| 8 |
## doc.write (''); |
## doc.write (''); |
| 9 |
## alert (doc.compatMode); |
## alert (doc.compatMode); |
| 10 |
|
|
| 11 |
## TODO: Control charcters and noncharacters are not allowed (HTML5 revision 1263) |
require IO::Handle; |
| 12 |
## TODO: 1252 parse error (revision 1264) |
|
| 13 |
## TODO: 8859-11 = 874 (revision 1271) |
my $HTML_NS = q<http://www.w3.org/1999/xhtml>; |
| 14 |
|
my $MML_NS = q<http://www.w3.org/1998/Math/MathML>; |
| 15 |
|
my $SVG_NS = q<http://www.w3.org/2000/svg>; |
| 16 |
|
my $XLINK_NS = q<http://www.w3.org/1999/xlink>; |
| 17 |
|
my $XML_NS = q<http://www.w3.org/XML/1998/namespace>; |
| 18 |
|
my $XMLNS_NS = q<http://www.w3.org/2000/xmlns/>; |
| 19 |
|
|
| 20 |
sub A_EL () { 0b1 } |
sub A_EL () { 0b1 } |
| 21 |
sub ADDRESS_EL () { 0b10 } |
sub ADDRESS_EL () { 0b10 } |
| 42 |
sub TABLE_ROW_GROUP_EL () { 0b10000000000000000000000 } |
sub TABLE_ROW_GROUP_EL () { 0b10000000000000000000000 } |
| 43 |
sub MISC_SCOPING_EL () { 0b100000000000000000000000 } |
sub MISC_SCOPING_EL () { 0b100000000000000000000000 } |
| 44 |
sub MISC_SPECIAL_EL () { 0b1000000000000000000000000 } |
sub MISC_SPECIAL_EL () { 0b1000000000000000000000000 } |
| 45 |
|
sub FOREIGN_EL () { 0b10000000000000000000000000 } |
| 46 |
|
sub FOREIGN_FLOW_CONTENT_EL () { 0b100000000000000000000000000 } |
| 47 |
|
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, |
| 213 |
wbr => MISC_SPECIAL_EL, |
wbr => MISC_SPECIAL_EL, |
| 214 |
}; |
}; |
| 215 |
|
|
| 216 |
|
my $el_category_f = { |
| 217 |
|
$MML_NS => { |
| 218 |
|
'annotation-xml' => MML_AXML_EL, |
| 219 |
|
mi => FOREIGN_FLOW_CONTENT_EL, |
| 220 |
|
mo => FOREIGN_FLOW_CONTENT_EL, |
| 221 |
|
mn => FOREIGN_FLOW_CONTENT_EL, |
| 222 |
|
ms => FOREIGN_FLOW_CONTENT_EL, |
| 223 |
|
mtext => FOREIGN_FLOW_CONTENT_EL, |
| 224 |
|
}, |
| 225 |
|
$SVG_NS => { |
| 226 |
|
foreignObject => FOREIGN_FLOW_CONTENT_EL, |
| 227 |
|
desc => FOREIGN_FLOW_CONTENT_EL, |
| 228 |
|
title => FOREIGN_FLOW_CONTENT_EL, |
| 229 |
|
}, |
| 230 |
|
## NOTE: In addition, FOREIGN_EL is set to non-HTML elements. |
| 231 |
|
}; |
| 232 |
|
|
| 233 |
|
my $svg_attr_name = { |
| 234 |
|
attributename => 'attributeName', |
| 235 |
|
attributetype => 'attributeType', |
| 236 |
|
basefrequency => 'baseFrequency', |
| 237 |
|
baseprofile => 'baseProfile', |
| 238 |
|
calcmode => 'calcMode', |
| 239 |
|
clippathunits => 'clipPathUnits', |
| 240 |
|
contentscripttype => 'contentScriptType', |
| 241 |
|
contentstyletype => 'contentStyleType', |
| 242 |
|
diffuseconstant => 'diffuseConstant', |
| 243 |
|
edgemode => 'edgeMode', |
| 244 |
|
externalresourcesrequired => 'externalResourcesRequired', |
| 245 |
|
filterres => 'filterRes', |
| 246 |
|
filterunits => 'filterUnits', |
| 247 |
|
glyphref => 'glyphRef', |
| 248 |
|
gradienttransform => 'gradientTransform', |
| 249 |
|
gradientunits => 'gradientUnits', |
| 250 |
|
kernelmatrix => 'kernelMatrix', |
| 251 |
|
kernelunitlength => 'kernelUnitLength', |
| 252 |
|
keypoints => 'keyPoints', |
| 253 |
|
keysplines => 'keySplines', |
| 254 |
|
keytimes => 'keyTimes', |
| 255 |
|
lengthadjust => 'lengthAdjust', |
| 256 |
|
limitingconeangle => 'limitingConeAngle', |
| 257 |
|
markerheight => 'markerHeight', |
| 258 |
|
markerunits => 'markerUnits', |
| 259 |
|
markerwidth => 'markerWidth', |
| 260 |
|
maskcontentunits => 'maskContentUnits', |
| 261 |
|
maskunits => 'maskUnits', |
| 262 |
|
numoctaves => 'numOctaves', |
| 263 |
|
pathlength => 'pathLength', |
| 264 |
|
patterncontentunits => 'patternContentUnits', |
| 265 |
|
patterntransform => 'patternTransform', |
| 266 |
|
patternunits => 'patternUnits', |
| 267 |
|
pointsatx => 'pointsAtX', |
| 268 |
|
pointsaty => 'pointsAtY', |
| 269 |
|
pointsatz => 'pointsAtZ', |
| 270 |
|
preservealpha => 'preserveAlpha', |
| 271 |
|
preserveaspectratio => 'preserveAspectRatio', |
| 272 |
|
primitiveunits => 'primitiveUnits', |
| 273 |
|
refx => 'refX', |
| 274 |
|
refy => 'refY', |
| 275 |
|
repeatcount => 'repeatCount', |
| 276 |
|
repeatdur => 'repeatDur', |
| 277 |
|
requiredextensions => 'requiredExtensions', |
| 278 |
|
requiredfeatures => 'requiredFeatures', |
| 279 |
|
specularconstant => 'specularConstant', |
| 280 |
|
specularexponent => 'specularExponent', |
| 281 |
|
spreadmethod => 'spreadMethod', |
| 282 |
|
startoffset => 'startOffset', |
| 283 |
|
stddeviation => 'stdDeviation', |
| 284 |
|
stitchtiles => 'stitchTiles', |
| 285 |
|
surfacescale => 'surfaceScale', |
| 286 |
|
systemlanguage => 'systemLanguage', |
| 287 |
|
tablevalues => 'tableValues', |
| 288 |
|
targetx => 'targetX', |
| 289 |
|
targety => 'targetY', |
| 290 |
|
textlength => 'textLength', |
| 291 |
|
viewbox => 'viewBox', |
| 292 |
|
viewtarget => 'viewTarget', |
| 293 |
|
xchannelselector => 'xChannelSelector', |
| 294 |
|
ychannelselector => 'yChannelSelector', |
| 295 |
|
zoomandpan => 'zoomAndPan', |
| 296 |
|
}; |
| 297 |
|
|
| 298 |
|
my $foreign_attr_xname = { |
| 299 |
|
'xlink:actuate' => [$XLINK_NS, ['xlink', 'actuate']], |
| 300 |
|
'xlink:arcrole' => [$XLINK_NS, ['xlink', 'arcrole']], |
| 301 |
|
'xlink:href' => [$XLINK_NS, ['xlink', 'href']], |
| 302 |
|
'xlink:role' => [$XLINK_NS, ['xlink', 'role']], |
| 303 |
|
'xlink:show' => [$XLINK_NS, ['xlink', 'show']], |
| 304 |
|
'xlink:title' => [$XLINK_NS, ['xlink', 'title']], |
| 305 |
|
'xlink:type' => [$XLINK_NS, ['xlink', 'type']], |
| 306 |
|
'xml:base' => [$XML_NS, ['xml', 'base']], |
| 307 |
|
'xml:lang' => [$XML_NS, ['xml', 'lang']], |
| 308 |
|
'xml:space' => [$XML_NS, ['xml', 'space']], |
| 309 |
|
'xmlns' => [$XMLNS_NS, [undef, 'xmlns']], |
| 310 |
|
'xmlns:xlink' => [$XMLNS_NS, ['xmlns', 'xlink']], |
| 311 |
|
}; |
| 312 |
|
|
| 313 |
|
## ISSUE: xmlns:xlink="non-xlink-ns" is not an error. |
| 314 |
|
|
| 315 |
my $c1_entity_char = { |
my $c1_entity_char = { |
| 316 |
0x80 => 0x20AC, |
0x80 => 0x20AC, |
| 317 |
0x81 => 0xFFFD, |
0x81 => 0xFFFD, |
| 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 = ref $_[0] ? shift : shift->new; |
my $self = ref $_[0] ? shift : shift->new; |
| 359 |
my $charset = shift; |
my $charset_name = shift; |
| 360 |
my $bytes_s = ref $_[0] ? $_[0] : \($_[0]); |
my $byte_stream = $_[0]; |
|
my $s; |
|
|
|
|
|
if (defined $charset) { |
|
|
require Encode; ## TODO: decode(utf8) don't delete BOM |
|
|
$s = \ (Encode::decode ($charset, $$bytes_s)); |
|
|
$self->{input_encoding} = lc $charset; ## TODO: normalize name |
|
|
$self->{confident} = 1; |
|
|
} else { |
|
|
## TODO: Implement HTML5 detection algorithm |
|
|
require Whatpm::Charset::UniversalCharDet; |
|
|
$charset = Whatpm::Charset::UniversalCharDet->detect_byte_string |
|
|
(substr ($$bytes_s, 0, 1024)); |
|
|
$charset ||= 'windows-1252'; |
|
|
$s = \ (Encode::decode ($charset, $$bytes_s)); |
|
|
$self->{input_encoding} = $charset; |
|
|
$self->{confident} = 0; |
|
|
} |
|
| 361 |
|
|
| 362 |
$self->{change_encoding} = sub { |
my $onerror = $_[2] || sub { |
| 363 |
my $self = shift; |
my (%opt) = @_; |
| 364 |
my $charset = lc shift; |
warn "Parse error ($opt{type})\n"; |
| 365 |
my $token = shift; |
}; |
| 366 |
## TODO: if $charset is supported |
$self->{parse_error} = $onerror; # updated later by parse_char_string |
|
## TODO: normalize charset name |
|
| 367 |
|
|
| 368 |
## "Change the encoding" algorithm: |
## HTML5 encoding sniffing algorithm |
| 369 |
|
require Message::Charset::Info; |
| 370 |
|
my $charset; |
| 371 |
|
my $buffer; |
| 372 |
|
my ($char_stream, $e_status); |
| 373 |
|
|
| 374 |
|
SNIFFING: { |
| 375 |
|
## NOTE: By setting |allow_fallback| option true when the |
| 376 |
|
## |get_decode_handle| method is invoked, we ignore what the HTML5 |
| 377 |
|
## spec requires, i.e. unsupported encoding should be ignored. |
| 378 |
|
## TODO: We should not do this unless the parser is invoked |
| 379 |
|
## in the conformance checking mode, in which this behavior |
| 380 |
|
## would be useful. |
| 381 |
|
|
| 382 |
## Step 1 |
## Step 1 |
| 383 |
if ($charset eq 'utf-16') { ## ISSUE: UTF-16BE -> UTF-8? UTF-16LE -> UTF-8? |
if (defined $charset_name) { |
| 384 |
$charset = 'utf-8'; |
$charset = Message::Charset::Info->get_by_html_name ($charset_name); |
| 385 |
|
## TODO: Is this ok? Transfer protocol's parameter should be |
| 386 |
|
## interpreted in its semantics? |
| 387 |
|
|
| 388 |
|
## ISSUE: Unsupported encoding is not ignored according to the spec. |
| 389 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 390 |
|
($byte_stream, allow_error_reporting => 1, |
| 391 |
|
allow_fallback => 1); |
| 392 |
|
if ($char_stream) { |
| 393 |
|
$self->{confident} = 1; |
| 394 |
|
last SNIFFING; |
| 395 |
|
} else { |
| 396 |
|
## TODO: unsupported error |
| 397 |
|
} |
| 398 |
} |
} |
| 399 |
|
|
| 400 |
## Step 2 |
## Step 2 |
| 401 |
if (defined $self->{input_encoding} and |
my $byte_buffer = ''; |
| 402 |
$self->{input_encoding} eq $charset) { |
for (1..1024) { |
| 403 |
|
my $char = $byte_stream->getc; |
| 404 |
|
last unless defined $char; |
| 405 |
|
$byte_buffer .= $char; |
| 406 |
|
} ## TODO: timeout |
| 407 |
|
|
| 408 |
|
## Step 3 |
| 409 |
|
if ($byte_buffer =~ /^\xFE\xFF/) { |
| 410 |
|
$charset = Message::Charset::Info->get_by_html_name ('utf-16be'); |
| 411 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 412 |
|
($byte_stream, allow_error_reporting => 1, |
| 413 |
|
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 414 |
$self->{confident} = 1; |
$self->{confident} = 1; |
| 415 |
return; |
last SNIFFING; |
| 416 |
|
} elsif ($byte_buffer =~ /^\xFF\xFE/) { |
| 417 |
|
$charset = Message::Charset::Info->get_by_html_name ('utf-16le'); |
| 418 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 419 |
|
($byte_stream, allow_error_reporting => 1, |
| 420 |
|
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 421 |
|
$self->{confident} = 1; |
| 422 |
|
last SNIFFING; |
| 423 |
|
} elsif ($byte_buffer =~ /^\xEF\xBB\xBF/) { |
| 424 |
|
$charset = Message::Charset::Info->get_by_html_name ('utf-8'); |
| 425 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 426 |
|
($byte_stream, allow_error_reporting => 1, |
| 427 |
|
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 428 |
|
$self->{confident} = 1; |
| 429 |
|
last SNIFFING; |
| 430 |
} |
} |
| 431 |
|
|
| 432 |
!!!parse-error (type => 'charset label detected:'.$self->{input_encoding}. |
## Step 4 |
| 433 |
':'.$charset, level => 'w', token => $token); |
## TODO: <meta charset> |
| 434 |
|
|
| 435 |
## Step 3 |
## Step 5 |
| 436 |
# if (can) { |
## TODO: from history |
|
## change the encoding on the fly. |
|
|
#$self->{confident} = 1; |
|
|
#return; |
|
|
# } |
|
| 437 |
|
|
| 438 |
## Step 4 |
## Step 6 |
| 439 |
throw Whatpm::HTML::RestartParser (charset => $charset); |
require Whatpm::Charset::UniversalCharDet; |
| 440 |
|
$charset_name = Whatpm::Charset::UniversalCharDet->detect_byte_string |
| 441 |
|
($byte_buffer); |
| 442 |
|
if (defined $charset_name) { |
| 443 |
|
$charset = Message::Charset::Info->get_by_html_name ($charset_name); |
| 444 |
|
|
| 445 |
|
## ISSUE: Unsupported encoding is not ignored according to the spec. |
| 446 |
|
require Whatpm::Charset::DecodeHandle; |
| 447 |
|
$buffer = Whatpm::Charset::DecodeHandle::ByteBuffer->new |
| 448 |
|
($byte_stream); |
| 449 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 450 |
|
($buffer, allow_error_reporting => 1, |
| 451 |
|
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 452 |
|
if ($char_stream) { |
| 453 |
|
$buffer->{buffer} = $byte_buffer; |
| 454 |
|
!!!parse-error (type => 'sniffing:chardet', |
| 455 |
|
text => $charset_name, |
| 456 |
|
level => $self->{level}->{info}, |
| 457 |
|
layer => 'encode', |
| 458 |
|
line => 1, column => 1); |
| 459 |
|
$self->{confident} = 0; |
| 460 |
|
last SNIFFING; |
| 461 |
|
} |
| 462 |
|
} |
| 463 |
|
|
| 464 |
|
## Step 7: default |
| 465 |
|
## TODO: Make this configurable. |
| 466 |
|
$charset = Message::Charset::Info->get_by_html_name ('windows-1252'); |
| 467 |
|
## NOTE: We choose |windows-1252| here, since |utf-8| should be |
| 468 |
|
## detectable in the step 6. |
| 469 |
|
require Whatpm::Charset::DecodeHandle; |
| 470 |
|
$buffer = Whatpm::Charset::DecodeHandle::ByteBuffer->new |
| 471 |
|
($byte_stream); |
| 472 |
|
($char_stream, $e_status) |
| 473 |
|
= $charset->get_decode_handle ($buffer, |
| 474 |
|
allow_error_reporting => 1, |
| 475 |
|
allow_fallback => 1, |
| 476 |
|
byte_buffer => \$byte_buffer); |
| 477 |
|
$buffer->{buffer} = $byte_buffer; |
| 478 |
|
!!!parse-error (type => 'sniffing:default', |
| 479 |
|
text => 'windows-1252', |
| 480 |
|
level => $self->{level}->{info}, |
| 481 |
|
line => 1, column => 1, |
| 482 |
|
layer => 'encode'); |
| 483 |
|
$self->{confident} = 0; |
| 484 |
|
} # SNIFFING |
| 485 |
|
|
| 486 |
|
if ($e_status & Message::Charset::Info::FALLBACK_ENCODING_IMPL ()) { |
| 487 |
|
$self->{input_encoding} = $charset->get_iana_name; ## TODO: Should we set actual charset decoder's encoding name? |
| 488 |
|
!!!parse-error (type => 'chardecode:fallback', |
| 489 |
|
#text => $self->{input_encoding}, |
| 490 |
|
level => $self->{level}->{uncertain}, |
| 491 |
|
line => 1, column => 1, |
| 492 |
|
layer => 'encode'); |
| 493 |
|
} elsif (not ($e_status & |
| 494 |
|
Message::Charset::Info::ERROR_REPORTING_ENCODING_IMPL())) { |
| 495 |
|
$self->{input_encoding} = $charset->get_iana_name; |
| 496 |
|
!!!parse-error (type => 'chardecode:no error', |
| 497 |
|
text => $self->{input_encoding}, |
| 498 |
|
level => $self->{level}->{uncertain}, |
| 499 |
|
line => 1, column => 1, |
| 500 |
|
layer => 'encode'); |
| 501 |
|
} else { |
| 502 |
|
$self->{input_encoding} = $charset->get_iana_name; |
| 503 |
|
} |
| 504 |
|
|
| 505 |
|
$self->{change_encoding} = sub { |
| 506 |
|
my $self = shift; |
| 507 |
|
$charset_name = shift; |
| 508 |
|
my $token = shift; |
| 509 |
|
|
| 510 |
|
$charset = Message::Charset::Info->get_by_html_name ($charset_name); |
| 511 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 512 |
|
($byte_stream, allow_error_reporting => 1, allow_fallback => 1, |
| 513 |
|
byte_buffer => \ $buffer->{buffer}); |
| 514 |
|
|
| 515 |
|
if ($char_stream) { # if supported |
| 516 |
|
## "Change the encoding" algorithm: |
| 517 |
|
|
| 518 |
|
## Step 1 |
| 519 |
|
if ($charset->{category} & |
| 520 |
|
Message::Charset::Info::CHARSET_CATEGORY_UTF16 ()) { |
| 521 |
|
$charset = Message::Charset::Info->get_by_html_name ('utf-8'); |
| 522 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 523 |
|
($byte_stream, |
| 524 |
|
byte_buffer => \ $buffer->{buffer}); |
| 525 |
|
} |
| 526 |
|
$charset_name = $charset->get_iana_name; |
| 527 |
|
|
| 528 |
|
## Step 2 |
| 529 |
|
if (defined $self->{input_encoding} and |
| 530 |
|
$self->{input_encoding} eq $charset_name) { |
| 531 |
|
!!!parse-error (type => 'charset label:matching', |
| 532 |
|
text => $charset_name, |
| 533 |
|
level => $self->{level}->{info}); |
| 534 |
|
$self->{confident} = 1; |
| 535 |
|
return; |
| 536 |
|
} |
| 537 |
|
|
| 538 |
|
!!!parse-error (type => 'charset label detected', |
| 539 |
|
text => $self->{input_encoding}, |
| 540 |
|
value => $charset_name, |
| 541 |
|
level => $self->{level}->{warn}, |
| 542 |
|
token => $token); |
| 543 |
|
|
| 544 |
|
## Step 3 |
| 545 |
|
# if (can) { |
| 546 |
|
## change the encoding on the fly. |
| 547 |
|
#$self->{confident} = 1; |
| 548 |
|
#return; |
| 549 |
|
# } |
| 550 |
|
|
| 551 |
|
## Step 4 |
| 552 |
|
throw Whatpm::HTML::RestartParser (); |
| 553 |
|
} |
| 554 |
}; # $self->{change_encoding} |
}; # $self->{change_encoding} |
| 555 |
|
|
| 556 |
|
my $char_onerror = sub { |
| 557 |
|
my (undef, $type, %opt) = @_; |
| 558 |
|
!!!parse-error (layer => 'encode', |
| 559 |
|
%opt, type => $type, |
| 560 |
|
line => $self->{line}, column => $self->{column} + 1); |
| 561 |
|
if ($opt{octets}) { |
| 562 |
|
${$opt{octets}} = "\x{FFFD}"; # relacement character |
| 563 |
|
} |
| 564 |
|
}; |
| 565 |
|
$char_stream->onerror ($char_onerror); |
| 566 |
|
|
| 567 |
my @args = @_; shift @args; # $s |
my @args = @_; shift @args; # $s |
| 568 |
my $return; |
my $return; |
| 569 |
try { |
try { |
| 570 |
$return = $self->parse_char_string ($s, @args); |
$return = $self->parse_char_stream ($char_stream, @args); |
| 571 |
} catch Whatpm::HTML::RestartParser with { |
} catch Whatpm::HTML::RestartParser with { |
| 572 |
my $charset = shift->{charset}; |
## NOTE: Invoked after {change_encoding}. |
| 573 |
$s = \ (Encode::decode ($charset, $$bytes_s)); |
|
| 574 |
$self->{input_encoding} = $charset; ## TODO: normalize |
if ($e_status & Message::Charset::Info::FALLBACK_ENCODING_IMPL ()) { |
| 575 |
|
$self->{input_encoding} = $charset->get_iana_name; ## TODO: Should we set actual charset decoder's encoding name? |
| 576 |
|
!!!parse-error (type => 'chardecode:fallback', |
| 577 |
|
level => $self->{level}->{uncertain}, |
| 578 |
|
#text => $self->{input_encoding}, |
| 579 |
|
line => 1, column => 1, |
| 580 |
|
layer => 'encode'); |
| 581 |
|
} elsif (not ($e_status & |
| 582 |
|
Message::Charset::Info::ERROR_REPORTING_ENCODING_IMPL())) { |
| 583 |
|
$self->{input_encoding} = $charset->get_iana_name; |
| 584 |
|
!!!parse-error (type => 'chardecode:no error', |
| 585 |
|
text => $self->{input_encoding}, |
| 586 |
|
level => $self->{level}->{uncertain}, |
| 587 |
|
line => 1, column => 1, |
| 588 |
|
layer => 'encode'); |
| 589 |
|
} else { |
| 590 |
|
$self->{input_encoding} = $charset->get_iana_name; |
| 591 |
|
} |
| 592 |
$self->{confident} = 1; |
$self->{confident} = 1; |
| 593 |
$return = $self->parse_char_string ($s, @args); |
$char_stream->onerror ($char_onerror); |
| 594 |
|
$return = $self->parse_char_stream ($char_stream, @args); |
| 595 |
}; |
}; |
| 596 |
return $return; |
return $return; |
| 597 |
} # parse_byte_string |
} # parse_byte_stream |
| 598 |
|
|
| 599 |
## NOTE: HTML5 spec says that the encoding layer MUST NOT strip BOM |
## NOTE: HTML5 spec says that the encoding layer MUST NOT strip BOM |
| 600 |
## 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 |
| 605 |
## 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 |
| 606 |
## strip the BOM and never strip any ZWNBSP. |
## strip the BOM and never strip any ZWNBSP. |
| 607 |
|
|
| 608 |
*parse_char_string = \&parse_string; |
sub parse_char_string ($$$;$) { |
| 609 |
|
my $self = shift; |
| 610 |
|
require utf8; |
| 611 |
|
my $s = ref $_[0] ? $_[0] : \($_[0]); |
| 612 |
|
open my $input, '<' . (utf8::is_utf8 ($$s) ? ':utf8' : ''), $s; |
| 613 |
|
return $self->parse_char_stream ($input, @_[1..$#_]); |
| 614 |
|
} # parse_char_string |
| 615 |
|
*parse_string = \&parse_char_string; |
| 616 |
|
|
| 617 |
sub parse_string ($$$;$) { |
sub parse_char_stream ($$$;$) { |
| 618 |
my $self = ref $_[0] ? shift : shift->new; |
my $self = ref $_[0] ? shift : shift->new; |
| 619 |
my $s = ref $_[0] ? $_[0] : \($_[0]); |
my $input = $_[0]; |
| 620 |
$self->{document} = $_[1]; |
$self->{document} = $_[1]; |
| 621 |
@{$self->{document}->child_nodes} = (); |
@{$self->{document}->child_nodes} = (); |
| 622 |
|
|
| 635 |
pop @{$self->{prev_char}}; |
pop @{$self->{prev_char}}; |
| 636 |
unshift @{$self->{prev_char}}, $self->{next_char}; |
unshift @{$self->{prev_char}}, $self->{next_char}; |
| 637 |
|
|
| 638 |
$self->{next_char} = -1 and return if $i >= length $$s; |
my $char; |
| 639 |
$self->{next_char} = ord substr $$s, $i++, 1; |
if (defined $self->{next_next_char}) { |
| 640 |
|
$char = $self->{next_next_char}; |
| 641 |
|
delete $self->{next_next_char}; |
| 642 |
|
} else { |
| 643 |
|
$char = $input->getc; |
| 644 |
|
} |
| 645 |
|
$self->{next_char} = -1 and return unless defined $char; |
| 646 |
|
$self->{next_char} = ord $char; |
| 647 |
|
|
| 648 |
($self->{line_prev}, $self->{column_prev}) |
($self->{line_prev}, $self->{column_prev}) |
| 649 |
= ($self->{line}, $self->{column}); |
= ($self->{line}, $self->{column}); |
| 650 |
$self->{column}++; |
$self->{column}++; |
| 651 |
|
|
| 652 |
if ($self->{next_char} == 0x000A) { # LF |
if ($self->{next_char} == 0x000A) { # LF |
| 653 |
|
!!!cp ('j1'); |
| 654 |
$self->{line}++; |
$self->{line}++; |
| 655 |
$self->{column} = 0; |
$self->{column} = 0; |
| 656 |
} elsif ($self->{next_char} == 0x000D) { # CR |
} elsif ($self->{next_char} == 0x000D) { # CR |
| 657 |
$i++ if substr ($$s, $i, 1) eq "\x0A"; |
!!!cp ('j2'); |
| 658 |
|
my $next = $input->getc; |
| 659 |
|
if (defined $next and $next ne "\x0A") { |
| 660 |
|
$self->{next_next_char} = $next; |
| 661 |
|
} |
| 662 |
$self->{next_char} = 0x000A; # LF # MUST |
$self->{next_char} = 0x000A; # LF # MUST |
| 663 |
$self->{line}++; |
$self->{line}++; |
| 664 |
$self->{column} = 0; |
$self->{column} = 0; |
| 665 |
} elsif ($self->{next_char} > 0x10FFFF) { |
} elsif ($self->{next_char} > 0x10FFFF) { |
| 666 |
|
!!!cp ('j3'); |
| 667 |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
| 668 |
} elsif ($self->{next_char} == 0x0000) { # NULL |
} elsif ($self->{next_char} == 0x0000) { # NULL |
| 669 |
|
!!!cp ('j4'); |
| 670 |
!!!parse-error (type => 'NULL'); |
!!!parse-error (type => 'NULL'); |
| 671 |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
| 672 |
|
} elsif ($self->{next_char} <= 0x0008 or |
| 673 |
|
(0x000E <= $self->{next_char} and $self->{next_char} <= 0x001F) or |
| 674 |
|
(0x007F <= $self->{next_char} and $self->{next_char} <= 0x009F) or |
| 675 |
|
(0xD800 <= $self->{next_char} and $self->{next_char} <= 0xDFFF) or |
| 676 |
|
(0xFDD0 <= $self->{next_char} and $self->{next_char} <= 0xFDDF) or |
| 677 |
|
{ |
| 678 |
|
0xFFFE => 1, 0xFFFF => 1, 0x1FFFE => 1, 0x1FFFF => 1, |
| 679 |
|
0x2FFFE => 1, 0x2FFFF => 1, 0x3FFFE => 1, 0x3FFFF => 1, |
| 680 |
|
0x4FFFE => 1, 0x4FFFF => 1, 0x5FFFE => 1, 0x5FFFF => 1, |
| 681 |
|
0x6FFFE => 1, 0x6FFFF => 1, 0x7FFFE => 1, 0x7FFFF => 1, |
| 682 |
|
0x8FFFE => 1, 0x8FFFF => 1, 0x9FFFE => 1, 0x9FFFF => 1, |
| 683 |
|
0xAFFFE => 1, 0xAFFFF => 1, 0xBFFFE => 1, 0xBFFFF => 1, |
| 684 |
|
0xCFFFE => 1, 0xCFFFF => 1, 0xDFFFE => 1, 0xDFFFF => 1, |
| 685 |
|
0xEFFFE => 1, 0xEFFFF => 1, 0xFFFFE => 1, 0xFFFFF => 1, |
| 686 |
|
0x10FFFE => 1, 0x10FFFF => 1, |
| 687 |
|
}->{$self->{next_char}}) { |
| 688 |
|
!!!cp ('j5'); |
| 689 |
|
if ($self->{next_char} < 0x10000) { |
| 690 |
|
!!!parse-error (type => 'control char', |
| 691 |
|
text => (sprintf 'U+%04X', $self->{next_char})); |
| 692 |
|
} else { |
| 693 |
|
!!!parse-error (type => 'control char', |
| 694 |
|
text => (sprintf 'U-%08X', $self->{next_char})); |
| 695 |
|
} |
| 696 |
} |
} |
| 697 |
}; |
}; |
| 698 |
$self->{prev_char} = [-1, -1, -1]; |
$self->{prev_char} = [-1, -1, -1]; |
| 716 |
delete $self->{parse_error}; # remove loop |
delete $self->{parse_error}; # remove loop |
| 717 |
|
|
| 718 |
return $self->{document}; |
return $self->{document}; |
| 719 |
} # parse_string |
} # parse_char_stream |
| 720 |
|
|
| 721 |
sub new ($) { |
sub new ($) { |
| 722 |
my $class = shift; |
my $class = shift; |
| 723 |
my $self = bless {}, $class; |
my $self = bless { |
| 724 |
|
level => {must => 'm', |
| 725 |
|
should => 's', |
| 726 |
|
warn => 'w', |
| 727 |
|
info => 'i', |
| 728 |
|
uncertain => 'u'}, |
| 729 |
|
}, $class; |
| 730 |
$self->{set_next_char} = sub { |
$self->{set_next_char} = sub { |
| 731 |
$self->{next_char} = -1; |
$self->{next_char} = -1; |
| 732 |
}; |
}; |
| 789 |
sub BOGUS_DOCTYPE_STATE () { 32 } |
sub BOGUS_DOCTYPE_STATE () { 32 } |
| 790 |
sub AFTER_ATTRIBUTE_VALUE_QUOTED_STATE () { 33 } |
sub AFTER_ATTRIBUTE_VALUE_QUOTED_STATE () { 33 } |
| 791 |
sub SELF_CLOSING_START_TAG_STATE () { 34 } |
sub SELF_CLOSING_START_TAG_STATE () { 34 } |
| 792 |
|
sub CDATA_BLOCK_STATE () { 35 } |
| 793 |
|
|
| 794 |
sub DOCTYPE_TOKEN () { 1 } |
sub DOCTYPE_TOKEN () { 1 } |
| 795 |
sub COMMENT_TOKEN () { 2 } |
sub COMMENT_TOKEN () { 2 } |
| 807 |
sub BODY_AFTER_IMS () { 0b100000000 } |
sub BODY_AFTER_IMS () { 0b100000000 } |
| 808 |
sub FRAME_IMS () { 0b1000000000 } |
sub FRAME_IMS () { 0b1000000000 } |
| 809 |
sub SELECT_IMS () { 0b10000000000 } |
sub SELECT_IMS () { 0b10000000000 } |
| 810 |
|
sub IN_FOREIGN_CONTENT_IM () { 0b100000000000 } |
| 811 |
|
## NOTE: "in foreign content" insertion mode is special; it is combined |
| 812 |
|
## with the secondary insertion mode. In this parser, they are stored |
| 813 |
|
## together in the bit-or'ed form. |
| 814 |
|
|
| 815 |
## NOTE: "initial" and "before html" insertion modes have no constants. |
## NOTE: "initial" and "before html" insertion modes have no constants. |
| 816 |
|
|
| 872 |
## |->{self_closing}| is used to save the value of |$self->{self_closing}| |
## |->{self_closing}| is used to save the value of |$self->{self_closing}| |
| 873 |
## while the token is pushed back to the stack. |
## while the token is pushed back to the stack. |
| 874 |
|
|
|
## 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? |
|
|
|
|
| 875 |
## Emitted token MUST immediately be handled by the tree construction state. |
## Emitted token MUST immediately be handled by the tree construction state. |
| 876 |
|
|
| 877 |
## 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 |
| 1087 |
redo A; |
redo A; |
| 1088 |
} else { |
} else { |
| 1089 |
!!!cp (23); |
!!!cp (23); |
| 1090 |
!!!parse-error (type => 'bare stago'); |
!!!parse-error (type => 'bare stago', |
| 1091 |
|
line => $self->{line_prev}, |
| 1092 |
|
column => $self->{column_prev}); |
| 1093 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1094 |
## reconsume |
## reconsume |
| 1095 |
|
|
| 1384 |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
| 1385 |
->{$self->{current_attribute}->{name}}) { # MUST |
->{$self->{current_attribute}->{name}}) { # MUST |
| 1386 |
!!!cp (57); |
!!!cp (57); |
| 1387 |
!!!parse-error (type => 'duplicate attribute:'.$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}); |
| 1388 |
## Discard $self->{current_attribute} # MUST |
## Discard $self->{current_attribute} # MUST |
| 1389 |
} else { |
} else { |
| 1390 |
!!!cp (58); |
!!!cp (58); |
| 1555 |
|
|
| 1556 |
redo A; |
redo A; |
| 1557 |
} else { |
} else { |
| 1558 |
!!!cp (82); |
if ($self->{next_char} == 0x0022 or # " |
| 1559 |
|
$self->{next_char} == 0x0027) { # ' |
| 1560 |
|
!!!cp (78); |
| 1561 |
|
!!!parse-error (type => 'bad attribute name'); |
| 1562 |
|
} else { |
| 1563 |
|
!!!cp (82); |
| 1564 |
|
} |
| 1565 |
$self->{current_attribute} |
$self->{current_attribute} |
| 1566 |
= {name => chr ($self->{next_char}), |
= {name => chr ($self->{next_char}), |
| 1567 |
value => '', |
value => '', |
| 1596 |
!!!next-input-character; |
!!!next-input-character; |
| 1597 |
redo A; |
redo A; |
| 1598 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1599 |
|
!!!parse-error (type => 'empty unquoted attribute value'); |
| 1600 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1601 |
!!!cp (87); |
!!!cp (87); |
| 1602 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1873 |
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
| 1874 |
!!!next-input-character; |
!!!next-input-character; |
| 1875 |
redo A; |
redo A; |
| 1876 |
|
} elsif ($self->{next_char} == -1) { |
| 1877 |
|
!!!parse-error (type => 'unclosed tag'); |
| 1878 |
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1879 |
|
!!!cp (122.3); |
| 1880 |
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1881 |
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1882 |
|
if ($self->{current_token}->{attributes}) { |
| 1883 |
|
!!!cp (122.1); |
| 1884 |
|
!!!parse-error (type => 'end tag attribute'); |
| 1885 |
|
} else { |
| 1886 |
|
## NOTE: This state should never be reached. |
| 1887 |
|
!!!cp (122.2); |
| 1888 |
|
} |
| 1889 |
|
} else { |
| 1890 |
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 1891 |
|
} |
| 1892 |
|
$self->{state} = DATA_STATE; |
| 1893 |
|
## Reconsume. |
| 1894 |
|
!!!emit ($self->{current_token}); # start tag or end tag |
| 1895 |
|
redo A; |
| 1896 |
} else { |
} else { |
| 1897 |
!!!cp ('124.1'); |
!!!cp ('124.1'); |
| 1898 |
!!!parse-error (type => 'no space between attributes'); |
!!!parse-error (type => 'no space between attributes'); |
| 1925 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 1926 |
|
|
| 1927 |
redo A; |
redo A; |
| 1928 |
|
} elsif ($self->{next_char} == -1) { |
| 1929 |
|
!!!parse-error (type => 'unclosed tag'); |
| 1930 |
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1931 |
|
!!!cp (124.7); |
| 1932 |
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1933 |
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1934 |
|
if ($self->{current_token}->{attributes}) { |
| 1935 |
|
!!!cp (124.5); |
| 1936 |
|
!!!parse-error (type => 'end tag attribute'); |
| 1937 |
|
} else { |
| 1938 |
|
## NOTE: This state should never be reached. |
| 1939 |
|
!!!cp (124.6); |
| 1940 |
|
} |
| 1941 |
|
} else { |
| 1942 |
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 1943 |
|
} |
| 1944 |
|
$self->{state} = DATA_STATE; |
| 1945 |
|
## Reconsume. |
| 1946 |
|
!!!emit ($self->{current_token}); # start tag or end tag |
| 1947 |
|
redo A; |
| 1948 |
} else { |
} else { |
| 1949 |
!!!cp ('124.4'); |
!!!cp ('124.4'); |
| 1950 |
!!!parse-error (type => 'nestc'); |
!!!parse-error (type => 'nestc'); |
| 2060 |
} else { |
} else { |
| 2061 |
!!!cp (135); |
!!!cp (135); |
| 2062 |
} |
} |
| 2063 |
|
} elsif ($self->{insertion_mode} & IN_FOREIGN_CONTENT_IM and |
| 2064 |
|
$self->{open_elements}->[-1]->[1] & FOREIGN_EL and |
| 2065 |
|
$self->{next_char} == 0x005B) { # [ |
| 2066 |
|
!!!next-input-character; |
| 2067 |
|
push @next_char, $self->{next_char}; |
| 2068 |
|
if ($self->{next_char} == 0x0043) { # C |
| 2069 |
|
!!!next-input-character; |
| 2070 |
|
push @next_char, $self->{next_char}; |
| 2071 |
|
if ($self->{next_char} == 0x0044) { # D |
| 2072 |
|
!!!next-input-character; |
| 2073 |
|
push @next_char, $self->{next_char}; |
| 2074 |
|
if ($self->{next_char} == 0x0041) { # A |
| 2075 |
|
!!!next-input-character; |
| 2076 |
|
push @next_char, $self->{next_char}; |
| 2077 |
|
if ($self->{next_char} == 0x0054) { # T |
| 2078 |
|
!!!next-input-character; |
| 2079 |
|
push @next_char, $self->{next_char}; |
| 2080 |
|
if ($self->{next_char} == 0x0041) { # A |
| 2081 |
|
!!!next-input-character; |
| 2082 |
|
push @next_char, $self->{next_char}; |
| 2083 |
|
if ($self->{next_char} == 0x005B) { # [ |
| 2084 |
|
!!!cp (135.1); |
| 2085 |
|
$self->{state} = CDATA_BLOCK_STATE; |
| 2086 |
|
!!!next-input-character; |
| 2087 |
|
redo A; |
| 2088 |
|
} else { |
| 2089 |
|
!!!cp (135.2); |
| 2090 |
|
} |
| 2091 |
|
} else { |
| 2092 |
|
!!!cp (135.3); |
| 2093 |
|
} |
| 2094 |
|
} else { |
| 2095 |
|
!!!cp (135.4); |
| 2096 |
|
} |
| 2097 |
|
} else { |
| 2098 |
|
!!!cp (135.5); |
| 2099 |
|
} |
| 2100 |
|
} else { |
| 2101 |
|
!!!cp (135.6); |
| 2102 |
|
} |
| 2103 |
|
} else { |
| 2104 |
|
!!!cp (135.7); |
| 2105 |
|
} |
| 2106 |
} else { |
} else { |
| 2107 |
!!!cp (136); |
!!!cp (136); |
| 2108 |
} |
} |
| 2702 |
redo A; |
redo A; |
| 2703 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 2704 |
!!!cp (208); |
!!!cp (208); |
| 2705 |
!!!parse-error (type => 'unclosed PUBLIC literal'); |
!!!parse-error (type => 'unclosed SYSTEM literal'); |
| 2706 |
|
|
| 2707 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 2708 |
!!!next-input-character; |
!!!next-input-character; |
| 2738 |
redo A; |
redo A; |
| 2739 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 2740 |
!!!cp (212); |
!!!cp (212); |
| 2741 |
!!!parse-error (type => 'unclosed PUBLIC literal'); |
!!!parse-error (type => 'unclosed SYSTEM literal'); |
| 2742 |
|
|
| 2743 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 2744 |
!!!next-input-character; |
!!!next-input-character; |
| 2786 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 2787 |
!!!cp (217); |
!!!cp (217); |
| 2788 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
|
|
|
| 2789 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 2790 |
## reconsume |
## reconsume |
| 2791 |
|
|
| 2826 |
!!!next-input-character; |
!!!next-input-character; |
| 2827 |
redo A; |
redo A; |
| 2828 |
} |
} |
| 2829 |
|
} elsif ($self->{state} == CDATA_BLOCK_STATE) { |
| 2830 |
|
my $s = ''; |
| 2831 |
|
|
| 2832 |
|
my ($l, $c) = ($self->{line}, $self->{column}); |
| 2833 |
|
|
| 2834 |
|
CS: while ($self->{next_char} != -1) { |
| 2835 |
|
if ($self->{next_char} == 0x005D) { # ] |
| 2836 |
|
!!!next-input-character; |
| 2837 |
|
if ($self->{next_char} == 0x005D) { # ] |
| 2838 |
|
!!!next-input-character; |
| 2839 |
|
MDC: { |
| 2840 |
|
if ($self->{next_char} == 0x003E) { # > |
| 2841 |
|
!!!cp (221.1); |
| 2842 |
|
!!!next-input-character; |
| 2843 |
|
last CS; |
| 2844 |
|
} elsif ($self->{next_char} == 0x005D) { # ] |
| 2845 |
|
!!!cp (221.2); |
| 2846 |
|
$s .= ']'; |
| 2847 |
|
!!!next-input-character; |
| 2848 |
|
redo MDC; |
| 2849 |
|
} else { |
| 2850 |
|
!!!cp (221.3); |
| 2851 |
|
$s .= ']]'; |
| 2852 |
|
# |
| 2853 |
|
} |
| 2854 |
|
} # MDC |
| 2855 |
|
} else { |
| 2856 |
|
!!!cp (221.4); |
| 2857 |
|
$s .= ']'; |
| 2858 |
|
# |
| 2859 |
|
} |
| 2860 |
|
} else { |
| 2861 |
|
!!!cp (221.5); |
| 2862 |
|
# |
| 2863 |
|
} |
| 2864 |
|
$s .= chr $self->{next_char}; |
| 2865 |
|
!!!next-input-character; |
| 2866 |
|
} # CS |
| 2867 |
|
|
| 2868 |
|
$self->{state} = DATA_STATE; |
| 2869 |
|
## next-input-character done or EOF, which is reconsumed. |
| 2870 |
|
|
| 2871 |
|
if (length $s) { |
| 2872 |
|
!!!cp (221.6); |
| 2873 |
|
!!!emit ({type => CHARACTER_TOKEN, data => $s, |
| 2874 |
|
line => $l, column => $c}); |
| 2875 |
|
} else { |
| 2876 |
|
!!!cp (221.7); |
| 2877 |
|
} |
| 2878 |
|
|
| 2879 |
|
redo A; |
| 2880 |
|
|
| 2881 |
|
## ISSUE: "text tokens" in spec. |
| 2882 |
|
## TODO: Streaming support |
| 2883 |
} else { |
} else { |
| 2884 |
die "$0: $self->{state}: Unknown state"; |
die "$0: $self->{state}: Unknown state"; |
| 2885 |
} |
} |
| 2947 |
|
|
| 2948 |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 2949 |
!!!cp (1008); |
!!!cp (1008); |
| 2950 |
!!!parse-error (type => (sprintf 'invalid character reference:U+%04X', $code), line => $l, column => $c); |
!!!parse-error (type => 'invalid character reference', |
| 2951 |
|
text => (sprintf 'U+%04X', $code), |
| 2952 |
|
line => $l, column => $c); |
| 2953 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 2954 |
} elsif ($code > 0x10FFFF) { |
} elsif ($code > 0x10FFFF) { |
| 2955 |
!!!cp (1009); |
!!!cp (1009); |
| 2956 |
!!!parse-error (type => (sprintf 'invalid character reference:U-%08X', $code), line => $l, column => $c); |
!!!parse-error (type => 'invalid character reference', |
| 2957 |
|
text => (sprintf 'U-%08X', $code), |
| 2958 |
|
line => $l, column => $c); |
| 2959 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 2960 |
} elsif ($code == 0x000D) { |
} elsif ($code == 0x000D) { |
| 2961 |
!!!cp (1010); |
!!!cp (1010); |
| 2963 |
$code = 0x000A; |
$code = 0x000A; |
| 2964 |
} elsif (0x80 <= $code and $code <= 0x9F) { |
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 2965 |
!!!cp (1011); |
!!!cp (1011); |
| 2966 |
!!!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); |
| 2967 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 2968 |
} |
} |
| 2969 |
|
|
| 2996 |
|
|
| 2997 |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 2998 |
!!!cp (1015); |
!!!cp (1015); |
| 2999 |
!!!parse-error (type => (sprintf 'invalid character reference:U+%04X', $code), line => $l, column => $c); |
!!!parse-error (type => 'invalid character reference', |
| 3000 |
|
text => (sprintf 'U+%04X', $code), |
| 3001 |
|
line => $l, column => $c); |
| 3002 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 3003 |
} elsif ($code > 0x10FFFF) { |
} elsif ($code > 0x10FFFF) { |
| 3004 |
!!!cp (1016); |
!!!cp (1016); |
| 3005 |
!!!parse-error (type => (sprintf 'invalid character reference:U-%08X', $code), line => $l, column => $c); |
!!!parse-error (type => 'invalid character reference', |
| 3006 |
|
text => (sprintf 'U-%08X', $code), |
| 3007 |
|
line => $l, column => $c); |
| 3008 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 3009 |
} elsif ($code == 0x000D) { |
} elsif ($code == 0x000D) { |
| 3010 |
!!!cp (1017); |
!!!cp (1017); |
| 3011 |
!!!parse-error (type => 'CR character reference', line => $l, column => $c); |
!!!parse-error (type => 'CR character reference', |
| 3012 |
|
line => $l, column => $c); |
| 3013 |
$code = 0x000A; |
$code = 0x000A; |
| 3014 |
} elsif (0x80 <= $code and $code <= 0x9F) { |
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 3015 |
!!!cp (1018); |
!!!cp (1018); |
| 3016 |
!!!parse-error (type => (sprintf 'C1 character reference:U+%04X', $code), line => $l, column => $c); |
!!!parse-error (type => 'C1 character reference', |
| 3017 |
|
text => (sprintf 'U+%04X', $code), |
| 3018 |
|
line => $l, column => $c); |
| 3019 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 3020 |
} |
} |
| 3021 |
|
|
| 3041 |
require Whatpm::_NamedEntityList; |
require Whatpm::_NamedEntityList; |
| 3042 |
our $EntityChar; |
our $EntityChar; |
| 3043 |
|
|
| 3044 |
while (length $entity_name < 10 and |
while (length $entity_name < 30 and |
| 3045 |
## NOTE: Some number greater than the maximum length of entity name |
## NOTE: Some number greater than the maximum length of entity name |
| 3046 |
((0x0041 <= $self->{next_char} and # a |
((0x0041 <= $self->{next_char} and # a |
| 3047 |
$self->{next_char} <= 0x005A) or # x |
$self->{next_char} <= 0x005A) or # x |
| 3113 |
## TODO: Turn mutation events off # MUST |
## TODO: Turn mutation events off # MUST |
| 3114 |
## TODO: Turn loose Document option (manakai extension) on |
## TODO: Turn loose Document option (manakai extension) on |
| 3115 |
$self->{document}->manakai_is_html (1); # MUST |
$self->{document}->manakai_is_html (1); # MUST |
| 3116 |
|
$self->{document}->set_user_data (manakai_source_line => 1); |
| 3117 |
|
$self->{document}->set_user_data (manakai_source_column => 1); |
| 3118 |
} # _initialize_tree_constructor |
} # _initialize_tree_constructor |
| 3119 |
|
|
| 3120 |
sub _terminate_tree_constructor ($) { |
sub _terminate_tree_constructor ($) { |
| 3169 |
## language. |
## language. |
| 3170 |
my $doctype_name = $token->{name}; |
my $doctype_name = $token->{name}; |
| 3171 |
$doctype_name = '' unless defined $doctype_name; |
$doctype_name = '' unless defined $doctype_name; |
| 3172 |
$doctype_name =~ tr/a-z/A-Z/; |
$doctype_name =~ tr/a-z/A-Z/; # ASCII case-insensitive |
| 3173 |
if (not defined $token->{name} or # <!DOCTYPE> |
if (not defined $token->{name} or # <!DOCTYPE> |
|
defined $token->{public_identifier} or |
|
| 3174 |
defined $token->{system_identifier}) { |
defined $token->{system_identifier}) { |
| 3175 |
!!!cp ('t1'); |
!!!cp ('t1'); |
| 3176 |
!!!parse-error (type => 'not HTML5', token => $token); |
!!!parse-error (type => 'not HTML5', token => $token); |
| 3177 |
} elsif ($doctype_name ne 'HTML') { |
} elsif ($doctype_name ne 'HTML') { |
| 3178 |
!!!cp ('t2'); |
!!!cp ('t2'); |
|
## ISSUE: ASCII case-insensitive? (in fact it does not matter) |
|
| 3179 |
!!!parse-error (type => 'not HTML5', token => $token); |
!!!parse-error (type => 'not HTML5', token => $token); |
| 3180 |
|
} elsif (defined $token->{public_identifier}) { |
| 3181 |
|
if ($token->{public_identifier} eq 'XSLT-compat') { |
| 3182 |
|
!!!cp ('t1.2'); |
| 3183 |
|
!!!parse-error (type => 'XSLT-compat', token => $token, |
| 3184 |
|
level => $self->{level}->{should}); |
| 3185 |
|
} else { |
| 3186 |
|
!!!parse-error (type => 'not HTML5', token => $token); |
| 3187 |
|
} |
| 3188 |
} else { |
} else { |
| 3189 |
!!!cp ('t3'); |
!!!cp ('t3'); |
| 3190 |
|
# |
| 3191 |
} |
} |
| 3192 |
|
|
| 3193 |
my $doctype = $self->{document}->create_document_type_definition |
my $doctype = $self->{document}->create_document_type_definition |
| 3208 |
} elsif (defined $token->{public_identifier}) { |
} elsif (defined $token->{public_identifier}) { |
| 3209 |
my $pubid = $token->{public_identifier}; |
my $pubid = $token->{public_identifier}; |
| 3210 |
$pubid =~ tr/a-z/A-z/; |
$pubid =~ tr/a-z/A-z/; |
| 3211 |
if ({ |
my $prefix = [ |
| 3212 |
"+//SILMARIL//DTD HTML PRO V0R11 19970101//EN" => 1, |
"+//SILMARIL//DTD HTML PRO V0R11 19970101//", |
| 3213 |
"-//ADVASOFT LTD//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1, |
"-//ADVASOFT LTD//DTD HTML 3.0 ASWEDIT + EXTENSIONS//", |
| 3214 |
"-//AS//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1, |
"-//AS//DTD HTML 3.0 ASWEDIT + EXTENSIONS//", |
| 3215 |
"-//IETF//DTD HTML 2.0 LEVEL 1//EN" => 1, |
"-//IETF//DTD HTML 2.0 LEVEL 1//", |
| 3216 |
"-//IETF//DTD HTML 2.0 LEVEL 2//EN" => 1, |
"-//IETF//DTD HTML 2.0 LEVEL 2//", |
| 3217 |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 1//EN" => 1, |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 1//", |
| 3218 |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 2//EN" => 1, |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 2//", |
| 3219 |
"-//IETF//DTD HTML 2.0 STRICT//EN" => 1, |
"-//IETF//DTD HTML 2.0 STRICT//", |
| 3220 |
"-//IETF//DTD HTML 2.0//EN" => 1, |
"-//IETF//DTD HTML 2.0//", |
| 3221 |
"-//IETF//DTD HTML 2.1E//EN" => 1, |
"-//IETF//DTD HTML 2.1E//", |
| 3222 |
"-//IETF//DTD HTML 3.0//EN" => 1, |
"-//IETF//DTD HTML 3.0//", |
| 3223 |
"-//IETF//DTD HTML 3.0//EN//" => 1, |
"-//IETF//DTD HTML 3.2 FINAL//", |
| 3224 |
"-//IETF//DTD HTML 3.2 FINAL//EN" => 1, |
"-//IETF//DTD HTML 3.2//", |
| 3225 |
"-//IETF//DTD HTML 3.2//EN" => 1, |
"-//IETF//DTD HTML 3//", |
| 3226 |
"-//IETF//DTD HTML 3//EN" => 1, |
"-//IETF//DTD HTML LEVEL 0//", |
| 3227 |
"-//IETF//DTD HTML LEVEL 0//EN" => 1, |
"-//IETF//DTD HTML LEVEL 1//", |
| 3228 |
"-//IETF//DTD HTML LEVEL 0//EN//2.0" => 1, |
"-//IETF//DTD HTML LEVEL 2//", |
| 3229 |
"-//IETF//DTD HTML LEVEL 1//EN" => 1, |
"-//IETF//DTD HTML LEVEL 3//", |
| 3230 |
"-//IETF//DTD HTML LEVEL 1//EN//2.0" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 0//", |
| 3231 |
"-//IETF//DTD HTML LEVEL 2//EN" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 1//", |
| 3232 |
"-//IETF//DTD HTML LEVEL 2//EN//2.0" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 2//", |
| 3233 |
"-//IETF//DTD HTML LEVEL 3//EN" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 3//", |
| 3234 |
"-//IETF//DTD HTML LEVEL 3//EN//3.0" => 1, |
"-//IETF//DTD HTML STRICT//", |
| 3235 |
"-//IETF//DTD HTML STRICT LEVEL 0//EN" => 1, |
"-//IETF//DTD HTML//", |
| 3236 |
"-//IETF//DTD HTML STRICT LEVEL 0//EN//2.0" => 1, |
"-//METRIUS//DTD METRIUS PRESENTATIONAL//", |
| 3237 |
"-//IETF//DTD HTML STRICT LEVEL 1//EN" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML STRICT//", |
| 3238 |
"-//IETF//DTD HTML STRICT LEVEL 1//EN//2.0" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML//", |
| 3239 |
"-//IETF//DTD HTML STRICT LEVEL 2//EN" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 TABLES//", |
| 3240 |
"-//IETF//DTD HTML STRICT LEVEL 2//EN//2.0" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML STRICT//", |
| 3241 |
"-//IETF//DTD HTML STRICT LEVEL 3//EN" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML//", |
| 3242 |
"-//IETF//DTD HTML STRICT LEVEL 3//EN//3.0" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 TABLES//", |
| 3243 |
"-//IETF//DTD HTML STRICT//EN" => 1, |
"-//NETSCAPE COMM. CORP.//DTD HTML//", |
| 3244 |
"-//IETF//DTD HTML STRICT//EN//2.0" => 1, |
"-//NETSCAPE COMM. CORP.//DTD STRICT HTML//", |
| 3245 |
"-//IETF//DTD HTML STRICT//EN//3.0" => 1, |
"-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//", |
| 3246 |
"-//IETF//DTD HTML//EN" => 1, |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//", |
| 3247 |
"-//IETF//DTD HTML//EN//2.0" => 1, |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED RELAXED 1.0//", |
| 3248 |
"-//IETF//DTD HTML//EN//3.0" => 1, |
"-//SOFTQUAD SOFTWARE//DTD HOTMETAL PRO 6.0::19990601::EXTENSIONS TO HTML 4.0//", |
| 3249 |
"-//METRIUS//DTD METRIUS PRESENTATIONAL//EN" => 1, |
"-//SOFTQUAD//DTD HOTMETAL PRO 4.0::19971010::EXTENSIONS TO HTML 4.0//", |
| 3250 |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML STRICT//EN" => 1, |
"-//SPYGLASS//DTD HTML 2.0 EXTENDED//", |
| 3251 |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML//EN" => 1, |
"-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//", |
| 3252 |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 TABLES//EN" => 1, |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//", |
| 3253 |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML STRICT//EN" => 1, |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA STRICT HTML//", |
| 3254 |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML//EN" => 1, |
"-//W3C//DTD HTML 3 1995-03-24//", |
| 3255 |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 TABLES//EN" => 1, |
"-//W3C//DTD HTML 3.2 DRAFT//", |
| 3256 |
"-//NETSCAPE COMM. CORP.//DTD HTML//EN" => 1, |
"-//W3C//DTD HTML 3.2 FINAL//", |
| 3257 |
"-//NETSCAPE COMM. CORP.//DTD STRICT HTML//EN" => 1, |
"-//W3C//DTD HTML 3.2//", |
| 3258 |
"-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//EN" => 1, |
"-//W3C//DTD HTML 3.2S DRAFT//", |
| 3259 |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//EN" => 1, |
"-//W3C//DTD HTML 4.0 FRAMESET//", |
| 3260 |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED RELAXED 1.0//EN" => 1, |
"-//W3C//DTD HTML 4.0 TRANSITIONAL//", |
| 3261 |
"-//SOFTQUAD SOFTWARE//DTD HOTMETAL PRO 6.0::19990601::EXTENSIONS TO HTML 4.0//EN" => 1, |
"-//W3C//DTD HTML EXPERIMETNAL 19960712//", |
| 3262 |
"-//SOFTQUAD//DTD HOTMETAL PRO 4.0::19971010::EXTENSIONS TO HTML 4.0//EN" => 1, |
"-//W3C//DTD HTML EXPERIMENTAL 970421//", |
| 3263 |
"-//SPYGLASS//DTD HTML 2.0 EXTENDED//EN" => 1, |
"-//W3C//DTD W3 HTML//", |
| 3264 |
"-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//EN" => 1, |
"-//W3O//DTD W3 HTML 3.0//", |
| 3265 |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//EN" => 1, |
"-//WEBTECHS//DTD MOZILLA HTML 2.0//", |
| 3266 |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA STRICT HTML//EN" => 1, |
"-//WEBTECHS//DTD MOZILLA HTML//", |
| 3267 |
"-//W3C//DTD HTML 3 1995-03-24//EN" => 1, |
]; # $prefix |
| 3268 |
"-//W3C//DTD HTML 3.2 DRAFT//EN" => 1, |
my $match; |
| 3269 |
"-//W3C//DTD HTML 3.2 FINAL//EN" => 1, |
for (@$prefix) { |
| 3270 |
"-//W3C//DTD HTML 3.2//EN" => 1, |
if (substr ($prefix, 0, length $_) eq $_) { |
| 3271 |
"-//W3C//DTD HTML 3.2S DRAFT//EN" => 1, |
$match = 1; |
| 3272 |
"-//W3C//DTD HTML 4.0 FRAMESET//EN" => 1, |
last; |
| 3273 |
"-//W3C//DTD HTML 4.0 TRANSITIONAL//EN" => 1, |
} |
| 3274 |
"-//W3C//DTD HTML EXPERIMETNAL 19960712//EN" => 1, |
} |
| 3275 |
"-//W3C//DTD HTML EXPERIMENTAL 970421//EN" => 1, |
if ($match or |
| 3276 |
"-//W3C//DTD W3 HTML//EN" => 1, |
$pubid eq "-//W3O//DTD W3 HTML STRICT 3.0//EN//" or |
| 3277 |
"-//W3O//DTD W3 HTML 3.0//EN" => 1, |
$pubid eq "-/W3C/DTD HTML 4.0 TRANSITIONAL/EN" or |
| 3278 |
"-//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}) { |
|
| 3279 |
!!!cp ('t5'); |
!!!cp ('t5'); |
| 3280 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 3281 |
} elsif ($pubid eq "-//W3C//DTD HTML 4.01 FRAMESET//EN" or |
} elsif ($pubid =~ m[^-//W3C//DTD HTML 4.01 FRAMESET//] or |
| 3282 |
$pubid eq "-//W3C//DTD HTML 4.01 TRANSITIONAL//EN") { |
$pubid =~ m[^-//W3C//DTD HTML 4.01 TRANSITIONAL//]) { |
| 3283 |
if (defined $token->{system_identifier}) { |
if (defined $token->{system_identifier}) { |
| 3284 |
!!!cp ('t6'); |
!!!cp ('t6'); |
| 3285 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 3287 |
!!!cp ('t7'); |
!!!cp ('t7'); |
| 3288 |
$self->{document}->manakai_compat_mode ('limited quirks'); |
$self->{document}->manakai_compat_mode ('limited quirks'); |
| 3289 |
} |
} |
| 3290 |
} elsif ($pubid eq "-//W3C//DTD XHTML 1.0 FRAMESET//EN" or |
} elsif ($pubid =~ m[^-//W3C//DTD XHTML 1.0 FRAMESET//] or |
| 3291 |
$pubid eq "-//W3C//DTD XHTML 1.0 TRANSITIONAL//EN") { |
$pubid =~ m[^-//W3C//DTD XHTML 1.0 TRANSITIONAL//]) { |
| 3292 |
!!!cp ('t8'); |
!!!cp ('t8'); |
| 3293 |
$self->{document}->manakai_compat_mode ('limited quirks'); |
$self->{document}->manakai_compat_mode ('limited quirks'); |
| 3294 |
} else { |
} else { |
| 3301 |
my $sysid = $token->{system_identifier}; |
my $sysid = $token->{system_identifier}; |
| 3302 |
$sysid =~ tr/A-Z/a-z/; |
$sysid =~ tr/A-Z/a-z/; |
| 3303 |
if ($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") { |
| 3304 |
## TODO: Check the spec: PUBLIC "(limited quirks)" "(quirks)" |
## NOTE: Ensure that |PUBLIC "(limited quirks)" "(quirks)"| is |
| 3305 |
|
## marked as quirks. |
| 3306 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 3307 |
!!!cp ('t11'); |
!!!cp ('t11'); |
| 3308 |
} else { |
} else { |
| 3406 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 3407 |
if ($token->{tag_name} eq 'html') { |
if ($token->{tag_name} eq 'html') { |
| 3408 |
my $root_element; |
my $root_element; |
| 3409 |
!!!create-element ($root_element, $token->{tag_name}, $token->{attributes}, $token); |
!!!create-element ($root_element, $HTML_NS, $token->{tag_name}, $token->{attributes}, $token); |
| 3410 |
$self->{document}->append_child ($root_element); |
$self->{document}->append_child ($root_element); |
| 3411 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 3412 |
[$root_element, $el_category->{html}]; |
[$root_element, $el_category->{html}]; |
| 3442 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 3443 |
} |
} |
| 3444 |
|
|
| 3445 |
my $root_element; !!!create-element ($root_element, 'html',, $token); |
my $root_element; |
| 3446 |
|
!!!create-element ($root_element, $HTML_NS, 'html',, $token); |
| 3447 |
$self->{document}->append_child ($root_element); |
$self->{document}->append_child ($root_element); |
| 3448 |
push @{$self->{open_elements}}, [$root_element, $el_category->{html}]; |
push @{$self->{open_elements}}, [$root_element, $el_category->{html}]; |
| 3449 |
|
|
| 3474 |
if ($self->{open_elements}->[0]->[0] eq $node->[0]) { |
if ($self->{open_elements}->[0]->[0] eq $node->[0]) { |
| 3475 |
$last = 1; |
$last = 1; |
| 3476 |
if (defined $self->{inner_html_node}) { |
if (defined $self->{inner_html_node}) { |
| 3477 |
if ($self->{inner_html_node}->[1] & TABLE_CELL_EL) { |
!!!cp ('t28'); |
| 3478 |
!!!cp ('t27'); |
$node = $self->{inner_html_node}; |
| 3479 |
# |
} else { |
| 3480 |
} else { |
die "_reset_insertion_mode: t27"; |
|
!!!cp ('t28'); |
|
|
$node = $self->{inner_html_node}; |
|
|
} |
|
| 3481 |
} |
} |
| 3482 |
} |
} |
| 3483 |
|
|
| 3484 |
## Step 4..13 |
## Step 4..14 |
| 3485 |
my $new_mode = { |
my $new_mode; |
| 3486 |
|
if ($node->[1] & FOREIGN_EL) { |
| 3487 |
|
!!!cp ('t28.1'); |
| 3488 |
|
## NOTE: Strictly spaking, the line below only applies to MathML and |
| 3489 |
|
## SVG elements. Currently the HTML syntax supports only MathML and |
| 3490 |
|
## SVG elements as foreigners. |
| 3491 |
|
$new_mode = IN_BODY_IM | IN_FOREIGN_CONTENT_IM; |
| 3492 |
|
} elsif ($node->[1] & TABLE_CELL_EL) { |
| 3493 |
|
if ($last) { |
| 3494 |
|
!!!cp ('t28.2'); |
| 3495 |
|
# |
| 3496 |
|
} else { |
| 3497 |
|
!!!cp ('t28.3'); |
| 3498 |
|
$new_mode = IN_CELL_IM; |
| 3499 |
|
} |
| 3500 |
|
} else { |
| 3501 |
|
!!!cp ('t28.4'); |
| 3502 |
|
$new_mode = { |
| 3503 |
select => IN_SELECT_IM, |
select => IN_SELECT_IM, |
| 3504 |
## NOTE: |option| and |optgroup| do not set |
## NOTE: |option| and |optgroup| do not set |
| 3505 |
## insertion mode to "in select" by themselves. |
## insertion mode to "in select" by themselves. |
|
td => IN_CELL_IM, |
|
|
th => IN_CELL_IM, |
|
| 3506 |
tr => IN_ROW_IM, |
tr => IN_ROW_IM, |
| 3507 |
tbody => IN_TABLE_BODY_IM, |
tbody => IN_TABLE_BODY_IM, |
| 3508 |
thead => IN_TABLE_BODY_IM, |
thead => IN_TABLE_BODY_IM, |
| 3514 |
body => IN_BODY_IM, |
body => IN_BODY_IM, |
| 3515 |
frameset => IN_FRAMESET_IM, |
frameset => IN_FRAMESET_IM, |
| 3516 |
}->{$node->[0]->manakai_local_name}; |
}->{$node->[0]->manakai_local_name}; |
| 3517 |
## TODO: Foreign namespace case OK? |
} |
| 3518 |
$self->{insertion_mode} = $new_mode and return if defined $new_mode; |
$self->{insertion_mode} = $new_mode and return if defined $new_mode; |
| 3519 |
|
|
| 3520 |
## Step 14 |
## Step 15 |
| 3521 |
if ($node->[1] & HTML_EL) { |
if ($node->[1] & HTML_EL) { |
| 3522 |
unless (defined $self->{head_element}) { |
unless (defined $self->{head_element}) { |
| 3523 |
!!!cp ('t29'); |
!!!cp ('t29'); |
| 3532 |
!!!cp ('t31'); |
!!!cp ('t31'); |
| 3533 |
} |
} |
| 3534 |
|
|
| 3535 |
## Step 15 |
## Step 16 |
| 3536 |
$self->{insertion_mode} = IN_BODY_IM and return if $last; |
$self->{insertion_mode} = IN_BODY_IM and return if $last; |
| 3537 |
|
|
| 3538 |
## Step 16 |
## Step 17 |
| 3539 |
$i--; |
$i--; |
| 3540 |
$node = $self->{open_elements}->[$i]; |
$node = $self->{open_elements}->[$i]; |
| 3541 |
|
|
| 3542 |
## Step 17 |
## Step 18 |
| 3543 |
redo S3; |
redo S3; |
| 3544 |
} # S3 |
} # S3 |
| 3545 |
|
|
| 3651 |
## Step 1 |
## Step 1 |
| 3652 |
my $start_tag_name = $token->{tag_name}; |
my $start_tag_name = $token->{tag_name}; |
| 3653 |
my $el; |
my $el; |
| 3654 |
!!!create-element ($el, $start_tag_name, $token->{attributes}, $token); |
!!!create-element ($el, $HTML_NS, $start_tag_name, $token->{attributes}, $token); |
| 3655 |
|
|
| 3656 |
## Step 2 |
## Step 2 |
| 3657 |
$insert->($el); |
$insert->($el); |
| 3689 |
## NOTE: An end-of-file token. |
## NOTE: An end-of-file token. |
| 3690 |
if ($content_model_flag == CDATA_CONTENT_MODEL) { |
if ($content_model_flag == CDATA_CONTENT_MODEL) { |
| 3691 |
!!!cp ('t43'); |
!!!cp ('t43'); |
| 3692 |
!!!parse-error (type => 'in CDATA:#'.$token->{type}, token => $token); |
!!!parse-error (type => 'in CDATA:#eof', token => $token); |
| 3693 |
} elsif ($content_model_flag == RCDATA_CONTENT_MODEL) { |
} elsif ($content_model_flag == RCDATA_CONTENT_MODEL) { |
| 3694 |
!!!cp ('t44'); |
!!!cp ('t44'); |
| 3695 |
!!!parse-error (type => 'in RCDATA:#'.$token->{type}, token => $token); |
!!!parse-error (type => 'in RCDATA:#eof', token => $token); |
| 3696 |
} else { |
} else { |
| 3697 |
die "$0: $content_model_flag in parse_rcdata"; |
die "$0: $content_model_flag in parse_rcdata"; |
| 3698 |
} |
} |
| 3702 |
|
|
| 3703 |
my $script_start_tag = sub () { |
my $script_start_tag = sub () { |
| 3704 |
my $script_el; |
my $script_el; |
| 3705 |
!!!create-element ($script_el, 'script', $token->{attributes}, $token); |
!!!create-element ($script_el, $HTML_NS, 'script', $token->{attributes}, $token); |
| 3706 |
## TODO: mark as "parser-inserted" |
## TODO: mark as "parser-inserted" |
| 3707 |
|
|
| 3708 |
$self->{content_model} = CDATA_CONTENT_MODEL; |
$self->{content_model} = CDATA_CONTENT_MODEL; |
| 3729 |
## Ignore the token |
## Ignore the token |
| 3730 |
} else { |
} else { |
| 3731 |
!!!cp ('t48'); |
!!!cp ('t48'); |
| 3732 |
!!!parse-error (type => 'in CDATA:#'.$token->{type}, token => $token); |
!!!parse-error (type => 'in CDATA:#eof', token => $token); |
| 3733 |
## ISSUE: And ignore? |
## ISSUE: And ignore? |
| 3734 |
## TODO: mark as "already executed" |
## TODO: mark as "already executed" |
| 3735 |
} |
} |
| 3780 |
} # AFE |
} # AFE |
| 3781 |
unless (defined $formatting_element) { |
unless (defined $formatting_element) { |
| 3782 |
!!!cp ('t53'); |
!!!cp ('t53'); |
| 3783 |
!!!parse-error (type => 'unmatched end tag:'.$tag_name, token => $end_tag_token); |
!!!parse-error (type => 'unmatched end tag', text => $tag_name, token => $end_tag_token); |
| 3784 |
## Ignore the token |
## Ignore the token |
| 3785 |
!!!next-token; |
!!!next-token; |
| 3786 |
return; |
return; |
| 3797 |
last INSCOPE; |
last INSCOPE; |
| 3798 |
} else { # in open elements but not in scope |
} else { # in open elements but not in scope |
| 3799 |
!!!cp ('t55'); |
!!!cp ('t55'); |
| 3800 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, |
!!!parse-error (type => 'unmatched end tag', |
| 3801 |
|
text => $token->{tag_name}, |
| 3802 |
token => $end_tag_token); |
token => $end_tag_token); |
| 3803 |
## Ignore the token |
## Ignore the token |
| 3804 |
!!!next-token; |
!!!next-token; |
| 3811 |
} # INSCOPE |
} # INSCOPE |
| 3812 |
unless (defined $formatting_element_i_in_open) { |
unless (defined $formatting_element_i_in_open) { |
| 3813 |
!!!cp ('t57'); |
!!!cp ('t57'); |
| 3814 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, |
!!!parse-error (type => 'unmatched end tag', |
| 3815 |
|
text => $token->{tag_name}, |
| 3816 |
token => $end_tag_token); |
token => $end_tag_token); |
| 3817 |
pop @$active_formatting_elements; # $formatting_element |
pop @$active_formatting_elements; # $formatting_element |
| 3818 |
!!!next-token; ## TODO: ok? |
!!!next-token; ## TODO: ok? |
| 3821 |
if (not $self->{open_elements}->[-1]->[0] eq $formatting_element->[0]) { |
if (not $self->{open_elements}->[-1]->[0] eq $formatting_element->[0]) { |
| 3822 |
!!!cp ('t58'); |
!!!cp ('t58'); |
| 3823 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 3824 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 3825 |
->manakai_local_name, |
->manakai_local_name, |
| 3826 |
token => $end_tag_token); |
token => $end_tag_token); |
| 3827 |
} |
} |
| 4027 |
} |
} |
| 4028 |
}; # $insert_to_foster |
}; # $insert_to_foster |
| 4029 |
|
|
| 4030 |
B: { |
B: while (1) { |
| 4031 |
if ($token->{type} == DOCTYPE_TOKEN) { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 4032 |
!!!cp ('t73'); |
!!!cp ('t73'); |
| 4033 |
!!!parse-error (type => 'DOCTYPE in the middle', token => $token); |
!!!parse-error (type => 'in html:#DOCTYPE', token => $token); |
| 4034 |
## Ignore the token |
## Ignore the token |
| 4035 |
## Stay in the phase |
## Stay in the phase |
| 4036 |
!!!next-token; |
!!!next-token; |
| 4037 |
redo B; |
next B; |
| 4038 |
} elsif ($token->{type} == START_TAG_TOKEN and |
} elsif ($token->{type} == START_TAG_TOKEN and |
| 4039 |
$token->{tag_name} eq 'html') { |
$token->{tag_name} eq 'html') { |
| 4040 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 4041 |
!!!cp ('t79'); |
!!!cp ('t79'); |
| 4042 |
!!!parse-error (type => 'after html:html', token => $token); |
!!!parse-error (type => 'after html', text => 'html', token => $token); |
| 4043 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 4044 |
} elsif ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 4045 |
!!!cp ('t80'); |
!!!cp ('t80'); |
| 4046 |
!!!parse-error (type => 'after html:html', token => $token); |
!!!parse-error (type => 'after html', text => 'html', token => $token); |
| 4047 |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 4048 |
} else { |
} else { |
| 4049 |
!!!cp ('t81'); |
!!!cp ('t81'); |
| 4062 |
} |
} |
| 4063 |
!!!nack ('t84.1'); |
!!!nack ('t84.1'); |
| 4064 |
!!!next-token; |
!!!next-token; |
| 4065 |
redo B; |
next B; |
| 4066 |
} elsif ($token->{type} == COMMENT_TOKEN) { |
} elsif ($token->{type} == COMMENT_TOKEN) { |
| 4067 |
my $comment = $self->{document}->create_comment ($token->{data}); |
my $comment = $self->{document}->create_comment ($token->{data}); |
| 4068 |
if ($self->{insertion_mode} & AFTER_HTML_IMS) { |
if ($self->{insertion_mode} & AFTER_HTML_IMS) { |
| 4076 |
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
| 4077 |
} |
} |
| 4078 |
!!!next-token; |
!!!next-token; |
| 4079 |
redo B; |
next B; |
| 4080 |
} elsif ($self->{insertion_mode} & HEAD_IMS) { |
} elsif ($self->{insertion_mode} & IN_FOREIGN_CONTENT_IM) { |
| 4081 |
|
if ($token->{type} == CHARACTER_TOKEN) { |
| 4082 |
|
!!!cp ('t87.1'); |
| 4083 |
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
| 4084 |
|
!!!next-token; |
| 4085 |
|
next B; |
| 4086 |
|
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 4087 |
|
if ((not {mglyph => 1, malignmark => 1}->{$token->{tag_name}} and |
| 4088 |
|
$self->{open_elements}->[-1]->[1] & FOREIGN_FLOW_CONTENT_EL) or |
| 4089 |
|
not ($self->{open_elements}->[-1]->[1] & FOREIGN_EL) or |
| 4090 |
|
($token->{tag_name} eq 'svg' and |
| 4091 |
|
$self->{open_elements}->[-1]->[1] & MML_AXML_EL)) { |
| 4092 |
|
## NOTE: "using the rules for secondary insertion mode"then"continue" |
| 4093 |
|
!!!cp ('t87.2'); |
| 4094 |
|
# |
| 4095 |
|
} elsif ({ |
| 4096 |
|
b => 1, big => 1, blockquote => 1, body => 1, br => 1, |
| 4097 |
|
center => 1, code => 1, dd => 1, div => 1, dl => 1, dt => 1, |
| 4098 |
|
em => 1, embed => 1, font => 1, h1 => 1, h2 => 1, h3 => 1, |
| 4099 |
|
h4 => 1, h5 => 1, h6 => 1, head => 1, hr => 1, i => 1, |
| 4100 |
|
img => 1, li => 1, listing => 1, menu => 1, meta => 1, |
| 4101 |
|
nobr => 1, ol => 1, p => 1, pre => 1, ruby => 1, s => 1, |
| 4102 |
|
small => 1, span => 1, strong => 1, strike => 1, sub => 1, |
| 4103 |
|
sup => 1, table => 1, tt => 1, u => 1, ul => 1, var => 1, |
| 4104 |
|
}->{$token->{tag_name}}) { |
| 4105 |
|
!!!cp ('t87.2'); |
| 4106 |
|
!!!parse-error (type => 'not closed', |
| 4107 |
|
text => $self->{open_elements}->[-1]->[0] |
| 4108 |
|
->manakai_local_name, |
| 4109 |
|
token => $token); |
| 4110 |
|
|
| 4111 |
|
pop @{$self->{open_elements}} |
| 4112 |
|
while $self->{open_elements}->[-1]->[1] & FOREIGN_EL; |
| 4113 |
|
|
| 4114 |
|
$self->{insertion_mode} &= ~ IN_FOREIGN_CONTENT_IM; |
| 4115 |
|
## Reprocess. |
| 4116 |
|
next B; |
| 4117 |
|
} else { |
| 4118 |
|
my $nsuri = $self->{open_elements}->[-1]->[0]->namespace_uri; |
| 4119 |
|
my $tag_name = $token->{tag_name}; |
| 4120 |
|
if ($nsuri eq $SVG_NS) { |
| 4121 |
|
$tag_name = { |
| 4122 |
|
altglyph => 'altGlyph', |
| 4123 |
|
altglyphdef => 'altGlyphDef', |
| 4124 |
|
altglyphitem => 'altGlyphItem', |
| 4125 |
|
animatecolor => 'animateColor', |
| 4126 |
|
animatemotion => 'animateMotion', |
| 4127 |
|
animatetransform => 'animateTransform', |
| 4128 |
|
clippath => 'clipPath', |
| 4129 |
|
feblend => 'feBlend', |
| 4130 |
|
fecolormatrix => 'feColorMatrix', |
| 4131 |
|
fecomponenttransfer => 'feComponentTransfer', |
| 4132 |
|
fecomposite => 'feComposite', |
| 4133 |
|
feconvolvematrix => 'feConvolveMatrix', |
| 4134 |
|
fediffuselighting => 'feDiffuseLighting', |
| 4135 |
|
fedisplacementmap => 'feDisplacementMap', |
| 4136 |
|
fedistantlight => 'feDistantLight', |
| 4137 |
|
feflood => 'feFlood', |
| 4138 |
|
fefunca => 'feFuncA', |
| 4139 |
|
fefuncb => 'feFuncB', |
| 4140 |
|
fefuncg => 'feFuncG', |
| 4141 |
|
fefuncr => 'feFuncR', |
| 4142 |
|
fegaussianblur => 'feGaussianBlur', |
| 4143 |
|
feimage => 'feImage', |
| 4144 |
|
femerge => 'feMerge', |
| 4145 |
|
femergenode => 'feMergeNode', |
| 4146 |
|
femorphology => 'feMorphology', |
| 4147 |
|
feoffset => 'feOffset', |
| 4148 |
|
fepointlight => 'fePointLight', |
| 4149 |
|
fespecularlighting => 'feSpecularLighting', |
| 4150 |
|
fespotlight => 'feSpotLight', |
| 4151 |
|
fetile => 'feTile', |
| 4152 |
|
feturbulence => 'feTurbulence', |
| 4153 |
|
foreignobject => 'foreignObject', |
| 4154 |
|
glyphref => 'glyphRef', |
| 4155 |
|
lineargradient => 'linearGradient', |
| 4156 |
|
radialgradient => 'radialGradient', |
| 4157 |
|
#solidcolor => 'solidColor', ## NOTE: Commented in spec (SVG1.2) |
| 4158 |
|
textpath => 'textPath', |
| 4159 |
|
}->{$tag_name} || $tag_name; |
| 4160 |
|
} |
| 4161 |
|
|
| 4162 |
|
## "adjust SVG attributes" (SVG only) - done in insert-element-f |
| 4163 |
|
|
| 4164 |
|
## "adjust foreign attributes" - done in insert-element-f |
| 4165 |
|
|
| 4166 |
|
!!!insert-element-f ($nsuri, $tag_name, $token->{attributes}, $token); |
| 4167 |
|
|
| 4168 |
|
if ($self->{self_closing}) { |
| 4169 |
|
pop @{$self->{open_elements}}; |
| 4170 |
|
!!!ack ('t87.3'); |
| 4171 |
|
} else { |
| 4172 |
|
!!!cp ('t87.4'); |
| 4173 |
|
} |
| 4174 |
|
|
| 4175 |
|
!!!next-token; |
| 4176 |
|
next B; |
| 4177 |
|
} |
| 4178 |
|
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 4179 |
|
## NOTE: "using the rules for secondary insertion mode" then "continue" |
| 4180 |
|
!!!cp ('t87.5'); |
| 4181 |
|
# |
| 4182 |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 4183 |
|
!!!cp ('t87.6'); |
| 4184 |
|
!!!parse-error (type => 'not closed', |
| 4185 |
|
text => $self->{open_elements}->[-1]->[0] |
| 4186 |
|
->manakai_local_name, |
| 4187 |
|
token => $token); |
| 4188 |
|
|
| 4189 |
|
pop @{$self->{open_elements}} |
| 4190 |
|
while $self->{open_elements}->[-1]->[1] & FOREIGN_EL; |
| 4191 |
|
|
| 4192 |
|
$self->{insertion_mode} &= ~ IN_FOREIGN_CONTENT_IM; |
| 4193 |
|
## Reprocess. |
| 4194 |
|
next B; |
| 4195 |
|
} else { |
| 4196 |
|
die "$0: $token->{type}: Unknown token type"; |
| 4197 |
|
} |
| 4198 |
|
} |
| 4199 |
|
|
| 4200 |
|
if ($self->{insertion_mode} & HEAD_IMS) { |
| 4201 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 4202 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 4203 |
unless ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
unless ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4207 |
!!!cp ('t88.1'); |
!!!cp ('t88.1'); |
| 4208 |
## Ignore the token. |
## Ignore the token. |
| 4209 |
!!!next-token; |
!!!next-token; |
| 4210 |
redo B; |
next B; |
| 4211 |
} |
} |
| 4212 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 4213 |
!!!cp ('t88'); |
!!!cp ('t88'); |
| 4214 |
!!!next-token; |
!!!next-token; |
| 4215 |
redo B; |
next B; |
| 4216 |
} |
} |
| 4217 |
} |
} |
| 4218 |
|
|
| 4219 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4220 |
!!!cp ('t89'); |
!!!cp ('t89'); |
| 4221 |
## As if <head> |
## As if <head> |
| 4222 |
!!!create-element ($self->{head_element}, 'head',, $token); |
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
| 4223 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 4224 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4225 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4232 |
!!!cp ('t90'); |
!!!cp ('t90'); |
| 4233 |
## As if </noscript> |
## As if </noscript> |
| 4234 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4235 |
!!!parse-error (type => 'in noscript:#character', token => $token); |
!!!parse-error (type => 'in noscript:#text', token => $token); |
| 4236 |
|
|
| 4237 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4238 |
## As if </head> |
## As if </head> |
| 4253 |
!!!insert-element ('body',, $token); |
!!!insert-element ('body',, $token); |
| 4254 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 4255 |
## reprocess |
## reprocess |
| 4256 |
redo B; |
next B; |
| 4257 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 4258 |
if ($token->{tag_name} eq 'head') { |
if ($token->{tag_name} eq 'head') { |
| 4259 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4260 |
!!!cp ('t93'); |
!!!cp ('t93'); |
| 4261 |
!!!create-element ($self->{head_element}, $token->{tag_name}, $token->{attributes}, $token); |
!!!create-element ($self->{head_element}, $HTML_NS, $token->{tag_name}, $token->{attributes}, $token); |
| 4262 |
$self->{open_elements}->[-1]->[0]->append_child |
$self->{open_elements}->[-1]->[0]->append_child |
| 4263 |
($self->{head_element}); |
($self->{head_element}); |
| 4264 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4266 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4267 |
!!!nack ('t93.1'); |
!!!nack ('t93.1'); |
| 4268 |
!!!next-token; |
!!!next-token; |
| 4269 |
redo B; |
next B; |
| 4270 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4271 |
!!!cp ('t94'); |
!!!cp ('t93.2'); |
| 4272 |
# |
!!!parse-error (type => 'after head', text => 'head', |
| 4273 |
|
token => $token); |
| 4274 |
|
## Ignore the token |
| 4275 |
|
!!!nack ('t93.3'); |
| 4276 |
|
!!!next-token; |
| 4277 |
|
next B; |
| 4278 |
} else { |
} else { |
| 4279 |
!!!cp ('t95'); |
!!!cp ('t95'); |
| 4280 |
!!!parse-error (type => 'in head:head', token => $token); # or in head noscript |
!!!parse-error (type => 'in head:head', |
| 4281 |
|
token => $token); # or in head noscript |
| 4282 |
## Ignore the token |
## Ignore the token |
| 4283 |
!!!nack ('t95.1'); |
!!!nack ('t95.1'); |
| 4284 |
!!!next-token; |
!!!next-token; |
| 4285 |
redo B; |
next B; |
| 4286 |
} |
} |
| 4287 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4288 |
!!!cp ('t96'); |
!!!cp ('t96'); |
| 4289 |
## As if <head> |
## As if <head> |
| 4290 |
!!!create-element ($self->{head_element}, 'head',, $token); |
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
| 4291 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 4292 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4293 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4294 |
|
|
| 4295 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4296 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4297 |
} else { |
} else { |
| 4298 |
!!!cp ('t97'); |
!!!cp ('t97'); |
| 4299 |
} |
} |
| 4300 |
|
|
| 4301 |
if ($token->{tag_name} eq 'base') { |
if ($token->{tag_name} eq 'base') { |
| 4302 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4303 |
!!!cp ('t98'); |
!!!cp ('t98'); |
| 4304 |
## As if </noscript> |
## As if </noscript> |
| 4305 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4306 |
!!!parse-error (type => 'in noscript:base', token => $token); |
!!!parse-error (type => 'in noscript', text => 'base', |
| 4307 |
|
token => $token); |
| 4308 |
|
|
| 4309 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4310 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4315 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4316 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4317 |
!!!cp ('t100'); |
!!!cp ('t100'); |
| 4318 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4319 |
|
text => $token->{tag_name}, token => $token); |
| 4320 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4321 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4322 |
} else { |
} else { |
| 4328 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 4329 |
!!!nack ('t101.1'); |
!!!nack ('t101.1'); |
| 4330 |
!!!next-token; |
!!!next-token; |
| 4331 |
redo B; |
next B; |
| 4332 |
} elsif ($token->{tag_name} eq 'link') { |
} elsif ($token->{tag_name} eq 'link') { |
| 4333 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4334 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4335 |
!!!cp ('t102'); |
!!!cp ('t102'); |
| 4336 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4337 |
|
text => $token->{tag_name}, token => $token); |
| 4338 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4339 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4340 |
} else { |
} else { |
| 4346 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 4347 |
!!!ack ('t103.1'); |
!!!ack ('t103.1'); |
| 4348 |
!!!next-token; |
!!!next-token; |
| 4349 |
redo B; |
next B; |
| 4350 |
} elsif ($token->{tag_name} eq 'meta') { |
} elsif ($token->{tag_name} eq 'meta') { |
| 4351 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4352 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4353 |
!!!cp ('t104'); |
!!!cp ('t104'); |
| 4354 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4355 |
|
text => $token->{tag_name}, token => $token); |
| 4356 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4357 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4358 |
} else { |
} else { |
| 4362 |
my $meta_el = pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
my $meta_el = pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 4363 |
|
|
| 4364 |
unless ($self->{confident}) { |
unless ($self->{confident}) { |
| 4365 |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
if ($token->{attributes}->{charset}) { |
| 4366 |
!!!cp ('t106'); |
!!!cp ('t106'); |
| 4367 |
|
## NOTE: Whether the encoding is supported or not is handled |
| 4368 |
|
## in the {change_encoding} callback. |
| 4369 |
$self->{change_encoding} |
$self->{change_encoding} |
| 4370 |
->($self, $token->{attributes}->{charset}->{value}, |
->($self, $token->{attributes}->{charset}->{value}, |
| 4371 |
$token); |
$token); |
| 4375 |
$token->{attributes}->{charset} |
$token->{attributes}->{charset} |
| 4376 |
->{has_reference}); |
->{has_reference}); |
| 4377 |
} elsif ($token->{attributes}->{content}) { |
} elsif ($token->{attributes}->{content}) { |
|
## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition. |
|
| 4378 |
if ($token->{attributes}->{content}->{value} |
if ($token->{attributes}->{content}->{value} |
| 4379 |
=~ /\A[^;]*;[\x09-\x0D\x20]*[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
=~ /[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
| 4380 |
[\x09-\x0D\x20]*= |
[\x09-\x0D\x20]*= |
| 4381 |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
| 4382 |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20\x3B]*))/x) { |
| 4383 |
!!!cp ('t107'); |
!!!cp ('t107'); |
| 4384 |
|
## NOTE: Whether the encoding is supported or not is handled |
| 4385 |
|
## in the {change_encoding} callback. |
| 4386 |
$self->{change_encoding} |
$self->{change_encoding} |
| 4387 |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3, |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3, |
| 4388 |
$token); |
$token); |
| 4415 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 4416 |
!!!ack ('t110.1'); |
!!!ack ('t110.1'); |
| 4417 |
!!!next-token; |
!!!next-token; |
| 4418 |
redo B; |
next B; |
| 4419 |
} elsif ($token->{tag_name} eq 'title') { |
} elsif ($token->{tag_name} eq 'title') { |
| 4420 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4421 |
!!!cp ('t111'); |
!!!cp ('t111'); |
| 4422 |
## As if </noscript> |
## As if </noscript> |
| 4423 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4424 |
!!!parse-error (type => 'in noscript:title', token => $token); |
!!!parse-error (type => 'in noscript', text => 'title', |
| 4425 |
|
token => $token); |
| 4426 |
|
|
| 4427 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4428 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4429 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4430 |
!!!cp ('t112'); |
!!!cp ('t112'); |
| 4431 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4432 |
|
text => $token->{tag_name}, token => $token); |
| 4433 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4434 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4435 |
} else { |
} else { |
| 4442 |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
| 4443 |
pop @{$self->{open_elements}} # <head> |
pop @{$self->{open_elements}} # <head> |
| 4444 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 4445 |
redo B; |
next B; |
| 4446 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($token->{tag_name} eq 'style' or |
| 4447 |
|
$token->{tag_name} eq 'noframes') { |
| 4448 |
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
| 4449 |
## insertion mode IN_HEAD_IM) |
## insertion mode IN_HEAD_IM) |
| 4450 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4451 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4452 |
!!!cp ('t114'); |
!!!cp ('t114'); |
| 4453 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4454 |
|
text => $token->{tag_name}, token => $token); |
| 4455 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4456 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4457 |
} else { |
} else { |
| 4460 |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 4461 |
pop @{$self->{open_elements}} # <head> |
pop @{$self->{open_elements}} # <head> |
| 4462 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 4463 |
redo B; |
next B; |
| 4464 |
} elsif ($token->{tag_name} eq 'noscript') { |
} elsif ($token->{tag_name} eq 'noscript') { |
| 4465 |
if ($self->{insertion_mode} == IN_HEAD_IM) { |
if ($self->{insertion_mode} == IN_HEAD_IM) { |
| 4466 |
!!!cp ('t116'); |
!!!cp ('t116'); |
| 4469 |
$self->{insertion_mode} = IN_HEAD_NOSCRIPT_IM; |
$self->{insertion_mode} = IN_HEAD_NOSCRIPT_IM; |
| 4470 |
!!!nack ('t116.1'); |
!!!nack ('t116.1'); |
| 4471 |
!!!next-token; |
!!!next-token; |
| 4472 |
redo B; |
next B; |
| 4473 |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4474 |
!!!cp ('t117'); |
!!!cp ('t117'); |
| 4475 |
!!!parse-error (type => 'in noscript:noscript', token => $token); |
!!!parse-error (type => 'in noscript', text => 'noscript', |
| 4476 |
|
token => $token); |
| 4477 |
## Ignore the token |
## Ignore the token |
| 4478 |
!!!nack ('t117.1'); |
!!!nack ('t117.1'); |
| 4479 |
!!!next-token; |
!!!next-token; |
| 4480 |
redo B; |
next B; |
| 4481 |
} else { |
} else { |
| 4482 |
!!!cp ('t118'); |
!!!cp ('t118'); |
| 4483 |
# |
# |
| 4487 |
!!!cp ('t119'); |
!!!cp ('t119'); |
| 4488 |
## As if </noscript> |
## As if </noscript> |
| 4489 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4490 |
!!!parse-error (type => 'in noscript:script', token => $token); |
!!!parse-error (type => 'in noscript', text => 'script', |
| 4491 |
|
token => $token); |
| 4492 |
|
|
| 4493 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4494 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4495 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4496 |
!!!cp ('t120'); |
!!!cp ('t120'); |
| 4497 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 4498 |
|
text => $token->{tag_name}, token => $token); |
| 4499 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4500 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4501 |
} else { |
} else { |
| 4506 |
$script_start_tag->(); |
$script_start_tag->(); |
| 4507 |
pop @{$self->{open_elements}} # <head> |
pop @{$self->{open_elements}} # <head> |
| 4508 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 4509 |
redo B; |
next B; |
| 4510 |
} elsif ($token->{tag_name} eq 'body' or |
} elsif ($token->{tag_name} eq 'body' or |
| 4511 |
$token->{tag_name} eq 'frameset') { |
$token->{tag_name} eq 'frameset') { |
| 4512 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4513 |
!!!cp ('t122'); |
!!!cp ('t122'); |
| 4514 |
## As if </noscript> |
## As if </noscript> |
| 4515 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4516 |
!!!parse-error (type => 'in noscript:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in noscript', |
| 4517 |
|
text => $token->{tag_name}, token => $token); |
| 4518 |
|
|
| 4519 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4520 |
## As if </head> |
## As if </head> |
| 4543 |
} |
} |
| 4544 |
!!!nack ('t127.1'); |
!!!nack ('t127.1'); |
| 4545 |
!!!next-token; |
!!!next-token; |
| 4546 |
redo B; |
next B; |
| 4547 |
} else { |
} else { |
| 4548 |
!!!cp ('t128'); |
!!!cp ('t128'); |
| 4549 |
# |
# |
| 4553 |
!!!cp ('t129'); |
!!!cp ('t129'); |
| 4554 |
## As if </noscript> |
## As if </noscript> |
| 4555 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4556 |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in noscript:/', |
| 4557 |
|
text => $token->{tag_name}, token => $token); |
| 4558 |
|
|
| 4559 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4560 |
## As if </head> |
## As if </head> |
| 4577 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 4578 |
## reprocess |
## reprocess |
| 4579 |
!!!ack-later; |
!!!ack-later; |
| 4580 |
redo B; |
next B; |
| 4581 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 4582 |
if ($token->{tag_name} eq 'head') { |
if ($token->{tag_name} eq 'head') { |
| 4583 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4584 |
!!!cp ('t132'); |
!!!cp ('t132'); |
| 4585 |
## As if <head> |
## As if <head> |
| 4586 |
!!!create-element ($self->{head_element}, 'head',, $token); |
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
| 4587 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 4588 |
push @{$self->{open_elements}}, |
push @{$self->{open_elements}}, |
| 4589 |
[$self->{head_element}, $el_category->{head}]; |
[$self->{head_element}, $el_category->{head}]; |
| 4592 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4593 |
$self->{insertion_mode} = AFTER_HEAD_IM; |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4594 |
!!!next-token; |
!!!next-token; |
| 4595 |
redo B; |
next B; |
| 4596 |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4597 |
!!!cp ('t133'); |
!!!cp ('t133'); |
| 4598 |
## As if </noscript> |
## As if </noscript> |
| 4599 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4600 |
!!!parse-error (type => 'in noscript:/head', token => $token); |
!!!parse-error (type => 'in noscript:/', |
| 4601 |
|
text => 'head', token => $token); |
| 4602 |
|
|
| 4603 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4604 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4605 |
$self->{insertion_mode} = AFTER_HEAD_IM; |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4606 |
!!!next-token; |
!!!next-token; |
| 4607 |
redo B; |
next B; |
| 4608 |
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 4609 |
!!!cp ('t134'); |
!!!cp ('t134'); |
| 4610 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4611 |
$self->{insertion_mode} = AFTER_HEAD_IM; |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4612 |
!!!next-token; |
!!!next-token; |
| 4613 |
redo B; |
next B; |
| 4614 |
|
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4615 |
|
!!!cp ('t134.1'); |
| 4616 |
|
!!!parse-error (type => 'unmatched end tag', text => 'head', |
| 4617 |
|
token => $token); |
| 4618 |
|
## Ignore the token |
| 4619 |
|
!!!next-token; |
| 4620 |
|
next B; |
| 4621 |
} else { |
} else { |
| 4622 |
!!!cp ('t135'); |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
|
# |
|
| 4623 |
} |
} |
| 4624 |
} elsif ($token->{tag_name} eq 'noscript') { |
} elsif ($token->{tag_name} eq 'noscript') { |
| 4625 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4627 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4628 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4629 |
!!!next-token; |
!!!next-token; |
| 4630 |
redo B; |
next B; |
| 4631 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM or |
| 4632 |
|
$self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4633 |
!!!cp ('t137'); |
!!!cp ('t137'); |
| 4634 |
!!!parse-error (type => 'unmatched end tag:noscript', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4635 |
|
text => 'noscript', token => $token); |
| 4636 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 4637 |
!!!next-token; |
!!!next-token; |
| 4638 |
redo B; |
next B; |
| 4639 |
} else { |
} else { |
| 4640 |
!!!cp ('t138'); |
!!!cp ('t138'); |
| 4641 |
# |
# |
| 4643 |
} elsif ({ |
} elsif ({ |
| 4644 |
body => 1, html => 1, |
body => 1, html => 1, |
| 4645 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 4646 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM or |
| 4647 |
!!!cp ('t139'); |
$self->{insertion_mode} == IN_HEAD_IM or |
| 4648 |
## As if <head> |
$self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
|
!!!create-element ($self->{head_element}, '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) { |
|
| 4649 |
!!!cp ('t140'); |
!!!cp ('t140'); |
| 4650 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4651 |
|
text => $token->{tag_name}, token => $token); |
| 4652 |
## Ignore the token |
## Ignore the token |
| 4653 |
!!!next-token; |
!!!next-token; |
| 4654 |
redo B; |
next B; |
| 4655 |
|
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4656 |
|
!!!cp ('t140.1'); |
| 4657 |
|
!!!parse-error (type => 'unmatched end tag', |
| 4658 |
|
text => $token->{tag_name}, token => $token); |
| 4659 |
|
## Ignore the token |
| 4660 |
|
!!!next-token; |
| 4661 |
|
next B; |
| 4662 |
} else { |
} else { |
| 4663 |
!!!cp ('t141'); |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
| 4664 |
} |
} |
| 4665 |
|
} elsif ($token->{tag_name} eq 'p') { |
| 4666 |
# |
!!!cp ('t142'); |
| 4667 |
} elsif ({ |
!!!parse-error (type => 'unmatched end tag', |
| 4668 |
p => 1, br => 1, |
text => $token->{tag_name}, token => $token); |
| 4669 |
}->{$token->{tag_name}}) { |
## Ignore the token |
| 4670 |
|
!!!next-token; |
| 4671 |
|
next B; |
| 4672 |
|
} elsif ($token->{tag_name} eq 'br') { |
| 4673 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4674 |
!!!cp ('t142'); |
!!!cp ('t142.2'); |
| 4675 |
## As if <head> |
## (before head) as if <head>, (in head) as if </head> |
| 4676 |
!!!create-element ($self->{head_element}, 'head',, $token); |
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
| 4677 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 4678 |
push @{$self->{open_elements}}, |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4679 |
[$self->{head_element}, $el_category->{head}]; |
|
| 4680 |
|
## Reprocess in the "after head" insertion mode... |
| 4681 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 4682 |
|
!!!cp ('t143.2'); |
| 4683 |
|
## As if </head> |
| 4684 |
|
pop @{$self->{open_elements}}; |
| 4685 |
|
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4686 |
|
|
| 4687 |
|
## Reprocess in the "after head" insertion mode... |
| 4688 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4689 |
|
!!!cp ('t143.3'); |
| 4690 |
|
## ISSUE: Two parse errors for <head><noscript></br> |
| 4691 |
|
!!!parse-error (type => 'unmatched end tag', |
| 4692 |
|
text => 'br', token => $token); |
| 4693 |
|
## As if </noscript> |
| 4694 |
|
pop @{$self->{open_elements}}; |
| 4695 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4696 |
|
|
| 4697 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4698 |
} else { |
## As if </head> |
| 4699 |
!!!cp ('t143'); |
pop @{$self->{open_elements}}; |
| 4700 |
} |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4701 |
|
|
| 4702 |
# |
## Reprocess in the "after head" insertion mode... |
| 4703 |
} else { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4704 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
!!!cp ('t143.4'); |
|
!!!cp ('t144'); |
|
| 4705 |
# |
# |
| 4706 |
} else { |
} else { |
| 4707 |
!!!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; |
|
|
redo B; |
|
| 4708 |
} |
} |
| 4709 |
|
|
| 4710 |
|
## ISSUE: does not agree with IE7 - it doesn't ignore </br>. |
| 4711 |
|
!!!parse-error (type => 'unmatched end tag', |
| 4712 |
|
text => 'br', token => $token); |
| 4713 |
|
## Ignore the token |
| 4714 |
|
!!!next-token; |
| 4715 |
|
next B; |
| 4716 |
|
} else { |
| 4717 |
|
!!!cp ('t145'); |
| 4718 |
|
!!!parse-error (type => 'unmatched end tag', |
| 4719 |
|
text => $token->{tag_name}, token => $token); |
| 4720 |
|
## Ignore the token |
| 4721 |
|
!!!next-token; |
| 4722 |
|
next B; |
| 4723 |
} |
} |
| 4724 |
|
|
| 4725 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4726 |
!!!cp ('t146'); |
!!!cp ('t146'); |
| 4727 |
## As if </noscript> |
## As if </noscript> |
| 4728 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4729 |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in noscript:/', |
| 4730 |
|
text => $token->{tag_name}, token => $token); |
| 4731 |
|
|
| 4732 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4733 |
## As if </head> |
## As if </head> |
| 4743 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4744 |
## ISSUE: This case cannot be reached? |
## ISSUE: This case cannot be reached? |
| 4745 |
!!!cp ('t148'); |
!!!cp ('t148'); |
| 4746 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4747 |
|
text => $token->{tag_name}, token => $token); |
| 4748 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 4749 |
!!!next-token; |
!!!next-token; |
| 4750 |
redo B; |
next B; |
| 4751 |
} else { |
} else { |
| 4752 |
!!!cp ('t149'); |
!!!cp ('t149'); |
| 4753 |
} |
} |
| 4757 |
!!!insert-element ('body',, $token); |
!!!insert-element ('body',, $token); |
| 4758 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 4759 |
## reprocess |
## reprocess |
| 4760 |
redo B; |
next B; |
| 4761 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 4762 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4763 |
!!!cp ('t149.1'); |
!!!cp ('t149.1'); |
| 4764 |
|
|
| 4765 |
## NOTE: As if <head> |
## NOTE: As if <head> |
| 4766 |
!!!create-element ($self->{head_element}, 'head',, $token); |
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
| 4767 |
$self->{open_elements}->[-1]->[0]->append_child |
$self->{open_elements}->[-1]->[0]->append_child |
| 4768 |
($self->{head_element}); |
($self->{head_element}); |
| 4769 |
#push @{$self->{open_elements}}, |
#push @{$self->{open_elements}}, |
| 4811 |
!!!insert-element ('body',, $token); |
!!!insert-element ('body',, $token); |
| 4812 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 4813 |
## NOTE: Reprocess. |
## NOTE: Reprocess. |
| 4814 |
redo B; |
next B; |
| 4815 |
} else { |
} else { |
| 4816 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 4817 |
} |
} |
| 4826 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
| 4827 |
|
|
| 4828 |
!!!next-token; |
!!!next-token; |
| 4829 |
redo B; |
next B; |
| 4830 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 4831 |
if ({ |
if ({ |
| 4832 |
caption => 1, col => 1, colgroup => 1, tbody => 1, |
caption => 1, col => 1, colgroup => 1, tbody => 1, |
| 4845 |
tag_name => $node->[0]->manakai_local_name, |
tag_name => $node->[0]->manakai_local_name, |
| 4846 |
line => $token->{line}, |
line => $token->{line}, |
| 4847 |
column => $token->{column}}; |
column => $token->{column}}; |
| 4848 |
redo B; |
next B; |
| 4849 |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
| 4850 |
!!!cp ('t152'); |
!!!cp ('t152'); |
| 4851 |
## ISSUE: This case can never be reached, maybe. |
## ISSUE: This case can never be reached, maybe. |
| 4855 |
|
|
| 4856 |
!!!cp ('t153'); |
!!!cp ('t153'); |
| 4857 |
!!!parse-error (type => 'start tag not allowed', |
!!!parse-error (type => 'start tag not allowed', |
| 4858 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 4859 |
## Ignore the token |
## Ignore the token |
| 4860 |
!!!nack ('t153.1'); |
!!!nack ('t153.1'); |
| 4861 |
!!!next-token; |
!!!next-token; |
| 4862 |
redo B; |
next B; |
| 4863 |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 4864 |
!!!parse-error (type => 'not closed:caption', token => $token); |
!!!parse-error (type => 'not closed', text => 'caption', |
| 4865 |
|
token => $token); |
| 4866 |
|
|
| 4867 |
## NOTE: As if </caption>. |
## NOTE: As if </caption>. |
| 4868 |
## have a table element in table scope |
## have a table element in table scope |
| 4882 |
|
|
| 4883 |
!!!cp ('t157'); |
!!!cp ('t157'); |
| 4884 |
!!!parse-error (type => 'start tag not allowed', |
!!!parse-error (type => 'start tag not allowed', |
| 4885 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 4886 |
## Ignore the token |
## Ignore the token |
| 4887 |
!!!nack ('t157.1'); |
!!!nack ('t157.1'); |
| 4888 |
!!!next-token; |
!!!next-token; |
| 4889 |
redo B; |
next B; |
| 4890 |
} # INSCOPE |
} # INSCOPE |
| 4891 |
|
|
| 4892 |
## generate implied end tags |
## generate implied end tags |
| 4899 |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
| 4900 |
!!!cp ('t159'); |
!!!cp ('t159'); |
| 4901 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 4902 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 4903 |
->manakai_local_name, |
->manakai_local_name, |
| 4904 |
token => $token); |
token => $token); |
| 4905 |
} else { |
} else { |
| 4914 |
|
|
| 4915 |
## reprocess |
## reprocess |
| 4916 |
!!!ack-later; |
!!!ack-later; |
| 4917 |
redo B; |
next B; |
| 4918 |
} else { |
} else { |
| 4919 |
!!!cp ('t161'); |
!!!cp ('t161'); |
| 4920 |
# |
# |
| 4941 |
} # INSCOPE |
} # INSCOPE |
| 4942 |
unless (defined $i) { |
unless (defined $i) { |
| 4943 |
!!!cp ('t165'); |
!!!cp ('t165'); |
| 4944 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4945 |
|
text => $token->{tag_name}, |
| 4946 |
|
token => $token); |
| 4947 |
## Ignore the token |
## Ignore the token |
| 4948 |
!!!next-token; |
!!!next-token; |
| 4949 |
redo B; |
next B; |
| 4950 |
} |
} |
| 4951 |
|
|
| 4952 |
## generate implied end tags |
## generate implied end tags |
| 4960 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 4961 |
!!!cp ('t167'); |
!!!cp ('t167'); |
| 4962 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 4963 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 4964 |
->manakai_local_name, |
->manakai_local_name, |
| 4965 |
token => $token); |
token => $token); |
| 4966 |
} else { |
} else { |
| 4974 |
$self->{insertion_mode} = IN_ROW_IM; |
$self->{insertion_mode} = IN_ROW_IM; |
| 4975 |
|
|
| 4976 |
!!!next-token; |
!!!next-token; |
| 4977 |
redo B; |
next B; |
| 4978 |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 4979 |
!!!cp ('t169'); |
!!!cp ('t169'); |
| 4980 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4981 |
|
text => $token->{tag_name}, token => $token); |
| 4982 |
## Ignore the token |
## Ignore the token |
| 4983 |
!!!next-token; |
!!!next-token; |
| 4984 |
redo B; |
next B; |
| 4985 |
} else { |
} else { |
| 4986 |
!!!cp ('t170'); |
!!!cp ('t170'); |
| 4987 |
# |
# |
| 5005 |
|
|
| 5006 |
!!!cp ('t173'); |
!!!cp ('t173'); |
| 5007 |
!!!parse-error (type => 'unmatched end tag', |
!!!parse-error (type => 'unmatched end tag', |
| 5008 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 5009 |
## Ignore the token |
## Ignore the token |
| 5010 |
!!!next-token; |
!!!next-token; |
| 5011 |
redo B; |
next B; |
| 5012 |
} # INSCOPE |
} # INSCOPE |
| 5013 |
|
|
| 5014 |
## generate implied end tags |
## generate implied end tags |
| 5021 |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
| 5022 |
!!!cp ('t175'); |
!!!cp ('t175'); |
| 5023 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5024 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5025 |
->manakai_local_name, |
->manakai_local_name, |
| 5026 |
token => $token); |
token => $token); |
| 5027 |
} else { |
} else { |
| 5035 |
$self->{insertion_mode} = IN_TABLE_IM; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 5036 |
|
|
| 5037 |
!!!next-token; |
!!!next-token; |
| 5038 |
redo B; |
next B; |
| 5039 |
} elsif ($self->{insertion_mode} == IN_CELL_IM) { |
} elsif ($self->{insertion_mode} == IN_CELL_IM) { |
| 5040 |
!!!cp ('t177'); |
!!!cp ('t177'); |
| 5041 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5042 |
|
text => $token->{tag_name}, token => $token); |
| 5043 |
## Ignore the token |
## Ignore the token |
| 5044 |
!!!next-token; |
!!!next-token; |
| 5045 |
redo B; |
next B; |
| 5046 |
} else { |
} else { |
| 5047 |
!!!cp ('t178'); |
!!!cp ('t178'); |
| 5048 |
# |
# |
| 5067 |
$token = {type => END_TAG_TOKEN, tag_name => $tn, |
$token = {type => END_TAG_TOKEN, tag_name => $tn, |
| 5068 |
line => $token->{line}, |
line => $token->{line}, |
| 5069 |
column => $token->{column}}; |
column => $token->{column}}; |
| 5070 |
redo B; |
next B; |
| 5071 |
} elsif ($node->[1] & TABLE_CELL_EL) { |
} elsif ($node->[1] & TABLE_CELL_EL) { |
| 5072 |
!!!cp ('t180'); |
!!!cp ('t180'); |
| 5073 |
$tn = $node->[0]->manakai_local_name; |
$tn = $node->[0]->manakai_local_name; |
| 5082 |
|
|
| 5083 |
!!!cp ('t182'); |
!!!cp ('t182'); |
| 5084 |
!!!parse-error (type => 'unmatched end tag', |
!!!parse-error (type => 'unmatched end tag', |
| 5085 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 5086 |
## Ignore the token |
## Ignore the token |
| 5087 |
!!!next-token; |
!!!next-token; |
| 5088 |
redo B; |
next B; |
| 5089 |
} # INSCOPE |
} # INSCOPE |
| 5090 |
} elsif ($token->{tag_name} eq 'table' and |
} elsif ($token->{tag_name} eq 'table' and |
| 5091 |
$self->{insertion_mode} == IN_CAPTION_IM) { |
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 5092 |
!!!parse-error (type => 'not closed:caption', token => $token); |
!!!parse-error (type => 'not closed', text => 'caption', |
| 5093 |
|
token => $token); |
| 5094 |
|
|
| 5095 |
## As if </caption> |
## As if </caption> |
| 5096 |
## have a table element in table scope |
## have a table element in table scope |
| 5108 |
} # INSCOPE |
} # INSCOPE |
| 5109 |
unless (defined $i) { |
unless (defined $i) { |
| 5110 |
!!!cp ('t186'); |
!!!cp ('t186'); |
| 5111 |
!!!parse-error (type => 'unmatched end tag:caption', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5112 |
|
text => 'caption', token => $token); |
| 5113 |
## Ignore the token |
## Ignore the token |
| 5114 |
!!!next-token; |
!!!next-token; |
| 5115 |
redo B; |
next B; |
| 5116 |
} |
} |
| 5117 |
|
|
| 5118 |
## generate implied end tags |
## generate implied end tags |
| 5124 |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
| 5125 |
!!!cp ('t188'); |
!!!cp ('t188'); |
| 5126 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5127 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5128 |
->manakai_local_name, |
->manakai_local_name, |
| 5129 |
token => $token); |
token => $token); |
| 5130 |
} else { |
} else { |
| 5138 |
$self->{insertion_mode} = IN_TABLE_IM; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 5139 |
|
|
| 5140 |
## reprocess |
## reprocess |
| 5141 |
redo B; |
next B; |
| 5142 |
} elsif ({ |
} elsif ({ |
| 5143 |
body => 1, col => 1, colgroup => 1, html => 1, |
body => 1, col => 1, colgroup => 1, html => 1, |
| 5144 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5145 |
if ($self->{insertion_mode} & BODY_TABLE_IMS) { |
if ($self->{insertion_mode} & BODY_TABLE_IMS) { |
| 5146 |
!!!cp ('t190'); |
!!!cp ('t190'); |
| 5147 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5148 |
|
text => $token->{tag_name}, token => $token); |
| 5149 |
## Ignore the token |
## Ignore the token |
| 5150 |
!!!next-token; |
!!!next-token; |
| 5151 |
redo B; |
next B; |
| 5152 |
} else { |
} else { |
| 5153 |
!!!cp ('t191'); |
!!!cp ('t191'); |
| 5154 |
# |
# |
| 5159 |
}->{$token->{tag_name}} and |
}->{$token->{tag_name}} and |
| 5160 |
$self->{insertion_mode} == IN_CAPTION_IM) { |
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 5161 |
!!!cp ('t192'); |
!!!cp ('t192'); |
| 5162 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5163 |
|
text => $token->{tag_name}, token => $token); |
| 5164 |
## Ignore the token |
## Ignore the token |
| 5165 |
!!!next-token; |
!!!next-token; |
| 5166 |
redo B; |
next B; |
| 5167 |
} else { |
} else { |
| 5168 |
!!!cp ('t193'); |
!!!cp ('t193'); |
| 5169 |
# |
# |
| 5194 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 5195 |
!!!cp ('t194'); |
!!!cp ('t194'); |
| 5196 |
!!!next-token; |
!!!next-token; |
| 5197 |
redo B; |
next B; |
| 5198 |
} else { |
} else { |
| 5199 |
!!!cp ('t195'); |
!!!cp ('t195'); |
| 5200 |
} |
} |
| 5201 |
} |
} |
| 5202 |
|
|
| 5203 |
!!!parse-error (type => 'in table:#character', token => $token); |
!!!parse-error (type => 'in table:#text', token => $token); |
| 5204 |
|
|
| 5205 |
## As if in body, but insert into foster parent element |
## As if in body, but insert into foster parent element |
| 5206 |
## ISSUE: Spec says that "whenever a node would be inserted |
## ISSUE: Spec says that "whenever a node would be inserted |
| 5249 |
} |
} |
| 5250 |
|
|
| 5251 |
!!!next-token; |
!!!next-token; |
| 5252 |
redo B; |
next B; |
| 5253 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 5254 |
if ({ |
if ({ |
| 5255 |
tr => ($self->{insertion_mode} != IN_ROW_IM), |
tr => ($self->{insertion_mode} != IN_ROW_IM), |
| 5256 |
th => 1, td => 1, |
th => 1, td => 1, |
| 5257 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5258 |
if ($self->{insertion_mode} == IN_TABLE_IM) { |
if ($self->{insertion_mode} == IN_TABLE_IM) { |
| 5259 |
## Clear back to table context |
## Clear back to table context |
| 5260 |
while (not ($self->{open_elements}->[-1]->[1] |
while (not ($self->{open_elements}->[-1]->[1] |
| 5261 |
& TABLE_SCOPING_EL)) { |
& TABLE_SCOPING_EL)) { |
| 5262 |
!!!cp ('t201'); |
!!!cp ('t201'); |
| 5263 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5264 |
} |
} |
| 5265 |
|
|
| 5266 |
!!!insert-element ('tbody',, $token); |
!!!insert-element ('tbody',, $token); |
| 5267 |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 5268 |
## reprocess in the "in table body" insertion mode... |
## reprocess in the "in table body" insertion mode... |
| 5269 |
} |
} |
| 5270 |
|
|
| 5271 |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
| 5272 |
unless ($token->{tag_name} eq 'tr') { |
unless ($token->{tag_name} eq 'tr') { |
| 5273 |
!!!cp ('t202'); |
!!!cp ('t202'); |
| 5274 |
!!!parse-error (type => 'missing start tag:tr', token => $token); |
!!!parse-error (type => 'missing start tag:tr', token => $token); |
| 5275 |
} |
} |
| 5276 |
|
|
| 5277 |
## Clear back to table body context |
## Clear back to table body context |
| 5278 |
while (not ($self->{open_elements}->[-1]->[1] |
while (not ($self->{open_elements}->[-1]->[1] |
| 5279 |
& TABLE_ROWS_SCOPING_EL)) { |
& TABLE_ROWS_SCOPING_EL)) { |
| 5280 |
!!!cp ('t203'); |
!!!cp ('t203'); |
| 5281 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
| 5282 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5283 |
} |
} |
| 5284 |
|
|
| 5285 |
$self->{insertion_mode} = IN_ROW_IM; |
$self->{insertion_mode} = IN_ROW_IM; |
| 5286 |
if ($token->{tag_name} eq 'tr') { |
if ($token->{tag_name} eq 'tr') { |
| 5288 |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5289 |
!!!nack ('t204'); |
!!!nack ('t204'); |
| 5290 |
!!!next-token; |
!!!next-token; |
| 5291 |
redo B; |
next B; |
| 5292 |
} else { |
} else { |
| 5293 |
!!!cp ('t205'); |
!!!cp ('t205'); |
| 5294 |
!!!insert-element ('tr',, $token); |
!!!insert-element ('tr',, $token); |
| 5312 |
|
|
| 5313 |
!!!nack ('t207.1'); |
!!!nack ('t207.1'); |
| 5314 |
!!!next-token; |
!!!next-token; |
| 5315 |
redo B; |
next B; |
| 5316 |
} elsif ({ |
} elsif ({ |
| 5317 |
caption => 1, col => 1, colgroup => 1, |
caption => 1, col => 1, colgroup => 1, |
| 5318 |
tbody => 1, tfoot => 1, thead => 1, |
tbody => 1, tfoot => 1, thead => 1, |
| 5336 |
unless (defined $i) { |
unless (defined $i) { |
| 5337 |
!!!cp ('t210'); |
!!!cp ('t210'); |
| 5338 |
## TODO: This type is wrong. |
## TODO: This type is wrong. |
| 5339 |
!!!parse-error (type => 'unmacthed end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmacthed end tag', |
| 5340 |
|
text => $token->{tag_name}, token => $token); |
| 5341 |
## Ignore the token |
## Ignore the token |
| 5342 |
!!!nack ('t210.1'); |
!!!nack ('t210.1'); |
| 5343 |
!!!next-token; |
!!!next-token; |
| 5344 |
redo B; |
next B; |
| 5345 |
} |
} |
| 5346 |
|
|
| 5347 |
## Clear back to table row context |
## Clear back to table row context |
| 5358 |
!!!cp ('t212'); |
!!!cp ('t212'); |
| 5359 |
## reprocess |
## reprocess |
| 5360 |
!!!ack-later; |
!!!ack-later; |
| 5361 |
redo B; |
next B; |
| 5362 |
} else { |
} else { |
| 5363 |
!!!cp ('t213'); |
!!!cp ('t213'); |
| 5364 |
## reprocess in the "in table body" insertion mode... |
## reprocess in the "in table body" insertion mode... |
| 5381 |
} # INSCOPE |
} # INSCOPE |
| 5382 |
unless (defined $i) { |
unless (defined $i) { |
| 5383 |
!!!cp ('t216'); |
!!!cp ('t216'); |
| 5384 |
## TODO: This erorr type ios wrong. |
## TODO: This erorr type is wrong. |
| 5385 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5386 |
|
text => $token->{tag_name}, token => $token); |
| 5387 |
## Ignore the token |
## Ignore the token |
| 5388 |
!!!nack ('t216.1'); |
!!!nack ('t216.1'); |
| 5389 |
!!!next-token; |
!!!next-token; |
| 5390 |
redo B; |
next B; |
| 5391 |
} |
} |
| 5392 |
|
|
| 5393 |
## Clear back to table body context |
## Clear back to table body context |
| 5425 |
$self->{insertion_mode} = IN_COLUMN_GROUP_IM; |
$self->{insertion_mode} = IN_COLUMN_GROUP_IM; |
| 5426 |
## reprocess |
## reprocess |
| 5427 |
!!!ack-later; |
!!!ack-later; |
| 5428 |
redo B; |
next B; |
| 5429 |
} elsif ({ |
} elsif ({ |
| 5430 |
caption => 1, |
caption => 1, |
| 5431 |
colgroup => 1, |
colgroup => 1, |
| 5452 |
}->{$token->{tag_name}}; |
}->{$token->{tag_name}}; |
| 5453 |
!!!next-token; |
!!!next-token; |
| 5454 |
!!!nack ('t220.1'); |
!!!nack ('t220.1'); |
| 5455 |
redo B; |
next B; |
| 5456 |
} else { |
} else { |
| 5457 |
die "$0: in table: <>: $token->{tag_name}"; |
die "$0: in table: <>: $token->{tag_name}"; |
| 5458 |
} |
} |
| 5459 |
} elsif ($token->{tag_name} eq 'table') { |
} elsif ($token->{tag_name} eq 'table') { |
| 5460 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5461 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5462 |
->manakai_local_name, |
->manakai_local_name, |
| 5463 |
token => $token); |
token => $token); |
| 5464 |
|
|
| 5479 |
unless (defined $i) { |
unless (defined $i) { |
| 5480 |
!!!cp ('t223'); |
!!!cp ('t223'); |
| 5481 |
## TODO: The following is wrong, maybe. |
## TODO: The following is wrong, maybe. |
| 5482 |
!!!parse-error (type => 'unmatched end tag:table', token => $token); |
!!!parse-error (type => 'unmatched end tag', text => 'table', |
| 5483 |
|
token => $token); |
| 5484 |
## Ignore tokens </table><table> |
## Ignore tokens </table><table> |
| 5485 |
!!!nack ('t223.1'); |
!!!nack ('t223.1'); |
| 5486 |
!!!next-token; |
!!!next-token; |
| 5487 |
redo B; |
next B; |
| 5488 |
} |
} |
| 5489 |
|
|
| 5490 |
## TODO: Followings are removed from the latest spec. |
## TODO: Followings are removed from the latest spec. |
| 5491 |
## generate implied end tags |
## generate implied end tags |
| 5492 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 5493 |
!!!cp ('t224'); |
!!!cp ('t224'); |
| 5498 |
!!!cp ('t225'); |
!!!cp ('t225'); |
| 5499 |
## NOTE: |<table><tr><table>| |
## NOTE: |<table><tr><table>| |
| 5500 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5501 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5502 |
->manakai_local_name, |
->manakai_local_name, |
| 5503 |
token => $token); |
token => $token); |
| 5504 |
} else { |
} else { |
| 5512 |
|
|
| 5513 |
## reprocess |
## reprocess |
| 5514 |
!!!ack-later; |
!!!ack-later; |
| 5515 |
redo B; |
next B; |
| 5516 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($token->{tag_name} eq 'style') { |
| 5517 |
if (not $open_tables->[-1]->[1]) { # tainted |
if (not $open_tables->[-1]->[1]) { # tainted |
| 5518 |
!!!cp ('t227.8'); |
!!!cp ('t227.8'); |
| 5519 |
## NOTE: This is a "as if in head" code clone. |
## NOTE: This is a "as if in head" code clone. |
| 5520 |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 5521 |
redo B; |
next B; |
| 5522 |
} else { |
} else { |
| 5523 |
!!!cp ('t227.7'); |
!!!cp ('t227.7'); |
| 5524 |
# |
# |
| 5528 |
!!!cp ('t227.6'); |
!!!cp ('t227.6'); |
| 5529 |
## NOTE: This is a "as if in head" code clone. |
## NOTE: This is a "as if in head" code clone. |
| 5530 |
$script_start_tag->(); |
$script_start_tag->(); |
| 5531 |
redo B; |
next B; |
| 5532 |
} else { |
} else { |
| 5533 |
!!!cp ('t227.5'); |
!!!cp ('t227.5'); |
| 5534 |
# |
# |
| 5539 |
my $type = lc $token->{attributes}->{type}->{value}; |
my $type = lc $token->{attributes}->{type}->{value}; |
| 5540 |
if ($type eq 'hidden') { |
if ($type eq 'hidden') { |
| 5541 |
!!!cp ('t227.3'); |
!!!cp ('t227.3'); |
| 5542 |
!!!parse-error (type => 'in table:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in table', |
| 5543 |
|
text => $token->{tag_name}, token => $token); |
| 5544 |
|
|
| 5545 |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5546 |
|
|
| 5550 |
|
|
| 5551 |
!!!next-token; |
!!!next-token; |
| 5552 |
!!!ack ('t227.2.1'); |
!!!ack ('t227.2.1'); |
| 5553 |
redo B; |
next B; |
| 5554 |
} else { |
} else { |
| 5555 |
!!!cp ('t227.2'); |
!!!cp ('t227.2'); |
| 5556 |
# |
# |
| 5568 |
# |
# |
| 5569 |
} |
} |
| 5570 |
|
|
| 5571 |
!!!parse-error (type => 'in table:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in table', text => $token->{tag_name}, |
| 5572 |
|
token => $token); |
| 5573 |
|
|
| 5574 |
$insert = $insert_to_foster; |
$insert = $insert_to_foster; |
| 5575 |
# |
# |
| 5591 |
} # INSCOPE |
} # INSCOPE |
| 5592 |
unless (defined $i) { |
unless (defined $i) { |
| 5593 |
!!!cp ('t230'); |
!!!cp ('t230'); |
| 5594 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5595 |
|
text => $token->{tag_name}, token => $token); |
| 5596 |
## Ignore the token |
## Ignore the token |
| 5597 |
!!!nack ('t230.1'); |
!!!nack ('t230.1'); |
| 5598 |
!!!next-token; |
!!!next-token; |
| 5599 |
redo B; |
next B; |
| 5600 |
} else { |
} else { |
| 5601 |
!!!cp ('t232'); |
!!!cp ('t232'); |
| 5602 |
} |
} |
| 5613 |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 5614 |
!!!next-token; |
!!!next-token; |
| 5615 |
!!!nack ('t231.1'); |
!!!nack ('t231.1'); |
| 5616 |
redo B; |
next B; |
| 5617 |
} elsif ($token->{tag_name} eq 'table') { |
} elsif ($token->{tag_name} eq 'table') { |
| 5618 |
if ($self->{insertion_mode} == IN_ROW_IM) { |
if ($self->{insertion_mode} == IN_ROW_IM) { |
| 5619 |
## As if </tr> |
## As if </tr> |
| 5633 |
unless (defined $i) { |
unless (defined $i) { |
| 5634 |
!!!cp ('t235'); |
!!!cp ('t235'); |
| 5635 |
## TODO: The following is wrong. |
## TODO: The following is wrong. |
| 5636 |
!!!parse-error (type => 'unmatched end tag:'.$token->{type}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5637 |
|
text => $token->{type}, token => $token); |
| 5638 |
## Ignore the token |
## Ignore the token |
| 5639 |
!!!nack ('t236.1'); |
!!!nack ('t236.1'); |
| 5640 |
!!!next-token; |
!!!next-token; |
| 5641 |
redo B; |
next B; |
| 5642 |
} |
} |
| 5643 |
|
|
| 5644 |
## Clear back to table row context |
## Clear back to table row context |
| 5670 |
} # INSCOPE |
} # INSCOPE |
| 5671 |
unless (defined $i) { |
unless (defined $i) { |
| 5672 |
!!!cp ('t239'); |
!!!cp ('t239'); |
| 5673 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5674 |
|
text => $token->{tag_name}, token => $token); |
| 5675 |
## Ignore the token |
## Ignore the token |
| 5676 |
!!!nack ('t239.1'); |
!!!nack ('t239.1'); |
| 5677 |
!!!next-token; |
!!!next-token; |
| 5678 |
redo B; |
next B; |
| 5679 |
} |
} |
| 5680 |
|
|
| 5681 |
## Clear back to table body context |
## Clear back to table body context |
| 5717 |
} # INSCOPE |
} # INSCOPE |
| 5718 |
unless (defined $i) { |
unless (defined $i) { |
| 5719 |
!!!cp ('t243'); |
!!!cp ('t243'); |
| 5720 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5721 |
|
text => $token->{tag_name}, token => $token); |
| 5722 |
## Ignore the token |
## Ignore the token |
| 5723 |
!!!nack ('t243.1'); |
!!!nack ('t243.1'); |
| 5724 |
!!!next-token; |
!!!next-token; |
| 5725 |
redo B; |
next B; |
| 5726 |
} |
} |
| 5727 |
|
|
| 5728 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 5731 |
$self->_reset_insertion_mode; |
$self->_reset_insertion_mode; |
| 5732 |
|
|
| 5733 |
!!!next-token; |
!!!next-token; |
| 5734 |
redo B; |
next B; |
| 5735 |
} elsif ({ |
} elsif ({ |
| 5736 |
tbody => 1, tfoot => 1, thead => 1, |
tbody => 1, tfoot => 1, thead => 1, |
| 5737 |
}->{$token->{tag_name}} and |
}->{$token->{tag_name}} and |
| 5752 |
} # INSCOPE |
} # INSCOPE |
| 5753 |
unless (defined $i) { |
unless (defined $i) { |
| 5754 |
!!!cp ('t249'); |
!!!cp ('t249'); |
| 5755 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5756 |
|
text => $token->{tag_name}, token => $token); |
| 5757 |
## Ignore the token |
## Ignore the token |
| 5758 |
!!!nack ('t249.1'); |
!!!nack ('t249.1'); |
| 5759 |
!!!next-token; |
!!!next-token; |
| 5760 |
redo B; |
next B; |
| 5761 |
} |
} |
| 5762 |
|
|
| 5763 |
## As if </tr> |
## As if </tr> |
| 5776 |
} # INSCOPE |
} # INSCOPE |
| 5777 |
unless (defined $i) { |
unless (defined $i) { |
| 5778 |
!!!cp ('t252'); |
!!!cp ('t252'); |
| 5779 |
!!!parse-error (type => 'unmatched end tag:tr', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5780 |
|
text => 'tr', token => $token); |
| 5781 |
## Ignore the token |
## Ignore the token |
| 5782 |
!!!nack ('t252.1'); |
!!!nack ('t252.1'); |
| 5783 |
!!!next-token; |
!!!next-token; |
| 5784 |
redo B; |
next B; |
| 5785 |
} |
} |
| 5786 |
|
|
| 5787 |
## Clear back to table row context |
## Clear back to table row context |
| 5812 |
} # INSCOPE |
} # INSCOPE |
| 5813 |
unless (defined $i) { |
unless (defined $i) { |
| 5814 |
!!!cp ('t256'); |
!!!cp ('t256'); |
| 5815 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5816 |
|
text => $token->{tag_name}, token => $token); |
| 5817 |
## Ignore the token |
## Ignore the token |
| 5818 |
!!!nack ('t256.1'); |
!!!nack ('t256.1'); |
| 5819 |
!!!next-token; |
!!!next-token; |
| 5820 |
redo B; |
next B; |
| 5821 |
} |
} |
| 5822 |
|
|
| 5823 |
## Clear back to table body context |
## Clear back to table body context |
| 5832 |
$self->{insertion_mode} = IN_TABLE_IM; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 5833 |
!!!nack ('t257.1'); |
!!!nack ('t257.1'); |
| 5834 |
!!!next-token; |
!!!next-token; |
| 5835 |
redo B; |
next B; |
| 5836 |
} elsif ({ |
} elsif ({ |
| 5837 |
body => 1, caption => 1, col => 1, colgroup => 1, |
body => 1, caption => 1, col => 1, colgroup => 1, |
| 5838 |
html => 1, td => 1, th => 1, |
html => 1, td => 1, th => 1, |
| 5840 |
tbody => 1, tfoot => 1, thead => 1, # $self->{insertion_mode} == IN_TABLE_IM |
tbody => 1, tfoot => 1, thead => 1, # $self->{insertion_mode} == IN_TABLE_IM |
| 5841 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5842 |
!!!cp ('t258'); |
!!!cp ('t258'); |
| 5843 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5844 |
|
text => $token->{tag_name}, token => $token); |
| 5845 |
## Ignore the token |
## Ignore the token |
| 5846 |
!!!nack ('t258.1'); |
!!!nack ('t258.1'); |
| 5847 |
!!!next-token; |
!!!next-token; |
| 5848 |
redo B; |
next B; |
| 5849 |
} else { |
} else { |
| 5850 |
!!!cp ('t259'); |
!!!cp ('t259'); |
| 5851 |
!!!parse-error (type => 'in table:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in table:/', |
| 5852 |
|
text => $token->{tag_name}, token => $token); |
| 5853 |
|
|
| 5854 |
$insert = $insert_to_foster; |
$insert = $insert_to_foster; |
| 5855 |
# |
# |
| 5877 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 5878 |
!!!cp ('t260'); |
!!!cp ('t260'); |
| 5879 |
!!!next-token; |
!!!next-token; |
| 5880 |
redo B; |
next B; |
| 5881 |
} |
} |
| 5882 |
} |
} |
| 5883 |
|
|
| 5890 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5891 |
!!!ack ('t262.1'); |
!!!ack ('t262.1'); |
| 5892 |
!!!next-token; |
!!!next-token; |
| 5893 |
redo B; |
next B; |
| 5894 |
} else { |
} else { |
| 5895 |
!!!cp ('t263'); |
!!!cp ('t263'); |
| 5896 |
# |
# |
| 5899 |
if ($token->{tag_name} eq 'colgroup') { |
if ($token->{tag_name} eq 'colgroup') { |
| 5900 |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
| 5901 |
!!!cp ('t264'); |
!!!cp ('t264'); |
| 5902 |
!!!parse-error (type => 'unmatched end tag:colgroup', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5903 |
|
text => 'colgroup', token => $token); |
| 5904 |
## Ignore the token |
## Ignore the token |
| 5905 |
!!!next-token; |
!!!next-token; |
| 5906 |
redo B; |
next B; |
| 5907 |
} else { |
} else { |
| 5908 |
!!!cp ('t265'); |
!!!cp ('t265'); |
| 5909 |
pop @{$self->{open_elements}}; # colgroup |
pop @{$self->{open_elements}}; # colgroup |
| 5910 |
$self->{insertion_mode} = IN_TABLE_IM; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 5911 |
!!!next-token; |
!!!next-token; |
| 5912 |
redo B; |
next B; |
| 5913 |
} |
} |
| 5914 |
} elsif ($token->{tag_name} eq 'col') { |
} elsif ($token->{tag_name} eq 'col') { |
| 5915 |
!!!cp ('t266'); |
!!!cp ('t266'); |
| 5916 |
!!!parse-error (type => 'unmatched end tag:col', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5917 |
|
text => 'col', token => $token); |
| 5918 |
## Ignore the token |
## Ignore the token |
| 5919 |
!!!next-token; |
!!!next-token; |
| 5920 |
redo B; |
next B; |
| 5921 |
} else { |
} else { |
| 5922 |
!!!cp ('t267'); |
!!!cp ('t267'); |
| 5923 |
# |
# |
| 5934 |
pop @{$self->{open_elements}}; # colgroup |
pop @{$self->{open_elements}}; # colgroup |
| 5935 |
$self->{insertion_mode} = IN_TABLE_IM; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 5936 |
## Reprocess. |
## Reprocess. |
| 5937 |
redo B; |
next B; |
| 5938 |
} |
} |
| 5939 |
} else { |
} else { |
| 5940 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 5944 |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
| 5945 |
!!!cp ('t269'); |
!!!cp ('t269'); |
| 5946 |
## TODO: Wrong error type? |
## TODO: Wrong error type? |
| 5947 |
!!!parse-error (type => 'unmatched end tag:colgroup', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5948 |
|
text => 'colgroup', token => $token); |
| 5949 |
## Ignore the token |
## Ignore the token |
| 5950 |
!!!nack ('t269.1'); |
!!!nack ('t269.1'); |
| 5951 |
!!!next-token; |
!!!next-token; |
| 5952 |
redo B; |
next B; |
| 5953 |
} else { |
} else { |
| 5954 |
!!!cp ('t270'); |
!!!cp ('t270'); |
| 5955 |
pop @{$self->{open_elements}}; # colgroup |
pop @{$self->{open_elements}}; # colgroup |
| 5956 |
$self->{insertion_mode} = IN_TABLE_IM; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 5957 |
!!!ack-later; |
!!!ack-later; |
| 5958 |
## reprocess |
## reprocess |
| 5959 |
redo B; |
next B; |
| 5960 |
} |
} |
| 5961 |
} elsif ($self->{insertion_mode} & SELECT_IMS) { |
} elsif ($self->{insertion_mode} & SELECT_IMS) { |
| 5962 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 5963 |
!!!cp ('t271'); |
!!!cp ('t271'); |
| 5964 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
| 5965 |
!!!next-token; |
!!!next-token; |
| 5966 |
redo B; |
next B; |
| 5967 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 5968 |
if ($token->{tag_name} eq 'option') { |
if ($token->{tag_name} eq 'option') { |
| 5969 |
if ($self->{open_elements}->[-1]->[1] & OPTION_EL) { |
if ($self->{open_elements}->[-1]->[1] & OPTION_EL) { |
| 5977 |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5978 |
!!!nack ('t273.1'); |
!!!nack ('t273.1'); |
| 5979 |
!!!next-token; |
!!!next-token; |
| 5980 |
redo B; |
next B; |
| 5981 |
} elsif ($token->{tag_name} eq 'optgroup') { |
} elsif ($token->{tag_name} eq 'optgroup') { |
| 5982 |
if ($self->{open_elements}->[-1]->[1] & OPTION_EL) { |
if ($self->{open_elements}->[-1]->[1] & OPTION_EL) { |
| 5983 |
!!!cp ('t274'); |
!!!cp ('t274'); |
| 5998 |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5999 |
!!!nack ('t277.1'); |
!!!nack ('t277.1'); |
| 6000 |
!!!next-token; |
!!!next-token; |
| 6001 |
redo B; |
next B; |
| 6002 |
} elsif ($token->{tag_name} eq 'select' or |
} elsif ({ |
| 6003 |
$token->{tag_name} eq 'input' or |
select => 1, input => 1, textarea => 1, |
| 6004 |
|
}->{$token->{tag_name}} or |
| 6005 |
($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
| 6006 |
{ |
{ |
| 6007 |
caption => 1, table => 1, |
caption => 1, table => 1, |
| 6009 |
tr => 1, td => 1, th => 1, |
tr => 1, td => 1, th => 1, |
| 6010 |
}->{$token->{tag_name}})) { |
}->{$token->{tag_name}})) { |
| 6011 |
## TODO: The type below is not good - <select> is replaced by </select> |
## TODO: The type below is not good - <select> is replaced by </select> |
| 6012 |
!!!parse-error (type => 'not closed:select', token => $token); |
!!!parse-error (type => 'not closed', text => 'select', |
| 6013 |
|
token => $token); |
| 6014 |
## NOTE: As if the token were </select> (<select> case) or |
## NOTE: As if the token were </select> (<select> case) or |
| 6015 |
## as if there were </select> (otherwise). |
## as if there were </select> (otherwise). |
| 6016 |
## have an element in table scope |
## have an element in table scope |
| 6028 |
} # INSCOPE |
} # INSCOPE |
| 6029 |
unless (defined $i) { |
unless (defined $i) { |
| 6030 |
!!!cp ('t280'); |
!!!cp ('t280'); |
| 6031 |
!!!parse-error (type => 'unmatched end tag:select', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6032 |
|
text => 'select', token => $token); |
| 6033 |
## Ignore the token |
## Ignore the token |
| 6034 |
!!!nack ('t280.1'); |
!!!nack ('t280.1'); |
| 6035 |
!!!next-token; |
!!!next-token; |
| 6036 |
redo B; |
next B; |
| 6037 |
} |
} |
| 6038 |
|
|
| 6039 |
!!!cp ('t281'); |
!!!cp ('t281'); |
| 6044 |
if ($token->{tag_name} eq 'select') { |
if ($token->{tag_name} eq 'select') { |
| 6045 |
!!!nack ('t281.2'); |
!!!nack ('t281.2'); |
| 6046 |
!!!next-token; |
!!!next-token; |
| 6047 |
redo B; |
next B; |
| 6048 |
} else { |
} else { |
| 6049 |
!!!cp ('t281.1'); |
!!!cp ('t281.1'); |
| 6050 |
!!!ack-later; |
!!!ack-later; |
| 6051 |
## Reprocess the token. |
## Reprocess the token. |
| 6052 |
redo B; |
next B; |
| 6053 |
} |
} |
| 6054 |
} else { |
} else { |
| 6055 |
!!!cp ('t282'); |
!!!cp ('t282'); |
| 6056 |
!!!parse-error (type => 'in select:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in select', |
| 6057 |
|
text => $token->{tag_name}, token => $token); |
| 6058 |
## Ignore the token |
## Ignore the token |
| 6059 |
!!!nack ('t282.1'); |
!!!nack ('t282.1'); |
| 6060 |
!!!next-token; |
!!!next-token; |
| 6061 |
redo B; |
next B; |
| 6062 |
} |
} |
| 6063 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 6064 |
if ($token->{tag_name} eq 'optgroup') { |
if ($token->{tag_name} eq 'optgroup') { |
| 6072 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 6073 |
} else { |
} else { |
| 6074 |
!!!cp ('t285'); |
!!!cp ('t285'); |
| 6075 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6076 |
|
text => $token->{tag_name}, token => $token); |
| 6077 |
## Ignore the token |
## Ignore the token |
| 6078 |
} |
} |
| 6079 |
!!!nack ('t285.1'); |
!!!nack ('t285.1'); |
| 6080 |
!!!next-token; |
!!!next-token; |
| 6081 |
redo B; |
next B; |
| 6082 |
} elsif ($token->{tag_name} eq 'option') { |
} elsif ($token->{tag_name} eq 'option') { |
| 6083 |
if ($self->{open_elements}->[-1]->[1] & OPTION_EL) { |
if ($self->{open_elements}->[-1]->[1] & OPTION_EL) { |
| 6084 |
!!!cp ('t286'); |
!!!cp ('t286'); |
| 6085 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 6086 |
} else { |
} else { |
| 6087 |
!!!cp ('t287'); |
!!!cp ('t287'); |
| 6088 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6089 |
|
text => $token->{tag_name}, token => $token); |
| 6090 |
## Ignore the token |
## Ignore the token |
| 6091 |
} |
} |
| 6092 |
!!!nack ('t287.1'); |
!!!nack ('t287.1'); |
| 6093 |
!!!next-token; |
!!!next-token; |
| 6094 |
redo B; |
next B; |
| 6095 |
} elsif ($token->{tag_name} eq 'select') { |
} elsif ($token->{tag_name} eq 'select') { |
| 6096 |
## have an element in table scope |
## have an element in table scope |
| 6097 |
my $i; |
my $i; |
| 6108 |
} # INSCOPE |
} # INSCOPE |
| 6109 |
unless (defined $i) { |
unless (defined $i) { |
| 6110 |
!!!cp ('t290'); |
!!!cp ('t290'); |
| 6111 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6112 |
|
text => $token->{tag_name}, token => $token); |
| 6113 |
## Ignore the token |
## Ignore the token |
| 6114 |
!!!nack ('t290.1'); |
!!!nack ('t290.1'); |
| 6115 |
!!!next-token; |
!!!next-token; |
| 6116 |
redo B; |
next B; |
| 6117 |
} |
} |
| 6118 |
|
|
| 6119 |
!!!cp ('t291'); |
!!!cp ('t291'); |
| 6123 |
|
|
| 6124 |
!!!nack ('t291.1'); |
!!!nack ('t291.1'); |
| 6125 |
!!!next-token; |
!!!next-token; |
| 6126 |
redo B; |
next B; |
| 6127 |
} elsif ($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
} elsif ($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
| 6128 |
{ |
{ |
| 6129 |
caption => 1, table => 1, tbody => 1, |
caption => 1, table => 1, tbody => 1, |
| 6130 |
tfoot => 1, thead => 1, tr => 1, td => 1, th => 1, |
tfoot => 1, thead => 1, tr => 1, td => 1, th => 1, |
| 6131 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6132 |
## TODO: The following is wrong? |
## TODO: The following is wrong? |
| 6133 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6134 |
|
text => $token->{tag_name}, token => $token); |
| 6135 |
|
|
| 6136 |
## have an element in table scope |
## have an element in table scope |
| 6137 |
my $i; |
my $i; |
| 6151 |
## Ignore the token |
## Ignore the token |
| 6152 |
!!!nack ('t294.1'); |
!!!nack ('t294.1'); |
| 6153 |
!!!next-token; |
!!!next-token; |
| 6154 |
redo B; |
next B; |
| 6155 |
} |
} |
| 6156 |
|
|
| 6157 |
## As if </select> |
## As if </select> |
| 6172 |
unless (defined $i) { |
unless (defined $i) { |
| 6173 |
!!!cp ('t297'); |
!!!cp ('t297'); |
| 6174 |
## TODO: The following error type is correct? |
## TODO: The following error type is correct? |
| 6175 |
!!!parse-error (type => 'unmatched end tag:select', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6176 |
|
text => 'select', token => $token); |
| 6177 |
## Ignore the </select> token |
## Ignore the </select> token |
| 6178 |
!!!nack ('t297.1'); |
!!!nack ('t297.1'); |
| 6179 |
!!!next-token; ## TODO: ok? |
!!!next-token; ## TODO: ok? |
| 6180 |
redo B; |
next B; |
| 6181 |
} |
} |
| 6182 |
|
|
| 6183 |
!!!cp ('t298'); |
!!!cp ('t298'); |
| 6187 |
|
|
| 6188 |
!!!ack-later; |
!!!ack-later; |
| 6189 |
## reprocess |
## reprocess |
| 6190 |
redo B; |
next B; |
| 6191 |
} else { |
} else { |
| 6192 |
!!!cp ('t299'); |
!!!cp ('t299'); |
| 6193 |
!!!parse-error (type => 'in select:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in select:/', |
| 6194 |
|
text => $token->{tag_name}, token => $token); |
| 6195 |
## Ignore the token |
## Ignore the token |
| 6196 |
!!!nack ('t299.3'); |
!!!nack ('t299.3'); |
| 6197 |
!!!next-token; |
!!!next-token; |
| 6198 |
redo B; |
next B; |
| 6199 |
} |
} |
| 6200 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 6201 |
unless ($self->{open_elements}->[-1]->[1] & HTML_EL and |
unless ($self->{open_elements}->[-1]->[1] & HTML_EL and |
| 6223 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 6224 |
!!!cp ('t300'); |
!!!cp ('t300'); |
| 6225 |
!!!next-token; |
!!!next-token; |
| 6226 |
redo B; |
next B; |
| 6227 |
} |
} |
| 6228 |
} |
} |
| 6229 |
|
|
| 6230 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 6231 |
!!!cp ('t301'); |
!!!cp ('t301'); |
| 6232 |
!!!parse-error (type => 'after html:#character', token => $token); |
!!!parse-error (type => 'after html:#text', token => $token); |
| 6233 |
|
|
| 6234 |
## Reprocess in the "after body" insertion mode. |
## Reprocess in the "after body" insertion mode. |
| 6235 |
} else { |
} else { |
| 6237 |
} |
} |
| 6238 |
|
|
| 6239 |
## "after body" insertion mode |
## "after body" insertion mode |
| 6240 |
!!!parse-error (type => 'after body:#character', token => $token); |
!!!parse-error (type => 'after body:#text', token => $token); |
| 6241 |
|
|
| 6242 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 6243 |
## reprocess |
## reprocess |
| 6244 |
redo B; |
next B; |
| 6245 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 6246 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 6247 |
!!!cp ('t303'); |
!!!cp ('t303'); |
| 6248 |
!!!parse-error (type => 'after html:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after html', |
| 6249 |
|
text => $token->{tag_name}, token => $token); |
| 6250 |
|
|
| 6251 |
## Reprocess in the "after body" insertion mode. |
## Reprocess in the "after body" insertion mode. |
| 6252 |
} else { |
} else { |
| 6254 |
} |
} |
| 6255 |
|
|
| 6256 |
## "after body" insertion mode |
## "after body" insertion mode |
| 6257 |
!!!parse-error (type => 'after body:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after body', |
| 6258 |
|
text => $token->{tag_name}, token => $token); |
| 6259 |
|
|
| 6260 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 6261 |
!!!ack-later; |
!!!ack-later; |
| 6262 |
## reprocess |
## reprocess |
| 6263 |
redo B; |
next B; |
| 6264 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 6265 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 6266 |
!!!cp ('t305'); |
!!!cp ('t305'); |
| 6267 |
!!!parse-error (type => 'after html:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after html:/', |
| 6268 |
|
text => $token->{tag_name}, token => $token); |
| 6269 |
|
|
| 6270 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 6271 |
## Reprocess in the "after body" insertion mode. |
## Reprocess in the "after body" insertion mode. |
| 6277 |
if ($token->{tag_name} eq 'html') { |
if ($token->{tag_name} eq 'html') { |
| 6278 |
if (defined $self->{inner_html_node}) { |
if (defined $self->{inner_html_node}) { |
| 6279 |
!!!cp ('t307'); |
!!!cp ('t307'); |
| 6280 |
!!!parse-error (type => 'unmatched end tag:html', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6281 |
|
text => 'html', token => $token); |
| 6282 |
## Ignore the token |
## Ignore the token |
| 6283 |
!!!next-token; |
!!!next-token; |
| 6284 |
redo B; |
next B; |
| 6285 |
} else { |
} else { |
| 6286 |
!!!cp ('t308'); |
!!!cp ('t308'); |
| 6287 |
$self->{insertion_mode} = AFTER_HTML_BODY_IM; |
$self->{insertion_mode} = AFTER_HTML_BODY_IM; |
| 6288 |
!!!next-token; |
!!!next-token; |
| 6289 |
redo B; |
next B; |
| 6290 |
} |
} |
| 6291 |
} else { |
} else { |
| 6292 |
!!!cp ('t309'); |
!!!cp ('t309'); |
| 6293 |
!!!parse-error (type => 'after body:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after body:/', |
| 6294 |
|
text => $token->{tag_name}, token => $token); |
| 6295 |
|
|
| 6296 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 6297 |
## reprocess |
## reprocess |
| 6298 |
redo B; |
next B; |
| 6299 |
} |
} |
| 6300 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 6301 |
!!!cp ('t309.2'); |
!!!cp ('t309.2'); |
| 6312 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 6313 |
!!!cp ('t310'); |
!!!cp ('t310'); |
| 6314 |
!!!next-token; |
!!!next-token; |
| 6315 |
redo B; |
next B; |
| 6316 |
} |
} |
| 6317 |
} |
} |
| 6318 |
|
|
| 6319 |
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
| 6320 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6321 |
!!!cp ('t311'); |
!!!cp ('t311'); |
| 6322 |
!!!parse-error (type => 'in frameset:#character', token => $token); |
!!!parse-error (type => 'in frameset:#text', token => $token); |
| 6323 |
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 6324 |
!!!cp ('t312'); |
!!!cp ('t312'); |
| 6325 |
!!!parse-error (type => 'after frameset:#character', token => $token); |
!!!parse-error (type => 'after frameset:#text', token => $token); |
| 6326 |
} else { # "after html frameset" |
} else { # "after after frameset" |
| 6327 |
!!!cp ('t313'); |
!!!cp ('t313'); |
| 6328 |
!!!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); |
|
| 6329 |
} |
} |
| 6330 |
|
|
| 6331 |
## Ignore the token. |
## Ignore the token. |
| 6336 |
!!!cp ('t315'); |
!!!cp ('t315'); |
| 6337 |
!!!next-token; |
!!!next-token; |
| 6338 |
} |
} |
| 6339 |
redo B; |
next B; |
| 6340 |
} |
} |
| 6341 |
|
|
| 6342 |
die qq[$0: Character "$token->{data}"]; |
die qq[$0: Character "$token->{data}"]; |
| 6343 |
} 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); |
|
|
|
|
|
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
|
|
## Process in the "after frameset" insertion mode. |
|
|
} else { |
|
|
!!!cp ('t317'); |
|
|
} |
|
|
|
|
| 6344 |
if ($token->{tag_name} eq 'frameset' and |
if ($token->{tag_name} eq 'frameset' and |
| 6345 |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6346 |
!!!cp ('t318'); |
!!!cp ('t318'); |
| 6347 |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 6348 |
!!!nack ('t318.1'); |
!!!nack ('t318.1'); |
| 6349 |
!!!next-token; |
!!!next-token; |
| 6350 |
redo B; |
next B; |
| 6351 |
} elsif ($token->{tag_name} eq 'frame' and |
} elsif ($token->{tag_name} eq 'frame' and |
| 6352 |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6353 |
!!!cp ('t319'); |
!!!cp ('t319'); |
| 6355 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 6356 |
!!!ack ('t319.1'); |
!!!ack ('t319.1'); |
| 6357 |
!!!next-token; |
!!!next-token; |
| 6358 |
redo B; |
next B; |
| 6359 |
} elsif ($token->{tag_name} eq 'noframes') { |
} elsif ($token->{tag_name} eq 'noframes') { |
| 6360 |
!!!cp ('t320'); |
!!!cp ('t320'); |
| 6361 |
## NOTE: As if in body. |
## NOTE: As if in head. |
| 6362 |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 6363 |
redo B; |
next B; |
| 6364 |
|
|
| 6365 |
|
## NOTE: |<!DOCTYPE HTML><frameset></frameset></html><noframes></noframes>| |
| 6366 |
|
## has no parse error. |
| 6367 |
} else { |
} else { |
| 6368 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6369 |
!!!cp ('t321'); |
!!!cp ('t321'); |
| 6370 |
!!!parse-error (type => 'in frameset:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in frameset', |
| 6371 |
} else { |
text => $token->{tag_name}, token => $token); |
| 6372 |
|
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 6373 |
!!!cp ('t322'); |
!!!cp ('t322'); |
| 6374 |
!!!parse-error (type => 'after frameset:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after frameset', |
| 6375 |
|
text => $token->{tag_name}, token => $token); |
| 6376 |
|
} else { # "after after frameset" |
| 6377 |
|
!!!cp ('t322.2'); |
| 6378 |
|
!!!parse-error (type => 'after after frameset', |
| 6379 |
|
text => $token->{tag_name}, token => $token); |
| 6380 |
} |
} |
| 6381 |
## Ignore the token |
## Ignore the token |
| 6382 |
!!!nack ('t322.1'); |
!!!nack ('t322.1'); |
| 6383 |
!!!next-token; |
!!!next-token; |
| 6384 |
redo B; |
next B; |
| 6385 |
} |
} |
| 6386 |
} elsif ($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); |
|
|
|
|
|
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
|
|
## Process in the "after frameset" insertion mode. |
|
|
} else { |
|
|
!!!cp ('t324'); |
|
|
} |
|
|
|
|
| 6387 |
if ($token->{tag_name} eq 'frameset' and |
if ($token->{tag_name} eq 'frameset' and |
| 6388 |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6389 |
if ($self->{open_elements}->[-1]->[1] & HTML_EL and |
if ($self->{open_elements}->[-1]->[1] & HTML_EL and |
| 6390 |
@{$self->{open_elements}} == 1) { |
@{$self->{open_elements}} == 1) { |
| 6391 |
!!!cp ('t325'); |
!!!cp ('t325'); |
| 6392 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 6393 |
|
text => $token->{tag_name}, token => $token); |
| 6394 |
## Ignore the token |
## Ignore the token |
| 6395 |
!!!next-token; |
!!!next-token; |
| 6396 |
} else { |
} else { |
| 6406 |
} else { |
} else { |
| 6407 |
!!!cp ('t328'); |
!!!cp ('t328'); |
| 6408 |
} |
} |
| 6409 |
redo B; |
next B; |
| 6410 |
} elsif ($token->{tag_name} eq 'html' and |
} elsif ($token->{tag_name} eq 'html' and |
| 6411 |
$self->{insertion_mode} == AFTER_FRAMESET_IM) { |
$self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 6412 |
!!!cp ('t329'); |
!!!cp ('t329'); |
| 6413 |
$self->{insertion_mode} = AFTER_HTML_FRAMESET_IM; |
$self->{insertion_mode} = AFTER_HTML_FRAMESET_IM; |
| 6414 |
!!!next-token; |
!!!next-token; |
| 6415 |
redo B; |
next B; |
| 6416 |
} else { |
} else { |
| 6417 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6418 |
!!!cp ('t330'); |
!!!cp ('t330'); |
| 6419 |
!!!parse-error (type => 'in frameset:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in frameset:/', |
| 6420 |
} else { |
text => $token->{tag_name}, token => $token); |
| 6421 |
|
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 6422 |
|
!!!cp ('t330.1'); |
| 6423 |
|
!!!parse-error (type => 'after frameset:/', |
| 6424 |
|
text => $token->{tag_name}, token => $token); |
| 6425 |
|
} else { # "after after html" |
| 6426 |
!!!cp ('t331'); |
!!!cp ('t331'); |
| 6427 |
!!!parse-error (type => 'after frameset:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after after frameset:/', |
| 6428 |
|
text => $token->{tag_name}, token => $token); |
| 6429 |
} |
} |
| 6430 |
## Ignore the token |
## Ignore the token |
| 6431 |
!!!next-token; |
!!!next-token; |
| 6432 |
redo B; |
next B; |
| 6433 |
} |
} |
| 6434 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 6435 |
unless ($self->{open_elements}->[-1]->[1] & HTML_EL and |
unless ($self->{open_elements}->[-1]->[1] & HTML_EL and |
| 6457 |
!!!cp ('t332'); |
!!!cp ('t332'); |
| 6458 |
## NOTE: This is an "as if in head" code clone |
## NOTE: This is an "as if in head" code clone |
| 6459 |
$script_start_tag->(); |
$script_start_tag->(); |
| 6460 |
redo B; |
next B; |
| 6461 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($token->{tag_name} eq 'style') { |
| 6462 |
!!!cp ('t333'); |
!!!cp ('t333'); |
| 6463 |
## NOTE: This is an "as if in head" code clone |
## NOTE: This is an "as if in head" code clone |
| 6464 |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 6465 |
redo B; |
next B; |
| 6466 |
} elsif ({ |
} elsif ({ |
| 6467 |
base => 1, link => 1, |
base => 1, link => 1, |
| 6468 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6472 |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 6473 |
!!!ack ('t334.1'); |
!!!ack ('t334.1'); |
| 6474 |
!!!next-token; |
!!!next-token; |
| 6475 |
redo B; |
next B; |
| 6476 |
} elsif ($token->{tag_name} eq 'meta') { |
} elsif ($token->{tag_name} eq 'meta') { |
| 6477 |
## NOTE: This is an "as if in head" code clone, only "-t" differs |
## NOTE: This is an "as if in head" code clone, only "-t" differs |
| 6478 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 6479 |
my $meta_el = pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
my $meta_el = pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 6480 |
|
|
| 6481 |
unless ($self->{confident}) { |
unless ($self->{confident}) { |
| 6482 |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
if ($token->{attributes}->{charset}) { |
| 6483 |
!!!cp ('t335'); |
!!!cp ('t335'); |
| 6484 |
|
## NOTE: Whether the encoding is supported or not is handled |
| 6485 |
|
## in the {change_encoding} callback. |
| 6486 |
$self->{change_encoding} |
$self->{change_encoding} |
| 6487 |
->($self, $token->{attributes}->{charset}->{value}, $token); |
->($self, $token->{attributes}->{charset}->{value}, $token); |
| 6488 |
|
|
| 6491 |
$token->{attributes}->{charset} |
$token->{attributes}->{charset} |
| 6492 |
->{has_reference}); |
->{has_reference}); |
| 6493 |
} elsif ($token->{attributes}->{content}) { |
} elsif ($token->{attributes}->{content}) { |
|
## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition. |
|
| 6494 |
if ($token->{attributes}->{content}->{value} |
if ($token->{attributes}->{content}->{value} |
| 6495 |
=~ /\A[^;]*;[\x09-\x0D\x20]*[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
=~ /[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
| 6496 |
[\x09-\x0D\x20]*= |
[\x09-\x0D\x20]*= |
| 6497 |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
| 6498 |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20\x3B]*))/x) { |
| 6499 |
!!!cp ('t336'); |
!!!cp ('t336'); |
| 6500 |
|
## NOTE: Whether the encoding is supported or not is handled |
| 6501 |
|
## in the {change_encoding} callback. |
| 6502 |
$self->{change_encoding} |
$self->{change_encoding} |
| 6503 |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3, $token); |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3, $token); |
| 6504 |
$meta_el->[0]->get_attribute_node_ns (undef, 'content') |
$meta_el->[0]->get_attribute_node_ns (undef, 'content') |
| 6526 |
|
|
| 6527 |
!!!ack ('t338.1'); |
!!!ack ('t338.1'); |
| 6528 |
!!!next-token; |
!!!next-token; |
| 6529 |
redo B; |
next B; |
| 6530 |
} elsif ($token->{tag_name} eq 'title') { |
} elsif ($token->{tag_name} eq 'title') { |
| 6531 |
!!!cp ('t341'); |
!!!cp ('t341'); |
| 6532 |
## NOTE: This is an "as if in head" code clone |
## NOTE: This is an "as if in head" code clone |
| 6533 |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
| 6534 |
redo B; |
next B; |
| 6535 |
} elsif ($token->{tag_name} eq 'body') { |
} elsif ($token->{tag_name} eq 'body') { |
| 6536 |
!!!parse-error (type => 'in body:body', token => $token); |
!!!parse-error (type => 'in body', text => 'body', token => $token); |
| 6537 |
|
|
| 6538 |
if (@{$self->{open_elements}} == 1 or |
if (@{$self->{open_elements}} == 1 or |
| 6539 |
not ($self->{open_elements}->[1]->[1] & BODY_EL)) { |
not ($self->{open_elements}->[1]->[1] & BODY_EL)) { |
| 6552 |
} |
} |
| 6553 |
!!!nack ('t343.1'); |
!!!nack ('t343.1'); |
| 6554 |
!!!next-token; |
!!!next-token; |
| 6555 |
redo B; |
next B; |
| 6556 |
} elsif ({ |
} elsif ({ |
| 6557 |
address => 1, blockquote => 1, center => 1, dir => 1, |
address => 1, blockquote => 1, center => 1, dir => 1, |
| 6558 |
div => 1, dl => 1, fieldset => 1, |
div => 1, dl => 1, fieldset => 1, |
| 6569 |
## Ignore the token |
## Ignore the token |
| 6570 |
!!!nack ('t350.1'); |
!!!nack ('t350.1'); |
| 6571 |
!!!next-token; |
!!!next-token; |
| 6572 |
redo B; |
next B; |
| 6573 |
} |
} |
| 6574 |
|
|
| 6575 |
## has a p element in scope |
## has a p element in scope |
| 6579 |
!!!back-token; # <form> |
!!!back-token; # <form> |
| 6580 |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
| 6581 |
line => $token->{line}, column => $token->{column}}; |
line => $token->{line}, column => $token->{column}}; |
| 6582 |
redo B; |
next B; |
| 6583 |
} elsif ($_->[1] & SCOPING_EL) { |
} elsif ($_->[1] & SCOPING_EL) { |
| 6584 |
!!!cp ('t345'); |
!!!cp ('t345'); |
| 6585 |
last INSCOPE; |
last INSCOPE; |
| 6625 |
!!!nack ('t347.1'); |
!!!nack ('t347.1'); |
| 6626 |
!!!next-token; |
!!!next-token; |
| 6627 |
} |
} |
| 6628 |
redo B; |
next B; |
| 6629 |
} elsif ({li => 1, dt => 1, dd => 1}->{$token->{tag_name}}) { |
} elsif ({li => 1, dt => 1, dd => 1}->{$token->{tag_name}}) { |
| 6630 |
## has a p element in scope |
## has a p element in scope |
| 6631 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 6634 |
!!!back-token; # <x> |
!!!back-token; # <x> |
| 6635 |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
| 6636 |
line => $token->{line}, column => $token->{column}}; |
line => $token->{line}, column => $token->{column}}; |
| 6637 |
redo B; |
next B; |
| 6638 |
} elsif ($_->[1] & SCOPING_EL) { |
} elsif ($_->[1] & SCOPING_EL) { |
| 6639 |
!!!cp ('t354'); |
!!!cp ('t354'); |
| 6640 |
last INSCOPE; |
last INSCOPE; |
| 6653 |
if ($i != -1) { |
if ($i != -1) { |
| 6654 |
!!!cp ('t355'); |
!!!cp ('t355'); |
| 6655 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 6656 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 6657 |
->manakai_local_name, |
->manakai_local_name, |
| 6658 |
token => $token); |
token => $token); |
| 6659 |
} else { |
} else { |
| 6686 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 6687 |
!!!nack ('t359.1'); |
!!!nack ('t359.1'); |
| 6688 |
!!!next-token; |
!!!next-token; |
| 6689 |
redo B; |
next B; |
| 6690 |
} elsif ($token->{tag_name} eq 'plaintext') { |
} elsif ($token->{tag_name} eq 'plaintext') { |
| 6691 |
## has a p element in scope |
## has a p element in scope |
| 6692 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 6695 |
!!!back-token; # <plaintext> |
!!!back-token; # <plaintext> |
| 6696 |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
| 6697 |
line => $token->{line}, column => $token->{column}}; |
line => $token->{line}, column => $token->{column}}; |
| 6698 |
redo B; |
next B; |
| 6699 |
} elsif ($_->[1] & SCOPING_EL) { |
} elsif ($_->[1] & SCOPING_EL) { |
| 6700 |
!!!cp ('t368'); |
!!!cp ('t368'); |
| 6701 |
last INSCOPE; |
last INSCOPE; |
| 6708 |
|
|
| 6709 |
!!!nack ('t368.1'); |
!!!nack ('t368.1'); |
| 6710 |
!!!next-token; |
!!!next-token; |
| 6711 |
redo B; |
next B; |
| 6712 |
} elsif ($token->{tag_name} eq 'a') { |
} elsif ($token->{tag_name} eq 'a') { |
| 6713 |
AFE: for my $i (reverse 0..$#$active_formatting_elements) { |
AFE: for my $i (reverse 0..$#$active_formatting_elements) { |
| 6714 |
my $node = $active_formatting_elements->[$i]; |
my $node = $active_formatting_elements->[$i]; |
| 6749 |
|
|
| 6750 |
!!!nack ('t374.1'); |
!!!nack ('t374.1'); |
| 6751 |
!!!next-token; |
!!!next-token; |
| 6752 |
redo B; |
next B; |
| 6753 |
} elsif ($token->{tag_name} eq 'nobr') { |
} elsif ($token->{tag_name} eq 'nobr') { |
| 6754 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 6755 |
|
|
| 6762 |
!!!back-token; # <nobr> |
!!!back-token; # <nobr> |
| 6763 |
$token = {type => END_TAG_TOKEN, tag_name => 'nobr', |
$token = {type => END_TAG_TOKEN, tag_name => 'nobr', |
| 6764 |
line => $token->{line}, column => $token->{column}}; |
line => $token->{line}, column => $token->{column}}; |
| 6765 |
redo B; |
next B; |
| 6766 |
} elsif ($node->[1] & SCOPING_EL) { |
} elsif ($node->[1] & SCOPING_EL) { |
| 6767 |
!!!cp ('t377'); |
!!!cp ('t377'); |
| 6768 |
last INSCOPE; |
last INSCOPE; |
| 6774 |
|
|
| 6775 |
!!!nack ('t377.1'); |
!!!nack ('t377.1'); |
| 6776 |
!!!next-token; |
!!!next-token; |
| 6777 |
redo B; |
next B; |
| 6778 |
} elsif ($token->{tag_name} eq 'button') { |
} elsif ($token->{tag_name} eq 'button') { |
| 6779 |
## has a button element in scope |
## has a button element in scope |
| 6780 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 6785 |
!!!back-token; # <button> |
!!!back-token; # <button> |
| 6786 |
$token = {type => END_TAG_TOKEN, tag_name => 'button', |
$token = {type => END_TAG_TOKEN, tag_name => 'button', |
| 6787 |
line => $token->{line}, column => $token->{column}}; |
line => $token->{line}, column => $token->{column}}; |
| 6788 |
redo B; |
next B; |
| 6789 |
} elsif ($node->[1] & SCOPING_EL) { |
} elsif ($node->[1] & SCOPING_EL) { |
| 6790 |
!!!cp ('t379'); |
!!!cp ('t379'); |
| 6791 |
last INSCOPE; |
last INSCOPE; |
| 6802 |
|
|
| 6803 |
!!!nack ('t379.1'); |
!!!nack ('t379.1'); |
| 6804 |
!!!next-token; |
!!!next-token; |
| 6805 |
redo B; |
next B; |
| 6806 |
} elsif ({ |
} elsif ({ |
| 6807 |
xmp => 1, |
xmp => 1, |
| 6808 |
iframe => 1, |
iframe => 1, |
| 6809 |
noembed => 1, |
noembed => 1, |
| 6810 |
noframes => 1, |
noframes => 1, ## NOTE: This is an "as if in head" code clone. |
| 6811 |
noscript => 0, ## TODO: 1 if scripting is enabled |
noscript => 0, ## TODO: 1 if scripting is enabled |
| 6812 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6813 |
if ($token->{tag_name} eq 'xmp') { |
if ($token->{tag_name} eq 'xmp') { |
| 6818 |
} |
} |
| 6819 |
## NOTE: There is an "as if in body" code clone. |
## NOTE: There is an "as if in body" code clone. |
| 6820 |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 6821 |
redo B; |
next B; |
| 6822 |
} elsif ($token->{tag_name} eq 'isindex') { |
} elsif ($token->{tag_name} eq 'isindex') { |
| 6823 |
!!!parse-error (type => 'isindex', token => $token); |
!!!parse-error (type => 'isindex', token => $token); |
| 6824 |
|
|
| 6827 |
## Ignore the token |
## Ignore the token |
| 6828 |
!!!nack ('t389'); ## NOTE: Not acknowledged. |
!!!nack ('t389'); ## NOTE: Not acknowledged. |
| 6829 |
!!!next-token; |
!!!next-token; |
| 6830 |
redo B; |
next B; |
| 6831 |
} else { |
} else { |
| 6832 |
|
!!!ack ('t391.1'); |
| 6833 |
|
|
| 6834 |
my $at = $token->{attributes}; |
my $at = $token->{attributes}; |
| 6835 |
my $form_attrs; |
my $form_attrs; |
| 6836 |
$form_attrs->{action} = $at->{action} if $at->{action}; |
$form_attrs->{action} = $at->{action} if $at->{action}; |
| 6874 |
line => $token->{line}, column => $token->{column}}, |
line => $token->{line}, column => $token->{column}}, |
| 6875 |
{type => END_TAG_TOKEN, tag_name => 'form', |
{type => END_TAG_TOKEN, tag_name => 'form', |
| 6876 |
line => $token->{line}, column => $token->{column}}; |
line => $token->{line}, column => $token->{column}}; |
|
!!!nack ('t391.1'); ## NOTE: Not acknowledged. |
|
| 6877 |
!!!back-token (@tokens); |
!!!back-token (@tokens); |
| 6878 |
!!!next-token; |
!!!next-token; |
| 6879 |
redo B; |
next B; |
| 6880 |
} |
} |
| 6881 |
} elsif ($token->{tag_name} eq 'textarea') { |
} elsif ($token->{tag_name} eq 'textarea') { |
| 6882 |
my $tag_name = $token->{tag_name}; |
my $tag_name = $token->{tag_name}; |
| 6883 |
my $el; |
my $el; |
| 6884 |
!!!create-element ($el, $token->{tag_name}, $token->{attributes}, $token); |
!!!create-element ($el, $HTML_NS, $token->{tag_name}, $token->{attributes}, $token); |
| 6885 |
|
|
| 6886 |
## TODO: $self->{form_element} if defined |
## TODO: $self->{form_element} if defined |
| 6887 |
$self->{content_model} = RCDATA_CONTENT_MODEL; |
$self->{content_model} = RCDATA_CONTENT_MODEL; |
| 6921 |
## Ignore the token |
## Ignore the token |
| 6922 |
} else { |
} else { |
| 6923 |
!!!cp ('t398'); |
!!!cp ('t398'); |
| 6924 |
!!!parse-error (type => 'in RCDATA:#'.$token->{type}, token => $token); |
!!!parse-error (type => 'in RCDATA:#eof', token => $token); |
| 6925 |
} |
} |
| 6926 |
!!!next-token; |
!!!next-token; |
| 6927 |
|
next B; |
| 6928 |
|
} elsif ($token->{tag_name} eq 'rt' or |
| 6929 |
|
$token->{tag_name} eq 'rp') { |
| 6930 |
|
## has a |ruby| element in scope |
| 6931 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 6932 |
|
my $node = $self->{open_elements}->[$_]; |
| 6933 |
|
if ($node->[1] & RUBY_EL) { |
| 6934 |
|
!!!cp ('t398.1'); |
| 6935 |
|
## generate implied end tags |
| 6936 |
|
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 6937 |
|
!!!cp ('t398.2'); |
| 6938 |
|
pop @{$self->{open_elements}}; |
| 6939 |
|
} |
| 6940 |
|
unless ($self->{open_elements}->[-1]->[1] & RUBY_EL) { |
| 6941 |
|
!!!cp ('t398.3'); |
| 6942 |
|
!!!parse-error (type => 'not closed', |
| 6943 |
|
text => $self->{open_elements}->[-1]->[0] |
| 6944 |
|
->manakai_local_name, |
| 6945 |
|
token => $token); |
| 6946 |
|
pop @{$self->{open_elements}} |
| 6947 |
|
while not $self->{open_elements}->[-1]->[1] & RUBY_EL; |
| 6948 |
|
} |
| 6949 |
|
last INSCOPE; |
| 6950 |
|
} elsif ($node->[1] & SCOPING_EL) { |
| 6951 |
|
!!!cp ('t398.4'); |
| 6952 |
|
last INSCOPE; |
| 6953 |
|
} |
| 6954 |
|
} # INSCOPE |
| 6955 |
|
|
| 6956 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 6957 |
|
|
| 6958 |
|
!!!nack ('t398.5'); |
| 6959 |
|
!!!next-token; |
| 6960 |
redo B; |
redo B; |
| 6961 |
|
} elsif ($token->{tag_name} eq 'math' or |
| 6962 |
|
$token->{tag_name} eq 'svg') { |
| 6963 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 6964 |
|
|
| 6965 |
|
## "Adjust MathML attributes" ('math' only) - done in insert-element-f |
| 6966 |
|
|
| 6967 |
|
## "adjust SVG attributes" ('svg' only) - done in insert-element-f |
| 6968 |
|
|
| 6969 |
|
## "adjust foreign attributes" - done in insert-element-f |
| 6970 |
|
|
| 6971 |
|
!!!insert-element-f ($token->{tag_name} eq 'math' ? $MML_NS : $SVG_NS, $token->{tag_name}, $token->{attributes}, $token); |
| 6972 |
|
|
| 6973 |
|
if ($self->{self_closing}) { |
| 6974 |
|
pop @{$self->{open_elements}}; |
| 6975 |
|
!!!ack ('t398.1'); |
| 6976 |
|
} else { |
| 6977 |
|
!!!cp ('t398.2'); |
| 6978 |
|
$self->{insertion_mode} |= IN_FOREIGN_CONTENT_IM; |
| 6979 |
|
## NOTE: |<body><math><mi><svg>| -> "in foreign content" insertion |
| 6980 |
|
## mode, "in body" (not "in foreign content") secondary insertion |
| 6981 |
|
## mode, maybe. |
| 6982 |
|
} |
| 6983 |
|
|
| 6984 |
|
!!!next-token; |
| 6985 |
|
next B; |
| 6986 |
} elsif ({ |
} elsif ({ |
| 6987 |
caption => 1, col => 1, colgroup => 1, frame => 1, |
caption => 1, col => 1, colgroup => 1, frame => 1, |
| 6988 |
frameset => 1, head => 1, option => 1, optgroup => 1, |
frameset => 1, head => 1, option => 1, optgroup => 1, |
| 6990 |
thead => 1, tr => 1, |
thead => 1, tr => 1, |
| 6991 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6992 |
!!!cp ('t401'); |
!!!cp ('t401'); |
| 6993 |
!!!parse-error (type => 'in body:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in body', |
| 6994 |
|
text => $token->{tag_name}, token => $token); |
| 6995 |
## Ignore the token |
## Ignore the token |
| 6996 |
!!!nack ('t401.1'); ## NOTE: |<col/>| or |<frame/>| here is an error. |
!!!nack ('t401.1'); ## NOTE: |<col/>| or |<frame/>| here is an error. |
| 6997 |
!!!next-token; |
!!!next-token; |
| 6998 |
redo B; |
next B; |
| 6999 |
|
|
| 7000 |
## ISSUE: An issue on HTML5 new elements in the spec. |
## ISSUE: An issue on HTML5 new elements in the spec. |
| 7001 |
} else { |
} else { |
| 7057 |
} |
} |
| 7058 |
|
|
| 7059 |
!!!next-token; |
!!!next-token; |
| 7060 |
redo B; |
next B; |
| 7061 |
} |
} |
| 7062 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 7063 |
if ($token->{tag_name} eq 'body') { |
if ($token->{tag_name} eq 'body') { |
| 7076 |
} |
} |
| 7077 |
|
|
| 7078 |
!!!parse-error (type => 'start tag not allowed', |
!!!parse-error (type => 'start tag not allowed', |
| 7079 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 7080 |
## NOTE: Ignore the token. |
## NOTE: Ignore the token. |
| 7081 |
!!!next-token; |
!!!next-token; |
| 7082 |
redo B; |
next B; |
| 7083 |
} # INSCOPE |
} # INSCOPE |
| 7084 |
|
|
| 7085 |
for (@{$self->{open_elements}}) { |
for (@{$self->{open_elements}}) { |
| 7086 |
unless ($_->[1] & ALL_END_TAG_OPTIONAL_EL) { |
unless ($_->[1] & ALL_END_TAG_OPTIONAL_EL) { |
| 7087 |
!!!cp ('t403'); |
!!!cp ('t403'); |
| 7088 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7089 |
value => $_->[0]->manakai_local_name, |
text => $_->[0]->manakai_local_name, |
| 7090 |
token => $token); |
token => $token); |
| 7091 |
last; |
last; |
| 7092 |
} else { |
} else { |
| 7096 |
|
|
| 7097 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 7098 |
!!!next-token; |
!!!next-token; |
| 7099 |
redo B; |
next B; |
| 7100 |
} elsif ($token->{tag_name} eq 'html') { |
} elsif ($token->{tag_name} eq 'html') { |
| 7101 |
## TODO: Update this code. It seems that the code below is not |
## TODO: Update this code. It seems that the code below is not |
| 7102 |
## up-to-date, though it has same effect as speced. |
## up-to-date, though it has same effect as speced. |
| 7106 |
unless ($self->{open_elements}->[-1]->[1] & BODY_EL) { |
unless ($self->{open_elements}->[-1]->[1] & BODY_EL) { |
| 7107 |
!!!cp ('t406'); |
!!!cp ('t406'); |
| 7108 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7109 |
value => $self->{open_elements}->[1]->[0] |
text => $self->{open_elements}->[1]->[0] |
| 7110 |
->manakai_local_name, |
->manakai_local_name, |
| 7111 |
token => $token); |
token => $token); |
| 7112 |
} else { |
} else { |
| 7114 |
} |
} |
| 7115 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 7116 |
## reprocess |
## reprocess |
| 7117 |
redo B; |
next B; |
| 7118 |
} else { |
} else { |
| 7119 |
!!!cp ('t408'); |
!!!cp ('t408'); |
| 7120 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7121 |
|
text => $token->{tag_name}, token => $token); |
| 7122 |
## Ignore the token |
## Ignore the token |
| 7123 |
!!!next-token; |
!!!next-token; |
| 7124 |
redo B; |
next B; |
| 7125 |
} |
} |
| 7126 |
} elsif ({ |
} elsif ({ |
| 7127 |
address => 1, blockquote => 1, center => 1, dir => 1, |
address => 1, blockquote => 1, center => 1, dir => 1, |
| 7146 |
|
|
| 7147 |
unless (defined $i) { # has an element in scope |
unless (defined $i) { # has an element in scope |
| 7148 |
!!!cp ('t413'); |
!!!cp ('t413'); |
| 7149 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7150 |
|
text => $token->{tag_name}, token => $token); |
| 7151 |
|
## NOTE: Ignore the token. |
| 7152 |
} else { |
} else { |
| 7153 |
## Step 1. generate implied end tags |
## Step 1. generate implied end tags |
| 7154 |
while ({ |
while ({ |
| 7155 |
|
## END_TAG_OPTIONAL_EL |
| 7156 |
dd => ($token->{tag_name} ne 'dd'), |
dd => ($token->{tag_name} ne 'dd'), |
| 7157 |
dt => ($token->{tag_name} ne 'dt'), |
dt => ($token->{tag_name} ne 'dt'), |
| 7158 |
li => ($token->{tag_name} ne 'li'), |
li => ($token->{tag_name} ne 'li'), |
| 7159 |
p => 1, |
p => 1, |
| 7160 |
|
rt => 1, |
| 7161 |
|
rp => 1, |
| 7162 |
}->{$self->{open_elements}->[-1]->[0]->manakai_local_name}) { |
}->{$self->{open_elements}->[-1]->[0]->manakai_local_name}) { |
| 7163 |
!!!cp ('t409'); |
!!!cp ('t409'); |
| 7164 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 7169 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 7170 |
!!!cp ('t412'); |
!!!cp ('t412'); |
| 7171 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7172 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 7173 |
->manakai_local_name, |
->manakai_local_name, |
| 7174 |
token => $token); |
token => $token); |
| 7175 |
} else { |
} else { |
| 7186 |
}->{$token->{tag_name}}; |
}->{$token->{tag_name}}; |
| 7187 |
} |
} |
| 7188 |
!!!next-token; |
!!!next-token; |
| 7189 |
redo B; |
next B; |
| 7190 |
} elsif ($token->{tag_name} eq 'form') { |
} elsif ($token->{tag_name} eq 'form') { |
| 7191 |
undef $self->{form_element}; |
undef $self->{form_element}; |
| 7192 |
|
|
| 7206 |
|
|
| 7207 |
unless (defined $i) { # has an element in scope |
unless (defined $i) { # has an element in scope |
| 7208 |
!!!cp ('t421'); |
!!!cp ('t421'); |
| 7209 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7210 |
|
text => $token->{tag_name}, token => $token); |
| 7211 |
|
## NOTE: Ignore the token. |
| 7212 |
} else { |
} else { |
| 7213 |
## Step 1. generate implied end tags |
## Step 1. generate implied end tags |
| 7214 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 7221 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 7222 |
!!!cp ('t417.1'); |
!!!cp ('t417.1'); |
| 7223 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7224 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 7225 |
->manakai_local_name, |
->manakai_local_name, |
| 7226 |
token => $token); |
token => $token); |
| 7227 |
} else { |
} else { |
| 7233 |
} |
} |
| 7234 |
|
|
| 7235 |
!!!next-token; |
!!!next-token; |
| 7236 |
redo B; |
next B; |
| 7237 |
} elsif ({ |
} elsif ({ |
| 7238 |
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
| 7239 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 7253 |
|
|
| 7254 |
unless (defined $i) { # has an element in scope |
unless (defined $i) { # has an element in scope |
| 7255 |
!!!cp ('t425.1'); |
!!!cp ('t425.1'); |
| 7256 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7257 |
|
text => $token->{tag_name}, token => $token); |
| 7258 |
|
## NOTE: Ignore the token. |
| 7259 |
} else { |
} else { |
| 7260 |
## Step 1. generate implied end tags |
## Step 1. generate implied end tags |
| 7261 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 7267 |
if ($self->{open_elements}->[-1]->[0]->manakai_local_name |
if ($self->{open_elements}->[-1]->[0]->manakai_local_name |
| 7268 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 7269 |
!!!cp ('t425'); |
!!!cp ('t425'); |
| 7270 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7271 |
|
text => $token->{tag_name}, token => $token); |
| 7272 |
} else { |
} else { |
| 7273 |
!!!cp ('t426'); |
!!!cp ('t426'); |
| 7274 |
} |
} |
| 7278 |
} |
} |
| 7279 |
|
|
| 7280 |
!!!next-token; |
!!!next-token; |
| 7281 |
redo B; |
next B; |
| 7282 |
} elsif ($token->{tag_name} eq 'p') { |
} elsif ($token->{tag_name} eq 'p') { |
| 7283 |
## has an element in scope |
## has an element in scope |
| 7284 |
my $i; |
my $i; |
| 7299 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 7300 |
!!!cp ('t412.1'); |
!!!cp ('t412.1'); |
| 7301 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7302 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 7303 |
->manakai_local_name, |
->manakai_local_name, |
| 7304 |
token => $token); |
token => $token); |
| 7305 |
} else { |
} else { |
| 7309 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 7310 |
} else { |
} else { |
| 7311 |
!!!cp ('t413.1'); |
!!!cp ('t413.1'); |
| 7312 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7313 |
|
text => $token->{tag_name}, token => $token); |
| 7314 |
|
|
| 7315 |
!!!cp ('t415.1'); |
!!!cp ('t415.1'); |
| 7316 |
## As if <p>, then reprocess the current token |
## As if <p>, then reprocess the current token |
| 7317 |
my $el; |
my $el; |
| 7318 |
!!!create-element ($el, 'p',, $token); |
!!!create-element ($el, $HTML_NS, 'p',, $token); |
| 7319 |
$insert->($el); |
$insert->($el); |
| 7320 |
## NOTE: Not inserted into |$self->{open_elements}|. |
## NOTE: Not inserted into |$self->{open_elements}|. |
| 7321 |
} |
} |
| 7322 |
|
|
| 7323 |
!!!next-token; |
!!!next-token; |
| 7324 |
redo B; |
next B; |
| 7325 |
} elsif ({ |
} elsif ({ |
| 7326 |
a => 1, |
a => 1, |
| 7327 |
b => 1, big => 1, em => 1, font => 1, i => 1, |
b => 1, big => 1, em => 1, font => 1, i => 1, |
| 7330 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 7331 |
!!!cp ('t427'); |
!!!cp ('t427'); |
| 7332 |
$formatting_end_tag->($token); |
$formatting_end_tag->($token); |
| 7333 |
redo B; |
next B; |
| 7334 |
} elsif ($token->{tag_name} eq 'br') { |
} elsif ($token->{tag_name} eq 'br') { |
| 7335 |
!!!cp ('t428'); |
!!!cp ('t428'); |
| 7336 |
!!!parse-error (type => 'unmatched end tag:br', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7337 |
|
text => 'br', token => $token); |
| 7338 |
|
|
| 7339 |
## As if <br> |
## As if <br> |
| 7340 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 7341 |
|
|
| 7342 |
my $el; |
my $el; |
| 7343 |
!!!create-element ($el, 'br',, $token); |
!!!create-element ($el, $HTML_NS, 'br',, $token); |
| 7344 |
$insert->($el); |
$insert->($el); |
| 7345 |
|
|
| 7346 |
## Ignore the token. |
## Ignore the token. |
| 7347 |
!!!next-token; |
!!!next-token; |
| 7348 |
redo B; |
next B; |
| 7349 |
} elsif ({ |
} elsif ({ |
| 7350 |
caption => 1, col => 1, colgroup => 1, frame => 1, |
caption => 1, col => 1, colgroup => 1, frame => 1, |
| 7351 |
frameset => 1, head => 1, option => 1, optgroup => 1, |
frameset => 1, head => 1, option => 1, optgroup => 1, |
| 7359 |
noscript => 0, ## TODO: if scripting is enabled |
noscript => 0, ## TODO: if scripting is enabled |
| 7360 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 7361 |
!!!cp ('t429'); |
!!!cp ('t429'); |
| 7362 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7363 |
|
text => $token->{tag_name}, token => $token); |
| 7364 |
## Ignore the token |
## Ignore the token |
| 7365 |
!!!next-token; |
!!!next-token; |
| 7366 |
redo B; |
next B; |
| 7367 |
|
|
| 7368 |
## ISSUE: Issue on HTML5 new elements in spec |
## ISSUE: Issue on HTML5 new elements in spec |
| 7369 |
|
|
| 7379 |
## generate implied end tags |
## generate implied end tags |
| 7380 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 7381 |
!!!cp ('t430'); |
!!!cp ('t430'); |
| 7382 |
## ISSUE: Can this case be reached? |
## NOTE: |<ruby><rt></ruby>|. |
| 7383 |
|
## ISSUE: <ruby><rt></rt> will also take this code path, |
| 7384 |
|
## which seems wrong. |
| 7385 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 7386 |
|
$node_i++; |
| 7387 |
} |
} |
| 7388 |
|
|
| 7389 |
## Step 2 |
## Step 2 |
| 7392 |
!!!cp ('t431'); |
!!!cp ('t431'); |
| 7393 |
## NOTE: <x><y></x> |
## NOTE: <x><y></x> |
| 7394 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 7395 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 7396 |
->manakai_local_name, |
->manakai_local_name, |
| 7397 |
token => $token); |
token => $token); |
| 7398 |
} else { |
} else { |
| 7400 |
} |
} |
| 7401 |
|
|
| 7402 |
## Step 3 |
## Step 3 |
| 7403 |
splice @{$self->{open_elements}}, $node_i; |
splice @{$self->{open_elements}}, $node_i if $node_i < 0; |
| 7404 |
|
|
| 7405 |
!!!next-token; |
!!!next-token; |
| 7406 |
last S2; |
last S2; |
| 7411 |
($node->[1] & SPECIAL_EL or |
($node->[1] & SPECIAL_EL or |
| 7412 |
$node->[1] & SCOPING_EL)) { |
$node->[1] & SCOPING_EL)) { |
| 7413 |
!!!cp ('t433'); |
!!!cp ('t433'); |
| 7414 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 7415 |
|
text => $token->{tag_name}, token => $token); |
| 7416 |
## Ignore the token |
## Ignore the token |
| 7417 |
!!!next-token; |
!!!next-token; |
| 7418 |
last S2; |
last S2; |
| 7428 |
## Step 5; |
## Step 5; |
| 7429 |
redo S2; |
redo S2; |
| 7430 |
} # S2 |
} # S2 |
| 7431 |
redo B; |
next B; |
| 7432 |
} |
} |
| 7433 |
} |
} |
| 7434 |
redo B; |
next B; |
| 7435 |
|
} continue { # B |
| 7436 |
|
if ($self->{insertion_mode} & IN_FOREIGN_CONTENT_IM) { |
| 7437 |
|
## NOTE: The code below is executed in cases where it does not have |
| 7438 |
|
## to be, but it it is harmless even in those cases. |
| 7439 |
|
## has an element in scope |
| 7440 |
|
INSCOPE: { |
| 7441 |
|
for (reverse 0..$#{$self->{open_elements}}) { |
| 7442 |
|
my $node = $self->{open_elements}->[$_]; |
| 7443 |
|
if ($node->[1] & FOREIGN_EL) { |
| 7444 |
|
last INSCOPE; |
| 7445 |
|
} elsif ($node->[1] & SCOPING_EL) { |
| 7446 |
|
last; |
| 7447 |
|
} |
| 7448 |
|
} |
| 7449 |
|
|
| 7450 |
|
## NOTE: No foreign element in scope. |
| 7451 |
|
$self->{insertion_mode} &= ~ IN_FOREIGN_CONTENT_IM; |
| 7452 |
|
} # INSCOPE |
| 7453 |
|
} |
| 7454 |
} # B |
} # B |
| 7455 |
|
|
| 7456 |
## Stop parsing # MUST |
## Stop parsing # MUST |
| 7527 |
!!!cp ('i4'); |
!!!cp ('i4'); |
| 7528 |
!!!parse-error (type => 'NULL'); |
!!!parse-error (type => 'NULL'); |
| 7529 |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
| 7530 |
|
} elsif ($self->{next_char} <= 0x0008 or |
| 7531 |
|
(0x000E <= $self->{next_char} and |
| 7532 |
|
$self->{next_char} <= 0x001F) or |
| 7533 |
|
(0x007F <= $self->{next_char} and |
| 7534 |
|
$self->{next_char} <= 0x009F) or |
| 7535 |
|
(0xD800 <= $self->{next_char} and |
| 7536 |
|
$self->{next_char} <= 0xDFFF) or |
| 7537 |
|
(0xFDD0 <= $self->{next_char} and |
| 7538 |
|
$self->{next_char} <= 0xFDDF) or |
| 7539 |
|
{ |
| 7540 |
|
0xFFFE => 1, 0xFFFF => 1, 0x1FFFE => 1, 0x1FFFF => 1, |
| 7541 |
|
0x2FFFE => 1, 0x2FFFF => 1, 0x3FFFE => 1, 0x3FFFF => 1, |
| 7542 |
|
0x4FFFE => 1, 0x4FFFF => 1, 0x5FFFE => 1, 0x5FFFF => 1, |
| 7543 |
|
0x6FFFE => 1, 0x6FFFF => 1, 0x7FFFE => 1, 0x7FFFF => 1, |
| 7544 |
|
0x8FFFE => 1, 0x8FFFF => 1, 0x9FFFE => 1, 0x9FFFF => 1, |
| 7545 |
|
0xAFFFE => 1, 0xAFFFF => 1, 0xBFFFE => 1, 0xBFFFF => 1, |
| 7546 |
|
0xCFFFE => 1, 0xCFFFF => 1, 0xDFFFE => 1, 0xDFFFF => 1, |
| 7547 |
|
0xEFFFE => 1, 0xEFFFF => 1, 0xFFFFE => 1, 0xFFFFF => 1, |
| 7548 |
|
0x10FFFE => 1, 0x10FFFF => 1, |
| 7549 |
|
}->{$self->{next_char}}) { |
| 7550 |
|
!!!cp ('i4.1'); |
| 7551 |
|
if ($self->{next_char} < 0x10000) { |
| 7552 |
|
!!!parse-error (type => 'control char', |
| 7553 |
|
text => (sprintf 'U+%04X', $self->{next_char})); |
| 7554 |
|
} else { |
| 7555 |
|
!!!parse-error (type => 'control char', |
| 7556 |
|
text => (sprintf 'U-%08X', $self->{next_char})); |
| 7557 |
|
} |
| 7558 |
} |
} |
| 7559 |
}; |
}; |
| 7560 |
$p->{prev_char} = [-1, -1, -1]; |
$p->{prev_char} = [-1, -1, -1]; |