| 1 |
package Whatpm::HTML; |
package Whatpm::HTML; |
| 2 |
use strict; |
use strict; |
| 3 |
our $VERSION=do{my @r=(q$Revision$=~/\d+/g);sprintf "%d."."%02d" x $#r,@r}; |
our $VERSION=do{my @r=(q$Revision$=~/\d+/g);sprintf "%d."."%02d" x $#r,@r}; |
| 4 |
|
use Error qw(:try); |
| 5 |
|
|
| 6 |
## ISSUE: |
## ISSUE: |
| 7 |
## var doc = implementation.createDocument (null, null, null); |
## var doc = implementation.createDocument (null, null, null); |
| 85 |
}; |
}; |
| 86 |
# $phrasing_category: all other elements |
# $phrasing_category: all other elements |
| 87 |
|
|
| 88 |
|
sub parse_byte_string ($$$$;$) { |
| 89 |
|
my $self = ref $_[0] ? shift : shift->new; |
| 90 |
|
my $charset = shift; |
| 91 |
|
my $bytes_s = ref $_[0] ? $_[0] : \($_[0]); |
| 92 |
|
my $s; |
| 93 |
|
|
| 94 |
|
if (defined $charset) { |
| 95 |
|
require Encode; ## TODO: decode(utf8) don't delete BOM |
| 96 |
|
$s = \ (Encode::decode ($charset, $$bytes_s)); |
| 97 |
|
$self->{input_encoding} = lc $charset; ## TODO: normalize name |
| 98 |
|
$self->{confident} = 1; |
| 99 |
|
} else { |
| 100 |
|
## TODO: Implement HTML5 detection algorithm |
| 101 |
|
require Whatpm::Charset::UniversalCharDet; |
| 102 |
|
$charset = Whatpm::Charset::UniversalCharDet->detect_byte_string |
| 103 |
|
(substr ($$bytes_s, 0, 1024)); |
| 104 |
|
$charset ||= 'windows-1252'; |
| 105 |
|
$s = \ (Encode::decode ($charset, $$bytes_s)); |
| 106 |
|
$self->{input_encoding} = $charset; |
| 107 |
|
$self->{confident} = 0; |
| 108 |
|
} |
| 109 |
|
|
| 110 |
|
$self->{change_encoding} = sub { |
| 111 |
|
my $self = shift; |
| 112 |
|
my $charset = lc shift; |
| 113 |
|
## TODO: if $charset is supported |
| 114 |
|
## TODO: normalize charset name |
| 115 |
|
|
| 116 |
|
## "Change the encoding" algorithm: |
| 117 |
|
|
| 118 |
|
## Step 1 |
| 119 |
|
if ($charset eq 'utf-16') { ## ISSUE: UTF-16BE -> UTF-8? UTF-16LE -> UTF-8? |
| 120 |
|
$charset = 'utf-8'; |
| 121 |
|
} |
| 122 |
|
|
| 123 |
|
## Step 2 |
| 124 |
|
if (defined $self->{input_encoding} and |
| 125 |
|
$self->{input_encoding} eq $charset) { |
| 126 |
|
$self->{confident} = 1; |
| 127 |
|
return; |
| 128 |
|
} |
| 129 |
|
|
| 130 |
|
!!!parse-error (type => 'charset label detected:'.$self->{input_encoding}. |
| 131 |
|
':'.$charset, level => 'w'); |
| 132 |
|
|
| 133 |
|
## Step 3 |
| 134 |
|
# if (can) { |
| 135 |
|
## change the encoding on the fly. |
| 136 |
|
#$self->{confident} = 1; |
| 137 |
|
#return; |
| 138 |
|
# } |
| 139 |
|
|
| 140 |
|
## Step 4 |
| 141 |
|
throw Whatpm::HTML::RestartParser (charset => $charset); |
| 142 |
|
}; # $self->{change_encoding} |
| 143 |
|
|
| 144 |
|
my @args = @_; shift @args; # $s |
| 145 |
|
my $return; |
| 146 |
|
try { |
| 147 |
|
$return = $self->parse_char_string ($s, @args); |
| 148 |
|
} catch Whatpm::HTML::RestartParser with { |
| 149 |
|
my $charset = shift->{charset}; |
| 150 |
|
$s = \ (Encode::decode ($charset, $$bytes_s)); |
| 151 |
|
$self->{input_encoding} = $charset; ## TODO: normalize |
| 152 |
|
$self->{confident} = 1; |
| 153 |
|
$return = $self->parse_char_string ($s, @args); |
| 154 |
|
}; |
| 155 |
|
return $return; |
| 156 |
|
} # parse_byte_string |
| 157 |
|
|
| 158 |
|
*parse_char_string = \&parse_string; |
| 159 |
|
|
| 160 |
sub parse_string ($$$;$) { |
sub parse_string ($$$;$) { |
| 161 |
my $self = shift->new; |
my $self = ref $_[0] ? shift : shift->new; |
| 162 |
my $s = \$_[0]; |
my $s = ref $_[0] ? $_[0] : \($_[0]); |
| 163 |
$self->{document} = $_[1]; |
$self->{document} = $_[1]; |
| 164 |
|
@{$self->{document}->child_nodes} = (); |
| 165 |
|
|
| 166 |
## NOTE: |set_inner_html| copies most of this method's code |
## NOTE: |set_inner_html| copies most of this method's code |
| 167 |
|
|
| 168 |
|
$self->{confident} = 1 unless exists $self->{confident}; |
| 169 |
|
$self->{document}->input_encoding ($self->{input_encoding}) |
| 170 |
|
if defined $self->{input_encoding}; |
| 171 |
|
|
| 172 |
my $i = 0; |
my $i = 0; |
| 173 |
my $line = 1; |
my $line = 1; |
| 174 |
my $column = 0; |
my $column = 0; |
| 225 |
$self->{parse_error} = sub { |
$self->{parse_error} = sub { |
| 226 |
# |
# |
| 227 |
}; |
}; |
| 228 |
|
$self->{change_encoding} = sub { |
| 229 |
|
# if ($_[0] is a supported encoding) { |
| 230 |
|
# run "change the encoding" algorithm; |
| 231 |
|
# throw Whatpm::HTML::RestartParser (charset => $new_encoding); |
| 232 |
|
# } |
| 233 |
|
}; |
| 234 |
|
$self->{application_cache_selection} = sub { |
| 235 |
|
# |
| 236 |
|
}; |
| 237 |
return $self; |
return $self; |
| 238 |
} # new |
} # new |
| 239 |
|
|
| 246 |
sub RCDATA_CONTENT_MODEL () { CM_ENTITY | CM_LIMITED_MARKUP } |
sub RCDATA_CONTENT_MODEL () { CM_ENTITY | CM_LIMITED_MARKUP } |
| 247 |
sub PCDATA_CONTENT_MODEL () { CM_ENTITY | CM_FULL_MARKUP } |
sub PCDATA_CONTENT_MODEL () { CM_ENTITY | CM_FULL_MARKUP } |
| 248 |
|
|
| 249 |
|
sub DATA_STATE () { 0 } |
| 250 |
|
sub ENTITY_DATA_STATE () { 1 } |
| 251 |
|
sub TAG_OPEN_STATE () { 2 } |
| 252 |
|
sub CLOSE_TAG_OPEN_STATE () { 3 } |
| 253 |
|
sub TAG_NAME_STATE () { 4 } |
| 254 |
|
sub BEFORE_ATTRIBUTE_NAME_STATE () { 5 } |
| 255 |
|
sub ATTRIBUTE_NAME_STATE () { 6 } |
| 256 |
|
sub AFTER_ATTRIBUTE_NAME_STATE () { 7 } |
| 257 |
|
sub BEFORE_ATTRIBUTE_VALUE_STATE () { 8 } |
| 258 |
|
sub ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE () { 9 } |
| 259 |
|
sub ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE () { 10 } |
| 260 |
|
sub ATTRIBUTE_VALUE_UNQUOTED_STATE () { 11 } |
| 261 |
|
sub ENTITY_IN_ATTRIBUTE_VALUE_STATE () { 12 } |
| 262 |
|
sub MARKUP_DECLARATION_OPEN_STATE () { 13 } |
| 263 |
|
sub COMMENT_START_STATE () { 14 } |
| 264 |
|
sub COMMENT_START_DASH_STATE () { 15 } |
| 265 |
|
sub COMMENT_STATE () { 16 } |
| 266 |
|
sub COMMENT_END_STATE () { 17 } |
| 267 |
|
sub COMMENT_END_DASH_STATE () { 18 } |
| 268 |
|
sub BOGUS_COMMENT_STATE () { 19 } |
| 269 |
|
sub DOCTYPE_STATE () { 20 } |
| 270 |
|
sub BEFORE_DOCTYPE_NAME_STATE () { 21 } |
| 271 |
|
sub DOCTYPE_NAME_STATE () { 22 } |
| 272 |
|
sub AFTER_DOCTYPE_NAME_STATE () { 23 } |
| 273 |
|
sub BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE () { 24 } |
| 274 |
|
sub DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE () { 25 } |
| 275 |
|
sub DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE () { 26 } |
| 276 |
|
sub AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE () { 27 } |
| 277 |
|
sub BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE () { 28 } |
| 278 |
|
sub DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE () { 29 } |
| 279 |
|
sub DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE () { 30 } |
| 280 |
|
sub AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE () { 31 } |
| 281 |
|
sub BOGUS_DOCTYPE_STATE () { 32 } |
| 282 |
|
|
| 283 |
|
sub DOCTYPE_TOKEN () { 1 } |
| 284 |
|
sub COMMENT_TOKEN () { 2 } |
| 285 |
|
sub START_TAG_TOKEN () { 3 } |
| 286 |
|
sub END_TAG_TOKEN () { 4 } |
| 287 |
|
sub END_OF_FILE_TOKEN () { 5 } |
| 288 |
|
sub CHARACTER_TOKEN () { 6 } |
| 289 |
|
|
| 290 |
|
sub AFTER_HTML_IMS () { 0b100 } |
| 291 |
|
sub HEAD_IMS () { 0b1000 } |
| 292 |
|
sub BODY_IMS () { 0b10000 } |
| 293 |
|
sub BODY_TABLE_IMS () { 0b100000 } |
| 294 |
|
sub TABLE_IMS () { 0b1000000 } |
| 295 |
|
sub ROW_IMS () { 0b10000000 } |
| 296 |
|
sub BODY_AFTER_IMS () { 0b100000000 } |
| 297 |
|
sub FRAME_IMS () { 0b1000000000 } |
| 298 |
|
|
| 299 |
|
sub AFTER_HTML_BODY_IM () { AFTER_HTML_IMS | BODY_AFTER_IMS } |
| 300 |
|
sub AFTER_HTML_FRAMESET_IM () { AFTER_HTML_IMS | FRAME_IMS } |
| 301 |
|
sub IN_HEAD_IM () { HEAD_IMS | 0b00 } |
| 302 |
|
sub IN_HEAD_NOSCRIPT_IM () { HEAD_IMS | 0b01 } |
| 303 |
|
sub AFTER_HEAD_IM () { HEAD_IMS | 0b10 } |
| 304 |
|
sub BEFORE_HEAD_IM () { HEAD_IMS | 0b11 } |
| 305 |
|
sub IN_BODY_IM () { BODY_IMS } |
| 306 |
|
sub IN_CELL_IM () { BODY_IMS | BODY_TABLE_IMS | 0b01 } |
| 307 |
|
sub IN_CAPTION_IM () { BODY_IMS | BODY_TABLE_IMS | 0b10 } |
| 308 |
|
sub IN_ROW_IM () { TABLE_IMS | ROW_IMS | 0b01 } |
| 309 |
|
sub IN_TABLE_BODY_IM () { TABLE_IMS | ROW_IMS | 0b10 } |
| 310 |
|
sub IN_TABLE_IM () { TABLE_IMS } |
| 311 |
|
sub AFTER_BODY_IM () { BODY_AFTER_IMS } |
| 312 |
|
sub IN_FRAMESET_IM () { FRAME_IMS | 0b01 } |
| 313 |
|
sub AFTER_FRAMESET_IM () { FRAME_IMS | 0b10 } |
| 314 |
|
sub IN_SELECT_IM () { 0b01 } |
| 315 |
|
sub IN_COLUMN_GROUP_IM () { 0b10 } |
| 316 |
|
|
| 317 |
## Implementations MUST act as if state machine in the spec |
## Implementations MUST act as if state machine in the spec |
| 318 |
|
|
| 319 |
sub _initialize_tokenizer ($) { |
sub _initialize_tokenizer ($) { |
| 320 |
my $self = shift; |
my $self = shift; |
| 321 |
$self->{state} = 'data'; # MUST |
$self->{state} = DATA_STATE; # MUST |
| 322 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # be |
$self->{content_model} = PCDATA_CONTENT_MODEL; # be |
| 323 |
undef $self->{current_token}; # start tag, end tag, comment, or DOCTYPE |
undef $self->{current_token}; # start tag, end tag, comment, or DOCTYPE |
| 324 |
undef $self->{current_attribute}; |
undef $self->{current_attribute}; |
| 332 |
} # _initialize_tokenizer |
} # _initialize_tokenizer |
| 333 |
|
|
| 334 |
## A token has: |
## A token has: |
| 335 |
## ->{type} eq 'DOCTYPE', 'start tag', 'end tag', 'comment', |
## ->{type} == DOCTYPE_TOKEN, START_TAG_TOKEN, END_TAG_TOKEN, COMMENT_TOKEN, |
| 336 |
## 'character', or 'end-of-file' |
## CHARACTER_TOKEN, or END_OF_FILE_TOKEN |
| 337 |
## ->{name} (DOCTYPE, start tag (tag name), end tag (tag name)) |
## ->{name} (DOCTYPE_TOKEN) |
| 338 |
## ->{public_identifier} (DOCTYPE) |
## ->{tag_name} (START_TAG_TOKEN, END_TAG_TOKEN) |
| 339 |
## ->{system_identifier} (DOCTYPE) |
## ->{public_identifier} (DOCTYPE_TOKEN) |
| 340 |
## ->{correct} == 1 or 0 (DOCTYPE) |
## ->{system_identifier} (DOCTYPE_TOKEN) |
| 341 |
## ->{attributes} isa HASH (start tag, end tag) |
## ->{correct} == 1 or 0 (DOCTYPE_TOKEN) |
| 342 |
## ->{data} (comment, character) |
## ->{attributes} isa HASH (START_TAG_TOKEN, END_TAG_TOKEN) |
| 343 |
|
## ->{data} (COMMENT_TOKEN, CHARACTER_TOKEN) |
| 344 |
|
|
| 345 |
## Emitted token MUST immediately be handled by the tree construction state. |
## Emitted token MUST immediately be handled by the tree construction state. |
| 346 |
|
|
| 350 |
## has completed loading. If one has, then it MUST be executed |
## has completed loading. If one has, then it MUST be executed |
| 351 |
## and removed from the list. |
## and removed from the list. |
| 352 |
|
|
| 353 |
|
## NOTE: HTML5 "Writing HTML documents" section, applied to |
| 354 |
|
## documents and not to user agents and conformance checkers, |
| 355 |
|
## contains some requirements that are not detected by the |
| 356 |
|
## parsing algorithm: |
| 357 |
|
## - Some requirements on character encoding declarations. ## TODO |
| 358 |
|
## - "Elements MUST NOT contain content that their content model disallows." |
| 359 |
|
## ... Some are parse error, some are not (will be reported by c.c.). |
| 360 |
|
## - Polytheistic slash SHOULD NOT be used. (Applied only to atheists.) ## TODO |
| 361 |
|
## - Text (in elements, attributes, and comments) SHOULD NOT contain |
| 362 |
|
## control characters other than space characters. ## TODO: (what is control character? C0, C1 and DEL? Unicode control character?) |
| 363 |
|
|
| 364 |
|
## TODO: HTML5 poses authors two SHOULD-level requirements that cannot |
| 365 |
|
## be detected by the HTML5 parsing algorithm: |
| 366 |
|
## - Text, |
| 367 |
|
|
| 368 |
sub _get_next_token ($) { |
sub _get_next_token ($) { |
| 369 |
my $self = shift; |
my $self = shift; |
| 370 |
if (@{$self->{token}}) { |
if (@{$self->{token}}) { |
| 372 |
} |
} |
| 373 |
|
|
| 374 |
A: { |
A: { |
| 375 |
if ($self->{state} eq 'data') { |
if ($self->{state} == DATA_STATE) { |
| 376 |
if ($self->{next_input_character} == 0x0026) { # & |
if ($self->{next_input_character} == 0x0026) { # & |
| 377 |
if ($self->{content_model} & CM_ENTITY) { # PCDATA | RCDATA |
if ($self->{content_model} & CM_ENTITY) { # PCDATA | RCDATA |
| 378 |
$self->{state} = 'entity data'; |
$self->{state} = ENTITY_DATA_STATE; |
| 379 |
!!!next-input-character; |
!!!next-input-character; |
| 380 |
redo A; |
redo A; |
| 381 |
} else { |
} else { |
| 397 |
if ($self->{content_model} & CM_FULL_MARKUP or # PCDATA |
if ($self->{content_model} & CM_FULL_MARKUP or # PCDATA |
| 398 |
(($self->{content_model} & CM_LIMITED_MARKUP) and # CDATA | RCDATA |
(($self->{content_model} & CM_LIMITED_MARKUP) and # CDATA | RCDATA |
| 399 |
not $self->{escape})) { |
not $self->{escape})) { |
| 400 |
$self->{state} = 'tag open'; |
$self->{state} = TAG_OPEN_STATE; |
| 401 |
!!!next-input-character; |
!!!next-input-character; |
| 402 |
redo A; |
redo A; |
| 403 |
} else { |
} else { |
| 414 |
|
|
| 415 |
# |
# |
| 416 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 417 |
!!!emit ({type => 'end-of-file'}); |
!!!emit ({type => END_OF_FILE_TOKEN}); |
| 418 |
last A; ## TODO: ok? |
last A; ## TODO: ok? |
| 419 |
} |
} |
| 420 |
# Anything else |
# Anything else |
| 421 |
my $token = {type => 'character', |
my $token = {type => CHARACTER_TOKEN, |
| 422 |
data => chr $self->{next_input_character}}; |
data => chr $self->{next_input_character}}; |
| 423 |
## Stay in the data state |
## Stay in the data state |
| 424 |
!!!next-input-character; |
!!!next-input-character; |
| 426 |
!!!emit ($token); |
!!!emit ($token); |
| 427 |
|
|
| 428 |
redo A; |
redo A; |
| 429 |
} elsif ($self->{state} eq 'entity data') { |
} elsif ($self->{state} == ENTITY_DATA_STATE) { |
| 430 |
## (cannot happen in CDATA state) |
## (cannot happen in CDATA state) |
| 431 |
|
|
| 432 |
my $token = $self->_tokenize_attempt_to_consume_an_entity (0); |
my $token = $self->_tokenize_attempt_to_consume_an_entity (0); |
| 433 |
|
|
| 434 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 435 |
# next-input-character is already done |
# next-input-character is already done |
| 436 |
|
|
| 437 |
unless (defined $token) { |
unless (defined $token) { |
| 438 |
!!!emit ({type => 'character', data => '&'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '&'}); |
| 439 |
} else { |
} else { |
| 440 |
!!!emit ($token); |
!!!emit ($token); |
| 441 |
} |
} |
| 442 |
|
|
| 443 |
redo A; |
redo A; |
| 444 |
} elsif ($self->{state} eq 'tag open') { |
} elsif ($self->{state} == TAG_OPEN_STATE) { |
| 445 |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
| 446 |
if ($self->{next_input_character} == 0x002F) { # / |
if ($self->{next_input_character} == 0x002F) { # / |
| 447 |
!!!next-input-character; |
!!!next-input-character; |
| 448 |
$self->{state} = 'close tag open'; |
$self->{state} = CLOSE_TAG_OPEN_STATE; |
| 449 |
redo A; |
redo A; |
| 450 |
} else { |
} else { |
| 451 |
## reconsume |
## reconsume |
| 452 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 453 |
|
|
| 454 |
!!!emit ({type => 'character', data => '<'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '<'}); |
| 455 |
|
|
| 456 |
redo A; |
redo A; |
| 457 |
} |
} |
| 458 |
} elsif ($self->{content_model} & CM_FULL_MARKUP) { # PCDATA |
} elsif ($self->{content_model} & CM_FULL_MARKUP) { # PCDATA |
| 459 |
if ($self->{next_input_character} == 0x0021) { # ! |
if ($self->{next_input_character} == 0x0021) { # ! |
| 460 |
$self->{state} = 'markup declaration open'; |
$self->{state} = MARKUP_DECLARATION_OPEN_STATE; |
| 461 |
!!!next-input-character; |
!!!next-input-character; |
| 462 |
redo A; |
redo A; |
| 463 |
} elsif ($self->{next_input_character} == 0x002F) { # / |
} elsif ($self->{next_input_character} == 0x002F) { # / |
| 464 |
$self->{state} = 'close tag open'; |
$self->{state} = CLOSE_TAG_OPEN_STATE; |
| 465 |
!!!next-input-character; |
!!!next-input-character; |
| 466 |
redo A; |
redo A; |
| 467 |
} elsif (0x0041 <= $self->{next_input_character} and |
} elsif (0x0041 <= $self->{next_input_character} and |
| 468 |
$self->{next_input_character} <= 0x005A) { # A..Z |
$self->{next_input_character} <= 0x005A) { # A..Z |
| 469 |
$self->{current_token} |
$self->{current_token} |
| 470 |
= {type => 'start tag', |
= {type => START_TAG_TOKEN, |
| 471 |
tag_name => chr ($self->{next_input_character} + 0x0020)}; |
tag_name => chr ($self->{next_input_character} + 0x0020)}; |
| 472 |
$self->{state} = 'tag name'; |
$self->{state} = TAG_NAME_STATE; |
| 473 |
!!!next-input-character; |
!!!next-input-character; |
| 474 |
redo A; |
redo A; |
| 475 |
} elsif (0x0061 <= $self->{next_input_character} and |
} elsif (0x0061 <= $self->{next_input_character} and |
| 476 |
$self->{next_input_character} <= 0x007A) { # a..z |
$self->{next_input_character} <= 0x007A) { # a..z |
| 477 |
$self->{current_token} = {type => 'start tag', |
$self->{current_token} = {type => START_TAG_TOKEN, |
| 478 |
tag_name => chr ($self->{next_input_character})}; |
tag_name => chr ($self->{next_input_character})}; |
| 479 |
$self->{state} = 'tag name'; |
$self->{state} = TAG_NAME_STATE; |
| 480 |
!!!next-input-character; |
!!!next-input-character; |
| 481 |
redo A; |
redo A; |
| 482 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 483 |
!!!parse-error (type => 'empty start tag'); |
!!!parse-error (type => 'empty start tag'); |
| 484 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 485 |
!!!next-input-character; |
!!!next-input-character; |
| 486 |
|
|
| 487 |
!!!emit ({type => 'character', data => '<>'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '<>'}); |
| 488 |
|
|
| 489 |
redo A; |
redo A; |
| 490 |
} elsif ($self->{next_input_character} == 0x003F) { # ? |
} elsif ($self->{next_input_character} == 0x003F) { # ? |
| 491 |
!!!parse-error (type => 'pio'); |
!!!parse-error (type => 'pio'); |
| 492 |
$self->{state} = 'bogus comment'; |
$self->{state} = BOGUS_COMMENT_STATE; |
| 493 |
## $self->{next_input_character} is intentionally left as is |
## $self->{next_input_character} is intentionally left as is |
| 494 |
redo A; |
redo A; |
| 495 |
} else { |
} else { |
| 496 |
!!!parse-error (type => 'bare stago'); |
!!!parse-error (type => 'bare stago'); |
| 497 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 498 |
## reconsume |
## reconsume |
| 499 |
|
|
| 500 |
!!!emit ({type => 'character', data => '<'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '<'}); |
| 501 |
|
|
| 502 |
redo A; |
redo A; |
| 503 |
} |
} |
| 504 |
} else { |
} else { |
| 505 |
die "$0: $self->{content_model} in tag open"; |
die "$0: $self->{content_model} in tag open"; |
| 506 |
} |
} |
| 507 |
} elsif ($self->{state} eq 'close tag open') { |
} elsif ($self->{state} == CLOSE_TAG_OPEN_STATE) { |
| 508 |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
| 509 |
if (defined $self->{last_emitted_start_tag_name}) { |
if (defined $self->{last_emitted_start_tag_name}) { |
| 510 |
## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564> |
## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564> |
| 519 |
} else { |
} else { |
| 520 |
$self->{next_input_character} = shift @next_char; # reconsume |
$self->{next_input_character} = shift @next_char; # reconsume |
| 521 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 522 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 523 |
|
|
| 524 |
!!!emit ({type => 'character', data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
| 525 |
|
|
| 526 |
redo A; |
redo A; |
| 527 |
} |
} |
| 538 |
$self->{next_input_character} == -1) { |
$self->{next_input_character} == -1) { |
| 539 |
$self->{next_input_character} = shift @next_char; # reconsume |
$self->{next_input_character} = shift @next_char; # reconsume |
| 540 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 541 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 542 |
!!!emit ({type => 'character', data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
| 543 |
redo A; |
redo A; |
| 544 |
} else { |
} else { |
| 545 |
$self->{next_input_character} = shift @next_char; |
$self->{next_input_character} = shift @next_char; |
| 549 |
} else { |
} else { |
| 550 |
## No start tag token has ever been emitted |
## No start tag token has ever been emitted |
| 551 |
# next-input-character is already done |
# next-input-character is already done |
| 552 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 553 |
!!!emit ({type => 'character', data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
| 554 |
redo A; |
redo A; |
| 555 |
} |
} |
| 556 |
} |
} |
| 557 |
|
|
| 558 |
if (0x0041 <= $self->{next_input_character} and |
if (0x0041 <= $self->{next_input_character} and |
| 559 |
$self->{next_input_character} <= 0x005A) { # A..Z |
$self->{next_input_character} <= 0x005A) { # A..Z |
| 560 |
$self->{current_token} = {type => 'end tag', |
$self->{current_token} = {type => END_TAG_TOKEN, |
| 561 |
tag_name => chr ($self->{next_input_character} + 0x0020)}; |
tag_name => chr ($self->{next_input_character} + 0x0020)}; |
| 562 |
$self->{state} = 'tag name'; |
$self->{state} = TAG_NAME_STATE; |
| 563 |
!!!next-input-character; |
!!!next-input-character; |
| 564 |
redo A; |
redo A; |
| 565 |
} elsif (0x0061 <= $self->{next_input_character} and |
} elsif (0x0061 <= $self->{next_input_character} and |
| 566 |
$self->{next_input_character} <= 0x007A) { # a..z |
$self->{next_input_character} <= 0x007A) { # a..z |
| 567 |
$self->{current_token} = {type => 'end tag', |
$self->{current_token} = {type => END_TAG_TOKEN, |
| 568 |
tag_name => chr ($self->{next_input_character})}; |
tag_name => chr ($self->{next_input_character})}; |
| 569 |
$self->{state} = 'tag name'; |
$self->{state} = TAG_NAME_STATE; |
| 570 |
!!!next-input-character; |
!!!next-input-character; |
| 571 |
redo A; |
redo A; |
| 572 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 573 |
!!!parse-error (type => 'empty end tag'); |
!!!parse-error (type => 'empty end tag'); |
| 574 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 575 |
!!!next-input-character; |
!!!next-input-character; |
| 576 |
redo A; |
redo A; |
| 577 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 578 |
!!!parse-error (type => 'bare etago'); |
!!!parse-error (type => 'bare etago'); |
| 579 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 580 |
# reconsume |
# reconsume |
| 581 |
|
|
| 582 |
!!!emit ({type => 'character', data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
| 583 |
|
|
| 584 |
redo A; |
redo A; |
| 585 |
} else { |
} else { |
| 586 |
!!!parse-error (type => 'bogus end tag'); |
!!!parse-error (type => 'bogus end tag'); |
| 587 |
$self->{state} = 'bogus comment'; |
$self->{state} = BOGUS_COMMENT_STATE; |
| 588 |
## $self->{next_input_character} is intentionally left as is |
## $self->{next_input_character} is intentionally left as is |
| 589 |
redo A; |
redo A; |
| 590 |
} |
} |
| 591 |
} elsif ($self->{state} eq 'tag name') { |
} elsif ($self->{state} == TAG_NAME_STATE) { |
| 592 |
if ($self->{next_input_character} == 0x0009 or # HT |
if ($self->{next_input_character} == 0x0009 or # HT |
| 593 |
$self->{next_input_character} == 0x000A or # LF |
$self->{next_input_character} == 0x000A or # LF |
| 594 |
$self->{next_input_character} == 0x000B or # VT |
$self->{next_input_character} == 0x000B or # VT |
| 595 |
$self->{next_input_character} == 0x000C or # FF |
$self->{next_input_character} == 0x000C or # FF |
| 596 |
$self->{next_input_character} == 0x0020) { # SP |
$self->{next_input_character} == 0x0020) { # SP |
| 597 |
$self->{state} = 'before attribute name'; |
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
| 598 |
!!!next-input-character; |
!!!next-input-character; |
| 599 |
redo A; |
redo A; |
| 600 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 601 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 602 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 603 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 604 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 605 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 606 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 607 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 608 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 610 |
} else { |
} else { |
| 611 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 612 |
} |
} |
| 613 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 614 |
!!!next-input-character; |
!!!next-input-character; |
| 615 |
|
|
| 616 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 625 |
redo A; |
redo A; |
| 626 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 627 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 628 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 629 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 630 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 631 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 632 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 633 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 634 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 635 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 637 |
} else { |
} else { |
| 638 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 639 |
} |
} |
| 640 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 641 |
# reconsume |
# reconsume |
| 642 |
|
|
| 643 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 646 |
} elsif ($self->{next_input_character} == 0x002F) { # / |
} elsif ($self->{next_input_character} == 0x002F) { # / |
| 647 |
!!!next-input-character; |
!!!next-input-character; |
| 648 |
if ($self->{next_input_character} == 0x003E and # > |
if ($self->{next_input_character} == 0x003E and # > |
| 649 |
$self->{current_token}->{type} eq 'start tag' and |
$self->{current_token}->{type} == START_TAG_TOKEN and |
| 650 |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
| 651 |
# permitted slash |
# permitted slash |
| 652 |
# |
# |
| 653 |
} else { |
} else { |
| 654 |
!!!parse-error (type => 'nestc'); |
!!!parse-error (type => 'nestc'); |
| 655 |
} |
} |
| 656 |
$self->{state} = 'before attribute name'; |
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
| 657 |
# next-input-character is already done |
# next-input-character is already done |
| 658 |
redo A; |
redo A; |
| 659 |
} else { |
} else { |
| 663 |
!!!next-input-character; |
!!!next-input-character; |
| 664 |
redo A; |
redo A; |
| 665 |
} |
} |
| 666 |
} elsif ($self->{state} eq 'before attribute name') { |
} elsif ($self->{state} == BEFORE_ATTRIBUTE_NAME_STATE) { |
| 667 |
if ($self->{next_input_character} == 0x0009 or # HT |
if ($self->{next_input_character} == 0x0009 or # HT |
| 668 |
$self->{next_input_character} == 0x000A or # LF |
$self->{next_input_character} == 0x000A or # LF |
| 669 |
$self->{next_input_character} == 0x000B or # VT |
$self->{next_input_character} == 0x000B or # VT |
| 673 |
!!!next-input-character; |
!!!next-input-character; |
| 674 |
redo A; |
redo A; |
| 675 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 676 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 677 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 678 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 679 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 680 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 681 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 682 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 683 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 685 |
} else { |
} else { |
| 686 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 687 |
} |
} |
| 688 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 689 |
!!!next-input-character; |
!!!next-input-character; |
| 690 |
|
|
| 691 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 695 |
$self->{next_input_character} <= 0x005A) { # A..Z |
$self->{next_input_character} <= 0x005A) { # A..Z |
| 696 |
$self->{current_attribute} = {name => chr ($self->{next_input_character} + 0x0020), |
$self->{current_attribute} = {name => chr ($self->{next_input_character} + 0x0020), |
| 697 |
value => ''}; |
value => ''}; |
| 698 |
$self->{state} = 'attribute name'; |
$self->{state} = ATTRIBUTE_NAME_STATE; |
| 699 |
!!!next-input-character; |
!!!next-input-character; |
| 700 |
redo A; |
redo A; |
| 701 |
} elsif ($self->{next_input_character} == 0x002F) { # / |
} elsif ($self->{next_input_character} == 0x002F) { # / |
| 702 |
!!!next-input-character; |
!!!next-input-character; |
| 703 |
if ($self->{next_input_character} == 0x003E and # > |
if ($self->{next_input_character} == 0x003E and # > |
| 704 |
$self->{current_token}->{type} eq 'start tag' and |
$self->{current_token}->{type} == START_TAG_TOKEN and |
| 705 |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
| 706 |
# permitted slash |
# permitted slash |
| 707 |
# |
# |
| 713 |
redo A; |
redo A; |
| 714 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 715 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 716 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 717 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 718 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 719 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 720 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 721 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 722 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 723 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 725 |
} else { |
} else { |
| 726 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 727 |
} |
} |
| 728 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 729 |
# reconsume |
# reconsume |
| 730 |
|
|
| 731 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 734 |
} else { |
} else { |
| 735 |
$self->{current_attribute} = {name => chr ($self->{next_input_character}), |
$self->{current_attribute} = {name => chr ($self->{next_input_character}), |
| 736 |
value => ''}; |
value => ''}; |
| 737 |
$self->{state} = 'attribute name'; |
$self->{state} = ATTRIBUTE_NAME_STATE; |
| 738 |
!!!next-input-character; |
!!!next-input-character; |
| 739 |
redo A; |
redo A; |
| 740 |
} |
} |
| 741 |
} elsif ($self->{state} eq 'attribute name') { |
} elsif ($self->{state} == ATTRIBUTE_NAME_STATE) { |
| 742 |
my $before_leave = sub { |
my $before_leave = sub { |
| 743 |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
| 744 |
->{$self->{current_attribute}->{name}}) { # MUST |
->{$self->{current_attribute}->{name}}) { # MUST |
| 756 |
$self->{next_input_character} == 0x000C or # FF |
$self->{next_input_character} == 0x000C or # FF |
| 757 |
$self->{next_input_character} == 0x0020) { # SP |
$self->{next_input_character} == 0x0020) { # SP |
| 758 |
$before_leave->(); |
$before_leave->(); |
| 759 |
$self->{state} = 'after attribute name'; |
$self->{state} = AFTER_ATTRIBUTE_NAME_STATE; |
| 760 |
!!!next-input-character; |
!!!next-input-character; |
| 761 |
redo A; |
redo A; |
| 762 |
} elsif ($self->{next_input_character} == 0x003D) { # = |
} elsif ($self->{next_input_character} == 0x003D) { # = |
| 763 |
$before_leave->(); |
$before_leave->(); |
| 764 |
$self->{state} = 'before attribute value'; |
$self->{state} = BEFORE_ATTRIBUTE_VALUE_STATE; |
| 765 |
!!!next-input-character; |
!!!next-input-character; |
| 766 |
redo A; |
redo A; |
| 767 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 768 |
$before_leave->(); |
$before_leave->(); |
| 769 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 770 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 771 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 772 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 773 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 774 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 775 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 776 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 778 |
} else { |
} else { |
| 779 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 780 |
} |
} |
| 781 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 782 |
!!!next-input-character; |
!!!next-input-character; |
| 783 |
|
|
| 784 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 794 |
$before_leave->(); |
$before_leave->(); |
| 795 |
!!!next-input-character; |
!!!next-input-character; |
| 796 |
if ($self->{next_input_character} == 0x003E and # > |
if ($self->{next_input_character} == 0x003E and # > |
| 797 |
$self->{current_token}->{type} eq 'start tag' and |
$self->{current_token}->{type} == START_TAG_TOKEN and |
| 798 |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
| 799 |
# permitted slash |
# permitted slash |
| 800 |
# |
# |
| 801 |
} else { |
} else { |
| 802 |
!!!parse-error (type => 'nestc'); |
!!!parse-error (type => 'nestc'); |
| 803 |
} |
} |
| 804 |
$self->{state} = 'before attribute name'; |
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
| 805 |
# next-input-character is already done |
# next-input-character is already done |
| 806 |
redo A; |
redo A; |
| 807 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 808 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 809 |
$before_leave->(); |
$before_leave->(); |
| 810 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 811 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 812 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 813 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 814 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 815 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 816 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 817 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 819 |
} else { |
} else { |
| 820 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 821 |
} |
} |
| 822 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 823 |
# reconsume |
# reconsume |
| 824 |
|
|
| 825 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 831 |
!!!next-input-character; |
!!!next-input-character; |
| 832 |
redo A; |
redo A; |
| 833 |
} |
} |
| 834 |
} elsif ($self->{state} eq 'after attribute name') { |
} elsif ($self->{state} == AFTER_ATTRIBUTE_NAME_STATE) { |
| 835 |
if ($self->{next_input_character} == 0x0009 or # HT |
if ($self->{next_input_character} == 0x0009 or # HT |
| 836 |
$self->{next_input_character} == 0x000A or # LF |
$self->{next_input_character} == 0x000A or # LF |
| 837 |
$self->{next_input_character} == 0x000B or # VT |
$self->{next_input_character} == 0x000B or # VT |
| 841 |
!!!next-input-character; |
!!!next-input-character; |
| 842 |
redo A; |
redo A; |
| 843 |
} elsif ($self->{next_input_character} == 0x003D) { # = |
} elsif ($self->{next_input_character} == 0x003D) { # = |
| 844 |
$self->{state} = 'before attribute value'; |
$self->{state} = BEFORE_ATTRIBUTE_VALUE_STATE; |
| 845 |
!!!next-input-character; |
!!!next-input-character; |
| 846 |
redo A; |
redo A; |
| 847 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 848 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 849 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 850 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 851 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 852 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 853 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 854 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 855 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 857 |
} else { |
} else { |
| 858 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 859 |
} |
} |
| 860 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 861 |
!!!next-input-character; |
!!!next-input-character; |
| 862 |
|
|
| 863 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 867 |
$self->{next_input_character} <= 0x005A) { # A..Z |
$self->{next_input_character} <= 0x005A) { # A..Z |
| 868 |
$self->{current_attribute} = {name => chr ($self->{next_input_character} + 0x0020), |
$self->{current_attribute} = {name => chr ($self->{next_input_character} + 0x0020), |
| 869 |
value => ''}; |
value => ''}; |
| 870 |
$self->{state} = 'attribute name'; |
$self->{state} = ATTRIBUTE_NAME_STATE; |
| 871 |
!!!next-input-character; |
!!!next-input-character; |
| 872 |
redo A; |
redo A; |
| 873 |
} elsif ($self->{next_input_character} == 0x002F) { # / |
} elsif ($self->{next_input_character} == 0x002F) { # / |
| 874 |
!!!next-input-character; |
!!!next-input-character; |
| 875 |
if ($self->{next_input_character} == 0x003E and # > |
if ($self->{next_input_character} == 0x003E and # > |
| 876 |
$self->{current_token}->{type} eq 'start tag' and |
$self->{current_token}->{type} == START_TAG_TOKEN and |
| 877 |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
| 878 |
# permitted slash |
# permitted slash |
| 879 |
# |
# |
| 881 |
!!!parse-error (type => 'nestc'); |
!!!parse-error (type => 'nestc'); |
| 882 |
## TODO: Different error type for <aa / bb> than <aa/> |
## TODO: Different error type for <aa / bb> than <aa/> |
| 883 |
} |
} |
| 884 |
$self->{state} = 'before attribute name'; |
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
| 885 |
# next-input-character is already done |
# next-input-character is already done |
| 886 |
redo A; |
redo A; |
| 887 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 888 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 889 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 890 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 891 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 892 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 893 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 894 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 895 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 896 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 898 |
} else { |
} else { |
| 899 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 900 |
} |
} |
| 901 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 902 |
# reconsume |
# reconsume |
| 903 |
|
|
| 904 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 907 |
} else { |
} else { |
| 908 |
$self->{current_attribute} = {name => chr ($self->{next_input_character}), |
$self->{current_attribute} = {name => chr ($self->{next_input_character}), |
| 909 |
value => ''}; |
value => ''}; |
| 910 |
$self->{state} = 'attribute name'; |
$self->{state} = ATTRIBUTE_NAME_STATE; |
| 911 |
!!!next-input-character; |
!!!next-input-character; |
| 912 |
redo A; |
redo A; |
| 913 |
} |
} |
| 914 |
} elsif ($self->{state} eq 'before attribute value') { |
} elsif ($self->{state} == BEFORE_ATTRIBUTE_VALUE_STATE) { |
| 915 |
if ($self->{next_input_character} == 0x0009 or # HT |
if ($self->{next_input_character} == 0x0009 or # HT |
| 916 |
$self->{next_input_character} == 0x000A or # LF |
$self->{next_input_character} == 0x000A or # LF |
| 917 |
$self->{next_input_character} == 0x000B or # VT |
$self->{next_input_character} == 0x000B or # VT |
| 921 |
!!!next-input-character; |
!!!next-input-character; |
| 922 |
redo A; |
redo A; |
| 923 |
} elsif ($self->{next_input_character} == 0x0022) { # " |
} elsif ($self->{next_input_character} == 0x0022) { # " |
| 924 |
$self->{state} = 'attribute value (double-quoted)'; |
$self->{state} = ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE; |
| 925 |
!!!next-input-character; |
!!!next-input-character; |
| 926 |
redo A; |
redo A; |
| 927 |
} elsif ($self->{next_input_character} == 0x0026) { # & |
} elsif ($self->{next_input_character} == 0x0026) { # & |
| 928 |
$self->{state} = 'attribute value (unquoted)'; |
$self->{state} = ATTRIBUTE_VALUE_UNQUOTED_STATE; |
| 929 |
## reconsume |
## reconsume |
| 930 |
redo A; |
redo A; |
| 931 |
} elsif ($self->{next_input_character} == 0x0027) { # ' |
} elsif ($self->{next_input_character} == 0x0027) { # ' |
| 932 |
$self->{state} = 'attribute value (single-quoted)'; |
$self->{state} = ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE; |
| 933 |
!!!next-input-character; |
!!!next-input-character; |
| 934 |
redo A; |
redo A; |
| 935 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 936 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 937 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 938 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 939 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 940 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 941 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 942 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 943 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 945 |
} else { |
} else { |
| 946 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 947 |
} |
} |
| 948 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 949 |
!!!next-input-character; |
!!!next-input-character; |
| 950 |
|
|
| 951 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 953 |
redo A; |
redo A; |
| 954 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 955 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 956 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 957 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 958 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 959 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 960 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 961 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 962 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 963 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 965 |
} else { |
} else { |
| 966 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 967 |
} |
} |
| 968 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 969 |
## reconsume |
## reconsume |
| 970 |
|
|
| 971 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 973 |
redo A; |
redo A; |
| 974 |
} else { |
} else { |
| 975 |
$self->{current_attribute}->{value} .= chr ($self->{next_input_character}); |
$self->{current_attribute}->{value} .= chr ($self->{next_input_character}); |
| 976 |
$self->{state} = 'attribute value (unquoted)'; |
$self->{state} = ATTRIBUTE_VALUE_UNQUOTED_STATE; |
| 977 |
!!!next-input-character; |
!!!next-input-character; |
| 978 |
redo A; |
redo A; |
| 979 |
} |
} |
| 980 |
} elsif ($self->{state} eq 'attribute value (double-quoted)') { |
} elsif ($self->{state} == ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE) { |
| 981 |
if ($self->{next_input_character} == 0x0022) { # " |
if ($self->{next_input_character} == 0x0022) { # " |
| 982 |
$self->{state} = 'before attribute name'; |
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
| 983 |
!!!next-input-character; |
!!!next-input-character; |
| 984 |
redo A; |
redo A; |
| 985 |
} elsif ($self->{next_input_character} == 0x0026) { # & |
} elsif ($self->{next_input_character} == 0x0026) { # & |
| 986 |
$self->{last_attribute_value_state} = 'attribute value (double-quoted)'; |
$self->{last_attribute_value_state} = $self->{state}; |
| 987 |
$self->{state} = 'entity in attribute value'; |
$self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE; |
| 988 |
!!!next-input-character; |
!!!next-input-character; |
| 989 |
redo A; |
redo A; |
| 990 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 991 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
| 992 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 993 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 994 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 995 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 996 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 997 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 998 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 999 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 1001 |
} else { |
} else { |
| 1002 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 1003 |
} |
} |
| 1004 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1005 |
## reconsume |
## reconsume |
| 1006 |
|
|
| 1007 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 1013 |
!!!next-input-character; |
!!!next-input-character; |
| 1014 |
redo A; |
redo A; |
| 1015 |
} |
} |
| 1016 |
} elsif ($self->{state} eq 'attribute value (single-quoted)') { |
} elsif ($self->{state} == ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE) { |
| 1017 |
if ($self->{next_input_character} == 0x0027) { # ' |
if ($self->{next_input_character} == 0x0027) { # ' |
| 1018 |
$self->{state} = 'before attribute name'; |
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
| 1019 |
!!!next-input-character; |
!!!next-input-character; |
| 1020 |
redo A; |
redo A; |
| 1021 |
} elsif ($self->{next_input_character} == 0x0026) { # & |
} elsif ($self->{next_input_character} == 0x0026) { # & |
| 1022 |
$self->{last_attribute_value_state} = 'attribute value (single-quoted)'; |
$self->{last_attribute_value_state} = $self->{state}; |
| 1023 |
$self->{state} = 'entity in attribute value'; |
$self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE; |
| 1024 |
!!!next-input-character; |
!!!next-input-character; |
| 1025 |
redo A; |
redo A; |
| 1026 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1027 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
| 1028 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1029 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 1030 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 1031 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1032 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1033 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1034 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 1035 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 1037 |
} else { |
} else { |
| 1038 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 1039 |
} |
} |
| 1040 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1041 |
## reconsume |
## reconsume |
| 1042 |
|
|
| 1043 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 1049 |
!!!next-input-character; |
!!!next-input-character; |
| 1050 |
redo A; |
redo A; |
| 1051 |
} |
} |
| 1052 |
} elsif ($self->{state} eq 'attribute value (unquoted)') { |
} elsif ($self->{state} == ATTRIBUTE_VALUE_UNQUOTED_STATE) { |
| 1053 |
if ($self->{next_input_character} == 0x0009 or # HT |
if ($self->{next_input_character} == 0x0009 or # HT |
| 1054 |
$self->{next_input_character} == 0x000A or # LF |
$self->{next_input_character} == 0x000A or # LF |
| 1055 |
$self->{next_input_character} == 0x000B or # HT |
$self->{next_input_character} == 0x000B or # HT |
| 1056 |
$self->{next_input_character} == 0x000C or # FF |
$self->{next_input_character} == 0x000C or # FF |
| 1057 |
$self->{next_input_character} == 0x0020) { # SP |
$self->{next_input_character} == 0x0020) { # SP |
| 1058 |
$self->{state} = 'before attribute name'; |
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
| 1059 |
!!!next-input-character; |
!!!next-input-character; |
| 1060 |
redo A; |
redo A; |
| 1061 |
} elsif ($self->{next_input_character} == 0x0026) { # & |
} elsif ($self->{next_input_character} == 0x0026) { # & |
| 1062 |
$self->{last_attribute_value_state} = 'attribute value (unquoted)'; |
$self->{last_attribute_value_state} = $self->{state}; |
| 1063 |
$self->{state} = 'entity in attribute value'; |
$self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE; |
| 1064 |
!!!next-input-character; |
!!!next-input-character; |
| 1065 |
redo A; |
redo A; |
| 1066 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1067 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1068 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 1069 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 1070 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1071 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1072 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1073 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 1074 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 1076 |
} else { |
} else { |
| 1077 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 1078 |
} |
} |
| 1079 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1080 |
!!!next-input-character; |
!!!next-input-character; |
| 1081 |
|
|
| 1082 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 1084 |
redo A; |
redo A; |
| 1085 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1086 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 1087 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1088 |
$self->{current_token}->{first_start_tag} |
$self->{current_token}->{first_start_tag} |
| 1089 |
= not defined $self->{last_emitted_start_tag_name}; |
= not defined $self->{last_emitted_start_tag_name}; |
| 1090 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1091 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1092 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1093 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 1094 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 1096 |
} else { |
} else { |
| 1097 |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
| 1098 |
} |
} |
| 1099 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1100 |
## reconsume |
## reconsume |
| 1101 |
|
|
| 1102 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
| 1108 |
!!!next-input-character; |
!!!next-input-character; |
| 1109 |
redo A; |
redo A; |
| 1110 |
} |
} |
| 1111 |
} elsif ($self->{state} eq 'entity in attribute value') { |
} elsif ($self->{state} == ENTITY_IN_ATTRIBUTE_VALUE_STATE) { |
| 1112 |
my $token = $self->_tokenize_attempt_to_consume_an_entity (1); |
my $token = $self->_tokenize_attempt_to_consume_an_entity (1); |
| 1113 |
|
|
| 1114 |
unless (defined $token) { |
unless (defined $token) { |
| 1121 |
$self->{state} = $self->{last_attribute_value_state}; |
$self->{state} = $self->{last_attribute_value_state}; |
| 1122 |
# next-input-character is already done |
# next-input-character is already done |
| 1123 |
redo A; |
redo A; |
| 1124 |
} elsif ($self->{state} eq 'bogus comment') { |
} elsif ($self->{state} == BOGUS_COMMENT_STATE) { |
| 1125 |
## (only happen if PCDATA state) |
## (only happen if PCDATA state) |
| 1126 |
|
|
| 1127 |
my $token = {type => 'comment', data => ''}; |
my $token = {type => COMMENT_TOKEN, data => ''}; |
| 1128 |
|
|
| 1129 |
BC: { |
BC: { |
| 1130 |
if ($self->{next_input_character} == 0x003E) { # > |
if ($self->{next_input_character} == 0x003E) { # > |
| 1131 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1132 |
!!!next-input-character; |
!!!next-input-character; |
| 1133 |
|
|
| 1134 |
!!!emit ($token); |
!!!emit ($token); |
| 1135 |
|
|
| 1136 |
redo A; |
redo A; |
| 1137 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1138 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1139 |
## reconsume |
## reconsume |
| 1140 |
|
|
| 1141 |
!!!emit ($token); |
!!!emit ($token); |
| 1147 |
redo BC; |
redo BC; |
| 1148 |
} |
} |
| 1149 |
} # BC |
} # BC |
| 1150 |
} elsif ($self->{state} eq 'markup declaration open') { |
} elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) { |
| 1151 |
## (only happen if PCDATA state) |
## (only happen if PCDATA state) |
| 1152 |
|
|
| 1153 |
my @next_char; |
my @next_char; |
| 1157 |
!!!next-input-character; |
!!!next-input-character; |
| 1158 |
push @next_char, $self->{next_input_character}; |
push @next_char, $self->{next_input_character}; |
| 1159 |
if ($self->{next_input_character} == 0x002D) { # - |
if ($self->{next_input_character} == 0x002D) { # - |
| 1160 |
$self->{current_token} = {type => 'comment', data => ''}; |
$self->{current_token} = {type => COMMENT_TOKEN, data => ''}; |
| 1161 |
$self->{state} = 'comment start'; |
$self->{state} = COMMENT_START_STATE; |
| 1162 |
!!!next-input-character; |
!!!next-input-character; |
| 1163 |
redo A; |
redo A; |
| 1164 |
} |
} |
| 1189 |
if ($self->{next_input_character} == 0x0045 or # E |
if ($self->{next_input_character} == 0x0045 or # E |
| 1190 |
$self->{next_input_character} == 0x0065) { # e |
$self->{next_input_character} == 0x0065) { # e |
| 1191 |
## ISSUE: What a stupid code this is! |
## ISSUE: What a stupid code this is! |
| 1192 |
$self->{state} = 'DOCTYPE'; |
$self->{state} = DOCTYPE_STATE; |
| 1193 |
!!!next-input-character; |
!!!next-input-character; |
| 1194 |
redo A; |
redo A; |
| 1195 |
} |
} |
| 1203 |
!!!parse-error (type => 'bogus comment'); |
!!!parse-error (type => 'bogus comment'); |
| 1204 |
$self->{next_input_character} = shift @next_char; |
$self->{next_input_character} = shift @next_char; |
| 1205 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 1206 |
$self->{state} = 'bogus comment'; |
$self->{state} = BOGUS_COMMENT_STATE; |
| 1207 |
redo A; |
redo A; |
| 1208 |
|
|
| 1209 |
## ISSUE: typos in spec: chacacters, is is a parse error |
## ISSUE: typos in spec: chacacters, is is a parse error |
| 1210 |
## ISSUE: spec is somewhat unclear on "is the first character that will be in the comment"; what is "that will be in the comment" is what the algorithm defines, isn't it? |
## ISSUE: spec is somewhat unclear on "is the first character that will be in the comment"; what is "that will be in the comment" is what the algorithm defines, isn't it? |
| 1211 |
} elsif ($self->{state} eq 'comment start') { |
} elsif ($self->{state} == COMMENT_START_STATE) { |
| 1212 |
if ($self->{next_input_character} == 0x002D) { # - |
if ($self->{next_input_character} == 0x002D) { # - |
| 1213 |
$self->{state} = 'comment start dash'; |
$self->{state} = COMMENT_START_DASH_STATE; |
| 1214 |
!!!next-input-character; |
!!!next-input-character; |
| 1215 |
redo A; |
redo A; |
| 1216 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1217 |
!!!parse-error (type => 'bogus comment'); |
!!!parse-error (type => 'bogus comment'); |
| 1218 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1219 |
!!!next-input-character; |
!!!next-input-character; |
| 1220 |
|
|
| 1221 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
| 1223 |
redo A; |
redo A; |
| 1224 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1225 |
!!!parse-error (type => 'unclosed comment'); |
!!!parse-error (type => 'unclosed comment'); |
| 1226 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1227 |
## reconsume |
## reconsume |
| 1228 |
|
|
| 1229 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
| 1232 |
} else { |
} else { |
| 1233 |
$self->{current_token}->{data} # comment |
$self->{current_token}->{data} # comment |
| 1234 |
.= chr ($self->{next_input_character}); |
.= chr ($self->{next_input_character}); |
| 1235 |
$self->{state} = 'comment'; |
$self->{state} = COMMENT_STATE; |
| 1236 |
!!!next-input-character; |
!!!next-input-character; |
| 1237 |
redo A; |
redo A; |
| 1238 |
} |
} |
| 1239 |
} elsif ($self->{state} eq 'comment start dash') { |
} elsif ($self->{state} == COMMENT_START_DASH_STATE) { |
| 1240 |
if ($self->{next_input_character} == 0x002D) { # - |
if ($self->{next_input_character} == 0x002D) { # - |
| 1241 |
$self->{state} = 'comment end'; |
$self->{state} = COMMENT_END_STATE; |
| 1242 |
!!!next-input-character; |
!!!next-input-character; |
| 1243 |
redo A; |
redo A; |
| 1244 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1245 |
!!!parse-error (type => 'bogus comment'); |
!!!parse-error (type => 'bogus comment'); |
| 1246 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1247 |
!!!next-input-character; |
!!!next-input-character; |
| 1248 |
|
|
| 1249 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
| 1251 |
redo A; |
redo A; |
| 1252 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1253 |
!!!parse-error (type => 'unclosed comment'); |
!!!parse-error (type => 'unclosed comment'); |
| 1254 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1255 |
## reconsume |
## reconsume |
| 1256 |
|
|
| 1257 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
| 1260 |
} else { |
} else { |
| 1261 |
$self->{current_token}->{data} # comment |
$self->{current_token}->{data} # comment |
| 1262 |
.= '-' . chr ($self->{next_input_character}); |
.= '-' . chr ($self->{next_input_character}); |
| 1263 |
$self->{state} = 'comment'; |
$self->{state} = COMMENT_STATE; |
| 1264 |
!!!next-input-character; |
!!!next-input-character; |
| 1265 |
redo A; |
redo A; |
| 1266 |
} |
} |
| 1267 |
} elsif ($self->{state} eq 'comment') { |
} elsif ($self->{state} == COMMENT_STATE) { |
| 1268 |
if ($self->{next_input_character} == 0x002D) { # - |
if ($self->{next_input_character} == 0x002D) { # - |
| 1269 |
$self->{state} = 'comment end dash'; |
$self->{state} = COMMENT_END_DASH_STATE; |
| 1270 |
!!!next-input-character; |
!!!next-input-character; |
| 1271 |
redo A; |
redo A; |
| 1272 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1273 |
!!!parse-error (type => 'unclosed comment'); |
!!!parse-error (type => 'unclosed comment'); |
| 1274 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1275 |
## reconsume |
## reconsume |
| 1276 |
|
|
| 1277 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
| 1283 |
!!!next-input-character; |
!!!next-input-character; |
| 1284 |
redo A; |
redo A; |
| 1285 |
} |
} |
| 1286 |
} elsif ($self->{state} eq 'comment end dash') { |
} elsif ($self->{state} == COMMENT_END_DASH_STATE) { |
| 1287 |
if ($self->{next_input_character} == 0x002D) { # - |
if ($self->{next_input_character} == 0x002D) { # - |
| 1288 |
$self->{state} = 'comment end'; |
$self->{state} = COMMENT_END_STATE; |
| 1289 |
!!!next-input-character; |
!!!next-input-character; |
| 1290 |
redo A; |
redo A; |
| 1291 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1292 |
!!!parse-error (type => 'unclosed comment'); |
!!!parse-error (type => 'unclosed comment'); |
| 1293 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1294 |
## reconsume |
## reconsume |
| 1295 |
|
|
| 1296 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
| 1298 |
redo A; |
redo A; |
| 1299 |
} else { |
} else { |
| 1300 |
$self->{current_token}->{data} .= '-' . chr ($self->{next_input_character}); # comment |
$self->{current_token}->{data} .= '-' . chr ($self->{next_input_character}); # comment |
| 1301 |
$self->{state} = 'comment'; |
$self->{state} = COMMENT_STATE; |
| 1302 |
!!!next-input-character; |
!!!next-input-character; |
| 1303 |
redo A; |
redo A; |
| 1304 |
} |
} |
| 1305 |
} elsif ($self->{state} eq 'comment end') { |
} elsif ($self->{state} == COMMENT_END_STATE) { |
| 1306 |
if ($self->{next_input_character} == 0x003E) { # > |
if ($self->{next_input_character} == 0x003E) { # > |
| 1307 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1308 |
!!!next-input-character; |
!!!next-input-character; |
| 1309 |
|
|
| 1310 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
| 1318 |
redo A; |
redo A; |
| 1319 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1320 |
!!!parse-error (type => 'unclosed comment'); |
!!!parse-error (type => 'unclosed comment'); |
| 1321 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1322 |
## reconsume |
## reconsume |
| 1323 |
|
|
| 1324 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
| 1327 |
} else { |
} else { |
| 1328 |
!!!parse-error (type => 'dash in comment'); |
!!!parse-error (type => 'dash in comment'); |
| 1329 |
$self->{current_token}->{data} .= '--' . chr ($self->{next_input_character}); # comment |
$self->{current_token}->{data} .= '--' . chr ($self->{next_input_character}); # comment |
| 1330 |
$self->{state} = 'comment'; |
$self->{state} = COMMENT_STATE; |
| 1331 |
!!!next-input-character; |
!!!next-input-character; |
| 1332 |
redo A; |
redo A; |
| 1333 |
} |
} |
| 1334 |
} elsif ($self->{state} eq 'DOCTYPE') { |
} elsif ($self->{state} == DOCTYPE_STATE) { |
| 1335 |
if ($self->{next_input_character} == 0x0009 or # HT |
if ($self->{next_input_character} == 0x0009 or # HT |
| 1336 |
$self->{next_input_character} == 0x000A or # LF |
$self->{next_input_character} == 0x000A or # LF |
| 1337 |
$self->{next_input_character} == 0x000B or # VT |
$self->{next_input_character} == 0x000B or # VT |
| 1338 |
$self->{next_input_character} == 0x000C or # FF |
$self->{next_input_character} == 0x000C or # FF |
| 1339 |
$self->{next_input_character} == 0x0020) { # SP |
$self->{next_input_character} == 0x0020) { # SP |
| 1340 |
$self->{state} = 'before DOCTYPE name'; |
$self->{state} = BEFORE_DOCTYPE_NAME_STATE; |
| 1341 |
!!!next-input-character; |
!!!next-input-character; |
| 1342 |
redo A; |
redo A; |
| 1343 |
} else { |
} else { |
| 1344 |
!!!parse-error (type => 'no space before DOCTYPE name'); |
!!!parse-error (type => 'no space before DOCTYPE name'); |
| 1345 |
$self->{state} = 'before DOCTYPE name'; |
$self->{state} = BEFORE_DOCTYPE_NAME_STATE; |
| 1346 |
## reconsume |
## reconsume |
| 1347 |
redo A; |
redo A; |
| 1348 |
} |
} |
| 1349 |
} elsif ($self->{state} eq 'before DOCTYPE name') { |
} elsif ($self->{state} == BEFORE_DOCTYPE_NAME_STATE) { |
| 1350 |
if ($self->{next_input_character} == 0x0009 or # HT |
if ($self->{next_input_character} == 0x0009 or # HT |
| 1351 |
$self->{next_input_character} == 0x000A or # LF |
$self->{next_input_character} == 0x000A or # LF |
| 1352 |
$self->{next_input_character} == 0x000B or # VT |
$self->{next_input_character} == 0x000B or # VT |
| 1357 |
redo A; |
redo A; |
| 1358 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1359 |
!!!parse-error (type => 'no DOCTYPE name'); |
!!!parse-error (type => 'no DOCTYPE name'); |
| 1360 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1361 |
!!!next-input-character; |
!!!next-input-character; |
| 1362 |
|
|
| 1363 |
!!!emit ({type => 'DOCTYPE'}); # incorrect |
!!!emit ({type => DOCTYPE_TOKEN}); # incorrect |
| 1364 |
|
|
| 1365 |
redo A; |
redo A; |
| 1366 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1367 |
!!!parse-error (type => 'no DOCTYPE name'); |
!!!parse-error (type => 'no DOCTYPE name'); |
| 1368 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1369 |
## reconsume |
## reconsume |
| 1370 |
|
|
| 1371 |
!!!emit ({type => 'DOCTYPE'}); # incorrect |
!!!emit ({type => DOCTYPE_TOKEN}); # incorrect |
| 1372 |
|
|
| 1373 |
redo A; |
redo A; |
| 1374 |
} else { |
} else { |
| 1375 |
$self->{current_token} |
$self->{current_token} |
| 1376 |
= {type => 'DOCTYPE', |
= {type => DOCTYPE_TOKEN, |
| 1377 |
name => chr ($self->{next_input_character}), |
name => chr ($self->{next_input_character}), |
| 1378 |
correct => 1}; |
correct => 1}; |
| 1379 |
## ISSUE: "Set the token's name name to the" in the spec |
## ISSUE: "Set the token's name name to the" in the spec |
| 1380 |
$self->{state} = 'DOCTYPE name'; |
$self->{state} = DOCTYPE_NAME_STATE; |
| 1381 |
!!!next-input-character; |
!!!next-input-character; |
| 1382 |
redo A; |
redo A; |
| 1383 |
} |
} |
| 1384 |
} elsif ($self->{state} eq 'DOCTYPE name') { |
} elsif ($self->{state} == DOCTYPE_NAME_STATE) { |
| 1385 |
## ISSUE: Redundant "First," in the spec. |
## ISSUE: Redundant "First," in the spec. |
| 1386 |
if ($self->{next_input_character} == 0x0009 or # HT |
if ($self->{next_input_character} == 0x0009 or # HT |
| 1387 |
$self->{next_input_character} == 0x000A or # LF |
$self->{next_input_character} == 0x000A or # LF |
| 1388 |
$self->{next_input_character} == 0x000B or # VT |
$self->{next_input_character} == 0x000B or # VT |
| 1389 |
$self->{next_input_character} == 0x000C or # FF |
$self->{next_input_character} == 0x000C or # FF |
| 1390 |
$self->{next_input_character} == 0x0020) { # SP |
$self->{next_input_character} == 0x0020) { # SP |
| 1391 |
$self->{state} = 'after DOCTYPE name'; |
$self->{state} = AFTER_DOCTYPE_NAME_STATE; |
| 1392 |
!!!next-input-character; |
!!!next-input-character; |
| 1393 |
redo A; |
redo A; |
| 1394 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1395 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1396 |
!!!next-input-character; |
!!!next-input-character; |
| 1397 |
|
|
| 1398 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
| 1400 |
redo A; |
redo A; |
| 1401 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1402 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1403 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1404 |
## reconsume |
## reconsume |
| 1405 |
|
|
| 1406 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1414 |
!!!next-input-character; |
!!!next-input-character; |
| 1415 |
redo A; |
redo A; |
| 1416 |
} |
} |
| 1417 |
} elsif ($self->{state} eq 'after DOCTYPE name') { |
} elsif ($self->{state} == AFTER_DOCTYPE_NAME_STATE) { |
| 1418 |
if ($self->{next_input_character} == 0x0009 or # HT |
if ($self->{next_input_character} == 0x0009 or # HT |
| 1419 |
$self->{next_input_character} == 0x000A or # LF |
$self->{next_input_character} == 0x000A or # LF |
| 1420 |
$self->{next_input_character} == 0x000B or # VT |
$self->{next_input_character} == 0x000B or # VT |
| 1424 |
!!!next-input-character; |
!!!next-input-character; |
| 1425 |
redo A; |
redo A; |
| 1426 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1427 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1428 |
!!!next-input-character; |
!!!next-input-character; |
| 1429 |
|
|
| 1430 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
| 1432 |
redo A; |
redo A; |
| 1433 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1434 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1435 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1436 |
## reconsume |
## reconsume |
| 1437 |
|
|
| 1438 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1456 |
!!!next-input-character; |
!!!next-input-character; |
| 1457 |
if ($self->{next_input_character} == 0x0043 or # C |
if ($self->{next_input_character} == 0x0043 or # C |
| 1458 |
$self->{next_input_character} == 0x0063) { # c |
$self->{next_input_character} == 0x0063) { # c |
| 1459 |
$self->{state} = 'before DOCTYPE public identifier'; |
$self->{state} = BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE; |
| 1460 |
!!!next-input-character; |
!!!next-input-character; |
| 1461 |
redo A; |
redo A; |
| 1462 |
} |
} |
| 1483 |
!!!next-input-character; |
!!!next-input-character; |
| 1484 |
if ($self->{next_input_character} == 0x004D or # M |
if ($self->{next_input_character} == 0x004D or # M |
| 1485 |
$self->{next_input_character} == 0x006D) { # m |
$self->{next_input_character} == 0x006D) { # m |
| 1486 |
$self->{state} = 'before DOCTYPE system identifier'; |
$self->{state} = BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE; |
| 1487 |
!!!next-input-character; |
!!!next-input-character; |
| 1488 |
redo A; |
redo A; |
| 1489 |
} |
} |
| 1499 |
} |
} |
| 1500 |
|
|
| 1501 |
!!!parse-error (type => 'string after DOCTYPE name'); |
!!!parse-error (type => 'string after DOCTYPE name'); |
| 1502 |
$self->{state} = 'bogus DOCTYPE'; |
$self->{state} = BOGUS_DOCTYPE_STATE; |
| 1503 |
# next-input-character is already done |
# next-input-character is already done |
| 1504 |
redo A; |
redo A; |
| 1505 |
} elsif ($self->{state} eq 'before DOCTYPE public identifier') { |
} elsif ($self->{state} == BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE) { |
| 1506 |
if ({ |
if ({ |
| 1507 |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
| 1508 |
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
| 1512 |
redo A; |
redo A; |
| 1513 |
} elsif ($self->{next_input_character} eq 0x0022) { # " |
} elsif ($self->{next_input_character} eq 0x0022) { # " |
| 1514 |
$self->{current_token}->{public_identifier} = ''; # DOCTYPE |
$self->{current_token}->{public_identifier} = ''; # DOCTYPE |
| 1515 |
$self->{state} = 'DOCTYPE public identifier (double-quoted)'; |
$self->{state} = DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE; |
| 1516 |
!!!next-input-character; |
!!!next-input-character; |
| 1517 |
redo A; |
redo A; |
| 1518 |
} elsif ($self->{next_input_character} eq 0x0027) { # ' |
} elsif ($self->{next_input_character} eq 0x0027) { # ' |
| 1519 |
$self->{current_token}->{public_identifier} = ''; # DOCTYPE |
$self->{current_token}->{public_identifier} = ''; # DOCTYPE |
| 1520 |
$self->{state} = 'DOCTYPE public identifier (single-quoted)'; |
$self->{state} = DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE; |
| 1521 |
!!!next-input-character; |
!!!next-input-character; |
| 1522 |
redo A; |
redo A; |
| 1523 |
} elsif ($self->{next_input_character} eq 0x003E) { # > |
} elsif ($self->{next_input_character} eq 0x003E) { # > |
| 1524 |
!!!parse-error (type => 'no PUBLIC literal'); |
!!!parse-error (type => 'no PUBLIC literal'); |
| 1525 |
|
|
| 1526 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1527 |
!!!next-input-character; |
!!!next-input-character; |
| 1528 |
|
|
| 1529 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1533 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1534 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1535 |
|
|
| 1536 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1537 |
## reconsume |
## reconsume |
| 1538 |
|
|
| 1539 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1542 |
redo A; |
redo A; |
| 1543 |
} else { |
} else { |
| 1544 |
!!!parse-error (type => 'string after PUBLIC'); |
!!!parse-error (type => 'string after PUBLIC'); |
| 1545 |
$self->{state} = 'bogus DOCTYPE'; |
$self->{state} = BOGUS_DOCTYPE_STATE; |
| 1546 |
!!!next-input-character; |
!!!next-input-character; |
| 1547 |
redo A; |
redo A; |
| 1548 |
} |
} |
| 1549 |
} elsif ($self->{state} eq 'DOCTYPE public identifier (double-quoted)') { |
} elsif ($self->{state} == DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE) { |
| 1550 |
if ($self->{next_input_character} == 0x0022) { # " |
if ($self->{next_input_character} == 0x0022) { # " |
| 1551 |
$self->{state} = 'after DOCTYPE public identifier'; |
$self->{state} = AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE; |
| 1552 |
!!!next-input-character; |
!!!next-input-character; |
| 1553 |
redo A; |
redo A; |
| 1554 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1555 |
!!!parse-error (type => 'unclosed PUBLIC literal'); |
!!!parse-error (type => 'unclosed PUBLIC literal'); |
| 1556 |
|
|
| 1557 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1558 |
## reconsume |
## reconsume |
| 1559 |
|
|
| 1560 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1568 |
!!!next-input-character; |
!!!next-input-character; |
| 1569 |
redo A; |
redo A; |
| 1570 |
} |
} |
| 1571 |
} elsif ($self->{state} eq 'DOCTYPE public identifier (single-quoted)') { |
} elsif ($self->{state} == DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE) { |
| 1572 |
if ($self->{next_input_character} == 0x0027) { # ' |
if ($self->{next_input_character} == 0x0027) { # ' |
| 1573 |
$self->{state} = 'after DOCTYPE public identifier'; |
$self->{state} = AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE; |
| 1574 |
!!!next-input-character; |
!!!next-input-character; |
| 1575 |
redo A; |
redo A; |
| 1576 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1577 |
!!!parse-error (type => 'unclosed PUBLIC literal'); |
!!!parse-error (type => 'unclosed PUBLIC literal'); |
| 1578 |
|
|
| 1579 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1580 |
## reconsume |
## reconsume |
| 1581 |
|
|
| 1582 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1590 |
!!!next-input-character; |
!!!next-input-character; |
| 1591 |
redo A; |
redo A; |
| 1592 |
} |
} |
| 1593 |
} elsif ($self->{state} eq 'after DOCTYPE public identifier') { |
} elsif ($self->{state} == AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE) { |
| 1594 |
if ({ |
if ({ |
| 1595 |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
| 1596 |
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
| 1600 |
redo A; |
redo A; |
| 1601 |
} elsif ($self->{next_input_character} == 0x0022) { # " |
} elsif ($self->{next_input_character} == 0x0022) { # " |
| 1602 |
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
| 1603 |
$self->{state} = 'DOCTYPE system identifier (double-quoted)'; |
$self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE; |
| 1604 |
!!!next-input-character; |
!!!next-input-character; |
| 1605 |
redo A; |
redo A; |
| 1606 |
} elsif ($self->{next_input_character} == 0x0027) { # ' |
} elsif ($self->{next_input_character} == 0x0027) { # ' |
| 1607 |
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
| 1608 |
$self->{state} = 'DOCTYPE system identifier (single-quoted)'; |
$self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE; |
| 1609 |
!!!next-input-character; |
!!!next-input-character; |
| 1610 |
redo A; |
redo A; |
| 1611 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1612 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1613 |
!!!next-input-character; |
!!!next-input-character; |
| 1614 |
|
|
| 1615 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
| 1618 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1619 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1620 |
|
|
| 1621 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1622 |
## reconsume |
## reconsume |
| 1623 |
|
|
| 1624 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1627 |
redo A; |
redo A; |
| 1628 |
} else { |
} else { |
| 1629 |
!!!parse-error (type => 'string after PUBLIC literal'); |
!!!parse-error (type => 'string after PUBLIC literal'); |
| 1630 |
$self->{state} = 'bogus DOCTYPE'; |
$self->{state} = BOGUS_DOCTYPE_STATE; |
| 1631 |
!!!next-input-character; |
!!!next-input-character; |
| 1632 |
redo A; |
redo A; |
| 1633 |
} |
} |
| 1634 |
} elsif ($self->{state} eq 'before DOCTYPE system identifier') { |
} elsif ($self->{state} == BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE) { |
| 1635 |
if ({ |
if ({ |
| 1636 |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
| 1637 |
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
| 1641 |
redo A; |
redo A; |
| 1642 |
} elsif ($self->{next_input_character} == 0x0022) { # " |
} elsif ($self->{next_input_character} == 0x0022) { # " |
| 1643 |
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
| 1644 |
$self->{state} = 'DOCTYPE system identifier (double-quoted)'; |
$self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE; |
| 1645 |
!!!next-input-character; |
!!!next-input-character; |
| 1646 |
redo A; |
redo A; |
| 1647 |
} elsif ($self->{next_input_character} == 0x0027) { # ' |
} elsif ($self->{next_input_character} == 0x0027) { # ' |
| 1648 |
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
| 1649 |
$self->{state} = 'DOCTYPE system identifier (single-quoted)'; |
$self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE; |
| 1650 |
!!!next-input-character; |
!!!next-input-character; |
| 1651 |
redo A; |
redo A; |
| 1652 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1653 |
!!!parse-error (type => 'no SYSTEM literal'); |
!!!parse-error (type => 'no SYSTEM literal'); |
| 1654 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1655 |
!!!next-input-character; |
!!!next-input-character; |
| 1656 |
|
|
| 1657 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1661 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1662 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1663 |
|
|
| 1664 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1665 |
## reconsume |
## reconsume |
| 1666 |
|
|
| 1667 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1670 |
redo A; |
redo A; |
| 1671 |
} else { |
} else { |
| 1672 |
!!!parse-error (type => 'string after SYSTEM'); |
!!!parse-error (type => 'string after SYSTEM'); |
| 1673 |
$self->{state} = 'bogus DOCTYPE'; |
$self->{state} = BOGUS_DOCTYPE_STATE; |
| 1674 |
!!!next-input-character; |
!!!next-input-character; |
| 1675 |
redo A; |
redo A; |
| 1676 |
} |
} |
| 1677 |
} elsif ($self->{state} eq 'DOCTYPE system identifier (double-quoted)') { |
} elsif ($self->{state} == DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE) { |
| 1678 |
if ($self->{next_input_character} == 0x0022) { # " |
if ($self->{next_input_character} == 0x0022) { # " |
| 1679 |
$self->{state} = 'after DOCTYPE system identifier'; |
$self->{state} = AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE; |
| 1680 |
!!!next-input-character; |
!!!next-input-character; |
| 1681 |
redo A; |
redo A; |
| 1682 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1683 |
!!!parse-error (type => 'unclosed SYSTEM literal'); |
!!!parse-error (type => 'unclosed SYSTEM literal'); |
| 1684 |
|
|
| 1685 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1686 |
## reconsume |
## reconsume |
| 1687 |
|
|
| 1688 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1696 |
!!!next-input-character; |
!!!next-input-character; |
| 1697 |
redo A; |
redo A; |
| 1698 |
} |
} |
| 1699 |
} elsif ($self->{state} eq 'DOCTYPE system identifier (single-quoted)') { |
} elsif ($self->{state} == DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE) { |
| 1700 |
if ($self->{next_input_character} == 0x0027) { # ' |
if ($self->{next_input_character} == 0x0027) { # ' |
| 1701 |
$self->{state} = 'after DOCTYPE system identifier'; |
$self->{state} = AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE; |
| 1702 |
!!!next-input-character; |
!!!next-input-character; |
| 1703 |
redo A; |
redo A; |
| 1704 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1705 |
!!!parse-error (type => 'unclosed SYSTEM literal'); |
!!!parse-error (type => 'unclosed SYSTEM literal'); |
| 1706 |
|
|
| 1707 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1708 |
## reconsume |
## reconsume |
| 1709 |
|
|
| 1710 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1718 |
!!!next-input-character; |
!!!next-input-character; |
| 1719 |
redo A; |
redo A; |
| 1720 |
} |
} |
| 1721 |
} elsif ($self->{state} eq 'after DOCTYPE system identifier') { |
} elsif ($self->{state} == AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE) { |
| 1722 |
if ({ |
if ({ |
| 1723 |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
| 1724 |
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
| 1727 |
!!!next-input-character; |
!!!next-input-character; |
| 1728 |
redo A; |
redo A; |
| 1729 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1730 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1731 |
!!!next-input-character; |
!!!next-input-character; |
| 1732 |
|
|
| 1733 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
| 1736 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1737 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1738 |
|
|
| 1739 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1740 |
## reconsume |
## reconsume |
| 1741 |
|
|
| 1742 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1745 |
redo A; |
redo A; |
| 1746 |
} else { |
} else { |
| 1747 |
!!!parse-error (type => 'string after SYSTEM literal'); |
!!!parse-error (type => 'string after SYSTEM literal'); |
| 1748 |
$self->{state} = 'bogus DOCTYPE'; |
$self->{state} = BOGUS_DOCTYPE_STATE; |
| 1749 |
!!!next-input-character; |
!!!next-input-character; |
| 1750 |
redo A; |
redo A; |
| 1751 |
} |
} |
| 1752 |
} elsif ($self->{state} eq 'bogus DOCTYPE') { |
} elsif ($self->{state} == BOGUS_DOCTYPE_STATE) { |
| 1753 |
if ($self->{next_input_character} == 0x003E) { # > |
if ($self->{next_input_character} == 0x003E) { # > |
| 1754 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1755 |
!!!next-input-character; |
!!!next-input-character; |
| 1756 |
|
|
| 1757 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1760 |
redo A; |
redo A; |
| 1761 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1762 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1763 |
$self->{state} = 'data'; |
$self->{state} = DATA_STATE; |
| 1764 |
## reconsume |
## reconsume |
| 1765 |
|
|
| 1766 |
delete $self->{current_token}->{correct}; |
delete $self->{current_token}->{correct}; |
| 1841 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 1842 |
} |
} |
| 1843 |
|
|
| 1844 |
return {type => 'character', data => chr $code}; |
return {type => CHARACTER_TOKEN, data => chr $code}; |
| 1845 |
} # X |
} # X |
| 1846 |
} elsif (0x0030 <= $self->{next_input_character} and |
} elsif (0x0030 <= $self->{next_input_character} and |
| 1847 |
$self->{next_input_character} <= 0x0039) { # 0..9 |
$self->{next_input_character} <= 0x0039) { # 0..9 |
| 1876 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 1877 |
} |
} |
| 1878 |
|
|
| 1879 |
return {type => 'character', data => chr $code}; |
return {type => CHARACTER_TOKEN, data => chr $code}; |
| 1880 |
} else { |
} else { |
| 1881 |
!!!parse-error (type => 'bare nero'); |
!!!parse-error (type => 'bare nero'); |
| 1882 |
!!!back-next-input-character ($self->{next_input_character}); |
!!!back-next-input-character ($self->{next_input_character}); |
| 1924 |
} |
} |
| 1925 |
|
|
| 1926 |
if ($match > 0) { |
if ($match > 0) { |
| 1927 |
return {type => 'character', data => $value}; |
return {type => CHARACTER_TOKEN, data => $value}; |
| 1928 |
} elsif ($match < 0) { |
} elsif ($match < 0) { |
| 1929 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'no refc'); |
| 1930 |
if ($in_attr and $match < -1) { |
if ($in_attr and $match < -1) { |
| 1931 |
return {type => 'character', data => '&'.$entity_name}; |
return {type => CHARACTER_TOKEN, data => '&'.$entity_name}; |
| 1932 |
} else { |
} else { |
| 1933 |
return {type => 'character', data => $value}; |
return {type => CHARACTER_TOKEN, data => $value}; |
| 1934 |
} |
} |
| 1935 |
} else { |
} else { |
| 1936 |
!!!parse-error (type => 'bare ero'); |
!!!parse-error (type => 'bare ero'); |
| 1937 |
## NOTE: No characters are consumed in the spec. |
## NOTE: No characters are consumed in the spec. |
| 1938 |
return {type => 'character', data => '&'.$value}; |
return {type => CHARACTER_TOKEN, data => '&'.$value}; |
| 1939 |
} |
} |
| 1940 |
} else { |
} else { |
| 1941 |
## no characters are consumed |
## no characters are consumed |
| 1977 |
|
|
| 1978 |
!!!next-token; |
!!!next-token; |
| 1979 |
|
|
| 1980 |
$self->{insertion_mode} = 'before head'; |
$self->{insertion_mode} = BEFORE_HEAD_IM; |
| 1981 |
undef $self->{form_element}; |
undef $self->{form_element}; |
| 1982 |
undef $self->{head_element}; |
undef $self->{head_element}; |
| 1983 |
$self->{open_elements} = []; |
$self->{open_elements} = []; |
| 1991 |
sub _tree_construction_initial ($) { |
sub _tree_construction_initial ($) { |
| 1992 |
my $self = shift; |
my $self = shift; |
| 1993 |
INITIAL: { |
INITIAL: { |
| 1994 |
if ($token->{type} eq 'DOCTYPE') { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 1995 |
## NOTE: Conformance checkers MAY, instead of reporting "not HTML5" |
## NOTE: Conformance checkers MAY, instead of reporting "not HTML5" |
| 1996 |
## error, switch to a conformance checking mode for another |
## error, switch to a conformance checking mode for another |
| 1997 |
## language. |
## language. |
| 2118 |
!!!next-token; |
!!!next-token; |
| 2119 |
return; |
return; |
| 2120 |
} elsif ({ |
} elsif ({ |
| 2121 |
'start tag' => 1, |
START_TAG_TOKEN, 1, |
| 2122 |
'end tag' => 1, |
END_TAG_TOKEN, 1, |
| 2123 |
'end-of-file' => 1, |
END_OF_FILE_TOKEN, 1, |
| 2124 |
}->{$token->{type}}) { |
}->{$token->{type}}) { |
| 2125 |
!!!parse-error (type => 'no DOCTYPE'); |
!!!parse-error (type => 'no DOCTYPE'); |
| 2126 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 2127 |
## Go to the root element phase |
## Go to the root element phase |
| 2128 |
## reprocess |
## reprocess |
| 2129 |
return; |
return; |
| 2130 |
} elsif ($token->{type} eq 'character') { |
} elsif ($token->{type} == CHARACTER_TOKEN) { |
| 2131 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
| 2132 |
## Ignore the token |
## Ignore the token |
| 2133 |
|
|
| 2143 |
## Go to the root element phase |
## Go to the root element phase |
| 2144 |
## reprocess |
## reprocess |
| 2145 |
return; |
return; |
| 2146 |
} elsif ($token->{type} eq 'comment') { |
} elsif ($token->{type} == COMMENT_TOKEN) { |
| 2147 |
my $comment = $self->{document}->create_comment ($token->{data}); |
my $comment = $self->{document}->create_comment ($token->{data}); |
| 2148 |
$self->{document}->append_child ($comment); |
$self->{document}->append_child ($comment); |
| 2149 |
|
|
| 2151 |
!!!next-token; |
!!!next-token; |
| 2152 |
redo INITIAL; |
redo INITIAL; |
| 2153 |
} else { |
} else { |
| 2154 |
die "$0: $token->{type}: Unknown token"; |
die "$0: $token->{type}: Unknown token type"; |
| 2155 |
} |
} |
| 2156 |
} # INITIAL |
} # INITIAL |
| 2157 |
} # _tree_construction_initial |
} # _tree_construction_initial |
| 2160 |
my $self = shift; |
my $self = shift; |
| 2161 |
|
|
| 2162 |
B: { |
B: { |
| 2163 |
if ($token->{type} eq 'DOCTYPE') { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 2164 |
!!!parse-error (type => 'in html:#DOCTYPE'); |
!!!parse-error (type => 'in html:#DOCTYPE'); |
| 2165 |
## Ignore the token |
## Ignore the token |
| 2166 |
## Stay in the phase |
## Stay in the phase |
| 2167 |
!!!next-token; |
!!!next-token; |
| 2168 |
redo B; |
redo B; |
| 2169 |
} elsif ($token->{type} eq 'comment') { |
} elsif ($token->{type} == COMMENT_TOKEN) { |
| 2170 |
my $comment = $self->{document}->create_comment ($token->{data}); |
my $comment = $self->{document}->create_comment ($token->{data}); |
| 2171 |
$self->{document}->append_child ($comment); |
$self->{document}->append_child ($comment); |
| 2172 |
## Stay in the phase |
## Stay in the phase |
| 2173 |
!!!next-token; |
!!!next-token; |
| 2174 |
redo B; |
redo B; |
| 2175 |
} elsif ($token->{type} eq 'character') { |
} elsif ($token->{type} == CHARACTER_TOKEN) { |
| 2176 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
| 2177 |
## Ignore the token. |
## Ignore the token. |
| 2178 |
|
|
| 2182 |
redo B; |
redo B; |
| 2183 |
} |
} |
| 2184 |
} |
} |
| 2185 |
|
|
| 2186 |
|
$self->{application_cache_selection}->(undef); |
| 2187 |
|
|
| 2188 |
|
# |
| 2189 |
|
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 2190 |
|
if ($token->{tag_name} eq 'html' and |
| 2191 |
|
$token->{attributes}->{manifest}) { ## ISSUE: Spec spells as "application" |
| 2192 |
|
$self->{application_cache_selection} |
| 2193 |
|
->($token->{attributes}->{manifest}->{value}); |
| 2194 |
|
## ISSUE: No relative reference resolution? |
| 2195 |
|
} else { |
| 2196 |
|
$self->{application_cache_selection}->(undef); |
| 2197 |
|
} |
| 2198 |
|
|
| 2199 |
|
## ISSUE: There is an issue in the spec |
| 2200 |
# |
# |
| 2201 |
} elsif ({ |
} elsif ({ |
| 2202 |
'start tag' => 1, |
END_TAG_TOKEN, 1, |
| 2203 |
'end tag' => 1, |
END_OF_FILE_TOKEN, 1, |
|
'end-of-file' => 1, |
|
| 2204 |
}->{$token->{type}}) { |
}->{$token->{type}}) { |
| 2205 |
|
$self->{application_cache_selection}->(undef); |
| 2206 |
|
|
| 2207 |
## ISSUE: There is an issue in the spec |
## ISSUE: There is an issue in the spec |
| 2208 |
# |
# |
| 2209 |
} else { |
} else { |
| 2210 |
die "$0: $token->{type}: Unknown token"; |
die "$0: $token->{type}: Unknown token type"; |
| 2211 |
} |
} |
| 2212 |
|
|
| 2213 |
my $root_element; !!!create-element ($root_element, 'html'); |
my $root_element; !!!create-element ($root_element, 'html'); |
| 2214 |
$self->{document}->append_child ($root_element); |
$self->{document}->append_child ($root_element); |
| 2215 |
push @{$self->{open_elements}}, [$root_element, 'html']; |
push @{$self->{open_elements}}, [$root_element, 'html']; |
| 2250 |
|
|
| 2251 |
## Step 4..13 |
## Step 4..13 |
| 2252 |
my $new_mode = { |
my $new_mode = { |
| 2253 |
select => 'in select', |
select => IN_SELECT_IM, |
| 2254 |
td => 'in cell', |
td => IN_CELL_IM, |
| 2255 |
th => 'in cell', |
th => IN_CELL_IM, |
| 2256 |
tr => 'in row', |
tr => IN_ROW_IM, |
| 2257 |
tbody => 'in table body', |
tbody => IN_TABLE_BODY_IM, |
| 2258 |
thead => 'in table head', |
thead => IN_TABLE_BODY_IM, |
| 2259 |
tfoot => 'in table foot', |
tfoot => IN_TABLE_BODY_IM, |
| 2260 |
caption => 'in caption', |
caption => IN_CAPTION_IM, |
| 2261 |
colgroup => 'in column group', |
colgroup => IN_COLUMN_GROUP_IM, |
| 2262 |
table => 'in table', |
table => IN_TABLE_IM, |
| 2263 |
head => 'in body', # not in head! |
head => IN_BODY_IM, # not in head! |
| 2264 |
body => 'in body', |
body => IN_BODY_IM, |
| 2265 |
frameset => 'in frameset', |
frameset => IN_FRAMESET_IM, |
| 2266 |
}->{$node->[1]}; |
}->{$node->[1]}; |
| 2267 |
$self->{insertion_mode} = $new_mode and return if defined $new_mode; |
$self->{insertion_mode} = $new_mode and return if defined $new_mode; |
| 2268 |
|
|
| 2269 |
## Step 14 |
## Step 14 |
| 2270 |
if ($node->[1] eq 'html') { |
if ($node->[1] eq 'html') { |
| 2271 |
unless (defined $self->{head_element}) { |
unless (defined $self->{head_element}) { |
| 2272 |
$self->{insertion_mode} = 'before head'; |
$self->{insertion_mode} = BEFORE_HEAD_IM; |
| 2273 |
} else { |
} else { |
| 2274 |
$self->{insertion_mode} = 'after head'; |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 2275 |
} |
} |
| 2276 |
return; |
return; |
| 2277 |
} |
} |
| 2278 |
|
|
| 2279 |
## Step 15 |
## Step 15 |
| 2280 |
$self->{insertion_mode} = 'in body' and return if $last; |
$self->{insertion_mode} = IN_BODY_IM and return if $last; |
| 2281 |
|
|
| 2282 |
## Step 16 |
## Step 16 |
| 2283 |
$i--; |
$i--; |
| 2291 |
sub _tree_construction_main ($) { |
sub _tree_construction_main ($) { |
| 2292 |
my $self = shift; |
my $self = shift; |
| 2293 |
|
|
|
my $previous_insertion_mode; |
|
|
|
|
| 2294 |
my $active_formatting_elements = []; |
my $active_formatting_elements = []; |
| 2295 |
|
|
| 2296 |
my $reconstruct_active_formatting_elements = sub { # MUST |
my $reconstruct_active_formatting_elements = sub { # MUST |
| 2391 |
## Step 4 |
## Step 4 |
| 2392 |
my $text = ''; |
my $text = ''; |
| 2393 |
!!!next-token; |
!!!next-token; |
| 2394 |
while ($token->{type} eq 'character') { # or until stop tokenizing |
while ($token->{type} == CHARACTER_TOKEN) { # or until stop tokenizing |
| 2395 |
$text .= $token->{data}; |
$text .= $token->{data}; |
| 2396 |
!!!next-token; |
!!!next-token; |
| 2397 |
} |
} |
| 2406 |
$self->{content_model} = PCDATA_CONTENT_MODEL; |
$self->{content_model} = PCDATA_CONTENT_MODEL; |
| 2407 |
|
|
| 2408 |
## Step 7 |
## Step 7 |
| 2409 |
if ($token->{type} eq 'end tag' and $token->{tag_name} eq $start_tag_name) { |
if ($token->{type} == END_TAG_TOKEN and $token->{tag_name} eq $start_tag_name) { |
| 2410 |
## Ignore the token |
## Ignore the token |
| 2411 |
} elsif ($content_model_flag == CDATA_CONTENT_MODEL) { |
} elsif ($content_model_flag == CDATA_CONTENT_MODEL) { |
| 2412 |
!!!parse-error (type => 'in CDATA:#'.$token->{type}); |
!!!parse-error (type => 'in CDATA:#'.$token->{type}); |
| 2429 |
|
|
| 2430 |
my $text = ''; |
my $text = ''; |
| 2431 |
!!!next-token; |
!!!next-token; |
| 2432 |
while ($token->{type} eq 'character') { |
while ($token->{type} == CHARACTER_TOKEN) { |
| 2433 |
$text .= $token->{data}; |
$text .= $token->{data}; |
| 2434 |
!!!next-token; |
!!!next-token; |
| 2435 |
} # stop if non-character token or tokenizer stops tokenising |
} # stop if non-character token or tokenizer stops tokenising |
| 2439 |
|
|
| 2440 |
$self->{content_model} = PCDATA_CONTENT_MODEL; |
$self->{content_model} = PCDATA_CONTENT_MODEL; |
| 2441 |
|
|
| 2442 |
if ($token->{type} eq 'end tag' and |
if ($token->{type} == END_TAG_TOKEN and |
| 2443 |
$token->{tag_name} eq 'script') { |
$token->{tag_name} eq 'script') { |
| 2444 |
## Ignore the token |
## Ignore the token |
| 2445 |
} else { |
} else { |
| 2682 |
} |
} |
| 2683 |
}; # $insert_to_foster |
}; # $insert_to_foster |
| 2684 |
|
|
| 2685 |
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}}) { |
|
|
$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; |
|
|
} |
|
|
} |
|
|
}; # $in_body |
|
| 2686 |
|
|
| 2687 |
B: { |
B: { |
| 2688 |
if ($token->{type} eq 'DOCTYPE') { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 2689 |
!!!parse-error (type => 'DOCTYPE in the middle'); |
!!!parse-error (type => 'DOCTYPE in the middle'); |
| 2690 |
## Ignore the token |
## Ignore the token |
| 2691 |
## Stay in the phase |
## Stay in the phase |
| 2692 |
!!!next-token; |
!!!next-token; |
| 2693 |
redo B; |
redo B; |
| 2694 |
} elsif ($token->{type} eq 'end-of-file') { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 2695 |
if ($token->{insertion_mode} ne 'trailing end') { |
if ($self->{insertion_mode} & AFTER_HTML_IMS) { |
| 2696 |
|
# |
| 2697 |
|
} else { |
| 2698 |
## Generate implied end tags |
## Generate implied end tags |
| 2699 |
if ({ |
if ({ |
| 2700 |
dd => 1, dt => 1, li => 1, p => 1, td => 1, th => 1, tr => 1, |
dd => 1, dt => 1, li => 1, p => 1, td => 1, th => 1, tr => 1, |
| 2701 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 2702 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 2703 |
!!!back-token; |
!!!back-token; |
| 2704 |
$token = {type => 'end tag', tag_name => $self->{open_elements}->[-1]->[1]}; |
$token = {type => END_TAG_TOKEN, tag_name => $self->{open_elements}->[-1]->[1]}; |
| 2705 |
redo B; |
redo B; |
| 2706 |
} |
} |
| 2707 |
|
|
| 2719 |
|
|
| 2720 |
## Stop parsing |
## Stop parsing |
| 2721 |
last B; |
last B; |
| 2722 |
} elsif ($token->{type} eq 'start tag' and |
} elsif ($token->{type} == START_TAG_TOKEN and |
| 2723 |
$token->{tag_name} eq 'html') { |
$token->{tag_name} eq 'html') { |
| 2724 |
if ($self->{insertion_mode} eq 'trailing end') { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 2725 |
## Turn into the main phase |
## Turn into the main phase |
| 2726 |
!!!parse-error (type => 'after html:html'); |
!!!parse-error (type => 'after html:html'); |
| 2727 |
$self->{insertion_mode} = $previous_insertion_mode; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 2728 |
|
} elsif ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 2729 |
|
## Turn into the main phase |
| 2730 |
|
!!!parse-error (type => 'after html:html'); |
| 2731 |
|
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 2732 |
} |
} |
| 2733 |
|
|
| 2734 |
## ISSUE: "aa<html>" is not a parse error. |
## ISSUE: "aa<html>" is not a parse error. |
| 2746 |
} |
} |
| 2747 |
!!!next-token; |
!!!next-token; |
| 2748 |
redo B; |
redo B; |
| 2749 |
} elsif ($token->{type} eq 'comment') { |
} elsif ($token->{type} == COMMENT_TOKEN) { |
| 2750 |
my $comment = $self->{document}->create_comment ($token->{data}); |
my $comment = $self->{document}->create_comment ($token->{data}); |
| 2751 |
if ($self->{insertion_mode} eq 'trailing end') { |
if ($self->{insertion_mode} & AFTER_HTML_IMS) { |
| 2752 |
$self->{document}->append_child ($comment); |
$self->{document}->append_child ($comment); |
| 2753 |
} elsif ($self->{insertion_mode} eq 'after body') { |
} elsif ($self->{insertion_mode} == AFTER_BODY_IM) { |
| 2754 |
$self->{open_elements}->[0]->[0]->append_child ($comment); |
$self->{open_elements}->[0]->[0]->append_child ($comment); |
| 2755 |
} else { |
} else { |
| 2756 |
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
| 2757 |
} |
} |
| 2758 |
!!!next-token; |
!!!next-token; |
| 2759 |
redo B; |
redo B; |
| 2760 |
} elsif ($self->{insertion_mode} eq 'before head') { |
} elsif ($self->{insertion_mode} & HEAD_IMS) { |
| 2761 |
if ($token->{type} eq 'character') { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 2762 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 2763 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 2764 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 2765 |
!!!next-token; |
!!!next-token; |
| 2766 |
redo B; |
redo B; |
| 2767 |
} |
} |
| 2768 |
} |
} |
| 2769 |
## As if <head> |
|
| 2770 |
!!!create-element ($self->{head_element}, 'head'); |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 2771 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
## As if <head> |
| 2772 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
!!!create-element ($self->{head_element}, 'head'); |
| 2773 |
$self->{insertion_mode} = 'in head'; |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 2774 |
|
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 2775 |
|
|
| 2776 |
|
## Reprocess in the "in head" insertion mode... |
| 2777 |
|
pop @{$self->{open_elements}}; |
| 2778 |
|
|
| 2779 |
|
## Reprocess in the "after head" insertion mode... |
| 2780 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2781 |
|
## As if </noscript> |
| 2782 |
|
pop @{$self->{open_elements}}; |
| 2783 |
|
!!!parse-error (type => 'in noscript:#character'); |
| 2784 |
|
|
| 2785 |
|
## Reprocess in the "in head" insertion mode... |
| 2786 |
|
## As if </head> |
| 2787 |
|
pop @{$self->{open_elements}}; |
| 2788 |
|
|
| 2789 |
|
## Reprocess in the "after head" insertion mode... |
| 2790 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 2791 |
|
pop @{$self->{open_elements}}; |
| 2792 |
|
|
| 2793 |
|
## Reprocess in the "after head" insertion mode... |
| 2794 |
|
} |
| 2795 |
|
|
| 2796 |
|
## "after head" insertion mode |
| 2797 |
|
## As if <body> |
| 2798 |
|
!!!insert-element ('body'); |
| 2799 |
|
$self->{insertion_mode} = IN_BODY_IM; |
| 2800 |
## reprocess |
## reprocess |
| 2801 |
redo B; |
redo B; |
| 2802 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
|
my $attr = $token->{tag_name} eq 'head' ? $token->{attributes} : {}; |
|
|
!!!create-element ($self->{head_element}, 'head', $attr); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
|
|
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
|
|
$self->{insertion_mode} = 'in head'; |
|
| 2803 |
if ($token->{tag_name} eq 'head') { |
if ($token->{tag_name} eq 'head') { |
| 2804 |
!!!next-token; |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 2805 |
#} elsif ({ |
!!!create-element ($self->{head_element}, $token->{tag_name}, $token->{attributes}); |
| 2806 |
# base => 1, link => 1, meta => 1, |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 2807 |
# script => 1, style => 1, title => 1, |
push @{$self->{open_elements}}, [$self->{head_element}, $token->{tag_name}]; |
| 2808 |
# }->{$token->{tag_name}}) { |
$self->{insertion_mode} = IN_HEAD_IM; |
| 2809 |
# ## reprocess |
!!!next-token; |
| 2810 |
} else { |
redo B; |
| 2811 |
## reprocess |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2812 |
} |
# |
| 2813 |
redo B; |
} else { |
| 2814 |
} elsif ($token->{type} eq 'end tag') { |
!!!parse-error (type => 'in head:head'); # or in head noscript |
| 2815 |
if ({ |
## Ignore the token |
| 2816 |
head => 1, body => 1, html => 1, |
!!!next-token; |
| 2817 |
p => 1, br => 1, |
redo B; |
| 2818 |
}->{$token->{tag_name}}) { |
} |
| 2819 |
|
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 2820 |
## As if <head> |
## As if <head> |
| 2821 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, 'head'); |
| 2822 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 2823 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 2824 |
$self->{insertion_mode} = 'in head'; |
|
| 2825 |
## reprocess |
$self->{insertion_mode} = IN_HEAD_IM; |
| 2826 |
redo B; |
## Reprocess in the "in head" insertion mode... |
|
} else { |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token ## ISSUE: An issue in the spec. |
|
|
!!!next-token; |
|
|
redo B; |
|
| 2827 |
} |
} |
| 2828 |
} else { |
|
| 2829 |
die "$0: $token->{type}: Unknown type"; |
if ($token->{tag_name} eq 'base') { |
| 2830 |
} |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2831 |
} elsif ($self->{insertion_mode} eq 'in head' or |
## As if </noscript> |
| 2832 |
$self->{insertion_mode} eq 'in head noscript' or |
pop @{$self->{open_elements}}; |
| 2833 |
$self->{insertion_mode} eq 'after head') { |
!!!parse-error (type => 'in noscript:base'); |
| 2834 |
if ($token->{type} eq 'character') { |
|
| 2835 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
$self->{insertion_mode} = IN_HEAD_IM; |
| 2836 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
## Reprocess in the "in head" insertion mode... |
|
unless (length $token->{data}) { |
|
|
!!!next-token; |
|
|
redo B; |
|
| 2837 |
} |
} |
| 2838 |
} |
|
|
|
|
|
# |
|
|
} elsif ($token->{type} eq 'start tag') { |
|
|
if ({base => ($self->{insertion_mode} eq 'in head' or |
|
|
$self->{insertion_mode} eq 'after head'), |
|
|
link => 1}->{$token->{tag_name}}) { |
|
| 2839 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 2840 |
if ($self->{insertion_mode} eq 'after head') { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2841 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 2842 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 2843 |
} |
} |
| 2844 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 2845 |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 2846 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} |
| 2847 |
if $self->{insertion_mode} eq 'after head'; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 2848 |
|
!!!next-token; |
| 2849 |
|
redo B; |
| 2850 |
|
} elsif ($token->{tag_name} eq 'link') { |
| 2851 |
|
## NOTE: There is a "as if in head" code clone. |
| 2852 |
|
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2853 |
|
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 2854 |
|
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 2855 |
|
} |
| 2856 |
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 2857 |
|
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 2858 |
|
pop @{$self->{open_elements}} |
| 2859 |
|
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 2860 |
!!!next-token; |
!!!next-token; |
| 2861 |
redo B; |
redo B; |
| 2862 |
} elsif ($token->{tag_name} eq 'meta') { |
} elsif ($token->{tag_name} eq 'meta') { |
| 2863 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 2864 |
if ($self->{insertion_mode} eq 'after head') { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2865 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 2866 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 2867 |
} |
} |
| 2869 |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 2870 |
|
|
| 2871 |
unless ($self->{confident}) { |
unless ($self->{confident}) { |
|
my $charset; |
|
| 2872 |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
| 2873 |
$charset = $token->{attributes}->{charset}->{value}; |
$self->{change_encoding} |
| 2874 |
} |
->($self, $token->{attributes}->{charset}->{value}); |
| 2875 |
if ($token->{attributes}->{'http-equiv'}) { |
} elsif ($token->{attributes}->{content}) { |
| 2876 |
## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition. |
## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition. |
| 2877 |
if ($token->{attributes}->{'http-equiv'}->{value} |
if ($token->{attributes}->{content}->{value} |
| 2878 |
=~ /\A[^;]*;[\x09-\x0D\x20]*charset[\x09-\x0D\x20]*= |
=~ /\A[^;]*;[\x09-\x0D\x20]*charset[\x09-\x0D\x20]*= |
| 2879 |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
| 2880 |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
| 2881 |
$charset = defined $1 ? $1 : defined $2 ? $2 : $3; |
$self->{change_encoding} |
| 2882 |
} ## TODO: And if supported |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3); |
| 2883 |
|
} |
| 2884 |
} |
} |
|
## TODO: Change the encoding |
|
| 2885 |
} |
} |
| 2886 |
|
|
|
## TODO: Extracting |charset| from |meta|. |
|
| 2887 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} |
| 2888 |
if $self->{insertion_mode} eq 'after head'; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 2889 |
!!!next-token; |
!!!next-token; |
| 2890 |
redo B; |
redo B; |
| 2891 |
} elsif ($token->{tag_name} eq 'title' and |
} elsif ($token->{tag_name} eq 'title') { |
| 2892 |
$self->{insertion_mode} eq 'in head') { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2893 |
## NOTE: There is a "as if in head" code clone. |
## As if </noscript> |
| 2894 |
if ($self->{insertion_mode} eq 'after head') { |
pop @{$self->{open_elements}}; |
| 2895 |
|
!!!parse-error (type => 'in noscript:title'); |
| 2896 |
|
|
| 2897 |
|
$self->{insertion_mode} = IN_HEAD_IM; |
| 2898 |
|
## Reprocess in the "in head" insertion mode... |
| 2899 |
|
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2900 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 2901 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 2902 |
} |
} |
| 2903 |
|
|
| 2904 |
|
## NOTE: There is a "as if in head" code clone. |
| 2905 |
my $parent = defined $self->{head_element} ? $self->{head_element} |
my $parent = defined $self->{head_element} ? $self->{head_element} |
| 2906 |
: $self->{open_elements}->[-1]->[0]; |
: $self->{open_elements}->[-1]->[0]; |
| 2907 |
$parse_rcdata->(RCDATA_CONTENT_MODEL, |
$parse_rcdata->(RCDATA_CONTENT_MODEL, |
| 2908 |
sub { $parent->append_child ($_[0]) }); |
sub { $parent->append_child ($_[0]) }); |
| 2909 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} |
| 2910 |
if $self->{insertion_mode} eq 'after head'; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 2911 |
redo B; |
redo B; |
| 2912 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($token->{tag_name} eq 'style') { |
| 2913 |
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
| 2914 |
## insertion mode 'in head') |
## insertion mode IN_HEAD_IM) |
| 2915 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 2916 |
if ($self->{insertion_mode} eq 'after head') { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2917 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 2918 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 2919 |
} |
} |
| 2920 |
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert_to_current); |
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert_to_current); |
| 2921 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} |
| 2922 |
if $self->{insertion_mode} eq 'after head'; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 2923 |
redo B; |
redo B; |
| 2924 |
} elsif ($token->{tag_name} eq 'noscript') { |
} elsif ($token->{tag_name} eq 'noscript') { |
| 2925 |
if ($self->{insertion_mode} eq 'in head') { |
if ($self->{insertion_mode} == IN_HEAD_IM) { |
| 2926 |
## NOTE: and scripting is disalbed |
## NOTE: and scripting is disalbed |
| 2927 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 2928 |
$self->{insertion_mode} = 'in head noscript'; |
$self->{insertion_mode} = IN_HEAD_NOSCRIPT_IM; |
| 2929 |
!!!next-token; |
!!!next-token; |
| 2930 |
redo B; |
redo B; |
| 2931 |
} elsif ($self->{insertion_mode} eq 'in head noscript') { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2932 |
!!!parse-error (type => 'in noscript:noscript'); |
!!!parse-error (type => 'in noscript:noscript'); |
| 2933 |
## Ignore the token |
## Ignore the token |
| 2934 |
|
!!!next-token; |
| 2935 |
redo B; |
redo B; |
| 2936 |
} else { |
} else { |
| 2937 |
# |
# |
| 2938 |
} |
} |
| 2939 |
} elsif ($token->{tag_name} eq 'head' and |
} elsif ($token->{tag_name} eq 'script') { |
| 2940 |
$self->{insertion_mode} ne 'after head') { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2941 |
!!!parse-error (type => 'in head:head'); # or in head noscript |
## As if </noscript> |
| 2942 |
## Ignore the token |
pop @{$self->{open_elements}}; |
| 2943 |
!!!next-token; |
!!!parse-error (type => 'in noscript:script'); |
| 2944 |
redo B; |
|
| 2945 |
} elsif ($self->{insertion_mode} ne 'in head noscript' and |
$self->{insertion_mode} = IN_HEAD_IM; |
| 2946 |
$token->{tag_name} eq 'script') { |
## Reprocess in the "in head" insertion mode... |
| 2947 |
if ($self->{insertion_mode} eq 'after head') { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2948 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 2949 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 2950 |
} |
} |
| 2951 |
|
|
| 2952 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 2953 |
$script_start_tag->($insert_to_current); |
$script_start_tag->($insert_to_current); |
| 2954 |
pop @{$self->{open_elements}} |
pop @{$self->{open_elements}} |
| 2955 |
if $self->{insertion_mode} eq 'after head'; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 2956 |
redo B; |
redo B; |
| 2957 |
} elsif ($self->{insertion_mode} eq 'after head' and |
} elsif ($token->{tag_name} eq 'body' or |
|
$token->{tag_name} eq 'body') { |
|
|
!!!insert-element ('body', $token->{attributes}); |
|
|
$self->{insertion_mode} = 'in body'; |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($self->{insertion_mode} eq 'after head' and |
|
| 2958 |
$token->{tag_name} eq 'frameset') { |
$token->{tag_name} eq 'frameset') { |
| 2959 |
!!!insert-element ('frameset', $token->{attributes}); |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2960 |
$self->{insertion_mode} = 'in frameset'; |
## As if </noscript> |
| 2961 |
|
pop @{$self->{open_elements}}; |
| 2962 |
|
!!!parse-error (type => 'in noscript:'.$token->{tag_name}); |
| 2963 |
|
|
| 2964 |
|
## Reprocess in the "in head" insertion mode... |
| 2965 |
|
## As if </head> |
| 2966 |
|
pop @{$self->{open_elements}}; |
| 2967 |
|
|
| 2968 |
|
## Reprocess in the "after head" insertion mode... |
| 2969 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 2970 |
|
pop @{$self->{open_elements}}; |
| 2971 |
|
|
| 2972 |
|
## Reprocess in the "after head" insertion mode... |
| 2973 |
|
} |
| 2974 |
|
|
| 2975 |
|
## "after head" insertion mode |
| 2976 |
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 2977 |
|
if ($token->{tag_name} eq 'body') { |
| 2978 |
|
$self->{insertion_mode} = IN_BODY_IM; |
| 2979 |
|
} elsif ($token->{tag_name} eq 'frameset') { |
| 2980 |
|
$self->{insertion_mode} = IN_FRAMESET_IM; |
| 2981 |
|
} else { |
| 2982 |
|
die "$0: tag name: $self->{tag_name}"; |
| 2983 |
|
} |
| 2984 |
!!!next-token; |
!!!next-token; |
| 2985 |
redo B; |
redo B; |
| 2986 |
} else { |
} else { |
| 2987 |
# |
# |
| 2988 |
} |
} |
| 2989 |
} elsif ($token->{type} eq 'end tag') { |
|
| 2990 |
if ($self->{insertion_mode} eq 'in head' and |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2991 |
$token->{tag_name} eq 'head') { |
## As if </noscript> |
| 2992 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2993 |
$self->{insertion_mode} = 'after head'; |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}); |
| 2994 |
!!!next-token; |
|
| 2995 |
redo B; |
## Reprocess in the "in head" insertion mode... |
| 2996 |
} elsif ($self->{insertion_mode} eq 'in head noscript' and |
## As if </head> |
|
$token->{tag_name} eq 'noscript') { |
|
| 2997 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
|
$self->{insertion_mode} = 'in head'; |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($self->{insertion_mode} eq 'in head' and |
|
|
{ |
|
|
body => 1, html => 1, |
|
|
p => 1, br => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
# |
|
|
} elsif ($self->{insertion_mode} eq 'in head noscript' and |
|
|
{ |
|
|
p => 1, br => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
# |
|
|
} elsif ($self->{insertion_mode} ne 'after head') { |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} else { |
|
|
# |
|
|
} |
|
|
} else { |
|
|
# |
|
|
} |
|
| 2998 |
|
|
| 2999 |
## As if </head> or </noscript> or <body> |
## Reprocess in the "after head" insertion mode... |
| 3000 |
if ($self->{insertion_mode} eq 'in head') { |
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 3001 |
pop @{$self->{open_elements}}; |
## As if </head> |
| 3002 |
$self->{insertion_mode} = 'after head'; |
pop @{$self->{open_elements}}; |
|
} elsif ($self->{insertion_mode} eq 'in head noscript') { |
|
|
pop @{$self->{open_elements}}; |
|
|
!!!parse-error (type => 'in noscript:'.(defined $token->{tag_name} ? ($token->{type} eq 'end tag' ? '/' : '') . $token->{tag_name} : '#' . $token->{type})); |
|
|
$self->{insertion_mode} = 'in head'; |
|
|
} else { # 'after head' |
|
|
!!!insert-element ('body'); |
|
|
$self->{insertion_mode} = 'in body'; |
|
|
} |
|
|
## reprocess |
|
|
redo B; |
|
| 3003 |
|
|
| 3004 |
## ISSUE: An issue in the spec. |
## Reprocess in the "after head" insertion mode... |
| 3005 |
} elsif ($self->{insertion_mode} eq 'in body') { |
} |
|
if ($token->{type} eq 'character') { |
|
|
## NOTE: There is a code clone of "character in body". |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
|
| 3006 |
|
|
| 3007 |
!!!next-token; |
## "after head" insertion mode |
| 3008 |
redo B; |
## As if <body> |
| 3009 |
} else { |
!!!insert-element ('body'); |
| 3010 |
$in_body->($insert_to_current); |
$self->{insertion_mode} = IN_BODY_IM; |
| 3011 |
|
## reprocess |
| 3012 |
redo B; |
redo B; |
| 3013 |
} |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 3014 |
} elsif ($self->{insertion_mode} eq 'in table') { |
if ($token->{tag_name} eq 'head') { |
| 3015 |
if ($token->{type} eq 'character') { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3016 |
## NOTE: There are "character in table" code clones. |
## As if <head> |
| 3017 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
!!!create-element ($self->{head_element}, 'head'); |
| 3018 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 3019 |
|
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3020 |
unless (length $token->{data}) { |
|
| 3021 |
|
## Reprocess in the "in head" insertion mode... |
| 3022 |
|
pop @{$self->{open_elements}}; |
| 3023 |
|
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 3024 |
|
!!!next-token; |
| 3025 |
|
redo B; |
| 3026 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 3027 |
|
## As if </noscript> |
| 3028 |
|
pop @{$self->{open_elements}}; |
| 3029 |
|
!!!parse-error (type => 'in noscript:script'); |
| 3030 |
|
|
| 3031 |
|
## Reprocess in the "in head" insertion mode... |
| 3032 |
|
pop @{$self->{open_elements}}; |
| 3033 |
|
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 3034 |
|
!!!next-token; |
| 3035 |
|
redo B; |
| 3036 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 3037 |
|
pop @{$self->{open_elements}}; |
| 3038 |
|
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 3039 |
!!!next-token; |
!!!next-token; |
| 3040 |
redo B; |
redo B; |
|
} |
|
|
} |
|
|
|
|
|
!!!parse-error (type => 'in table:#character'); |
|
|
|
|
|
## As if in body, but insert into foster parent element |
|
|
## ISSUE: Spec says that "whenever a node would be inserted |
|
|
## into the current node" while characters might not be |
|
|
## result in a new Text node. |
|
|
$reconstruct_active_formatting_elements->($insert_to_foster); |
|
|
|
|
|
if ({ |
|
|
table => 1, tbody => 1, tfoot => 1, |
|
|
thead => 1, tr => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
# MUST |
|
|
my $foster_parent_element; |
|
|
my $next_sibling; |
|
|
my $prev_sibling; |
|
|
OE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
if ($self->{open_elements}->[$_]->[1] eq 'table') { |
|
|
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
|
|
if (defined $parent and $parent->node_type == 1) { |
|
|
$foster_parent_element = $parent; |
|
|
$next_sibling = $self->{open_elements}->[$_]->[0]; |
|
|
$prev_sibling = $next_sibling->previous_sibling; |
|
|
} else { |
|
|
$foster_parent_element = $self->{open_elements}->[$_ - 1]->[0]; |
|
|
$prev_sibling = $foster_parent_element->last_child; |
|
|
} |
|
|
last OE; |
|
|
} |
|
|
} # OE |
|
|
$foster_parent_element = $self->{open_elements}->[0]->[0] and |
|
|
$prev_sibling = $foster_parent_element->last_child |
|
|
unless defined $foster_parent_element; |
|
|
if (defined $prev_sibling and |
|
|
$prev_sibling->node_type == 3) { |
|
|
$prev_sibling->manakai_append_text ($token->{data}); |
|
| 3041 |
} else { |
} else { |
| 3042 |
$foster_parent_element->insert_before |
# |
|
($self->{document}->create_text_node ($token->{data}), |
|
|
$next_sibling); |
|
| 3043 |
} |
} |
| 3044 |
} else { |
} elsif ($token->{tag_name} eq 'noscript') { |
| 3045 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
|
} |
|
|
|
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{type} eq 'start tag') { |
|
|
if ({ |
|
|
caption => 1, |
|
|
colgroup => 1, |
|
|
tbody => 1, tfoot => 1, thead => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
## Clear back to table context |
|
|
while ($self->{open_elements}->[-1]->[1] ne 'table' and |
|
|
$self->{open_elements}->[-1]->[1] ne 'html') { |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 3046 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3047 |
|
$self->{insertion_mode} = IN_HEAD_IM; |
| 3048 |
|
!!!next-token; |
| 3049 |
|
redo B; |
| 3050 |
|
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3051 |
|
!!!parse-error (type => 'unmatched end tag:noscript'); |
| 3052 |
|
## Ignore the token ## ISSUE: An issue in the spec. |
| 3053 |
|
!!!next-token; |
| 3054 |
|
redo B; |
| 3055 |
|
} else { |
| 3056 |
|
# |
| 3057 |
} |
} |
|
|
|
|
push @$active_formatting_elements, ['#marker', ''] |
|
|
if $token->{tag_name} eq 'caption'; |
|
|
|
|
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
|
|
$self->{insertion_mode} = { |
|
|
caption => 'in caption', |
|
|
colgroup => 'in column group', |
|
|
tbody => 'in table body', |
|
|
tfoot => 'in table body', |
|
|
thead => 'in table body', |
|
|
}->{$token->{tag_name}}; |
|
|
!!!next-token; |
|
|
redo B; |
|
| 3058 |
} elsif ({ |
} elsif ({ |
| 3059 |
col => 1, |
body => 1, html => 1, |
|
td => 1, th => 1, tr => 1, |
|
| 3060 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 3061 |
## Clear back to table context |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3062 |
while ($self->{open_elements}->[-1]->[1] ne 'table' and |
## As if <head> |
| 3063 |
$self->{open_elements}->[-1]->[1] ne 'html') { |
!!!create-element ($self->{head_element}, 'head'); |
| 3064 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 3065 |
pop @{$self->{open_elements}}; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
|
} |
|
|
|
|
|
!!!insert-element ($token->{tag_name} eq 'col' ? 'colgroup' : 'tbody'); |
|
|
$self->{insertion_mode} = $token->{tag_name} eq 'col' |
|
|
? 'in column group' : 'in table body'; |
|
|
## reprocess |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'table') { |
|
|
## NOTE: There are code clones for this "table in table" |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 3066 |
|
|
| 3067 |
## As if </table> |
$self->{insertion_mode} = IN_HEAD_IM; |
| 3068 |
## have a table element in table scope |
## Reprocess in the "in head" insertion mode... |
| 3069 |
my $i; |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 3070 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3071 |
my $node = $self->{open_elements}->[$_]; |
## Ignore the token |
|
if ($node->[1] eq 'table') { |
|
|
$i = $_; |
|
|
last INSCOPE; |
|
|
} elsif ({ |
|
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
unless (defined $i) { |
|
|
!!!parse-error (type => 'unmatched end tag:table'); |
|
|
## Ignore tokens </table><table> |
|
| 3072 |
!!!next-token; |
!!!next-token; |
| 3073 |
redo B; |
redo B; |
| 3074 |
} |
} |
| 3075 |
|
|
| 3076 |
## generate implied end tags |
# |
| 3077 |
if ({ |
} elsif ({ |
| 3078 |
dd => 1, dt => 1, li => 1, p => 1, |
p => 1, br => 1, |
| 3079 |
td => 1, th => 1, tr => 1, |
}->{$token->{tag_name}}) { |
| 3080 |
tbody => 1, tfoot=> 1, thead => 1, |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 3081 |
}->{$self->{open_elements}->[-1]->[1]}) { |
## As if <head> |
| 3082 |
!!!back-token; # <table> |
!!!create-element ($self->{head_element}, 'head'); |
| 3083 |
$token = {type => 'end tag', tag_name => 'table'}; |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 3084 |
!!!back-token; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
|
$token = {type => 'end tag', |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
|
} |
|
| 3085 |
|
|
| 3086 |
if ($self->{open_elements}->[-1]->[1] ne 'table') { |
$self->{insertion_mode} = IN_HEAD_IM; |
| 3087 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
## Reprocess in the "in head" insertion mode... |
| 3088 |
} |
} |
| 3089 |
|
|
|
splice @{$self->{open_elements}}, $i; |
|
|
|
|
|
$self->_reset_insertion_mode; |
|
|
|
|
|
## reprocess |
|
|
redo B; |
|
|
} else { |
|
| 3090 |
# |
# |
| 3091 |
} |
} else { |
| 3092 |
} elsif ($token->{type} eq 'end tag') { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 3093 |
if ($token->{tag_name} eq 'table') { |
# |
| 3094 |
## have a table element in table scope |
} else { |
|
my $i; |
|
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
my $node = $self->{open_elements}->[$_]; |
|
|
if ($node->[1] eq $token->{tag_name}) { |
|
|
$i = $_; |
|
|
last INSCOPE; |
|
|
} elsif ({ |
|
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
unless (defined $i) { |
|
| 3095 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3096 |
## Ignore the token |
## Ignore the token |
| 3097 |
!!!next-token; |
!!!next-token; |
| 3098 |
redo B; |
redo B; |
| 3099 |
} |
} |
| 3100 |
|
} |
|
## generate implied end tags |
|
|
if ({ |
|
|
dd => 1, dt => 1, li => 1, p => 1, |
|
|
td => 1, th => 1, tr => 1, |
|
|
tbody => 1, tfoot=> 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
|
} |
|
|
|
|
|
if ($self->{open_elements}->[-1]->[1] ne 'table') { |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
|
} |
|
| 3101 |
|
|
| 3102 |
splice @{$self->{open_elements}}, $i; |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 3103 |
|
## As if </noscript> |
| 3104 |
|
pop @{$self->{open_elements}}; |
| 3105 |
|
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}); |
| 3106 |
|
|
| 3107 |
|
## Reprocess in the "in head" insertion mode... |
| 3108 |
|
## As if </head> |
| 3109 |
|
pop @{$self->{open_elements}}; |
| 3110 |
|
|
| 3111 |
$self->_reset_insertion_mode; |
## Reprocess in the "after head" insertion mode... |
| 3112 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 3113 |
|
## As if </head> |
| 3114 |
|
pop @{$self->{open_elements}}; |
| 3115 |
|
|
| 3116 |
!!!next-token; |
## Reprocess in the "after head" insertion mode... |
| 3117 |
redo B; |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
|
} elsif ({ |
|
|
body => 1, caption => 1, col => 1, colgroup => 1, |
|
|
html => 1, tbody => 1, td => 1, tfoot => 1, th => 1, |
|
|
thead => 1, tr => 1, |
|
|
}->{$token->{tag_name}}) { |
|
| 3118 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3119 |
## Ignore the token |
## Ignore the token ## ISSUE: An issue in the spec. |
| 3120 |
!!!next-token; |
!!!next-token; |
| 3121 |
redo B; |
redo B; |
|
} else { |
|
|
# |
|
| 3122 |
} |
} |
| 3123 |
|
|
| 3124 |
|
## "after head" insertion mode |
| 3125 |
|
## As if <body> |
| 3126 |
|
!!!insert-element ('body'); |
| 3127 |
|
$self->{insertion_mode} = IN_BODY_IM; |
| 3128 |
|
## reprocess |
| 3129 |
|
redo B; |
| 3130 |
} else { |
} else { |
| 3131 |
# |
die "$0: $token->{type}: Unknown token type"; |
| 3132 |
} |
} |
| 3133 |
|
|
| 3134 |
!!!parse-error (type => 'in table:'.$token->{tag_name}); |
## ISSUE: An issue in the spec. |
| 3135 |
$in_body->($insert_to_foster); |
} elsif ($self->{insertion_mode} & BODY_IMS) { |
| 3136 |
redo B; |
if ($token->{type} == CHARACTER_TOKEN) { |
| 3137 |
} elsif ($self->{insertion_mode} eq 'in caption') { |
## NOTE: There is a code clone of "character in body". |
|
if ($token->{type} eq 'character') { |
|
|
## NOTE: This is a code clone of "character in body". |
|
| 3138 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 3139 |
|
|
| 3140 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
| 3141 |
|
|
| 3142 |
!!!next-token; |
!!!next-token; |
| 3143 |
redo B; |
redo B; |
| 3144 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 3145 |
if ({ |
if ({ |
| 3146 |
caption => 1, col => 1, colgroup => 1, tbody => 1, |
caption => 1, col => 1, colgroup => 1, tbody => 1, |
| 3147 |
td => 1, tfoot => 1, th => 1, thead => 1, tr => 1, |
td => 1, tfoot => 1, th => 1, thead => 1, tr => 1, |
| 3148 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 3149 |
!!!parse-error (type => 'not closed:caption'); |
if ($self->{insertion_mode} == IN_CELL_IM) { |
| 3150 |
|
## have an element in table scope |
| 3151 |
|
my $tn; |
| 3152 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3153 |
|
my $node = $self->{open_elements}->[$_]; |
| 3154 |
|
if ($node->[1] eq 'td' or $node->[1] eq 'th') { |
| 3155 |
|
$tn = $node->[1]; |
| 3156 |
|
last INSCOPE; |
| 3157 |
|
} elsif ({ |
| 3158 |
|
table => 1, html => 1, |
| 3159 |
|
}->{$node->[1]}) { |
| 3160 |
|
last INSCOPE; |
| 3161 |
|
} |
| 3162 |
|
} # INSCOPE |
| 3163 |
|
unless (defined $tn) { |
| 3164 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3165 |
|
## Ignore the token |
| 3166 |
|
!!!next-token; |
| 3167 |
|
redo B; |
| 3168 |
|
} |
| 3169 |
|
|
| 3170 |
|
## Close the cell |
| 3171 |
|
!!!back-token; # <?> |
| 3172 |
|
$token = {type => END_TAG_TOKEN, tag_name => $tn}; |
| 3173 |
|
redo B; |
| 3174 |
|
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 3175 |
|
!!!parse-error (type => 'not closed:caption'); |
| 3176 |
|
|
| 3177 |
|
## As if </caption> |
| 3178 |
|
## have a table element in table scope |
| 3179 |
|
my $i; |
| 3180 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3181 |
|
my $node = $self->{open_elements}->[$_]; |
| 3182 |
|
if ($node->[1] eq 'caption') { |
| 3183 |
|
$i = $_; |
| 3184 |
|
last INSCOPE; |
| 3185 |
|
} elsif ({ |
| 3186 |
|
table => 1, html => 1, |
| 3187 |
|
}->{$node->[1]}) { |
| 3188 |
|
last INSCOPE; |
| 3189 |
|
} |
| 3190 |
|
} # INSCOPE |
| 3191 |
|
unless (defined $i) { |
| 3192 |
|
!!!parse-error (type => 'unmatched end tag:caption'); |
| 3193 |
|
## Ignore the token |
| 3194 |
|
!!!next-token; |
| 3195 |
|
redo B; |
| 3196 |
|
} |
| 3197 |
|
|
| 3198 |
|
## generate implied end tags |
| 3199 |
|
if ({ |
| 3200 |
|
dd => 1, dt => 1, li => 1, p => 1, |
| 3201 |
|
td => 1, th => 1, tr => 1, |
| 3202 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3203 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3204 |
|
!!!back-token; # <?> |
| 3205 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'caption'}; |
| 3206 |
|
!!!back-token; |
| 3207 |
|
$token = {type => END_TAG_TOKEN, |
| 3208 |
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3209 |
|
redo B; |
| 3210 |
|
} |
| 3211 |
|
|
| 3212 |
## As if </caption> |
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
| 3213 |
## have a table element in table scope |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
my $i; |
|
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
my $node = $self->{open_elements}->[$_]; |
|
|
if ($node->[1] eq 'caption') { |
|
|
$i = $_; |
|
|
last INSCOPE; |
|
|
} elsif ({ |
|
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
|
last INSCOPE; |
|
| 3214 |
} |
} |
| 3215 |
} # INSCOPE |
|
| 3216 |
unless (defined $i) { |
splice @{$self->{open_elements}}, $i; |
| 3217 |
!!!parse-error (type => 'unmatched end tag:caption'); |
|
| 3218 |
|
$clear_up_to_marker->(); |
| 3219 |
|
|
| 3220 |
|
$self->{insertion_mode} = IN_TABLE_IM; |
| 3221 |
|
|
| 3222 |
|
## reprocess |
| 3223 |
|
redo B; |
| 3224 |
|
} else { |
| 3225 |
|
# |
| 3226 |
|
} |
| 3227 |
|
} else { |
| 3228 |
|
# |
| 3229 |
|
} |
| 3230 |
|
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 3231 |
|
if ($token->{tag_name} eq 'td' or $token->{tag_name} eq 'th') { |
| 3232 |
|
if ($self->{insertion_mode} == IN_CELL_IM) { |
| 3233 |
|
## have an element in table scope |
| 3234 |
|
my $i; |
| 3235 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3236 |
|
my $node = $self->{open_elements}->[$_]; |
| 3237 |
|
if ($node->[1] eq $token->{tag_name}) { |
| 3238 |
|
$i = $_; |
| 3239 |
|
last INSCOPE; |
| 3240 |
|
} elsif ({ |
| 3241 |
|
table => 1, html => 1, |
| 3242 |
|
}->{$node->[1]}) { |
| 3243 |
|
last INSCOPE; |
| 3244 |
|
} |
| 3245 |
|
} # INSCOPE |
| 3246 |
|
unless (defined $i) { |
| 3247 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3248 |
|
## Ignore the token |
| 3249 |
|
!!!next-token; |
| 3250 |
|
redo B; |
| 3251 |
|
} |
| 3252 |
|
|
| 3253 |
|
## generate implied end tags |
| 3254 |
|
if ({ |
| 3255 |
|
dd => 1, dt => 1, li => 1, p => 1, |
| 3256 |
|
td => ($token->{tag_name} eq 'th'), |
| 3257 |
|
th => ($token->{tag_name} eq 'td'), |
| 3258 |
|
tr => 1, |
| 3259 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3260 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3261 |
|
!!!back-token; |
| 3262 |
|
$token = {type => END_TAG_TOKEN, |
| 3263 |
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3264 |
|
redo B; |
| 3265 |
|
} |
| 3266 |
|
|
| 3267 |
|
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
| 3268 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3269 |
|
} |
| 3270 |
|
|
| 3271 |
|
splice @{$self->{open_elements}}, $i; |
| 3272 |
|
|
| 3273 |
|
$clear_up_to_marker->(); |
| 3274 |
|
|
| 3275 |
|
$self->{insertion_mode} = IN_ROW_IM; |
| 3276 |
|
|
| 3277 |
|
!!!next-token; |
| 3278 |
|
redo B; |
| 3279 |
|
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 3280 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3281 |
## Ignore the token |
## Ignore the token |
| 3282 |
!!!next-token; |
!!!next-token; |
| 3283 |
redo B; |
redo B; |
| 3284 |
|
} else { |
| 3285 |
|
# |
| 3286 |
} |
} |
| 3287 |
|
} elsif ($token->{tag_name} eq 'caption') { |
| 3288 |
## generate implied end tags |
if ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 3289 |
if ({ |
## have a table element in table scope |
| 3290 |
dd => 1, dt => 1, li => 1, p => 1, |
my $i; |
| 3291 |
td => 1, th => 1, tr => 1, |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3292 |
tbody => 1, tfoot=> 1, thead => 1, |
my $node = $self->{open_elements}->[$_]; |
| 3293 |
}->{$self->{open_elements}->[-1]->[1]}) { |
if ($node->[1] eq $token->{tag_name}) { |
| 3294 |
!!!back-token; # <?> |
$i = $_; |
| 3295 |
$token = {type => 'end tag', tag_name => 'caption'}; |
last INSCOPE; |
| 3296 |
!!!back-token; |
} elsif ({ |
| 3297 |
$token = {type => 'end tag', |
table => 1, html => 1, |
| 3298 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
}->{$node->[1]}) { |
| 3299 |
|
last INSCOPE; |
| 3300 |
|
} |
| 3301 |
|
} # INSCOPE |
| 3302 |
|
unless (defined $i) { |
| 3303 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3304 |
|
## Ignore the token |
| 3305 |
|
!!!next-token; |
| 3306 |
|
redo B; |
| 3307 |
|
} |
| 3308 |
|
|
| 3309 |
|
## generate implied end tags |
| 3310 |
|
if ({ |
| 3311 |
|
dd => 1, dt => 1, li => 1, p => 1, |
| 3312 |
|
td => 1, th => 1, tr => 1, |
| 3313 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3314 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3315 |
|
!!!back-token; |
| 3316 |
|
$token = {type => END_TAG_TOKEN, |
| 3317 |
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3318 |
|
redo B; |
| 3319 |
|
} |
| 3320 |
|
|
| 3321 |
|
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
| 3322 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3323 |
|
} |
| 3324 |
|
|
| 3325 |
|
splice @{$self->{open_elements}}, $i; |
| 3326 |
|
|
| 3327 |
|
$clear_up_to_marker->(); |
| 3328 |
|
|
| 3329 |
|
$self->{insertion_mode} = IN_TABLE_IM; |
| 3330 |
|
|
| 3331 |
|
!!!next-token; |
| 3332 |
redo B; |
redo B; |
| 3333 |
|
} elsif ($self->{insertion_mode} == IN_CELL_IM) { |
| 3334 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3335 |
|
## Ignore the token |
| 3336 |
|
!!!next-token; |
| 3337 |
|
redo B; |
| 3338 |
|
} else { |
| 3339 |
|
# |
| 3340 |
} |
} |
| 3341 |
|
} elsif ({ |
| 3342 |
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
table => 1, tbody => 1, tfoot => 1, |
| 3343 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
thead => 1, tr => 1, |
| 3344 |
} |
}->{$token->{tag_name}} and |
| 3345 |
|
$self->{insertion_mode} == IN_CELL_IM) { |
| 3346 |
splice @{$self->{open_elements}}, $i; |
## have an element in table scope |
|
|
|
|
$clear_up_to_marker->(); |
|
|
|
|
|
$self->{insertion_mode} = 'in table'; |
|
|
|
|
|
## reprocess |
|
|
redo B; |
|
|
} else { |
|
|
# |
|
|
} |
|
|
} elsif ($token->{type} eq 'end tag') { |
|
|
if ($token->{tag_name} eq 'caption') { |
|
|
## have a table element in table scope |
|
| 3347 |
my $i; |
my $i; |
| 3348 |
|
my $tn; |
| 3349 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3350 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 3351 |
if ($node->[1] eq $token->{tag_name}) { |
if ($node->[1] eq $token->{tag_name}) { |
| 3352 |
$i = $_; |
$i = $_; |
| 3353 |
last INSCOPE; |
last INSCOPE; |
| 3354 |
|
} elsif ($node->[1] eq 'td' or $node->[1] eq 'th') { |
| 3355 |
|
$tn = $node->[1]; |
| 3356 |
|
## NOTE: There is exactly one |td| or |th| element |
| 3357 |
|
## in scope in the stack of open elements by definition. |
| 3358 |
} elsif ({ |
} elsif ({ |
| 3359 |
table => 1, html => 1, |
table => 1, html => 1, |
| 3360 |
}->{$node->[1]}) { |
}->{$node->[1]}) { |
| 3367 |
!!!next-token; |
!!!next-token; |
| 3368 |
redo B; |
redo B; |
| 3369 |
} |
} |
|
|
|
|
## generate implied end tags |
|
|
if ({ |
|
|
dd => 1, dt => 1, li => 1, p => 1, |
|
|
td => 1, th => 1, tr => 1, |
|
|
tbody => 1, tfoot=> 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
|
} |
|
|
|
|
|
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
|
} |
|
|
|
|
|
splice @{$self->{open_elements}}, $i; |
|
|
|
|
|
$clear_up_to_marker->(); |
|
| 3370 |
|
|
| 3371 |
$self->{insertion_mode} = 'in table'; |
## Close the cell |
| 3372 |
|
!!!back-token; # </?> |
| 3373 |
!!!next-token; |
$token = {type => END_TAG_TOKEN, tag_name => $tn}; |
| 3374 |
redo B; |
redo B; |
| 3375 |
} elsif ($token->{tag_name} eq 'table') { |
} elsif ($token->{tag_name} eq 'table' and |
| 3376 |
|
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 3377 |
!!!parse-error (type => 'not closed:caption'); |
!!!parse-error (type => 'not closed:caption'); |
| 3378 |
|
|
| 3379 |
## As if </caption> |
## As if </caption> |
| 3404 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 3405 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3406 |
!!!back-token; # </table> |
!!!back-token; # </table> |
| 3407 |
$token = {type => 'end tag', tag_name => 'caption'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'caption'}; |
| 3408 |
!!!back-token; |
!!!back-token; |
| 3409 |
$token = {type => 'end tag', |
$token = {type => END_TAG_TOKEN, |
| 3410 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3411 |
redo B; |
redo B; |
| 3412 |
} |
} |
| 3419 |
|
|
| 3420 |
$clear_up_to_marker->(); |
$clear_up_to_marker->(); |
| 3421 |
|
|
| 3422 |
$self->{insertion_mode} = 'in table'; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 3423 |
|
|
| 3424 |
## reprocess |
## reprocess |
| 3425 |
redo B; |
redo B; |
| 3426 |
} elsif ({ |
} elsif ({ |
| 3427 |
body => 1, col => 1, colgroup => 1, |
body => 1, col => 1, colgroup => 1, html => 1, |
|
html => 1, tbody => 1, td => 1, tfoot => 1, |
|
|
th => 1, thead => 1, tr => 1, |
|
| 3428 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 3429 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
if ($self->{insertion_mode} & BODY_TABLE_IMS) { |
| 3430 |
## Ignore the token |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
redo B; |
|
|
} else { |
|
|
# |
|
|
} |
|
|
} else { |
|
|
# |
|
|
} |
|
|
|
|
|
$in_body->($insert_to_current); |
|
|
redo B; |
|
|
} elsif ($self->{insertion_mode} eq 'in column group') { |
|
|
if ($token->{type} eq 'character') { |
|
|
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
|
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
|
|
unless (length $token->{data}) { |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
|
} |
|
|
|
|
|
# |
|
|
} elsif ($token->{type} eq 'start tag') { |
|
|
if ($token->{tag_name} eq 'col') { |
|
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
|
|
pop @{$self->{open_elements}}; |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} else { |
|
|
# |
|
|
} |
|
|
} elsif ($token->{type} eq 'end tag') { |
|
|
if ($token->{tag_name} eq 'colgroup') { |
|
|
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
|
|
!!!parse-error (type => 'unmatched end tag:colgroup'); |
|
| 3431 |
## Ignore the token |
## Ignore the token |
| 3432 |
!!!next-token; |
!!!next-token; |
| 3433 |
redo B; |
redo B; |
| 3434 |
} else { |
} else { |
| 3435 |
pop @{$self->{open_elements}}; # colgroup |
# |
|
$self->{insertion_mode} = 'in table'; |
|
|
!!!next-token; |
|
|
redo B; |
|
| 3436 |
} |
} |
| 3437 |
} elsif ($token->{tag_name} eq 'col') { |
} elsif ({ |
| 3438 |
!!!parse-error (type => 'unmatched end tag:col'); |
tbody => 1, tfoot => 1, |
| 3439 |
|
thead => 1, tr => 1, |
| 3440 |
|
}->{$token->{tag_name}} and |
| 3441 |
|
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 3442 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3443 |
## Ignore the token |
## Ignore the token |
| 3444 |
!!!next-token; |
!!!next-token; |
| 3445 |
redo B; |
redo B; |
| 3446 |
} else { |
} else { |
| 3447 |
# |
# |
| 3448 |
} |
} |
| 3449 |
} else { |
} else { |
| 3450 |
# |
die "$0: $token->{type}: Unknown token type"; |
| 3451 |
} |
} |
| 3452 |
|
|
| 3453 |
## As if </colgroup> |
$insert = $insert_to_current; |
| 3454 |
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
# |
| 3455 |
!!!parse-error (type => 'unmatched end tag:colgroup'); |
} elsif ($self->{insertion_mode} & TABLE_IMS) { |
| 3456 |
## Ignore the token |
if ($token->{type} == CHARACTER_TOKEN) { |
|
!!!next-token; |
|
|
redo B; |
|
|
} else { |
|
|
pop @{$self->{open_elements}}; # colgroup |
|
|
$self->{insertion_mode} = 'in table'; |
|
|
## reprocess |
|
|
redo B; |
|
|
} |
|
|
} elsif ($self->{insertion_mode} eq 'in table body') { |
|
|
if ($token->{type} eq 'character') { |
|
|
## NOTE: This is a "character in table" code clone. |
|
| 3457 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 3458 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 3459 |
|
|
| 3470 |
## into the current node" while characters might not be |
## into the current node" while characters might not be |
| 3471 |
## result in a new Text node. |
## result in a new Text node. |
| 3472 |
$reconstruct_active_formatting_elements->($insert_to_foster); |
$reconstruct_active_formatting_elements->($insert_to_foster); |
| 3473 |
|
|
| 3474 |
if ({ |
if ({ |
| 3475 |
table => 1, tbody => 1, tfoot => 1, |
table => 1, tbody => 1, tfoot => 1, |
| 3476 |
thead => 1, tr => 1, |
thead => 1, tr => 1, |
| 3510 |
|
|
| 3511 |
!!!next-token; |
!!!next-token; |
| 3512 |
redo B; |
redo B; |
| 3513 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 3514 |
if ({ |
if ({ |
| 3515 |
tr => 1, |
tr => ($self->{insertion_mode} != IN_ROW_IM), |
| 3516 |
th => 1, td => 1, |
th => 1, td => 1, |
| 3517 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 3518 |
unless ($token->{tag_name} eq 'tr') { |
if ($self->{insertion_mode} == IN_TABLE_IM) { |
| 3519 |
!!!parse-error (type => 'missing start tag:tr'); |
## Clear back to table context |
| 3520 |
|
while ($self->{open_elements}->[-1]->[1] ne 'table' and |
| 3521 |
|
$self->{open_elements}->[-1]->[1] ne 'html') { |
| 3522 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3523 |
|
pop @{$self->{open_elements}}; |
| 3524 |
|
} |
| 3525 |
|
|
| 3526 |
|
!!!insert-element ('tbody'); |
| 3527 |
|
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 3528 |
|
## reprocess in the "in table body" insertion mode... |
| 3529 |
} |
} |
| 3530 |
|
|
| 3531 |
## Clear back to table body context |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
| 3532 |
|
unless ($token->{tag_name} eq 'tr') { |
| 3533 |
|
!!!parse-error (type => 'missing start tag:tr'); |
| 3534 |
|
} |
| 3535 |
|
|
| 3536 |
|
## Clear back to table body context |
| 3537 |
|
while (not { |
| 3538 |
|
tbody => 1, tfoot => 1, thead => 1, html => 1, |
| 3539 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3540 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3541 |
|
pop @{$self->{open_elements}}; |
| 3542 |
|
} |
| 3543 |
|
|
| 3544 |
|
$self->{insertion_mode} = IN_ROW_IM; |
| 3545 |
|
if ($token->{tag_name} eq 'tr') { |
| 3546 |
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 3547 |
|
!!!next-token; |
| 3548 |
|
redo B; |
| 3549 |
|
} else { |
| 3550 |
|
!!!insert-element ('tr'); |
| 3551 |
|
## reprocess in the "in row" insertion mode |
| 3552 |
|
} |
| 3553 |
|
} |
| 3554 |
|
|
| 3555 |
|
## Clear back to table row context |
| 3556 |
while (not { |
while (not { |
| 3557 |
tbody => 1, tfoot => 1, thead => 1, html => 1, |
tr => 1, html => 1, |
| 3558 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3559 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3560 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3561 |
} |
} |
| 3562 |
|
|
| 3563 |
$self->{insertion_mode} = 'in row'; |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 3564 |
if ($token->{tag_name} eq 'tr') { |
$self->{insertion_mode} = IN_CELL_IM; |
| 3565 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
|
| 3566 |
!!!next-token; |
push @$active_formatting_elements, ['#marker', '']; |
| 3567 |
} else { |
|
| 3568 |
!!!insert-element ('tr'); |
!!!next-token; |
|
## reprocess |
|
|
} |
|
| 3569 |
redo B; |
redo B; |
| 3570 |
} elsif ({ |
} elsif ({ |
| 3571 |
caption => 1, col => 1, colgroup => 1, |
caption => 1, col => 1, colgroup => 1, |
| 3572 |
tbody => 1, tfoot => 1, thead => 1, |
tbody => 1, tfoot => 1, thead => 1, |
| 3573 |
|
tr => 1, # $self->{insertion_mode} == IN_ROW_IM |
| 3574 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 3575 |
## have an element in table scope |
if ($self->{insertion_mode} == IN_ROW_IM) { |
| 3576 |
my $i; |
## As if </tr> |
| 3577 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
## have an element in table scope |
| 3578 |
my $node = $self->{open_elements}->[$_]; |
my $i; |
| 3579 |
if ({ |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3580 |
tbody => 1, thead => 1, tfoot => 1, |
my $node = $self->{open_elements}->[$_]; |
| 3581 |
}->{$node->[1]}) { |
if ($node->[1] eq 'tr') { |
| 3582 |
$i = $_; |
$i = $_; |
| 3583 |
last INSCOPE; |
last INSCOPE; |
| 3584 |
} elsif ({ |
} elsif ({ |
| 3585 |
table => 1, html => 1, |
table => 1, html => 1, |
| 3586 |
}->{$node->[1]}) { |
}->{$node->[1]}) { |
| 3587 |
last INSCOPE; |
last INSCOPE; |
| 3588 |
|
} |
| 3589 |
|
} # INSCOPE |
| 3590 |
|
unless (defined $i) { |
| 3591 |
|
!!!parse-error (type => 'unmacthed end tag:'.$token->{tag_name}); |
| 3592 |
|
## Ignore the token |
| 3593 |
|
!!!next-token; |
| 3594 |
|
redo B; |
| 3595 |
|
} |
| 3596 |
|
|
| 3597 |
|
## Clear back to table row context |
| 3598 |
|
while (not { |
| 3599 |
|
tr => 1, html => 1, |
| 3600 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3601 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3602 |
|
pop @{$self->{open_elements}}; |
| 3603 |
|
} |
| 3604 |
|
|
| 3605 |
|
pop @{$self->{open_elements}}; # tr |
| 3606 |
|
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 3607 |
|
if ($token->{tag_name} eq 'tr') { |
| 3608 |
|
## reprocess |
| 3609 |
|
redo B; |
| 3610 |
|
} else { |
| 3611 |
|
## reprocess in the "in table body" insertion mode... |
| 3612 |
} |
} |
|
} # INSCOPE |
|
|
unless (defined $i) { |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
| 3613 |
} |
} |
| 3614 |
|
|
| 3615 |
## Clear back to table body context |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
| 3616 |
while (not { |
## have an element in table scope |
| 3617 |
tbody => 1, tfoot => 1, thead => 1, html => 1, |
my $i; |
| 3618 |
}->{$self->{open_elements}->[-1]->[1]}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3619 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
my $node = $self->{open_elements}->[$_]; |
| 3620 |
|
if ({ |
| 3621 |
|
tbody => 1, thead => 1, tfoot => 1, |
| 3622 |
|
}->{$node->[1]}) { |
| 3623 |
|
$i = $_; |
| 3624 |
|
last INSCOPE; |
| 3625 |
|
} elsif ({ |
| 3626 |
|
table => 1, html => 1, |
| 3627 |
|
}->{$node->[1]}) { |
| 3628 |
|
last INSCOPE; |
| 3629 |
|
} |
| 3630 |
|
} # INSCOPE |
| 3631 |
|
unless (defined $i) { |
| 3632 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3633 |
|
## Ignore the token |
| 3634 |
|
!!!next-token; |
| 3635 |
|
redo B; |
| 3636 |
|
} |
| 3637 |
|
|
| 3638 |
|
## Clear back to table body context |
| 3639 |
|
while (not { |
| 3640 |
|
tbody => 1, tfoot => 1, thead => 1, html => 1, |
| 3641 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3642 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3643 |
|
pop @{$self->{open_elements}}; |
| 3644 |
|
} |
| 3645 |
|
|
| 3646 |
|
## As if <{current node}> |
| 3647 |
|
## have an element in table scope |
| 3648 |
|
## true by definition |
| 3649 |
|
|
| 3650 |
|
## Clear back to table body context |
| 3651 |
|
## nop by definition |
| 3652 |
|
|
| 3653 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3654 |
|
$self->{insertion_mode} = IN_TABLE_IM; |
| 3655 |
|
## reprocess in "in table" insertion mode... |
| 3656 |
} |
} |
| 3657 |
|
|
| 3658 |
## As if <{current node}> |
if ($token->{tag_name} eq 'col') { |
| 3659 |
## have an element in table scope |
## Clear back to table context |
| 3660 |
## true by definition |
while ($self->{open_elements}->[-1]->[1] ne 'table' and |
| 3661 |
|
$self->{open_elements}->[-1]->[1] ne 'html') { |
| 3662 |
## Clear back to table body context |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3663 |
## nop by definition |
pop @{$self->{open_elements}}; |
| 3664 |
|
} |
| 3665 |
pop @{$self->{open_elements}}; |
|
| 3666 |
$self->{insertion_mode} = 'in table'; |
!!!insert-element ('colgroup'); |
| 3667 |
## reprocess |
$self->{insertion_mode} = IN_COLUMN_GROUP_IM; |
| 3668 |
redo B; |
## reprocess |
| 3669 |
|
redo B; |
| 3670 |
|
} elsif ({ |
| 3671 |
|
caption => 1, |
| 3672 |
|
colgroup => 1, |
| 3673 |
|
tbody => 1, tfoot => 1, thead => 1, |
| 3674 |
|
}->{$token->{tag_name}}) { |
| 3675 |
|
## Clear back to table context |
| 3676 |
|
while ($self->{open_elements}->[-1]->[1] ne 'table' and |
| 3677 |
|
$self->{open_elements}->[-1]->[1] ne 'html') { |
| 3678 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3679 |
|
pop @{$self->{open_elements}}; |
| 3680 |
|
} |
| 3681 |
|
|
| 3682 |
|
push @$active_formatting_elements, ['#marker', ''] |
| 3683 |
|
if $token->{tag_name} eq 'caption'; |
| 3684 |
|
|
| 3685 |
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 3686 |
|
$self->{insertion_mode} = { |
| 3687 |
|
caption => IN_CAPTION_IM, |
| 3688 |
|
colgroup => IN_COLUMN_GROUP_IM, |
| 3689 |
|
tbody => IN_TABLE_BODY_IM, |
| 3690 |
|
tfoot => IN_TABLE_BODY_IM, |
| 3691 |
|
thead => IN_TABLE_BODY_IM, |
| 3692 |
|
}->{$token->{tag_name}}; |
| 3693 |
|
!!!next-token; |
| 3694 |
|
redo B; |
| 3695 |
|
} else { |
| 3696 |
|
die "$0: in table: <>: $token->{tag_name}"; |
| 3697 |
|
} |
| 3698 |
} elsif ($token->{tag_name} eq 'table') { |
} elsif ($token->{tag_name} eq 'table') { |
| 3699 |
## NOTE: This is a code clone of "table in table" |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
!!!parse-error (type => 'not closed:table'); |
|
| 3700 |
|
|
| 3701 |
## As if </table> |
## As if </table> |
| 3702 |
## have a table element in table scope |
## have a table element in table scope |
| 3726 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 3727 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3728 |
!!!back-token; # <table> |
!!!back-token; # <table> |
| 3729 |
$token = {type => 'end tag', tag_name => 'table'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'table'}; |
| 3730 |
!!!back-token; |
!!!back-token; |
| 3731 |
$token = {type => 'end tag', |
$token = {type => END_TAG_TOKEN, |
| 3732 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3733 |
redo B; |
redo B; |
| 3734 |
} |
} |
| 3739 |
|
|
| 3740 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 3741 |
|
|
| 3742 |
$self->_reset_insertion_mode; |
$self->_reset_insertion_mode; |
| 3743 |
|
|
| 3744 |
## reprocess |
## reprocess |
| 3745 |
redo B; |
redo B; |
| 3746 |
} else { |
} else { |
| 3747 |
# |
!!!parse-error (type => 'in table:'.$token->{tag_name}); |
| 3748 |
} |
|
| 3749 |
} elsif ($token->{type} eq 'end tag') { |
$insert = $insert_to_foster; |
| 3750 |
if ({ |
# |
| 3751 |
tbody => 1, tfoot => 1, thead => 1, |
} |
| 3752 |
}->{$token->{tag_name}}) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 3753 |
|
if ($token->{tag_name} eq 'tr' and |
| 3754 |
|
$self->{insertion_mode} == IN_ROW_IM) { |
| 3755 |
## have an element in table scope |
## have an element in table scope |
| 3756 |
my $i; |
my $i; |
| 3757 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3772 |
redo B; |
redo B; |
| 3773 |
} |
} |
| 3774 |
|
|
| 3775 |
## Clear back to table body context |
## Clear back to table row context |
| 3776 |
while (not { |
while (not { |
| 3777 |
tbody => 1, tfoot => 1, thead => 1, html => 1, |
tr => 1, html => 1, |
| 3778 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3779 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3780 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3781 |
} |
} |
| 3782 |
|
|
| 3783 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; # tr |
| 3784 |
$self->{insertion_mode} = 'in table'; |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 3785 |
!!!next-token; |
!!!next-token; |
| 3786 |
redo B; |
redo B; |
| 3787 |
} elsif ($token->{tag_name} eq 'table') { |
} elsif ($token->{tag_name} eq 'table') { |
| 3788 |
## have an element in table scope |
if ($self->{insertion_mode} == IN_ROW_IM) { |
| 3789 |
my $i; |
## As if </tr> |
| 3790 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
## have an element in table scope |
| 3791 |
my $node = $self->{open_elements}->[$_]; |
my $i; |
| 3792 |
if ({ |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3793 |
tbody => 1, thead => 1, tfoot => 1, |
my $node = $self->{open_elements}->[$_]; |
| 3794 |
}->{$node->[1]}) { |
if ($node->[1] eq 'tr') { |
| 3795 |
$i = $_; |
$i = $_; |
| 3796 |
last INSCOPE; |
last INSCOPE; |
| 3797 |
} elsif ({ |
} elsif ({ |
| 3798 |
table => 1, html => 1, |
table => 1, html => 1, |
| 3799 |
}->{$node->[1]}) { |
}->{$node->[1]}) { |
| 3800 |
last INSCOPE; |
last INSCOPE; |
| 3801 |
|
} |
| 3802 |
|
} # INSCOPE |
| 3803 |
|
unless (defined $i) { |
| 3804 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{type}); |
| 3805 |
|
## Ignore the token |
| 3806 |
|
!!!next-token; |
| 3807 |
|
redo B; |
| 3808 |
} |
} |
| 3809 |
} # INSCOPE |
|
| 3810 |
unless (defined $i) { |
## Clear back to table row context |
| 3811 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
while (not { |
| 3812 |
## Ignore the token |
tr => 1, html => 1, |
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
|
|
|
|
## Clear back to table body context |
|
|
while (not { |
|
|
tbody => 1, tfoot => 1, thead => 1, html => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
|
pop @{$self->{open_elements}}; |
|
|
} |
|
|
|
|
|
## As if <{current node}> |
|
|
## have an element in table scope |
|
|
## true by definition |
|
|
|
|
|
## Clear back to table body context |
|
|
## nop by definition |
|
|
|
|
|
pop @{$self->{open_elements}}; |
|
|
$self->{insertion_mode} = 'in table'; |
|
|
## reprocess |
|
|
redo B; |
|
|
} elsif ({ |
|
|
body => 1, caption => 1, col => 1, colgroup => 1, |
|
|
html => 1, td => 1, th => 1, tr => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} else { |
|
|
# |
|
|
} |
|
|
} else { |
|
|
# |
|
|
} |
|
|
|
|
|
## As if in table |
|
|
!!!parse-error (type => 'in table:'.$token->{tag_name}); |
|
|
$in_body->($insert_to_foster); |
|
|
redo B; |
|
|
} elsif ($self->{insertion_mode} eq 'in row') { |
|
|
if ($token->{type} eq 'character') { |
|
|
## NOTE: This is a "character in table" code clone. |
|
|
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
|
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
|
|
|
|
|
unless (length $token->{data}) { |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
|
} |
|
|
|
|
|
!!!parse-error (type => 'in table:#character'); |
|
|
|
|
|
## As if in body, but insert into foster parent element |
|
|
## ISSUE: Spec says that "whenever a node would be inserted |
|
|
## into the current node" while characters might not be |
|
|
## result in a new Text node. |
|
|
$reconstruct_active_formatting_elements->($insert_to_foster); |
|
|
|
|
|
if ({ |
|
|
table => 1, tbody => 1, tfoot => 1, |
|
|
thead => 1, tr => 1, |
|
| 3813 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3814 |
# MUST |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3815 |
my $foster_parent_element; |
pop @{$self->{open_elements}}; |
| 3816 |
my $next_sibling; |
} |
| 3817 |
my $prev_sibling; |
|
| 3818 |
OE: for (reverse 0..$#{$self->{open_elements}}) { |
pop @{$self->{open_elements}}; # tr |
| 3819 |
if ($self->{open_elements}->[$_]->[1] eq 'table') { |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 3820 |
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
## reprocess in the "in table body" insertion mode... |
| 3821 |
if (defined $parent and $parent->node_type == 1) { |
} |
| 3822 |
$foster_parent_element = $parent; |
|
| 3823 |
$next_sibling = $self->{open_elements}->[$_]->[0]; |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
| 3824 |
$prev_sibling = $next_sibling->previous_sibling; |
## have an element in table scope |
| 3825 |
} else { |
my $i; |
| 3826 |
$foster_parent_element = $self->{open_elements}->[$_ - 1]->[0]; |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3827 |
$prev_sibling = $foster_parent_element->last_child; |
my $node = $self->{open_elements}->[$_]; |
| 3828 |
|
if ({ |
| 3829 |
|
tbody => 1, thead => 1, tfoot => 1, |
| 3830 |
|
}->{$node->[1]}) { |
| 3831 |
|
$i = $_; |
| 3832 |
|
last INSCOPE; |
| 3833 |
|
} elsif ({ |
| 3834 |
|
table => 1, html => 1, |
| 3835 |
|
}->{$node->[1]}) { |
| 3836 |
|
last INSCOPE; |
| 3837 |
} |
} |
| 3838 |
last OE; |
} # INSCOPE |
| 3839 |
|
unless (defined $i) { |
| 3840 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3841 |
|
## Ignore the token |
| 3842 |
|
!!!next-token; |
| 3843 |
|
redo B; |
| 3844 |
} |
} |
| 3845 |
} # OE |
|
| 3846 |
$foster_parent_element = $self->{open_elements}->[0]->[0] and |
## Clear back to table body context |
| 3847 |
$prev_sibling = $foster_parent_element->last_child |
while (not { |
| 3848 |
unless defined $foster_parent_element; |
tbody => 1, tfoot => 1, thead => 1, html => 1, |
| 3849 |
if (defined $prev_sibling and |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3850 |
$prev_sibling->node_type == 3) { |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3851 |
$prev_sibling->manakai_append_text ($token->{data}); |
pop @{$self->{open_elements}}; |
|
} else { |
|
|
$foster_parent_element->insert_before |
|
|
($self->{document}->create_text_node ($token->{data}), |
|
|
$next_sibling); |
|
|
} |
|
|
} else { |
|
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
|
|
} |
|
|
|
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{type} eq 'start tag') { |
|
|
if ($token->{tag_name} eq 'th' or |
|
|
$token->{tag_name} eq 'td') { |
|
|
## Clear back to table row context |
|
|
while (not { |
|
|
tr => 1, html => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
|
pop @{$self->{open_elements}}; |
|
|
} |
|
|
|
|
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
|
|
$self->{insertion_mode} = 'in cell'; |
|
|
|
|
|
push @$active_formatting_elements, ['#marker', '']; |
|
|
|
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ({ |
|
|
caption => 1, col => 1, colgroup => 1, |
|
|
tbody => 1, tfoot => 1, thead => 1, tr => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
## As if </tr> |
|
|
## have an element in table scope |
|
|
my $i; |
|
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
my $node = $self->{open_elements}->[$_]; |
|
|
if ($node->[1] eq 'tr') { |
|
|
$i = $_; |
|
|
last INSCOPE; |
|
|
} elsif ({ |
|
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
|
last INSCOPE; |
|
| 3852 |
} |
} |
| 3853 |
} # INSCOPE |
|
| 3854 |
unless (defined $i) { |
## As if <{current node}> |
| 3855 |
!!!parse-error (type => 'unmacthed end tag:'.$token->{tag_name}); |
## have an element in table scope |
| 3856 |
## Ignore the token |
## true by definition |
| 3857 |
!!!next-token; |
|
| 3858 |
redo B; |
## Clear back to table body context |
| 3859 |
} |
## nop by definition |
| 3860 |
|
|
|
## Clear back to table row context |
|
|
while (not { |
|
|
tr => 1, html => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
| 3861 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3862 |
|
$self->{insertion_mode} = IN_TABLE_IM; |
| 3863 |
|
## reprocess in the "in table" insertion mode... |
| 3864 |
} |
} |
| 3865 |
|
|
|
pop @{$self->{open_elements}}; # tr |
|
|
$self->{insertion_mode} = 'in table body'; |
|
|
## reprocess |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'table') { |
|
|
## NOTE: This is a code clone of "table in table" |
|
|
!!!parse-error (type => 'not closed:table'); |
|
|
|
|
|
## As if </table> |
|
| 3866 |
## have a table element in table scope |
## have a table element in table scope |
| 3867 |
my $i; |
my $i; |
| 3868 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3869 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 3870 |
if ($node->[1] eq 'table') { |
if ($node->[1] eq $token->{tag_name}) { |
| 3871 |
$i = $_; |
$i = $_; |
| 3872 |
last INSCOPE; |
last INSCOPE; |
| 3873 |
} elsif ({ |
} elsif ({ |
| 3877 |
} |
} |
| 3878 |
} # INSCOPE |
} # INSCOPE |
| 3879 |
unless (defined $i) { |
unless (defined $i) { |
| 3880 |
!!!parse-error (type => 'unmatched end tag:table'); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3881 |
## Ignore tokens </table><table> |
## Ignore the token |
| 3882 |
!!!next-token; |
!!!next-token; |
| 3883 |
redo B; |
redo B; |
| 3884 |
} |
} |
| 3885 |
|
|
| 3886 |
## generate implied end tags |
## generate implied end tags |
| 3887 |
if ({ |
if ({ |
| 3888 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3889 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3890 |
tbody => 1, tfoot=> 1, thead => 1, |
tbody => 1, tfoot=> 1, thead => 1, |
| 3891 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
|
!!!back-token; # <table> |
|
|
$token = {type => 'end tag', tag_name => 'table'}; |
|
| 3892 |
!!!back-token; |
!!!back-token; |
| 3893 |
$token = {type => 'end tag', |
$token = {type => END_TAG_TOKEN, |
| 3894 |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3895 |
redo B; |
redo B; |
| 3896 |
} |
} |
| 3897 |
|
|
| 3898 |
if ($self->{open_elements}->[-1]->[1] ne 'table') { |
if ($self->{open_elements}->[-1]->[1] ne 'table') { |
| 3899 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3900 |
} |
} |
| 3901 |
|
|
| 3902 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 3903 |
|
|
| 3904 |
$self->_reset_insertion_mode; |
$self->_reset_insertion_mode; |
| 3905 |
|
|
|
## reprocess |
|
|
redo B; |
|
|
} else { |
|
|
# |
|
|
} |
|
|
} elsif ($token->{type} eq 'end tag') { |
|
|
if ($token->{tag_name} eq 'tr') { |
|
|
## have an element in table scope |
|
|
my $i; |
|
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
my $node = $self->{open_elements}->[$_]; |
|
|
if ($node->[1] eq $token->{tag_name}) { |
|
|
$i = $_; |
|
|
last INSCOPE; |
|
|
} elsif ({ |
|
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
unless (defined $i) { |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
|
|
|
|
## Clear back to table row context |
|
|
while (not { |
|
|
tr => 1, html => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
|
pop @{$self->{open_elements}}; |
|
|
} |
|
|
|
|
|
pop @{$self->{open_elements}}; # tr |
|
|
$self->{insertion_mode} = 'in table body'; |
|
| 3906 |
!!!next-token; |
!!!next-token; |
| 3907 |
redo B; |
redo B; |
|
} elsif ($token->{tag_name} eq 'table') { |
|
|
## As if </tr> |
|
|
## have an element in table scope |
|
|
my $i; |
|
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
my $node = $self->{open_elements}->[$_]; |
|
|
if ($node->[1] eq 'tr') { |
|
|
$i = $_; |
|
|
last INSCOPE; |
|
|
} elsif ({ |
|
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
unless (defined $i) { |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{type}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
|
|
|
|
## Clear back to table row context |
|
|
while (not { |
|
|
tr => 1, html => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
|
pop @{$self->{open_elements}}; |
|
|
} |
|
|
|
|
|
pop @{$self->{open_elements}}; # tr |
|
|
$self->{insertion_mode} = 'in table body'; |
|
|
## reprocess |
|
|
redo B; |
|
| 3908 |
} elsif ({ |
} elsif ({ |
| 3909 |
tbody => 1, tfoot => 1, thead => 1, |
tbody => 1, tfoot => 1, thead => 1, |
| 3910 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}} and |
| 3911 |
## have an element in table scope |
$self->{insertion_mode} & ROW_IMS) { |
| 3912 |
my $i; |
if ($self->{insertion_mode} == IN_ROW_IM) { |
| 3913 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
## have an element in table scope |
| 3914 |
my $node = $self->{open_elements}->[$_]; |
my $i; |
| 3915 |
if ($node->[1] eq $token->{tag_name}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3916 |
$i = $_; |
my $node = $self->{open_elements}->[$_]; |
| 3917 |
last INSCOPE; |
if ($node->[1] eq $token->{tag_name}) { |
| 3918 |
} elsif ({ |
$i = $_; |
| 3919 |
table => 1, html => 1, |
last INSCOPE; |
| 3920 |
}->{$node->[1]}) { |
} elsif ({ |
| 3921 |
last INSCOPE; |
table => 1, html => 1, |
| 3922 |
|
}->{$node->[1]}) { |
| 3923 |
|
last INSCOPE; |
| 3924 |
|
} |
| 3925 |
|
} # INSCOPE |
| 3926 |
|
unless (defined $i) { |
| 3927 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3928 |
|
## Ignore the token |
| 3929 |
|
!!!next-token; |
| 3930 |
|
redo B; |
| 3931 |
|
} |
| 3932 |
|
|
| 3933 |
|
## As if </tr> |
| 3934 |
|
## have an element in table scope |
| 3935 |
|
my $i; |
| 3936 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3937 |
|
my $node = $self->{open_elements}->[$_]; |
| 3938 |
|
if ($node->[1] eq 'tr') { |
| 3939 |
|
$i = $_; |
| 3940 |
|
last INSCOPE; |
| 3941 |
|
} elsif ({ |
| 3942 |
|
table => 1, html => 1, |
| 3943 |
|
}->{$node->[1]}) { |
| 3944 |
|
last INSCOPE; |
| 3945 |
|
} |
| 3946 |
|
} # INSCOPE |
| 3947 |
|
unless (defined $i) { |
| 3948 |
|
!!!parse-error (type => 'unmatched end tag:tr'); |
| 3949 |
|
## Ignore the token |
| 3950 |
|
!!!next-token; |
| 3951 |
|
redo B; |
| 3952 |
|
} |
| 3953 |
|
|
| 3954 |
|
## Clear back to table row context |
| 3955 |
|
while (not { |
| 3956 |
|
tr => 1, html => 1, |
| 3957 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3958 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3959 |
|
pop @{$self->{open_elements}}; |
| 3960 |
} |
} |
| 3961 |
} # INSCOPE |
|
| 3962 |
unless (defined $i) { |
pop @{$self->{open_elements}}; # tr |
| 3963 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 3964 |
## Ignore the token |
## reprocess in the "in table body" insertion mode... |
|
!!!next-token; |
|
|
redo B; |
|
| 3965 |
} |
} |
| 3966 |
|
|
|
## As if </tr> |
|
| 3967 |
## have an element in table scope |
## have an element in table scope |
| 3968 |
my $i; |
my $i; |
| 3969 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3970 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 3971 |
if ($node->[1] eq 'tr') { |
if ($node->[1] eq $token->{tag_name}) { |
| 3972 |
$i = $_; |
$i = $_; |
| 3973 |
last INSCOPE; |
last INSCOPE; |
| 3974 |
} elsif ({ |
} elsif ({ |
| 3978 |
} |
} |
| 3979 |
} # INSCOPE |
} # INSCOPE |
| 3980 |
unless (defined $i) { |
unless (defined $i) { |
| 3981 |
!!!parse-error (type => 'unmatched end tag:tr'); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3982 |
## Ignore the token |
## Ignore the token |
| 3983 |
!!!next-token; |
!!!next-token; |
| 3984 |
redo B; |
redo B; |
| 3985 |
} |
} |
| 3986 |
|
|
| 3987 |
## Clear back to table row context |
## Clear back to table body context |
| 3988 |
while (not { |
while (not { |
| 3989 |
tr => 1, html => 1, |
tbody => 1, tfoot => 1, thead => 1, html => 1, |
| 3990 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3991 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3992 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3993 |
} |
} |
| 3994 |
|
|
| 3995 |
pop @{$self->{open_elements}}; # tr |
pop @{$self->{open_elements}}; |
| 3996 |
$self->{insertion_mode} = 'in table body'; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 3997 |
## reprocess |
!!!next-token; |
| 3998 |
redo B; |
redo B; |
| 3999 |
} elsif ({ |
} elsif ({ |
| 4000 |
body => 1, caption => 1, col => 1, |
body => 1, caption => 1, col => 1, colgroup => 1, |
| 4001 |
colgroup => 1, html => 1, td => 1, th => 1, |
html => 1, td => 1, th => 1, |
| 4002 |
|
tr => 1, # $self->{insertion_mode} == IN_ROW_IM |
| 4003 |
|
tbody => 1, tfoot => 1, thead => 1, # $self->{insertion_mode} == IN_TABLE_IM |
| 4004 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 4005 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 4006 |
## Ignore the token |
## Ignore the token |
| 4007 |
!!!next-token; |
!!!next-token; |
| 4008 |
redo B; |
redo B; |
| 4009 |
} else { |
} else { |
| 4010 |
# |
!!!parse-error (type => 'in table:/'.$token->{tag_name}); |
|
} |
|
|
} else { |
|
|
# |
|
|
} |
|
|
|
|
|
## As if in table |
|
|
!!!parse-error (type => 'in table:'.$token->{tag_name}); |
|
|
$in_body->($insert_to_foster); |
|
|
redo B; |
|
|
} elsif ($self->{insertion_mode} eq 'in cell') { |
|
|
if ($token->{type} eq 'character') { |
|
|
## NOTE: This is a code clone of "character in body". |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
|
| 4011 |
|
|
| 4012 |
!!!next-token; |
$insert = $insert_to_foster; |
| 4013 |
redo B; |
# |
| 4014 |
} elsif ($token->{type} eq 'start tag') { |
} |
| 4015 |
if ({ |
} else { |
| 4016 |
caption => 1, col => 1, colgroup => 1, |
die "$0: $token->{type}: Unknown token type"; |
| 4017 |
tbody => 1, td => 1, tfoot => 1, th => 1, |
} |
| 4018 |
thead => 1, tr => 1, |
} elsif ($self->{insertion_mode} == IN_COLUMN_GROUP_IM) { |
| 4019 |
}->{$token->{tag_name}}) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 4020 |
## have an element in table scope |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 4021 |
my $tn; |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 4022 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
unless (length $token->{data}) { |
|
my $node = $self->{open_elements}->[$_]; |
|
|
if ($node->[1] eq 'td' or $node->[1] eq 'th') { |
|
|
$tn = $node->[1]; |
|
|
last INSCOPE; |
|
|
} elsif ({ |
|
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
unless (defined $tn) { |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
| 4023 |
!!!next-token; |
!!!next-token; |
| 4024 |
redo B; |
redo B; |
| 4025 |
} |
} |
| 4026 |
|
} |
| 4027 |
## Close the cell |
|
| 4028 |
!!!back-token; # <?> |
# |
| 4029 |
$token = {type => 'end tag', tag_name => $tn}; |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 4030 |
|
if ($token->{tag_name} eq 'col') { |
| 4031 |
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 4032 |
|
pop @{$self->{open_elements}}; |
| 4033 |
|
!!!next-token; |
| 4034 |
redo B; |
redo B; |
| 4035 |
} else { |
} else { |
| 4036 |
# |
# |
| 4037 |
} |
} |
| 4038 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 4039 |
if ($token->{tag_name} eq 'td' or $token->{tag_name} eq 'th') { |
if ($token->{tag_name} eq 'colgroup') { |
| 4040 |
## have an element in table scope |
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
| 4041 |
my $i; |
!!!parse-error (type => 'unmatched end tag:colgroup'); |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
my $node = $self->{open_elements}->[$_]; |
|
|
if ($node->[1] eq $token->{tag_name}) { |
|
|
$i = $_; |
|
|
last INSCOPE; |
|
|
} elsif ({ |
|
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
unless (defined $i) { |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
| 4042 |
## Ignore the token |
## Ignore the token |
| 4043 |
!!!next-token; |
!!!next-token; |
| 4044 |
redo B; |
redo B; |
| 4045 |
|
} else { |
| 4046 |
|
pop @{$self->{open_elements}}; # colgroup |
| 4047 |
|
$self->{insertion_mode} = IN_TABLE_IM; |
| 4048 |
|
!!!next-token; |
| 4049 |
|
redo B; |
| 4050 |
} |
} |
| 4051 |
|
} elsif ($token->{tag_name} eq 'col') { |
| 4052 |
## generate implied end tags |
!!!parse-error (type => 'unmatched end tag:col'); |
|
if ({ |
|
|
dd => 1, dt => 1, li => 1, p => 1, |
|
|
td => ($token->{tag_name} eq 'th'), |
|
|
th => ($token->{tag_name} eq 'td'), |
|
|
tr => 1, |
|
|
tbody => 1, tfoot=> 1, thead => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
|
} |
|
|
|
|
|
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
|
} |
|
|
|
|
|
splice @{$self->{open_elements}}, $i; |
|
|
|
|
|
$clear_up_to_marker->(); |
|
|
|
|
|
$self->{insertion_mode} = 'in row'; |
|
|
|
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ({ |
|
|
body => 1, caption => 1, col => 1, |
|
|
colgroup => 1, html => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
| 4053 |
## Ignore the token |
## Ignore the token |
| 4054 |
!!!next-token; |
!!!next-token; |
| 4055 |
redo B; |
redo B; |
|
} elsif ({ |
|
|
table => 1, tbody => 1, tfoot => 1, |
|
|
thead => 1, tr => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
## have an element in table scope |
|
|
my $i; |
|
|
my $tn; |
|
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
my $node = $self->{open_elements}->[$_]; |
|
|
if ($node->[1] eq $token->{tag_name}) { |
|
|
$i = $_; |
|
|
last INSCOPE; |
|
|
} elsif ($node->[1] eq 'td' or $node->[1] eq 'th') { |
|
|
$tn = $node->[1]; |
|
|
## NOTE: There is exactly one |td| or |th| element |
|
|
## in scope in the stack of open elements by definition. |
|
|
} elsif ({ |
|
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
unless (defined $i) { |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
|
|
|
|
## Close the cell |
|
|
!!!back-token; # </?> |
|
|
$token = {type => 'end tag', tag_name => $tn}; |
|
|
redo B; |
|
| 4056 |
} else { |
} else { |
| 4057 |
# |
# |
| 4058 |
} |
} |
| 4059 |
} else { |
} else { |
| 4060 |
# |
# |
| 4061 |
} |
} |
| 4062 |
|
|
| 4063 |
$in_body->($insert_to_current); |
## As if </colgroup> |
| 4064 |
redo B; |
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
| 4065 |
} elsif ($self->{insertion_mode} eq 'in select') { |
!!!parse-error (type => 'unmatched end tag:colgroup'); |
| 4066 |
if ($token->{type} eq 'character') { |
## Ignore the token |
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
|
| 4067 |
!!!next-token; |
!!!next-token; |
| 4068 |
redo B; |
redo B; |
| 4069 |
} elsif ($token->{type} eq 'start tag') { |
} else { |
| 4070 |
|
pop @{$self->{open_elements}}; # colgroup |
| 4071 |
|
$self->{insertion_mode} = IN_TABLE_IM; |
| 4072 |
|
## reprocess |
| 4073 |
|
redo B; |
| 4074 |
|
} |
| 4075 |
|
} elsif ($self->{insertion_mode} == IN_SELECT_IM) { |
| 4076 |
|
if ($token->{type} == CHARACTER_TOKEN) { |
| 4077 |
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
| 4078 |
|
!!!next-token; |
| 4079 |
|
redo B; |
| 4080 |
|
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 4081 |
if ($token->{tag_name} eq 'option') { |
if ($token->{tag_name} eq 'option') { |
| 4082 |
if ($self->{open_elements}->[-1]->[1] eq 'option') { |
if ($self->{open_elements}->[-1]->[1] eq 'option') { |
| 4083 |
## As if </option> |
## As if </option> |
| 4130 |
|
|
| 4131 |
!!!next-token; |
!!!next-token; |
| 4132 |
redo B; |
redo B; |
| 4133 |
} else { |
} else { |
| 4134 |
# |
!!!parse-error (type => 'in select:'.$token->{tag_name}); |
| 4135 |
} |
## Ignore the token |
| 4136 |
} elsif ($token->{type} eq 'end tag') { |
!!!next-token; |
| 4137 |
|
redo B; |
| 4138 |
|
} |
| 4139 |
|
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 4140 |
if ($token->{tag_name} eq 'optgroup') { |
if ($token->{tag_name} eq 'optgroup') { |
| 4141 |
if ($self->{open_elements}->[-1]->[1] eq 'option' and |
if ($self->{open_elements}->[-1]->[1] eq 'option' and |
| 4142 |
$self->{open_elements}->[-2]->[1] eq 'optgroup') { |
$self->{open_elements}->[-2]->[1] eq 'optgroup') { |
| 4238 |
|
|
| 4239 |
## reprocess |
## reprocess |
| 4240 |
redo B; |
redo B; |
| 4241 |
} else { |
} else { |
| 4242 |
# |
!!!parse-error (type => 'in select:/'.$token->{tag_name}); |
|
} |
|
|
} else { |
|
|
# |
|
|
} |
|
|
|
|
|
!!!parse-error (type => 'in select:'.$token->{tag_name}); |
|
| 4243 |
## Ignore the token |
## Ignore the token |
| 4244 |
!!!next-token; |
!!!next-token; |
| 4245 |
redo B; |
redo B; |
| 4246 |
} elsif ($self->{insertion_mode} eq 'after body') { |
} |
| 4247 |
if ($token->{type} eq 'character') { |
} else { |
| 4248 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
die "$0: $token->{type}: Unknown token type"; |
| 4249 |
my $data = $1; |
} |
| 4250 |
## As if in body |
} elsif ($self->{insertion_mode} & BODY_AFTER_IMS) { |
| 4251 |
$reconstruct_active_formatting_elements->($insert_to_current); |
if ($token->{type} == CHARACTER_TOKEN) { |
| 4252 |
|
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 4253 |
|
my $data = $1; |
| 4254 |
|
## As if in body |
| 4255 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4256 |
|
|
| 4257 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 4258 |
|
|
| 4259 |
|
unless (length $token->{data}) { |
| 4260 |
|
!!!next-token; |
| 4261 |
|
redo B; |
| 4262 |
|
} |
| 4263 |
|
} |
| 4264 |
|
|
| 4265 |
|
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 4266 |
|
!!!parse-error (type => 'after html:#character'); |
| 4267 |
|
|
| 4268 |
unless (length $token->{data}) { |
## Reprocess in the "main" phase, "after body" insertion mode... |
| 4269 |
!!!next-token; |
} |
| 4270 |
redo B; |
|
| 4271 |
} |
## "after body" insertion mode |
| 4272 |
} |
!!!parse-error (type => 'after body:#character'); |
| 4273 |
|
|
| 4274 |
# |
$self->{insertion_mode} = IN_BODY_IM; |
| 4275 |
!!!parse-error (type => 'after body:#character'); |
## reprocess |
| 4276 |
} elsif ($token->{type} eq 'start tag') { |
redo B; |
| 4277 |
!!!parse-error (type => 'after body:'.$token->{tag_name}); |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 4278 |
# |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 4279 |
} elsif ($token->{type} eq 'end tag') { |
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
| 4280 |
if ($token->{tag_name} eq 'html') { |
|
| 4281 |
if (defined $self->{inner_html_node}) { |
## Reprocess in the "main" phase, "after body" insertion mode... |
| 4282 |
!!!parse-error (type => 'unmatched end tag:html'); |
} |
| 4283 |
## Ignore the token |
|
| 4284 |
!!!next-token; |
## "after body" insertion mode |
| 4285 |
redo B; |
!!!parse-error (type => 'after body:'.$token->{tag_name}); |
| 4286 |
} else { |
|
| 4287 |
$previous_insertion_mode = $self->{insertion_mode}; |
$self->{insertion_mode} = IN_BODY_IM; |
| 4288 |
$self->{insertion_mode} = 'trailing end'; |
## reprocess |
| 4289 |
!!!next-token; |
redo B; |
| 4290 |
redo B; |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 4291 |
} |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 4292 |
} else { |
!!!parse-error (type => 'after html:/'.$token->{tag_name}); |
| 4293 |
!!!parse-error (type => 'after body:/'.$token->{tag_name}); |
|
| 4294 |
} |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 4295 |
|
## Reprocess in the "main" phase, "after body" insertion mode... |
| 4296 |
|
} |
| 4297 |
|
|
| 4298 |
|
## "after body" insertion mode |
| 4299 |
|
if ($token->{tag_name} eq 'html') { |
| 4300 |
|
if (defined $self->{inner_html_node}) { |
| 4301 |
|
!!!parse-error (type => 'unmatched end tag:html'); |
| 4302 |
|
## Ignore the token |
| 4303 |
|
!!!next-token; |
| 4304 |
|
redo B; |
| 4305 |
} else { |
} else { |
| 4306 |
die "$0: $token->{type}: Unknown token type"; |
$self->{insertion_mode} = AFTER_HTML_BODY_IM; |
| 4307 |
|
!!!next-token; |
| 4308 |
|
redo B; |
| 4309 |
} |
} |
| 4310 |
|
} else { |
| 4311 |
|
!!!parse-error (type => 'after body:/'.$token->{tag_name}); |
| 4312 |
|
|
| 4313 |
$self->{insertion_mode} = 'in body'; |
$self->{insertion_mode} = IN_BODY_IM; |
| 4314 |
## reprocess |
## reprocess |
| 4315 |
redo B; |
redo B; |
| 4316 |
} elsif ($self->{insertion_mode} eq 'in frameset') { |
} |
| 4317 |
if ($token->{type} eq 'character') { |
} else { |
| 4318 |
|
die "$0: $token->{type}: Unknown token type"; |
| 4319 |
|
} |
| 4320 |
|
} elsif ($self->{insertion_mode} & FRAME_IMS) { |
| 4321 |
|
if ($token->{type} == CHARACTER_TOKEN) { |
| 4322 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 4323 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 4324 |
|
|
| 4325 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 4326 |
!!!next-token; |
!!!next-token; |
| 4327 |
redo B; |
redo B; |
| 4328 |
} |
} |
| 4329 |
} |
} |
| 4330 |
|
|
| 4331 |
|
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
| 4332 |
|
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 4333 |
|
!!!parse-error (type => 'in frameset:#character'); |
| 4334 |
|
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 4335 |
|
!!!parse-error (type => 'after frameset:#character'); |
| 4336 |
|
} else { # "after html frameset" |
| 4337 |
|
!!!parse-error (type => 'after html:#character'); |
| 4338 |
|
|
| 4339 |
|
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 4340 |
|
## Reprocess in the "main" phase, "after frameset"... |
| 4341 |
|
!!!parse-error (type => 'after frameset:#character'); |
| 4342 |
|
} |
| 4343 |
|
|
| 4344 |
|
## Ignore the token. |
| 4345 |
|
if (length $token->{data}) { |
| 4346 |
|
## reprocess the rest of characters |
| 4347 |
|
} else { |
| 4348 |
|
!!!next-token; |
| 4349 |
|
} |
| 4350 |
|
redo B; |
| 4351 |
|
} |
| 4352 |
|
|
| 4353 |
|
die qq[$0: Character "$token->{data}"]; |
| 4354 |
|
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 4355 |
|
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 4356 |
|
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
| 4357 |
|
|
| 4358 |
!!!parse-error (type => 'in frameset:#character'); |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 4359 |
## Ignore the token |
## Process in the "main" phase, "after frameset" insertion mode... |
| 4360 |
!!!next-token; |
} |
| 4361 |
redo B; |
|
| 4362 |
} elsif ($token->{type} eq 'start tag') { |
if ($token->{tag_name} eq 'frameset' and |
| 4363 |
if ($token->{tag_name} eq 'frameset') { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 4364 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 4365 |
!!!next-token; |
!!!next-token; |
| 4366 |
redo B; |
redo B; |
| 4367 |
} elsif ($token->{tag_name} eq 'frame') { |
} elsif ($token->{tag_name} eq 'frame' and |
| 4368 |
|
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 4369 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 4370 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4371 |
!!!next-token; |
!!!next-token; |
| 4372 |
redo B; |
redo B; |
| 4373 |
} elsif ($token->{tag_name} eq 'noframes') { |
} elsif ($token->{tag_name} eq 'noframes') { |
| 4374 |
$in_body->($insert_to_current); |
## NOTE: As if in body. |
| 4375 |
|
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert_to_current); |
| 4376 |
redo B; |
redo B; |
| 4377 |
} else { |
} else { |
| 4378 |
!!!parse-error (type => 'in frameset:'.$token->{tag_name}); |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 4379 |
|
!!!parse-error (type => 'in frameset:'.$token->{tag_name}); |
| 4380 |
|
} else { |
| 4381 |
|
!!!parse-error (type => 'after frameset:'.$token->{tag_name}); |
| 4382 |
|
} |
| 4383 |
## Ignore the token |
## Ignore the token |
| 4384 |
!!!next-token; |
!!!next-token; |
| 4385 |
redo B; |
redo B; |
| 4386 |
} |
} |
| 4387 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 4388 |
if ($token->{tag_name} eq 'frameset') { |
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 4389 |
|
!!!parse-error (type => 'after html:/'.$token->{tag_name}); |
| 4390 |
|
|
| 4391 |
|
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 4392 |
|
## Process in the "main" phase, "after frameset" insertion mode... |
| 4393 |
|
} |
| 4394 |
|
|
| 4395 |
|
if ($token->{tag_name} eq 'frameset' and |
| 4396 |
|
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 4397 |
if ($self->{open_elements}->[-1]->[1] eq 'html' and |
if ($self->{open_elements}->[-1]->[1] eq 'html' and |
| 4398 |
@{$self->{open_elements}} == 1) { |
@{$self->{open_elements}} == 1) { |
| 4399 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 4406 |
|
|
| 4407 |
if (not defined $self->{inner_html_node} and |
if (not defined $self->{inner_html_node} and |
| 4408 |
$self->{open_elements}->[-1]->[1] ne 'frameset') { |
$self->{open_elements}->[-1]->[1] ne 'frameset') { |
| 4409 |
$self->{insertion_mode} = 'after frameset'; |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 4410 |
} |
} |
| 4411 |
redo B; |
redo B; |
| 4412 |
|
} elsif ($token->{tag_name} eq 'html' and |
| 4413 |
|
$self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 4414 |
|
$self->{insertion_mode} = AFTER_HTML_FRAMESET_IM; |
| 4415 |
|
!!!next-token; |
| 4416 |
|
redo B; |
| 4417 |
} else { |
} else { |
| 4418 |
!!!parse-error (type => 'in frameset:/'.$token->{tag_name}); |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 4419 |
|
!!!parse-error (type => 'in frameset:/'.$token->{tag_name}); |
| 4420 |
|
} else { |
| 4421 |
|
!!!parse-error (type => 'after frameset:/'.$token->{tag_name}); |
| 4422 |
|
} |
| 4423 |
## Ignore the token |
## Ignore the token |
| 4424 |
!!!next-token; |
!!!next-token; |
| 4425 |
redo B; |
redo B; |
| 4427 |
} else { |
} else { |
| 4428 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 4429 |
} |
} |
|
} elsif ($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); |
|
| 4430 |
|
|
| 4431 |
unless (length $token->{data}) { |
## ISSUE: An issue in spec here |
| 4432 |
!!!next-token; |
} else { |
| 4433 |
redo B; |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
| 4434 |
} |
} |
|
} |
|
| 4435 |
|
|
| 4436 |
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
## "in body" insertion mode |
| 4437 |
!!!parse-error (type => 'after frameset:#character'); |
if ($token->{type} == START_TAG_TOKEN) { |
| 4438 |
|
if ($token->{tag_name} eq 'script') { |
| 4439 |
|
## NOTE: This is an "as if in head" code clone |
| 4440 |
|
$script_start_tag->($insert); |
| 4441 |
|
redo B; |
| 4442 |
|
} elsif ($token->{tag_name} eq 'style') { |
| 4443 |
|
## NOTE: This is an "as if in head" code clone |
| 4444 |
|
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert); |
| 4445 |
|
redo B; |
| 4446 |
|
} elsif ({ |
| 4447 |
|
base => 1, link => 1, |
| 4448 |
|
}->{$token->{tag_name}}) { |
| 4449 |
|
## NOTE: This is an "as if in head" code clone, only "-t" differs |
| 4450 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4451 |
|
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 4452 |
|
!!!next-token; |
| 4453 |
|
redo B; |
| 4454 |
|
} elsif ($token->{tag_name} eq 'meta') { |
| 4455 |
|
## NOTE: This is an "as if in head" code clone, only "-t" differs |
| 4456 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4457 |
|
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 4458 |
|
|
| 4459 |
## Ignore the token. |
unless ($self->{confident}) { |
| 4460 |
if (length $token->{data}) { |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
| 4461 |
## reprocess the rest of characters |
$self->{change_encoding} |
| 4462 |
} else { |
->($self, $token->{attributes}->{charset}->{value}); |
| 4463 |
!!!next-token; |
} elsif ($token->{attributes}->{content}) { |
| 4464 |
} |
## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition. |
| 4465 |
redo B; |
if ($token->{attributes}->{content}->{value} |
| 4466 |
|
=~ /\A[^;]*;[\x09-\x0D\x20]*charset[\x09-\x0D\x20]*= |
| 4467 |
|
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
| 4468 |
|
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
| 4469 |
|
$self->{change_encoding} |
| 4470 |
|
->($self, defined $1 ? $1 : defined $2 ? $2 : $3); |
| 4471 |
} |
} |
| 4472 |
|
} |
| 4473 |
|
} |
| 4474 |
|
|
| 4475 |
die qq[$0: Character "$token->{data}"]; |
!!!next-token; |
| 4476 |
} elsif ($token->{type} eq 'start tag') { |
redo B; |
| 4477 |
if ($token->{tag_name} eq 'noframes') { |
} elsif ($token->{tag_name} eq 'title') { |
| 4478 |
$in_body->($insert_to_current); |
!!!parse-error (type => 'in body:title'); |
| 4479 |
redo B; |
## NOTE: This is an "as if in head" code clone |
| 4480 |
} else { |
$parse_rcdata->(RCDATA_CONTENT_MODEL, sub { |
| 4481 |
!!!parse-error (type => 'after frameset:'.$token->{tag_name}); |
if (defined $self->{head_element}) { |
| 4482 |
|
$self->{head_element}->append_child ($_[0]); |
| 4483 |
|
} else { |
| 4484 |
|
$insert->($_[0]); |
| 4485 |
|
} |
| 4486 |
|
}); |
| 4487 |
|
redo B; |
| 4488 |
|
} elsif ($token->{tag_name} eq 'body') { |
| 4489 |
|
!!!parse-error (type => 'in body:body'); |
| 4490 |
|
|
| 4491 |
|
if (@{$self->{open_elements}} == 1 or |
| 4492 |
|
$self->{open_elements}->[1]->[1] ne 'body') { |
| 4493 |
## Ignore the token |
## Ignore the token |
| 4494 |
|
} else { |
| 4495 |
|
my $body_el = $self->{open_elements}->[1]->[0]; |
| 4496 |
|
for my $attr_name (keys %{$token->{attributes}}) { |
| 4497 |
|
unless ($body_el->has_attribute_ns (undef, $attr_name)) { |
| 4498 |
|
$body_el->set_attribute_ns |
| 4499 |
|
(undef, [undef, $attr_name], |
| 4500 |
|
$token->{attributes}->{$attr_name}->{value}); |
| 4501 |
|
} |
| 4502 |
|
} |
| 4503 |
|
} |
| 4504 |
|
!!!next-token; |
| 4505 |
|
redo B; |
| 4506 |
|
} elsif ({ |
| 4507 |
|
address => 1, blockquote => 1, center => 1, dir => 1, |
| 4508 |
|
div => 1, dl => 1, fieldset => 1, listing => 1, |
| 4509 |
|
menu => 1, ol => 1, p => 1, ul => 1, |
| 4510 |
|
pre => 1, |
| 4511 |
|
}->{$token->{tag_name}}) { |
| 4512 |
|
## has a p element in scope |
| 4513 |
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4514 |
|
if ($_->[1] eq 'p') { |
| 4515 |
|
!!!back-token; |
| 4516 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4517 |
|
redo B; |
| 4518 |
|
} elsif ({ |
| 4519 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4520 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4521 |
|
}->{$_->[1]}) { |
| 4522 |
|
last INSCOPE; |
| 4523 |
|
} |
| 4524 |
|
} # INSCOPE |
| 4525 |
|
|
| 4526 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4527 |
|
if ($token->{tag_name} eq 'pre') { |
| 4528 |
|
!!!next-token; |
| 4529 |
|
if ($token->{type} == CHARACTER_TOKEN) { |
| 4530 |
|
$token->{data} =~ s/^\x0A//; |
| 4531 |
|
unless (length $token->{data}) { |
| 4532 |
|
!!!next-token; |
| 4533 |
|
} |
| 4534 |
|
} |
| 4535 |
|
} else { |
| 4536 |
!!!next-token; |
!!!next-token; |
|
redo B; |
|
| 4537 |
} |
} |
| 4538 |
} elsif ($token->{type} eq 'end tag') { |
redo B; |
| 4539 |
if ($token->{tag_name} eq 'html') { |
} elsif ($token->{tag_name} eq 'form') { |
| 4540 |
$previous_insertion_mode = $self->{insertion_mode}; |
if (defined $self->{form_element}) { |
| 4541 |
$self->{insertion_mode} = 'trailing end'; |
!!!parse-error (type => 'in form:form'); |
| 4542 |
|
## Ignore the token |
| 4543 |
!!!next-token; |
!!!next-token; |
| 4544 |
redo B; |
redo B; |
| 4545 |
} else { |
} else { |
| 4546 |
!!!parse-error (type => 'after frameset:/'.$token->{tag_name}); |
## has a p element in scope |
| 4547 |
## Ignore the token |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4548 |
|
if ($_->[1] eq 'p') { |
| 4549 |
|
!!!back-token; |
| 4550 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4551 |
|
redo B; |
| 4552 |
|
} elsif ({ |
| 4553 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4554 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4555 |
|
}->{$_->[1]}) { |
| 4556 |
|
last INSCOPE; |
| 4557 |
|
} |
| 4558 |
|
} # INSCOPE |
| 4559 |
|
|
| 4560 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4561 |
|
$self->{form_element} = $self->{open_elements}->[-1]->[0]; |
| 4562 |
!!!next-token; |
!!!next-token; |
| 4563 |
redo B; |
redo B; |
| 4564 |
} |
} |
| 4565 |
} else { |
} elsif ($token->{tag_name} eq 'li') { |
| 4566 |
die "$0: $token->{type}: Unknown token type"; |
## has a p element in scope |
| 4567 |
} |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4568 |
|
if ($_->[1] eq 'p') { |
| 4569 |
|
!!!back-token; |
| 4570 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4571 |
|
redo B; |
| 4572 |
|
} elsif ({ |
| 4573 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4574 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4575 |
|
}->{$_->[1]}) { |
| 4576 |
|
last INSCOPE; |
| 4577 |
|
} |
| 4578 |
|
} # INSCOPE |
| 4579 |
|
|
| 4580 |
|
## Step 1 |
| 4581 |
|
my $i = -1; |
| 4582 |
|
my $node = $self->{open_elements}->[$i]; |
| 4583 |
|
LI: { |
| 4584 |
|
## Step 2 |
| 4585 |
|
if ($node->[1] eq 'li') { |
| 4586 |
|
if ($i != -1) { |
| 4587 |
|
!!!parse-error (type => 'end tag missing:'. |
| 4588 |
|
$self->{open_elements}->[-1]->[1]); |
| 4589 |
|
} |
| 4590 |
|
splice @{$self->{open_elements}}, $i; |
| 4591 |
|
last LI; |
| 4592 |
|
} |
| 4593 |
|
|
| 4594 |
|
## Step 3 |
| 4595 |
|
if (not $formatting_category->{$node->[1]} and |
| 4596 |
|
#not $phrasing_category->{$node->[1]} and |
| 4597 |
|
($special_category->{$node->[1]} or |
| 4598 |
|
$scoping_category->{$node->[1]}) and |
| 4599 |
|
$node->[1] ne 'address' and $node->[1] ne 'div') { |
| 4600 |
|
last LI; |
| 4601 |
|
} |
| 4602 |
|
|
| 4603 |
|
## Step 4 |
| 4604 |
|
$i--; |
| 4605 |
|
$node = $self->{open_elements}->[$i]; |
| 4606 |
|
redo LI; |
| 4607 |
|
} # LI |
| 4608 |
|
|
| 4609 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4610 |
|
!!!next-token; |
| 4611 |
|
redo B; |
| 4612 |
|
} elsif ($token->{tag_name} eq 'dd' or $token->{tag_name} eq 'dt') { |
| 4613 |
|
## has a p element in scope |
| 4614 |
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4615 |
|
if ($_->[1] eq 'p') { |
| 4616 |
|
!!!back-token; |
| 4617 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4618 |
|
redo B; |
| 4619 |
|
} elsif ({ |
| 4620 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4621 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4622 |
|
}->{$_->[1]}) { |
| 4623 |
|
last INSCOPE; |
| 4624 |
|
} |
| 4625 |
|
} # INSCOPE |
| 4626 |
|
|
| 4627 |
|
## Step 1 |
| 4628 |
|
my $i = -1; |
| 4629 |
|
my $node = $self->{open_elements}->[$i]; |
| 4630 |
|
LI: { |
| 4631 |
|
## Step 2 |
| 4632 |
|
if ($node->[1] eq 'dt' or $node->[1] eq 'dd') { |
| 4633 |
|
if ($i != -1) { |
| 4634 |
|
!!!parse-error (type => 'end tag missing:'. |
| 4635 |
|
$self->{open_elements}->[-1]->[1]); |
| 4636 |
|
} |
| 4637 |
|
splice @{$self->{open_elements}}, $i; |
| 4638 |
|
last LI; |
| 4639 |
|
} |
| 4640 |
|
|
| 4641 |
|
## Step 3 |
| 4642 |
|
if (not $formatting_category->{$node->[1]} and |
| 4643 |
|
#not $phrasing_category->{$node->[1]} and |
| 4644 |
|
($special_category->{$node->[1]} or |
| 4645 |
|
$scoping_category->{$node->[1]}) and |
| 4646 |
|
$node->[1] ne 'address' and $node->[1] ne 'div') { |
| 4647 |
|
last LI; |
| 4648 |
|
} |
| 4649 |
|
|
| 4650 |
|
## Step 4 |
| 4651 |
|
$i--; |
| 4652 |
|
$node = $self->{open_elements}->[$i]; |
| 4653 |
|
redo LI; |
| 4654 |
|
} # LI |
| 4655 |
|
|
| 4656 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4657 |
|
!!!next-token; |
| 4658 |
|
redo B; |
| 4659 |
|
} elsif ($token->{tag_name} eq 'plaintext') { |
| 4660 |
|
## has a p element in scope |
| 4661 |
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4662 |
|
if ($_->[1] eq 'p') { |
| 4663 |
|
!!!back-token; |
| 4664 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4665 |
|
redo B; |
| 4666 |
|
} elsif ({ |
| 4667 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4668 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4669 |
|
}->{$_->[1]}) { |
| 4670 |
|
last INSCOPE; |
| 4671 |
|
} |
| 4672 |
|
} # INSCOPE |
| 4673 |
|
|
| 4674 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4675 |
|
|
| 4676 |
|
$self->{content_model} = PLAINTEXT_CONTENT_MODEL; |
| 4677 |
|
|
| 4678 |
|
!!!next-token; |
| 4679 |
|
redo B; |
| 4680 |
|
} elsif ({ |
| 4681 |
|
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
| 4682 |
|
}->{$token->{tag_name}}) { |
| 4683 |
|
## has a p element in scope |
| 4684 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4685 |
|
my $node = $self->{open_elements}->[$_]; |
| 4686 |
|
if ($node->[1] eq 'p') { |
| 4687 |
|
!!!back-token; |
| 4688 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4689 |
|
redo B; |
| 4690 |
|
} elsif ({ |
| 4691 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4692 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4693 |
|
}->{$node->[1]}) { |
| 4694 |
|
last INSCOPE; |
| 4695 |
|
} |
| 4696 |
|
} # INSCOPE |
| 4697 |
|
|
| 4698 |
|
## NOTE: See <http://html5.org/tools/web-apps-tracker?from=925&to=926> |
| 4699 |
|
## has an element in scope |
| 4700 |
|
#my $i; |
| 4701 |
|
#INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4702 |
|
# my $node = $self->{open_elements}->[$_]; |
| 4703 |
|
# if ({ |
| 4704 |
|
# h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
| 4705 |
|
# }->{$node->[1]}) { |
| 4706 |
|
# $i = $_; |
| 4707 |
|
# last INSCOPE; |
| 4708 |
|
# } elsif ({ |
| 4709 |
|
# table => 1, caption => 1, td => 1, th => 1, |
| 4710 |
|
# button => 1, marquee => 1, object => 1, html => 1, |
| 4711 |
|
# }->{$node->[1]}) { |
| 4712 |
|
# last INSCOPE; |
| 4713 |
|
# } |
| 4714 |
|
#} # INSCOPE |
| 4715 |
|
# |
| 4716 |
|
#if (defined $i) { |
| 4717 |
|
# !!! parse-error (type => 'in hn:hn'); |
| 4718 |
|
# splice @{$self->{open_elements}}, $i; |
| 4719 |
|
#} |
| 4720 |
|
|
| 4721 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4722 |
|
|
| 4723 |
|
!!!next-token; |
| 4724 |
|
redo B; |
| 4725 |
|
} elsif ($token->{tag_name} eq 'a') { |
| 4726 |
|
AFE: for my $i (reverse 0..$#$active_formatting_elements) { |
| 4727 |
|
my $node = $active_formatting_elements->[$i]; |
| 4728 |
|
if ($node->[1] eq 'a') { |
| 4729 |
|
!!!parse-error (type => 'in a:a'); |
| 4730 |
|
|
| 4731 |
|
!!!back-token; |
| 4732 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'a'}; |
| 4733 |
|
$formatting_end_tag->($token->{tag_name}); |
| 4734 |
|
|
| 4735 |
|
AFE2: for (reverse 0..$#$active_formatting_elements) { |
| 4736 |
|
if ($active_formatting_elements->[$_]->[0] eq $node->[0]) { |
| 4737 |
|
splice @$active_formatting_elements, $_, 1; |
| 4738 |
|
last AFE2; |
| 4739 |
|
} |
| 4740 |
|
} # AFE2 |
| 4741 |
|
OE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4742 |
|
if ($self->{open_elements}->[$_]->[0] eq $node->[0]) { |
| 4743 |
|
splice @{$self->{open_elements}}, $_, 1; |
| 4744 |
|
last OE; |
| 4745 |
|
} |
| 4746 |
|
} # OE |
| 4747 |
|
last AFE; |
| 4748 |
|
} elsif ($node->[0] eq '#marker') { |
| 4749 |
|
last AFE; |
| 4750 |
|
} |
| 4751 |
|
} # AFE |
| 4752 |
|
|
| 4753 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4754 |
|
|
| 4755 |
## ISSUE: An issue in spec here |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4756 |
} elsif ($self->{insertion_mode} eq 'trailing end') { |
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
| 4757 |
## states in the main stage is preserved yet # MUST |
|
| 4758 |
|
!!!next-token; |
| 4759 |
if ($token->{type} eq 'character') { |
redo B; |
| 4760 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
} elsif ({ |
| 4761 |
my $data = $1; |
b => 1, big => 1, em => 1, font => 1, i => 1, |
| 4762 |
## As if in the main phase. |
s => 1, small => 1, strile => 1, |
| 4763 |
## NOTE: The insertion mode in the main phase |
strong => 1, tt => 1, u => 1, |
| 4764 |
## just before the phase has been changed to the trailing |
}->{$token->{tag_name}}) { |
| 4765 |
## end phase is either "after body" or "after frameset". |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4766 |
$reconstruct_active_formatting_elements->($insert_to_current); |
|
| 4767 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4768 |
|
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
| 4769 |
|
|
| 4770 |
|
!!!next-token; |
| 4771 |
|
redo B; |
| 4772 |
|
} elsif ($token->{tag_name} eq 'nobr') { |
| 4773 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4774 |
|
|
| 4775 |
|
## has a |nobr| element in scope |
| 4776 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4777 |
|
my $node = $self->{open_elements}->[$_]; |
| 4778 |
|
if ($node->[1] eq 'nobr') { |
| 4779 |
|
!!!parse-error (type => 'in nobr:nobr'); |
| 4780 |
|
!!!back-token; |
| 4781 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'nobr'}; |
| 4782 |
|
redo B; |
| 4783 |
|
} elsif ({ |
| 4784 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4785 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4786 |
|
}->{$node->[1]}) { |
| 4787 |
|
last INSCOPE; |
| 4788 |
|
} |
| 4789 |
|
} # INSCOPE |
| 4790 |
|
|
| 4791 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4792 |
|
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
| 4793 |
|
|
| 4794 |
|
!!!next-token; |
| 4795 |
|
redo B; |
| 4796 |
|
} elsif ($token->{tag_name} eq 'button') { |
| 4797 |
|
## has a button element in scope |
| 4798 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4799 |
|
my $node = $self->{open_elements}->[$_]; |
| 4800 |
|
if ($node->[1] eq 'button') { |
| 4801 |
|
!!!parse-error (type => 'in button:button'); |
| 4802 |
|
!!!back-token; |
| 4803 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'button'}; |
| 4804 |
|
redo B; |
| 4805 |
|
} elsif ({ |
| 4806 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4807 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4808 |
|
}->{$node->[1]}) { |
| 4809 |
|
last INSCOPE; |
| 4810 |
|
} |
| 4811 |
|
} # INSCOPE |
| 4812 |
|
|
| 4813 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4814 |
|
|
| 4815 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4816 |
|
push @$active_formatting_elements, ['#marker', '']; |
| 4817 |
|
|
| 4818 |
|
!!!next-token; |
| 4819 |
|
redo B; |
| 4820 |
|
} elsif ($token->{tag_name} eq 'marquee' or |
| 4821 |
|
$token->{tag_name} eq 'object') { |
| 4822 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4823 |
|
|
| 4824 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4825 |
|
push @$active_formatting_elements, ['#marker', '']; |
| 4826 |
|
|
| 4827 |
|
!!!next-token; |
| 4828 |
|
redo B; |
| 4829 |
|
} elsif ($token->{tag_name} eq 'xmp') { |
| 4830 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4831 |
|
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert); |
| 4832 |
|
redo B; |
| 4833 |
|
} elsif ($token->{tag_name} eq 'table') { |
| 4834 |
|
## has a p element in scope |
| 4835 |
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4836 |
|
if ($_->[1] eq 'p') { |
| 4837 |
|
!!!back-token; |
| 4838 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4839 |
|
redo B; |
| 4840 |
|
} elsif ({ |
| 4841 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4842 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4843 |
|
}->{$_->[1]}) { |
| 4844 |
|
last INSCOPE; |
| 4845 |
|
} |
| 4846 |
|
} # INSCOPE |
| 4847 |
|
|
| 4848 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4849 |
|
|
| 4850 |
|
$self->{insertion_mode} = IN_TABLE_IM; |
| 4851 |
|
|
| 4852 |
|
!!!next-token; |
| 4853 |
|
redo B; |
| 4854 |
|
} elsif ({ |
| 4855 |
|
area => 1, basefont => 1, bgsound => 1, br => 1, |
| 4856 |
|
embed => 1, img => 1, param => 1, spacer => 1, wbr => 1, |
| 4857 |
|
image => 1, |
| 4858 |
|
}->{$token->{tag_name}}) { |
| 4859 |
|
if ($token->{tag_name} eq 'image') { |
| 4860 |
|
!!!parse-error (type => 'image'); |
| 4861 |
|
$token->{tag_name} = 'img'; |
| 4862 |
|
} |
| 4863 |
|
|
| 4864 |
|
## NOTE: There is an "as if <br>" code clone. |
| 4865 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4866 |
|
|
| 4867 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4868 |
|
pop @{$self->{open_elements}}; |
| 4869 |
|
|
| 4870 |
|
!!!next-token; |
| 4871 |
|
redo B; |
| 4872 |
|
} elsif ($token->{tag_name} eq 'hr') { |
| 4873 |
|
## has a p element in scope |
| 4874 |
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4875 |
|
if ($_->[1] eq 'p') { |
| 4876 |
|
!!!back-token; |
| 4877 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
| 4878 |
|
redo B; |
| 4879 |
|
} elsif ({ |
| 4880 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 4881 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 4882 |
|
}->{$_->[1]}) { |
| 4883 |
|
last INSCOPE; |
| 4884 |
|
} |
| 4885 |
|
} # INSCOPE |
| 4886 |
|
|
| 4887 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($data); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4888 |
|
pop @{$self->{open_elements}}; |
| 4889 |
|
|
| 4890 |
|
!!!next-token; |
| 4891 |
|
redo B; |
| 4892 |
|
} elsif ($token->{tag_name} eq 'input') { |
| 4893 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4894 |
|
|
| 4895 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4896 |
|
## TODO: associate with $self->{form_element} if defined |
| 4897 |
|
pop @{$self->{open_elements}}; |
| 4898 |
|
|
| 4899 |
|
!!!next-token; |
| 4900 |
|
redo B; |
| 4901 |
|
} elsif ($token->{tag_name} eq 'isindex') { |
| 4902 |
|
!!!parse-error (type => 'isindex'); |
| 4903 |
|
|
| 4904 |
|
if (defined $self->{form_element}) { |
| 4905 |
|
## Ignore the token |
| 4906 |
|
!!!next-token; |
| 4907 |
|
redo B; |
| 4908 |
|
} else { |
| 4909 |
|
my $at = $token->{attributes}; |
| 4910 |
|
my $form_attrs; |
| 4911 |
|
$form_attrs->{action} = $at->{action} if $at->{action}; |
| 4912 |
|
my $prompt_attr = $at->{prompt}; |
| 4913 |
|
$at->{name} = {name => 'name', value => 'isindex'}; |
| 4914 |
|
delete $at->{action}; |
| 4915 |
|
delete $at->{prompt}; |
| 4916 |
|
my @tokens = ( |
| 4917 |
|
{type => START_TAG_TOKEN, tag_name => 'form', |
| 4918 |
|
attributes => $form_attrs}, |
| 4919 |
|
{type => START_TAG_TOKEN, tag_name => 'hr'}, |
| 4920 |
|
{type => START_TAG_TOKEN, tag_name => 'p'}, |
| 4921 |
|
{type => START_TAG_TOKEN, tag_name => 'label'}, |
| 4922 |
|
); |
| 4923 |
|
if ($prompt_attr) { |
| 4924 |
|
push @tokens, {type => CHARACTER_TOKEN, data => $prompt_attr->{value}}; |
| 4925 |
|
} else { |
| 4926 |
|
push @tokens, {type => CHARACTER_TOKEN, |
| 4927 |
|
data => 'This is a searchable index. Insert your search keywords here: '}; # SHOULD |
| 4928 |
|
## TODO: make this configurable |
| 4929 |
|
} |
| 4930 |
|
push @tokens, |
| 4931 |
|
{type => START_TAG_TOKEN, tag_name => 'input', attributes => $at}, |
| 4932 |
|
#{type => CHARACTER_TOKEN, data => ''}, # SHOULD |
| 4933 |
|
{type => END_TAG_TOKEN, tag_name => 'label'}, |
| 4934 |
|
{type => END_TAG_TOKEN, tag_name => 'p'}, |
| 4935 |
|
{type => START_TAG_TOKEN, tag_name => 'hr'}, |
| 4936 |
|
{type => END_TAG_TOKEN, tag_name => 'form'}; |
| 4937 |
|
$token = shift @tokens; |
| 4938 |
|
!!!back-token (@tokens); |
| 4939 |
|
redo B; |
| 4940 |
|
} |
| 4941 |
|
} elsif ($token->{tag_name} eq 'textarea') { |
| 4942 |
|
my $tag_name = $token->{tag_name}; |
| 4943 |
|
my $el; |
| 4944 |
|
!!!create-element ($el, $token->{tag_name}, $token->{attributes}); |
| 4945 |
|
|
| 4946 |
|
## TODO: $self->{form_element} if defined |
| 4947 |
|
$self->{content_model} = RCDATA_CONTENT_MODEL; |
| 4948 |
|
delete $self->{escape}; # MUST |
| 4949 |
|
|
| 4950 |
|
$insert->($el); |
| 4951 |
|
|
| 4952 |
|
my $text = ''; |
| 4953 |
|
!!!next-token; |
| 4954 |
|
if ($token->{type} == CHARACTER_TOKEN) { |
| 4955 |
|
$token->{data} =~ s/^\x0A//; |
| 4956 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 4957 |
!!!next-token; |
!!!next-token; |
|
redo B; |
|
| 4958 |
} |
} |
| 4959 |
} |
} |
| 4960 |
|
while ($token->{type} == CHARACTER_TOKEN) { |
| 4961 |
|
$text .= $token->{data}; |
| 4962 |
|
!!!next-token; |
| 4963 |
|
} |
| 4964 |
|
if (length $text) { |
| 4965 |
|
$el->manakai_append_text ($text); |
| 4966 |
|
} |
| 4967 |
|
|
| 4968 |
|
$self->{content_model} = PCDATA_CONTENT_MODEL; |
| 4969 |
|
|
| 4970 |
|
if ($token->{type} == END_TAG_TOKEN and |
| 4971 |
|
$token->{tag_name} eq $tag_name) { |
| 4972 |
|
## Ignore the token |
| 4973 |
|
} else { |
| 4974 |
|
!!!parse-error (type => 'in RCDATA:#'.$token->{type}); |
| 4975 |
|
} |
| 4976 |
|
!!!next-token; |
| 4977 |
|
redo B; |
| 4978 |
|
} elsif ({ |
| 4979 |
|
iframe => 1, |
| 4980 |
|
noembed => 1, |
| 4981 |
|
noframes => 1, |
| 4982 |
|
noscript => 0, ## TODO: 1 if scripting is enabled |
| 4983 |
|
}->{$token->{tag_name}}) { |
| 4984 |
|
## NOTE: There is an "as if in body" code clone. |
| 4985 |
|
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert); |
| 4986 |
|
redo B; |
| 4987 |
|
} elsif ($token->{tag_name} eq 'select') { |
| 4988 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4989 |
|
|
| 4990 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 4991 |
|
|
| 4992 |
|
$self->{insertion_mode} = IN_SELECT_IM; |
| 4993 |
|
!!!next-token; |
| 4994 |
|
redo B; |
| 4995 |
|
} elsif ({ |
| 4996 |
|
caption => 1, col => 1, colgroup => 1, frame => 1, |
| 4997 |
|
frameset => 1, head => 1, option => 1, optgroup => 1, |
| 4998 |
|
tbody => 1, td => 1, tfoot => 1, th => 1, |
| 4999 |
|
thead => 1, tr => 1, |
| 5000 |
|
}->{$token->{tag_name}}) { |
| 5001 |
|
!!!parse-error (type => 'in body:'.$token->{tag_name}); |
| 5002 |
|
## Ignore the token |
| 5003 |
|
!!!next-token; |
| 5004 |
|
redo B; |
| 5005 |
|
|
| 5006 |
|
## ISSUE: An issue on HTML5 new elements in the spec. |
| 5007 |
|
} else { |
| 5008 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 5009 |
|
|
| 5010 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 5011 |
|
|
| 5012 |
|
!!!next-token; |
| 5013 |
|
redo B; |
| 5014 |
|
} |
| 5015 |
|
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 5016 |
|
if ($token->{tag_name} eq 'body') { |
| 5017 |
|
if (@{$self->{open_elements}} > 1 and |
| 5018 |
|
$self->{open_elements}->[1]->[1] eq 'body') { |
| 5019 |
|
for (@{$self->{open_elements}}) { |
| 5020 |
|
unless ({ |
| 5021 |
|
dd => 1, dt => 1, li => 1, p => 1, td => 1, |
| 5022 |
|
th => 1, tr => 1, body => 1, html => 1, |
| 5023 |
|
tbody => 1, tfoot => 1, thead => 1, |
| 5024 |
|
}->{$_->[1]}) { |
| 5025 |
|
!!!parse-error (type => 'not closed:'.$_->[1]); |
| 5026 |
|
} |
| 5027 |
|
} |
| 5028 |
|
|
| 5029 |
!!!parse-error (type => 'after html:#character'); |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 5030 |
$self->{insertion_mode} = $previous_insertion_mode; |
!!!next-token; |
| 5031 |
## reprocess |
redo B; |
| 5032 |
|
} else { |
| 5033 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 5034 |
|
## Ignore the token |
| 5035 |
|
!!!next-token; |
| 5036 |
|
redo B; |
| 5037 |
|
} |
| 5038 |
|
} elsif ($token->{tag_name} eq 'html') { |
| 5039 |
|
if (@{$self->{open_elements}} > 1 and $self->{open_elements}->[1]->[1] eq 'body') { |
| 5040 |
|
## ISSUE: There is an issue in the spec. |
| 5041 |
|
if ($self->{open_elements}->[-1]->[1] ne 'body') { |
| 5042 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[1]->[1]); |
| 5043 |
|
} |
| 5044 |
|
$self->{insertion_mode} = AFTER_BODY_IM; |
| 5045 |
|
## reprocess |
| 5046 |
|
redo B; |
| 5047 |
|
} else { |
| 5048 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 5049 |
|
## Ignore the token |
| 5050 |
|
!!!next-token; |
| 5051 |
|
redo B; |
| 5052 |
|
} |
| 5053 |
|
} elsif ({ |
| 5054 |
|
address => 1, blockquote => 1, center => 1, dir => 1, |
| 5055 |
|
div => 1, dl => 1, fieldset => 1, listing => 1, |
| 5056 |
|
menu => 1, ol => 1, pre => 1, ul => 1, |
| 5057 |
|
p => 1, |
| 5058 |
|
dd => 1, dt => 1, li => 1, |
| 5059 |
|
button => 1, marquee => 1, object => 1, |
| 5060 |
|
}->{$token->{tag_name}}) { |
| 5061 |
|
## has an element in scope |
| 5062 |
|
my $i; |
| 5063 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5064 |
|
my $node = $self->{open_elements}->[$_]; |
| 5065 |
|
if ($node->[1] eq $token->{tag_name}) { |
| 5066 |
|
## generate implied end tags |
| 5067 |
|
if ({ |
| 5068 |
|
dd => ($token->{tag_name} ne 'dd'), |
| 5069 |
|
dt => ($token->{tag_name} ne 'dt'), |
| 5070 |
|
li => ($token->{tag_name} ne 'li'), |
| 5071 |
|
p => ($token->{tag_name} ne 'p'), |
| 5072 |
|
td => 1, th => 1, tr => 1, |
| 5073 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 5074 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 5075 |
|
!!!back-token; |
| 5076 |
|
$token = {type => END_TAG_TOKEN, |
| 5077 |
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 5078 |
|
redo B; |
| 5079 |
|
} |
| 5080 |
|
$i = $_; |
| 5081 |
|
last INSCOPE unless $token->{tag_name} eq 'p'; |
| 5082 |
|
} elsif ({ |
| 5083 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 5084 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 5085 |
|
}->{$node->[1]}) { |
| 5086 |
|
last INSCOPE; |
| 5087 |
|
} |
| 5088 |
|
} # INSCOPE |
| 5089 |
|
|
| 5090 |
|
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
| 5091 |
|
if (defined $i) { |
| 5092 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 5093 |
|
} else { |
| 5094 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 5095 |
|
} |
| 5096 |
|
} |
| 5097 |
|
|
| 5098 |
|
if (defined $i) { |
| 5099 |
|
splice @{$self->{open_elements}}, $i; |
| 5100 |
|
} elsif ($token->{tag_name} eq 'p') { |
| 5101 |
|
## As if <p>, then reprocess the current token |
| 5102 |
|
my $el; |
| 5103 |
|
!!!create-element ($el, 'p'); |
| 5104 |
|
$insert->($el); |
| 5105 |
|
} |
| 5106 |
|
$clear_up_to_marker->() |
| 5107 |
|
if { |
| 5108 |
|
button => 1, marquee => 1, object => 1, |
| 5109 |
|
}->{$token->{tag_name}}; |
| 5110 |
|
!!!next-token; |
| 5111 |
redo B; |
redo B; |
| 5112 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{tag_name} eq 'form') { |
| 5113 |
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
## has an element in scope |
| 5114 |
$self->{insertion_mode} = $previous_insertion_mode; |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5115 |
## reprocess |
my $node = $self->{open_elements}->[$_]; |
| 5116 |
|
if ($node->[1] eq $token->{tag_name}) { |
| 5117 |
|
## generate implied end tags |
| 5118 |
|
if ({ |
| 5119 |
|
dd => 1, dt => 1, li => 1, p => 1, |
| 5120 |
|
td => 1, th => 1, tr => 1, |
| 5121 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 5122 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 5123 |
|
!!!back-token; |
| 5124 |
|
$token = {type => END_TAG_TOKEN, |
| 5125 |
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 5126 |
|
redo B; |
| 5127 |
|
} |
| 5128 |
|
last INSCOPE; |
| 5129 |
|
} elsif ({ |
| 5130 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 5131 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 5132 |
|
}->{$node->[1]}) { |
| 5133 |
|
last INSCOPE; |
| 5134 |
|
} |
| 5135 |
|
} # INSCOPE |
| 5136 |
|
|
| 5137 |
|
if ($self->{open_elements}->[-1]->[1] eq $token->{tag_name}) { |
| 5138 |
|
pop @{$self->{open_elements}}; |
| 5139 |
|
} else { |
| 5140 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 5141 |
|
} |
| 5142 |
|
|
| 5143 |
|
undef $self->{form_element}; |
| 5144 |
|
!!!next-token; |
| 5145 |
redo B; |
redo B; |
| 5146 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ({ |
| 5147 |
!!!parse-error (type => 'after html:/'.$token->{tag_name}); |
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
| 5148 |
$self->{insertion_mode} = $previous_insertion_mode; |
}->{$token->{tag_name}}) { |
| 5149 |
## reprocess |
## has an element in scope |
| 5150 |
|
my $i; |
| 5151 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5152 |
|
my $node = $self->{open_elements}->[$_]; |
| 5153 |
|
if ({ |
| 5154 |
|
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
| 5155 |
|
}->{$node->[1]}) { |
| 5156 |
|
## generate implied end tags |
| 5157 |
|
if ({ |
| 5158 |
|
dd => 1, dt => 1, li => 1, p => 1, |
| 5159 |
|
td => 1, th => 1, tr => 1, |
| 5160 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 5161 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 5162 |
|
!!!back-token; |
| 5163 |
|
$token = {type => END_TAG_TOKEN, |
| 5164 |
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 5165 |
|
redo B; |
| 5166 |
|
} |
| 5167 |
|
$i = $_; |
| 5168 |
|
last INSCOPE; |
| 5169 |
|
} elsif ({ |
| 5170 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 5171 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 5172 |
|
}->{$node->[1]}) { |
| 5173 |
|
last INSCOPE; |
| 5174 |
|
} |
| 5175 |
|
} # INSCOPE |
| 5176 |
|
|
| 5177 |
|
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
| 5178 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 5179 |
|
} |
| 5180 |
|
|
| 5181 |
|
splice @{$self->{open_elements}}, $i if defined $i; |
| 5182 |
|
!!!next-token; |
| 5183 |
|
redo B; |
| 5184 |
|
} elsif ({ |
| 5185 |
|
a => 1, |
| 5186 |
|
b => 1, big => 1, em => 1, font => 1, i => 1, |
| 5187 |
|
nobr => 1, s => 1, small => 1, strile => 1, |
| 5188 |
|
strong => 1, tt => 1, u => 1, |
| 5189 |
|
}->{$token->{tag_name}}) { |
| 5190 |
|
$formatting_end_tag->($token->{tag_name}); |
| 5191 |
|
redo B; |
| 5192 |
|
} elsif ($token->{tag_name} eq 'br') { |
| 5193 |
|
!!!parse-error (type => 'unmatched end tag:br'); |
| 5194 |
|
|
| 5195 |
|
## As if <br> |
| 5196 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 5197 |
|
|
| 5198 |
|
my $el; |
| 5199 |
|
!!!create-element ($el, 'br'); |
| 5200 |
|
$insert->($el); |
| 5201 |
|
|
| 5202 |
|
## Ignore the token. |
| 5203 |
|
!!!next-token; |
| 5204 |
redo B; |
redo B; |
| 5205 |
|
} elsif ({ |
| 5206 |
|
caption => 1, col => 1, colgroup => 1, frame => 1, |
| 5207 |
|
frameset => 1, head => 1, option => 1, optgroup => 1, |
| 5208 |
|
tbody => 1, td => 1, tfoot => 1, th => 1, |
| 5209 |
|
thead => 1, tr => 1, |
| 5210 |
|
area => 1, basefont => 1, bgsound => 1, |
| 5211 |
|
embed => 1, hr => 1, iframe => 1, image => 1, |
| 5212 |
|
img => 1, input => 1, isindex => 1, noembed => 1, |
| 5213 |
|
noframes => 1, param => 1, select => 1, spacer => 1, |
| 5214 |
|
table => 1, textarea => 1, wbr => 1, |
| 5215 |
|
noscript => 0, ## TODO: if scripting is enabled |
| 5216 |
|
}->{$token->{tag_name}}) { |
| 5217 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 5218 |
|
## Ignore the token |
| 5219 |
|
!!!next-token; |
| 5220 |
|
redo B; |
| 5221 |
|
|
| 5222 |
|
## ISSUE: Issue on HTML5 new elements in spec |
| 5223 |
|
|
| 5224 |
} else { |
} else { |
| 5225 |
die "$0: $token->{type}: Unknown token"; |
## Step 1 |
| 5226 |
|
my $node_i = -1; |
| 5227 |
|
my $node = $self->{open_elements}->[$node_i]; |
| 5228 |
|
|
| 5229 |
|
## Step 2 |
| 5230 |
|
S2: { |
| 5231 |
|
if ($node->[1] eq $token->{tag_name}) { |
| 5232 |
|
## Step 1 |
| 5233 |
|
## generate implied end tags |
| 5234 |
|
if ({ |
| 5235 |
|
dd => 1, dt => 1, li => 1, p => 1, |
| 5236 |
|
td => 1, th => 1, tr => 1, |
| 5237 |
|
tbody => 1, tfoot => 1, thead => 1, |
| 5238 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 5239 |
|
!!!back-token; |
| 5240 |
|
$token = {type => END_TAG_TOKEN, |
| 5241 |
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 5242 |
|
redo B; |
| 5243 |
|
} |
| 5244 |
|
|
| 5245 |
|
## Step 2 |
| 5246 |
|
if ($token->{tag_name} ne $self->{open_elements}->[-1]->[1]) { |
| 5247 |
|
## NOTE: <x><y></x> |
| 5248 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 5249 |
|
} |
| 5250 |
|
|
| 5251 |
|
## Step 3 |
| 5252 |
|
splice @{$self->{open_elements}}, $node_i; |
| 5253 |
|
|
| 5254 |
|
!!!next-token; |
| 5255 |
|
last S2; |
| 5256 |
|
} else { |
| 5257 |
|
## Step 3 |
| 5258 |
|
if (not $formatting_category->{$node->[1]} and |
| 5259 |
|
#not $phrasing_category->{$node->[1]} and |
| 5260 |
|
($special_category->{$node->[1]} or |
| 5261 |
|
$scoping_category->{$node->[1]})) { |
| 5262 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 5263 |
|
## Ignore the token |
| 5264 |
|
!!!next-token; |
| 5265 |
|
last S2; |
| 5266 |
|
} |
| 5267 |
|
} |
| 5268 |
|
|
| 5269 |
|
## Step 4 |
| 5270 |
|
$node_i--; |
| 5271 |
|
$node = $self->{open_elements}->[$node_i]; |
| 5272 |
|
|
| 5273 |
|
## Step 5; |
| 5274 |
|
redo S2; |
| 5275 |
|
} # S2 |
| 5276 |
|
redo B; |
| 5277 |
} |
} |
|
} else { |
|
|
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
|
| 5278 |
} |
} |
| 5279 |
|
redo B; |
| 5280 |
} # B |
} # B |
| 5281 |
|
|
| 5282 |
|
## NOTE: The "trailing end" phase in HTML5 is split into |
| 5283 |
|
## two insertion modes: "after html body" and "after html frameset". |
| 5284 |
|
## NOTE: States in the main stage is preserved while |
| 5285 |
|
## the parser stays in the trailing end phase. # MUST |
| 5286 |
|
|
| 5287 |
## Stop parsing # MUST |
## Stop parsing # MUST |
| 5288 |
|
|
| 5289 |
## TODO: script stuffs |
## TODO: script stuffs |
| 5295 |
my $s = \$_[0]; |
my $s = \$_[0]; |
| 5296 |
my $onerror = $_[1]; |
my $onerror = $_[1]; |
| 5297 |
|
|
| 5298 |
|
## ISSUE: Should {confident} be true? |
| 5299 |
|
|
| 5300 |
my $nt = $node->node_type; |
my $nt = $node->node_type; |
| 5301 |
if ($nt == 9) { |
if ($nt == 9) { |
| 5302 |
# MUST |
# MUST |
| 5449 |
|
|
| 5450 |
} # tree construction stage |
} # tree construction stage |
| 5451 |
|
|
| 5452 |
sub get_inner_html ($$$) { |
package Whatpm::HTML::RestartParser; |
| 5453 |
my (undef, $node, $on_error) = @_; |
push our @ISA, 'Error'; |
|
|
|
|
## Step 1 |
|
|
my $s = ''; |
|
|
|
|
|
my $in_cdata; |
|
|
my $parent = $node; |
|
|
while (defined $parent) { |
|
|
if ($parent->node_type == 1 and |
|
|
$parent->namespace_uri eq 'http://www.w3.org/1999/xhtml' and |
|
|
{ |
|
|
style => 1, script => 1, xmp => 1, iframe => 1, |
|
|
noembed => 1, noframes => 1, noscript => 1, |
|
|
}->{$parent->local_name}) { ## TODO: case thingy |
|
|
$in_cdata = 1; |
|
|
} |
|
|
$parent = $parent->parent_node; |
|
|
} |
|
|
|
|
|
## Step 2 |
|
|
my @node = @{$node->child_nodes}; |
|
|
C: while (@node) { |
|
|
my $child = shift @node; |
|
|
unless (ref $child) { |
|
|
if ($child eq 'cdata-out') { |
|
|
$in_cdata = 0; |
|
|
} else { |
|
|
$s .= $child; # end tag |
|
|
} |
|
|
next C; |
|
|
} |
|
|
|
|
|
my $nt = $child->node_type; |
|
|
if ($nt == 1) { # Element |
|
|
my $tag_name = $child->tag_name; ## TODO: manakai_tag_name |
|
|
$s .= '<' . $tag_name; |
|
|
## NOTE: Non-HTML case: |
|
|
## <http://permalink.gmane.org/gmane.org.w3c.whatwg.discuss/11191> |
|
|
|
|
|
my @attrs = @{$child->attributes}; # sort order MUST be stable |
|
|
for my $attr (@attrs) { # order is implementation dependent |
|
|
my $attr_name = $attr->name; ## TODO: manakai_name |
|
|
$s .= ' ' . $attr_name . '="'; |
|
|
my $attr_value = $attr->value; |
|
|
## escape |
|
|
$attr_value =~ s/&/&/g; |
|
|
$attr_value =~ s/</</g; |
|
|
$attr_value =~ s/>/>/g; |
|
|
$attr_value =~ s/"/"/g; |
|
|
$s .= $attr_value . '"'; |
|
|
} |
|
|
$s .= '>'; |
|
|
|
|
|
next C if { |
|
|
area => 1, base => 1, basefont => 1, bgsound => 1, |
|
|
br => 1, col => 1, embed => 1, frame => 1, hr => 1, |
|
|
img => 1, input => 1, link => 1, meta => 1, param => 1, |
|
|
spacer => 1, wbr => 1, |
|
|
}->{$tag_name}; |
|
|
|
|
|
$s .= "\x0A" if $tag_name eq 'pre' or $tag_name eq 'textarea'; |
|
|
|
|
|
if (not $in_cdata and { |
|
|
style => 1, script => 1, xmp => 1, iframe => 1, |
|
|
noembed => 1, noframes => 1, noscript => 1, |
|
|
plaintext => 1, |
|
|
}->{$tag_name}) { |
|
|
unshift @node, 'cdata-out'; |
|
|
$in_cdata = 1; |
|
|
} |
|
|
|
|
|
unshift @node, @{$child->child_nodes}, '</' . $tag_name . '>'; |
|
|
} elsif ($nt == 3 or $nt == 4) { |
|
|
if ($in_cdata) { |
|
|
$s .= $child->data; |
|
|
} else { |
|
|
my $value = $child->data; |
|
|
$value =~ s/&/&/g; |
|
|
$value =~ s/</</g; |
|
|
$value =~ s/>/>/g; |
|
|
$value =~ s/"/"/g; |
|
|
$s .= $value; |
|
|
} |
|
|
} elsif ($nt == 8) { |
|
|
$s .= '<!--' . $child->data . '-->'; |
|
|
} elsif ($nt == 10) { |
|
|
$s .= '<!DOCTYPE ' . $child->name . '>'; |
|
|
} elsif ($nt == 5) { # entrefs |
|
|
push @node, @{$child->child_nodes}; |
|
|
} else { |
|
|
$on_error->($child) if defined $on_error; |
|
|
} |
|
|
## ISSUE: This code does not support PIs. |
|
|
} # C |
|
|
|
|
|
## Step 3 |
|
|
return \$s; |
|
|
} # get_inner_html |
|
| 5454 |
|
|
| 5455 |
1; |
1; |
| 5456 |
# $Date$ |
# $Date$ |