| 147 |
$self->{parse_error} = sub { |
$self->{parse_error} = sub { |
| 148 |
# |
# |
| 149 |
}; |
}; |
| 150 |
|
$self->{application_cache_selection} = sub { |
| 151 |
|
# |
| 152 |
|
}; |
| 153 |
return $self; |
return $self; |
| 154 |
} # new |
} # new |
| 155 |
|
|
| 162 |
sub RCDATA_CONTENT_MODEL () { CM_ENTITY | CM_LIMITED_MARKUP } |
sub RCDATA_CONTENT_MODEL () { CM_ENTITY | CM_LIMITED_MARKUP } |
| 163 |
sub PCDATA_CONTENT_MODEL () { CM_ENTITY | CM_FULL_MARKUP } |
sub PCDATA_CONTENT_MODEL () { CM_ENTITY | CM_FULL_MARKUP } |
| 164 |
|
|
| 165 |
|
sub DATA_STATE () { 0 } |
| 166 |
|
sub ENTITY_DATA_STATE () { 1 } |
| 167 |
|
sub TAG_OPEN_STATE () { 2 } |
| 168 |
|
sub CLOSE_TAG_OPEN_STATE () { 3 } |
| 169 |
|
sub TAG_NAME_STATE () { 4 } |
| 170 |
|
sub BEFORE_ATTRIBUTE_NAME_STATE () { 5 } |
| 171 |
|
sub ATTRIBUTE_NAME_STATE () { 6 } |
| 172 |
|
sub AFTER_ATTRIBUTE_NAME_STATE () { 7 } |
| 173 |
|
sub BEFORE_ATTRIBUTE_VALUE_STATE () { 8 } |
| 174 |
|
sub ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE () { 9 } |
| 175 |
|
sub ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE () { 10 } |
| 176 |
|
sub ATTRIBUTE_VALUE_UNQUOTED_STATE () { 11 } |
| 177 |
|
sub ENTITY_IN_ATTRIBUTE_VALUE_STATE () { 12 } |
| 178 |
|
sub MARKUP_DECLARATION_OPEN_STATE () { 13 } |
| 179 |
|
sub COMMENT_START_STATE () { 14 } |
| 180 |
|
sub COMMENT_START_DASH_STATE () { 15 } |
| 181 |
|
sub COMMENT_STATE () { 16 } |
| 182 |
|
sub COMMENT_END_STATE () { 17 } |
| 183 |
|
sub COMMENT_END_DASH_STATE () { 18 } |
| 184 |
|
sub BOGUS_COMMENT_STATE () { 19 } |
| 185 |
|
sub DOCTYPE_STATE () { 20 } |
| 186 |
|
sub BEFORE_DOCTYPE_NAME_STATE () { 21 } |
| 187 |
|
sub DOCTYPE_NAME_STATE () { 22 } |
| 188 |
|
sub AFTER_DOCTYPE_NAME_STATE () { 23 } |
| 189 |
|
sub BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE () { 24 } |
| 190 |
|
sub DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE () { 25 } |
| 191 |
|
sub DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE () { 26 } |
| 192 |
|
sub AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE () { 27 } |
| 193 |
|
sub BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE () { 28 } |
| 194 |
|
sub DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE () { 29 } |
| 195 |
|
sub DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE () { 30 } |
| 196 |
|
sub AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE () { 31 } |
| 197 |
|
sub BOGUS_DOCTYPE_STATE () { 32 } |
| 198 |
|
|
| 199 |
|
sub DOCTYPE_TOKEN () { 1 } |
| 200 |
|
sub COMMENT_TOKEN () { 2 } |
| 201 |
|
sub START_TAG_TOKEN () { 3 } |
| 202 |
|
sub END_TAG_TOKEN () { 4 } |
| 203 |
|
sub END_OF_FILE_TOKEN () { 5 } |
| 204 |
|
sub CHARACTER_TOKEN () { 6 } |
| 205 |
|
|
| 206 |
|
sub AFTER_HTML_IMS () { 0b100 } |
| 207 |
|
sub HEAD_IMS () { 0b1000 } |
| 208 |
|
sub BODY_IMS () { 0b10000 } |
| 209 |
|
sub BODY_TABLE_IMS () { 0b100000 } |
| 210 |
|
sub TABLE_IMS () { 0b1000000 } |
| 211 |
|
sub ROW_IMS () { 0b10000000 } |
| 212 |
|
sub BODY_AFTER_IMS () { 0b100000000 } |
| 213 |
|
sub FRAME_IMS () { 0b1000000000 } |
| 214 |
|
|
| 215 |
|
sub AFTER_HTML_BODY_IM () { AFTER_HTML_IMS | BODY_AFTER_IMS } |
| 216 |
|
sub AFTER_HTML_FRAMESET_IM () { AFTER_HTML_IMS | FRAME_IMS } |
| 217 |
|
sub IN_HEAD_IM () { HEAD_IMS | 0b00 } |
| 218 |
|
sub IN_HEAD_NOSCRIPT_IM () { HEAD_IMS | 0b01 } |
| 219 |
|
sub AFTER_HEAD_IM () { HEAD_IMS | 0b10 } |
| 220 |
|
sub BEFORE_HEAD_IM () { HEAD_IMS | 0b11 } |
| 221 |
|
sub IN_BODY_IM () { BODY_IMS } |
| 222 |
|
sub IN_CELL_IM () { BODY_IMS | BODY_TABLE_IMS | 0b01 } |
| 223 |
|
sub IN_CAPTION_IM () { BODY_IMS | BODY_TABLE_IMS | 0b10 } |
| 224 |
|
sub IN_ROW_IM () { TABLE_IMS | ROW_IMS | 0b01 } |
| 225 |
|
sub IN_TABLE_BODY_IM () { TABLE_IMS | ROW_IMS | 0b10 } |
| 226 |
|
sub IN_TABLE_IM () { TABLE_IMS } |
| 227 |
|
sub AFTER_BODY_IM () { BODY_AFTER_IMS } |
| 228 |
|
sub IN_FRAMESET_IM () { FRAME_IMS | 0b01 } |
| 229 |
|
sub AFTER_FRAMESET_IM () { FRAME_IMS | 0b10 } |
| 230 |
|
sub IN_SELECT_IM () { 0b01 } |
| 231 |
|
sub IN_COLUMN_GROUP_IM () { 0b10 } |
| 232 |
|
|
| 233 |
## Implementations MUST act as if state machine in the spec |
## Implementations MUST act as if state machine in the spec |
| 234 |
|
|
| 235 |
sub _initialize_tokenizer ($) { |
sub _initialize_tokenizer ($) { |
| 236 |
my $self = shift; |
my $self = shift; |
| 237 |
$self->{state} = 'data'; # MUST |
$self->{state} = DATA_STATE; # MUST |
| 238 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # be |
$self->{content_model} = PCDATA_CONTENT_MODEL; # be |
| 239 |
undef $self->{current_token}; # start tag, end tag, comment, or DOCTYPE |
undef $self->{current_token}; # start tag, end tag, comment, or DOCTYPE |
| 240 |
undef $self->{current_attribute}; |
undef $self->{current_attribute}; |
| 248 |
} # _initialize_tokenizer |
} # _initialize_tokenizer |
| 249 |
|
|
| 250 |
## A token has: |
## A token has: |
| 251 |
## ->{type} eq 'DOCTYPE', 'start tag', 'end tag', 'comment', |
## ->{type} == DOCTYPE_TOKEN, START_TAG_TOKEN, END_TAG_TOKEN, COMMENT_TOKEN, |
| 252 |
## 'character', or 'end-of-file' |
## CHARACTER_TOKEN, or END_OF_FILE_TOKEN |
| 253 |
## ->{name} (DOCTYPE, start tag (tag name), end tag (tag name)) |
## ->{name} (DOCTYPE_TOKEN) |
| 254 |
## ->{public_identifier} (DOCTYPE) |
## ->{tag_name} (START_TAG_TOKEN, END_TAG_TOKEN) |
| 255 |
## ->{system_identifier} (DOCTYPE) |
## ->{public_identifier} (DOCTYPE_TOKEN) |
| 256 |
## ->{correct} == 1 or 0 (DOCTYPE) |
## ->{system_identifier} (DOCTYPE_TOKEN) |
| 257 |
## ->{attributes} isa HASH (start tag, end tag) |
## ->{correct} == 1 or 0 (DOCTYPE_TOKEN) |
| 258 |
## ->{data} (comment, character) |
## ->{attributes} isa HASH (START_TAG_TOKEN, END_TAG_TOKEN) |
| 259 |
|
## ->{data} (COMMENT_TOKEN, CHARACTER_TOKEN) |
| 260 |
|
|
| 261 |
## Emitted token MUST immediately be handled by the tree construction state. |
## Emitted token MUST immediately be handled by the tree construction state. |
| 262 |
|
|
| 266 |
## has completed loading. If one has, then it MUST be executed |
## has completed loading. If one has, then it MUST be executed |
| 267 |
## and removed from the list. |
## and removed from the list. |
| 268 |
|
|
| 269 |
|
## NOTE: HTML5 "Writing HTML documents" section, applied to |
| 270 |
|
## documents and not to user agents and conformance checkers, |
| 271 |
|
## contains some requirements that are not detected by the |
| 272 |
|
## parsing algorithm: |
| 273 |
|
## - Some requirements on character encoding declarations. ## TODO |
| 274 |
|
## - "Elements MUST NOT contain content that their content model disallows." |
| 275 |
|
## ... Some are parse error, some are not (will be reported by c.c.). |
| 276 |
|
## - Polytheistic slash SHOULD NOT be used. (Applied only to atheists.) ## TODO |
| 277 |
|
## - Text (in elements, attributes, and comments) SHOULD NOT contain |
| 278 |
|
## control characters other than space characters. ## TODO: (what is control character? C0, C1 and DEL? Unicode control character?) |
| 279 |
|
|
| 280 |
|
## TODO: HTML5 poses authors two SHOULD-level requirements that cannot |
| 281 |
|
## be detected by the HTML5 parsing algorithm: |
| 282 |
|
## - Text, |
| 283 |
|
|
| 284 |
sub _get_next_token ($) { |
sub _get_next_token ($) { |
| 285 |
my $self = shift; |
my $self = shift; |
| 286 |
if (@{$self->{token}}) { |
if (@{$self->{token}}) { |
| 288 |
} |
} |
| 289 |
|
|
| 290 |
A: { |
A: { |
| 291 |
if ($self->{state} eq 'data') { |
if ($self->{state} == DATA_STATE) { |
| 292 |
if ($self->{next_input_character} == 0x0026) { # & |
if ($self->{next_input_character} == 0x0026) { # & |
| 293 |
if ($self->{content_model} & CM_ENTITY) { # PCDATA | RCDATA |
if ($self->{content_model} & CM_ENTITY) { # PCDATA | RCDATA |
| 294 |
$self->{state} = 'entity data'; |
$self->{state} = ENTITY_DATA_STATE; |
| 295 |
!!!next-input-character; |
!!!next-input-character; |
| 296 |
redo A; |
redo A; |
| 297 |
} else { |
} else { |
| 313 |
if ($self->{content_model} & CM_FULL_MARKUP or # PCDATA |
if ($self->{content_model} & CM_FULL_MARKUP or # PCDATA |
| 314 |
(($self->{content_model} & CM_LIMITED_MARKUP) and # CDATA | RCDATA |
(($self->{content_model} & CM_LIMITED_MARKUP) and # CDATA | RCDATA |
| 315 |
not $self->{escape})) { |
not $self->{escape})) { |
| 316 |
$self->{state} = 'tag open'; |
$self->{state} = TAG_OPEN_STATE; |
| 317 |
!!!next-input-character; |
!!!next-input-character; |
| 318 |
redo A; |
redo A; |
| 319 |
} else { |
} else { |
| 330 |
|
|
| 331 |
# |
# |
| 332 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 333 |
!!!emit ({type => 'end-of-file'}); |
!!!emit ({type => END_OF_FILE_TOKEN}); |
| 334 |
last A; ## TODO: ok? |
last A; ## TODO: ok? |
| 335 |
} |
} |
| 336 |
# Anything else |
# Anything else |
| 337 |
my $token = {type => 'character', |
my $token = {type => CHARACTER_TOKEN, |
| 338 |
data => chr $self->{next_input_character}}; |
data => chr $self->{next_input_character}}; |
| 339 |
## Stay in the data state |
## Stay in the data state |
| 340 |
!!!next-input-character; |
!!!next-input-character; |
| 342 |
!!!emit ($token); |
!!!emit ($token); |
| 343 |
|
|
| 344 |
redo A; |
redo A; |
| 345 |
} elsif ($self->{state} eq 'entity data') { |
} elsif ($self->{state} == ENTITY_DATA_STATE) { |
| 346 |
## (cannot happen in CDATA state) |
## (cannot happen in CDATA state) |
| 347 |
|
|
| 348 |
my $token = $self->_tokenize_attempt_to_consume_an_entity (0); |
my $token = $self->_tokenize_attempt_to_consume_an_entity (0); |
| 349 |
|
|
| 350 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 351 |
# next-input-character is already done |
# next-input-character is already done |
| 352 |
|
|
| 353 |
unless (defined $token) { |
unless (defined $token) { |
| 354 |
!!!emit ({type => 'character', data => '&'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '&'}); |
| 355 |
} else { |
} else { |
| 356 |
!!!emit ($token); |
!!!emit ($token); |
| 357 |
} |
} |
| 358 |
|
|
| 359 |
redo A; |
redo A; |
| 360 |
} elsif ($self->{state} eq 'tag open') { |
} elsif ($self->{state} == TAG_OPEN_STATE) { |
| 361 |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
| 362 |
if ($self->{next_input_character} == 0x002F) { # / |
if ($self->{next_input_character} == 0x002F) { # / |
| 363 |
!!!next-input-character; |
!!!next-input-character; |
| 364 |
$self->{state} = 'close tag open'; |
$self->{state} = CLOSE_TAG_OPEN_STATE; |
| 365 |
redo A; |
redo A; |
| 366 |
} else { |
} else { |
| 367 |
## reconsume |
## reconsume |
| 368 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 369 |
|
|
| 370 |
!!!emit ({type => 'character', data => '<'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '<'}); |
| 371 |
|
|
| 372 |
redo A; |
redo A; |
| 373 |
} |
} |
| 374 |
} elsif ($self->{content_model} & CM_FULL_MARKUP) { # PCDATA |
} elsif ($self->{content_model} & CM_FULL_MARKUP) { # PCDATA |
| 375 |
if ($self->{next_input_character} == 0x0021) { # ! |
if ($self->{next_input_character} == 0x0021) { # ! |
| 376 |
$self->{state} = 'markup declaration open'; |
$self->{state} = MARKUP_DECLARATION_OPEN_STATE; |
| 377 |
!!!next-input-character; |
!!!next-input-character; |
| 378 |
redo A; |
redo A; |
| 379 |
} elsif ($self->{next_input_character} == 0x002F) { # / |
} elsif ($self->{next_input_character} == 0x002F) { # / |
| 380 |
$self->{state} = 'close tag open'; |
$self->{state} = CLOSE_TAG_OPEN_STATE; |
| 381 |
!!!next-input-character; |
!!!next-input-character; |
| 382 |
redo A; |
redo A; |
| 383 |
} elsif (0x0041 <= $self->{next_input_character} and |
} elsif (0x0041 <= $self->{next_input_character} and |
| 384 |
$self->{next_input_character} <= 0x005A) { # A..Z |
$self->{next_input_character} <= 0x005A) { # A..Z |
| 385 |
$self->{current_token} |
$self->{current_token} |
| 386 |
= {type => 'start tag', |
= {type => START_TAG_TOKEN, |
| 387 |
tag_name => chr ($self->{next_input_character} + 0x0020)}; |
tag_name => chr ($self->{next_input_character} + 0x0020)}; |
| 388 |
$self->{state} = 'tag name'; |
$self->{state} = TAG_NAME_STATE; |
| 389 |
!!!next-input-character; |
!!!next-input-character; |
| 390 |
redo A; |
redo A; |
| 391 |
} elsif (0x0061 <= $self->{next_input_character} and |
} elsif (0x0061 <= $self->{next_input_character} and |
| 392 |
$self->{next_input_character} <= 0x007A) { # a..z |
$self->{next_input_character} <= 0x007A) { # a..z |
| 393 |
$self->{current_token} = {type => 'start tag', |
$self->{current_token} = {type => START_TAG_TOKEN, |
| 394 |
tag_name => chr ($self->{next_input_character})}; |
tag_name => chr ($self->{next_input_character})}; |
| 395 |
$self->{state} = 'tag name'; |
$self->{state} = TAG_NAME_STATE; |
| 396 |
!!!next-input-character; |
!!!next-input-character; |
| 397 |
redo A; |
redo A; |
| 398 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 399 |
!!!parse-error (type => 'empty start tag'); |
!!!parse-error (type => 'empty start tag'); |
| 400 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 401 |
!!!next-input-character; |
!!!next-input-character; |
| 402 |
|
|
| 403 |
!!!emit ({type => 'character', data => '<>'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '<>'}); |
| 404 |
|
|
| 405 |
redo A; |
redo A; |
| 406 |
} elsif ($self->{next_input_character} == 0x003F) { # ? |
} elsif ($self->{next_input_character} == 0x003F) { # ? |
| 407 |
!!!parse-error (type => 'pio'); |
!!!parse-error (type => 'pio'); |
| 408 |
$self->{state} = 'bogus comment'; |
$self->{state} = BOGUS_COMMENT_STATE; |
| 409 |
## $self->{next_input_character} is intentionally left as is |
## $self->{next_input_character} is intentionally left as is |
| 410 |
redo A; |
redo A; |
| 411 |
} else { |
} else { |
| 412 |
!!!parse-error (type => 'bare stago'); |
!!!parse-error (type => 'bare stago'); |
| 413 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 414 |
## reconsume |
## reconsume |
| 415 |
|
|
| 416 |
!!!emit ({type => 'character', data => '<'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '<'}); |
| 417 |
|
|
| 418 |
redo A; |
redo A; |
| 419 |
} |
} |
| 420 |
} else { |
} else { |
| 421 |
die "$0: $self->{content_model} in tag open"; |
die "$0: $self->{content_model} in tag open"; |
| 422 |
} |
} |
| 423 |
} elsif ($self->{state} eq 'close tag open') { |
} elsif ($self->{state} == CLOSE_TAG_OPEN_STATE) { |
| 424 |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
| 425 |
if (defined $self->{last_emitted_start_tag_name}) { |
if (defined $self->{last_emitted_start_tag_name}) { |
| 426 |
## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564> |
## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564> |
| 435 |
} else { |
} else { |
| 436 |
$self->{next_input_character} = shift @next_char; # reconsume |
$self->{next_input_character} = shift @next_char; # reconsume |
| 437 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 438 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 439 |
|
|
| 440 |
!!!emit ({type => 'character', data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
| 441 |
|
|
| 442 |
redo A; |
redo A; |
| 443 |
} |
} |
| 454 |
$self->{next_input_character} == -1) { |
$self->{next_input_character} == -1) { |
| 455 |
$self->{next_input_character} = shift @next_char; # reconsume |
$self->{next_input_character} = shift @next_char; # reconsume |
| 456 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 457 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 458 |
!!!emit ({type => 'character', data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
| 459 |
redo A; |
redo A; |
| 460 |
} else { |
} else { |
| 461 |
$self->{next_input_character} = shift @next_char; |
$self->{next_input_character} = shift @next_char; |
| 465 |
} else { |
} else { |
| 466 |
## No start tag token has ever been emitted |
## No start tag token has ever been emitted |
| 467 |
# next-input-character is already done |
# next-input-character is already done |
| 468 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 469 |
!!!emit ({type => 'character', data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
| 470 |
redo A; |
redo A; |
| 471 |
} |
} |
| 472 |
} |
} |
| 473 |
|
|
| 474 |
if (0x0041 <= $self->{next_input_character} and |
if (0x0041 <= $self->{next_input_character} and |
| 475 |
$self->{next_input_character} <= 0x005A) { # A..Z |
$self->{next_input_character} <= 0x005A) { # A..Z |
| 476 |
$self->{current_token} = {type => 'end tag', |
$self->{current_token} = {type => END_TAG_TOKEN, |
| 477 |
tag_name => chr ($self->{next_input_character} + 0x0020)}; |
tag_name => chr ($self->{next_input_character} + 0x0020)}; |
| 478 |
$self->{state} = 'tag name'; |
$self->{state} = TAG_NAME_STATE; |
| 479 |
!!!next-input-character; |
!!!next-input-character; |
| 480 |
redo A; |
redo A; |
| 481 |
} elsif (0x0061 <= $self->{next_input_character} and |
} elsif (0x0061 <= $self->{next_input_character} and |
| 482 |
$self->{next_input_character} <= 0x007A) { # a..z |
$self->{next_input_character} <= 0x007A) { # a..z |
| 483 |
$self->{current_token} = {type => 'end tag', |
$self->{current_token} = {type => END_TAG_TOKEN, |
| 484 |
tag_name => chr ($self->{next_input_character})}; |
tag_name => chr ($self->{next_input_character})}; |
| 485 |
$self->{state} = 'tag name'; |
$self->{state} = TAG_NAME_STATE; |
| 486 |
!!!next-input-character; |
!!!next-input-character; |
| 487 |
redo A; |
redo A; |
| 488 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 489 |
!!!parse-error (type => 'empty end tag'); |
!!!parse-error (type => 'empty end tag'); |
| 490 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 491 |
!!!next-input-character; |
!!!next-input-character; |
| 492 |
redo A; |
redo A; |
| 493 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 494 |
!!!parse-error (type => 'bare etago'); |
!!!parse-error (type => 'bare etago'); |
| 495 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 496 |
# reconsume |
# reconsume |
| 497 |
|
|
| 498 |
!!!emit ({type => 'character', data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
| 499 |
|
|
| 500 |
redo A; |
redo A; |
| 501 |
} else { |
} else { |
| 502 |
!!!parse-error (type => 'bogus end tag'); |
!!!parse-error (type => 'bogus end tag'); |
| 503 |
$self->{state} = 'bogus comment'; |
$self->{state} = BOGUS_COMMENT_STATE; |
| 504 |
## $self->{next_input_character} is intentionally left as is |
## $self->{next_input_character} is intentionally left as is |
| 505 |
redo A; |
redo A; |
| 506 |
} |
} |
| 507 |
} elsif ($self->{state} eq 'tag name') { |
} elsif ($self->{state} == TAG_NAME_STATE) { |
| 508 |
if ($self->{next_input_character} == 0x0009 or # HT |
if ($self->{next_input_character} == 0x0009 or # HT |
| 509 |
$self->{next_input_character} == 0x000A or # LF |
$self->{next_input_character} == 0x000A or # LF |
| 510 |
$self->{next_input_character} == 0x000B or # VT |
$self->{next_input_character} == 0x000B or # VT |
| 511 |
$self->{next_input_character} == 0x000C or # FF |
$self->{next_input_character} == 0x000C or # FF |
| 512 |
$self->{next_input_character} == 0x0020) { # SP |
$self->{next_input_character} == 0x0020) { # SP |
| 513 |
$self->{state} = 'before attribute name'; |
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
| 514 |
!!!next-input-character; |
!!!next-input-character; |
| 515 |
redo A; |
redo A; |
| 516 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 517 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 518 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 519 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 520 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 521 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 522 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 523 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 524 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 526 |
} else { |
} else { |
| 527 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 528 |
} |
} |
| 529 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 530 |
!!!next-input-character; |
!!!next-input-character; |
| 531 |
|
|
| 532 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 541 |
redo A; |
redo A; |
| 542 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 543 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 544 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 545 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 546 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 547 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 548 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 549 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 550 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 551 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 553 |
} else { |
} else { |
| 554 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 555 |
} |
} |
| 556 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 557 |
# reconsume |
# reconsume |
| 558 |
|
|
| 559 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 562 |
} elsif ($self->{next_input_character} == 0x002F) { # / |
} elsif ($self->{next_input_character} == 0x002F) { # / |
| 563 |
!!!next-input-character; |
!!!next-input-character; |
| 564 |
if ($self->{next_input_character} == 0x003E and # > |
if ($self->{next_input_character} == 0x003E and # > |
| 565 |
$self->{current_token}->{type} eq 'start tag' and |
$self->{current_token}->{type} == START_TAG_TOKEN and |
| 566 |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
| 567 |
# permitted slash |
# permitted slash |
| 568 |
# |
# |
| 569 |
} else { |
} else { |
| 570 |
!!!parse-error (type => 'nestc'); |
!!!parse-error (type => 'nestc'); |
| 571 |
} |
} |
| 572 |
$self->{state} = 'before attribute name'; |
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
| 573 |
# next-input-character is already done |
# next-input-character is already done |
| 574 |
redo A; |
redo A; |
| 575 |
} else { |
} else { |
| 579 |
!!!next-input-character; |
!!!next-input-character; |
| 580 |
redo A; |
redo A; |
| 581 |
} |
} |
| 582 |
} elsif ($self->{state} eq 'before attribute name') { |
} elsif ($self->{state} == BEFORE_ATTRIBUTE_NAME_STATE) { |
| 583 |
if ($self->{next_input_character} == 0x0009 or # HT |
if ($self->{next_input_character} == 0x0009 or # HT |
| 584 |
$self->{next_input_character} == 0x000A or # LF |
$self->{next_input_character} == 0x000A or # LF |
| 585 |
$self->{next_input_character} == 0x000B or # VT |
$self->{next_input_character} == 0x000B or # VT |
| 589 |
!!!next-input-character; |
!!!next-input-character; |
| 590 |
redo A; |
redo A; |
| 591 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 592 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 593 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 594 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 595 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 596 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 597 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 598 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 599 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 601 |
} else { |
} else { |
| 602 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 603 |
} |
} |
| 604 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 605 |
!!!next-input-character; |
!!!next-input-character; |
| 606 |
|
|
| 607 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 611 |
$self->{next_input_character} <= 0x005A) { # A..Z |
$self->{next_input_character} <= 0x005A) { # A..Z |
| 612 |
$self->{current_attribute} = {name => chr ($self->{next_input_character} + 0x0020), |
$self->{current_attribute} = {name => chr ($self->{next_input_character} + 0x0020), |
| 613 |
value => ''}; |
value => ''}; |
| 614 |
$self->{state} = 'attribute name'; |
$self->{state} = ATTRIBUTE_NAME_STATE; |
| 615 |
!!!next-input-character; |
!!!next-input-character; |
| 616 |
redo A; |
redo A; |
| 617 |
} elsif ($self->{next_input_character} == 0x002F) { # / |
} elsif ($self->{next_input_character} == 0x002F) { # / |
| 618 |
!!!next-input-character; |
!!!next-input-character; |
| 619 |
if ($self->{next_input_character} == 0x003E and # > |
if ($self->{next_input_character} == 0x003E and # > |
| 620 |
$self->{current_token}->{type} eq 'start tag' and |
$self->{current_token}->{type} == START_TAG_TOKEN and |
| 621 |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
| 622 |
# permitted slash |
# permitted slash |
| 623 |
# |
# |
| 629 |
redo A; |
redo A; |
| 630 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 631 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 632 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 633 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 634 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 635 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 636 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 637 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 638 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 639 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 641 |
} else { |
} else { |
| 642 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 643 |
} |
} |
| 644 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 645 |
# reconsume |
# reconsume |
| 646 |
|
|
| 647 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 650 |
} else { |
} else { |
| 651 |
$self->{current_attribute} = {name => chr ($self->{next_input_character}), |
$self->{current_attribute} = {name => chr ($self->{next_input_character}), |
| 652 |
value => ''}; |
value => ''}; |
| 653 |
$self->{state} = 'attribute name'; |
$self->{state} = ATTRIBUTE_NAME_STATE; |
| 654 |
!!!next-input-character; |
!!!next-input-character; |
| 655 |
redo A; |
redo A; |
| 656 |
} |
} |
| 657 |
} elsif ($self->{state} eq 'attribute name') { |
} elsif ($self->{state} == ATTRIBUTE_NAME_STATE) { |
| 658 |
my $before_leave = sub { |
my $before_leave = sub { |
| 659 |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
| 660 |
->{$self->{current_attribute}->{name}}) { # MUST |
->{$self->{current_attribute}->{name}}) { # MUST |
| 672 |
$self->{next_input_character} == 0x000C or # FF |
$self->{next_input_character} == 0x000C or # FF |
| 673 |
$self->{next_input_character} == 0x0020) { # SP |
$self->{next_input_character} == 0x0020) { # SP |
| 674 |
$before_leave->(); |
$before_leave->(); |
| 675 |
$self->{state} = 'after attribute name'; |
$self->{state} = AFTER_ATTRIBUTE_NAME_STATE; |
| 676 |
!!!next-input-character; |
!!!next-input-character; |
| 677 |
redo A; |
redo A; |
| 678 |
} elsif ($self->{next_input_character} == 0x003D) { # = |
} elsif ($self->{next_input_character} == 0x003D) { # = |
| 679 |
$before_leave->(); |
$before_leave->(); |
| 680 |
$self->{state} = 'before attribute value'; |
$self->{state} = BEFORE_ATTRIBUTE_VALUE_STATE; |
| 681 |
!!!next-input-character; |
!!!next-input-character; |
| 682 |
redo A; |
redo A; |
| 683 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 684 |
$before_leave->(); |
$before_leave->(); |
| 685 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 686 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 687 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 688 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 689 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 690 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 691 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 692 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 694 |
} else { |
} else { |
| 695 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 696 |
} |
} |
| 697 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 698 |
!!!next-input-character; |
!!!next-input-character; |
| 699 |
|
|
| 700 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 710 |
$before_leave->(); |
$before_leave->(); |
| 711 |
!!!next-input-character; |
!!!next-input-character; |
| 712 |
if ($self->{next_input_character} == 0x003E and # > |
if ($self->{next_input_character} == 0x003E and # > |
| 713 |
$self->{current_token}->{type} eq 'start tag' and |
$self->{current_token}->{type} == START_TAG_TOKEN and |
| 714 |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
| 715 |
# permitted slash |
# permitted slash |
| 716 |
# |
# |
| 717 |
} else { |
} else { |
| 718 |
!!!parse-error (type => 'nestc'); |
!!!parse-error (type => 'nestc'); |
| 719 |
} |
} |
| 720 |
$self->{state} = 'before attribute name'; |
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
| 721 |
# next-input-character is already done |
# next-input-character is already done |
| 722 |
redo A; |
redo A; |
| 723 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 724 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 725 |
$before_leave->(); |
$before_leave->(); |
| 726 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 727 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 728 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 729 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 730 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 731 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 732 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 733 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 735 |
} else { |
} else { |
| 736 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 737 |
} |
} |
| 738 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 739 |
# reconsume |
# reconsume |
| 740 |
|
|
| 741 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 747 |
!!!next-input-character; |
!!!next-input-character; |
| 748 |
redo A; |
redo A; |
| 749 |
} |
} |
| 750 |
} elsif ($self->{state} eq 'after attribute name') { |
} elsif ($self->{state} == AFTER_ATTRIBUTE_NAME_STATE) { |
| 751 |
if ($self->{next_input_character} == 0x0009 or # HT |
if ($self->{next_input_character} == 0x0009 or # HT |
| 752 |
$self->{next_input_character} == 0x000A or # LF |
$self->{next_input_character} == 0x000A or # LF |
| 753 |
$self->{next_input_character} == 0x000B or # VT |
$self->{next_input_character} == 0x000B or # VT |
| 757 |
!!!next-input-character; |
!!!next-input-character; |
| 758 |
redo A; |
redo A; |
| 759 |
} elsif ($self->{next_input_character} == 0x003D) { # = |
} elsif ($self->{next_input_character} == 0x003D) { # = |
| 760 |
$self->{state} = 'before attribute value'; |
$self->{state} = BEFORE_ATTRIBUTE_VALUE_STATE; |
| 761 |
!!!next-input-character; |
!!!next-input-character; |
| 762 |
redo A; |
redo A; |
| 763 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 764 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 765 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 766 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 767 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 768 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 769 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 770 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 771 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 773 |
} else { |
} else { |
| 774 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 775 |
} |
} |
| 776 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 777 |
!!!next-input-character; |
!!!next-input-character; |
| 778 |
|
|
| 779 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 783 |
$self->{next_input_character} <= 0x005A) { # A..Z |
$self->{next_input_character} <= 0x005A) { # A..Z |
| 784 |
$self->{current_attribute} = {name => chr ($self->{next_input_character} + 0x0020), |
$self->{current_attribute} = {name => chr ($self->{next_input_character} + 0x0020), |
| 785 |
value => ''}; |
value => ''}; |
| 786 |
$self->{state} = 'attribute name'; |
$self->{state} = ATTRIBUTE_NAME_STATE; |
| 787 |
!!!next-input-character; |
!!!next-input-character; |
| 788 |
redo A; |
redo A; |
| 789 |
} elsif ($self->{next_input_character} == 0x002F) { # / |
} elsif ($self->{next_input_character} == 0x002F) { # / |
| 790 |
!!!next-input-character; |
!!!next-input-character; |
| 791 |
if ($self->{next_input_character} == 0x003E and # > |
if ($self->{next_input_character} == 0x003E and # > |
| 792 |
$self->{current_token}->{type} eq 'start tag' and |
$self->{current_token}->{type} == START_TAG_TOKEN and |
| 793 |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
| 794 |
# permitted slash |
# permitted slash |
| 795 |
# |
# |
| 797 |
!!!parse-error (type => 'nestc'); |
!!!parse-error (type => 'nestc'); |
| 798 |
## TODO: Different error type for <aa / bb> than <aa/> |
## TODO: Different error type for <aa / bb> than <aa/> |
| 799 |
} |
} |
| 800 |
$self->{state} = 'before attribute name'; |
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
| 801 |
# next-input-character is already done |
# next-input-character is already done |
| 802 |
redo A; |
redo A; |
| 803 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 804 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 805 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 806 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 807 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 808 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 809 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 810 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 811 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 812 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 814 |
} else { |
} else { |
| 815 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 816 |
} |
} |
| 817 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 818 |
# reconsume |
# reconsume |
| 819 |
|
|
| 820 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 823 |
} else { |
} else { |
| 824 |
$self->{current_attribute} = {name => chr ($self->{next_input_character}), |
$self->{current_attribute} = {name => chr ($self->{next_input_character}), |
| 825 |
value => ''}; |
value => ''}; |
| 826 |
$self->{state} = 'attribute name'; |
$self->{state} = ATTRIBUTE_NAME_STATE; |
| 827 |
!!!next-input-character; |
!!!next-input-character; |
| 828 |
redo A; |
redo A; |
| 829 |
} |
} |
| 830 |
} elsif ($self->{state} eq 'before attribute value') { |
} elsif ($self->{state} == BEFORE_ATTRIBUTE_VALUE_STATE) { |
| 831 |
if ($self->{next_input_character} == 0x0009 or # HT |
if ($self->{next_input_character} == 0x0009 or # HT |
| 832 |
$self->{next_input_character} == 0x000A or # LF |
$self->{next_input_character} == 0x000A or # LF |
| 833 |
$self->{next_input_character} == 0x000B or # VT |
$self->{next_input_character} == 0x000B or # VT |
| 837 |
!!!next-input-character; |
!!!next-input-character; |
| 838 |
redo A; |
redo A; |
| 839 |
} elsif ($self->{next_input_character} == 0x0022) { # " |
} elsif ($self->{next_input_character} == 0x0022) { # " |
| 840 |
$self->{state} = 'attribute value (double-quoted)'; |
$self->{state} = ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE; |
| 841 |
!!!next-input-character; |
!!!next-input-character; |
| 842 |
redo A; |
redo A; |
| 843 |
} elsif ($self->{next_input_character} == 0x0026) { # & |
} elsif ($self->{next_input_character} == 0x0026) { # & |
| 844 |
$self->{state} = 'attribute value (unquoted)'; |
$self->{state} = ATTRIBUTE_VALUE_UNQUOTED_STATE; |
| 845 |
## reconsume |
## reconsume |
| 846 |
redo A; |
redo A; |
| 847 |
} elsif ($self->{next_input_character} == 0x0027) { # ' |
} elsif ($self->{next_input_character} == 0x0027) { # ' |
| 848 |
$self->{state} = 'attribute value (single-quoted)'; |
$self->{state} = ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE; |
| 849 |
!!!next-input-character; |
!!!next-input-character; |
| 850 |
redo A; |
redo A; |
| 851 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 852 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 853 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 854 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 855 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 856 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 857 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 858 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 859 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 861 |
} else { |
} else { |
| 862 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 863 |
} |
} |
| 864 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 865 |
!!!next-input-character; |
!!!next-input-character; |
| 866 |
|
|
| 867 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 869 |
redo A; |
redo A; |
| 870 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 871 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 872 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 873 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 874 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 875 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 876 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 877 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 878 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 879 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 881 |
} else { |
} else { |
| 882 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 883 |
} |
} |
| 884 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 885 |
## reconsume |
## reconsume |
| 886 |
|
|
| 887 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 889 |
redo A; |
redo A; |
| 890 |
} else { |
} else { |
| 891 |
$self->{current_attribute}->{value} .= chr ($self->{next_input_character}); |
$self->{current_attribute}->{value} .= chr ($self->{next_input_character}); |
| 892 |
$self->{state} = 'attribute value (unquoted)'; |
$self->{state} = ATTRIBUTE_VALUE_UNQUOTED_STATE; |
| 893 |
!!!next-input-character; |
!!!next-input-character; |
| 894 |
redo A; |
redo A; |
| 895 |
} |
} |
| 896 |
} elsif ($self->{state} eq 'attribute value (double-quoted)') { |
} elsif ($self->{state} == ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE) { |
| 897 |
if ($self->{next_input_character} == 0x0022) { # " |
if ($self->{next_input_character} == 0x0022) { # " |
| 898 |
$self->{state} = 'before attribute name'; |
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
| 899 |
!!!next-input-character; |
!!!next-input-character; |
| 900 |
redo A; |
redo A; |
| 901 |
} elsif ($self->{next_input_character} == 0x0026) { # & |
} elsif ($self->{next_input_character} == 0x0026) { # & |
| 902 |
$self->{last_attribute_value_state} = 'attribute value (double-quoted)'; |
$self->{last_attribute_value_state} = $self->{state}; |
| 903 |
$self->{state} = 'entity in attribute value'; |
$self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE; |
| 904 |
!!!next-input-character; |
!!!next-input-character; |
| 905 |
redo A; |
redo A; |
| 906 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 907 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
| 908 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 909 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 910 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 911 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 912 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 913 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 914 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 915 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 917 |
} else { |
} else { |
| 918 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 919 |
} |
} |
| 920 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 921 |
## reconsume |
## reconsume |
| 922 |
|
|
| 923 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 929 |
!!!next-input-character; |
!!!next-input-character; |
| 930 |
redo A; |
redo A; |
| 931 |
} |
} |
| 932 |
} elsif ($self->{state} eq 'attribute value (single-quoted)') { |
} elsif ($self->{state} == ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE) { |
| 933 |
if ($self->{next_input_character} == 0x0027) { # ' |
if ($self->{next_input_character} == 0x0027) { # ' |
| 934 |
$self->{state} = 'before attribute name'; |
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
| 935 |
!!!next-input-character; |
!!!next-input-character; |
| 936 |
redo A; |
redo A; |
| 937 |
} elsif ($self->{next_input_character} == 0x0026) { # & |
} elsif ($self->{next_input_character} == 0x0026) { # & |
| 938 |
$self->{last_attribute_value_state} = 'attribute value (single-quoted)'; |
$self->{last_attribute_value_state} = $self->{state}; |
| 939 |
$self->{state} = 'entity in attribute value'; |
$self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE; |
| 940 |
!!!next-input-character; |
!!!next-input-character; |
| 941 |
redo A; |
redo A; |
| 942 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 943 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
| 944 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 945 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 946 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 947 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 948 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 949 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 950 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 951 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 953 |
} else { |
} else { |
| 954 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 955 |
} |
} |
| 956 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 957 |
## reconsume |
## reconsume |
| 958 |
|
|
| 959 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 965 |
!!!next-input-character; |
!!!next-input-character; |
| 966 |
redo A; |
redo A; |
| 967 |
} |
} |
| 968 |
} elsif ($self->{state} eq 'attribute value (unquoted)') { |
} elsif ($self->{state} == ATTRIBUTE_VALUE_UNQUOTED_STATE) { |
| 969 |
if ($self->{next_input_character} == 0x0009 or # HT |
if ($self->{next_input_character} == 0x0009 or # HT |
| 970 |
$self->{next_input_character} == 0x000A or # LF |
$self->{next_input_character} == 0x000A or # LF |
| 971 |
$self->{next_input_character} == 0x000B or # HT |
$self->{next_input_character} == 0x000B or # HT |
| 972 |
$self->{next_input_character} == 0x000C or # FF |
$self->{next_input_character} == 0x000C or # FF |
| 973 |
$self->{next_input_character} == 0x0020) { # SP |
$self->{next_input_character} == 0x0020) { # SP |
| 974 |
$self->{state} = 'before attribute name'; |
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
| 975 |
!!!next-input-character; |
!!!next-input-character; |
| 976 |
redo A; |
redo A; |
| 977 |
} elsif ($self->{next_input_character} == 0x0026) { # & |
} elsif ($self->{next_input_character} == 0x0026) { # & |
| 978 |
$self->{last_attribute_value_state} = 'attribute value (unquoted)'; |
$self->{last_attribute_value_state} = $self->{state}; |
| 979 |
$self->{state} = 'entity in attribute value'; |
$self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE; |
| 980 |
!!!next-input-character; |
!!!next-input-character; |
| 981 |
redo A; |
redo A; |
| 982 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 983 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 984 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 985 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 986 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 987 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 988 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 989 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 990 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 992 |
} else { |
} else { |
| 993 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 994 |
} |
} |
| 995 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 996 |
!!!next-input-character; |
!!!next-input-character; |
| 997 |
|
|
| 998 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 1000 |
redo A; |
redo A; |
| 1001 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1002 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 1003 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1004 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 1005 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 1006 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1007 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1008 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1009 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 1010 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 1012 |
} else { |
} else { |
| 1013 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 1014 |
} |
} |
| 1015 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1016 |
## reconsume |
## reconsume |
| 1017 |
|
|
| 1018 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 1024 |
!!!next-input-character; |
!!!next-input-character; |
| 1025 |
redo A; |
redo A; |
| 1026 |
} |
} |
| 1027 |
} elsif ($self->{state} eq 'entity in attribute value') { |
} elsif ($self->{state} == ENTITY_IN_ATTRIBUTE_VALUE_STATE) { |
| 1028 |
my $token = $self->_tokenize_attempt_to_consume_an_entity (1); |
my $token = $self->_tokenize_attempt_to_consume_an_entity (1); |
| 1029 |
|
|
| 1030 |
unless (defined $token) { |
unless (defined $token) { |
| 1037 |
$self->{state} = $self->{last_attribute_value_state}; |
$self->{state} = $self->{last_attribute_value_state}; |
| 1038 |
# next-input-character is already done |
# next-input-character is already done |
| 1039 |
redo A; |
redo A; |
| 1040 |
} elsif ($self->{state} eq 'bogus comment') { |
} elsif ($self->{state} == BOGUS_COMMENT_STATE) { |
| 1041 |
## (only happen if PCDATA state) |
## (only happen if PCDATA state) |
| 1042 |
|
|
| 1043 |
my $token = {type => 'comment', data => ''}; |
my $token = {type => COMMENT_TOKEN, data => ''}; |
| 1044 |
|
|
| 1045 |
BC: { |
BC: { |
| 1046 |
if ($self->{next_input_character} == 0x003E) { # > |
if ($self->{next_input_character} == 0x003E) { # > |
| 1047 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1048 |
!!!next-input-character; |
!!!next-input-character; |
| 1049 |
|
|
| 1050 |
!!!emit ($token); |
!!!emit ($token); |
| 1051 |
|
|
| 1052 |
redo A; |
redo A; |
| 1053 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1054 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1055 |
## reconsume |
## reconsume |
| 1056 |
|
|
| 1057 |
!!!emit ($token); |
!!!emit ($token); |
| 1063 |
redo BC; |
redo BC; |
| 1064 |
} |
} |
| 1065 |
} # BC |
} # BC |
| 1066 |
} elsif ($self->{state} eq 'markup declaration open') { |
} elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) { |
| 1067 |
## (only happen if PCDATA state) |
## (only happen if PCDATA state) |
| 1068 |
|
|
| 1069 |
my @next_char; |
my @next_char; |
| 1073 |
!!!next-input-character; |
!!!next-input-character; |
| 1074 |
push @next_char, $self->{next_input_character}; |
push @next_char, $self->{next_input_character}; |
| 1075 |
if ($self->{next_input_character} == 0x002D) { # - |
if ($self->{next_input_character} == 0x002D) { # - |
| 1076 |
$self->{current_token} = {type => 'comment', data => ''}; |
$self->{current_token} = {type => COMMENT_TOKEN, data => ''}; |
| 1077 |
$self->{state} = 'comment start'; |
$self->{state} = COMMENT_START_STATE; |
| 1078 |
!!!next-input-character; |
!!!next-input-character; |
| 1079 |
redo A; |
redo A; |
| 1080 |
} |
} |
| 1105 |
if ($self->{next_input_character} == 0x0045 or # E |
if ($self->{next_input_character} == 0x0045 or # E |
| 1106 |
$self->{next_input_character} == 0x0065) { # e |
$self->{next_input_character} == 0x0065) { # e |
| 1107 |
## ISSUE: What a stupid code this is! |
## ISSUE: What a stupid code this is! |
| 1108 |
$self->{state} = 'DOCTYPE'; |
$self->{state} = DOCTYPE_STATE; |
| 1109 |
!!!next-input-character; |
!!!next-input-character; |
| 1110 |
redo A; |
redo A; |
| 1111 |
} |
} |
| 1119 |
!!!parse-error (type => 'bogus comment'); |
!!!parse-error (type => 'bogus comment'); |
| 1120 |
$self->{next_input_character} = shift @next_char; |
$self->{next_input_character} = shift @next_char; |
| 1121 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 1122 |
$self->{state} = 'bogus comment'; |
$self->{state} = BOGUS_COMMENT_STATE; |
| 1123 |
redo A; |
redo A; |
| 1124 |
|
|
| 1125 |
## ISSUE: typos in spec: chacacters, is is a parse error |
## ISSUE: typos in spec: chacacters, is is a parse error |
| 1126 |
## ISSUE: spec is somewhat unclear on "is the first character that will be in the comment"; what is "that will be in the comment" is what the algorithm defines, isn't it? |
## ISSUE: spec is somewhat unclear on "is the first character that will be in the comment"; what is "that will be in the comment" is what the algorithm defines, isn't it? |
| 1127 |
} elsif ($self->{state} eq 'comment start') { |
} elsif ($self->{state} == COMMENT_START_STATE) { |
| 1128 |
if ($self->{next_input_character} == 0x002D) { # - |
if ($self->{next_input_character} == 0x002D) { # - |
| 1129 |
$self->{state} = 'comment start dash'; |
$self->{state} = COMMENT_START_DASH_STATE; |
| 1130 |
!!!next-input-character; |
!!!next-input-character; |
| 1131 |
redo A; |
redo A; |
| 1132 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1133 |
!!!parse-error (type => 'bogus comment'); |
!!!parse-error (type => 'bogus comment'); |
| 1134 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1135 |
!!!next-input-character; |
!!!next-input-character; |
| 1136 |
|
|
| 1137 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
| 1139 |
redo A; |
redo A; |
| 1140 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1141 |
!!!parse-error (type => 'unclosed comment'); |
!!!parse-error (type => 'unclosed comment'); |
| 1142 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1143 |
## reconsume |
## reconsume |
| 1144 |
|
|
| 1145 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
| 1148 |
} else { |
} else { |
| 1149 |
$self->{current_token}->{data} # comment |
$self->{current_token}->{data} # comment |
| 1150 |
.= chr ($self->{next_input_character}); |
.= chr ($self->{next_input_character}); |
| 1151 |
$self->{state} = 'comment'; |
$self->{state} = COMMENT_STATE; |
| 1152 |
!!!next-input-character; |
!!!next-input-character; |
| 1153 |
redo A; |
redo A; |
| 1154 |
} |
} |
| 1155 |
} elsif ($self->{state} eq 'comment start dash') { |
} elsif ($self->{state} == COMMENT_START_DASH_STATE) { |
| 1156 |
if ($self->{next_input_character} == 0x002D) { # - |
if ($self->{next_input_character} == 0x002D) { # - |
| 1157 |
$self->{state} = 'comment end'; |
$self->{state} = COMMENT_END_STATE; |
| 1158 |
!!!next-input-character; |
!!!next-input-character; |
| 1159 |
redo A; |
redo A; |
| 1160 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1161 |
!!!parse-error (type => 'bogus comment'); |
!!!parse-error (type => 'bogus comment'); |
| 1162 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1163 |
!!!next-input-character; |
!!!next-input-character; |
| 1164 |
|
|
| 1165 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
| 1167 |
redo A; |
redo A; |
| 1168 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1169 |
!!!parse-error (type => 'unclosed comment'); |
!!!parse-error (type => 'unclosed comment'); |
| 1170 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1171 |
## reconsume |
## reconsume |
| 1172 |
|
|
| 1173 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
| 1176 |
} else { |
} else { |
| 1177 |
$self->{current_token}->{data} # comment |
$self->{current_token}->{data} # comment |
| 1178 |
.= '-' . chr ($self->{next_input_character}); |
.= '-' . chr ($self->{next_input_character}); |
| 1179 |
$self->{state} = 'comment'; |
$self->{state} = COMMENT_STATE; |
| 1180 |
!!!next-input-character; |
!!!next-input-character; |
| 1181 |
redo A; |
redo A; |
| 1182 |
} |
} |
| 1183 |
} elsif ($self->{state} eq 'comment') { |
} elsif ($self->{state} == COMMENT_STATE) { |
| 1184 |
if ($self->{next_input_character} == 0x002D) { # - |
if ($self->{next_input_character} == 0x002D) { # - |
| 1185 |
$self->{state} = 'comment end dash'; |
$self->{state} = COMMENT_END_DASH_STATE; |
| 1186 |
!!!next-input-character; |
!!!next-input-character; |
| 1187 |
redo A; |
redo A; |
| 1188 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1189 |
!!!parse-error (type => 'unclosed comment'); |
!!!parse-error (type => 'unclosed comment'); |
| 1190 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1191 |
## reconsume |
## reconsume |
| 1192 |
|
|
| 1193 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
| 1199 |
!!!next-input-character; |
!!!next-input-character; |
| 1200 |
redo A; |
redo A; |
| 1201 |
} |
} |
| 1202 |
} elsif ($self->{state} eq 'comment end dash') { |
} elsif ($self->{state} == COMMENT_END_DASH_STATE) { |
| 1203 |
if ($self->{next_input_character} == 0x002D) { # - |
if ($self->{next_input_character} == 0x002D) { # - |
| 1204 |
$self->{state} = 'comment end'; |
$self->{state} = COMMENT_END_STATE; |
| 1205 |
!!!next-input-character; |
!!!next-input-character; |
| 1206 |
redo A; |
redo A; |
| 1207 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1208 |
!!!parse-error (type => 'unclosed comment'); |
!!!parse-error (type => 'unclosed comment'); |
| 1209 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1210 |
## reconsume |
## reconsume |
| 1211 |
|
|
| 1212 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
| 1214 |
redo A; |
redo A; |
| 1215 |
} else { |
} else { |
| 1216 |
$self->{current_token}->{data} .= '-' . chr ($self->{next_input_character}); # comment |
$self->{current_token}->{data} .= '-' . chr ($self->{next_input_character}); # comment |
| 1217 |
$self->{state} = 'comment'; |
$self->{state} = COMMENT_STATE; |
| 1218 |
!!!next-input-character; |
!!!next-input-character; |
| 1219 |
redo A; |
redo A; |
| 1220 |
} |
} |
| 1221 |
} elsif ($self->{state} eq 'comment end') { |
} elsif ($self->{state} == COMMENT_END_STATE) { |
| 1222 |
if ($self->{next_input_character} == 0x003E) { # > |
if ($self->{next_input_character} == 0x003E) { # > |
| 1223 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1224 |
!!!next-input-character; |
!!!next-input-character; |
| 1225 |
|
|
| 1226 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
| 1234 |
redo A; |
redo A; |
| 1235 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1236 |
!!!parse-error (type => 'unclosed comment'); |
!!!parse-error (type => 'unclosed comment'); |
| 1237 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1238 |
## reconsume |
## reconsume |
| 1239 |
|
|
| 1240 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
| 1243 |
} else { |
} else { |
| 1244 |
!!!parse-error (type => 'dash in comment'); |
!!!parse-error (type => 'dash in comment'); |
| 1245 |
$self->{current_token}->{data} .= '--' . chr ($self->{next_input_character}); # comment |
$self->{current_token}->{data} .= '--' . chr ($self->{next_input_character}); # comment |
| 1246 |
$self->{state} = 'comment'; |
$self->{state} = COMMENT_STATE; |
| 1247 |
!!!next-input-character; |
!!!next-input-character; |
| 1248 |
redo A; |
redo A; |
| 1249 |
} |
} |
| 1250 |
} elsif ($self->{state} eq 'DOCTYPE') { |
} elsif ($self->{state} == DOCTYPE_STATE) { |
| 1251 |
if ($self->{next_input_character} == 0x0009 or # HT |
if ($self->{next_input_character} == 0x0009 or # HT |
| 1252 |
$self->{next_input_character} == 0x000A or # LF |
$self->{next_input_character} == 0x000A or # LF |
| 1253 |
$self->{next_input_character} == 0x000B or # VT |
$self->{next_input_character} == 0x000B or # VT |
| 1254 |
$self->{next_input_character} == 0x000C or # FF |
$self->{next_input_character} == 0x000C or # FF |
| 1255 |
$self->{next_input_character} == 0x0020) { # SP |
$self->{next_input_character} == 0x0020) { # SP |
| 1256 |
$self->{state} = 'before DOCTYPE name'; |
$self->{state} = BEFORE_DOCTYPE_NAME_STATE; |
| 1257 |
!!!next-input-character; |
!!!next-input-character; |
| 1258 |
redo A; |
redo A; |
| 1259 |
} else { |
} else { |
| 1260 |
!!!parse-error (type => 'no space before DOCTYPE name'); |
!!!parse-error (type => 'no space before DOCTYPE name'); |
| 1261 |
$self->{state} = 'before DOCTYPE name'; |
$self->{state} = BEFORE_DOCTYPE_NAME_STATE; |
| 1262 |
## reconsume |
## reconsume |
| 1263 |
redo A; |
redo A; |
| 1264 |
} |
} |
| 1265 |
} elsif ($self->{state} eq 'before DOCTYPE name') { |
} elsif ($self->{state} == BEFORE_DOCTYPE_NAME_STATE) { |
| 1266 |
if ($self->{next_input_character} == 0x0009 or # HT |
if ($self->{next_input_character} == 0x0009 or # HT |
| 1267 |
$self->{next_input_character} == 0x000A or # LF |
$self->{next_input_character} == 0x000A or # LF |
| 1268 |
$self->{next_input_character} == 0x000B or # VT |
$self->{next_input_character} == 0x000B or # VT |
| 1273 |
redo A; |
redo A; |
| 1274 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1275 |
!!!parse-error (type => 'no DOCTYPE name'); |
!!!parse-error (type => 'no DOCTYPE name'); |
| 1276 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1277 |
!!!next-input-character; |
!!!next-input-character; |
| 1278 |
|
|
| 1279 |
!!!emit ({type => 'DOCTYPE'}); # incorrect |
!!!emit ({type => DOCTYPE_TOKEN}); # incorrect |
| 1280 |
|
|
| 1281 |
redo A; |
redo A; |
| 1282 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1283 |
!!!parse-error (type => 'no DOCTYPE name'); |
!!!parse-error (type => 'no DOCTYPE name'); |
| 1284 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1285 |
## reconsume |
## reconsume |
| 1286 |
|
|
| 1287 |
!!!emit ({type => 'DOCTYPE'}); # incorrect |
!!!emit ({type => DOCTYPE_TOKEN}); # incorrect |
| 1288 |
|
|
| 1289 |
redo A; |
redo A; |
| 1290 |
} else { |
} else { |
| 1291 |
$self->{current_token} |
$self->{current_token} |
| 1292 |
= {type => 'DOCTYPE', |
= {type => DOCTYPE_TOKEN, |
| 1293 |
name => chr ($self->{next_input_character}), |
name => chr ($self->{next_input_character}), |
| 1294 |
correct => 1}; |
correct => 1}; |
| 1295 |
## ISSUE: "Set the token's name name to the" in the spec |
## ISSUE: "Set the token's name name to the" in the spec |
| 1296 |
$self->{state} = 'DOCTYPE name'; |
$self->{state} = DOCTYPE_NAME_STATE; |
| 1297 |
!!!next-input-character; |
!!!next-input-character; |
| 1298 |
redo A; |
redo A; |
| 1299 |
} |
} |
| 1300 |
} elsif ($self->{state} eq 'DOCTYPE name') { |
} elsif ($self->{state} == DOCTYPE_NAME_STATE) { |
| 1301 |
## ISSUE: Redundant "First," in the spec. |
## ISSUE: Redundant "First," in the spec. |
| 1302 |
if ($self->{next_input_character} == 0x0009 or # HT |
if ($self->{next_input_character} == 0x0009 or # HT |
| 1303 |
$self->{next_input_character} == 0x000A or # LF |
$self->{next_input_character} == 0x000A or # LF |
| 1304 |
$self->{next_input_character} == 0x000B or # VT |
$self->{next_input_character} == 0x000B or # VT |
| 1305 |
$self->{next_input_character} == 0x000C or # FF |
$self->{next_input_character} == 0x000C or # FF |
| 1306 |
$self->{next_input_character} == 0x0020) { # SP |
$self->{next_input_character} == 0x0020) { # SP |
| 1307 |
$self->{state} = 'after DOCTYPE name'; |
$self->{state} = AFTER_DOCTYPE_NAME_STATE; |
| 1308 |
!!!next-input-character; |
!!!next-input-character; |
| 1309 |
redo A; |
redo A; |
| 1310 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1311 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1312 |
!!!next-input-character; |
!!!next-input-character; |
| 1313 |
|
|
| 1314 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
| 1316 |
redo A; |
redo A; |
| 1317 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1318 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1319 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1320 |
## reconsume |
## reconsume |
| 1321 |
|
|
| 1322 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1330 |
!!!next-input-character; |
!!!next-input-character; |
| 1331 |
redo A; |
redo A; |
| 1332 |
} |
} |
| 1333 |
} elsif ($self->{state} eq 'after DOCTYPE name') { |
} elsif ($self->{state} == AFTER_DOCTYPE_NAME_STATE) { |
| 1334 |
if ($self->{next_input_character} == 0x0009 or # HT |
if ($self->{next_input_character} == 0x0009 or # HT |
| 1335 |
$self->{next_input_character} == 0x000A or # LF |
$self->{next_input_character} == 0x000A or # LF |
| 1336 |
$self->{next_input_character} == 0x000B or # VT |
$self->{next_input_character} == 0x000B or # VT |
| 1340 |
!!!next-input-character; |
!!!next-input-character; |
| 1341 |
redo A; |
redo A; |
| 1342 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1343 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1344 |
!!!next-input-character; |
!!!next-input-character; |
| 1345 |
|
|
| 1346 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
| 1348 |
redo A; |
redo A; |
| 1349 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1350 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1351 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1352 |
## reconsume |
## reconsume |
| 1353 |
|
|
| 1354 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1372 |
!!!next-input-character; |
!!!next-input-character; |
| 1373 |
if ($self->{next_input_character} == 0x0043 or # C |
if ($self->{next_input_character} == 0x0043 or # C |
| 1374 |
$self->{next_input_character} == 0x0063) { # c |
$self->{next_input_character} == 0x0063) { # c |
| 1375 |
$self->{state} = 'before DOCTYPE public identifier'; |
$self->{state} = BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE; |
| 1376 |
!!!next-input-character; |
!!!next-input-character; |
| 1377 |
redo A; |
redo A; |
| 1378 |
} |
} |
| 1399 |
!!!next-input-character; |
!!!next-input-character; |
| 1400 |
if ($self->{next_input_character} == 0x004D or # M |
if ($self->{next_input_character} == 0x004D or # M |
| 1401 |
$self->{next_input_character} == 0x006D) { # m |
$self->{next_input_character} == 0x006D) { # m |
| 1402 |
$self->{state} = 'before DOCTYPE system identifier'; |
$self->{state} = BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE; |
| 1403 |
!!!next-input-character; |
!!!next-input-character; |
| 1404 |
redo A; |
redo A; |
| 1405 |
} |
} |
| 1415 |
} |
} |
| 1416 |
|
|
| 1417 |
!!!parse-error (type => 'string after DOCTYPE name'); |
!!!parse-error (type => 'string after DOCTYPE name'); |
| 1418 |
$self->{state} = 'bogus DOCTYPE'; |
$self->{state} = BOGUS_DOCTYPE_STATE; |
| 1419 |
# next-input-character is already done |
# next-input-character is already done |
| 1420 |
redo A; |
redo A; |
| 1421 |
} elsif ($self->{state} eq 'before DOCTYPE public identifier') { |
} elsif ($self->{state} == BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE) { |
| 1422 |
if ({ |
if ({ |
| 1423 |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
| 1424 |
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
| 1428 |
redo A; |
redo A; |
| 1429 |
} elsif ($self->{next_input_character} eq 0x0022) { # " |
} elsif ($self->{next_input_character} eq 0x0022) { # " |
| 1430 |
$self->{current_token}->{public_identifier} = ''; # DOCTYPE |
$self->{current_token}->{public_identifier} = ''; # DOCTYPE |
| 1431 |
$self->{state} = 'DOCTYPE public identifier (double-quoted)'; |
$self->{state} = DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE; |
| 1432 |
!!!next-input-character; |
!!!next-input-character; |
| 1433 |
redo A; |
redo A; |
| 1434 |
} elsif ($self->{next_input_character} eq 0x0027) { # ' |
} elsif ($self->{next_input_character} eq 0x0027) { # ' |
| 1435 |
$self->{current_token}->{public_identifier} = ''; # DOCTYPE |
$self->{current_token}->{public_identifier} = ''; # DOCTYPE |
| 1436 |
$self->{state} = 'DOCTYPE public identifier (single-quoted)'; |
$self->{state} = DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE; |
| 1437 |
!!!next-input-character; |
!!!next-input-character; |
| 1438 |
redo A; |
redo A; |
| 1439 |
} elsif ($self->{next_input_character} eq 0x003E) { # > |
} elsif ($self->{next_input_character} eq 0x003E) { # > |
| 1440 |
!!!parse-error (type => 'no PUBLIC literal'); |
!!!parse-error (type => 'no PUBLIC literal'); |
| 1441 |
|
|
| 1442 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1443 |
!!!next-input-character; |
!!!next-input-character; |
| 1444 |
|
|
| 1445 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1449 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1450 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1451 |
|
|
| 1452 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1453 |
## reconsume |
## reconsume |
| 1454 |
|
|
| 1455 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1458 |
redo A; |
redo A; |
| 1459 |
} else { |
} else { |
| 1460 |
!!!parse-error (type => 'string after PUBLIC'); |
!!!parse-error (type => 'string after PUBLIC'); |
| 1461 |
$self->{state} = 'bogus DOCTYPE'; |
$self->{state} = BOGUS_DOCTYPE_STATE; |
| 1462 |
!!!next-input-character; |
!!!next-input-character; |
| 1463 |
redo A; |
redo A; |
| 1464 |
} |
} |
| 1465 |
} elsif ($self->{state} eq 'DOCTYPE public identifier (double-quoted)') { |
} elsif ($self->{state} == DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE) { |
| 1466 |
if ($self->{next_input_character} == 0x0022) { # " |
if ($self->{next_input_character} == 0x0022) { # " |
| 1467 |
$self->{state} = 'after DOCTYPE public identifier'; |
$self->{state} = AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE; |
| 1468 |
!!!next-input-character; |
!!!next-input-character; |
| 1469 |
redo A; |
redo A; |
| 1470 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1471 |
!!!parse-error (type => 'unclosed PUBLIC literal'); |
!!!parse-error (type => 'unclosed PUBLIC literal'); |
| 1472 |
|
|
| 1473 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1474 |
## reconsume |
## reconsume |
| 1475 |
|
|
| 1476 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1484 |
!!!next-input-character; |
!!!next-input-character; |
| 1485 |
redo A; |
redo A; |
| 1486 |
} |
} |
| 1487 |
} elsif ($self->{state} eq 'DOCTYPE public identifier (single-quoted)') { |
} elsif ($self->{state} == DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE) { |
| 1488 |
if ($self->{next_input_character} == 0x0027) { # ' |
if ($self->{next_input_character} == 0x0027) { # ' |
| 1489 |
$self->{state} = 'after DOCTYPE public identifier'; |
$self->{state} = AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE; |
| 1490 |
!!!next-input-character; |
!!!next-input-character; |
| 1491 |
redo A; |
redo A; |
| 1492 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1493 |
!!!parse-error (type => 'unclosed PUBLIC literal'); |
!!!parse-error (type => 'unclosed PUBLIC literal'); |
| 1494 |
|
|
| 1495 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1496 |
## reconsume |
## reconsume |
| 1497 |
|
|
| 1498 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1506 |
!!!next-input-character; |
!!!next-input-character; |
| 1507 |
redo A; |
redo A; |
| 1508 |
} |
} |
| 1509 |
} elsif ($self->{state} eq 'after DOCTYPE public identifier') { |
} elsif ($self->{state} == AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE) { |
| 1510 |
if ({ |
if ({ |
| 1511 |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
| 1512 |
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
| 1516 |
redo A; |
redo A; |
| 1517 |
} elsif ($self->{next_input_character} == 0x0022) { # " |
} elsif ($self->{next_input_character} == 0x0022) { # " |
| 1518 |
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
| 1519 |
$self->{state} = 'DOCTYPE system identifier (double-quoted)'; |
$self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE; |
| 1520 |
!!!next-input-character; |
!!!next-input-character; |
| 1521 |
redo A; |
redo A; |
| 1522 |
} elsif ($self->{next_input_character} == 0x0027) { # ' |
} elsif ($self->{next_input_character} == 0x0027) { # ' |
| 1523 |
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
| 1524 |
$self->{state} = 'DOCTYPE system identifier (single-quoted)'; |
$self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE; |
| 1525 |
!!!next-input-character; |
!!!next-input-character; |
| 1526 |
redo A; |
redo A; |
| 1527 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1528 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1529 |
!!!next-input-character; |
!!!next-input-character; |
| 1530 |
|
|
| 1531 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
| 1534 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1535 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1536 |
|
|
| 1537 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1538 |
## reconsume |
## reconsume |
| 1539 |
|
|
| 1540 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1543 |
redo A; |
redo A; |
| 1544 |
} else { |
} else { |
| 1545 |
!!!parse-error (type => 'string after PUBLIC literal'); |
!!!parse-error (type => 'string after PUBLIC literal'); |
| 1546 |
$self->{state} = 'bogus DOCTYPE'; |
$self->{state} = BOGUS_DOCTYPE_STATE; |
| 1547 |
!!!next-input-character; |
!!!next-input-character; |
| 1548 |
redo A; |
redo A; |
| 1549 |
} |
} |
| 1550 |
} elsif ($self->{state} eq 'before DOCTYPE system identifier') { |
} elsif ($self->{state} == BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE) { |
| 1551 |
if ({ |
if ({ |
| 1552 |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
| 1553 |
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
| 1557 |
redo A; |
redo A; |
| 1558 |
} elsif ($self->{next_input_character} == 0x0022) { # " |
} elsif ($self->{next_input_character} == 0x0022) { # " |
| 1559 |
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
| 1560 |
$self->{state} = 'DOCTYPE system identifier (double-quoted)'; |
$self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE; |
| 1561 |
!!!next-input-character; |
!!!next-input-character; |
| 1562 |
redo A; |
redo A; |
| 1563 |
} elsif ($self->{next_input_character} == 0x0027) { # ' |
} elsif ($self->{next_input_character} == 0x0027) { # ' |
| 1564 |
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
| 1565 |
$self->{state} = 'DOCTYPE system identifier (single-quoted)'; |
$self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE; |
| 1566 |
!!!next-input-character; |
!!!next-input-character; |
| 1567 |
redo A; |
redo A; |
| 1568 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1569 |
!!!parse-error (type => 'no SYSTEM literal'); |
!!!parse-error (type => 'no SYSTEM literal'); |
| 1570 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1571 |
!!!next-input-character; |
!!!next-input-character; |
| 1572 |
|
|
| 1573 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1577 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1578 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1579 |
|
|
| 1580 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1581 |
## reconsume |
## reconsume |
| 1582 |
|
|
| 1583 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1586 |
redo A; |
redo A; |
| 1587 |
} else { |
} else { |
| 1588 |
!!!parse-error (type => 'string after SYSTEM'); |
!!!parse-error (type => 'string after SYSTEM'); |
| 1589 |
$self->{state} = 'bogus DOCTYPE'; |
$self->{state} = BOGUS_DOCTYPE_STATE; |
| 1590 |
!!!next-input-character; |
!!!next-input-character; |
| 1591 |
redo A; |
redo A; |
| 1592 |
} |
} |
| 1593 |
} elsif ($self->{state} eq 'DOCTYPE system identifier (double-quoted)') { |
} elsif ($self->{state} == DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE) { |
| 1594 |
if ($self->{next_input_character} == 0x0022) { # " |
if ($self->{next_input_character} == 0x0022) { # " |
| 1595 |
$self->{state} = 'after DOCTYPE system identifier'; |
$self->{state} = AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE; |
| 1596 |
!!!next-input-character; |
!!!next-input-character; |
| 1597 |
redo A; |
redo A; |
| 1598 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1599 |
!!!parse-error (type => 'unclosed SYSTEM literal'); |
!!!parse-error (type => 'unclosed SYSTEM literal'); |
| 1600 |
|
|
| 1601 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1602 |
## reconsume |
## reconsume |
| 1603 |
|
|
| 1604 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1612 |
!!!next-input-character; |
!!!next-input-character; |
| 1613 |
redo A; |
redo A; |
| 1614 |
} |
} |
| 1615 |
} elsif ($self->{state} eq 'DOCTYPE system identifier (single-quoted)') { |
} elsif ($self->{state} == DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE) { |
| 1616 |
if ($self->{next_input_character} == 0x0027) { # ' |
if ($self->{next_input_character} == 0x0027) { # ' |
| 1617 |
$self->{state} = 'after DOCTYPE system identifier'; |
$self->{state} = AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE; |
| 1618 |
!!!next-input-character; |
!!!next-input-character; |
| 1619 |
redo A; |
redo A; |
| 1620 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1621 |
!!!parse-error (type => 'unclosed SYSTEM literal'); |
!!!parse-error (type => 'unclosed SYSTEM literal'); |
| 1622 |
|
|
| 1623 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1624 |
## reconsume |
## reconsume |
| 1625 |
|
|
| 1626 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1634 |
!!!next-input-character; |
!!!next-input-character; |
| 1635 |
redo A; |
redo A; |
| 1636 |
} |
} |
| 1637 |
} elsif ($self->{state} eq 'after DOCTYPE system identifier') { |
} elsif ($self->{state} == AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE) { |
| 1638 |
if ({ |
if ({ |
| 1639 |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
| 1640 |
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
| 1643 |
!!!next-input-character; |
!!!next-input-character; |
| 1644 |
redo A; |
redo A; |
| 1645 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1646 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1647 |
!!!next-input-character; |
!!!next-input-character; |
| 1648 |
|
|
| 1649 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
| 1652 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1653 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1654 |
|
|
| 1655 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1656 |
## reconsume |
## reconsume |
| 1657 |
|
|
| 1658 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1661 |
redo A; |
redo A; |
| 1662 |
} else { |
} else { |
| 1663 |
!!!parse-error (type => 'string after SYSTEM literal'); |
!!!parse-error (type => 'string after SYSTEM literal'); |
| 1664 |
$self->{state} = 'bogus DOCTYPE'; |
$self->{state} = BOGUS_DOCTYPE_STATE; |
| 1665 |
!!!next-input-character; |
!!!next-input-character; |
| 1666 |
redo A; |
redo A; |
| 1667 |
} |
} |
| 1668 |
} elsif ($self->{state} eq 'bogus DOCTYPE') { |
} elsif ($self->{state} == BOGUS_DOCTYPE_STATE) { |
| 1669 |
if ($self->{next_input_character} == 0x003E) { # > |
if ($self->{next_input_character} == 0x003E) { # > |
| 1670 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1671 |
!!!next-input-character; |
!!!next-input-character; |
| 1672 |
|
|
| 1673 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1676 |
redo A; |
redo A; |
| 1677 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1678 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1679 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1680 |
## reconsume |
## reconsume |
| 1681 |
|
|
| 1682 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1757 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 1758 |
} |
} |
| 1759 |
|
|
| 1760 |
return {type => 'character', data => chr $code}; |
return {type => CHARACTER_TOKEN, data => chr $code}; |
| 1761 |
} # X |
} # X |
| 1762 |
} elsif (0x0030 <= $self->{next_input_character} and |
} elsif (0x0030 <= $self->{next_input_character} and |
| 1763 |
$self->{next_input_character} <= 0x0039) { # 0..9 |
$self->{next_input_character} <= 0x0039) { # 0..9 |
| 1792 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 1793 |
} |
} |
| 1794 |
|
|
| 1795 |
return {type => 'character', data => chr $code}; |
return {type => CHARACTER_TOKEN, data => chr $code}; |
| 1796 |
} else { |
} else { |
| 1797 |
!!!parse-error (type => 'bare nero'); |
!!!parse-error (type => 'bare nero'); |
| 1798 |
!!!back-next-input-character ($self->{next_input_character}); |
!!!back-next-input-character ($self->{next_input_character}); |
| 1840 |
} |
} |
| 1841 |
|
|
| 1842 |
if ($match > 0) { |
if ($match > 0) { |
| 1843 |
return {type => 'character', data => $value}; |
return {type => CHARACTER_TOKEN, data => $value}; |
| 1844 |
} elsif ($match < 0) { |
} elsif ($match < 0) { |
| 1845 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'no refc'); |
| 1846 |
if ($in_attr and $match < -1) { |
if ($in_attr and $match < -1) { |
| 1847 |
return {type => 'character', data => '&'.$entity_name}; |
return {type => CHARACTER_TOKEN, data => '&'.$entity_name}; |
| 1848 |
} else { |
} else { |
| 1849 |
return {type => 'character', data => $value}; |
return {type => CHARACTER_TOKEN, data => $value}; |
| 1850 |
} |
} |
| 1851 |
} else { |
} else { |
| 1852 |
!!!parse-error (type => 'bare ero'); |
!!!parse-error (type => 'bare ero'); |
| 1853 |
## NOTE: No characters are consumed in the spec. |
## NOTE: No characters are consumed in the spec. |
| 1854 |
return {type => 'character', data => '&'.$value}; |
return {type => CHARACTER_TOKEN, data => '&'.$value}; |
| 1855 |
} |
} |
| 1856 |
} else { |
} else { |
| 1857 |
## no characters are consumed |
## no characters are consumed |
| 1893 |
|
|
| 1894 |
!!!next-token; |
!!!next-token; |
| 1895 |
|
|
| 1896 |
$self->{insertion_mode} = 'before head'; |
$self->{insertion_mode} = BEFORE_HEAD_IM; |
| 1897 |
undef $self->{form_element}; |
undef $self->{form_element}; |
| 1898 |
undef $self->{head_element}; |
undef $self->{head_element}; |
| 1899 |
$self->{open_elements} = []; |
$self->{open_elements} = []; |
| 1907 |
sub _tree_construction_initial ($) { |
sub _tree_construction_initial ($) { |
| 1908 |
my $self = shift; |
my $self = shift; |
| 1909 |
INITIAL: { |
INITIAL: { |
| 1910 |
if ($token->{type} eq 'DOCTYPE') { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 1911 |
## NOTE: Conformance checkers MAY, instead of reporting "not HTML5" |
## NOTE: Conformance checkers MAY, instead of reporting "not HTML5" |
| 1912 |
## error, switch to a conformance checking mode for another |
## error, switch to a conformance checking mode for another |
| 1913 |
## language. |
## language. |
| 2034 |
!!!next-token; |
!!!next-token; |
| 2035 |
return; |
return; |
| 2036 |
} elsif ({ |
} elsif ({ |
| 2037 |
'start tag' => 1, |
START_TAG_TOKEN, 1, |
| 2038 |
'end tag' => 1, |
END_TAG_TOKEN, 1, |
| 2039 |
'end-of-file' => 1, |
END_OF_FILE_TOKEN, 1, |
| 2040 |
}->{$token->{type}}) { |
}->{$token->{type}}) { |
| 2041 |
!!!parse-error (type => 'no DOCTYPE'); |
!!!parse-error (type => 'no DOCTYPE'); |
| 2042 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 2043 |
## Go to the root element phase |
## Go to the root element phase |
| 2044 |
## reprocess |
## reprocess |
| 2045 |
return; |
return; |
| 2046 |
} elsif ($token->{type} eq 'character') { |
} elsif ($token->{type} == CHARACTER_TOKEN) { |
| 2047 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
| 2048 |
## Ignore the token |
## Ignore the token |
| 2049 |
|
|
| 2059 |
## Go to the root element phase |
## Go to the root element phase |
| 2060 |
## reprocess |
## reprocess |
| 2061 |
return; |
return; |
| 2062 |
} elsif ($token->{type} eq 'comment') { |
} elsif ($token->{type} == COMMENT_TOKEN) { |
| 2063 |
my $comment = $self->{document}->create_comment ($token->{data}); |
my $comment = $self->{document}->create_comment ($token->{data}); |
| 2064 |
$self->{document}->append_child ($comment); |
$self->{document}->append_child ($comment); |
| 2065 |
|
|
| 2067 |
!!!next-token; |
!!!next-token; |
| 2068 |
redo INITIAL; |
redo INITIAL; |
| 2069 |
} else { |
} else { |
| 2070 |
die "$0: $token->{type}: Unknown token"; |
die "$0: $token->{type}: Unknown token type"; |
| 2071 |
} |
} |
| 2072 |
} # INITIAL |
} # INITIAL |
| 2073 |
} # _tree_construction_initial |
} # _tree_construction_initial |
| 2076 |
my $self = shift; |
my $self = shift; |
| 2077 |
|
|
| 2078 |
B: { |
B: { |
| 2079 |
if ($token->{type} eq 'DOCTYPE') { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 2080 |
!!!parse-error (type => 'in html:#DOCTYPE'); |
!!!parse-error (type => 'in html:#DOCTYPE'); |
| 2081 |
## Ignore the token |
## Ignore the token |
| 2082 |
## Stay in the phase |
## Stay in the phase |
| 2083 |
!!!next-token; |
!!!next-token; |
| 2084 |
redo B; |
redo B; |
| 2085 |
} elsif ($token->{type} eq 'comment') { |
} elsif ($token->{type} == COMMENT_TOKEN) { |
| 2086 |
my $comment = $self->{document}->create_comment ($token->{data}); |
my $comment = $self->{document}->create_comment ($token->{data}); |
| 2087 |
$self->{document}->append_child ($comment); |
$self->{document}->append_child ($comment); |
| 2088 |
## Stay in the phase |
## Stay in the phase |
| 2089 |
!!!next-token; |
!!!next-token; |
| 2090 |
redo B; |
redo B; |
| 2091 |
} elsif ($token->{type} eq 'character') { |
} elsif ($token->{type} == CHARACTER_TOKEN) { |
| 2092 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
| 2093 |
## Ignore the token. |
## Ignore the token. |
| 2094 |
|
|
| 2098 |
redo B; |
redo B; |
| 2099 |
} |
} |
| 2100 |
} |
} |
| 2101 |
|
|
| 2102 |
|
$self->{application_cache_selection}->(undef); |
| 2103 |
|
|
| 2104 |
|
# |
| 2105 |
|
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 2106 |
|
if ($token->{tag_name} eq 'html' and |
| 2107 |
|
$token->{attributes}->{manifest}) { ## ISSUE: Spec spells as "application" |
| 2108 |
|
$self->{application_cache_selection} |
| 2109 |
|
->($token->{attributes}->{manifest}->{value}); |
| 2110 |
|
## ISSUE: No relative reference resolution? |
| 2111 |
|
} else { |
| 2112 |
|
$self->{application_cache_selection}->(undef); |
| 2113 |
|
} |
| 2114 |
|
|
| 2115 |
|
## ISSUE: There is an issue in the spec |
| 2116 |
# |
# |
| 2117 |
} elsif ({ |
} elsif ({ |
| 2118 |
'start tag' => 1, |
END_TAG_TOKEN, 1, |
| 2119 |
'end tag' => 1, |
END_OF_FILE_TOKEN, 1, |
|
'end-of-file' => 1, |
|
| 2120 |
}->{$token->{type}}) { |
}->{$token->{type}}) { |
| 2121 |
|
$self->{application_cache_selection}->(undef); |
| 2122 |
|
|
| 2123 |
## ISSUE: There is an issue in the spec |
## ISSUE: There is an issue in the spec |
| 2124 |
# |
# |
| 2125 |
} else { |
} else { |
| 2126 |
die "$0: $token->{type}: Unknown token"; |
die "$0: $token->{type}: Unknown token type"; |
| 2127 |
} |
} |
| 2128 |
|
|
| 2129 |
my $root_element; !!!create-element ($root_element, 'html'); |
my $root_element; !!!create-element ($root_element, 'html'); |
| 2130 |
$self->{document}->append_child ($root_element); |
$self->{document}->append_child ($root_element); |
| 2131 |
push @{$self->{open_elements}}, [$root_element, 'html']; |
push @{$self->{open_elements}}, [$root_element, 'html']; |
| 2166 |
|
|
| 2167 |
## Step 4..13 |
## Step 4..13 |
| 2168 |
my $new_mode = { |
my $new_mode = { |
| 2169 |
select => 'in select', |
select => IN_SELECT_IM, |
| 2170 |
td => 'in cell', |
td => IN_CELL_IM, |
| 2171 |
th => 'in cell', |
th => IN_CELL_IM, |
| 2172 |
tr => 'in row', |
tr => IN_ROW_IM, |
| 2173 |
tbody => 'in table body', |
tbody => IN_TABLE_BODY_IM, |
| 2174 |
thead => 'in table body', |
thead => IN_TABLE_BODY_IM, |
| 2175 |
tfoot => 'in table body', |
tfoot => IN_TABLE_BODY_IM, |
| 2176 |
caption => 'in caption', |
caption => IN_CAPTION_IM, |
| 2177 |
colgroup => 'in column group', |
colgroup => IN_COLUMN_GROUP_IM, |
| 2178 |
table => 'in table', |
table => IN_TABLE_IM, |
| 2179 |
head => 'in body', # not in head! |
head => IN_BODY_IM, # not in head! |
| 2180 |
body => 'in body', |
body => IN_BODY_IM, |
| 2181 |
frameset => 'in frameset', |
frameset => IN_FRAMESET_IM, |
| 2182 |
}->{$node->[1]}; |
}->{$node->[1]}; |
| 2183 |
$self->{insertion_mode} = $new_mode and return if defined $new_mode; |
$self->{insertion_mode} = $new_mode and return if defined $new_mode; |
| 2184 |
|
|
| 2185 |
## Step 14 |
## Step 14 |
| 2186 |
if ($node->[1] eq 'html') { |
if ($node->[1] eq 'html') { |
| 2187 |
unless (defined $self->{head_element}) { |
unless (defined $self->{head_element}) { |
| 2188 |
$self->{insertion_mode} = 'before head'; |
$self->{insertion_mode} = BEFORE_HEAD_IM; |
| 2189 |
} else { |
} else { |
| 2190 |
$self->{insertion_mode} = 'after head'; |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 2191 |
} |
} |
| 2192 |
return; |
return; |
| 2193 |
} |
} |
| 2194 |
|
|
| 2195 |
## Step 15 |
## Step 15 |
| 2196 |
$self->{insertion_mode} = 'in body' and return if $last; |
$self->{insertion_mode} = IN_BODY_IM and return if $last; |
| 2197 |
|
|
| 2198 |
## Step 16 |
## Step 16 |
| 2199 |
$i--; |
$i--; |
| 2207 |
sub _tree_construction_main ($) { |
sub _tree_construction_main ($) { |
| 2208 |
my $self = shift; |
my $self = shift; |
| 2209 |
|
|
|
my $previous_insertion_mode; |
|
|
|
|
| 2210 |
my $active_formatting_elements = []; |
my $active_formatting_elements = []; |
| 2211 |
|
|
| 2212 |
my $reconstruct_active_formatting_elements = sub { # MUST |
my $reconstruct_active_formatting_elements = sub { # MUST |
| 2307 |
## Step 4 |
## Step 4 |
| 2308 |
my $text = ''; |
my $text = ''; |
| 2309 |
!!!next-token; |
!!!next-token; |
| 2310 |
while ($token->{type} eq 'character') { # or until stop tokenizing |
while ($token->{type} == CHARACTER_TOKEN) { # or until stop tokenizing |
| 2311 |
$text .= $token->{data}; |
$text .= $token->{data}; |
| 2312 |
!!!next-token; |
!!!next-token; |
| 2313 |
} |
} |
| 2322 |
$self->{content_model} = PCDATA_CONTENT_MODEL; |
$self->{content_model} = PCDATA_CONTENT_MODEL; |
| 2323 |
|
|
| 2324 |
## Step 7 |
## Step 7 |
| 2325 |
if ($token->{type} eq 'end tag' and $token->{tag_name} eq $start_tag_name) { |
if ($token->{type} == END_TAG_TOKEN and $token->{tag_name} eq $start_tag_name) { |
| 2326 |
## Ignore the token |
## Ignore the token |
| 2327 |
} elsif ($content_model_flag == CDATA_CONTENT_MODEL) { |
} elsif ($content_model_flag == CDATA_CONTENT_MODEL) { |
| 2328 |
!!!parse-error (type => 'in CDATA:#'.$token->{type}); |
!!!parse-error (type => 'in CDATA:#'.$token->{type}); |
| 2345 |
|
|
| 2346 |
my $text = ''; |
my $text = ''; |
| 2347 |
!!!next-token; |
!!!next-token; |
| 2348 |
while ($token->{type} eq 'character') { |
while ($token->{type} == CHARACTER_TOKEN) { |
| 2349 |
$text .= $token->{data}; |
$text .= $token->{data}; |
| 2350 |
!!!next-token; |
!!!next-token; |
| 2351 |
} # stop if non-character token or tokenizer stops tokenising |
} # stop if non-character token or tokenizer stops tokenising |
| 2355 |
|
|
| 2356 |
$self->{content_model} = PCDATA_CONTENT_MODEL; |
$self->{content_model} = PCDATA_CONTENT_MODEL; |
| 2357 |
|
|
| 2358 |
if ($token->{type} eq 'end tag' and |
if ($token->{type} == END_TAG_TOKEN and |
| 2359 |
$token->{tag_name} eq 'script') { |
$token->{tag_name} eq 'script') { |
| 2360 |
## Ignore the token |
## Ignore the token |
| 2361 |
} else { |
} else { |
| 2598 |
} |
} |
| 2599 |
}; # $insert_to_foster |
}; # $insert_to_foster |
| 2600 |
|
|
| 2601 |
my $in_body = sub { |
my $insert; |
|
my $insert = shift; |
|
|
if ($token->{type} eq 'start tag') { |
|
|
if ($token->{tag_name} eq 'script') { |
|
|
## NOTE: This is an "as if in head" code clone |
|
|
$script_start_tag->($insert); |
|
|
return; |
|
|
} elsif ($token->{tag_name} eq 'style') { |
|
|
## NOTE: This is an "as if in head" code clone |
|
|
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert); |
|
|
return; |
|
|
} elsif ({ |
|
|
base => 1, link => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
## NOTE: This is an "as if in head" code clone, only "-t" differs |
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ($token->{tag_name} eq 'meta') { |
|
|
## NOTE: This is an "as if in head" code clone, only "-t" differs |
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
|
|
|
|
|
unless ($self->{confident}) { |
|
|
my $charset; |
|
|
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
|
|
$charset = $token->{attributes}->{charset}->{value}; |
|
|
} |
|
|
if ($token->{attributes}->{'http-equiv'}) { |
|
|
## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition. |
|
|
if ($token->{attributes}->{'http-equiv'}->{value} |
|
|
=~ /\A[^;]*;[\x09-\x0D\x20]*charset[\x09-\x0D\x20]*= |
|
|
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
|
|
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
|
|
$charset = defined $1 ? $1 : defined $2 ? $2 : $3; |
|
|
} ## TODO: And if supported |
|
|
} |
|
|
## TODO: Change the encoding |
|
|
} |
|
|
|
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ($token->{tag_name} eq 'title') { |
|
|
!!!parse-error (type => 'in body:title'); |
|
|
## NOTE: This is an "as if in head" code clone |
|
|
$parse_rcdata->(RCDATA_CONTENT_MODEL, sub { |
|
|
if (defined $self->{head_element}) { |
|
|
$self->{head_element}->append_child ($_[0]); |
|
|
} else { |
|
|
$insert->($_[0]); |
|
|
} |
|
|
}); |
|
|
return; |
|
|
} elsif ($token->{tag_name} eq 'body') { |
|
|
!!!parse-error (type => 'in body:body'); |
|
|
|
|
|
if (@{$self->{open_elements}} == 1 or |
|
|
$self->{open_elements}->[1]->[1] ne 'body') { |
|
|
## Ignore the token |
|
|
} else { |
|
|
my $body_el = $self->{open_elements}->[1]->[0]; |
|
|
for my $attr_name (keys %{$token->{attributes}}) { |
|
|
unless ($body_el->has_attribute_ns (undef, $attr_name)) { |
|
|
$body_el->set_attribute_ns |
|
|
(undef, [undef, $attr_name], |
|
|
$token->{attributes}->{$attr_name}->{value}); |
|
|
} |
|
|
} |
|
|
} |
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ({ |
|
|
address => 1, blockquote => 1, center => 1, dir => 1, |
|
|
div => 1, dl => 1, fieldset => 1, listing => 1, |
|
|
menu => 1, ol => 1, p => 1, ul => 1, |
|
|
pre => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
## has a p element in scope |
|
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
|
|
if ($_->[1] eq 'p') { |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', tag_name => 'p'}; |
|
|
return; |
|
|
} elsif ({ |
|
|
table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
if ($token->{tag_name} eq 'pre') { |
|
|
!!!next-token; |
|
|
if ($token->{type} eq 'character') { |
|
|
$token->{data} =~ s/^\x0A//; |
|
|
unless (length $token->{data}) { |
|
|
!!!next-token; |
|
|
} |
|
|
} |
|
|
} else { |
|
|
!!!next-token; |
|
|
} |
|
|
return; |
|
|
} elsif ($token->{tag_name} eq 'form') { |
|
|
if (defined $self->{form_element}) { |
|
|
!!!parse-error (type => 'in form:form'); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
return; |
|
|
} else { |
|
|
## has a p element in scope |
|
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
|
|
if ($_->[1] eq 'p') { |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', tag_name => 'p'}; |
|
|
return; |
|
|
} elsif ({ |
|
|
table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
$self->{form_element} = $self->{open_elements}->[-1]->[0]; |
|
|
!!!next-token; |
|
|
return; |
|
|
} |
|
|
} elsif ($token->{tag_name} eq 'li') { |
|
|
## has a p element in scope |
|
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
|
|
if ($_->[1] eq 'p') { |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', tag_name => 'p'}; |
|
|
return; |
|
|
} elsif ({ |
|
|
table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
## Step 1 |
|
|
my $i = -1; |
|
|
my $node = $self->{open_elements}->[$i]; |
|
|
LI: { |
|
|
## Step 2 |
|
|
if ($node->[1] eq 'li') { |
|
|
if ($i != -1) { |
|
|
!!!parse-error (type => 'end tag missing:'. |
|
|
$self->{open_elements}->[-1]->[1]); |
|
|
} |
|
|
splice @{$self->{open_elements}}, $i; |
|
|
last LI; |
|
|
} |
|
|
|
|
|
## Step 3 |
|
|
if (not $formatting_category->{$node->[1]} and |
|
|
#not $phrasing_category->{$node->[1]} and |
|
|
($special_category->{$node->[1]} or |
|
|
$scoping_category->{$node->[1]}) and |
|
|
$node->[1] ne 'address' and $node->[1] ne 'div') { |
|
|
last LI; |
|
|
} |
|
|
|
|
|
## Step 4 |
|
|
$i--; |
|
|
$node = $self->{open_elements}->[$i]; |
|
|
redo LI; |
|
|
} # LI |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ($token->{tag_name} eq 'dd' or $token->{tag_name} eq 'dt') { |
|
|
## has a p element in scope |
|
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
|
|
if ($_->[1] eq 'p') { |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', tag_name => 'p'}; |
|
|
return; |
|
|
} elsif ({ |
|
|
table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
## Step 1 |
|
|
my $i = -1; |
|
|
my $node = $self->{open_elements}->[$i]; |
|
|
LI: { |
|
|
## Step 2 |
|
|
if ($node->[1] eq 'dt' or $node->[1] eq 'dd') { |
|
|
if ($i != -1) { |
|
|
!!!parse-error (type => 'end tag missing:'. |
|
|
$self->{open_elements}->[-1]->[1]); |
|
|
} |
|
|
splice @{$self->{open_elements}}, $i; |
|
|
last LI; |
|
|
} |
|
|
|
|
|
## Step 3 |
|
|
if (not $formatting_category->{$node->[1]} and |
|
|
#not $phrasing_category->{$node->[1]} and |
|
|
($special_category->{$node->[1]} or |
|
|
$scoping_category->{$node->[1]}) and |
|
|
$node->[1] ne 'address' and $node->[1] ne 'div') { |
|
|
last LI; |
|
|
} |
|
|
|
|
|
## Step 4 |
|
|
$i--; |
|
|
$node = $self->{open_elements}->[$i]; |
|
|
redo LI; |
|
|
} # LI |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ($token->{tag_name} eq 'plaintext') { |
|
|
## has a p element in scope |
|
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
|
|
if ($_->[1] eq 'p') { |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', tag_name => 'p'}; |
|
|
return; |
|
|
} elsif ({ |
|
|
table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
|
|
|
$self->{content_model} = PLAINTEXT_CONTENT_MODEL; |
|
|
|
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ({ |
|
|
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
## has a p element in scope |
|
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
my $node = $self->{open_elements}->[$_]; |
|
|
if ($node->[1] eq 'p') { |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', tag_name => 'p'}; |
|
|
return; |
|
|
} elsif ({ |
|
|
table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
## NOTE: See <http://html5.org/tools/web-apps-tracker?from=925&to=926> |
|
|
## has an element in scope |
|
|
#my $i; |
|
|
#INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
# my $node = $self->{open_elements}->[$_]; |
|
|
# if ({ |
|
|
# h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
|
|
# }->{$node->[1]}) { |
|
|
# $i = $_; |
|
|
# last INSCOPE; |
|
|
# } elsif ({ |
|
|
# table => 1, caption => 1, td => 1, th => 1, |
|
|
# button => 1, marquee => 1, object => 1, html => 1, |
|
|
# }->{$node->[1]}) { |
|
|
# last INSCOPE; |
|
|
# } |
|
|
#} # INSCOPE |
|
|
# |
|
|
#if (defined $i) { |
|
|
# !!! parse-error (type => 'in hn:hn'); |
|
|
# splice @{$self->{open_elements}}, $i; |
|
|
#} |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
|
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ($token->{tag_name} eq 'a') { |
|
|
AFE: for my $i (reverse 0..$#$active_formatting_elements) { |
|
|
my $node = $active_formatting_elements->[$i]; |
|
|
if ($node->[1] eq 'a') { |
|
|
!!!parse-error (type => 'in a:a'); |
|
|
|
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', tag_name => 'a'}; |
|
|
$formatting_end_tag->($token->{tag_name}); |
|
|
|
|
|
AFE2: for (reverse 0..$#$active_formatting_elements) { |
|
|
if ($active_formatting_elements->[$_]->[0] eq $node->[0]) { |
|
|
splice @$active_formatting_elements, $_, 1; |
|
|
last AFE2; |
|
|
} |
|
|
} # AFE2 |
|
|
OE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
if ($self->{open_elements}->[$_]->[0] eq $node->[0]) { |
|
|
splice @{$self->{open_elements}}, $_, 1; |
|
|
last OE; |
|
|
} |
|
|
} # OE |
|
|
last AFE; |
|
|
} elsif ($node->[0] eq '#marker') { |
|
|
last AFE; |
|
|
} |
|
|
} # AFE |
|
|
|
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
|
|
|
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ({ |
|
|
b => 1, big => 1, em => 1, font => 1, i => 1, |
|
|
s => 1, small => 1, strile => 1, |
|
|
strong => 1, tt => 1, u => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
|
|
|
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ($token->{tag_name} eq 'nobr') { |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
## has a |nobr| element in scope |
|
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
my $node = $self->{open_elements}->[$_]; |
|
|
if ($node->[1] eq 'nobr') { |
|
|
!!!parse-error (type => 'not closed:nobr'); |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', tag_name => 'nobr'}; |
|
|
return; |
|
|
} elsif ({ |
|
|
table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
|
|
|
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ($token->{tag_name} eq 'button') { |
|
|
## has a button element in scope |
|
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
my $node = $self->{open_elements}->[$_]; |
|
|
if ($node->[1] eq 'button') { |
|
|
!!!parse-error (type => 'in button:button'); |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', tag_name => 'button'}; |
|
|
return; |
|
|
} elsif ({ |
|
|
table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
push @$active_formatting_elements, ['#marker', '']; |
|
|
|
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ($token->{tag_name} eq 'marquee' or |
|
|
$token->{tag_name} eq 'object') { |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
push @$active_formatting_elements, ['#marker', '']; |
|
|
|
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ($token->{tag_name} eq 'xmp') { |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert); |
|
|
return; |
|
|
} elsif ($token->{tag_name} eq 'table') { |
|
|
## has a p element in scope |
|
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
|
|
if ($_->[1] eq 'p') { |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', tag_name => 'p'}; |
|
|
return; |
|
|
} elsif ({ |
|
|
table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
|
|
|
$self->{insertion_mode} = 'in table'; |
|
|
|
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ({ |
|
|
area => 1, basefont => 1, bgsound => 1, br => 1, |
|
|
embed => 1, img => 1, param => 1, spacer => 1, wbr => 1, |
|
|
image => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
if ($token->{tag_name} eq 'image') { |
|
|
!!!parse-error (type => 'image'); |
|
|
$token->{tag_name} = 'img'; |
|
|
} |
|
|
|
|
|
## NOTE: There is an "as if <br>" code clone. |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
pop @{$self->{open_elements}}; |
|
|
|
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ($token->{tag_name} eq 'hr') { |
|
|
## has a p element in scope |
|
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
|
|
if ($_->[1] eq 'p') { |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', tag_name => 'p'}; |
|
|
return; |
|
|
} elsif ({ |
|
|
table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
pop @{$self->{open_elements}}; |
|
|
|
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ($token->{tag_name} eq 'input') { |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
## TODO: associate with $self->{form_element} if defined |
|
|
pop @{$self->{open_elements}}; |
|
|
|
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ($token->{tag_name} eq 'isindex') { |
|
|
!!!parse-error (type => 'isindex'); |
|
|
|
|
|
if (defined $self->{form_element}) { |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
return; |
|
|
} else { |
|
|
my $at = $token->{attributes}; |
|
|
my $form_attrs; |
|
|
$form_attrs->{action} = $at->{action} if $at->{action}; |
|
|
my $prompt_attr = $at->{prompt}; |
|
|
$at->{name} = {name => 'name', value => 'isindex'}; |
|
|
delete $at->{action}; |
|
|
delete $at->{prompt}; |
|
|
my @tokens = ( |
|
|
{type => 'start tag', tag_name => 'form', |
|
|
attributes => $form_attrs}, |
|
|
{type => 'start tag', tag_name => 'hr'}, |
|
|
{type => 'start tag', tag_name => 'p'}, |
|
|
{type => 'start tag', tag_name => 'label'}, |
|
|
); |
|
|
if ($prompt_attr) { |
|
|
push @tokens, {type => 'character', data => $prompt_attr->{value}}; |
|
|
} else { |
|
|
push @tokens, {type => 'character', |
|
|
data => 'This is a searchable index. Insert your search keywords here: '}; # SHOULD |
|
|
## TODO: make this configurable |
|
|
} |
|
|
push @tokens, |
|
|
{type => 'start tag', tag_name => 'input', attributes => $at}, |
|
|
#{type => 'character', data => ''}, # SHOULD |
|
|
{type => 'end tag', tag_name => 'label'}, |
|
|
{type => 'end tag', tag_name => 'p'}, |
|
|
{type => 'start tag', tag_name => 'hr'}, |
|
|
{type => 'end tag', tag_name => 'form'}; |
|
|
$token = shift @tokens; |
|
|
!!!back-token (@tokens); |
|
|
return; |
|
|
} |
|
|
} elsif ($token->{tag_name} eq 'textarea') { |
|
|
my $tag_name = $token->{tag_name}; |
|
|
my $el; |
|
|
!!!create-element ($el, $token->{tag_name}, $token->{attributes}); |
|
|
|
|
|
## TODO: $self->{form_element} if defined |
|
|
$self->{content_model} = RCDATA_CONTENT_MODEL; |
|
|
delete $self->{escape}; # MUST |
|
|
|
|
|
$insert->($el); |
|
|
|
|
|
my $text = ''; |
|
|
!!!next-token; |
|
|
if ($token->{type} eq 'character') { |
|
|
$token->{data} =~ s/^\x0A//; |
|
|
unless (length $token->{data}) { |
|
|
!!!next-token; |
|
|
} |
|
|
} |
|
|
while ($token->{type} eq 'character') { |
|
|
$text .= $token->{data}; |
|
|
!!!next-token; |
|
|
} |
|
|
if (length $text) { |
|
|
$el->manakai_append_text ($text); |
|
|
} |
|
|
|
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; |
|
|
|
|
|
if ($token->{type} eq 'end tag' and |
|
|
$token->{tag_name} eq $tag_name) { |
|
|
## Ignore the token |
|
|
} else { |
|
|
!!!parse-error (type => 'in RCDATA:#'.$token->{type}); |
|
|
} |
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ({ |
|
|
iframe => 1, |
|
|
noembed => 1, |
|
|
noframes => 1, |
|
|
noscript => 0, ## TODO: 1 if scripting is enabled |
|
|
}->{$token->{tag_name}}) { |
|
|
## NOTE: There are two "as if in body" code clones. |
|
|
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert); |
|
|
return; |
|
|
} elsif ($token->{tag_name} eq 'select') { |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
|
|
|
$self->{insertion_mode} = 'in select'; |
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ({ |
|
|
caption => 1, col => 1, colgroup => 1, frame => 1, |
|
|
frameset => 1, head => 1, option => 1, optgroup => 1, |
|
|
tbody => 1, td => 1, tfoot => 1, th => 1, |
|
|
thead => 1, tr => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
!!!parse-error (type => 'in body:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
return; |
|
|
|
|
|
## ISSUE: An issue on HTML5 new elements in the spec. |
|
|
} else { |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
|
|
|
!!!next-token; |
|
|
return; |
|
|
} |
|
|
} elsif ($token->{type} eq 'end tag') { |
|
|
if ($token->{tag_name} eq 'body') { |
|
|
if (@{$self->{open_elements}} > 1 and |
|
|
$self->{open_elements}->[1]->[1] eq 'body') { |
|
|
for (@{$self->{open_elements}}) { |
|
|
unless ({ |
|
|
dd => 1, dt => 1, li => 1, p => 1, td => 1, |
|
|
th => 1, tr => 1, body => 1, html => 1, |
|
|
tbody => 1, tfoot => 1, thead => 1, |
|
|
}->{$_->[1]}) { |
|
|
!!!parse-error (type => 'not closed:'.$_->[1]); |
|
|
} |
|
|
} |
|
|
|
|
|
$self->{insertion_mode} = 'after body'; |
|
|
!!!next-token; |
|
|
return; |
|
|
} else { |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
return; |
|
|
} |
|
|
} elsif ($token->{tag_name} eq 'html') { |
|
|
if (@{$self->{open_elements}} > 1 and $self->{open_elements}->[1]->[1] eq 'body') { |
|
|
## ISSUE: There is an issue in the spec. |
|
|
if ($self->{open_elements}->[-1]->[1] ne 'body') { |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[1]->[1]); |
|
|
} |
|
|
$self->{insertion_mode} = 'after body'; |
|
|
## reprocess |
|
|
return; |
|
|
} else { |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
return; |
|
|
} |
|
|
} elsif ({ |
|
|
address => 1, blockquote => 1, center => 1, dir => 1, |
|
|
div => 1, dl => 1, fieldset => 1, listing => 1, |
|
|
menu => 1, ol => 1, pre => 1, ul => 1, |
|
|
p => 1, |
|
|
dd => 1, dt => 1, li => 1, |
|
|
button => 1, marquee => 1, object => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
## has an element in scope |
|
|
my $i; |
|
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
my $node = $self->{open_elements}->[$_]; |
|
|
if ($node->[1] eq $token->{tag_name}) { |
|
|
## generate implied end tags |
|
|
if ({ |
|
|
dd => ($token->{tag_name} ne 'dd'), |
|
|
dt => ($token->{tag_name} ne 'dt'), |
|
|
li => ($token->{tag_name} ne 'li'), |
|
|
p => ($token->{tag_name} ne 'p'), |
|
|
td => 1, th => 1, tr => 1, |
|
|
tbody => 1, tfoot=> 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
return; |
|
|
} |
|
|
$i = $_; |
|
|
last INSCOPE unless $token->{tag_name} eq 'p'; |
|
|
} elsif ({ |
|
|
table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
|
|
if (defined $i) { |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
|
} else { |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
} |
|
|
} |
|
|
|
|
|
if (defined $i) { |
|
|
splice @{$self->{open_elements}}, $i; |
|
|
} elsif ($token->{tag_name} eq 'p') { |
|
|
## As if <p>, then reprocess the current token |
|
|
my $el; |
|
|
!!!create-element ($el, 'p'); |
|
|
$insert->($el); |
|
|
} |
|
|
$clear_up_to_marker->() |
|
|
if { |
|
|
button => 1, marquee => 1, object => 1, |
|
|
}->{$token->{tag_name}}; |
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ($token->{tag_name} eq 'form') { |
|
|
## has an element in scope |
|
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
my $node = $self->{open_elements}->[$_]; |
|
|
if ($node->[1] eq $token->{tag_name}) { |
|
|
## generate implied end tags |
|
|
if ({ |
|
|
dd => 1, dt => 1, li => 1, p => 1, |
|
|
td => 1, th => 1, tr => 1, |
|
|
tbody => 1, tfoot=> 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
return; |
|
|
} |
|
|
last INSCOPE; |
|
|
} elsif ({ |
|
|
table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
if ($self->{open_elements}->[-1]->[1] eq $token->{tag_name}) { |
|
|
pop @{$self->{open_elements}}; |
|
|
} else { |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
|
} |
|
|
|
|
|
undef $self->{form_element}; |
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ({ |
|
|
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
## has an element in scope |
|
|
my $i; |
|
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
my $node = $self->{open_elements}->[$_]; |
|
|
if ({ |
|
|
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
|
|
}->{$node->[1]}) { |
|
|
## generate implied end tags |
|
|
if ({ |
|
|
dd => 1, dt => 1, li => 1, p => 1, |
|
|
td => 1, th => 1, tr => 1, |
|
|
tbody => 1, tfoot=> 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
return; |
|
|
} |
|
|
$i = $_; |
|
|
last INSCOPE; |
|
|
} elsif ({ |
|
|
table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
|
} |
|
|
|
|
|
splice @{$self->{open_elements}}, $i if defined $i; |
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ({ |
|
|
a => 1, |
|
|
b => 1, big => 1, em => 1, font => 1, i => 1, |
|
|
nobr => 1, s => 1, small => 1, strile => 1, |
|
|
strong => 1, tt => 1, u => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
$formatting_end_tag->($token->{tag_name}); |
|
|
return; |
|
|
} elsif ($token->{tag_name} eq 'br') { |
|
|
!!!parse-error (type => 'unmatched end tag:br'); |
|
|
|
|
|
## As if <br> |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
my $el; |
|
|
!!!create-element ($el, 'br'); |
|
|
$insert->($el); |
|
|
|
|
|
## Ignore the token. |
|
|
!!!next-token; |
|
|
return; |
|
|
} elsif ({ |
|
|
caption => 1, col => 1, colgroup => 1, frame => 1, |
|
|
frameset => 1, head => 1, option => 1, optgroup => 1, |
|
|
tbody => 1, td => 1, tfoot => 1, th => 1, |
|
|
thead => 1, tr => 1, |
|
|
area => 1, basefont => 1, bgsound => 1, |
|
|
embed => 1, hr => 1, iframe => 1, image => 1, |
|
|
img => 1, input => 1, isindex => 1, noembed => 1, |
|
|
noframes => 1, param => 1, select => 1, spacer => 1, |
|
|
table => 1, textarea => 1, wbr => 1, |
|
|
noscript => 0, ## TODO: if scripting is enabled |
|
|
}->{$token->{tag_name}}) { |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
return; |
|
|
|
|
|
## ISSUE: Issue on HTML5 new elements in spec |
|
|
|
|
|
} else { |
|
|
## Step 1 |
|
|
my $node_i = -1; |
|
|
my $node = $self->{open_elements}->[$node_i]; |
|
|
|
|
|
## Step 2 |
|
|
S2: { |
|
|
if ($node->[1] eq $token->{tag_name}) { |
|
|
## Step 1 |
|
|
## generate implied end tags |
|
|
if ({ |
|
|
dd => 1, dt => 1, li => 1, p => 1, |
|
|
td => 1, th => 1, tr => 1, |
|
|
tbody => 1, tfoot=> 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
return; |
|
|
} |
|
|
|
|
|
## Step 2 |
|
|
if ($token->{tag_name} ne $self->{open_elements}->[-1]->[1]) { |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
|
} |
|
|
|
|
|
## Step 3 |
|
|
splice @{$self->{open_elements}}, $node_i; |
|
|
|
|
|
!!!next-token; |
|
|
last S2; |
|
|
} else { |
|
|
## Step 3 |
|
|
if (not $formatting_category->{$node->[1]} and |
|
|
#not $phrasing_category->{$node->[1]} and |
|
|
($special_category->{$node->[1]} or |
|
|
$scoping_category->{$node->[1]})) { |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
last S2; |
|
|
} |
|
|
} |
|
|
|
|
|
## Step 4 |
|
|
$node_i--; |
|
|
$node = $self->{open_elements}->[$node_i]; |
|
|
|
|
|
## Step 5; |
|
|
redo S2; |
|
|
} # S2 |
|
|
return; |
|
|
} |
|
|
} |
|
|
}; # $in_body |
|
| 2602 |
|
|
| 2603 |
B: { |
B: { |
| 2604 |
if ($token->{type} eq 'DOCTYPE') { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 2605 |
!!!parse-error (type => 'DOCTYPE in the middle'); |
!!!parse-error (type => 'DOCTYPE in the middle'); |
| 2606 |
## Ignore the token |
## Ignore the token |
| 2607 |
## Stay in the phase |
## Stay in the phase |
| 2608 |
!!!next-token; |
!!!next-token; |
| 2609 |
redo B; |
redo B; |
| 2610 |
} elsif ($token->{type} eq 'end-of-file') { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 2611 |
if ($token->{insertion_mode} ne 'trailing end') { |
if ($self->{insertion_mode} & AFTER_HTML_IMS) { |
| 2612 |
|
# |
| 2613 |
|
} else { |
| 2614 |
## Generate implied end tags |
## Generate implied end tags |
| 2615 |
if ({ |
if ({ |
| 2616 |
dd => 1, dt => 1, li => 1, p => 1, td => 1, th => 1, tr => 1, |
dd => 1, dt => 1, li => 1, p => 1, td => 1, th => 1, tr => 1, |
| 2617 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 2618 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 2619 |
!!!back-token; |
!!!back-token; |
| 2620 |
$token = {type => 'end tag', tag_name => $self->{open_elements}->[-1]->[1]}; |
$token = {type => END_TAG_TOKEN, tag_name => $self->{open_elements}->[-1]->[1]}; |
| 2621 |
redo B; |
redo B; |
| 2622 |
} |
} |
| 2623 |
|
|
| 2635 |
|
|
| 2636 |
## Stop parsing |
## Stop parsing |
| 2637 |
last B; |
last B; |
| 2638 |
} elsif ($token->{type} eq 'start tag' and |
} elsif ($token->{type} == START_TAG_TOKEN and |
| 2639 |
$token->{tag_name} eq 'html') { |
$token->{tag_name} eq 'html') { |
| 2640 |
if ($self->{insertion_mode} eq 'trailing end') { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 2641 |
## Turn into the main phase |
## Turn into the main phase |
| 2642 |
!!!parse-error (type => 'after html:html'); |
!!!parse-error (type => 'after html:html'); |
| 2643 |
$self->{insertion_mode} = $previous_insertion_mode; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 2644 |
|
} elsif ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 2645 |
|
## Turn into the main phase |
| 2646 |
|
!!!parse-error (type => 'after html:html'); |
| 2647 |
|
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 2648 |
} |
} |
| 2649 |
|
|
| 2650 |
## ISSUE: "aa<html>" is not a parse error. |
## ISSUE: "aa<html>" is not a parse error. |
| 2662 |
} |
} |
| 2663 |
!!!next-token; |
!!!next-token; |
| 2664 |
redo B; |
redo B; |
| 2665 |
} elsif ($token->{type} eq 'comment') { |
} elsif ($token->{type} == COMMENT_TOKEN) { |
| 2666 |
my $comment = $self->{document}->create_comment ($token->{data}); |
my $comment = $self->{document}->create_comment ($token->{data}); |
| 2667 |
if ($self->{insertion_mode} eq 'trailing end') { |
if ($self->{insertion_mode} & AFTER_HTML_IMS) { |
| 2668 |
$self->{document}->append_child ($comment); |
$self->{document}->append_child ($comment); |
| 2669 |
} elsif ($self->{insertion_mode} eq 'after body') { |
} elsif ($self->{insertion_mode} == AFTER_BODY_IM) { |
| 2670 |
$self->{open_elements}->[0]->[0]->append_child ($comment); |
$self->{open_elements}->[0]->[0]->append_child ($comment); |
| 2671 |
} else { |
} else { |
| 2672 |
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
| 2673 |
} |
} |
| 2674 |
!!!next-token; |
!!!next-token; |
| 2675 |
redo B; |
redo B; |
| 2676 |
} elsif ($self->{insertion_mode} eq 'in head' or |
} elsif ($self->{insertion_mode} & HEAD_IMS) { |
| 2677 |
$self->{insertion_mode} eq 'in head noscript' or |
if ($token->{type} == CHARACTER_TOKEN) { |
|
$self->{insertion_mode} eq 'after head' or |
|
|
$self->{insertion_mode} eq 'before head') { |
|
|
if ($token->{type} eq 'character') { |
|
| 2678 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 2679 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 2680 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 2683 |
} |
} |
| 2684 |
} |
} |
| 2685 |
|
|
| 2686 |
if ($self->{insertion_mode} eq 'before head') { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 2687 |
## As if <head> |
## As if <head> |
| 2688 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, 'head'); |
| 2689 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 2693 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2694 |
|
|
| 2695 |
## Reprocess in the "after head" insertion mode... |
## Reprocess in the "after head" insertion mode... |
| 2696 |
} elsif ($self->{insertion_mode} eq 'in head noscript') { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2697 |
## As if </noscript> |
## As if </noscript> |
| 2698 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2699 |
!!!parse-error (type => 'in noscript:#character'); |
!!!parse-error (type => 'in noscript:#character'); |
| 2703 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2704 |
|
|
| 2705 |
## Reprocess in the "after head" insertion mode... |
## Reprocess in the "after head" insertion mode... |
| 2706 |
} elsif ($self->{insertion_mode} eq 'in head') { |
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 2707 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2708 |
|
|
| 2709 |
## Reprocess in the "after head" insertion mode... |
## Reprocess in the "after head" insertion mode... |
| 2712 |
## "after head" insertion mode |
## "after head" insertion mode |
| 2713 |
## As if <body> |
## As if <body> |
| 2714 |
!!!insert-element ('body'); |
!!!insert-element ('body'); |
| 2715 |
$self->{insertion_mode} = 'in body'; |
$self->{insertion_mode} = IN_BODY_IM; |
| 2716 |
## reprocess |
## reprocess |
| 2717 |
redo B; |
redo B; |
| 2718 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 2719 |
if ($token->{tag_name} eq 'head') { |
if ($token->{tag_name} eq 'head') { |
| 2720 |
if ($self->{insertion_mode} eq 'before head') { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 2721 |
!!!create-element ($self->{head_element}, $token->{tag_name}, $token->{attributes}); |
!!!create-element ($self->{head_element}, $token->{tag_name}, $token->{attributes}); |
| 2722 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 2723 |
push @{$self->{open_elements}}, [$self->{head_element}, $token->{tag_name}]; |
push @{$self->{open_elements}}, [$self->{head_element}, $token->{tag_name}]; |
| 2724 |
$self->{insertion_mode} = 'in head'; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 2725 |
!!!next-token; |
!!!next-token; |
| 2726 |
redo B; |
redo B; |
| 2727 |
} elsif ($self->{insertion_mode} ne 'after head') { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2728 |
|
# |
| 2729 |
|
} else { |
| 2730 |
!!!parse-error (type => 'in head:head'); # or in head noscript |
!!!parse-error (type => 'in head:head'); # or in head noscript |
| 2731 |
## Ignore the token |
## Ignore the token |
| 2732 |
!!!next-token; |
!!!next-token; |
| 2733 |
redo B; |
redo B; |
|
} else { |
|
|
# |
|
| 2734 |
} |
} |
| 2735 |
} elsif ($self->{insertion_mode} eq 'before head') { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 2736 |
## As if <head> |
## As if <head> |
| 2737 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, 'head'); |
| 2738 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 2739 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 2740 |
|
|
| 2741 |
$self->{insertion_mode} = 'in head'; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 2742 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 2743 |
} |
} |
| 2744 |
|
|
| 2745 |
if ($token->{tag_name} eq 'base') { |
if ($token->{tag_name} eq 'base') { |
| 2746 |
if ($self->{insertion_mode} eq 'in head noscript') { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2747 |
## As if </noscript> |
## As if </noscript> |
| 2748 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2749 |
!!!parse-error (type => 'in noscript:base'); |
!!!parse-error (type => 'in noscript:base'); |
| 2750 |
|
|
| 2751 |
$self->{insertion_mode} = 'in head'; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 2752 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 2753 |
} |
} |
| 2754 |
|
|
| 2755 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 2756 |
if ($self->{insertion_mode} eq 'after head') { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2757 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 2758 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 2759 |
} |
} |
| 2760 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 2761 |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 2762 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} |
| 2763 |
if $self->{insertion_mode} eq 'after head'; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 2764 |
!!!next-token; |
!!!next-token; |
| 2765 |
redo B; |
redo B; |
| 2766 |
} elsif ($token->{tag_name} eq 'link') { |
} elsif ($token->{tag_name} eq 'link') { |
| 2767 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 2768 |
if ($self->{insertion_mode} eq 'after head') { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2769 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 2770 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 2771 |
} |
} |
| 2772 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 2773 |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 2774 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} |
| 2775 |
if $self->{insertion_mode} eq 'after head'; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 2776 |
!!!next-token; |
!!!next-token; |
| 2777 |
redo B; |
redo B; |
| 2778 |
} elsif ($token->{tag_name} eq 'meta') { |
} elsif ($token->{tag_name} eq 'meta') { |
| 2779 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 2780 |
if ($self->{insertion_mode} eq 'after head') { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2781 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 2782 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 2783 |
} |
} |
| 2803 |
|
|
| 2804 |
## TODO: Extracting |charset| from |meta|. |
## TODO: Extracting |charset| from |meta|. |
| 2805 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} |
| 2806 |
if $self->{insertion_mode} eq 'after head'; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 2807 |
!!!next-token; |
!!!next-token; |
| 2808 |
redo B; |
redo B; |
| 2809 |
} elsif ($token->{tag_name} eq 'title') { |
} elsif ($token->{tag_name} eq 'title') { |
| 2810 |
if ($self->{insertion_mode} eq 'in head noscript') { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2811 |
## As if </noscript> |
## As if </noscript> |
| 2812 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2813 |
!!!parse-error (type => 'in noscript:title'); |
!!!parse-error (type => 'in noscript:title'); |
| 2814 |
|
|
| 2815 |
$self->{insertion_mode} = 'in head'; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 2816 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 2817 |
} elsif ($self->{insertion_mode} eq 'after head') { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2818 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 2819 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 2820 |
} |
} |
| 2825 |
$parse_rcdata->(RCDATA_CONTENT_MODEL, |
$parse_rcdata->(RCDATA_CONTENT_MODEL, |
| 2826 |
sub { $parent->append_child ($_[0]) }); |
sub { $parent->append_child ($_[0]) }); |
| 2827 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} |
| 2828 |
if $self->{insertion_mode} eq 'after head'; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 2829 |
redo B; |
redo B; |
| 2830 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($token->{tag_name} eq 'style') { |
| 2831 |
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
| 2832 |
## insertion mode 'in head') |
## insertion mode IN_HEAD_IM) |
| 2833 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 2834 |
if ($self->{insertion_mode} eq 'after head') { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2835 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 2836 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 2837 |
} |
} |
| 2838 |
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert_to_current); |
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert_to_current); |
| 2839 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} |
| 2840 |
if $self->{insertion_mode} eq 'after head'; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 2841 |
redo B; |
redo B; |
| 2842 |
} elsif ($token->{tag_name} eq 'noscript') { |
} elsif ($token->{tag_name} eq 'noscript') { |
| 2843 |
if ($self->{insertion_mode} eq 'in head') { |
if ($self->{insertion_mode} == IN_HEAD_IM) { |
| 2844 |
## NOTE: and scripting is disalbed |
## NOTE: and scripting is disalbed |
| 2845 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 2846 |
$self->{insertion_mode} = 'in head noscript'; |
$self->{insertion_mode} = IN_HEAD_NOSCRIPT_IM; |
| 2847 |
!!!next-token; |
!!!next-token; |
| 2848 |
redo B; |
redo B; |
| 2849 |
} elsif ($self->{insertion_mode} eq 'in head noscript') { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2850 |
!!!parse-error (type => 'in noscript:noscript'); |
!!!parse-error (type => 'in noscript:noscript'); |
| 2851 |
## Ignore the token |
## Ignore the token |
| 2852 |
!!!next-token; |
!!!next-token; |
| 2855 |
# |
# |
| 2856 |
} |
} |
| 2857 |
} elsif ($token->{tag_name} eq 'script') { |
} elsif ($token->{tag_name} eq 'script') { |
| 2858 |
if ($self->{insertion_mode} eq 'in head noscript') { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2859 |
## As if </noscript> |
## As if </noscript> |
| 2860 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2861 |
!!!parse-error (type => 'in noscript:script'); |
!!!parse-error (type => 'in noscript:script'); |
| 2862 |
|
|
| 2863 |
$self->{insertion_mode} = 'in head'; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 2864 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 2865 |
} elsif ($self->{insertion_mode} eq 'after head') { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2866 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 2867 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 2868 |
} |
} |
| 2870 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 2871 |
$script_start_tag->($insert_to_current); |
$script_start_tag->($insert_to_current); |
| 2872 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} |
| 2873 |
if $self->{insertion_mode} eq 'after head'; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 2874 |
redo B; |
redo B; |
| 2875 |
} elsif ($token->{tag_name} eq 'body' or |
} elsif ($token->{tag_name} eq 'body' or |
| 2876 |
$token->{tag_name} eq 'frameset') { |
$token->{tag_name} eq 'frameset') { |
| 2877 |
if ($self->{insertion_mode} eq 'in head noscript') { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2878 |
## As if </noscript> |
## As if </noscript> |
| 2879 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2880 |
!!!parse-error (type => 'in noscript:'.$token->{tag_name}); |
!!!parse-error (type => 'in noscript:'.$token->{tag_name}); |
| 2884 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2885 |
|
|
| 2886 |
## Reprocess in the "after head" insertion mode... |
## Reprocess in the "after head" insertion mode... |
| 2887 |
} elsif ($self->{insertion_mode} eq 'in head') { |
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 2888 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2889 |
|
|
| 2890 |
## Reprocess in the "after head" insertion mode... |
## Reprocess in the "after head" insertion mode... |
| 2892 |
|
|
| 2893 |
## "after head" insertion mode |
## "after head" insertion mode |
| 2894 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 2895 |
$self->{insertion_mode} = 'in '.$token->{tag_name}; |
if ($token->{tag_name} eq 'body') { |
| 2896 |
|
$self->{insertion_mode} = IN_BODY_IM; |
| 2897 |
|
} elsif ($token->{tag_name} eq 'frameset') { |
| 2898 |
|
$self->{insertion_mode} = IN_FRAMESET_IM; |
| 2899 |
|
} else { |
| 2900 |
|
die "$0: tag name: $self->{tag_name}"; |
| 2901 |
|
} |
| 2902 |
!!!next-token; |
!!!next-token; |
| 2903 |
redo B; |
redo B; |
| 2904 |
} else { |
} else { |
| 2905 |
# |
# |
| 2906 |
} |
} |
| 2907 |
|
|
| 2908 |
if ($self->{insertion_mode} eq 'in head noscript') { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2909 |
## As if </noscript> |
## As if </noscript> |
| 2910 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2911 |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}); |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}); |
| 2915 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2916 |
|
|
| 2917 |
## Reprocess in the "after head" insertion mode... |
## Reprocess in the "after head" insertion mode... |
| 2918 |
} elsif ($self->{insertion_mode} eq 'in head') { |
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 2919 |
## As if </head> |
## As if </head> |
| 2920 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2921 |
|
|
| 2925 |
## "after head" insertion mode |
## "after head" insertion mode |
| 2926 |
## As if <body> |
## As if <body> |
| 2927 |
!!!insert-element ('body'); |
!!!insert-element ('body'); |
| 2928 |
$self->{insertion_mode} = 'in body'; |
$self->{insertion_mode} = IN_BODY_IM; |
| 2929 |
## reprocess |
## reprocess |
| 2930 |
redo B; |
redo B; |
| 2931 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 2932 |
if ($token->{tag_name} eq 'head') { |
if ($token->{tag_name} eq 'head') { |
| 2933 |
if ($self->{insertion_mode} eq 'before head') { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 2934 |
## As if <head> |
## As if <head> |
| 2935 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, 'head'); |
| 2936 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 2938 |
|
|
| 2939 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 2940 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2941 |
$self->{insertion_mode} = 'after head'; |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 2942 |
!!!next-token; |
!!!next-token; |
| 2943 |
redo B; |
redo B; |
| 2944 |
} elsif ($self->{insertion_mode} eq 'in head noscript') { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2945 |
## As if </noscript> |
## As if </noscript> |
| 2946 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2947 |
!!!parse-error (type => 'in noscript:script'); |
!!!parse-error (type => 'in noscript:script'); |
| 2948 |
|
|
| 2949 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 2950 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2951 |
$self->{insertion_mode} = 'after head'; |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 2952 |
!!!next-token; |
!!!next-token; |
| 2953 |
redo B; |
redo B; |
| 2954 |
} elsif ($self->{insertion_mode} eq 'in head') { |
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 2955 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2956 |
$self->{insertion_mode} = 'after head'; |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 2957 |
!!!next-token; |
!!!next-token; |
| 2958 |
redo B; |
redo B; |
| 2959 |
} else { |
} else { |
| 2960 |
# |
# |
| 2961 |
} |
} |
| 2962 |
} elsif ($token->{tag_name} eq 'noscript') { |
} elsif ($token->{tag_name} eq 'noscript') { |
| 2963 |
if ($self->{insertion_mode} eq 'in head noscript') { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2964 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2965 |
$self->{insertion_mode} = 'in head'; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 2966 |
!!!next-token; |
!!!next-token; |
| 2967 |
redo B; |
redo B; |
| 2968 |
} elsif ($self->{insertion_mode} eq 'before head') { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 2969 |
!!!parse-error (type => 'unmatched end tag:noscript'); |
!!!parse-error (type => 'unmatched end tag:noscript'); |
| 2970 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 2971 |
!!!next-token; |
!!!next-token; |
| 2976 |
} elsif ({ |
} elsif ({ |
| 2977 |
body => 1, html => 1, |
body => 1, html => 1, |
| 2978 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 2979 |
if ($self->{insertion_mode} eq 'before head') { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 2980 |
## As if <head> |
## As if <head> |
| 2981 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, 'head'); |
| 2982 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 2983 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 2984 |
|
|
| 2985 |
$self->{insertion_mode} = 'in head'; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 2986 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 2987 |
} elsif ($self->{insertion_mode} eq 'in head noscript') { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2988 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 2989 |
## Ignore the token |
## Ignore the token |
| 2990 |
!!!next-token; |
!!!next-token; |
| 2995 |
} elsif ({ |
} elsif ({ |
| 2996 |
p => 1, br => 1, |
p => 1, br => 1, |
| 2997 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 2998 |
if ($self->{insertion_mode} eq 'before head') { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 2999 |
## As if <head> |
## As if <head> |
| 3000 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, 'head'); |
| 3001 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 3002 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3003 |
|
|
| 3004 |
$self->{insertion_mode} = 'in head'; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 3005 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 3006 |
} |
} |
| 3007 |
|
|
| 3008 |
# |
# |
| 3009 |
} else { |
} else { |
| 3010 |
if ($self->{insertion_mode} ne 'after head') { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 3011 |
|
# |
| 3012 |
|
} else { |
| 3013 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3014 |
## Ignore the token |
## Ignore the token |
| 3015 |
!!!next-token; |
!!!next-token; |
| 3016 |
redo B; |
redo B; |
|
} else { |
|
|
# |
|
| 3017 |
} |
} |
| 3018 |
} |
} |
| 3019 |
|
|
| 3020 |
if ($self->{insertion_mode} eq 'in head noscript') { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 3021 |
## As if </noscript> |
## As if </noscript> |
| 3022 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3023 |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}); |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}); |
| 3027 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3028 |
|
|
| 3029 |
## Reprocess in the "after head" insertion mode... |
## Reprocess in the "after head" insertion mode... |
| 3030 |
} elsif ($self->{insertion_mode} eq 'in head') { |
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 3031 |
## As if </head> |
## As if </head> |
| 3032 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3033 |
|
|
| 3034 |
## Reprocess in the "after head" insertion mode... |
## Reprocess in the "after head" insertion mode... |
| 3035 |
} elsif ($self->{insertion_mode} eq 'before head') { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3036 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3037 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 3038 |
!!!next-token; |
!!!next-token; |
| 3042 |
## "after head" insertion mode |
## "after head" insertion mode |
| 3043 |
## As if <body> |
## As if <body> |
| 3044 |
!!!insert-element ('body'); |
!!!insert-element ('body'); |
| 3045 |
$self->{insertion_mode} = 'in body'; |
$self->{insertion_mode} = IN_BODY_IM; |
| 3046 |
## reprocess |
## reprocess |
| 3047 |
redo B; |
redo B; |
| 3048 |
} else { |
} else { |
| 3050 |
} |
} |
| 3051 |
|
|
| 3052 |
## ISSUE: An issue in the spec. |
## ISSUE: An issue in the spec. |
| 3053 |
} elsif ($self->{insertion_mode} eq 'in body' or |
} elsif ($self->{insertion_mode} & BODY_IMS) { |
| 3054 |
$self->{insertion_mode} eq 'in cell' or |
if ($token->{type} == CHARACTER_TOKEN) { |
|
$self->{insertion_mode} eq 'in caption') { |
|
|
if ($token->{type} eq 'character') { |
|
| 3055 |
## NOTE: There is a code clone of "character in body". |
## NOTE: There is a code clone of "character in body". |
| 3056 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 3057 |
|
|
| 3059 |
|
|
| 3060 |
!!!next-token; |
!!!next-token; |
| 3061 |
redo B; |
redo B; |
| 3062 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 3063 |
if ({ |
if ({ |
| 3064 |
caption => 1, col => 1, colgroup => 1, tbody => 1, |
caption => 1, col => 1, colgroup => 1, tbody => 1, |
| 3065 |
td => 1, tfoot => 1, th => 1, thead => 1, tr => 1, |
td => 1, tfoot => 1, th => 1, thead => 1, tr => 1, |
| 3066 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 3067 |
if ($self->{insertion_mode} eq 'in cell') { |
if ($self->{insertion_mode} == IN_CELL_IM) { |
| 3068 |
## have an element in table scope |
## have an element in table scope |
| 3069 |
my $tn; |
my $tn; |
| 3070 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3087 |
|
|
| 3088 |
## Close the cell |
## Close the cell |
| 3089 |
!!!back-token; # <?> |
!!!back-token; # <?> |
| 3090 |
$token = {type => 'end tag', tag_name => $tn}; |
$token = {type => END_TAG_TOKEN, tag_name => $tn}; |
| 3091 |
redo B; |
redo B; |
| 3092 |
} elsif ($self->{insertion_mode} eq 'in caption') { |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 3093 |
!!!parse-error (type => 'not closed:caption'); |
!!!parse-error (type => 'not closed:caption'); |
| 3094 |
|
|
| 3095 |
## As if </caption> |
## As if </caption> |
| 3120 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 3121 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3122 |
!!!back-token; # <?> |
!!!back-token; # <?> |
| 3123 |
$token = {type => 'end tag', tag_name => 'caption'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'caption'}; |
| 3124 |
!!!back-token; |
!!!back-token; |
| 3125 |
$token = {type => 'end tag', |
$token = {type => END_TAG_TOKEN, |
| 3126 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3127 |
redo B; |
redo B; |
| 3128 |
} |
} |
| 3135 |
|
|
| 3136 |
$clear_up_to_marker->(); |
$clear_up_to_marker->(); |
| 3137 |
|
|
| 3138 |
$self->{insertion_mode} = 'in table'; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 3139 |
|
|
| 3140 |
## reprocess |
## reprocess |
| 3141 |
redo B; |
redo B; |
| 3145 |
} else { |
} else { |
| 3146 |
# |
# |
| 3147 |
} |
} |
| 3148 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 3149 |
if ($token->{tag_name} eq 'td' or $token->{tag_name} eq 'th') { |
if ($token->{tag_name} eq 'td' or $token->{tag_name} eq 'th') { |
| 3150 |
if ($self->{insertion_mode} eq 'in cell') { |
if ($self->{insertion_mode} == IN_CELL_IM) { |
| 3151 |
## have an element in table scope |
## have an element in table scope |
| 3152 |
my $i; |
my $i; |
| 3153 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3177 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 3178 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3179 |
!!!back-token; |
!!!back-token; |
| 3180 |
$token = {type => 'end tag', |
$token = {type => END_TAG_TOKEN, |
| 3181 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3182 |
redo B; |
redo B; |
| 3183 |
} |
} |
| 3190 |
|
|
| 3191 |
$clear_up_to_marker->(); |
$clear_up_to_marker->(); |
| 3192 |
|
|
| 3193 |
$self->{insertion_mode} = 'in row'; |
$self->{insertion_mode} = IN_ROW_IM; |
| 3194 |
|
|
| 3195 |
!!!next-token; |
!!!next-token; |
| 3196 |
redo B; |
redo B; |
| 3197 |
} elsif ($self->{insertion_mode} eq 'in caption') { |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 3198 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3199 |
## Ignore the token |
## Ignore the token |
| 3200 |
!!!next-token; |
!!!next-token; |
| 3203 |
# |
# |
| 3204 |
} |
} |
| 3205 |
} elsif ($token->{tag_name} eq 'caption') { |
} elsif ($token->{tag_name} eq 'caption') { |
| 3206 |
if ($self->{insertion_mode} eq 'in caption') { |
if ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 3207 |
## have a table element in table scope |
## have a table element in table scope |
| 3208 |
my $i; |
my $i; |
| 3209 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3231 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 3232 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3233 |
!!!back-token; |
!!!back-token; |
| 3234 |
$token = {type => 'end tag', |
$token = {type => END_TAG_TOKEN, |
| 3235 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3236 |
redo B; |
redo B; |
| 3237 |
} |
} |
| 3244 |
|
|
| 3245 |
$clear_up_to_marker->(); |
$clear_up_to_marker->(); |
| 3246 |
|
|
| 3247 |
$self->{insertion_mode} = 'in table'; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 3248 |
|
|
| 3249 |
!!!next-token; |
!!!next-token; |
| 3250 |
redo B; |
redo B; |
| 3251 |
} elsif ($self->{insertion_mode} eq 'in cell') { |
} elsif ($self->{insertion_mode} == IN_CELL_IM) { |
| 3252 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3253 |
## Ignore the token |
## Ignore the token |
| 3254 |
!!!next-token; |
!!!next-token; |
| 3260 |
table => 1, tbody => 1, tfoot => 1, |
table => 1, tbody => 1, tfoot => 1, |
| 3261 |
thead => 1, tr => 1, |
thead => 1, tr => 1, |
| 3262 |
}->{$token->{tag_name}} and |
}->{$token->{tag_name}} and |
| 3263 |
$self->{insertion_mode} eq 'in cell') { |
$self->{insertion_mode} == IN_CELL_IM) { |
| 3264 |
## have an element in table scope |
## have an element in table scope |
| 3265 |
my $i; |
my $i; |
| 3266 |
my $tn; |
my $tn; |
| 3288 |
|
|
| 3289 |
## Close the cell |
## Close the cell |
| 3290 |
!!!back-token; # </?> |
!!!back-token; # </?> |
| 3291 |
$token = {type => 'end tag', tag_name => $tn}; |
$token = {type => END_TAG_TOKEN, tag_name => $tn}; |
| 3292 |
redo B; |
redo B; |
| 3293 |
} elsif ($token->{tag_name} eq 'table' and |
} elsif ($token->{tag_name} eq 'table' and |
| 3294 |
$self->{insertion_mode} eq 'in caption') { |
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 3295 |
!!!parse-error (type => 'not closed:caption'); |
!!!parse-error (type => 'not closed:caption'); |
| 3296 |
|
|
| 3297 |
## As if </caption> |
## As if </caption> |
| 3322 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 3323 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3324 |
!!!back-token; # </table> |
!!!back-token; # </table> |
| 3325 |
$token = {type => 'end tag', tag_name => 'caption'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'caption'}; |
| 3326 |
!!!back-token; |
!!!back-token; |
| 3327 |
$token = {type => 'end tag', |
$token = {type => END_TAG_TOKEN, |
| 3328 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3329 |
redo B; |
redo B; |
| 3330 |
} |
} |
| 3337 |
|
|
| 3338 |
$clear_up_to_marker->(); |
$clear_up_to_marker->(); |
| 3339 |
|
|
| 3340 |
$self->{insertion_mode} = 'in table'; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 3341 |
|
|
| 3342 |
## reprocess |
## reprocess |
| 3343 |
redo B; |
redo B; |
| 3344 |
} elsif ({ |
} elsif ({ |
| 3345 |
body => 1, col => 1, colgroup => 1, html => 1, |
body => 1, col => 1, colgroup => 1, html => 1, |
| 3346 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 3347 |
if ($self->{insertion_mode} eq 'in cell' or |
if ($self->{insertion_mode} & BODY_TABLE_IMS) { |
|
$self->{insertion_mode} eq 'in caption') { |
|
| 3348 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3349 |
## Ignore the token |
## Ignore the token |
| 3350 |
!!!next-token; |
!!!next-token; |
| 3356 |
tbody => 1, tfoot => 1, |
tbody => 1, tfoot => 1, |
| 3357 |
thead => 1, tr => 1, |
thead => 1, tr => 1, |
| 3358 |
}->{$token->{tag_name}} and |
}->{$token->{tag_name}} and |
| 3359 |
$self->{insertion_mode} eq 'in caption') { |
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 3360 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3361 |
## Ignore the token |
## Ignore the token |
| 3362 |
!!!next-token; |
!!!next-token; |
| 3364 |
} else { |
} else { |
| 3365 |
# |
# |
| 3366 |
} |
} |
| 3367 |
} else { |
} else { |
| 3368 |
# |
die "$0: $token->{type}: Unknown token type"; |
| 3369 |
} |
} |
| 3370 |
|
|
| 3371 |
$in_body->($insert_to_current); |
$insert = $insert_to_current; |
| 3372 |
redo B; |
# |
| 3373 |
} elsif ($self->{insertion_mode} eq 'in row' or |
} elsif ($self->{insertion_mode} & TABLE_IMS) { |
| 3374 |
$self->{insertion_mode} eq 'in table body' or |
if ($token->{type} == CHARACTER_TOKEN) { |
|
$self->{insertion_mode} eq 'in table') { |
|
|
if ($token->{type} eq 'character') { |
|
|
## NOTE: There are "character in table" code clones. |
|
| 3375 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 3376 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 3377 |
|
|
| 3428 |
|
|
| 3429 |
!!!next-token; |
!!!next-token; |
| 3430 |
redo B; |
redo B; |
| 3431 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 3432 |
if ({ |
if ({ |
| 3433 |
tr => ($self->{insertion_mode} ne 'in row'), |
tr => ($self->{insertion_mode} != IN_ROW_IM), |
| 3434 |
th => 1, td => 1, |
th => 1, td => 1, |
| 3435 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 3436 |
if ($self->{insertion_mode} eq 'in table') { |
if ($self->{insertion_mode} == IN_TABLE_IM) { |
| 3437 |
## Clear back to table context |
## Clear back to table context |
| 3438 |
while ($self->{open_elements}->[-1]->[1] ne 'table' and |
while ($self->{open_elements}->[-1]->[1] ne 'table' and |
| 3439 |
$self->{open_elements}->[-1]->[1] ne 'html') { |
$self->{open_elements}->[-1]->[1] ne 'html') { |
| 3442 |
} |
} |
| 3443 |
|
|
| 3444 |
!!!insert-element ('tbody'); |
!!!insert-element ('tbody'); |
| 3445 |
$self->{insertion_mode} = 'in table body'; |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 3446 |
## reprocess in the "in table body" insertion mode... |
## reprocess in the "in table body" insertion mode... |
| 3447 |
} |
} |
| 3448 |
|
|
| 3449 |
if ($self->{insertion_mode} eq 'in table body') { |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
| 3450 |
unless ($token->{tag_name} eq 'tr') { |
unless ($token->{tag_name} eq 'tr') { |
| 3451 |
!!!parse-error (type => 'missing start tag:tr'); |
!!!parse-error (type => 'missing start tag:tr'); |
| 3452 |
} |
} |
| 3459 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3460 |
} |
} |
| 3461 |
|
|
| 3462 |
$self->{insertion_mode} = 'in row'; |
$self->{insertion_mode} = IN_ROW_IM; |
| 3463 |
if ($token->{tag_name} eq 'tr') { |
if ($token->{tag_name} eq 'tr') { |
| 3464 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 3465 |
!!!next-token; |
!!!next-token; |
| 3479 |
} |
} |
| 3480 |
|
|
| 3481 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 3482 |
$self->{insertion_mode} = 'in cell'; |
$self->{insertion_mode} = IN_CELL_IM; |
| 3483 |
|
|
| 3484 |
push @$active_formatting_elements, ['#marker', '']; |
push @$active_formatting_elements, ['#marker', '']; |
| 3485 |
|
|
| 3488 |
} elsif ({ |
} elsif ({ |
| 3489 |
caption => 1, col => 1, colgroup => 1, |
caption => 1, col => 1, colgroup => 1, |
| 3490 |
tbody => 1, tfoot => 1, thead => 1, |
tbody => 1, tfoot => 1, thead => 1, |
| 3491 |
tr => 1, # $self->{insertion_mode} eq 'in row' |
tr => 1, # $self->{insertion_mode} == IN_ROW_IM |
| 3492 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 3493 |
if ($self->{insertion_mode} eq 'in row') { |
if ($self->{insertion_mode} == IN_ROW_IM) { |
| 3494 |
## As if </tr> |
## As if </tr> |
| 3495 |
## have an element in table scope |
## have an element in table scope |
| 3496 |
my $i; |
my $i; |
| 3521 |
} |
} |
| 3522 |
|
|
| 3523 |
pop @{$self->{open_elements}}; # tr |
pop @{$self->{open_elements}}; # tr |
| 3524 |
$self->{insertion_mode} = 'in table body'; |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 3525 |
if ($token->{tag_name} eq 'tr') { |
if ($token->{tag_name} eq 'tr') { |
| 3526 |
## reprocess |
## reprocess |
| 3527 |
redo B; |
redo B; |
| 3530 |
} |
} |
| 3531 |
} |
} |
| 3532 |
|
|
| 3533 |
if ($self->{insertion_mode} eq 'in table body') { |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
| 3534 |
## have an element in table scope |
## have an element in table scope |
| 3535 |
my $i; |
my $i; |
| 3536 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3569 |
## nop by definition |
## nop by definition |
| 3570 |
|
|
| 3571 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3572 |
$self->{insertion_mode} = 'in table'; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 3573 |
## reprocess in "in table" insertion mode... |
## reprocess in "in table" insertion mode... |
| 3574 |
} |
} |
| 3575 |
|
|
| 3582 |
} |
} |
| 3583 |
|
|
| 3584 |
!!!insert-element ('colgroup'); |
!!!insert-element ('colgroup'); |
| 3585 |
$self->{insertion_mode} = 'in column group'; |
$self->{insertion_mode} = IN_COLUMN_GROUP_IM; |
| 3586 |
## reprocess |
## reprocess |
| 3587 |
redo B; |
redo B; |
| 3588 |
} elsif ({ |
} elsif ({ |
| 3602 |
|
|
| 3603 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 3604 |
$self->{insertion_mode} = { |
$self->{insertion_mode} = { |
| 3605 |
caption => 'in caption', |
caption => IN_CAPTION_IM, |
| 3606 |
colgroup => 'in column group', |
colgroup => IN_COLUMN_GROUP_IM, |
| 3607 |
tbody => 'in table body', |
tbody => IN_TABLE_BODY_IM, |
| 3608 |
tfoot => 'in table body', |
tfoot => IN_TABLE_BODY_IM, |
| 3609 |
thead => 'in table body', |
thead => IN_TABLE_BODY_IM, |
| 3610 |
}->{$token->{tag_name}}; |
}->{$token->{tag_name}}; |
| 3611 |
!!!next-token; |
!!!next-token; |
| 3612 |
redo B; |
redo B; |
| 3614 |
die "$0: in table: <>: $token->{tag_name}"; |
die "$0: in table: <>: $token->{tag_name}"; |
| 3615 |
} |
} |
| 3616 |
} elsif ($token->{tag_name} eq 'table') { |
} elsif ($token->{tag_name} eq 'table') { |
|
## NOTE: There are code clones for this "table in table" |
|
| 3617 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3618 |
|
|
| 3619 |
## As if </table> |
## As if </table> |
| 3644 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 3645 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3646 |
!!!back-token; # <table> |
!!!back-token; # <table> |
| 3647 |
$token = {type => 'end tag', tag_name => 'table'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'table'}; |
| 3648 |
!!!back-token; |
!!!back-token; |
| 3649 |
$token = {type => 'end tag', |
$token = {type => END_TAG_TOKEN, |
| 3650 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3651 |
redo B; |
redo B; |
| 3652 |
} |
} |
| 3661 |
|
|
| 3662 |
## reprocess |
## reprocess |
| 3663 |
redo B; |
redo B; |
| 3664 |
} else { |
} else { |
| 3665 |
# |
!!!parse-error (type => 'in table:'.$token->{tag_name}); |
| 3666 |
} |
|
| 3667 |
} elsif ($token->{type} eq 'end tag') { |
$insert = $insert_to_foster; |
| 3668 |
|
# |
| 3669 |
|
} |
| 3670 |
|
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 3671 |
if ($token->{tag_name} eq 'tr' and |
if ($token->{tag_name} eq 'tr' and |
| 3672 |
$self->{insertion_mode} eq 'in row') { |
$self->{insertion_mode} == IN_ROW_IM) { |
| 3673 |
## have an element in table scope |
## have an element in table scope |
| 3674 |
my $i; |
my $i; |
| 3675 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3699 |
} |
} |
| 3700 |
|
|
| 3701 |
pop @{$self->{open_elements}}; # tr |
pop @{$self->{open_elements}}; # tr |
| 3702 |
$self->{insertion_mode} = 'in table body'; |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 3703 |
!!!next-token; |
!!!next-token; |
| 3704 |
redo B; |
redo B; |
| 3705 |
} elsif ($token->{tag_name} eq 'table') { |
} elsif ($token->{tag_name} eq 'table') { |
| 3706 |
if ($self->{insertion_mode} eq 'in row') { |
if ($self->{insertion_mode} == IN_ROW_IM) { |
| 3707 |
## As if </tr> |
## As if </tr> |
| 3708 |
## have an element in table scope |
## have an element in table scope |
| 3709 |
my $i; |
my $i; |
| 3734 |
} |
} |
| 3735 |
|
|
| 3736 |
pop @{$self->{open_elements}}; # tr |
pop @{$self->{open_elements}}; # tr |
| 3737 |
$self->{insertion_mode} = 'in table body'; |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 3738 |
## reprocess in the "in table body" insertion mode... |
## reprocess in the "in table body" insertion mode... |
| 3739 |
} |
} |
| 3740 |
|
|
| 3741 |
if ($self->{insertion_mode} eq 'in table body') { |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
| 3742 |
## have an element in table scope |
## have an element in table scope |
| 3743 |
my $i; |
my $i; |
| 3744 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3777 |
## nop by definition |
## nop by definition |
| 3778 |
|
|
| 3779 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3780 |
$self->{insertion_mode} = 'in table'; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 3781 |
## reprocess in the "in table" insertion mode... |
## reprocess in the "in table" insertion mode... |
| 3782 |
} |
} |
| 3783 |
|
|
| 3808 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 3809 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3810 |
!!!back-token; |
!!!back-token; |
| 3811 |
$token = {type => 'end tag', |
$token = {type => END_TAG_TOKEN, |
| 3812 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3813 |
redo B; |
redo B; |
| 3814 |
} |
} |
| 3826 |
} elsif ({ |
} elsif ({ |
| 3827 |
tbody => 1, tfoot => 1, thead => 1, |
tbody => 1, tfoot => 1, thead => 1, |
| 3828 |
}->{$token->{tag_name}} and |
}->{$token->{tag_name}} and |
| 3829 |
($self->{insertion_mode} eq 'in row' or |
$self->{insertion_mode} & ROW_IMS) { |
| 3830 |
$self->{insertion_mode} eq 'in table body')) { |
if ($self->{insertion_mode} == IN_ROW_IM) { |
|
if ($self->{insertion_mode} eq 'in row') { |
|
| 3831 |
## have an element in table scope |
## have an element in table scope |
| 3832 |
my $i; |
my $i; |
| 3833 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3878 |
} |
} |
| 3879 |
|
|
| 3880 |
pop @{$self->{open_elements}}; # tr |
pop @{$self->{open_elements}}; # tr |
| 3881 |
$self->{insertion_mode} = 'in table body'; |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 3882 |
## reprocess in the "in table body" insertion mode... |
## reprocess in the "in table body" insertion mode... |
| 3883 |
} |
} |
| 3884 |
|
|
| 3911 |
} |
} |
| 3912 |
|
|
| 3913 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3914 |
$self->{insertion_mode} = 'in table'; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 3915 |
!!!next-token; |
!!!next-token; |
| 3916 |
redo B; |
redo B; |
| 3917 |
} elsif ({ |
} elsif ({ |
| 3918 |
body => 1, caption => 1, col => 1, colgroup => 1, |
body => 1, caption => 1, col => 1, colgroup => 1, |
| 3919 |
html => 1, td => 1, th => 1, |
html => 1, td => 1, th => 1, |
| 3920 |
tr => 1, # $self->{insertion_mode} eq 'in row' |
tr => 1, # $self->{insertion_mode} == IN_ROW_IM |
| 3921 |
tbody => 1, tfoot => 1, thead => 1, # $self->{insertion_mode} eq 'in table' |
tbody => 1, tfoot => 1, thead => 1, # $self->{insertion_mode} == IN_TABLE_IM |
| 3922 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 3923 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3924 |
## Ignore the token |
## Ignore the token |
| 3925 |
!!!next-token; |
!!!next-token; |
| 3926 |
redo B; |
redo B; |
| 3927 |
} else { |
} else { |
| 3928 |
# |
!!!parse-error (type => 'in table:/'.$token->{tag_name}); |
|
} |
|
|
} else { |
|
|
die "$0: $token->{type}: Unknown token type"; |
|
|
} |
|
| 3929 |
|
|
| 3930 |
!!!parse-error (type => 'in table:'.$token->{tag_name}); |
$insert = $insert_to_foster; |
| 3931 |
$in_body->($insert_to_foster); |
# |
| 3932 |
redo B; |
} |
| 3933 |
} elsif ($self->{insertion_mode} eq 'in column group') { |
} else { |
| 3934 |
if ($token->{type} eq 'character') { |
die "$0: $token->{type}: Unknown token type"; |
| 3935 |
|
} |
| 3936 |
|
} elsif ($self->{insertion_mode} == IN_COLUMN_GROUP_IM) { |
| 3937 |
|
if ($token->{type} == CHARACTER_TOKEN) { |
| 3938 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 3939 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 3940 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 3944 |
} |
} |
| 3945 |
|
|
| 3946 |
# |
# |
| 3947 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 3948 |
if ($token->{tag_name} eq 'col') { |
if ($token->{tag_name} eq 'col') { |
| 3949 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 3950 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3953 |
} else { |
} else { |
| 3954 |
# |
# |
| 3955 |
} |
} |
| 3956 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 3957 |
if ($token->{tag_name} eq 'colgroup') { |
if ($token->{tag_name} eq 'colgroup') { |
| 3958 |
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
| 3959 |
!!!parse-error (type => 'unmatched end tag:colgroup'); |
!!!parse-error (type => 'unmatched end tag:colgroup'); |
| 3962 |
redo B; |
redo B; |
| 3963 |
} else { |
} else { |
| 3964 |
pop @{$self->{open_elements}}; # colgroup |
pop @{$self->{open_elements}}; # colgroup |
| 3965 |
$self->{insertion_mode} = 'in table'; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 3966 |
!!!next-token; |
!!!next-token; |
| 3967 |
redo B; |
redo B; |
| 3968 |
} |
} |
| 3986 |
redo B; |
redo B; |
| 3987 |
} else { |
} else { |
| 3988 |
pop @{$self->{open_elements}}; # colgroup |
pop @{$self->{open_elements}}; # colgroup |
| 3989 |
$self->{insertion_mode} = 'in table'; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 3990 |
## reprocess |
## reprocess |
| 3991 |
redo B; |
redo B; |
| 3992 |
} |
} |
| 3993 |
} elsif ($self->{insertion_mode} eq 'in select') { |
} elsif ($self->{insertion_mode} == IN_SELECT_IM) { |
| 3994 |
if ($token->{type} eq 'character') { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 3995 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
| 3996 |
!!!next-token; |
!!!next-token; |
| 3997 |
redo B; |
redo B; |
| 3998 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 3999 |
if ($token->{tag_name} eq 'option') { |
if ($token->{tag_name} eq 'option') { |
| 4000 |
if ($self->{open_elements}->[-1]->[1] eq 'option') { |
if ($self->{open_elements}->[-1]->[1] eq 'option') { |
| 4001 |
## As if </option> |
## As if </option> |
| 4048 |
|
|
| 4049 |
!!!next-token; |
!!!next-token; |
| 4050 |
redo B; |
redo B; |
| 4051 |
} else { |
} else { |
| 4052 |
# |
!!!parse-error (type => 'in select:'.$token->{tag_name}); |
| 4053 |
} |
## Ignore the token |
| 4054 |
} elsif ($token->{type} eq 'end tag') { |
!!!next-token; |
| 4055 |
|
redo B; |
| 4056 |
|
} |
| 4057 |
|
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 4058 |
if ($token->{tag_name} eq 'optgroup') { |
if ($token->{tag_name} eq 'optgroup') { |
| 4059 |
if ($self->{open_elements}->[-1]->[1] eq 'option' and |
if ($self->{open_elements}->[-1]->[1] eq 'option' and |
| 4060 |
$self->{open_elements}->[-2]->[1] eq 'optgroup') { |
$self->{open_elements}->[-2]->[1] eq 'optgroup') { |
| 4156 |
|
|
| 4157 |
## reprocess |
## reprocess |
| 4158 |
redo B; |
redo B; |
| 4159 |
} else { |
} else { |
| 4160 |
# |
!!!parse-error (type => 'in select:/'.$token->{tag_name}); |
|
} |
|
|
} else { |
|
|
# |
|
|
} |
|
|
|
|
|
!!!parse-error (type => 'in select:'.$token->{tag_name}); |
|
| 4161 |
## Ignore the token |
## Ignore the token |
| 4162 |
!!!next-token; |
!!!next-token; |
| 4163 |
redo B; |
redo B; |
| 4164 |
} elsif ($self->{insertion_mode} eq 'after body') { |
} |
| 4165 |
if ($token->{type} eq 'character') { |
} else { |
| 4166 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
die "$0: $token->{type}: Unknown token type"; |
| 4167 |
my $data = $1; |
} |
| 4168 |
## As if in body |
} elsif ($self->{insertion_mode} & BODY_AFTER_IMS) { |
| 4169 |
$reconstruct_active_formatting_elements->($insert_to_current); |
if ($token->{type} == CHARACTER_TOKEN) { |
| 4170 |
|
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 4171 |
|
my $data = $1; |
| 4172 |
|
## As if in body |
| 4173 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4174 |
|
|
| 4175 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 4176 |
|
|
| 4177 |
|
unless (length $token->{data}) { |
| 4178 |
|
!!!next-token; |
| 4179 |
|
redo B; |
| 4180 |
|
} |
| 4181 |
|
} |
| 4182 |
|
|
| 4183 |
|
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 4184 |
|
!!!parse-error (type => 'after html:#character'); |
| 4185 |
|
|
| 4186 |
unless (length $token->{data}) { |
## Reprocess in the "main" phase, "after body" insertion mode... |
| 4187 |
!!!next-token; |
} |
| 4188 |
redo B; |
|
| 4189 |
} |
## "after body" insertion mode |
| 4190 |
} |
!!!parse-error (type => 'after body:#character'); |
| 4191 |
|
|
| 4192 |
# |
$self->{insertion_mode} = IN_BODY_IM; |
| 4193 |
!!!parse-error (type => 'after body:#character'); |
## reprocess |
| 4194 |
} elsif ($token->{type} eq 'start tag') { |
redo B; |
| 4195 |
!!!parse-error (type => 'after body:'.$token->{tag_name}); |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 4196 |
# |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 4197 |
} elsif ($token->{type} eq 'end tag') { |
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
| 4198 |
if ($token->{tag_name} eq 'html') { |
|
| 4199 |
if (defined $self->{inner_html_node}) { |
## Reprocess in the "main" phase, "after body" insertion mode... |
| 4200 |
!!!parse-error (type => 'unmatched end tag:html'); |
} |
| 4201 |
## Ignore the token |
|
| 4202 |
!!!next-token; |
## "after body" insertion mode |
| 4203 |
redo B; |
!!!parse-error (type => 'after body:'.$token->{tag_name}); |
| 4204 |
} else { |
|
| 4205 |
$previous_insertion_mode = $self->{insertion_mode}; |
$self->{insertion_mode} = IN_BODY_IM; |
| 4206 |
$self->{insertion_mode} = 'trailing end'; |
## reprocess |
| 4207 |
!!!next-token; |
redo B; |
| 4208 |
redo B; |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 4209 |
} |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 4210 |
} else { |
!!!parse-error (type => 'after html:/'.$token->{tag_name}); |
| 4211 |
!!!parse-error (type => 'after body:/'.$token->{tag_name}); |
|
| 4212 |
} |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 4213 |
|
## Reprocess in the "main" phase, "after body" insertion mode... |
| 4214 |
|
} |
| 4215 |
|
|
| 4216 |
|
## "after body" insertion mode |
| 4217 |
|
if ($token->{tag_name} eq 'html') { |
| 4218 |
|
if (defined $self->{inner_html_node}) { |
| 4219 |
|
!!!parse-error (type => 'unmatched end tag:html'); |
| 4220 |
|
## Ignore the token |
| 4221 |
|
!!!next-token; |
| 4222 |
|
redo B; |
| 4223 |
} else { |
} else { |
| 4224 |
die "$0: $token->{type}: Unknown token type"; |
$self->{insertion_mode} = AFTER_HTML_BODY_IM; |
| 4225 |
|
!!!next-token; |
| 4226 |
|
redo B; |
| 4227 |
} |
} |
| 4228 |
|
} else { |
| 4229 |
|
!!!parse-error (type => 'after body:/'.$token->{tag_name}); |
| 4230 |
|
|
| 4231 |
$self->{insertion_mode} = 'in body'; |
$self->{insertion_mode} = IN_BODY_IM; |
| 4232 |
## reprocess |
## reprocess |
| 4233 |
redo B; |
redo B; |
| 4234 |
} elsif ($self->{insertion_mode} eq 'in frameset') { |
} |
| 4235 |
if ($token->{type} eq 'character') { |
} else { |
| 4236 |
|
die "$0: $token->{type}: Unknown token type"; |
| 4237 |
|
} |
| 4238 |
|
} elsif ($self->{insertion_mode} & FRAME_IMS) { |
| 4239 |
|
if ($token->{type} == CHARACTER_TOKEN) { |
| 4240 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 4241 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 4242 |
|
|
| 4243 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 4244 |
!!!next-token; |
!!!next-token; |
| 4245 |
redo B; |
redo B; |
| 4246 |
} |
} |
| 4247 |
} |
} |
| 4248 |
|
|
| 4249 |
|
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
| 4250 |
|
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 4251 |
|
!!!parse-error (type => 'in frameset:#character'); |
| 4252 |
|
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 4253 |
|
!!!parse-error (type => 'after frameset:#character'); |
| 4254 |
|
} else { # "after html frameset" |
| 4255 |
|
!!!parse-error (type => 'after html:#character'); |
| 4256 |
|
|
| 4257 |
|
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 4258 |
|
## Reprocess in the "main" phase, "after frameset"... |
| 4259 |
|
!!!parse-error (type => 'after frameset:#character'); |
| 4260 |
|
} |
| 4261 |
|
|
| 4262 |
|
## Ignore the token. |
| 4263 |
|
if (length $token->{data}) { |
| 4264 |
|
## reprocess the rest of characters |
| 4265 |
|
} else { |
| 4266 |
|
!!!next-token; |
| 4267 |
|
} |
| 4268 |
|
redo B; |
| 4269 |
|
} |
| 4270 |
|
|
| 4271 |
|
die qq[$0: Character "$token->{data}"]; |
| 4272 |
|
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 4273 |
|
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 4274 |
|
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
| 4275 |
|
|
| 4276 |
!!!parse-error (type => 'in frameset:#character'); |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 4277 |
## Ignore the token |
## Process in the "main" phase, "after frameset" insertion mode... |
| 4278 |
!!!next-token; |
} |
| 4279 |
redo B; |
|
| 4280 |
} elsif ($token->{type} eq 'start tag') { |
if ($token->{tag_name} eq 'frameset' and |
| 4281 |
if ($token->{tag_name} eq 'frameset') { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 4282 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 4283 |
!!!next-token; |
!!!next-token; |
| 4284 |
redo B; |
redo B; |
| 4285 |
} elsif ($token->{tag_name} eq 'frame') { |
} elsif ($token->{tag_name} eq 'frame' and |
| 4286 |
|
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 4287 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 4288 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4289 |
!!!next-token; |
!!!next-token; |
| 4293 |
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert_to_current); |
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert_to_current); |
| 4294 |
redo B; |
redo B; |
| 4295 |
} else { |
} else { |
| 4296 |
!!!parse-error (type => 'in frameset:'.$token->{tag_name}); |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 4297 |
|
!!!parse-error (type => 'in frameset:'.$token->{tag_name}); |
| 4298 |
|
} else { |
| 4299 |
|
!!!parse-error (type => 'after frameset:'.$token->{tag_name}); |
| 4300 |
|
} |
| 4301 |
## Ignore the token |
## Ignore the token |
| 4302 |
!!!next-token; |
!!!next-token; |
| 4303 |
redo B; |
redo B; |
| 4304 |
} |
} |
| 4305 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 4306 |
if ($token->{tag_name} eq 'frameset') { |
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 4307 |
|
!!!parse-error (type => 'after html:/'.$token->{tag_name}); |
| 4308 |
|
|
| 4309 |
|
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 4310 |
|
## Process in the "main" phase, "after frameset" insertion mode... |
| 4311 |
|
} |
| 4312 |
|
|
| 4313 |
|
if ($token->{tag_name} eq 'frameset' and |
| 4314 |
|
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 4315 |
if ($self->{open_elements}->[-1]->[1] eq 'html' and |
if ($self->{open_elements}->[-1]->[1] eq 'html' and |
| 4316 |
@{$self->{open_elements}} == 1) { |
@{$self->{open_elements}} == 1) { |
| 4317 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 4324 |
|
|
| 4325 |
if (not defined $self->{inner_html_node} and |
if (not defined $self->{inner_html_node} and |
| 4326 |
$self->{open_elements}->[-1]->[1] ne 'frameset') { |
$self->{open_elements}->[-1]->[1] ne 'frameset') { |
| 4327 |
$self->{insertion_mode} = 'after frameset'; |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 4328 |
} |
} |
| 4329 |
redo B; |
redo B; |
| 4330 |
|
} elsif ($token->{tag_name} eq 'html' and |
| 4331 |
|
$self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 4332 |
|
$self->{insertion_mode} = AFTER_HTML_FRAMESET_IM; |
| 4333 |
|
!!!next-token; |
| 4334 |
|
redo B; |
| 4335 |
} else { |
} else { |
| 4336 |
!!!parse-error (type => 'in frameset:/'.$token->{tag_name}); |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 4337 |
|
!!!parse-error (type => 'in frameset:/'.$token->{tag_name}); |
| 4338 |
|
} else { |
| 4339 |
|
!!!parse-error (type => 'after frameset:/'.$token->{tag_name}); |
| 4340 |
|
} |
| 4341 |
## Ignore the token |
## Ignore the token |
| 4342 |
!!!next-token; |
!!!next-token; |
| 4343 |
redo B; |
redo B; |
| 4345 |
} else { |
} else { |
| 4346 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 4347 |
} |
} |
|
} elsif ($self->{insertion_mode} eq 'after frameset') { |
|
|
if ($token->{type} eq 'character') { |
|
|
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
|
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
|
| 4348 |
|
|
| 4349 |
unless (length $token->{data}) { |
## ISSUE: An issue in spec here |
| 4350 |
!!!next-token; |
} else { |
| 4351 |
redo B; |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
| 4352 |
} |
} |
|
} |
|
| 4353 |
|
|
| 4354 |
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
## "in body" insertion mode |
| 4355 |
!!!parse-error (type => 'after frameset:#character'); |
if ($token->{type} == START_TAG_TOKEN) { |
| 4356 |
|
if ($token->{tag_name} eq 'script') { |
| 4357 |
|
## NOTE: This is an "as if in head" code clone |
| 4358 |
|
$script_start_tag->($insert); |
| 4359 |
|
redo B; |
| 4360 |
|
} elsif ($token->{tag_name} eq 'style') { |
| 4361 |
|
## NOTE: This is an "as if in head" code clone |
| 4362 |
|
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert); |
| 4363 |
|
redo B; |
| 4364 |
|
} elsif ({ |
| 4365 |
|
base => 1, link => 1, |
| 4366 |
|
}->{$token->{tag_name}}) { |
| 4367 |
|
## NOTE: This is an "as if in head" code clone, only "-t" differs |
| 4368 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4369 |
|
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 4370 |
|
!!!next-token; |
| 4371 |
|
redo B; |
| 4372 |
|
} elsif ($token->{tag_name} eq 'meta') { |
| 4373 |
|
## NOTE: This is an "as if in head" code clone, only "-t" differs |
| 4374 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4375 |
|
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 4376 |
|
|
| 4377 |
## Ignore the token. |
unless ($self->{confident}) { |
| 4378 |
if (length $token->{data}) { |
my $charset; |
| 4379 |
## reprocess the rest of characters |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
| 4380 |
} else { |
$charset = $token->{attributes}->{charset}->{value}; |
| 4381 |
!!!next-token; |
} |
| 4382 |
} |
if ($token->{attributes}->{'http-equiv'}) { |
| 4383 |
redo B; |
## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition. |
| 4384 |
} |
if ($token->{attributes}->{'http-equiv'}->{value} |
| 4385 |
|
=~ /\A[^;]*;[\x09-\x0D\x20]*charset[\x09-\x0D\x20]*= |
| 4386 |
|
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
| 4387 |
|
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
| 4388 |
|
$charset = defined $1 ? $1 : defined $2 ? $2 : $3; |
| 4389 |
|
} ## TODO: And if supported |
| 4390 |
|
} |
| 4391 |
|
## TODO: Change the encoding |
| 4392 |
|
} |
| 4393 |
|
|
| 4394 |
die qq[$0: Character "$token->{data}"]; |
!!!next-token; |
| 4395 |
} elsif ($token->{type} eq 'start tag') { |
redo B; |
| 4396 |
if ($token->{tag_name} eq 'noframes') { |
} elsif ($token->{tag_name} eq 'title') { |
| 4397 |
## NOTE: As if in body. |
!!!parse-error (type => 'in body:title'); |
| 4398 |
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert_to_current); |
## NOTE: This is an "as if in head" code clone |
| 4399 |
redo B; |
$parse_rcdata->(RCDATA_CONTENT_MODEL, sub { |
| 4400 |
} else { |
if (defined $self->{head_element}) { |
| 4401 |
!!!parse-error (type => 'after frameset:'.$token->{tag_name}); |
$self->{head_element}->append_child ($_[0]); |
| 4402 |
|
} else { |
| 4403 |
|
$insert->($_[0]); |
| 4404 |
|
} |
| 4405 |
|
}); |
| 4406 |
|
redo B; |
| 4407 |
|
} elsif ($token->{tag_name} eq 'body') { |
| 4408 |
|
!!!parse-error (type => 'in body:body'); |
| 4409 |
|
|
| 4410 |
|
if (@{$self->{open_elements}} == 1 or |
| 4411 |
|
$self->{open_elements}->[1]->[1] ne 'body') { |
| 4412 |
## Ignore the token |
## Ignore the token |
| 4413 |
|
} else { |
| 4414 |
|
my $body_el = $self->{open_elements}->[1]->[0]; |
| 4415 |
|
for my $attr_name (keys %{$token->{attributes}}) { |
| 4416 |
|
unless ($body_el->has_attribute_ns (undef, $attr_name)) { |
| 4417 |
|
$body_el->set_attribute_ns |
| 4418 |
|
(undef, [undef, $attr_name], |
| 4419 |
|
$token->{attributes}->{$attr_name}->{value}); |
| 4420 |
|
} |
| 4421 |
|
} |
| 4422 |
|
} |
| 4423 |
|
!!!next-token; |
| 4424 |
|
redo B; |
| 4425 |
|
} elsif ({ |
| 4426 |
|
address => 1, blockquote => 1, center => 1, dir => 1, |
| 4427 |
|
div => 1, dl => 1, fieldset => 1, listing => 1, |
| 4428 |
|
menu => 1, ol => 1, p => 1, ul => 1, |
| 4429 |
|
pre => 1, |
| 4430 |
|
}->{$token->{tag_name}}) { |
| 4431 |
|
## has a p element in scope |
| 4432 |
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4433 |
|
if ($_->[1] eq 'p') { |
| 4434 |
|
!!!back-token; |
| 4435 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4436 |
|
redo B; |
| 4437 |
|
} elsif ({ |
| 4438 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4439 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4440 |
|
}->{$_->[1]}) { |
| 4441 |
|
last INSCOPE; |
| 4442 |
|
} |
| 4443 |
|
} # INSCOPE |
| 4444 |
|
|
| 4445 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4446 |
|
if ($token->{tag_name} eq 'pre') { |
| 4447 |
|
!!!next-token; |
| 4448 |
|
if ($token->{type} == CHARACTER_TOKEN) { |
| 4449 |
|
$token->{data} =~ s/^\x0A//; |
| 4450 |
|
unless (length $token->{data}) { |
| 4451 |
|
!!!next-token; |
| 4452 |
|
} |
| 4453 |
|
} |
| 4454 |
|
} else { |
| 4455 |
!!!next-token; |
!!!next-token; |
|
redo B; |
|
| 4456 |
} |
} |
| 4457 |
} elsif ($token->{type} eq 'end tag') { |
redo B; |
| 4458 |
if ($token->{tag_name} eq 'html') { |
} elsif ($token->{tag_name} eq 'form') { |
| 4459 |
$previous_insertion_mode = $self->{insertion_mode}; |
if (defined $self->{form_element}) { |
| 4460 |
$self->{insertion_mode} = 'trailing end'; |
!!!parse-error (type => 'in form:form'); |
| 4461 |
|
## Ignore the token |
| 4462 |
!!!next-token; |
!!!next-token; |
| 4463 |
redo B; |
redo B; |
| 4464 |
} else { |
} else { |
| 4465 |
!!!parse-error (type => 'after frameset:/'.$token->{tag_name}); |
## has a p element in scope |
| 4466 |
## Ignore the token |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4467 |
|
if ($_->[1] eq 'p') { |
| 4468 |
|
!!!back-token; |
| 4469 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4470 |
|
redo B; |
| 4471 |
|
} elsif ({ |
| 4472 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4473 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4474 |
|
}->{$_->[1]}) { |
| 4475 |
|
last INSCOPE; |
| 4476 |
|
} |
| 4477 |
|
} # INSCOPE |
| 4478 |
|
|
| 4479 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4480 |
|
$self->{form_element} = $self->{open_elements}->[-1]->[0]; |
| 4481 |
!!!next-token; |
!!!next-token; |
| 4482 |
redo B; |
redo B; |
| 4483 |
} |
} |
| 4484 |
} else { |
} elsif ($token->{tag_name} eq 'li') { |
| 4485 |
die "$0: $token->{type}: Unknown token type"; |
## has a p element in scope |
| 4486 |
} |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4487 |
|
if ($_->[1] eq 'p') { |
| 4488 |
|
!!!back-token; |
| 4489 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4490 |
|
redo B; |
| 4491 |
|
} elsif ({ |
| 4492 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4493 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4494 |
|
}->{$_->[1]}) { |
| 4495 |
|
last INSCOPE; |
| 4496 |
|
} |
| 4497 |
|
} # INSCOPE |
| 4498 |
|
|
| 4499 |
|
## Step 1 |
| 4500 |
|
my $i = -1; |
| 4501 |
|
my $node = $self->{open_elements}->[$i]; |
| 4502 |
|
LI: { |
| 4503 |
|
## Step 2 |
| 4504 |
|
if ($node->[1] eq 'li') { |
| 4505 |
|
if ($i != -1) { |
| 4506 |
|
!!!parse-error (type => 'end tag missing:'. |
| 4507 |
|
$self->{open_elements}->[-1]->[1]); |
| 4508 |
|
} |
| 4509 |
|
splice @{$self->{open_elements}}, $i; |
| 4510 |
|
last LI; |
| 4511 |
|
} |
| 4512 |
|
|
| 4513 |
|
## Step 3 |
| 4514 |
|
if (not $formatting_category->{$node->[1]} and |
| 4515 |
|
#not $phrasing_category->{$node->[1]} and |
| 4516 |
|
($special_category->{$node->[1]} or |
| 4517 |
|
$scoping_category->{$node->[1]}) and |
| 4518 |
|
$node->[1] ne 'address' and $node->[1] ne 'div') { |
| 4519 |
|
last LI; |
| 4520 |
|
} |
| 4521 |
|
|
| 4522 |
|
## Step 4 |
| 4523 |
|
$i--; |
| 4524 |
|
$node = $self->{open_elements}->[$i]; |
| 4525 |
|
redo LI; |
| 4526 |
|
} # LI |
| 4527 |
|
|
| 4528 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4529 |
|
!!!next-token; |
| 4530 |
|
redo B; |
| 4531 |
|
} elsif ($token->{tag_name} eq 'dd' or $token->{tag_name} eq 'dt') { |
| 4532 |
|
## has a p element in scope |
| 4533 |
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4534 |
|
if ($_->[1] eq 'p') { |
| 4535 |
|
!!!back-token; |
| 4536 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4537 |
|
redo B; |
| 4538 |
|
} elsif ({ |
| 4539 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4540 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4541 |
|
}->{$_->[1]}) { |
| 4542 |
|
last INSCOPE; |
| 4543 |
|
} |
| 4544 |
|
} # INSCOPE |
| 4545 |
|
|
| 4546 |
|
## Step 1 |
| 4547 |
|
my $i = -1; |
| 4548 |
|
my $node = $self->{open_elements}->[$i]; |
| 4549 |
|
LI: { |
| 4550 |
|
## Step 2 |
| 4551 |
|
if ($node->[1] eq 'dt' or $node->[1] eq 'dd') { |
| 4552 |
|
if ($i != -1) { |
| 4553 |
|
!!!parse-error (type => 'end tag missing:'. |
| 4554 |
|
$self->{open_elements}->[-1]->[1]); |
| 4555 |
|
} |
| 4556 |
|
splice @{$self->{open_elements}}, $i; |
| 4557 |
|
last LI; |
| 4558 |
|
} |
| 4559 |
|
|
| 4560 |
|
## Step 3 |
| 4561 |
|
if (not $formatting_category->{$node->[1]} and |
| 4562 |
|
#not $phrasing_category->{$node->[1]} and |
| 4563 |
|
($special_category->{$node->[1]} or |
| 4564 |
|
$scoping_category->{$node->[1]}) and |
| 4565 |
|
$node->[1] ne 'address' and $node->[1] ne 'div') { |
| 4566 |
|
last LI; |
| 4567 |
|
} |
| 4568 |
|
|
| 4569 |
|
## Step 4 |
| 4570 |
|
$i--; |
| 4571 |
|
$node = $self->{open_elements}->[$i]; |
| 4572 |
|
redo LI; |
| 4573 |
|
} # LI |
| 4574 |
|
|
| 4575 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4576 |
|
!!!next-token; |
| 4577 |
|
redo B; |
| 4578 |
|
} elsif ($token->{tag_name} eq 'plaintext') { |
| 4579 |
|
## has a p element in scope |
| 4580 |
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4581 |
|
if ($_->[1] eq 'p') { |
| 4582 |
|
!!!back-token; |
| 4583 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4584 |
|
redo B; |
| 4585 |
|
} elsif ({ |
| 4586 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4587 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4588 |
|
}->{$_->[1]}) { |
| 4589 |
|
last INSCOPE; |
| 4590 |
|
} |
| 4591 |
|
} # INSCOPE |
| 4592 |
|
|
| 4593 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4594 |
|
|
| 4595 |
|
$self->{content_model} = PLAINTEXT_CONTENT_MODEL; |
| 4596 |
|
|
| 4597 |
|
!!!next-token; |
| 4598 |
|
redo B; |
| 4599 |
|
} elsif ({ |
| 4600 |
|
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
| 4601 |
|
}->{$token->{tag_name}}) { |
| 4602 |
|
## has a p element in scope |
| 4603 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4604 |
|
my $node = $self->{open_elements}->[$_]; |
| 4605 |
|
if ($node->[1] eq 'p') { |
| 4606 |
|
!!!back-token; |
| 4607 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4608 |
|
redo B; |
| 4609 |
|
} elsif ({ |
| 4610 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4611 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4612 |
|
}->{$node->[1]}) { |
| 4613 |
|
last INSCOPE; |
| 4614 |
|
} |
| 4615 |
|
} # INSCOPE |
| 4616 |
|
|
| 4617 |
|
## NOTE: See <http://html5.org/tools/web-apps-tracker?from=925&to=926> |
| 4618 |
|
## has an element in scope |
| 4619 |
|
#my $i; |
| 4620 |
|
#INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4621 |
|
# my $node = $self->{open_elements}->[$_]; |
| 4622 |
|
# if ({ |
| 4623 |
|
# h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
| 4624 |
|
# }->{$node->[1]}) { |
| 4625 |
|
# $i = $_; |
| 4626 |
|
# last INSCOPE; |
| 4627 |
|
# } elsif ({ |
| 4628 |
|
# table => 1, caption => 1, td => 1, th => 1, |
| 4629 |
|
# button => 1, marquee => 1, object => 1, html => 1, |
| 4630 |
|
# }->{$node->[1]}) { |
| 4631 |
|
# last INSCOPE; |
| 4632 |
|
# } |
| 4633 |
|
#} # INSCOPE |
| 4634 |
|
# |
| 4635 |
|
#if (defined $i) { |
| 4636 |
|
# !!! parse-error (type => 'in hn:hn'); |
| 4637 |
|
# splice @{$self->{open_elements}}, $i; |
| 4638 |
|
#} |
| 4639 |
|
|
| 4640 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4641 |
|
|
| 4642 |
|
!!!next-token; |
| 4643 |
|
redo B; |
| 4644 |
|
} elsif ($token->{tag_name} eq 'a') { |
| 4645 |
|
AFE: for my $i (reverse 0..$#$active_formatting_elements) { |
| 4646 |
|
my $node = $active_formatting_elements->[$i]; |
| 4647 |
|
if ($node->[1] eq 'a') { |
| 4648 |
|
!!!parse-error (type => 'in a:a'); |
| 4649 |
|
|
| 4650 |
|
!!!back-token; |
| 4651 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'a'}; |
| 4652 |
|
$formatting_end_tag->($token->{tag_name}); |
| 4653 |
|
|
| 4654 |
|
AFE2: for (reverse 0..$#$active_formatting_elements) { |
| 4655 |
|
if ($active_formatting_elements->[$_]->[0] eq $node->[0]) { |
| 4656 |
|
splice @$active_formatting_elements, $_, 1; |
| 4657 |
|
last AFE2; |
| 4658 |
|
} |
| 4659 |
|
} # AFE2 |
| 4660 |
|
OE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4661 |
|
if ($self->{open_elements}->[$_]->[0] eq $node->[0]) { |
| 4662 |
|
splice @{$self->{open_elements}}, $_, 1; |
| 4663 |
|
last OE; |
| 4664 |
|
} |
| 4665 |
|
} # OE |
| 4666 |
|
last AFE; |
| 4667 |
|
} elsif ($node->[0] eq '#marker') { |
| 4668 |
|
last AFE; |
| 4669 |
|
} |
| 4670 |
|
} # AFE |
| 4671 |
|
|
| 4672 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4673 |
|
|
| 4674 |
## ISSUE: An issue in spec here |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4675 |
} elsif ($self->{insertion_mode} eq 'trailing end') { |
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
| 4676 |
## states in the main stage is preserved yet # MUST |
|
| 4677 |
|
!!!next-token; |
| 4678 |
if ($token->{type} eq 'character') { |
redo B; |
| 4679 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
} elsif ({ |
| 4680 |
my $data = $1; |
b => 1, big => 1, em => 1, font => 1, i => 1, |
| 4681 |
## As if in the main phase. |
s => 1, small => 1, strile => 1, |
| 4682 |
## NOTE: The insertion mode in the main phase |
strong => 1, tt => 1, u => 1, |
| 4683 |
## just before the phase has been changed to the trailing |
}->{$token->{tag_name}}) { |
| 4684 |
## end phase is either "after body" or "after frameset". |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4685 |
$reconstruct_active_formatting_elements->($insert_to_current); |
|
| 4686 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4687 |
|
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
| 4688 |
|
|
| 4689 |
|
!!!next-token; |
| 4690 |
|
redo B; |
| 4691 |
|
} elsif ($token->{tag_name} eq 'nobr') { |
| 4692 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4693 |
|
|
| 4694 |
|
## has a |nobr| element in scope |
| 4695 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4696 |
|
my $node = $self->{open_elements}->[$_]; |
| 4697 |
|
if ($node->[1] eq 'nobr') { |
| 4698 |
|
!!!parse-error (type => 'in nobr:nobr'); |
| 4699 |
|
!!!back-token; |
| 4700 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'nobr'}; |
| 4701 |
|
redo B; |
| 4702 |
|
} elsif ({ |
| 4703 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4704 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4705 |
|
}->{$node->[1]}) { |
| 4706 |
|
last INSCOPE; |
| 4707 |
|
} |
| 4708 |
|
} # INSCOPE |
| 4709 |
|
|
| 4710 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4711 |
|
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
| 4712 |
|
|
| 4713 |
|
!!!next-token; |
| 4714 |
|
redo B; |
| 4715 |
|
} elsif ($token->{tag_name} eq 'button') { |
| 4716 |
|
## has a button element in scope |
| 4717 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4718 |
|
my $node = $self->{open_elements}->[$_]; |
| 4719 |
|
if ($node->[1] eq 'button') { |
| 4720 |
|
!!!parse-error (type => 'in button:button'); |
| 4721 |
|
!!!back-token; |
| 4722 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'button'}; |
| 4723 |
|
redo B; |
| 4724 |
|
} elsif ({ |
| 4725 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4726 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4727 |
|
}->{$node->[1]}) { |
| 4728 |
|
last INSCOPE; |
| 4729 |
|
} |
| 4730 |
|
} # INSCOPE |
| 4731 |
|
|
| 4732 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4733 |
|
|
| 4734 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4735 |
|
push @$active_formatting_elements, ['#marker', '']; |
| 4736 |
|
|
| 4737 |
|
!!!next-token; |
| 4738 |
|
redo B; |
| 4739 |
|
} elsif ($token->{tag_name} eq 'marquee' or |
| 4740 |
|
$token->{tag_name} eq 'object') { |
| 4741 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4742 |
|
|
| 4743 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4744 |
|
push @$active_formatting_elements, ['#marker', '']; |
| 4745 |
|
|
| 4746 |
|
!!!next-token; |
| 4747 |
|
redo B; |
| 4748 |
|
} elsif ($token->{tag_name} eq 'xmp') { |
| 4749 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4750 |
|
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert); |
| 4751 |
|
redo B; |
| 4752 |
|
} elsif ($token->{tag_name} eq 'table') { |
| 4753 |
|
## has a p element in scope |
| 4754 |
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4755 |
|
if ($_->[1] eq 'p') { |
| 4756 |
|
!!!back-token; |
| 4757 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4758 |
|
redo B; |
| 4759 |
|
} elsif ({ |
| 4760 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4761 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4762 |
|
}->{$_->[1]}) { |
| 4763 |
|
last INSCOPE; |
| 4764 |
|
} |
| 4765 |
|
} # INSCOPE |
| 4766 |
|
|
| 4767 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($data); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4768 |
|
|
| 4769 |
|
$self->{insertion_mode} = IN_TABLE_IM; |
| 4770 |
|
|
| 4771 |
|
!!!next-token; |
| 4772 |
|
redo B; |
| 4773 |
|
} elsif ({ |
| 4774 |
|
area => 1, basefont => 1, bgsound => 1, br => 1, |
| 4775 |
|
embed => 1, img => 1, param => 1, spacer => 1, wbr => 1, |
| 4776 |
|
image => 1, |
| 4777 |
|
}->{$token->{tag_name}}) { |
| 4778 |
|
if ($token->{tag_name} eq 'image') { |
| 4779 |
|
!!!parse-error (type => 'image'); |
| 4780 |
|
$token->{tag_name} = 'img'; |
| 4781 |
|
} |
| 4782 |
|
|
| 4783 |
|
## NOTE: There is an "as if <br>" code clone. |
| 4784 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4785 |
|
|
| 4786 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4787 |
|
pop @{$self->{open_elements}}; |
| 4788 |
|
|
| 4789 |
|
!!!next-token; |
| 4790 |
|
redo B; |
| 4791 |
|
} elsif ($token->{tag_name} eq 'hr') { |
| 4792 |
|
## has a p element in scope |
| 4793 |
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4794 |
|
if ($_->[1] eq 'p') { |
| 4795 |
|
!!!back-token; |
| 4796 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4797 |
|
redo B; |
| 4798 |
|
} elsif ({ |
| 4799 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4800 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4801 |
|
}->{$_->[1]}) { |
| 4802 |
|
last INSCOPE; |
| 4803 |
|
} |
| 4804 |
|
} # INSCOPE |
| 4805 |
|
|
| 4806 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4807 |
|
pop @{$self->{open_elements}}; |
| 4808 |
|
|
| 4809 |
|
!!!next-token; |
| 4810 |
|
redo B; |
| 4811 |
|
} elsif ($token->{tag_name} eq 'input') { |
| 4812 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4813 |
|
|
| 4814 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4815 |
|
## TODO: associate with $self->{form_element} if defined |
| 4816 |
|
pop @{$self->{open_elements}}; |
| 4817 |
|
|
| 4818 |
|
!!!next-token; |
| 4819 |
|
redo B; |
| 4820 |
|
} elsif ($token->{tag_name} eq 'isindex') { |
| 4821 |
|
!!!parse-error (type => 'isindex'); |
| 4822 |
|
|
| 4823 |
|
if (defined $self->{form_element}) { |
| 4824 |
|
## Ignore the token |
| 4825 |
|
!!!next-token; |
| 4826 |
|
redo B; |
| 4827 |
|
} else { |
| 4828 |
|
my $at = $token->{attributes}; |
| 4829 |
|
my $form_attrs; |
| 4830 |
|
$form_attrs->{action} = $at->{action} if $at->{action}; |
| 4831 |
|
my $prompt_attr = $at->{prompt}; |
| 4832 |
|
$at->{name} = {name => 'name', value => 'isindex'}; |
| 4833 |
|
delete $at->{action}; |
| 4834 |
|
delete $at->{prompt}; |
| 4835 |
|
my @tokens = ( |
| 4836 |
|
{type => START_TAG_TOKEN, tag_name => 'form', |
| 4837 |
|
attributes => $form_attrs}, |
| 4838 |
|
{type => START_TAG_TOKEN, tag_name => 'hr'}, |
| 4839 |
|
{type => START_TAG_TOKEN, tag_name => 'p'}, |
| 4840 |
|
{type => START_TAG_TOKEN, tag_name => 'label'}, |
| 4841 |
|
); |
| 4842 |
|
if ($prompt_attr) { |
| 4843 |
|
push @tokens, {type => CHARACTER_TOKEN, data => $prompt_attr->{value}}; |
| 4844 |
|
} else { |
| 4845 |
|
push @tokens, {type => CHARACTER_TOKEN, |
| 4846 |
|
data => 'This is a searchable index. Insert your search keywords here: '}; # SHOULD |
| 4847 |
|
## TODO: make this configurable |
| 4848 |
|
} |
| 4849 |
|
push @tokens, |
| 4850 |
|
{type => START_TAG_TOKEN, tag_name => 'input', attributes => $at}, |
| 4851 |
|
#{type => CHARACTER_TOKEN, data => ''}, # SHOULD |
| 4852 |
|
{type => END_TAG_TOKEN, tag_name => 'label'}, |
| 4853 |
|
{type => END_TAG_TOKEN, tag_name => 'p'}, |
| 4854 |
|
{type => START_TAG_TOKEN, tag_name => 'hr'}, |
| 4855 |
|
{type => END_TAG_TOKEN, tag_name => 'form'}; |
| 4856 |
|
$token = shift @tokens; |
| 4857 |
|
!!!back-token (@tokens); |
| 4858 |
|
redo B; |
| 4859 |
|
} |
| 4860 |
|
} elsif ($token->{tag_name} eq 'textarea') { |
| 4861 |
|
my $tag_name = $token->{tag_name}; |
| 4862 |
|
my $el; |
| 4863 |
|
!!!create-element ($el, $token->{tag_name}, $token->{attributes}); |
| 4864 |
|
|
| 4865 |
|
## TODO: $self->{form_element} if defined |
| 4866 |
|
$self->{content_model} = RCDATA_CONTENT_MODEL; |
| 4867 |
|
delete $self->{escape}; # MUST |
| 4868 |
|
|
| 4869 |
|
$insert->($el); |
| 4870 |
|
|
| 4871 |
|
my $text = ''; |
| 4872 |
|
!!!next-token; |
| 4873 |
|
if ($token->{type} == CHARACTER_TOKEN) { |
| 4874 |
|
$token->{data} =~ s/^\x0A//; |
| 4875 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 4876 |
!!!next-token; |
!!!next-token; |
|
redo B; |
|
| 4877 |
} |
} |
| 4878 |
} |
} |
| 4879 |
|
while ($token->{type} == CHARACTER_TOKEN) { |
| 4880 |
|
$text .= $token->{data}; |
| 4881 |
|
!!!next-token; |
| 4882 |
|
} |
| 4883 |
|
if (length $text) { |
| 4884 |
|
$el->manakai_append_text ($text); |
| 4885 |
|
} |
| 4886 |
|
|
| 4887 |
|
$self->{content_model} = PCDATA_CONTENT_MODEL; |
| 4888 |
|
|
| 4889 |
|
if ($token->{type} == END_TAG_TOKEN and |
| 4890 |
|
$token->{tag_name} eq $tag_name) { |
| 4891 |
|
## Ignore the token |
| 4892 |
|
} else { |
| 4893 |
|
!!!parse-error (type => 'in RCDATA:#'.$token->{type}); |
| 4894 |
|
} |
| 4895 |
|
!!!next-token; |
| 4896 |
|
redo B; |
| 4897 |
|
} elsif ({ |
| 4898 |
|
iframe => 1, |
| 4899 |
|
noembed => 1, |
| 4900 |
|
noframes => 1, |
| 4901 |
|
noscript => 0, ## TODO: 1 if scripting is enabled |
| 4902 |
|
}->{$token->{tag_name}}) { |
| 4903 |
|
## NOTE: There is an "as if in body" code clone. |
| 4904 |
|
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert); |
| 4905 |
|
redo B; |
| 4906 |
|
} elsif ($token->{tag_name} eq 'select') { |
| 4907 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4908 |
|
|
| 4909 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4910 |
|
|
| 4911 |
|
$self->{insertion_mode} = IN_SELECT_IM; |
| 4912 |
|
!!!next-token; |
| 4913 |
|
redo B; |
| 4914 |
|
} elsif ({ |
| 4915 |
|
caption => 1, col => 1, colgroup => 1, frame => 1, |
| 4916 |
|
frameset => 1, head => 1, option => 1, optgroup => 1, |
| 4917 |
|
tbody => 1, td => 1, tfoot => 1, th => 1, |
| 4918 |
|
thead => 1, tr => 1, |
| 4919 |
|
}->{$token->{tag_name}}) { |
| 4920 |
|
!!!parse-error (type => 'in body:'.$token->{tag_name}); |
| 4921 |
|
## Ignore the token |
| 4922 |
|
!!!next-token; |
| 4923 |
|
redo B; |
| 4924 |
|
|
| 4925 |
|
## ISSUE: An issue on HTML5 new elements in the spec. |
| 4926 |
|
} else { |
| 4927 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4928 |
|
|
| 4929 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4930 |
|
|
| 4931 |
|
!!!next-token; |
| 4932 |
|
redo B; |
| 4933 |
|
} |
| 4934 |
|
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 4935 |
|
if ($token->{tag_name} eq 'body') { |
| 4936 |
|
if (@{$self->{open_elements}} > 1 and |
| 4937 |
|
$self->{open_elements}->[1]->[1] eq 'body') { |
| 4938 |
|
for (@{$self->{open_elements}}) { |
| 4939 |
|
unless ({ |
| 4940 |
|
dd => 1, dt => 1, li => 1, p => 1, td => 1, |
| 4941 |
|
th => 1, tr => 1, body => 1, html => 1, |
| 4942 |
|
tbody => 1, tfoot => 1, thead => 1, |
| 4943 |
|
}->{$_->[1]}) { |
| 4944 |
|
!!!parse-error (type => 'not closed:'.$_->[1]); |
| 4945 |
|
} |
| 4946 |
|
} |
| 4947 |
|
|
| 4948 |
!!!parse-error (type => 'after html:#character'); |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 4949 |
$self->{insertion_mode} = $previous_insertion_mode; |
!!!next-token; |
| 4950 |
## reprocess |
redo B; |
| 4951 |
|
} else { |
| 4952 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 4953 |
|
## Ignore the token |
| 4954 |
|
!!!next-token; |
| 4955 |
|
redo B; |
| 4956 |
|
} |
| 4957 |
|
} elsif ($token->{tag_name} eq 'html') { |
| 4958 |
|
if (@{$self->{open_elements}} > 1 and $self->{open_elements}->[1]->[1] eq 'body') { |
| 4959 |
|
## ISSUE: There is an issue in the spec. |
| 4960 |
|
if ($self->{open_elements}->[-1]->[1] ne 'body') { |
| 4961 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[1]->[1]); |
| 4962 |
|
} |
| 4963 |
|
$self->{insertion_mode} = AFTER_BODY_IM; |
| 4964 |
|
## reprocess |
| 4965 |
|
redo B; |
| 4966 |
|
} else { |
| 4967 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 4968 |
|
## Ignore the token |
| 4969 |
|
!!!next-token; |
| 4970 |
|
redo B; |
| 4971 |
|
} |
| 4972 |
|
} elsif ({ |
| 4973 |
|
address => 1, blockquote => 1, center => 1, dir => 1, |
| 4974 |
|
div => 1, dl => 1, fieldset => 1, listing => 1, |
| 4975 |
|
menu => 1, ol => 1, pre => 1, ul => 1, |
| 4976 |
|
p => 1, |
| 4977 |
|
dd => 1, dt => 1, li => 1, |
| 4978 |
|
button => 1, marquee => 1, object => 1, |
| 4979 |
|
}->{$token->{tag_name}}) { |
| 4980 |
|
## has an element in scope |
| 4981 |
|
my $i; |
| 4982 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4983 |
|
my $node = $self->{open_elements}->[$_]; |
| 4984 |
|
if ($node->[1] eq $token->{tag_name}) { |
| 4985 |
|
## generate implied end tags |
| 4986 |
|
if ({ |
| 4987 |
|
dd => ($token->{tag_name} ne 'dd'), |
| 4988 |
|
dt => ($token->{tag_name} ne 'dt'), |
| 4989 |
|
li => ($token->{tag_name} ne 'li'), |
| 4990 |
|
p => ($token->{tag_name} ne 'p'), |
| 4991 |
|
td => 1, th => 1, tr => 1, |
| 4992 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 4993 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4994 |
|
!!!back-token; |
| 4995 |
|
$token = {type => END_TAG_TOKEN, |
| 4996 |
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 4997 |
|
redo B; |
| 4998 |
|
} |
| 4999 |
|
$i = $_; |
| 5000 |
|
last INSCOPE unless $token->{tag_name} eq 'p'; |
| 5001 |
|
} elsif ({ |
| 5002 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 5003 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 5004 |
|
}->{$node->[1]}) { |
| 5005 |
|
last INSCOPE; |
| 5006 |
|
} |
| 5007 |
|
} # INSCOPE |
| 5008 |
|
|
| 5009 |
|
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
| 5010 |
|
if (defined $i) { |
| 5011 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 5012 |
|
} else { |
| 5013 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 5014 |
|
} |
| 5015 |
|
} |
| 5016 |
|
|
| 5017 |
|
if (defined $i) { |
| 5018 |
|
splice @{$self->{open_elements}}, $i; |
| 5019 |
|
} elsif ($token->{tag_name} eq 'p') { |
| 5020 |
|
## As if <p>, then reprocess the current token |
| 5021 |
|
my $el; |
| 5022 |
|
!!!create-element ($el, 'p'); |
| 5023 |
|
$insert->($el); |
| 5024 |
|
} |
| 5025 |
|
$clear_up_to_marker->() |
| 5026 |
|
if { |
| 5027 |
|
button => 1, marquee => 1, object => 1, |
| 5028 |
|
}->{$token->{tag_name}}; |
| 5029 |
|
!!!next-token; |
| 5030 |
redo B; |
redo B; |
| 5031 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{tag_name} eq 'form') { |
| 5032 |
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
## has an element in scope |
| 5033 |
$self->{insertion_mode} = $previous_insertion_mode; |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5034 |
## reprocess |
my $node = $self->{open_elements}->[$_]; |
| 5035 |
|
if ($node->[1] eq $token->{tag_name}) { |
| 5036 |
|
## generate implied end tags |
| 5037 |
|
if ({ |
| 5038 |
|
dd => 1, dt => 1, li => 1, p => 1, |
| 5039 |
|
td => 1, th => 1, tr => 1, |
| 5040 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 5041 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 5042 |
|
!!!back-token; |
| 5043 |
|
$token = {type => END_TAG_TOKEN, |
| 5044 |
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 5045 |
|
redo B; |
| 5046 |
|
} |
| 5047 |
|
last INSCOPE; |
| 5048 |
|
} elsif ({ |
| 5049 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 5050 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 5051 |
|
}->{$node->[1]}) { |
| 5052 |
|
last INSCOPE; |
| 5053 |
|
} |
| 5054 |
|
} # INSCOPE |
| 5055 |
|
|
| 5056 |
|
if ($self->{open_elements}->[-1]->[1] eq $token->{tag_name}) { |
| 5057 |
|
pop @{$self->{open_elements}}; |
| 5058 |
|
} else { |
| 5059 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 5060 |
|
} |
| 5061 |
|
|
| 5062 |
|
undef $self->{form_element}; |
| 5063 |
|
!!!next-token; |
| 5064 |
redo B; |
redo B; |
| 5065 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ({ |
| 5066 |
!!!parse-error (type => 'after html:/'.$token->{tag_name}); |
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
| 5067 |
$self->{insertion_mode} = $previous_insertion_mode; |
}->{$token->{tag_name}}) { |
| 5068 |
## reprocess |
## has an element in scope |
| 5069 |
|
my $i; |
| 5070 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5071 |
|
my $node = $self->{open_elements}->[$_]; |
| 5072 |
|
if ({ |
| 5073 |
|
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
| 5074 |
|
}->{$node->[1]}) { |
| 5075 |
|
## generate implied end tags |
| 5076 |
|
if ({ |
| 5077 |
|
dd => 1, dt => 1, li => 1, p => 1, |
| 5078 |
|
td => 1, th => 1, tr => 1, |
| 5079 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 5080 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 5081 |
|
!!!back-token; |
| 5082 |
|
$token = {type => END_TAG_TOKEN, |
| 5083 |
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 5084 |
|
redo B; |
| 5085 |
|
} |
| 5086 |
|
$i = $_; |
| 5087 |
|
last INSCOPE; |
| 5088 |
|
} elsif ({ |
| 5089 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 5090 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 5091 |
|
}->{$node->[1]}) { |
| 5092 |
|
last INSCOPE; |
| 5093 |
|
} |
| 5094 |
|
} # INSCOPE |
| 5095 |
|
|
| 5096 |
|
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
| 5097 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 5098 |
|
} |
| 5099 |
|
|
| 5100 |
|
splice @{$self->{open_elements}}, $i if defined $i; |
| 5101 |
|
!!!next-token; |
| 5102 |
|
redo B; |
| 5103 |
|
} elsif ({ |
| 5104 |
|
a => 1, |
| 5105 |
|
b => 1, big => 1, em => 1, font => 1, i => 1, |
| 5106 |
|
nobr => 1, s => 1, small => 1, strile => 1, |
| 5107 |
|
strong => 1, tt => 1, u => 1, |
| 5108 |
|
}->{$token->{tag_name}}) { |
| 5109 |
|
$formatting_end_tag->($token->{tag_name}); |
| 5110 |
|
redo B; |
| 5111 |
|
} elsif ($token->{tag_name} eq 'br') { |
| 5112 |
|
!!!parse-error (type => 'unmatched end tag:br'); |
| 5113 |
|
|
| 5114 |
|
## As if <br> |
| 5115 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 5116 |
|
|
| 5117 |
|
my $el; |
| 5118 |
|
!!!create-element ($el, 'br'); |
| 5119 |
|
$insert->($el); |
| 5120 |
|
|
| 5121 |
|
## Ignore the token. |
| 5122 |
|
!!!next-token; |
| 5123 |
|
redo B; |
| 5124 |
|
} elsif ({ |
| 5125 |
|
caption => 1, col => 1, colgroup => 1, frame => 1, |
| 5126 |
|
frameset => 1, head => 1, option => 1, optgroup => 1, |
| 5127 |
|
tbody => 1, td => 1, tfoot => 1, th => 1, |
| 5128 |
|
thead => 1, tr => 1, |
| 5129 |
|
area => 1, basefont => 1, bgsound => 1, |
| 5130 |
|
embed => 1, hr => 1, iframe => 1, image => 1, |
| 5131 |
|
img => 1, input => 1, isindex => 1, noembed => 1, |
| 5132 |
|
noframes => 1, param => 1, select => 1, spacer => 1, |
| 5133 |
|
table => 1, textarea => 1, wbr => 1, |
| 5134 |
|
noscript => 0, ## TODO: if scripting is enabled |
| 5135 |
|
}->{$token->{tag_name}}) { |
| 5136 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 5137 |
|
## Ignore the token |
| 5138 |
|
!!!next-token; |
| 5139 |
redo B; |
redo B; |
| 5140 |
|
|
| 5141 |
|
## ISSUE: Issue on HTML5 new elements in spec |
| 5142 |
|
|
| 5143 |
} else { |
} else { |
| 5144 |
die "$0: $token->{type}: Unknown token"; |
## Step 1 |
| 5145 |
|
my $node_i = -1; |
| 5146 |
|
my $node = $self->{open_elements}->[$node_i]; |
| 5147 |
|
|
| 5148 |
|
## Step 2 |
| 5149 |
|
S2: { |
| 5150 |
|
if ($node->[1] eq $token->{tag_name}) { |
| 5151 |
|
## Step 1 |
| 5152 |
|
## generate implied end tags |
| 5153 |
|
if ({ |
| 5154 |
|
dd => 1, dt => 1, li => 1, p => 1, |
| 5155 |
|
td => 1, th => 1, tr => 1, |
| 5156 |
|
tbody => 1, tfoot => 1, thead => 1, |
| 5157 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 5158 |
|
!!!back-token; |
| 5159 |
|
$token = {type => END_TAG_TOKEN, |
| 5160 |
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 5161 |
|
redo B; |
| 5162 |
|
} |
| 5163 |
|
|
| 5164 |
|
## Step 2 |
| 5165 |
|
if ($token->{tag_name} ne $self->{open_elements}->[-1]->[1]) { |
| 5166 |
|
## NOTE: <x><y></x> |
| 5167 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 5168 |
|
} |
| 5169 |
|
|
| 5170 |
|
## Step 3 |
| 5171 |
|
splice @{$self->{open_elements}}, $node_i; |
| 5172 |
|
|
| 5173 |
|
!!!next-token; |
| 5174 |
|
last S2; |
| 5175 |
|
} else { |
| 5176 |
|
## Step 3 |
| 5177 |
|
if (not $formatting_category->{$node->[1]} and |
| 5178 |
|
#not $phrasing_category->{$node->[1]} and |
| 5179 |
|
($special_category->{$node->[1]} or |
| 5180 |
|
$scoping_category->{$node->[1]})) { |
| 5181 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 5182 |
|
## Ignore the token |
| 5183 |
|
!!!next-token; |
| 5184 |
|
last S2; |
| 5185 |
|
} |
| 5186 |
|
} |
| 5187 |
|
|
| 5188 |
|
## Step 4 |
| 5189 |
|
$node_i--; |
| 5190 |
|
$node = $self->{open_elements}->[$node_i]; |
| 5191 |
|
|
| 5192 |
|
## Step 5; |
| 5193 |
|
redo S2; |
| 5194 |
|
} # S2 |
| 5195 |
|
redo B; |
| 5196 |
} |
} |
|
} else { |
|
|
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
|
| 5197 |
} |
} |
| 5198 |
|
redo B; |
| 5199 |
} # B |
} # B |
| 5200 |
|
|
| 5201 |
|
## NOTE: The "trailing end" phase in HTML5 is split into |
| 5202 |
|
## two insertion modes: "after html body" and "after html frameset". |
| 5203 |
|
## NOTE: States in the main stage is preserved while |
| 5204 |
|
## the parser stays in the trailing end phase. # MUST |
| 5205 |
|
|
| 5206 |
## Stop parsing # MUST |
## Stop parsing # MUST |
| 5207 |
|
|
| 5208 |
## TODO: script stuffs |
## TODO: script stuffs |