| 74 |
textarea => 1, tfoot => 1, thead => 1, title => 1, tr => 1, ul => 1, wbr => 1, |
textarea => 1, tfoot => 1, thead => 1, title => 1, tr => 1, ul => 1, wbr => 1, |
| 75 |
}; |
}; |
| 76 |
my $scoping_category = { |
my $scoping_category = { |
| 77 |
button => 1, caption => 1, html => 1, marquee => 1, object => 1, |
applet => 1, button => 1, caption => 1, html => 1, marquee => 1, object => 1, |
| 78 |
table => 1, td => 1, th => 1, |
table => 1, td => 1, th => 1, |
| 79 |
}; |
}; |
| 80 |
my $formatting_category = { |
my $formatting_category = { |
| 108 |
$self->{change_encoding} = sub { |
$self->{change_encoding} = sub { |
| 109 |
my $self = shift; |
my $self = shift; |
| 110 |
my $charset = lc shift; |
my $charset = lc shift; |
| 111 |
|
my $token = shift; |
| 112 |
## TODO: if $charset is supported |
## TODO: if $charset is supported |
| 113 |
## TODO: normalize charset name |
## TODO: normalize charset name |
| 114 |
|
|
| 127 |
} |
} |
| 128 |
|
|
| 129 |
!!!parse-error (type => 'charset label detected:'.$self->{input_encoding}. |
!!!parse-error (type => 'charset label detected:'.$self->{input_encoding}. |
| 130 |
':'.$charset, level => 'w'); |
':'.$charset, level => 'w', token => $token); |
| 131 |
|
|
| 132 |
## Step 3 |
## Step 3 |
| 133 |
# if (can) { |
# if (can) { |
| 178 |
if defined $self->{input_encoding}; |
if defined $self->{input_encoding}; |
| 179 |
|
|
| 180 |
my $i = 0; |
my $i = 0; |
| 181 |
my $line = 1; |
$self->{line_prev} = $self->{line} = 1; |
| 182 |
my $column = 0; |
$self->{column_prev} = $self->{column} = 0; |
| 183 |
$self->{set_next_char} = sub { |
$self->{set_next_char} = sub { |
| 184 |
my $self = shift; |
my $self = shift; |
| 185 |
|
|
| 188 |
|
|
| 189 |
$self->{next_char} = -1 and return if $i >= length $$s; |
$self->{next_char} = -1 and return if $i >= length $$s; |
| 190 |
$self->{next_char} = ord substr $$s, $i++, 1; |
$self->{next_char} = ord substr $$s, $i++, 1; |
| 191 |
$column++; |
|
| 192 |
|
($self->{line_prev}, $self->{column_prev}) |
| 193 |
|
= ($self->{line}, $self->{column}); |
| 194 |
|
$self->{column}++; |
| 195 |
|
|
| 196 |
if ($self->{next_char} == 0x000A) { # LF |
if ($self->{next_char} == 0x000A) { # LF |
| 197 |
$line++; |
$self->{line}++; |
| 198 |
$column = 0; |
$self->{column} = 0; |
| 199 |
} elsif ($self->{next_char} == 0x000D) { # CR |
} elsif ($self->{next_char} == 0x000D) { # CR |
| 200 |
$i++ if substr ($$s, $i, 1) eq "\x0A"; |
$i++ if substr ($$s, $i, 1) eq "\x0A"; |
| 201 |
$self->{next_char} = 0x000A; # LF # MUST |
$self->{next_char} = 0x000A; # LF # MUST |
| 202 |
$line++; |
$self->{line}++; |
| 203 |
$column = 0; |
$self->{column} = 0; |
| 204 |
} elsif ($self->{next_char} > 0x10FFFF) { |
} elsif ($self->{next_char} > 0x10FFFF) { |
| 205 |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
| 206 |
} elsif ($self->{next_char} == 0x0000) { # NULL |
} elsif ($self->{next_char} == 0x0000) { # NULL |
| 213 |
|
|
| 214 |
my $onerror = $_[2] || sub { |
my $onerror = $_[2] || sub { |
| 215 |
my (%opt) = @_; |
my (%opt) = @_; |
| 216 |
warn "Parse error ($opt{type}) at line $opt{line} column $opt{column}\n"; |
my $line = $opt{token} ? $opt{token}->{line} : $opt{line}; |
| 217 |
|
my $column = $opt{token} ? $opt{token}->{column} : $opt{column}; |
| 218 |
|
warn "Parse error ($opt{type}) at line $line column $column\n"; |
| 219 |
}; |
}; |
| 220 |
$self->{parse_error} = sub { |
$self->{parse_error} = sub { |
| 221 |
$onerror->(@_, line => $line, column => $column); |
$onerror->(line => $self->{line}, column => $self->{column}, @_); |
| 222 |
}; |
}; |
| 223 |
|
|
| 224 |
$self->_initialize_tokenizer; |
$self->_initialize_tokenizer; |
| 226 |
$self->_construct_tree; |
$self->_construct_tree; |
| 227 |
$self->_terminate_tree_constructor; |
$self->_terminate_tree_constructor; |
| 228 |
|
|
| 229 |
|
delete $self->{parse_error}; # remove loop |
| 230 |
|
|
| 231 |
return $self->{document}; |
return $self->{document}; |
| 232 |
} # parse_string |
} # parse_string |
| 233 |
|
|
| 311 |
sub ROW_IMS () { 0b10000000 } |
sub ROW_IMS () { 0b10000000 } |
| 312 |
sub BODY_AFTER_IMS () { 0b100000000 } |
sub BODY_AFTER_IMS () { 0b100000000 } |
| 313 |
sub FRAME_IMS () { 0b1000000000 } |
sub FRAME_IMS () { 0b1000000000 } |
| 314 |
|
sub SELECT_IMS () { 0b10000000000 } |
| 315 |
|
|
| 316 |
## NOTE: "initial" and "before html" insertion modes have no constants. |
## NOTE: "initial" and "before html" insertion modes have no constants. |
| 317 |
|
|
| 334 |
sub AFTER_BODY_IM () { BODY_AFTER_IMS } |
sub AFTER_BODY_IM () { BODY_AFTER_IMS } |
| 335 |
sub IN_FRAMESET_IM () { FRAME_IMS | 0b01 } |
sub IN_FRAMESET_IM () { FRAME_IMS | 0b01 } |
| 336 |
sub AFTER_FRAMESET_IM () { FRAME_IMS | 0b10 } |
sub AFTER_FRAMESET_IM () { FRAME_IMS | 0b10 } |
| 337 |
sub IN_SELECT_IM () { 0b01 } |
sub IN_SELECT_IM () { SELECT_IMS | 0b01 } |
| 338 |
|
sub IN_SELECT_IN_TABLE_IM () { SELECT_IMS | 0b10 } |
| 339 |
sub IN_COLUMN_GROUP_IM () { 0b10 } |
sub IN_COLUMN_GROUP_IM () { 0b10 } |
| 340 |
|
|
| 341 |
## Implementations MUST act as if state machine in the spec |
## Implementations MUST act as if state machine in the spec |
| 457 |
# |
# |
| 458 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 459 |
!!!cp (11); |
!!!cp (11); |
| 460 |
!!!emit ({type => END_OF_FILE_TOKEN}); |
!!!emit ({type => END_OF_FILE_TOKEN, |
| 461 |
|
line => $self->{line}, column => $self->{column}}); |
| 462 |
last A; ## TODO: ok? |
last A; ## TODO: ok? |
| 463 |
} else { |
} else { |
| 464 |
!!!cp (12); |
!!!cp (12); |
| 465 |
} |
} |
| 466 |
# Anything else |
# Anything else |
| 467 |
my $token = {type => CHARACTER_TOKEN, |
my $token = {type => CHARACTER_TOKEN, |
| 468 |
data => chr $self->{next_char}}; |
data => chr $self->{next_char}, |
| 469 |
|
#line => $self->{line}, column => $self->{column}, |
| 470 |
|
}; |
| 471 |
## Stay in the data state |
## Stay in the data state |
| 472 |
!!!next-input-character; |
!!!next-input-character; |
| 473 |
|
|
| 476 |
redo A; |
redo A; |
| 477 |
} elsif ($self->{state} == ENTITY_DATA_STATE) { |
} elsif ($self->{state} == ENTITY_DATA_STATE) { |
| 478 |
## (cannot happen in CDATA state) |
## (cannot happen in CDATA state) |
| 479 |
|
|
| 480 |
|
#my ($l, $c) = ($self->{line_prev}, $self->{column_prev}); |
| 481 |
|
|
| 482 |
my $token = $self->_tokenize_attempt_to_consume_an_entity (0, -1); |
my $token = $self->_tokenize_attempt_to_consume_an_entity (0, -1); |
| 483 |
|
|
| 486 |
|
|
| 487 |
unless (defined $token) { |
unless (defined $token) { |
| 488 |
!!!cp (13); |
!!!cp (13); |
| 489 |
!!!emit ({type => CHARACTER_TOKEN, data => '&'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '&', |
| 490 |
|
#line => $l, column => $c, |
| 491 |
|
}); |
| 492 |
} else { |
} else { |
| 493 |
!!!cp (14); |
!!!cp (14); |
| 494 |
!!!emit ($token); |
!!!emit ($token); |
| 507 |
## reconsume |
## reconsume |
| 508 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 509 |
|
|
| 510 |
!!!emit ({type => CHARACTER_TOKEN, data => '<'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '<', |
| 511 |
|
#line => $self->{line_prev}, |
| 512 |
|
#column => $self->{column_prev}, |
| 513 |
|
}); |
| 514 |
|
|
| 515 |
redo A; |
redo A; |
| 516 |
} |
} |
| 530 |
!!!cp (19); |
!!!cp (19); |
| 531 |
$self->{current_token} |
$self->{current_token} |
| 532 |
= {type => START_TAG_TOKEN, |
= {type => START_TAG_TOKEN, |
| 533 |
tag_name => chr ($self->{next_char} + 0x0020)}; |
tag_name => chr ($self->{next_char} + 0x0020), |
| 534 |
|
line => $self->{line_prev}, |
| 535 |
|
column => $self->{column_prev}}; |
| 536 |
$self->{state} = TAG_NAME_STATE; |
$self->{state} = TAG_NAME_STATE; |
| 537 |
!!!next-input-character; |
!!!next-input-character; |
| 538 |
redo A; |
redo A; |
| 540 |
$self->{next_char} <= 0x007A) { # a..z |
$self->{next_char} <= 0x007A) { # a..z |
| 541 |
!!!cp (20); |
!!!cp (20); |
| 542 |
$self->{current_token} = {type => START_TAG_TOKEN, |
$self->{current_token} = {type => START_TAG_TOKEN, |
| 543 |
tag_name => chr ($self->{next_char})}; |
tag_name => chr ($self->{next_char}), |
| 544 |
|
line => $self->{line_prev}, |
| 545 |
|
column => $self->{column_prev}}; |
| 546 |
$self->{state} = TAG_NAME_STATE; |
$self->{state} = TAG_NAME_STATE; |
| 547 |
!!!next-input-character; |
!!!next-input-character; |
| 548 |
redo A; |
redo A; |
| 549 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 550 |
!!!cp (21); |
!!!cp (21); |
| 551 |
!!!parse-error (type => 'empty start tag'); |
!!!parse-error (type => 'empty start tag', |
| 552 |
|
line => $self->{line_prev}, |
| 553 |
|
column => $self->{column_prev}); |
| 554 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 555 |
!!!next-input-character; |
!!!next-input-character; |
| 556 |
|
|
| 557 |
!!!emit ({type => CHARACTER_TOKEN, data => '<>'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '<>', |
| 558 |
|
#line => $self->{line_prev}, |
| 559 |
|
#column => $self->{column_prev}, |
| 560 |
|
}); |
| 561 |
|
|
| 562 |
redo A; |
redo A; |
| 563 |
} elsif ($self->{next_char} == 0x003F) { # ? |
} elsif ($self->{next_char} == 0x003F) { # ? |
| 564 |
!!!cp (22); |
!!!cp (22); |
| 565 |
!!!parse-error (type => 'pio'); |
!!!parse-error (type => 'pio', |
| 566 |
|
line => $self->{line_prev}, |
| 567 |
|
column => $self->{column_prev}); |
| 568 |
$self->{state} = BOGUS_COMMENT_STATE; |
$self->{state} = BOGUS_COMMENT_STATE; |
| 569 |
|
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
| 570 |
|
#line => $self->{line_prev}, |
| 571 |
|
#column => $self->{column_prev}, |
| 572 |
|
}; |
| 573 |
## $self->{next_char} is intentionally left as is |
## $self->{next_char} is intentionally left as is |
| 574 |
redo A; |
redo A; |
| 575 |
} else { |
} else { |
| 578 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 579 |
## reconsume |
## reconsume |
| 580 |
|
|
| 581 |
!!!emit ({type => CHARACTER_TOKEN, data => '<'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '<', |
| 582 |
|
#line => $self->{line_prev}, |
| 583 |
|
#column => $self->{column_prev}, |
| 584 |
|
}); |
| 585 |
|
|
| 586 |
redo A; |
redo A; |
| 587 |
} |
} |
| 589 |
die "$0: $self->{content_model} in tag open"; |
die "$0: $self->{content_model} in tag open"; |
| 590 |
} |
} |
| 591 |
} elsif ($self->{state} == CLOSE_TAG_OPEN_STATE) { |
} elsif ($self->{state} == CLOSE_TAG_OPEN_STATE) { |
| 592 |
|
my ($l, $c) = ($self->{line_prev}, $self->{column_prev} - 1); # "<"of"</" |
| 593 |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
| 594 |
if (defined $self->{last_emitted_start_tag_name}) { |
if (defined $self->{last_emitted_start_tag_name}) { |
| 595 |
|
|
| 596 |
## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564> |
## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564> |
| 597 |
my @next_char; |
my @next_char; |
| 598 |
TAGNAME: for (my $i = 0; $i < length $self->{last_emitted_start_tag_name}; $i++) { |
TAGNAME: for (my $i = 0; $i < length $self->{last_emitted_start_tag_name}; $i++) { |
| 609 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 610 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 611 |
|
|
| 612 |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</', |
| 613 |
|
#line => $l, column => $c, |
| 614 |
|
}); |
| 615 |
|
|
| 616 |
redo A; |
redo A; |
| 617 |
} |
} |
| 630 |
$self->{next_char} = shift @next_char; # reconsume |
$self->{next_char} = shift @next_char; # reconsume |
| 631 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 632 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 633 |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</', |
| 634 |
|
#line => $l, column => $c, |
| 635 |
|
}); |
| 636 |
redo A; |
redo A; |
| 637 |
} else { |
} else { |
| 638 |
!!!cp (27); |
!!!cp (27); |
| 645 |
!!!cp (28); |
!!!cp (28); |
| 646 |
# next-input-character is already done |
# next-input-character is already done |
| 647 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 648 |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</', |
| 649 |
|
#line => $l, column => $c, |
| 650 |
|
}); |
| 651 |
redo A; |
redo A; |
| 652 |
} |
} |
| 653 |
} |
} |
| 655 |
if (0x0041 <= $self->{next_char} and |
if (0x0041 <= $self->{next_char} and |
| 656 |
$self->{next_char} <= 0x005A) { # A..Z |
$self->{next_char} <= 0x005A) { # A..Z |
| 657 |
!!!cp (29); |
!!!cp (29); |
| 658 |
$self->{current_token} = {type => END_TAG_TOKEN, |
$self->{current_token} |
| 659 |
tag_name => chr ($self->{next_char} + 0x0020)}; |
= {type => END_TAG_TOKEN, |
| 660 |
|
tag_name => chr ($self->{next_char} + 0x0020), |
| 661 |
|
line => $l, column => $c}; |
| 662 |
$self->{state} = TAG_NAME_STATE; |
$self->{state} = TAG_NAME_STATE; |
| 663 |
!!!next-input-character; |
!!!next-input-character; |
| 664 |
redo A; |
redo A; |
| 666 |
$self->{next_char} <= 0x007A) { # a..z |
$self->{next_char} <= 0x007A) { # a..z |
| 667 |
!!!cp (30); |
!!!cp (30); |
| 668 |
$self->{current_token} = {type => END_TAG_TOKEN, |
$self->{current_token} = {type => END_TAG_TOKEN, |
| 669 |
tag_name => chr ($self->{next_char})}; |
tag_name => chr ($self->{next_char}), |
| 670 |
|
line => $l, column => $c}; |
| 671 |
$self->{state} = TAG_NAME_STATE; |
$self->{state} = TAG_NAME_STATE; |
| 672 |
!!!next-input-character; |
!!!next-input-character; |
| 673 |
redo A; |
redo A; |
| 674 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 675 |
!!!cp (31); |
!!!cp (31); |
| 676 |
!!!parse-error (type => 'empty end tag'); |
!!!parse-error (type => 'empty end tag', |
| 677 |
|
line => $self->{line_prev}, ## "<" in "</>" |
| 678 |
|
column => $self->{column_prev} - 1); |
| 679 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 680 |
!!!next-input-character; |
!!!next-input-character; |
| 681 |
redo A; |
redo A; |
| 685 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 686 |
# reconsume |
# reconsume |
| 687 |
|
|
| 688 |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</', |
| 689 |
|
#line => $l, column => $c, |
| 690 |
|
}); |
| 691 |
|
|
| 692 |
redo A; |
redo A; |
| 693 |
} else { |
} else { |
| 694 |
!!!cp (33); |
!!!cp (33); |
| 695 |
!!!parse-error (type => 'bogus end tag'); |
!!!parse-error (type => 'bogus end tag'); |
| 696 |
$self->{state} = BOGUS_COMMENT_STATE; |
$self->{state} = BOGUS_COMMENT_STATE; |
| 697 |
|
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
| 698 |
|
#line => $self->{line_prev}, # "<" of "</" |
| 699 |
|
#column => $self->{column_prev} - 1, |
| 700 |
|
}; |
| 701 |
## $self->{next_char} is intentionally left as is |
## $self->{next_char} is intentionally left as is |
| 702 |
redo A; |
redo A; |
| 703 |
} |
} |
| 714 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 715 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 716 |
!!!cp (35); |
!!!cp (35); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 717 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 718 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 719 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 745 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 746 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 747 |
!!!cp (39); |
!!!cp (39); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 748 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 749 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 750 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 800 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 801 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 802 |
!!!cp (46); |
!!!cp (46); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 803 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 804 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 805 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 845 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 846 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 847 |
!!!cp (52); |
!!!cp (52); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 848 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 849 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 850 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 914 |
$before_leave->(); |
$before_leave->(); |
| 915 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 916 |
!!!cp (61); |
!!!cp (61); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 917 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 918 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 919 |
!!!cp (62); |
!!!cp (62); |
| 958 |
$before_leave->(); |
$before_leave->(); |
| 959 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 960 |
!!!cp (66); |
!!!cp (66); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 961 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 962 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 963 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1008 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1009 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1010 |
!!!cp (73); |
!!!cp (73); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1011 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1012 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1013 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1055 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 1056 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1057 |
!!!cp (79); |
!!!cp (79); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1058 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1059 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1060 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1110 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1111 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1112 |
!!!cp (87); |
!!!cp (87); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1113 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1114 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1115 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1133 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 1134 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1135 |
!!!cp (90); |
!!!cp (90); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1136 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1137 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1138 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1180 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
| 1181 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1182 |
!!!cp (97); |
!!!cp (97); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1183 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1184 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1185 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1222 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
| 1223 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1224 |
!!!cp (103); |
!!!cp (103); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1225 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1226 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1227 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1267 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1268 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1269 |
!!!cp (109); |
!!!cp (109); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1270 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1271 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1272 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1290 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 1291 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1292 |
!!!cp (112); |
!!!cp (112); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1293 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1294 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1295 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1360 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1361 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1362 |
!!!cp (119); |
!!!cp (119); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1363 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1364 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1365 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1404 |
} elsif ($self->{state} == BOGUS_COMMENT_STATE) { |
} elsif ($self->{state} == BOGUS_COMMENT_STATE) { |
| 1405 |
## (only happen if PCDATA state) |
## (only happen if PCDATA state) |
| 1406 |
|
|
| 1407 |
my $token = {type => COMMENT_TOKEN, data => ''}; |
## NOTE: Set by the previous state |
| 1408 |
|
#my $token = {type => COMMENT_TOKEN, data => ''}; |
| 1409 |
|
|
| 1410 |
BC: { |
BC: { |
| 1411 |
if ($self->{next_char} == 0x003E) { # > |
if ($self->{next_char} == 0x003E) { # > |
| 1413 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1414 |
!!!next-input-character; |
!!!next-input-character; |
| 1415 |
|
|
| 1416 |
!!!emit ($token); |
!!!emit ($self->{current_token}); # comment |
| 1417 |
|
|
| 1418 |
redo A; |
redo A; |
| 1419 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 1421 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1422 |
## reconsume |
## reconsume |
| 1423 |
|
|
| 1424 |
!!!emit ($token); |
!!!emit ($self->{current_token}); # comment |
| 1425 |
|
|
| 1426 |
redo A; |
redo A; |
| 1427 |
} else { |
} else { |
| 1428 |
!!!cp (126); |
!!!cp (126); |
| 1429 |
$token->{data} .= chr ($self->{next_char}); |
$self->{current_token}->{data} .= chr ($self->{next_char}); # comment |
| 1430 |
!!!next-input-character; |
!!!next-input-character; |
| 1431 |
redo BC; |
redo BC; |
| 1432 |
} |
} |
| 1436 |
} elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) { |
} elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) { |
| 1437 |
## (only happen if PCDATA state) |
## (only happen if PCDATA state) |
| 1438 |
|
|
| 1439 |
|
#my ($l, $c) = ($self->{line_prev}, $self->{column_prev} - 1); |
| 1440 |
|
|
| 1441 |
my @next_char; |
my @next_char; |
| 1442 |
push @next_char, $self->{next_char}; |
push @next_char, $self->{next_char}; |
| 1443 |
|
|
| 1446 |
push @next_char, $self->{next_char}; |
push @next_char, $self->{next_char}; |
| 1447 |
if ($self->{next_char} == 0x002D) { # - |
if ($self->{next_char} == 0x002D) { # - |
| 1448 |
!!!cp (127); |
!!!cp (127); |
| 1449 |
$self->{current_token} = {type => COMMENT_TOKEN, data => ''}; |
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
| 1450 |
|
#line => $l, column => $c, |
| 1451 |
|
}; |
| 1452 |
$self->{state} = COMMENT_START_STATE; |
$self->{state} = COMMENT_START_STATE; |
| 1453 |
!!!next-input-character; |
!!!next-input-character; |
| 1454 |
redo A; |
redo A; |
| 1484 |
!!!cp (129); |
!!!cp (129); |
| 1485 |
## TODO: What a stupid code this is! |
## TODO: What a stupid code this is! |
| 1486 |
$self->{state} = DOCTYPE_STATE; |
$self->{state} = DOCTYPE_STATE; |
| 1487 |
|
$self->{current_token} = {type => DOCTYPE_TOKEN, |
| 1488 |
|
quirks => 1, |
| 1489 |
|
#line => $l, column => $c, |
| 1490 |
|
}; |
| 1491 |
!!!next-input-character; |
!!!next-input-character; |
| 1492 |
redo A; |
redo A; |
| 1493 |
} else { |
} else { |
| 1516 |
$self->{next_char} = shift @next_char; |
$self->{next_char} = shift @next_char; |
| 1517 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 1518 |
$self->{state} = BOGUS_COMMENT_STATE; |
$self->{state} = BOGUS_COMMENT_STATE; |
| 1519 |
|
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
| 1520 |
|
#line => $l, column => $c, |
| 1521 |
|
}; |
| 1522 |
redo A; |
redo A; |
| 1523 |
|
|
| 1524 |
## ISSUE: typos in spec: chacacters, is is a parse error |
## ISSUE: typos in spec: chacacters, is is a parse error |
| 1642 |
redo A; |
redo A; |
| 1643 |
} elsif ($self->{next_char} == 0x002D) { # - |
} elsif ($self->{next_char} == 0x002D) { # - |
| 1644 |
!!!cp (152); |
!!!cp (152); |
| 1645 |
!!!parse-error (type => 'dash in comment'); |
!!!parse-error (type => 'dash in comment', |
| 1646 |
|
line => $self->{line_prev}, |
| 1647 |
|
column => $self->{column_prev}); |
| 1648 |
$self->{current_token}->{data} .= '-'; # comment |
$self->{current_token}->{data} .= '-'; # comment |
| 1649 |
## Stay in the state |
## Stay in the state |
| 1650 |
!!!next-input-character; |
!!!next-input-character; |
| 1660 |
redo A; |
redo A; |
| 1661 |
} else { |
} else { |
| 1662 |
!!!cp (154); |
!!!cp (154); |
| 1663 |
!!!parse-error (type => 'dash in comment'); |
!!!parse-error (type => 'dash in comment', |
| 1664 |
|
line => $self->{line_prev}, |
| 1665 |
|
column => $self->{column_prev}); |
| 1666 |
$self->{current_token}->{data} .= '--' . chr ($self->{next_char}); # comment |
$self->{current_token}->{data} .= '--' . chr ($self->{next_char}); # comment |
| 1667 |
$self->{state} = COMMENT_STATE; |
$self->{state} = COMMENT_STATE; |
| 1668 |
!!!next-input-character; |
!!!next-input-character; |
| 1701 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1702 |
!!!next-input-character; |
!!!next-input-character; |
| 1703 |
|
|
| 1704 |
!!!emit ({type => DOCTYPE_TOKEN, quirks => 1}); |
!!!emit ($self->{current_token}); # DOCTYPE (quirks) |
| 1705 |
|
|
| 1706 |
redo A; |
redo A; |
| 1707 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 1710 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1711 |
## reconsume |
## reconsume |
| 1712 |
|
|
| 1713 |
!!!emit ({type => DOCTYPE_TOKEN, quirks => 1}); |
!!!emit ($self->{current_token}); # DOCTYPE (quirks) |
| 1714 |
|
|
| 1715 |
redo A; |
redo A; |
| 1716 |
} else { |
} else { |
| 1717 |
!!!cp (160); |
!!!cp (160); |
| 1718 |
$self->{current_token} |
$self->{current_token}->{name} = chr $self->{next_char}; |
| 1719 |
= {type => DOCTYPE_TOKEN, |
delete $self->{current_token}->{quirks}; |
|
name => chr ($self->{next_char}), |
|
|
#quirks => 0, |
|
|
}; |
|
| 1720 |
## ISSUE: "Set the token's name name to the" in the spec |
## ISSUE: "Set the token's name name to the" in the spec |
| 1721 |
$self->{state} = DOCTYPE_NAME_STATE; |
$self->{state} = DOCTYPE_NAME_STATE; |
| 1722 |
!!!next-input-character; |
!!!next-input-character; |
| 2243 |
sub _tokenize_attempt_to_consume_an_entity ($$$) { |
sub _tokenize_attempt_to_consume_an_entity ($$$) { |
| 2244 |
my ($self, $in_attr, $additional) = @_; |
my ($self, $in_attr, $additional) = @_; |
| 2245 |
|
|
| 2246 |
|
my ($l, $c) = ($self->{line_prev}, $self->{column_prev}); |
| 2247 |
|
|
| 2248 |
if ({ |
if ({ |
| 2249 |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, # HT, LF, VT, FF, |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, # HT, LF, VT, FF, |
| 2250 |
0x0020 => 1, 0x003C => 1, 0x0026 => 1, -1 => 1, # SP, <, & # 0x000D # CR |
0x0020 => 1, 0x003C => 1, 0x0026 => 1, -1 => 1, # SP, <, & # 0x000D # CR |
| 2285 |
redo X; |
redo X; |
| 2286 |
} elsif (not defined $code) { # no hexadecimal digit |
} elsif (not defined $code) { # no hexadecimal digit |
| 2287 |
!!!cp (1005); |
!!!cp (1005); |
| 2288 |
!!!parse-error (type => 'bare hcro'); |
!!!parse-error (type => 'bare hcro', line => $l, column => $c); |
| 2289 |
!!!back-next-input-character ($x_char, $self->{next_char}); |
!!!back-next-input-character ($x_char, $self->{next_char}); |
| 2290 |
$self->{next_char} = 0x0023; # # |
$self->{next_char} = 0x0023; # # |
| 2291 |
return undef; |
return undef; |
| 2294 |
!!!next-input-character; |
!!!next-input-character; |
| 2295 |
} else { |
} else { |
| 2296 |
!!!cp (1007); |
!!!cp (1007); |
| 2297 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'no refc', line => $l, column => $c); |
| 2298 |
} |
} |
| 2299 |
|
|
| 2300 |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 2301 |
!!!cp (1008); |
!!!cp (1008); |
| 2302 |
!!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code); |
!!!parse-error (type => (sprintf 'invalid character reference:U+%04X', $code), line => $l, column => $c); |
| 2303 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 2304 |
} elsif ($code > 0x10FFFF) { |
} elsif ($code > 0x10FFFF) { |
| 2305 |
!!!cp (1009); |
!!!cp (1009); |
| 2306 |
!!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code); |
!!!parse-error (type => (sprintf 'invalid character reference:U-%08X', $code), line => $l, column => $c); |
| 2307 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 2308 |
} elsif ($code == 0x000D) { |
} elsif ($code == 0x000D) { |
| 2309 |
!!!cp (1010); |
!!!cp (1010); |
| 2310 |
!!!parse-error (type => 'CR character reference'); |
!!!parse-error (type => 'CR character reference', line => $l, column => $c); |
| 2311 |
$code = 0x000A; |
$code = 0x000A; |
| 2312 |
} elsif (0x80 <= $code and $code <= 0x9F) { |
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 2313 |
!!!cp (1011); |
!!!cp (1011); |
| 2314 |
!!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code); |
!!!parse-error (type => (sprintf 'C1 character reference:U+%04X', $code), line => $l, column => $c); |
| 2315 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 2316 |
} |
} |
| 2317 |
|
|
| 2318 |
return {type => CHARACTER_TOKEN, data => chr $code, |
return {type => CHARACTER_TOKEN, data => chr $code, |
| 2319 |
has_reference => 1}; |
has_reference => 1, |
| 2320 |
|
#line => $l, column => $c, |
| 2321 |
|
}; |
| 2322 |
} # X |
} # X |
| 2323 |
} elsif (0x0030 <= $self->{next_char} and |
} elsif (0x0030 <= $self->{next_char} and |
| 2324 |
$self->{next_char} <= 0x0039) { # 0..9 |
$self->{next_char} <= 0x0039) { # 0..9 |
| 2339 |
!!!next-input-character; |
!!!next-input-character; |
| 2340 |
} else { |
} else { |
| 2341 |
!!!cp (1014); |
!!!cp (1014); |
| 2342 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'no refc', line => $l, column => $c); |
| 2343 |
} |
} |
| 2344 |
|
|
| 2345 |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 2346 |
!!!cp (1015); |
!!!cp (1015); |
| 2347 |
!!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code); |
!!!parse-error (type => (sprintf 'invalid character reference:U+%04X', $code), line => $l, column => $c); |
| 2348 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 2349 |
} elsif ($code > 0x10FFFF) { |
} elsif ($code > 0x10FFFF) { |
| 2350 |
!!!cp (1016); |
!!!cp (1016); |
| 2351 |
!!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code); |
!!!parse-error (type => (sprintf 'invalid character reference:U-%08X', $code), line => $l, column => $c); |
| 2352 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 2353 |
} elsif ($code == 0x000D) { |
} elsif ($code == 0x000D) { |
| 2354 |
!!!cp (1017); |
!!!cp (1017); |
| 2355 |
!!!parse-error (type => 'CR character reference'); |
!!!parse-error (type => 'CR character reference', line => $l, column => $c); |
| 2356 |
$code = 0x000A; |
$code = 0x000A; |
| 2357 |
} elsif (0x80 <= $code and $code <= 0x9F) { |
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 2358 |
!!!cp (1018); |
!!!cp (1018); |
| 2359 |
!!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code); |
!!!parse-error (type => (sprintf 'C1 character reference:U+%04X', $code), line => $l, column => $c); |
| 2360 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 2361 |
} |
} |
| 2362 |
|
|
| 2363 |
return {type => CHARACTER_TOKEN, data => chr $code, has_reference => 1}; |
return {type => CHARACTER_TOKEN, data => chr $code, has_reference => 1, |
| 2364 |
|
#line => $l, column => $c, |
| 2365 |
|
}; |
| 2366 |
} else { |
} else { |
| 2367 |
!!!cp (1019); |
!!!cp (1019); |
| 2368 |
!!!parse-error (type => 'bare nero'); |
!!!parse-error (type => 'bare nero', line => $l, column => $c); |
| 2369 |
!!!back-next-input-character ($self->{next_char}); |
!!!back-next-input-character ($self->{next_char}); |
| 2370 |
$self->{next_char} = 0x0023; # # |
$self->{next_char} = 0x0023; # # |
| 2371 |
return undef; |
return undef; |
| 2415 |
|
|
| 2416 |
if ($match > 0) { |
if ($match > 0) { |
| 2417 |
!!!cp (1023); |
!!!cp (1023); |
| 2418 |
return {type => CHARACTER_TOKEN, data => $value, has_reference => 1}; |
return {type => CHARACTER_TOKEN, data => $value, has_reference => 1, |
| 2419 |
|
#line => $l, column => $c, |
| 2420 |
|
}; |
| 2421 |
} elsif ($match < 0) { |
} elsif ($match < 0) { |
| 2422 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'no refc', line => $l, column => $c); |
| 2423 |
if ($in_attr and $match < -1) { |
if ($in_attr and $match < -1) { |
| 2424 |
!!!cp (1024); |
!!!cp (1024); |
| 2425 |
return {type => CHARACTER_TOKEN, data => '&'.$entity_name}; |
return {type => CHARACTER_TOKEN, data => '&'.$entity_name, |
| 2426 |
|
#line => $l, column => $c, |
| 2427 |
|
}; |
| 2428 |
} else { |
} else { |
| 2429 |
!!!cp (1025); |
!!!cp (1025); |
| 2430 |
return {type => CHARACTER_TOKEN, data => $value, has_reference => 1}; |
return {type => CHARACTER_TOKEN, data => $value, has_reference => 1, |
| 2431 |
|
#line => $l, column => $c, |
| 2432 |
|
}; |
| 2433 |
} |
} |
| 2434 |
} else { |
} else { |
| 2435 |
!!!cp (1026); |
!!!cp (1026); |
| 2436 |
!!!parse-error (type => 'bare ero'); |
!!!parse-error (type => 'bare ero', line => $l, column => $c); |
| 2437 |
## NOTE: "No characters are consumed" in the spec. |
## NOTE: "No characters are consumed" in the spec. |
| 2438 |
return {type => CHARACTER_TOKEN, data => '&'.$value}; |
return {type => CHARACTER_TOKEN, data => '&'.$value, |
| 2439 |
|
#line => $l, column => $c, |
| 2440 |
|
}; |
| 2441 |
} |
} |
| 2442 |
} else { |
} else { |
| 2443 |
!!!cp (1027); |
!!!cp (1027); |
| 2444 |
## no characters are consumed |
## no characters are consumed |
| 2445 |
!!!parse-error (type => 'bare ero'); |
!!!parse-error (type => 'bare ero', line => $l, column => $c); |
| 2446 |
return undef; |
return undef; |
| 2447 |
} |
} |
| 2448 |
} # _tokenize_attempt_to_consume_an_entity |
} # _tokenize_attempt_to_consume_an_entity |
| 2513 |
defined $token->{public_identifier} or |
defined $token->{public_identifier} or |
| 2514 |
defined $token->{system_identifier}) { |
defined $token->{system_identifier}) { |
| 2515 |
!!!cp ('t1'); |
!!!cp ('t1'); |
| 2516 |
!!!parse-error (type => 'not HTML5'); |
!!!parse-error (type => 'not HTML5', token => $token); |
| 2517 |
} elsif ($doctype_name ne 'HTML') { |
} elsif ($doctype_name ne 'HTML') { |
| 2518 |
!!!cp ('t2'); |
!!!cp ('t2'); |
| 2519 |
## ISSUE: ASCII case-insensitive? (in fact it does not matter) |
## ISSUE: ASCII case-insensitive? (in fact it does not matter) |
| 2520 |
!!!parse-error (type => 'not HTML5'); |
!!!parse-error (type => 'not HTML5', token => $token); |
| 2521 |
} else { |
} else { |
| 2522 |
!!!cp ('t3'); |
!!!cp ('t3'); |
| 2523 |
} |
} |
| 2656 |
END_OF_FILE_TOKEN, 1, |
END_OF_FILE_TOKEN, 1, |
| 2657 |
}->{$token->{type}}) { |
}->{$token->{type}}) { |
| 2658 |
!!!cp ('t14'); |
!!!cp ('t14'); |
| 2659 |
!!!parse-error (type => 'no DOCTYPE'); |
!!!parse-error (type => 'no DOCTYPE', token => $token); |
| 2660 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 2661 |
## Go to the "before html" insertion mode. |
## Go to the "before html" insertion mode. |
| 2662 |
## reprocess |
## reprocess |
| 2677 |
!!!cp ('t17'); |
!!!cp ('t17'); |
| 2678 |
} |
} |
| 2679 |
|
|
| 2680 |
!!!parse-error (type => 'no DOCTYPE'); |
!!!parse-error (type => 'no DOCTYPE', token => $token); |
| 2681 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 2682 |
## Go to the "before html" insertion mode. |
## Go to the "before html" insertion mode. |
| 2683 |
## reprocess |
## reprocess |
| 2706 |
B: { |
B: { |
| 2707 |
if ($token->{type} == DOCTYPE_TOKEN) { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 2708 |
!!!cp ('t19'); |
!!!cp ('t19'); |
| 2709 |
!!!parse-error (type => 'in html:#DOCTYPE'); |
!!!parse-error (type => 'in html:#DOCTYPE', token => $token); |
| 2710 |
## Ignore the token |
## Ignore the token |
| 2711 |
## Stay in the insertion mode. |
## Stay in the insertion mode. |
| 2712 |
!!!next-token; |
!!!next-token; |
| 2740 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 2741 |
if ($token->{tag_name} eq 'html') { |
if ($token->{tag_name} eq 'html') { |
| 2742 |
my $root_element; |
my $root_element; |
| 2743 |
!!!create-element ($root_element, $token->{tag_name}, $token->{attributes}); |
!!!create-element ($root_element, $token->{tag_name}, $token->{attributes}, $token); |
| 2744 |
$self->{document}->append_child ($root_element); |
$self->{document}->append_child ($root_element); |
| 2745 |
push @{$self->{open_elements}}, [$root_element, 'html']; |
push @{$self->{open_elements}}, [$root_element, 'html']; |
| 2746 |
|
|
| 2748 |
!!!cp ('t24'); |
!!!cp ('t24'); |
| 2749 |
$self->{application_cache_selection} |
$self->{application_cache_selection} |
| 2750 |
->($token->{attributes}->{manifest}->{value}); |
->($token->{attributes}->{manifest}->{value}); |
| 2751 |
## ISSUE: No relative reference resolution? |
## ISSUE: Spec is unclear on relative references. |
| 2752 |
|
## According to Hixie (#whatwg 2008-03-19), it should be |
| 2753 |
|
## resolved against the base URI of the document in HTML |
| 2754 |
|
## or xml:base of the element in XHTML. |
| 2755 |
} else { |
} else { |
| 2756 |
!!!cp ('t25'); |
!!!cp ('t25'); |
| 2757 |
$self->{application_cache_selection}->(undef); |
$self->{application_cache_selection}->(undef); |
| 2773 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 2774 |
} |
} |
| 2775 |
|
|
| 2776 |
my $root_element; !!!create-element ($root_element, 'html'); |
my $root_element; !!!create-element ($root_element, 'html',, $token); |
| 2777 |
$self->{document}->append_child ($root_element); |
$self->{document}->append_child ($root_element); |
| 2778 |
push @{$self->{open_elements}}, [$root_element, 'html']; |
push @{$self->{open_elements}}, [$root_element, 'html']; |
| 2779 |
|
|
| 2800 |
|
|
| 2801 |
## Step 3 |
## Step 3 |
| 2802 |
S3: { |
S3: { |
|
## ISSUE: Oops! "If node is the first node in the stack of open |
|
|
## elements, then set last to true. If the context element of the |
|
|
## HTML fragment parsing algorithm is neither a td element nor a |
|
|
## th element, then set node to the context element. (fragment case)": |
|
|
## The second "if" is in the scope of the first "if"!? |
|
| 2803 |
if ($self->{open_elements}->[0]->[0] eq $node->[0]) { |
if ($self->{open_elements}->[0]->[0] eq $node->[0]) { |
| 2804 |
$last = 1; |
$last = 1; |
| 2805 |
if (defined $self->{inner_html_node}) { |
if (defined $self->{inner_html_node}) { |
| 2960 |
!!!cp ('t39'); |
!!!cp ('t39'); |
| 2961 |
}; # $clear_up_to_marker |
}; # $clear_up_to_marker |
| 2962 |
|
|
| 2963 |
my $parse_rcdata = sub ($$) { |
my $insert; |
| 2964 |
my ($content_model_flag, $insert) = @_; |
|
| 2965 |
|
my $parse_rcdata = sub ($) { |
| 2966 |
|
my ($content_model_flag) = @_; |
| 2967 |
|
|
| 2968 |
## Step 1 |
## Step 1 |
| 2969 |
my $start_tag_name = $token->{tag_name}; |
my $start_tag_name = $token->{tag_name}; |
| 2970 |
my $el; |
my $el; |
| 2971 |
!!!create-element ($el, $start_tag_name, $token->{attributes}); |
!!!create-element ($el, $start_tag_name, $token->{attributes}, $token); |
| 2972 |
|
|
| 2973 |
## Step 2 |
## Step 2 |
| 2974 |
$insert->($el); # /context node/->append_child ($el) |
$insert->($el); |
| 2975 |
|
|
| 2976 |
## Step 3 |
## Step 3 |
| 2977 |
$self->{content_model} = $content_model_flag; # CDATA or RCDATA |
$self->{content_model} = $content_model_flag; # CDATA or RCDATA |
| 3001 |
$token->{tag_name} eq $start_tag_name) { |
$token->{tag_name} eq $start_tag_name) { |
| 3002 |
!!!cp ('t42'); |
!!!cp ('t42'); |
| 3003 |
## Ignore the token |
## Ignore the token |
|
} elsif ($content_model_flag == CDATA_CONTENT_MODEL) { |
|
|
!!!cp ('t43'); |
|
|
!!!parse-error (type => 'in CDATA:#'.$token->{type}); |
|
|
} elsif ($content_model_flag == RCDATA_CONTENT_MODEL) { |
|
|
!!!cp ('t44'); |
|
|
!!!parse-error (type => 'in RCDATA:#'.$token->{type}); |
|
| 3004 |
} else { |
} else { |
| 3005 |
die "$0: $content_model_flag in parse_rcdata"; |
## NOTE: An end-of-file token. |
| 3006 |
|
if ($content_model_flag == CDATA_CONTENT_MODEL) { |
| 3007 |
|
!!!cp ('t43'); |
| 3008 |
|
!!!parse-error (type => 'in CDATA:#'.$token->{type}, token => $token); |
| 3009 |
|
} elsif ($content_model_flag == RCDATA_CONTENT_MODEL) { |
| 3010 |
|
!!!cp ('t44'); |
| 3011 |
|
!!!parse-error (type => 'in RCDATA:#'.$token->{type}, token => $token); |
| 3012 |
|
} else { |
| 3013 |
|
die "$0: $content_model_flag in parse_rcdata"; |
| 3014 |
|
} |
| 3015 |
} |
} |
| 3016 |
!!!next-token; |
!!!next-token; |
| 3017 |
}; # $parse_rcdata |
}; # $parse_rcdata |
| 3018 |
|
|
| 3019 |
my $script_start_tag = sub ($) { |
my $script_start_tag = sub () { |
|
my $insert = $_[0]; |
|
| 3020 |
my $script_el; |
my $script_el; |
| 3021 |
!!!create-element ($script_el, 'script', $token->{attributes}); |
!!!create-element ($script_el, 'script', $token->{attributes}, $token); |
| 3022 |
## TODO: mark as "parser-inserted" |
## TODO: mark as "parser-inserted" |
| 3023 |
|
|
| 3024 |
$self->{content_model} = CDATA_CONTENT_MODEL; |
$self->{content_model} = CDATA_CONTENT_MODEL; |
| 3044 |
## Ignore the token |
## Ignore the token |
| 3045 |
} else { |
} else { |
| 3046 |
!!!cp ('t48'); |
!!!cp ('t48'); |
| 3047 |
!!!parse-error (type => 'in CDATA:#'.$token->{type}); |
!!!parse-error (type => 'in CDATA:#'.$token->{type}, token => $token); |
| 3048 |
## ISSUE: And ignore? |
## ISSUE: And ignore? |
| 3049 |
## TODO: mark as "already executed" |
## TODO: mark as "already executed" |
| 3050 |
} |
} |
| 3067 |
!!!next-token; |
!!!next-token; |
| 3068 |
}; # $script_start_tag |
}; # $script_start_tag |
| 3069 |
|
|
| 3070 |
|
## NOTE: $open_tables->[-1]->[0] is the "current table" element node. |
| 3071 |
|
## NOTE: $open_tables->[-1]->[1] is the "tainted" flag. |
| 3072 |
|
my $open_tables = [[$self->{open_elements}->[0]->[0]]]; |
| 3073 |
|
|
| 3074 |
my $formatting_end_tag = sub { |
my $formatting_end_tag = sub { |
| 3075 |
my $tag_name = shift; |
my $end_tag_token = shift; |
| 3076 |
|
my $tag_name = $end_tag_token->{tag_name}; |
| 3077 |
|
|
| 3078 |
|
## NOTE: The adoption agency algorithm (AAA). |
| 3079 |
|
|
| 3080 |
FET: { |
FET: { |
| 3081 |
## Step 1 |
## Step 1 |
| 3094 |
} # AFE |
} # AFE |
| 3095 |
unless (defined $formatting_element) { |
unless (defined $formatting_element) { |
| 3096 |
!!!cp ('t53'); |
!!!cp ('t53'); |
| 3097 |
!!!parse-error (type => 'unmatched end tag:'.$tag_name); |
!!!parse-error (type => 'unmatched end tag:'.$tag_name, token => $end_tag_token); |
| 3098 |
## Ignore the token |
## Ignore the token |
| 3099 |
!!!next-token; |
!!!next-token; |
| 3100 |
return; |
return; |
| 3111 |
last INSCOPE; |
last INSCOPE; |
| 3112 |
} else { # in open elements but not in scope |
} else { # in open elements but not in scope |
| 3113 |
!!!cp ('t55'); |
!!!cp ('t55'); |
| 3114 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, |
| 3115 |
|
token => $end_tag_token); |
| 3116 |
## Ignore the token |
## Ignore the token |
| 3117 |
!!!next-token; |
!!!next-token; |
| 3118 |
return; |
return; |
| 3119 |
} |
} |
| 3120 |
} elsif ({ |
} elsif ({ |
| 3121 |
table => 1, caption => 1, td => 1, th => 1, |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 3122 |
button => 1, marquee => 1, object => 1, html => 1, |
button => 1, marquee => 1, object => 1, html => 1, |
| 3123 |
}->{$node->[1]}) { |
}->{$node->[1]}) { |
| 3124 |
!!!cp ('t56'); |
!!!cp ('t56'); |
| 3127 |
} # INSCOPE |
} # INSCOPE |
| 3128 |
unless (defined $formatting_element_i_in_open) { |
unless (defined $formatting_element_i_in_open) { |
| 3129 |
!!!cp ('t57'); |
!!!cp ('t57'); |
| 3130 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, |
| 3131 |
|
token => $end_tag_token); |
| 3132 |
pop @$active_formatting_elements; # $formatting_element |
pop @$active_formatting_elements; # $formatting_element |
| 3133 |
!!!next-token; ## TODO: ok? |
!!!next-token; ## TODO: ok? |
| 3134 |
return; |
return; |
| 3135 |
} |
} |
| 3136 |
if (not $self->{open_elements}->[-1]->[0] eq $formatting_element->[0]) { |
if (not $self->{open_elements}->[-1]->[0] eq $formatting_element->[0]) { |
| 3137 |
!!!cp ('t58'); |
!!!cp ('t58'); |
| 3138 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], |
| 3139 |
|
token => $end_tag_token); |
| 3140 |
} |
} |
| 3141 |
|
|
| 3142 |
## Step 2 |
## Step 2 |
| 3147 |
if (not $formatting_category->{$node->[1]} and |
if (not $formatting_category->{$node->[1]} and |
| 3148 |
#not $phrasing_category->{$node->[1]} and |
#not $phrasing_category->{$node->[1]} and |
| 3149 |
($special_category->{$node->[1]} or |
($special_category->{$node->[1]} or |
| 3150 |
$scoping_category->{$node->[1]})) { |
$scoping_category->{$node->[1]})) { ## Scoping is redundant, maybe |
| 3151 |
!!!cp ('t59'); |
!!!cp ('t59'); |
| 3152 |
$furthest_block = $node; |
$furthest_block = $node; |
| 3153 |
$furthest_block_i_in_open = $_; |
$furthest_block_i_in_open = $_; |
| 3233 |
} # S7 |
} # S7 |
| 3234 |
|
|
| 3235 |
## Step 8 |
## Step 8 |
| 3236 |
$common_ancestor_node->[0]->append_child ($last_node->[0]); |
if ({ |
| 3237 |
|
table => 1, tbody => 1, tfoot => 1, thead => 1, tr => 1, |
| 3238 |
|
}->{$common_ancestor_node->[1]}) { |
| 3239 |
|
my $foster_parent_element; |
| 3240 |
|
my $next_sibling; |
| 3241 |
|
OE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3242 |
|
if ($self->{open_elements}->[$_]->[1] eq 'table') { |
| 3243 |
|
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
| 3244 |
|
if (defined $parent and $parent->node_type == 1) { |
| 3245 |
|
!!!cp ('t65.1'); |
| 3246 |
|
$foster_parent_element = $parent; |
| 3247 |
|
$next_sibling = $self->{open_elements}->[$_]->[0]; |
| 3248 |
|
} else { |
| 3249 |
|
!!!cp ('t65.2'); |
| 3250 |
|
$foster_parent_element |
| 3251 |
|
= $self->{open_elements}->[$_ - 1]->[0]; |
| 3252 |
|
} |
| 3253 |
|
last OE; |
| 3254 |
|
} |
| 3255 |
|
} # OE |
| 3256 |
|
$foster_parent_element = $self->{open_elements}->[0]->[0] |
| 3257 |
|
unless defined $foster_parent_element; |
| 3258 |
|
$foster_parent_element->insert_before ($last_node->[0], $next_sibling); |
| 3259 |
|
$open_tables->[-1]->[1] = 1; # tainted |
| 3260 |
|
} else { |
| 3261 |
|
!!!cp ('t65.3'); |
| 3262 |
|
$common_ancestor_node->[0]->append_child ($last_node->[0]); |
| 3263 |
|
} |
| 3264 |
|
|
| 3265 |
## Step 9 |
## Step 9 |
| 3266 |
my $clone = [$formatting_element->[0]->clone_node (0), |
my $clone = [$formatting_element->[0]->clone_node (0), |
| 3306 |
} # FET |
} # FET |
| 3307 |
}; # $formatting_end_tag |
}; # $formatting_end_tag |
| 3308 |
|
|
| 3309 |
my $insert_to_current = sub { |
$insert = my $insert_to_current = sub { |
| 3310 |
$self->{open_elements}->[-1]->[0]->append_child ($_[0]); |
$self->{open_elements}->[-1]->[0]->append_child ($_[0]); |
| 3311 |
}; # $insert_to_current |
}; # $insert_to_current |
| 3312 |
|
|
| 3313 |
my $insert_to_foster = sub { |
my $insert_to_foster = sub { |
| 3314 |
my $child = shift; |
my $child = shift; |
| 3315 |
if ({ |
if ({ |
| 3316 |
table => 1, tbody => 1, tfoot => 1, |
table => 1, tbody => 1, tfoot => 1, thead => 1, tr => 1, |
| 3317 |
thead => 1, tr => 1, |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3318 |
}->{$self->{open_elements}->[-1]->[1]}) { |
# MUST |
| 3319 |
# MUST |
my $foster_parent_element; |
| 3320 |
my $foster_parent_element; |
my $next_sibling; |
|
my $next_sibling; |
|
| 3321 |
OE: for (reverse 0..$#{$self->{open_elements}}) { |
OE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3322 |
if ($self->{open_elements}->[$_]->[1] eq 'table') { |
if ($self->{open_elements}->[$_]->[1] eq 'table') { |
| 3323 |
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
| 3337 |
unless defined $foster_parent_element; |
unless defined $foster_parent_element; |
| 3338 |
$foster_parent_element->insert_before |
$foster_parent_element->insert_before |
| 3339 |
($child, $next_sibling); |
($child, $next_sibling); |
| 3340 |
} else { |
$open_tables->[-1]->[1] = 1; # tainted |
| 3341 |
!!!cp ('t72'); |
} else { |
| 3342 |
$self->{open_elements}->[-1]->[0]->append_child ($child); |
!!!cp ('t72'); |
| 3343 |
} |
$self->{open_elements}->[-1]->[0]->append_child ($child); |
| 3344 |
|
} |
| 3345 |
}; # $insert_to_foster |
}; # $insert_to_foster |
| 3346 |
|
|
|
my $insert; |
|
|
|
|
| 3347 |
B: { |
B: { |
| 3348 |
if ($token->{type} == DOCTYPE_TOKEN) { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 3349 |
!!!cp ('t73'); |
!!!cp ('t73'); |
| 3350 |
!!!parse-error (type => 'DOCTYPE in the middle'); |
!!!parse-error (type => 'DOCTYPE in the middle', token => $token); |
| 3351 |
## Ignore the token |
## Ignore the token |
| 3352 |
## Stay in the phase |
## Stay in the phase |
| 3353 |
!!!next-token; |
!!!next-token; |
| 3354 |
redo B; |
redo B; |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
|
|
if ($self->{insertion_mode} & AFTER_HTML_IMS) { |
|
|
!!!cp ('t74'); |
|
|
# |
|
|
} else { |
|
|
## Generate implied end tags |
|
|
if ({ |
|
|
dd => 1, dt => 1, li => 1, p => 1, td => 1, th => 1, tr => 1, |
|
|
tbody => 1, tfoot=> 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!cp ('t75'); |
|
|
!!!back-token; |
|
|
$token = {type => END_TAG_TOKEN, tag_name => $self->{open_elements}->[-1]->[1]}; |
|
|
redo B; |
|
|
} |
|
|
|
|
|
if (@{$self->{open_elements}} > 2 or |
|
|
(@{$self->{open_elements}} == 2 and $self->{open_elements}->[1]->[1] ne 'body')) { |
|
|
!!!cp ('t76'); |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
|
} elsif (defined $self->{inner_html_node} and |
|
|
@{$self->{open_elements}} > 1 and |
|
|
$self->{open_elements}->[1]->[1] ne 'body') { |
|
|
## ISSUE: This case is never reached. |
|
|
!!!cp ('t77'); |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
|
} else { |
|
|
!!!cp ('t78'); |
|
|
} |
|
|
|
|
|
## ISSUE: There is an issue in the spec. |
|
|
} |
|
|
|
|
|
## Stop parsing |
|
|
last B; |
|
| 3355 |
} elsif ($token->{type} == START_TAG_TOKEN and |
} elsif ($token->{type} == START_TAG_TOKEN and |
| 3356 |
$token->{tag_name} eq 'html') { |
$token->{tag_name} eq 'html') { |
| 3357 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 3358 |
!!!cp ('t79'); |
!!!cp ('t79'); |
| 3359 |
!!!parse-error (type => 'after html:html'); |
!!!parse-error (type => 'after html:html', token => $token); |
| 3360 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 3361 |
} elsif ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 3362 |
!!!cp ('t80'); |
!!!cp ('t80'); |
| 3363 |
!!!parse-error (type => 'after html:html'); |
!!!parse-error (type => 'after html:html', token => $token); |
| 3364 |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 3365 |
} else { |
} else { |
| 3366 |
!!!cp ('t81'); |
!!!cp ('t81'); |
| 3367 |
} |
} |
| 3368 |
|
|
| 3369 |
!!!cp ('t82'); |
!!!cp ('t82'); |
| 3370 |
!!!parse-error (type => 'not first start tag'); |
!!!parse-error (type => 'not first start tag', token => $token); |
| 3371 |
my $top_el = $self->{open_elements}->[0]->[0]; |
my $top_el = $self->{open_elements}->[0]->[0]; |
| 3372 |
for my $attr_name (keys %{$token->{attributes}}) { |
for my $attr_name (keys %{$token->{attributes}}) { |
| 3373 |
unless ($top_el->has_attribute_ns (undef, $attr_name)) { |
unless ($top_el->has_attribute_ns (undef, $attr_name)) { |
| 3396 |
} elsif ($self->{insertion_mode} & HEAD_IMS) { |
} elsif ($self->{insertion_mode} & HEAD_IMS) { |
| 3397 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 3398 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 3399 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
unless ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3400 |
|
!!!cp ('t88.2'); |
| 3401 |
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 3402 |
|
} else { |
| 3403 |
|
!!!cp ('t88.1'); |
| 3404 |
|
## Ignore the token. |
| 3405 |
|
!!!next-token; |
| 3406 |
|
redo B; |
| 3407 |
|
} |
| 3408 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 3409 |
!!!cp ('t88'); |
!!!cp ('t88'); |
| 3410 |
!!!next-token; |
!!!next-token; |
| 3415 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3416 |
!!!cp ('t89'); |
!!!cp ('t89'); |
| 3417 |
## As if <head> |
## As if <head> |
| 3418 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, 'head',, $token); |
| 3419 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 3420 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3421 |
|
|
| 3427 |
!!!cp ('t90'); |
!!!cp ('t90'); |
| 3428 |
## As if </noscript> |
## As if </noscript> |
| 3429 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3430 |
!!!parse-error (type => 'in noscript:#character'); |
!!!parse-error (type => 'in noscript:#character', token => $token); |
| 3431 |
|
|
| 3432 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 3433 |
## As if </head> |
## As if </head> |
| 3445 |
|
|
| 3446 |
## "after head" insertion mode |
## "after head" insertion mode |
| 3447 |
## As if <body> |
## As if <body> |
| 3448 |
!!!insert-element ('body'); |
!!!insert-element ('body',, $token); |
| 3449 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 3450 |
## reprocess |
## reprocess |
| 3451 |
redo B; |
redo B; |
| 3453 |
if ($token->{tag_name} eq 'head') { |
if ($token->{tag_name} eq 'head') { |
| 3454 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3455 |
!!!cp ('t93'); |
!!!cp ('t93'); |
| 3456 |
!!!create-element ($self->{head_element}, $token->{tag_name}, $token->{attributes}); |
!!!create-element ($self->{head_element}, $token->{tag_name}, $token->{attributes}, $token); |
| 3457 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 3458 |
push @{$self->{open_elements}}, [$self->{head_element}, $token->{tag_name}]; |
push @{$self->{open_elements}}, [$self->{head_element}, $token->{tag_name}]; |
| 3459 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 3464 |
# |
# |
| 3465 |
} else { |
} else { |
| 3466 |
!!!cp ('t95'); |
!!!cp ('t95'); |
| 3467 |
!!!parse-error (type => 'in head:head'); # or in head noscript |
!!!parse-error (type => 'in head:head', token => $token); # or in head noscript |
| 3468 |
## Ignore the token |
## Ignore the token |
| 3469 |
!!!next-token; |
!!!next-token; |
| 3470 |
redo B; |
redo B; |
| 3472 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3473 |
!!!cp ('t96'); |
!!!cp ('t96'); |
| 3474 |
## As if <head> |
## As if <head> |
| 3475 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, 'head',, $token); |
| 3476 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 3477 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3478 |
|
|
| 3487 |
!!!cp ('t98'); |
!!!cp ('t98'); |
| 3488 |
## As if </noscript> |
## As if </noscript> |
| 3489 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3490 |
!!!parse-error (type => 'in noscript:base'); |
!!!parse-error (type => 'in noscript:base', token => $token); |
| 3491 |
|
|
| 3492 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 3493 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 3498 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 3499 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 3500 |
!!!cp ('t100'); |
!!!cp ('t100'); |
| 3501 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
| 3502 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3503 |
} else { |
} else { |
| 3504 |
!!!cp ('t101'); |
!!!cp ('t101'); |
| 3505 |
} |
} |
| 3506 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 3507 |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 3508 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} # <head> |
| 3509 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 3510 |
!!!next-token; |
!!!next-token; |
| 3511 |
redo B; |
redo B; |
| 3513 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 3514 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 3515 |
!!!cp ('t102'); |
!!!cp ('t102'); |
| 3516 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
| 3517 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3518 |
} else { |
} else { |
| 3519 |
!!!cp ('t103'); |
!!!cp ('t103'); |
| 3520 |
} |
} |
| 3521 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 3522 |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 3523 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} # <head> |
| 3524 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 3525 |
!!!next-token; |
!!!next-token; |
| 3526 |
redo B; |
redo B; |
| 3528 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 3529 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 3530 |
!!!cp ('t104'); |
!!!cp ('t104'); |
| 3531 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
| 3532 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3533 |
} else { |
} else { |
| 3534 |
!!!cp ('t105'); |
!!!cp ('t105'); |
| 3535 |
} |
} |
| 3536 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 3537 |
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. |
| 3538 |
|
|
| 3539 |
unless ($self->{confident}) { |
unless ($self->{confident}) { |
| 3540 |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
| 3541 |
!!!cp ('t106'); |
!!!cp ('t106'); |
| 3542 |
$self->{change_encoding} |
$self->{change_encoding} |
| 3543 |
->($self, $token->{attributes}->{charset}->{value}); |
->($self, $token->{attributes}->{charset}->{value}, |
| 3544 |
|
$token); |
| 3545 |
|
|
| 3546 |
$meta_el->[0]->get_attribute_node_ns (undef, 'charset') |
$meta_el->[0]->get_attribute_node_ns (undef, 'charset') |
| 3547 |
->set_user_data (manakai_has_reference => |
->set_user_data (manakai_has_reference => |
| 3556 |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
| 3557 |
!!!cp ('t107'); |
!!!cp ('t107'); |
| 3558 |
$self->{change_encoding} |
$self->{change_encoding} |
| 3559 |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3); |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3, |
| 3560 |
|
$token); |
| 3561 |
$meta_el->[0]->get_attribute_node_ns (undef, 'content') |
$meta_el->[0]->get_attribute_node_ns (undef, 'content') |
| 3562 |
->set_user_data (manakai_has_reference => |
->set_user_data (manakai_has_reference => |
| 3563 |
$token->{attributes}->{content} |
$token->{attributes}->{content} |
| 3583 |
} |
} |
| 3584 |
} |
} |
| 3585 |
|
|
| 3586 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} # <head> |
| 3587 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 3588 |
!!!next-token; |
!!!next-token; |
| 3589 |
redo B; |
redo B; |
| 3592 |
!!!cp ('t111'); |
!!!cp ('t111'); |
| 3593 |
## As if </noscript> |
## As if </noscript> |
| 3594 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3595 |
!!!parse-error (type => 'in noscript:title'); |
!!!parse-error (type => 'in noscript:title', token => $token); |
| 3596 |
|
|
| 3597 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 3598 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 3599 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 3600 |
!!!cp ('t112'); |
!!!cp ('t112'); |
| 3601 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
| 3602 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3603 |
} else { |
} else { |
| 3604 |
!!!cp ('t113'); |
!!!cp ('t113'); |
| 3607 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 3608 |
my $parent = defined $self->{head_element} ? $self->{head_element} |
my $parent = defined $self->{head_element} ? $self->{head_element} |
| 3609 |
: $self->{open_elements}->[-1]->[0]; |
: $self->{open_elements}->[-1]->[0]; |
| 3610 |
$parse_rcdata->(RCDATA_CONTENT_MODEL, |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
| 3611 |
sub { $parent->append_child ($_[0]) }); |
pop @{$self->{open_elements}} # <head> |
|
pop @{$self->{open_elements}} |
|
| 3612 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 3613 |
redo B; |
redo B; |
| 3614 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($token->{tag_name} eq 'style') { |
| 3617 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 3618 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 3619 |
!!!cp ('t114'); |
!!!cp ('t114'); |
| 3620 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
| 3621 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3622 |
} else { |
} else { |
| 3623 |
!!!cp ('t115'); |
!!!cp ('t115'); |
| 3624 |
} |
} |
| 3625 |
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert_to_current); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 3626 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} # <head> |
| 3627 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 3628 |
redo B; |
redo B; |
| 3629 |
} elsif ($token->{tag_name} eq 'noscript') { |
} elsif ($token->{tag_name} eq 'noscript') { |
| 3630 |
if ($self->{insertion_mode} == IN_HEAD_IM) { |
if ($self->{insertion_mode} == IN_HEAD_IM) { |
| 3631 |
!!!cp ('t116'); |
!!!cp ('t116'); |
| 3632 |
## NOTE: and scripting is disalbed |
## NOTE: and scripting is disalbed |
| 3633 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 3634 |
$self->{insertion_mode} = IN_HEAD_NOSCRIPT_IM; |
$self->{insertion_mode} = IN_HEAD_NOSCRIPT_IM; |
| 3635 |
!!!next-token; |
!!!next-token; |
| 3636 |
redo B; |
redo B; |
| 3637 |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 3638 |
!!!cp ('t117'); |
!!!cp ('t117'); |
| 3639 |
!!!parse-error (type => 'in noscript:noscript'); |
!!!parse-error (type => 'in noscript:noscript', token => $token); |
| 3640 |
## Ignore the token |
## Ignore the token |
| 3641 |
!!!next-token; |
!!!next-token; |
| 3642 |
redo B; |
redo B; |
| 3649 |
!!!cp ('t119'); |
!!!cp ('t119'); |
| 3650 |
## As if </noscript> |
## As if </noscript> |
| 3651 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3652 |
!!!parse-error (type => 'in noscript:script'); |
!!!parse-error (type => 'in noscript:script', token => $token); |
| 3653 |
|
|
| 3654 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 3655 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 3656 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 3657 |
!!!cp ('t120'); |
!!!cp ('t120'); |
| 3658 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
| 3659 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3660 |
} else { |
} else { |
| 3661 |
!!!cp ('t121'); |
!!!cp ('t121'); |
| 3662 |
} |
} |
| 3663 |
|
|
| 3664 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 3665 |
$script_start_tag->($insert_to_current); |
$script_start_tag->(); |
| 3666 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} # <head> |
| 3667 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 3668 |
redo B; |
redo B; |
| 3669 |
} elsif ($token->{tag_name} eq 'body' or |
} elsif ($token->{tag_name} eq 'body' or |
| 3672 |
!!!cp ('t122'); |
!!!cp ('t122'); |
| 3673 |
## As if </noscript> |
## As if </noscript> |
| 3674 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3675 |
!!!parse-error (type => 'in noscript:'.$token->{tag_name}); |
!!!parse-error (type => 'in noscript:'.$token->{tag_name}, token => $token); |
| 3676 |
|
|
| 3677 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 3678 |
## As if </head> |
## As if </head> |
| 3689 |
} |
} |
| 3690 |
|
|
| 3691 |
## "after head" insertion mode |
## "after head" insertion mode |
| 3692 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 3693 |
if ($token->{tag_name} eq 'body') { |
if ($token->{tag_name} eq 'body') { |
| 3694 |
!!!cp ('t126'); |
!!!cp ('t126'); |
| 3695 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 3710 |
!!!cp ('t129'); |
!!!cp ('t129'); |
| 3711 |
## As if </noscript> |
## As if </noscript> |
| 3712 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3713 |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}); |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}, token => $token); |
| 3714 |
|
|
| 3715 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 3716 |
## As if </head> |
## As if </head> |
| 3729 |
|
|
| 3730 |
## "after head" insertion mode |
## "after head" insertion mode |
| 3731 |
## As if <body> |
## As if <body> |
| 3732 |
!!!insert-element ('body'); |
!!!insert-element ('body',, $token); |
| 3733 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 3734 |
## reprocess |
## reprocess |
| 3735 |
redo B; |
redo B; |
| 3738 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3739 |
!!!cp ('t132'); |
!!!cp ('t132'); |
| 3740 |
## As if <head> |
## As if <head> |
| 3741 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, 'head',, $token); |
| 3742 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 3743 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3744 |
|
|
| 3751 |
!!!cp ('t133'); |
!!!cp ('t133'); |
| 3752 |
## As if </noscript> |
## As if </noscript> |
| 3753 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3754 |
!!!parse-error (type => 'in noscript:/head'); |
!!!parse-error (type => 'in noscript:/head', token => $token); |
| 3755 |
|
|
| 3756 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 3757 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3777 |
redo B; |
redo B; |
| 3778 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3779 |
!!!cp ('t137'); |
!!!cp ('t137'); |
| 3780 |
!!!parse-error (type => 'unmatched end tag:noscript'); |
!!!parse-error (type => 'unmatched end tag:noscript', token => $token); |
| 3781 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 3782 |
!!!next-token; |
!!!next-token; |
| 3783 |
redo B; |
redo B; |
| 3791 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3792 |
!!!cp ('t139'); |
!!!cp ('t139'); |
| 3793 |
## As if <head> |
## As if <head> |
| 3794 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, 'head',, $token); |
| 3795 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 3796 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3797 |
|
|
| 3799 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 3800 |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 3801 |
!!!cp ('t140'); |
!!!cp ('t140'); |
| 3802 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 3803 |
## Ignore the token |
## Ignore the token |
| 3804 |
!!!next-token; |
!!!next-token; |
| 3805 |
redo B; |
redo B; |
| 3814 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3815 |
!!!cp ('t142'); |
!!!cp ('t142'); |
| 3816 |
## As if <head> |
## As if <head> |
| 3817 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, 'head',, $token); |
| 3818 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 3819 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3820 |
|
|
| 3831 |
# |
# |
| 3832 |
} else { |
} else { |
| 3833 |
!!!cp ('t145'); |
!!!cp ('t145'); |
| 3834 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 3835 |
## Ignore the token |
## Ignore the token |
| 3836 |
!!!next-token; |
!!!next-token; |
| 3837 |
redo B; |
redo B; |
| 3842 |
!!!cp ('t146'); |
!!!cp ('t146'); |
| 3843 |
## As if </noscript> |
## As if </noscript> |
| 3844 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3845 |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}); |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}, token => $token); |
| 3846 |
|
|
| 3847 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 3848 |
## As if </head> |
## As if </head> |
| 3858 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3859 |
## ISSUE: This case cannot be reached? |
## ISSUE: This case cannot be reached? |
| 3860 |
!!!cp ('t148'); |
!!!cp ('t148'); |
| 3861 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 3862 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 3863 |
!!!next-token; |
!!!next-token; |
| 3864 |
redo B; |
redo B; |
| 3868 |
|
|
| 3869 |
## "after head" insertion mode |
## "after head" insertion mode |
| 3870 |
## As if <body> |
## As if <body> |
| 3871 |
!!!insert-element ('body'); |
!!!insert-element ('body',, $token); |
| 3872 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 3873 |
## reprocess |
## reprocess |
| 3874 |
redo B; |
redo B; |
| 3875 |
} else { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 3876 |
die "$0: $token->{type}: Unknown token type"; |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3877 |
} |
!!!cp ('t149.1'); |
| 3878 |
|
|
| 3879 |
|
## NOTE: As if <head> |
| 3880 |
|
!!!create-element ($self->{head_element}, 'head',, $token); |
| 3881 |
|
$self->{open_elements}->[-1]->[0]->append_child |
| 3882 |
|
($self->{head_element}); |
| 3883 |
|
#push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3884 |
|
#$self->{insertion_mode} = IN_HEAD_IM; |
| 3885 |
|
## NOTE: Reprocess. |
| 3886 |
|
|
| 3887 |
|
## NOTE: As if </head> |
| 3888 |
|
#pop @{$self->{open_elements}}; |
| 3889 |
|
#$self->{insertion_mode} = IN_AFTER_HEAD_IM; |
| 3890 |
|
## NOTE: Reprocess. |
| 3891 |
|
|
| 3892 |
|
# |
| 3893 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 3894 |
|
!!!cp ('t149.2'); |
| 3895 |
|
|
| 3896 |
|
## NOTE: As if </head> |
| 3897 |
|
pop @{$self->{open_elements}}; |
| 3898 |
|
#$self->{insertion_mode} = IN_AFTER_HEAD_IM; |
| 3899 |
|
## NOTE: Reprocess. |
| 3900 |
|
|
| 3901 |
|
# |
| 3902 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 3903 |
|
!!!cp ('t149.3'); |
| 3904 |
|
|
| 3905 |
|
!!!parse-error (type => 'in noscript:#eof', token => $token); |
| 3906 |
|
|
| 3907 |
|
## As if </noscript> |
| 3908 |
|
pop @{$self->{open_elements}}; |
| 3909 |
|
#$self->{insertion_mode} = IN_HEAD_IM; |
| 3910 |
|
## NOTE: Reprocess. |
| 3911 |
|
|
| 3912 |
|
## NOTE: As if </head> |
| 3913 |
|
pop @{$self->{open_elements}}; |
| 3914 |
|
#$self->{insertion_mode} = IN_AFTER_HEAD_IM; |
| 3915 |
|
## NOTE: Reprocess. |
| 3916 |
|
|
| 3917 |
|
# |
| 3918 |
|
} else { |
| 3919 |
|
!!!cp ('t149.4'); |
| 3920 |
|
# |
| 3921 |
|
} |
| 3922 |
|
|
| 3923 |
|
## NOTE: As if <body> |
| 3924 |
|
!!!insert-element ('body',, $token); |
| 3925 |
|
$self->{insertion_mode} = IN_BODY_IM; |
| 3926 |
|
## NOTE: Reprocess. |
| 3927 |
|
redo B; |
| 3928 |
|
} else { |
| 3929 |
|
die "$0: $token->{type}: Unknown token type"; |
| 3930 |
|
} |
| 3931 |
|
|
| 3932 |
## ISSUE: An issue in the spec. |
## ISSUE: An issue in the spec. |
| 3933 |
} elsif ($self->{insertion_mode} & BODY_IMS) { |
} elsif ($self->{insertion_mode} & BODY_IMS) { |
| 3947 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 3948 |
if ($self->{insertion_mode} == IN_CELL_IM) { |
if ($self->{insertion_mode} == IN_CELL_IM) { |
| 3949 |
## have an element in table scope |
## have an element in table scope |
| 3950 |
my $tn; |
for (reverse 0..$#{$self->{open_elements}}) { |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
| 3951 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 3952 |
if ($node->[1] eq 'td' or $node->[1] eq 'th') { |
if ($node->[1] eq 'td' or $node->[1] eq 'th') { |
| 3953 |
!!!cp ('t151'); |
!!!cp ('t151'); |
| 3954 |
$tn = $node->[1]; |
|
| 3955 |
last INSCOPE; |
## Close the cell |
| 3956 |
|
!!!back-token; # <?> |
| 3957 |
|
$token = {type => END_TAG_TOKEN, tag_name => $node->[1], |
| 3958 |
|
line => $token->{line}, |
| 3959 |
|
column => $token->{column}}; |
| 3960 |
|
redo B; |
| 3961 |
} elsif ({ |
} elsif ({ |
| 3962 |
table => 1, html => 1, |
table => 1, html => 1, |
| 3963 |
}->{$node->[1]}) { |
}->{$node->[1]}) { |
| 3964 |
!!!cp ('t152'); |
!!!cp ('t152'); |
| 3965 |
last INSCOPE; |
## ISSUE: This case can never be reached, maybe. |
| 3966 |
|
last; |
| 3967 |
} |
} |
| 3968 |
} # INSCOPE |
} |
| 3969 |
unless (defined $tn) { |
|
| 3970 |
!!!cp ('t153'); |
!!!cp ('t153'); |
| 3971 |
## TODO: This error type is wrong. |
!!!parse-error (type => 'start tag not allowed', |
| 3972 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
value => $token->{tag_name}, token => $token); |
| 3973 |
## Ignore the token |
## Ignore the token |
| 3974 |
!!!next-token; |
!!!next-token; |
|
redo B; |
|
|
} |
|
|
|
|
|
!!!cp ('t154'); |
|
|
## Close the cell |
|
|
!!!back-token; # <?> |
|
|
$token = {type => END_TAG_TOKEN, tag_name => $tn}; |
|
| 3975 |
redo B; |
redo B; |
| 3976 |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 3977 |
!!!parse-error (type => 'not closed:caption'); |
!!!parse-error (type => 'not closed:caption', token => $token); |
| 3978 |
|
|
| 3979 |
## As if </caption> |
## NOTE: As if </caption>. |
| 3980 |
## have a table element in table scope |
## have a table element in table scope |
| 3981 |
my $i; |
my $i; |
| 3982 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: { |
| 3983 |
my $node = $self->{open_elements}->[$_]; |
for (reverse 0..$#{$self->{open_elements}}) { |
| 3984 |
if ($node->[1] eq 'caption') { |
my $node = $self->{open_elements}->[$_]; |
| 3985 |
!!!cp ('t155'); |
if ($node->[1] eq 'caption') { |
| 3986 |
$i = $_; |
!!!cp ('t155'); |
| 3987 |
last INSCOPE; |
$i = $_; |
| 3988 |
} elsif ({ |
last INSCOPE; |
| 3989 |
table => 1, html => 1, |
} elsif ({ |
| 3990 |
}->{$node->[1]}) { |
table => 1, html => 1, |
| 3991 |
!!!cp ('t156'); |
}->{$node->[1]}) { |
| 3992 |
last INSCOPE; |
!!!cp ('t156'); |
| 3993 |
|
last; |
| 3994 |
|
} |
| 3995 |
} |
} |
| 3996 |
|
|
| 3997 |
|
!!!cp ('t157'); |
| 3998 |
|
!!!parse-error (type => 'start tag not allowed', |
| 3999 |
|
value => $token->{tag_name}, token => $token); |
| 4000 |
|
## Ignore the token |
| 4001 |
|
!!!next-token; |
| 4002 |
|
redo B; |
| 4003 |
} # INSCOPE |
} # INSCOPE |
|
unless (defined $i) { |
|
|
!!!cp ('t157'); |
|
|
## TODO: this type is wrong. |
|
|
!!!parse-error (type => 'unmatched end tag:caption'); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
| 4004 |
|
|
| 4005 |
## generate implied end tags |
## generate implied end tags |
| 4006 |
if ({ |
while ({ |
| 4007 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 4008 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
## NOTE: Maybe the following elements never appear here. |
|
|
td => 1, th => 1, tr => 1, |
|
|
tbody => 1, tfoot => 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 4009 |
!!!cp ('t158'); |
!!!cp ('t158'); |
| 4010 |
!!!back-token; # <?> |
pop @{$self->{open_elements}}; |
|
$token = {type => END_TAG_TOKEN, tag_name => 'caption'}; |
|
|
!!!back-token; |
|
|
$token = {type => END_TAG_TOKEN, |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
| 4011 |
} |
} |
| 4012 |
|
|
| 4013 |
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
| 4014 |
!!!cp ('t159'); |
!!!cp ('t159'); |
| 4015 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 4016 |
} else { |
} else { |
| 4017 |
!!!cp ('t160'); |
!!!cp ('t160'); |
| 4018 |
} |
} |
| 4053 |
} # INSCOPE |
} # INSCOPE |
| 4054 |
unless (defined $i) { |
unless (defined $i) { |
| 4055 |
!!!cp ('t165'); |
!!!cp ('t165'); |
| 4056 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4057 |
## Ignore the token |
## Ignore the token |
| 4058 |
!!!next-token; |
!!!next-token; |
| 4059 |
redo B; |
redo B; |
| 4060 |
} |
} |
| 4061 |
|
|
| 4062 |
## generate implied end tags |
## generate implied end tags |
| 4063 |
if ({ |
while ({ |
| 4064 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 4065 |
td => ($token->{tag_name} eq 'th'), |
}->{$self->{open_elements}->[-1]->[1]}) { |
|
th => ($token->{tag_name} eq 'td'), |
|
|
|
|
|
## NOTE: Maybe the following elements never appear here. |
|
|
tr => 1, |
|
|
tbody => 1, tfoot => 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 4066 |
!!!cp ('t166'); |
!!!cp ('t166'); |
| 4067 |
!!!back-token; |
pop @{$self->{open_elements}}; |
|
$token = {type => END_TAG_TOKEN, |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
| 4068 |
} |
} |
| 4069 |
|
|
| 4070 |
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
| 4071 |
!!!cp ('t167'); |
!!!cp ('t167'); |
| 4072 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 4073 |
} else { |
} else { |
| 4074 |
!!!cp ('t168'); |
!!!cp ('t168'); |
| 4075 |
} |
} |
| 4084 |
redo B; |
redo B; |
| 4085 |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 4086 |
!!!cp ('t169'); |
!!!cp ('t169'); |
| 4087 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4088 |
## Ignore the token |
## Ignore the token |
| 4089 |
!!!next-token; |
!!!next-token; |
| 4090 |
redo B; |
redo B; |
| 4096 |
if ($self->{insertion_mode} == IN_CAPTION_IM) { |
if ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 4097 |
## have a table element in table scope |
## have a table element in table scope |
| 4098 |
my $i; |
my $i; |
| 4099 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: { |
| 4100 |
my $node = $self->{open_elements}->[$_]; |
for (reverse 0..$#{$self->{open_elements}}) { |
| 4101 |
if ($node->[1] eq $token->{tag_name}) { |
my $node = $self->{open_elements}->[$_]; |
| 4102 |
!!!cp ('t171'); |
if ($node->[1] eq $token->{tag_name}) { |
| 4103 |
$i = $_; |
!!!cp ('t171'); |
| 4104 |
last INSCOPE; |
$i = $_; |
| 4105 |
} elsif ({ |
last INSCOPE; |
| 4106 |
table => 1, html => 1, |
} elsif ({ |
| 4107 |
}->{$node->[1]}) { |
table => 1, html => 1, |
| 4108 |
!!!cp ('t172'); |
}->{$node->[1]}) { |
| 4109 |
last INSCOPE; |
!!!cp ('t172'); |
| 4110 |
|
last; |
| 4111 |
|
} |
| 4112 |
} |
} |
| 4113 |
|
|
| 4114 |
|
!!!cp ('t173'); |
| 4115 |
|
!!!parse-error (type => 'unmatched end tag', |
| 4116 |
|
value => $token->{tag_name}, token => $token); |
| 4117 |
|
## Ignore the token |
| 4118 |
|
!!!next-token; |
| 4119 |
|
redo B; |
| 4120 |
} # INSCOPE |
} # INSCOPE |
|
unless (defined $i) { |
|
|
!!!cp ('t173'); |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
| 4121 |
|
|
| 4122 |
## generate implied end tags |
## generate implied end tags |
| 4123 |
if ({ |
while ({ |
| 4124 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 4125 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
## NOTE: The following elements never appear here, maybe. |
|
|
td => 1, th => 1, tr => 1, |
|
|
tbody => 1, tfoot => 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 4126 |
!!!cp ('t174'); |
!!!cp ('t174'); |
| 4127 |
!!!back-token; |
pop @{$self->{open_elements}}; |
|
$token = {type => END_TAG_TOKEN, |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
| 4128 |
} |
} |
| 4129 |
|
|
| 4130 |
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
| 4131 |
!!!cp ('t175'); |
!!!cp ('t175'); |
| 4132 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 4133 |
} else { |
} else { |
| 4134 |
!!!cp ('t176'); |
!!!cp ('t176'); |
| 4135 |
} |
} |
| 4144 |
redo B; |
redo B; |
| 4145 |
} elsif ($self->{insertion_mode} == IN_CELL_IM) { |
} elsif ($self->{insertion_mode} == IN_CELL_IM) { |
| 4146 |
!!!cp ('t177'); |
!!!cp ('t177'); |
| 4147 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4148 |
## Ignore the token |
## Ignore the token |
| 4149 |
!!!next-token; |
!!!next-token; |
| 4150 |
redo B; |
redo B; |
| 4160 |
## have an element in table scope |
## have an element in table scope |
| 4161 |
my $i; |
my $i; |
| 4162 |
my $tn; |
my $tn; |
| 4163 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: { |
| 4164 |
my $node = $self->{open_elements}->[$_]; |
for (reverse 0..$#{$self->{open_elements}}) { |
| 4165 |
if ($node->[1] eq $token->{tag_name}) { |
my $node = $self->{open_elements}->[$_]; |
| 4166 |
!!!cp ('t179'); |
if ($node->[1] eq $token->{tag_name}) { |
| 4167 |
$i = $_; |
!!!cp ('t179'); |
| 4168 |
last INSCOPE; |
$i = $_; |
| 4169 |
} elsif ($node->[1] eq 'td' or $node->[1] eq 'th') { |
|
| 4170 |
!!!cp ('t180'); |
## Close the cell |
| 4171 |
$tn = $node->[1]; |
!!!back-token; # </?> |
| 4172 |
## NOTE: There is exactly one |td| or |th| element |
$token = {type => END_TAG_TOKEN, tag_name => $tn, |
| 4173 |
## in scope in the stack of open elements by definition. |
line => $token->{line}, |
| 4174 |
} elsif ({ |
column => $token->{column}}; |
| 4175 |
table => 1, html => 1, |
redo B; |
| 4176 |
}->{$node->[1]}) { |
} elsif ($node->[1] eq 'td' or $node->[1] eq 'th') { |
| 4177 |
!!!cp ('t181'); |
!!!cp ('t180'); |
| 4178 |
last INSCOPE; |
$tn = $node->[1]; |
| 4179 |
|
## NOTE: There is exactly one |td| or |th| element |
| 4180 |
|
## in scope in the stack of open elements by definition. |
| 4181 |
|
} elsif ({ |
| 4182 |
|
table => 1, html => 1, |
| 4183 |
|
}->{$node->[1]}) { |
| 4184 |
|
## ISSUE: Can this be reached? |
| 4185 |
|
!!!cp ('t181'); |
| 4186 |
|
last; |
| 4187 |
|
} |
| 4188 |
} |
} |
| 4189 |
} # INSCOPE |
|
|
unless (defined $i) { |
|
| 4190 |
!!!cp ('t182'); |
!!!cp ('t182'); |
| 4191 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 4192 |
|
value => $token->{tag_name}, token => $token); |
| 4193 |
## Ignore the token |
## Ignore the token |
| 4194 |
!!!next-token; |
!!!next-token; |
| 4195 |
redo B; |
redo B; |
| 4196 |
} else { |
} # INSCOPE |
|
!!!cp ('t183'); |
|
|
} |
|
|
|
|
|
## Close the cell |
|
|
!!!back-token; # </?> |
|
|
$token = {type => END_TAG_TOKEN, tag_name => $tn}; |
|
|
redo B; |
|
| 4197 |
} elsif ($token->{tag_name} eq 'table' and |
} elsif ($token->{tag_name} eq 'table' and |
| 4198 |
$self->{insertion_mode} == IN_CAPTION_IM) { |
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 4199 |
!!!parse-error (type => 'not closed:caption'); |
!!!parse-error (type => 'not closed:caption', token => $token); |
| 4200 |
|
|
| 4201 |
## As if </caption> |
## As if </caption> |
| 4202 |
## have a table element in table scope |
## have a table element in table scope |
| 4216 |
} # INSCOPE |
} # INSCOPE |
| 4217 |
unless (defined $i) { |
unless (defined $i) { |
| 4218 |
!!!cp ('t186'); |
!!!cp ('t186'); |
| 4219 |
!!!parse-error (type => 'unmatched end tag:caption'); |
!!!parse-error (type => 'unmatched end tag:caption', token => $token); |
| 4220 |
## Ignore the token |
## Ignore the token |
| 4221 |
!!!next-token; |
!!!next-token; |
| 4222 |
redo B; |
redo B; |
| 4223 |
} |
} |
| 4224 |
|
|
| 4225 |
## generate implied end tags |
## generate implied end tags |
| 4226 |
if ({ |
while ({ |
| 4227 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 4228 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
## NOTE: The following elements never appear, maybe. |
|
|
td => 1, th => 1, tr => 1, |
|
|
tbody => 1, tfoot => 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 4229 |
!!!cp ('t187'); |
!!!cp ('t187'); |
| 4230 |
!!!back-token; # </table> |
pop @{$self->{open_elements}}; |
|
$token = {type => END_TAG_TOKEN, tag_name => 'caption'}; |
|
|
!!!back-token; |
|
|
$token = {type => END_TAG_TOKEN, |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
| 4231 |
} |
} |
| 4232 |
|
|
| 4233 |
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
| 4234 |
!!!cp ('t188'); |
!!!cp ('t188'); |
| 4235 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 4236 |
} else { |
} else { |
| 4237 |
!!!cp ('t189'); |
!!!cp ('t189'); |
| 4238 |
} |
} |
| 4250 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 4251 |
if ($self->{insertion_mode} & BODY_TABLE_IMS) { |
if ($self->{insertion_mode} & BODY_TABLE_IMS) { |
| 4252 |
!!!cp ('t190'); |
!!!cp ('t190'); |
| 4253 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4254 |
## Ignore the token |
## Ignore the token |
| 4255 |
!!!next-token; |
!!!next-token; |
| 4256 |
redo B; |
redo B; |
| 4264 |
}->{$token->{tag_name}} and |
}->{$token->{tag_name}} and |
| 4265 |
$self->{insertion_mode} == IN_CAPTION_IM) { |
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 4266 |
!!!cp ('t192'); |
!!!cp ('t192'); |
| 4267 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4268 |
## Ignore the token |
## Ignore the token |
| 4269 |
!!!next-token; |
!!!next-token; |
| 4270 |
redo B; |
redo B; |
| 4272 |
!!!cp ('t193'); |
!!!cp ('t193'); |
| 4273 |
# |
# |
| 4274 |
} |
} |
| 4275 |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 4276 |
|
for my $entry (@{$self->{open_elements}}) { |
| 4277 |
|
if (not { |
| 4278 |
|
dd => 1, dt => 1, li => 1, p => 1, tbody => 1, td => 1, tfoot => 1, |
| 4279 |
|
th => 1, thead => 1, tr => 1, body => 1, html => 1, |
| 4280 |
|
}->{$entry->[1]}) { |
| 4281 |
|
!!!cp ('t75'); |
| 4282 |
|
!!!parse-error (type => 'in body:#eof', token => $token); |
| 4283 |
|
last; |
| 4284 |
|
} |
| 4285 |
|
} |
| 4286 |
|
|
| 4287 |
|
## Stop parsing. |
| 4288 |
|
last B; |
| 4289 |
} else { |
} else { |
| 4290 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 4291 |
} |
} |
| 4294 |
# |
# |
| 4295 |
} elsif ($self->{insertion_mode} & TABLE_IMS) { |
} elsif ($self->{insertion_mode} & TABLE_IMS) { |
| 4296 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 4297 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if (not $open_tables->[-1]->[1] and # tainted |
| 4298 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 4299 |
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 4300 |
|
|
| 4301 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 4302 |
!!!cp ('t194'); |
!!!cp ('t194'); |
| 4303 |
!!!next-token; |
!!!next-token; |
| 4304 |
redo B; |
redo B; |
| 4305 |
} else { |
} else { |
| 4306 |
!!!cp ('t195'); |
!!!cp ('t195'); |
| 4307 |
} |
} |
| 4308 |
} |
} |
| 4309 |
|
|
| 4310 |
!!!parse-error (type => 'in table:#character'); |
!!!parse-error (type => 'in table:#character', token => $token); |
| 4311 |
|
|
| 4312 |
## As if in body, but insert into foster parent element |
## As if in body, but insert into foster parent element |
| 4313 |
## ISSUE: Spec says that "whenever a node would be inserted |
## ISSUE: Spec says that "whenever a node would be inserted |
| 4352 |
($self->{document}->create_text_node ($token->{data}), |
($self->{document}->create_text_node ($token->{data}), |
| 4353 |
$next_sibling); |
$next_sibling); |
| 4354 |
} |
} |
| 4355 |
} else { |
$open_tables->[-1]->[1] = 1; # tainted |
| 4356 |
!!!cp ('t200'); |
} else { |
| 4357 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
!!!cp ('t200'); |
| 4358 |
} |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
| 4359 |
|
} |
| 4360 |
|
|
| 4361 |
!!!next-token; |
!!!next-token; |
| 4362 |
redo B; |
redo B; |
| 4363 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 4364 |
if ({ |
if ({ |
| 4365 |
tr => ($self->{insertion_mode} != IN_ROW_IM), |
tr => ($self->{insertion_mode} != IN_ROW_IM), |
| 4370 |
while ($self->{open_elements}->[-1]->[1] ne 'table' and |
while ($self->{open_elements}->[-1]->[1] ne 'table' and |
| 4371 |
$self->{open_elements}->[-1]->[1] ne 'html') { |
$self->{open_elements}->[-1]->[1] ne 'html') { |
| 4372 |
!!!cp ('t201'); |
!!!cp ('t201'); |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4373 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4374 |
} |
} |
| 4375 |
|
|
| 4376 |
!!!insert-element ('tbody'); |
!!!insert-element ('tbody',, $token); |
| 4377 |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 4378 |
## reprocess in the "in table body" insertion mode... |
## reprocess in the "in table body" insertion mode... |
| 4379 |
} |
} |
| 4381 |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
| 4382 |
unless ($token->{tag_name} eq 'tr') { |
unless ($token->{tag_name} eq 'tr') { |
| 4383 |
!!!cp ('t202'); |
!!!cp ('t202'); |
| 4384 |
!!!parse-error (type => 'missing start tag:tr'); |
!!!parse-error (type => 'missing start tag:tr', token => $token); |
| 4385 |
} |
} |
| 4386 |
|
|
| 4387 |
## Clear back to table body context |
## Clear back to table body context |
| 4390 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4391 |
!!!cp ('t203'); |
!!!cp ('t203'); |
| 4392 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4393 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4394 |
} |
} |
| 4395 |
|
|
| 4396 |
$self->{insertion_mode} = IN_ROW_IM; |
$self->{insertion_mode} = IN_ROW_IM; |
| 4397 |
if ($token->{tag_name} eq 'tr') { |
if ($token->{tag_name} eq 'tr') { |
| 4398 |
!!!cp ('t204'); |
!!!cp ('t204'); |
| 4399 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 4400 |
!!!next-token; |
!!!next-token; |
| 4401 |
redo B; |
redo B; |
| 4402 |
} else { |
} else { |
| 4403 |
!!!cp ('t205'); |
!!!cp ('t205'); |
| 4404 |
!!!insert-element ('tr'); |
!!!insert-element ('tr',, $token); |
| 4405 |
## reprocess in the "in row" insertion mode |
## reprocess in the "in row" insertion mode |
| 4406 |
} |
} |
| 4407 |
} else { |
} else { |
| 4413 |
tr => 1, html => 1, |
tr => 1, html => 1, |
| 4414 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4415 |
!!!cp ('t207'); |
!!!cp ('t207'); |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4416 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4417 |
} |
} |
| 4418 |
|
|
| 4419 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 4420 |
$self->{insertion_mode} = IN_CELL_IM; |
$self->{insertion_mode} = IN_CELL_IM; |
| 4421 |
|
|
| 4422 |
push @$active_formatting_elements, ['#marker', '']; |
push @$active_formatting_elements, ['#marker', '']; |
| 4451 |
unless (defined $i) { |
unless (defined $i) { |
| 4452 |
!!!cp ('t210'); |
!!!cp ('t210'); |
| 4453 |
## TODO: This type is wrong. |
## TODO: This type is wrong. |
| 4454 |
!!!parse-error (type => 'unmacthed end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmacthed end tag:'.$token->{tag_name}, token => $token); |
| 4455 |
## Ignore the token |
## Ignore the token |
| 4456 |
!!!next-token; |
!!!next-token; |
| 4457 |
redo B; |
redo B; |
| 4463 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4464 |
!!!cp ('t211'); |
!!!cp ('t211'); |
| 4465 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4466 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4467 |
} |
} |
| 4468 |
|
|
| 4499 |
unless (defined $i) { |
unless (defined $i) { |
| 4500 |
!!!cp ('t216'); |
!!!cp ('t216'); |
| 4501 |
## TODO: This erorr type ios wrong. |
## TODO: This erorr type ios wrong. |
| 4502 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4503 |
## Ignore the token |
## Ignore the token |
| 4504 |
!!!next-token; |
!!!next-token; |
| 4505 |
redo B; |
redo B; |
| 4511 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4512 |
!!!cp ('t217'); |
!!!cp ('t217'); |
| 4513 |
## ISSUE: Can this state be reached? |
## ISSUE: Can this state be reached? |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4514 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4515 |
} |
} |
| 4516 |
|
|
| 4534 |
$self->{open_elements}->[-1]->[1] ne 'html') { |
$self->{open_elements}->[-1]->[1] ne 'html') { |
| 4535 |
!!!cp ('t219'); |
!!!cp ('t219'); |
| 4536 |
## ISSUE: Can this state be reached? |
## ISSUE: Can this state be reached? |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4537 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4538 |
} |
} |
| 4539 |
|
|
| 4540 |
!!!insert-element ('colgroup'); |
!!!insert-element ('colgroup',, $token); |
| 4541 |
$self->{insertion_mode} = IN_COLUMN_GROUP_IM; |
$self->{insertion_mode} = IN_COLUMN_GROUP_IM; |
| 4542 |
## reprocess |
## reprocess |
| 4543 |
redo B; |
redo B; |
| 4551 |
$self->{open_elements}->[-1]->[1] ne 'html') { |
$self->{open_elements}->[-1]->[1] ne 'html') { |
| 4552 |
!!!cp ('t220'); |
!!!cp ('t220'); |
| 4553 |
## ISSUE: Can this state be reached? |
## ISSUE: Can this state be reached? |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4554 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4555 |
} |
} |
| 4556 |
|
|
| 4557 |
push @$active_formatting_elements, ['#marker', ''] |
push @$active_formatting_elements, ['#marker', ''] |
| 4558 |
if $token->{tag_name} eq 'caption'; |
if $token->{tag_name} eq 'caption'; |
| 4559 |
|
|
| 4560 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 4561 |
$self->{insertion_mode} = { |
$self->{insertion_mode} = { |
| 4562 |
caption => IN_CAPTION_IM, |
caption => IN_CAPTION_IM, |
| 4563 |
colgroup => IN_COLUMN_GROUP_IM, |
colgroup => IN_COLUMN_GROUP_IM, |
| 4571 |
die "$0: in table: <>: $token->{tag_name}"; |
die "$0: in table: <>: $token->{tag_name}"; |
| 4572 |
} |
} |
| 4573 |
} elsif ($token->{tag_name} eq 'table') { |
} elsif ($token->{tag_name} eq 'table') { |
| 4574 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 4575 |
|
|
| 4576 |
## As if </table> |
## As if </table> |
| 4577 |
## have a table element in table scope |
## have a table element in table scope |
| 4593 |
unless (defined $i) { |
unless (defined $i) { |
| 4594 |
!!!cp ('t223'); |
!!!cp ('t223'); |
| 4595 |
## TODO: The following is wrong, maybe. |
## TODO: The following is wrong, maybe. |
| 4596 |
!!!parse-error (type => 'unmatched end tag:table'); |
!!!parse-error (type => 'unmatched end tag:table', token => $token); |
| 4597 |
## Ignore tokens </table><table> |
## Ignore tokens </table><table> |
| 4598 |
!!!next-token; |
!!!next-token; |
| 4599 |
redo B; |
redo B; |
| 4600 |
} |
} |
| 4601 |
|
|
| 4602 |
|
## TODO: Followings are removed from the latest spec. |
| 4603 |
## generate implied end tags |
## generate implied end tags |
| 4604 |
if ({ |
while ({ |
| 4605 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 4606 |
td => 1, th => 1, tr => 1, |
}->{$self->{open_elements}->[-1]->[1]}) { |
|
tbody => 1, tfoot=> 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 4607 |
!!!cp ('t224'); |
!!!cp ('t224'); |
| 4608 |
!!!back-token; # <table> |
pop @{$self->{open_elements}}; |
|
$token = {type => END_TAG_TOKEN, tag_name => 'table'}; |
|
|
!!!back-token; |
|
|
$token = {type => END_TAG_TOKEN, |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
| 4609 |
} |
} |
| 4610 |
|
|
| 4611 |
if ($self->{open_elements}->[-1]->[1] ne 'table') { |
if ($self->{open_elements}->[-1]->[1] ne 'table') { |
| 4612 |
!!!cp ('t225'); |
!!!cp ('t225'); |
| 4613 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
| 4614 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 4615 |
} else { |
} else { |
| 4616 |
!!!cp ('t226'); |
!!!cp ('t226'); |
| 4617 |
} |
} |
| 4618 |
|
|
| 4619 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 4620 |
|
pop @{$open_tables}; |
| 4621 |
|
|
| 4622 |
$self->_reset_insertion_mode; |
$self->_reset_insertion_mode; |
| 4623 |
|
|
| 4624 |
## reprocess |
## reprocess |
| 4625 |
redo B; |
redo B; |
| 4626 |
|
} elsif ($token->{tag_name} eq 'style') { |
| 4627 |
|
if (not $open_tables->[-1]->[1]) { # tainted |
| 4628 |
|
!!!cp ('t227.8'); |
| 4629 |
|
## NOTE: This is a "as if in head" code clone. |
| 4630 |
|
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 4631 |
|
redo B; |
| 4632 |
|
} else { |
| 4633 |
|
!!!cp ('t227.7'); |
| 4634 |
|
# |
| 4635 |
|
} |
| 4636 |
|
} elsif ($token->{tag_name} eq 'script') { |
| 4637 |
|
if (not $open_tables->[-1]->[1]) { # tainted |
| 4638 |
|
!!!cp ('t227.6'); |
| 4639 |
|
## NOTE: This is a "as if in head" code clone. |
| 4640 |
|
$script_start_tag->(); |
| 4641 |
|
redo B; |
| 4642 |
|
} else { |
| 4643 |
|
!!!cp ('t227.5'); |
| 4644 |
|
# |
| 4645 |
|
} |
| 4646 |
|
} elsif ($token->{tag_name} eq 'input') { |
| 4647 |
|
if (not $open_tables->[-1]->[1]) { # tainted |
| 4648 |
|
if ($token->{attributes}->{type}) { ## TODO: case |
| 4649 |
|
my $type = lc $token->{attributes}->{type}->{value}; |
| 4650 |
|
if ($type eq 'hidden') { |
| 4651 |
|
!!!cp ('t227.3'); |
| 4652 |
|
!!!parse-error (type => 'in table:'.$token->{tag_name}, token => $token); |
| 4653 |
|
|
| 4654 |
|
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 4655 |
|
|
| 4656 |
|
## TODO: form element pointer |
| 4657 |
|
|
| 4658 |
|
pop @{$self->{open_elements}}; |
| 4659 |
|
|
| 4660 |
|
!!!next-token; |
| 4661 |
|
redo B; |
| 4662 |
|
} else { |
| 4663 |
|
!!!cp ('t227.2'); |
| 4664 |
|
# |
| 4665 |
|
} |
| 4666 |
|
} else { |
| 4667 |
|
!!!cp ('t227.1'); |
| 4668 |
|
# |
| 4669 |
|
} |
| 4670 |
|
} else { |
| 4671 |
|
!!!cp ('t227.4'); |
| 4672 |
|
# |
| 4673 |
|
} |
| 4674 |
} else { |
} else { |
| 4675 |
!!!cp ('t227'); |
!!!cp ('t227'); |
|
!!!parse-error (type => 'in table:'.$token->{tag_name}); |
|
|
|
|
|
$insert = $insert_to_foster; |
|
| 4676 |
# |
# |
| 4677 |
} |
} |
| 4678 |
|
|
| 4679 |
|
!!!parse-error (type => 'in table:'.$token->{tag_name}, token => $token); |
| 4680 |
|
|
| 4681 |
|
$insert = $insert_to_foster; |
| 4682 |
|
# |
| 4683 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 4684 |
if ($token->{tag_name} eq 'tr' and |
if ($token->{tag_name} eq 'tr' and |
| 4685 |
$self->{insertion_mode} == IN_ROW_IM) { |
$self->{insertion_mode} == IN_ROW_IM) { |
| 4700 |
} # INSCOPE |
} # INSCOPE |
| 4701 |
unless (defined $i) { |
unless (defined $i) { |
| 4702 |
!!!cp ('t230'); |
!!!cp ('t230'); |
| 4703 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4704 |
## Ignore the token |
## Ignore the token |
| 4705 |
!!!next-token; |
!!!next-token; |
| 4706 |
redo B; |
redo B; |
| 4714 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4715 |
!!!cp ('t231'); |
!!!cp ('t231'); |
| 4716 |
## ISSUE: Can this state be reached? |
## ISSUE: Can this state be reached? |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4717 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4718 |
} |
} |
| 4719 |
|
|
| 4742 |
unless (defined $i) { |
unless (defined $i) { |
| 4743 |
!!!cp ('t235'); |
!!!cp ('t235'); |
| 4744 |
## TODO: The following is wrong. |
## TODO: The following is wrong. |
| 4745 |
!!!parse-error (type => 'unmatched end tag:'.$token->{type}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{type}, token => $token); |
| 4746 |
## Ignore the token |
## Ignore the token |
| 4747 |
!!!next-token; |
!!!next-token; |
| 4748 |
redo B; |
redo B; |
| 4754 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4755 |
!!!cp ('t236'); |
!!!cp ('t236'); |
| 4756 |
## ISSUE: Can this state be reached? |
## ISSUE: Can this state be reached? |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4757 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4758 |
} |
} |
| 4759 |
|
|
| 4782 |
} # INSCOPE |
} # INSCOPE |
| 4783 |
unless (defined $i) { |
unless (defined $i) { |
| 4784 |
!!!cp ('t239'); |
!!!cp ('t239'); |
| 4785 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4786 |
## Ignore the token |
## Ignore the token |
| 4787 |
!!!next-token; |
!!!next-token; |
| 4788 |
redo B; |
redo B; |
| 4793 |
tbody => 1, tfoot => 1, thead => 1, html => 1, |
tbody => 1, tfoot => 1, thead => 1, html => 1, |
| 4794 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4795 |
!!!cp ('t240'); |
!!!cp ('t240'); |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4796 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4797 |
} |
} |
| 4798 |
|
|
| 4808 |
## reprocess in the "in table" insertion mode... |
## reprocess in the "in table" insertion mode... |
| 4809 |
} |
} |
| 4810 |
|
|
| 4811 |
|
## NOTE: </table> in the "in table" insertion mode. |
| 4812 |
|
## When you edit the code fragment below, please ensure that |
| 4813 |
|
## the code for <table> in the "in table" insertion mode |
| 4814 |
|
## is synced with it. |
| 4815 |
|
|
| 4816 |
## have a table element in table scope |
## have a table element in table scope |
| 4817 |
my $i; |
my $i; |
| 4818 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4830 |
} # INSCOPE |
} # INSCOPE |
| 4831 |
unless (defined $i) { |
unless (defined $i) { |
| 4832 |
!!!cp ('t243'); |
!!!cp ('t243'); |
| 4833 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4834 |
## Ignore the token |
## Ignore the token |
| 4835 |
!!!next-token; |
!!!next-token; |
| 4836 |
redo B; |
redo B; |
| 4837 |
} |
} |
|
|
|
|
## generate implied end tags |
|
|
if ({ |
|
|
dd => 1, dt => 1, li => 1, p => 1, |
|
|
td => 1, th => 1, tr => 1, |
|
|
tbody => 1, tfoot=> 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!cp ('t244'); |
|
|
## ISSUE: Can this case be reached? |
|
|
!!!back-token; |
|
|
$token = {type => END_TAG_TOKEN, |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
|
} |
|
|
|
|
|
if ($self->{open_elements}->[-1]->[1] ne 'table') { |
|
|
!!!cp ('t245'); |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
|
} else { |
|
|
!!!cp ('t246'); |
|
|
} |
|
| 4838 |
|
|
| 4839 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 4840 |
|
pop @{$open_tables}; |
| 4841 |
|
|
| 4842 |
$self->_reset_insertion_mode; |
$self->_reset_insertion_mode; |
| 4843 |
|
|
| 4865 |
} # INSCOPE |
} # INSCOPE |
| 4866 |
unless (defined $i) { |
unless (defined $i) { |
| 4867 |
!!!cp ('t249'); |
!!!cp ('t249'); |
| 4868 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4869 |
## Ignore the token |
## Ignore the token |
| 4870 |
!!!next-token; |
!!!next-token; |
| 4871 |
redo B; |
redo B; |
| 4889 |
} # INSCOPE |
} # INSCOPE |
| 4890 |
unless (defined $i) { |
unless (defined $i) { |
| 4891 |
!!!cp ('t252'); |
!!!cp ('t252'); |
| 4892 |
!!!parse-error (type => 'unmatched end tag:tr'); |
!!!parse-error (type => 'unmatched end tag:tr', token => $token); |
| 4893 |
## Ignore the token |
## Ignore the token |
| 4894 |
!!!next-token; |
!!!next-token; |
| 4895 |
redo B; |
redo B; |
| 4901 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4902 |
!!!cp ('t253'); |
!!!cp ('t253'); |
| 4903 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4904 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4905 |
} |
} |
| 4906 |
|
|
| 4926 |
} # INSCOPE |
} # INSCOPE |
| 4927 |
unless (defined $i) { |
unless (defined $i) { |
| 4928 |
!!!cp ('t256'); |
!!!cp ('t256'); |
| 4929 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4930 |
## Ignore the token |
## Ignore the token |
| 4931 |
!!!next-token; |
!!!next-token; |
| 4932 |
redo B; |
redo B; |
| 4938 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4939 |
!!!cp ('t257'); |
!!!cp ('t257'); |
| 4940 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4941 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4942 |
} |
} |
| 4943 |
|
|
| 4952 |
tbody => 1, tfoot => 1, thead => 1, # $self->{insertion_mode} == IN_TABLE_IM |
tbody => 1, tfoot => 1, thead => 1, # $self->{insertion_mode} == IN_TABLE_IM |
| 4953 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 4954 |
!!!cp ('t258'); |
!!!cp ('t258'); |
| 4955 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4956 |
## Ignore the token |
## Ignore the token |
| 4957 |
!!!next-token; |
!!!next-token; |
| 4958 |
redo B; |
redo B; |
| 4959 |
} else { |
} else { |
| 4960 |
!!!cp ('t259'); |
!!!cp ('t259'); |
| 4961 |
!!!parse-error (type => 'in table:/'.$token->{tag_name}); |
!!!parse-error (type => 'in table:/'.$token->{tag_name}, token => $token); |
| 4962 |
|
|
| 4963 |
$insert = $insert_to_foster; |
$insert = $insert_to_foster; |
| 4964 |
# |
# |
| 4965 |
} |
} |
| 4966 |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 4967 |
|
unless ($self->{open_elements}->[-1]->[1] eq 'html' and |
| 4968 |
|
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 4969 |
|
!!!parse-error (type => 'in body:#eof', token => $token); |
| 4970 |
|
!!!cp ('t259.1'); |
| 4971 |
|
# |
| 4972 |
|
} else { |
| 4973 |
|
!!!cp ('t259.2'); |
| 4974 |
|
# |
| 4975 |
|
} |
| 4976 |
|
|
| 4977 |
|
## Stop parsing |
| 4978 |
|
last B; |
| 4979 |
} else { |
} else { |
| 4980 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 4981 |
} |
} |
| 4995 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 4996 |
if ($token->{tag_name} eq 'col') { |
if ($token->{tag_name} eq 'col') { |
| 4997 |
!!!cp ('t262'); |
!!!cp ('t262'); |
| 4998 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 4999 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5000 |
!!!next-token; |
!!!next-token; |
| 5001 |
redo B; |
redo B; |
| 5007 |
if ($token->{tag_name} eq 'colgroup') { |
if ($token->{tag_name} eq 'colgroup') { |
| 5008 |
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
| 5009 |
!!!cp ('t264'); |
!!!cp ('t264'); |
| 5010 |
!!!parse-error (type => 'unmatched end tag:colgroup'); |
!!!parse-error (type => 'unmatched end tag:colgroup', token => $token); |
| 5011 |
## Ignore the token |
## Ignore the token |
| 5012 |
!!!next-token; |
!!!next-token; |
| 5013 |
redo B; |
redo B; |
| 5020 |
} |
} |
| 5021 |
} elsif ($token->{tag_name} eq 'col') { |
} elsif ($token->{tag_name} eq 'col') { |
| 5022 |
!!!cp ('t266'); |
!!!cp ('t266'); |
| 5023 |
!!!parse-error (type => 'unmatched end tag:col'); |
!!!parse-error (type => 'unmatched end tag:col', token => $token); |
| 5024 |
## Ignore the token |
## Ignore the token |
| 5025 |
!!!next-token; |
!!!next-token; |
| 5026 |
redo B; |
redo B; |
| 5028 |
!!!cp ('t267'); |
!!!cp ('t267'); |
| 5029 |
# |
# |
| 5030 |
} |
} |
| 5031 |
} else { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 5032 |
die "$0: $token->{type}: Unknown token type"; |
if ($self->{open_elements}->[-1]->[1] eq 'html' or |
| 5033 |
} |
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 5034 |
|
!!!cp ('t270.2'); |
| 5035 |
|
## Stop parsing. |
| 5036 |
|
last B; |
| 5037 |
|
} else { |
| 5038 |
|
## NOTE: As if </colgroup>. |
| 5039 |
|
!!!cp ('t270.1'); |
| 5040 |
|
pop @{$self->{open_elements}}; # colgroup |
| 5041 |
|
$self->{insertion_mode} = IN_TABLE_IM; |
| 5042 |
|
## Reprocess. |
| 5043 |
|
redo B; |
| 5044 |
|
} |
| 5045 |
|
} else { |
| 5046 |
|
die "$0: $token->{type}: Unknown token type"; |
| 5047 |
|
} |
| 5048 |
|
|
| 5049 |
## As if </colgroup> |
## As if </colgroup> |
| 5050 |
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
| 5051 |
!!!cp ('t269'); |
!!!cp ('t269'); |
| 5052 |
!!!parse-error (type => 'unmatched end tag:colgroup'); |
## TODO: Wrong error type? |
| 5053 |
|
!!!parse-error (type => 'unmatched end tag:colgroup', token => $token); |
| 5054 |
## Ignore the token |
## Ignore the token |
| 5055 |
!!!next-token; |
!!!next-token; |
| 5056 |
redo B; |
redo B; |
| 5061 |
## reprocess |
## reprocess |
| 5062 |
redo B; |
redo B; |
| 5063 |
} |
} |
| 5064 |
} elsif ($self->{insertion_mode} == IN_SELECT_IM) { |
} elsif ($self->{insertion_mode} & SELECT_IMS) { |
| 5065 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 5066 |
!!!cp ('t271'); |
!!!cp ('t271'); |
| 5067 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
| 5077 |
!!!cp ('t273'); |
!!!cp ('t273'); |
| 5078 |
} |
} |
| 5079 |
|
|
| 5080 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5081 |
!!!next-token; |
!!!next-token; |
| 5082 |
redo B; |
redo B; |
| 5083 |
} elsif ($token->{tag_name} eq 'optgroup') { |
} elsif ($token->{tag_name} eq 'optgroup') { |
| 5097 |
!!!cp ('t277'); |
!!!cp ('t277'); |
| 5098 |
} |
} |
| 5099 |
|
|
| 5100 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5101 |
!!!next-token; |
!!!next-token; |
| 5102 |
redo B; |
redo B; |
| 5103 |
} elsif ($token->{tag_name} eq 'select') { |
} elsif ($token->{tag_name} eq 'select' or |
| 5104 |
## TODO: The type below is not good - <select> is replaced by </select> |
$token->{tag_name} eq 'input' or |
| 5105 |
!!!parse-error (type => 'not closed:select'); |
($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
| 5106 |
## As if </select> instead |
{ |
| 5107 |
|
caption => 1, table => 1, |
| 5108 |
|
tbody => 1, tfoot => 1, thead => 1, |
| 5109 |
|
tr => 1, td => 1, th => 1, |
| 5110 |
|
}->{$token->{tag_name}})) { |
| 5111 |
|
## TODO: The type below is not good - <select> is replaced by </select> |
| 5112 |
|
!!!parse-error (type => 'not closed:select', token => $token); |
| 5113 |
|
## NOTE: As if the token were </select> (<select> case) or |
| 5114 |
|
## as if there were </select> (otherwise). |
| 5115 |
## have an element in table scope |
## have an element in table scope |
| 5116 |
my $i; |
my $i; |
| 5117 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5118 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5119 |
if ($node->[1] eq $token->{tag_name}) { |
if ($node->[1] eq 'select') { |
| 5120 |
!!!cp ('t278'); |
!!!cp ('t278'); |
| 5121 |
$i = $_; |
$i = $_; |
| 5122 |
last INSCOPE; |
last INSCOPE; |
| 5129 |
} # INSCOPE |
} # INSCOPE |
| 5130 |
unless (defined $i) { |
unless (defined $i) { |
| 5131 |
!!!cp ('t280'); |
!!!cp ('t280'); |
| 5132 |
!!!parse-error (type => 'unmatched end tag:select'); |
!!!parse-error (type => 'unmatched end tag:select', token => $token); |
| 5133 |
## Ignore the token |
## Ignore the token |
| 5134 |
!!!next-token; |
!!!next-token; |
| 5135 |
redo B; |
redo B; |
| 5140 |
|
|
| 5141 |
$self->_reset_insertion_mode; |
$self->_reset_insertion_mode; |
| 5142 |
|
|
| 5143 |
!!!next-token; |
if ($token->{tag_name} eq 'select') { |
| 5144 |
redo B; |
!!!cp ('t281.2'); |
| 5145 |
|
!!!next-token; |
| 5146 |
|
redo B; |
| 5147 |
|
} else { |
| 5148 |
|
!!!cp ('t281.1'); |
| 5149 |
|
## Reprocess the token. |
| 5150 |
|
redo B; |
| 5151 |
|
} |
| 5152 |
} else { |
} else { |
| 5153 |
!!!cp ('t282'); |
!!!cp ('t282'); |
| 5154 |
!!!parse-error (type => 'in select:'.$token->{tag_name}); |
!!!parse-error (type => 'in select:'.$token->{tag_name}, token => $token); |
| 5155 |
## Ignore the token |
## Ignore the token |
| 5156 |
!!!next-token; |
!!!next-token; |
| 5157 |
redo B; |
redo B; |
| 5168 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5169 |
} else { |
} else { |
| 5170 |
!!!cp ('t285'); |
!!!cp ('t285'); |
| 5171 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 5172 |
## Ignore the token |
## Ignore the token |
| 5173 |
} |
} |
| 5174 |
!!!next-token; |
!!!next-token; |
| 5179 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5180 |
} else { |
} else { |
| 5181 |
!!!cp ('t287'); |
!!!cp ('t287'); |
| 5182 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 5183 |
## Ignore the token |
## Ignore the token |
| 5184 |
} |
} |
| 5185 |
!!!next-token; |
!!!next-token; |
| 5202 |
} # INSCOPE |
} # INSCOPE |
| 5203 |
unless (defined $i) { |
unless (defined $i) { |
| 5204 |
!!!cp ('t290'); |
!!!cp ('t290'); |
| 5205 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 5206 |
## Ignore the token |
## Ignore the token |
| 5207 |
!!!next-token; |
!!!next-token; |
| 5208 |
redo B; |
redo B; |
| 5215 |
|
|
| 5216 |
!!!next-token; |
!!!next-token; |
| 5217 |
redo B; |
redo B; |
| 5218 |
} elsif ({ |
} elsif ($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
| 5219 |
caption => 1, table => 1, tbody => 1, |
{ |
| 5220 |
tfoot => 1, thead => 1, tr => 1, td => 1, th => 1, |
caption => 1, table => 1, tbody => 1, |
| 5221 |
}->{$token->{tag_name}}) { |
tfoot => 1, thead => 1, tr => 1, td => 1, th => 1, |
| 5222 |
|
}->{$token->{tag_name}}) { |
| 5223 |
## TODO: The following is wrong? |
## TODO: The following is wrong? |
| 5224 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 5225 |
|
|
| 5226 |
## have an element in table scope |
## have an element in table scope |
| 5227 |
my $i; |
my $i; |
| 5265 |
unless (defined $i) { |
unless (defined $i) { |
| 5266 |
!!!cp ('t297'); |
!!!cp ('t297'); |
| 5267 |
## TODO: The following error type is correct? |
## TODO: The following error type is correct? |
| 5268 |
!!!parse-error (type => 'unmatched end tag:select'); |
!!!parse-error (type => 'unmatched end tag:select', token => $token); |
| 5269 |
## Ignore the </select> token |
## Ignore the </select> token |
| 5270 |
!!!next-token; ## TODO: ok? |
!!!next-token; ## TODO: ok? |
| 5271 |
redo B; |
redo B; |
| 5280 |
redo B; |
redo B; |
| 5281 |
} else { |
} else { |
| 5282 |
!!!cp ('t299'); |
!!!cp ('t299'); |
| 5283 |
!!!parse-error (type => 'in select:/'.$token->{tag_name}); |
!!!parse-error (type => 'in select:/'.$token->{tag_name}, token => $token); |
| 5284 |
## Ignore the token |
## Ignore the token |
| 5285 |
!!!next-token; |
!!!next-token; |
| 5286 |
redo B; |
redo B; |
| 5287 |
} |
} |
| 5288 |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 5289 |
|
unless ($self->{open_elements}->[-1]->[1] eq 'html' and |
| 5290 |
|
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 5291 |
|
!!!cp ('t299.1'); |
| 5292 |
|
!!!parse-error (type => 'in body:#eof', token => $token); |
| 5293 |
|
} else { |
| 5294 |
|
!!!cp ('t299.2'); |
| 5295 |
|
} |
| 5296 |
|
|
| 5297 |
|
## Stop parsing. |
| 5298 |
|
last B; |
| 5299 |
} else { |
} else { |
| 5300 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 5301 |
} |
} |
| 5317 |
|
|
| 5318 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 5319 |
!!!cp ('t301'); |
!!!cp ('t301'); |
| 5320 |
!!!parse-error (type => 'after html:#character'); |
!!!parse-error (type => 'after html:#character', token => $token); |
| 5321 |
|
|
| 5322 |
## Reprocess in the "after body" insertion mode. |
## Reprocess in the "after body" insertion mode. |
| 5323 |
} else { |
} else { |
| 5325 |
} |
} |
| 5326 |
|
|
| 5327 |
## "after body" insertion mode |
## "after body" insertion mode |
| 5328 |
!!!parse-error (type => 'after body:#character'); |
!!!parse-error (type => 'after body:#character', token => $token); |
| 5329 |
|
|
| 5330 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 5331 |
## reprocess |
## reprocess |
| 5333 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 5334 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 5335 |
!!!cp ('t303'); |
!!!cp ('t303'); |
| 5336 |
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
!!!parse-error (type => 'after html:'.$token->{tag_name}, token => $token); |
| 5337 |
|
|
| 5338 |
## Reprocess in the "after body" insertion mode. |
## Reprocess in the "after body" insertion mode. |
| 5339 |
} else { |
} else { |
| 5341 |
} |
} |
| 5342 |
|
|
| 5343 |
## "after body" insertion mode |
## "after body" insertion mode |
| 5344 |
!!!parse-error (type => 'after body:'.$token->{tag_name}); |
!!!parse-error (type => 'after body:'.$token->{tag_name}, token => $token); |
| 5345 |
|
|
| 5346 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 5347 |
## reprocess |
## reprocess |
| 5349 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 5350 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 5351 |
!!!cp ('t305'); |
!!!cp ('t305'); |
| 5352 |
!!!parse-error (type => 'after html:/'.$token->{tag_name}); |
!!!parse-error (type => 'after html:/'.$token->{tag_name}, token => $token); |
| 5353 |
|
|
| 5354 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 5355 |
## Reprocess in the "after body" insertion mode. |
## Reprocess in the "after body" insertion mode. |
| 5361 |
if ($token->{tag_name} eq 'html') { |
if ($token->{tag_name} eq 'html') { |
| 5362 |
if (defined $self->{inner_html_node}) { |
if (defined $self->{inner_html_node}) { |
| 5363 |
!!!cp ('t307'); |
!!!cp ('t307'); |
| 5364 |
!!!parse-error (type => 'unmatched end tag:html'); |
!!!parse-error (type => 'unmatched end tag:html', token => $token); |
| 5365 |
## Ignore the token |
## Ignore the token |
| 5366 |
!!!next-token; |
!!!next-token; |
| 5367 |
redo B; |
redo B; |
| 5373 |
} |
} |
| 5374 |
} else { |
} else { |
| 5375 |
!!!cp ('t309'); |
!!!cp ('t309'); |
| 5376 |
!!!parse-error (type => 'after body:/'.$token->{tag_name}); |
!!!parse-error (type => 'after body:/'.$token->{tag_name}, token => $token); |
| 5377 |
|
|
| 5378 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 5379 |
## reprocess |
## reprocess |
| 5380 |
redo B; |
redo B; |
| 5381 |
} |
} |
| 5382 |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 5383 |
|
!!!cp ('t309.2'); |
| 5384 |
|
## Stop parsing |
| 5385 |
|
last B; |
| 5386 |
} else { |
} else { |
| 5387 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 5388 |
} |
} |
| 5401 |
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
| 5402 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 5403 |
!!!cp ('t311'); |
!!!cp ('t311'); |
| 5404 |
!!!parse-error (type => 'in frameset:#character'); |
!!!parse-error (type => 'in frameset:#character', token => $token); |
| 5405 |
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 5406 |
!!!cp ('t312'); |
!!!cp ('t312'); |
| 5407 |
!!!parse-error (type => 'after frameset:#character'); |
!!!parse-error (type => 'after frameset:#character', token => $token); |
| 5408 |
} else { # "after html frameset" |
} else { # "after html frameset" |
| 5409 |
!!!cp ('t313'); |
!!!cp ('t313'); |
| 5410 |
!!!parse-error (type => 'after html:#character'); |
!!!parse-error (type => 'after html:#character', token => $token); |
| 5411 |
|
|
| 5412 |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 5413 |
## Reprocess in the "after frameset" insertion mode. |
## Reprocess in the "after frameset" insertion mode. |
| 5414 |
!!!parse-error (type => 'after frameset:#character'); |
!!!parse-error (type => 'after frameset:#character', token => $token); |
| 5415 |
} |
} |
| 5416 |
|
|
| 5417 |
## Ignore the token. |
## Ignore the token. |
| 5429 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 5430 |
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 5431 |
!!!cp ('t316'); |
!!!cp ('t316'); |
| 5432 |
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
!!!parse-error (type => 'after html:'.$token->{tag_name}, token => $token); |
| 5433 |
|
|
| 5434 |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 5435 |
## Process in the "after frameset" insertion mode. |
## Process in the "after frameset" insertion mode. |
| 5440 |
if ($token->{tag_name} eq 'frameset' and |
if ($token->{tag_name} eq 'frameset' and |
| 5441 |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 5442 |
!!!cp ('t318'); |
!!!cp ('t318'); |
| 5443 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5444 |
!!!next-token; |
!!!next-token; |
| 5445 |
redo B; |
redo B; |
| 5446 |
} elsif ($token->{tag_name} eq 'frame' and |
} elsif ($token->{tag_name} eq 'frame' and |
| 5447 |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 5448 |
!!!cp ('t319'); |
!!!cp ('t319'); |
| 5449 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5450 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5451 |
!!!next-token; |
!!!next-token; |
| 5452 |
redo B; |
redo B; |
| 5453 |
} elsif ($token->{tag_name} eq 'noframes') { |
} elsif ($token->{tag_name} eq 'noframes') { |
| 5454 |
!!!cp ('t320'); |
!!!cp ('t320'); |
| 5455 |
## NOTE: As if in body. |
## NOTE: As if in body. |
| 5456 |
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert_to_current); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 5457 |
redo B; |
redo B; |
| 5458 |
} else { |
} else { |
| 5459 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 5460 |
!!!cp ('t321'); |
!!!cp ('t321'); |
| 5461 |
!!!parse-error (type => 'in frameset:'.$token->{tag_name}); |
!!!parse-error (type => 'in frameset:'.$token->{tag_name}, token => $token); |
| 5462 |
} else { |
} else { |
| 5463 |
!!!cp ('t322'); |
!!!cp ('t322'); |
| 5464 |
!!!parse-error (type => 'after frameset:'.$token->{tag_name}); |
!!!parse-error (type => 'after frameset:'.$token->{tag_name}, token => $token); |
| 5465 |
} |
} |
| 5466 |
## Ignore the token |
## Ignore the token |
| 5467 |
!!!next-token; |
!!!next-token; |
| 5470 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 5471 |
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 5472 |
!!!cp ('t323'); |
!!!cp ('t323'); |
| 5473 |
!!!parse-error (type => 'after html:/'.$token->{tag_name}); |
!!!parse-error (type => 'after html:/'.$token->{tag_name}, token => $token); |
| 5474 |
|
|
| 5475 |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 5476 |
## Process in the "after frameset" insertion mode. |
## Process in the "after frameset" insertion mode. |
| 5483 |
if ($self->{open_elements}->[-1]->[1] eq 'html' and |
if ($self->{open_elements}->[-1]->[1] eq 'html' and |
| 5484 |
@{$self->{open_elements}} == 1) { |
@{$self->{open_elements}} == 1) { |
| 5485 |
!!!cp ('t325'); |
!!!cp ('t325'); |
| 5486 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 5487 |
## Ignore the token |
## Ignore the token |
| 5488 |
!!!next-token; |
!!!next-token; |
| 5489 |
} else { |
} else { |
| 5509 |
} else { |
} else { |
| 5510 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 5511 |
!!!cp ('t330'); |
!!!cp ('t330'); |
| 5512 |
!!!parse-error (type => 'in frameset:/'.$token->{tag_name}); |
!!!parse-error (type => 'in frameset:/'.$token->{tag_name}, token => $token); |
| 5513 |
} else { |
} else { |
| 5514 |
!!!cp ('t331'); |
!!!cp ('t331'); |
| 5515 |
!!!parse-error (type => 'after frameset:/'.$token->{tag_name}); |
!!!parse-error (type => 'after frameset:/'.$token->{tag_name}, token => $token); |
| 5516 |
} |
} |
| 5517 |
## Ignore the token |
## Ignore the token |
| 5518 |
!!!next-token; |
!!!next-token; |
| 5519 |
redo B; |
redo B; |
| 5520 |
} |
} |
| 5521 |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 5522 |
|
unless ($self->{open_elements}->[-1]->[1] eq 'html' and |
| 5523 |
|
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 5524 |
|
!!!cp ('t331.1'); |
| 5525 |
|
!!!parse-error (type => 'in body:#eof', token => $token); |
| 5526 |
|
} else { |
| 5527 |
|
!!!cp ('t331.2'); |
| 5528 |
|
} |
| 5529 |
|
|
| 5530 |
|
## Stop parsing |
| 5531 |
|
last B; |
| 5532 |
} else { |
} else { |
| 5533 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 5534 |
} |
} |
| 5543 |
if ($token->{tag_name} eq 'script') { |
if ($token->{tag_name} eq 'script') { |
| 5544 |
!!!cp ('t332'); |
!!!cp ('t332'); |
| 5545 |
## NOTE: This is an "as if in head" code clone |
## NOTE: This is an "as if in head" code clone |
| 5546 |
$script_start_tag->($insert); |
$script_start_tag->(); |
| 5547 |
redo B; |
redo B; |
| 5548 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($token->{tag_name} eq 'style') { |
| 5549 |
!!!cp ('t333'); |
!!!cp ('t333'); |
| 5550 |
## NOTE: This is an "as if in head" code clone |
## NOTE: This is an "as if in head" code clone |
| 5551 |
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 5552 |
redo B; |
redo B; |
| 5553 |
} elsif ({ |
} elsif ({ |
| 5554 |
base => 1, link => 1, |
base => 1, link => 1, |
| 5555 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5556 |
!!!cp ('t334'); |
!!!cp ('t334'); |
| 5557 |
## NOTE: This is an "as if in head" code clone, only "-t" differs |
## NOTE: This is an "as if in head" code clone, only "-t" differs |
| 5558 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 5559 |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 5560 |
!!!next-token; |
!!!next-token; |
| 5561 |
redo B; |
redo B; |
| 5562 |
} elsif ($token->{tag_name} eq 'meta') { |
} elsif ($token->{tag_name} eq 'meta') { |
| 5563 |
## NOTE: This is an "as if in head" code clone, only "-t" differs |
## NOTE: This is an "as if in head" code clone, only "-t" differs |
| 5564 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 5565 |
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. |
| 5566 |
|
|
| 5567 |
unless ($self->{confident}) { |
unless ($self->{confident}) { |
| 5568 |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
| 5569 |
!!!cp ('t335'); |
!!!cp ('t335'); |
| 5570 |
$self->{change_encoding} |
$self->{change_encoding} |
| 5571 |
->($self, $token->{attributes}->{charset}->{value}); |
->($self, $token->{attributes}->{charset}->{value}, $token); |
| 5572 |
|
|
| 5573 |
$meta_el->[0]->get_attribute_node_ns (undef, 'charset') |
$meta_el->[0]->get_attribute_node_ns (undef, 'charset') |
| 5574 |
->set_user_data (manakai_has_reference => |
->set_user_data (manakai_has_reference => |
| 5583 |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
| 5584 |
!!!cp ('t336'); |
!!!cp ('t336'); |
| 5585 |
$self->{change_encoding} |
$self->{change_encoding} |
| 5586 |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3); |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3, $token); |
| 5587 |
$meta_el->[0]->get_attribute_node_ns (undef, 'content') |
$meta_el->[0]->get_attribute_node_ns (undef, 'content') |
| 5588 |
->set_user_data (manakai_has_reference => |
->set_user_data (manakai_has_reference => |
| 5589 |
$token->{attributes}->{content} |
$token->{attributes}->{content} |
| 5611 |
redo B; |
redo B; |
| 5612 |
} elsif ($token->{tag_name} eq 'title') { |
} elsif ($token->{tag_name} eq 'title') { |
| 5613 |
!!!cp ('t341'); |
!!!cp ('t341'); |
|
!!!parse-error (type => 'in body:title'); |
|
| 5614 |
## NOTE: This is an "as if in head" code clone |
## NOTE: This is an "as if in head" code clone |
| 5615 |
$parse_rcdata->(RCDATA_CONTENT_MODEL, sub { |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
|
if (defined $self->{head_element}) { |
|
|
!!!cp ('t339'); |
|
|
$self->{head_element}->append_child ($_[0]); |
|
|
} else { |
|
|
!!!cp ('t340'); |
|
|
$insert->($_[0]); |
|
|
} |
|
|
}); |
|
| 5616 |
redo B; |
redo B; |
| 5617 |
} elsif ($token->{tag_name} eq 'body') { |
} elsif ($token->{tag_name} eq 'body') { |
| 5618 |
!!!parse-error (type => 'in body:body'); |
!!!parse-error (type => 'in body:body', token => $token); |
| 5619 |
|
|
| 5620 |
if (@{$self->{open_elements}} == 1 or |
if (@{$self->{open_elements}} == 1 or |
| 5621 |
$self->{open_elements}->[1]->[1] ne 'body') { |
$self->{open_elements}->[1]->[1] ne 'body') { |
| 5636 |
redo B; |
redo B; |
| 5637 |
} elsif ({ |
} elsif ({ |
| 5638 |
address => 1, blockquote => 1, center => 1, dir => 1, |
address => 1, blockquote => 1, center => 1, dir => 1, |
| 5639 |
div => 1, dl => 1, fieldset => 1, listing => 1, |
div => 1, dl => 1, fieldset => 1, |
| 5640 |
|
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
| 5641 |
menu => 1, ol => 1, p => 1, ul => 1, |
menu => 1, ol => 1, p => 1, ul => 1, |
| 5642 |
pre => 1, |
pre => 1, listing => 1, |
| 5643 |
|
form => 1, |
| 5644 |
|
table => 1, |
| 5645 |
|
hr => 1, |
| 5646 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5647 |
|
if ($token->{tag_name} eq 'form' and defined $self->{form_element}) { |
| 5648 |
|
!!!cp ('t350'); |
| 5649 |
|
!!!parse-error (type => 'in form:form', token => $token); |
| 5650 |
|
## Ignore the token |
| 5651 |
|
!!!next-token; |
| 5652 |
|
redo B; |
| 5653 |
|
} |
| 5654 |
|
|
| 5655 |
## has a p element in scope |
## has a p element in scope |
| 5656 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 5657 |
if ($_->[1] eq 'p') { |
if ($_->[1] eq 'p') { |
| 5658 |
!!!cp ('t344'); |
!!!cp ('t344'); |
| 5659 |
!!!back-token; |
!!!back-token; |
| 5660 |
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
| 5661 |
|
line => $token->{line}, column => $token->{column}}; |
| 5662 |
redo B; |
redo B; |
| 5663 |
} elsif ({ |
} elsif ({ |
| 5664 |
table => 1, caption => 1, td => 1, th => 1, |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 5665 |
button => 1, marquee => 1, object => 1, html => 1, |
button => 1, marquee => 1, object => 1, html => 1, |
| 5666 |
}->{$_->[1]}) { |
}->{$_->[1]}) { |
| 5667 |
!!!cp ('t345'); |
!!!cp ('t345'); |
| 5669 |
} |
} |
| 5670 |
} # INSCOPE |
} # INSCOPE |
| 5671 |
|
|
| 5672 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 5673 |
if ($token->{tag_name} eq 'pre') { |
if ($token->{tag_name} eq 'pre' or $token->{tag_name} eq 'listing') { |
| 5674 |
!!!next-token; |
!!!next-token; |
| 5675 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 5676 |
$token->{data} =~ s/^\x0A//; |
$token->{data} =~ s/^\x0A//; |
| 5683 |
} else { |
} else { |
| 5684 |
!!!cp ('t348'); |
!!!cp ('t348'); |
| 5685 |
} |
} |
| 5686 |
} else { |
} elsif ($token->{tag_name} eq 'form') { |
| 5687 |
!!!cp ('t347'); |
!!!cp ('t347.1'); |
| 5688 |
|
$self->{form_element} = $self->{open_elements}->[-1]->[0]; |
| 5689 |
|
|
| 5690 |
!!!next-token; |
!!!next-token; |
| 5691 |
} |
} elsif ($token->{tag_name} eq 'table') { |
| 5692 |
redo B; |
!!!cp ('t382'); |
| 5693 |
} elsif ($token->{tag_name} eq 'form') { |
push @{$open_tables}, [$self->{open_elements}->[-1]->[0]]; |
| 5694 |
if (defined $self->{form_element}) { |
|
| 5695 |
!!!cp ('t350'); |
$self->{insertion_mode} = IN_TABLE_IM; |
| 5696 |
!!!parse-error (type => 'in form:form'); |
|
| 5697 |
## Ignore the token |
!!!next-token; |
| 5698 |
|
} elsif ($token->{tag_name} eq 'hr') { |
| 5699 |
|
!!!cp ('t386'); |
| 5700 |
|
pop @{$self->{open_elements}}; |
| 5701 |
|
|
| 5702 |
!!!next-token; |
!!!next-token; |
|
redo B; |
|
| 5703 |
} else { |
} else { |
| 5704 |
## has a p element in scope |
!!!cp ('t347'); |
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
|
|
if ($_->[1] eq 'p') { |
|
|
!!!cp ('t351'); |
|
|
!!!back-token; |
|
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
|
|
redo B; |
|
|
} elsif ({ |
|
|
table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
|
!!!cp ('t352'); |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
$self->{form_element} = $self->{open_elements}->[-1]->[0]; |
|
| 5705 |
!!!next-token; |
!!!next-token; |
|
redo B; |
|
| 5706 |
} |
} |
| 5707 |
} elsif ($token->{tag_name} eq 'li') { |
redo B; |
| 5708 |
|
} elsif ({li => 1, dt => 1, dd => 1}->{$token->{tag_name}}) { |
| 5709 |
## has a p element in scope |
## has a p element in scope |
| 5710 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 5711 |
if ($_->[1] eq 'p') { |
if ($_->[1] eq 'p') { |
| 5712 |
!!!cp ('t353'); |
!!!cp ('t353'); |
| 5713 |
!!!back-token; |
!!!back-token; |
| 5714 |
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
| 5715 |
|
line => $token->{line}, column => $token->{column}}; |
| 5716 |
redo B; |
redo B; |
| 5717 |
} elsif ({ |
} elsif ({ |
| 5718 |
table => 1, caption => 1, td => 1, th => 1, |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 5719 |
button => 1, marquee => 1, object => 1, html => 1, |
button => 1, marquee => 1, object => 1, html => 1, |
| 5720 |
}->{$_->[1]}) { |
}->{$_->[1]}) { |
| 5721 |
!!!cp ('t354'); |
!!!cp ('t354'); |
| 5726 |
## Step 1 |
## Step 1 |
| 5727 |
my $i = -1; |
my $i = -1; |
| 5728 |
my $node = $self->{open_elements}->[$i]; |
my $node = $self->{open_elements}->[$i]; |
| 5729 |
|
my $li_or_dtdd = {li => {li => 1}, |
| 5730 |
|
dt => {dt => 1, dd => 1}, |
| 5731 |
|
dd => {dt => 1, dd => 1}}->{$token->{tag_name}}; |
| 5732 |
LI: { |
LI: { |
| 5733 |
## Step 2 |
## Step 2 |
| 5734 |
if ($node->[1] eq 'li') { |
if ($li_or_dtdd->{$node->[1]}) { |
| 5735 |
if ($i != -1) { |
if ($i != -1) { |
| 5736 |
!!!cp ('t355'); |
!!!cp ('t355'); |
| 5737 |
!!!parse-error (type => 'end tag missing:'. |
!!!parse-error (type => 'end tag missing:'. |
| 5738 |
$self->{open_elements}->[-1]->[1]); |
$self->{open_elements}->[-1]->[1], token => $token); |
| 5739 |
} else { |
} else { |
| 5740 |
!!!cp ('t356'); |
!!!cp ('t356'); |
| 5741 |
} |
} |
| 5762 |
redo LI; |
redo LI; |
| 5763 |
} # LI |
} # LI |
| 5764 |
|
|
| 5765 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'dd' or $token->{tag_name} eq 'dt') { |
|
|
## has a p element in scope |
|
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
|
|
if ($_->[1] eq 'p') { |
|
|
!!!cp ('t360'); |
|
|
!!!back-token; |
|
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
|
|
redo B; |
|
|
} elsif ({ |
|
|
table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
|
!!!cp ('t361'); |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
## Step 1 |
|
|
my $i = -1; |
|
|
my $node = $self->{open_elements}->[$i]; |
|
|
LI: { |
|
|
## Step 2 |
|
|
if ($node->[1] eq 'dt' or $node->[1] eq 'dd') { |
|
|
if ($i != -1) { |
|
|
!!!cp ('t362'); |
|
|
!!!parse-error (type => 'end tag missing:'. |
|
|
$self->{open_elements}->[-1]->[1]); |
|
|
} else { |
|
|
!!!cp ('t363'); |
|
|
} |
|
|
splice @{$self->{open_elements}}, $i; |
|
|
last LI; |
|
|
} else { |
|
|
!!!cp ('t364'); |
|
|
} |
|
|
|
|
|
## Step 3 |
|
|
if (not $formatting_category->{$node->[1]} and |
|
|
#not $phrasing_category->{$node->[1]} and |
|
|
($special_category->{$node->[1]} or |
|
|
$scoping_category->{$node->[1]}) and |
|
|
$node->[1] ne 'address' and $node->[1] ne 'div') { |
|
|
!!!cp ('t365'); |
|
|
last LI; |
|
|
} |
|
|
|
|
|
!!!cp ('t366'); |
|
|
## Step 4 |
|
|
$i--; |
|
|
$node = $self->{open_elements}->[$i]; |
|
|
redo LI; |
|
|
} # LI |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
| 5766 |
!!!next-token; |
!!!next-token; |
| 5767 |
redo B; |
redo B; |
| 5768 |
} elsif ($token->{tag_name} eq 'plaintext') { |
} elsif ($token->{tag_name} eq 'plaintext') { |
| 5771 |
if ($_->[1] eq 'p') { |
if ($_->[1] eq 'p') { |
| 5772 |
!!!cp ('t367'); |
!!!cp ('t367'); |
| 5773 |
!!!back-token; |
!!!back-token; |
| 5774 |
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
| 5775 |
|
line => $token->{line}, column => $token->{column}}; |
| 5776 |
redo B; |
redo B; |
| 5777 |
} elsif ({ |
} elsif ({ |
| 5778 |
table => 1, caption => 1, td => 1, th => 1, |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 5779 |
button => 1, marquee => 1, object => 1, html => 1, |
button => 1, marquee => 1, object => 1, html => 1, |
| 5780 |
}->{$_->[1]}) { |
}->{$_->[1]}) { |
| 5781 |
!!!cp ('t368'); |
!!!cp ('t368'); |
| 5783 |
} |
} |
| 5784 |
} # INSCOPE |
} # INSCOPE |
| 5785 |
|
|
| 5786 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 5787 |
|
|
| 5788 |
$self->{content_model} = PLAINTEXT_CONTENT_MODEL; |
$self->{content_model} = PLAINTEXT_CONTENT_MODEL; |
| 5789 |
|
|
| 5790 |
!!!next-token; |
!!!next-token; |
| 5791 |
redo B; |
redo B; |
|
} elsif ({ |
|
|
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
## has a p element in scope |
|
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
my $node = $self->{open_elements}->[$_]; |
|
|
if ($node->[1] eq 'p') { |
|
|
!!!cp ('t369'); |
|
|
!!!back-token; |
|
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
|
|
redo B; |
|
|
} elsif ({ |
|
|
table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
|
!!!cp ('t370'); |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
## NOTE: See <http://html5.org/tools/web-apps-tracker?from=925&to=926> |
|
|
## has an element in scope |
|
|
#my $i; |
|
|
#INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
# my $node = $self->{open_elements}->[$_]; |
|
|
# if ({ |
|
|
# h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
|
|
# }->{$node->[1]}) { |
|
|
# $i = $_; |
|
|
# last INSCOPE; |
|
|
# } elsif ({ |
|
|
# table => 1, caption => 1, td => 1, th => 1, |
|
|
# button => 1, marquee => 1, object => 1, html => 1, |
|
|
# }->{$node->[1]}) { |
|
|
# last INSCOPE; |
|
|
# } |
|
|
#} # INSCOPE |
|
|
# |
|
|
#if (defined $i) { |
|
|
# !!! parse-error (type => 'in hn:hn'); |
|
|
# splice @{$self->{open_elements}}, $i; |
|
|
#} |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
|
|
|
!!!next-token; |
|
|
redo B; |
|
| 5792 |
} elsif ($token->{tag_name} eq 'a') { |
} elsif ($token->{tag_name} eq 'a') { |
| 5793 |
AFE: for my $i (reverse 0..$#$active_formatting_elements) { |
AFE: for my $i (reverse 0..$#$active_formatting_elements) { |
| 5794 |
my $node = $active_formatting_elements->[$i]; |
my $node = $active_formatting_elements->[$i]; |
| 5795 |
if ($node->[1] eq 'a') { |
if ($node->[1] eq 'a') { |
| 5796 |
!!!cp ('t371'); |
!!!cp ('t371'); |
| 5797 |
!!!parse-error (type => 'in a:a'); |
!!!parse-error (type => 'in a:a', token => $token); |
| 5798 |
|
|
| 5799 |
!!!back-token; |
!!!back-token; |
| 5800 |
$token = {type => END_TAG_TOKEN, tag_name => 'a'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'a', |
| 5801 |
$formatting_end_tag->($token->{tag_name}); |
line => $token->{line}, column => $token->{column}}; |
| 5802 |
|
$formatting_end_tag->($token); |
| 5803 |
|
|
| 5804 |
AFE2: for (reverse 0..$#$active_formatting_elements) { |
AFE2: for (reverse 0..$#$active_formatting_elements) { |
| 5805 |
if ($active_formatting_elements->[$_]->[0] eq $node->[0]) { |
if ($active_formatting_elements->[$_]->[0] eq $node->[0]) { |
| 5824 |
|
|
| 5825 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 5826 |
|
|
| 5827 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 5828 |
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
| 5829 |
|
|
| 5830 |
!!!next-token; |
!!!next-token; |
| 5831 |
redo B; |
redo B; |
|
} elsif ({ |
|
|
b => 1, big => 1, em => 1, font => 1, i => 1, |
|
|
s => 1, small => 1, strile => 1, |
|
|
strong => 1, tt => 1, u => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
!!!cp ('t375'); |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
|
|
|
|
|
!!!next-token; |
|
|
redo B; |
|
| 5832 |
} elsif ($token->{tag_name} eq 'nobr') { |
} elsif ($token->{tag_name} eq 'nobr') { |
| 5833 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 5834 |
|
|
| 5837 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5838 |
if ($node->[1] eq 'nobr') { |
if ($node->[1] eq 'nobr') { |
| 5839 |
!!!cp ('t376'); |
!!!cp ('t376'); |
| 5840 |
!!!parse-error (type => 'in nobr:nobr'); |
!!!parse-error (type => 'in nobr:nobr', token => $token); |
| 5841 |
!!!back-token; |
!!!back-token; |
| 5842 |
$token = {type => END_TAG_TOKEN, tag_name => 'nobr'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'nobr', |
| 5843 |
|
line => $token->{line}, column => $token->{column}}; |
| 5844 |
redo B; |
redo B; |
| 5845 |
} elsif ({ |
} elsif ({ |
| 5846 |
table => 1, caption => 1, td => 1, th => 1, |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 5847 |
button => 1, marquee => 1, object => 1, html => 1, |
button => 1, marquee => 1, object => 1, html => 1, |
| 5848 |
}->{$node->[1]}) { |
}->{$node->[1]}) { |
| 5849 |
!!!cp ('t377'); |
!!!cp ('t377'); |
| 5851 |
} |
} |
| 5852 |
} # INSCOPE |
} # INSCOPE |
| 5853 |
|
|
| 5854 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 5855 |
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
| 5856 |
|
|
| 5857 |
!!!next-token; |
!!!next-token; |
| 5862 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5863 |
if ($node->[1] eq 'button') { |
if ($node->[1] eq 'button') { |
| 5864 |
!!!cp ('t378'); |
!!!cp ('t378'); |
| 5865 |
!!!parse-error (type => 'in button:button'); |
!!!parse-error (type => 'in button:button', token => $token); |
| 5866 |
!!!back-token; |
!!!back-token; |
| 5867 |
$token = {type => END_TAG_TOKEN, tag_name => 'button'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'button', |
| 5868 |
|
line => $token->{line}, column => $token->{column}}; |
| 5869 |
redo B; |
redo B; |
| 5870 |
} elsif ({ |
} elsif ({ |
| 5871 |
table => 1, caption => 1, td => 1, th => 1, |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 5872 |
button => 1, marquee => 1, object => 1, html => 1, |
button => 1, marquee => 1, object => 1, html => 1, |
| 5873 |
}->{$node->[1]}) { |
}->{$node->[1]}) { |
| 5874 |
!!!cp ('t379'); |
!!!cp ('t379'); |
| 5878 |
|
|
| 5879 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 5880 |
|
|
| 5881 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 5882 |
push @$active_formatting_elements, ['#marker', '']; |
|
| 5883 |
|
## TODO: associate with $self->{form_element} if defined |
| 5884 |
|
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'marquee' or |
|
|
$token->{tag_name} eq 'object') { |
|
|
!!!cp ('t380'); |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
| 5885 |
push @$active_formatting_elements, ['#marker', '']; |
push @$active_formatting_elements, ['#marker', '']; |
| 5886 |
|
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'xmp') { |
|
|
!!!cp ('t381'); |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert); |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'table') { |
|
|
## has a p element in scope |
|
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
|
|
if ($_->[1] eq 'p') { |
|
|
!!!cp ('t382'); |
|
|
!!!back-token; |
|
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
|
|
redo B; |
|
|
} elsif ({ |
|
|
table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
|
!!!cp ('t383'); |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
|
|
|
$self->{insertion_mode} = IN_TABLE_IM; |
|
|
|
|
| 5887 |
!!!next-token; |
!!!next-token; |
| 5888 |
redo B; |
redo B; |
| 5889 |
} elsif ({ |
} elsif ({ |
| 5890 |
area => 1, basefont => 1, bgsound => 1, br => 1, |
xmp => 1, |
| 5891 |
embed => 1, img => 1, param => 1, spacer => 1, wbr => 1, |
iframe => 1, |
| 5892 |
image => 1, |
noembed => 1, |
| 5893 |
|
noframes => 1, |
| 5894 |
|
noscript => 0, ## TODO: 1 if scripting is enabled |
| 5895 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5896 |
if ($token->{tag_name} eq 'image') { |
if ($token->{tag_name} eq 'xmp') { |
| 5897 |
!!!cp ('t384'); |
!!!cp ('t381'); |
| 5898 |
!!!parse-error (type => 'image'); |
$reconstruct_active_formatting_elements->($insert_to_current); |
|
$token->{tag_name} = 'img'; |
|
| 5899 |
} else { |
} else { |
| 5900 |
!!!cp ('t385'); |
!!!cp ('t399'); |
| 5901 |
} |
} |
| 5902 |
|
## NOTE: There is an "as if in body" code clone. |
| 5903 |
## NOTE: There is an "as if <br>" code clone. |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
pop @{$self->{open_elements}}; |
|
|
|
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'hr') { |
|
|
## has a p element in scope |
|
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
|
|
if ($_->[1] eq 'p') { |
|
|
!!!cp ('t386'); |
|
|
!!!back-token; |
|
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
|
|
redo B; |
|
|
} elsif ({ |
|
|
table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
|
!!!cp ('t387'); |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
pop @{$self->{open_elements}}; |
|
|
|
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'input') { |
|
|
!!!cp ('t388'); |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
## TODO: associate with $self->{form_element} if defined |
|
|
pop @{$self->{open_elements}}; |
|
|
|
|
|
!!!next-token; |
|
| 5904 |
redo B; |
redo B; |
| 5905 |
} elsif ($token->{tag_name} eq 'isindex') { |
} elsif ($token->{tag_name} eq 'isindex') { |
| 5906 |
!!!parse-error (type => 'isindex'); |
!!!parse-error (type => 'isindex', token => $token); |
| 5907 |
|
|
| 5908 |
if (defined $self->{form_element}) { |
if (defined $self->{form_element}) { |
| 5909 |
!!!cp ('t389'); |
!!!cp ('t389'); |
| 5920 |
delete $at->{prompt}; |
delete $at->{prompt}; |
| 5921 |
my @tokens = ( |
my @tokens = ( |
| 5922 |
{type => START_TAG_TOKEN, tag_name => 'form', |
{type => START_TAG_TOKEN, tag_name => 'form', |
| 5923 |
attributes => $form_attrs}, |
attributes => $form_attrs, |
| 5924 |
{type => START_TAG_TOKEN, tag_name => 'hr'}, |
line => $token->{line}, column => $token->{column}}, |
| 5925 |
{type => START_TAG_TOKEN, tag_name => 'p'}, |
{type => START_TAG_TOKEN, tag_name => 'hr', |
| 5926 |
{type => START_TAG_TOKEN, tag_name => 'label'}, |
line => $token->{line}, column => $token->{column}}, |
| 5927 |
|
{type => START_TAG_TOKEN, tag_name => 'p', |
| 5928 |
|
line => $token->{line}, column => $token->{column}}, |
| 5929 |
|
{type => START_TAG_TOKEN, tag_name => 'label', |
| 5930 |
|
line => $token->{line}, column => $token->{column}}, |
| 5931 |
); |
); |
| 5932 |
if ($prompt_attr) { |
if ($prompt_attr) { |
| 5933 |
!!!cp ('t390'); |
!!!cp ('t390'); |
| 5934 |
push @tokens, {type => CHARACTER_TOKEN, data => $prompt_attr->{value}}; |
push @tokens, {type => CHARACTER_TOKEN, data => $prompt_attr->{value}, |
| 5935 |
|
#line => $token->{line}, column => $token->{column}, |
| 5936 |
|
}; |
| 5937 |
} else { |
} else { |
| 5938 |
!!!cp ('t391'); |
!!!cp ('t391'); |
| 5939 |
push @tokens, {type => CHARACTER_TOKEN, |
push @tokens, {type => CHARACTER_TOKEN, |
| 5940 |
data => 'This is a searchable index. Insert your search keywords here: '}; # SHOULD |
data => 'This is a searchable index. Insert your search keywords here: ', |
| 5941 |
|
#line => $token->{line}, column => $token->{column}, |
| 5942 |
|
}; # SHOULD |
| 5943 |
## TODO: make this configurable |
## TODO: make this configurable |
| 5944 |
} |
} |
| 5945 |
push @tokens, |
push @tokens, |
| 5946 |
{type => START_TAG_TOKEN, tag_name => 'input', attributes => $at}, |
{type => START_TAG_TOKEN, tag_name => 'input', attributes => $at, |
| 5947 |
|
line => $token->{line}, column => $token->{column}}, |
| 5948 |
#{type => CHARACTER_TOKEN, data => ''}, # SHOULD |
#{type => CHARACTER_TOKEN, data => ''}, # SHOULD |
| 5949 |
{type => END_TAG_TOKEN, tag_name => 'label'}, |
{type => END_TAG_TOKEN, tag_name => 'label', |
| 5950 |
{type => END_TAG_TOKEN, tag_name => 'p'}, |
line => $token->{line}, column => $token->{column}}, |
| 5951 |
{type => START_TAG_TOKEN, tag_name => 'hr'}, |
{type => END_TAG_TOKEN, tag_name => 'p', |
| 5952 |
{type => END_TAG_TOKEN, tag_name => 'form'}; |
line => $token->{line}, column => $token->{column}}, |
| 5953 |
|
{type => START_TAG_TOKEN, tag_name => 'hr', |
| 5954 |
|
line => $token->{line}, column => $token->{column}}, |
| 5955 |
|
{type => END_TAG_TOKEN, tag_name => 'form', |
| 5956 |
|
line => $token->{line}, column => $token->{column}}; |
| 5957 |
$token = shift @tokens; |
$token = shift @tokens; |
| 5958 |
!!!back-token (@tokens); |
!!!back-token (@tokens); |
| 5959 |
redo B; |
redo B; |
| 5961 |
} elsif ($token->{tag_name} eq 'textarea') { |
} elsif ($token->{tag_name} eq 'textarea') { |
| 5962 |
my $tag_name = $token->{tag_name}; |
my $tag_name = $token->{tag_name}; |
| 5963 |
my $el; |
my $el; |
| 5964 |
!!!create-element ($el, $token->{tag_name}, $token->{attributes}); |
!!!create-element ($el, $token->{tag_name}, $token->{attributes}, $token); |
| 5965 |
|
|
| 5966 |
## TODO: $self->{form_element} if defined |
## TODO: $self->{form_element} if defined |
| 5967 |
$self->{content_model} = RCDATA_CONTENT_MODEL; |
$self->{content_model} = RCDATA_CONTENT_MODEL; |
| 6000 |
## Ignore the token |
## Ignore the token |
| 6001 |
} else { |
} else { |
| 6002 |
!!!cp ('t398'); |
!!!cp ('t398'); |
| 6003 |
!!!parse-error (type => 'in RCDATA:#'.$token->{type}); |
!!!parse-error (type => 'in RCDATA:#'.$token->{type}, token => $token); |
| 6004 |
} |
} |
| 6005 |
!!!next-token; |
!!!next-token; |
| 6006 |
redo B; |
redo B; |
| 6007 |
} elsif ({ |
} elsif ({ |
|
iframe => 1, |
|
|
noembed => 1, |
|
|
noframes => 1, |
|
|
noscript => 0, ## TODO: 1 if scripting is enabled |
|
|
}->{$token->{tag_name}}) { |
|
|
!!!cp ('t399'); |
|
|
## NOTE: There is an "as if in body" code clone. |
|
|
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert); |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'select') { |
|
|
!!!cp ('t400'); |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
|
|
|
$self->{insertion_mode} = IN_SELECT_IM; |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ({ |
|
| 6008 |
caption => 1, col => 1, colgroup => 1, frame => 1, |
caption => 1, col => 1, colgroup => 1, frame => 1, |
| 6009 |
frameset => 1, head => 1, option => 1, optgroup => 1, |
frameset => 1, head => 1, option => 1, optgroup => 1, |
| 6010 |
tbody => 1, td => 1, tfoot => 1, th => 1, |
tbody => 1, td => 1, tfoot => 1, th => 1, |
| 6011 |
thead => 1, tr => 1, |
thead => 1, tr => 1, |
| 6012 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6013 |
!!!cp ('t401'); |
!!!cp ('t401'); |
| 6014 |
!!!parse-error (type => 'in body:'.$token->{tag_name}); |
!!!parse-error (type => 'in body:'.$token->{tag_name}, token => $token); |
| 6015 |
## Ignore the token |
## Ignore the token |
| 6016 |
!!!next-token; |
!!!next-token; |
| 6017 |
redo B; |
redo B; |
| 6018 |
|
|
| 6019 |
## ISSUE: An issue on HTML5 new elements in the spec. |
## ISSUE: An issue on HTML5 new elements in the spec. |
| 6020 |
} else { |
} else { |
| 6021 |
!!!cp ('t402'); |
if ($token->{tag_name} eq 'image') { |
| 6022 |
|
!!!cp ('t384'); |
| 6023 |
|
!!!parse-error (type => 'image', token => $token); |
| 6024 |
|
$token->{tag_name} = 'img'; |
| 6025 |
|
} else { |
| 6026 |
|
!!!cp ('t385'); |
| 6027 |
|
} |
| 6028 |
|
|
| 6029 |
|
## NOTE: There is an "as if <br>" code clone. |
| 6030 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 6031 |
|
|
| 6032 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 6033 |
|
|
| 6034 |
|
if ({ |
| 6035 |
|
applet => 1, marquee => 1, object => 1, |
| 6036 |
|
}->{$token->{tag_name}}) { |
| 6037 |
|
!!!cp ('t380'); |
| 6038 |
|
push @$active_formatting_elements, ['#marker', '']; |
| 6039 |
|
} elsif ({ |
| 6040 |
|
b => 1, big => 1, em => 1, font => 1, i => 1, |
| 6041 |
|
s => 1, small => 1, strile => 1, |
| 6042 |
|
strong => 1, tt => 1, u => 1, |
| 6043 |
|
}->{$token->{tag_name}}) { |
| 6044 |
|
!!!cp ('t375'); |
| 6045 |
|
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
| 6046 |
|
} elsif ($token->{tag_name} eq 'input') { |
| 6047 |
|
!!!cp ('t388'); |
| 6048 |
|
## TODO: associate with $self->{form_element} if defined |
| 6049 |
|
pop @{$self->{open_elements}}; |
| 6050 |
|
} elsif ({ |
| 6051 |
|
area => 1, basefont => 1, bgsound => 1, br => 1, |
| 6052 |
|
embed => 1, img => 1, param => 1, spacer => 1, wbr => 1, |
| 6053 |
|
#image => 1, |
| 6054 |
|
}->{$token->{tag_name}}) { |
| 6055 |
|
!!!cp ('t388.1'); |
| 6056 |
|
pop @{$self->{open_elements}}; |
| 6057 |
|
} elsif ($token->{tag_name} eq 'select') { |
| 6058 |
|
## TODO: associate with $self->{form_element} if defined |
| 6059 |
|
|
| 6060 |
|
if ($self->{insertion_mode} & TABLE_IMS or |
| 6061 |
|
$self->{insertion_mode} & BODY_TABLE_IMS or |
| 6062 |
|
$self->{insertion_mode} == IN_COLUMN_GROUP_IM) { |
| 6063 |
|
!!!cp ('t400.1'); |
| 6064 |
|
$self->{insertion_mode} = IN_SELECT_IN_TABLE_IM; |
| 6065 |
|
} else { |
| 6066 |
|
!!!cp ('t400.2'); |
| 6067 |
|
$self->{insertion_mode} = IN_SELECT_IM; |
| 6068 |
|
} |
| 6069 |
|
} else { |
| 6070 |
|
!!!cp ('t402'); |
| 6071 |
|
} |
| 6072 |
|
|
| 6073 |
!!!next-token; |
!!!next-token; |
| 6074 |
redo B; |
redo B; |
| 6075 |
} |
} |
| 6076 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 6077 |
if ($token->{tag_name} eq 'body') { |
if ($token->{tag_name} eq 'body') { |
| 6078 |
if (@{$self->{open_elements}} > 1 and |
## has a |body| element in scope |
| 6079 |
$self->{open_elements}->[1]->[1] eq 'body') { |
my $i; |
| 6080 |
for (@{$self->{open_elements}}) { |
INSCOPE: { |
| 6081 |
unless ({ |
for (reverse @{$self->{open_elements}}) { |
| 6082 |
dd => 1, dt => 1, li => 1, p => 1, td => 1, |
if ($_->[1] eq 'body') { |
| 6083 |
th => 1, tr => 1, body => 1, html => 1, |
!!!cp ('t405'); |
| 6084 |
tbody => 1, tfoot => 1, thead => 1, |
$i = $_; |
| 6085 |
}->{$_->[1]}) { |
last INSCOPE; |
| 6086 |
!!!cp ('t403'); |
} elsif ({ |
| 6087 |
!!!parse-error (type => 'not closed:'.$_->[1]); |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 6088 |
} else { |
button => 1, marquee => 1, object => 1, html => 1, |
| 6089 |
!!!cp ('t404'); |
}->{$_->[1]}) { |
| 6090 |
|
!!!cp ('t405.1'); |
| 6091 |
|
last; |
| 6092 |
} |
} |
| 6093 |
} |
} |
| 6094 |
|
|
| 6095 |
$self->{insertion_mode} = AFTER_BODY_IM; |
!!!parse-error (type => 'start tag not allowed', |
| 6096 |
!!!next-token; |
value => $token->{tag_name}, token => $token); |
| 6097 |
redo B; |
## NOTE: Ignore the token. |
|
} else { |
|
|
!!!cp ('t405'); |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
| 6098 |
!!!next-token; |
!!!next-token; |
| 6099 |
redo B; |
redo B; |
| 6100 |
|
} # INSCOPE |
| 6101 |
|
|
| 6102 |
|
for (@{$self->{open_elements}}) { |
| 6103 |
|
unless ({ |
| 6104 |
|
dd => 1, dt => 1, li => 1, p => 1, td => 1, |
| 6105 |
|
th => 1, tr => 1, body => 1, html => 1, |
| 6106 |
|
tbody => 1, tfoot => 1, thead => 1, |
| 6107 |
|
}->{$_->[1]}) { |
| 6108 |
|
!!!cp ('t403'); |
| 6109 |
|
!!!parse-error (type => 'not closed:'.$_->[1], token => $token); |
| 6110 |
|
last; |
| 6111 |
|
} else { |
| 6112 |
|
!!!cp ('t404'); |
| 6113 |
|
} |
| 6114 |
} |
} |
| 6115 |
|
|
| 6116 |
|
$self->{insertion_mode} = AFTER_BODY_IM; |
| 6117 |
|
!!!next-token; |
| 6118 |
|
redo B; |
| 6119 |
} elsif ($token->{tag_name} eq 'html') { |
} elsif ($token->{tag_name} eq 'html') { |
| 6120 |
if (@{$self->{open_elements}} > 1 and $self->{open_elements}->[1]->[1] eq 'body') { |
if (@{$self->{open_elements}} > 1 and $self->{open_elements}->[1]->[1] eq 'body') { |
| 6121 |
## ISSUE: There is an issue in the spec. |
## ISSUE: There is an issue in the spec. |
| 6122 |
if ($self->{open_elements}->[-1]->[1] ne 'body') { |
if ($self->{open_elements}->[-1]->[1] ne 'body') { |
| 6123 |
!!!cp ('t406'); |
!!!cp ('t406'); |
| 6124 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[1]->[1], token => $token); |
| 6125 |
} else { |
} else { |
| 6126 |
!!!cp ('t407'); |
!!!cp ('t407'); |
| 6127 |
} |
} |
| 6130 |
redo B; |
redo B; |
| 6131 |
} else { |
} else { |
| 6132 |
!!!cp ('t408'); |
!!!cp ('t408'); |
| 6133 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 6134 |
## Ignore the token |
## Ignore the token |
| 6135 |
!!!next-token; |
!!!next-token; |
| 6136 |
redo B; |
redo B; |
| 6139 |
address => 1, blockquote => 1, center => 1, dir => 1, |
address => 1, blockquote => 1, center => 1, dir => 1, |
| 6140 |
div => 1, dl => 1, fieldset => 1, listing => 1, |
div => 1, dl => 1, fieldset => 1, listing => 1, |
| 6141 |
menu => 1, ol => 1, pre => 1, ul => 1, |
menu => 1, ol => 1, pre => 1, ul => 1, |
|
p => 1, |
|
| 6142 |
dd => 1, dt => 1, li => 1, |
dd => 1, dt => 1, li => 1, |
| 6143 |
button => 1, marquee => 1, object => 1, |
applet => 1, button => 1, marquee => 1, object => 1, |
| 6144 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6145 |
## has an element in scope |
## has an element in scope |
| 6146 |
my $i; |
my $i; |
| 6147 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 6148 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 6149 |
if ($node->[1] eq $token->{tag_name}) { |
if ($node->[1] eq $token->{tag_name}) { |
|
## generate implied end tags |
|
|
if ({ |
|
|
dd => ($token->{tag_name} ne 'dd'), |
|
|
dt => ($token->{tag_name} ne 'dt'), |
|
|
li => ($token->{tag_name} ne 'li'), |
|
|
p => ($token->{tag_name} ne 'p'), |
|
|
td => 1, th => 1, tr => 1, |
|
|
tbody => 1, tfoot=> 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!cp ('t409'); |
|
|
!!!back-token; |
|
|
$token = {type => END_TAG_TOKEN, |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
|
} |
|
|
|
|
| 6150 |
!!!cp ('t410'); |
!!!cp ('t410'); |
| 6151 |
$i = $_; |
$i = $_; |
| 6152 |
last INSCOPE unless $token->{tag_name} eq 'p'; |
last INSCOPE; |
| 6153 |
} elsif ({ |
} elsif ({ |
| 6154 |
table => 1, caption => 1, td => 1, th => 1, |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 6155 |
button => 1, marquee => 1, object => 1, html => 1, |
button => 1, marquee => 1, object => 1, html => 1, |
| 6156 |
}->{$node->[1]}) { |
}->{$node->[1]}) { |
| 6157 |
!!!cp ('t411'); |
!!!cp ('t411'); |
| 6158 |
last INSCOPE; |
last INSCOPE; |
| 6159 |
} |
} |
| 6160 |
} # INSCOPE |
} # INSCOPE |
| 6161 |
|
|
| 6162 |
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
unless (defined $i) { # has an element in scope |
| 6163 |
if (defined $i) { |
!!!cp ('t413'); |
| 6164 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 6165 |
|
} else { |
| 6166 |
|
## Step 1. generate implied end tags |
| 6167 |
|
while ({ |
| 6168 |
|
dd => ($token->{tag_name} ne 'dd'), |
| 6169 |
|
dt => ($token->{tag_name} ne 'dt'), |
| 6170 |
|
li => ($token->{tag_name} ne 'li'), |
| 6171 |
|
p => 1, |
| 6172 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 6173 |
|
!!!cp ('t409'); |
| 6174 |
|
pop @{$self->{open_elements}}; |
| 6175 |
|
} |
| 6176 |
|
|
| 6177 |
|
## Step 2. |
| 6178 |
|
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
| 6179 |
!!!cp ('t412'); |
!!!cp ('t412'); |
| 6180 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 6181 |
} else { |
} else { |
| 6182 |
!!!cp ('t413'); |
!!!cp ('t414'); |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
| 6183 |
} |
} |
| 6184 |
} |
|
| 6185 |
|
## Step 3. |
|
if (defined $i) { |
|
|
!!!cp ('t414'); |
|
| 6186 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 6187 |
} elsif ($token->{tag_name} eq 'p') { |
|
| 6188 |
!!!cp ('t415'); |
## Step 4. |
| 6189 |
## As if <p>, then reprocess the current token |
$clear_up_to_marker->() |
| 6190 |
my $el; |
if { |
| 6191 |
!!!create-element ($el, 'p'); |
applet => 1, button => 1, marquee => 1, object => 1, |
| 6192 |
$insert->($el); |
}->{$token->{tag_name}}; |
|
} else { |
|
|
!!!cp ('t416'); |
|
| 6193 |
} |
} |
|
$clear_up_to_marker->() |
|
|
if { |
|
|
button => 1, marquee => 1, object => 1, |
|
|
}->{$token->{tag_name}}; |
|
| 6194 |
!!!next-token; |
!!!next-token; |
| 6195 |
redo B; |
redo B; |
| 6196 |
} elsif ($token->{tag_name} eq 'form') { |
} elsif ($token->{tag_name} eq 'form') { |
| 6197 |
|
undef $self->{form_element}; |
| 6198 |
|
|
| 6199 |
## has an element in scope |
## has an element in scope |
| 6200 |
|
my $i; |
| 6201 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 6202 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 6203 |
if ($node->[1] eq $token->{tag_name}) { |
if ($node->[1] eq $token->{tag_name}) { |
|
## generate implied end tags |
|
|
if ({ |
|
|
dd => 1, dt => 1, li => 1, p => 1, |
|
|
|
|
|
## NOTE: The following elements never appear here, maybe. |
|
|
td => 1, th => 1, tr => 1, |
|
|
tbody => 1, tfoot => 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!cp ('t417'); |
|
|
!!!back-token; |
|
|
$token = {type => END_TAG_TOKEN, |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
|
} |
|
|
|
|
| 6204 |
!!!cp ('t418'); |
!!!cp ('t418'); |
| 6205 |
|
$i = $_; |
| 6206 |
last INSCOPE; |
last INSCOPE; |
| 6207 |
} elsif ({ |
} elsif ({ |
| 6208 |
table => 1, caption => 1, td => 1, th => 1, |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 6209 |
button => 1, marquee => 1, object => 1, html => 1, |
button => 1, marquee => 1, object => 1, html => 1, |
| 6210 |
}->{$node->[1]}) { |
}->{$node->[1]}) { |
| 6211 |
!!!cp ('t419'); |
!!!cp ('t419'); |
| 6212 |
last INSCOPE; |
last INSCOPE; |
| 6213 |
} |
} |
| 6214 |
} # INSCOPE |
} # INSCOPE |
| 6215 |
|
|
| 6216 |
if ($self->{open_elements}->[-1]->[1] eq $token->{tag_name}) { |
unless (defined $i) { # has an element in scope |
|
!!!cp ('t420'); |
|
|
pop @{$self->{open_elements}}; |
|
|
} else { |
|
| 6217 |
!!!cp ('t421'); |
!!!cp ('t421'); |
| 6218 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 6219 |
|
} else { |
| 6220 |
|
## Step 1. generate implied end tags |
| 6221 |
|
while ({ |
| 6222 |
|
dd => 1, dt => 1, li => 1, p => 1, |
| 6223 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 6224 |
|
!!!cp ('t417'); |
| 6225 |
|
pop @{$self->{open_elements}}; |
| 6226 |
|
} |
| 6227 |
|
|
| 6228 |
|
## Step 2. |
| 6229 |
|
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
| 6230 |
|
!!!cp ('t417.1'); |
| 6231 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 6232 |
|
} else { |
| 6233 |
|
!!!cp ('t420'); |
| 6234 |
|
} |
| 6235 |
|
|
| 6236 |
|
## Step 3. |
| 6237 |
|
splice @{$self->{open_elements}}, $i; |
| 6238 |
} |
} |
| 6239 |
|
|
|
undef $self->{form_element}; |
|
| 6240 |
!!!next-token; |
!!!next-token; |
| 6241 |
redo B; |
redo B; |
| 6242 |
} elsif ({ |
} elsif ({ |
| 6249 |
if ({ |
if ({ |
| 6250 |
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
| 6251 |
}->{$node->[1]}) { |
}->{$node->[1]}) { |
|
## generate implied end tags |
|
|
if ({ |
|
|
dd => 1, dt => 1, li => 1, p => 1, |
|
|
td => 1, th => 1, tr => 1, |
|
|
tbody => 1, tfoot=> 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!cp ('t422'); |
|
|
!!!back-token; |
|
|
$token = {type => END_TAG_TOKEN, |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
|
} |
|
|
|
|
| 6252 |
!!!cp ('t423'); |
!!!cp ('t423'); |
| 6253 |
$i = $_; |
$i = $_; |
| 6254 |
last INSCOPE; |
last INSCOPE; |
| 6255 |
} elsif ({ |
} elsif ({ |
| 6256 |
table => 1, caption => 1, td => 1, th => 1, |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 6257 |
button => 1, marquee => 1, object => 1, html => 1, |
button => 1, marquee => 1, object => 1, html => 1, |
| 6258 |
}->{$node->[1]}) { |
}->{$node->[1]}) { |
| 6259 |
!!!cp ('t424'); |
!!!cp ('t424'); |
| 6260 |
last INSCOPE; |
last INSCOPE; |
| 6261 |
} |
} |
| 6262 |
} # INSCOPE |
} # INSCOPE |
| 6263 |
|
|
| 6264 |
|
unless (defined $i) { # has an element in scope |
| 6265 |
|
!!!cp ('t425.1'); |
| 6266 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 6267 |
|
} else { |
| 6268 |
|
## Step 1. generate implied end tags |
| 6269 |
|
while ({ |
| 6270 |
|
dd => 1, dt => 1, li => 1, p => 1, |
| 6271 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 6272 |
|
!!!cp ('t422'); |
| 6273 |
|
pop @{$self->{open_elements}}; |
| 6274 |
|
} |
| 6275 |
|
|
| 6276 |
|
## Step 2. |
| 6277 |
|
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
| 6278 |
|
!!!cp ('t425'); |
| 6279 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 6280 |
|
} else { |
| 6281 |
|
!!!cp ('t426'); |
| 6282 |
|
} |
| 6283 |
|
|
| 6284 |
|
## Step 3. |
| 6285 |
|
splice @{$self->{open_elements}}, $i; |
| 6286 |
|
} |
| 6287 |
|
|
| 6288 |
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
!!!next-token; |
| 6289 |
!!!cp ('t425'); |
redo B; |
| 6290 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
} elsif ($token->{tag_name} eq 'p') { |
| 6291 |
|
## has an element in scope |
| 6292 |
|
my $i; |
| 6293 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 6294 |
|
my $node = $self->{open_elements}->[$_]; |
| 6295 |
|
if ($node->[1] eq $token->{tag_name}) { |
| 6296 |
|
!!!cp ('t410.1'); |
| 6297 |
|
$i = $_; |
| 6298 |
|
last INSCOPE; |
| 6299 |
|
} elsif ({ |
| 6300 |
|
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 6301 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 6302 |
|
}->{$node->[1]}) { |
| 6303 |
|
!!!cp ('t411.1'); |
| 6304 |
|
last INSCOPE; |
| 6305 |
|
} |
| 6306 |
|
} # INSCOPE |
| 6307 |
|
|
| 6308 |
|
if (defined $i) { |
| 6309 |
|
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
| 6310 |
|
!!!cp ('t412.1'); |
| 6311 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 6312 |
|
} else { |
| 6313 |
|
!!!cp ('t414.1'); |
| 6314 |
|
} |
| 6315 |
|
|
| 6316 |
|
splice @{$self->{open_elements}}, $i; |
| 6317 |
} else { |
} else { |
| 6318 |
!!!cp ('t426'); |
!!!cp ('t413.1'); |
| 6319 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 6320 |
|
|
| 6321 |
|
!!!cp ('t415.1'); |
| 6322 |
|
## As if <p>, then reprocess the current token |
| 6323 |
|
my $el; |
| 6324 |
|
!!!create-element ($el, 'p',, $token); |
| 6325 |
|
$insert->($el); |
| 6326 |
|
## NOTE: Not inserted into |$self->{open_elements}|. |
| 6327 |
} |
} |
| 6328 |
|
|
|
splice @{$self->{open_elements}}, $i if defined $i; |
|
| 6329 |
!!!next-token; |
!!!next-token; |
| 6330 |
redo B; |
redo B; |
| 6331 |
} elsif ({ |
} elsif ({ |
| 6335 |
strong => 1, tt => 1, u => 1, |
strong => 1, tt => 1, u => 1, |
| 6336 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6337 |
!!!cp ('t427'); |
!!!cp ('t427'); |
| 6338 |
$formatting_end_tag->($token->{tag_name}); |
$formatting_end_tag->($token); |
| 6339 |
redo B; |
redo B; |
| 6340 |
} elsif ($token->{tag_name} eq 'br') { |
} elsif ($token->{tag_name} eq 'br') { |
| 6341 |
!!!cp ('t428'); |
!!!cp ('t428'); |
| 6342 |
!!!parse-error (type => 'unmatched end tag:br'); |
!!!parse-error (type => 'unmatched end tag:br', token => $token); |
| 6343 |
|
|
| 6344 |
## As if <br> |
## As if <br> |
| 6345 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 6346 |
|
|
| 6347 |
my $el; |
my $el; |
| 6348 |
!!!create-element ($el, 'br'); |
!!!create-element ($el, 'br',, $token); |
| 6349 |
$insert->($el); |
$insert->($el); |
| 6350 |
|
|
| 6351 |
## Ignore the token. |
## Ignore the token. |
| 6364 |
noscript => 0, ## TODO: if scripting is enabled |
noscript => 0, ## TODO: if scripting is enabled |
| 6365 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6366 |
!!!cp ('t429'); |
!!!cp ('t429'); |
| 6367 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 6368 |
## Ignore the token |
## Ignore the token |
| 6369 |
!!!next-token; |
!!!next-token; |
| 6370 |
redo B; |
redo B; |
| 6381 |
if ($node->[1] eq $token->{tag_name}) { |
if ($node->[1] eq $token->{tag_name}) { |
| 6382 |
## Step 1 |
## Step 1 |
| 6383 |
## generate implied end tags |
## generate implied end tags |
| 6384 |
if ({ |
while ({ |
| 6385 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 6386 |
td => 1, th => 1, tr => 1, |
}->{$self->{open_elements}->[-1]->[1]}) { |
|
tbody => 1, tfoot => 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 6387 |
!!!cp ('t430'); |
!!!cp ('t430'); |
| 6388 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
| 6389 |
!!!back-token; |
pop @{$self->{open_elements}}; |
|
$token = {type => END_TAG_TOKEN, |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
| 6390 |
} |
} |
| 6391 |
|
|
| 6392 |
## Step 2 |
## Step 2 |
| 6393 |
if ($token->{tag_name} ne $self->{open_elements}->[-1]->[1]) { |
if ($token->{tag_name} ne $self->{open_elements}->[-1]->[1]) { |
| 6394 |
!!!cp ('t431'); |
!!!cp ('t431'); |
| 6395 |
## NOTE: <x><y></x> |
## NOTE: <x><y></x> |
| 6396 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 6397 |
} else { |
} else { |
| 6398 |
!!!cp ('t432'); |
!!!cp ('t432'); |
| 6399 |
} |
} |
| 6410 |
($special_category->{$node->[1]} or |
($special_category->{$node->[1]} or |
| 6411 |
$scoping_category->{$node->[1]})) { |
$scoping_category->{$node->[1]})) { |
| 6412 |
!!!cp ('t433'); |
!!!cp ('t433'); |
| 6413 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 6414 |
## Ignore the token |
## Ignore the token |
| 6415 |
!!!next-token; |
!!!next-token; |
| 6416 |
last S2; |
last S2; |