| 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; |
|
## TODO: 1252 parse error (revision 1264) |
|
|
## TODO: 8859-11 = 874 (revision 1271) |
|
| 12 |
|
|
| 13 |
my $HTML_NS = q<http://www.w3.org/1999/xhtml>; |
my $HTML_NS = q<http://www.w3.org/1999/xhtml>; |
| 14 |
my $MML_NS = q<http://www.w3.org/1998/Math/MathML>; |
my $MML_NS = q<http://www.w3.org/1998/Math/MathML>; |
| 45 |
sub FOREIGN_EL () { 0b10000000000000000000000000 } |
sub FOREIGN_EL () { 0b10000000000000000000000000 } |
| 46 |
sub FOREIGN_FLOW_CONTENT_EL () { 0b100000000000000000000000000 } |
sub FOREIGN_FLOW_CONTENT_EL () { 0b100000000000000000000000000 } |
| 47 |
sub MML_AXML_EL () { 0b1000000000000000000000000000 } |
sub MML_AXML_EL () { 0b1000000000000000000000000000 } |
| 48 |
|
sub RUBY_EL () { 0b10000000000000000000000000000 } |
| 49 |
|
sub RUBY_COMPONENT_EL () { 0b100000000000000000000000000000 } |
| 50 |
|
|
| 51 |
sub TABLE_ROWS_EL () { |
sub TABLE_ROWS_EL () { |
| 52 |
TABLE_EL | |
TABLE_EL | |
| 54 |
TABLE_ROW_GROUP_EL |
TABLE_ROW_GROUP_EL |
| 55 |
} |
} |
| 56 |
|
|
| 57 |
|
## NOTE: Used in "generate implied end tags" algorithm. |
| 58 |
|
## NOTE: There is a code where a modified version of END_TAG_OPTIONAL_EL |
| 59 |
|
## is used in "generate implied end tags" implementation (search for the |
| 60 |
|
## function mae). |
| 61 |
sub END_TAG_OPTIONAL_EL () { |
sub END_TAG_OPTIONAL_EL () { |
| 62 |
DD_EL | |
DD_EL | |
| 63 |
DT_EL | |
DT_EL | |
| 64 |
LI_EL | |
LI_EL | |
| 65 |
P_EL |
P_EL | |
| 66 |
|
RUBY_COMPONENT_EL |
| 67 |
} |
} |
| 68 |
|
|
| 69 |
|
## NOTE: Used in </body> and EOF algorithms. |
| 70 |
sub ALL_END_TAG_OPTIONAL_EL () { |
sub ALL_END_TAG_OPTIONAL_EL () { |
| 71 |
END_TAG_OPTIONAL_EL | |
DD_EL | |
| 72 |
|
DT_EL | |
| 73 |
|
LI_EL | |
| 74 |
|
P_EL | |
| 75 |
|
|
| 76 |
BODY_EL | |
BODY_EL | |
| 77 |
HTML_EL | |
HTML_EL | |
| 78 |
TABLE_CELL_EL | |
TABLE_CELL_EL | |
| 108 |
ADDRESS_EL | |
ADDRESS_EL | |
| 109 |
BODY_EL | |
BODY_EL | |
| 110 |
DIV_EL | |
DIV_EL | |
| 111 |
END_TAG_OPTIONAL_EL | |
|
| 112 |
|
DD_EL | |
| 113 |
|
DT_EL | |
| 114 |
|
LI_EL | |
| 115 |
|
P_EL | |
| 116 |
|
|
| 117 |
FORM_EL | |
FORM_EL | |
| 118 |
FRAMESET_EL | |
FRAMESET_EL | |
| 119 |
HEADING_EL | |
HEADING_EL | |
| 187 |
param => MISC_SPECIAL_EL, |
param => MISC_SPECIAL_EL, |
| 188 |
plaintext => MISC_SPECIAL_EL, |
plaintext => MISC_SPECIAL_EL, |
| 189 |
pre => MISC_SPECIAL_EL, |
pre => MISC_SPECIAL_EL, |
| 190 |
|
rp => RUBY_COMPONENT_EL, |
| 191 |
|
rt => RUBY_COMPONENT_EL, |
| 192 |
|
ruby => RUBY_EL, |
| 193 |
s => FORMATTING_EL, |
s => FORMATTING_EL, |
| 194 |
script => MISC_SPECIAL_EL, |
script => MISC_SPECIAL_EL, |
| 195 |
select => SELECT_EL, |
select => SELECT_EL, |
| 223 |
mtext => FOREIGN_FLOW_CONTENT_EL, |
mtext => FOREIGN_FLOW_CONTENT_EL, |
| 224 |
}, |
}, |
| 225 |
$SVG_NS => { |
$SVG_NS => { |
| 226 |
foreignobject => FOREIGN_FLOW_CONTENT_EL, ## TODO: case |
foreignObject => FOREIGN_FLOW_CONTENT_EL, |
| 227 |
desc => FOREIGN_FLOW_CONTENT_EL, |
desc => FOREIGN_FLOW_CONTENT_EL, |
| 228 |
title => FOREIGN_FLOW_CONTENT_EL, |
title => FOREIGN_FLOW_CONTENT_EL, |
| 229 |
}, |
}, |
| 230 |
## NOTE: In addition, FOREIGN_EL is set to non-HTML elements. |
## 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 |
| 367 |
## TODO: normalize charset name |
|
| 368 |
|
## HTML5 encoding sniffing algorithm |
| 369 |
|
require Message::Charset::Info; |
| 370 |
|
my $charset; |
| 371 |
|
my $buffer; |
| 372 |
|
my ($char_stream, $e_status); |
| 373 |
|
|
| 374 |
## "Change the encoding" algorithm: |
SNIFFING: { |
| 375 |
|
|
| 376 |
## Step 1 |
## Step 1 |
| 377 |
if ($charset eq 'utf-16') { ## ISSUE: UTF-16BE -> UTF-8? UTF-16LE -> UTF-8? |
if (defined $charset_name) { |
| 378 |
$charset = 'utf-8'; |
$charset = Message::Charset::Info->get_by_iana_name ($charset_name); |
| 379 |
|
|
| 380 |
|
## ISSUE: Unsupported encoding is not ignored according to the spec. |
| 381 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 382 |
|
($byte_stream, allow_error_reporting => 1, |
| 383 |
|
allow_fallback => 1); |
| 384 |
|
if ($char_stream) { |
| 385 |
|
$self->{confident} = 1; |
| 386 |
|
last SNIFFING; |
| 387 |
|
} else { |
| 388 |
|
## TODO: unsupported error |
| 389 |
|
} |
| 390 |
} |
} |
| 391 |
|
|
| 392 |
## Step 2 |
## Step 2 |
| 393 |
if (defined $self->{input_encoding} and |
my $byte_buffer = ''; |
| 394 |
$self->{input_encoding} eq $charset) { |
for (1..1024) { |
| 395 |
|
my $char = $byte_stream->getc; |
| 396 |
|
last unless defined $char; |
| 397 |
|
$byte_buffer .= $char; |
| 398 |
|
} ## TODO: timeout |
| 399 |
|
|
| 400 |
|
## Step 3 |
| 401 |
|
if ($byte_buffer =~ /^\xFE\xFF/) { |
| 402 |
|
$charset = Message::Charset::Info->get_by_iana_name ('utf-16be'); |
| 403 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 404 |
|
($byte_stream, allow_error_reporting => 1, |
| 405 |
|
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 406 |
$self->{confident} = 1; |
$self->{confident} = 1; |
| 407 |
return; |
last SNIFFING; |
| 408 |
|
} elsif ($byte_buffer =~ /^\xFF\xFE/) { |
| 409 |
|
$charset = Message::Charset::Info->get_by_iana_name ('utf-16le'); |
| 410 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 411 |
|
($byte_stream, allow_error_reporting => 1, |
| 412 |
|
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 413 |
|
$self->{confident} = 1; |
| 414 |
|
last SNIFFING; |
| 415 |
|
} elsif ($byte_buffer =~ /^\xEF\xBB\xBF/) { |
| 416 |
|
$charset = Message::Charset::Info->get_by_iana_name ('utf-8'); |
| 417 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 418 |
|
($byte_stream, allow_error_reporting => 1, |
| 419 |
|
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 420 |
|
$self->{confident} = 1; |
| 421 |
|
last SNIFFING; |
| 422 |
} |
} |
| 423 |
|
|
| 424 |
!!!parse-error (type => 'charset label detected:'.$self->{input_encoding}. |
## Step 4 |
| 425 |
':'.$charset, level => 'w', token => $token); |
## TODO: <meta charset> |
| 426 |
|
|
| 427 |
## Step 3 |
## Step 5 |
| 428 |
# if (can) { |
## TODO: from history |
|
## change the encoding on the fly. |
|
|
#$self->{confident} = 1; |
|
|
#return; |
|
|
# } |
|
| 429 |
|
|
| 430 |
## Step 4 |
## Step 6 |
| 431 |
throw Whatpm::HTML::RestartParser (charset => $charset); |
require Whatpm::Charset::UniversalCharDet; |
| 432 |
|
$charset_name = Whatpm::Charset::UniversalCharDet->detect_byte_string |
| 433 |
|
($byte_buffer); |
| 434 |
|
if (defined $charset_name) { |
| 435 |
|
$charset = Message::Charset::Info->get_by_iana_name ($charset_name); |
| 436 |
|
|
| 437 |
|
## ISSUE: Unsupported encoding is not ignored according to the spec. |
| 438 |
|
require Whatpm::Charset::DecodeHandle; |
| 439 |
|
$buffer = Whatpm::Charset::DecodeHandle::ByteBuffer->new |
| 440 |
|
($byte_stream); |
| 441 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 442 |
|
($buffer, allow_error_reporting => 1, |
| 443 |
|
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 444 |
|
if ($char_stream) { |
| 445 |
|
$buffer->{buffer} = $byte_buffer; |
| 446 |
|
!!!parse-error (type => 'sniffing:chardet', ## TODO: type name |
| 447 |
|
value => $charset_name, |
| 448 |
|
level => $self->{info_level}, |
| 449 |
|
line => 1, column => 1); |
| 450 |
|
$self->{confident} = 0; |
| 451 |
|
last SNIFFING; |
| 452 |
|
} |
| 453 |
|
} |
| 454 |
|
|
| 455 |
|
## Step 7: default |
| 456 |
|
## TODO: Make this configurable. |
| 457 |
|
$charset = Message::Charset::Info->get_by_iana_name ('windows-1252'); |
| 458 |
|
## NOTE: We choose |windows-1252| here, since |utf-8| should be |
| 459 |
|
## detectable in the step 6. |
| 460 |
|
require Whatpm::Charset::DecodeHandle; |
| 461 |
|
$buffer = Whatpm::Charset::DecodeHandle::ByteBuffer->new |
| 462 |
|
($byte_stream); |
| 463 |
|
($char_stream, $e_status) |
| 464 |
|
= $charset->get_decode_handle ($buffer, |
| 465 |
|
allow_error_reporting => 1, |
| 466 |
|
allow_fallback => 1, |
| 467 |
|
byte_buffer => \$byte_buffer); |
| 468 |
|
$buffer->{buffer} = $byte_buffer; |
| 469 |
|
!!!parse-error (type => 'sniffing:default', ## TODO: type name |
| 470 |
|
value => 'windows-1252', |
| 471 |
|
level => $self->{info_level}, |
| 472 |
|
line => 1, column => 1); |
| 473 |
|
$self->{confident} = 0; |
| 474 |
|
} # SNIFFING |
| 475 |
|
|
| 476 |
|
$self->{input_encoding} = $charset->get_iana_name; |
| 477 |
|
if ($e_status & Message::Charset::Info::FALLBACK_ENCODING_IMPL ()) { |
| 478 |
|
!!!parse-error (type => 'chardecode:fallback', ## TODO: type name |
| 479 |
|
value => $self->{input_encoding}, |
| 480 |
|
level => $self->{unsupported_level}, |
| 481 |
|
line => 1, column => 1); |
| 482 |
|
} elsif (not ($e_status & |
| 483 |
|
Message::Charset::Info::ERROR_REPORTING_ENCODING_IMPL())) { |
| 484 |
|
!!!parse-error (type => 'chardecode:no error', ## TODO: type name |
| 485 |
|
value => $self->{input_encoding}, |
| 486 |
|
level => $self->{unsupported_level}, |
| 487 |
|
line => 1, column => 1); |
| 488 |
|
} |
| 489 |
|
|
| 490 |
|
$self->{change_encoding} = sub { |
| 491 |
|
my $self = shift; |
| 492 |
|
$charset_name = shift; |
| 493 |
|
my $token = shift; |
| 494 |
|
|
| 495 |
|
$charset = Message::Charset::Info->get_by_iana_name ($charset_name); |
| 496 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 497 |
|
($byte_stream, allow_error_reporting => 1, allow_fallback => 1, |
| 498 |
|
byte_buffer => \ $buffer->{buffer}); |
| 499 |
|
|
| 500 |
|
if ($char_stream) { # if supported |
| 501 |
|
## "Change the encoding" algorithm: |
| 502 |
|
|
| 503 |
|
## Step 1 |
| 504 |
|
if ($charset->{category} & |
| 505 |
|
Message::Charset::Info::CHARSET_CATEGORY_UTF16 ()) { |
| 506 |
|
$charset = Message::Charset::Info->get_by_iana_name ('utf-8'); |
| 507 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 508 |
|
($byte_stream, |
| 509 |
|
byte_buffer => \ $buffer->{buffer}); |
| 510 |
|
} |
| 511 |
|
$charset_name = $charset->get_iana_name; |
| 512 |
|
|
| 513 |
|
## Step 2 |
| 514 |
|
if (defined $self->{input_encoding} and |
| 515 |
|
$self->{input_encoding} eq $charset_name) { |
| 516 |
|
!!!parse-error (type => 'charset label:matching', ## TODO: type |
| 517 |
|
value => $charset_name, |
| 518 |
|
level => $self->{info_level}); |
| 519 |
|
$self->{confident} = 1; |
| 520 |
|
return; |
| 521 |
|
} |
| 522 |
|
|
| 523 |
|
!!!parse-error (type => 'charset label detected:'.$self->{input_encoding}. |
| 524 |
|
':'.$charset_name, level => 'w', token => $token); |
| 525 |
|
|
| 526 |
|
## Step 3 |
| 527 |
|
# if (can) { |
| 528 |
|
## change the encoding on the fly. |
| 529 |
|
#$self->{confident} = 1; |
| 530 |
|
#return; |
| 531 |
|
# } |
| 532 |
|
|
| 533 |
|
## Step 4 |
| 534 |
|
throw Whatpm::HTML::RestartParser (); |
| 535 |
|
} |
| 536 |
}; # $self->{change_encoding} |
}; # $self->{change_encoding} |
| 537 |
|
|
| 538 |
|
my $char_onerror = sub { |
| 539 |
|
my (undef, $type, %opt) = @_; |
| 540 |
|
!!!parse-error (%opt, type => $type, |
| 541 |
|
line => $self->{line}, column => $self->{column} + 1); |
| 542 |
|
if ($opt{octets}) { |
| 543 |
|
${$opt{octets}} = "\x{FFFD}"; # relacement character |
| 544 |
|
} |
| 545 |
|
}; |
| 546 |
|
$char_stream->onerror ($char_onerror); |
| 547 |
|
|
| 548 |
my @args = @_; shift @args; # $s |
my @args = @_; shift @args; # $s |
| 549 |
my $return; |
my $return; |
| 550 |
try { |
try { |
| 551 |
$return = $self->parse_char_string ($s, @args); |
$return = $self->parse_char_stream ($char_stream, @args); |
| 552 |
} catch Whatpm::HTML::RestartParser with { |
} catch Whatpm::HTML::RestartParser with { |
| 553 |
my $charset = shift->{charset}; |
## NOTE: Invoked after {change_encoding}. |
| 554 |
$s = \ (Encode::decode ($charset, $$bytes_s)); |
|
| 555 |
$self->{input_encoding} = $charset; ## TODO: normalize |
$self->{input_encoding} = $charset->get_iana_name; |
| 556 |
|
if ($e_status & Message::Charset::Info::FALLBACK_ENCODING_IMPL ()) { |
| 557 |
|
!!!parse-error (type => 'chardecode:fallback', ## TODO: type name |
| 558 |
|
value => $self->{input_encoding}, |
| 559 |
|
level => $self->{unsupported_level}, |
| 560 |
|
line => 1, column => 1); |
| 561 |
|
} elsif (not ($e_status & |
| 562 |
|
Message::Charset::Info::ERROR_REPORTING_ENCODING_IMPL())) { |
| 563 |
|
!!!parse-error (type => 'chardecode:no error', ## TODO: type name |
| 564 |
|
value => $self->{input_encoding}, |
| 565 |
|
level => $self->{unsupported_level}, |
| 566 |
|
line => 1, column => 1); |
| 567 |
|
} |
| 568 |
$self->{confident} = 1; |
$self->{confident} = 1; |
| 569 |
$return = $self->parse_char_string ($s, @args); |
$char_stream->onerror ($char_onerror); |
| 570 |
|
$return = $self->parse_char_stream ($char_stream, @args); |
| 571 |
}; |
}; |
| 572 |
return $return; |
return $return; |
| 573 |
} # parse_byte_string |
} # parse_byte_stream |
| 574 |
|
|
| 575 |
## NOTE: HTML5 spec says that the encoding layer MUST NOT strip BOM |
## NOTE: HTML5 spec says that the encoding layer MUST NOT strip BOM |
| 576 |
## 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 |
| 581 |
## 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 |
| 582 |
## strip the BOM and never strip any ZWNBSP. |
## strip the BOM and never strip any ZWNBSP. |
| 583 |
|
|
| 584 |
*parse_char_string = \&parse_string; |
sub parse_char_string ($$$;$) { |
| 585 |
|
my $self = shift; |
| 586 |
|
require utf8; |
| 587 |
|
my $s = ref $_[0] ? $_[0] : \($_[0]); |
| 588 |
|
open my $input, '<' . (utf8::is_utf8 ($$s) ? ':utf8' : ''), $s; |
| 589 |
|
return $self->parse_char_stream ($input, @_[1..$#_]); |
| 590 |
|
} # parse_char_string |
| 591 |
|
*parse_string = \&parse_char_string; |
| 592 |
|
|
| 593 |
sub parse_string ($$$;$) { |
sub parse_char_stream ($$$;$) { |
| 594 |
my $self = ref $_[0] ? shift : shift->new; |
my $self = ref $_[0] ? shift : shift->new; |
| 595 |
my $s = ref $_[0] ? $_[0] : \($_[0]); |
my $input = $_[0]; |
| 596 |
$self->{document} = $_[1]; |
$self->{document} = $_[1]; |
| 597 |
@{$self->{document}->child_nodes} = (); |
@{$self->{document}->child_nodes} = (); |
| 598 |
|
|
| 611 |
pop @{$self->{prev_char}}; |
pop @{$self->{prev_char}}; |
| 612 |
unshift @{$self->{prev_char}}, $self->{next_char}; |
unshift @{$self->{prev_char}}, $self->{next_char}; |
| 613 |
|
|
| 614 |
$self->{next_char} = -1 and return if $i >= length $$s; |
my $char; |
| 615 |
$self->{next_char} = ord substr $$s, $i++, 1; |
if (defined $self->{next_next_char}) { |
| 616 |
|
$char = $self->{next_next_char}; |
| 617 |
|
delete $self->{next_next_char}; |
| 618 |
|
} else { |
| 619 |
|
$char = $input->getc; |
| 620 |
|
} |
| 621 |
|
$self->{next_char} = -1 and return unless defined $char; |
| 622 |
|
$self->{next_char} = ord $char; |
| 623 |
|
|
| 624 |
($self->{line_prev}, $self->{column_prev}) |
($self->{line_prev}, $self->{column_prev}) |
| 625 |
= ($self->{line}, $self->{column}); |
= ($self->{line}, $self->{column}); |
| 626 |
$self->{column}++; |
$self->{column}++; |
| 627 |
|
|
| 628 |
if ($self->{next_char} == 0x000A) { # LF |
if ($self->{next_char} == 0x000A) { # LF |
| 629 |
|
!!!cp ('j1'); |
| 630 |
$self->{line}++; |
$self->{line}++; |
| 631 |
$self->{column} = 0; |
$self->{column} = 0; |
| 632 |
} elsif ($self->{next_char} == 0x000D) { # CR |
} elsif ($self->{next_char} == 0x000D) { # CR |
| 633 |
$i++ if substr ($$s, $i, 1) eq "\x0A"; |
!!!cp ('j2'); |
| 634 |
|
my $next = $input->getc; |
| 635 |
|
if (defined $next and $next ne "\x0A") { |
| 636 |
|
$self->{next_next_char} = $next; |
| 637 |
|
} |
| 638 |
$self->{next_char} = 0x000A; # LF # MUST |
$self->{next_char} = 0x000A; # LF # MUST |
| 639 |
$self->{line}++; |
$self->{line}++; |
| 640 |
$self->{column} = 0; |
$self->{column} = 0; |
| 641 |
} elsif ($self->{next_char} > 0x10FFFF) { |
} elsif ($self->{next_char} > 0x10FFFF) { |
| 642 |
|
!!!cp ('j3'); |
| 643 |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
| 644 |
} elsif ($self->{next_char} == 0x0000) { # NULL |
} elsif ($self->{next_char} == 0x0000) { # NULL |
| 645 |
|
!!!cp ('j4'); |
| 646 |
!!!parse-error (type => 'NULL'); |
!!!parse-error (type => 'NULL'); |
| 647 |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
| 648 |
|
} elsif ($self->{next_char} <= 0x0008 or |
| 649 |
|
(0x000E <= $self->{next_char} and $self->{next_char} <= 0x001F) or |
| 650 |
|
(0x007F <= $self->{next_char} and $self->{next_char} <= 0x009F) or |
| 651 |
|
(0xD800 <= $self->{next_char} and $self->{next_char} <= 0xDFFF) or |
| 652 |
|
(0xFDD0 <= $self->{next_char} and $self->{next_char} <= 0xFDDF) or |
| 653 |
|
{ |
| 654 |
|
0xFFFE => 1, 0xFFFF => 1, 0x1FFFE => 1, 0x1FFFF => 1, |
| 655 |
|
0x2FFFE => 1, 0x2FFFF => 1, 0x3FFFE => 1, 0x3FFFF => 1, |
| 656 |
|
0x4FFFE => 1, 0x4FFFF => 1, 0x5FFFE => 1, 0x5FFFF => 1, |
| 657 |
|
0x6FFFE => 1, 0x6FFFF => 1, 0x7FFFE => 1, 0x7FFFF => 1, |
| 658 |
|
0x8FFFE => 1, 0x8FFFF => 1, 0x9FFFE => 1, 0x9FFFF => 1, |
| 659 |
|
0xAFFFE => 1, 0xAFFFF => 1, 0xBFFFE => 1, 0xBFFFF => 1, |
| 660 |
|
0xCFFFE => 1, 0xCFFFF => 1, 0xDFFFE => 1, 0xDFFFF => 1, |
| 661 |
|
0xEFFFE => 1, 0xEFFFF => 1, 0xFFFFE => 1, 0xFFFFF => 1, |
| 662 |
|
0x10FFFE => 1, 0x10FFFF => 1, |
| 663 |
|
}->{$self->{next_char}}) { |
| 664 |
|
!!!cp ('j5'); |
| 665 |
|
!!!parse-error (type => 'control char', level => $self->{must_level}); |
| 666 |
|
## TODO: error type documentation |
| 667 |
} |
} |
| 668 |
}; |
}; |
| 669 |
$self->{prev_char} = [-1, -1, -1]; |
$self->{prev_char} = [-1, -1, -1]; |
| 687 |
delete $self->{parse_error}; # remove loop |
delete $self->{parse_error}; # remove loop |
| 688 |
|
|
| 689 |
return $self->{document}; |
return $self->{document}; |
| 690 |
} # parse_string |
} # parse_char_stream |
| 691 |
|
|
| 692 |
sub new ($) { |
sub new ($) { |
| 693 |
my $class = shift; |
my $class = shift; |
| 694 |
my $self = bless {}, $class; |
my $self = bless { |
| 695 |
|
must_level => 'm', |
| 696 |
|
should_level => 's', |
| 697 |
|
good_level => 'w', |
| 698 |
|
warn_level => 'w', |
| 699 |
|
info_level => 'i', |
| 700 |
|
unsupported_level => 'u', |
| 701 |
|
}, $class; |
| 702 |
$self->{set_next_char} = sub { |
$self->{set_next_char} = sub { |
| 703 |
$self->{next_char} = -1; |
$self->{next_char} = -1; |
| 704 |
}; |
}; |
| 844 |
## |->{self_closing}| is used to save the value of |$self->{self_closing}| |
## |->{self_closing}| is used to save the value of |$self->{self_closing}| |
| 845 |
## while the token is pushed back to the stack. |
## while the token is pushed back to the stack. |
| 846 |
|
|
|
## 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? |
|
|
|
|
| 847 |
## Emitted token MUST immediately be handled by the tree construction state. |
## Emitted token MUST immediately be handled by the tree construction state. |
| 848 |
|
|
| 849 |
## 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 |
| 1059 |
redo A; |
redo A; |
| 1060 |
} else { |
} else { |
| 1061 |
!!!cp (23); |
!!!cp (23); |
| 1062 |
!!!parse-error (type => 'bare stago'); |
!!!parse-error (type => 'bare stago', |
| 1063 |
|
line => $self->{line_prev}, |
| 1064 |
|
column => $self->{column_prev}); |
| 1065 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1066 |
## reconsume |
## reconsume |
| 1067 |
|
|
| 1838 |
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
| 1839 |
!!!next-input-character; |
!!!next-input-character; |
| 1840 |
redo A; |
redo A; |
| 1841 |
|
} elsif ($self->{next_char} == -1) { |
| 1842 |
|
!!!parse-error (type => 'unclosed tag'); |
| 1843 |
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1844 |
|
!!!cp (122.3); |
| 1845 |
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1846 |
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1847 |
|
if ($self->{current_token}->{attributes}) { |
| 1848 |
|
!!!cp (122.1); |
| 1849 |
|
!!!parse-error (type => 'end tag attribute'); |
| 1850 |
|
} else { |
| 1851 |
|
## NOTE: This state should never be reached. |
| 1852 |
|
!!!cp (122.2); |
| 1853 |
|
} |
| 1854 |
|
} else { |
| 1855 |
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 1856 |
|
} |
| 1857 |
|
$self->{state} = DATA_STATE; |
| 1858 |
|
## Reconsume. |
| 1859 |
|
!!!emit ($self->{current_token}); # start tag or end tag |
| 1860 |
|
redo A; |
| 1861 |
} else { |
} else { |
| 1862 |
!!!cp ('124.1'); |
!!!cp ('124.1'); |
| 1863 |
!!!parse-error (type => 'no space between attributes'); |
!!!parse-error (type => 'no space between attributes'); |
| 1890 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 1891 |
|
|
| 1892 |
redo A; |
redo A; |
| 1893 |
|
} elsif ($self->{next_char} == -1) { |
| 1894 |
|
!!!parse-error (type => 'unclosed tag'); |
| 1895 |
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1896 |
|
!!!cp (124.7); |
| 1897 |
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1898 |
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1899 |
|
if ($self->{current_token}->{attributes}) { |
| 1900 |
|
!!!cp (124.5); |
| 1901 |
|
!!!parse-error (type => 'end tag attribute'); |
| 1902 |
|
} else { |
| 1903 |
|
## NOTE: This state should never be reached. |
| 1904 |
|
!!!cp (124.6); |
| 1905 |
|
} |
| 1906 |
|
} else { |
| 1907 |
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 1908 |
|
} |
| 1909 |
|
$self->{state} = DATA_STATE; |
| 1910 |
|
## Reconsume. |
| 1911 |
|
!!!emit ($self->{current_token}); # start tag or end tag |
| 1912 |
|
redo A; |
| 1913 |
} else { |
} else { |
| 1914 |
!!!cp ('124.4'); |
!!!cp ('124.4'); |
| 1915 |
!!!parse-error (type => 'nestc'); |
!!!parse-error (type => 'nestc'); |
| 2751 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 2752 |
!!!cp (217); |
!!!cp (217); |
| 2753 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
|
|
|
| 2754 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 2755 |
## reconsume |
## reconsume |
| 2756 |
|
|
| 2995 |
require Whatpm::_NamedEntityList; |
require Whatpm::_NamedEntityList; |
| 2996 |
our $EntityChar; |
our $EntityChar; |
| 2997 |
|
|
| 2998 |
while (length $entity_name < 10 and |
while (length $entity_name < 30 and |
| 2999 |
## NOTE: Some number greater than the maximum length of entity name |
## NOTE: Some number greater than the maximum length of entity name |
| 3000 |
((0x0041 <= $self->{next_char} and # a |
((0x0041 <= $self->{next_char} and # a |
| 3001 |
$self->{next_char} <= 0x005A) or # x |
$self->{next_char} <= 0x005A) or # x |
| 3153 |
} elsif (defined $token->{public_identifier}) { |
} elsif (defined $token->{public_identifier}) { |
| 3154 |
my $pubid = $token->{public_identifier}; |
my $pubid = $token->{public_identifier}; |
| 3155 |
$pubid =~ tr/a-z/A-z/; |
$pubid =~ tr/a-z/A-z/; |
| 3156 |
if ({ |
my $prefix = [ |
| 3157 |
"+//SILMARIL//DTD HTML PRO V0R11 19970101//EN" => 1, |
"+//SILMARIL//DTD HTML PRO V0R11 19970101//", |
| 3158 |
"-//ADVASOFT LTD//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1, |
"-//ADVASOFT LTD//DTD HTML 3.0 ASWEDIT + EXTENSIONS//", |
| 3159 |
"-//AS//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1, |
"-//AS//DTD HTML 3.0 ASWEDIT + EXTENSIONS//", |
| 3160 |
"-//IETF//DTD HTML 2.0 LEVEL 1//EN" => 1, |
"-//IETF//DTD HTML 2.0 LEVEL 1//", |
| 3161 |
"-//IETF//DTD HTML 2.0 LEVEL 2//EN" => 1, |
"-//IETF//DTD HTML 2.0 LEVEL 2//", |
| 3162 |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 1//EN" => 1, |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 1//", |
| 3163 |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 2//EN" => 1, |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 2//", |
| 3164 |
"-//IETF//DTD HTML 2.0 STRICT//EN" => 1, |
"-//IETF//DTD HTML 2.0 STRICT//", |
| 3165 |
"-//IETF//DTD HTML 2.0//EN" => 1, |
"-//IETF//DTD HTML 2.0//", |
| 3166 |
"-//IETF//DTD HTML 2.1E//EN" => 1, |
"-//IETF//DTD HTML 2.1E//", |
| 3167 |
"-//IETF//DTD HTML 3.0//EN" => 1, |
"-//IETF//DTD HTML 3.0//", |
| 3168 |
"-//IETF//DTD HTML 3.0//EN//" => 1, |
"-//IETF//DTD HTML 3.2 FINAL//", |
| 3169 |
"-//IETF//DTD HTML 3.2 FINAL//EN" => 1, |
"-//IETF//DTD HTML 3.2//", |
| 3170 |
"-//IETF//DTD HTML 3.2//EN" => 1, |
"-//IETF//DTD HTML 3//", |
| 3171 |
"-//IETF//DTD HTML 3//EN" => 1, |
"-//IETF//DTD HTML LEVEL 0//", |
| 3172 |
"-//IETF//DTD HTML LEVEL 0//EN" => 1, |
"-//IETF//DTD HTML LEVEL 1//", |
| 3173 |
"-//IETF//DTD HTML LEVEL 0//EN//2.0" => 1, |
"-//IETF//DTD HTML LEVEL 2//", |
| 3174 |
"-//IETF//DTD HTML LEVEL 1//EN" => 1, |
"-//IETF//DTD HTML LEVEL 3//", |
| 3175 |
"-//IETF//DTD HTML LEVEL 1//EN//2.0" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 0//", |
| 3176 |
"-//IETF//DTD HTML LEVEL 2//EN" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 1//", |
| 3177 |
"-//IETF//DTD HTML LEVEL 2//EN//2.0" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 2//", |
| 3178 |
"-//IETF//DTD HTML LEVEL 3//EN" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 3//", |
| 3179 |
"-//IETF//DTD HTML LEVEL 3//EN//3.0" => 1, |
"-//IETF//DTD HTML STRICT//", |
| 3180 |
"-//IETF//DTD HTML STRICT LEVEL 0//EN" => 1, |
"-//IETF//DTD HTML//", |
| 3181 |
"-//IETF//DTD HTML STRICT LEVEL 0//EN//2.0" => 1, |
"-//METRIUS//DTD METRIUS PRESENTATIONAL//", |
| 3182 |
"-//IETF//DTD HTML STRICT LEVEL 1//EN" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML STRICT//", |
| 3183 |
"-//IETF//DTD HTML STRICT LEVEL 1//EN//2.0" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML//", |
| 3184 |
"-//IETF//DTD HTML STRICT LEVEL 2//EN" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 TABLES//", |
| 3185 |
"-//IETF//DTD HTML STRICT LEVEL 2//EN//2.0" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML STRICT//", |
| 3186 |
"-//IETF//DTD HTML STRICT LEVEL 3//EN" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML//", |
| 3187 |
"-//IETF//DTD HTML STRICT LEVEL 3//EN//3.0" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 TABLES//", |
| 3188 |
"-//IETF//DTD HTML STRICT//EN" => 1, |
"-//NETSCAPE COMM. CORP.//DTD HTML//", |
| 3189 |
"-//IETF//DTD HTML STRICT//EN//2.0" => 1, |
"-//NETSCAPE COMM. CORP.//DTD STRICT HTML//", |
| 3190 |
"-//IETF//DTD HTML STRICT//EN//3.0" => 1, |
"-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//", |
| 3191 |
"-//IETF//DTD HTML//EN" => 1, |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//", |
| 3192 |
"-//IETF//DTD HTML//EN//2.0" => 1, |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED RELAXED 1.0//", |
| 3193 |
"-//IETF//DTD HTML//EN//3.0" => 1, |
"-//SOFTQUAD SOFTWARE//DTD HOTMETAL PRO 6.0::19990601::EXTENSIONS TO HTML 4.0//", |
| 3194 |
"-//METRIUS//DTD METRIUS PRESENTATIONAL//EN" => 1, |
"-//SOFTQUAD//DTD HOTMETAL PRO 4.0::19971010::EXTENSIONS TO HTML 4.0//", |
| 3195 |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML STRICT//EN" => 1, |
"-//SPYGLASS//DTD HTML 2.0 EXTENDED//", |
| 3196 |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML//EN" => 1, |
"-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//", |
| 3197 |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 TABLES//EN" => 1, |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//", |
| 3198 |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML STRICT//EN" => 1, |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA STRICT HTML//", |
| 3199 |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML//EN" => 1, |
"-//W3C//DTD HTML 3 1995-03-24//", |
| 3200 |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 TABLES//EN" => 1, |
"-//W3C//DTD HTML 3.2 DRAFT//", |
| 3201 |
"-//NETSCAPE COMM. CORP.//DTD HTML//EN" => 1, |
"-//W3C//DTD HTML 3.2 FINAL//", |
| 3202 |
"-//NETSCAPE COMM. CORP.//DTD STRICT HTML//EN" => 1, |
"-//W3C//DTD HTML 3.2//", |
| 3203 |
"-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//EN" => 1, |
"-//W3C//DTD HTML 3.2S DRAFT//", |
| 3204 |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//EN" => 1, |
"-//W3C//DTD HTML 4.0 FRAMESET//", |
| 3205 |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED RELAXED 1.0//EN" => 1, |
"-//W3C//DTD HTML 4.0 TRANSITIONAL//", |
| 3206 |
"-//SOFTQUAD SOFTWARE//DTD HOTMETAL PRO 6.0::19990601::EXTENSIONS TO HTML 4.0//EN" => 1, |
"-//W3C//DTD HTML EXPERIMETNAL 19960712//", |
| 3207 |
"-//SOFTQUAD//DTD HOTMETAL PRO 4.0::19971010::EXTENSIONS TO HTML 4.0//EN" => 1, |
"-//W3C//DTD HTML EXPERIMENTAL 970421//", |
| 3208 |
"-//SPYGLASS//DTD HTML 2.0 EXTENDED//EN" => 1, |
"-//W3C//DTD W3 HTML//", |
| 3209 |
"-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//EN" => 1, |
"-//W3O//DTD W3 HTML 3.0//", |
| 3210 |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//EN" => 1, |
"-//WEBTECHS//DTD MOZILLA HTML 2.0//", |
| 3211 |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA STRICT HTML//EN" => 1, |
"-//WEBTECHS//DTD MOZILLA HTML//", |
| 3212 |
"-//W3C//DTD HTML 3 1995-03-24//EN" => 1, |
]; # $prefix |
| 3213 |
"-//W3C//DTD HTML 3.2 DRAFT//EN" => 1, |
my $match; |
| 3214 |
"-//W3C//DTD HTML 3.2 FINAL//EN" => 1, |
for (@$prefix) { |
| 3215 |
"-//W3C//DTD HTML 3.2//EN" => 1, |
if (substr ($prefix, 0, length $_) eq $_) { |
| 3216 |
"-//W3C//DTD HTML 3.2S DRAFT//EN" => 1, |
$match = 1; |
| 3217 |
"-//W3C//DTD HTML 4.0 FRAMESET//EN" => 1, |
last; |
| 3218 |
"-//W3C//DTD HTML 4.0 TRANSITIONAL//EN" => 1, |
} |
| 3219 |
"-//W3C//DTD HTML EXPERIMETNAL 19960712//EN" => 1, |
} |
| 3220 |
"-//W3C//DTD HTML EXPERIMENTAL 970421//EN" => 1, |
if ($match or |
| 3221 |
"-//W3C//DTD W3 HTML//EN" => 1, |
$pubid eq "-//W3O//DTD W3 HTML STRICT 3.0//EN//" or |
| 3222 |
"-//W3O//DTD W3 HTML 3.0//EN" => 1, |
$pubid eq "-/W3C/DTD HTML 4.0 TRANSITIONAL/EN" or |
| 3223 |
"-//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}) { |
|
| 3224 |
!!!cp ('t5'); |
!!!cp ('t5'); |
| 3225 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 3226 |
} elsif ($pubid eq "-//W3C//DTD HTML 4.01 FRAMESET//EN" or |
} elsif ($pubid =~ m[^-//W3C//DTD HTML 4.01 FRAMESET//] or |
| 3227 |
$pubid eq "-//W3C//DTD HTML 4.01 TRANSITIONAL//EN") { |
$pubid =~ m[^-//W3C//DTD HTML 4.01 TRANSITIONAL//]) { |
| 3228 |
if (defined $token->{system_identifier}) { |
if (defined $token->{system_identifier}) { |
| 3229 |
!!!cp ('t6'); |
!!!cp ('t6'); |
| 3230 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 3232 |
!!!cp ('t7'); |
!!!cp ('t7'); |
| 3233 |
$self->{document}->manakai_compat_mode ('limited quirks'); |
$self->{document}->manakai_compat_mode ('limited quirks'); |
| 3234 |
} |
} |
| 3235 |
} elsif ($pubid eq "-//W3C//DTD XHTML 1.0 FRAMESET//EN" or |
} elsif ($pubid =~ m[^-//W3C//DTD XHTML 1.0 FRAMESET//] or |
| 3236 |
$pubid eq "-//W3C//DTD XHTML 1.0 TRANSITIONAL//EN") { |
$pubid =~ m[^-//W3C//DTD XHTML 1.0 TRANSITIONAL//]) { |
| 3237 |
!!!cp ('t8'); |
!!!cp ('t8'); |
| 3238 |
$self->{document}->manakai_compat_mode ('limited quirks'); |
$self->{document}->manakai_compat_mode ('limited quirks'); |
| 3239 |
} else { |
} else { |
| 3246 |
my $sysid = $token->{system_identifier}; |
my $sysid = $token->{system_identifier}; |
| 3247 |
$sysid =~ tr/A-Z/a-z/; |
$sysid =~ tr/A-Z/a-z/; |
| 3248 |
if ($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") { |
| 3249 |
## TODO: Check the spec: PUBLIC "(limited quirks)" "(quirks)" |
## NOTE: Ensure that |PUBLIC "(limited quirks)" "(quirks)"| is |
| 3250 |
|
## marked as quirks. |
| 3251 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 3252 |
!!!cp ('t11'); |
!!!cp ('t11'); |
| 3253 |
} else { |
} else { |
| 3419 |
if ($self->{open_elements}->[0]->[0] eq $node->[0]) { |
if ($self->{open_elements}->[0]->[0] eq $node->[0]) { |
| 3420 |
$last = 1; |
$last = 1; |
| 3421 |
if (defined $self->{inner_html_node}) { |
if (defined $self->{inner_html_node}) { |
| 3422 |
if ($self->{inner_html_node}->[1] & TABLE_CELL_EL) { |
!!!cp ('t28'); |
| 3423 |
!!!cp ('t27'); |
$node = $self->{inner_html_node}; |
| 3424 |
# |
} else { |
| 3425 |
} else { |
die "_reset_insertion_mode: t27"; |
|
!!!cp ('t28'); |
|
|
$node = $self->{inner_html_node}; |
|
|
} |
|
| 3426 |
} |
} |
| 3427 |
} |
} |
| 3428 |
|
|
| 3429 |
## Step 4..14 |
## Step 4..14 |
| 3430 |
my $new_mode; |
my $new_mode; |
| 3431 |
if ($node->[1] & FOREIGN_EL) { |
if ($node->[1] & FOREIGN_EL) { |
| 3432 |
## NOTE: Strictly spaking, the line below only applies to MathML and |
!!!cp ('t28.1'); |
| 3433 |
## SVG elements. Currently the HTML syntax supports only MathML and |
## NOTE: Strictly spaking, the line below only applies to MathML and |
| 3434 |
## SVG elements as foreigners. |
## SVG elements. Currently the HTML syntax supports only MathML and |
| 3435 |
$new_mode = $self->{insertion_mode} | IN_FOREIGN_CONTENT_IM; |
## SVG elements as foreigners. |
| 3436 |
## ISSUE: What is set as the secondary insertion mode? |
$new_mode = IN_BODY_IM | IN_FOREIGN_CONTENT_IM; |
| 3437 |
} else { |
} elsif ($node->[1] & TABLE_CELL_EL) { |
| 3438 |
$new_mode = { |
if ($last) { |
| 3439 |
|
!!!cp ('t28.2'); |
| 3440 |
|
# |
| 3441 |
|
} else { |
| 3442 |
|
!!!cp ('t28.3'); |
| 3443 |
|
$new_mode = IN_CELL_IM; |
| 3444 |
|
} |
| 3445 |
|
} else { |
| 3446 |
|
!!!cp ('t28.4'); |
| 3447 |
|
$new_mode = { |
| 3448 |
select => IN_SELECT_IM, |
select => IN_SELECT_IM, |
| 3449 |
## NOTE: |option| and |optgroup| do not set |
## NOTE: |option| and |optgroup| do not set |
| 3450 |
## insertion mode to "in select" by themselves. |
## insertion mode to "in select" by themselves. |
|
td => IN_CELL_IM, |
|
|
th => IN_CELL_IM, |
|
| 3451 |
tr => IN_ROW_IM, |
tr => IN_ROW_IM, |
| 3452 |
tbody => IN_TABLE_BODY_IM, |
tbody => IN_TABLE_BODY_IM, |
| 3453 |
thead => IN_TABLE_BODY_IM, |
thead => IN_TABLE_BODY_IM, |
| 3459 |
body => IN_BODY_IM, |
body => IN_BODY_IM, |
| 3460 |
frameset => IN_FRAMESET_IM, |
frameset => IN_FRAMESET_IM, |
| 3461 |
}->{$node->[0]->manakai_local_name}; |
}->{$node->[0]->manakai_local_name}; |
| 3462 |
} |
} |
| 3463 |
$self->{insertion_mode} = $new_mode and return if defined $new_mode; |
$self->{insertion_mode} = $new_mode and return if defined $new_mode; |
| 3464 |
|
|
| 3465 |
## Step 15 |
## Step 15 |
| 3466 |
if ($node->[1] & HTML_EL) { |
if ($node->[1] & HTML_EL) { |
| 4027 |
!!!next-token; |
!!!next-token; |
| 4028 |
next B; |
next B; |
| 4029 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 4030 |
if ($self->{open_elements}->[-1]->[1] & FOREIGN_FLOW_CONTENT_EL or |
if ((not {mglyph => 1, malignmark => 1}->{$token->{tag_name}} and |
| 4031 |
|
$self->{open_elements}->[-1]->[1] & FOREIGN_FLOW_CONTENT_EL) or |
| 4032 |
not ($self->{open_elements}->[-1]->[1] & FOREIGN_EL) or |
not ($self->{open_elements}->[-1]->[1] & FOREIGN_EL) or |
| 4033 |
($token->{tag_name} eq 'svg' and |
($token->{tag_name} eq 'svg' and |
| 4034 |
$self->{open_elements}->[-1]->[1] & MML_AXML_EL)) { |
$self->{open_elements}->[-1]->[1] & MML_AXML_EL)) { |
| 4036 |
!!!cp ('t87.2'); |
!!!cp ('t87.2'); |
| 4037 |
# |
# |
| 4038 |
} elsif ({ |
} elsif ({ |
| 4039 |
## TODO: |
b => 1, big => 1, blockquote => 1, body => 1, br => 1, |
| 4040 |
|
center => 1, code => 1, dd => 1, div => 1, dl => 1, dt => 1, |
| 4041 |
|
em => 1, embed => 1, font => 1, h1 => 1, h2 => 1, h3 => 1, |
| 4042 |
|
h4 => 1, h5 => 1, h6 => 1, head => 1, hr => 1, i => 1, |
| 4043 |
|
img => 1, li => 1, listing => 1, menu => 1, meta => 1, |
| 4044 |
|
nobr => 1, ol => 1, p => 1, pre => 1, ruby => 1, s => 1, |
| 4045 |
|
small => 1, span => 1, strong => 1, strike => 1, sub => 1, |
| 4046 |
|
sup => 1, table => 1, tt => 1, u => 1, ul => 1, var => 1, |
| 4047 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 4048 |
!!!cp ('t87.2'); |
!!!cp ('t87.2'); |
| 4049 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 4054 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} |
| 4055 |
while $self->{open_elements}->[-1]->[1] & FOREIGN_EL; |
while $self->{open_elements}->[-1]->[1] & FOREIGN_EL; |
| 4056 |
|
|
| 4057 |
$self->{insertion_mode} &= ~ $self->{insertion_mode}; |
$self->{insertion_mode} &= ~ IN_FOREIGN_CONTENT_IM; |
| 4058 |
## Reprocess. |
## Reprocess. |
| 4059 |
next B; |
next B; |
| 4060 |
} else { |
} else { |
| 4061 |
## TODO: case fixup |
my $nsuri = $self->{open_elements}->[-1]->[0]->namespace_uri; |
| 4062 |
|
my $tag_name = $token->{tag_name}; |
| 4063 |
|
if ($nsuri eq $SVG_NS) { |
| 4064 |
|
$tag_name = { |
| 4065 |
|
altglyph => 'altGlyph', |
| 4066 |
|
altglyphdef => 'altGlyphDef', |
| 4067 |
|
altglyphitem => 'altGlyphItem', |
| 4068 |
|
animatecolor => 'animateColor', |
| 4069 |
|
animatemotion => 'animateMotion', |
| 4070 |
|
animatetransform => 'animateTransform', |
| 4071 |
|
clippath => 'clipPath', |
| 4072 |
|
feblend => 'feBlend', |
| 4073 |
|
fecolormatrix => 'feColorMatrix', |
| 4074 |
|
fecomponenttransfer => 'feComponentTransfer', |
| 4075 |
|
fecomposite => 'feComposite', |
| 4076 |
|
feconvolvematrix => 'feConvolveMatrix', |
| 4077 |
|
fediffuselighting => 'feDiffuseLighting', |
| 4078 |
|
fedisplacementmap => 'feDisplacementMap', |
| 4079 |
|
fedistantlight => 'feDistantLight', |
| 4080 |
|
feflood => 'feFlood', |
| 4081 |
|
fefunca => 'feFuncA', |
| 4082 |
|
fefuncb => 'feFuncB', |
| 4083 |
|
fefuncg => 'feFuncG', |
| 4084 |
|
fefuncr => 'feFuncR', |
| 4085 |
|
fegaussianblur => 'feGaussianBlur', |
| 4086 |
|
feimage => 'feImage', |
| 4087 |
|
femerge => 'feMerge', |
| 4088 |
|
femergenode => 'feMergeNode', |
| 4089 |
|
femorphology => 'feMorphology', |
| 4090 |
|
feoffset => 'feOffset', |
| 4091 |
|
fepointlight => 'fePointLight', |
| 4092 |
|
fespecularlighting => 'feSpecularLighting', |
| 4093 |
|
fespotlight => 'feSpotLight', |
| 4094 |
|
fetile => 'feTile', |
| 4095 |
|
feturbulence => 'feTurbulence', |
| 4096 |
|
foreignobject => 'foreignObject', |
| 4097 |
|
glyphref => 'glyphRef', |
| 4098 |
|
lineargradient => 'linearGradient', |
| 4099 |
|
radialgradient => 'radialGradient', |
| 4100 |
|
#solidcolor => 'solidColor', ## NOTE: Commented in spec (SVG1.2) |
| 4101 |
|
textpath => 'textPath', |
| 4102 |
|
}->{$tag_name} || $tag_name; |
| 4103 |
|
} |
| 4104 |
|
|
| 4105 |
|
## "adjust SVG attributes" (SVG only) - done in insert-element-f |
| 4106 |
|
|
| 4107 |
!!!insert-element-f ($self->{open_elements}->[-1]->[0]->namespace_uri, $token); |
## "adjust foreign attributes" - done in insert-element-f |
| 4108 |
|
|
| 4109 |
|
!!!insert-element-f ($nsuri, $tag_name, $token->{attributes}, $token); |
| 4110 |
|
|
| 4111 |
if ($self->{self_closing}) { |
if ($self->{self_closing}) { |
| 4112 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4123 |
!!!cp ('t87.5'); |
!!!cp ('t87.5'); |
| 4124 |
# |
# |
| 4125 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
|
## NOTE: "using the rules for secondary insertion mode" then "continue" |
|
| 4126 |
!!!cp ('t87.6'); |
!!!cp ('t87.6'); |
| 4127 |
# |
!!!parse-error (type => 'not closed', |
| 4128 |
## TODO: ... |
value => $self->{open_elements}->[-1]->[0] |
| 4129 |
|
->manakai_local_name, |
| 4130 |
|
token => $token); |
| 4131 |
|
|
| 4132 |
|
pop @{$self->{open_elements}} |
| 4133 |
|
while $self->{open_elements}->[-1]->[1] & FOREIGN_EL; |
| 4134 |
|
|
| 4135 |
|
$self->{insertion_mode} &= ~ IN_FOREIGN_CONTENT_IM; |
| 4136 |
|
## Reprocess. |
| 4137 |
|
next B; |
| 4138 |
} else { |
} else { |
| 4139 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 4140 |
} |
} |
| 4211 |
!!!next-token; |
!!!next-token; |
| 4212 |
next B; |
next B; |
| 4213 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4214 |
!!!cp ('t94'); |
!!!cp ('t93.2'); |
| 4215 |
# |
!!!parse-error (type => 'after head:head', token => $token); ## TODO: error type |
| 4216 |
|
## Ignore the token |
| 4217 |
|
!!!nack ('t93.3'); |
| 4218 |
|
!!!next-token; |
| 4219 |
|
next B; |
| 4220 |
} else { |
} else { |
| 4221 |
!!!cp ('t95'); |
!!!cp ('t95'); |
| 4222 |
!!!parse-error (type => 'in head:head', token => $token); # or in head noscript |
!!!parse-error (type => 'in head:head', token => $token); # or in head noscript |
| 4299 |
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. |
| 4300 |
|
|
| 4301 |
unless ($self->{confident}) { |
unless ($self->{confident}) { |
| 4302 |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
if ($token->{attributes}->{charset}) { |
| 4303 |
!!!cp ('t106'); |
!!!cp ('t106'); |
| 4304 |
|
## NOTE: Whether the encoding is supported or not is handled |
| 4305 |
|
## in the {change_encoding} callback. |
| 4306 |
$self->{change_encoding} |
$self->{change_encoding} |
| 4307 |
->($self, $token->{attributes}->{charset}->{value}, |
->($self, $token->{attributes}->{charset}->{value}, |
| 4308 |
$token); |
$token); |
| 4312 |
$token->{attributes}->{charset} |
$token->{attributes}->{charset} |
| 4313 |
->{has_reference}); |
->{has_reference}); |
| 4314 |
} elsif ($token->{attributes}->{content}) { |
} elsif ($token->{attributes}->{content}) { |
|
## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition. |
|
| 4315 |
if ($token->{attributes}->{content}->{value} |
if ($token->{attributes}->{content}->{value} |
| 4316 |
=~ /\A[^;]*;[\x09-\x0D\x20]*[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
=~ /[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
| 4317 |
[\x09-\x0D\x20]*= |
[\x09-\x0D\x20]*= |
| 4318 |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
| 4319 |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20\x3B]*))/x) { |
| 4320 |
!!!cp ('t107'); |
!!!cp ('t107'); |
| 4321 |
|
## NOTE: Whether the encoding is supported or not is handled |
| 4322 |
|
## in the {change_encoding} callback. |
| 4323 |
$self->{change_encoding} |
$self->{change_encoding} |
| 4324 |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3, |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3, |
| 4325 |
$token); |
$token); |
| 4378 |
pop @{$self->{open_elements}} # <head> |
pop @{$self->{open_elements}} # <head> |
| 4379 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 4380 |
next B; |
next B; |
| 4381 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($token->{tag_name} eq 'style' or |
| 4382 |
|
$token->{tag_name} eq 'noframes') { |
| 4383 |
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
| 4384 |
## insertion mode IN_HEAD_IM) |
## insertion mode IN_HEAD_IM) |
| 4385 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4539 |
$self->{insertion_mode} = AFTER_HEAD_IM; |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4540 |
!!!next-token; |
!!!next-token; |
| 4541 |
next B; |
next B; |
| 4542 |
|
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4543 |
|
!!!cp ('t134.1'); |
| 4544 |
|
!!!parse-error (type => 'unmatched end tag:head', token => $token); |
| 4545 |
|
## Ignore the token |
| 4546 |
|
!!!next-token; |
| 4547 |
|
next B; |
| 4548 |
} else { |
} else { |
| 4549 |
!!!cp ('t135'); |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
|
# |
|
| 4550 |
} |
} |
| 4551 |
} elsif ($token->{tag_name} eq 'noscript') { |
} elsif ($token->{tag_name} eq 'noscript') { |
| 4552 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4555 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4556 |
!!!next-token; |
!!!next-token; |
| 4557 |
next B; |
next B; |
| 4558 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM or |
| 4559 |
|
$self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4560 |
!!!cp ('t137'); |
!!!cp ('t137'); |
| 4561 |
!!!parse-error (type => 'unmatched end tag:noscript', token => $token); |
!!!parse-error (type => 'unmatched end tag:noscript', token => $token); |
| 4562 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 4569 |
} elsif ({ |
} elsif ({ |
| 4570 |
body => 1, html => 1, |
body => 1, html => 1, |
| 4571 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 4572 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM or |
| 4573 |
!!!cp ('t139'); |
$self->{insertion_mode} == IN_HEAD_IM or |
| 4574 |
## As if <head> |
$self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
|
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
|
|
push @{$self->{open_elements}}, |
|
|
[$self->{head_element}, $el_category->{head}]; |
|
|
|
|
|
$self->{insertion_mode} = IN_HEAD_IM; |
|
|
## Reprocess in the "in head" insertion mode... |
|
|
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
|
| 4575 |
!!!cp ('t140'); |
!!!cp ('t140'); |
| 4576 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4577 |
## Ignore the token |
## Ignore the token |
| 4578 |
!!!next-token; |
!!!next-token; |
| 4579 |
next B; |
next B; |
| 4580 |
|
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4581 |
|
!!!cp ('t140.1'); |
| 4582 |
|
!!!parse-error (type => 'unmatched end tag:' . $token->{tag_name}, token => $token); |
| 4583 |
|
## Ignore the token |
| 4584 |
|
!!!next-token; |
| 4585 |
|
next B; |
| 4586 |
} else { |
} else { |
| 4587 |
!!!cp ('t141'); |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
| 4588 |
} |
} |
| 4589 |
|
} elsif ($token->{tag_name} eq 'p') { |
| 4590 |
# |
!!!cp ('t142'); |
| 4591 |
} elsif ({ |
!!!parse-error (type => 'unmatched end tag:p', token => $token); |
| 4592 |
p => 1, br => 1, |
## Ignore the token |
| 4593 |
}->{$token->{tag_name}}) { |
!!!next-token; |
| 4594 |
|
next B; |
| 4595 |
|
} elsif ($token->{tag_name} eq 'br') { |
| 4596 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4597 |
!!!cp ('t142'); |
!!!cp ('t142.2'); |
| 4598 |
## As if <head> |
## (before head) as if <head>, (in head) as if </head> |
| 4599 |
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
| 4600 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 4601 |
push @{$self->{open_elements}}, |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4602 |
[$self->{head_element}, $el_category->{head}]; |
|
| 4603 |
|
## Reprocess in the "after head" insertion mode... |
| 4604 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 4605 |
|
!!!cp ('t143.2'); |
| 4606 |
|
## As if </head> |
| 4607 |
|
pop @{$self->{open_elements}}; |
| 4608 |
|
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4609 |
|
|
| 4610 |
|
## Reprocess in the "after head" insertion mode... |
| 4611 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4612 |
|
!!!cp ('t143.3'); |
| 4613 |
|
## ISSUE: Two parse errors for <head><noscript></br> |
| 4614 |
|
!!!parse-error (type => 'unmatched end tag:br', token => $token); |
| 4615 |
|
## As if </noscript> |
| 4616 |
|
pop @{$self->{open_elements}}; |
| 4617 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4618 |
|
|
| 4619 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4620 |
} else { |
## As if </head> |
| 4621 |
!!!cp ('t143'); |
pop @{$self->{open_elements}}; |
| 4622 |
} |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4623 |
|
|
| 4624 |
# |
## Reprocess in the "after head" insertion mode... |
| 4625 |
} else { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4626 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
!!!cp ('t143.4'); |
|
!!!cp ('t144'); |
|
| 4627 |
# |
# |
| 4628 |
} else { |
} else { |
| 4629 |
!!!cp ('t145'); |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
next B; |
|
| 4630 |
} |
} |
| 4631 |
|
|
| 4632 |
|
## ISSUE: does not agree with IE7 - it doesn't ignore </br>. |
| 4633 |
|
!!!parse-error (type => 'unmatched end tag:br', token => $token); |
| 4634 |
|
## Ignore the token |
| 4635 |
|
!!!next-token; |
| 4636 |
|
next B; |
| 4637 |
|
} else { |
| 4638 |
|
!!!cp ('t145'); |
| 4639 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4640 |
|
## Ignore the token |
| 4641 |
|
!!!next-token; |
| 4642 |
|
next B; |
| 4643 |
} |
} |
| 4644 |
|
|
| 4645 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 5393 |
next B; |
next B; |
| 5394 |
} |
} |
| 5395 |
|
|
| 5396 |
## TODO: Followings are removed from the latest spec. |
## TODO: Followings are removed from the latest spec. |
| 5397 |
## generate implied end tags |
## generate implied end tags |
| 5398 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 5399 |
!!!cp ('t224'); |
!!!cp ('t224'); |
| 5891 |
!!!nack ('t277.1'); |
!!!nack ('t277.1'); |
| 5892 |
!!!next-token; |
!!!next-token; |
| 5893 |
next B; |
next B; |
| 5894 |
} elsif ($token->{tag_name} eq 'select' or |
} elsif ({ |
| 5895 |
$token->{tag_name} eq 'input' or |
select => 1, input => 1, textarea => 1, |
| 5896 |
|
}->{$token->{tag_name}} or |
| 5897 |
($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
| 5898 |
{ |
{ |
| 5899 |
caption => 1, table => 1, |
caption => 1, table => 1, |
| 6250 |
next B; |
next B; |
| 6251 |
} elsif ($token->{tag_name} eq 'noframes') { |
} elsif ($token->{tag_name} eq 'noframes') { |
| 6252 |
!!!cp ('t320'); |
!!!cp ('t320'); |
| 6253 |
## NOTE: As if in body. |
## NOTE: As if in head. |
| 6254 |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 6255 |
next B; |
next B; |
| 6256 |
} else { |
} else { |
| 6365 |
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. |
| 6366 |
|
|
| 6367 |
unless ($self->{confident}) { |
unless ($self->{confident}) { |
| 6368 |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
if ($token->{attributes}->{charset}) { |
| 6369 |
!!!cp ('t335'); |
!!!cp ('t335'); |
| 6370 |
|
## NOTE: Whether the encoding is supported or not is handled |
| 6371 |
|
## in the {change_encoding} callback. |
| 6372 |
$self->{change_encoding} |
$self->{change_encoding} |
| 6373 |
->($self, $token->{attributes}->{charset}->{value}, $token); |
->($self, $token->{attributes}->{charset}->{value}, $token); |
| 6374 |
|
|
| 6377 |
$token->{attributes}->{charset} |
$token->{attributes}->{charset} |
| 6378 |
->{has_reference}); |
->{has_reference}); |
| 6379 |
} elsif ($token->{attributes}->{content}) { |
} elsif ($token->{attributes}->{content}) { |
|
## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition. |
|
| 6380 |
if ($token->{attributes}->{content}->{value} |
if ($token->{attributes}->{content}->{value} |
| 6381 |
=~ /\A[^;]*;[\x09-\x0D\x20]*[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
=~ /[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
| 6382 |
[\x09-\x0D\x20]*= |
[\x09-\x0D\x20]*= |
| 6383 |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
| 6384 |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20\x3B]*))/x) { |
| 6385 |
!!!cp ('t336'); |
!!!cp ('t336'); |
| 6386 |
|
## NOTE: Whether the encoding is supported or not is handled |
| 6387 |
|
## in the {change_encoding} callback. |
| 6388 |
$self->{change_encoding} |
$self->{change_encoding} |
| 6389 |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3, $token); |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3, $token); |
| 6390 |
$meta_el->[0]->get_attribute_node_ns (undef, 'content') |
$meta_el->[0]->get_attribute_node_ns (undef, 'content') |
| 6693 |
xmp => 1, |
xmp => 1, |
| 6694 |
iframe => 1, |
iframe => 1, |
| 6695 |
noembed => 1, |
noembed => 1, |
| 6696 |
noframes => 1, |
noframes => 1, ## NOTE: This is an "as if in head" code clone. |
| 6697 |
noscript => 0, ## TODO: 1 if scripting is enabled |
noscript => 0, ## TODO: 1 if scripting is enabled |
| 6698 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6699 |
if ($token->{tag_name} eq 'xmp') { |
if ($token->{tag_name} eq 'xmp') { |
| 6715 |
!!!next-token; |
!!!next-token; |
| 6716 |
next B; |
next B; |
| 6717 |
} else { |
} else { |
| 6718 |
|
!!!ack ('t391.1'); |
| 6719 |
|
|
| 6720 |
my $at = $token->{attributes}; |
my $at = $token->{attributes}; |
| 6721 |
my $form_attrs; |
my $form_attrs; |
| 6722 |
$form_attrs->{action} = $at->{action} if $at->{action}; |
$form_attrs->{action} = $at->{action} if $at->{action}; |
| 6760 |
line => $token->{line}, column => $token->{column}}, |
line => $token->{line}, column => $token->{column}}, |
| 6761 |
{type => END_TAG_TOKEN, tag_name => 'form', |
{type => END_TAG_TOKEN, tag_name => 'form', |
| 6762 |
line => $token->{line}, column => $token->{column}}; |
line => $token->{line}, column => $token->{column}}; |
|
!!!nack ('t391.1'); ## NOTE: Not acknowledged. |
|
| 6763 |
!!!back-token (@tokens); |
!!!back-token (@tokens); |
| 6764 |
!!!next-token; |
!!!next-token; |
| 6765 |
next B; |
next B; |
| 6811 |
} |
} |
| 6812 |
!!!next-token; |
!!!next-token; |
| 6813 |
next B; |
next B; |
| 6814 |
|
} elsif ($token->{tag_name} eq 'rt' or |
| 6815 |
|
$token->{tag_name} eq 'rp') { |
| 6816 |
|
## has a |ruby| element in scope |
| 6817 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 6818 |
|
my $node = $self->{open_elements}->[$_]; |
| 6819 |
|
if ($node->[1] & RUBY_EL) { |
| 6820 |
|
!!!cp ('t398.1'); |
| 6821 |
|
## generate implied end tags |
| 6822 |
|
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 6823 |
|
!!!cp ('t398.2'); |
| 6824 |
|
pop @{$self->{open_elements}}; |
| 6825 |
|
} |
| 6826 |
|
unless ($self->{open_elements}->[-1]->[1] & RUBY_EL) { |
| 6827 |
|
!!!cp ('t398.3'); |
| 6828 |
|
!!!parse-error (type => 'not closed', |
| 6829 |
|
value => $self->{open_elements}->[-1]->[0] |
| 6830 |
|
->manakai_local_name, |
| 6831 |
|
token => $token); |
| 6832 |
|
pop @{$self->{open_elements}} |
| 6833 |
|
while not $self->{open_elements}->[-1]->[1] & RUBY_EL; |
| 6834 |
|
} |
| 6835 |
|
last INSCOPE; |
| 6836 |
|
} elsif ($node->[1] & SCOPING_EL) { |
| 6837 |
|
!!!cp ('t398.4'); |
| 6838 |
|
last INSCOPE; |
| 6839 |
|
} |
| 6840 |
|
} # INSCOPE |
| 6841 |
|
|
| 6842 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 6843 |
|
|
| 6844 |
|
!!!nack ('t398.5'); |
| 6845 |
|
!!!next-token; |
| 6846 |
|
redo B; |
| 6847 |
} elsif ($token->{tag_name} eq 'math' or |
} elsif ($token->{tag_name} eq 'math' or |
| 6848 |
$token->{tag_name} eq 'svg') { |
$token->{tag_name} eq 'svg') { |
| 6849 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 6850 |
|
|
| 6851 |
|
## "adjust SVG attributes" ('svg' only) - done in insert-element-f |
| 6852 |
|
|
| 6853 |
|
## "adjust foreign attributes" - done in insert-element-f |
| 6854 |
|
|
| 6855 |
!!!insert-element-f ($token->{tag_name} eq 'math' ? $MML_NS : $SVG_NS, $token); |
!!!insert-element-f ($token->{tag_name} eq 'math' ? $MML_NS : $SVG_NS, $token->{tag_name}, $token->{attributes}, $token); |
| 6856 |
|
|
| 6857 |
if ($self->{self_closing}) { |
if ($self->{self_closing}) { |
| 6858 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 7032 |
} else { |
} else { |
| 7033 |
## Step 1. generate implied end tags |
## Step 1. generate implied end tags |
| 7034 |
while ({ |
while ({ |
| 7035 |
|
## END_TAG_OPTIONAL_EL |
| 7036 |
dd => ($token->{tag_name} ne 'dd'), |
dd => ($token->{tag_name} ne 'dd'), |
| 7037 |
dt => ($token->{tag_name} ne 'dt'), |
dt => ($token->{tag_name} ne 'dt'), |
| 7038 |
li => ($token->{tag_name} ne 'li'), |
li => ($token->{tag_name} ne 'li'), |
| 7039 |
p => 1, |
p => 1, |
| 7040 |
|
rt => 1, |
| 7041 |
|
rp => 1, |
| 7042 |
}->{$self->{open_elements}->[-1]->[0]->manakai_local_name}) { |
}->{$self->{open_elements}->[-1]->[0]->manakai_local_name}) { |
| 7043 |
!!!cp ('t409'); |
!!!cp ('t409'); |
| 7044 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 7251 |
## generate implied end tags |
## generate implied end tags |
| 7252 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 7253 |
!!!cp ('t430'); |
!!!cp ('t430'); |
| 7254 |
## ISSUE: Can this case be reached? |
## NOTE: |<ruby><rt></ruby>|. |
| 7255 |
|
## ISSUE: <ruby><rt></rt> will also take this code path, |
| 7256 |
|
## which seems wrong. |
| 7257 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 7258 |
|
$node_i++; |
| 7259 |
} |
} |
| 7260 |
|
|
| 7261 |
## Step 2 |
## Step 2 |
| 7272 |
} |
} |
| 7273 |
|
|
| 7274 |
## Step 3 |
## Step 3 |
| 7275 |
splice @{$self->{open_elements}}, $node_i; |
splice @{$self->{open_elements}}, $node_i if $node_i < 0; |
| 7276 |
|
|
| 7277 |
!!!next-token; |
!!!next-token; |
| 7278 |
last S2; |
last S2; |
| 7398 |
!!!cp ('i4'); |
!!!cp ('i4'); |
| 7399 |
!!!parse-error (type => 'NULL'); |
!!!parse-error (type => 'NULL'); |
| 7400 |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
| 7401 |
|
} elsif ($self->{next_char} <= 0x0008 or |
| 7402 |
|
(0x000E <= $self->{next_char} and |
| 7403 |
|
$self->{next_char} <= 0x001F) or |
| 7404 |
|
(0x007F <= $self->{next_char} and |
| 7405 |
|
$self->{next_char} <= 0x009F) or |
| 7406 |
|
(0xD800 <= $self->{next_char} and |
| 7407 |
|
$self->{next_char} <= 0xDFFF) or |
| 7408 |
|
(0xFDD0 <= $self->{next_char} and |
| 7409 |
|
$self->{next_char} <= 0xFDDF) or |
| 7410 |
|
{ |
| 7411 |
|
0xFFFE => 1, 0xFFFF => 1, 0x1FFFE => 1, 0x1FFFF => 1, |
| 7412 |
|
0x2FFFE => 1, 0x2FFFF => 1, 0x3FFFE => 1, 0x3FFFF => 1, |
| 7413 |
|
0x4FFFE => 1, 0x4FFFF => 1, 0x5FFFE => 1, 0x5FFFF => 1, |
| 7414 |
|
0x6FFFE => 1, 0x6FFFF => 1, 0x7FFFE => 1, 0x7FFFF => 1, |
| 7415 |
|
0x8FFFE => 1, 0x8FFFF => 1, 0x9FFFE => 1, 0x9FFFF => 1, |
| 7416 |
|
0xAFFFE => 1, 0xAFFFF => 1, 0xBFFFE => 1, 0xBFFFF => 1, |
| 7417 |
|
0xCFFFE => 1, 0xCFFFF => 1, 0xDFFFE => 1, 0xDFFFF => 1, |
| 7418 |
|
0xEFFFE => 1, 0xEFFFF => 1, 0xFFFFE => 1, 0xFFFFF => 1, |
| 7419 |
|
0x10FFFE => 1, 0x10FFFF => 1, |
| 7420 |
|
}->{$self->{next_char}}) { |
| 7421 |
|
!!!cp ('i4.1'); |
| 7422 |
|
!!!parse-error (type => 'control char', level => $self->{must_level}); |
| 7423 |
|
## TODO: error type documentation |
| 7424 |
} |
} |
| 7425 |
}; |
}; |
| 7426 |
$p->{prev_char} = [-1, -1, -1]; |
$p->{prev_char} = [-1, -1, -1]; |