |
$self->{insertion_mode} = $new_mode and return if defined $new_mode; |
| 3602 |
|
|
| 3603 |
## Step 15 |
## Step 15 |
| 3604 |
if ($node->[1] & HTML_EL) { |
if ($node->[1] & HTML_EL) { |
| 3772 |
## NOTE: An end-of-file token. |
## NOTE: An end-of-file token. |
| 3773 |
if ($content_model_flag == CDATA_CONTENT_MODEL) { |
if ($content_model_flag == CDATA_CONTENT_MODEL) { |
| 3774 |
!!!cp ('t43'); |
!!!cp ('t43'); |
| 3775 |
!!!parse-error (type => 'in CDATA:#'.$token->{type}, token => $token); |
!!!parse-error (type => 'in CDATA:#eof', token => $token); |
| 3776 |
} elsif ($content_model_flag == RCDATA_CONTENT_MODEL) { |
} elsif ($content_model_flag == RCDATA_CONTENT_MODEL) { |
| 3777 |
!!!cp ('t44'); |
!!!cp ('t44'); |
| 3778 |
!!!parse-error (type => 'in RCDATA:#'.$token->{type}, token => $token); |
!!!parse-error (type => 'in RCDATA:#eof', token => $token); |
| 3779 |
} else { |
} else { |
| 3780 |
die "$0: $content_model_flag in parse_rcdata"; |
die "$0: $content_model_flag in parse_rcdata"; |
| 3781 |
} |
} |
| 3812 |
## Ignore the token |
## Ignore the token |
| 3813 |
} else { |
} else { |
| 3814 |
!!!cp ('t48'); |
!!!cp ('t48'); |
| 3815 |
!!!parse-error (type => 'in CDATA:#'.$token->{type}, token => $token); |
!!!parse-error (type => 'in CDATA:#eof', token => $token); |
| 3816 |
## ISSUE: And ignore? |
## ISSUE: And ignore? |
| 3817 |
## TODO: mark as "already executed" |
## TODO: mark as "already executed" |
| 3818 |
} |
} |
| 3863 |
} # AFE |
} # AFE |
| 3864 |
unless (defined $formatting_element) { |
unless (defined $formatting_element) { |
| 3865 |
!!!cp ('t53'); |
!!!cp ('t53'); |
| 3866 |
!!!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); |
| 3867 |
## Ignore the token |
## Ignore the token |
| 3868 |
!!!next-token; |
!!!next-token; |
| 3869 |
return; |
return; |
| 3880 |
last INSCOPE; |
last INSCOPE; |
| 3881 |
} else { # in open elements but not in scope |
} else { # in open elements but not in scope |
| 3882 |
!!!cp ('t55'); |
!!!cp ('t55'); |
| 3883 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, |
!!!parse-error (type => 'unmatched end tag', |
| 3884 |
|
text => $token->{tag_name}, |
| 3885 |
token => $end_tag_token); |
token => $end_tag_token); |
| 3886 |
## Ignore the token |
## Ignore the token |
| 3887 |
!!!next-token; |
!!!next-token; |
| 3894 |
} # INSCOPE |
} # INSCOPE |
| 3895 |
unless (defined $formatting_element_i_in_open) { |
unless (defined $formatting_element_i_in_open) { |
| 3896 |
!!!cp ('t57'); |
!!!cp ('t57'); |
| 3897 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, |
!!!parse-error (type => 'unmatched end tag', |
| 3898 |
|
text => $token->{tag_name}, |
| 3899 |
token => $end_tag_token); |
token => $end_tag_token); |
| 3900 |
pop @$active_formatting_elements; # $formatting_element |
pop @$active_formatting_elements; # $formatting_element |
| 3901 |
!!!next-token; ## TODO: ok? |
!!!next-token; ## TODO: ok? |
| 3904 |
if (not $self->{open_elements}->[-1]->[0] eq $formatting_element->[0]) { |
if (not $self->{open_elements}->[-1]->[0] eq $formatting_element->[0]) { |
| 3905 |
!!!cp ('t58'); |
!!!cp ('t58'); |
| 3906 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 3907 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 3908 |
->manakai_local_name, |
->manakai_local_name, |
| 3909 |
token => $end_tag_token); |
token => $end_tag_token); |
| 3910 |
} |
} |
| 4113 |
B: while (1) { |
B: while (1) { |
| 4114 |
if ($token->{type} == DOCTYPE_TOKEN) { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 4115 |
!!!cp ('t73'); |
!!!cp ('t73'); |
| 4116 |
!!!parse-error (type => 'DOCTYPE in the middle', token => $token); |
!!!parse-error (type => 'in html:#DOCTYPE', token => $token); |
| 4117 |
## Ignore the token |
## Ignore the token |
| 4118 |
## Stay in the phase |
## Stay in the phase |
| 4119 |
!!!next-token; |
!!!next-token; |
| 4122 |
$token->{tag_name} eq 'html') { |
$token->{tag_name} eq 'html') { |
| 4123 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 4124 |
!!!cp ('t79'); |
!!!cp ('t79'); |
| 4125 |
!!!parse-error (type => 'after html:html', token => $token); |
!!!parse-error (type => 'after html', text => 'html', token => $token); |
| 4126 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 4127 |
} elsif ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 4128 |
!!!cp ('t80'); |
!!!cp ('t80'); |
| 4129 |
!!!parse-error (type => 'after html:html', token => $token); |
!!!parse-error (type => 'after html', text => 'html', token => $token); |
| 4130 |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 4131 |
} else { |
} else { |
| 4132 |
!!!cp ('t81'); |
!!!cp ('t81'); |
| 4177 |
# |
# |
| 4178 |
} elsif ({ |
} elsif ({ |
| 4179 |
b => 1, big => 1, blockquote => 1, body => 1, br => 1, |
b => 1, big => 1, blockquote => 1, body => 1, br => 1, |
| 4180 |
center => 1, code => 1, dd => 1, div => 1, dl => 1, em => 1, |
center => 1, code => 1, dd => 1, div => 1, dl => 1, dt => 1, |
| 4181 |
embed => 1, font => 1, h1 => 1, h2 => 1, h3 => 1, ## No h4! |
em => 1, embed => 1, font => 1, h1 => 1, h2 => 1, h3 => 1, |
| 4182 |
h5 => 1, h6 => 1, head => 1, hr => 1, i => 1, img => 1, |
h4 => 1, h5 => 1, h6 => 1, head => 1, hr => 1, i => 1, |
| 4183 |
li => 1, menu => 1, meta => 1, nobr => 1, p => 1, pre => 1, |
img => 1, li => 1, listing => 1, menu => 1, meta => 1, |
| 4184 |
ruby => 1, s => 1, small => 1, span => 1, strong => 1, |
nobr => 1, ol => 1, p => 1, pre => 1, ruby => 1, s => 1, |
| 4185 |
sub => 1, sup => 1, table => 1, tt => 1, u => 1, ul => 1, |
small => 1, span => 1, strong => 1, strike => 1, sub => 1, |
| 4186 |
var => 1, |
sup => 1, table => 1, tt => 1, u => 1, ul => 1, var => 1, |
| 4187 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 4188 |
!!!cp ('t87.2'); |
!!!cp ('t87.2'); |
| 4189 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 4190 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 4191 |
->manakai_local_name, |
->manakai_local_name, |
| 4192 |
token => $token); |
token => $token); |
| 4193 |
|
|
| 4263 |
!!!cp ('t87.5'); |
!!!cp ('t87.5'); |
| 4264 |
# |
# |
| 4265 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
|
## NOTE: "using the rules for secondary insertion mode" then "continue" |
|
| 4266 |
!!!cp ('t87.6'); |
!!!cp ('t87.6'); |
| 4267 |
# |
!!!parse-error (type => 'not closed', |
| 4268 |
## TODO: ... |
text => $self->{open_elements}->[-1]->[0] |
| 4269 |
|
->manakai_local_name, |
| 4270 |
|
token => $token); |
| 4271 |
|
|
| 4272 |
|
pop @{$self->{open_elements}} |
| 4273 |
|
while $self->{open_elements}->[-1]->[1] & FOREIGN_EL; |
| 4274 |
|
|
| 4275 |
|
$self->{insertion_mode} &= ~ IN_FOREIGN_CONTENT_IM; |
| 4276 |
|
## Reprocess. |
| 4277 |
|
next B; |
| 4278 |
} else { |
} else { |
| 4279 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 4280 |
} |
} |
| 4315 |
!!!cp ('t90'); |
!!!cp ('t90'); |
| 4316 |
## As if </noscript> |
## As if </noscript> |
| 4317 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4318 |
!!!parse-error (type => 'in noscript:#character', token => $token); |
!!!parse-error (type => 'in noscript:#text', token => $token); |
| 4319 |
|
|
| 4320 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4321 |
## As if </head> |
## As if </head> |
| 4351 |
!!!next-token; |
!!!next-token; |
| 4352 |
next B; |
next B; |
| 4353 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4354 |
!!!cp ('t94'); |
!!!cp ('t93.2'); |
| 4355 |
# |
!!!parse-error (type => 'after head', text => 'head', |
| 4356 |
|
token => $token); |
| 4357 |
|
## Ignore the token |
| 4358 |
|
!!!nack ('t93.3'); |
| 4359 |
|
!!!next-token; |
| 4360 |
|
next B; |
| 4361 |
} else { |
} else { |
| 4362 |
!!!cp ('t95'); |
!!!cp ('t95'); |
| 4363 |
!!!parse-error (type => 'in head:head', token => $token); # or in head noscript |
!!!parse-error (type => 'in head:head', |
| 4364 |
|
token => $token); # or in head noscript |
| 4365 |
## Ignore the token |
## Ignore the token |
| 4366 |
!!!nack ('t95.1'); |
!!!nack ('t95.1'); |
| 4367 |
!!!next-token; |
!!!next-token; |
| 4386 |
!!!cp ('t98'); |
!!!cp ('t98'); |
| 4387 |
## As if </noscript> |
## As if </noscript> |
| 4388 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4389 |
!!!parse-error (type => 'in noscript:base', token => $token); |
!!!parse-error (type => 'in noscript', text => 'base', |
| 4390 |
|
token => $token); |
| 4391 |
|
|
| 4392 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4393 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4398 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4399 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4400 |
!!!cp ('t100'); |
!!!cp ('t100'); |
| 4401 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4402 |
|
text => $token->{tag_name}, token => $token); |
| 4403 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4404 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4405 |
} else { |
} else { |
| 4416 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4417 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4418 |
!!!cp ('t102'); |
!!!cp ('t102'); |
| 4419 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4420 |
|
text => $token->{tag_name}, token => $token); |
| 4421 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4422 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4423 |
} else { |
} else { |
| 4434 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4435 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4436 |
!!!cp ('t104'); |
!!!cp ('t104'); |
| 4437 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4438 |
|
text => $token->{tag_name}, token => $token); |
| 4439 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4440 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4441 |
} else { |
} else { |
| 4459 |
->{has_reference}); |
->{has_reference}); |
| 4460 |
} elsif ($token->{attributes}->{content}) { |
} elsif ($token->{attributes}->{content}) { |
| 4461 |
if ($token->{attributes}->{content}->{value} |
if ($token->{attributes}->{content}->{value} |
| 4462 |
=~ /\A[^;]*;[\x09-\x0D\x20]*[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
=~ /[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
| 4463 |
[\x09-\x0D\x20]*= |
[\x09-\x0D\x20]*= |
| 4464 |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
| 4465 |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20\x3B]*))/x) { |
| 4466 |
!!!cp ('t107'); |
!!!cp ('t107'); |
| 4467 |
## NOTE: Whether the encoding is supported or not is handled |
## NOTE: Whether the encoding is supported or not is handled |
| 4468 |
## in the {change_encoding} callback. |
## in the {change_encoding} callback. |
| 4504 |
!!!cp ('t111'); |
!!!cp ('t111'); |
| 4505 |
## As if </noscript> |
## As if </noscript> |
| 4506 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4507 |
!!!parse-error (type => 'in noscript:title', token => $token); |
!!!parse-error (type => 'in noscript', text => 'title', |
| 4508 |
|
token => $token); |
| 4509 |
|
|
| 4510 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4511 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4512 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4513 |
!!!cp ('t112'); |
!!!cp ('t112'); |
| 4514 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4515 |
|
text => $token->{tag_name}, token => $token); |
| 4516 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4517 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4518 |
} else { |
} else { |
| 4526 |
pop @{$self->{open_elements}} # <head> |
pop @{$self->{open_elements}} # <head> |
| 4527 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 4528 |
next B; |
next B; |
| 4529 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($token->{tag_name} eq 'style' or |
| 4530 |
|
$token->{tag_name} eq 'noframes') { |
| 4531 |
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
| 4532 |
## insertion mode IN_HEAD_IM) |
## insertion mode IN_HEAD_IM) |
| 4533 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4534 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4535 |
!!!cp ('t114'); |
!!!cp ('t114'); |
| 4536 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4537 |
|
text => $token->{tag_name}, token => $token); |
| 4538 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4539 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4540 |
} else { |
} else { |
| 4555 |
next B; |
next B; |
| 4556 |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4557 |
!!!cp ('t117'); |
!!!cp ('t117'); |
| 4558 |
!!!parse-error (type => 'in noscript:noscript', token => $token); |
!!!parse-error (type => 'in noscript', text => 'noscript', |
| 4559 |
|
token => $token); |
| 4560 |
## Ignore the token |
## Ignore the token |
| 4561 |
!!!nack ('t117.1'); |
!!!nack ('t117.1'); |
| 4562 |
!!!next-token; |
!!!next-token; |
| 4570 |
!!!cp ('t119'); |
!!!cp ('t119'); |
| 4571 |
## As if </noscript> |
## As if </noscript> |
| 4572 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4573 |
!!!parse-error (type => 'in noscript:script', token => $token); |
!!!parse-error (type => 'in noscript', text => 'script', |
| 4574 |
|
token => $token); |
| 4575 |
|
|
| 4576 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4577 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4578 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4579 |
!!!cp ('t120'); |
!!!cp ('t120'); |
| 4580 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4581 |
|
text => $token->{tag_name}, token => $token); |
| 4582 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4583 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4584 |
} else { |
} else { |
| 4596 |
!!!cp ('t122'); |
!!!cp ('t122'); |
| 4597 |
## As if </noscript> |
## As if </noscript> |
| 4598 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4599 |
!!!parse-error (type => 'in noscript:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in noscript', |
| 4600 |
|
text => $token->{tag_name}, token => $token); |
| 4601 |
|
|
| 4602 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4603 |
## As if </head> |
## As if </head> |
| 4636 |
!!!cp ('t129'); |
!!!cp ('t129'); |
| 4637 |
## As if </noscript> |
## As if </noscript> |
| 4638 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4639 |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in noscript:/', |
| 4640 |
|
text => $token->{tag_name}, token => $token); |
| 4641 |
|
|
| 4642 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4643 |
## As if </head> |
## As if </head> |
| 4680 |
!!!cp ('t133'); |
!!!cp ('t133'); |
| 4681 |
## As if </noscript> |
## As if </noscript> |
| 4682 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4683 |
!!!parse-error (type => 'in noscript:/head', token => $token); |
!!!parse-error (type => 'in noscript:/', |
| 4684 |
|
text => 'head', token => $token); |
| 4685 |
|
|
| 4686 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4687 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4694 |
$self->{insertion_mode} = AFTER_HEAD_IM; |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4695 |
!!!next-token; |
!!!next-token; |
| 4696 |
next B; |
next B; |
| 4697 |
|
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4698 |
|
!!!cp ('t134.1'); |
| 4699 |
|
!!!parse-error (type => 'unmatched end tag', text => 'head', |
| 4700 |
|
token => $token); |
| 4701 |
|
## Ignore the token |
| 4702 |
|
!!!next-token; |
| 4703 |
|
next B; |
| 4704 |
} else { |
} else { |
| 4705 |
!!!cp ('t135'); |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
|
# |
|
| 4706 |
} |
} |
| 4707 |
} elsif ($token->{tag_name} eq 'noscript') { |
} elsif ($token->{tag_name} eq 'noscript') { |
| 4708 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4711 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4712 |
!!!next-token; |
!!!next-token; |
| 4713 |
next B; |
next B; |
| 4714 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM or |
| 4715 |
|
$self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4716 |
!!!cp ('t137'); |
!!!cp ('t137'); |
| 4717 |
!!!parse-error (type => 'unmatched end tag:noscript', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4718 |
|
text => 'noscript', token => $token); |
| 4719 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 4720 |
!!!next-token; |
!!!next-token; |
| 4721 |
next B; |
next B; |
| 4726 |
} elsif ({ |
} elsif ({ |
| 4727 |
body => 1, html => 1, |
body => 1, html => 1, |
| 4728 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 4729 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM or |
| 4730 |
!!!cp ('t139'); |
$self->{insertion_mode} == IN_HEAD_IM or |
| 4731 |
## As if <head> |
$self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
|
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
|
|
push @{$self->{open_elements}}, |
|
|
[$self->{head_element}, $el_category->{head}]; |
|
|
|
|
|
$self->{insertion_mode} = IN_HEAD_IM; |
|
|
## Reprocess in the "in head" insertion mode... |
|
|
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
|
| 4732 |
!!!cp ('t140'); |
!!!cp ('t140'); |
| 4733 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4734 |
|
text => $token->{tag_name}, token => $token); |
| 4735 |
|
## Ignore the token |
| 4736 |
|
!!!next-token; |
| 4737 |
|
next B; |
| 4738 |
|
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4739 |
|
!!!cp ('t140.1'); |
| 4740 |
|
!!!parse-error (type => 'unmatched end tag', |
| 4741 |
|
text => $token->{tag_name}, token => $token); |
| 4742 |
## Ignore the token |
## Ignore the token |
| 4743 |
!!!next-token; |
!!!next-token; |
| 4744 |
next B; |
next B; |
| 4745 |
} else { |
} else { |
| 4746 |
!!!cp ('t141'); |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
| 4747 |
} |
} |
| 4748 |
|
} elsif ($token->{tag_name} eq 'p') { |
| 4749 |
# |
!!!cp ('t142'); |
| 4750 |
} elsif ({ |
!!!parse-error (type => 'unmatched end tag', |
| 4751 |
p => 1, br => 1, |
text => $token->{tag_name}, token => $token); |
| 4752 |
}->{$token->{tag_name}}) { |
## Ignore the token |
| 4753 |
|
!!!next-token; |
| 4754 |
|
next B; |
| 4755 |
|
} elsif ($token->{tag_name} eq 'br') { |
| 4756 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4757 |
!!!cp ('t142'); |
!!!cp ('t142.2'); |
| 4758 |
## As if <head> |
## (before head) as if <head>, (in head) as if </head> |
| 4759 |
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
| 4760 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 4761 |
push @{$self->{open_elements}}, |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4762 |
[$self->{head_element}, $el_category->{head}]; |
|
| 4763 |
|
## Reprocess in the "after head" insertion mode... |
| 4764 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 4765 |
|
!!!cp ('t143.2'); |
| 4766 |
|
## As if </head> |
| 4767 |
|
pop @{$self->{open_elements}}; |
| 4768 |
|
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4769 |
|
|
| 4770 |
|
## Reprocess in the "after head" insertion mode... |
| 4771 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4772 |
|
!!!cp ('t143.3'); |
| 4773 |
|
## ISSUE: Two parse errors for <head><noscript></br> |
| 4774 |
|
!!!parse-error (type => 'unmatched end tag', |
| 4775 |
|
text => 'br', token => $token); |
| 4776 |
|
## As if </noscript> |
| 4777 |
|
pop @{$self->{open_elements}}; |
| 4778 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4779 |
|
|
| 4780 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4781 |
} else { |
## As if </head> |
| 4782 |
!!!cp ('t143'); |
pop @{$self->{open_elements}}; |
| 4783 |
} |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4784 |
|
|
| 4785 |
# |
## Reprocess in the "after head" insertion mode... |
| 4786 |
} else { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4787 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
!!!cp ('t143.4'); |
|
!!!cp ('t144'); |
|
| 4788 |
# |
# |
| 4789 |
} else { |
} else { |
| 4790 |
!!!cp ('t145'); |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
next B; |
|
| 4791 |
} |
} |
| 4792 |
|
|
| 4793 |
|
## ISSUE: does not agree with IE7 - it doesn't ignore </br>. |
| 4794 |
|
!!!parse-error (type => 'unmatched end tag', |
| 4795 |
|
text => 'br', token => $token); |
| 4796 |
|
## Ignore the token |
| 4797 |
|
!!!next-token; |
| 4798 |
|
next B; |
| 4799 |
|
} else { |
| 4800 |
|
!!!cp ('t145'); |
| 4801 |
|
!!!parse-error (type => 'unmatched end tag', |
| 4802 |
|
text => $token->{tag_name}, token => $token); |
| 4803 |
|
## Ignore the token |
| 4804 |
|
!!!next-token; |
| 4805 |
|
next B; |
| 4806 |
} |
} |
| 4807 |
|
|
| 4808 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4809 |
!!!cp ('t146'); |
!!!cp ('t146'); |
| 4810 |
## As if </noscript> |
## As if </noscript> |
| 4811 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4812 |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in noscript:/', |
| 4813 |
|
text => $token->{tag_name}, token => $token); |
| 4814 |
|
|
| 4815 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4816 |
## As if </head> |
## As if </head> |
| 4826 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4827 |
## ISSUE: This case cannot be reached? |
## ISSUE: This case cannot be reached? |
| 4828 |
!!!cp ('t148'); |
!!!cp ('t148'); |
| 4829 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4830 |
|
text => $token->{tag_name}, token => $token); |
| 4831 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 4832 |
!!!next-token; |
!!!next-token; |
| 4833 |
next B; |
next B; |
| 4938 |
|
|
| 4939 |
!!!cp ('t153'); |
!!!cp ('t153'); |
| 4940 |
!!!parse-error (type => 'start tag not allowed', |
!!!parse-error (type => 'start tag not allowed', |
| 4941 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 4942 |
## Ignore the token |
## Ignore the token |
| 4943 |
!!!nack ('t153.1'); |
!!!nack ('t153.1'); |
| 4944 |
!!!next-token; |
!!!next-token; |
| 4945 |
next B; |
next B; |
| 4946 |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 4947 |
!!!parse-error (type => 'not closed:caption', token => $token); |
!!!parse-error (type => 'not closed', text => 'caption', |
| 4948 |
|
token => $token); |
| 4949 |
|
|
| 4950 |
## NOTE: As if </caption>. |
## NOTE: As if </caption>. |
| 4951 |
## have a table element in table scope |
## have a table element in table scope |
| 4965 |
|
|
| 4966 |
!!!cp ('t157'); |
!!!cp ('t157'); |
| 4967 |
!!!parse-error (type => 'start tag not allowed', |
!!!parse-error (type => 'start tag not allowed', |
| 4968 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 4969 |
## Ignore the token |
## Ignore the token |
| 4970 |
!!!nack ('t157.1'); |
!!!nack ('t157.1'); |
| 4971 |
!!!next-token; |
!!!next-token; |
| 4982 |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
| 4983 |
!!!cp ('t159'); |
!!!cp ('t159'); |
| 4984 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 4985 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 4986 |
->manakai_local_name, |
->manakai_local_name, |
| 4987 |
token => $token); |
token => $token); |
| 4988 |
} else { |
} else { |
| 5024 |
} # INSCOPE |
} # INSCOPE |
| 5025 |
unless (defined $i) { |
unless (defined $i) { |
| 5026 |
!!!cp ('t165'); |
!!!cp ('t165'); |
| 5027 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5028 |
|
text => $token->{tag_name}, |
| 5029 |
|
token => $token); |
| 5030 |
## Ignore the token |
## Ignore the token |
| 5031 |
!!!next-token; |
!!!next-token; |
| 5032 |
next B; |
next B; |
| 5043 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 5044 |
!!!cp ('t167'); |
!!!cp ('t167'); |
| 5045 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5046 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5047 |
->manakai_local_name, |
->manakai_local_name, |
| 5048 |
token => $token); |
token => $token); |
| 5049 |
} else { |
} else { |
| 5060 |
next B; |
next B; |
| 5061 |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 5062 |
!!!cp ('t169'); |
!!!cp ('t169'); |
| 5063 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5064 |
|
text => $token->{tag_name}, token => $token); |
| 5065 |
## Ignore the token |
## Ignore the token |
| 5066 |
!!!next-token; |
!!!next-token; |
| 5067 |
next B; |
next B; |
| 5088 |
|
|
| 5089 |
!!!cp ('t173'); |
!!!cp ('t173'); |
| 5090 |
!!!parse-error (type => 'unmatched end tag', |
!!!parse-error (type => 'unmatched end tag', |
| 5091 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 5092 |
## Ignore the token |
## Ignore the token |
| 5093 |
!!!next-token; |
!!!next-token; |
| 5094 |
next B; |
next B; |
| 5104 |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
| 5105 |
!!!cp ('t175'); |
!!!cp ('t175'); |
| 5106 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5107 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5108 |
->manakai_local_name, |
->manakai_local_name, |
| 5109 |
token => $token); |
token => $token); |
| 5110 |
} else { |
} else { |
| 5121 |
next B; |
next B; |
| 5122 |
} elsif ($self->{insertion_mode} == IN_CELL_IM) { |
} elsif ($self->{insertion_mode} == IN_CELL_IM) { |
| 5123 |
!!!cp ('t177'); |
!!!cp ('t177'); |
| 5124 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5125 |
|
text => $token->{tag_name}, token => $token); |
| 5126 |
## Ignore the token |
## Ignore the token |
| 5127 |
!!!next-token; |
!!!next-token; |
| 5128 |
next B; |
next B; |
| 5165 |
|
|
| 5166 |
!!!cp ('t182'); |
!!!cp ('t182'); |
| 5167 |
!!!parse-error (type => 'unmatched end tag', |
!!!parse-error (type => 'unmatched end tag', |
| 5168 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 5169 |
## Ignore the token |
## Ignore the token |
| 5170 |
!!!next-token; |
!!!next-token; |
| 5171 |
next B; |
next B; |
| 5172 |
} # INSCOPE |
} # INSCOPE |
| 5173 |
} elsif ($token->{tag_name} eq 'table' and |
} elsif ($token->{tag_name} eq 'table' and |
| 5174 |
$self->{insertion_mode} == IN_CAPTION_IM) { |
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 5175 |
!!!parse-error (type => 'not closed:caption', token => $token); |
!!!parse-error (type => 'not closed', text => 'caption', |
| 5176 |
|
token => $token); |
| 5177 |
|
|
| 5178 |
## As if </caption> |
## As if </caption> |
| 5179 |
## have a table element in table scope |
## have a table element in table scope |
| 5191 |
} # INSCOPE |
} # INSCOPE |
| 5192 |
unless (defined $i) { |
unless (defined $i) { |
| 5193 |
!!!cp ('t186'); |
!!!cp ('t186'); |
| 5194 |
!!!parse-error (type => 'unmatched end tag:caption', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5195 |
|
text => 'caption', token => $token); |
| 5196 |
## Ignore the token |
## Ignore the token |
| 5197 |
!!!next-token; |
!!!next-token; |
| 5198 |
next B; |
next B; |
| 5207 |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
| 5208 |
!!!cp ('t188'); |
!!!cp ('t188'); |
| 5209 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5210 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5211 |
->manakai_local_name, |
->manakai_local_name, |
| 5212 |
token => $token); |
token => $token); |
| 5213 |
} else { |
} else { |
| 5227 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5228 |
if ($self->{insertion_mode} & BODY_TABLE_IMS) { |
if ($self->{insertion_mode} & BODY_TABLE_IMS) { |
| 5229 |
!!!cp ('t190'); |
!!!cp ('t190'); |
| 5230 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5231 |
|
text => $token->{tag_name}, token => $token); |
| 5232 |
## Ignore the token |
## Ignore the token |
| 5233 |
!!!next-token; |
!!!next-token; |
| 5234 |
next B; |
next B; |
| 5242 |
}->{$token->{tag_name}} and |
}->{$token->{tag_name}} and |
| 5243 |
$self->{insertion_mode} == IN_CAPTION_IM) { |
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 5244 |
!!!cp ('t192'); |
!!!cp ('t192'); |
| 5245 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5246 |
|
text => $token->{tag_name}, token => $token); |
| 5247 |
## Ignore the token |
## Ignore the token |
| 5248 |
!!!next-token; |
!!!next-token; |
| 5249 |
next B; |
next B; |
| 5283 |
} |
} |
| 5284 |
} |
} |
| 5285 |
|
|
| 5286 |
!!!parse-error (type => 'in table:#character', token => $token); |
!!!parse-error (type => 'in table:#text', token => $token); |
| 5287 |
|
|
| 5288 |
## As if in body, but insert into foster parent element |
## As if in body, but insert into foster parent element |
| 5289 |
## ISSUE: Spec says that "whenever a node would be inserted |
## ISSUE: Spec says that "whenever a node would be inserted |
| 5334 |
!!!next-token; |
!!!next-token; |
| 5335 |
next B; |
next B; |
| 5336 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 5337 |
if ({ |
if ({ |
| 5338 |
tr => ($self->{insertion_mode} != IN_ROW_IM), |
tr => ($self->{insertion_mode} != IN_ROW_IM), |
| 5339 |
th => 1, td => 1, |
th => 1, td => 1, |
| 5340 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5341 |
if ($self->{insertion_mode} == IN_TABLE_IM) { |
if ($self->{insertion_mode} == IN_TABLE_IM) { |
| 5342 |
## Clear back to table context |
## Clear back to table context |
| 5343 |
while (not ($self->{open_elements}->[-1]->[1] |
while (not ($self->{open_elements}->[-1]->[1] |
| 5344 |
& TABLE_SCOPING_EL)) { |
& TABLE_SCOPING_EL)) { |
| 5345 |
!!!cp ('t201'); |
!!!cp ('t201'); |
| 5346 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5347 |
} |
} |
| 5348 |
|
|
| 5349 |
!!!insert-element ('tbody',, $token); |
!!!insert-element ('tbody',, $token); |
| 5350 |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 5351 |
## reprocess in the "in table body" insertion mode... |
## reprocess in the "in table body" insertion mode... |
| 5352 |
} |
} |
| 5353 |
|
|
| 5354 |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
| 5355 |
unless ($token->{tag_name} eq 'tr') { |
unless ($token->{tag_name} eq 'tr') { |
| 5356 |
!!!cp ('t202'); |
!!!cp ('t202'); |
| 5357 |
!!!parse-error (type => 'missing start tag:tr', token => $token); |
!!!parse-error (type => 'missing start tag:tr', token => $token); |
| 5358 |
} |
} |
| 5359 |
|
|
| 5360 |
## Clear back to table body context |
## Clear back to table body context |
| 5361 |
while (not ($self->{open_elements}->[-1]->[1] |
while (not ($self->{open_elements}->[-1]->[1] |
| 5362 |
& TABLE_ROWS_SCOPING_EL)) { |
& TABLE_ROWS_SCOPING_EL)) { |
| 5363 |
!!!cp ('t203'); |
!!!cp ('t203'); |
| 5364 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
| 5365 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5366 |
} |
} |
| 5367 |
|
|
| 5368 |
$self->{insertion_mode} = IN_ROW_IM; |
$self->{insertion_mode} = IN_ROW_IM; |
| 5369 |
if ($token->{tag_name} eq 'tr') { |
if ($token->{tag_name} eq 'tr') { |
| 5419 |
unless (defined $i) { |
unless (defined $i) { |
| 5420 |
!!!cp ('t210'); |
!!!cp ('t210'); |
| 5421 |
## TODO: This type is wrong. |
## TODO: This type is wrong. |
| 5422 |
!!!parse-error (type => 'unmacthed end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmacthed end tag', |
| 5423 |
|
text => $token->{tag_name}, token => $token); |
| 5424 |
## Ignore the token |
## Ignore the token |
| 5425 |
!!!nack ('t210.1'); |
!!!nack ('t210.1'); |
| 5426 |
!!!next-token; |
!!!next-token; |
| 5464 |
} # INSCOPE |
} # INSCOPE |
| 5465 |
unless (defined $i) { |
unless (defined $i) { |
| 5466 |
!!!cp ('t216'); |
!!!cp ('t216'); |
| 5467 |
## TODO: This erorr type ios wrong. |
## TODO: This erorr type is wrong. |
| 5468 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5469 |
|
text => $token->{tag_name}, token => $token); |
| 5470 |
## Ignore the token |
## Ignore the token |
| 5471 |
!!!nack ('t216.1'); |
!!!nack ('t216.1'); |
| 5472 |
!!!next-token; |
!!!next-token; |
| 5541 |
} |
} |
| 5542 |
} elsif ($token->{tag_name} eq 'table') { |
} elsif ($token->{tag_name} eq 'table') { |
| 5543 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5544 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5545 |
->manakai_local_name, |
->manakai_local_name, |
| 5546 |
token => $token); |
token => $token); |
| 5547 |
|
|
| 5562 |
unless (defined $i) { |
unless (defined $i) { |
| 5563 |
!!!cp ('t223'); |
!!!cp ('t223'); |
| 5564 |
## TODO: The following is wrong, maybe. |
## TODO: The following is wrong, maybe. |
| 5565 |
!!!parse-error (type => 'unmatched end tag:table', token => $token); |
!!!parse-error (type => 'unmatched end tag', text => 'table', |
| 5566 |
|
token => $token); |
| 5567 |
## Ignore tokens </table><table> |
## Ignore tokens </table><table> |
| 5568 |
!!!nack ('t223.1'); |
!!!nack ('t223.1'); |
| 5569 |
!!!next-token; |
!!!next-token; |
| 5570 |
next B; |
next B; |
| 5571 |
} |
} |
| 5572 |
|
|
| 5573 |
## TODO: Followings are removed from the latest spec. |
## TODO: Followings are removed from the latest spec. |
| 5574 |
## generate implied end tags |
## generate implied end tags |
| 5575 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 5576 |
!!!cp ('t224'); |
!!!cp ('t224'); |
| 5581 |
!!!cp ('t225'); |
!!!cp ('t225'); |
| 5582 |
## NOTE: |<table><tr><table>| |
## NOTE: |<table><tr><table>| |
| 5583 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5584 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5585 |
->manakai_local_name, |
->manakai_local_name, |
| 5586 |
token => $token); |
token => $token); |
| 5587 |
} else { |
} else { |
| 5622 |
my $type = lc $token->{attributes}->{type}->{value}; |
my $type = lc $token->{attributes}->{type}->{value}; |
| 5623 |
if ($type eq 'hidden') { |
if ($type eq 'hidden') { |
| 5624 |
!!!cp ('t227.3'); |
!!!cp ('t227.3'); |
| 5625 |
!!!parse-error (type => 'in table:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in table', |
| 5626 |
|
text => $token->{tag_name}, token => $token); |
| 5627 |
|
|
| 5628 |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5629 |
|
|
| 5651 |
# |
# |
| 5652 |
} |
} |
| 5653 |
|
|
| 5654 |
!!!parse-error (type => 'in table:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in table', text => $token->{tag_name}, |
| 5655 |
|
token => $token); |
| 5656 |
|
|
| 5657 |
$insert = $insert_to_foster; |
$insert = $insert_to_foster; |
| 5658 |
# |
# |
| 5674 |
} # INSCOPE |
} # INSCOPE |
| 5675 |
unless (defined $i) { |
unless (defined $i) { |
| 5676 |
!!!cp ('t230'); |
!!!cp ('t230'); |
| 5677 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5678 |
|
text => $token->{tag_name}, token => $token); |
| 5679 |
## Ignore the token |
## Ignore the token |
| 5680 |
!!!nack ('t230.1'); |
!!!nack ('t230.1'); |
| 5681 |
!!!next-token; |
!!!next-token; |
| 5716 |
unless (defined $i) { |
unless (defined $i) { |
| 5717 |
!!!cp ('t235'); |
!!!cp ('t235'); |
| 5718 |
## TODO: The following is wrong. |
## TODO: The following is wrong. |
| 5719 |
!!!parse-error (type => 'unmatched end tag:'.$token->{type}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5720 |
|
text => $token->{type}, token => $token); |
| 5721 |
## Ignore the token |
## Ignore the token |
| 5722 |
!!!nack ('t236.1'); |
!!!nack ('t236.1'); |
| 5723 |
!!!next-token; |
!!!next-token; |
| 5753 |
} # INSCOPE |
} # INSCOPE |
| 5754 |
unless (defined $i) { |
unless (defined $i) { |
| 5755 |
!!!cp ('t239'); |
!!!cp ('t239'); |
| 5756 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5757 |
|
text => $token->{tag_name}, token => $token); |
| 5758 |
## Ignore the token |
## Ignore the token |
| 5759 |
!!!nack ('t239.1'); |
!!!nack ('t239.1'); |
| 5760 |
!!!next-token; |
!!!next-token; |
| 5800 |
} # INSCOPE |
} # INSCOPE |
| 5801 |
unless (defined $i) { |
unless (defined $i) { |
| 5802 |
!!!cp ('t243'); |
!!!cp ('t243'); |
| 5803 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5804 |
|
text => $token->{tag_name}, token => $token); |
| 5805 |
## Ignore the token |
## Ignore the token |
| 5806 |
!!!nack ('t243.1'); |
!!!nack ('t243.1'); |
| 5807 |
!!!next-token; |
!!!next-token; |
| 5835 |
} # INSCOPE |
} # INSCOPE |
| 5836 |
unless (defined $i) { |
unless (defined $i) { |
| 5837 |
!!!cp ('t249'); |
!!!cp ('t249'); |
| 5838 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5839 |
|
text => $token->{tag_name}, token => $token); |
| 5840 |
## Ignore the token |
## Ignore the token |
| 5841 |
!!!nack ('t249.1'); |
!!!nack ('t249.1'); |
| 5842 |
!!!next-token; |
!!!next-token; |
| 5859 |
} # INSCOPE |
} # INSCOPE |
| 5860 |
unless (defined $i) { |
unless (defined $i) { |
| 5861 |
!!!cp ('t252'); |
!!!cp ('t252'); |
| 5862 |
!!!parse-error (type => 'unmatched end tag:tr', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5863 |
|
text => 'tr', token => $token); |
| 5864 |
## Ignore the token |
## Ignore the token |
| 5865 |
!!!nack ('t252.1'); |
!!!nack ('t252.1'); |
| 5866 |
!!!next-token; |
!!!next-token; |
| 5895 |
} # INSCOPE |
} # INSCOPE |
| 5896 |
unless (defined $i) { |
unless (defined $i) { |
| 5897 |
!!!cp ('t256'); |
!!!cp ('t256'); |
| 5898 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5899 |
|
text => $token->{tag_name}, token => $token); |
| 5900 |
## Ignore the token |
## Ignore the token |
| 5901 |
!!!nack ('t256.1'); |
!!!nack ('t256.1'); |
| 5902 |
!!!next-token; |
!!!next-token; |
| 5923 |
tbody => 1, tfoot => 1, thead => 1, # $self->{insertion_mode} == IN_TABLE_IM |
tbody => 1, tfoot => 1, thead => 1, # $self->{insertion_mode} == IN_TABLE_IM |
| 5924 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5925 |
!!!cp ('t258'); |
!!!cp ('t258'); |
| 5926 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5927 |
|
text => $token->{tag_name}, token => $token); |
| 5928 |
## Ignore the token |
## Ignore the token |
| 5929 |
!!!nack ('t258.1'); |
!!!nack ('t258.1'); |
| 5930 |
!!!next-token; |
!!!next-token; |
| 5931 |
next B; |
next B; |
| 5932 |
} else { |
} else { |
| 5933 |
!!!cp ('t259'); |
!!!cp ('t259'); |
| 5934 |
!!!parse-error (type => 'in table:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in table:/', |
| 5935 |
|
text => $token->{tag_name}, token => $token); |
| 5936 |
|
|
| 5937 |
$insert = $insert_to_foster; |
$insert = $insert_to_foster; |
| 5938 |
# |
# |
| 5982 |
if ($token->{tag_name} eq 'colgroup') { |
if ($token->{tag_name} eq 'colgroup') { |
| 5983 |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
| 5984 |
!!!cp ('t264'); |
!!!cp ('t264'); |
| 5985 |
!!!parse-error (type => 'unmatched end tag:colgroup', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5986 |
|
text => 'colgroup', token => $token); |
| 5987 |
## Ignore the token |
## Ignore the token |
| 5988 |
!!!next-token; |
!!!next-token; |
| 5989 |
next B; |
next B; |
| 5996 |
} |
} |
| 5997 |
} elsif ($token->{tag_name} eq 'col') { |
} elsif ($token->{tag_name} eq 'col') { |
| 5998 |
!!!cp ('t266'); |
!!!cp ('t266'); |
| 5999 |
!!!parse-error (type => 'unmatched end tag:col', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6000 |
|
text => 'col', token => $token); |
| 6001 |
## Ignore the token |
## Ignore the token |
| 6002 |
!!!next-token; |
!!!next-token; |
| 6003 |
next B; |
next B; |
| 6027 |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
| 6028 |
!!!cp ('t269'); |
!!!cp ('t269'); |
| 6029 |
## TODO: Wrong error type? |
## TODO: Wrong error type? |
| 6030 |
!!!parse-error (type => 'unmatched end tag:colgroup', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6031 |
|
text => 'colgroup', token => $token); |
| 6032 |
## Ignore the token |
## Ignore the token |
| 6033 |
!!!nack ('t269.1'); |
!!!nack ('t269.1'); |
| 6034 |
!!!next-token; |
!!!next-token; |
| 6082 |
!!!nack ('t277.1'); |
!!!nack ('t277.1'); |
| 6083 |
!!!next-token; |
!!!next-token; |
| 6084 |
next B; |
next B; |
| 6085 |
} elsif ($token->{tag_name} eq 'select' or |
} elsif ({ |
| 6086 |
$token->{tag_name} eq 'input' or |
select => 1, input => 1, textarea => 1, |
| 6087 |
|
}->{$token->{tag_name}} or |
| 6088 |
($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
| 6089 |
{ |
{ |
| 6090 |
caption => 1, table => 1, |
caption => 1, table => 1, |
| 6092 |
tr => 1, td => 1, th => 1, |
tr => 1, td => 1, th => 1, |
| 6093 |
}->{$token->{tag_name}})) { |
}->{$token->{tag_name}})) { |
| 6094 |
## TODO: The type below is not good - <select> is replaced by </select> |
## TODO: The type below is not good - <select> is replaced by </select> |
| 6095 |
!!!parse-error (type => 'not closed:select', token => $token); |
!!!parse-error (type => 'not closed', text => 'select', |
| 6096 |
|
token => $token); |
| 6097 |
## NOTE: As if the token were </select> (<select> case) or |
## NOTE: As if the token were </select> (<select> case) or |
| 6098 |
## as if there were </select> (otherwise). |
## as if there were </select> (otherwise). |
| 6099 |
## have an element in table scope |
## have an element in table scope |
| 6111 |
} # INSCOPE |
} # INSCOPE |
| 6112 |
unless (defined $i) { |
unless (defined $i) { |
| 6113 |
!!!cp ('t280'); |
!!!cp ('t280'); |
| 6114 |
!!!parse-error (type => 'unmatched end tag:select', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6115 |
|
text => 'select', token => $token); |
| 6116 |
## Ignore the token |
## Ignore the token |
| 6117 |
!!!nack ('t280.1'); |
!!!nack ('t280.1'); |
| 6118 |
!!!next-token; |
!!!next-token; |
| 6136 |
} |
} |
| 6137 |
} else { |
} else { |
| 6138 |
!!!cp ('t282'); |
!!!cp ('t282'); |
| 6139 |
!!!parse-error (type => 'in select:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in select', |
| 6140 |
|
text => $token->{tag_name}, token => $token); |
| 6141 |
## Ignore the token |
## Ignore the token |
| 6142 |
!!!nack ('t282.1'); |
!!!nack ('t282.1'); |
| 6143 |
!!!next-token; |
!!!next-token; |
| 6155 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 6156 |
} else { |
} else { |
| 6157 |
!!!cp ('t285'); |
!!!cp ('t285'); |
| 6158 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6159 |
|
text => $token->{tag_name}, token => $token); |
| 6160 |
## Ignore the token |
## Ignore the token |
| 6161 |
} |
} |
| 6162 |
!!!nack ('t285.1'); |
!!!nack ('t285.1'); |
| 6168 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 6169 |
} else { |
} else { |
| 6170 |
!!!cp ('t287'); |
!!!cp ('t287'); |
| 6171 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6172 |
|
text => $token->{tag_name}, token => $token); |
| 6173 |
## Ignore the token |
## Ignore the token |
| 6174 |
} |
} |
| 6175 |
!!!nack ('t287.1'); |
!!!nack ('t287.1'); |
| 6191 |
} # INSCOPE |
} # INSCOPE |
| 6192 |
unless (defined $i) { |
unless (defined $i) { |
| 6193 |
!!!cp ('t290'); |
!!!cp ('t290'); |
| 6194 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6195 |
|
text => $token->{tag_name}, token => $token); |
| 6196 |
## Ignore the token |
## Ignore the token |
| 6197 |
!!!nack ('t290.1'); |
!!!nack ('t290.1'); |
| 6198 |
!!!next-token; |
!!!next-token; |
| 6213 |
tfoot => 1, thead => 1, tr => 1, td => 1, th => 1, |
tfoot => 1, thead => 1, tr => 1, td => 1, th => 1, |
| 6214 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6215 |
## TODO: The following is wrong? |
## TODO: The following is wrong? |
| 6216 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6217 |
|
text => $token->{tag_name}, token => $token); |
| 6218 |
|
|
| 6219 |
## have an element in table scope |
## have an element in table scope |
| 6220 |
my $i; |
my $i; |
| 6255 |
unless (defined $i) { |
unless (defined $i) { |
| 6256 |
!!!cp ('t297'); |
!!!cp ('t297'); |
| 6257 |
## TODO: The following error type is correct? |
## TODO: The following error type is correct? |
| 6258 |
!!!parse-error (type => 'unmatched end tag:select', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6259 |
|
text => 'select', token => $token); |
| 6260 |
## Ignore the </select> token |
## Ignore the </select> token |
| 6261 |
!!!nack ('t297.1'); |
!!!nack ('t297.1'); |
| 6262 |
!!!next-token; ## TODO: ok? |
!!!next-token; ## TODO: ok? |
| 6273 |
next B; |
next B; |
| 6274 |
} else { |
} else { |
| 6275 |
!!!cp ('t299'); |
!!!cp ('t299'); |
| 6276 |
!!!parse-error (type => 'in select:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in select:/', |
| 6277 |
|
text => $token->{tag_name}, token => $token); |
| 6278 |
## Ignore the token |
## Ignore the token |
| 6279 |
!!!nack ('t299.3'); |
!!!nack ('t299.3'); |
| 6280 |
!!!next-token; |
!!!next-token; |
| 6312 |
|
|
| 6313 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 6314 |
!!!cp ('t301'); |
!!!cp ('t301'); |
| 6315 |
!!!parse-error (type => 'after html:#character', token => $token); |
!!!parse-error (type => 'after html:#text', token => $token); |
| 6316 |
|
|
| 6317 |
## Reprocess in the "after body" insertion mode. |
## Reprocess in the "after body" insertion mode. |
| 6318 |
} else { |
} else { |
| 6320 |
} |
} |
| 6321 |
|
|
| 6322 |
## "after body" insertion mode |
## "after body" insertion mode |
| 6323 |
!!!parse-error (type => 'after body:#character', token => $token); |
!!!parse-error (type => 'after body:#text', token => $token); |
| 6324 |
|
|
| 6325 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 6326 |
## reprocess |
## reprocess |
| 6328 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 6329 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 6330 |
!!!cp ('t303'); |
!!!cp ('t303'); |
| 6331 |
!!!parse-error (type => 'after html:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after html', |
| 6332 |
|
text => $token->{tag_name}, token => $token); |
| 6333 |
|
|
| 6334 |
## Reprocess in the "after body" insertion mode. |
## Reprocess in the "after body" insertion mode. |
| 6335 |
} else { |
} else { |
| 6337 |
} |
} |
| 6338 |
|
|
| 6339 |
## "after body" insertion mode |
## "after body" insertion mode |
| 6340 |
!!!parse-error (type => 'after body:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after body', |
| 6341 |
|
text => $token->{tag_name}, token => $token); |
| 6342 |
|
|
| 6343 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 6344 |
!!!ack-later; |
!!!ack-later; |
| 6347 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 6348 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 6349 |
!!!cp ('t305'); |
!!!cp ('t305'); |
| 6350 |
!!!parse-error (type => 'after html:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after html:/', |
| 6351 |
|
text => $token->{tag_name}, token => $token); |
| 6352 |
|
|
| 6353 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 6354 |
## Reprocess in the "after body" insertion mode. |
## Reprocess in the "after body" insertion mode. |
| 6360 |
if ($token->{tag_name} eq 'html') { |
if ($token->{tag_name} eq 'html') { |
| 6361 |
if (defined $self->{inner_html_node}) { |
if (defined $self->{inner_html_node}) { |
| 6362 |
!!!cp ('t307'); |
!!!cp ('t307'); |
| 6363 |
!!!parse-error (type => 'unmatched end tag:html', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6364 |
|
text => 'html', token => $token); |
| 6365 |
## Ignore the token |
## Ignore the token |
| 6366 |
!!!next-token; |
!!!next-token; |
| 6367 |
next B; |
next B; |
| 6373 |
} |
} |
| 6374 |
} else { |
} else { |
| 6375 |
!!!cp ('t309'); |
!!!cp ('t309'); |
| 6376 |
!!!parse-error (type => 'after body:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after body:/', |
| 6377 |
|
text => $token->{tag_name}, token => $token); |
| 6378 |
|
|
| 6379 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 6380 |
## reprocess |
## reprocess |
| 6402 |
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
| 6403 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6404 |
!!!cp ('t311'); |
!!!cp ('t311'); |
| 6405 |
!!!parse-error (type => 'in frameset:#character', token => $token); |
!!!parse-error (type => 'in frameset:#text', token => $token); |
| 6406 |
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 6407 |
!!!cp ('t312'); |
!!!cp ('t312'); |
| 6408 |
!!!parse-error (type => 'after frameset:#character', token => $token); |
!!!parse-error (type => 'after frameset:#text', token => $token); |
| 6409 |
} else { # "after html frameset" |
} else { # "after after frameset" |
| 6410 |
!!!cp ('t313'); |
!!!cp ('t313'); |
| 6411 |
!!!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); |
|
| 6412 |
} |
} |
| 6413 |
|
|
| 6414 |
## Ignore the token. |
## Ignore the token. |
| 6424 |
|
|
| 6425 |
die qq[$0: Character "$token->{data}"]; |
die qq[$0: Character "$token->{data}"]; |
| 6426 |
} 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'); |
|
|
} |
|
|
|
|
| 6427 |
if ($token->{tag_name} eq 'frameset' and |
if ($token->{tag_name} eq 'frameset' and |
| 6428 |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6429 |
!!!cp ('t318'); |
!!!cp ('t318'); |
| 6441 |
next B; |
next B; |
| 6442 |
} elsif ($token->{tag_name} eq 'noframes') { |
} elsif ($token->{tag_name} eq 'noframes') { |
| 6443 |
!!!cp ('t320'); |
!!!cp ('t320'); |
| 6444 |
## NOTE: As if in body. |
## NOTE: As if in head. |
| 6445 |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 6446 |
next B; |
next B; |
| 6447 |
|
|
| 6448 |
|
## NOTE: |<!DOCTYPE HTML><frameset></frameset></html><noframes></noframes>| |
| 6449 |
|
## has no parse error. |
| 6450 |
} else { |
} else { |
| 6451 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6452 |
!!!cp ('t321'); |
!!!cp ('t321'); |
| 6453 |
!!!parse-error (type => 'in frameset:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in frameset', |
| 6454 |
} else { |
text => $token->{tag_name}, token => $token); |
| 6455 |
|
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 6456 |
!!!cp ('t322'); |
!!!cp ('t322'); |
| 6457 |
!!!parse-error (type => 'after frameset:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after frameset', |
| 6458 |
|
text => $token->{tag_name}, token => $token); |
| 6459 |
|
} else { # "after after frameset" |
| 6460 |
|
!!!cp ('t322.2'); |
| 6461 |
|
!!!parse-error (type => 'after after frameset', |
| 6462 |
|
text => $token->{tag_name}, token => $token); |
| 6463 |
} |
} |
| 6464 |
## Ignore the token |
## Ignore the token |
| 6465 |
!!!nack ('t322.1'); |
!!!nack ('t322.1'); |
| 6467 |
next B; |
next B; |
| 6468 |
} |
} |
| 6469 |
} 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'); |
|
|
} |
|
|
|
|
| 6470 |
if ($token->{tag_name} eq 'frameset' and |
if ($token->{tag_name} eq 'frameset' and |
| 6471 |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6472 |
if ($self->{open_elements}->[-1]->[1] & HTML_EL and |
if ($self->{open_elements}->[-1]->[1] & HTML_EL and |
| 6473 |
@{$self->{open_elements}} == 1) { |
@{$self->{open_elements}} == 1) { |
| 6474 |
!!!cp ('t325'); |
!!!cp ('t325'); |
| 6475 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6476 |
|
text => $token->{tag_name}, token => $token); |
| 6477 |
## Ignore the token |
## Ignore the token |
| 6478 |
!!!next-token; |
!!!next-token; |
| 6479 |
} else { |
} else { |
| 6499 |
} else { |
} else { |
| 6500 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6501 |
!!!cp ('t330'); |
!!!cp ('t330'); |
| 6502 |
!!!parse-error (type => 'in frameset:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in frameset:/', |
| 6503 |
} else { |
text => $token->{tag_name}, token => $token); |
| 6504 |
|
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 6505 |
|
!!!cp ('t330.1'); |
| 6506 |
|
!!!parse-error (type => 'after frameset:/', |
| 6507 |
|
text => $token->{tag_name}, token => $token); |
| 6508 |
|
} else { # "after after html" |
| 6509 |
!!!cp ('t331'); |
!!!cp ('t331'); |
| 6510 |
!!!parse-error (type => 'after frameset:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after after frameset:/', |
| 6511 |
|
text => $token->{tag_name}, token => $token); |
| 6512 |
} |
} |
| 6513 |
## Ignore the token |
## Ignore the token |
| 6514 |
!!!next-token; |
!!!next-token; |
| 6575 |
->{has_reference}); |
->{has_reference}); |
| 6576 |
} elsif ($token->{attributes}->{content}) { |
} elsif ($token->{attributes}->{content}) { |
| 6577 |
if ($token->{attributes}->{content}->{value} |
if ($token->{attributes}->{content}->{value} |
| 6578 |
=~ /\A[^;]*;[\x09-\x0D\x20]*[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
=~ /[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
| 6579 |
[\x09-\x0D\x20]*= |
[\x09-\x0D\x20]*= |
| 6580 |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
| 6581 |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20\x3B]*))/x) { |
| 6582 |
!!!cp ('t336'); |
!!!cp ('t336'); |
| 6583 |
## NOTE: Whether the encoding is supported or not is handled |
## NOTE: Whether the encoding is supported or not is handled |
| 6584 |
## in the {change_encoding} callback. |
## in the {change_encoding} callback. |
| 6616 |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
| 6617 |
next B; |
next B; |
| 6618 |
} elsif ($token->{tag_name} eq 'body') { |
} elsif ($token->{tag_name} eq 'body') { |
| 6619 |
!!!parse-error (type => 'in body:body', token => $token); |
!!!parse-error (type => 'in body', text => 'body', token => $token); |
| 6620 |
|
|
| 6621 |
if (@{$self->{open_elements}} == 1 or |
if (@{$self->{open_elements}} == 1 or |
| 6622 |
not ($self->{open_elements}->[1]->[1] & BODY_EL)) { |
not ($self->{open_elements}->[1]->[1] & BODY_EL)) { |
| 6736 |
if ($i != -1) { |
if ($i != -1) { |
| 6737 |
!!!cp ('t355'); |
!!!cp ('t355'); |
| 6738 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 6739 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 6740 |
->manakai_local_name, |
->manakai_local_name, |
| 6741 |
token => $token); |
token => $token); |
| 6742 |
} else { |
} else { |
| 6890 |
xmp => 1, |
xmp => 1, |
| 6891 |
iframe => 1, |
iframe => 1, |
| 6892 |
noembed => 1, |
noembed => 1, |
| 6893 |
noframes => 1, |
noframes => 1, ## NOTE: This is an "as if in head" code clone. |
| 6894 |
noscript => 0, ## TODO: 1 if scripting is enabled |
noscript => 0, ## TODO: 1 if scripting is enabled |
| 6895 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6896 |
if ($token->{tag_name} eq 'xmp') { |
if ($token->{tag_name} eq 'xmp') { |
| 6912 |
!!!next-token; |
!!!next-token; |
| 6913 |
next B; |
next B; |
| 6914 |
} else { |
} else { |
| 6915 |
|
!!!ack ('t391.1'); |
| 6916 |
|
|
| 6917 |
my $at = $token->{attributes}; |
my $at = $token->{attributes}; |
| 6918 |
my $form_attrs; |
my $form_attrs; |
| 6919 |
$form_attrs->{action} = $at->{action} if $at->{action}; |
$form_attrs->{action} = $at->{action} if $at->{action}; |
| 6957 |
line => $token->{line}, column => $token->{column}}, |
line => $token->{line}, column => $token->{column}}, |
| 6958 |
{type => END_TAG_TOKEN, tag_name => 'form', |
{type => END_TAG_TOKEN, tag_name => 'form', |
| 6959 |
line => $token->{line}, column => $token->{column}}; |
line => $token->{line}, column => $token->{column}}; |
|
!!!nack ('t391.1'); ## NOTE: Not acknowledged. |
|
| 6960 |
!!!back-token (@tokens); |
!!!back-token (@tokens); |
| 6961 |
!!!next-token; |
!!!next-token; |
| 6962 |
next B; |
next B; |
| 7004 |
## Ignore the token |
## Ignore the token |
| 7005 |
} else { |
} else { |
| 7006 |
!!!cp ('t398'); |
!!!cp ('t398'); |
| 7007 |
!!!parse-error (type => 'in RCDATA:#'.$token->{type}, token => $token); |
!!!parse-error (type => 'in RCDATA:#eof', token => $token); |
| 7008 |
} |
} |
| 7009 |
!!!next-token; |
!!!next-token; |
| 7010 |
next B; |
next B; |
| 7011 |
|
} elsif ($token->{tag_name} eq 'rt' or |
| 7012 |
|
$token->{tag_name} eq 'rp') { |
| 7013 |
|
## has a |ruby| element in scope |
| 7014 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 7015 |
|
my $node = $self->{open_elements}->[$_]; |
| 7016 |
|
if ($node->[1] & RUBY_EL) { |
| 7017 |
|
!!!cp ('t398.1'); |
| 7018 |
|
## generate implied end tags |
| 7019 |
|
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 7020 |
|
!!!cp ('t398.2'); |
| 7021 |
|
pop @{$self->{open_elements}}; |
| 7022 |
|
} |
| 7023 |
|
unless ($self->{open_elements}->[-1]->[1] & RUBY_EL) { |
| 7024 |
|
!!!cp ('t398.3'); |
| 7025 |
|
!!!parse-error (type => 'not closed', |
| 7026 |
|
text => $self->{open_elements}->[-1]->[0] |
| 7027 |
|
->manakai_local_name, |
| 7028 |
|
token => $token); |
| 7029 |
|
pop @{$self->{open_elements}} |
| 7030 |
|
while not $self->{open_elements}->[-1]->[1] & RUBY_EL; |
| 7031 |
|
} |
| 7032 |
|
last INSCOPE; |
| 7033 |
|
} elsif ($node->[1] & SCOPING_EL) { |
| 7034 |
|
!!!cp ('t398.4'); |
| 7035 |
|
last INSCOPE; |
| 7036 |
|
} |
| 7037 |
|
} # INSCOPE |
| 7038 |
|
|
| 7039 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 7040 |
|
|
| 7041 |
|
!!!nack ('t398.5'); |
| 7042 |
|
!!!next-token; |
| 7043 |
|
redo B; |
| 7044 |
} elsif ($token->{tag_name} eq 'math' or |
} elsif ($token->{tag_name} eq 'math' or |
| 7045 |
$token->{tag_name} eq 'svg') { |
$token->{tag_name} eq 'svg') { |
| 7046 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 7047 |
|
|
| 7048 |
|
## "Adjust MathML attributes" ('math' only) - done in insert-element-f |
| 7049 |
|
|
| 7050 |
## "adjust SVG attributes" ('svg' only) - done in insert-element-f |
## "adjust SVG attributes" ('svg' only) - done in insert-element-f |
| 7051 |
|
|
| 7052 |
## "adjust foreign attributes" - done in insert-element-f |
## "adjust foreign attributes" - done in insert-element-f |
| 7073 |
thead => 1, tr => 1, |
thead => 1, tr => 1, |
| 7074 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 7075 |
!!!cp ('t401'); |
!!!cp ('t401'); |
| 7076 |
!!!parse-error (type => 'in body:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in body', |
| 7077 |
|
text => $token->{tag_name}, token => $token); |
| 7078 |
## Ignore the token |
## Ignore the token |
| 7079 |
!!!nack ('t401.1'); ## NOTE: |<col/>| or |<frame/>| here is an error. |
!!!nack ('t401.1'); ## NOTE: |<col/>| or |<frame/>| here is an error. |
| 7080 |
!!!next-token; |
!!!next-token; |
| 7159 |
} |
} |
| 7160 |
|
|
| 7161 |
!!!parse-error (type => 'start tag not allowed', |
!!!parse-error (type => 'start tag not allowed', |
| 7162 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 7163 |
## NOTE: Ignore the token. |
## NOTE: Ignore the token. |
| 7164 |
!!!next-token; |
!!!next-token; |
| 7165 |
next B; |
next B; |
| 7169 |
unless ($_->[1] & ALL_END_TAG_OPTIONAL_EL) { |
unless ($_->[1] & ALL_END_TAG_OPTIONAL_EL) { |
| 7170 |
!!!cp ('t403'); |
!!!cp ('t403'); |
| 7171 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7172 |
value => $_->[0]->manakai_local_name, |
text => $_->[0]->manakai_local_name, |
| 7173 |
token => $token); |
token => $token); |
| 7174 |
last; |
last; |
| 7175 |
} else { |
} else { |
| 7189 |
unless ($self->{open_elements}->[-1]->[1] & BODY_EL) { |
unless ($self->{open_elements}->[-1]->[1] & BODY_EL) { |
| 7190 |
!!!cp ('t406'); |
!!!cp ('t406'); |
| 7191 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7192 |
value => $self->{open_elements}->[1]->[0] |
text => $self->{open_elements}->[1]->[0] |
| 7193 |
->manakai_local_name, |
->manakai_local_name, |
| 7194 |
token => $token); |
token => $token); |
| 7195 |
} else { |
} else { |
| 7200 |
next B; |
next B; |
| 7201 |
} else { |
} else { |
| 7202 |
!!!cp ('t408'); |
!!!cp ('t408'); |
| 7203 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7204 |
|
text => $token->{tag_name}, token => $token); |
| 7205 |
## Ignore the token |
## Ignore the token |
| 7206 |
!!!next-token; |
!!!next-token; |
| 7207 |
next B; |
next B; |
| 7229 |
|
|
| 7230 |
unless (defined $i) { # has an element in scope |
unless (defined $i) { # has an element in scope |
| 7231 |
!!!cp ('t413'); |
!!!cp ('t413'); |
| 7232 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7233 |
|
text => $token->{tag_name}, token => $token); |
| 7234 |
|
## NOTE: Ignore the token. |
| 7235 |
} else { |
} else { |
| 7236 |
## Step 1. generate implied end tags |
## Step 1. generate implied end tags |
| 7237 |
while ({ |
while ({ |
| 7238 |
|
## END_TAG_OPTIONAL_EL |
| 7239 |
dd => ($token->{tag_name} ne 'dd'), |
dd => ($token->{tag_name} ne 'dd'), |
| 7240 |
dt => ($token->{tag_name} ne 'dt'), |
dt => ($token->{tag_name} ne 'dt'), |
| 7241 |
li => ($token->{tag_name} ne 'li'), |
li => ($token->{tag_name} ne 'li'), |
| 7242 |
p => 1, |
p => 1, |
| 7243 |
|
rt => 1, |
| 7244 |
|
rp => 1, |
| 7245 |
}->{$self->{open_elements}->[-1]->[0]->manakai_local_name}) { |
}->{$self->{open_elements}->[-1]->[0]->manakai_local_name}) { |
| 7246 |
!!!cp ('t409'); |
!!!cp ('t409'); |
| 7247 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 7252 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 7253 |
!!!cp ('t412'); |
!!!cp ('t412'); |
| 7254 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7255 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 7256 |
->manakai_local_name, |
->manakai_local_name, |
| 7257 |
token => $token); |
token => $token); |
| 7258 |
} else { |
} else { |
| 7289 |
|
|
| 7290 |
unless (defined $i) { # has an element in scope |
unless (defined $i) { # has an element in scope |
| 7291 |
!!!cp ('t421'); |
!!!cp ('t421'); |
| 7292 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7293 |
|
text => $token->{tag_name}, token => $token); |
| 7294 |
|
## NOTE: Ignore the token. |
| 7295 |
} else { |
} else { |
| 7296 |
## Step 1. generate implied end tags |
## Step 1. generate implied end tags |
| 7297 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 7304 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 7305 |
!!!cp ('t417.1'); |
!!!cp ('t417.1'); |
| 7306 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7307 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 7308 |
->manakai_local_name, |
->manakai_local_name, |
| 7309 |
token => $token); |
token => $token); |
| 7310 |
} else { |
} else { |
| 7336 |
|
|
| 7337 |
unless (defined $i) { # has an element in scope |
unless (defined $i) { # has an element in scope |
| 7338 |
!!!cp ('t425.1'); |
!!!cp ('t425.1'); |
| 7339 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7340 |
|
text => $token->{tag_name}, token => $token); |
| 7341 |
|
## NOTE: Ignore the token. |
| 7342 |
} else { |
} else { |
| 7343 |
## Step 1. generate implied end tags |
## Step 1. generate implied end tags |
| 7344 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 7350 |
if ($self->{open_elements}->[-1]->[0]->manakai_local_name |
if ($self->{open_elements}->[-1]->[0]->manakai_local_name |
| 7351 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 7352 |
!!!cp ('t425'); |
!!!cp ('t425'); |
| 7353 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7354 |
|
text => $token->{tag_name}, token => $token); |
| 7355 |
} else { |
} else { |
| 7356 |
!!!cp ('t426'); |
!!!cp ('t426'); |
| 7357 |
} |
} |
| 7382 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 7383 |
!!!cp ('t412.1'); |
!!!cp ('t412.1'); |
| 7384 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7385 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 7386 |
->manakai_local_name, |
->manakai_local_name, |
| 7387 |
token => $token); |
token => $token); |
| 7388 |
} else { |
} else { |
| 7392 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 7393 |
} else { |
} else { |
| 7394 |
!!!cp ('t413.1'); |
!!!cp ('t413.1'); |
| 7395 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7396 |
|
text => $token->{tag_name}, token => $token); |
| 7397 |
|
|
| 7398 |
!!!cp ('t415.1'); |
!!!cp ('t415.1'); |
| 7399 |
## As if <p>, then reprocess the current token |
## As if <p>, then reprocess the current token |
| 7416 |
next B; |
next B; |
| 7417 |
} elsif ($token->{tag_name} eq 'br') { |
} elsif ($token->{tag_name} eq 'br') { |
| 7418 |
!!!cp ('t428'); |
!!!cp ('t428'); |
| 7419 |
!!!parse-error (type => 'unmatched end tag:br', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7420 |
|
text => 'br', token => $token); |
| 7421 |
|
|
| 7422 |
## As if <br> |
## As if <br> |
| 7423 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 7442 |
noscript => 0, ## TODO: if scripting is enabled |
noscript => 0, ## TODO: if scripting is enabled |
| 7443 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 7444 |
!!!cp ('t429'); |
!!!cp ('t429'); |
| 7445 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7446 |
|
text => $token->{tag_name}, token => $token); |
| 7447 |
## Ignore the token |
## Ignore the token |
| 7448 |
!!!next-token; |
!!!next-token; |
| 7449 |
next B; |
next B; |
| 7462 |
## generate implied end tags |
## generate implied end tags |
| 7463 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 7464 |
!!!cp ('t430'); |
!!!cp ('t430'); |
| 7465 |
## ISSUE: Can this case be reached? |
## NOTE: |<ruby><rt></ruby>|. |
| 7466 |
|
## ISSUE: <ruby><rt></rt> will also take this code path, |
| 7467 |
|
## which seems wrong. |
| 7468 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 7469 |
|
$node_i++; |
| 7470 |
} |
} |
| 7471 |
|
|
| 7472 |
## Step 2 |
## Step 2 |
| 7475 |
!!!cp ('t431'); |
!!!cp ('t431'); |
| 7476 |
## NOTE: <x><y></x> |
## NOTE: <x><y></x> |
| 7477 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7478 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 7479 |
->manakai_local_name, |
->manakai_local_name, |
| 7480 |
token => $token); |
token => $token); |
| 7481 |
} else { |
} else { |
| 7483 |
} |
} |
| 7484 |
|
|
| 7485 |
## Step 3 |
## Step 3 |
| 7486 |
splice @{$self->{open_elements}}, $node_i; |
splice @{$self->{open_elements}}, $node_i if $node_i < 0; |
| 7487 |
|
|
| 7488 |
!!!next-token; |
!!!next-token; |
| 7489 |
last S2; |
last S2; |
| 7494 |
($node->[1] & SPECIAL_EL or |
($node->[1] & SPECIAL_EL or |
| 7495 |
$node->[1] & SCOPING_EL)) { |
$node->[1] & SCOPING_EL)) { |
| 7496 |
!!!cp ('t433'); |
!!!cp ('t433'); |
| 7497 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7498 |
|
text => $token->{tag_name}, token => $token); |
| 7499 |
## Ignore the token |
## Ignore the token |
| 7500 |
!!!next-token; |
!!!next-token; |
| 7501 |
last S2; |
last S2; |
| 7541 |
## TODO: script stuffs |
## TODO: script stuffs |
| 7542 |
} # _tree_construct_main |
} # _tree_construct_main |
| 7543 |
|
|
| 7544 |
sub set_inner_html ($$$) { |
sub set_inner_html ($$$;$) { |
| 7545 |
my $class = shift; |
my $class = shift; |
| 7546 |
my $node = shift; |
my $node = shift; |
| 7547 |
my $s = \$_[0]; |
my $s = \$_[0]; |
| 7548 |
my $onerror = $_[1]; |
my $onerror = $_[1]; |
| 7549 |
|
my $get_wrapper = $_[2] || sub ($) { return $_[0] }; |
| 7550 |
|
|
| 7551 |
## ISSUE: Should {confident} be true? |
## ISSUE: Should {confident} be true? |
| 7552 |
|
|
| 7565 |
} |
} |
| 7566 |
|
|
| 7567 |
## Step 3, 4, 5 # MUST |
## Step 3, 4, 5 # MUST |
| 7568 |
$class->parse_string ($$s => $node, $onerror); |
$class->parse_char_string ($$s => $node, $onerror, $get_wrapper); |
| 7569 |
} elsif ($nt == 1) { |
} elsif ($nt == 1) { |
| 7570 |
## TODO: If non-html element |
## TODO: If non-html element |
| 7571 |
|
|
| 7572 |
## NOTE: Most of this code is copied from |parse_string| |
## NOTE: Most of this code is copied from |parse_string| |
| 7573 |
|
|
| 7574 |
|
## TODO: Support for $get_wrapper |
| 7575 |
|
|
| 7576 |
## Step 1 # MUST |
## Step 1 # MUST |
| 7577 |
my $this_doc = $node->owner_document; |
my $this_doc = $node->owner_document; |
| 7578 |
my $doc = $this_doc->implementation->create_document; |
my $doc = $this_doc->implementation->create_document; |
| 7634 |
0x10FFFE => 1, 0x10FFFF => 1, |
0x10FFFE => 1, 0x10FFFF => 1, |
| 7635 |
}->{$self->{next_char}}) { |
}->{$self->{next_char}}) { |
| 7636 |
!!!cp ('i4.1'); |
!!!cp ('i4.1'); |
| 7637 |
!!!parse-error (type => 'control char', level => $self->{must_level}); |
if ($self->{next_char} < 0x10000) { |
| 7638 |
## TODO: error type documentation |
!!!parse-error (type => 'control char', |
| 7639 |
|
text => (sprintf 'U+%04X', $self->{next_char})); |
| 7640 |
|
} else { |
| 7641 |
|
!!!parse-error (type => 'control char', |
| 7642 |
|
text => (sprintf 'U-%08X', $self->{next_char})); |
| 7643 |
|
} |
| 7644 |
} |
} |
| 7645 |
}; |
}; |
| 7646 |
$p->{prev_char} = [-1, -1, -1]; |
$p->{prev_char} = [-1, -1, -1]; |