| 177 |
if defined $self->{input_encoding}; |
if defined $self->{input_encoding}; |
| 178 |
|
|
| 179 |
my $i = 0; |
my $i = 0; |
| 180 |
my $line = 1; |
$self->{line_prev} = $self->{line} = 1; |
| 181 |
my $column = 0; |
$self->{column_prev} = $self->{column} = 0; |
| 182 |
$self->{set_next_char} = sub { |
$self->{set_next_char} = sub { |
| 183 |
my $self = shift; |
my $self = shift; |
| 184 |
|
|
| 187 |
|
|
| 188 |
$self->{next_char} = -1 and return if $i >= length $$s; |
$self->{next_char} = -1 and return if $i >= length $$s; |
| 189 |
$self->{next_char} = ord substr $$s, $i++, 1; |
$self->{next_char} = ord substr $$s, $i++, 1; |
| 190 |
$column++; |
|
| 191 |
|
($self->{line_prev}, $self->{column_prev}) |
| 192 |
|
= ($self->{line}, $self->{column}); |
| 193 |
|
$self->{column}++; |
| 194 |
|
|
| 195 |
if ($self->{next_char} == 0x000A) { # LF |
if ($self->{next_char} == 0x000A) { # LF |
| 196 |
$line++; |
$self->{line}++; |
| 197 |
$column = 0; |
$self->{column} = 0; |
| 198 |
} elsif ($self->{next_char} == 0x000D) { # CR |
} elsif ($self->{next_char} == 0x000D) { # CR |
| 199 |
$i++ if substr ($$s, $i, 1) eq "\x0A"; |
$i++ if substr ($$s, $i, 1) eq "\x0A"; |
| 200 |
$self->{next_char} = 0x000A; # LF # MUST |
$self->{next_char} = 0x000A; # LF # MUST |
| 201 |
$line++; |
$self->{line}++; |
| 202 |
$column = 0; |
$self->{column} = 0; |
| 203 |
} elsif ($self->{next_char} > 0x10FFFF) { |
} elsif ($self->{next_char} > 0x10FFFF) { |
| 204 |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
| 205 |
} elsif ($self->{next_char} == 0x0000) { # NULL |
} elsif ($self->{next_char} == 0x0000) { # NULL |
| 212 |
|
|
| 213 |
my $onerror = $_[2] || sub { |
my $onerror = $_[2] || sub { |
| 214 |
my (%opt) = @_; |
my (%opt) = @_; |
| 215 |
warn "Parse error ($opt{type}) at line $opt{line} column $opt{column}\n"; |
my $line = $opt{token} ? $opt{token}->{line} : $opt{line}; |
| 216 |
|
my $column = $opt{token} ? $opt{token}->{column} : $opt{column}; |
| 217 |
|
warn "Parse error ($opt{type}) at line $line column $column\n"; |
| 218 |
}; |
}; |
| 219 |
$self->{parse_error} = sub { |
$self->{parse_error} = sub { |
| 220 |
$onerror->(@_, line => $line, column => $column); |
$onerror->(line => $self->{line}, column => $self->{column}, @_); |
| 221 |
}; |
}; |
| 222 |
|
|
| 223 |
$self->_initialize_tokenizer; |
$self->_initialize_tokenizer; |
| 225 |
$self->_construct_tree; |
$self->_construct_tree; |
| 226 |
$self->_terminate_tree_constructor; |
$self->_terminate_tree_constructor; |
| 227 |
|
|
| 228 |
|
delete $self->{parse_error}; # remove loop |
| 229 |
|
|
| 230 |
return $self->{document}; |
return $self->{document}; |
| 231 |
} # parse_string |
} # parse_string |
| 232 |
|
|
| 456 |
# |
# |
| 457 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 458 |
!!!cp (11); |
!!!cp (11); |
| 459 |
!!!emit ({type => END_OF_FILE_TOKEN}); |
!!!emit ({type => END_OF_FILE_TOKEN, |
| 460 |
|
line => $self->{line}, column => $self->{column}}); |
| 461 |
last A; ## TODO: ok? |
last A; ## TODO: ok? |
| 462 |
} else { |
} else { |
| 463 |
!!!cp (12); |
!!!cp (12); |
| 464 |
} |
} |
| 465 |
# Anything else |
# Anything else |
| 466 |
my $token = {type => CHARACTER_TOKEN, |
my $token = {type => CHARACTER_TOKEN, |
| 467 |
data => chr $self->{next_char}}; |
data => chr $self->{next_char}, |
| 468 |
|
line => $self->{line}, column => $self->{column}}; |
| 469 |
## Stay in the data state |
## Stay in the data state |
| 470 |
!!!next-input-character; |
!!!next-input-character; |
| 471 |
|
|
| 474 |
redo A; |
redo A; |
| 475 |
} elsif ($self->{state} == ENTITY_DATA_STATE) { |
} elsif ($self->{state} == ENTITY_DATA_STATE) { |
| 476 |
## (cannot happen in CDATA state) |
## (cannot happen in CDATA state) |
| 477 |
|
|
| 478 |
|
my ($l, $c) = ($self->{line_prev}, $self->{column_prev}); |
| 479 |
|
|
| 480 |
my $token = $self->_tokenize_attempt_to_consume_an_entity (0, -1); |
my $token = $self->_tokenize_attempt_to_consume_an_entity (0, -1); |
| 481 |
|
|
| 484 |
|
|
| 485 |
unless (defined $token) { |
unless (defined $token) { |
| 486 |
!!!cp (13); |
!!!cp (13); |
| 487 |
!!!emit ({type => CHARACTER_TOKEN, data => '&'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '&', |
| 488 |
|
line => $l, column => $c}); |
| 489 |
} else { |
} else { |
| 490 |
!!!cp (14); |
!!!cp (14); |
| 491 |
!!!emit ($token); |
!!!emit ($token); |
| 504 |
## reconsume |
## reconsume |
| 505 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 506 |
|
|
| 507 |
!!!emit ({type => CHARACTER_TOKEN, data => '<'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '<', |
| 508 |
|
line => $self->{line_prev}, |
| 509 |
|
column => $self->{column_prev}}); |
| 510 |
|
|
| 511 |
redo A; |
redo A; |
| 512 |
} |
} |
| 526 |
!!!cp (19); |
!!!cp (19); |
| 527 |
$self->{current_token} |
$self->{current_token} |
| 528 |
= {type => START_TAG_TOKEN, |
= {type => START_TAG_TOKEN, |
| 529 |
tag_name => chr ($self->{next_char} + 0x0020)}; |
tag_name => chr ($self->{next_char} + 0x0020), |
| 530 |
|
line => $self->{line_prev}, |
| 531 |
|
column => $self->{column_prev}}; |
| 532 |
$self->{state} = TAG_NAME_STATE; |
$self->{state} = TAG_NAME_STATE; |
| 533 |
!!!next-input-character; |
!!!next-input-character; |
| 534 |
redo A; |
redo A; |
| 536 |
$self->{next_char} <= 0x007A) { # a..z |
$self->{next_char} <= 0x007A) { # a..z |
| 537 |
!!!cp (20); |
!!!cp (20); |
| 538 |
$self->{current_token} = {type => START_TAG_TOKEN, |
$self->{current_token} = {type => START_TAG_TOKEN, |
| 539 |
tag_name => chr ($self->{next_char})}; |
tag_name => chr ($self->{next_char}), |
| 540 |
|
line => $self->{line_prev}, |
| 541 |
|
column => $self->{column_prev}}; |
| 542 |
$self->{state} = TAG_NAME_STATE; |
$self->{state} = TAG_NAME_STATE; |
| 543 |
!!!next-input-character; |
!!!next-input-character; |
| 544 |
redo A; |
redo A; |
| 548 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 549 |
!!!next-input-character; |
!!!next-input-character; |
| 550 |
|
|
| 551 |
!!!emit ({type => CHARACTER_TOKEN, data => '<>'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '<>', |
| 552 |
|
line => $self->{line_prev}, |
| 553 |
|
column => $self->{column_prev}}); |
| 554 |
|
|
| 555 |
redo A; |
redo A; |
| 556 |
} elsif ($self->{next_char} == 0x003F) { # ? |
} elsif ($self->{next_char} == 0x003F) { # ? |
| 557 |
!!!cp (22); |
!!!cp (22); |
| 558 |
!!!parse-error (type => 'pio'); |
!!!parse-error (type => 'pio'); |
| 559 |
$self->{state} = BOGUS_COMMENT_STATE; |
$self->{state} = BOGUS_COMMENT_STATE; |
| 560 |
|
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
| 561 |
|
line => $self->{line_prev}, |
| 562 |
|
column => $self->{column_prev}}; |
| 563 |
## $self->{next_char} is intentionally left as is |
## $self->{next_char} is intentionally left as is |
| 564 |
redo A; |
redo A; |
| 565 |
} else { |
} else { |
| 568 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 569 |
## reconsume |
## reconsume |
| 570 |
|
|
| 571 |
!!!emit ({type => CHARACTER_TOKEN, data => '<'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '<', |
| 572 |
|
line => $self->{line_prev}, |
| 573 |
|
column => $self->{column_prev}}); |
| 574 |
|
|
| 575 |
redo A; |
redo A; |
| 576 |
} |
} |
| 578 |
die "$0: $self->{content_model} in tag open"; |
die "$0: $self->{content_model} in tag open"; |
| 579 |
} |
} |
| 580 |
} elsif ($self->{state} == CLOSE_TAG_OPEN_STATE) { |
} elsif ($self->{state} == CLOSE_TAG_OPEN_STATE) { |
| 581 |
|
my ($l, $c) = ($self->{line_prev}, $self->{column_prev}); |
| 582 |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
| 583 |
if (defined $self->{last_emitted_start_tag_name}) { |
if (defined $self->{last_emitted_start_tag_name}) { |
| 584 |
|
|
| 585 |
## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564> |
## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564> |
| 586 |
my @next_char; |
my @next_char; |
| 587 |
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++) { |
| 598 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 599 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 600 |
|
|
| 601 |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</', |
| 602 |
|
line => $l, column => $c}); |
| 603 |
|
|
| 604 |
redo A; |
redo A; |
| 605 |
} |
} |
| 618 |
$self->{next_char} = shift @next_char; # reconsume |
$self->{next_char} = shift @next_char; # reconsume |
| 619 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 620 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 621 |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</', |
| 622 |
|
line => $l, column => $c}); |
| 623 |
redo A; |
redo A; |
| 624 |
} else { |
} else { |
| 625 |
!!!cp (27); |
!!!cp (27); |
| 632 |
!!!cp (28); |
!!!cp (28); |
| 633 |
# next-input-character is already done |
# next-input-character is already done |
| 634 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 635 |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</', |
| 636 |
|
line => $l, column => $c}); |
| 637 |
redo A; |
redo A; |
| 638 |
} |
} |
| 639 |
} |
} |
| 641 |
if (0x0041 <= $self->{next_char} and |
if (0x0041 <= $self->{next_char} and |
| 642 |
$self->{next_char} <= 0x005A) { # A..Z |
$self->{next_char} <= 0x005A) { # A..Z |
| 643 |
!!!cp (29); |
!!!cp (29); |
| 644 |
$self->{current_token} = {type => END_TAG_TOKEN, |
$self->{current_token} |
| 645 |
tag_name => chr ($self->{next_char} + 0x0020)}; |
= {type => END_TAG_TOKEN, |
| 646 |
|
tag_name => chr ($self->{next_char} + 0x0020), |
| 647 |
|
line => $l, column => $c}; |
| 648 |
$self->{state} = TAG_NAME_STATE; |
$self->{state} = TAG_NAME_STATE; |
| 649 |
!!!next-input-character; |
!!!next-input-character; |
| 650 |
redo A; |
redo A; |
| 652 |
$self->{next_char} <= 0x007A) { # a..z |
$self->{next_char} <= 0x007A) { # a..z |
| 653 |
!!!cp (30); |
!!!cp (30); |
| 654 |
$self->{current_token} = {type => END_TAG_TOKEN, |
$self->{current_token} = {type => END_TAG_TOKEN, |
| 655 |
tag_name => chr ($self->{next_char})}; |
tag_name => chr ($self->{next_char}), |
| 656 |
|
line => $l, column => $c}; |
| 657 |
$self->{state} = TAG_NAME_STATE; |
$self->{state} = TAG_NAME_STATE; |
| 658 |
!!!next-input-character; |
!!!next-input-character; |
| 659 |
redo A; |
redo A; |
| 669 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 670 |
# reconsume |
# reconsume |
| 671 |
|
|
| 672 |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</', |
| 673 |
|
line => $l, column => $c}); |
| 674 |
|
|
| 675 |
redo A; |
redo A; |
| 676 |
} else { |
} else { |
| 677 |
!!!cp (33); |
!!!cp (33); |
| 678 |
!!!parse-error (type => 'bogus end tag'); |
!!!parse-error (type => 'bogus end tag'); |
| 679 |
$self->{state} = BOGUS_COMMENT_STATE; |
$self->{state} = BOGUS_COMMENT_STATE; |
| 680 |
|
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
| 681 |
|
line => $self->{line_prev}, # "<" of "</" |
| 682 |
|
column => $self->{column_prev} - 1}; |
| 683 |
## $self->{next_char} is intentionally left as is |
## $self->{next_char} is intentionally left as is |
| 684 |
redo A; |
redo A; |
| 685 |
} |
} |
| 1416 |
} elsif ($self->{state} == BOGUS_COMMENT_STATE) { |
} elsif ($self->{state} == BOGUS_COMMENT_STATE) { |
| 1417 |
## (only happen if PCDATA state) |
## (only happen if PCDATA state) |
| 1418 |
|
|
| 1419 |
my $token = {type => COMMENT_TOKEN, data => ''}; |
## NOTE: Set by the previous state |
| 1420 |
|
#my $token = {type => COMMENT_TOKEN, data => ''}; |
| 1421 |
|
|
| 1422 |
BC: { |
BC: { |
| 1423 |
if ($self->{next_char} == 0x003E) { # > |
if ($self->{next_char} == 0x003E) { # > |
| 1425 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1426 |
!!!next-input-character; |
!!!next-input-character; |
| 1427 |
|
|
| 1428 |
!!!emit ($token); |
!!!emit ($self->{current_token}); # comment |
| 1429 |
|
|
| 1430 |
redo A; |
redo A; |
| 1431 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 1433 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1434 |
## reconsume |
## reconsume |
| 1435 |
|
|
| 1436 |
!!!emit ($token); |
!!!emit ($self->{current_token}); # comment |
| 1437 |
|
|
| 1438 |
redo A; |
redo A; |
| 1439 |
} else { |
} else { |
| 1440 |
!!!cp (126); |
!!!cp (126); |
| 1441 |
$token->{data} .= chr ($self->{next_char}); |
$self->{current_token}->{data} .= chr ($self->{next_char}); # comment |
| 1442 |
!!!next-input-character; |
!!!next-input-character; |
| 1443 |
redo BC; |
redo BC; |
| 1444 |
} |
} |
| 1448 |
} elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) { |
} elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) { |
| 1449 |
## (only happen if PCDATA state) |
## (only happen if PCDATA state) |
| 1450 |
|
|
| 1451 |
|
my ($l, $c) = ($self->{line_prev}, $self->{column_prev} - 1); |
| 1452 |
|
|
| 1453 |
my @next_char; |
my @next_char; |
| 1454 |
push @next_char, $self->{next_char}; |
push @next_char, $self->{next_char}; |
| 1455 |
|
|
| 1458 |
push @next_char, $self->{next_char}; |
push @next_char, $self->{next_char}; |
| 1459 |
if ($self->{next_char} == 0x002D) { # - |
if ($self->{next_char} == 0x002D) { # - |
| 1460 |
!!!cp (127); |
!!!cp (127); |
| 1461 |
$self->{current_token} = {type => COMMENT_TOKEN, data => ''}; |
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
| 1462 |
|
line => $l, column => $c}; |
| 1463 |
$self->{state} = COMMENT_START_STATE; |
$self->{state} = COMMENT_START_STATE; |
| 1464 |
!!!next-input-character; |
!!!next-input-character; |
| 1465 |
redo A; |
redo A; |
| 1495 |
!!!cp (129); |
!!!cp (129); |
| 1496 |
## TODO: What a stupid code this is! |
## TODO: What a stupid code this is! |
| 1497 |
$self->{state} = DOCTYPE_STATE; |
$self->{state} = DOCTYPE_STATE; |
| 1498 |
|
$self->{current_token} = {type => DOCTYPE_TOKEN, |
| 1499 |
|
quirks => 1, |
| 1500 |
|
line => $l, column => $c}; |
| 1501 |
!!!next-input-character; |
!!!next-input-character; |
| 1502 |
redo A; |
redo A; |
| 1503 |
} else { |
} else { |
| 1526 |
$self->{next_char} = shift @next_char; |
$self->{next_char} = shift @next_char; |
| 1527 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 1528 |
$self->{state} = BOGUS_COMMENT_STATE; |
$self->{state} = BOGUS_COMMENT_STATE; |
| 1529 |
|
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
| 1530 |
|
line => $l, column => $c}; |
| 1531 |
redo A; |
redo A; |
| 1532 |
|
|
| 1533 |
## ISSUE: typos in spec: chacacters, is is a parse error |
## ISSUE: typos in spec: chacacters, is is a parse error |
| 1706 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1707 |
!!!next-input-character; |
!!!next-input-character; |
| 1708 |
|
|
| 1709 |
!!!emit ({type => DOCTYPE_TOKEN, quirks => 1}); |
!!!emit ($self->{current_token}); # DOCTYPE (quirks) |
| 1710 |
|
|
| 1711 |
redo A; |
redo A; |
| 1712 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 1715 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1716 |
## reconsume |
## reconsume |
| 1717 |
|
|
| 1718 |
!!!emit ({type => DOCTYPE_TOKEN, quirks => 1}); |
!!!emit ($self->{current_token}); # DOCTYPE (quirks) |
| 1719 |
|
|
| 1720 |
redo A; |
redo A; |
| 1721 |
} else { |
} else { |
| 1722 |
!!!cp (160); |
!!!cp (160); |
| 1723 |
$self->{current_token} |
$self->{current_token}->{name} = chr $self->{next_char}; |
| 1724 |
= {type => DOCTYPE_TOKEN, |
delete $self->{current_token}->{quirks}; |
|
name => chr ($self->{next_char}), |
|
|
#quirks => 0, |
|
|
}; |
|
| 1725 |
## ISSUE: "Set the token's name name to the" in the spec |
## ISSUE: "Set the token's name name to the" in the spec |
| 1726 |
$self->{state} = DOCTYPE_NAME_STATE; |
$self->{state} = DOCTYPE_NAME_STATE; |
| 1727 |
!!!next-input-character; |
!!!next-input-character; |
| 2248 |
sub _tokenize_attempt_to_consume_an_entity ($$$) { |
sub _tokenize_attempt_to_consume_an_entity ($$$) { |
| 2249 |
my ($self, $in_attr, $additional) = @_; |
my ($self, $in_attr, $additional) = @_; |
| 2250 |
|
|
| 2251 |
|
my ($l, $c) = ($self->{line_prev}, $self->{column_prev}); |
| 2252 |
|
|
| 2253 |
if ({ |
if ({ |
| 2254 |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, # HT, LF, VT, FF, |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, # HT, LF, VT, FF, |
| 2255 |
0x0020 => 1, 0x003C => 1, 0x0026 => 1, -1 => 1, # SP, <, & # 0x000D # CR |
0x0020 => 1, 0x003C => 1, 0x0026 => 1, -1 => 1, # SP, <, & # 0x000D # CR |
| 2290 |
redo X; |
redo X; |
| 2291 |
} elsif (not defined $code) { # no hexadecimal digit |
} elsif (not defined $code) { # no hexadecimal digit |
| 2292 |
!!!cp (1005); |
!!!cp (1005); |
| 2293 |
!!!parse-error (type => 'bare hcro'); |
!!!parse-error (type => 'bare hcro', line => $l, column => $c); |
| 2294 |
!!!back-next-input-character ($x_char, $self->{next_char}); |
!!!back-next-input-character ($x_char, $self->{next_char}); |
| 2295 |
$self->{next_char} = 0x0023; # # |
$self->{next_char} = 0x0023; # # |
| 2296 |
return undef; |
return undef; |
| 2299 |
!!!next-input-character; |
!!!next-input-character; |
| 2300 |
} else { |
} else { |
| 2301 |
!!!cp (1007); |
!!!cp (1007); |
| 2302 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'no refc', line => $l, column => $c); |
| 2303 |
} |
} |
| 2304 |
|
|
| 2305 |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 2306 |
!!!cp (1008); |
!!!cp (1008); |
| 2307 |
!!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code); |
!!!parse-error (type => (sprintf 'invalid character reference:U+%04X', $code), line => $l, column => $c); |
| 2308 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 2309 |
} elsif ($code > 0x10FFFF) { |
} elsif ($code > 0x10FFFF) { |
| 2310 |
!!!cp (1009); |
!!!cp (1009); |
| 2311 |
!!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code); |
!!!parse-error (type => (sprintf 'invalid character reference:U-%08X', $code), line => $l, column => $c); |
| 2312 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 2313 |
} elsif ($code == 0x000D) { |
} elsif ($code == 0x000D) { |
| 2314 |
!!!cp (1010); |
!!!cp (1010); |
| 2315 |
!!!parse-error (type => 'CR character reference'); |
!!!parse-error (type => 'CR character reference', line => $l, column => $c); |
| 2316 |
$code = 0x000A; |
$code = 0x000A; |
| 2317 |
} elsif (0x80 <= $code and $code <= 0x9F) { |
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 2318 |
!!!cp (1011); |
!!!cp (1011); |
| 2319 |
!!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code); |
!!!parse-error (type => (sprintf 'C1 character reference:U+%04X', $code), line => $l, column => $c); |
| 2320 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 2321 |
} |
} |
| 2322 |
|
|
| 2323 |
return {type => CHARACTER_TOKEN, data => chr $code, |
return {type => CHARACTER_TOKEN, data => chr $code, |
| 2324 |
has_reference => 1}; |
has_reference => 1, line => $l, column => $c}; |
| 2325 |
} # X |
} # X |
| 2326 |
} elsif (0x0030 <= $self->{next_char} and |
} elsif (0x0030 <= $self->{next_char} and |
| 2327 |
$self->{next_char} <= 0x0039) { # 0..9 |
$self->{next_char} <= 0x0039) { # 0..9 |
| 2342 |
!!!next-input-character; |
!!!next-input-character; |
| 2343 |
} else { |
} else { |
| 2344 |
!!!cp (1014); |
!!!cp (1014); |
| 2345 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'no refc', line => $l, column => $c); |
| 2346 |
} |
} |
| 2347 |
|
|
| 2348 |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 2349 |
!!!cp (1015); |
!!!cp (1015); |
| 2350 |
!!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code); |
!!!parse-error (type => (sprintf 'invalid character reference:U+%04X', $code), line => $l, column => $c); |
| 2351 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 2352 |
} elsif ($code > 0x10FFFF) { |
} elsif ($code > 0x10FFFF) { |
| 2353 |
!!!cp (1016); |
!!!cp (1016); |
| 2354 |
!!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code); |
!!!parse-error (type => (sprintf 'invalid character reference:U-%08X', $code), line => $l, column => $c); |
| 2355 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 2356 |
} elsif ($code == 0x000D) { |
} elsif ($code == 0x000D) { |
| 2357 |
!!!cp (1017); |
!!!cp (1017); |
| 2358 |
!!!parse-error (type => 'CR character reference'); |
!!!parse-error (type => 'CR character reference', line => $l, column => $c); |
| 2359 |
$code = 0x000A; |
$code = 0x000A; |
| 2360 |
} elsif (0x80 <= $code and $code <= 0x9F) { |
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 2361 |
!!!cp (1018); |
!!!cp (1018); |
| 2362 |
!!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code); |
!!!parse-error (type => (sprintf 'C1 character reference:U+%04X', $code), line => $l, column => $c); |
| 2363 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 2364 |
} |
} |
| 2365 |
|
|
| 2366 |
return {type => CHARACTER_TOKEN, data => chr $code, has_reference => 1}; |
return {type => CHARACTER_TOKEN, data => chr $code, has_reference => 1, |
| 2367 |
|
line => $l, column => $c}; |
| 2368 |
} else { |
} else { |
| 2369 |
!!!cp (1019); |
!!!cp (1019); |
| 2370 |
!!!parse-error (type => 'bare nero'); |
!!!parse-error (type => 'bare nero', line => $l, column => $c); |
| 2371 |
!!!back-next-input-character ($self->{next_char}); |
!!!back-next-input-character ($self->{next_char}); |
| 2372 |
$self->{next_char} = 0x0023; # # |
$self->{next_char} = 0x0023; # # |
| 2373 |
return undef; |
return undef; |
| 2417 |
|
|
| 2418 |
if ($match > 0) { |
if ($match > 0) { |
| 2419 |
!!!cp (1023); |
!!!cp (1023); |
| 2420 |
return {type => CHARACTER_TOKEN, data => $value, has_reference => 1}; |
return {type => CHARACTER_TOKEN, data => $value, has_reference => 1, |
| 2421 |
|
line => $l, column => $c}; |
| 2422 |
} elsif ($match < 0) { |
} elsif ($match < 0) { |
| 2423 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'no refc', line => $l, column => $c); |
| 2424 |
if ($in_attr and $match < -1) { |
if ($in_attr and $match < -1) { |
| 2425 |
!!!cp (1024); |
!!!cp (1024); |
| 2426 |
return {type => CHARACTER_TOKEN, data => '&'.$entity_name}; |
return {type => CHARACTER_TOKEN, data => '&'.$entity_name, |
| 2427 |
|
line => $l, column => $c}; |
| 2428 |
} else { |
} else { |
| 2429 |
!!!cp (1025); |
!!!cp (1025); |
| 2430 |
return {type => CHARACTER_TOKEN, data => $value, has_reference => 1}; |
return {type => CHARACTER_TOKEN, data => $value, has_reference => 1, |
| 2431 |
|
line => $l, column => $c}; |
| 2432 |
} |
} |
| 2433 |
} else { |
} else { |
| 2434 |
!!!cp (1026); |
!!!cp (1026); |
| 2435 |
!!!parse-error (type => 'bare ero'); |
!!!parse-error (type => 'bare ero', line => $l, column => $c); |
| 2436 |
## NOTE: "No characters are consumed" in the spec. |
## NOTE: "No characters are consumed" in the spec. |
| 2437 |
return {type => CHARACTER_TOKEN, data => '&'.$value}; |
return {type => CHARACTER_TOKEN, data => '&'.$value, |
| 2438 |
|
line => $l, column => $c}; |
| 2439 |
} |
} |
| 2440 |
} else { |
} else { |
| 2441 |
!!!cp (1027); |
!!!cp (1027); |
| 2442 |
## no characters are consumed |
## no characters are consumed |
| 2443 |
!!!parse-error (type => 'bare ero'); |
!!!parse-error (type => 'bare ero', line => $l, column => $c); |
| 2444 |
return undef; |
return undef; |
| 2445 |
} |
} |
| 2446 |
} # _tokenize_attempt_to_consume_an_entity |
} # _tokenize_attempt_to_consume_an_entity |
| 3343 |
## Stay in the phase |
## Stay in the phase |
| 3344 |
!!!next-token; |
!!!next-token; |
| 3345 |
redo B; |
redo B; |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
|
|
if ($self->{insertion_mode} & AFTER_HTML_IMS) { |
|
|
!!!cp ('t74'); |
|
|
# |
|
|
} else { |
|
|
## Generate implied end tags |
|
|
while ({ |
|
|
dd => 1, dt => 1, li => 1, p => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!cp ('t75'); |
|
|
pop @{$self->{open_elements}}; |
|
|
} |
|
|
|
|
|
if (@{$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; |
|
| 3346 |
} elsif ($token->{type} == START_TAG_TOKEN and |
} elsif ($token->{type} == START_TAG_TOKEN and |
| 3347 |
$token->{tag_name} eq 'html') { |
$token->{tag_name} eq 'html') { |
| 3348 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 3861 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 3862 |
## reprocess |
## reprocess |
| 3863 |
redo B; |
redo B; |
| 3864 |
} else { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 3865 |
die "$0: $token->{type}: Unknown token type"; |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3866 |
} |
!!!cp ('t149.1'); |
| 3867 |
|
|
| 3868 |
|
## NOTE: As if <head> |
| 3869 |
|
!!!create-element ($self->{head_element}, 'head'); |
| 3870 |
|
$self->{open_elements}->[-1]->[0]->append_child |
| 3871 |
|
($self->{head_element}); |
| 3872 |
|
#push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3873 |
|
#$self->{insertion_mode} = IN_HEAD_IM; |
| 3874 |
|
## NOTE: Reprocess. |
| 3875 |
|
|
| 3876 |
|
## NOTE: As if </head> |
| 3877 |
|
#pop @{$self->{open_elements}}; |
| 3878 |
|
#$self->{insertion_mode} = IN_AFTER_HEAD_IM; |
| 3879 |
|
## NOTE: Reprocess. |
| 3880 |
|
|
| 3881 |
|
# |
| 3882 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 3883 |
|
!!!cp ('t149.2'); |
| 3884 |
|
|
| 3885 |
|
## NOTE: As if </head> |
| 3886 |
|
pop @{$self->{open_elements}}; |
| 3887 |
|
#$self->{insertion_mode} = IN_AFTER_HEAD_IM; |
| 3888 |
|
## NOTE: Reprocess. |
| 3889 |
|
|
| 3890 |
|
# |
| 3891 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 3892 |
|
!!!cp ('t149.3'); |
| 3893 |
|
|
| 3894 |
|
!!!parse-error (type => 'in noscript:#eof'); |
| 3895 |
|
|
| 3896 |
|
## As if </noscript> |
| 3897 |
|
pop @{$self->{open_elements}}; |
| 3898 |
|
#$self->{insertion_mode} = IN_HEAD_IM; |
| 3899 |
|
## NOTE: Reprocess. |
| 3900 |
|
|
| 3901 |
|
## NOTE: As if </head> |
| 3902 |
|
pop @{$self->{open_elements}}; |
| 3903 |
|
#$self->{insertion_mode} = IN_AFTER_HEAD_IM; |
| 3904 |
|
## NOTE: Reprocess. |
| 3905 |
|
|
| 3906 |
|
# |
| 3907 |
|
} else { |
| 3908 |
|
!!!cp ('t149.4'); |
| 3909 |
|
# |
| 3910 |
|
} |
| 3911 |
|
|
| 3912 |
|
## NOTE: As if <body> |
| 3913 |
|
!!!insert-element ('body'); |
| 3914 |
|
$self->{insertion_mode} = IN_BODY_IM; |
| 3915 |
|
## NOTE: Reprocess. |
| 3916 |
|
redo B; |
| 3917 |
|
} else { |
| 3918 |
|
die "$0: $token->{type}: Unknown token type"; |
| 3919 |
|
} |
| 3920 |
|
|
| 3921 |
## ISSUE: An issue in the spec. |
## ISSUE: An issue in the spec. |
| 3922 |
} elsif ($self->{insertion_mode} & BODY_IMS) { |
} elsif ($self->{insertion_mode} & BODY_IMS) { |
| 3936 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 3937 |
if ($self->{insertion_mode} == IN_CELL_IM) { |
if ($self->{insertion_mode} == IN_CELL_IM) { |
| 3938 |
## have an element in table scope |
## have an element in table scope |
| 3939 |
my $tn; |
for (reverse 0..$#{$self->{open_elements}}) { |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
| 3940 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 3941 |
if ($node->[1] eq 'td' or $node->[1] eq 'th') { |
if ($node->[1] eq 'td' or $node->[1] eq 'th') { |
| 3942 |
!!!cp ('t151'); |
!!!cp ('t151'); |
| 3943 |
$tn = $node->[1]; |
|
| 3944 |
last INSCOPE; |
## Close the cell |
| 3945 |
|
!!!back-token; # <?> |
| 3946 |
|
$token = {type => END_TAG_TOKEN, tag_name => $node->[1]}; |
| 3947 |
|
redo B; |
| 3948 |
} elsif ({ |
} elsif ({ |
| 3949 |
table => 1, html => 1, |
table => 1, html => 1, |
| 3950 |
}->{$node->[1]}) { |
}->{$node->[1]}) { |
| 3951 |
!!!cp ('t152'); |
!!!cp ('t152'); |
| 3952 |
last INSCOPE; |
## ISSUE: This case can never be reached, maybe. |
| 3953 |
} |
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; |
|
| 3954 |
} |
} |
| 3955 |
|
} |
| 3956 |
!!!cp ('t154'); |
|
| 3957 |
## Close the cell |
!!!cp ('t153'); |
| 3958 |
!!!back-token; # <?> |
!!!parse-error (type => 'start tag not allowed', |
| 3959 |
$token = {type => END_TAG_TOKEN, tag_name => $tn}; |
value => $token->{tag_name}); |
| 3960 |
|
## Ignore the token |
| 3961 |
|
!!!next-token; |
| 3962 |
redo B; |
redo B; |
| 3963 |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 3964 |
!!!parse-error (type => 'not closed:caption'); |
!!!parse-error (type => 'not closed:caption'); |
| 3965 |
|
|
| 3966 |
## As if </caption> |
## NOTE: As if </caption>. |
| 3967 |
## have a table element in table scope |
## have a table element in table scope |
| 3968 |
my $i; |
my $i; |
| 3969 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: { |
| 3970 |
my $node = $self->{open_elements}->[$_]; |
for (reverse 0..$#{$self->{open_elements}}) { |
| 3971 |
if ($node->[1] eq 'caption') { |
my $node = $self->{open_elements}->[$_]; |
| 3972 |
!!!cp ('t155'); |
if ($node->[1] eq 'caption') { |
| 3973 |
$i = $_; |
!!!cp ('t155'); |
| 3974 |
last INSCOPE; |
$i = $_; |
| 3975 |
} elsif ({ |
last INSCOPE; |
| 3976 |
table => 1, html => 1, |
} elsif ({ |
| 3977 |
}->{$node->[1]}) { |
table => 1, html => 1, |
| 3978 |
!!!cp ('t156'); |
}->{$node->[1]}) { |
| 3979 |
last INSCOPE; |
!!!cp ('t156'); |
| 3980 |
|
last; |
| 3981 |
|
} |
| 3982 |
} |
} |
| 3983 |
|
|
| 3984 |
|
!!!cp ('t157'); |
| 3985 |
|
!!!parse-error (type => 'start tag not allowed', |
| 3986 |
|
value => $token->{tag_name}); |
| 3987 |
|
## Ignore the token |
| 3988 |
|
!!!next-token; |
| 3989 |
|
redo B; |
| 3990 |
} # INSCOPE |
} # INSCOPE |
|
unless (defined $i) { |
|
|
!!!cp ('t157'); |
|
|
## TODO: this type is wrong. |
|
|
!!!parse-error (type => 'unmatched end tag:caption'); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
| 3991 |
|
|
| 3992 |
## generate implied end tags |
## generate implied end tags |
| 3993 |
while ({ |
while ({ |
| 4083 |
if ($self->{insertion_mode} == IN_CAPTION_IM) { |
if ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 4084 |
## have a table element in table scope |
## have a table element in table scope |
| 4085 |
my $i; |
my $i; |
| 4086 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: { |
| 4087 |
my $node = $self->{open_elements}->[$_]; |
for (reverse 0..$#{$self->{open_elements}}) { |
| 4088 |
if ($node->[1] eq $token->{tag_name}) { |
my $node = $self->{open_elements}->[$_]; |
| 4089 |
!!!cp ('t171'); |
if ($node->[1] eq $token->{tag_name}) { |
| 4090 |
$i = $_; |
!!!cp ('t171'); |
| 4091 |
last INSCOPE; |
$i = $_; |
| 4092 |
} elsif ({ |
last INSCOPE; |
| 4093 |
table => 1, html => 1, |
} elsif ({ |
| 4094 |
}->{$node->[1]}) { |
table => 1, html => 1, |
| 4095 |
!!!cp ('t172'); |
}->{$node->[1]}) { |
| 4096 |
last INSCOPE; |
!!!cp ('t172'); |
| 4097 |
|
last; |
| 4098 |
|
} |
| 4099 |
} |
} |
| 4100 |
|
|
| 4101 |
|
!!!cp ('t173'); |
| 4102 |
|
!!!parse-error (type => 'unmatched end tag', |
| 4103 |
|
value => $token->{tag_name}); |
| 4104 |
|
## Ignore the token |
| 4105 |
|
!!!next-token; |
| 4106 |
|
redo B; |
| 4107 |
} # INSCOPE |
} # INSCOPE |
|
unless (defined $i) { |
|
|
!!!cp ('t173'); |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
| 4108 |
|
|
| 4109 |
## generate implied end tags |
## generate implied end tags |
| 4110 |
while ({ |
while ({ |
| 4147 |
## have an element in table scope |
## have an element in table scope |
| 4148 |
my $i; |
my $i; |
| 4149 |
my $tn; |
my $tn; |
| 4150 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: { |
| 4151 |
my $node = $self->{open_elements}->[$_]; |
for (reverse 0..$#{$self->{open_elements}}) { |
| 4152 |
if ($node->[1] eq $token->{tag_name}) { |
my $node = $self->{open_elements}->[$_]; |
| 4153 |
!!!cp ('t179'); |
if ($node->[1] eq $token->{tag_name}) { |
| 4154 |
$i = $_; |
!!!cp ('t179'); |
| 4155 |
last INSCOPE; |
$i = $_; |
| 4156 |
} elsif ($node->[1] eq 'td' or $node->[1] eq 'th') { |
|
| 4157 |
!!!cp ('t180'); |
## Close the cell |
| 4158 |
$tn = $node->[1]; |
!!!back-token; # </?> |
| 4159 |
## NOTE: There is exactly one |td| or |th| element |
$token = {type => END_TAG_TOKEN, tag_name => $tn}; |
| 4160 |
## in scope in the stack of open elements by definition. |
redo B; |
| 4161 |
} elsif ({ |
} elsif ($node->[1] eq 'td' or $node->[1] eq 'th') { |
| 4162 |
table => 1, html => 1, |
!!!cp ('t180'); |
| 4163 |
}->{$node->[1]}) { |
$tn = $node->[1]; |
| 4164 |
!!!cp ('t181'); |
## NOTE: There is exactly one |td| or |th| element |
| 4165 |
last INSCOPE; |
## in scope in the stack of open elements by definition. |
| 4166 |
|
} elsif ({ |
| 4167 |
|
table => 1, html => 1, |
| 4168 |
|
}->{$node->[1]}) { |
| 4169 |
|
## ISSUE: Can this be reached? |
| 4170 |
|
!!!cp ('t181'); |
| 4171 |
|
last; |
| 4172 |
|
} |
| 4173 |
} |
} |
| 4174 |
} # INSCOPE |
|
|
unless (defined $i) { |
|
| 4175 |
!!!cp ('t182'); |
!!!cp ('t182'); |
| 4176 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 4177 |
|
value => $token->{tag_name}); |
| 4178 |
## Ignore the token |
## Ignore the token |
| 4179 |
!!!next-token; |
!!!next-token; |
| 4180 |
redo B; |
redo B; |
| 4181 |
} else { |
} # INSCOPE |
|
!!!cp ('t183'); |
|
|
} |
|
|
|
|
|
## Close the cell |
|
|
!!!back-token; # </?> |
|
|
$token = {type => END_TAG_TOKEN, tag_name => $tn}; |
|
|
redo B; |
|
| 4182 |
} elsif ($token->{tag_name} eq 'table' and |
} elsif ($token->{tag_name} eq 'table' and |
| 4183 |
$self->{insertion_mode} == IN_CAPTION_IM) { |
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 4184 |
!!!parse-error (type => 'not closed:caption'); |
!!!parse-error (type => 'not closed:caption'); |
| 4257 |
!!!cp ('t193'); |
!!!cp ('t193'); |
| 4258 |
# |
# |
| 4259 |
} |
} |
| 4260 |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 4261 |
|
for my $entry (@{$self->{open_elements}}) { |
| 4262 |
|
if (not { |
| 4263 |
|
dd => 1, dt => 1, li => 1, p => 1, tbody => 1, td => 1, tfoot => 1, |
| 4264 |
|
th => 1, thead => 1, tr => 1, body => 1, html => 1, |
| 4265 |
|
}->{$entry->[1]}) { |
| 4266 |
|
!!!cp ('t75'); |
| 4267 |
|
!!!parse-error (type => 'in body:#eof'); |
| 4268 |
|
last; |
| 4269 |
|
} |
| 4270 |
|
} |
| 4271 |
|
|
| 4272 |
|
## Stop parsing. |
| 4273 |
|
last B; |
| 4274 |
} else { |
} else { |
| 4275 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 4276 |
} |
} |
| 4584 |
redo B; |
redo B; |
| 4585 |
} |
} |
| 4586 |
|
|
| 4587 |
|
## TODO: Followings are removed from the latest spec. |
| 4588 |
## generate implied end tags |
## generate implied end tags |
| 4589 |
while ({ |
while ({ |
| 4590 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 4948 |
$insert = $insert_to_foster; |
$insert = $insert_to_foster; |
| 4949 |
# |
# |
| 4950 |
} |
} |
| 4951 |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 4952 |
|
unless ($self->{open_elements}->[-1]->[1] eq 'html' and |
| 4953 |
|
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 4954 |
|
!!!parse-error (type => 'in body:#eof'); |
| 4955 |
|
!!!cp ('t259.1'); |
| 4956 |
|
# |
| 4957 |
|
} else { |
| 4958 |
|
!!!cp ('t259.2'); |
| 4959 |
|
# |
| 4960 |
|
} |
| 4961 |
|
|
| 4962 |
|
## Stop parsing |
| 4963 |
|
last B; |
| 4964 |
} else { |
} else { |
| 4965 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 4966 |
} |
} |
| 5013 |
!!!cp ('t267'); |
!!!cp ('t267'); |
| 5014 |
# |
# |
| 5015 |
} |
} |
| 5016 |
} else { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 5017 |
die "$0: $token->{type}: Unknown token type"; |
if ($self->{open_elements}->[-1]->[1] eq 'html' or |
| 5018 |
} |
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 5019 |
|
!!!cp ('t270.2'); |
| 5020 |
|
## Stop parsing. |
| 5021 |
|
last B; |
| 5022 |
|
} else { |
| 5023 |
|
## NOTE: As if </colgroup>. |
| 5024 |
|
!!!cp ('t270.1'); |
| 5025 |
|
pop @{$self->{open_elements}}; # colgroup |
| 5026 |
|
$self->{insertion_mode} = IN_TABLE_IM; |
| 5027 |
|
## Reprocess. |
| 5028 |
|
redo B; |
| 5029 |
|
} |
| 5030 |
|
} else { |
| 5031 |
|
die "$0: $token->{type}: Unknown token type"; |
| 5032 |
|
} |
| 5033 |
|
|
| 5034 |
## As if </colgroup> |
## As if </colgroup> |
| 5035 |
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
| 5036 |
!!!cp ('t269'); |
!!!cp ('t269'); |
| 5037 |
|
## TODO: Wrong error type? |
| 5038 |
!!!parse-error (type => 'unmatched end tag:colgroup'); |
!!!parse-error (type => 'unmatched end tag:colgroup'); |
| 5039 |
## Ignore the token |
## Ignore the token |
| 5040 |
!!!next-token; |
!!!next-token; |
| 5270 |
!!!next-token; |
!!!next-token; |
| 5271 |
redo B; |
redo B; |
| 5272 |
} |
} |
| 5273 |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 5274 |
|
unless ($self->{open_elements}->[-1]->[1] eq 'html' and |
| 5275 |
|
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 5276 |
|
!!!cp ('t299.1'); |
| 5277 |
|
!!!parse-error (type => 'in body:#eof'); |
| 5278 |
|
} else { |
| 5279 |
|
!!!cp ('t299.2'); |
| 5280 |
|
} |
| 5281 |
|
|
| 5282 |
|
## Stop parsing. |
| 5283 |
|
last B; |
| 5284 |
} else { |
} else { |
| 5285 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 5286 |
} |
} |
| 5364 |
## reprocess |
## reprocess |
| 5365 |
redo B; |
redo B; |
| 5366 |
} |
} |
| 5367 |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 5368 |
|
!!!cp ('t309.2'); |
| 5369 |
|
## Stop parsing |
| 5370 |
|
last B; |
| 5371 |
} else { |
} else { |
| 5372 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 5373 |
} |
} |
| 5503 |
!!!next-token; |
!!!next-token; |
| 5504 |
redo B; |
redo B; |
| 5505 |
} |
} |
| 5506 |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 5507 |
|
unless ($self->{open_elements}->[-1]->[1] eq 'html' and |
| 5508 |
|
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 5509 |
|
!!!cp ('t331.1'); |
| 5510 |
|
!!!parse-error (type => 'in body:#eof'); |
| 5511 |
|
} else { |
| 5512 |
|
!!!cp ('t331.2'); |
| 5513 |
|
} |
| 5514 |
|
|
| 5515 |
|
## Stop parsing |
| 5516 |
|
last B; |
| 5517 |
} else { |
} else { |
| 5518 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 5519 |
} |
} |
| 5625 |
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
| 5626 |
menu => 1, ol => 1, p => 1, ul => 1, |
menu => 1, ol => 1, p => 1, ul => 1, |
| 5627 |
pre => 1, listing => 1, |
pre => 1, listing => 1, |
| 5628 |
|
form => 1, |
| 5629 |
|
table => 1, |
| 5630 |
|
hr => 1, |
| 5631 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5632 |
|
if ($token->{tag_name} eq 'form' and defined $self->{form_element}) { |
| 5633 |
|
!!!cp ('t350'); |
| 5634 |
|
!!!parse-error (type => 'in form:form'); |
| 5635 |
|
## Ignore the token |
| 5636 |
|
!!!next-token; |
| 5637 |
|
redo B; |
| 5638 |
|
} |
| 5639 |
|
|
| 5640 |
## has a p element in scope |
## has a p element in scope |
| 5641 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 5642 |
if ($_->[1] eq 'p') { |
if ($_->[1] eq 'p') { |
| 5667 |
} else { |
} else { |
| 5668 |
!!!cp ('t348'); |
!!!cp ('t348'); |
| 5669 |
} |
} |
| 5670 |
} else { |
} elsif ($token->{tag_name} eq 'form') { |
| 5671 |
!!!cp ('t347'); |
!!!cp ('t347.1'); |
| 5672 |
|
$self->{form_element} = $self->{open_elements}->[-1]->[0]; |
| 5673 |
|
|
| 5674 |
!!!next-token; |
!!!next-token; |
| 5675 |
} |
} elsif ($token->{tag_name} eq 'table') { |
| 5676 |
redo B; |
!!!cp ('t382'); |
| 5677 |
} elsif ($token->{tag_name} eq 'form') { |
push @{$open_tables}, [$self->{open_elements}->[-1]->[0]]; |
| 5678 |
if (defined $self->{form_element}) { |
|
| 5679 |
!!!cp ('t350'); |
$self->{insertion_mode} = IN_TABLE_IM; |
| 5680 |
!!!parse-error (type => 'in form:form'); |
|
| 5681 |
## Ignore the token |
!!!next-token; |
| 5682 |
|
} elsif ($token->{tag_name} eq 'hr') { |
| 5683 |
|
!!!cp ('t386'); |
| 5684 |
|
pop @{$self->{open_elements}}; |
| 5685 |
|
|
| 5686 |
!!!next-token; |
!!!next-token; |
|
redo B; |
|
| 5687 |
} else { |
} else { |
| 5688 |
## has a p element in scope |
!!!cp ('t347'); |
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
|
|
if ($_->[1] eq 'p') { |
|
|
!!!cp ('t351'); |
|
|
!!!back-token; |
|
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
|
|
redo B; |
|
|
} elsif ({ |
|
|
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
|
!!!cp ('t352'); |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
$self->{form_element} = $self->{open_elements}->[-1]->[0]; |
|
| 5689 |
!!!next-token; |
!!!next-token; |
|
redo B; |
|
| 5690 |
} |
} |
| 5691 |
} elsif ($token->{tag_name} eq 'li') { |
redo B; |
| 5692 |
|
} elsif ({li => 1, dt => 1, dd => 1}->{$token->{tag_name}}) { |
| 5693 |
## has a p element in scope |
## has a p element in scope |
| 5694 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 5695 |
if ($_->[1] eq 'p') { |
if ($_->[1] eq 'p') { |
| 5709 |
## Step 1 |
## Step 1 |
| 5710 |
my $i = -1; |
my $i = -1; |
| 5711 |
my $node = $self->{open_elements}->[$i]; |
my $node = $self->{open_elements}->[$i]; |
| 5712 |
|
my $li_or_dtdd = {li => {li => 1}, |
| 5713 |
|
dt => {dt => 1, dd => 1}, |
| 5714 |
|
dd => {dt => 1, dd => 1}}->{$token->{tag_name}}; |
| 5715 |
LI: { |
LI: { |
| 5716 |
## Step 2 |
## Step 2 |
| 5717 |
if ($node->[1] eq 'li') { |
if ($li_or_dtdd->{$node->[1]}) { |
| 5718 |
if ($i != -1) { |
if ($i != -1) { |
| 5719 |
!!!cp ('t355'); |
!!!cp ('t355'); |
| 5720 |
!!!parse-error (type => 'end tag missing:'. |
!!!parse-error (type => 'end tag missing:'. |
| 5748 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 5749 |
!!!next-token; |
!!!next-token; |
| 5750 |
redo B; |
redo B; |
|
} elsif ($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; |
|
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
|
|
redo B; |
|
|
} elsif ({ |
|
|
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[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}, $token->{attributes}); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 5751 |
} elsif ($token->{tag_name} eq 'plaintext') { |
} elsif ($token->{tag_name} eq 'plaintext') { |
| 5752 |
## has a p element in scope |
## has a p element in scope |
| 5753 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 5810 |
|
|
| 5811 |
!!!next-token; |
!!!next-token; |
| 5812 |
redo B; |
redo B; |
|
} elsif ({ |
|
|
b => 1, big => 1, em => 1, font => 1, i => 1, |
|
|
s => 1, small => 1, strile => 1, |
|
|
strong => 1, tt => 1, u => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
!!!cp ('t375'); |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
|
|
|
|
|
!!!next-token; |
|
|
redo B; |
|
| 5813 |
} elsif ($token->{tag_name} eq 'nobr') { |
} elsif ($token->{tag_name} eq 'nobr') { |
| 5814 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 5815 |
|
|
| 5866 |
!!!next-token; |
!!!next-token; |
| 5867 |
redo B; |
redo B; |
| 5868 |
} elsif ({ |
} elsif ({ |
| 5869 |
applet => 1, marquee => 1, object => 1, |
xmp => 1, |
| 5870 |
}->{$token->{tag_name}}) { |
iframe => 1, |
| 5871 |
!!!cp ('t380'); |
noembed => 1, |
| 5872 |
$reconstruct_active_formatting_elements->($insert_to_current); |
noframes => 1, |
| 5873 |
|
noscript => 0, ## TODO: 1 if scripting is enabled |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
push @$active_formatting_elements, ['#marker', '']; |
|
|
|
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'xmp') { |
|
|
!!!cp ('t381'); |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
$parse_rcdata->(CDATA_CONTENT_MODEL); |
|
|
redo B; |
|
|
} elsif ($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; |
|
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
|
|
redo B; |
|
|
} elsif ({ |
|
|
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
|
!!!cp ('t383'); |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
push @{$open_tables}, [$self->{open_elements}->[-1]->[0]]; |
|
|
|
|
|
$self->{insertion_mode} = IN_TABLE_IM; |
|
|
|
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ({ |
|
|
area => 1, basefont => 1, bgsound => 1, br => 1, |
|
|
embed => 1, img => 1, param => 1, spacer => 1, wbr => 1, |
|
|
image => 1, |
|
| 5874 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5875 |
if ($token->{tag_name} eq 'image') { |
if ($token->{tag_name} eq 'xmp') { |
| 5876 |
!!!cp ('t384'); |
!!!cp ('t381'); |
| 5877 |
!!!parse-error (type => 'image'); |
$reconstruct_active_formatting_elements->($insert_to_current); |
|
$token->{tag_name} = 'img'; |
|
| 5878 |
} else { |
} else { |
| 5879 |
!!!cp ('t385'); |
!!!cp ('t399'); |
| 5880 |
} |
} |
| 5881 |
|
## NOTE: There is an "as if in body" code clone. |
| 5882 |
## 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; |
|
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
|
|
redo B; |
|
|
} elsif ({ |
|
|
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[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; |
|
| 5883 |
redo B; |
redo B; |
| 5884 |
} elsif ($token->{tag_name} eq 'isindex') { |
} elsif ($token->{tag_name} eq 'isindex') { |
| 5885 |
!!!parse-error (type => 'isindex'); |
!!!parse-error (type => 'isindex'); |
| 5971 |
!!!next-token; |
!!!next-token; |
| 5972 |
redo B; |
redo B; |
| 5973 |
} 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. |
|
|
$parse_rcdata->(CDATA_CONTENT_MODEL); |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'select') { |
|
|
!!!cp ('t400'); |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
|
|
|
## TODO: associate with $self->{form_element} if defined |
|
|
|
|
|
if ($self->{insertion_mode} & TABLE_IMS or |
|
|
$self->{insertion_mode} & BODY_TABLE_IMS or |
|
|
$self->{insertion_mode} == IN_COLUMN_GROUP_IM) { |
|
|
!!!cp ('t400.1'); |
|
|
$self->{insertion_mode} = IN_SELECT_IN_TABLE_IM; |
|
|
} else { |
|
|
!!!cp ('t400.2'); |
|
|
$self->{insertion_mode} = IN_SELECT_IM; |
|
|
} |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ({ |
|
| 5974 |
caption => 1, col => 1, colgroup => 1, frame => 1, |
caption => 1, col => 1, colgroup => 1, frame => 1, |
| 5975 |
frameset => 1, head => 1, option => 1, optgroup => 1, |
frameset => 1, head => 1, option => 1, optgroup => 1, |
| 5976 |
tbody => 1, td => 1, tfoot => 1, th => 1, |
tbody => 1, td => 1, tfoot => 1, th => 1, |
| 5984 |
|
|
| 5985 |
## ISSUE: An issue on HTML5 new elements in the spec. |
## ISSUE: An issue on HTML5 new elements in the spec. |
| 5986 |
} else { |
} else { |
| 5987 |
!!!cp ('t402'); |
if ($token->{tag_name} eq 'image') { |
| 5988 |
|
!!!cp ('t384'); |
| 5989 |
|
!!!parse-error (type => 'image'); |
| 5990 |
|
$token->{tag_name} = 'img'; |
| 5991 |
|
} else { |
| 5992 |
|
!!!cp ('t385'); |
| 5993 |
|
} |
| 5994 |
|
|
| 5995 |
|
## NOTE: There is an "as if <br>" code clone. |
| 5996 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 5997 |
|
|
| 5998 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 5999 |
|
|
| 6000 |
|
if ({ |
| 6001 |
|
applet => 1, marquee => 1, object => 1, |
| 6002 |
|
}->{$token->{tag_name}}) { |
| 6003 |
|
!!!cp ('t380'); |
| 6004 |
|
push @$active_formatting_elements, ['#marker', '']; |
| 6005 |
|
} elsif ({ |
| 6006 |
|
b => 1, big => 1, em => 1, font => 1, i => 1, |
| 6007 |
|
s => 1, small => 1, strile => 1, |
| 6008 |
|
strong => 1, tt => 1, u => 1, |
| 6009 |
|
}->{$token->{tag_name}}) { |
| 6010 |
|
!!!cp ('t375'); |
| 6011 |
|
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
| 6012 |
|
} elsif ($token->{tag_name} eq 'input') { |
| 6013 |
|
!!!cp ('t388'); |
| 6014 |
|
## TODO: associate with $self->{form_element} if defined |
| 6015 |
|
pop @{$self->{open_elements}}; |
| 6016 |
|
} elsif ({ |
| 6017 |
|
area => 1, basefont => 1, bgsound => 1, br => 1, |
| 6018 |
|
embed => 1, img => 1, param => 1, spacer => 1, wbr => 1, |
| 6019 |
|
#image => 1, |
| 6020 |
|
}->{$token->{tag_name}}) { |
| 6021 |
|
!!!cp ('t388.1'); |
| 6022 |
|
pop @{$self->{open_elements}}; |
| 6023 |
|
} elsif ($token->{tag_name} eq 'select') { |
| 6024 |
|
## TODO: associate with $self->{form_element} if defined |
| 6025 |
|
|
| 6026 |
|
if ($self->{insertion_mode} & TABLE_IMS or |
| 6027 |
|
$self->{insertion_mode} & BODY_TABLE_IMS or |
| 6028 |
|
$self->{insertion_mode} == IN_COLUMN_GROUP_IM) { |
| 6029 |
|
!!!cp ('t400.1'); |
| 6030 |
|
$self->{insertion_mode} = IN_SELECT_IN_TABLE_IM; |
| 6031 |
|
} else { |
| 6032 |
|
!!!cp ('t400.2'); |
| 6033 |
|
$self->{insertion_mode} = IN_SELECT_IM; |
| 6034 |
|
} |
| 6035 |
|
} else { |
| 6036 |
|
!!!cp ('t402'); |
| 6037 |
|
} |
| 6038 |
|
|
| 6039 |
!!!next-token; |
!!!next-token; |
| 6040 |
redo B; |
redo B; |
| 6041 |
} |
} |
| 6042 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 6043 |
if ($token->{tag_name} eq 'body') { |
if ($token->{tag_name} eq 'body') { |
| 6044 |
if (@{$self->{open_elements}} > 1 and |
## has a |body| element in scope |
| 6045 |
$self->{open_elements}->[1]->[1] eq 'body') { |
my $i; |
| 6046 |
for (@{$self->{open_elements}}) { |
INSCOPE: { |
| 6047 |
unless ({ |
for (reverse @{$self->{open_elements}}) { |
| 6048 |
dd => 1, dt => 1, li => 1, p => 1, td => 1, |
if ($_->[1] eq 'body') { |
| 6049 |
th => 1, tr => 1, body => 1, html => 1, |
!!!cp ('t405'); |
| 6050 |
tbody => 1, tfoot => 1, thead => 1, |
$i = $_; |
| 6051 |
}->{$_->[1]}) { |
last INSCOPE; |
| 6052 |
!!!cp ('t403'); |
} elsif ({ |
| 6053 |
!!!parse-error (type => 'not closed:'.$_->[1]); |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
| 6054 |
} else { |
button => 1, marquee => 1, object => 1, html => 1, |
| 6055 |
!!!cp ('t404'); |
}->{$_->[1]}) { |
| 6056 |
|
!!!cp ('t405.1'); |
| 6057 |
|
last; |
| 6058 |
} |
} |
| 6059 |
} |
} |
| 6060 |
|
|
| 6061 |
$self->{insertion_mode} = AFTER_BODY_IM; |
!!!parse-error (type => 'start tag not allowed', |
| 6062 |
!!!next-token; |
value => $token->{tag_name}); |
| 6063 |
redo B; |
## NOTE: Ignore the token. |
|
} else { |
|
|
!!!cp ('t405'); |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
| 6064 |
!!!next-token; |
!!!next-token; |
| 6065 |
redo B; |
redo B; |
| 6066 |
|
} # INSCOPE |
| 6067 |
|
|
| 6068 |
|
for (@{$self->{open_elements}}) { |
| 6069 |
|
unless ({ |
| 6070 |
|
dd => 1, dt => 1, li => 1, p => 1, td => 1, |
| 6071 |
|
th => 1, tr => 1, body => 1, html => 1, |
| 6072 |
|
tbody => 1, tfoot => 1, thead => 1, |
| 6073 |
|
}->{$_->[1]}) { |
| 6074 |
|
!!!cp ('t403'); |
| 6075 |
|
!!!parse-error (type => 'not closed:'.$_->[1]); |
| 6076 |
|
last; |
| 6077 |
|
} else { |
| 6078 |
|
!!!cp ('t404'); |
| 6079 |
|
} |
| 6080 |
} |
} |
| 6081 |
|
|
| 6082 |
|
$self->{insertion_mode} = AFTER_BODY_IM; |
| 6083 |
|
!!!next-token; |
| 6084 |
|
redo B; |
| 6085 |
} elsif ($token->{tag_name} eq 'html') { |
} elsif ($token->{tag_name} eq 'html') { |
| 6086 |
if (@{$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') { |
| 6087 |
## ISSUE: There is an issue in the spec. |
## ISSUE: There is an issue in the spec. |