| 7 |
## doc.write (''); |
## doc.write (''); |
| 8 |
## alert (doc.compatMode); |
## alert (doc.compatMode); |
| 9 |
|
|
| 10 |
|
## ISSUE: HTML5 revision 967 says that the encoding layer MUST NOT |
| 11 |
|
## strip BOM and the HTML layer MUST ignore it. Whether we can do it |
| 12 |
|
## is not yet clear. |
| 13 |
|
## "{U+FEFF}..." in UTF-16BE/UTF-16LE is three or four characters? |
| 14 |
|
## "{U+FEFF}..." in GB18030? |
| 15 |
|
|
| 16 |
my $permitted_slash_tag_name = { |
my $permitted_slash_tag_name = { |
| 17 |
base => 1, |
base => 1, |
| 18 |
link => 1, |
link => 1, |
| 253 |
} elsif ($self->{state} eq 'entity data') { |
} elsif ($self->{state} eq 'entity data') { |
| 254 |
## (cannot happen in CDATA state) |
## (cannot happen in CDATA state) |
| 255 |
|
|
| 256 |
my $token = $self->_tokenize_attempt_to_consume_an_entity; |
my $token = $self->_tokenize_attempt_to_consume_an_entity (0); |
| 257 |
|
|
| 258 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 259 |
# next-input-character is already done |
# next-input-character is already done |
| 333 |
if ($self->{content_model_flag} eq 'RCDATA' or |
if ($self->{content_model_flag} eq 'RCDATA' or |
| 334 |
$self->{content_model_flag} eq 'CDATA') { |
$self->{content_model_flag} eq 'CDATA') { |
| 335 |
if (defined $self->{last_emitted_start_tag_name}) { |
if (defined $self->{last_emitted_start_tag_name}) { |
| 336 |
|
## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564> |
| 337 |
my @next_char; |
my @next_char; |
| 338 |
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++) { |
| 339 |
push @next_char, $self->{next_input_character}; |
push @next_char, $self->{next_input_character}; |
| 425 |
redo A; |
redo A; |
| 426 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 427 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 428 |
|
$self->{current_token}->{first_start_tag} |
| 429 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 430 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 431 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 432 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 452 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 453 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 454 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 455 |
|
$self->{current_token}->{first_start_tag} |
| 456 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 457 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 458 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 459 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 500 |
redo A; |
redo A; |
| 501 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 502 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 503 |
|
$self->{current_token}->{first_start_tag} |
| 504 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 505 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 506 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 507 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 540 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 541 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 542 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 543 |
|
$self->{current_token}->{first_start_tag} |
| 544 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 545 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 546 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 547 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 568 |
my $before_leave = sub { |
my $before_leave = sub { |
| 569 |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
| 570 |
->{$self->{current_attribute}->{name}}) { # MUST |
->{$self->{current_attribute}->{name}}) { # MUST |
| 571 |
!!!parse-error (type => 'dupulicate attribute'); |
!!!parse-error (type => 'duplicate attribute:'.$self->{current_attribute}->{name}); |
| 572 |
## Discard $self->{current_attribute} # MUST |
## Discard $self->{current_attribute} # MUST |
| 573 |
} else { |
} else { |
| 574 |
$self->{current_token}->{attributes}->{$self->{current_attribute}->{name}} |
$self->{current_token}->{attributes}->{$self->{current_attribute}->{name}} |
| 593 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 594 |
$before_leave->(); |
$before_leave->(); |
| 595 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 596 |
|
$self->{current_token}->{first_start_tag} |
| 597 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 598 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 599 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 600 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 634 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 635 |
$before_leave->(); |
$before_leave->(); |
| 636 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 637 |
|
$self->{current_token}->{first_start_tag} |
| 638 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 639 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 640 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 641 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 672 |
redo A; |
redo A; |
| 673 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 674 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 675 |
|
$self->{current_token}->{first_start_tag} |
| 676 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 677 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 678 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 679 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 705 |
# |
# |
| 706 |
} else { |
} else { |
| 707 |
!!!parse-error (type => 'nestc'); |
!!!parse-error (type => 'nestc'); |
| 708 |
|
## TODO: Different error type for <aa / bb> than <aa/> |
| 709 |
} |
} |
| 710 |
$self->{state} = 'before attribute name'; |
$self->{state} = 'before attribute name'; |
| 711 |
# next-input-character is already done |
# next-input-character is already done |
| 713 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 714 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 715 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 716 |
|
$self->{current_token}->{first_start_tag} |
| 717 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 718 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 719 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 720 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 760 |
redo A; |
redo A; |
| 761 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 762 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 763 |
|
$self->{current_token}->{first_start_tag} |
| 764 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 765 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 766 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 767 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 780 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 781 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 782 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 783 |
|
$self->{current_token}->{first_start_tag} |
| 784 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 785 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 786 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 787 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 816 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 817 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
| 818 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 819 |
|
$self->{current_token}->{first_start_tag} |
| 820 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 821 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 822 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 823 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 852 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 853 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
| 854 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 855 |
|
$self->{current_token}->{first_start_tag} |
| 856 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 857 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 858 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 859 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 891 |
redo A; |
redo A; |
| 892 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 893 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 894 |
|
$self->{current_token}->{first_start_tag} |
| 895 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 896 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 897 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 898 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 911 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 912 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 913 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 914 |
|
$self->{current_token}->{first_start_tag} |
| 915 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 916 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 917 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 918 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 935 |
redo A; |
redo A; |
| 936 |
} |
} |
| 937 |
} elsif ($self->{state} eq 'entity in attribute value') { |
} elsif ($self->{state} eq 'entity in attribute value') { |
| 938 |
my $token = $self->_tokenize_attempt_to_consume_an_entity; |
my $token = $self->_tokenize_attempt_to_consume_an_entity (1); |
| 939 |
|
|
| 940 |
unless (defined $token) { |
unless (defined $token) { |
| 941 |
$self->{current_attribute}->{value} .= '&'; |
$self->{current_attribute}->{value} .= '&'; |
| 1026 |
} |
} |
| 1027 |
} |
} |
| 1028 |
|
|
| 1029 |
!!!parse-error (type => 'bogus comment open'); |
!!!parse-error (type => 'bogus comment'); |
| 1030 |
$self->{next_input_character} = shift @next_char; |
$self->{next_input_character} = shift @next_char; |
| 1031 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 1032 |
$self->{state} = 'bogus comment'; |
$self->{state} = 'bogus comment'; |
| 1085 |
redo A; |
redo A; |
| 1086 |
} else { |
} else { |
| 1087 |
$self->{current_token}->{data} # comment |
$self->{current_token}->{data} # comment |
| 1088 |
.= chr ($self->{next_input_character}); |
.= '-' . chr ($self->{next_input_character}); |
| 1089 |
$self->{state} = 'comment'; |
$self->{state} = 'comment'; |
| 1090 |
!!!next-input-character; |
!!!next-input-character; |
| 1091 |
redo A; |
redo A; |
| 1445 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1446 |
|
|
| 1447 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 1448 |
## recomsume |
## reconsume |
| 1449 |
|
|
| 1450 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1451 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
| 1488 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1489 |
|
|
| 1490 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 1491 |
## recomsume |
## reconsume |
| 1492 |
|
|
| 1493 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1494 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
| 1495 |
|
|
| 1496 |
redo A; |
redo A; |
| 1497 |
} else { |
} else { |
| 1498 |
!!!parse-error (type => 'string after PUBLIC literal'); |
!!!parse-error (type => 'string after SYSTEM'); |
| 1499 |
$self->{state} = 'bogus DOCTYPE'; |
$self->{state} = 'bogus DOCTYPE'; |
| 1500 |
!!!next-input-character; |
!!!next-input-character; |
| 1501 |
redo A; |
redo A; |
| 1563 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1564 |
|
|
| 1565 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 1566 |
## recomsume |
## reconsume |
| 1567 |
|
|
| 1568 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1569 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
| 1606 |
die "$0: _get_next_token: unexpected case"; |
die "$0: _get_next_token: unexpected case"; |
| 1607 |
} # _get_next_token |
} # _get_next_token |
| 1608 |
|
|
| 1609 |
sub _tokenize_attempt_to_consume_an_entity ($) { |
sub _tokenize_attempt_to_consume_an_entity ($$) { |
| 1610 |
my $self = shift; |
my ($self, $in_attr) = @_; |
| 1611 |
|
|
| 1612 |
if ({ |
if ({ |
| 1613 |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, # HT, LF, VT, FF, |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, # HT, LF, VT, FF, |
| 1620 |
!!!next-input-character; |
!!!next-input-character; |
| 1621 |
if ($self->{next_input_character} == 0x0078 or # x |
if ($self->{next_input_character} == 0x0078 or # x |
| 1622 |
$self->{next_input_character} == 0x0058) { # X |
$self->{next_input_character} == 0x0058) { # X |
| 1623 |
my $num; |
my $code; |
| 1624 |
X: { |
X: { |
| 1625 |
my $x_char = $self->{next_input_character}; |
my $x_char = $self->{next_input_character}; |
| 1626 |
!!!next-input-character; |
!!!next-input-character; |
| 1627 |
if (0x0030 <= $self->{next_input_character} and |
if (0x0030 <= $self->{next_input_character} and |
| 1628 |
$self->{next_input_character} <= 0x0039) { # 0..9 |
$self->{next_input_character} <= 0x0039) { # 0..9 |
| 1629 |
$num ||= 0; |
$code ||= 0; |
| 1630 |
$num *= 0x10; |
$code *= 0x10; |
| 1631 |
$num += $self->{next_input_character} - 0x0030; |
$code += $self->{next_input_character} - 0x0030; |
| 1632 |
redo X; |
redo X; |
| 1633 |
} elsif (0x0061 <= $self->{next_input_character} and |
} elsif (0x0061 <= $self->{next_input_character} and |
| 1634 |
$self->{next_input_character} <= 0x0066) { # a..f |
$self->{next_input_character} <= 0x0066) { # a..f |
| 1635 |
## ISSUE: the spec says U+0078, which is apparently incorrect |
$code ||= 0; |
| 1636 |
$num ||= 0; |
$code *= 0x10; |
| 1637 |
$num *= 0x10; |
$code += $self->{next_input_character} - 0x0060 + 9; |
|
$num += $self->{next_input_character} - 0x0060 + 9; |
|
| 1638 |
redo X; |
redo X; |
| 1639 |
} elsif (0x0041 <= $self->{next_input_character} and |
} elsif (0x0041 <= $self->{next_input_character} and |
| 1640 |
$self->{next_input_character} <= 0x0046) { # A..F |
$self->{next_input_character} <= 0x0046) { # A..F |
| 1641 |
## ISSUE: the spec says U+0058, which is apparently incorrect |
$code ||= 0; |
| 1642 |
$num ||= 0; |
$code *= 0x10; |
| 1643 |
$num *= 0x10; |
$code += $self->{next_input_character} - 0x0040 + 9; |
|
$num += $self->{next_input_character} - 0x0040 + 9; |
|
| 1644 |
redo X; |
redo X; |
| 1645 |
} elsif (not defined $num) { # no hexadecimal digit |
} elsif (not defined $code) { # no hexadecimal digit |
| 1646 |
!!!parse-error (type => 'bare hcro'); |
!!!parse-error (type => 'bare hcro'); |
| 1647 |
|
!!!back-next-input-character ($x_char, $self->{next_input_character}); |
| 1648 |
$self->{next_input_character} = 0x0023; # # |
$self->{next_input_character} = 0x0023; # # |
|
!!!back-next-input-character ($x_char); |
|
| 1649 |
return undef; |
return undef; |
| 1650 |
} elsif ($self->{next_input_character} == 0x003B) { # ; |
} elsif ($self->{next_input_character} == 0x003B) { # ; |
| 1651 |
!!!next-input-character; |
!!!next-input-character; |
| 1653 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'no refc'); |
| 1654 |
} |
} |
| 1655 |
|
|
| 1656 |
## TODO: check the definition for |a valid Unicode character|. |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 1657 |
## <http://lists.whatwg.org/pipermail/whatwg-whatwg.org/2006-December/thread.html#8189> |
!!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code); |
| 1658 |
if ($num > 1114111 or $num == 0) { |
$code = 0xFFFD; |
| 1659 |
$num = 0xFFFD; # REPLACEMENT CHARACTER |
} elsif ($code > 0x10FFFF) { |
| 1660 |
## ISSUE: Why this is not an error? |
!!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code); |
| 1661 |
} elsif (0x80 <= $num and $num <= 0x9F) { |
$code = 0xFFFD; |
| 1662 |
!!!parse-error (type => sprintf 'c1 entity:U+%04X', $num); |
} elsif ($code == 0x000D) { |
| 1663 |
$num = $c1_entity_char->{$num}; |
!!!parse-error (type => 'CR character reference'); |
| 1664 |
|
$code = 0x000A; |
| 1665 |
|
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 1666 |
|
!!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code); |
| 1667 |
|
$code = $c1_entity_char->{$code}; |
| 1668 |
} |
} |
| 1669 |
|
|
| 1670 |
return {type => 'character', data => chr $num}; |
return {type => 'character', data => chr $code}; |
| 1671 |
} # X |
} # X |
| 1672 |
} elsif (0x0030 <= $self->{next_input_character} and |
} elsif (0x0030 <= $self->{next_input_character} and |
| 1673 |
$self->{next_input_character} <= 0x0039) { # 0..9 |
$self->{next_input_character} <= 0x0039) { # 0..9 |
| 1688 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'no refc'); |
| 1689 |
} |
} |
| 1690 |
|
|
| 1691 |
## TODO: check the definition for |a valid Unicode character|. |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 1692 |
if ($code > 1114111 or $code == 0) { |
!!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code); |
| 1693 |
$code = 0xFFFD; # REPLACEMENT CHARACTER |
$code = 0xFFFD; |
| 1694 |
## ISSUE: Why this is not an error? |
} elsif ($code > 0x10FFFF) { |
| 1695 |
|
!!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code); |
| 1696 |
|
$code = 0xFFFD; |
| 1697 |
|
} elsif ($code == 0x000D) { |
| 1698 |
|
!!!parse-error (type => 'CR character reference'); |
| 1699 |
|
$code = 0x000A; |
| 1700 |
} elsif (0x80 <= $code and $code <= 0x9F) { |
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 1701 |
!!!parse-error (type => sprintf 'c1 entity:U+%04X', $code); |
!!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code); |
| 1702 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 1703 |
} |
} |
| 1704 |
|
|
| 1717 |
!!!next-input-character; |
!!!next-input-character; |
| 1718 |
|
|
| 1719 |
my $value = $entity_name; |
my $value = $entity_name; |
| 1720 |
my $match; |
my $match = 0; |
| 1721 |
require Whatpm::_NamedEntityList; |
require Whatpm::_NamedEntityList; |
| 1722 |
our $EntityChar; |
our $EntityChar; |
| 1723 |
|
|
| 1732 |
$self->{next_input_character} == 0x003B)) { # ; |
$self->{next_input_character} == 0x003B)) { # ; |
| 1733 |
$entity_name .= chr $self->{next_input_character}; |
$entity_name .= chr $self->{next_input_character}; |
| 1734 |
if (defined $EntityChar->{$entity_name}) { |
if (defined $EntityChar->{$entity_name}) { |
|
$value = $EntityChar->{$entity_name}; |
|
| 1735 |
if ($self->{next_input_character} == 0x003B) { # ; |
if ($self->{next_input_character} == 0x003B) { # ; |
| 1736 |
|
$value = $EntityChar->{$entity_name}; |
| 1737 |
$match = 1; |
$match = 1; |
| 1738 |
!!!next-input-character; |
!!!next-input-character; |
| 1739 |
last; |
last; |
| 1740 |
} else { |
} else { |
| 1741 |
|
$value = $EntityChar->{$entity_name}; |
| 1742 |
$match = -1; |
$match = -1; |
| 1743 |
|
!!!next-input-character; |
| 1744 |
} |
} |
| 1745 |
} else { |
} else { |
| 1746 |
$value .= chr $self->{next_input_character}; |
$value .= chr $self->{next_input_character}; |
| 1747 |
|
$match *= 2; |
| 1748 |
|
!!!next-input-character; |
| 1749 |
} |
} |
|
!!!next-input-character; |
|
| 1750 |
} |
} |
| 1751 |
|
|
| 1752 |
if ($match > 0) { |
if ($match > 0) { |
| 1753 |
return {type => 'character', data => $value}; |
return {type => 'character', data => $value}; |
| 1754 |
} elsif ($match < 0) { |
} elsif ($match < 0) { |
| 1755 |
!!!parse-error (type => 'refc'); |
!!!parse-error (type => 'no refc'); |
| 1756 |
return {type => 'character', data => $value}; |
if ($in_attr and $match < -1) { |
| 1757 |
|
return {type => 'character', data => '&'.$entity_name}; |
| 1758 |
|
} else { |
| 1759 |
|
return {type => 'character', data => $value}; |
| 1760 |
|
} |
| 1761 |
} else { |
} else { |
| 1762 |
!!!parse-error (type => 'bare ero'); |
!!!parse-error (type => 'bare ero'); |
| 1763 |
## NOTE: No characters are consumed in the spec. |
## NOTE: No characters are consumed in the spec. |
| 1764 |
!!!back-token ({type => 'character', data => $value}); |
return {type => 'character', data => '&'.$value}; |
|
return undef; |
|
| 1765 |
} |
} |
| 1766 |
} else { |
} else { |
| 1767 |
## no characters are consumed |
## no characters are consumed |
| 1956 |
} elsif ($token->{type} eq 'character') { |
} elsif ($token->{type} eq 'character') { |
| 1957 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
| 1958 |
## Ignore the token |
## Ignore the token |
| 1959 |
|
|
| 1960 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 1961 |
## Stay in the phase |
## Stay in the phase |
| 1962 |
!!!next-token; |
!!!next-token; |
| 1999 |
!!!next-token; |
!!!next-token; |
| 2000 |
redo B; |
redo B; |
| 2001 |
} elsif ($token->{type} eq 'character') { |
} elsif ($token->{type} eq 'character') { |
| 2002 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
| 2003 |
$self->{document}->manakai_append_text ($1); |
## Ignore the token. |
| 2004 |
## ISSUE: DOM3 Core does not allow Document > Text |
|
| 2005 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 2006 |
## Stay in the phase |
## Stay in the phase |
| 2007 |
!!!next-token; |
!!!next-token; |
| 2022 |
my $root_element; !!!create-element ($root_element, 'html'); |
my $root_element; !!!create-element ($root_element, 'html'); |
| 2023 |
$self->{document}->append_child ($root_element); |
$self->{document}->append_child ($root_element); |
| 2024 |
push @{$self->{open_elements}}, [$root_element, 'html']; |
push @{$self->{open_elements}}, [$root_element, 'html']; |
|
#$phase = 'main'; |
|
| 2025 |
## reprocess |
## reprocess |
| 2026 |
#redo B; |
#redo B; |
| 2027 |
return; |
return; ## Go to the main phase. |
| 2028 |
} # B |
} # B |
| 2029 |
} # _tree_construction_root_element |
} # _tree_construction_root_element |
| 2030 |
|
|
| 2040 |
|
|
| 2041 |
## Step 3 |
## Step 3 |
| 2042 |
S3: { |
S3: { |
| 2043 |
$last = 1 if $self->{open_elements}->[0]->[0] eq $node->[0]; |
## ISSUE: Oops! "If node is the first node in the stack of open |
| 2044 |
if (defined $self->{inner_html_node}) { |
## elements, then set last to true. If the context element of the |
| 2045 |
if ($self->{inner_html_node}->[1] eq 'td' or |
## HTML fragment parsing algorithm is neither a td element nor a |
| 2046 |
$self->{inner_html_node}->[1] eq 'th') { |
## th element, then set node to the context element. (fragment case)": |
| 2047 |
# |
## The second "if" is in the scope of the first "if"!? |
| 2048 |
} else { |
if ($self->{open_elements}->[0]->[0] eq $node->[0]) { |
| 2049 |
$node = $self->{inner_html_node}; |
$last = 1; |
| 2050 |
|
if (defined $self->{inner_html_node}) { |
| 2051 |
|
if ($self->{inner_html_node}->[1] eq 'td' or |
| 2052 |
|
$self->{inner_html_node}->[1] eq 'th') { |
| 2053 |
|
# |
| 2054 |
|
} else { |
| 2055 |
|
$node = $self->{inner_html_node}; |
| 2056 |
|
} |
| 2057 |
} |
} |
| 2058 |
} |
} |
| 2059 |
|
|
| 2100 |
sub _tree_construction_main ($) { |
sub _tree_construction_main ($) { |
| 2101 |
my $self = shift; |
my $self = shift; |
| 2102 |
|
|
| 2103 |
my $phase = 'main'; |
my $previous_insertion_mode; |
| 2104 |
|
|
| 2105 |
my $active_formatting_elements = []; |
my $active_formatting_elements = []; |
| 2106 |
|
|
| 2501 |
$parse_rcdata->('CDATA', $insert); |
$parse_rcdata->('CDATA', $insert); |
| 2502 |
return; |
return; |
| 2503 |
} elsif ({ |
} elsif ({ |
| 2504 |
base => 1, link => 1, meta => 1, |
base => 1, link => 1, |
| 2505 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 2506 |
## NOTE: This is an "as if in head" code clone, only "-t" differs |
## NOTE: This is an "as if in head" code clone, only "-t" differs |
| 2507 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 2508 |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 2509 |
!!!next-token; |
!!!next-token; |
| 2510 |
return; |
return; |
| 2511 |
|
} elsif ($token->{tag_name} eq 'meta') { |
| 2512 |
|
## NOTE: This is an "as if in head" code clone, only "-t" differs |
| 2513 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 2514 |
|
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 2515 |
|
|
| 2516 |
|
unless ($self->{confident}) { |
| 2517 |
|
my $charset; |
| 2518 |
|
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
| 2519 |
|
$charset = $token->{attributes}->{charset}->{value}; |
| 2520 |
|
} |
| 2521 |
|
if ($token->{attributes}->{'http-equiv'}) { |
| 2522 |
|
## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition. |
| 2523 |
|
if ($token->{attributes}->{'http-equiv'}->{value} |
| 2524 |
|
=~ /\A[^;]*;[\x09-\x0D\x20]*charset[\x09-\x0D\x20]*= |
| 2525 |
|
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
| 2526 |
|
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
| 2527 |
|
$charset = defined $1 ? $1 : defined $2 ? $2 : $3; |
| 2528 |
|
} ## TODO: And if supported |
| 2529 |
|
} |
| 2530 |
|
## TODO: Change the encoding |
| 2531 |
|
} |
| 2532 |
|
|
| 2533 |
|
!!!next-token; |
| 2534 |
|
return; |
| 2535 |
} elsif ($token->{tag_name} eq 'title') { |
} elsif ($token->{tag_name} eq 'title') { |
| 2536 |
!!!parse-error (type => 'in body:title'); |
!!!parse-error (type => 'in body:title'); |
| 2537 |
## NOTE: This is an "as if in head" code clone |
## NOTE: This is an "as if in head" code clone |
| 2538 |
$parse_rcdata->('RCDATA', $insert); |
$parse_rcdata->('RCDATA', sub { |
| 2539 |
|
if (defined $self->{head_element}) { |
| 2540 |
|
$self->{head_element}->append_child ($_[0]); |
| 2541 |
|
} else { |
| 2542 |
|
$insert->($_[0]); |
| 2543 |
|
} |
| 2544 |
|
}); |
| 2545 |
return; |
return; |
| 2546 |
} elsif ($token->{tag_name} eq 'body') { |
} elsif ($token->{tag_name} eq 'body') { |
| 2547 |
!!!parse-error (type => 'in body:body'); |
!!!parse-error (type => 'in body:body'); |
| 2644 |
if ($i != -1) { |
if ($i != -1) { |
| 2645 |
!!!parse-error (type => 'end tag missing:'. |
!!!parse-error (type => 'end tag missing:'. |
| 2646 |
$self->{open_elements}->[-1]->[1]); |
$self->{open_elements}->[-1]->[1]); |
|
## TODO: test |
|
| 2647 |
} |
} |
| 2648 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 2649 |
last LI; |
last LI; |
| 2691 |
if ($i != -1) { |
if ($i != -1) { |
| 2692 |
!!!parse-error (type => 'end tag missing:'. |
!!!parse-error (type => 'end tag missing:'. |
| 2693 |
$self->{open_elements}->[-1]->[1]); |
$self->{open_elements}->[-1]->[1]); |
|
## TODO: test |
|
| 2694 |
} |
} |
| 2695 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 2696 |
last LI; |
last LI; |
| 2834 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 2835 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 2836 |
if ($node->[1] eq 'nobr') { |
if ($node->[1] eq 'nobr') { |
| 2837 |
|
!!!parse-error (type => 'not closed:nobr'); |
| 2838 |
!!!back-token; |
!!!back-token; |
| 2839 |
$token = {type => 'end tag', tag_name => 'nobr'}; |
$token = {type => 'end tag', tag_name => 'nobr'}; |
| 2840 |
return; |
return; |
| 2918 |
!!!parse-error (type => 'image'); |
!!!parse-error (type => 'image'); |
| 2919 |
$token->{tag_name} = 'img'; |
$token->{tag_name} = 'img'; |
| 2920 |
} |
} |
| 2921 |
|
|
| 2922 |
|
## NOTE: There is an "as if <br>" code clone. |
| 2923 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 2924 |
|
|
| 2925 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 3077 |
unless ({ |
unless ({ |
| 3078 |
dd => 1, dt => 1, li => 1, p => 1, td => 1, |
dd => 1, dt => 1, li => 1, p => 1, td => 1, |
| 3079 |
th => 1, tr => 1, body => 1, html => 1, |
th => 1, tr => 1, body => 1, html => 1, |
| 3080 |
|
tbody => 1, tfoot => 1, thead => 1, |
| 3081 |
}->{$_->[1]}) { |
}->{$_->[1]}) { |
| 3082 |
!!!parse-error (type => 'not closed:'.$_->[1]); |
!!!parse-error (type => 'not closed:'.$_->[1]); |
| 3083 |
} |
} |
| 3127 |
li => ($token->{tag_name} ne 'li'), |
li => ($token->{tag_name} ne 'li'), |
| 3128 |
p => ($token->{tag_name} ne 'p'), |
p => ($token->{tag_name} ne 'p'), |
| 3129 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3130 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3131 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3132 |
!!!back-token; |
!!!back-token; |
| 3133 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 3145 |
} # INSCOPE |
} # INSCOPE |
| 3146 |
|
|
| 3147 |
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
| 3148 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
if (defined $i) { |
| 3149 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3150 |
|
} else { |
| 3151 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3152 |
|
} |
| 3153 |
} |
} |
| 3154 |
|
|
| 3155 |
splice @{$self->{open_elements}}, $i if defined $i; |
if (defined $i) { |
| 3156 |
|
splice @{$self->{open_elements}}, $i; |
| 3157 |
|
} elsif ($token->{tag_name} eq 'p') { |
| 3158 |
|
## As if <p>, then reprocess the current token |
| 3159 |
|
my $el; |
| 3160 |
|
!!!create-element ($el, 'p'); |
| 3161 |
|
$insert->($el); |
| 3162 |
|
} |
| 3163 |
$clear_up_to_marker->() |
$clear_up_to_marker->() |
| 3164 |
if { |
if { |
| 3165 |
button => 1, marquee => 1, object => 1, |
button => 1, marquee => 1, object => 1, |
| 3175 |
if ({ |
if ({ |
| 3176 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3177 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3178 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3179 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3180 |
!!!back-token; |
!!!back-token; |
| 3181 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 3214 |
if ({ |
if ({ |
| 3215 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3216 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3217 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3218 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3219 |
!!!back-token; |
!!!back-token; |
| 3220 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 3245 |
strong => 1, tt => 1, u => 1, |
strong => 1, tt => 1, u => 1, |
| 3246 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 3247 |
$formatting_end_tag->($token->{tag_name}); |
$formatting_end_tag->($token->{tag_name}); |
| 3248 |
## TODO: <http://html5.org/tools/web-apps-tracker?from=883&to=884> |
return; |
| 3249 |
|
} elsif ($token->{tag_name} eq 'br') { |
| 3250 |
|
!!!parse-error (type => 'unmatched end tag:br'); |
| 3251 |
|
|
| 3252 |
|
## As if <br> |
| 3253 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 3254 |
|
|
| 3255 |
|
my $el; |
| 3256 |
|
!!!create-element ($el, 'br'); |
| 3257 |
|
$insert->($el); |
| 3258 |
|
|
| 3259 |
|
## Ignore the token. |
| 3260 |
|
!!!next-token; |
| 3261 |
return; |
return; |
| 3262 |
} elsif ({ |
} elsif ({ |
| 3263 |
caption => 1, col => 1, colgroup => 1, frame => 1, |
caption => 1, col => 1, colgroup => 1, frame => 1, |
| 3264 |
frameset => 1, head => 1, option => 1, optgroup => 1, |
frameset => 1, head => 1, option => 1, optgroup => 1, |
| 3265 |
tbody => 1, td => 1, tfoot => 1, th => 1, |
tbody => 1, td => 1, tfoot => 1, th => 1, |
| 3266 |
thead => 1, tr => 1, |
thead => 1, tr => 1, |
| 3267 |
area => 1, basefont => 1, bgsound => 1, br => 1, |
area => 1, basefont => 1, bgsound => 1, |
| 3268 |
embed => 1, hr => 1, iframe => 1, image => 1, |
embed => 1, hr => 1, iframe => 1, image => 1, |
| 3269 |
img => 1, input => 1, isindex => 1, noembed => 1, |
img => 1, input => 1, isindex => 1, noembed => 1, |
| 3270 |
noframes => 1, param => 1, select => 1, spacer => 1, |
noframes => 1, param => 1, select => 1, spacer => 1, |
| 3291 |
if ({ |
if ({ |
| 3292 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3293 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3294 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3295 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3296 |
!!!back-token; |
!!!back-token; |
| 3297 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 3335 |
}; # $in_body |
}; # $in_body |
| 3336 |
|
|
| 3337 |
B: { |
B: { |
| 3338 |
if ($phase eq 'main') { |
if ($token->{type} eq 'DOCTYPE') { |
| 3339 |
if ($token->{type} eq 'DOCTYPE') { |
!!!parse-error (type => 'DOCTYPE in the middle'); |
| 3340 |
!!!parse-error (type => 'in html:#DOCTYPE'); |
## Ignore the token |
| 3341 |
## Ignore the token |
## Stay in the phase |
| 3342 |
## Stay in the phase |
!!!next-token; |
| 3343 |
!!!next-token; |
redo B; |
| 3344 |
redo B; |
} elsif ($token->{type} eq 'end-of-file') { |
| 3345 |
} elsif ($token->{type} eq 'start tag' and |
if ($token->{insertion_mode} ne 'trailing end') { |
|
$token->{tag_name} eq 'html') { |
|
|
## TODO: unless it is the first start tag token, parse-error |
|
|
my $top_el = $self->{open_elements}->[0]->[0]; |
|
|
for my $attr_name (keys %{$token->{attributes}}) { |
|
|
unless ($top_el->has_attribute_ns (undef, $attr_name)) { |
|
|
$top_el->set_attribute_ns |
|
|
(undef, [undef, $attr_name], |
|
|
$token->{attributes}->{$attr_name}->{value}); |
|
|
} |
|
|
} |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{type} eq 'end-of-file') { |
|
| 3346 |
## Generate implied end tags |
## Generate implied end tags |
| 3347 |
if ({ |
if ({ |
| 3348 |
dd => 1, dt => 1, li => 1, p => 1, td => 1, th => 1, tr => 1, |
dd => 1, dt => 1, li => 1, p => 1, td => 1, th => 1, tr => 1, |
| 3349 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3350 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3351 |
!!!back-token; |
!!!back-token; |
| 3352 |
$token = {type => 'end tag', tag_name => $self->{open_elements}->[-1]->[1]}; |
$token = {type => 'end tag', tag_name => $self->{open_elements}->[-1]->[1]}; |
| 3362 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3363 |
} |
} |
| 3364 |
|
|
|
## Stop parsing |
|
|
last B; |
|
|
|
|
| 3365 |
## ISSUE: There is an issue in the spec. |
## ISSUE: There is an issue in the spec. |
| 3366 |
|
} |
| 3367 |
|
|
| 3368 |
|
## Stop parsing |
| 3369 |
|
last B; |
| 3370 |
|
} elsif ($token->{type} eq 'start tag' and |
| 3371 |
|
$token->{tag_name} eq 'html') { |
| 3372 |
|
if ($self->{insertion_mode} eq 'trailing end') { |
| 3373 |
|
## Turn into the main phase |
| 3374 |
|
!!!parse-error (type => 'after html:html'); |
| 3375 |
|
$self->{insertion_mode} = $previous_insertion_mode; |
| 3376 |
|
} |
| 3377 |
|
|
| 3378 |
|
## ISSUE: "aa<html>" is not a parse error. |
| 3379 |
|
## ISSUE: "<html>" in fragment is not a parse error. |
| 3380 |
|
unless ($token->{first_start_tag}) { |
| 3381 |
|
!!!parse-error (type => 'not first start tag'); |
| 3382 |
|
} |
| 3383 |
|
my $top_el = $self->{open_elements}->[0]->[0]; |
| 3384 |
|
for my $attr_name (keys %{$token->{attributes}}) { |
| 3385 |
|
unless ($top_el->has_attribute_ns (undef, $attr_name)) { |
| 3386 |
|
$top_el->set_attribute_ns |
| 3387 |
|
(undef, [undef, $attr_name], |
| 3388 |
|
$token->{attributes}->{$attr_name}->{value}); |
| 3389 |
|
} |
| 3390 |
|
} |
| 3391 |
|
!!!next-token; |
| 3392 |
|
redo B; |
| 3393 |
|
} elsif ($token->{type} eq 'comment') { |
| 3394 |
|
my $comment = $self->{document}->create_comment ($token->{data}); |
| 3395 |
|
if ($self->{insertion_mode} eq 'trailing end') { |
| 3396 |
|
$self->{document}->append_child ($comment); |
| 3397 |
|
} elsif ($self->{insertion_mode} eq 'after body') { |
| 3398 |
|
$self->{open_elements}->[0]->[0]->append_child ($comment); |
| 3399 |
} else { |
} else { |
| 3400 |
if ($self->{insertion_mode} eq 'before head') { |
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
| 3401 |
|
} |
| 3402 |
|
!!!next-token; |
| 3403 |
|
redo B; |
| 3404 |
|
} elsif ($self->{insertion_mode} eq 'before head') { |
| 3405 |
if ($token->{type} eq 'character') { |
if ($token->{type} eq 'character') { |
| 3406 |
if ($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); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 3417 |
$self->{insertion_mode} = 'in head'; |
$self->{insertion_mode} = 'in head'; |
| 3418 |
## reprocess |
## reprocess |
| 3419 |
redo B; |
redo B; |
|
} elsif ($token->{type} eq 'comment') { |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 3420 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 3421 |
my $attr = $token->{tag_name} eq 'head' ? $token->{attributes} : {}; |
my $attr = $token->{tag_name} eq 'head' ? $token->{attributes} : {}; |
| 3422 |
!!!create-element ($self->{head_element}, 'head', $attr); |
!!!create-element ($self->{head_element}, 'head', $attr); |
| 3435 |
} |
} |
| 3436 |
redo B; |
redo B; |
| 3437 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} eq 'end tag') { |
| 3438 |
if ({head => 1, body => 1, html => 1}->{$token->{tag_name}}) { |
if ({ |
| 3439 |
|
head => 1, body => 1, html => 1, |
| 3440 |
|
p => 1, br => 1, |
| 3441 |
|
}->{$token->{tag_name}}) { |
| 3442 |
## As if <head> |
## As if <head> |
| 3443 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, 'head'); |
| 3444 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 3468 |
} |
} |
| 3469 |
|
|
| 3470 |
# |
# |
|
} elsif ($token->{type} eq 'comment') { |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 3471 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 3472 |
if ({base => ($self->{insertion_mode} eq 'in head' or |
if ({base => ($self->{insertion_mode} eq 'in head' or |
| 3473 |
$self->{insertion_mode} eq 'after head'), |
$self->{insertion_mode} eq 'after head'), |
| 3474 |
link => 1, meta => 1}->{$token->{tag_name}}) { |
link => 1}->{$token->{tag_name}}) { |
| 3475 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 3476 |
if ($self->{insertion_mode} eq 'after head') { |
if ($self->{insertion_mode} eq 'after head') { |
| 3477 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 3483 |
if $self->{insertion_mode} eq 'after head'; |
if $self->{insertion_mode} eq 'after head'; |
| 3484 |
!!!next-token; |
!!!next-token; |
| 3485 |
redo B; |
redo B; |
| 3486 |
|
} elsif ($token->{tag_name} eq 'meta') { |
| 3487 |
|
## NOTE: There is a "as if in head" code clone. |
| 3488 |
|
if ($self->{insertion_mode} eq 'after head') { |
| 3489 |
|
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 3490 |
|
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3491 |
|
} |
| 3492 |
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 3493 |
|
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 3494 |
|
|
| 3495 |
|
unless ($self->{confident}) { |
| 3496 |
|
my $charset; |
| 3497 |
|
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
| 3498 |
|
$charset = $token->{attributes}->{charset}->{value}; |
| 3499 |
|
} |
| 3500 |
|
if ($token->{attributes}->{'http-equiv'}) { |
| 3501 |
|
## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition. |
| 3502 |
|
if ($token->{attributes}->{'http-equiv'}->{value} |
| 3503 |
|
=~ /\A[^;]*;[\x09-\x0D\x20]*charset[\x09-\x0D\x20]*= |
| 3504 |
|
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
| 3505 |
|
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
| 3506 |
|
$charset = defined $1 ? $1 : defined $2 ? $2 : $3; |
| 3507 |
|
} ## TODO: And if supported |
| 3508 |
|
} |
| 3509 |
|
## TODO: Change the encoding |
| 3510 |
|
} |
| 3511 |
|
|
| 3512 |
|
## TODO: Extracting |charset| from |meta|. |
| 3513 |
|
pop @{$self->{open_elements}} |
| 3514 |
|
if $self->{insertion_mode} eq 'after head'; |
| 3515 |
|
!!!next-token; |
| 3516 |
|
redo B; |
| 3517 |
} elsif ($token->{tag_name} eq 'title' and |
} elsif ($token->{tag_name} eq 'title' and |
| 3518 |
$self->{insertion_mode} eq 'in head') { |
$self->{insertion_mode} eq 'in head') { |
| 3519 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 3521 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 3522 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3523 |
} |
} |
| 3524 |
$parse_rcdata->('RCDATA', $insert_to_current); |
my $parent = defined $self->{head_element} ? $self->{head_element} |
| 3525 |
|
: $self->{open_elements}->[-1]->[0]; |
| 3526 |
|
$parse_rcdata->('RCDATA', sub { $parent->append_child ($_[0]) }); |
| 3527 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} |
| 3528 |
if $self->{insertion_mode} eq 'after head'; |
if $self->{insertion_mode} eq 'after head'; |
| 3529 |
redo B; |
redo B; |
| 3547 |
!!!next-token; |
!!!next-token; |
| 3548 |
redo B; |
redo B; |
| 3549 |
} elsif ($self->{insertion_mode} eq 'in head noscript') { |
} elsif ($self->{insertion_mode} eq 'in head noscript') { |
| 3550 |
!!!parse-error (type => 'noscript in noscript'); |
!!!parse-error (type => 'in noscript:noscript'); |
| 3551 |
## Ignore the token |
## Ignore the token |
| 3552 |
redo B; |
redo B; |
| 3553 |
} else { |
} else { |
| 3599 |
!!!next-token; |
!!!next-token; |
| 3600 |
redo B; |
redo B; |
| 3601 |
} elsif ($self->{insertion_mode} eq 'in head' and |
} elsif ($self->{insertion_mode} eq 'in head' and |
| 3602 |
($token->{tag_name} eq 'body' or |
{ |
| 3603 |
$token->{tag_name} eq 'html')) { |
body => 1, html => 1, |
| 3604 |
|
p => 1, br => 1, |
| 3605 |
|
}->{$token->{tag_name}}) { |
| 3606 |
|
# |
| 3607 |
|
} elsif ($self->{insertion_mode} eq 'in head noscript' and |
| 3608 |
|
{ |
| 3609 |
|
p => 1, br => 1, |
| 3610 |
|
}->{$token->{tag_name}}) { |
| 3611 |
# |
# |
| 3612 |
} elsif ($self->{insertion_mode} ne 'after head') { |
} elsif ($self->{insertion_mode} ne 'after head') { |
| 3613 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3646 |
|
|
| 3647 |
!!!next-token; |
!!!next-token; |
| 3648 |
redo B; |
redo B; |
|
} elsif ($token->{type} eq 'comment') { |
|
|
## NOTE: There is a code clone of "comment in body". |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 3649 |
} else { |
} else { |
| 3650 |
$in_body->($insert_to_current); |
$in_body->($insert_to_current); |
| 3651 |
redo B; |
redo B; |
| 3709 |
|
|
| 3710 |
!!!next-token; |
!!!next-token; |
| 3711 |
redo B; |
redo B; |
|
} elsif ($token->{type} eq 'comment') { |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 3712 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 3713 |
if ({ |
if ({ |
| 3714 |
caption => 1, |
caption => 1, |
| 3780 |
if ({ |
if ({ |
| 3781 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3782 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3783 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3784 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3785 |
!!!back-token; # <table> |
!!!back-token; # <table> |
| 3786 |
$token = {type => 'end tag', tag_name => 'table'}; |
$token = {type => 'end tag', tag_name => 'table'}; |
| 3829 |
if ({ |
if ({ |
| 3830 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3831 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3832 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3833 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3834 |
!!!back-token; |
!!!back-token; |
| 3835 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 3875 |
|
|
| 3876 |
!!!next-token; |
!!!next-token; |
| 3877 |
redo B; |
redo B; |
|
} elsif ($token->{type} eq 'comment') { |
|
|
## NOTE: This is a code clone of "comment in body". |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 3878 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 3879 |
if ({ |
if ({ |
| 3880 |
caption => 1, col => 1, colgroup => 1, tbody => 1, |
caption => 1, col => 1, colgroup => 1, tbody => 1, |
| 3907 |
if ({ |
if ({ |
| 3908 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3909 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3910 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3911 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3912 |
!!!back-token; # <?> |
!!!back-token; # <?> |
| 3913 |
$token = {type => 'end tag', tag_name => 'caption'}; |
$token = {type => 'end tag', tag_name => 'caption'}; |
| 3958 |
if ({ |
if ({ |
| 3959 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3960 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3961 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3962 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3963 |
!!!back-token; |
!!!back-token; |
| 3964 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 4006 |
if ({ |
if ({ |
| 4007 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 4008 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 4009 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 4010 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4011 |
!!!back-token; # </table> |
!!!back-token; # </table> |
| 4012 |
$token = {type => 'end tag', tag_name => 'caption'}; |
$token = {type => 'end tag', tag_name => 'caption'}; |
| 4056 |
} |
} |
| 4057 |
|
|
| 4058 |
# |
# |
|
} elsif ($token->{type} eq 'comment') { |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 4059 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 4060 |
if ($token->{tag_name} eq 'col') { |
if ($token->{tag_name} eq 'col') { |
| 4061 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 4161 |
|
|
| 4162 |
!!!next-token; |
!!!next-token; |
| 4163 |
redo B; |
redo B; |
|
} elsif ($token->{type} eq 'comment') { |
|
|
## Copied from 'in table' |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 4164 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 4165 |
if ({ |
if ({ |
| 4166 |
tr => 1, |
tr => 1, |
| 4261 |
if ({ |
if ({ |
| 4262 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 4263 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 4264 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 4265 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4266 |
!!!back-token; # <table> |
!!!back-token; # <table> |
| 4267 |
$token = {type => 'end tag', tag_name => 'table'}; |
$token = {type => 'end tag', tag_name => 'table'}; |
| 4440 |
|
|
| 4441 |
!!!next-token; |
!!!next-token; |
| 4442 |
redo B; |
redo B; |
|
} elsif ($token->{type} eq 'comment') { |
|
|
## Copied from 'in table' |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 4443 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 4444 |
if ($token->{tag_name} eq 'th' or |
if ($token->{tag_name} eq 'th' or |
| 4445 |
$token->{tag_name} eq 'td') { |
$token->{tag_name} eq 'td') { |
| 4524 |
if ({ |
if ({ |
| 4525 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 4526 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 4527 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 4528 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4529 |
!!!back-token; # <table> |
!!!back-token; # <table> |
| 4530 |
$token = {type => 'end tag', tag_name => 'table'}; |
$token = {type => 'end tag', tag_name => 'table'}; |
| 4699 |
|
|
| 4700 |
!!!next-token; |
!!!next-token; |
| 4701 |
redo B; |
redo B; |
|
} elsif ($token->{type} eq 'comment') { |
|
|
## NOTE: This is a code clone of "comment in body". |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 4702 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 4703 |
if ({ |
if ({ |
| 4704 |
caption => 1, col => 1, colgroup => 1, |
caption => 1, col => 1, colgroup => 1, |
| 4760 |
td => ($token->{tag_name} eq 'th'), |
td => ($token->{tag_name} eq 'th'), |
| 4761 |
th => ($token->{tag_name} eq 'td'), |
th => ($token->{tag_name} eq 'td'), |
| 4762 |
tr => 1, |
tr => 1, |
| 4763 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 4764 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4765 |
!!!back-token; |
!!!back-token; |
| 4766 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 4835 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
| 4836 |
!!!next-token; |
!!!next-token; |
| 4837 |
redo B; |
redo B; |
|
} elsif ($token->{type} eq 'comment') { |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 4838 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 4839 |
if ($token->{tag_name} eq 'option') { |
if ($token->{tag_name} eq 'option') { |
| 4840 |
if ($self->{open_elements}->[-1]->[1] eq 'option') { |
if ($self->{open_elements}->[-1]->[1] eq 'option') { |
| 5007 |
} elsif ($self->{insertion_mode} eq 'after body') { |
} elsif ($self->{insertion_mode} eq 'after body') { |
| 5008 |
if ($token->{type} eq 'character') { |
if ($token->{type} eq 'character') { |
| 5009 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 5010 |
|
my $data = $1; |
| 5011 |
## As if in body |
## As if in body |
| 5012 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 5013 |
|
|
| 5014 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 5015 |
|
|
| 5016 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 5017 |
!!!next-token; |
!!!next-token; |
| 5020 |
} |
} |
| 5021 |
|
|
| 5022 |
# |
# |
| 5023 |
!!!parse-error (type => 'after body:#'.$token->{type}); |
!!!parse-error (type => 'after body:#character'); |
|
} elsif ($token->{type} eq 'comment') { |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[0]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 5024 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 5025 |
!!!parse-error (type => 'after body:'.$token->{tag_name}); |
!!!parse-error (type => 'after body:'.$token->{tag_name}); |
| 5026 |
# |
# |
| 5032 |
!!!next-token; |
!!!next-token; |
| 5033 |
redo B; |
redo B; |
| 5034 |
} else { |
} else { |
| 5035 |
$phase = 'trailing end'; |
$previous_insertion_mode = $self->{insertion_mode}; |
| 5036 |
|
$self->{insertion_mode} = 'trailing end'; |
| 5037 |
!!!next-token; |
!!!next-token; |
| 5038 |
redo B; |
redo B; |
| 5039 |
} |
} |
| 5041 |
!!!parse-error (type => 'after body:/'.$token->{tag_name}); |
!!!parse-error (type => 'after body:/'.$token->{tag_name}); |
| 5042 |
} |
} |
| 5043 |
} else { |
} else { |
| 5044 |
!!!parse-error (type => 'after body:#'.$token->{type}); |
die "$0: $token->{type}: Unknown token type"; |
| 5045 |
} |
} |
| 5046 |
|
|
| 5047 |
$self->{insertion_mode} = 'in body'; |
$self->{insertion_mode} = 'in body'; |
| 5048 |
## reprocess |
## reprocess |
| 5049 |
redo B; |
redo B; |
| 5050 |
} elsif ($self->{insertion_mode} eq 'in frameset') { |
} elsif ($self->{insertion_mode} eq 'in frameset') { |
| 5051 |
if ($token->{type} eq 'character') { |
if ($token->{type} eq 'character') { |
| 5052 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 5053 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
|
|
|
|
unless (length $token->{data}) { |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
|
} |
|
| 5054 |
|
|
| 5055 |
# |
unless (length $token->{data}) { |
|
} elsif ($token->{type} eq 'comment') { |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
| 5056 |
!!!next-token; |
!!!next-token; |
| 5057 |
redo B; |
redo B; |
|
} elsif ($token->{type} eq 'start tag') { |
|
|
if ($token->{tag_name} eq 'frameset') { |
|
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'frame') { |
|
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
|
|
pop @{$self->{open_elements}}; |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'noframes') { |
|
|
$in_body->($insert_to_current); |
|
|
redo B; |
|
|
} else { |
|
|
# |
|
|
} |
|
|
} elsif ($token->{type} eq 'end tag') { |
|
|
if ($token->{tag_name} eq 'frameset') { |
|
|
if ($self->{open_elements}->[-1]->[1] eq 'html' and |
|
|
@{$self->{open_elements}} == 1) { |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
} else { |
|
|
pop @{$self->{open_elements}}; |
|
|
!!!next-token; |
|
|
} |
|
|
|
|
|
## if not inner_html and |
|
|
if ($self->{open_elements}->[-1]->[1] ne 'frameset') { |
|
|
$self->{insertion_mode} = 'after frameset'; |
|
|
} |
|
|
redo B; |
|
|
} else { |
|
|
# |
|
|
} |
|
|
} else { |
|
|
# |
|
| 5058 |
} |
} |
| 5059 |
|
} |
| 5060 |
if (defined $token->{tag_name}) { |
|
| 5061 |
!!!parse-error (type => 'in frameset:'.$token->{tag_name}); |
!!!parse-error (type => 'in frameset:#character'); |
| 5062 |
|
## Ignore the token |
| 5063 |
|
!!!next-token; |
| 5064 |
|
redo B; |
| 5065 |
|
} elsif ($token->{type} eq 'start tag') { |
| 5066 |
|
if ($token->{tag_name} eq 'frameset') { |
| 5067 |
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 5068 |
|
!!!next-token; |
| 5069 |
|
redo B; |
| 5070 |
|
} elsif ($token->{tag_name} eq 'frame') { |
| 5071 |
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 5072 |
|
pop @{$self->{open_elements}}; |
| 5073 |
|
!!!next-token; |
| 5074 |
|
redo B; |
| 5075 |
|
} elsif ($token->{tag_name} eq 'noframes') { |
| 5076 |
|
$in_body->($insert_to_current); |
| 5077 |
|
redo B; |
| 5078 |
|
} else { |
| 5079 |
|
!!!parse-error (type => 'in frameset:'.$token->{tag_name}); |
| 5080 |
|
## Ignore the token |
| 5081 |
|
!!!next-token; |
| 5082 |
|
redo B; |
| 5083 |
|
} |
| 5084 |
|
} elsif ($token->{type} eq 'end tag') { |
| 5085 |
|
if ($token->{tag_name} eq 'frameset') { |
| 5086 |
|
if ($self->{open_elements}->[-1]->[1] eq 'html' and |
| 5087 |
|
@{$self->{open_elements}} == 1) { |
| 5088 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 5089 |
|
## Ignore the token |
| 5090 |
|
!!!next-token; |
| 5091 |
} else { |
} else { |
| 5092 |
!!!parse-error (type => 'in frameset:#'.$token->{type}); |
pop @{$self->{open_elements}}; |
| 5093 |
|
!!!next-token; |
| 5094 |
|
} |
| 5095 |
|
|
| 5096 |
|
if (not defined $self->{inner_html_node} and |
| 5097 |
|
$self->{open_elements}->[-1]->[1] ne 'frameset') { |
| 5098 |
|
$self->{insertion_mode} = 'after frameset'; |
| 5099 |
} |
} |
| 5100 |
|
redo B; |
| 5101 |
|
} else { |
| 5102 |
|
!!!parse-error (type => 'in frameset:/'.$token->{tag_name}); |
| 5103 |
## Ignore the token |
## Ignore the token |
| 5104 |
!!!next-token; |
!!!next-token; |
| 5105 |
redo B; |
redo B; |
| 5106 |
} elsif ($self->{insertion_mode} eq 'after frameset') { |
} |
| 5107 |
if ($token->{type} eq 'character') { |
} else { |
| 5108 |
|
die "$0: $token->{type}: Unknown token type"; |
| 5109 |
|
} |
| 5110 |
|
} elsif ($self->{insertion_mode} eq 'after frameset') { |
| 5111 |
|
if ($token->{type} eq 'character') { |
| 5112 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 5113 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 5114 |
|
|
| 5115 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 5116 |
!!!next-token; |
!!!next-token; |
| 5118 |
} |
} |
| 5119 |
} |
} |
| 5120 |
|
|
| 5121 |
# |
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
| 5122 |
} elsif ($token->{type} eq 'comment') { |
!!!parse-error (type => 'after frameset:#character'); |
| 5123 |
my $comment = $self->{document}->create_comment ($token->{data}); |
|
| 5124 |
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
## Ignore the token. |
| 5125 |
!!!next-token; |
if (length $token->{data}) { |
| 5126 |
redo B; |
## reprocess the rest of characters |
| 5127 |
} elsif ($token->{type} eq 'start tag') { |
} else { |
| 5128 |
if ($token->{tag_name} eq 'noframes') { |
!!!next-token; |
| 5129 |
$in_body->($insert_to_current); |
} |
|
redo B; |
|
|
} else { |
|
|
# |
|
|
} |
|
|
} elsif ($token->{type} eq 'end tag') { |
|
|
if ($token->{tag_name} eq 'html') { |
|
|
$phase = 'trailing end'; |
|
|
!!!next-token; |
|
| 5130 |
redo B; |
redo B; |
|
} else { |
|
|
# |
|
| 5131 |
} |
} |
| 5132 |
} else { |
|
| 5133 |
# |
die qq[$0: Character "$token->{data}"]; |
| 5134 |
} |
} elsif ($token->{type} eq 'start tag') { |
| 5135 |
|
if ($token->{tag_name} eq 'noframes') { |
| 5136 |
if (defined $token->{tag_name}) { |
$in_body->($insert_to_current); |
| 5137 |
!!!parse-error (type => 'after frameset:'.$token->{tag_name}); |
redo B; |
| 5138 |
} else { |
} else { |
| 5139 |
!!!parse-error (type => 'after frameset:#'.$token->{type}); |
!!!parse-error (type => 'after frameset:'.$token->{tag_name}); |
|
} |
|
| 5140 |
## Ignore the token |
## Ignore the token |
| 5141 |
!!!next-token; |
!!!next-token; |
| 5142 |
redo B; |
redo B; |
| 5143 |
|
} |
| 5144 |
## ISSUE: An issue in spec there |
} elsif ($token->{type} eq 'end tag') { |
| 5145 |
|
if ($token->{tag_name} eq 'html') { |
| 5146 |
|
$previous_insertion_mode = $self->{insertion_mode}; |
| 5147 |
|
$self->{insertion_mode} = 'trailing end'; |
| 5148 |
|
!!!next-token; |
| 5149 |
|
redo B; |
| 5150 |
} else { |
} else { |
| 5151 |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
!!!parse-error (type => 'after frameset:/'.$token->{tag_name}); |
| 5152 |
|
## Ignore the token |
| 5153 |
|
!!!next-token; |
| 5154 |
|
redo B; |
| 5155 |
} |
} |
| 5156 |
|
} else { |
| 5157 |
|
die "$0: $token->{type}: Unknown token type"; |
| 5158 |
} |
} |
| 5159 |
} elsif ($phase eq 'trailing end') { |
|
| 5160 |
|
## ISSUE: An issue in spec here |
| 5161 |
|
} elsif ($self->{insertion_mode} eq 'trailing end') { |
| 5162 |
## states in the main stage is preserved yet # MUST |
## states in the main stage is preserved yet # MUST |
| 5163 |
|
|
| 5164 |
if ($token->{type} eq 'DOCTYPE') { |
if ($token->{type} eq 'character') { |
|
!!!parse-error (type => 'after html:#DOCTYPE'); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{type} eq 'comment') { |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{document}->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{type} eq 'character') { |
|
| 5165 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 5166 |
my $data = $1; |
my $data = $1; |
| 5167 |
## As if in the main phase. |
## As if in the main phase. |
| 5168 |
## NOTE: The insertion mode in the main phase |
## NOTE: The insertion mode in the main phase |
| 5169 |
## just before the phase has been changed to the trailing |
## just before the phase has been changed to the trailing |
| 5170 |
## end phase is either "after body" or "after frameset". |
## end phase is either "after body" or "after frameset". |
| 5171 |
$reconstruct_active_formatting_elements->($insert_to_current) |
$reconstruct_active_formatting_elements->($insert_to_current); |
|
if $phase eq 'main'; |
|
| 5172 |
|
|
| 5173 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($data); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($data); |
| 5174 |
|
|
| 5179 |
} |
} |
| 5180 |
|
|
| 5181 |
!!!parse-error (type => 'after html:#character'); |
!!!parse-error (type => 'after html:#character'); |
| 5182 |
$phase = 'main'; |
$self->{insertion_mode} = $previous_insertion_mode; |
| 5183 |
## reprocess |
## reprocess |
| 5184 |
redo B; |
redo B; |
| 5185 |
} elsif ($token->{type} eq 'start tag' or |
} elsif ($token->{type} eq 'start tag') { |
|
$token->{type} eq 'end tag') { |
|
| 5186 |
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
| 5187 |
$phase = 'main'; |
$self->{insertion_mode} = $previous_insertion_mode; |
| 5188 |
|
## reprocess |
| 5189 |
|
redo B; |
| 5190 |
|
} elsif ($token->{type} eq 'end tag') { |
| 5191 |
|
!!!parse-error (type => 'after html:/'.$token->{tag_name}); |
| 5192 |
|
$self->{insertion_mode} = $previous_insertion_mode; |
| 5193 |
## reprocess |
## reprocess |
| 5194 |
redo B; |
redo B; |
|
} elsif ($token->{type} eq 'end-of-file') { |
|
|
## Stop parsing |
|
|
last B; |
|
| 5195 |
} else { |
} else { |
| 5196 |
die "$0: $token->{type}: Unknown token"; |
die "$0: $token->{type}: Unknown token"; |
| 5197 |
} |
} |
| 5198 |
|
} else { |
| 5199 |
|
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
| 5200 |
} |
} |
| 5201 |
} # B |
} # B |
| 5202 |
|
|
| 5396 |
|
|
| 5397 |
my $nt = $child->node_type; |
my $nt = $child->node_type; |
| 5398 |
if ($nt == 1) { # Element |
if ($nt == 1) { # Element |
| 5399 |
my $tag_name = lc $child->tag_name; ## ISSUE: Definition of "lowercase" |
my $tag_name = $child->tag_name; ## TODO: manakai_tag_name |
| 5400 |
$s .= '<' . $tag_name; |
$s .= '<' . $tag_name; |
| 5401 |
|
## NOTE: Non-HTML case: |
| 5402 |
## ISSUE: Non-html elements |
## <http://permalink.gmane.org/gmane.org.w3c.whatwg.discuss/11191> |
| 5403 |
|
|
| 5404 |
my @attrs = @{$child->attributes}; # sort order MUST be stable |
my @attrs = @{$child->attributes}; # sort order MUST be stable |
| 5405 |
for my $attr (@attrs) { # order is implementation dependent |
for my $attr (@attrs) { # order is implementation dependent |
| 5406 |
my $attr_name = lc $attr->name; ## ISSUE: Definition of "lowercase" |
my $attr_name = $attr->name; ## TODO: manakai_name |
| 5407 |
$s .= ' ' . $attr_name . '="'; |
$s .= ' ' . $attr_name . '="'; |
| 5408 |
my $attr_value = $attr->value; |
my $attr_value = $attr->value; |
| 5409 |
## escape |
## escape |
| 5427 |
if (not $in_cdata and { |
if (not $in_cdata and { |
| 5428 |
style => 1, script => 1, xmp => 1, iframe => 1, |
style => 1, script => 1, xmp => 1, iframe => 1, |
| 5429 |
noembed => 1, noframes => 1, noscript => 1, |
noembed => 1, noframes => 1, noscript => 1, |
| 5430 |
|
plaintext => 1, |
| 5431 |
}->{$tag_name}) { |
}->{$tag_name}) { |
| 5432 |
unshift @node, 'cdata-out'; |
unshift @node, 'cdata-out'; |
| 5433 |
$in_cdata = 1; |
$in_cdata = 1; |