| 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'; |
$self->{state} = 'data'; |
| 259 |
# next-input-character is already done |
# next-input-character is already done |
| 332 |
} elsif ($self->{state} eq 'close tag open') { |
} elsif ($self->{state} eq 'close tag open') { |
| 333 |
if ($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 |
my @next_char; |
if (defined $self->{last_emitted_start_tag_name}) { |
| 336 |
TAGNAME: for (my $i = 0; $i < length $self->{last_emitted_start_tag_name}; $i++) { |
## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564> |
| 337 |
|
my @next_char; |
| 338 |
|
TAGNAME: for (my $i = 0; $i < length $self->{last_emitted_start_tag_name}; $i++) { |
| 339 |
|
push @next_char, $self->{next_input_character}; |
| 340 |
|
my $c = ord substr ($self->{last_emitted_start_tag_name}, $i, 1); |
| 341 |
|
my $C = 0x0061 <= $c && $c <= 0x007A ? $c - 0x0020 : $c; |
| 342 |
|
if ($self->{next_input_character} == $c or $self->{next_input_character} == $C) { |
| 343 |
|
!!!next-input-character; |
| 344 |
|
next TAGNAME; |
| 345 |
|
} else { |
| 346 |
|
$self->{next_input_character} = shift @next_char; # reconsume |
| 347 |
|
!!!back-next-input-character (@next_char); |
| 348 |
|
$self->{state} = 'data'; |
| 349 |
|
|
| 350 |
|
!!!emit ({type => 'character', data => '</'}); |
| 351 |
|
|
| 352 |
|
redo A; |
| 353 |
|
} |
| 354 |
|
} |
| 355 |
push @next_char, $self->{next_input_character}; |
push @next_char, $self->{next_input_character}; |
| 356 |
my $c = ord substr ($self->{last_emitted_start_tag_name}, $i, 1); |
|
| 357 |
my $C = 0x0061 <= $c && $c <= 0x007A ? $c - 0x0020 : $c; |
unless ($self->{next_input_character} == 0x0009 or # HT |
| 358 |
if ($self->{next_input_character} == $c or $self->{next_input_character} == $C) { |
$self->{next_input_character} == 0x000A or # LF |
| 359 |
!!!next-input-character; |
$self->{next_input_character} == 0x000B or # VT |
| 360 |
next TAGNAME; |
$self->{next_input_character} == 0x000C or # FF |
| 361 |
} else { |
$self->{next_input_character} == 0x0020 or # SP |
| 362 |
|
$self->{next_input_character} == 0x003E or # > |
| 363 |
|
$self->{next_input_character} == 0x002F or # / |
| 364 |
|
$self->{next_input_character} == -1) { |
| 365 |
$self->{next_input_character} = shift @next_char; # reconsume |
$self->{next_input_character} = shift @next_char; # reconsume |
| 366 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 367 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
|
|
|
| 368 |
!!!emit ({type => 'character', data => '</'}); |
!!!emit ({type => 'character', data => '</'}); |
|
|
|
| 369 |
redo A; |
redo A; |
| 370 |
|
} else { |
| 371 |
|
$self->{next_input_character} = shift @next_char; |
| 372 |
|
!!!back-next-input-character (@next_char); |
| 373 |
|
# and consume... |
| 374 |
} |
} |
| 375 |
} |
} else { |
| 376 |
push @next_char, $self->{next_input_character}; |
## No start tag token has ever been emitted |
| 377 |
|
# next-input-character is already done |
|
unless ($self->{next_input_character} == 0x0009 or # HT |
|
|
$self->{next_input_character} == 0x000A or # LF |
|
|
$self->{next_input_character} == 0x000B or # VT |
|
|
$self->{next_input_character} == 0x000C or # FF |
|
|
$self->{next_input_character} == 0x0020 or # SP |
|
|
$self->{next_input_character} == 0x003E or # > |
|
|
$self->{next_input_character} == 0x002F or # / |
|
|
$self->{next_input_character} == -1) { |
|
|
$self->{next_input_character} = shift @next_char; # reconsume |
|
|
!!!back-next-input-character (@next_char); |
|
| 378 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
|
|
|
| 379 |
!!!emit ({type => 'character', data => '</'}); |
!!!emit ({type => 'character', data => '</'}); |
|
|
|
| 380 |
redo A; |
redo A; |
|
} else { |
|
|
$self->{next_input_character} = shift @next_char; |
|
|
!!!back-next-input-character (@next_char); |
|
|
# and consume... |
|
| 381 |
} |
} |
| 382 |
} |
} |
| 383 |
|
|
| 425 |
redo A; |
redo A; |
| 426 |
} elsif ($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 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 440 |
!!!next-input-character; |
!!!next-input-character; |
| 441 |
|
|
| 442 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 443 |
|
|
| 444 |
redo A; |
redo A; |
| 445 |
} elsif (0x0041 <= $self->{next_input_character} and |
} elsif (0x0041 <= $self->{next_input_character} and |
| 452 |
} elsif ($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 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 467 |
# reconsume |
# reconsume |
| 468 |
|
|
| 469 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 470 |
|
|
| 471 |
redo A; |
redo A; |
| 472 |
} elsif ($self->{next_input_character} == 0x002F) { # / |
} elsif ($self->{next_input_character} == 0x002F) { # / |
| 500 |
redo A; |
redo A; |
| 501 |
} elsif ($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 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 515 |
!!!next-input-character; |
!!!next-input-character; |
| 516 |
|
|
| 517 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 518 |
|
|
| 519 |
redo A; |
redo A; |
| 520 |
} elsif (0x0041 <= $self->{next_input_character} and |
} elsif (0x0041 <= $self->{next_input_character} and |
| 540 |
} elsif ($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 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 555 |
# reconsume |
# reconsume |
| 556 |
|
|
| 557 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 558 |
|
|
| 559 |
redo A; |
redo A; |
| 560 |
} else { |
} else { |
| 593 |
} elsif ($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 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 608 |
!!!next-input-character; |
!!!next-input-character; |
| 609 |
|
|
| 610 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 611 |
|
|
| 612 |
redo A; |
redo A; |
| 613 |
} elsif (0x0041 <= $self->{next_input_character} and |
} elsif (0x0041 <= $self->{next_input_character} and |
| 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 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 649 |
# reconsume |
# reconsume |
| 650 |
|
|
| 651 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 652 |
|
|
| 653 |
redo A; |
redo A; |
| 654 |
} else { |
} else { |
| 672 |
redo A; |
redo A; |
| 673 |
} elsif ($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 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 687 |
!!!next-input-character; |
!!!next-input-character; |
| 688 |
|
|
| 689 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 690 |
|
|
| 691 |
redo A; |
redo A; |
| 692 |
} elsif (0x0041 <= $self->{next_input_character} and |
} elsif (0x0041 <= $self->{next_input_character} and |
| 712 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 713 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 714 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 715 |
|
$self->{current_token}->{first_start_tag} |
| 716 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 717 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 718 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 719 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 727 |
# reconsume |
# reconsume |
| 728 |
|
|
| 729 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 730 |
|
|
| 731 |
redo A; |
redo A; |
| 732 |
} else { |
} else { |
| 759 |
redo A; |
redo A; |
| 760 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 761 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 762 |
|
$self->{current_token}->{first_start_tag} |
| 763 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 764 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 765 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 766 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 774 |
!!!next-input-character; |
!!!next-input-character; |
| 775 |
|
|
| 776 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 777 |
|
|
| 778 |
redo A; |
redo A; |
| 779 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 780 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 781 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 782 |
|
$self->{current_token}->{first_start_tag} |
| 783 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 784 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 785 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 786 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 794 |
## reconsume |
## reconsume |
| 795 |
|
|
| 796 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 797 |
|
|
| 798 |
redo A; |
redo A; |
| 799 |
} else { |
} else { |
| 815 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 816 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
| 817 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 818 |
|
$self->{current_token}->{first_start_tag} |
| 819 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 820 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 821 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 822 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 830 |
## reconsume |
## reconsume |
| 831 |
|
|
| 832 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 833 |
|
|
| 834 |
redo A; |
redo A; |
| 835 |
} else { |
} else { |
| 851 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 852 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
| 853 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 854 |
|
$self->{current_token}->{first_start_tag} |
| 855 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 856 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 857 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 858 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 866 |
## reconsume |
## reconsume |
| 867 |
|
|
| 868 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 869 |
|
|
| 870 |
redo A; |
redo A; |
| 871 |
} else { |
} else { |
| 890 |
redo A; |
redo A; |
| 891 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 892 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 893 |
|
$self->{current_token}->{first_start_tag} |
| 894 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 895 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 896 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 897 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 905 |
!!!next-input-character; |
!!!next-input-character; |
| 906 |
|
|
| 907 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 908 |
|
|
| 909 |
redo A; |
redo A; |
| 910 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 911 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 912 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 913 |
|
$self->{current_token}->{first_start_tag} |
| 914 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 915 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 916 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 917 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model_flag} = 'PCDATA'; # MUST |
| 925 |
## reconsume |
## reconsume |
| 926 |
|
|
| 927 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 928 |
|
|
| 929 |
redo A; |
redo A; |
| 930 |
} else { |
} else { |
| 934 |
redo A; |
redo A; |
| 935 |
} |
} |
| 936 |
} elsif ($self->{state} eq 'entity in attribute value') { |
} elsif ($self->{state} eq 'entity in attribute value') { |
| 937 |
my $token = $self->_tokenize_attempt_to_consume_an_entity; |
my $token = $self->_tokenize_attempt_to_consume_an_entity (1); |
| 938 |
|
|
| 939 |
unless (defined $token) { |
unless (defined $token) { |
| 940 |
$self->{current_attribute}->{value} .= '&'; |
$self->{current_attribute}->{value} .= '&'; |
| 983 |
push @next_char, $self->{next_input_character}; |
push @next_char, $self->{next_input_character}; |
| 984 |
if ($self->{next_input_character} == 0x002D) { # - |
if ($self->{next_input_character} == 0x002D) { # - |
| 985 |
$self->{current_token} = {type => 'comment', data => ''}; |
$self->{current_token} = {type => 'comment', data => ''}; |
| 986 |
$self->{state} = 'comment'; |
$self->{state} = 'comment start'; |
| 987 |
!!!next-input-character; |
!!!next-input-character; |
| 988 |
redo A; |
redo A; |
| 989 |
} |
} |
| 1025 |
} |
} |
| 1026 |
} |
} |
| 1027 |
|
|
| 1028 |
!!!parse-error (type => 'bogus comment open'); |
!!!parse-error (type => 'bogus comment'); |
| 1029 |
$self->{next_input_character} = shift @next_char; |
$self->{next_input_character} = shift @next_char; |
| 1030 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 1031 |
$self->{state} = 'bogus comment'; |
$self->{state} = 'bogus comment'; |
| 1033 |
|
|
| 1034 |
## ISSUE: typos in spec: chacacters, is is a parse error |
## ISSUE: typos in spec: chacacters, is is a parse error |
| 1035 |
## ISSUE: spec is somewhat unclear on "is the first character that will be in the comment"; what is "that will be in the comment" is what the algorithm defines, isn't it? |
## ISSUE: spec is somewhat unclear on "is the first character that will be in the comment"; what is "that will be in the comment" is what the algorithm defines, isn't it? |
| 1036 |
|
} elsif ($self->{state} eq 'comment start') { |
| 1037 |
|
if ($self->{next_input_character} == 0x002D) { # - |
| 1038 |
|
$self->{state} = 'comment start dash'; |
| 1039 |
|
!!!next-input-character; |
| 1040 |
|
redo A; |
| 1041 |
|
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1042 |
|
!!!parse-error (type => 'bogus comment'); |
| 1043 |
|
$self->{state} = 'data'; |
| 1044 |
|
!!!next-input-character; |
| 1045 |
|
|
| 1046 |
|
!!!emit ($self->{current_token}); # comment |
| 1047 |
|
|
| 1048 |
|
redo A; |
| 1049 |
|
} elsif ($self->{next_input_character} == -1) { |
| 1050 |
|
!!!parse-error (type => 'unclosed comment'); |
| 1051 |
|
$self->{state} = 'data'; |
| 1052 |
|
## reconsume |
| 1053 |
|
|
| 1054 |
|
!!!emit ($self->{current_token}); # comment |
| 1055 |
|
|
| 1056 |
|
redo A; |
| 1057 |
|
} else { |
| 1058 |
|
$self->{current_token}->{data} # comment |
| 1059 |
|
.= chr ($self->{next_input_character}); |
| 1060 |
|
$self->{state} = 'comment'; |
| 1061 |
|
!!!next-input-character; |
| 1062 |
|
redo A; |
| 1063 |
|
} |
| 1064 |
|
} elsif ($self->{state} eq 'comment start dash') { |
| 1065 |
|
if ($self->{next_input_character} == 0x002D) { # - |
| 1066 |
|
$self->{state} = 'comment end'; |
| 1067 |
|
!!!next-input-character; |
| 1068 |
|
redo A; |
| 1069 |
|
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1070 |
|
!!!parse-error (type => 'bogus comment'); |
| 1071 |
|
$self->{state} = 'data'; |
| 1072 |
|
!!!next-input-character; |
| 1073 |
|
|
| 1074 |
|
!!!emit ($self->{current_token}); # comment |
| 1075 |
|
|
| 1076 |
|
redo A; |
| 1077 |
|
} elsif ($self->{next_input_character} == -1) { |
| 1078 |
|
!!!parse-error (type => 'unclosed comment'); |
| 1079 |
|
$self->{state} = 'data'; |
| 1080 |
|
## reconsume |
| 1081 |
|
|
| 1082 |
|
!!!emit ($self->{current_token}); # comment |
| 1083 |
|
|
| 1084 |
|
redo A; |
| 1085 |
|
} else { |
| 1086 |
|
$self->{current_token}->{data} # comment |
| 1087 |
|
.= chr ($self->{next_input_character}); |
| 1088 |
|
$self->{state} = 'comment'; |
| 1089 |
|
!!!next-input-character; |
| 1090 |
|
redo A; |
| 1091 |
|
} |
| 1092 |
} elsif ($self->{state} eq 'comment') { |
} elsif ($self->{state} eq 'comment') { |
| 1093 |
if ($self->{next_input_character} == 0x002D) { # - |
if ($self->{next_input_character} == 0x002D) { # - |
| 1094 |
$self->{state} = 'comment dash'; |
$self->{state} = 'comment end dash'; |
| 1095 |
!!!next-input-character; |
!!!next-input-character; |
| 1096 |
redo A; |
redo A; |
| 1097 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1100 |
## reconsume |
## reconsume |
| 1101 |
|
|
| 1102 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
|
undef $self->{current_token}; |
|
| 1103 |
|
|
| 1104 |
redo A; |
redo A; |
| 1105 |
} else { |
} else { |
| 1108 |
!!!next-input-character; |
!!!next-input-character; |
| 1109 |
redo A; |
redo A; |
| 1110 |
} |
} |
| 1111 |
} elsif ($self->{state} eq 'comment dash') { |
} elsif ($self->{state} eq 'comment end dash') { |
| 1112 |
if ($self->{next_input_character} == 0x002D) { # - |
if ($self->{next_input_character} == 0x002D) { # - |
| 1113 |
$self->{state} = 'comment end'; |
$self->{state} = 'comment end'; |
| 1114 |
!!!next-input-character; |
!!!next-input-character; |
| 1119 |
## reconsume |
## reconsume |
| 1120 |
|
|
| 1121 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
|
undef $self->{current_token}; |
|
| 1122 |
|
|
| 1123 |
redo A; |
redo A; |
| 1124 |
} else { |
} else { |
| 1133 |
!!!next-input-character; |
!!!next-input-character; |
| 1134 |
|
|
| 1135 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
|
undef $self->{current_token}; |
|
| 1136 |
|
|
| 1137 |
redo A; |
redo A; |
| 1138 |
} elsif ($self->{next_input_character} == 0x002D) { # - |
} elsif ($self->{next_input_character} == 0x002D) { # - |
| 1147 |
## reconsume |
## reconsume |
| 1148 |
|
|
| 1149 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
|
undef $self->{current_token}; |
|
| 1150 |
|
|
| 1151 |
redo A; |
redo A; |
| 1152 |
} else { |
} else { |
| 1221 |
!!!next-input-character; |
!!!next-input-character; |
| 1222 |
|
|
| 1223 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1224 |
|
|
| 1225 |
redo A; |
redo A; |
| 1226 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1230 |
|
|
| 1231 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1232 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1233 |
|
|
| 1234 |
redo A; |
redo A; |
| 1235 |
} else { |
} else { |
| 1253 |
!!!next-input-character; |
!!!next-input-character; |
| 1254 |
|
|
| 1255 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1256 |
|
|
| 1257 |
redo A; |
redo A; |
| 1258 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1262 |
|
|
| 1263 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1264 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1265 |
|
|
| 1266 |
redo A; |
redo A; |
| 1267 |
} elsif ($self->{next_input_character} == 0x0050 or # P |
} elsif ($self->{next_input_character} == 0x0050 or # P |
| 1353 |
|
|
| 1354 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1355 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1356 |
|
|
| 1357 |
redo A; |
redo A; |
| 1358 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1363 |
|
|
| 1364 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1365 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1366 |
|
|
| 1367 |
redo A; |
redo A; |
| 1368 |
} else { |
} else { |
| 1384 |
|
|
| 1385 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1386 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1387 |
|
|
| 1388 |
redo A; |
redo A; |
| 1389 |
} else { |
} else { |
| 1406 |
|
|
| 1407 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1408 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1409 |
|
|
| 1410 |
redo A; |
redo A; |
| 1411 |
} else { |
} else { |
| 1438 |
!!!next-input-character; |
!!!next-input-character; |
| 1439 |
|
|
| 1440 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1441 |
|
|
| 1442 |
redo A; |
redo A; |
| 1443 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1444 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1445 |
|
|
| 1446 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 1447 |
## recomsume |
## reconsume |
| 1448 |
|
|
| 1449 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1450 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1451 |
|
|
| 1452 |
redo A; |
redo A; |
| 1453 |
} else { |
} else { |
| 1481 |
|
|
| 1482 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1483 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1484 |
|
|
| 1485 |
redo A; |
redo A; |
| 1486 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1487 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1488 |
|
|
| 1489 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 1490 |
## recomsume |
## reconsume |
| 1491 |
|
|
| 1492 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1493 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1494 |
|
|
| 1495 |
redo A; |
redo A; |
| 1496 |
} else { |
} else { |
| 1497 |
!!!parse-error (type => 'string after PUBLIC literal'); |
!!!parse-error (type => 'string after SYSTEM'); |
| 1498 |
$self->{state} = 'bogus DOCTYPE'; |
$self->{state} = 'bogus DOCTYPE'; |
| 1499 |
!!!next-input-character; |
!!!next-input-character; |
| 1500 |
redo A; |
redo A; |
| 1512 |
|
|
| 1513 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1514 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1515 |
|
|
| 1516 |
redo A; |
redo A; |
| 1517 |
} else { |
} else { |
| 1534 |
|
|
| 1535 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1536 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1537 |
|
|
| 1538 |
redo A; |
redo A; |
| 1539 |
} else { |
} else { |
| 1556 |
!!!next-input-character; |
!!!next-input-character; |
| 1557 |
|
|
| 1558 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1559 |
|
|
| 1560 |
redo A; |
redo A; |
| 1561 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1562 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1563 |
|
|
| 1564 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 1565 |
## recomsume |
## reconsume |
| 1566 |
|
|
| 1567 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1568 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1569 |
|
|
| 1570 |
redo A; |
redo A; |
| 1571 |
} else { |
} else { |
| 1581 |
|
|
| 1582 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1583 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1584 |
|
|
| 1585 |
redo A; |
redo A; |
| 1586 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1590 |
|
|
| 1591 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1592 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1593 |
|
|
| 1594 |
redo A; |
redo A; |
| 1595 |
} else { |
} else { |
| 1605 |
die "$0: _get_next_token: unexpected case"; |
die "$0: _get_next_token: unexpected case"; |
| 1606 |
} # _get_next_token |
} # _get_next_token |
| 1607 |
|
|
| 1608 |
sub _tokenize_attempt_to_consume_an_entity ($) { |
sub _tokenize_attempt_to_consume_an_entity ($$) { |
| 1609 |
my $self = shift; |
my ($self, $in_attr) = @_; |
| 1610 |
|
|
| 1611 |
if ($self->{next_input_character} == 0x0023) { # # |
if ({ |
| 1612 |
|
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, # HT, LF, VT, FF, |
| 1613 |
|
0x0020 => 1, 0x003C => 1, 0x0026 => 1, -1 => 1, # SP, <, & # 0x000D # CR |
| 1614 |
|
}->{$self->{next_input_character}}) { |
| 1615 |
|
## Don't consume |
| 1616 |
|
## No error |
| 1617 |
|
return undef; |
| 1618 |
|
} elsif ($self->{next_input_character} == 0x0023) { # # |
| 1619 |
!!!next-input-character; |
!!!next-input-character; |
| 1620 |
if ($self->{next_input_character} == 0x0078 or # x |
if ($self->{next_input_character} == 0x0078 or # x |
| 1621 |
$self->{next_input_character} == 0x0058) { # X |
$self->{next_input_character} == 0x0058) { # X |
| 1622 |
my $num; |
my $code; |
| 1623 |
X: { |
X: { |
| 1624 |
my $x_char = $self->{next_input_character}; |
my $x_char = $self->{next_input_character}; |
| 1625 |
!!!next-input-character; |
!!!next-input-character; |
| 1626 |
if (0x0030 <= $self->{next_input_character} and |
if (0x0030 <= $self->{next_input_character} and |
| 1627 |
$self->{next_input_character} <= 0x0039) { # 0..9 |
$self->{next_input_character} <= 0x0039) { # 0..9 |
| 1628 |
$num ||= 0; |
$code ||= 0; |
| 1629 |
$num *= 0x10; |
$code *= 0x10; |
| 1630 |
$num += $self->{next_input_character} - 0x0030; |
$code += $self->{next_input_character} - 0x0030; |
| 1631 |
redo X; |
redo X; |
| 1632 |
} elsif (0x0061 <= $self->{next_input_character} and |
} elsif (0x0061 <= $self->{next_input_character} and |
| 1633 |
$self->{next_input_character} <= 0x0066) { # a..f |
$self->{next_input_character} <= 0x0066) { # a..f |
| 1634 |
## ISSUE: the spec says U+0078, which is apparently incorrect |
$code ||= 0; |
| 1635 |
$num ||= 0; |
$code *= 0x10; |
| 1636 |
$num *= 0x10; |
$code += $self->{next_input_character} - 0x0060 + 9; |
|
$num += $self->{next_input_character} - 0x0060 + 9; |
|
| 1637 |
redo X; |
redo X; |
| 1638 |
} elsif (0x0041 <= $self->{next_input_character} and |
} elsif (0x0041 <= $self->{next_input_character} and |
| 1639 |
$self->{next_input_character} <= 0x0046) { # A..F |
$self->{next_input_character} <= 0x0046) { # A..F |
| 1640 |
## ISSUE: the spec says U+0058, which is apparently incorrect |
$code ||= 0; |
| 1641 |
$num ||= 0; |
$code *= 0x10; |
| 1642 |
$num *= 0x10; |
$code += $self->{next_input_character} - 0x0040 + 9; |
|
$num += $self->{next_input_character} - 0x0040 + 9; |
|
| 1643 |
redo X; |
redo X; |
| 1644 |
} elsif (not defined $num) { # no hexadecimal digit |
} elsif (not defined $code) { # no hexadecimal digit |
| 1645 |
!!!parse-error (type => 'bare hcro'); |
!!!parse-error (type => 'bare hcro'); |
| 1646 |
$self->{next_input_character} = 0x0023; # # |
$self->{next_input_character} = 0x0023; # # |
| 1647 |
!!!back-next-input-character ($x_char); |
!!!back-next-input-character ($x_char); |
| 1652 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'no refc'); |
| 1653 |
} |
} |
| 1654 |
|
|
| 1655 |
## TODO: check the definition for |a valid Unicode character|. |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 1656 |
## <http://lists.whatwg.org/pipermail/whatwg-whatwg.org/2006-December/thread.html#8189> |
!!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code); |
| 1657 |
if ($num > 1114111 or $num == 0) { |
$code = 0xFFFD; |
| 1658 |
$num = 0xFFFD; # REPLACEMENT CHARACTER |
} elsif ($code > 0x10FFFF) { |
| 1659 |
## ISSUE: Why this is not an error? |
!!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code); |
| 1660 |
} elsif (0x80 <= $num and $num <= 0x9F) { |
$code = 0xFFFD; |
| 1661 |
!!!parse-error (type => sprintf 'c1 entity:U+%04X', $num); |
} elsif ($code == 0x000D) { |
| 1662 |
$num = $c1_entity_char->{$num}; |
!!!parse-error (type => 'CR character reference'); |
| 1663 |
|
$code = 0x000A; |
| 1664 |
|
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 1665 |
|
!!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code); |
| 1666 |
|
$code = $c1_entity_char->{$code}; |
| 1667 |
} |
} |
| 1668 |
|
|
| 1669 |
return {type => 'character', data => chr $num}; |
return {type => 'character', data => chr $code}; |
| 1670 |
} # X |
} # X |
| 1671 |
} elsif (0x0030 <= $self->{next_input_character} and |
} elsif (0x0030 <= $self->{next_input_character} and |
| 1672 |
$self->{next_input_character} <= 0x0039) { # 0..9 |
$self->{next_input_character} <= 0x0039) { # 0..9 |
| 1687 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'no refc'); |
| 1688 |
} |
} |
| 1689 |
|
|
| 1690 |
## TODO: check the definition for |a valid Unicode character|. |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 1691 |
if ($code > 1114111 or $code == 0) { |
!!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code); |
| 1692 |
$code = 0xFFFD; # REPLACEMENT CHARACTER |
$code = 0xFFFD; |
| 1693 |
## ISSUE: Why this is not an error? |
} elsif ($code > 0x10FFFF) { |
| 1694 |
|
!!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code); |
| 1695 |
|
$code = 0xFFFD; |
| 1696 |
|
} elsif ($code == 0x000D) { |
| 1697 |
|
!!!parse-error (type => 'CR character reference'); |
| 1698 |
|
$code = 0x000A; |
| 1699 |
} elsif (0x80 <= $code and $code <= 0x9F) { |
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 1700 |
!!!parse-error (type => sprintf 'c1 entity:U+%04X', $code); |
!!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code); |
| 1701 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 1702 |
} |
} |
| 1703 |
|
|
| 1731 |
$self->{next_input_character} == 0x003B)) { # ; |
$self->{next_input_character} == 0x003B)) { # ; |
| 1732 |
$entity_name .= chr $self->{next_input_character}; |
$entity_name .= chr $self->{next_input_character}; |
| 1733 |
if (defined $EntityChar->{$entity_name}) { |
if (defined $EntityChar->{$entity_name}) { |
|
$value = $EntityChar->{$entity_name}; |
|
| 1734 |
if ($self->{next_input_character} == 0x003B) { # ; |
if ($self->{next_input_character} == 0x003B) { # ; |
| 1735 |
|
$value = $EntityChar->{$entity_name}; |
| 1736 |
$match = 1; |
$match = 1; |
| 1737 |
!!!next-input-character; |
!!!next-input-character; |
| 1738 |
last; |
last; |
| 1739 |
} else { |
} elsif (not $in_attr) { |
| 1740 |
|
$value = $EntityChar->{$entity_name}; |
| 1741 |
$match = -1; |
$match = -1; |
| 1742 |
|
} else { |
| 1743 |
|
$value .= chr $self->{next_input_character}; |
| 1744 |
} |
} |
| 1745 |
} else { |
} else { |
| 1746 |
$value .= chr $self->{next_input_character}; |
$value .= chr $self->{next_input_character}; |
| 1751 |
if ($match > 0) { |
if ($match > 0) { |
| 1752 |
return {type => 'character', data => $value}; |
return {type => 'character', data => $value}; |
| 1753 |
} elsif ($match < 0) { |
} elsif ($match < 0) { |
| 1754 |
!!!parse-error (type => 'refc'); |
!!!parse-error (type => 'no refc'); |
| 1755 |
return {type => 'character', data => $value}; |
return {type => 'character', data => $value}; |
| 1756 |
} else { |
} else { |
| 1757 |
!!!parse-error (type => 'bare ero'); |
!!!parse-error (type => 'bare ero'); |
| 1758 |
## NOTE: No characters are consumed in the spec. |
## NOTE: No characters are consumed in the spec. |
| 1759 |
!!!back-token ({type => 'character', data => $value}); |
return {type => 'character', data => '&'.$value}; |
|
return undef; |
|
| 1760 |
} |
} |
| 1761 |
} else { |
} else { |
| 1762 |
## no characters are consumed |
## no characters are consumed |
| 1951 |
} elsif ($token->{type} eq 'character') { |
} elsif ($token->{type} eq 'character') { |
| 1952 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
| 1953 |
## Ignore the token |
## Ignore the token |
| 1954 |
|
|
| 1955 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 1956 |
## Stay in the phase |
## Stay in the phase |
| 1957 |
!!!next-token; |
!!!next-token; |
| 1994 |
!!!next-token; |
!!!next-token; |
| 1995 |
redo B; |
redo B; |
| 1996 |
} elsif ($token->{type} eq 'character') { |
} elsif ($token->{type} eq 'character') { |
| 1997 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
| 1998 |
$self->{document}->manakai_append_text ($1); |
## Ignore the token. |
| 1999 |
## ISSUE: DOM3 Core does not allow Document > Text |
|
| 2000 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 2001 |
## Stay in the phase |
## Stay in the phase |
| 2002 |
!!!next-token; |
!!!next-token; |
| 2036 |
|
|
| 2037 |
## Step 3 |
## Step 3 |
| 2038 |
S3: { |
S3: { |
| 2039 |
$last = 1 if $self->{open_elements}->[0]->[0] eq $node->[0]; |
## ISSUE: Oops! "If node is the first node in the stack of open |
| 2040 |
if (defined $self->{inner_html_node}) { |
## elements, then set last to true. If the context element of the |
| 2041 |
if ($self->{inner_html_node}->[1] eq 'td' or |
## HTML fragment parsing algorithm is neither a td element nor a |
| 2042 |
$self->{inner_html_node}->[1] eq 'th') { |
## th element, then set node to the context element. (fragment case)": |
| 2043 |
# |
## The second "if" is in the scope of the first "if"!? |
| 2044 |
} else { |
if ($self->{open_elements}->[0]->[0] eq $node->[0]) { |
| 2045 |
$node = $self->{inner_html_node}; |
$last = 1; |
| 2046 |
|
if (defined $self->{inner_html_node}) { |
| 2047 |
|
if ($self->{inner_html_node}->[1] eq 'td' or |
| 2048 |
|
$self->{inner_html_node}->[1] eq 'th') { |
| 2049 |
|
# |
| 2050 |
|
} else { |
| 2051 |
|
$node = $self->{inner_html_node}; |
| 2052 |
|
} |
| 2053 |
} |
} |
| 2054 |
} |
} |
| 2055 |
|
|
| 2180 |
} |
} |
| 2181 |
}; # $clear_up_to_marker |
}; # $clear_up_to_marker |
| 2182 |
|
|
| 2183 |
my $style_start_tag = sub { |
my $parse_rcdata = sub ($$) { |
| 2184 |
my $style_el; !!!create-element ($style_el, 'style', $token->{attributes}); |
my ($content_model_flag, $insert) = @_; |
| 2185 |
## $self->{insertion_mode} eq 'in head' and ... (always true) |
|
| 2186 |
(($self->{insertion_mode} eq 'in head' and defined $self->{head_element}) |
## Step 1 |
| 2187 |
? $self->{head_element} : $self->{open_elements}->[-1]->[0]) |
my $start_tag_name = $token->{tag_name}; |
| 2188 |
->append_child ($style_el); |
my $el; |
| 2189 |
$self->{content_model_flag} = 'CDATA'; |
!!!create-element ($el, $start_tag_name, $token->{attributes}); |
| 2190 |
|
|
| 2191 |
|
## Step 2 |
| 2192 |
|
$insert->($el); # /context node/->append_child ($el) |
| 2193 |
|
|
| 2194 |
|
## Step 3 |
| 2195 |
|
$self->{content_model_flag} = $content_model_flag; # CDATA or RCDATA |
| 2196 |
delete $self->{escape}; # MUST |
delete $self->{escape}; # MUST |
| 2197 |
|
|
| 2198 |
|
## Step 4 |
| 2199 |
my $text = ''; |
my $text = ''; |
| 2200 |
!!!next-token; |
!!!next-token; |
| 2201 |
while ($token->{type} eq 'character') { |
while ($token->{type} eq 'character') { # or until stop tokenizing |
| 2202 |
$text .= $token->{data}; |
$text .= $token->{data}; |
| 2203 |
!!!next-token; |
!!!next-token; |
| 2204 |
} # stop if non-character token or tokenizer stops tokenising |
} |
| 2205 |
|
|
| 2206 |
|
## Step 5 |
| 2207 |
if (length $text) { |
if (length $text) { |
| 2208 |
$style_el->manakai_append_text ($text); |
my $text = $self->{document}->create_text_node ($text); |
| 2209 |
|
$el->append_child ($text); |
| 2210 |
} |
} |
| 2211 |
|
|
| 2212 |
|
## Step 6 |
| 2213 |
$self->{content_model_flag} = 'PCDATA'; |
$self->{content_model_flag} = 'PCDATA'; |
| 2214 |
|
|
| 2215 |
if ($token->{type} eq 'end tag' and $token->{tag_name} eq 'style') { |
## Step 7 |
| 2216 |
|
if ($token->{type} eq 'end tag' and $token->{tag_name} eq $start_tag_name) { |
| 2217 |
## Ignore the token |
## Ignore the token |
| 2218 |
} else { |
} else { |
| 2219 |
!!!parse-error (type => 'in CDATA:#'.$token->{type}); |
!!!parse-error (type => 'in '.$content_model_flag.':#'.$token->{type}); |
|
## ISSUE: And ignore? |
|
| 2220 |
} |
} |
| 2221 |
!!!next-token; |
!!!next-token; |
| 2222 |
}; # $style_start_tag |
}; # $parse_rcdata |
| 2223 |
|
|
| 2224 |
my $script_start_tag = sub { |
my $script_start_tag = sub ($) { |
| 2225 |
|
my $insert = $_[0]; |
| 2226 |
my $script_el; |
my $script_el; |
| 2227 |
!!!create-element ($script_el, 'script', $token->{attributes}); |
!!!create-element ($script_el, 'script', $token->{attributes}); |
| 2228 |
## TODO: mark as "parser-inserted" |
## TODO: mark as "parser-inserted" |
| 2256 |
} else { |
} else { |
| 2257 |
## TODO: $old_insertion_point = current insertion point |
## TODO: $old_insertion_point = current insertion point |
| 2258 |
## TODO: insertion point = just before the next input character |
## TODO: insertion point = just before the next input character |
| 2259 |
|
|
| 2260 |
(($self->{insertion_mode} eq 'in head' and defined $self->{head_element}) |
$insert->($script_el); |
|
? $self->{head_element} : $self->{open_elements}->[-1]->[0])->append_child ($script_el); |
|
| 2261 |
|
|
| 2262 |
## TODO: insertion point = $old_insertion_point (might be "undefined") |
## TODO: insertion point = $old_insertion_point (might be "undefined") |
| 2263 |
|
|
| 2451 |
}; # $formatting_end_tag |
}; # $formatting_end_tag |
| 2452 |
|
|
| 2453 |
my $insert_to_current = sub { |
my $insert_to_current = sub { |
| 2454 |
$self->{open_elements}->[-1]->[0]->append_child (shift); |
$self->{open_elements}->[-1]->[0]->append_child ($_[0]); |
| 2455 |
}; # $insert_to_current |
}; # $insert_to_current |
| 2456 |
|
|
| 2457 |
my $insert_to_foster = sub { |
my $insert_to_foster = sub { |
| 2489 |
my $insert = shift; |
my $insert = shift; |
| 2490 |
if ($token->{type} eq 'start tag') { |
if ($token->{type} eq 'start tag') { |
| 2491 |
if ($token->{tag_name} eq 'script') { |
if ($token->{tag_name} eq 'script') { |
| 2492 |
$script_start_tag->(); |
## NOTE: This is an "as if in head" code clone |
| 2493 |
|
$script_start_tag->($insert); |
| 2494 |
return; |
return; |
| 2495 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($token->{tag_name} eq 'style') { |
| 2496 |
$style_start_tag->(); |
## NOTE: This is an "as if in head" code clone |
| 2497 |
|
$parse_rcdata->('CDATA', $insert); |
| 2498 |
return; |
return; |
| 2499 |
} elsif ({ |
} elsif ({ |
| 2500 |
base => 1, link => 1, meta => 1, |
base => 1, link => 1, meta => 1, |
| 2501 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 2502 |
!!!parse-error (type => 'in body:'.$token->{tag_name}); |
## NOTE: This is an "as if in head" code clone, only "-t" differs |
| 2503 |
## NOTE: This is an "as if in head" code clone |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 2504 |
my $el; |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
|
!!!create-element ($el, $token->{tag_name}, $token->{attributes}); |
|
|
if (defined $self->{head_element}) { |
|
|
$self->{head_element}->append_child ($el); |
|
|
} else { |
|
|
$insert->($el); |
|
|
} |
|
|
|
|
| 2505 |
!!!next-token; |
!!!next-token; |
| 2506 |
|
## TODO: Extracting |charset| from |meta|. |
| 2507 |
return; |
return; |
| 2508 |
} elsif ($token->{tag_name} eq 'title') { |
} elsif ($token->{tag_name} eq 'title') { |
| 2509 |
!!!parse-error (type => 'in body:title'); |
!!!parse-error (type => 'in body:title'); |
| 2510 |
## NOTE: There is an "as if in head" code clone |
## NOTE: This is an "as if in head" code clone |
| 2511 |
my $title_el; |
$parse_rcdata->('RCDATA', sub { |
| 2512 |
!!!create-element ($title_el, 'title', $token->{attributes}); |
if (defined $self->{head_element}) { |
| 2513 |
(defined $self->{head_element} ? $self->{head_element} : $self->{open_elements}->[-1]->[0]) |
$self->{head_element}->append_child ($_[0]); |
| 2514 |
->append_child ($title_el); |
} else { |
| 2515 |
$self->{content_model_flag} = 'RCDATA'; |
$insert->($_[0]); |
| 2516 |
delete $self->{escape}; # MUST |
} |
| 2517 |
|
}); |
|
my $text = ''; |
|
|
!!!next-token; |
|
|
while ($token->{type} eq 'character') { |
|
|
$text .= $token->{data}; |
|
|
!!!next-token; |
|
|
} |
|
|
if (length $text) { |
|
|
$title_el->manakai_append_text ($text); |
|
|
} |
|
|
|
|
|
$self->{content_model_flag} = 'PCDATA'; |
|
|
|
|
|
if ($token->{type} eq 'end tag' and |
|
|
$token->{tag_name} eq 'title') { |
|
|
## Ignore the token |
|
|
} else { |
|
|
!!!parse-error (type => 'in RCDATA:#'.$token->{type}); |
|
|
## ISSUE: And ignore? |
|
|
} |
|
|
!!!next-token; |
|
| 2518 |
return; |
return; |
| 2519 |
} elsif ($token->{tag_name} eq 'body') { |
} elsif ($token->{tag_name} eq 'body') { |
| 2520 |
!!!parse-error (type => 'in body:body'); |
!!!parse-error (type => 'in body:body'); |
| 2617 |
if ($i != -1) { |
if ($i != -1) { |
| 2618 |
!!!parse-error (type => 'end tag missing:'. |
!!!parse-error (type => 'end tag missing:'. |
| 2619 |
$self->{open_elements}->[-1]->[1]); |
$self->{open_elements}->[-1]->[1]); |
|
## TODO: test |
|
| 2620 |
} |
} |
| 2621 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 2622 |
last LI; |
last LI; |
| 2664 |
if ($i != -1) { |
if ($i != -1) { |
| 2665 |
!!!parse-error (type => 'end tag missing:'. |
!!!parse-error (type => 'end tag missing:'. |
| 2666 |
$self->{open_elements}->[-1]->[1]); |
$self->{open_elements}->[-1]->[1]); |
|
## TODO: test |
|
| 2667 |
} |
} |
| 2668 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 2669 |
last LI; |
last LI; |
| 2726 |
} |
} |
| 2727 |
} # INSCOPE |
} # INSCOPE |
| 2728 |
|
|
| 2729 |
|
## NOTE: See <http://html5.org/tools/web-apps-tracker?from=925&to=926> |
| 2730 |
## has an element in scope |
## has an element in scope |
| 2731 |
my $i; |
#my $i; |
| 2732 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
#INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 2733 |
my $node = $self->{open_elements}->[$_]; |
# my $node = $self->{open_elements}->[$_]; |
| 2734 |
if ({ |
# if ({ |
| 2735 |
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
# h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
| 2736 |
}->{$node->[1]}) { |
# }->{$node->[1]}) { |
| 2737 |
$i = $_; |
# $i = $_; |
| 2738 |
last INSCOPE; |
# last INSCOPE; |
| 2739 |
} elsif ({ |
# } elsif ({ |
| 2740 |
table => 1, caption => 1, td => 1, th => 1, |
# table => 1, caption => 1, td => 1, th => 1, |
| 2741 |
button => 1, marquee => 1, object => 1, html => 1, |
# button => 1, marquee => 1, object => 1, html => 1, |
| 2742 |
}->{$node->[1]}) { |
# }->{$node->[1]}) { |
| 2743 |
last INSCOPE; |
# last INSCOPE; |
| 2744 |
} |
# } |
| 2745 |
} # INSCOPE |
#} # INSCOPE |
| 2746 |
|
# |
| 2747 |
if (defined $i) { |
#if (defined $i) { |
| 2748 |
!!!parse-error (type => 'in hn:hn'); |
# !!! parse-error (type => 'in hn:hn'); |
| 2749 |
splice @{$self->{open_elements}}, $i; |
# splice @{$self->{open_elements}}, $i; |
| 2750 |
} |
#} |
| 2751 |
|
|
| 2752 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 2753 |
|
|
| 2807 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 2808 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 2809 |
if ($node->[1] eq 'nobr') { |
if ($node->[1] eq 'nobr') { |
| 2810 |
|
!!!parse-error (type => 'not closed:nobr'); |
| 2811 |
!!!back-token; |
!!!back-token; |
| 2812 |
$token = {type => 'end tag', tag_name => 'nobr'}; |
$token = {type => 'end tag', tag_name => 'nobr'}; |
| 2813 |
return; |
return; |
| 2859 |
return; |
return; |
| 2860 |
} elsif ($token->{tag_name} eq 'xmp') { |
} elsif ($token->{tag_name} eq 'xmp') { |
| 2861 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 2862 |
|
$parse_rcdata->('CDATA', $insert); |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
|
|
|
$self->{content_model_flag} = 'CDATA'; |
|
|
delete $self->{escape}; # MUST |
|
|
|
|
|
!!!next-token; |
|
| 2863 |
return; |
return; |
| 2864 |
} elsif ($token->{tag_name} eq 'table') { |
} elsif ($token->{tag_name} eq 'table') { |
| 2865 |
## has a p element in scope |
## has a p element in scope |
| 2891 |
!!!parse-error (type => 'image'); |
!!!parse-error (type => 'image'); |
| 2892 |
$token->{tag_name} = 'img'; |
$token->{tag_name} = 'img'; |
| 2893 |
} |
} |
| 2894 |
|
|
| 2895 |
|
## NOTE: There is an "as if <br>" code clone. |
| 2896 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 2897 |
|
|
| 2898 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 2938 |
return; |
return; |
| 2939 |
} else { |
} else { |
| 2940 |
my $at = $token->{attributes}; |
my $at = $token->{attributes}; |
| 2941 |
|
my $form_attrs; |
| 2942 |
|
$form_attrs->{action} = $at->{action} if $at->{action}; |
| 2943 |
|
my $prompt_attr = $at->{prompt}; |
| 2944 |
$at->{name} = {name => 'name', value => 'isindex'}; |
$at->{name} = {name => 'name', value => 'isindex'}; |
| 2945 |
|
delete $at->{action}; |
| 2946 |
|
delete $at->{prompt}; |
| 2947 |
my @tokens = ( |
my @tokens = ( |
| 2948 |
{type => 'start tag', tag_name => 'form'}, |
{type => 'start tag', tag_name => 'form', |
| 2949 |
|
attributes => $form_attrs}, |
| 2950 |
{type => 'start tag', tag_name => 'hr'}, |
{type => 'start tag', tag_name => 'hr'}, |
| 2951 |
{type => 'start tag', tag_name => 'p'}, |
{type => 'start tag', tag_name => 'p'}, |
| 2952 |
{type => 'start tag', tag_name => 'label'}, |
{type => 'start tag', tag_name => 'label'}, |
| 2953 |
{type => 'character', |
); |
| 2954 |
data => 'This is a searchable index. Insert your search keywords here: '}, # SHOULD |
if ($prompt_attr) { |
| 2955 |
## TODO: make this configurable |
push @tokens, {type => 'character', data => $prompt_attr->{value}}; |
| 2956 |
|
} else { |
| 2957 |
|
push @tokens, {type => 'character', |
| 2958 |
|
data => 'This is a searchable index. Insert your search keywords here: '}; # SHOULD |
| 2959 |
|
## TODO: make this configurable |
| 2960 |
|
} |
| 2961 |
|
push @tokens, |
| 2962 |
{type => 'start tag', tag_name => 'input', attributes => $at}, |
{type => 'start tag', tag_name => 'input', attributes => $at}, |
| 2963 |
#{type => 'character', data => ''}, # SHOULD |
#{type => 'character', data => ''}, # SHOULD |
| 2964 |
{type => 'end tag', tag_name => 'label'}, |
{type => 'end tag', tag_name => 'label'}, |
| 2965 |
{type => 'end tag', tag_name => 'p'}, |
{type => 'end tag', tag_name => 'p'}, |
| 2966 |
{type => 'start tag', tag_name => 'hr'}, |
{type => 'start tag', tag_name => 'hr'}, |
| 2967 |
{type => 'end tag', tag_name => 'form'}, |
{type => 'end tag', tag_name => 'form'}; |
|
); |
|
| 2968 |
$token = shift @tokens; |
$token = shift @tokens; |
| 2969 |
!!!back-token (@tokens); |
!!!back-token (@tokens); |
| 2970 |
return; |
return; |
| 2971 |
} |
} |
| 2972 |
} elsif ({ |
} elsif ($token->{tag_name} eq 'textarea') { |
|
textarea => 1, |
|
|
iframe => 1, |
|
|
noembed => 1, |
|
|
noframes => 1, |
|
|
noscript => 0, ## TODO: 1 if scripting is enabled |
|
|
}->{$token->{tag_name}}) { |
|
| 2973 |
my $tag_name = $token->{tag_name}; |
my $tag_name = $token->{tag_name}; |
| 2974 |
my $el; |
my $el; |
| 2975 |
!!!create-element ($el, $token->{tag_name}, $token->{attributes}); |
!!!create-element ($el, $token->{tag_name}, $token->{attributes}); |
| 2976 |
|
|
| 2977 |
if ($token->{tag_name} eq 'textarea') { |
## TODO: $self->{form_element} if defined |
| 2978 |
## TODO: $self->{form_element} if defined |
$self->{content_model_flag} = 'RCDATA'; |
|
$self->{content_model_flag} = 'RCDATA'; |
|
|
} else { |
|
|
$self->{content_model_flag} = 'CDATA'; |
|
|
} |
|
| 2979 |
delete $self->{escape}; # MUST |
delete $self->{escape}; # MUST |
| 2980 |
|
|
| 2981 |
$insert->($el); |
$insert->($el); |
| 2982 |
|
|
| 2983 |
my $text = ''; |
my $text = ''; |
| 2984 |
if ($token->{tag_name} eq 'textarea') { |
!!!next-token; |
| 2985 |
!!!next-token; |
if ($token->{type} eq 'character') { |
| 2986 |
if ($token->{type} eq 'character') { |
$token->{data} =~ s/^\x0A//; |
| 2987 |
$token->{data} =~ s/^\x0A//; |
unless (length $token->{data}) { |
| 2988 |
unless (length $token->{data}) { |
!!!next-token; |
|
!!!next-token; |
|
|
} |
|
| 2989 |
} |
} |
|
} else { |
|
|
!!!next-token; |
|
| 2990 |
} |
} |
| 2991 |
while ($token->{type} eq 'character') { |
while ($token->{type} eq 'character') { |
| 2992 |
$text .= $token->{data}; |
$text .= $token->{data}; |
| 3002 |
$token->{tag_name} eq $tag_name) { |
$token->{tag_name} eq $tag_name) { |
| 3003 |
## Ignore the token |
## Ignore the token |
| 3004 |
} else { |
} else { |
| 3005 |
if ($token->{tag_name} eq 'textarea') { |
!!!parse-error (type => 'in RCDATA:#'.$token->{type}); |
|
!!!parse-error (type => 'in RCDATA:#'.$token->{type}); |
|
|
} else { |
|
|
!!!parse-error (type => 'in CDATA:#'.$token->{type}); |
|
|
} |
|
|
## ISSUE: And ignore? |
|
| 3006 |
} |
} |
| 3007 |
!!!next-token; |
!!!next-token; |
| 3008 |
return; |
return; |
| 3009 |
|
} elsif ({ |
| 3010 |
|
iframe => 1, |
| 3011 |
|
noembed => 1, |
| 3012 |
|
noframes => 1, |
| 3013 |
|
noscript => 0, ## TODO: 1 if scripting is enabled |
| 3014 |
|
}->{$token->{tag_name}}) { |
| 3015 |
|
$parse_rcdata->('CDATA', $insert); |
| 3016 |
|
return; |
| 3017 |
} elsif ($token->{tag_name} eq 'select') { |
} elsif ($token->{tag_name} eq 'select') { |
| 3018 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 3019 |
|
|
| 3044 |
} |
} |
| 3045 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} eq 'end tag') { |
| 3046 |
if ($token->{tag_name} eq 'body') { |
if ($token->{tag_name} eq 'body') { |
| 3047 |
if (@{$self->{open_elements}} > 1 and $self->{open_elements}->[1]->[1] eq 'body') { |
if (@{$self->{open_elements}} > 1 and |
| 3048 |
## ISSUE: There is an issue in the spec. |
$self->{open_elements}->[1]->[1] eq 'body') { |
| 3049 |
if ($self->{open_elements}->[-1]->[1] ne 'body') { |
for (@{$self->{open_elements}}) { |
| 3050 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
unless ({ |
| 3051 |
|
dd => 1, dt => 1, li => 1, p => 1, td => 1, |
| 3052 |
|
th => 1, tr => 1, body => 1, html => 1, |
| 3053 |
|
tbody => 1, tfoot => 1, thead => 1, |
| 3054 |
|
}->{$_->[1]}) { |
| 3055 |
|
!!!parse-error (type => 'not closed:'.$_->[1]); |
| 3056 |
|
} |
| 3057 |
} |
} |
| 3058 |
|
|
| 3059 |
$self->{insertion_mode} = 'after body'; |
$self->{insertion_mode} = 'after body'; |
| 3060 |
!!!next-token; |
!!!next-token; |
| 3061 |
return; |
return; |
| 3100 |
li => ($token->{tag_name} ne 'li'), |
li => ($token->{tag_name} ne 'li'), |
| 3101 |
p => ($token->{tag_name} ne 'p'), |
p => ($token->{tag_name} ne 'p'), |
| 3102 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3103 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3104 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3105 |
!!!back-token; |
!!!back-token; |
| 3106 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 3121 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3122 |
} |
} |
| 3123 |
|
|
| 3124 |
splice @{$self->{open_elements}}, $i if defined $i; |
if (defined $i) { |
| 3125 |
|
splice @{$self->{open_elements}}, $i; |
| 3126 |
|
} elsif ($token->{tag_name} eq 'p') { |
| 3127 |
|
## As if <p>, then reprocess the current token |
| 3128 |
|
my $el; |
| 3129 |
|
!!!create-element ($el, 'p'); |
| 3130 |
|
$insert->($el); |
| 3131 |
|
} |
| 3132 |
$clear_up_to_marker->() |
$clear_up_to_marker->() |
| 3133 |
if { |
if { |
| 3134 |
button => 1, marquee => 1, object => 1, |
button => 1, marquee => 1, object => 1, |
| 3144 |
if ({ |
if ({ |
| 3145 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3146 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3147 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3148 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3149 |
!!!back-token; |
!!!back-token; |
| 3150 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 3183 |
if ({ |
if ({ |
| 3184 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3185 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3186 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3187 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3188 |
!!!back-token; |
!!!back-token; |
| 3189 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 3214 |
strong => 1, tt => 1, u => 1, |
strong => 1, tt => 1, u => 1, |
| 3215 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 3216 |
$formatting_end_tag->($token->{tag_name}); |
$formatting_end_tag->($token->{tag_name}); |
| 3217 |
## TODO: <http://html5.org/tools/web-apps-tracker?from=883&to=884> |
return; |
| 3218 |
|
} elsif ($token->{tag_name} eq 'br') { |
| 3219 |
|
!!!parse-error (type => 'unmatched end tag:br'); |
| 3220 |
|
|
| 3221 |
|
## As if <br> |
| 3222 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 3223 |
|
|
| 3224 |
|
my $el; |
| 3225 |
|
!!!create-element ($el, 'br'); |
| 3226 |
|
$insert->($el); |
| 3227 |
|
|
| 3228 |
|
## Ignore the token. |
| 3229 |
|
!!!next-token; |
| 3230 |
return; |
return; |
| 3231 |
} elsif ({ |
} elsif ({ |
| 3232 |
caption => 1, col => 1, colgroup => 1, frame => 1, |
caption => 1, col => 1, colgroup => 1, frame => 1, |
| 3233 |
frameset => 1, head => 1, option => 1, optgroup => 1, |
frameset => 1, head => 1, option => 1, optgroup => 1, |
| 3234 |
tbody => 1, td => 1, tfoot => 1, th => 1, |
tbody => 1, td => 1, tfoot => 1, th => 1, |
| 3235 |
thead => 1, tr => 1, |
thead => 1, tr => 1, |
| 3236 |
area => 1, basefont => 1, bgsound => 1, br => 1, |
area => 1, basefont => 1, bgsound => 1, |
| 3237 |
embed => 1, hr => 1, iframe => 1, image => 1, |
embed => 1, hr => 1, iframe => 1, image => 1, |
| 3238 |
img => 1, input => 1, isindex => 1, noembed => 1, |
img => 1, input => 1, isindex => 1, noembed => 1, |
| 3239 |
noframes => 1, param => 1, select => 1, spacer => 1, |
noframes => 1, param => 1, select => 1, spacer => 1, |
| 3260 |
if ({ |
if ({ |
| 3261 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3262 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3263 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3264 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3265 |
!!!back-token; |
!!!back-token; |
| 3266 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 3284 |
#not $phrasing_category->{$node->[1]} and |
#not $phrasing_category->{$node->[1]} and |
| 3285 |
($special_category->{$node->[1]} or |
($special_category->{$node->[1]} or |
| 3286 |
$scoping_category->{$node->[1]})) { |
$scoping_category->{$node->[1]})) { |
| 3287 |
!!!parse-error (type => 'not closed:'.$node->[1]); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3288 |
## Ignore the token |
## Ignore the token |
| 3289 |
!!!next-token; |
!!!next-token; |
| 3290 |
last S2; |
last S2; |
| 3313 |
redo B; |
redo B; |
| 3314 |
} elsif ($token->{type} eq 'start tag' and |
} elsif ($token->{type} eq 'start tag' and |
| 3315 |
$token->{tag_name} eq 'html') { |
$token->{tag_name} eq 'html') { |
| 3316 |
## TODO: unless it is the first start tag token, parse-error |
## ISSUE: "aa<html>" is not a parse error. |
| 3317 |
|
## ISSUE: "<html>" in fragment is not a parse error. |
| 3318 |
|
unless ($token->{first_start_tag}) { |
| 3319 |
|
!!!parse-error (type => 'not first start tag'); |
| 3320 |
|
} |
| 3321 |
my $top_el = $self->{open_elements}->[0]->[0]; |
my $top_el = $self->{open_elements}->[0]->[0]; |
| 3322 |
for my $attr_name (keys %{$token->{attributes}}) { |
for my $attr_name (keys %{$token->{attributes}}) { |
| 3323 |
unless ($top_el->has_attribute_ns (undef, $attr_name)) { |
unless ($top_el->has_attribute_ns (undef, $attr_name)) { |
| 3332 |
## Generate implied end tags |
## Generate implied end tags |
| 3333 |
if ({ |
if ({ |
| 3334 |
dd => 1, dt => 1, li => 1, p => 1, td => 1, th => 1, tr => 1, |
dd => 1, dt => 1, li => 1, p => 1, td => 1, th => 1, tr => 1, |
| 3335 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3336 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3337 |
!!!back-token; |
!!!back-token; |
| 3338 |
$token = {type => 'end tag', tag_name => $self->{open_elements}->[-1]->[1]}; |
$token = {type => 'end tag', tag_name => $self->{open_elements}->[-1]->[1]}; |
| 3392 |
} |
} |
| 3393 |
redo B; |
redo B; |
| 3394 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} eq 'end tag') { |
| 3395 |
if ($token->{tag_name} eq 'html') { |
if ({ |
| 3396 |
|
head => 1, body => 1, html => 1, |
| 3397 |
|
p => 1, br => 1, |
| 3398 |
|
}->{$token->{tag_name}}) { |
| 3399 |
## As if <head> |
## As if <head> |
| 3400 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, 'head'); |
| 3401 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 3405 |
redo B; |
redo B; |
| 3406 |
} else { |
} else { |
| 3407 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3408 |
## Ignore the token |
## Ignore the token ## ISSUE: An issue in the spec. |
| 3409 |
!!!next-token; |
!!!next-token; |
| 3410 |
redo B; |
redo B; |
| 3411 |
} |
} |
| 3412 |
} else { |
} else { |
| 3413 |
die "$0: $token->{type}: Unknown type"; |
die "$0: $token->{type}: Unknown type"; |
| 3414 |
} |
} |
| 3415 |
} elsif ($self->{insertion_mode} eq 'in head') { |
} elsif ($self->{insertion_mode} eq 'in head' or |
| 3416 |
|
$self->{insertion_mode} eq 'in head noscript' or |
| 3417 |
|
$self->{insertion_mode} eq 'after head') { |
| 3418 |
if ($token->{type} eq 'character') { |
if ($token->{type} eq 'character') { |
| 3419 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 3420 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 3431 |
!!!next-token; |
!!!next-token; |
| 3432 |
redo B; |
redo B; |
| 3433 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 3434 |
if ($token->{tag_name} eq 'title') { |
if ({base => ($self->{insertion_mode} eq 'in head' or |
| 3435 |
## NOTE: There is an "as if in head" code clone |
$self->{insertion_mode} eq 'after head'), |
| 3436 |
my $title_el; |
link => 1, meta => 1}->{$token->{tag_name}}) { |
| 3437 |
!!!create-element ($title_el, 'title', $token->{attributes}); |
## NOTE: There is a "as if in head" code clone. |
| 3438 |
(defined $self->{head_element} ? $self->{head_element} : $self->{open_elements}->[-1]->[0]) |
if ($self->{insertion_mode} eq 'after head') { |
| 3439 |
->append_child ($title_el); |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 3440 |
$self->{content_model_flag} = 'RCDATA'; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3441 |
delete $self->{escape}; # MUST |
} |
| 3442 |
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 3443 |
my $text = ''; |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 3444 |
|
## TODO: Extracting |charset| from |meta|. |
| 3445 |
|
pop @{$self->{open_elements}} |
| 3446 |
|
if $self->{insertion_mode} eq 'after head'; |
| 3447 |
!!!next-token; |
!!!next-token; |
| 3448 |
while ($token->{type} eq 'character') { |
redo B; |
| 3449 |
$text .= $token->{data}; |
} elsif ($token->{tag_name} eq 'title' and |
| 3450 |
|
$self->{insertion_mode} eq 'in head') { |
| 3451 |
|
## NOTE: There is a "as if in head" code clone. |
| 3452 |
|
if ($self->{insertion_mode} eq 'after head') { |
| 3453 |
|
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 3454 |
|
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3455 |
|
} |
| 3456 |
|
my $parent = defined $self->{head_element} ? $self->{head_element} |
| 3457 |
|
: $self->{open_elements}->[-1]->[0]; |
| 3458 |
|
$parse_rcdata->('RCDATA', sub { $parent->append_child ($_[0]) }); |
| 3459 |
|
pop @{$self->{open_elements}} |
| 3460 |
|
if $self->{insertion_mode} eq 'after head'; |
| 3461 |
|
redo B; |
| 3462 |
|
} elsif ($token->{tag_name} eq 'style') { |
| 3463 |
|
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
| 3464 |
|
## insertion mode 'in head') |
| 3465 |
|
## NOTE: There is a "as if in head" code clone. |
| 3466 |
|
if ($self->{insertion_mode} eq 'after head') { |
| 3467 |
|
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 3468 |
|
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3469 |
|
} |
| 3470 |
|
$parse_rcdata->('CDATA', $insert_to_current); |
| 3471 |
|
pop @{$self->{open_elements}} |
| 3472 |
|
if $self->{insertion_mode} eq 'after head'; |
| 3473 |
|
redo B; |
| 3474 |
|
} elsif ($token->{tag_name} eq 'noscript') { |
| 3475 |
|
if ($self->{insertion_mode} eq 'in head') { |
| 3476 |
|
## NOTE: and scripting is disalbed |
| 3477 |
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 3478 |
|
$self->{insertion_mode} = 'in head noscript'; |
| 3479 |
!!!next-token; |
!!!next-token; |
| 3480 |
} |
redo B; |
| 3481 |
if (length $text) { |
} elsif ($self->{insertion_mode} eq 'in head noscript') { |
| 3482 |
$title_el->manakai_append_text ($text); |
!!!parse-error (type => 'in noscript:noscript'); |
|
} |
|
|
|
|
|
$self->{content_model_flag} = 'PCDATA'; |
|
|
|
|
|
if ($token->{type} eq 'end tag' and |
|
|
$token->{tag_name} eq 'title') { |
|
| 3483 |
## Ignore the token |
## Ignore the token |
| 3484 |
|
redo B; |
| 3485 |
} else { |
} else { |
| 3486 |
!!!parse-error (type => 'in RCDATA:#'.$token->{type}); |
# |
|
## ISSUE: And ignore? |
|
| 3487 |
} |
} |
| 3488 |
|
} elsif ($token->{tag_name} eq 'head' and |
| 3489 |
|
$self->{insertion_mode} ne 'after head') { |
| 3490 |
|
!!!parse-error (type => 'in head:head'); # or in head noscript |
| 3491 |
|
## Ignore the token |
| 3492 |
!!!next-token; |
!!!next-token; |
| 3493 |
redo B; |
redo B; |
| 3494 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($self->{insertion_mode} ne 'in head noscript' and |
| 3495 |
$style_start_tag->(); |
$token->{tag_name} eq 'script') { |
| 3496 |
redo B; |
if ($self->{insertion_mode} eq 'after head') { |
| 3497 |
} elsif ($token->{tag_name} eq 'script') { |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 3498 |
$script_start_tag->(); |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3499 |
|
} |
| 3500 |
|
## NOTE: There is a "as if in head" code clone. |
| 3501 |
|
$script_start_tag->($insert_to_current); |
| 3502 |
|
pop @{$self->{open_elements}} |
| 3503 |
|
if $self->{insertion_mode} eq 'after head'; |
| 3504 |
redo B; |
redo B; |
| 3505 |
} elsif ({base => 1, link => 1, meta => 1}->{$token->{tag_name}}) { |
} elsif ($self->{insertion_mode} eq 'after head' and |
| 3506 |
## NOTE: There are "as if in head" code clones |
$token->{tag_name} eq 'body') { |
| 3507 |
my $el; |
!!!insert-element ('body', $token->{attributes}); |
| 3508 |
!!!create-element ($el, $token->{tag_name}, $token->{attributes}); |
$self->{insertion_mode} = 'in body'; |
|
(defined $self->{head_element} ? $self->{head_element} : $self->{open_elements}->[-1]->[0]) |
|
|
->append_child ($el); |
|
|
|
|
| 3509 |
!!!next-token; |
!!!next-token; |
| 3510 |
redo B; |
redo B; |
| 3511 |
} elsif ($token->{tag_name} eq 'head') { |
} elsif ($self->{insertion_mode} eq 'after head' and |
| 3512 |
!!!parse-error (type => 'in head:head'); |
$token->{tag_name} eq 'frameset') { |
| 3513 |
## Ignore the token |
!!!insert-element ('frameset', $token->{attributes}); |
| 3514 |
|
$self->{insertion_mode} = 'in frameset'; |
| 3515 |
!!!next-token; |
!!!next-token; |
| 3516 |
redo B; |
redo B; |
| 3517 |
} else { |
} else { |
| 3518 |
# |
# |
| 3519 |
} |
} |
| 3520 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} eq 'end tag') { |
| 3521 |
if ($token->{tag_name} eq 'head') { |
if ($self->{insertion_mode} eq 'in head' and |
| 3522 |
if ($self->{open_elements}->[-1]->[1] eq 'head') { |
$token->{tag_name} eq 'head') { |
| 3523 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
|
} else { |
|
|
!!!parse-error (type => 'unmatched end tag:head'); |
|
|
} |
|
| 3524 |
$self->{insertion_mode} = 'after head'; |
$self->{insertion_mode} = 'after head'; |
| 3525 |
!!!next-token; |
!!!next-token; |
| 3526 |
redo B; |
redo B; |
| 3527 |
} elsif ($token->{tag_name} eq 'html') { |
} elsif ($self->{insertion_mode} eq 'in head noscript' and |
| 3528 |
|
$token->{tag_name} eq 'noscript') { |
| 3529 |
|
pop @{$self->{open_elements}}; |
| 3530 |
|
$self->{insertion_mode} = 'in head'; |
| 3531 |
|
!!!next-token; |
| 3532 |
|
redo B; |
| 3533 |
|
} elsif ($self->{insertion_mode} eq 'in head' and |
| 3534 |
|
{ |
| 3535 |
|
body => 1, html => 1, |
| 3536 |
|
p => 1, br => 1, |
| 3537 |
|
}->{$token->{tag_name}}) { |
| 3538 |
# |
# |
| 3539 |
} else { |
} elsif ($self->{insertion_mode} eq 'in head noscript' and |
| 3540 |
|
{ |
| 3541 |
|
p => 1, br => 1, |
| 3542 |
|
}->{$token->{tag_name}}) { |
| 3543 |
|
# |
| 3544 |
|
} elsif ($self->{insertion_mode} ne 'after head') { |
| 3545 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3546 |
## Ignore the token |
## Ignore the token |
| 3547 |
!!!next-token; |
!!!next-token; |
| 3548 |
redo B; |
redo B; |
| 3549 |
|
} else { |
| 3550 |
|
# |
| 3551 |
} |
} |
| 3552 |
} else { |
} else { |
| 3553 |
# |
# |
| 3554 |
} |
} |
| 3555 |
|
|
| 3556 |
if ($self->{open_elements}->[-1]->[1] eq 'head') { |
## As if </head> or </noscript> or <body> |
| 3557 |
## As if </head> |
if ($self->{insertion_mode} eq 'in head') { |
| 3558 |
|
pop @{$self->{open_elements}}; |
| 3559 |
|
$self->{insertion_mode} = 'after head'; |
| 3560 |
|
} elsif ($self->{insertion_mode} eq 'in head noscript') { |
| 3561 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3562 |
|
!!!parse-error (type => 'in noscript:'.(defined $token->{tag_name} ? ($token->{type} eq 'end tag' ? '/' : '') . $token->{tag_name} : '#' . $token->{type})); |
| 3563 |
|
$self->{insertion_mode} = 'in head'; |
| 3564 |
|
} else { # 'after head' |
| 3565 |
|
!!!insert-element ('body'); |
| 3566 |
|
$self->{insertion_mode} = 'in body'; |
| 3567 |
} |
} |
|
$self->{insertion_mode} = 'after head'; |
|
| 3568 |
## reprocess |
## reprocess |
| 3569 |
redo B; |
redo B; |
| 3570 |
|
|
| 3571 |
## ISSUE: An issue in the spec. |
## ISSUE: An issue in the spec. |
|
} elsif ($self->{insertion_mode} eq 'after head') { |
|
|
if ($token->{type} eq 'character') { |
|
|
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
|
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
|
|
unless (length $token->{data}) { |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
|
} |
|
|
|
|
|
# |
|
|
} elsif ($token->{type} eq 'comment') { |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{type} eq 'start tag') { |
|
|
if ($token->{tag_name} eq 'body') { |
|
|
!!!insert-element ('body', $token->{attributes}); |
|
|
$self->{insertion_mode} = 'in body'; |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'frameset') { |
|
|
!!!insert-element ('frameset', $token->{attributes}); |
|
|
$self->{insertion_mode} = 'in frameset'; |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ({ |
|
|
base => 1, link => 1, meta => 1, |
|
|
script => 1, style => 1, title => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
|
|
$self->{insertion_mode} = 'in head'; |
|
|
## reprocess |
|
|
redo B; |
|
|
} else { |
|
|
# |
|
|
} |
|
|
} else { |
|
|
# |
|
|
} |
|
|
|
|
|
## As if <body> |
|
|
!!!insert-element ('body'); |
|
|
$self->{insertion_mode} = 'in body'; |
|
|
## reprocess |
|
|
redo B; |
|
| 3572 |
} elsif ($self->{insertion_mode} eq 'in body') { |
} elsif ($self->{insertion_mode} eq 'in body') { |
| 3573 |
if ($token->{type} eq 'character') { |
if ($token->{type} eq 'character') { |
| 3574 |
## NOTE: There is a code clone of "character in body". |
## NOTE: There is a code clone of "character in body". |
| 3723 |
if ({ |
if ({ |
| 3724 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3725 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3726 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3727 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3728 |
!!!back-token; # <table> |
!!!back-token; # <table> |
| 3729 |
$token = {type => 'end tag', tag_name => 'table'}; |
$token = {type => 'end tag', tag_name => 'table'}; |
| 3772 |
if ({ |
if ({ |
| 3773 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3774 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3775 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3776 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3777 |
!!!back-token; |
!!!back-token; |
| 3778 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 3856 |
if ({ |
if ({ |
| 3857 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3858 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3859 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3860 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3861 |
!!!back-token; # <?> |
!!!back-token; # <?> |
| 3862 |
$token = {type => 'end tag', tag_name => 'caption'}; |
$token = {type => 'end tag', tag_name => 'caption'}; |
| 3907 |
if ({ |
if ({ |
| 3908 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3909 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3910 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3911 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3912 |
!!!back-token; |
!!!back-token; |
| 3913 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 3955 |
if ({ |
if ({ |
| 3956 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3957 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3958 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3959 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3960 |
!!!back-token; # </table> |
!!!back-token; # </table> |
| 3961 |
$token = {type => 'end tag', tag_name => 'caption'}; |
$token = {type => 'end tag', tag_name => 'caption'}; |
| 4221 |
if ({ |
if ({ |
| 4222 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 4223 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 4224 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 4225 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4226 |
!!!back-token; # <table> |
!!!back-token; # <table> |
| 4227 |
$token = {type => 'end tag', tag_name => 'table'}; |
$token = {type => 'end tag', tag_name => 'table'}; |
| 4490 |
if ({ |
if ({ |
| 4491 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 4492 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 4493 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 4494 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4495 |
!!!back-token; # <table> |
!!!back-token; # <table> |
| 4496 |
$token = {type => 'end tag', tag_name => 'table'}; |
$token = {type => 'end tag', tag_name => 'table'}; |
| 4732 |
td => ($token->{tag_name} eq 'th'), |
td => ($token->{tag_name} eq 'th'), |
| 4733 |
th => ($token->{tag_name} eq 'td'), |
th => ($token->{tag_name} eq 'td'), |
| 4734 |
tr => 1, |
tr => 1, |
| 4735 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 4736 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4737 |
!!!back-token; |
!!!back-token; |
| 4738 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 5085 |
} |
} |
| 5086 |
|
|
| 5087 |
if (defined $token->{tag_name}) { |
if (defined $token->{tag_name}) { |
| 5088 |
!!!parse-error (type => 'in frameset:'.$token->{tag_name}); |
!!!parse-error (type => 'in frameset:'.($token->{type} eq 'end tag' ? '/' : '').$token->{tag_name}); |
| 5089 |
} else { |
} else { |
| 5090 |
!!!parse-error (type => 'in frameset:#'.$token->{type}); |
!!!parse-error (type => 'in frameset:#'.$token->{type}); |
| 5091 |
} |
} |
| 5129 |
} |
} |
| 5130 |
|
|
| 5131 |
if (defined $token->{tag_name}) { |
if (defined $token->{tag_name}) { |
| 5132 |
!!!parse-error (type => 'after frameset:'.$token->{tag_name}); |
!!!parse-error (type => 'after frameset:'.($token->{tag_name} eq 'end tag' ? '/' : '').$token->{tag_name}); |
| 5133 |
} else { |
} else { |
| 5134 |
!!!parse-error (type => 'after frameset:#'.$token->{type}); |
!!!parse-error (type => 'after frameset:#'.$token->{type}); |
| 5135 |
} |
} |
| 5179 |
redo B; |
redo B; |
| 5180 |
} elsif ($token->{type} eq 'start tag' or |
} elsif ($token->{type} eq 'start tag' or |
| 5181 |
$token->{type} eq 'end tag') { |
$token->{type} eq 'end tag') { |
| 5182 |
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
!!!parse-error (type => 'after html:'.($token->{type} eq 'end tag' ? '/' : '').$token->{tag_name}); |
| 5183 |
$phase = 'main'; |
$phase = 'main'; |
| 5184 |
## reprocess |
## reprocess |
| 5185 |
redo B; |
redo B; |
| 5388 |
|
|
| 5389 |
my $nt = $child->node_type; |
my $nt = $child->node_type; |
| 5390 |
if ($nt == 1) { # Element |
if ($nt == 1) { # Element |
| 5391 |
my $tag_name = lc $child->tag_name; ## ISSUE: Definition of "lowercase" |
my $tag_name = $child->tag_name; ## TODO: manakai_tag_name |
| 5392 |
$s .= '<' . $tag_name; |
$s .= '<' . $tag_name; |
| 5393 |
|
## NOTE: Non-HTML case: |
| 5394 |
## ISSUE: Non-html elements |
## <http://permalink.gmane.org/gmane.org.w3c.whatwg.discuss/11191> |
| 5395 |
|
|
| 5396 |
my @attrs = @{$child->attributes}; # sort order MUST be stable |
my @attrs = @{$child->attributes}; # sort order MUST be stable |
| 5397 |
for my $attr (@attrs) { # order is implementation dependent |
for my $attr (@attrs) { # order is implementation dependent |
| 5398 |
my $attr_name = lc $attr->name; ## ISSUE: Definition of "lowercase" |
my $attr_name = $attr->name; ## TODO: manakai_name |
| 5399 |
$s .= ' ' . $attr_name . '="'; |
$s .= ' ' . $attr_name . '="'; |
| 5400 |
my $attr_value = $attr->value; |
my $attr_value = $attr->value; |
| 5401 |
## escape |
## escape |
| 5414 |
spacer => 1, wbr => 1, |
spacer => 1, wbr => 1, |
| 5415 |
}->{$tag_name}; |
}->{$tag_name}; |
| 5416 |
|
|
| 5417 |
|
$s .= "\x0A" if $tag_name eq 'pre' or $tag_name eq 'textarea'; |
| 5418 |
|
|
| 5419 |
if (not $in_cdata and { |
if (not $in_cdata and { |
| 5420 |
style => 1, script => 1, xmp => 1, iframe => 1, |
style => 1, script => 1, xmp => 1, iframe => 1, |
| 5421 |
noembed => 1, noframes => 1, noscript => 1, |
noembed => 1, noframes => 1, noscript => 1, |
| 5422 |
|
plaintext => 1, |
| 5423 |
}->{$tag_name}) { |
}->{$tag_name}) { |
| 5424 |
unshift @node, 'cdata-out'; |
unshift @node, 'cdata-out'; |
| 5425 |
$in_cdata = 1; |
$in_cdata = 1; |