| 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 $self->{document}; |
| 232 |
} # parse_string |
} # parse_string |
| 233 |
|
|
| 311 |
sub ROW_IMS () { 0b10000000 } |
sub ROW_IMS () { 0b10000000 } |
| 312 |
sub BODY_AFTER_IMS () { 0b100000000 } |
sub BODY_AFTER_IMS () { 0b100000000 } |
| 313 |
sub FRAME_IMS () { 0b1000000000 } |
sub FRAME_IMS () { 0b1000000000 } |
| 314 |
|
sub SELECT_IMS () { 0b10000000000 } |
| 315 |
|
|
| 316 |
|
## NOTE: "initial" and "before html" insertion modes have no constants. |
| 317 |
|
|
| 318 |
|
## NOTE: "after after body" insertion mode. |
| 319 |
sub AFTER_HTML_BODY_IM () { AFTER_HTML_IMS | BODY_AFTER_IMS } |
sub AFTER_HTML_BODY_IM () { AFTER_HTML_IMS | BODY_AFTER_IMS } |
| 320 |
|
|
| 321 |
|
## NOTE: "after after frameset" insertion mode. |
| 322 |
sub AFTER_HTML_FRAMESET_IM () { AFTER_HTML_IMS | FRAME_IMS } |
sub AFTER_HTML_FRAMESET_IM () { AFTER_HTML_IMS | FRAME_IMS } |
| 323 |
|
|
| 324 |
sub IN_HEAD_IM () { HEAD_IMS | 0b00 } |
sub IN_HEAD_IM () { HEAD_IMS | 0b00 } |
| 325 |
sub IN_HEAD_NOSCRIPT_IM () { HEAD_IMS | 0b01 } |
sub IN_HEAD_NOSCRIPT_IM () { HEAD_IMS | 0b01 } |
| 326 |
sub AFTER_HEAD_IM () { HEAD_IMS | 0b10 } |
sub AFTER_HEAD_IM () { HEAD_IMS | 0b10 } |
| 334 |
sub AFTER_BODY_IM () { BODY_AFTER_IMS } |
sub AFTER_BODY_IM () { BODY_AFTER_IMS } |
| 335 |
sub IN_FRAMESET_IM () { FRAME_IMS | 0b01 } |
sub IN_FRAMESET_IM () { FRAME_IMS | 0b01 } |
| 336 |
sub AFTER_FRAMESET_IM () { FRAME_IMS | 0b10 } |
sub AFTER_FRAMESET_IM () { FRAME_IMS | 0b10 } |
| 337 |
sub IN_SELECT_IM () { 0b01 } |
sub IN_SELECT_IM () { SELECT_IMS | 0b01 } |
| 338 |
|
sub IN_SELECT_IN_TABLE_IM () { SELECT_IMS | 0b10 } |
| 339 |
sub IN_COLUMN_GROUP_IM () { 0b10 } |
sub IN_COLUMN_GROUP_IM () { 0b10 } |
| 340 |
|
|
| 341 |
## Implementations MUST act as if state machine in the spec |
## Implementations MUST act as if state machine in the spec |
| 457 |
# |
# |
| 458 |
} elsif ($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 |
| 821 |
} elsif (0x0041 <= $self->{next_char} and |
} elsif (0x0041 <= $self->{next_char} and |
| 822 |
$self->{next_char} <= 0x005A) { # A..Z |
$self->{next_char} <= 0x005A) { # A..Z |
| 823 |
!!!cp (49); |
!!!cp (49); |
| 824 |
$self->{current_attribute} = {name => chr ($self->{next_char} + 0x0020), |
$self->{current_attribute} |
| 825 |
value => ''}; |
= {name => chr ($self->{next_char} + 0x0020), |
| 826 |
|
value => '', |
| 827 |
|
line => $self->{line}, column => $self->{column}}; |
| 828 |
$self->{state} = ATTRIBUTE_NAME_STATE; |
$self->{state} = ATTRIBUTE_NAME_STATE; |
| 829 |
!!!next-input-character; |
!!!next-input-character; |
| 830 |
redo A; |
redo A; |
| 847 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 848 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 849 |
!!!cp (52); |
!!!cp (52); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 850 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 851 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 852 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 876 |
} else { |
} else { |
| 877 |
!!!cp (56); |
!!!cp (56); |
| 878 |
} |
} |
| 879 |
$self->{current_attribute} = {name => chr ($self->{next_char}), |
$self->{current_attribute} |
| 880 |
value => ''}; |
= {name => chr ($self->{next_char}), |
| 881 |
|
value => '', |
| 882 |
|
line => $self->{line}, column => $self->{column}}; |
| 883 |
$self->{state} = ATTRIBUTE_NAME_STATE; |
$self->{state} = ATTRIBUTE_NAME_STATE; |
| 884 |
!!!next-input-character; |
!!!next-input-character; |
| 885 |
redo A; |
redo A; |
| 889 |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
| 890 |
->{$self->{current_attribute}->{name}}) { # MUST |
->{$self->{current_attribute}->{name}}) { # MUST |
| 891 |
!!!cp (57); |
!!!cp (57); |
| 892 |
!!!parse-error (type => 'duplicate attribute:'.$self->{current_attribute}->{name}); |
!!!parse-error (type => 'duplicate attribute:'.$self->{current_attribute}->{name}, line => $self->{current_attribute}->{line}, column => $self->{current_attribute}->{column}); |
| 893 |
## Discard $self->{current_attribute} # MUST |
## Discard $self->{current_attribute} # MUST |
| 894 |
} else { |
} else { |
| 895 |
!!!cp (58); |
!!!cp (58); |
| 918 |
$before_leave->(); |
$before_leave->(); |
| 919 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 920 |
!!!cp (61); |
!!!cp (61); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 921 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 922 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 923 |
!!!cp (62); |
!!!cp (62); |
| 962 |
$before_leave->(); |
$before_leave->(); |
| 963 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 964 |
!!!cp (66); |
!!!cp (66); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 965 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 966 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 967 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1012 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1013 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1014 |
!!!cp (73); |
!!!cp (73); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1015 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1016 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1017 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1034 |
} elsif (0x0041 <= $self->{next_char} and |
} elsif (0x0041 <= $self->{next_char} and |
| 1035 |
$self->{next_char} <= 0x005A) { # A..Z |
$self->{next_char} <= 0x005A) { # A..Z |
| 1036 |
!!!cp (76); |
!!!cp (76); |
| 1037 |
$self->{current_attribute} = {name => chr ($self->{next_char} + 0x0020), |
$self->{current_attribute} |
| 1038 |
value => ''}; |
= {name => chr ($self->{next_char} + 0x0020), |
| 1039 |
|
value => '', |
| 1040 |
|
line => $self->{line}, column => $self->{column}}; |
| 1041 |
$self->{state} = ATTRIBUTE_NAME_STATE; |
$self->{state} = ATTRIBUTE_NAME_STATE; |
| 1042 |
!!!next-input-character; |
!!!next-input-character; |
| 1043 |
redo A; |
redo A; |
| 1061 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 1062 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1063 |
!!!cp (79); |
!!!cp (79); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1064 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1065 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1066 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1082 |
redo A; |
redo A; |
| 1083 |
} else { |
} else { |
| 1084 |
!!!cp (82); |
!!!cp (82); |
| 1085 |
$self->{current_attribute} = {name => chr ($self->{next_char}), |
$self->{current_attribute} |
| 1086 |
value => ''}; |
= {name => chr ($self->{next_char}), |
| 1087 |
|
value => '', |
| 1088 |
|
line => $self->{line}, column => $self->{column}}; |
| 1089 |
$self->{state} = ATTRIBUTE_NAME_STATE; |
$self->{state} = ATTRIBUTE_NAME_STATE; |
| 1090 |
!!!next-input-character; |
!!!next-input-character; |
| 1091 |
redo A; |
redo A; |
| 1118 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1119 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1120 |
!!!cp (87); |
!!!cp (87); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1121 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1122 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1123 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1141 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 1142 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1143 |
!!!cp (90); |
!!!cp (90); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1144 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1145 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1146 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1188 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
| 1189 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1190 |
!!!cp (97); |
!!!cp (97); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1191 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1192 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1193 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1230 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
| 1231 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1232 |
!!!cp (103); |
!!!cp (103); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1233 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1234 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1235 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1275 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1276 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1277 |
!!!cp (109); |
!!!cp (109); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1278 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1279 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1280 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1298 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 1299 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1300 |
!!!cp (112); |
!!!cp (112); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1301 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1302 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1303 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1368 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1369 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1370 |
!!!cp (119); |
!!!cp (119); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1371 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1372 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1373 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1412 |
} elsif ($self->{state} == BOGUS_COMMENT_STATE) { |
} elsif ($self->{state} == BOGUS_COMMENT_STATE) { |
| 1413 |
## (only happen if PCDATA state) |
## (only happen if PCDATA state) |
| 1414 |
|
|
| 1415 |
my $token = {type => COMMENT_TOKEN, data => ''}; |
## NOTE: Set by the previous state |
| 1416 |
|
#my $token = {type => COMMENT_TOKEN, data => ''}; |
| 1417 |
|
|
| 1418 |
BC: { |
BC: { |
| 1419 |
if ($self->{next_char} == 0x003E) { # > |
if ($self->{next_char} == 0x003E) { # > |
| 1421 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1422 |
!!!next-input-character; |
!!!next-input-character; |
| 1423 |
|
|
| 1424 |
!!!emit ($token); |
!!!emit ($self->{current_token}); # comment |
| 1425 |
|
|
| 1426 |
redo A; |
redo A; |
| 1427 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 1429 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1430 |
## reconsume |
## reconsume |
| 1431 |
|
|
| 1432 |
!!!emit ($token); |
!!!emit ($self->{current_token}); # comment |
| 1433 |
|
|
| 1434 |
redo A; |
redo A; |
| 1435 |
} else { |
} else { |
| 1436 |
!!!cp (126); |
!!!cp (126); |
| 1437 |
$token->{data} .= chr ($self->{next_char}); |
$self->{current_token}->{data} .= chr ($self->{next_char}); # comment |
| 1438 |
!!!next-input-character; |
!!!next-input-character; |
| 1439 |
redo BC; |
redo BC; |
| 1440 |
} |
} |
| 1444 |
} elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) { |
} elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) { |
| 1445 |
## (only happen if PCDATA state) |
## (only happen if PCDATA state) |
| 1446 |
|
|
| 1447 |
|
my ($l, $c) = ($self->{line_prev}, $self->{column_prev} - 1); |
| 1448 |
|
|
| 1449 |
my @next_char; |
my @next_char; |
| 1450 |
push @next_char, $self->{next_char}; |
push @next_char, $self->{next_char}; |
| 1451 |
|
|
| 1454 |
push @next_char, $self->{next_char}; |
push @next_char, $self->{next_char}; |
| 1455 |
if ($self->{next_char} == 0x002D) { # - |
if ($self->{next_char} == 0x002D) { # - |
| 1456 |
!!!cp (127); |
!!!cp (127); |
| 1457 |
$self->{current_token} = {type => COMMENT_TOKEN, data => ''}; |
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
| 1458 |
|
line => $l, column => $c, |
| 1459 |
|
}; |
| 1460 |
$self->{state} = COMMENT_START_STATE; |
$self->{state} = COMMENT_START_STATE; |
| 1461 |
!!!next-input-character; |
!!!next-input-character; |
| 1462 |
redo A; |
redo A; |
| 1492 |
!!!cp (129); |
!!!cp (129); |
| 1493 |
## TODO: What a stupid code this is! |
## TODO: What a stupid code this is! |
| 1494 |
$self->{state} = DOCTYPE_STATE; |
$self->{state} = DOCTYPE_STATE; |
| 1495 |
|
$self->{current_token} = {type => DOCTYPE_TOKEN, |
| 1496 |
|
quirks => 1, |
| 1497 |
|
line => $l, column => $c, |
| 1498 |
|
}; |
| 1499 |
!!!next-input-character; |
!!!next-input-character; |
| 1500 |
redo A; |
redo A; |
| 1501 |
} else { |
} else { |
| 1524 |
$self->{next_char} = shift @next_char; |
$self->{next_char} = shift @next_char; |
| 1525 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 1526 |
$self->{state} = BOGUS_COMMENT_STATE; |
$self->{state} = BOGUS_COMMENT_STATE; |
| 1527 |
|
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
| 1528 |
|
line => $l, column => $c, |
| 1529 |
|
}; |
| 1530 |
redo A; |
redo A; |
| 1531 |
|
|
| 1532 |
## ISSUE: typos in spec: chacacters, is is a parse error |
## ISSUE: typos in spec: chacacters, is is a parse error |
| 1650 |
redo A; |
redo A; |
| 1651 |
} elsif ($self->{next_char} == 0x002D) { # - |
} elsif ($self->{next_char} == 0x002D) { # - |
| 1652 |
!!!cp (152); |
!!!cp (152); |
| 1653 |
!!!parse-error (type => 'dash in comment'); |
!!!parse-error (type => 'dash in comment', |
| 1654 |
|
line => $self->{line_prev}, |
| 1655 |
|
column => $self->{column_prev}); |
| 1656 |
$self->{current_token}->{data} .= '-'; # comment |
$self->{current_token}->{data} .= '-'; # comment |
| 1657 |
## Stay in the state |
## Stay in the state |
| 1658 |
!!!next-input-character; |
!!!next-input-character; |
| 1668 |
redo A; |
redo A; |
| 1669 |
} else { |
} else { |
| 1670 |
!!!cp (154); |
!!!cp (154); |
| 1671 |
!!!parse-error (type => 'dash in comment'); |
!!!parse-error (type => 'dash in comment', |
| 1672 |
|
line => $self->{line_prev}, |
| 1673 |
|
column => $self->{column_prev}); |
| 1674 |
$self->{current_token}->{data} .= '--' . chr ($self->{next_char}); # comment |
$self->{current_token}->{data} .= '--' . chr ($self->{next_char}); # comment |
| 1675 |
$self->{state} = COMMENT_STATE; |
$self->{state} = COMMENT_STATE; |
| 1676 |
!!!next-input-character; |
!!!next-input-character; |
| 1709 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1710 |
!!!next-input-character; |
!!!next-input-character; |
| 1711 |
|
|
| 1712 |
!!!emit ({type => DOCTYPE_TOKEN, quirks => 1}); |
!!!emit ($self->{current_token}); # DOCTYPE (quirks) |
| 1713 |
|
|
| 1714 |
redo A; |
redo A; |
| 1715 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 1718 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1719 |
## reconsume |
## reconsume |
| 1720 |
|
|
| 1721 |
!!!emit ({type => DOCTYPE_TOKEN, quirks => 1}); |
!!!emit ($self->{current_token}); # DOCTYPE (quirks) |
| 1722 |
|
|
| 1723 |
redo A; |
redo A; |
| 1724 |
} else { |
} else { |
| 1725 |
!!!cp (160); |
!!!cp (160); |
| 1726 |
$self->{current_token} |
$self->{current_token}->{name} = chr $self->{next_char}; |
| 1727 |
= {type => DOCTYPE_TOKEN, |
delete $self->{current_token}->{quirks}; |
|
name => chr ($self->{next_char}), |
|
|
#quirks => 0, |
|
|
}; |
|
| 1728 |
## ISSUE: "Set the token's name name to the" in the spec |
## ISSUE: "Set the token's name name to the" in the spec |
| 1729 |
$self->{state} = DOCTYPE_NAME_STATE; |
$self->{state} = DOCTYPE_NAME_STATE; |
| 1730 |
!!!next-input-character; |
!!!next-input-character; |
| 2251 |
sub _tokenize_attempt_to_consume_an_entity ($$$) { |
sub _tokenize_attempt_to_consume_an_entity ($$$) { |
| 2252 |
my ($self, $in_attr, $additional) = @_; |
my ($self, $in_attr, $additional) = @_; |
| 2253 |
|
|
| 2254 |
|
my ($l, $c) = ($self->{line_prev}, $self->{column_prev}); |
| 2255 |
|
|
| 2256 |
if ({ |
if ({ |
| 2257 |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, # HT, LF, VT, FF, |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, # HT, LF, VT, FF, |
| 2258 |
0x0020 => 1, 0x003C => 1, 0x0026 => 1, -1 => 1, # SP, <, & # 0x000D # CR |
0x0020 => 1, 0x003C => 1, 0x0026 => 1, -1 => 1, # SP, <, & # 0x000D # CR |
| 2293 |
redo X; |
redo X; |
| 2294 |
} elsif (not defined $code) { # no hexadecimal digit |
} elsif (not defined $code) { # no hexadecimal digit |
| 2295 |
!!!cp (1005); |
!!!cp (1005); |
| 2296 |
!!!parse-error (type => 'bare hcro'); |
!!!parse-error (type => 'bare hcro', line => $l, column => $c); |
| 2297 |
!!!back-next-input-character ($x_char, $self->{next_char}); |
!!!back-next-input-character ($x_char, $self->{next_char}); |
| 2298 |
$self->{next_char} = 0x0023; # # |
$self->{next_char} = 0x0023; # # |
| 2299 |
return undef; |
return undef; |
| 2302 |
!!!next-input-character; |
!!!next-input-character; |
| 2303 |
} else { |
} else { |
| 2304 |
!!!cp (1007); |
!!!cp (1007); |
| 2305 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'no refc', line => $l, column => $c); |
| 2306 |
} |
} |
| 2307 |
|
|
| 2308 |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 2309 |
!!!cp (1008); |
!!!cp (1008); |
| 2310 |
!!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code); |
!!!parse-error (type => (sprintf 'invalid character reference:U+%04X', $code), line => $l, column => $c); |
| 2311 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 2312 |
} elsif ($code > 0x10FFFF) { |
} elsif ($code > 0x10FFFF) { |
| 2313 |
!!!cp (1009); |
!!!cp (1009); |
| 2314 |
!!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code); |
!!!parse-error (type => (sprintf 'invalid character reference:U-%08X', $code), line => $l, column => $c); |
| 2315 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 2316 |
} elsif ($code == 0x000D) { |
} elsif ($code == 0x000D) { |
| 2317 |
!!!cp (1010); |
!!!cp (1010); |
| 2318 |
!!!parse-error (type => 'CR character reference'); |
!!!parse-error (type => 'CR character reference', line => $l, column => $c); |
| 2319 |
$code = 0x000A; |
$code = 0x000A; |
| 2320 |
} elsif (0x80 <= $code and $code <= 0x9F) { |
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 2321 |
!!!cp (1011); |
!!!cp (1011); |
| 2322 |
!!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code); |
!!!parse-error (type => (sprintf 'C1 character reference:U+%04X', $code), line => $l, column => $c); |
| 2323 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 2324 |
} |
} |
| 2325 |
|
|
| 2326 |
return {type => CHARACTER_TOKEN, data => chr $code, |
return {type => CHARACTER_TOKEN, data => chr $code, |
| 2327 |
has_reference => 1}; |
has_reference => 1, |
| 2328 |
|
line => $l, column => $c, |
| 2329 |
|
}; |
| 2330 |
} # X |
} # X |
| 2331 |
} elsif (0x0030 <= $self->{next_char} and |
} elsif (0x0030 <= $self->{next_char} and |
| 2332 |
$self->{next_char} <= 0x0039) { # 0..9 |
$self->{next_char} <= 0x0039) { # 0..9 |
| 2347 |
!!!next-input-character; |
!!!next-input-character; |
| 2348 |
} else { |
} else { |
| 2349 |
!!!cp (1014); |
!!!cp (1014); |
| 2350 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'no refc', line => $l, column => $c); |
| 2351 |
} |
} |
| 2352 |
|
|
| 2353 |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 2354 |
!!!cp (1015); |
!!!cp (1015); |
| 2355 |
!!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code); |
!!!parse-error (type => (sprintf 'invalid character reference:U+%04X', $code), line => $l, column => $c); |
| 2356 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 2357 |
} elsif ($code > 0x10FFFF) { |
} elsif ($code > 0x10FFFF) { |
| 2358 |
!!!cp (1016); |
!!!cp (1016); |
| 2359 |
!!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code); |
!!!parse-error (type => (sprintf 'invalid character reference:U-%08X', $code), line => $l, column => $c); |
| 2360 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 2361 |
} elsif ($code == 0x000D) { |
} elsif ($code == 0x000D) { |
| 2362 |
!!!cp (1017); |
!!!cp (1017); |
| 2363 |
!!!parse-error (type => 'CR character reference'); |
!!!parse-error (type => 'CR character reference', line => $l, column => $c); |
| 2364 |
$code = 0x000A; |
$code = 0x000A; |
| 2365 |
} elsif (0x80 <= $code and $code <= 0x9F) { |
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 2366 |
!!!cp (1018); |
!!!cp (1018); |
| 2367 |
!!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code); |
!!!parse-error (type => (sprintf 'C1 character reference:U+%04X', $code), line => $l, column => $c); |
| 2368 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 2369 |
} |
} |
| 2370 |
|
|
| 2371 |
return {type => CHARACTER_TOKEN, data => chr $code, has_reference => 1}; |
return {type => CHARACTER_TOKEN, data => chr $code, has_reference => 1, |
| 2372 |
|
line => $l, column => $c, |
| 2373 |
|
}; |
| 2374 |
} else { |
} else { |
| 2375 |
!!!cp (1019); |
!!!cp (1019); |
| 2376 |
!!!parse-error (type => 'bare nero'); |
!!!parse-error (type => 'bare nero', line => $l, column => $c); |
| 2377 |
!!!back-next-input-character ($self->{next_char}); |
!!!back-next-input-character ($self->{next_char}); |
| 2378 |
$self->{next_char} = 0x0023; # # |
$self->{next_char} = 0x0023; # # |
| 2379 |
return undef; |
return undef; |
| 2423 |
|
|
| 2424 |
if ($match > 0) { |
if ($match > 0) { |
| 2425 |
!!!cp (1023); |
!!!cp (1023); |
| 2426 |
return {type => CHARACTER_TOKEN, data => $value, has_reference => 1}; |
return {type => CHARACTER_TOKEN, data => $value, has_reference => 1, |
| 2427 |
|
line => $l, column => $c, |
| 2428 |
|
}; |
| 2429 |
} elsif ($match < 0) { |
} elsif ($match < 0) { |
| 2430 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'no refc', line => $l, column => $c); |
| 2431 |
if ($in_attr and $match < -1) { |
if ($in_attr and $match < -1) { |
| 2432 |
!!!cp (1024); |
!!!cp (1024); |
| 2433 |
return {type => CHARACTER_TOKEN, data => '&'.$entity_name}; |
return {type => CHARACTER_TOKEN, data => '&'.$entity_name, |
| 2434 |
|
line => $l, column => $c, |
| 2435 |
|
}; |
| 2436 |
} else { |
} else { |
| 2437 |
!!!cp (1025); |
!!!cp (1025); |
| 2438 |
return {type => CHARACTER_TOKEN, data => $value, has_reference => 1}; |
return {type => CHARACTER_TOKEN, data => $value, has_reference => 1, |
| 2439 |
|
line => $l, column => $c, |
| 2440 |
|
}; |
| 2441 |
} |
} |
| 2442 |
} else { |
} else { |
| 2443 |
!!!cp (1026); |
!!!cp (1026); |
| 2444 |
!!!parse-error (type => 'bare ero'); |
!!!parse-error (type => 'bare ero', line => $l, column => $c); |
| 2445 |
## NOTE: "No characters are consumed" in the spec. |
## NOTE: "No characters are consumed" in the spec. |
| 2446 |
return {type => CHARACTER_TOKEN, data => '&'.$value}; |
return {type => CHARACTER_TOKEN, data => '&'.$value, |
| 2447 |
|
line => $l, column => $c, |
| 2448 |
|
}; |
| 2449 |
} |
} |
| 2450 |
} else { |
} else { |
| 2451 |
!!!cp (1027); |
!!!cp (1027); |
| 2452 |
## no characters are consumed |
## no characters are consumed |
| 2453 |
!!!parse-error (type => 'bare ero'); |
!!!parse-error (type => 'bare ero', line => $l, column => $c); |
| 2454 |
return undef; |
return undef; |
| 2455 |
} |
} |
| 2456 |
} # _tokenize_attempt_to_consume_an_entity |
} # _tokenize_attempt_to_consume_an_entity |
| 2488 |
|
|
| 2489 |
!!!next-token; |
!!!next-token; |
| 2490 |
|
|
|
$self->{insertion_mode} = BEFORE_HEAD_IM; |
|
| 2491 |
undef $self->{form_element}; |
undef $self->{form_element}; |
| 2492 |
undef $self->{head_element}; |
undef $self->{head_element}; |
| 2493 |
$self->{open_elements} = []; |
$self->{open_elements} = []; |
| 2494 |
undef $self->{inner_html_node}; |
undef $self->{inner_html_node}; |
| 2495 |
|
|
| 2496 |
|
## NOTE: The "initial" insertion mode. |
| 2497 |
$self->_tree_construction_initial; # MUST |
$self->_tree_construction_initial; # MUST |
| 2498 |
|
|
| 2499 |
|
## NOTE: The "before html" insertion mode. |
| 2500 |
$self->_tree_construction_root_element; |
$self->_tree_construction_root_element; |
| 2501 |
|
$self->{insertion_mode} = BEFORE_HEAD_IM; |
| 2502 |
|
|
| 2503 |
|
## NOTE: The "before head" insertion mode and so on. |
| 2504 |
$self->_tree_construction_main; |
$self->_tree_construction_main; |
| 2505 |
} # _construct_tree |
} # _construct_tree |
| 2506 |
|
|
| 2507 |
sub _tree_construction_initial ($) { |
sub _tree_construction_initial ($) { |
| 2508 |
my $self = shift; |
my $self = shift; |
| 2509 |
|
|
| 2510 |
|
## NOTE: "initial" insertion mode |
| 2511 |
|
|
| 2512 |
INITIAL: { |
INITIAL: { |
| 2513 |
if ($token->{type} == DOCTYPE_TOKEN) { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 2514 |
## NOTE: Conformance checkers MAY, instead of reporting "not HTML5" |
## NOTE: Conformance checkers MAY, instead of reporting "not HTML5" |
| 2521 |
defined $token->{public_identifier} or |
defined $token->{public_identifier} or |
| 2522 |
defined $token->{system_identifier}) { |
defined $token->{system_identifier}) { |
| 2523 |
!!!cp ('t1'); |
!!!cp ('t1'); |
| 2524 |
!!!parse-error (type => 'not HTML5'); |
!!!parse-error (type => 'not HTML5', token => $token); |
| 2525 |
} elsif ($doctype_name ne 'HTML') { |
} elsif ($doctype_name ne 'HTML') { |
| 2526 |
!!!cp ('t2'); |
!!!cp ('t2'); |
| 2527 |
## ISSUE: ASCII case-insensitive? (in fact it does not matter) |
## ISSUE: ASCII case-insensitive? (in fact it does not matter) |
| 2528 |
!!!parse-error (type => 'not HTML5'); |
!!!parse-error (type => 'not HTML5', token => $token); |
| 2529 |
} else { |
} else { |
| 2530 |
!!!cp ('t3'); |
!!!cp ('t3'); |
| 2531 |
} |
} |
| 2655 |
!!!cp ('t13'); |
!!!cp ('t13'); |
| 2656 |
} |
} |
| 2657 |
|
|
| 2658 |
## Go to the root element phase. |
## Go to the "before html" insertion mode. |
| 2659 |
!!!next-token; |
!!!next-token; |
| 2660 |
return; |
return; |
| 2661 |
} elsif ({ |
} elsif ({ |
| 2664 |
END_OF_FILE_TOKEN, 1, |
END_OF_FILE_TOKEN, 1, |
| 2665 |
}->{$token->{type}}) { |
}->{$token->{type}}) { |
| 2666 |
!!!cp ('t14'); |
!!!cp ('t14'); |
| 2667 |
!!!parse-error (type => 'no DOCTYPE'); |
!!!parse-error (type => 'no DOCTYPE', token => $token); |
| 2668 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 2669 |
## Go to the root element phase |
## Go to the "before html" insertion mode. |
| 2670 |
## reprocess |
## reprocess |
| 2671 |
return; |
return; |
| 2672 |
} elsif ($token->{type} == CHARACTER_TOKEN) { |
} elsif ($token->{type} == CHARACTER_TOKEN) { |
| 2675 |
|
|
| 2676 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 2677 |
!!!cp ('t15'); |
!!!cp ('t15'); |
| 2678 |
## Stay in the phase |
## Stay in the insertion mode. |
| 2679 |
!!!next-token; |
!!!next-token; |
| 2680 |
redo INITIAL; |
redo INITIAL; |
| 2681 |
} else { |
} else { |
| 2685 |
!!!cp ('t17'); |
!!!cp ('t17'); |
| 2686 |
} |
} |
| 2687 |
|
|
| 2688 |
!!!parse-error (type => 'no DOCTYPE'); |
!!!parse-error (type => 'no DOCTYPE', token => $token); |
| 2689 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 2690 |
## Go to the root element phase |
## Go to the "before html" insertion mode. |
| 2691 |
## reprocess |
## reprocess |
| 2692 |
return; |
return; |
| 2693 |
} elsif ($token->{type} == COMMENT_TOKEN) { |
} elsif ($token->{type} == COMMENT_TOKEN) { |
| 2695 |
my $comment = $self->{document}->create_comment ($token->{data}); |
my $comment = $self->{document}->create_comment ($token->{data}); |
| 2696 |
$self->{document}->append_child ($comment); |
$self->{document}->append_child ($comment); |
| 2697 |
|
|
| 2698 |
## Stay in the phase. |
## Stay in the insertion mode. |
| 2699 |
!!!next-token; |
!!!next-token; |
| 2700 |
redo INITIAL; |
redo INITIAL; |
| 2701 |
} else { |
} else { |
| 2708 |
|
|
| 2709 |
sub _tree_construction_root_element ($) { |
sub _tree_construction_root_element ($) { |
| 2710 |
my $self = shift; |
my $self = shift; |
| 2711 |
|
|
| 2712 |
|
## NOTE: "before html" insertion mode. |
| 2713 |
|
|
| 2714 |
B: { |
B: { |
| 2715 |
if ($token->{type} == DOCTYPE_TOKEN) { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 2716 |
!!!cp ('t19'); |
!!!cp ('t19'); |
| 2717 |
!!!parse-error (type => 'in html:#DOCTYPE'); |
!!!parse-error (type => 'in html:#DOCTYPE', token => $token); |
| 2718 |
## Ignore the token |
## Ignore the token |
| 2719 |
## Stay in the phase |
## Stay in the insertion mode. |
| 2720 |
!!!next-token; |
!!!next-token; |
| 2721 |
redo B; |
redo B; |
| 2722 |
} elsif ($token->{type} == COMMENT_TOKEN) { |
} elsif ($token->{type} == COMMENT_TOKEN) { |
| 2723 |
!!!cp ('t20'); |
!!!cp ('t20'); |
| 2724 |
my $comment = $self->{document}->create_comment ($token->{data}); |
my $comment = $self->{document}->create_comment ($token->{data}); |
| 2725 |
$self->{document}->append_child ($comment); |
$self->{document}->append_child ($comment); |
| 2726 |
## Stay in the phase |
## Stay in the insertion mode. |
| 2727 |
!!!next-token; |
!!!next-token; |
| 2728 |
redo B; |
redo B; |
| 2729 |
} elsif ($token->{type} == CHARACTER_TOKEN) { |
} elsif ($token->{type} == CHARACTER_TOKEN) { |
| 2732 |
|
|
| 2733 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 2734 |
!!!cp ('t21'); |
!!!cp ('t21'); |
| 2735 |
## Stay in the phase |
## Stay in the insertion mode. |
| 2736 |
!!!next-token; |
!!!next-token; |
| 2737 |
redo B; |
redo B; |
| 2738 |
} else { |
} else { |
| 2746 |
|
|
| 2747 |
# |
# |
| 2748 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 2749 |
if ($token->{tag_name} eq 'html' and |
if ($token->{tag_name} eq 'html') { |
| 2750 |
$token->{attributes}->{manifest}) { |
my $root_element; |
| 2751 |
!!!cp ('t24'); |
!!!create-element ($root_element, $token->{tag_name}, $token->{attributes}, $token); |
| 2752 |
$self->{application_cache_selection} |
$self->{document}->append_child ($root_element); |
| 2753 |
->($token->{attributes}->{manifest}->{value}); |
push @{$self->{open_elements}}, [$root_element, 'html']; |
| 2754 |
## ISSUE: No relative reference resolution? |
|
| 2755 |
|
if ($token->{attributes}->{manifest}) { |
| 2756 |
|
!!!cp ('t24'); |
| 2757 |
|
$self->{application_cache_selection} |
| 2758 |
|
->($token->{attributes}->{manifest}->{value}); |
| 2759 |
|
## ISSUE: Spec is unclear on relative references. |
| 2760 |
|
## According to Hixie (#whatwg 2008-03-19), it should be |
| 2761 |
|
## resolved against the base URI of the document in HTML |
| 2762 |
|
## or xml:base of the element in XHTML. |
| 2763 |
|
} else { |
| 2764 |
|
!!!cp ('t25'); |
| 2765 |
|
$self->{application_cache_selection}->(undef); |
| 2766 |
|
} |
| 2767 |
|
|
| 2768 |
|
!!!next-token; |
| 2769 |
|
return; ## Go to the "before head" insertion mode. |
| 2770 |
} else { |
} else { |
| 2771 |
!!!cp ('t25'); |
!!!cp ('t25.1'); |
| 2772 |
$self->{application_cache_selection}->(undef); |
# |
| 2773 |
} |
} |
|
|
|
|
## ISSUE: There is an issue in the spec |
|
|
# |
|
| 2774 |
} elsif ({ |
} elsif ({ |
| 2775 |
END_TAG_TOKEN, 1, |
END_TAG_TOKEN, 1, |
| 2776 |
END_OF_FILE_TOKEN, 1, |
END_OF_FILE_TOKEN, 1, |
| 2777 |
}->{$token->{type}}) { |
}->{$token->{type}}) { |
| 2778 |
!!!cp ('t26'); |
!!!cp ('t26'); |
|
$self->{application_cache_selection}->(undef); |
|
|
|
|
|
## ISSUE: There is an issue in the spec |
|
| 2779 |
# |
# |
| 2780 |
} else { |
} else { |
| 2781 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 2782 |
} |
} |
| 2783 |
|
|
| 2784 |
my $root_element; !!!create-element ($root_element, 'html'); |
my $root_element; !!!create-element ($root_element, 'html',, $token); |
| 2785 |
$self->{document}->append_child ($root_element); |
$self->{document}->append_child ($root_element); |
| 2786 |
push @{$self->{open_elements}}, [$root_element, 'html']; |
push @{$self->{open_elements}}, [$root_element, 'html']; |
| 2787 |
## reprocess |
|
| 2788 |
#redo B; |
$self->{application_cache_selection}->(undef); |
| 2789 |
return; ## Go to the main phase. |
|
| 2790 |
|
## NOTE: Reprocess the token. |
| 2791 |
|
return; ## Go to the "before head" insertion mode. |
| 2792 |
|
|
| 2793 |
|
## ISSUE: There is an issue in the spec |
| 2794 |
} # B |
} # B |
| 2795 |
|
|
| 2796 |
die "$0: _tree_construction_root_element: This should never be reached"; |
die "$0: _tree_construction_root_element: This should never be reached"; |
| 2808 |
|
|
| 2809 |
## Step 3 |
## Step 3 |
| 2810 |
S3: { |
S3: { |
|
## ISSUE: Oops! "If node is the first node in the stack of open |
|
|
## elements, then set last to true. If the context element of the |
|
|
## HTML fragment parsing algorithm is neither a td element nor a |
|
|
## th element, then set node to the context element. (fragment case)": |
|
|
## The second "if" is in the scope of the first "if"!? |
|
| 2811 |
if ($self->{open_elements}->[0]->[0] eq $node->[0]) { |
if ($self->{open_elements}->[0]->[0] eq $node->[0]) { |
| 2812 |
$last = 1; |
$last = 1; |
| 2813 |
if (defined $self->{inner_html_node}) { |
if (defined $self->{inner_html_node}) { |
| 2968 |
!!!cp ('t39'); |
!!!cp ('t39'); |
| 2969 |
}; # $clear_up_to_marker |
}; # $clear_up_to_marker |
| 2970 |
|
|
| 2971 |
my $parse_rcdata = sub ($$) { |
my $insert; |
| 2972 |
my ($content_model_flag, $insert) = @_; |
|
| 2973 |
|
my $parse_rcdata = sub ($) { |
| 2974 |
|
my ($content_model_flag) = @_; |
| 2975 |
|
|
| 2976 |
## Step 1 |
## Step 1 |
| 2977 |
my $start_tag_name = $token->{tag_name}; |
my $start_tag_name = $token->{tag_name}; |
| 2978 |
my $el; |
my $el; |
| 2979 |
!!!create-element ($el, $start_tag_name, $token->{attributes}); |
!!!create-element ($el, $start_tag_name, $token->{attributes}, $token); |
| 2980 |
|
|
| 2981 |
## Step 2 |
## Step 2 |
| 2982 |
$insert->($el); # /context node/->append_child ($el) |
$insert->($el); |
| 2983 |
|
|
| 2984 |
## Step 3 |
## Step 3 |
| 2985 |
$self->{content_model} = $content_model_flag; # CDATA or RCDATA |
$self->{content_model} = $content_model_flag; # CDATA or RCDATA |
| 3009 |
$token->{tag_name} eq $start_tag_name) { |
$token->{tag_name} eq $start_tag_name) { |
| 3010 |
!!!cp ('t42'); |
!!!cp ('t42'); |
| 3011 |
## 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}); |
|
| 3012 |
} else { |
} else { |
| 3013 |
die "$0: $content_model_flag in parse_rcdata"; |
## NOTE: An end-of-file token. |
| 3014 |
|
if ($content_model_flag == CDATA_CONTENT_MODEL) { |
| 3015 |
|
!!!cp ('t43'); |
| 3016 |
|
!!!parse-error (type => 'in CDATA:#'.$token->{type}, token => $token); |
| 3017 |
|
} elsif ($content_model_flag == RCDATA_CONTENT_MODEL) { |
| 3018 |
|
!!!cp ('t44'); |
| 3019 |
|
!!!parse-error (type => 'in RCDATA:#'.$token->{type}, token => $token); |
| 3020 |
|
} else { |
| 3021 |
|
die "$0: $content_model_flag in parse_rcdata"; |
| 3022 |
|
} |
| 3023 |
} |
} |
| 3024 |
!!!next-token; |
!!!next-token; |
| 3025 |
}; # $parse_rcdata |
}; # $parse_rcdata |
| 3026 |
|
|
| 3027 |
my $script_start_tag = sub ($) { |
my $script_start_tag = sub () { |
|
my $insert = $_[0]; |
|
| 3028 |
my $script_el; |
my $script_el; |
| 3029 |
!!!create-element ($script_el, 'script', $token->{attributes}); |
!!!create-element ($script_el, 'script', $token->{attributes}, $token); |
| 3030 |
## TODO: mark as "parser-inserted" |
## TODO: mark as "parser-inserted" |
| 3031 |
|
|
| 3032 |
$self->{content_model} = CDATA_CONTENT_MODEL; |
$self->{content_model} = CDATA_CONTENT_MODEL; |
| 3052 |
## Ignore the token |
## Ignore the token |
| 3053 |
} else { |
} else { |
| 3054 |
!!!cp ('t48'); |
!!!cp ('t48'); |
| 3055 |
!!!parse-error (type => 'in CDATA:#'.$token->{type}); |
!!!parse-error (type => 'in CDATA:#'.$token->{type}, token => $token); |
| 3056 |
## ISSUE: And ignore? |
## ISSUE: And ignore? |
| 3057 |
## TODO: mark as "already executed" |
## TODO: mark as "already executed" |
| 3058 |
} |
} |
| 3075 |
!!!next-token; |
!!!next-token; |
| 3076 |
}; # $script_start_tag |
}; # $script_start_tag |
| 3077 |
|
|
| 3078 |
|
## NOTE: $open_tables->[-1]->[0] is the "current table" element node. |
| 3079 |
|
## NOTE: $open_tables->[-1]->[1] is the "tainted" flag. |
| 3080 |
|
my $open_tables = [[$self->{open_elements}->[0]->[0]]]; |
| 3081 |
|
|
| 3082 |
my $formatting_end_tag = sub { |
my $formatting_end_tag = sub { |
| 3083 |
my $tag_name = shift; |
my $end_tag_token = shift; |
| 3084 |
|
my $tag_name = $end_tag_token->{tag_name}; |
| 3085 |
|
|
| 3086 |
|
## NOTE: The adoption agency algorithm (AAA). |
| 3087 |
|
|
| 3088 |
FET: { |
FET: { |
| 3089 |
## Step 1 |
## Step 1 |
| 3102 |
} # AFE |
} # AFE |
| 3103 |
unless (defined $formatting_element) { |
unless (defined $formatting_element) { |
| 3104 |
!!!cp ('t53'); |
!!!cp ('t53'); |
| 3105 |
!!!parse-error (type => 'unmatched end tag:'.$tag_name); |
!!!parse-error (type => 'unmatched end tag:'.$tag_name, token => $end_tag_token); |
| 3106 |
## Ignore the token |
## Ignore the token |
| 3107 |
!!!next-token; |
!!!next-token; |
| 3108 |
return; |
return; |
| 3119 |
last INSCOPE; |
last INSCOPE; |
| 3120 |
} else { # in open elements but not in scope |
} else { # in open elements but not in scope |
| 3121 |
!!!cp ('t55'); |
!!!cp ('t55'); |
| 3122 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, |
| 3123 |
|
token => $end_tag_token); |
| 3124 |
## Ignore the token |
## Ignore the token |
| 3125 |
!!!next-token; |
!!!next-token; |
| 3126 |
return; |
return; |
| 3127 |
} |
} |
| 3128 |
} elsif ({ |
} elsif ({ |
| 3129 |
table => 1, caption => 1, td => 1, th => 1, |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 3130 |
button => 1, marquee => 1, object => 1, html => 1, |
button => 1, marquee => 1, object => 1, html => 1, |
| 3131 |
}->{$node->[1]}) { |
}->{$node->[1]}) { |
| 3132 |
!!!cp ('t56'); |
!!!cp ('t56'); |
| 3135 |
} # INSCOPE |
} # INSCOPE |
| 3136 |
unless (defined $formatting_element_i_in_open) { |
unless (defined $formatting_element_i_in_open) { |
| 3137 |
!!!cp ('t57'); |
!!!cp ('t57'); |
| 3138 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, |
| 3139 |
|
token => $end_tag_token); |
| 3140 |
pop @$active_formatting_elements; # $formatting_element |
pop @$active_formatting_elements; # $formatting_element |
| 3141 |
!!!next-token; ## TODO: ok? |
!!!next-token; ## TODO: ok? |
| 3142 |
return; |
return; |
| 3143 |
} |
} |
| 3144 |
if (not $self->{open_elements}->[-1]->[0] eq $formatting_element->[0]) { |
if (not $self->{open_elements}->[-1]->[0] eq $formatting_element->[0]) { |
| 3145 |
!!!cp ('t58'); |
!!!cp ('t58'); |
| 3146 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], |
| 3147 |
|
token => $end_tag_token); |
| 3148 |
} |
} |
| 3149 |
|
|
| 3150 |
## Step 2 |
## Step 2 |
| 3155 |
if (not $formatting_category->{$node->[1]} and |
if (not $formatting_category->{$node->[1]} and |
| 3156 |
#not $phrasing_category->{$node->[1]} and |
#not $phrasing_category->{$node->[1]} and |
| 3157 |
($special_category->{$node->[1]} or |
($special_category->{$node->[1]} or |
| 3158 |
$scoping_category->{$node->[1]})) { |
$scoping_category->{$node->[1]})) { ## Scoping is redundant, maybe |
| 3159 |
!!!cp ('t59'); |
!!!cp ('t59'); |
| 3160 |
$furthest_block = $node; |
$furthest_block = $node; |
| 3161 |
$furthest_block_i_in_open = $_; |
$furthest_block_i_in_open = $_; |
| 3241 |
} # S7 |
} # S7 |
| 3242 |
|
|
| 3243 |
## Step 8 |
## Step 8 |
| 3244 |
$common_ancestor_node->[0]->append_child ($last_node->[0]); |
if ({ |
| 3245 |
|
table => 1, tbody => 1, tfoot => 1, thead => 1, tr => 1, |
| 3246 |
|
}->{$common_ancestor_node->[1]}) { |
| 3247 |
|
my $foster_parent_element; |
| 3248 |
|
my $next_sibling; |
| 3249 |
|
OE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3250 |
|
if ($self->{open_elements}->[$_]->[1] eq 'table') { |
| 3251 |
|
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
| 3252 |
|
if (defined $parent and $parent->node_type == 1) { |
| 3253 |
|
!!!cp ('t65.1'); |
| 3254 |
|
$foster_parent_element = $parent; |
| 3255 |
|
$next_sibling = $self->{open_elements}->[$_]->[0]; |
| 3256 |
|
} else { |
| 3257 |
|
!!!cp ('t65.2'); |
| 3258 |
|
$foster_parent_element |
| 3259 |
|
= $self->{open_elements}->[$_ - 1]->[0]; |
| 3260 |
|
} |
| 3261 |
|
last OE; |
| 3262 |
|
} |
| 3263 |
|
} # OE |
| 3264 |
|
$foster_parent_element = $self->{open_elements}->[0]->[0] |
| 3265 |
|
unless defined $foster_parent_element; |
| 3266 |
|
$foster_parent_element->insert_before ($last_node->[0], $next_sibling); |
| 3267 |
|
$open_tables->[-1]->[1] = 1; # tainted |
| 3268 |
|
} else { |
| 3269 |
|
!!!cp ('t65.3'); |
| 3270 |
|
$common_ancestor_node->[0]->append_child ($last_node->[0]); |
| 3271 |
|
} |
| 3272 |
|
|
| 3273 |
## Step 9 |
## Step 9 |
| 3274 |
my $clone = [$formatting_element->[0]->clone_node (0), |
my $clone = [$formatting_element->[0]->clone_node (0), |
| 3314 |
} # FET |
} # FET |
| 3315 |
}; # $formatting_end_tag |
}; # $formatting_end_tag |
| 3316 |
|
|
| 3317 |
my $insert_to_current = sub { |
$insert = my $insert_to_current = sub { |
| 3318 |
$self->{open_elements}->[-1]->[0]->append_child ($_[0]); |
$self->{open_elements}->[-1]->[0]->append_child ($_[0]); |
| 3319 |
}; # $insert_to_current |
}; # $insert_to_current |
| 3320 |
|
|
| 3321 |
my $insert_to_foster = sub { |
my $insert_to_foster = sub { |
| 3322 |
my $child = shift; |
my $child = shift; |
| 3323 |
if ({ |
if ({ |
| 3324 |
table => 1, tbody => 1, tfoot => 1, |
table => 1, tbody => 1, tfoot => 1, thead => 1, tr => 1, |
| 3325 |
thead => 1, tr => 1, |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3326 |
}->{$self->{open_elements}->[-1]->[1]}) { |
# MUST |
| 3327 |
# MUST |
my $foster_parent_element; |
| 3328 |
my $foster_parent_element; |
my $next_sibling; |
|
my $next_sibling; |
|
| 3329 |
OE: for (reverse 0..$#{$self->{open_elements}}) { |
OE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3330 |
if ($self->{open_elements}->[$_]->[1] eq 'table') { |
if ($self->{open_elements}->[$_]->[1] eq 'table') { |
| 3331 |
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
| 3345 |
unless defined $foster_parent_element; |
unless defined $foster_parent_element; |
| 3346 |
$foster_parent_element->insert_before |
$foster_parent_element->insert_before |
| 3347 |
($child, $next_sibling); |
($child, $next_sibling); |
| 3348 |
} else { |
$open_tables->[-1]->[1] = 1; # tainted |
| 3349 |
!!!cp ('t72'); |
} else { |
| 3350 |
$self->{open_elements}->[-1]->[0]->append_child ($child); |
!!!cp ('t72'); |
| 3351 |
} |
$self->{open_elements}->[-1]->[0]->append_child ($child); |
| 3352 |
|
} |
| 3353 |
}; # $insert_to_foster |
}; # $insert_to_foster |
| 3354 |
|
|
|
my $insert; |
|
|
|
|
| 3355 |
B: { |
B: { |
| 3356 |
if ($token->{type} == DOCTYPE_TOKEN) { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 3357 |
!!!cp ('t73'); |
!!!cp ('t73'); |
| 3358 |
!!!parse-error (type => 'DOCTYPE in the middle'); |
!!!parse-error (type => 'DOCTYPE in the middle', token => $token); |
| 3359 |
## Ignore the token |
## Ignore the token |
| 3360 |
## Stay in the phase |
## Stay in the phase |
| 3361 |
!!!next-token; |
!!!next-token; |
| 3362 |
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; |
|
| 3363 |
} elsif ($token->{type} == START_TAG_TOKEN and |
} elsif ($token->{type} == START_TAG_TOKEN and |
| 3364 |
$token->{tag_name} eq 'html') { |
$token->{tag_name} eq 'html') { |
| 3365 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 3366 |
!!!cp ('t79'); |
!!!cp ('t79'); |
| 3367 |
## Turn into the main phase |
!!!parse-error (type => 'after html:html', token => $token); |
|
!!!parse-error (type => 'after html:html'); |
|
| 3368 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 3369 |
} elsif ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 3370 |
!!!cp ('t80'); |
!!!cp ('t80'); |
| 3371 |
## Turn into the main phase |
!!!parse-error (type => 'after html:html', token => $token); |
|
!!!parse-error (type => 'after html:html'); |
|
| 3372 |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 3373 |
} else { |
} else { |
| 3374 |
!!!cp ('t81'); |
!!!cp ('t81'); |
| 3375 |
} |
} |
| 3376 |
|
|
| 3377 |
## ISSUE: "aa<html>" is not a parse error. |
!!!cp ('t82'); |
| 3378 |
## ISSUE: "<html>" in fragment is not a parse error. |
!!!parse-error (type => 'not first start tag', token => $token); |
|
unless ($token->{first_start_tag}) { |
|
|
!!!cp ('t82'); |
|
|
!!!parse-error (type => 'not first start tag'); |
|
|
} else { |
|
|
!!!cp ('t83'); |
|
|
} |
|
| 3379 |
my $top_el = $self->{open_elements}->[0]->[0]; |
my $top_el = $self->{open_elements}->[0]->[0]; |
| 3380 |
for my $attr_name (keys %{$token->{attributes}}) { |
for my $attr_name (keys %{$token->{attributes}}) { |
| 3381 |
unless ($top_el->has_attribute_ns (undef, $attr_name)) { |
unless ($top_el->has_attribute_ns (undef, $attr_name)) { |
| 3404 |
} elsif ($self->{insertion_mode} & HEAD_IMS) { |
} elsif ($self->{insertion_mode} & HEAD_IMS) { |
| 3405 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 3406 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 3407 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
unless ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3408 |
|
!!!cp ('t88.2'); |
| 3409 |
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 3410 |
|
} else { |
| 3411 |
|
!!!cp ('t88.1'); |
| 3412 |
|
## Ignore the token. |
| 3413 |
|
!!!next-token; |
| 3414 |
|
redo B; |
| 3415 |
|
} |
| 3416 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 3417 |
!!!cp ('t88'); |
!!!cp ('t88'); |
| 3418 |
!!!next-token; |
!!!next-token; |
| 3423 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3424 |
!!!cp ('t89'); |
!!!cp ('t89'); |
| 3425 |
## As if <head> |
## As if <head> |
| 3426 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, 'head',, $token); |
| 3427 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 3428 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3429 |
|
|
| 3435 |
!!!cp ('t90'); |
!!!cp ('t90'); |
| 3436 |
## As if </noscript> |
## As if </noscript> |
| 3437 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3438 |
!!!parse-error (type => 'in noscript:#character'); |
!!!parse-error (type => 'in noscript:#character', token => $token); |
| 3439 |
|
|
| 3440 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 3441 |
## As if </head> |
## As if </head> |
| 3453 |
|
|
| 3454 |
## "after head" insertion mode |
## "after head" insertion mode |
| 3455 |
## As if <body> |
## As if <body> |
| 3456 |
!!!insert-element ('body'); |
!!!insert-element ('body',, $token); |
| 3457 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 3458 |
## reprocess |
## reprocess |
| 3459 |
redo B; |
redo B; |
| 3461 |
if ($token->{tag_name} eq 'head') { |
if ($token->{tag_name} eq 'head') { |
| 3462 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3463 |
!!!cp ('t93'); |
!!!cp ('t93'); |
| 3464 |
!!!create-element ($self->{head_element}, $token->{tag_name}, $token->{attributes}); |
!!!create-element ($self->{head_element}, $token->{tag_name}, $token->{attributes}, $token); |
| 3465 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 3466 |
push @{$self->{open_elements}}, [$self->{head_element}, $token->{tag_name}]; |
push @{$self->{open_elements}}, [$self->{head_element}, $token->{tag_name}]; |
| 3467 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 3472 |
# |
# |
| 3473 |
} else { |
} else { |
| 3474 |
!!!cp ('t95'); |
!!!cp ('t95'); |
| 3475 |
!!!parse-error (type => 'in head:head'); # or in head noscript |
!!!parse-error (type => 'in head:head', token => $token); # or in head noscript |
| 3476 |
## Ignore the token |
## Ignore the token |
| 3477 |
!!!next-token; |
!!!next-token; |
| 3478 |
redo B; |
redo B; |
| 3480 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3481 |
!!!cp ('t96'); |
!!!cp ('t96'); |
| 3482 |
## As if <head> |
## As if <head> |
| 3483 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, 'head',, $token); |
| 3484 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 3485 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3486 |
|
|
| 3495 |
!!!cp ('t98'); |
!!!cp ('t98'); |
| 3496 |
## As if </noscript> |
## As if </noscript> |
| 3497 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3498 |
!!!parse-error (type => 'in noscript:base'); |
!!!parse-error (type => 'in noscript:base', token => $token); |
| 3499 |
|
|
| 3500 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 3501 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 3506 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 3507 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 3508 |
!!!cp ('t100'); |
!!!cp ('t100'); |
| 3509 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
| 3510 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3511 |
} else { |
} else { |
| 3512 |
!!!cp ('t101'); |
!!!cp ('t101'); |
| 3513 |
} |
} |
| 3514 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 3515 |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 3516 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} # <head> |
| 3517 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 3518 |
!!!next-token; |
!!!next-token; |
| 3519 |
redo B; |
redo B; |
| 3521 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 3522 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 3523 |
!!!cp ('t102'); |
!!!cp ('t102'); |
| 3524 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
| 3525 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3526 |
} else { |
} else { |
| 3527 |
!!!cp ('t103'); |
!!!cp ('t103'); |
| 3528 |
} |
} |
| 3529 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 3530 |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 3531 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} # <head> |
| 3532 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 3533 |
!!!next-token; |
!!!next-token; |
| 3534 |
redo B; |
redo B; |
| 3536 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 3537 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 3538 |
!!!cp ('t104'); |
!!!cp ('t104'); |
| 3539 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
| 3540 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3541 |
} else { |
} else { |
| 3542 |
!!!cp ('t105'); |
!!!cp ('t105'); |
| 3543 |
} |
} |
| 3544 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 3545 |
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. |
| 3546 |
|
|
| 3547 |
unless ($self->{confident}) { |
unless ($self->{confident}) { |
| 3548 |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
| 3549 |
!!!cp ('t106'); |
!!!cp ('t106'); |
| 3550 |
$self->{change_encoding} |
$self->{change_encoding} |
| 3551 |
->($self, $token->{attributes}->{charset}->{value}); |
->($self, $token->{attributes}->{charset}->{value}, |
| 3552 |
|
$token); |
| 3553 |
|
|
| 3554 |
$meta_el->[0]->get_attribute_node_ns (undef, 'charset') |
$meta_el->[0]->get_attribute_node_ns (undef, 'charset') |
| 3555 |
->set_user_data (manakai_has_reference => |
->set_user_data (manakai_has_reference => |
| 3564 |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
| 3565 |
!!!cp ('t107'); |
!!!cp ('t107'); |
| 3566 |
$self->{change_encoding} |
$self->{change_encoding} |
| 3567 |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3); |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3, |
| 3568 |
|
$token); |
| 3569 |
$meta_el->[0]->get_attribute_node_ns (undef, 'content') |
$meta_el->[0]->get_attribute_node_ns (undef, 'content') |
| 3570 |
->set_user_data (manakai_has_reference => |
->set_user_data (manakai_has_reference => |
| 3571 |
$token->{attributes}->{content} |
$token->{attributes}->{content} |
| 3591 |
} |
} |
| 3592 |
} |
} |
| 3593 |
|
|
| 3594 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} # <head> |
| 3595 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 3596 |
!!!next-token; |
!!!next-token; |
| 3597 |
redo B; |
redo B; |
| 3600 |
!!!cp ('t111'); |
!!!cp ('t111'); |
| 3601 |
## As if </noscript> |
## As if </noscript> |
| 3602 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3603 |
!!!parse-error (type => 'in noscript:title'); |
!!!parse-error (type => 'in noscript:title', token => $token); |
| 3604 |
|
|
| 3605 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 3606 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 3607 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 3608 |
!!!cp ('t112'); |
!!!cp ('t112'); |
| 3609 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
| 3610 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3611 |
} else { |
} else { |
| 3612 |
!!!cp ('t113'); |
!!!cp ('t113'); |
| 3615 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 3616 |
my $parent = defined $self->{head_element} ? $self->{head_element} |
my $parent = defined $self->{head_element} ? $self->{head_element} |
| 3617 |
: $self->{open_elements}->[-1]->[0]; |
: $self->{open_elements}->[-1]->[0]; |
| 3618 |
$parse_rcdata->(RCDATA_CONTENT_MODEL, |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
| 3619 |
sub { $parent->append_child ($_[0]) }); |
pop @{$self->{open_elements}} # <head> |
|
pop @{$self->{open_elements}} |
|
| 3620 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 3621 |
redo B; |
redo B; |
| 3622 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($token->{tag_name} eq 'style') { |
| 3625 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 3626 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 3627 |
!!!cp ('t114'); |
!!!cp ('t114'); |
| 3628 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
| 3629 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3630 |
} else { |
} else { |
| 3631 |
!!!cp ('t115'); |
!!!cp ('t115'); |
| 3632 |
} |
} |
| 3633 |
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert_to_current); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 3634 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} # <head> |
| 3635 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 3636 |
redo B; |
redo B; |
| 3637 |
} elsif ($token->{tag_name} eq 'noscript') { |
} elsif ($token->{tag_name} eq 'noscript') { |
| 3638 |
if ($self->{insertion_mode} == IN_HEAD_IM) { |
if ($self->{insertion_mode} == IN_HEAD_IM) { |
| 3639 |
!!!cp ('t116'); |
!!!cp ('t116'); |
| 3640 |
## NOTE: and scripting is disalbed |
## NOTE: and scripting is disalbed |
| 3641 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 3642 |
$self->{insertion_mode} = IN_HEAD_NOSCRIPT_IM; |
$self->{insertion_mode} = IN_HEAD_NOSCRIPT_IM; |
| 3643 |
!!!next-token; |
!!!next-token; |
| 3644 |
redo B; |
redo B; |
| 3645 |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 3646 |
!!!cp ('t117'); |
!!!cp ('t117'); |
| 3647 |
!!!parse-error (type => 'in noscript:noscript'); |
!!!parse-error (type => 'in noscript:noscript', token => $token); |
| 3648 |
## Ignore the token |
## Ignore the token |
| 3649 |
!!!next-token; |
!!!next-token; |
| 3650 |
redo B; |
redo B; |
| 3657 |
!!!cp ('t119'); |
!!!cp ('t119'); |
| 3658 |
## As if </noscript> |
## As if </noscript> |
| 3659 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3660 |
!!!parse-error (type => 'in noscript:script'); |
!!!parse-error (type => 'in noscript:script', token => $token); |
| 3661 |
|
|
| 3662 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 3663 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 3664 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 3665 |
!!!cp ('t120'); |
!!!cp ('t120'); |
| 3666 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
| 3667 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3668 |
} else { |
} else { |
| 3669 |
!!!cp ('t121'); |
!!!cp ('t121'); |
| 3670 |
} |
} |
| 3671 |
|
|
| 3672 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 3673 |
$script_start_tag->($insert_to_current); |
$script_start_tag->(); |
| 3674 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} # <head> |
| 3675 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 3676 |
redo B; |
redo B; |
| 3677 |
} elsif ($token->{tag_name} eq 'body' or |
} elsif ($token->{tag_name} eq 'body' or |
| 3680 |
!!!cp ('t122'); |
!!!cp ('t122'); |
| 3681 |
## As if </noscript> |
## As if </noscript> |
| 3682 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3683 |
!!!parse-error (type => 'in noscript:'.$token->{tag_name}); |
!!!parse-error (type => 'in noscript:'.$token->{tag_name}, token => $token); |
| 3684 |
|
|
| 3685 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 3686 |
## As if </head> |
## As if </head> |
| 3697 |
} |
} |
| 3698 |
|
|
| 3699 |
## "after head" insertion mode |
## "after head" insertion mode |
| 3700 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 3701 |
if ($token->{tag_name} eq 'body') { |
if ($token->{tag_name} eq 'body') { |
| 3702 |
!!!cp ('t126'); |
!!!cp ('t126'); |
| 3703 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 3718 |
!!!cp ('t129'); |
!!!cp ('t129'); |
| 3719 |
## As if </noscript> |
## As if </noscript> |
| 3720 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3721 |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}); |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}, token => $token); |
| 3722 |
|
|
| 3723 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 3724 |
## As if </head> |
## As if </head> |
| 3737 |
|
|
| 3738 |
## "after head" insertion mode |
## "after head" insertion mode |
| 3739 |
## As if <body> |
## As if <body> |
| 3740 |
!!!insert-element ('body'); |
!!!insert-element ('body',, $token); |
| 3741 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 3742 |
## reprocess |
## reprocess |
| 3743 |
redo B; |
redo B; |
| 3746 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3747 |
!!!cp ('t132'); |
!!!cp ('t132'); |
| 3748 |
## As if <head> |
## As if <head> |
| 3749 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, 'head',, $token); |
| 3750 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 3751 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3752 |
|
|
| 3759 |
!!!cp ('t133'); |
!!!cp ('t133'); |
| 3760 |
## As if </noscript> |
## As if </noscript> |
| 3761 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3762 |
!!!parse-error (type => 'in noscript:/head'); |
!!!parse-error (type => 'in noscript:/head', token => $token); |
| 3763 |
|
|
| 3764 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 3765 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3785 |
redo B; |
redo B; |
| 3786 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3787 |
!!!cp ('t137'); |
!!!cp ('t137'); |
| 3788 |
!!!parse-error (type => 'unmatched end tag:noscript'); |
!!!parse-error (type => 'unmatched end tag:noscript', token => $token); |
| 3789 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 3790 |
!!!next-token; |
!!!next-token; |
| 3791 |
redo B; |
redo B; |
| 3799 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3800 |
!!!cp ('t139'); |
!!!cp ('t139'); |
| 3801 |
## As if <head> |
## As if <head> |
| 3802 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, 'head',, $token); |
| 3803 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 3804 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3805 |
|
|
| 3807 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 3808 |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 3809 |
!!!cp ('t140'); |
!!!cp ('t140'); |
| 3810 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 3811 |
## Ignore the token |
## Ignore the token |
| 3812 |
!!!next-token; |
!!!next-token; |
| 3813 |
redo B; |
redo B; |
| 3822 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3823 |
!!!cp ('t142'); |
!!!cp ('t142'); |
| 3824 |
## As if <head> |
## As if <head> |
| 3825 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, 'head',, $token); |
| 3826 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 3827 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3828 |
|
|
| 3839 |
# |
# |
| 3840 |
} else { |
} else { |
| 3841 |
!!!cp ('t145'); |
!!!cp ('t145'); |
| 3842 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 3843 |
## Ignore the token |
## Ignore the token |
| 3844 |
!!!next-token; |
!!!next-token; |
| 3845 |
redo B; |
redo B; |
| 3850 |
!!!cp ('t146'); |
!!!cp ('t146'); |
| 3851 |
## As if </noscript> |
## As if </noscript> |
| 3852 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3853 |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}); |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}, token => $token); |
| 3854 |
|
|
| 3855 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 3856 |
## As if </head> |
## As if </head> |
| 3866 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3867 |
## ISSUE: This case cannot be reached? |
## ISSUE: This case cannot be reached? |
| 3868 |
!!!cp ('t148'); |
!!!cp ('t148'); |
| 3869 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 3870 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 3871 |
!!!next-token; |
!!!next-token; |
| 3872 |
redo B; |
redo B; |
| 3876 |
|
|
| 3877 |
## "after head" insertion mode |
## "after head" insertion mode |
| 3878 |
## As if <body> |
## As if <body> |
| 3879 |
!!!insert-element ('body'); |
!!!insert-element ('body',, $token); |
| 3880 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 3881 |
## reprocess |
## reprocess |
| 3882 |
redo B; |
redo B; |
| 3883 |
} else { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 3884 |
die "$0: $token->{type}: Unknown token type"; |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3885 |
} |
!!!cp ('t149.1'); |
| 3886 |
|
|
| 3887 |
|
## NOTE: As if <head> |
| 3888 |
|
!!!create-element ($self->{head_element}, 'head',, $token); |
| 3889 |
|
$self->{open_elements}->[-1]->[0]->append_child |
| 3890 |
|
($self->{head_element}); |
| 3891 |
|
#push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3892 |
|
#$self->{insertion_mode} = IN_HEAD_IM; |
| 3893 |
|
## NOTE: Reprocess. |
| 3894 |
|
|
| 3895 |
|
## NOTE: As if </head> |
| 3896 |
|
#pop @{$self->{open_elements}}; |
| 3897 |
|
#$self->{insertion_mode} = IN_AFTER_HEAD_IM; |
| 3898 |
|
## NOTE: Reprocess. |
| 3899 |
|
|
| 3900 |
|
# |
| 3901 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 3902 |
|
!!!cp ('t149.2'); |
| 3903 |
|
|
| 3904 |
|
## NOTE: As if </head> |
| 3905 |
|
pop @{$self->{open_elements}}; |
| 3906 |
|
#$self->{insertion_mode} = IN_AFTER_HEAD_IM; |
| 3907 |
|
## NOTE: Reprocess. |
| 3908 |
|
|
| 3909 |
|
# |
| 3910 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 3911 |
|
!!!cp ('t149.3'); |
| 3912 |
|
|
| 3913 |
|
!!!parse-error (type => 'in noscript:#eof', token => $token); |
| 3914 |
|
|
| 3915 |
|
## As if </noscript> |
| 3916 |
|
pop @{$self->{open_elements}}; |
| 3917 |
|
#$self->{insertion_mode} = IN_HEAD_IM; |
| 3918 |
|
## NOTE: Reprocess. |
| 3919 |
|
|
| 3920 |
|
## NOTE: As if </head> |
| 3921 |
|
pop @{$self->{open_elements}}; |
| 3922 |
|
#$self->{insertion_mode} = IN_AFTER_HEAD_IM; |
| 3923 |
|
## NOTE: Reprocess. |
| 3924 |
|
|
| 3925 |
|
# |
| 3926 |
|
} else { |
| 3927 |
|
!!!cp ('t149.4'); |
| 3928 |
|
# |
| 3929 |
|
} |
| 3930 |
|
|
| 3931 |
|
## NOTE: As if <body> |
| 3932 |
|
!!!insert-element ('body',, $token); |
| 3933 |
|
$self->{insertion_mode} = IN_BODY_IM; |
| 3934 |
|
## NOTE: Reprocess. |
| 3935 |
|
redo B; |
| 3936 |
|
} else { |
| 3937 |
|
die "$0: $token->{type}: Unknown token type"; |
| 3938 |
|
} |
| 3939 |
|
|
| 3940 |
## ISSUE: An issue in the spec. |
## ISSUE: An issue in the spec. |
| 3941 |
} elsif ($self->{insertion_mode} & BODY_IMS) { |
} elsif ($self->{insertion_mode} & BODY_IMS) { |
| 3955 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 3956 |
if ($self->{insertion_mode} == IN_CELL_IM) { |
if ($self->{insertion_mode} == IN_CELL_IM) { |
| 3957 |
## have an element in table scope |
## have an element in table scope |
| 3958 |
my $tn; |
for (reverse 0..$#{$self->{open_elements}}) { |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
| 3959 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 3960 |
if ($node->[1] eq 'td' or $node->[1] eq 'th') { |
if ($node->[1] eq 'td' or $node->[1] eq 'th') { |
| 3961 |
!!!cp ('t151'); |
!!!cp ('t151'); |
| 3962 |
$tn = $node->[1]; |
|
| 3963 |
last INSCOPE; |
## Close the cell |
| 3964 |
|
!!!back-token; # <?> |
| 3965 |
|
$token = {type => END_TAG_TOKEN, tag_name => $node->[1], |
| 3966 |
|
line => $token->{line}, |
| 3967 |
|
column => $token->{column}}; |
| 3968 |
|
redo B; |
| 3969 |
} elsif ({ |
} elsif ({ |
| 3970 |
table => 1, html => 1, |
table => 1, html => 1, |
| 3971 |
}->{$node->[1]}) { |
}->{$node->[1]}) { |
| 3972 |
!!!cp ('t152'); |
!!!cp ('t152'); |
| 3973 |
last INSCOPE; |
## ISSUE: This case can never be reached, maybe. |
| 3974 |
} |
last; |
|
} # INSCOPE |
|
|
unless (defined $tn) { |
|
|
!!!cp ('t153'); |
|
|
## TODO: This error type is wrong. |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
| 3975 |
} |
} |
| 3976 |
|
} |
| 3977 |
!!!cp ('t154'); |
|
| 3978 |
## Close the cell |
!!!cp ('t153'); |
| 3979 |
!!!back-token; # <?> |
!!!parse-error (type => 'start tag not allowed', |
| 3980 |
$token = {type => END_TAG_TOKEN, tag_name => $tn}; |
value => $token->{tag_name}, token => $token); |
| 3981 |
|
## Ignore the token |
| 3982 |
|
!!!next-token; |
| 3983 |
redo B; |
redo B; |
| 3984 |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 3985 |
!!!parse-error (type => 'not closed:caption'); |
!!!parse-error (type => 'not closed:caption', token => $token); |
| 3986 |
|
|
| 3987 |
## As if </caption> |
## NOTE: As if </caption>. |
| 3988 |
## have a table element in table scope |
## have a table element in table scope |
| 3989 |
my $i; |
my $i; |
| 3990 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: { |
| 3991 |
my $node = $self->{open_elements}->[$_]; |
for (reverse 0..$#{$self->{open_elements}}) { |
| 3992 |
if ($node->[1] eq 'caption') { |
my $node = $self->{open_elements}->[$_]; |
| 3993 |
!!!cp ('t155'); |
if ($node->[1] eq 'caption') { |
| 3994 |
$i = $_; |
!!!cp ('t155'); |
| 3995 |
last INSCOPE; |
$i = $_; |
| 3996 |
} elsif ({ |
last INSCOPE; |
| 3997 |
table => 1, html => 1, |
} elsif ({ |
| 3998 |
}->{$node->[1]}) { |
table => 1, html => 1, |
| 3999 |
!!!cp ('t156'); |
}->{$node->[1]}) { |
| 4000 |
last INSCOPE; |
!!!cp ('t156'); |
| 4001 |
|
last; |
| 4002 |
|
} |
| 4003 |
} |
} |
| 4004 |
|
|
| 4005 |
|
!!!cp ('t157'); |
| 4006 |
|
!!!parse-error (type => 'start tag not allowed', |
| 4007 |
|
value => $token->{tag_name}, token => $token); |
| 4008 |
|
## Ignore the token |
| 4009 |
|
!!!next-token; |
| 4010 |
|
redo B; |
| 4011 |
} # 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; |
|
|
} |
|
| 4012 |
|
|
| 4013 |
## generate implied end tags |
## generate implied end tags |
| 4014 |
if ({ |
while ({ |
| 4015 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 4016 |
|
}->{$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]}) { |
|
| 4017 |
!!!cp ('t158'); |
!!!cp ('t158'); |
| 4018 |
!!!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; |
|
| 4019 |
} |
} |
| 4020 |
|
|
| 4021 |
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
| 4022 |
!!!cp ('t159'); |
!!!cp ('t159'); |
| 4023 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 4024 |
} else { |
} else { |
| 4025 |
!!!cp ('t160'); |
!!!cp ('t160'); |
| 4026 |
} |
} |
| 4061 |
} # INSCOPE |
} # INSCOPE |
| 4062 |
unless (defined $i) { |
unless (defined $i) { |
| 4063 |
!!!cp ('t165'); |
!!!cp ('t165'); |
| 4064 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4065 |
## Ignore the token |
## Ignore the token |
| 4066 |
!!!next-token; |
!!!next-token; |
| 4067 |
redo B; |
redo B; |
| 4068 |
} |
} |
| 4069 |
|
|
| 4070 |
## generate implied end tags |
## generate implied end tags |
| 4071 |
if ({ |
while ({ |
| 4072 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 4073 |
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]}) { |
|
| 4074 |
!!!cp ('t166'); |
!!!cp ('t166'); |
| 4075 |
!!!back-token; |
pop @{$self->{open_elements}}; |
|
$token = {type => END_TAG_TOKEN, |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
| 4076 |
} |
} |
| 4077 |
|
|
| 4078 |
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
| 4079 |
!!!cp ('t167'); |
!!!cp ('t167'); |
| 4080 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 4081 |
} else { |
} else { |
| 4082 |
!!!cp ('t168'); |
!!!cp ('t168'); |
| 4083 |
} |
} |
| 4092 |
redo B; |
redo B; |
| 4093 |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 4094 |
!!!cp ('t169'); |
!!!cp ('t169'); |
| 4095 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4096 |
## Ignore the token |
## Ignore the token |
| 4097 |
!!!next-token; |
!!!next-token; |
| 4098 |
redo B; |
redo B; |
| 4104 |
if ($self->{insertion_mode} == IN_CAPTION_IM) { |
if ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 4105 |
## have a table element in table scope |
## have a table element in table scope |
| 4106 |
my $i; |
my $i; |
| 4107 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: { |
| 4108 |
my $node = $self->{open_elements}->[$_]; |
for (reverse 0..$#{$self->{open_elements}}) { |
| 4109 |
if ($node->[1] eq $token->{tag_name}) { |
my $node = $self->{open_elements}->[$_]; |
| 4110 |
!!!cp ('t171'); |
if ($node->[1] eq $token->{tag_name}) { |
| 4111 |
$i = $_; |
!!!cp ('t171'); |
| 4112 |
last INSCOPE; |
$i = $_; |
| 4113 |
} elsif ({ |
last INSCOPE; |
| 4114 |
table => 1, html => 1, |
} elsif ({ |
| 4115 |
}->{$node->[1]}) { |
table => 1, html => 1, |
| 4116 |
!!!cp ('t172'); |
}->{$node->[1]}) { |
| 4117 |
last INSCOPE; |
!!!cp ('t172'); |
| 4118 |
|
last; |
| 4119 |
|
} |
| 4120 |
} |
} |
| 4121 |
|
|
| 4122 |
|
!!!cp ('t173'); |
| 4123 |
|
!!!parse-error (type => 'unmatched end tag', |
| 4124 |
|
value => $token->{tag_name}, token => $token); |
| 4125 |
|
## Ignore the token |
| 4126 |
|
!!!next-token; |
| 4127 |
|
redo B; |
| 4128 |
} # INSCOPE |
} # INSCOPE |
|
unless (defined $i) { |
|
|
!!!cp ('t173'); |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
| 4129 |
|
|
| 4130 |
## generate implied end tags |
## generate implied end tags |
| 4131 |
if ({ |
while ({ |
| 4132 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 4133 |
|
}->{$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]}) { |
|
| 4134 |
!!!cp ('t174'); |
!!!cp ('t174'); |
| 4135 |
!!!back-token; |
pop @{$self->{open_elements}}; |
|
$token = {type => END_TAG_TOKEN, |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
| 4136 |
} |
} |
| 4137 |
|
|
| 4138 |
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
| 4139 |
!!!cp ('t175'); |
!!!cp ('t175'); |
| 4140 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 4141 |
} else { |
} else { |
| 4142 |
!!!cp ('t176'); |
!!!cp ('t176'); |
| 4143 |
} |
} |
| 4152 |
redo B; |
redo B; |
| 4153 |
} elsif ($self->{insertion_mode} == IN_CELL_IM) { |
} elsif ($self->{insertion_mode} == IN_CELL_IM) { |
| 4154 |
!!!cp ('t177'); |
!!!cp ('t177'); |
| 4155 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4156 |
## Ignore the token |
## Ignore the token |
| 4157 |
!!!next-token; |
!!!next-token; |
| 4158 |
redo B; |
redo B; |
| 4168 |
## have an element in table scope |
## have an element in table scope |
| 4169 |
my $i; |
my $i; |
| 4170 |
my $tn; |
my $tn; |
| 4171 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: { |
| 4172 |
my $node = $self->{open_elements}->[$_]; |
for (reverse 0..$#{$self->{open_elements}}) { |
| 4173 |
if ($node->[1] eq $token->{tag_name}) { |
my $node = $self->{open_elements}->[$_]; |
| 4174 |
!!!cp ('t179'); |
if ($node->[1] eq $token->{tag_name}) { |
| 4175 |
$i = $_; |
!!!cp ('t179'); |
| 4176 |
last INSCOPE; |
$i = $_; |
| 4177 |
} elsif ($node->[1] eq 'td' or $node->[1] eq 'th') { |
|
| 4178 |
!!!cp ('t180'); |
## Close the cell |
| 4179 |
$tn = $node->[1]; |
!!!back-token; # </?> |
| 4180 |
## NOTE: There is exactly one |td| or |th| element |
$token = {type => END_TAG_TOKEN, tag_name => $tn, |
| 4181 |
## in scope in the stack of open elements by definition. |
line => $token->{line}, |
| 4182 |
} elsif ({ |
column => $token->{column}}; |
| 4183 |
table => 1, html => 1, |
redo B; |
| 4184 |
}->{$node->[1]}) { |
} elsif ($node->[1] eq 'td' or $node->[1] eq 'th') { |
| 4185 |
!!!cp ('t181'); |
!!!cp ('t180'); |
| 4186 |
last INSCOPE; |
$tn = $node->[1]; |
| 4187 |
|
## NOTE: There is exactly one |td| or |th| element |
| 4188 |
|
## in scope in the stack of open elements by definition. |
| 4189 |
|
} elsif ({ |
| 4190 |
|
table => 1, html => 1, |
| 4191 |
|
}->{$node->[1]}) { |
| 4192 |
|
## ISSUE: Can this be reached? |
| 4193 |
|
!!!cp ('t181'); |
| 4194 |
|
last; |
| 4195 |
|
} |
| 4196 |
} |
} |
| 4197 |
} # INSCOPE |
|
|
unless (defined $i) { |
|
| 4198 |
!!!cp ('t182'); |
!!!cp ('t182'); |
| 4199 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 4200 |
|
value => $token->{tag_name}, token => $token); |
| 4201 |
## Ignore the token |
## Ignore the token |
| 4202 |
!!!next-token; |
!!!next-token; |
| 4203 |
redo B; |
redo B; |
| 4204 |
} else { |
} # INSCOPE |
|
!!!cp ('t183'); |
|
|
} |
|
|
|
|
|
## Close the cell |
|
|
!!!back-token; # </?> |
|
|
$token = {type => END_TAG_TOKEN, tag_name => $tn}; |
|
|
redo B; |
|
| 4205 |
} elsif ($token->{tag_name} eq 'table' and |
} elsif ($token->{tag_name} eq 'table' and |
| 4206 |
$self->{insertion_mode} == IN_CAPTION_IM) { |
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 4207 |
!!!parse-error (type => 'not closed:caption'); |
!!!parse-error (type => 'not closed:caption', token => $token); |
| 4208 |
|
|
| 4209 |
## As if </caption> |
## As if </caption> |
| 4210 |
## have a table element in table scope |
## have a table element in table scope |
| 4224 |
} # INSCOPE |
} # INSCOPE |
| 4225 |
unless (defined $i) { |
unless (defined $i) { |
| 4226 |
!!!cp ('t186'); |
!!!cp ('t186'); |
| 4227 |
!!!parse-error (type => 'unmatched end tag:caption'); |
!!!parse-error (type => 'unmatched end tag:caption', token => $token); |
| 4228 |
## Ignore the token |
## Ignore the token |
| 4229 |
!!!next-token; |
!!!next-token; |
| 4230 |
redo B; |
redo B; |
| 4231 |
} |
} |
| 4232 |
|
|
| 4233 |
## generate implied end tags |
## generate implied end tags |
| 4234 |
if ({ |
while ({ |
| 4235 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 4236 |
|
}->{$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]}) { |
|
| 4237 |
!!!cp ('t187'); |
!!!cp ('t187'); |
| 4238 |
!!!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; |
|
| 4239 |
} |
} |
| 4240 |
|
|
| 4241 |
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
| 4242 |
!!!cp ('t188'); |
!!!cp ('t188'); |
| 4243 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 4244 |
} else { |
} else { |
| 4245 |
!!!cp ('t189'); |
!!!cp ('t189'); |
| 4246 |
} |
} |
| 4258 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 4259 |
if ($self->{insertion_mode} & BODY_TABLE_IMS) { |
if ($self->{insertion_mode} & BODY_TABLE_IMS) { |
| 4260 |
!!!cp ('t190'); |
!!!cp ('t190'); |
| 4261 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4262 |
## Ignore the token |
## Ignore the token |
| 4263 |
!!!next-token; |
!!!next-token; |
| 4264 |
redo B; |
redo B; |
| 4272 |
}->{$token->{tag_name}} and |
}->{$token->{tag_name}} and |
| 4273 |
$self->{insertion_mode} == IN_CAPTION_IM) { |
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 4274 |
!!!cp ('t192'); |
!!!cp ('t192'); |
| 4275 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4276 |
## Ignore the token |
## Ignore the token |
| 4277 |
!!!next-token; |
!!!next-token; |
| 4278 |
redo B; |
redo B; |
| 4280 |
!!!cp ('t193'); |
!!!cp ('t193'); |
| 4281 |
# |
# |
| 4282 |
} |
} |
| 4283 |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 4284 |
|
for my $entry (@{$self->{open_elements}}) { |
| 4285 |
|
if (not { |
| 4286 |
|
dd => 1, dt => 1, li => 1, p => 1, tbody => 1, td => 1, tfoot => 1, |
| 4287 |
|
th => 1, thead => 1, tr => 1, body => 1, html => 1, |
| 4288 |
|
}->{$entry->[1]}) { |
| 4289 |
|
!!!cp ('t75'); |
| 4290 |
|
!!!parse-error (type => 'in body:#eof', token => $token); |
| 4291 |
|
last; |
| 4292 |
|
} |
| 4293 |
|
} |
| 4294 |
|
|
| 4295 |
|
## Stop parsing. |
| 4296 |
|
last B; |
| 4297 |
} else { |
} else { |
| 4298 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 4299 |
} |
} |
| 4302 |
# |
# |
| 4303 |
} elsif ($self->{insertion_mode} & TABLE_IMS) { |
} elsif ($self->{insertion_mode} & TABLE_IMS) { |
| 4304 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 4305 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if (not $open_tables->[-1]->[1] and # tainted |
| 4306 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 4307 |
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 4308 |
|
|
| 4309 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 4310 |
!!!cp ('t194'); |
!!!cp ('t194'); |
| 4311 |
!!!next-token; |
!!!next-token; |
| 4312 |
redo B; |
redo B; |
| 4313 |
} else { |
} else { |
| 4314 |
!!!cp ('t195'); |
!!!cp ('t195'); |
| 4315 |
} |
} |
| 4316 |
} |
} |
| 4317 |
|
|
| 4318 |
!!!parse-error (type => 'in table:#character'); |
!!!parse-error (type => 'in table:#character', token => $token); |
| 4319 |
|
|
| 4320 |
## As if in body, but insert into foster parent element |
## As if in body, but insert into foster parent element |
| 4321 |
## ISSUE: Spec says that "whenever a node would be inserted |
## ISSUE: Spec says that "whenever a node would be inserted |
| 4360 |
($self->{document}->create_text_node ($token->{data}), |
($self->{document}->create_text_node ($token->{data}), |
| 4361 |
$next_sibling); |
$next_sibling); |
| 4362 |
} |
} |
| 4363 |
} else { |
$open_tables->[-1]->[1] = 1; # tainted |
| 4364 |
!!!cp ('t200'); |
} else { |
| 4365 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
!!!cp ('t200'); |
| 4366 |
} |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
| 4367 |
|
} |
| 4368 |
|
|
| 4369 |
!!!next-token; |
!!!next-token; |
| 4370 |
redo B; |
redo B; |
| 4371 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 4372 |
if ({ |
if ({ |
| 4373 |
tr => ($self->{insertion_mode} != IN_ROW_IM), |
tr => ($self->{insertion_mode} != IN_ROW_IM), |
| 4378 |
while ($self->{open_elements}->[-1]->[1] ne 'table' and |
while ($self->{open_elements}->[-1]->[1] ne 'table' and |
| 4379 |
$self->{open_elements}->[-1]->[1] ne 'html') { |
$self->{open_elements}->[-1]->[1] ne 'html') { |
| 4380 |
!!!cp ('t201'); |
!!!cp ('t201'); |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4381 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4382 |
} |
} |
| 4383 |
|
|
| 4384 |
!!!insert-element ('tbody'); |
!!!insert-element ('tbody',, $token); |
| 4385 |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 4386 |
## reprocess in the "in table body" insertion mode... |
## reprocess in the "in table body" insertion mode... |
| 4387 |
} |
} |
| 4389 |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
| 4390 |
unless ($token->{tag_name} eq 'tr') { |
unless ($token->{tag_name} eq 'tr') { |
| 4391 |
!!!cp ('t202'); |
!!!cp ('t202'); |
| 4392 |
!!!parse-error (type => 'missing start tag:tr'); |
!!!parse-error (type => 'missing start tag:tr', token => $token); |
| 4393 |
} |
} |
| 4394 |
|
|
| 4395 |
## Clear back to table body context |
## Clear back to table body context |
| 4398 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4399 |
!!!cp ('t203'); |
!!!cp ('t203'); |
| 4400 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4401 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4402 |
} |
} |
| 4403 |
|
|
| 4404 |
$self->{insertion_mode} = IN_ROW_IM; |
$self->{insertion_mode} = IN_ROW_IM; |
| 4405 |
if ($token->{tag_name} eq 'tr') { |
if ($token->{tag_name} eq 'tr') { |
| 4406 |
!!!cp ('t204'); |
!!!cp ('t204'); |
| 4407 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 4408 |
!!!next-token; |
!!!next-token; |
| 4409 |
redo B; |
redo B; |
| 4410 |
} else { |
} else { |
| 4411 |
!!!cp ('t205'); |
!!!cp ('t205'); |
| 4412 |
!!!insert-element ('tr'); |
!!!insert-element ('tr',, $token); |
| 4413 |
## reprocess in the "in row" insertion mode |
## reprocess in the "in row" insertion mode |
| 4414 |
} |
} |
| 4415 |
} else { |
} else { |
| 4421 |
tr => 1, html => 1, |
tr => 1, html => 1, |
| 4422 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4423 |
!!!cp ('t207'); |
!!!cp ('t207'); |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4424 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4425 |
} |
} |
| 4426 |
|
|
| 4427 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 4428 |
$self->{insertion_mode} = IN_CELL_IM; |
$self->{insertion_mode} = IN_CELL_IM; |
| 4429 |
|
|
| 4430 |
push @$active_formatting_elements, ['#marker', '']; |
push @$active_formatting_elements, ['#marker', '']; |
| 4459 |
unless (defined $i) { |
unless (defined $i) { |
| 4460 |
!!!cp ('t210'); |
!!!cp ('t210'); |
| 4461 |
## TODO: This type is wrong. |
## TODO: This type is wrong. |
| 4462 |
!!!parse-error (type => 'unmacthed end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmacthed end tag:'.$token->{tag_name}, token => $token); |
| 4463 |
## Ignore the token |
## Ignore the token |
| 4464 |
!!!next-token; |
!!!next-token; |
| 4465 |
redo B; |
redo B; |
| 4471 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4472 |
!!!cp ('t211'); |
!!!cp ('t211'); |
| 4473 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4474 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4475 |
} |
} |
| 4476 |
|
|
| 4507 |
unless (defined $i) { |
unless (defined $i) { |
| 4508 |
!!!cp ('t216'); |
!!!cp ('t216'); |
| 4509 |
## TODO: This erorr type ios wrong. |
## TODO: This erorr type ios wrong. |
| 4510 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4511 |
## Ignore the token |
## Ignore the token |
| 4512 |
!!!next-token; |
!!!next-token; |
| 4513 |
redo B; |
redo B; |
| 4519 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4520 |
!!!cp ('t217'); |
!!!cp ('t217'); |
| 4521 |
## ISSUE: Can this state be reached? |
## ISSUE: Can this state be reached? |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4522 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4523 |
} |
} |
| 4524 |
|
|
| 4542 |
$self->{open_elements}->[-1]->[1] ne 'html') { |
$self->{open_elements}->[-1]->[1] ne 'html') { |
| 4543 |
!!!cp ('t219'); |
!!!cp ('t219'); |
| 4544 |
## ISSUE: Can this state be reached? |
## ISSUE: Can this state be reached? |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4545 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4546 |
} |
} |
| 4547 |
|
|
| 4548 |
!!!insert-element ('colgroup'); |
!!!insert-element ('colgroup',, $token); |
| 4549 |
$self->{insertion_mode} = IN_COLUMN_GROUP_IM; |
$self->{insertion_mode} = IN_COLUMN_GROUP_IM; |
| 4550 |
## reprocess |
## reprocess |
| 4551 |
redo B; |
redo B; |
| 4559 |
$self->{open_elements}->[-1]->[1] ne 'html') { |
$self->{open_elements}->[-1]->[1] ne 'html') { |
| 4560 |
!!!cp ('t220'); |
!!!cp ('t220'); |
| 4561 |
## ISSUE: Can this state be reached? |
## ISSUE: Can this state be reached? |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4562 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4563 |
} |
} |
| 4564 |
|
|
| 4565 |
push @$active_formatting_elements, ['#marker', ''] |
push @$active_formatting_elements, ['#marker', ''] |
| 4566 |
if $token->{tag_name} eq 'caption'; |
if $token->{tag_name} eq 'caption'; |
| 4567 |
|
|
| 4568 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 4569 |
$self->{insertion_mode} = { |
$self->{insertion_mode} = { |
| 4570 |
caption => IN_CAPTION_IM, |
caption => IN_CAPTION_IM, |
| 4571 |
colgroup => IN_COLUMN_GROUP_IM, |
colgroup => IN_COLUMN_GROUP_IM, |
| 4579 |
die "$0: in table: <>: $token->{tag_name}"; |
die "$0: in table: <>: $token->{tag_name}"; |
| 4580 |
} |
} |
| 4581 |
} elsif ($token->{tag_name} eq 'table') { |
} elsif ($token->{tag_name} eq 'table') { |
| 4582 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 4583 |
|
|
| 4584 |
## As if </table> |
## As if </table> |
| 4585 |
## have a table element in table scope |
## have a table element in table scope |
| 4601 |
unless (defined $i) { |
unless (defined $i) { |
| 4602 |
!!!cp ('t223'); |
!!!cp ('t223'); |
| 4603 |
## TODO: The following is wrong, maybe. |
## TODO: The following is wrong, maybe. |
| 4604 |
!!!parse-error (type => 'unmatched end tag:table'); |
!!!parse-error (type => 'unmatched end tag:table', token => $token); |
| 4605 |
## Ignore tokens </table><table> |
## Ignore tokens </table><table> |
| 4606 |
!!!next-token; |
!!!next-token; |
| 4607 |
redo B; |
redo B; |
| 4608 |
} |
} |
| 4609 |
|
|
| 4610 |
|
## TODO: Followings are removed from the latest spec. |
| 4611 |
## generate implied end tags |
## generate implied end tags |
| 4612 |
if ({ |
while ({ |
| 4613 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 4614 |
td => 1, th => 1, tr => 1, |
}->{$self->{open_elements}->[-1]->[1]}) { |
|
tbody => 1, tfoot=> 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 4615 |
!!!cp ('t224'); |
!!!cp ('t224'); |
| 4616 |
!!!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; |
|
| 4617 |
} |
} |
| 4618 |
|
|
| 4619 |
if ($self->{open_elements}->[-1]->[1] ne 'table') { |
if ($self->{open_elements}->[-1]->[1] ne 'table') { |
| 4620 |
!!!cp ('t225'); |
!!!cp ('t225'); |
| 4621 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
| 4622 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 4623 |
} else { |
} else { |
| 4624 |
!!!cp ('t226'); |
!!!cp ('t226'); |
| 4625 |
} |
} |
| 4626 |
|
|
| 4627 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 4628 |
|
pop @{$open_tables}; |
| 4629 |
|
|
| 4630 |
$self->_reset_insertion_mode; |
$self->_reset_insertion_mode; |
| 4631 |
|
|
| 4632 |
## reprocess |
## reprocess |
| 4633 |
redo B; |
redo B; |
| 4634 |
|
} elsif ($token->{tag_name} eq 'style') { |
| 4635 |
|
if (not $open_tables->[-1]->[1]) { # tainted |
| 4636 |
|
!!!cp ('t227.8'); |
| 4637 |
|
## NOTE: This is a "as if in head" code clone. |
| 4638 |
|
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 4639 |
|
redo B; |
| 4640 |
|
} else { |
| 4641 |
|
!!!cp ('t227.7'); |
| 4642 |
|
# |
| 4643 |
|
} |
| 4644 |
|
} elsif ($token->{tag_name} eq 'script') { |
| 4645 |
|
if (not $open_tables->[-1]->[1]) { # tainted |
| 4646 |
|
!!!cp ('t227.6'); |
| 4647 |
|
## NOTE: This is a "as if in head" code clone. |
| 4648 |
|
$script_start_tag->(); |
| 4649 |
|
redo B; |
| 4650 |
|
} else { |
| 4651 |
|
!!!cp ('t227.5'); |
| 4652 |
|
# |
| 4653 |
|
} |
| 4654 |
|
} elsif ($token->{tag_name} eq 'input') { |
| 4655 |
|
if (not $open_tables->[-1]->[1]) { # tainted |
| 4656 |
|
if ($token->{attributes}->{type}) { ## TODO: case |
| 4657 |
|
my $type = lc $token->{attributes}->{type}->{value}; |
| 4658 |
|
if ($type eq 'hidden') { |
| 4659 |
|
!!!cp ('t227.3'); |
| 4660 |
|
!!!parse-error (type => 'in table:'.$token->{tag_name}, token => $token); |
| 4661 |
|
|
| 4662 |
|
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 4663 |
|
|
| 4664 |
|
## TODO: form element pointer |
| 4665 |
|
|
| 4666 |
|
pop @{$self->{open_elements}}; |
| 4667 |
|
|
| 4668 |
|
!!!next-token; |
| 4669 |
|
redo B; |
| 4670 |
|
} else { |
| 4671 |
|
!!!cp ('t227.2'); |
| 4672 |
|
# |
| 4673 |
|
} |
| 4674 |
|
} else { |
| 4675 |
|
!!!cp ('t227.1'); |
| 4676 |
|
# |
| 4677 |
|
} |
| 4678 |
|
} else { |
| 4679 |
|
!!!cp ('t227.4'); |
| 4680 |
|
# |
| 4681 |
|
} |
| 4682 |
} else { |
} else { |
| 4683 |
!!!cp ('t227'); |
!!!cp ('t227'); |
|
!!!parse-error (type => 'in table:'.$token->{tag_name}); |
|
|
|
|
|
$insert = $insert_to_foster; |
|
| 4684 |
# |
# |
| 4685 |
} |
} |
| 4686 |
|
|
| 4687 |
|
!!!parse-error (type => 'in table:'.$token->{tag_name}, token => $token); |
| 4688 |
|
|
| 4689 |
|
$insert = $insert_to_foster; |
| 4690 |
|
# |
| 4691 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 4692 |
if ($token->{tag_name} eq 'tr' and |
if ($token->{tag_name} eq 'tr' and |
| 4693 |
$self->{insertion_mode} == IN_ROW_IM) { |
$self->{insertion_mode} == IN_ROW_IM) { |
| 4708 |
} # INSCOPE |
} # INSCOPE |
| 4709 |
unless (defined $i) { |
unless (defined $i) { |
| 4710 |
!!!cp ('t230'); |
!!!cp ('t230'); |
| 4711 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4712 |
## Ignore the token |
## Ignore the token |
| 4713 |
!!!next-token; |
!!!next-token; |
| 4714 |
redo B; |
redo B; |
| 4722 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4723 |
!!!cp ('t231'); |
!!!cp ('t231'); |
| 4724 |
## ISSUE: Can this state be reached? |
## ISSUE: Can this state be reached? |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4725 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4726 |
} |
} |
| 4727 |
|
|
| 4750 |
unless (defined $i) { |
unless (defined $i) { |
| 4751 |
!!!cp ('t235'); |
!!!cp ('t235'); |
| 4752 |
## TODO: The following is wrong. |
## TODO: The following is wrong. |
| 4753 |
!!!parse-error (type => 'unmatched end tag:'.$token->{type}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{type}, token => $token); |
| 4754 |
## Ignore the token |
## Ignore the token |
| 4755 |
!!!next-token; |
!!!next-token; |
| 4756 |
redo B; |
redo B; |
| 4762 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4763 |
!!!cp ('t236'); |
!!!cp ('t236'); |
| 4764 |
## ISSUE: Can this state be reached? |
## ISSUE: Can this state be reached? |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4765 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4766 |
} |
} |
| 4767 |
|
|
| 4790 |
} # INSCOPE |
} # INSCOPE |
| 4791 |
unless (defined $i) { |
unless (defined $i) { |
| 4792 |
!!!cp ('t239'); |
!!!cp ('t239'); |
| 4793 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4794 |
## Ignore the token |
## Ignore the token |
| 4795 |
!!!next-token; |
!!!next-token; |
| 4796 |
redo B; |
redo B; |
| 4801 |
tbody => 1, tfoot => 1, thead => 1, html => 1, |
tbody => 1, tfoot => 1, thead => 1, html => 1, |
| 4802 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4803 |
!!!cp ('t240'); |
!!!cp ('t240'); |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4804 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4805 |
} |
} |
| 4806 |
|
|
| 4816 |
## reprocess in the "in table" insertion mode... |
## reprocess in the "in table" insertion mode... |
| 4817 |
} |
} |
| 4818 |
|
|
| 4819 |
|
## NOTE: </table> in the "in table" insertion mode. |
| 4820 |
|
## When you edit the code fragment below, please ensure that |
| 4821 |
|
## the code for <table> in the "in table" insertion mode |
| 4822 |
|
## is synced with it. |
| 4823 |
|
|
| 4824 |
## have a table element in table scope |
## have a table element in table scope |
| 4825 |
my $i; |
my $i; |
| 4826 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4838 |
} # INSCOPE |
} # INSCOPE |
| 4839 |
unless (defined $i) { |
unless (defined $i) { |
| 4840 |
!!!cp ('t243'); |
!!!cp ('t243'); |
| 4841 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4842 |
## Ignore the token |
## Ignore the token |
| 4843 |
!!!next-token; |
!!!next-token; |
| 4844 |
redo B; |
redo B; |
| 4845 |
} |
} |
|
|
|
|
## 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'); |
|
|
} |
|
| 4846 |
|
|
| 4847 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 4848 |
|
pop @{$open_tables}; |
| 4849 |
|
|
| 4850 |
$self->_reset_insertion_mode; |
$self->_reset_insertion_mode; |
| 4851 |
|
|
| 4873 |
} # INSCOPE |
} # INSCOPE |
| 4874 |
unless (defined $i) { |
unless (defined $i) { |
| 4875 |
!!!cp ('t249'); |
!!!cp ('t249'); |
| 4876 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4877 |
## Ignore the token |
## Ignore the token |
| 4878 |
!!!next-token; |
!!!next-token; |
| 4879 |
redo B; |
redo B; |
| 4897 |
} # INSCOPE |
} # INSCOPE |
| 4898 |
unless (defined $i) { |
unless (defined $i) { |
| 4899 |
!!!cp ('t252'); |
!!!cp ('t252'); |
| 4900 |
!!!parse-error (type => 'unmatched end tag:tr'); |
!!!parse-error (type => 'unmatched end tag:tr', token => $token); |
| 4901 |
## Ignore the token |
## Ignore the token |
| 4902 |
!!!next-token; |
!!!next-token; |
| 4903 |
redo B; |
redo B; |
| 4909 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4910 |
!!!cp ('t253'); |
!!!cp ('t253'); |
| 4911 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4912 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4913 |
} |
} |
| 4914 |
|
|
| 4934 |
} # INSCOPE |
} # INSCOPE |
| 4935 |
unless (defined $i) { |
unless (defined $i) { |
| 4936 |
!!!cp ('t256'); |
!!!cp ('t256'); |
| 4937 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4938 |
## Ignore the token |
## Ignore the token |
| 4939 |
!!!next-token; |
!!!next-token; |
| 4940 |
redo B; |
redo B; |
| 4946 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4947 |
!!!cp ('t257'); |
!!!cp ('t257'); |
| 4948 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 4949 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4950 |
} |
} |
| 4951 |
|
|
| 4960 |
tbody => 1, tfoot => 1, thead => 1, # $self->{insertion_mode} == IN_TABLE_IM |
tbody => 1, tfoot => 1, thead => 1, # $self->{insertion_mode} == IN_TABLE_IM |
| 4961 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 4962 |
!!!cp ('t258'); |
!!!cp ('t258'); |
| 4963 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 4964 |
## Ignore the token |
## Ignore the token |
| 4965 |
!!!next-token; |
!!!next-token; |
| 4966 |
redo B; |
redo B; |
| 4967 |
} else { |
} else { |
| 4968 |
!!!cp ('t259'); |
!!!cp ('t259'); |
| 4969 |
!!!parse-error (type => 'in table:/'.$token->{tag_name}); |
!!!parse-error (type => 'in table:/'.$token->{tag_name}, token => $token); |
| 4970 |
|
|
| 4971 |
$insert = $insert_to_foster; |
$insert = $insert_to_foster; |
| 4972 |
# |
# |
| 4973 |
} |
} |
| 4974 |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 4975 |
|
unless ($self->{open_elements}->[-1]->[1] eq 'html' and |
| 4976 |
|
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 4977 |
|
!!!parse-error (type => 'in body:#eof', token => $token); |
| 4978 |
|
!!!cp ('t259.1'); |
| 4979 |
|
# |
| 4980 |
|
} else { |
| 4981 |
|
!!!cp ('t259.2'); |
| 4982 |
|
# |
| 4983 |
|
} |
| 4984 |
|
|
| 4985 |
|
## Stop parsing |
| 4986 |
|
last B; |
| 4987 |
} else { |
} else { |
| 4988 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 4989 |
} |
} |
| 5003 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 5004 |
if ($token->{tag_name} eq 'col') { |
if ($token->{tag_name} eq 'col') { |
| 5005 |
!!!cp ('t262'); |
!!!cp ('t262'); |
| 5006 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5007 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5008 |
!!!next-token; |
!!!next-token; |
| 5009 |
redo B; |
redo B; |
| 5015 |
if ($token->{tag_name} eq 'colgroup') { |
if ($token->{tag_name} eq 'colgroup') { |
| 5016 |
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
| 5017 |
!!!cp ('t264'); |
!!!cp ('t264'); |
| 5018 |
!!!parse-error (type => 'unmatched end tag:colgroup'); |
!!!parse-error (type => 'unmatched end tag:colgroup', token => $token); |
| 5019 |
## Ignore the token |
## Ignore the token |
| 5020 |
!!!next-token; |
!!!next-token; |
| 5021 |
redo B; |
redo B; |
| 5028 |
} |
} |
| 5029 |
} elsif ($token->{tag_name} eq 'col') { |
} elsif ($token->{tag_name} eq 'col') { |
| 5030 |
!!!cp ('t266'); |
!!!cp ('t266'); |
| 5031 |
!!!parse-error (type => 'unmatched end tag:col'); |
!!!parse-error (type => 'unmatched end tag:col', token => $token); |
| 5032 |
## Ignore the token |
## Ignore the token |
| 5033 |
!!!next-token; |
!!!next-token; |
| 5034 |
redo B; |
redo B; |
| 5036 |
!!!cp ('t267'); |
!!!cp ('t267'); |
| 5037 |
# |
# |
| 5038 |
} |
} |
| 5039 |
} else { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 5040 |
die "$0: $token->{type}: Unknown token type"; |
if ($self->{open_elements}->[-1]->[1] eq 'html' or |
| 5041 |
} |
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 5042 |
|
!!!cp ('t270.2'); |
| 5043 |
|
## Stop parsing. |
| 5044 |
|
last B; |
| 5045 |
|
} else { |
| 5046 |
|
## NOTE: As if </colgroup>. |
| 5047 |
|
!!!cp ('t270.1'); |
| 5048 |
|
pop @{$self->{open_elements}}; # colgroup |
| 5049 |
|
$self->{insertion_mode} = IN_TABLE_IM; |
| 5050 |
|
## Reprocess. |
| 5051 |
|
redo B; |
| 5052 |
|
} |
| 5053 |
|
} else { |
| 5054 |
|
die "$0: $token->{type}: Unknown token type"; |
| 5055 |
|
} |
| 5056 |
|
|
| 5057 |
## As if </colgroup> |
## As if </colgroup> |
| 5058 |
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
| 5059 |
!!!cp ('t269'); |
!!!cp ('t269'); |
| 5060 |
!!!parse-error (type => 'unmatched end tag:colgroup'); |
## TODO: Wrong error type? |
| 5061 |
|
!!!parse-error (type => 'unmatched end tag:colgroup', token => $token); |
| 5062 |
## Ignore the token |
## Ignore the token |
| 5063 |
!!!next-token; |
!!!next-token; |
| 5064 |
redo B; |
redo B; |
| 5069 |
## reprocess |
## reprocess |
| 5070 |
redo B; |
redo B; |
| 5071 |
} |
} |
| 5072 |
} elsif ($self->{insertion_mode} == IN_SELECT_IM) { |
} elsif ($self->{insertion_mode} & SELECT_IMS) { |
| 5073 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 5074 |
!!!cp ('t271'); |
!!!cp ('t271'); |
| 5075 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
| 5085 |
!!!cp ('t273'); |
!!!cp ('t273'); |
| 5086 |
} |
} |
| 5087 |
|
|
| 5088 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5089 |
!!!next-token; |
!!!next-token; |
| 5090 |
redo B; |
redo B; |
| 5091 |
} elsif ($token->{tag_name} eq 'optgroup') { |
} elsif ($token->{tag_name} eq 'optgroup') { |
| 5105 |
!!!cp ('t277'); |
!!!cp ('t277'); |
| 5106 |
} |
} |
| 5107 |
|
|
| 5108 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5109 |
!!!next-token; |
!!!next-token; |
| 5110 |
redo B; |
redo B; |
| 5111 |
} elsif ($token->{tag_name} eq 'select') { |
} elsif ($token->{tag_name} eq 'select' or |
| 5112 |
## TODO: The type below is not good - <select> is replaced by </select> |
$token->{tag_name} eq 'input' or |
| 5113 |
!!!parse-error (type => 'not closed:select'); |
($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
| 5114 |
## As if </select> instead |
{ |
| 5115 |
|
caption => 1, table => 1, |
| 5116 |
|
tbody => 1, tfoot => 1, thead => 1, |
| 5117 |
|
tr => 1, td => 1, th => 1, |
| 5118 |
|
}->{$token->{tag_name}})) { |
| 5119 |
|
## TODO: The type below is not good - <select> is replaced by </select> |
| 5120 |
|
!!!parse-error (type => 'not closed:select', token => $token); |
| 5121 |
|
## NOTE: As if the token were </select> (<select> case) or |
| 5122 |
|
## as if there were </select> (otherwise). |
| 5123 |
## have an element in table scope |
## have an element in table scope |
| 5124 |
my $i; |
my $i; |
| 5125 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5126 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5127 |
if ($node->[1] eq $token->{tag_name}) { |
if ($node->[1] eq 'select') { |
| 5128 |
!!!cp ('t278'); |
!!!cp ('t278'); |
| 5129 |
$i = $_; |
$i = $_; |
| 5130 |
last INSCOPE; |
last INSCOPE; |
| 5137 |
} # INSCOPE |
} # INSCOPE |
| 5138 |
unless (defined $i) { |
unless (defined $i) { |
| 5139 |
!!!cp ('t280'); |
!!!cp ('t280'); |
| 5140 |
!!!parse-error (type => 'unmatched end tag:select'); |
!!!parse-error (type => 'unmatched end tag:select', token => $token); |
| 5141 |
## Ignore the token |
## Ignore the token |
| 5142 |
!!!next-token; |
!!!next-token; |
| 5143 |
redo B; |
redo B; |
| 5148 |
|
|
| 5149 |
$self->_reset_insertion_mode; |
$self->_reset_insertion_mode; |
| 5150 |
|
|
| 5151 |
!!!next-token; |
if ($token->{tag_name} eq 'select') { |
| 5152 |
redo B; |
!!!cp ('t281.2'); |
| 5153 |
|
!!!next-token; |
| 5154 |
|
redo B; |
| 5155 |
|
} else { |
| 5156 |
|
!!!cp ('t281.1'); |
| 5157 |
|
## Reprocess the token. |
| 5158 |
|
redo B; |
| 5159 |
|
} |
| 5160 |
} else { |
} else { |
| 5161 |
!!!cp ('t282'); |
!!!cp ('t282'); |
| 5162 |
!!!parse-error (type => 'in select:'.$token->{tag_name}); |
!!!parse-error (type => 'in select:'.$token->{tag_name}, token => $token); |
| 5163 |
## Ignore the token |
## Ignore the token |
| 5164 |
!!!next-token; |
!!!next-token; |
| 5165 |
redo B; |
redo B; |
| 5176 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5177 |
} else { |
} else { |
| 5178 |
!!!cp ('t285'); |
!!!cp ('t285'); |
| 5179 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 5180 |
## Ignore the token |
## Ignore the token |
| 5181 |
} |
} |
| 5182 |
!!!next-token; |
!!!next-token; |
| 5187 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5188 |
} else { |
} else { |
| 5189 |
!!!cp ('t287'); |
!!!cp ('t287'); |
| 5190 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 5191 |
## Ignore the token |
## Ignore the token |
| 5192 |
} |
} |
| 5193 |
!!!next-token; |
!!!next-token; |
| 5210 |
} # INSCOPE |
} # INSCOPE |
| 5211 |
unless (defined $i) { |
unless (defined $i) { |
| 5212 |
!!!cp ('t290'); |
!!!cp ('t290'); |
| 5213 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 5214 |
## Ignore the token |
## Ignore the token |
| 5215 |
!!!next-token; |
!!!next-token; |
| 5216 |
redo B; |
redo B; |
| 5223 |
|
|
| 5224 |
!!!next-token; |
!!!next-token; |
| 5225 |
redo B; |
redo B; |
| 5226 |
} elsif ({ |
} elsif ($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
| 5227 |
caption => 1, table => 1, tbody => 1, |
{ |
| 5228 |
tfoot => 1, thead => 1, tr => 1, td => 1, th => 1, |
caption => 1, table => 1, tbody => 1, |
| 5229 |
}->{$token->{tag_name}}) { |
tfoot => 1, thead => 1, tr => 1, td => 1, th => 1, |
| 5230 |
|
}->{$token->{tag_name}}) { |
| 5231 |
## TODO: The following is wrong? |
## TODO: The following is wrong? |
| 5232 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 5233 |
|
|
| 5234 |
## have an element in table scope |
## have an element in table scope |
| 5235 |
my $i; |
my $i; |
| 5273 |
unless (defined $i) { |
unless (defined $i) { |
| 5274 |
!!!cp ('t297'); |
!!!cp ('t297'); |
| 5275 |
## TODO: The following error type is correct? |
## TODO: The following error type is correct? |
| 5276 |
!!!parse-error (type => 'unmatched end tag:select'); |
!!!parse-error (type => 'unmatched end tag:select', token => $token); |
| 5277 |
## Ignore the </select> token |
## Ignore the </select> token |
| 5278 |
!!!next-token; ## TODO: ok? |
!!!next-token; ## TODO: ok? |
| 5279 |
redo B; |
redo B; |
| 5288 |
redo B; |
redo B; |
| 5289 |
} else { |
} else { |
| 5290 |
!!!cp ('t299'); |
!!!cp ('t299'); |
| 5291 |
!!!parse-error (type => 'in select:/'.$token->{tag_name}); |
!!!parse-error (type => 'in select:/'.$token->{tag_name}, token => $token); |
| 5292 |
## Ignore the token |
## Ignore the token |
| 5293 |
!!!next-token; |
!!!next-token; |
| 5294 |
redo B; |
redo B; |
| 5295 |
} |
} |
| 5296 |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 5297 |
|
unless ($self->{open_elements}->[-1]->[1] eq 'html' and |
| 5298 |
|
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 5299 |
|
!!!cp ('t299.1'); |
| 5300 |
|
!!!parse-error (type => 'in body:#eof', token => $token); |
| 5301 |
|
} else { |
| 5302 |
|
!!!cp ('t299.2'); |
| 5303 |
|
} |
| 5304 |
|
|
| 5305 |
|
## Stop parsing. |
| 5306 |
|
last B; |
| 5307 |
} else { |
} else { |
| 5308 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 5309 |
} |
} |
| 5325 |
|
|
| 5326 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 5327 |
!!!cp ('t301'); |
!!!cp ('t301'); |
| 5328 |
!!!parse-error (type => 'after html:#character'); |
!!!parse-error (type => 'after html:#character', token => $token); |
| 5329 |
|
|
| 5330 |
## Reprocess in the "main" phase, "after body" insertion mode... |
## Reprocess in the "after body" insertion mode. |
| 5331 |
} else { |
} else { |
| 5332 |
!!!cp ('t302'); |
!!!cp ('t302'); |
| 5333 |
} |
} |
| 5334 |
|
|
| 5335 |
## "after body" insertion mode |
## "after body" insertion mode |
| 5336 |
!!!parse-error (type => 'after body:#character'); |
!!!parse-error (type => 'after body:#character', token => $token); |
| 5337 |
|
|
| 5338 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 5339 |
## reprocess |
## reprocess |
| 5341 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 5342 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 5343 |
!!!cp ('t303'); |
!!!cp ('t303'); |
| 5344 |
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
!!!parse-error (type => 'after html:'.$token->{tag_name}, token => $token); |
| 5345 |
|
|
| 5346 |
## Reprocess in the "main" phase, "after body" insertion mode... |
## Reprocess in the "after body" insertion mode. |
| 5347 |
} else { |
} else { |
| 5348 |
!!!cp ('t304'); |
!!!cp ('t304'); |
| 5349 |
} |
} |
| 5350 |
|
|
| 5351 |
## "after body" insertion mode |
## "after body" insertion mode |
| 5352 |
!!!parse-error (type => 'after body:'.$token->{tag_name}); |
!!!parse-error (type => 'after body:'.$token->{tag_name}, token => $token); |
| 5353 |
|
|
| 5354 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 5355 |
## reprocess |
## reprocess |
| 5357 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 5358 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 5359 |
!!!cp ('t305'); |
!!!cp ('t305'); |
| 5360 |
!!!parse-error (type => 'after html:/'.$token->{tag_name}); |
!!!parse-error (type => 'after html:/'.$token->{tag_name}, token => $token); |
| 5361 |
|
|
| 5362 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 5363 |
## Reprocess in the "main" phase, "after body" insertion mode... |
## Reprocess in the "after body" insertion mode. |
| 5364 |
} else { |
} else { |
| 5365 |
!!!cp ('t306'); |
!!!cp ('t306'); |
| 5366 |
} |
} |
| 5369 |
if ($token->{tag_name} eq 'html') { |
if ($token->{tag_name} eq 'html') { |
| 5370 |
if (defined $self->{inner_html_node}) { |
if (defined $self->{inner_html_node}) { |
| 5371 |
!!!cp ('t307'); |
!!!cp ('t307'); |
| 5372 |
!!!parse-error (type => 'unmatched end tag:html'); |
!!!parse-error (type => 'unmatched end tag:html', token => $token); |
| 5373 |
## Ignore the token |
## Ignore the token |
| 5374 |
!!!next-token; |
!!!next-token; |
| 5375 |
redo B; |
redo B; |
| 5381 |
} |
} |
| 5382 |
} else { |
} else { |
| 5383 |
!!!cp ('t309'); |
!!!cp ('t309'); |
| 5384 |
!!!parse-error (type => 'after body:/'.$token->{tag_name}); |
!!!parse-error (type => 'after body:/'.$token->{tag_name}, token => $token); |
| 5385 |
|
|
| 5386 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 5387 |
## reprocess |
## reprocess |
| 5388 |
redo B; |
redo B; |
| 5389 |
} |
} |
| 5390 |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 5391 |
|
!!!cp ('t309.2'); |
| 5392 |
|
## Stop parsing |
| 5393 |
|
last B; |
| 5394 |
} else { |
} else { |
| 5395 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 5396 |
} |
} |
| 5409 |
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
| 5410 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 5411 |
!!!cp ('t311'); |
!!!cp ('t311'); |
| 5412 |
!!!parse-error (type => 'in frameset:#character'); |
!!!parse-error (type => 'in frameset:#character', token => $token); |
| 5413 |
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 5414 |
!!!cp ('t312'); |
!!!cp ('t312'); |
| 5415 |
!!!parse-error (type => 'after frameset:#character'); |
!!!parse-error (type => 'after frameset:#character', token => $token); |
| 5416 |
} else { # "after html frameset" |
} else { # "after html frameset" |
| 5417 |
!!!cp ('t313'); |
!!!cp ('t313'); |
| 5418 |
!!!parse-error (type => 'after html:#character'); |
!!!parse-error (type => 'after html:#character', token => $token); |
| 5419 |
|
|
| 5420 |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 5421 |
## Reprocess in the "main" phase, "after frameset"... |
## Reprocess in the "after frameset" insertion mode. |
| 5422 |
!!!parse-error (type => 'after frameset:#character'); |
!!!parse-error (type => 'after frameset:#character', token => $token); |
| 5423 |
} |
} |
| 5424 |
|
|
| 5425 |
## Ignore the token. |
## Ignore the token. |
| 5437 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 5438 |
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 5439 |
!!!cp ('t316'); |
!!!cp ('t316'); |
| 5440 |
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
!!!parse-error (type => 'after html:'.$token->{tag_name}, token => $token); |
| 5441 |
|
|
| 5442 |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 5443 |
## Process in the "main" phase, "after frameset" insertion mode... |
## Process in the "after frameset" insertion mode. |
| 5444 |
} else { |
} else { |
| 5445 |
!!!cp ('t317'); |
!!!cp ('t317'); |
| 5446 |
} |
} |
| 5448 |
if ($token->{tag_name} eq 'frameset' and |
if ($token->{tag_name} eq 'frameset' and |
| 5449 |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 5450 |
!!!cp ('t318'); |
!!!cp ('t318'); |
| 5451 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5452 |
!!!next-token; |
!!!next-token; |
| 5453 |
redo B; |
redo B; |
| 5454 |
} elsif ($token->{tag_name} eq 'frame' and |
} elsif ($token->{tag_name} eq 'frame' and |
| 5455 |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 5456 |
!!!cp ('t319'); |
!!!cp ('t319'); |
| 5457 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5458 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5459 |
!!!next-token; |
!!!next-token; |
| 5460 |
redo B; |
redo B; |
| 5461 |
} elsif ($token->{tag_name} eq 'noframes') { |
} elsif ($token->{tag_name} eq 'noframes') { |
| 5462 |
!!!cp ('t320'); |
!!!cp ('t320'); |
| 5463 |
## NOTE: As if in body. |
## NOTE: As if in body. |
| 5464 |
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert_to_current); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 5465 |
redo B; |
redo B; |
| 5466 |
} else { |
} else { |
| 5467 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 5468 |
!!!cp ('t321'); |
!!!cp ('t321'); |
| 5469 |
!!!parse-error (type => 'in frameset:'.$token->{tag_name}); |
!!!parse-error (type => 'in frameset:'.$token->{tag_name}, token => $token); |
| 5470 |
} else { |
} else { |
| 5471 |
!!!cp ('t322'); |
!!!cp ('t322'); |
| 5472 |
!!!parse-error (type => 'after frameset:'.$token->{tag_name}); |
!!!parse-error (type => 'after frameset:'.$token->{tag_name}, token => $token); |
| 5473 |
} |
} |
| 5474 |
## Ignore the token |
## Ignore the token |
| 5475 |
!!!next-token; |
!!!next-token; |
| 5478 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 5479 |
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 5480 |
!!!cp ('t323'); |
!!!cp ('t323'); |
| 5481 |
!!!parse-error (type => 'after html:/'.$token->{tag_name}); |
!!!parse-error (type => 'after html:/'.$token->{tag_name}, token => $token); |
| 5482 |
|
|
| 5483 |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 5484 |
## Process in the "main" phase, "after frameset" insertion mode... |
## Process in the "after frameset" insertion mode. |
| 5485 |
} else { |
} else { |
| 5486 |
!!!cp ('t324'); |
!!!cp ('t324'); |
| 5487 |
} |
} |
| 5491 |
if ($self->{open_elements}->[-1]->[1] eq 'html' and |
if ($self->{open_elements}->[-1]->[1] eq 'html' and |
| 5492 |
@{$self->{open_elements}} == 1) { |
@{$self->{open_elements}} == 1) { |
| 5493 |
!!!cp ('t325'); |
!!!cp ('t325'); |
| 5494 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 5495 |
## Ignore the token |
## Ignore the token |
| 5496 |
!!!next-token; |
!!!next-token; |
| 5497 |
} else { |
} else { |
| 5517 |
} else { |
} else { |
| 5518 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 5519 |
!!!cp ('t330'); |
!!!cp ('t330'); |
| 5520 |
!!!parse-error (type => 'in frameset:/'.$token->{tag_name}); |
!!!parse-error (type => 'in frameset:/'.$token->{tag_name}, token => $token); |
| 5521 |
} else { |
} else { |
| 5522 |
!!!cp ('t331'); |
!!!cp ('t331'); |
| 5523 |
!!!parse-error (type => 'after frameset:/'.$token->{tag_name}); |
!!!parse-error (type => 'after frameset:/'.$token->{tag_name}, token => $token); |
| 5524 |
} |
} |
| 5525 |
## Ignore the token |
## Ignore the token |
| 5526 |
!!!next-token; |
!!!next-token; |
| 5527 |
redo B; |
redo B; |
| 5528 |
} |
} |
| 5529 |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 5530 |
|
unless ($self->{open_elements}->[-1]->[1] eq 'html' and |
| 5531 |
|
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 5532 |
|
!!!cp ('t331.1'); |
| 5533 |
|
!!!parse-error (type => 'in body:#eof', token => $token); |
| 5534 |
|
} else { |
| 5535 |
|
!!!cp ('t331.2'); |
| 5536 |
|
} |
| 5537 |
|
|
| 5538 |
|
## Stop parsing |
| 5539 |
|
last B; |
| 5540 |
} else { |
} else { |
| 5541 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 5542 |
} |
} |
| 5551 |
if ($token->{tag_name} eq 'script') { |
if ($token->{tag_name} eq 'script') { |
| 5552 |
!!!cp ('t332'); |
!!!cp ('t332'); |
| 5553 |
## NOTE: This is an "as if in head" code clone |
## NOTE: This is an "as if in head" code clone |
| 5554 |
$script_start_tag->($insert); |
$script_start_tag->(); |
| 5555 |
redo B; |
redo B; |
| 5556 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($token->{tag_name} eq 'style') { |
| 5557 |
!!!cp ('t333'); |
!!!cp ('t333'); |
| 5558 |
## NOTE: This is an "as if in head" code clone |
## NOTE: This is an "as if in head" code clone |
| 5559 |
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 5560 |
redo B; |
redo B; |
| 5561 |
} elsif ({ |
} elsif ({ |
| 5562 |
base => 1, link => 1, |
base => 1, link => 1, |
| 5563 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5564 |
!!!cp ('t334'); |
!!!cp ('t334'); |
| 5565 |
## 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 |
| 5566 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 5567 |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 5568 |
!!!next-token; |
!!!next-token; |
| 5569 |
redo B; |
redo B; |
| 5570 |
} elsif ($token->{tag_name} eq 'meta') { |
} elsif ($token->{tag_name} eq 'meta') { |
| 5571 |
## 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 |
| 5572 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 5573 |
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. |
| 5574 |
|
|
| 5575 |
unless ($self->{confident}) { |
unless ($self->{confident}) { |
| 5576 |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
| 5577 |
!!!cp ('t335'); |
!!!cp ('t335'); |
| 5578 |
$self->{change_encoding} |
$self->{change_encoding} |
| 5579 |
->($self, $token->{attributes}->{charset}->{value}); |
->($self, $token->{attributes}->{charset}->{value}, $token); |
| 5580 |
|
|
| 5581 |
$meta_el->[0]->get_attribute_node_ns (undef, 'charset') |
$meta_el->[0]->get_attribute_node_ns (undef, 'charset') |
| 5582 |
->set_user_data (manakai_has_reference => |
->set_user_data (manakai_has_reference => |
| 5591 |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
| 5592 |
!!!cp ('t336'); |
!!!cp ('t336'); |
| 5593 |
$self->{change_encoding} |
$self->{change_encoding} |
| 5594 |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3); |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3, $token); |
| 5595 |
$meta_el->[0]->get_attribute_node_ns (undef, 'content') |
$meta_el->[0]->get_attribute_node_ns (undef, 'content') |
| 5596 |
->set_user_data (manakai_has_reference => |
->set_user_data (manakai_has_reference => |
| 5597 |
$token->{attributes}->{content} |
$token->{attributes}->{content} |
| 5619 |
redo B; |
redo B; |
| 5620 |
} elsif ($token->{tag_name} eq 'title') { |
} elsif ($token->{tag_name} eq 'title') { |
| 5621 |
!!!cp ('t341'); |
!!!cp ('t341'); |
|
!!!parse-error (type => 'in body:title'); |
|
| 5622 |
## NOTE: This is an "as if in head" code clone |
## NOTE: This is an "as if in head" code clone |
| 5623 |
$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]); |
|
|
} |
|
|
}); |
|
| 5624 |
redo B; |
redo B; |
| 5625 |
} elsif ($token->{tag_name} eq 'body') { |
} elsif ($token->{tag_name} eq 'body') { |
| 5626 |
!!!parse-error (type => 'in body:body'); |
!!!parse-error (type => 'in body:body', token => $token); |
| 5627 |
|
|
| 5628 |
if (@{$self->{open_elements}} == 1 or |
if (@{$self->{open_elements}} == 1 or |
| 5629 |
$self->{open_elements}->[1]->[1] ne 'body') { |
$self->{open_elements}->[1]->[1] ne 'body') { |
| 5644 |
redo B; |
redo B; |
| 5645 |
} elsif ({ |
} elsif ({ |
| 5646 |
address => 1, blockquote => 1, center => 1, dir => 1, |
address => 1, blockquote => 1, center => 1, dir => 1, |
| 5647 |
div => 1, dl => 1, fieldset => 1, listing => 1, |
div => 1, dl => 1, fieldset => 1, |
| 5648 |
|
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
| 5649 |
menu => 1, ol => 1, p => 1, ul => 1, |
menu => 1, ol => 1, p => 1, ul => 1, |
| 5650 |
pre => 1, |
pre => 1, listing => 1, |
| 5651 |
|
form => 1, |
| 5652 |
|
table => 1, |
| 5653 |
|
hr => 1, |
| 5654 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5655 |
|
if ($token->{tag_name} eq 'form' and defined $self->{form_element}) { |
| 5656 |
|
!!!cp ('t350'); |
| 5657 |
|
!!!parse-error (type => 'in form:form', token => $token); |
| 5658 |
|
## Ignore the token |
| 5659 |
|
!!!next-token; |
| 5660 |
|
redo B; |
| 5661 |
|
} |
| 5662 |
|
|
| 5663 |
## has a p element in scope |
## has a p element in scope |
| 5664 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 5665 |
if ($_->[1] eq 'p') { |
if ($_->[1] eq 'p') { |
| 5666 |
!!!cp ('t344'); |
!!!cp ('t344'); |
| 5667 |
!!!back-token; |
!!!back-token; |
| 5668 |
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
| 5669 |
|
line => $token->{line}, column => $token->{column}}; |
| 5670 |
redo B; |
redo B; |
| 5671 |
} elsif ({ |
} elsif ({ |
| 5672 |
table => 1, caption => 1, td => 1, th => 1, |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 5673 |
button => 1, marquee => 1, object => 1, html => 1, |
button => 1, marquee => 1, object => 1, html => 1, |
| 5674 |
}->{$_->[1]}) { |
}->{$_->[1]}) { |
| 5675 |
!!!cp ('t345'); |
!!!cp ('t345'); |
| 5677 |
} |
} |
| 5678 |
} # INSCOPE |
} # INSCOPE |
| 5679 |
|
|
| 5680 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 5681 |
if ($token->{tag_name} eq 'pre') { |
if ($token->{tag_name} eq 'pre' or $token->{tag_name} eq 'listing') { |
| 5682 |
!!!next-token; |
!!!next-token; |
| 5683 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 5684 |
$token->{data} =~ s/^\x0A//; |
$token->{data} =~ s/^\x0A//; |
| 5691 |
} else { |
} else { |
| 5692 |
!!!cp ('t348'); |
!!!cp ('t348'); |
| 5693 |
} |
} |
| 5694 |
} else { |
} elsif ($token->{tag_name} eq 'form') { |
| 5695 |
!!!cp ('t347'); |
!!!cp ('t347.1'); |
| 5696 |
|
$self->{form_element} = $self->{open_elements}->[-1]->[0]; |
| 5697 |
|
|
| 5698 |
!!!next-token; |
!!!next-token; |
| 5699 |
} |
} elsif ($token->{tag_name} eq 'table') { |
| 5700 |
redo B; |
!!!cp ('t382'); |
| 5701 |
} elsif ($token->{tag_name} eq 'form') { |
push @{$open_tables}, [$self->{open_elements}->[-1]->[0]]; |
| 5702 |
if (defined $self->{form_element}) { |
|
| 5703 |
!!!cp ('t350'); |
$self->{insertion_mode} = IN_TABLE_IM; |
| 5704 |
!!!parse-error (type => 'in form:form'); |
|
| 5705 |
## Ignore the token |
!!!next-token; |
| 5706 |
|
} elsif ($token->{tag_name} eq 'hr') { |
| 5707 |
|
!!!cp ('t386'); |
| 5708 |
|
pop @{$self->{open_elements}}; |
| 5709 |
|
|
| 5710 |
!!!next-token; |
!!!next-token; |
|
redo B; |
|
| 5711 |
} else { |
} else { |
| 5712 |
## 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]; |
|
| 5713 |
!!!next-token; |
!!!next-token; |
|
redo B; |
|
| 5714 |
} |
} |
| 5715 |
} elsif ($token->{tag_name} eq 'li') { |
redo B; |
| 5716 |
|
} elsif ({li => 1, dt => 1, dd => 1}->{$token->{tag_name}}) { |
| 5717 |
## has a p element in scope |
## has a p element in scope |
| 5718 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 5719 |
if ($_->[1] eq 'p') { |
if ($_->[1] eq 'p') { |
| 5720 |
!!!cp ('t353'); |
!!!cp ('t353'); |
| 5721 |
!!!back-token; |
!!!back-token; |
| 5722 |
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
| 5723 |
|
line => $token->{line}, column => $token->{column}}; |
| 5724 |
redo B; |
redo B; |
| 5725 |
} elsif ({ |
} elsif ({ |
| 5726 |
table => 1, caption => 1, td => 1, th => 1, |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 5727 |
button => 1, marquee => 1, object => 1, html => 1, |
button => 1, marquee => 1, object => 1, html => 1, |
| 5728 |
}->{$_->[1]}) { |
}->{$_->[1]}) { |
| 5729 |
!!!cp ('t354'); |
!!!cp ('t354'); |
| 5734 |
## Step 1 |
## Step 1 |
| 5735 |
my $i = -1; |
my $i = -1; |
| 5736 |
my $node = $self->{open_elements}->[$i]; |
my $node = $self->{open_elements}->[$i]; |
| 5737 |
|
my $li_or_dtdd = {li => {li => 1}, |
| 5738 |
|
dt => {dt => 1, dd => 1}, |
| 5739 |
|
dd => {dt => 1, dd => 1}}->{$token->{tag_name}}; |
| 5740 |
LI: { |
LI: { |
| 5741 |
## Step 2 |
## Step 2 |
| 5742 |
if ($node->[1] eq 'li') { |
if ($li_or_dtdd->{$node->[1]}) { |
| 5743 |
if ($i != -1) { |
if ($i != -1) { |
| 5744 |
!!!cp ('t355'); |
!!!cp ('t355'); |
| 5745 |
!!!parse-error (type => 'end tag missing:'. |
!!!parse-error (type => 'end tag missing:'. |
| 5746 |
$self->{open_elements}->[-1]->[1]); |
$self->{open_elements}->[-1]->[1], token => $token); |
| 5747 |
} else { |
} else { |
| 5748 |
!!!cp ('t356'); |
!!!cp ('t356'); |
| 5749 |
} |
} |
| 5770 |
redo LI; |
redo LI; |
| 5771 |
} # LI |
} # LI |
| 5772 |
|
|
| 5773 |
!!!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}); |
|
| 5774 |
!!!next-token; |
!!!next-token; |
| 5775 |
redo B; |
redo B; |
| 5776 |
} elsif ($token->{tag_name} eq 'plaintext') { |
} elsif ($token->{tag_name} eq 'plaintext') { |
| 5779 |
if ($_->[1] eq 'p') { |
if ($_->[1] eq 'p') { |
| 5780 |
!!!cp ('t367'); |
!!!cp ('t367'); |
| 5781 |
!!!back-token; |
!!!back-token; |
| 5782 |
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
| 5783 |
|
line => $token->{line}, column => $token->{column}}; |
| 5784 |
redo B; |
redo B; |
| 5785 |
} elsif ({ |
} elsif ({ |
| 5786 |
table => 1, caption => 1, td => 1, th => 1, |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 5787 |
button => 1, marquee => 1, object => 1, html => 1, |
button => 1, marquee => 1, object => 1, html => 1, |
| 5788 |
}->{$_->[1]}) { |
}->{$_->[1]}) { |
| 5789 |
!!!cp ('t368'); |
!!!cp ('t368'); |
| 5791 |
} |
} |
| 5792 |
} # INSCOPE |
} # INSCOPE |
| 5793 |
|
|
| 5794 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 5795 |
|
|
| 5796 |
$self->{content_model} = PLAINTEXT_CONTENT_MODEL; |
$self->{content_model} = PLAINTEXT_CONTENT_MODEL; |
| 5797 |
|
|
| 5798 |
!!!next-token; |
!!!next-token; |
| 5799 |
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; |
|
| 5800 |
} elsif ($token->{tag_name} eq 'a') { |
} elsif ($token->{tag_name} eq 'a') { |
| 5801 |
AFE: for my $i (reverse 0..$#$active_formatting_elements) { |
AFE: for my $i (reverse 0..$#$active_formatting_elements) { |
| 5802 |
my $node = $active_formatting_elements->[$i]; |
my $node = $active_formatting_elements->[$i]; |
| 5803 |
if ($node->[1] eq 'a') { |
if ($node->[1] eq 'a') { |
| 5804 |
!!!cp ('t371'); |
!!!cp ('t371'); |
| 5805 |
!!!parse-error (type => 'in a:a'); |
!!!parse-error (type => 'in a:a', token => $token); |
| 5806 |
|
|
| 5807 |
!!!back-token; |
!!!back-token; |
| 5808 |
$token = {type => END_TAG_TOKEN, tag_name => 'a'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'a', |
| 5809 |
$formatting_end_tag->($token->{tag_name}); |
line => $token->{line}, column => $token->{column}}; |
| 5810 |
|
$formatting_end_tag->($token); |
| 5811 |
|
|
| 5812 |
AFE2: for (reverse 0..$#$active_formatting_elements) { |
AFE2: for (reverse 0..$#$active_formatting_elements) { |
| 5813 |
if ($active_formatting_elements->[$_]->[0] eq $node->[0]) { |
if ($active_formatting_elements->[$_]->[0] eq $node->[0]) { |
| 5832 |
|
|
| 5833 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 5834 |
|
|
| 5835 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 5836 |
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
| 5837 |
|
|
| 5838 |
!!!next-token; |
!!!next-token; |
| 5839 |
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; |
|
| 5840 |
} elsif ($token->{tag_name} eq 'nobr') { |
} elsif ($token->{tag_name} eq 'nobr') { |
| 5841 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 5842 |
|
|
| 5845 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5846 |
if ($node->[1] eq 'nobr') { |
if ($node->[1] eq 'nobr') { |
| 5847 |
!!!cp ('t376'); |
!!!cp ('t376'); |
| 5848 |
!!!parse-error (type => 'in nobr:nobr'); |
!!!parse-error (type => 'in nobr:nobr', token => $token); |
| 5849 |
!!!back-token; |
!!!back-token; |
| 5850 |
$token = {type => END_TAG_TOKEN, tag_name => 'nobr'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'nobr', |
| 5851 |
|
line => $token->{line}, column => $token->{column}}; |
| 5852 |
redo B; |
redo B; |
| 5853 |
} elsif ({ |
} elsif ({ |
| 5854 |
table => 1, caption => 1, td => 1, th => 1, |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 5855 |
button => 1, marquee => 1, object => 1, html => 1, |
button => 1, marquee => 1, object => 1, html => 1, |
| 5856 |
}->{$node->[1]}) { |
}->{$node->[1]}) { |
| 5857 |
!!!cp ('t377'); |
!!!cp ('t377'); |
| 5859 |
} |
} |
| 5860 |
} # INSCOPE |
} # INSCOPE |
| 5861 |
|
|
| 5862 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 5863 |
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
| 5864 |
|
|
| 5865 |
!!!next-token; |
!!!next-token; |
| 5870 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5871 |
if ($node->[1] eq 'button') { |
if ($node->[1] eq 'button') { |
| 5872 |
!!!cp ('t378'); |
!!!cp ('t378'); |
| 5873 |
!!!parse-error (type => 'in button:button'); |
!!!parse-error (type => 'in button:button', token => $token); |
| 5874 |
!!!back-token; |
!!!back-token; |
| 5875 |
$token = {type => END_TAG_TOKEN, tag_name => 'button'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'button', |
| 5876 |
|
line => $token->{line}, column => $token->{column}}; |
| 5877 |
redo B; |
redo B; |
| 5878 |
} elsif ({ |
} elsif ({ |
| 5879 |
table => 1, caption => 1, td => 1, th => 1, |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 5880 |
button => 1, marquee => 1, object => 1, html => 1, |
button => 1, marquee => 1, object => 1, html => 1, |
| 5881 |
}->{$node->[1]}) { |
}->{$node->[1]}) { |
| 5882 |
!!!cp ('t379'); |
!!!cp ('t379'); |
| 5886 |
|
|
| 5887 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 5888 |
|
|
| 5889 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 5890 |
push @$active_formatting_elements, ['#marker', '']; |
|
| 5891 |
|
## TODO: associate with $self->{form_element} if defined |
| 5892 |
|
|
|
!!!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}); |
|
| 5893 |
push @$active_formatting_elements, ['#marker', '']; |
push @$active_formatting_elements, ['#marker', '']; |
| 5894 |
|
|
|
!!!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; |
|
|
|
|
| 5895 |
!!!next-token; |
!!!next-token; |
| 5896 |
redo B; |
redo B; |
| 5897 |
} elsif ({ |
} elsif ({ |
| 5898 |
area => 1, basefont => 1, bgsound => 1, br => 1, |
xmp => 1, |
| 5899 |
embed => 1, img => 1, param => 1, spacer => 1, wbr => 1, |
iframe => 1, |
| 5900 |
image => 1, |
noembed => 1, |
| 5901 |
|
noframes => 1, |
| 5902 |
|
noscript => 0, ## TODO: 1 if scripting is enabled |
| 5903 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5904 |
if ($token->{tag_name} eq 'image') { |
if ($token->{tag_name} eq 'xmp') { |
| 5905 |
!!!cp ('t384'); |
!!!cp ('t381'); |
| 5906 |
!!!parse-error (type => 'image'); |
$reconstruct_active_formatting_elements->($insert_to_current); |
|
$token->{tag_name} = 'img'; |
|
| 5907 |
} else { |
} else { |
| 5908 |
!!!cp ('t385'); |
!!!cp ('t399'); |
| 5909 |
} |
} |
| 5910 |
|
## NOTE: There is an "as if in body" code clone. |
| 5911 |
## 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; |
|
| 5912 |
redo B; |
redo B; |
| 5913 |
} elsif ($token->{tag_name} eq 'isindex') { |
} elsif ($token->{tag_name} eq 'isindex') { |
| 5914 |
!!!parse-error (type => 'isindex'); |
!!!parse-error (type => 'isindex', token => $token); |
| 5915 |
|
|
| 5916 |
if (defined $self->{form_element}) { |
if (defined $self->{form_element}) { |
| 5917 |
!!!cp ('t389'); |
!!!cp ('t389'); |
| 5928 |
delete $at->{prompt}; |
delete $at->{prompt}; |
| 5929 |
my @tokens = ( |
my @tokens = ( |
| 5930 |
{type => START_TAG_TOKEN, tag_name => 'form', |
{type => START_TAG_TOKEN, tag_name => 'form', |
| 5931 |
attributes => $form_attrs}, |
attributes => $form_attrs, |
| 5932 |
{type => START_TAG_TOKEN, tag_name => 'hr'}, |
line => $token->{line}, column => $token->{column}}, |
| 5933 |
{type => START_TAG_TOKEN, tag_name => 'p'}, |
{type => START_TAG_TOKEN, tag_name => 'hr', |
| 5934 |
{type => START_TAG_TOKEN, tag_name => 'label'}, |
line => $token->{line}, column => $token->{column}}, |
| 5935 |
|
{type => START_TAG_TOKEN, tag_name => 'p', |
| 5936 |
|
line => $token->{line}, column => $token->{column}}, |
| 5937 |
|
{type => START_TAG_TOKEN, tag_name => 'label', |
| 5938 |
|
line => $token->{line}, column => $token->{column}}, |
| 5939 |
); |
); |
| 5940 |
if ($prompt_attr) { |
if ($prompt_attr) { |
| 5941 |
!!!cp ('t390'); |
!!!cp ('t390'); |
| 5942 |
push @tokens, {type => CHARACTER_TOKEN, data => $prompt_attr->{value}}; |
push @tokens, {type => CHARACTER_TOKEN, data => $prompt_attr->{value}, |
| 5943 |
|
#line => $token->{line}, column => $token->{column}, |
| 5944 |
|
}; |
| 5945 |
} else { |
} else { |
| 5946 |
!!!cp ('t391'); |
!!!cp ('t391'); |
| 5947 |
push @tokens, {type => CHARACTER_TOKEN, |
push @tokens, {type => CHARACTER_TOKEN, |
| 5948 |
data => 'This is a searchable index. Insert your search keywords here: '}; # SHOULD |
data => 'This is a searchable index. Insert your search keywords here: ', |
| 5949 |
|
#line => $token->{line}, column => $token->{column}, |
| 5950 |
|
}; # SHOULD |
| 5951 |
## TODO: make this configurable |
## TODO: make this configurable |
| 5952 |
} |
} |
| 5953 |
push @tokens, |
push @tokens, |
| 5954 |
{type => START_TAG_TOKEN, tag_name => 'input', attributes => $at}, |
{type => START_TAG_TOKEN, tag_name => 'input', attributes => $at, |
| 5955 |
|
line => $token->{line}, column => $token->{column}}, |
| 5956 |
#{type => CHARACTER_TOKEN, data => ''}, # SHOULD |
#{type => CHARACTER_TOKEN, data => ''}, # SHOULD |
| 5957 |
{type => END_TAG_TOKEN, tag_name => 'label'}, |
{type => END_TAG_TOKEN, tag_name => 'label', |
| 5958 |
{type => END_TAG_TOKEN, tag_name => 'p'}, |
line => $token->{line}, column => $token->{column}}, |
| 5959 |
{type => START_TAG_TOKEN, tag_name => 'hr'}, |
{type => END_TAG_TOKEN, tag_name => 'p', |
| 5960 |
{type => END_TAG_TOKEN, tag_name => 'form'}; |
line => $token->{line}, column => $token->{column}}, |
| 5961 |
|
{type => START_TAG_TOKEN, tag_name => 'hr', |
| 5962 |
|
line => $token->{line}, column => $token->{column}}, |
| 5963 |
|
{type => END_TAG_TOKEN, tag_name => 'form', |
| 5964 |
|
line => $token->{line}, column => $token->{column}}; |
| 5965 |
$token = shift @tokens; |
$token = shift @tokens; |
| 5966 |
!!!back-token (@tokens); |
!!!back-token (@tokens); |
| 5967 |
redo B; |
redo B; |
| 5969 |
} elsif ($token->{tag_name} eq 'textarea') { |
} elsif ($token->{tag_name} eq 'textarea') { |
| 5970 |
my $tag_name = $token->{tag_name}; |
my $tag_name = $token->{tag_name}; |
| 5971 |
my $el; |
my $el; |
| 5972 |
!!!create-element ($el, $token->{tag_name}, $token->{attributes}); |
!!!create-element ($el, $token->{tag_name}, $token->{attributes}, $token); |
| 5973 |
|
|
| 5974 |
## TODO: $self->{form_element} if defined |
## TODO: $self->{form_element} if defined |
| 5975 |
$self->{content_model} = RCDATA_CONTENT_MODEL; |
$self->{content_model} = RCDATA_CONTENT_MODEL; |
| 6008 |
## Ignore the token |
## Ignore the token |
| 6009 |
} else { |
} else { |
| 6010 |
!!!cp ('t398'); |
!!!cp ('t398'); |
| 6011 |
!!!parse-error (type => 'in RCDATA:#'.$token->{type}); |
!!!parse-error (type => 'in RCDATA:#'.$token->{type}, token => $token); |
| 6012 |
} |
} |
| 6013 |
!!!next-token; |
!!!next-token; |
| 6014 |
redo B; |
redo B; |
| 6015 |
} 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 ({ |
|
| 6016 |
caption => 1, col => 1, colgroup => 1, frame => 1, |
caption => 1, col => 1, colgroup => 1, frame => 1, |
| 6017 |
frameset => 1, head => 1, option => 1, optgroup => 1, |
frameset => 1, head => 1, option => 1, optgroup => 1, |
| 6018 |
tbody => 1, td => 1, tfoot => 1, th => 1, |
tbody => 1, td => 1, tfoot => 1, th => 1, |
| 6019 |
thead => 1, tr => 1, |
thead => 1, tr => 1, |
| 6020 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6021 |
!!!cp ('t401'); |
!!!cp ('t401'); |
| 6022 |
!!!parse-error (type => 'in body:'.$token->{tag_name}); |
!!!parse-error (type => 'in body:'.$token->{tag_name}, token => $token); |
| 6023 |
## Ignore the token |
## Ignore the token |
| 6024 |
!!!next-token; |
!!!next-token; |
| 6025 |
redo B; |
redo B; |
| 6026 |
|
|
| 6027 |
## ISSUE: An issue on HTML5 new elements in the spec. |
## ISSUE: An issue on HTML5 new elements in the spec. |
| 6028 |
} else { |
} else { |
| 6029 |
!!!cp ('t402'); |
if ($token->{tag_name} eq 'image') { |
| 6030 |
|
!!!cp ('t384'); |
| 6031 |
|
!!!parse-error (type => 'image', token => $token); |
| 6032 |
|
$token->{tag_name} = 'img'; |
| 6033 |
|
} else { |
| 6034 |
|
!!!cp ('t385'); |
| 6035 |
|
} |
| 6036 |
|
|
| 6037 |
|
## NOTE: There is an "as if <br>" code clone. |
| 6038 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 6039 |
|
|
| 6040 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 6041 |
|
|
| 6042 |
|
if ({ |
| 6043 |
|
applet => 1, marquee => 1, object => 1, |
| 6044 |
|
}->{$token->{tag_name}}) { |
| 6045 |
|
!!!cp ('t380'); |
| 6046 |
|
push @$active_formatting_elements, ['#marker', '']; |
| 6047 |
|
} elsif ({ |
| 6048 |
|
b => 1, big => 1, em => 1, font => 1, i => 1, |
| 6049 |
|
s => 1, small => 1, strile => 1, |
| 6050 |
|
strong => 1, tt => 1, u => 1, |
| 6051 |
|
}->{$token->{tag_name}}) { |
| 6052 |
|
!!!cp ('t375'); |
| 6053 |
|
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
| 6054 |
|
} elsif ($token->{tag_name} eq 'input') { |
| 6055 |
|
!!!cp ('t388'); |
| 6056 |
|
## TODO: associate with $self->{form_element} if defined |
| 6057 |
|
pop @{$self->{open_elements}}; |
| 6058 |
|
} elsif ({ |
| 6059 |
|
area => 1, basefont => 1, bgsound => 1, br => 1, |
| 6060 |
|
embed => 1, img => 1, param => 1, spacer => 1, wbr => 1, |
| 6061 |
|
#image => 1, |
| 6062 |
|
}->{$token->{tag_name}}) { |
| 6063 |
|
!!!cp ('t388.1'); |
| 6064 |
|
pop @{$self->{open_elements}}; |
| 6065 |
|
} elsif ($token->{tag_name} eq 'select') { |
| 6066 |
|
## TODO: associate with $self->{form_element} if defined |
| 6067 |
|
|
| 6068 |
|
if ($self->{insertion_mode} & TABLE_IMS or |
| 6069 |
|
$self->{insertion_mode} & BODY_TABLE_IMS or |
| 6070 |
|
$self->{insertion_mode} == IN_COLUMN_GROUP_IM) { |
| 6071 |
|
!!!cp ('t400.1'); |
| 6072 |
|
$self->{insertion_mode} = IN_SELECT_IN_TABLE_IM; |
| 6073 |
|
} else { |
| 6074 |
|
!!!cp ('t400.2'); |
| 6075 |
|
$self->{insertion_mode} = IN_SELECT_IM; |
| 6076 |
|
} |
| 6077 |
|
} else { |
| 6078 |
|
!!!cp ('t402'); |
| 6079 |
|
} |
| 6080 |
|
|
| 6081 |
!!!next-token; |
!!!next-token; |
| 6082 |
redo B; |
redo B; |
| 6083 |
} |
} |
| 6084 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 6085 |
if ($token->{tag_name} eq 'body') { |
if ($token->{tag_name} eq 'body') { |
| 6086 |
if (@{$self->{open_elements}} > 1 and |
## has a |body| element in scope |
| 6087 |
$self->{open_elements}->[1]->[1] eq 'body') { |
my $i; |
| 6088 |
for (@{$self->{open_elements}}) { |
INSCOPE: { |
| 6089 |
unless ({ |
for (reverse @{$self->{open_elements}}) { |
| 6090 |
dd => 1, dt => 1, li => 1, p => 1, td => 1, |
if ($_->[1] eq 'body') { |
| 6091 |
th => 1, tr => 1, body => 1, html => 1, |
!!!cp ('t405'); |
| 6092 |
tbody => 1, tfoot => 1, thead => 1, |
$i = $_; |
| 6093 |
}->{$_->[1]}) { |
last INSCOPE; |
| 6094 |
!!!cp ('t403'); |
} elsif ({ |
| 6095 |
!!!parse-error (type => 'not closed:'.$_->[1]); |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 6096 |
} else { |
button => 1, marquee => 1, object => 1, html => 1, |
| 6097 |
!!!cp ('t404'); |
}->{$_->[1]}) { |
| 6098 |
|
!!!cp ('t405.1'); |
| 6099 |
|
last; |
| 6100 |
} |
} |
| 6101 |
} |
} |
| 6102 |
|
|
| 6103 |
$self->{insertion_mode} = AFTER_BODY_IM; |
!!!parse-error (type => 'start tag not allowed', |
| 6104 |
!!!next-token; |
value => $token->{tag_name}, token => $token); |
| 6105 |
redo B; |
## NOTE: Ignore the token. |
|
} else { |
|
|
!!!cp ('t405'); |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
| 6106 |
!!!next-token; |
!!!next-token; |
| 6107 |
redo B; |
redo B; |
| 6108 |
|
} # INSCOPE |
| 6109 |
|
|
| 6110 |
|
for (@{$self->{open_elements}}) { |
| 6111 |
|
unless ({ |
| 6112 |
|
dd => 1, dt => 1, li => 1, p => 1, td => 1, |
| 6113 |
|
th => 1, tr => 1, body => 1, html => 1, |
| 6114 |
|
tbody => 1, tfoot => 1, thead => 1, |
| 6115 |
|
}->{$_->[1]}) { |
| 6116 |
|
!!!cp ('t403'); |
| 6117 |
|
!!!parse-error (type => 'not closed:'.$_->[1], token => $token); |
| 6118 |
|
last; |
| 6119 |
|
} else { |
| 6120 |
|
!!!cp ('t404'); |
| 6121 |
|
} |
| 6122 |
} |
} |
| 6123 |
|
|
| 6124 |
|
$self->{insertion_mode} = AFTER_BODY_IM; |
| 6125 |
|
!!!next-token; |
| 6126 |
|
redo B; |
| 6127 |
} elsif ($token->{tag_name} eq 'html') { |
} elsif ($token->{tag_name} eq 'html') { |
| 6128 |
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') { |
| 6129 |
## ISSUE: There is an issue in the spec. |
## ISSUE: There is an issue in the spec. |
| 6130 |
if ($self->{open_elements}->[-1]->[1] ne 'body') { |
if ($self->{open_elements}->[-1]->[1] ne 'body') { |
| 6131 |
!!!cp ('t406'); |
!!!cp ('t406'); |
| 6132 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[1]->[1], token => $token); |
| 6133 |
} else { |
} else { |
| 6134 |
!!!cp ('t407'); |
!!!cp ('t407'); |
| 6135 |
} |
} |
| 6138 |
redo B; |
redo B; |
| 6139 |
} else { |
} else { |
| 6140 |
!!!cp ('t408'); |
!!!cp ('t408'); |
| 6141 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 6142 |
## Ignore the token |
## Ignore the token |
| 6143 |
!!!next-token; |
!!!next-token; |
| 6144 |
redo B; |
redo B; |
| 6147 |
address => 1, blockquote => 1, center => 1, dir => 1, |
address => 1, blockquote => 1, center => 1, dir => 1, |
| 6148 |
div => 1, dl => 1, fieldset => 1, listing => 1, |
div => 1, dl => 1, fieldset => 1, listing => 1, |
| 6149 |
menu => 1, ol => 1, pre => 1, ul => 1, |
menu => 1, ol => 1, pre => 1, ul => 1, |
|
p => 1, |
|
| 6150 |
dd => 1, dt => 1, li => 1, |
dd => 1, dt => 1, li => 1, |
| 6151 |
button => 1, marquee => 1, object => 1, |
applet => 1, button => 1, marquee => 1, object => 1, |
| 6152 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6153 |
## has an element in scope |
## has an element in scope |
| 6154 |
my $i; |
my $i; |
| 6155 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 6156 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 6157 |
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; |
|
|
} |
|
|
|
|
| 6158 |
!!!cp ('t410'); |
!!!cp ('t410'); |
| 6159 |
$i = $_; |
$i = $_; |
| 6160 |
last INSCOPE unless $token->{tag_name} eq 'p'; |
last INSCOPE; |
| 6161 |
} elsif ({ |
} elsif ({ |
| 6162 |
table => 1, caption => 1, td => 1, th => 1, |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 6163 |
button => 1, marquee => 1, object => 1, html => 1, |
button => 1, marquee => 1, object => 1, html => 1, |
| 6164 |
}->{$node->[1]}) { |
}->{$node->[1]}) { |
| 6165 |
!!!cp ('t411'); |
!!!cp ('t411'); |
| 6166 |
last INSCOPE; |
last INSCOPE; |
| 6167 |
} |
} |
| 6168 |
} # INSCOPE |
} # INSCOPE |
| 6169 |
|
|
| 6170 |
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
unless (defined $i) { # has an element in scope |
| 6171 |
if (defined $i) { |
!!!cp ('t413'); |
| 6172 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 6173 |
|
} else { |
| 6174 |
|
## Step 1. generate implied end tags |
| 6175 |
|
while ({ |
| 6176 |
|
dd => ($token->{tag_name} ne 'dd'), |
| 6177 |
|
dt => ($token->{tag_name} ne 'dt'), |
| 6178 |
|
li => ($token->{tag_name} ne 'li'), |
| 6179 |
|
p => 1, |
| 6180 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 6181 |
|
!!!cp ('t409'); |
| 6182 |
|
pop @{$self->{open_elements}}; |
| 6183 |
|
} |
| 6184 |
|
|
| 6185 |
|
## Step 2. |
| 6186 |
|
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
| 6187 |
!!!cp ('t412'); |
!!!cp ('t412'); |
| 6188 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 6189 |
} else { |
} else { |
| 6190 |
!!!cp ('t413'); |
!!!cp ('t414'); |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
| 6191 |
} |
} |
| 6192 |
} |
|
| 6193 |
|
## Step 3. |
|
if (defined $i) { |
|
|
!!!cp ('t414'); |
|
| 6194 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 6195 |
} elsif ($token->{tag_name} eq 'p') { |
|
| 6196 |
!!!cp ('t415'); |
## Step 4. |
| 6197 |
## As if <p>, then reprocess the current token |
$clear_up_to_marker->() |
| 6198 |
my $el; |
if { |
| 6199 |
!!!create-element ($el, 'p'); |
applet => 1, button => 1, marquee => 1, object => 1, |
| 6200 |
$insert->($el); |
}->{$token->{tag_name}}; |
|
} else { |
|
|
!!!cp ('t416'); |
|
| 6201 |
} |
} |
|
$clear_up_to_marker->() |
|
|
if { |
|
|
button => 1, marquee => 1, object => 1, |
|
|
}->{$token->{tag_name}}; |
|
| 6202 |
!!!next-token; |
!!!next-token; |
| 6203 |
redo B; |
redo B; |
| 6204 |
} elsif ($token->{tag_name} eq 'form') { |
} elsif ($token->{tag_name} eq 'form') { |
| 6205 |
|
undef $self->{form_element}; |
| 6206 |
|
|
| 6207 |
## has an element in scope |
## has an element in scope |
| 6208 |
|
my $i; |
| 6209 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 6210 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 6211 |
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; |
|
|
} |
|
|
|
|
| 6212 |
!!!cp ('t418'); |
!!!cp ('t418'); |
| 6213 |
|
$i = $_; |
| 6214 |
last INSCOPE; |
last INSCOPE; |
| 6215 |
} elsif ({ |
} elsif ({ |
| 6216 |
table => 1, caption => 1, td => 1, th => 1, |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 6217 |
button => 1, marquee => 1, object => 1, html => 1, |
button => 1, marquee => 1, object => 1, html => 1, |
| 6218 |
}->{$node->[1]}) { |
}->{$node->[1]}) { |
| 6219 |
!!!cp ('t419'); |
!!!cp ('t419'); |
| 6220 |
last INSCOPE; |
last INSCOPE; |
| 6221 |
} |
} |
| 6222 |
} # INSCOPE |
} # INSCOPE |
| 6223 |
|
|
| 6224 |
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 { |
|
| 6225 |
!!!cp ('t421'); |
!!!cp ('t421'); |
| 6226 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 6227 |
|
} else { |
| 6228 |
|
## Step 1. generate implied end tags |
| 6229 |
|
while ({ |
| 6230 |
|
dd => 1, dt => 1, li => 1, p => 1, |
| 6231 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 6232 |
|
!!!cp ('t417'); |
| 6233 |
|
pop @{$self->{open_elements}}; |
| 6234 |
|
} |
| 6235 |
|
|
| 6236 |
|
## Step 2. |
| 6237 |
|
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
| 6238 |
|
!!!cp ('t417.1'); |
| 6239 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 6240 |
|
} else { |
| 6241 |
|
!!!cp ('t420'); |
| 6242 |
|
} |
| 6243 |
|
|
| 6244 |
|
## Step 3. |
| 6245 |
|
splice @{$self->{open_elements}}, $i; |
| 6246 |
} |
} |
| 6247 |
|
|
|
undef $self->{form_element}; |
|
| 6248 |
!!!next-token; |
!!!next-token; |
| 6249 |
redo B; |
redo B; |
| 6250 |
} elsif ({ |
} elsif ({ |
| 6257 |
if ({ |
if ({ |
| 6258 |
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
| 6259 |
}->{$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; |
|
|
} |
|
|
|
|
| 6260 |
!!!cp ('t423'); |
!!!cp ('t423'); |
| 6261 |
$i = $_; |
$i = $_; |
| 6262 |
last INSCOPE; |
last INSCOPE; |
| 6263 |
} elsif ({ |
} elsif ({ |
| 6264 |
table => 1, caption => 1, td => 1, th => 1, |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 6265 |
button => 1, marquee => 1, object => 1, html => 1, |
button => 1, marquee => 1, object => 1, html => 1, |
| 6266 |
}->{$node->[1]}) { |
}->{$node->[1]}) { |
| 6267 |
!!!cp ('t424'); |
!!!cp ('t424'); |
| 6268 |
last INSCOPE; |
last INSCOPE; |
| 6269 |
} |
} |
| 6270 |
} # INSCOPE |
} # INSCOPE |
| 6271 |
|
|
| 6272 |
|
unless (defined $i) { # has an element in scope |
| 6273 |
|
!!!cp ('t425.1'); |
| 6274 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 6275 |
|
} else { |
| 6276 |
|
## Step 1. generate implied end tags |
| 6277 |
|
while ({ |
| 6278 |
|
dd => 1, dt => 1, li => 1, p => 1, |
| 6279 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 6280 |
|
!!!cp ('t422'); |
| 6281 |
|
pop @{$self->{open_elements}}; |
| 6282 |
|
} |
| 6283 |
|
|
| 6284 |
|
## Step 2. |
| 6285 |
|
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
| 6286 |
|
!!!cp ('t425'); |
| 6287 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 6288 |
|
} else { |
| 6289 |
|
!!!cp ('t426'); |
| 6290 |
|
} |
| 6291 |
|
|
| 6292 |
|
## Step 3. |
| 6293 |
|
splice @{$self->{open_elements}}, $i; |
| 6294 |
|
} |
| 6295 |
|
|
| 6296 |
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
!!!next-token; |
| 6297 |
!!!cp ('t425'); |
redo B; |
| 6298 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
} elsif ($token->{tag_name} eq 'p') { |
| 6299 |
|
## has an element in scope |
| 6300 |
|
my $i; |
| 6301 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 6302 |
|
my $node = $self->{open_elements}->[$_]; |
| 6303 |
|
if ($node->[1] eq $token->{tag_name}) { |
| 6304 |
|
!!!cp ('t410.1'); |
| 6305 |
|
$i = $_; |
| 6306 |
|
last INSCOPE; |
| 6307 |
|
} elsif ({ |
| 6308 |
|
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 6309 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 6310 |
|
}->{$node->[1]}) { |
| 6311 |
|
!!!cp ('t411.1'); |
| 6312 |
|
last INSCOPE; |
| 6313 |
|
} |
| 6314 |
|
} # INSCOPE |
| 6315 |
|
|
| 6316 |
|
if (defined $i) { |
| 6317 |
|
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
| 6318 |
|
!!!cp ('t412.1'); |
| 6319 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 6320 |
|
} else { |
| 6321 |
|
!!!cp ('t414.1'); |
| 6322 |
|
} |
| 6323 |
|
|
| 6324 |
|
splice @{$self->{open_elements}}, $i; |
| 6325 |
} else { |
} else { |
| 6326 |
!!!cp ('t426'); |
!!!cp ('t413.1'); |
| 6327 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 6328 |
|
|
| 6329 |
|
!!!cp ('t415.1'); |
| 6330 |
|
## As if <p>, then reprocess the current token |
| 6331 |
|
my $el; |
| 6332 |
|
!!!create-element ($el, 'p',, $token); |
| 6333 |
|
$insert->($el); |
| 6334 |
|
## NOTE: Not inserted into |$self->{open_elements}|. |
| 6335 |
} |
} |
| 6336 |
|
|
|
splice @{$self->{open_elements}}, $i if defined $i; |
|
| 6337 |
!!!next-token; |
!!!next-token; |
| 6338 |
redo B; |
redo B; |
| 6339 |
} elsif ({ |
} elsif ({ |
| 6343 |
strong => 1, tt => 1, u => 1, |
strong => 1, tt => 1, u => 1, |
| 6344 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6345 |
!!!cp ('t427'); |
!!!cp ('t427'); |
| 6346 |
$formatting_end_tag->($token->{tag_name}); |
$formatting_end_tag->($token); |
| 6347 |
redo B; |
redo B; |
| 6348 |
} elsif ($token->{tag_name} eq 'br') { |
} elsif ($token->{tag_name} eq 'br') { |
| 6349 |
!!!cp ('t428'); |
!!!cp ('t428'); |
| 6350 |
!!!parse-error (type => 'unmatched end tag:br'); |
!!!parse-error (type => 'unmatched end tag:br', token => $token); |
| 6351 |
|
|
| 6352 |
## As if <br> |
## As if <br> |
| 6353 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 6354 |
|
|
| 6355 |
my $el; |
my $el; |
| 6356 |
!!!create-element ($el, 'br'); |
!!!create-element ($el, 'br',, $token); |
| 6357 |
$insert->($el); |
$insert->($el); |
| 6358 |
|
|
| 6359 |
## Ignore the token. |
## Ignore the token. |
| 6372 |
noscript => 0, ## TODO: if scripting is enabled |
noscript => 0, ## TODO: if scripting is enabled |
| 6373 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6374 |
!!!cp ('t429'); |
!!!cp ('t429'); |
| 6375 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 6376 |
## Ignore the token |
## Ignore the token |
| 6377 |
!!!next-token; |
!!!next-token; |
| 6378 |
redo B; |
redo B; |
| 6389 |
if ($node->[1] eq $token->{tag_name}) { |
if ($node->[1] eq $token->{tag_name}) { |
| 6390 |
## Step 1 |
## Step 1 |
| 6391 |
## generate implied end tags |
## generate implied end tags |
| 6392 |
if ({ |
while ({ |
| 6393 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 6394 |
td => 1, th => 1, tr => 1, |
}->{$self->{open_elements}->[-1]->[1]}) { |
|
tbody => 1, tfoot => 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 6395 |
!!!cp ('t430'); |
!!!cp ('t430'); |
| 6396 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
| 6397 |
!!!back-token; |
pop @{$self->{open_elements}}; |
|
$token = {type => END_TAG_TOKEN, |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
| 6398 |
} |
} |
| 6399 |
|
|
| 6400 |
## Step 2 |
## Step 2 |
| 6401 |
if ($token->{tag_name} ne $self->{open_elements}->[-1]->[1]) { |
if ($token->{tag_name} ne $self->{open_elements}->[-1]->[1]) { |
| 6402 |
!!!cp ('t431'); |
!!!cp ('t431'); |
| 6403 |
## NOTE: <x><y></x> |
## NOTE: <x><y></x> |
| 6404 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1], token => $token); |
| 6405 |
} else { |
} else { |
| 6406 |
!!!cp ('t432'); |
!!!cp ('t432'); |
| 6407 |
} |
} |
| 6418 |
($special_category->{$node->[1]} or |
($special_category->{$node->[1]} or |
| 6419 |
$scoping_category->{$node->[1]})) { |
$scoping_category->{$node->[1]})) { |
| 6420 |
!!!cp ('t433'); |
!!!cp ('t433'); |
| 6421 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
| 6422 |
## Ignore the token |
## Ignore the token |
| 6423 |
!!!next-token; |
!!!next-token; |
| 6424 |
last S2; |
last S2; |
| 6440 |
redo B; |
redo B; |
| 6441 |
} # B |
} # B |
| 6442 |
|
|
|
## NOTE: The "trailing end" phase in HTML5 is split into |
|
|
## two insertion modes: "after html body" and "after html frameset". |
|
|
## NOTE: States in the main stage is preserved while |
|
|
## the parser stays in the trailing end phase. # MUST |
|
|
|
|
| 6443 |
## Stop parsing # MUST |
## Stop parsing # MUST |
| 6444 |
|
|
| 6445 |
## TODO: script stuffs |
## TODO: script stuffs |
| 6481 |
my $p = $class->new; |
my $p = $class->new; |
| 6482 |
$p->{document} = $doc; |
$p->{document} = $doc; |
| 6483 |
|
|
| 6484 |
## Step 9 # MUST |
## Step 8 # MUST |
| 6485 |
my $i = 0; |
my $i = 0; |
| 6486 |
my $line = 1; |
$p->{line_prev} = $p->{line} = 1; |
| 6487 |
my $column = 0; |
$p->{column_prev} = $p->{column} = 0; |
| 6488 |
$p->{set_next_char} = sub { |
$p->{set_next_char} = sub { |
| 6489 |
my $self = shift; |
my $self = shift; |
| 6490 |
|
|
| 6493 |
|
|
| 6494 |
$self->{next_char} = -1 and return if $i >= length $$s; |
$self->{next_char} = -1 and return if $i >= length $$s; |
| 6495 |
$self->{next_char} = ord substr $$s, $i++, 1; |
$self->{next_char} = ord substr $$s, $i++, 1; |
| 6496 |
$column++; |
|
| 6497 |
|
($p->{line_prev}, $p->{column_prev}) = ($p->{line}, $p->{column}); |
| 6498 |
|
$p->{column}++; |
| 6499 |
|
|
| 6500 |
if ($self->{next_char} == 0x000A) { # LF |
if ($self->{next_char} == 0x000A) { # LF |
| 6501 |
$line++; |
$p->{line}++; |
| 6502 |
$column = 0; |
$p->{column} = 0; |
| 6503 |
!!!cp ('i1'); |
!!!cp ('i1'); |
| 6504 |
} elsif ($self->{next_char} == 0x000D) { # CR |
} elsif ($self->{next_char} == 0x000D) { # CR |
| 6505 |
$i++ if substr ($$s, $i, 1) eq "\x0A"; |
$i++ if substr ($$s, $i, 1) eq "\x0A"; |
| 6506 |
$self->{next_char} = 0x000A; # LF # MUST |
$self->{next_char} = 0x000A; # LF # MUST |
| 6507 |
$line++; |
$p->{line}++; |
| 6508 |
$column = 0; |
$p->{column} = 0; |
| 6509 |
!!!cp ('i2'); |
!!!cp ('i2'); |
| 6510 |
} elsif ($self->{next_char} > 0x10FFFF) { |
} elsif ($self->{next_char} > 0x10FFFF) { |
| 6511 |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
| 6521 |
|
|
| 6522 |
my $ponerror = $onerror || sub { |
my $ponerror = $onerror || sub { |
| 6523 |
my (%opt) = @_; |
my (%opt) = @_; |
| 6524 |
warn "Parse error ($opt{type}) at line $opt{line} column $opt{column}\n"; |
my $line = $opt{line}; |
| 6525 |
|
my $column = $opt{column}; |
| 6526 |
|
if (defined $opt{token} and defined $opt{token}->{line}) { |
| 6527 |
|
$line = $opt{token}->{line}; |
| 6528 |
|
$column = $opt{token}->{column}; |
| 6529 |
|
} |
| 6530 |
|
warn "Parse error ($opt{type}) at line $line column $column\n"; |
| 6531 |
}; |
}; |
| 6532 |
$p->{parse_error} = sub { |
$p->{parse_error} = sub { |
| 6533 |
$ponerror->(@_, line => $line, column => $column); |
$ponerror->(line => $p->{line}, column => $p->{column}, @_); |
| 6534 |
}; |
}; |
| 6535 |
|
|
| 6536 |
$p->_initialize_tokenizer; |
$p->_initialize_tokenizer; |
| 6556 |
|
|
| 6557 |
$p->{inner_html_node} = [$node, $node_ln]; |
$p->{inner_html_node} = [$node, $node_ln]; |
| 6558 |
|
|
| 6559 |
## Step 4 |
## Step 3 |
| 6560 |
my $root = $doc->create_element_ns |
my $root = $doc->create_element_ns |
| 6561 |
('http://www.w3.org/1999/xhtml', [undef, 'html']); |
('http://www.w3.org/1999/xhtml', [undef, 'html']); |
| 6562 |
|
|
| 6563 |
## Step 5 # MUST |
## Step 4 # MUST |
| 6564 |
$doc->append_child ($root); |
$doc->append_child ($root); |
| 6565 |
|
|
| 6566 |
## Step 6 # MUST |
## Step 5 # MUST |
| 6567 |
push @{$p->{open_elements}}, [$root, 'html']; |
push @{$p->{open_elements}}, [$root, 'html']; |
| 6568 |
|
|
| 6569 |
undef $p->{head_element}; |
undef $p->{head_element}; |
| 6570 |
|
|
| 6571 |
## Step 7 # MUST |
## Step 6 # MUST |
| 6572 |
$p->_reset_insertion_mode; |
$p->_reset_insertion_mode; |
| 6573 |
|
|
| 6574 |
## Step 8 # MUST |
## Step 7 # MUST |
| 6575 |
my $anode = $node; |
my $anode = $node; |
| 6576 |
AN: while (defined $anode) { |
AN: while (defined $anode) { |
| 6577 |
if ($anode->node_type == 1) { |
if ($anode->node_type == 1) { |
| 6587 |
$anode = $anode->parent_node; |
$anode = $anode->parent_node; |
| 6588 |
} # AN |
} # AN |
| 6589 |
|
|
| 6590 |
## Step 3 # MUST |
## Step 9 # MUST |
|
## Step 10 # MUST |
|
| 6591 |
{ |
{ |
| 6592 |
my $self = $p; |
my $self = $p; |
| 6593 |
!!!next-token; |
!!!next-token; |
| 6594 |
} |
} |
| 6595 |
$p->_tree_construction_main; |
$p->_tree_construction_main; |
| 6596 |
|
|
| 6597 |
## Step 11 # MUST |
## Step 10 # MUST |
| 6598 |
my @cn = @{$node->child_nodes}; |
my @cn = @{$node->child_nodes}; |
| 6599 |
for (@cn) { |
for (@cn) { |
| 6600 |
$node->remove_child ($_); |
$node->remove_child ($_); |
| 6601 |
} |
} |
| 6602 |
## ISSUE: mutation events? read-only? |
## ISSUE: mutation events? read-only? |
| 6603 |
|
|
| 6604 |
## Step 12 # MUST |
## Step 11 # MUST |
| 6605 |
@cn = @{$root->child_nodes}; |
@cn = @{$root->child_nodes}; |
| 6606 |
for (@cn) { |
for (@cn) { |
| 6607 |
$this_doc->adopt_node ($_); |
$this_doc->adopt_node ($_); |
| 6610 |
## ISSUE: mutation events? |
## ISSUE: mutation events? |
| 6611 |
|
|
| 6612 |
$p->_terminate_tree_constructor; |
$p->_terminate_tree_constructor; |
| 6613 |
|
|
| 6614 |
|
delete $p->{parse_error}; # delete loop |
| 6615 |
} else { |
} else { |
| 6616 |
die "$0: |set_inner_html| is not defined for node of type $nt"; |
die "$0: |set_inner_html| is not defined for node of type $nt"; |
| 6617 |
} |
} |