| 159 |
sub RCDATA_CONTENT_MODEL () { CM_ENTITY | CM_LIMITED_MARKUP } |
sub RCDATA_CONTENT_MODEL () { CM_ENTITY | CM_LIMITED_MARKUP } |
| 160 |
sub PCDATA_CONTENT_MODEL () { CM_ENTITY | CM_FULL_MARKUP } |
sub PCDATA_CONTENT_MODEL () { CM_ENTITY | CM_FULL_MARKUP } |
| 161 |
|
|
| 162 |
|
sub DOCTYPE_TOKEN () { 1 } |
| 163 |
|
sub COMMENT_TOKEN () { 2 } |
| 164 |
|
sub START_TAG_TOKEN () { 3 } |
| 165 |
|
sub END_TAG_TOKEN () { 4 } |
| 166 |
|
sub END_OF_FILE_TOKEN () { 5 } |
| 167 |
|
sub CHARACTER_TOKEN () { 6 } |
| 168 |
|
|
| 169 |
sub AFTER_HTML_IMS () { 0b100 } |
sub AFTER_HTML_IMS () { 0b100 } |
| 170 |
sub HEAD_IMS () { 0b1000 } |
sub HEAD_IMS () { 0b1000 } |
| 171 |
sub BODY_IMS () { 0b10000 } |
sub BODY_IMS () { 0b10000 } |
| 172 |
sub BODY_TABLE_IMS () { 0b100000 | BODY_IMS } |
sub BODY_TABLE_IMS () { 0b100000 } |
| 173 |
sub TABLE_IMS () { 0b1000000 } |
sub TABLE_IMS () { 0b1000000 } |
| 174 |
sub ROW_IMS () { 0b10000000 | TABLE_IMS } |
sub ROW_IMS () { 0b10000000 } |
| 175 |
sub BODY_AFTER_IMS () { 0b100000000 } |
sub BODY_AFTER_IMS () { 0b100000000 } |
| 176 |
sub FRAME_IMS () { 0b1000000000 } |
sub FRAME_IMS () { 0b1000000000 } |
| 177 |
|
|
| 182 |
sub AFTER_HEAD_IM () { HEAD_IMS | 0b10 } |
sub AFTER_HEAD_IM () { HEAD_IMS | 0b10 } |
| 183 |
sub BEFORE_HEAD_IM () { HEAD_IMS | 0b11 } |
sub BEFORE_HEAD_IM () { HEAD_IMS | 0b11 } |
| 184 |
sub IN_BODY_IM () { BODY_IMS } |
sub IN_BODY_IM () { BODY_IMS } |
| 185 |
sub IN_CELL_IM () { BODY_TABLE_IMS | 0b01 } |
sub IN_CELL_IM () { BODY_IMS | BODY_TABLE_IMS | 0b01 } |
| 186 |
sub IN_CAPTION_IM () { BODY_TABLE_IMS | 0b10 } |
sub IN_CAPTION_IM () { BODY_IMS | BODY_TABLE_IMS | 0b10 } |
| 187 |
sub IN_ROW_IM () { ROW_IMS | 0b01 } |
sub IN_ROW_IM () { TABLE_IMS | ROW_IMS | 0b01 } |
| 188 |
sub IN_TABLE_BODY_IM () { ROW_IMS | 0b10 } |
sub IN_TABLE_BODY_IM () { TABLE_IMS | ROW_IMS | 0b10 } |
| 189 |
sub IN_TABLE_IM () { TABLE_IMS } |
sub IN_TABLE_IM () { TABLE_IMS } |
| 190 |
sub AFTER_BODY_IM () { BODY_AFTER_IMS } |
sub AFTER_BODY_IM () { BODY_AFTER_IMS } |
| 191 |
sub IN_FRAMESET_IM () { FRAME_IMS | 0b01 } |
sub IN_FRAMESET_IM () { FRAME_IMS | 0b01 } |
| 211 |
} # _initialize_tokenizer |
} # _initialize_tokenizer |
| 212 |
|
|
| 213 |
## A token has: |
## A token has: |
| 214 |
## ->{type} eq 'DOCTYPE', 'start tag', 'end tag', 'comment', |
## ->{type} == DOCTYPE_TOKEN, START_TAG_TOKEN, END_TAG_TOKEN, COMMENT_TOKEN, |
| 215 |
## 'character', or 'end-of-file' |
## CHARACTER_TOKEN, or END_OF_FILE_TOKEN |
| 216 |
## ->{name} (DOCTYPE, start tag (tag name), end tag (tag name)) |
## ->{name} (DOCTYPE_TOKEN) |
| 217 |
## ->{public_identifier} (DOCTYPE) |
## ->{tag_name} (START_TAG_TOKEN, END_TAG_TOKEN) |
| 218 |
## ->{system_identifier} (DOCTYPE) |
## ->{public_identifier} (DOCTYPE_TOKEN) |
| 219 |
## ->{correct} == 1 or 0 (DOCTYPE) |
## ->{system_identifier} (DOCTYPE_TOKEN) |
| 220 |
## ->{attributes} isa HASH (start tag, end tag) |
## ->{correct} == 1 or 0 (DOCTYPE_TOKEN) |
| 221 |
## ->{data} (comment, character) |
## ->{attributes} isa HASH (START_TAG_TOKEN, END_TAG_TOKEN) |
| 222 |
|
## ->{data} (COMMENT_TOKEN, CHARACTER_TOKEN) |
| 223 |
|
|
| 224 |
## Emitted token MUST immediately be handled by the tree construction state. |
## Emitted token MUST immediately be handled by the tree construction state. |
| 225 |
|
|
| 278 |
|
|
| 279 |
# |
# |
| 280 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 281 |
!!!emit ({type => 'end-of-file'}); |
!!!emit ({type => END_OF_FILE_TOKEN}); |
| 282 |
last A; ## TODO: ok? |
last A; ## TODO: ok? |
| 283 |
} |
} |
| 284 |
# Anything else |
# Anything else |
| 285 |
my $token = {type => 'character', |
my $token = {type => CHARACTER_TOKEN, |
| 286 |
data => chr $self->{next_input_character}}; |
data => chr $self->{next_input_character}}; |
| 287 |
## Stay in the data state |
## Stay in the data state |
| 288 |
!!!next-input-character; |
!!!next-input-character; |
| 299 |
# next-input-character is already done |
# next-input-character is already done |
| 300 |
|
|
| 301 |
unless (defined $token) { |
unless (defined $token) { |
| 302 |
!!!emit ({type => 'character', data => '&'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '&'}); |
| 303 |
} else { |
} else { |
| 304 |
!!!emit ($token); |
!!!emit ($token); |
| 305 |
} |
} |
| 315 |
## reconsume |
## reconsume |
| 316 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 317 |
|
|
| 318 |
!!!emit ({type => 'character', data => '<'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '<'}); |
| 319 |
|
|
| 320 |
redo A; |
redo A; |
| 321 |
} |
} |
| 331 |
} elsif (0x0041 <= $self->{next_input_character} and |
} elsif (0x0041 <= $self->{next_input_character} and |
| 332 |
$self->{next_input_character} <= 0x005A) { # A..Z |
$self->{next_input_character} <= 0x005A) { # A..Z |
| 333 |
$self->{current_token} |
$self->{current_token} |
| 334 |
= {type => 'start tag', |
= {type => START_TAG_TOKEN, |
| 335 |
tag_name => chr ($self->{next_input_character} + 0x0020)}; |
tag_name => chr ($self->{next_input_character} + 0x0020)}; |
| 336 |
$self->{state} = 'tag name'; |
$self->{state} = 'tag name'; |
| 337 |
!!!next-input-character; |
!!!next-input-character; |
| 338 |
redo A; |
redo A; |
| 339 |
} elsif (0x0061 <= $self->{next_input_character} and |
} elsif (0x0061 <= $self->{next_input_character} and |
| 340 |
$self->{next_input_character} <= 0x007A) { # a..z |
$self->{next_input_character} <= 0x007A) { # a..z |
| 341 |
$self->{current_token} = {type => 'start tag', |
$self->{current_token} = {type => START_TAG_TOKEN, |
| 342 |
tag_name => chr ($self->{next_input_character})}; |
tag_name => chr ($self->{next_input_character})}; |
| 343 |
$self->{state} = 'tag name'; |
$self->{state} = 'tag name'; |
| 344 |
!!!next-input-character; |
!!!next-input-character; |
| 348 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 349 |
!!!next-input-character; |
!!!next-input-character; |
| 350 |
|
|
| 351 |
!!!emit ({type => 'character', data => '<>'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '<>'}); |
| 352 |
|
|
| 353 |
redo A; |
redo A; |
| 354 |
} elsif ($self->{next_input_character} == 0x003F) { # ? |
} elsif ($self->{next_input_character} == 0x003F) { # ? |
| 361 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 362 |
## reconsume |
## reconsume |
| 363 |
|
|
| 364 |
!!!emit ({type => 'character', data => '<'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '<'}); |
| 365 |
|
|
| 366 |
redo A; |
redo A; |
| 367 |
} |
} |
| 385 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 386 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 387 |
|
|
| 388 |
!!!emit ({type => 'character', data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
| 389 |
|
|
| 390 |
redo A; |
redo A; |
| 391 |
} |
} |
| 403 |
$self->{next_input_character} = shift @next_char; # reconsume |
$self->{next_input_character} = shift @next_char; # reconsume |
| 404 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 405 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 406 |
!!!emit ({type => 'character', data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
| 407 |
redo A; |
redo A; |
| 408 |
} else { |
} else { |
| 409 |
$self->{next_input_character} = shift @next_char; |
$self->{next_input_character} = shift @next_char; |
| 414 |
## No start tag token has ever been emitted |
## No start tag token has ever been emitted |
| 415 |
# next-input-character is already done |
# next-input-character is already done |
| 416 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 417 |
!!!emit ({type => 'character', data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
| 418 |
redo A; |
redo A; |
| 419 |
} |
} |
| 420 |
} |
} |
| 421 |
|
|
| 422 |
if (0x0041 <= $self->{next_input_character} and |
if (0x0041 <= $self->{next_input_character} and |
| 423 |
$self->{next_input_character} <= 0x005A) { # A..Z |
$self->{next_input_character} <= 0x005A) { # A..Z |
| 424 |
$self->{current_token} = {type => 'end tag', |
$self->{current_token} = {type => END_TAG_TOKEN, |
| 425 |
tag_name => chr ($self->{next_input_character} + 0x0020)}; |
tag_name => chr ($self->{next_input_character} + 0x0020)}; |
| 426 |
$self->{state} = 'tag name'; |
$self->{state} = 'tag name'; |
| 427 |
!!!next-input-character; |
!!!next-input-character; |
| 428 |
redo A; |
redo A; |
| 429 |
} elsif (0x0061 <= $self->{next_input_character} and |
} elsif (0x0061 <= $self->{next_input_character} and |
| 430 |
$self->{next_input_character} <= 0x007A) { # a..z |
$self->{next_input_character} <= 0x007A) { # a..z |
| 431 |
$self->{current_token} = {type => 'end tag', |
$self->{current_token} = {type => END_TAG_TOKEN, |
| 432 |
tag_name => chr ($self->{next_input_character})}; |
tag_name => chr ($self->{next_input_character})}; |
| 433 |
$self->{state} = 'tag name'; |
$self->{state} = 'tag name'; |
| 434 |
!!!next-input-character; |
!!!next-input-character; |
| 443 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 444 |
# reconsume |
# reconsume |
| 445 |
|
|
| 446 |
!!!emit ({type => 'character', data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
| 447 |
|
|
| 448 |
redo A; |
redo A; |
| 449 |
} else { |
} else { |
| 462 |
!!!next-input-character; |
!!!next-input-character; |
| 463 |
redo A; |
redo A; |
| 464 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 465 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 466 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 467 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 468 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 469 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 470 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 471 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 472 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 489 |
redo A; |
redo A; |
| 490 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 491 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 492 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 493 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 494 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 495 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 496 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 497 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 498 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 499 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 510 |
} elsif ($self->{next_input_character} == 0x002F) { # / |
} elsif ($self->{next_input_character} == 0x002F) { # / |
| 511 |
!!!next-input-character; |
!!!next-input-character; |
| 512 |
if ($self->{next_input_character} == 0x003E and # > |
if ($self->{next_input_character} == 0x003E and # > |
| 513 |
$self->{current_token}->{type} eq 'start tag' and |
$self->{current_token}->{type} == START_TAG_TOKEN and |
| 514 |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
| 515 |
# permitted slash |
# permitted slash |
| 516 |
# |
# |
| 537 |
!!!next-input-character; |
!!!next-input-character; |
| 538 |
redo A; |
redo A; |
| 539 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 540 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 541 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 542 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 543 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 544 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 545 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 546 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 547 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 565 |
} elsif ($self->{next_input_character} == 0x002F) { # / |
} elsif ($self->{next_input_character} == 0x002F) { # / |
| 566 |
!!!next-input-character; |
!!!next-input-character; |
| 567 |
if ($self->{next_input_character} == 0x003E and # > |
if ($self->{next_input_character} == 0x003E and # > |
| 568 |
$self->{current_token}->{type} eq 'start tag' and |
$self->{current_token}->{type} == START_TAG_TOKEN and |
| 569 |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
| 570 |
# permitted slash |
# permitted slash |
| 571 |
# |
# |
| 577 |
redo A; |
redo A; |
| 578 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 579 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 580 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 581 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 582 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 583 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 584 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 585 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 586 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 587 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 630 |
redo A; |
redo A; |
| 631 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 632 |
$before_leave->(); |
$before_leave->(); |
| 633 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 634 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 635 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 636 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 637 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 638 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 639 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 640 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 658 |
$before_leave->(); |
$before_leave->(); |
| 659 |
!!!next-input-character; |
!!!next-input-character; |
| 660 |
if ($self->{next_input_character} == 0x003E and # > |
if ($self->{next_input_character} == 0x003E and # > |
| 661 |
$self->{current_token}->{type} eq 'start tag' and |
$self->{current_token}->{type} == START_TAG_TOKEN and |
| 662 |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
| 663 |
# permitted slash |
# permitted slash |
| 664 |
# |
# |
| 671 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 672 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 673 |
$before_leave->(); |
$before_leave->(); |
| 674 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 675 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 676 |
= not defined $self->{last_emitted_start_tag_name}; |
= 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} == END_TAG_TOKEN) { |
| 679 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 680 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 681 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 709 |
!!!next-input-character; |
!!!next-input-character; |
| 710 |
redo A; |
redo A; |
| 711 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 712 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 713 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 714 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 715 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 716 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 717 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 718 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 719 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 737 |
} elsif ($self->{next_input_character} == 0x002F) { # / |
} elsif ($self->{next_input_character} == 0x002F) { # / |
| 738 |
!!!next-input-character; |
!!!next-input-character; |
| 739 |
if ($self->{next_input_character} == 0x003E and # > |
if ($self->{next_input_character} == 0x003E and # > |
| 740 |
$self->{current_token}->{type} eq 'start tag' and |
$self->{current_token}->{type} == START_TAG_TOKEN and |
| 741 |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
| 742 |
# permitted slash |
# permitted slash |
| 743 |
# |
# |
| 750 |
redo A; |
redo A; |
| 751 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 752 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 753 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 754 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 755 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 756 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 757 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 758 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 759 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 760 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 797 |
!!!next-input-character; |
!!!next-input-character; |
| 798 |
redo A; |
redo A; |
| 799 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 800 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 801 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 802 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 803 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 804 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 805 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 806 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 807 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 817 |
redo A; |
redo A; |
| 818 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 819 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 820 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 821 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 822 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 823 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 824 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 825 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 826 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 827 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 853 |
redo A; |
redo A; |
| 854 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 855 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
| 856 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 857 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 858 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 859 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 860 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 861 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 862 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 863 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 889 |
redo A; |
redo A; |
| 890 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 891 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
| 892 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 893 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 894 |
= not defined $self->{last_emitted_start_tag_name}; |
= 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} == END_TAG_TOKEN) { |
| 897 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 898 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 899 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 928 |
!!!next-input-character; |
!!!next-input-character; |
| 929 |
redo A; |
redo A; |
| 930 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 931 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 932 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 933 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 934 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 935 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 936 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 937 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 938 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 948 |
redo A; |
redo A; |
| 949 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 950 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 951 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 952 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 953 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 954 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 955 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 956 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 957 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 958 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 988 |
} elsif ($self->{state} eq 'bogus comment') { |
} elsif ($self->{state} eq 'bogus comment') { |
| 989 |
## (only happen if PCDATA state) |
## (only happen if PCDATA state) |
| 990 |
|
|
| 991 |
my $token = {type => 'comment', data => ''}; |
my $token = {type => COMMENT_TOKEN, data => ''}; |
| 992 |
|
|
| 993 |
BC: { |
BC: { |
| 994 |
if ($self->{next_input_character} == 0x003E) { # > |
if ($self->{next_input_character} == 0x003E) { # > |
| 1021 |
!!!next-input-character; |
!!!next-input-character; |
| 1022 |
push @next_char, $self->{next_input_character}; |
push @next_char, $self->{next_input_character}; |
| 1023 |
if ($self->{next_input_character} == 0x002D) { # - |
if ($self->{next_input_character} == 0x002D) { # - |
| 1024 |
$self->{current_token} = {type => 'comment', data => ''}; |
$self->{current_token} = {type => COMMENT_TOKEN, data => ''}; |
| 1025 |
$self->{state} = 'comment start'; |
$self->{state} = 'comment start'; |
| 1026 |
!!!next-input-character; |
!!!next-input-character; |
| 1027 |
redo A; |
redo A; |
| 1224 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 1225 |
!!!next-input-character; |
!!!next-input-character; |
| 1226 |
|
|
| 1227 |
!!!emit ({type => 'DOCTYPE'}); # incorrect |
!!!emit ({type => DOCTYPE_TOKEN}); # incorrect |
| 1228 |
|
|
| 1229 |
redo A; |
redo A; |
| 1230 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1232 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 1233 |
## reconsume |
## reconsume |
| 1234 |
|
|
| 1235 |
!!!emit ({type => 'DOCTYPE'}); # incorrect |
!!!emit ({type => DOCTYPE_TOKEN}); # incorrect |
| 1236 |
|
|
| 1237 |
redo A; |
redo A; |
| 1238 |
} else { |
} else { |
| 1239 |
$self->{current_token} |
$self->{current_token} |
| 1240 |
= {type => 'DOCTYPE', |
= {type => DOCTYPE_TOKEN, |
| 1241 |
name => chr ($self->{next_input_character}), |
name => chr ($self->{next_input_character}), |
| 1242 |
correct => 1}; |
correct => 1}; |
| 1243 |
## ISSUE: "Set the token's name name to the" in the spec |
## ISSUE: "Set the token's name name to the" in the spec |
| 1705 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 1706 |
} |
} |
| 1707 |
|
|
| 1708 |
return {type => 'character', data => chr $code}; |
return {type => CHARACTER_TOKEN, data => chr $code}; |
| 1709 |
} # X |
} # X |
| 1710 |
} elsif (0x0030 <= $self->{next_input_character} and |
} elsif (0x0030 <= $self->{next_input_character} and |
| 1711 |
$self->{next_input_character} <= 0x0039) { # 0..9 |
$self->{next_input_character} <= 0x0039) { # 0..9 |
| 1740 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 1741 |
} |
} |
| 1742 |
|
|
| 1743 |
return {type => 'character', data => chr $code}; |
return {type => CHARACTER_TOKEN, data => chr $code}; |
| 1744 |
} else { |
} else { |
| 1745 |
!!!parse-error (type => 'bare nero'); |
!!!parse-error (type => 'bare nero'); |
| 1746 |
!!!back-next-input-character ($self->{next_input_character}); |
!!!back-next-input-character ($self->{next_input_character}); |
| 1788 |
} |
} |
| 1789 |
|
|
| 1790 |
if ($match > 0) { |
if ($match > 0) { |
| 1791 |
return {type => 'character', data => $value}; |
return {type => CHARACTER_TOKEN, data => $value}; |
| 1792 |
} elsif ($match < 0) { |
} elsif ($match < 0) { |
| 1793 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'no refc'); |
| 1794 |
if ($in_attr and $match < -1) { |
if ($in_attr and $match < -1) { |
| 1795 |
return {type => 'character', data => '&'.$entity_name}; |
return {type => CHARACTER_TOKEN, data => '&'.$entity_name}; |
| 1796 |
} else { |
} else { |
| 1797 |
return {type => 'character', data => $value}; |
return {type => CHARACTER_TOKEN, data => $value}; |
| 1798 |
} |
} |
| 1799 |
} else { |
} else { |
| 1800 |
!!!parse-error (type => 'bare ero'); |
!!!parse-error (type => 'bare ero'); |
| 1801 |
## NOTE: No characters are consumed in the spec. |
## NOTE: No characters are consumed in the spec. |
| 1802 |
return {type => 'character', data => '&'.$value}; |
return {type => CHARACTER_TOKEN, data => '&'.$value}; |
| 1803 |
} |
} |
| 1804 |
} else { |
} else { |
| 1805 |
## no characters are consumed |
## no characters are consumed |
| 1855 |
sub _tree_construction_initial ($) { |
sub _tree_construction_initial ($) { |
| 1856 |
my $self = shift; |
my $self = shift; |
| 1857 |
INITIAL: { |
INITIAL: { |
| 1858 |
if ($token->{type} eq 'DOCTYPE') { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 1859 |
## NOTE: Conformance checkers MAY, instead of reporting "not HTML5" |
## NOTE: Conformance checkers MAY, instead of reporting "not HTML5" |
| 1860 |
## error, switch to a conformance checking mode for another |
## error, switch to a conformance checking mode for another |
| 1861 |
## language. |
## language. |
| 1982 |
!!!next-token; |
!!!next-token; |
| 1983 |
return; |
return; |
| 1984 |
} elsif ({ |
} elsif ({ |
| 1985 |
'start tag' => 1, |
START_TAG_TOKEN, 1, |
| 1986 |
'end tag' => 1, |
END_TAG_TOKEN, 1, |
| 1987 |
'end-of-file' => 1, |
END_OF_FILE_TOKEN, 1, |
| 1988 |
}->{$token->{type}}) { |
}->{$token->{type}}) { |
| 1989 |
!!!parse-error (type => 'no DOCTYPE'); |
!!!parse-error (type => 'no DOCTYPE'); |
| 1990 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 1991 |
## Go to the root element phase |
## Go to the root element phase |
| 1992 |
## reprocess |
## reprocess |
| 1993 |
return; |
return; |
| 1994 |
} elsif ($token->{type} eq 'character') { |
} elsif ($token->{type} == CHARACTER_TOKEN) { |
| 1995 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
| 1996 |
## Ignore the token |
## Ignore the token |
| 1997 |
|
|
| 2007 |
## Go to the root element phase |
## Go to the root element phase |
| 2008 |
## reprocess |
## reprocess |
| 2009 |
return; |
return; |
| 2010 |
} elsif ($token->{type} eq 'comment') { |
} elsif ($token->{type} == COMMENT_TOKEN) { |
| 2011 |
my $comment = $self->{document}->create_comment ($token->{data}); |
my $comment = $self->{document}->create_comment ($token->{data}); |
| 2012 |
$self->{document}->append_child ($comment); |
$self->{document}->append_child ($comment); |
| 2013 |
|
|
| 2015 |
!!!next-token; |
!!!next-token; |
| 2016 |
redo INITIAL; |
redo INITIAL; |
| 2017 |
} else { |
} else { |
| 2018 |
die "$0: $token->{type}: Unknown token"; |
die "$0: $token->{type}: Unknown token type"; |
| 2019 |
} |
} |
| 2020 |
} # INITIAL |
} # INITIAL |
| 2021 |
} # _tree_construction_initial |
} # _tree_construction_initial |
| 2024 |
my $self = shift; |
my $self = shift; |
| 2025 |
|
|
| 2026 |
B: { |
B: { |
| 2027 |
if ($token->{type} eq 'DOCTYPE') { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 2028 |
!!!parse-error (type => 'in html:#DOCTYPE'); |
!!!parse-error (type => 'in html:#DOCTYPE'); |
| 2029 |
## Ignore the token |
## Ignore the token |
| 2030 |
## Stay in the phase |
## Stay in the phase |
| 2031 |
!!!next-token; |
!!!next-token; |
| 2032 |
redo B; |
redo B; |
| 2033 |
} elsif ($token->{type} eq 'comment') { |
} elsif ($token->{type} == COMMENT_TOKEN) { |
| 2034 |
my $comment = $self->{document}->create_comment ($token->{data}); |
my $comment = $self->{document}->create_comment ($token->{data}); |
| 2035 |
$self->{document}->append_child ($comment); |
$self->{document}->append_child ($comment); |
| 2036 |
## Stay in the phase |
## Stay in the phase |
| 2037 |
!!!next-token; |
!!!next-token; |
| 2038 |
redo B; |
redo B; |
| 2039 |
} elsif ($token->{type} eq 'character') { |
} elsif ($token->{type} == CHARACTER_TOKEN) { |
| 2040 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
| 2041 |
## Ignore the token. |
## Ignore the token. |
| 2042 |
|
|
| 2048 |
} |
} |
| 2049 |
# |
# |
| 2050 |
} elsif ({ |
} elsif ({ |
| 2051 |
'start tag' => 1, |
START_TAG_TOKEN, 1, |
| 2052 |
'end tag' => 1, |
END_TAG_TOKEN, 1, |
| 2053 |
'end-of-file' => 1, |
END_OF_FILE_TOKEN, 1, |
| 2054 |
}->{$token->{type}}) { |
}->{$token->{type}}) { |
| 2055 |
## ISSUE: There is an issue in the spec |
## ISSUE: There is an issue in the spec |
| 2056 |
# |
# |
| 2057 |
} else { |
} else { |
| 2058 |
die "$0: $token->{type}: Unknown token"; |
die "$0: $token->{type}: Unknown token type"; |
| 2059 |
} |
} |
| 2060 |
my $root_element; !!!create-element ($root_element, 'html'); |
my $root_element; !!!create-element ($root_element, 'html'); |
| 2061 |
$self->{document}->append_child ($root_element); |
$self->{document}->append_child ($root_element); |
| 2238 |
## Step 4 |
## Step 4 |
| 2239 |
my $text = ''; |
my $text = ''; |
| 2240 |
!!!next-token; |
!!!next-token; |
| 2241 |
while ($token->{type} eq 'character') { # or until stop tokenizing |
while ($token->{type} == CHARACTER_TOKEN) { # or until stop tokenizing |
| 2242 |
$text .= $token->{data}; |
$text .= $token->{data}; |
| 2243 |
!!!next-token; |
!!!next-token; |
| 2244 |
} |
} |
| 2253 |
$self->{content_model} = PCDATA_CONTENT_MODEL; |
$self->{content_model} = PCDATA_CONTENT_MODEL; |
| 2254 |
|
|
| 2255 |
## Step 7 |
## Step 7 |
| 2256 |
if ($token->{type} eq 'end tag' and $token->{tag_name} eq $start_tag_name) { |
if ($token->{type} == END_TAG_TOKEN and $token->{tag_name} eq $start_tag_name) { |
| 2257 |
## Ignore the token |
## Ignore the token |
| 2258 |
} elsif ($content_model_flag == CDATA_CONTENT_MODEL) { |
} elsif ($content_model_flag == CDATA_CONTENT_MODEL) { |
| 2259 |
!!!parse-error (type => 'in CDATA:#'.$token->{type}); |
!!!parse-error (type => 'in CDATA:#'.$token->{type}); |
| 2276 |
|
|
| 2277 |
my $text = ''; |
my $text = ''; |
| 2278 |
!!!next-token; |
!!!next-token; |
| 2279 |
while ($token->{type} eq 'character') { |
while ($token->{type} == CHARACTER_TOKEN) { |
| 2280 |
$text .= $token->{data}; |
$text .= $token->{data}; |
| 2281 |
!!!next-token; |
!!!next-token; |
| 2282 |
} # stop if non-character token or tokenizer stops tokenising |
} # stop if non-character token or tokenizer stops tokenising |
| 2286 |
|
|
| 2287 |
$self->{content_model} = PCDATA_CONTENT_MODEL; |
$self->{content_model} = PCDATA_CONTENT_MODEL; |
| 2288 |
|
|
| 2289 |
if ($token->{type} eq 'end tag' and |
if ($token->{type} == END_TAG_TOKEN and |
| 2290 |
$token->{tag_name} eq 'script') { |
$token->{tag_name} eq 'script') { |
| 2291 |
## Ignore the token |
## Ignore the token |
| 2292 |
} else { |
} else { |
| 2532 |
my $insert; |
my $insert; |
| 2533 |
|
|
| 2534 |
B: { |
B: { |
| 2535 |
if ($token->{type} eq 'DOCTYPE') { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 2536 |
!!!parse-error (type => 'DOCTYPE in the middle'); |
!!!parse-error (type => 'DOCTYPE in the middle'); |
| 2537 |
## Ignore the token |
## Ignore the token |
| 2538 |
## Stay in the phase |
## Stay in the phase |
| 2539 |
!!!next-token; |
!!!next-token; |
| 2540 |
redo B; |
redo B; |
| 2541 |
} elsif ($token->{type} eq 'end-of-file') { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 2542 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM or |
if ($self->{insertion_mode} & AFTER_HTML_IMS) { |
|
$self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
|
| 2543 |
# |
# |
| 2544 |
} else { |
} else { |
| 2545 |
## Generate implied end tags |
## Generate implied end tags |
| 2548 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 2549 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 2550 |
!!!back-token; |
!!!back-token; |
| 2551 |
$token = {type => 'end tag', tag_name => $self->{open_elements}->[-1]->[1]}; |
$token = {type => END_TAG_TOKEN, tag_name => $self->{open_elements}->[-1]->[1]}; |
| 2552 |
redo B; |
redo B; |
| 2553 |
} |
} |
| 2554 |
|
|
| 2566 |
|
|
| 2567 |
## Stop parsing |
## Stop parsing |
| 2568 |
last B; |
last B; |
| 2569 |
} elsif ($token->{type} eq 'start tag' and |
} elsif ($token->{type} == START_TAG_TOKEN and |
| 2570 |
$token->{tag_name} eq 'html') { |
$token->{tag_name} eq 'html') { |
| 2571 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 2572 |
## Turn into the main phase |
## Turn into the main phase |
| 2593 |
} |
} |
| 2594 |
!!!next-token; |
!!!next-token; |
| 2595 |
redo B; |
redo B; |
| 2596 |
} elsif ($token->{type} eq 'comment') { |
} elsif ($token->{type} == COMMENT_TOKEN) { |
| 2597 |
my $comment = $self->{document}->create_comment ($token->{data}); |
my $comment = $self->{document}->create_comment ($token->{data}); |
| 2598 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM or |
if ($self->{insertion_mode} & AFTER_HTML_IMS) { |
|
$self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
|
| 2599 |
$self->{document}->append_child ($comment); |
$self->{document}->append_child ($comment); |
| 2600 |
} elsif ($self->{insertion_mode} == AFTER_BODY_IM) { |
} elsif ($self->{insertion_mode} == AFTER_BODY_IM) { |
| 2601 |
$self->{open_elements}->[0]->[0]->append_child ($comment); |
$self->{open_elements}->[0]->[0]->append_child ($comment); |
| 2604 |
} |
} |
| 2605 |
!!!next-token; |
!!!next-token; |
| 2606 |
redo B; |
redo B; |
| 2607 |
} elsif ($self->{insertion_mode} == IN_HEAD_IM or |
} elsif ($self->{insertion_mode} & HEAD_IMS) { |
| 2608 |
$self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM or |
if ($token->{type} == CHARACTER_TOKEN) { |
|
$self->{insertion_mode} == AFTER_HEAD_IM or |
|
|
$self->{insertion_mode} == BEFORE_HEAD_IM) { |
|
|
if ($token->{type} eq 'character') { |
|
| 2609 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 2610 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 2611 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 2646 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 2647 |
## reprocess |
## reprocess |
| 2648 |
redo B; |
redo B; |
| 2649 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 2650 |
if ($token->{tag_name} eq 'head') { |
if ($token->{tag_name} eq 'head') { |
| 2651 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 2652 |
!!!create-element ($self->{head_element}, $token->{tag_name}, $token->{attributes}); |
!!!create-element ($self->{head_element}, $token->{tag_name}, $token->{attributes}); |
| 2859 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 2860 |
## reprocess |
## reprocess |
| 2861 |
redo B; |
redo B; |
| 2862 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 2863 |
if ($token->{tag_name} eq 'head') { |
if ($token->{tag_name} eq 'head') { |
| 2864 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 2865 |
## As if <head> |
## As if <head> |
| 2981 |
} |
} |
| 2982 |
|
|
| 2983 |
## ISSUE: An issue in the spec. |
## ISSUE: An issue in the spec. |
| 2984 |
} elsif ($self->{insertion_mode} == IN_BODY_IM or |
} elsif ($self->{insertion_mode} & BODY_IMS) { |
| 2985 |
$self->{insertion_mode} == IN_CELL_IM or |
if ($token->{type} == CHARACTER_TOKEN) { |
|
$self->{insertion_mode} == IN_CAPTION_IM) { |
|
|
if ($token->{type} eq 'character') { |
|
| 2986 |
## NOTE: There is a code clone of "character in body". |
## NOTE: There is a code clone of "character in body". |
| 2987 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 2988 |
|
|
| 2990 |
|
|
| 2991 |
!!!next-token; |
!!!next-token; |
| 2992 |
redo B; |
redo B; |
| 2993 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 2994 |
if ({ |
if ({ |
| 2995 |
caption => 1, col => 1, colgroup => 1, tbody => 1, |
caption => 1, col => 1, colgroup => 1, tbody => 1, |
| 2996 |
td => 1, tfoot => 1, th => 1, thead => 1, tr => 1, |
td => 1, tfoot => 1, th => 1, thead => 1, tr => 1, |
| 3018 |
|
|
| 3019 |
## Close the cell |
## Close the cell |
| 3020 |
!!!back-token; # <?> |
!!!back-token; # <?> |
| 3021 |
$token = {type => 'end tag', tag_name => $tn}; |
$token = {type => END_TAG_TOKEN, tag_name => $tn}; |
| 3022 |
redo B; |
redo B; |
| 3023 |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 3024 |
!!!parse-error (type => 'not closed:caption'); |
!!!parse-error (type => 'not closed:caption'); |
| 3051 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 3052 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3053 |
!!!back-token; # <?> |
!!!back-token; # <?> |
| 3054 |
$token = {type => 'end tag', tag_name => 'caption'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'caption'}; |
| 3055 |
!!!back-token; |
!!!back-token; |
| 3056 |
$token = {type => 'end tag', |
$token = {type => END_TAG_TOKEN, |
| 3057 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3058 |
redo B; |
redo B; |
| 3059 |
} |
} |
| 3076 |
} else { |
} else { |
| 3077 |
# |
# |
| 3078 |
} |
} |
| 3079 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 3080 |
if ($token->{tag_name} eq 'td' or $token->{tag_name} eq 'th') { |
if ($token->{tag_name} eq 'td' or $token->{tag_name} eq 'th') { |
| 3081 |
if ($self->{insertion_mode} == IN_CELL_IM) { |
if ($self->{insertion_mode} == IN_CELL_IM) { |
| 3082 |
## have an element in table scope |
## have an element in table scope |
| 3108 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 3109 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3110 |
!!!back-token; |
!!!back-token; |
| 3111 |
$token = {type => 'end tag', |
$token = {type => END_TAG_TOKEN, |
| 3112 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3113 |
redo B; |
redo B; |
| 3114 |
} |
} |
| 3162 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 3163 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3164 |
!!!back-token; |
!!!back-token; |
| 3165 |
$token = {type => 'end tag', |
$token = {type => END_TAG_TOKEN, |
| 3166 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3167 |
redo B; |
redo B; |
| 3168 |
} |
} |
| 3219 |
|
|
| 3220 |
## Close the cell |
## Close the cell |
| 3221 |
!!!back-token; # </?> |
!!!back-token; # </?> |
| 3222 |
$token = {type => 'end tag', tag_name => $tn}; |
$token = {type => END_TAG_TOKEN, tag_name => $tn}; |
| 3223 |
redo B; |
redo B; |
| 3224 |
} elsif ($token->{tag_name} eq 'table' and |
} elsif ($token->{tag_name} eq 'table' and |
| 3225 |
$self->{insertion_mode} == IN_CAPTION_IM) { |
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 3253 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 3254 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3255 |
!!!back-token; # </table> |
!!!back-token; # </table> |
| 3256 |
$token = {type => 'end tag', tag_name => 'caption'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'caption'}; |
| 3257 |
!!!back-token; |
!!!back-token; |
| 3258 |
$token = {type => 'end tag', |
$token = {type => END_TAG_TOKEN, |
| 3259 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3260 |
redo B; |
redo B; |
| 3261 |
} |
} |
| 3275 |
} elsif ({ |
} elsif ({ |
| 3276 |
body => 1, col => 1, colgroup => 1, html => 1, |
body => 1, col => 1, colgroup => 1, html => 1, |
| 3277 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 3278 |
if ($self->{insertion_mode} == IN_CELL_IM or |
if ($self->{insertion_mode} & BODY_TABLE_IMS) { |
|
$self->{insertion_mode} == IN_CAPTION_IM) { |
|
| 3279 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3280 |
## Ignore the token |
## Ignore the token |
| 3281 |
!!!next-token; |
!!!next-token; |
| 3301 |
|
|
| 3302 |
$insert = $insert_to_current; |
$insert = $insert_to_current; |
| 3303 |
# |
# |
| 3304 |
} elsif ($self->{insertion_mode} == IN_ROW_IM or |
} elsif ($self->{insertion_mode} & TABLE_IMS) { |
| 3305 |
$self->{insertion_mode} == IN_TABLE_BODY_IM or |
if ($token->{type} == CHARACTER_TOKEN) { |
|
$self->{insertion_mode} == IN_TABLE_IM) { |
|
|
if ($token->{type} eq 'character') { |
|
| 3306 |
## NOTE: There are "character in table" code clones. |
## NOTE: There are "character in table" code clones. |
| 3307 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 3308 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 3360 |
|
|
| 3361 |
!!!next-token; |
!!!next-token; |
| 3362 |
redo B; |
redo B; |
| 3363 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 3364 |
if ({ |
if ({ |
| 3365 |
tr => ($self->{insertion_mode} != IN_ROW_IM), |
tr => ($self->{insertion_mode} != IN_ROW_IM), |
| 3366 |
th => 1, td => 1, |
th => 1, td => 1, |
| 3577 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 3578 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3579 |
!!!back-token; # <table> |
!!!back-token; # <table> |
| 3580 |
$token = {type => 'end tag', tag_name => 'table'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'table'}; |
| 3581 |
!!!back-token; |
!!!back-token; |
| 3582 |
$token = {type => 'end tag', |
$token = {type => END_TAG_TOKEN, |
| 3583 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3584 |
redo B; |
redo B; |
| 3585 |
} |
} |
| 3597 |
} else { |
} else { |
| 3598 |
# |
# |
| 3599 |
} |
} |
| 3600 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 3601 |
if ($token->{tag_name} eq 'tr' and |
if ($token->{tag_name} eq 'tr' and |
| 3602 |
$self->{insertion_mode} == IN_ROW_IM) { |
$self->{insertion_mode} == IN_ROW_IM) { |
| 3603 |
## have an element in table scope |
## have an element in table scope |
| 3738 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 3739 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3740 |
!!!back-token; |
!!!back-token; |
| 3741 |
$token = {type => 'end tag', |
$token = {type => END_TAG_TOKEN, |
| 3742 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3743 |
redo B; |
redo B; |
| 3744 |
} |
} |
| 3756 |
} elsif ({ |
} elsif ({ |
| 3757 |
tbody => 1, tfoot => 1, thead => 1, |
tbody => 1, tfoot => 1, thead => 1, |
| 3758 |
}->{$token->{tag_name}} and |
}->{$token->{tag_name}} and |
| 3759 |
($self->{insertion_mode} == IN_ROW_IM or |
$self->{insertion_mode} & ROW_IMS) { |
|
$self->{insertion_mode} == IN_TABLE_BODY_IM)) { |
|
| 3760 |
if ($self->{insertion_mode} == IN_ROW_IM) { |
if ($self->{insertion_mode} == IN_ROW_IM) { |
| 3761 |
## have an element in table scope |
## have an element in table scope |
| 3762 |
my $i; |
my $i; |
| 3866 |
$insert = $insert_to_foster; |
$insert = $insert_to_foster; |
| 3867 |
# |
# |
| 3868 |
} elsif ($self->{insertion_mode} == IN_COLUMN_GROUP_IM) { |
} elsif ($self->{insertion_mode} == IN_COLUMN_GROUP_IM) { |
| 3869 |
if ($token->{type} eq 'character') { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 3870 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 3871 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 3872 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 3876 |
} |
} |
| 3877 |
|
|
| 3878 |
# |
# |
| 3879 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 3880 |
if ($token->{tag_name} eq 'col') { |
if ($token->{tag_name} eq 'col') { |
| 3881 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 3882 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3885 |
} else { |
} else { |
| 3886 |
# |
# |
| 3887 |
} |
} |
| 3888 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 3889 |
if ($token->{tag_name} eq 'colgroup') { |
if ($token->{tag_name} eq 'colgroup') { |
| 3890 |
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
| 3891 |
!!!parse-error (type => 'unmatched end tag:colgroup'); |
!!!parse-error (type => 'unmatched end tag:colgroup'); |
| 3923 |
redo B; |
redo B; |
| 3924 |
} |
} |
| 3925 |
} elsif ($self->{insertion_mode} == IN_SELECT_IM) { |
} elsif ($self->{insertion_mode} == IN_SELECT_IM) { |
| 3926 |
if ($token->{type} eq 'character') { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 3927 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
| 3928 |
!!!next-token; |
!!!next-token; |
| 3929 |
redo B; |
redo B; |
| 3930 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 3931 |
if ($token->{tag_name} eq 'option') { |
if ($token->{tag_name} eq 'option') { |
| 3932 |
if ($self->{open_elements}->[-1]->[1] eq 'option') { |
if ($self->{open_elements}->[-1]->[1] eq 'option') { |
| 3933 |
## As if </option> |
## As if </option> |
| 3983 |
} else { |
} else { |
| 3984 |
# |
# |
| 3985 |
} |
} |
| 3986 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 3987 |
if ($token->{tag_name} eq 'optgroup') { |
if ($token->{tag_name} eq 'optgroup') { |
| 3988 |
if ($self->{open_elements}->[-1]->[1] eq 'option' and |
if ($self->{open_elements}->[-1]->[1] eq 'option' and |
| 3989 |
$self->{open_elements}->[-2]->[1] eq 'optgroup') { |
$self->{open_elements}->[-2]->[1] eq 'optgroup') { |
| 4096 |
## Ignore the token |
## Ignore the token |
| 4097 |
!!!next-token; |
!!!next-token; |
| 4098 |
redo B; |
redo B; |
| 4099 |
} elsif ($self->{insertion_mode} == AFTER_BODY_IM or |
} elsif ($self->{insertion_mode} & BODY_AFTER_IMS) { |
| 4100 |
$self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($token->{type} == CHARACTER_TOKEN) { |
|
if ($token->{type} eq 'character') { |
|
| 4101 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 4102 |
my $data = $1; |
my $data = $1; |
| 4103 |
## As if in body |
## As if in body |
| 4123 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 4124 |
## reprocess |
## reprocess |
| 4125 |
redo B; |
redo B; |
| 4126 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 4127 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 4128 |
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
| 4129 |
|
|
| 4136 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 4137 |
## reprocess |
## reprocess |
| 4138 |
redo B; |
redo B; |
| 4139 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 4140 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 4141 |
!!!parse-error (type => 'after html:/'.$token->{tag_name}); |
!!!parse-error (type => 'after html:/'.$token->{tag_name}); |
| 4142 |
|
|
| 4166 |
} else { |
} else { |
| 4167 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 4168 |
} |
} |
| 4169 |
} elsif ($self->{insertion_mode} == IN_FRAMESET_IM or |
} elsif ($self->{insertion_mode} & FRAME_IMS) { |
| 4170 |
$self->{insertion_mode} == AFTER_FRAMESET_IM or |
if ($token->{type} == CHARACTER_TOKEN) { |
|
$self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
|
|
if ($token->{type} eq 'character') { |
|
| 4171 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 4172 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 4173 |
|
|
| 4200 |
} |
} |
| 4201 |
|
|
| 4202 |
die qq[$0: Character "$token->{data}"]; |
die qq[$0: Character "$token->{data}"]; |
| 4203 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 4204 |
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 4205 |
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
| 4206 |
|
|
| 4233 |
!!!next-token; |
!!!next-token; |
| 4234 |
redo B; |
redo B; |
| 4235 |
} |
} |
| 4236 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 4237 |
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 4238 |
!!!parse-error (type => 'after html:/'.$token->{tag_name}); |
!!!parse-error (type => 'after html:/'.$token->{tag_name}); |
| 4239 |
|
|
| 4283 |
} |
} |
| 4284 |
|
|
| 4285 |
## "in body" insertion mode |
## "in body" insertion mode |
| 4286 |
if ($token->{type} eq 'start tag') { |
if ($token->{type} == START_TAG_TOKEN) { |
| 4287 |
if ($token->{tag_name} eq 'script') { |
if ($token->{tag_name} eq 'script') { |
| 4288 |
## NOTE: This is an "as if in head" code clone |
## NOTE: This is an "as if in head" code clone |
| 4289 |
$script_start_tag->($insert); |
$script_start_tag->($insert); |
| 4363 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4364 |
if ($_->[1] eq 'p') { |
if ($_->[1] eq 'p') { |
| 4365 |
!!!back-token; |
!!!back-token; |
| 4366 |
$token = {type => 'end tag', tag_name => 'p'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4367 |
redo B; |
redo B; |
| 4368 |
} elsif ({ |
} elsif ({ |
| 4369 |
table => 1, caption => 1, td => 1, th => 1, |
table => 1, caption => 1, td => 1, th => 1, |
| 4376 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4377 |
if ($token->{tag_name} eq 'pre') { |
if ($token->{tag_name} eq 'pre') { |
| 4378 |
!!!next-token; |
!!!next-token; |
| 4379 |
if ($token->{type} eq 'character') { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 4380 |
$token->{data} =~ s/^\x0A//; |
$token->{data} =~ s/^\x0A//; |
| 4381 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 4382 |
!!!next-token; |
!!!next-token; |
| 4397 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4398 |
if ($_->[1] eq 'p') { |
if ($_->[1] eq 'p') { |
| 4399 |
!!!back-token; |
!!!back-token; |
| 4400 |
$token = {type => 'end tag', tag_name => 'p'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4401 |
redo B; |
redo B; |
| 4402 |
} elsif ({ |
} elsif ({ |
| 4403 |
table => 1, caption => 1, td => 1, th => 1, |
table => 1, caption => 1, td => 1, th => 1, |
| 4417 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4418 |
if ($_->[1] eq 'p') { |
if ($_->[1] eq 'p') { |
| 4419 |
!!!back-token; |
!!!back-token; |
| 4420 |
$token = {type => 'end tag', tag_name => 'p'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4421 |
redo B; |
redo B; |
| 4422 |
} elsif ({ |
} elsif ({ |
| 4423 |
table => 1, caption => 1, td => 1, th => 1, |
table => 1, caption => 1, td => 1, th => 1, |
| 4464 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4465 |
if ($_->[1] eq 'p') { |
if ($_->[1] eq 'p') { |
| 4466 |
!!!back-token; |
!!!back-token; |
| 4467 |
$token = {type => 'end tag', tag_name => 'p'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4468 |
redo B; |
redo B; |
| 4469 |
} elsif ({ |
} elsif ({ |
| 4470 |
table => 1, caption => 1, td => 1, th => 1, |
table => 1, caption => 1, td => 1, th => 1, |
| 4511 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4512 |
if ($_->[1] eq 'p') { |
if ($_->[1] eq 'p') { |
| 4513 |
!!!back-token; |
!!!back-token; |
| 4514 |
$token = {type => 'end tag', tag_name => 'p'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4515 |
redo B; |
redo B; |
| 4516 |
} elsif ({ |
} elsif ({ |
| 4517 |
table => 1, caption => 1, td => 1, th => 1, |
table => 1, caption => 1, td => 1, th => 1, |
| 4535 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 4536 |
if ($node->[1] eq 'p') { |
if ($node->[1] eq 'p') { |
| 4537 |
!!!back-token; |
!!!back-token; |
| 4538 |
$token = {type => 'end tag', tag_name => 'p'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4539 |
redo B; |
redo B; |
| 4540 |
} elsif ({ |
} elsif ({ |
| 4541 |
table => 1, caption => 1, td => 1, th => 1, |
table => 1, caption => 1, td => 1, th => 1, |
| 4579 |
!!!parse-error (type => 'in a:a'); |
!!!parse-error (type => 'in a:a'); |
| 4580 |
|
|
| 4581 |
!!!back-token; |
!!!back-token; |
| 4582 |
$token = {type => 'end tag', tag_name => 'a'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'a'}; |
| 4583 |
$formatting_end_tag->($token->{tag_name}); |
$formatting_end_tag->($token->{tag_name}); |
| 4584 |
|
|
| 4585 |
AFE2: for (reverse 0..$#$active_formatting_elements) { |
AFE2: for (reverse 0..$#$active_formatting_elements) { |
| 4628 |
if ($node->[1] eq 'nobr') { |
if ($node->[1] eq 'nobr') { |
| 4629 |
!!!parse-error (type => 'not closed:nobr'); |
!!!parse-error (type => 'not closed:nobr'); |
| 4630 |
!!!back-token; |
!!!back-token; |
| 4631 |
$token = {type => 'end tag', tag_name => 'nobr'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'nobr'}; |
| 4632 |
redo B; |
redo B; |
| 4633 |
} elsif ({ |
} elsif ({ |
| 4634 |
table => 1, caption => 1, td => 1, th => 1, |
table => 1, caption => 1, td => 1, th => 1, |
| 4650 |
if ($node->[1] eq 'button') { |
if ($node->[1] eq 'button') { |
| 4651 |
!!!parse-error (type => 'in button:button'); |
!!!parse-error (type => 'in button:button'); |
| 4652 |
!!!back-token; |
!!!back-token; |
| 4653 |
$token = {type => 'end tag', tag_name => 'button'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'button'}; |
| 4654 |
redo B; |
redo B; |
| 4655 |
} elsif ({ |
} elsif ({ |
| 4656 |
table => 1, caption => 1, td => 1, th => 1, |
table => 1, caption => 1, td => 1, th => 1, |
| 4685 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4686 |
if ($_->[1] eq 'p') { |
if ($_->[1] eq 'p') { |
| 4687 |
!!!back-token; |
!!!back-token; |
| 4688 |
$token = {type => 'end tag', tag_name => 'p'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4689 |
redo B; |
redo B; |
| 4690 |
} elsif ({ |
} elsif ({ |
| 4691 |
table => 1, caption => 1, td => 1, th => 1, |
table => 1, caption => 1, td => 1, th => 1, |
| 4724 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4725 |
if ($_->[1] eq 'p') { |
if ($_->[1] eq 'p') { |
| 4726 |
!!!back-token; |
!!!back-token; |
| 4727 |
$token = {type => 'end tag', tag_name => 'p'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4728 |
redo B; |
redo B; |
| 4729 |
} elsif ({ |
} elsif ({ |
| 4730 |
table => 1, caption => 1, td => 1, th => 1, |
table => 1, caption => 1, td => 1, th => 1, |
| 4764 |
delete $at->{action}; |
delete $at->{action}; |
| 4765 |
delete $at->{prompt}; |
delete $at->{prompt}; |
| 4766 |
my @tokens = ( |
my @tokens = ( |
| 4767 |
{type => 'start tag', tag_name => 'form', |
{type => START_TAG_TOKEN, tag_name => 'form', |
| 4768 |
attributes => $form_attrs}, |
attributes => $form_attrs}, |
| 4769 |
{type => 'start tag', tag_name => 'hr'}, |
{type => START_TAG_TOKEN, tag_name => 'hr'}, |
| 4770 |
{type => 'start tag', tag_name => 'p'}, |
{type => START_TAG_TOKEN, tag_name => 'p'}, |
| 4771 |
{type => 'start tag', tag_name => 'label'}, |
{type => START_TAG_TOKEN, tag_name => 'label'}, |
| 4772 |
); |
); |
| 4773 |
if ($prompt_attr) { |
if ($prompt_attr) { |
| 4774 |
push @tokens, {type => 'character', data => $prompt_attr->{value}}; |
push @tokens, {type => CHARACTER_TOKEN, data => $prompt_attr->{value}}; |
| 4775 |
} else { |
} else { |
| 4776 |
push @tokens, {type => 'character', |
push @tokens, {type => CHARACTER_TOKEN, |
| 4777 |
data => 'This is a searchable index. Insert your search keywords here: '}; # SHOULD |
data => 'This is a searchable index. Insert your search keywords here: '}; # SHOULD |
| 4778 |
## TODO: make this configurable |
## TODO: make this configurable |
| 4779 |
} |
} |
| 4780 |
push @tokens, |
push @tokens, |
| 4781 |
{type => 'start tag', tag_name => 'input', attributes => $at}, |
{type => START_TAG_TOKEN, tag_name => 'input', attributes => $at}, |
| 4782 |
#{type => 'character', data => ''}, # SHOULD |
#{type => CHARACTER_TOKEN, data => ''}, # SHOULD |
| 4783 |
{type => 'end tag', tag_name => 'label'}, |
{type => END_TAG_TOKEN, tag_name => 'label'}, |
| 4784 |
{type => 'end tag', tag_name => 'p'}, |
{type => END_TAG_TOKEN, tag_name => 'p'}, |
| 4785 |
{type => 'start tag', tag_name => 'hr'}, |
{type => START_TAG_TOKEN, tag_name => 'hr'}, |
| 4786 |
{type => 'end tag', tag_name => 'form'}; |
{type => END_TAG_TOKEN, tag_name => 'form'}; |
| 4787 |
$token = shift @tokens; |
$token = shift @tokens; |
| 4788 |
!!!back-token (@tokens); |
!!!back-token (@tokens); |
| 4789 |
redo B; |
redo B; |
| 4801 |
|
|
| 4802 |
my $text = ''; |
my $text = ''; |
| 4803 |
!!!next-token; |
!!!next-token; |
| 4804 |
if ($token->{type} eq 'character') { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 4805 |
$token->{data} =~ s/^\x0A//; |
$token->{data} =~ s/^\x0A//; |
| 4806 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 4807 |
!!!next-token; |
!!!next-token; |
| 4808 |
} |
} |
| 4809 |
} |
} |
| 4810 |
while ($token->{type} eq 'character') { |
while ($token->{type} == CHARACTER_TOKEN) { |
| 4811 |
$text .= $token->{data}; |
$text .= $token->{data}; |
| 4812 |
!!!next-token; |
!!!next-token; |
| 4813 |
} |
} |
| 4817 |
|
|
| 4818 |
$self->{content_model} = PCDATA_CONTENT_MODEL; |
$self->{content_model} = PCDATA_CONTENT_MODEL; |
| 4819 |
|
|
| 4820 |
if ($token->{type} eq 'end tag' and |
if ($token->{type} == END_TAG_TOKEN and |
| 4821 |
$token->{tag_name} eq $tag_name) { |
$token->{tag_name} eq $tag_name) { |
| 4822 |
## Ignore the token |
## Ignore the token |
| 4823 |
} else { |
} else { |
| 4862 |
!!!next-token; |
!!!next-token; |
| 4863 |
redo B; |
redo B; |
| 4864 |
} |
} |
| 4865 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 4866 |
if ($token->{tag_name} eq 'body') { |
if ($token->{tag_name} eq 'body') { |
| 4867 |
if (@{$self->{open_elements}} > 1 and |
if (@{$self->{open_elements}} > 1 and |
| 4868 |
$self->{open_elements}->[1]->[1] eq 'body') { |
$self->{open_elements}->[1]->[1] eq 'body') { |
| 4923 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 4924 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4925 |
!!!back-token; |
!!!back-token; |
| 4926 |
$token = {type => 'end tag', |
$token = {type => END_TAG_TOKEN, |
| 4927 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 4928 |
redo B; |
redo B; |
| 4929 |
} |
} |
| 4971 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 4972 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4973 |
!!!back-token; |
!!!back-token; |
| 4974 |
$token = {type => 'end tag', |
$token = {type => END_TAG_TOKEN, |
| 4975 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 4976 |
redo B; |
redo B; |
| 4977 |
} |
} |
| 5010 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 5011 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 5012 |
!!!back-token; |
!!!back-token; |
| 5013 |
$token = {type => 'end tag', |
$token = {type => END_TAG_TOKEN, |
| 5014 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 5015 |
redo B; |
redo B; |
| 5016 |
} |
} |
| 5084 |
if ({ |
if ({ |
| 5085 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 5086 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 5087 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot => 1, thead => 1, |
| 5088 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 5089 |
!!!back-token; |
!!!back-token; |
| 5090 |
$token = {type => 'end tag', |
$token = {type => END_TAG_TOKEN, |
| 5091 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 5092 |
redo B; |
redo B; |
| 5093 |
} |
} |