Parent Directory
| 
Revision Log
++ whatpm/t/ChangeLog 16 Jul 2007 04:51:17 -0000 * tree-test-1.dat: Tests for |<html>| in trailing end phase and |</frameset>| in after frameset mode are added. * tree-test-2.dat: Tests for |</frameset>| in |frameset| fragment parsing are added. 2007-07-16 Wakaba <wakaba@suika.fam.cx> ++ whatpm/Whatpm/ChangeLog 16 Jul 2007 04:49:33 -0000 * HTML.pm.src (main and trailin end phases): Token types |DOCTYPE|, |comment|, |end-of-file|, and |<html>| are factored out. Error types |in html:#DOCTYPE| and |after html:#DOCTYPE| are merged into |DOCTYPE in the middle|. |</frameset>| in fragment parsing mode changed the insertion mode. 2007-07-16 Wakaba <wakaba@suika.fam.cx>
| 1 | wakaba | 1.2 | package Whatpm::HTML; |
| 2 | wakaba | 1.1 | use strict; |
| 3 | wakaba | 1.36 | our $VERSION=do{my @r=(q$Revision: 1.35 $=~/\d+/g);sprintf "%d."."%02d" x $#r,@r}; |
| 4 | wakaba | 1.1 | |
| 5 | wakaba | 1.18 | ## ISSUE: |
| 6 | ## var doc = implementation.createDocument (null, null, null); | ||
| 7 | ## doc.write (''); | ||
| 8 | ## alert (doc.compatMode); | ||
| 9 | wakaba | 1.1 | |
| 10 | wakaba | 1.31 | ## ISSUE: HTML5 revision 967 says that the encoding layer MUST NOT |
| 11 | ## strip BOM and the HTML layer MUST ignore it. Whether we can do it | ||
| 12 | ## is not yet clear. | ||
| 13 | ## "{U+FEFF}..." in UTF-16BE/UTF-16LE is three or four characters? | ||
| 14 | ## "{U+FEFF}..." in GB18030? | ||
| 15 | |||
| 16 | wakaba | 1.1 | my $permitted_slash_tag_name = { |
| 17 | base => 1, | ||
| 18 | link => 1, | ||
| 19 | meta => 1, | ||
| 20 | hr => 1, | ||
| 21 | br => 1, | ||
| 22 | img=> 1, | ||
| 23 | embed => 1, | ||
| 24 | param => 1, | ||
| 25 | area => 1, | ||
| 26 | col => 1, | ||
| 27 | input => 1, | ||
| 28 | }; | ||
| 29 | |||
| 30 | wakaba | 1.4 | my $c1_entity_char = { |
| 31 | wakaba | 1.9 | 0x80 => 0x20AC, |
| 32 | 0x81 => 0xFFFD, | ||
| 33 | 0x82 => 0x201A, | ||
| 34 | 0x83 => 0x0192, | ||
| 35 | 0x84 => 0x201E, | ||
| 36 | 0x85 => 0x2026, | ||
| 37 | 0x86 => 0x2020, | ||
| 38 | 0x87 => 0x2021, | ||
| 39 | 0x88 => 0x02C6, | ||
| 40 | 0x89 => 0x2030, | ||
| 41 | 0x8A => 0x0160, | ||
| 42 | 0x8B => 0x2039, | ||
| 43 | 0x8C => 0x0152, | ||
| 44 | 0x8D => 0xFFFD, | ||
| 45 | 0x8E => 0x017D, | ||
| 46 | 0x8F => 0xFFFD, | ||
| 47 | 0x90 => 0xFFFD, | ||
| 48 | 0x91 => 0x2018, | ||
| 49 | 0x92 => 0x2019, | ||
| 50 | 0x93 => 0x201C, | ||
| 51 | 0x94 => 0x201D, | ||
| 52 | 0x95 => 0x2022, | ||
| 53 | 0x96 => 0x2013, | ||
| 54 | 0x97 => 0x2014, | ||
| 55 | 0x98 => 0x02DC, | ||
| 56 | 0x99 => 0x2122, | ||
| 57 | 0x9A => 0x0161, | ||
| 58 | 0x9B => 0x203A, | ||
| 59 | 0x9C => 0x0153, | ||
| 60 | 0x9D => 0xFFFD, | ||
| 61 | 0x9E => 0x017E, | ||
| 62 | 0x9F => 0x0178, | ||
| 63 | wakaba | 1.4 | }; # $c1_entity_char |
| 64 | wakaba | 1.1 | |
| 65 | my $special_category = { | ||
| 66 | address => 1, area => 1, base => 1, basefont => 1, bgsound => 1, | ||
| 67 | blockquote => 1, body => 1, br => 1, center => 1, col => 1, colgroup => 1, | ||
| 68 | dd => 1, dir => 1, div => 1, dl => 1, dt => 1, embed => 1, fieldset => 1, | ||
| 69 | form => 1, frame => 1, frameset => 1, h1 => 1, h2 => 1, h3 => 1, | ||
| 70 | h4 => 1, h5 => 1, h6 => 1, head => 1, hr => 1, iframe => 1, image => 1, | ||
| 71 | img => 1, input => 1, isindex => 1, li => 1, link => 1, listing => 1, | ||
| 72 | menu => 1, meta => 1, noembed => 1, noframes => 1, noscript => 1, | ||
| 73 | ol => 1, optgroup => 1, option => 1, p => 1, param => 1, plaintext => 1, | ||
| 74 | pre => 1, script => 1, select => 1, spacer => 1, style => 1, tbody => 1, | ||
| 75 | textarea => 1, tfoot => 1, thead => 1, title => 1, tr => 1, ul => 1, wbr => 1, | ||
| 76 | }; | ||
| 77 | my $scoping_category = { | ||
| 78 | button => 1, caption => 1, html => 1, marquee => 1, object => 1, | ||
| 79 | table => 1, td => 1, th => 1, | ||
| 80 | }; | ||
| 81 | my $formatting_category = { | ||
| 82 | a => 1, b => 1, big => 1, em => 1, font => 1, i => 1, nobr => 1, | ||
| 83 | s => 1, small => 1, strile => 1, strong => 1, tt => 1, u => 1, | ||
| 84 | }; | ||
| 85 | # $phrasing_category: all other elements | ||
| 86 | |||
| 87 | sub parse_string ($$$;$) { | ||
| 88 | my $self = shift->new; | ||
| 89 | my $s = \$_[0]; | ||
| 90 | $self->{document} = $_[1]; | ||
| 91 | |||
| 92 | wakaba | 1.3 | ## NOTE: |set_inner_html| copies most of this method's code |
| 93 | |||
| 94 | wakaba | 1.1 | my $i = 0; |
| 95 | wakaba | 1.3 | my $line = 1; |
| 96 | my $column = 0; | ||
| 97 | wakaba | 1.1 | $self->{set_next_input_character} = sub { |
| 98 | my $self = shift; | ||
| 99 | wakaba | 1.13 | |
| 100 | pop @{$self->{prev_input_character}}; | ||
| 101 | unshift @{$self->{prev_input_character}}, $self->{next_input_character}; | ||
| 102 | |||
| 103 | wakaba | 1.1 | $self->{next_input_character} = -1 and return if $i >= length $$s; |
| 104 | $self->{next_input_character} = ord substr $$s, $i++, 1; | ||
| 105 | wakaba | 1.3 | $column++; |
| 106 | wakaba | 1.1 | |
| 107 | wakaba | 1.4 | if ($self->{next_input_character} == 0x000A) { # LF |
| 108 | $line++; | ||
| 109 | $column = 0; | ||
| 110 | } elsif ($self->{next_input_character} == 0x000D) { # CR | ||
| 111 | wakaba | 1.15 | $i++ if substr ($$s, $i, 1) eq "\x0A"; |
| 112 | wakaba | 1.1 | $self->{next_input_character} = 0x000A; # LF # MUST |
| 113 | wakaba | 1.3 | $line++; |
| 114 | wakaba | 1.4 | $column = 0; |
| 115 | wakaba | 1.1 | } elsif ($self->{next_input_character} > 0x10FFFF) { |
| 116 | $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST | ||
| 117 | } elsif ($self->{next_input_character} == 0x0000) { # NULL | ||
| 118 | wakaba | 1.8 | $self->{parse_error}-> (type => 'NULL'); |
| 119 | wakaba | 1.1 | $self->{next_input_character} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
| 120 | } | ||
| 121 | }; | ||
| 122 | wakaba | 1.13 | $self->{prev_input_character} = [-1, -1, -1]; |
| 123 | $self->{next_input_character} = -1; | ||
| 124 | wakaba | 1.1 | |
| 125 | wakaba | 1.3 | my $onerror = $_[2] || sub { |
| 126 | my (%opt) = @_; | ||
| 127 | warn "Parse error ($opt{type}) at line $opt{line} column $opt{column}\n"; | ||
| 128 | }; | ||
| 129 | $self->{parse_error} = sub { | ||
| 130 | $onerror->(@_, line => $line, column => $column); | ||
| 131 | wakaba | 1.1 | }; |
| 132 | |||
| 133 | $self->_initialize_tokenizer; | ||
| 134 | $self->_initialize_tree_constructor; | ||
| 135 | $self->_construct_tree; | ||
| 136 | $self->_terminate_tree_constructor; | ||
| 137 | |||
| 138 | return $self->{document}; | ||
| 139 | } # parse_string | ||
| 140 | |||
| 141 | sub new ($) { | ||
| 142 | my $class = shift; | ||
| 143 | my $self = bless {}, $class; | ||
| 144 | $self->{set_next_input_character} = sub { | ||
| 145 | $self->{next_input_character} = -1; | ||
| 146 | }; | ||
| 147 | $self->{parse_error} = sub { | ||
| 148 | # | ||
| 149 | }; | ||
| 150 | return $self; | ||
| 151 | } # new | ||
| 152 | |||
| 153 | ## Implementations MUST act as if state machine in the spec | ||
| 154 | |||
| 155 | sub _initialize_tokenizer ($) { | ||
| 156 | my $self = shift; | ||
| 157 | $self->{state} = 'data'; # MUST | ||
| 158 | $self->{content_model_flag} = 'PCDATA'; # be | ||
| 159 | undef $self->{current_token}; # start tag, end tag, comment, or DOCTYPE | ||
| 160 | undef $self->{current_attribute}; | ||
| 161 | undef $self->{last_emitted_start_tag_name}; | ||
| 162 | undef $self->{last_attribute_value_state}; | ||
| 163 | $self->{char} = []; | ||
| 164 | # $self->{next_input_character} | ||
| 165 | |||
| 166 | if (@{$self->{char}}) { | ||
| 167 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 168 | } else { | ||
| 169 | $self->{set_next_input_character}->($self); | ||
| 170 | } | ||
| 171 | |||
| 172 | $self->{token} = []; | ||
| 173 | wakaba | 1.18 | # $self->{escape} |
| 174 | wakaba | 1.1 | } # _initialize_tokenizer |
| 175 | |||
| 176 | ## A token has: | ||
| 177 | ## ->{type} eq 'DOCTYPE', 'start tag', 'end tag', 'comment', | ||
| 178 | ## 'character', or 'end-of-file' | ||
| 179 | wakaba | 1.18 | ## ->{name} (DOCTYPE, start tag (tag name), end tag (tag name)) |
| 180 | ## ->{public_identifier} (DOCTYPE) | ||
| 181 | ## ->{system_identifier} (DOCTYPE) | ||
| 182 | ## ->{correct} == 1 or 0 (DOCTYPE) | ||
| 183 | wakaba | 1.1 | ## ->{attributes} isa HASH (start tag, end tag) |
| 184 | ## ->{data} (comment, character) | ||
| 185 | |||
| 186 | ## Emitted token MUST immediately be handled by the tree construction state. | ||
| 187 | |||
| 188 | ## Before each step, UA MAY check to see if either one of the scripts in | ||
| 189 | ## "list of scripts that will execute as soon as possible" or the first | ||
| 190 | ## script in the "list of scripts that will execute asynchronously", | ||
| 191 | ## has completed loading. If one has, then it MUST be executed | ||
| 192 | ## and removed from the list. | ||
| 193 | |||
| 194 | sub _get_next_token ($) { | ||
| 195 | my $self = shift; | ||
| 196 | if (@{$self->{token}}) { | ||
| 197 | return shift @{$self->{token}}; | ||
| 198 | } | ||
| 199 | |||
| 200 | A: { | ||
| 201 | if ($self->{state} eq 'data') { | ||
| 202 | if ($self->{next_input_character} == 0x0026) { # & | ||
| 203 | if ($self->{content_model_flag} eq 'PCDATA' or | ||
| 204 | $self->{content_model_flag} eq 'RCDATA') { | ||
| 205 | $self->{state} = 'entity data'; | ||
| 206 | |||
| 207 | if (@{$self->{char}}) { | ||
| 208 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 209 | } else { | ||
| 210 | $self->{set_next_input_character}->($self); | ||
| 211 | } | ||
| 212 | |||
| 213 | redo A; | ||
| 214 | } else { | ||
| 215 | # | ||
| 216 | } | ||
| 217 | wakaba | 1.13 | } elsif ($self->{next_input_character} == 0x002D) { # - |
| 218 | if ($self->{content_model_flag} eq 'RCDATA' or | ||
| 219 | $self->{content_model_flag} eq 'CDATA') { | ||
| 220 | unless ($self->{escape}) { | ||
| 221 | if ($self->{prev_input_character}->[0] == 0x002D and # - | ||
| 222 | $self->{prev_input_character}->[1] == 0x0021 and # ! | ||
| 223 | $self->{prev_input_character}->[2] == 0x003C) { # < | ||
| 224 | $self->{escape} = 1; | ||
| 225 | } | ||
| 226 | } | ||
| 227 | } | ||
| 228 | |||
| 229 | # | ||
| 230 | wakaba | 1.1 | } elsif ($self->{next_input_character} == 0x003C) { # < |
| 231 | wakaba | 1.13 | if ($self->{content_model_flag} eq 'PCDATA' or |
| 232 | (($self->{content_model_flag} eq 'CDATA' or | ||
| 233 | $self->{content_model_flag} eq 'RCDATA') and | ||
| 234 | not $self->{escape})) { | ||
| 235 | wakaba | 1.1 | $self->{state} = 'tag open'; |
| 236 | |||
| 237 | if (@{$self->{char}}) { | ||
| 238 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 239 | } else { | ||
| 240 | $self->{set_next_input_character}->($self); | ||
| 241 | } | ||
| 242 | |||
| 243 | redo A; | ||
| 244 | } else { | ||
| 245 | # | ||
| 246 | } | ||
| 247 | wakaba | 1.13 | } elsif ($self->{next_input_character} == 0x003E) { # > |
| 248 | if ($self->{escape} and | ||
| 249 | ($self->{content_model_flag} eq 'RCDATA' or | ||
| 250 | $self->{content_model_flag} eq 'CDATA')) { | ||
| 251 | if ($self->{prev_input_character}->[0] == 0x002D and # - | ||
| 252 | $self->{prev_input_character}->[1] == 0x002D) { # - | ||
| 253 | delete $self->{escape}; | ||
| 254 | } | ||
| 255 | } | ||
| 256 | |||
| 257 | # | ||
| 258 | wakaba | 1.1 | } elsif ($self->{next_input_character} == -1) { |
| 259 | return ({type => 'end-of-file'}); | ||
| 260 | last A; ## TODO: ok? | ||
| 261 | } | ||
| 262 | # Anything else | ||
| 263 | my $token = {type => 'character', | ||
| 264 | data => chr $self->{next_input_character}}; | ||
| 265 | ## Stay in the data state | ||
| 266 | |||
| 267 | if (@{$self->{char}}) { | ||
| 268 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 269 | } else { | ||
| 270 | $self->{set_next_input_character}->($self); | ||
| 271 | } | ||
| 272 | |||
| 273 | |||
| 274 | return ($token); | ||
| 275 | |||
| 276 | redo A; | ||
| 277 | } elsif ($self->{state} eq 'entity data') { | ||
| 278 | ## (cannot happen in CDATA state) | ||
| 279 | |||
| 280 | wakaba | 1.26 | my $token = $self->_tokenize_attempt_to_consume_an_entity (0); |
| 281 | wakaba | 1.1 | |
| 282 | $self->{state} = 'data'; | ||
| 283 | # next-input-character is already done | ||
| 284 | |||
| 285 | unless (defined $token) { | ||
| 286 | return ({type => 'character', data => '&'}); | ||
| 287 | } else { | ||
| 288 | return ($token); | ||
| 289 | } | ||
| 290 | |||
| 291 | redo A; | ||
| 292 | } elsif ($self->{state} eq 'tag open') { | ||
| 293 | if ($self->{content_model_flag} eq 'RCDATA' or | ||
| 294 | $self->{content_model_flag} eq 'CDATA') { | ||
| 295 | if ($self->{next_input_character} == 0x002F) { # / | ||
| 296 | |||
| 297 | if (@{$self->{char}}) { | ||
| 298 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 299 | } else { | ||
| 300 | $self->{set_next_input_character}->($self); | ||
| 301 | } | ||
| 302 | |||
| 303 | $self->{state} = 'close tag open'; | ||
| 304 | redo A; | ||
| 305 | } else { | ||
| 306 | ## reconsume | ||
| 307 | $self->{state} = 'data'; | ||
| 308 | |||
| 309 | return ({type => 'character', data => '<'}); | ||
| 310 | |||
| 311 | redo A; | ||
| 312 | } | ||
| 313 | } elsif ($self->{content_model_flag} eq 'PCDATA') { | ||
| 314 | if ($self->{next_input_character} == 0x0021) { # ! | ||
| 315 | $self->{state} = 'markup declaration open'; | ||
| 316 | |||
| 317 | if (@{$self->{char}}) { | ||
| 318 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 319 | } else { | ||
| 320 | $self->{set_next_input_character}->($self); | ||
| 321 | } | ||
| 322 | |||
| 323 | redo A; | ||
| 324 | } elsif ($self->{next_input_character} == 0x002F) { # / | ||
| 325 | $self->{state} = 'close tag open'; | ||
| 326 | |||
| 327 | if (@{$self->{char}}) { | ||
| 328 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 329 | } else { | ||
| 330 | $self->{set_next_input_character}->($self); | ||
| 331 | } | ||
| 332 | |||
| 333 | redo A; | ||
| 334 | } elsif (0x0041 <= $self->{next_input_character} and | ||
| 335 | $self->{next_input_character} <= 0x005A) { # A..Z | ||
| 336 | $self->{current_token} | ||
| 337 | = {type => 'start tag', | ||
| 338 | tag_name => chr ($self->{next_input_character} + 0x0020)}; | ||
| 339 | $self->{state} = 'tag name'; | ||
| 340 | |||
| 341 | if (@{$self->{char}}) { | ||
| 342 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 343 | } else { | ||
| 344 | $self->{set_next_input_character}->($self); | ||
| 345 | } | ||
| 346 | |||
| 347 | redo A; | ||
| 348 | } elsif (0x0061 <= $self->{next_input_character} and | ||
| 349 | $self->{next_input_character} <= 0x007A) { # a..z | ||
| 350 | $self->{current_token} = {type => 'start tag', | ||
| 351 | tag_name => chr ($self->{next_input_character})}; | ||
| 352 | $self->{state} = 'tag name'; | ||
| 353 | |||
| 354 | if (@{$self->{char}}) { | ||
| 355 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 356 | } else { | ||
| 357 | $self->{set_next_input_character}->($self); | ||
| 358 | } | ||
| 359 | |||
| 360 | redo A; | ||
| 361 | } elsif ($self->{next_input_character} == 0x003E) { # > | ||
| 362 | wakaba | 1.3 | $self->{parse_error}-> (type => 'empty start tag'); |
| 363 | wakaba | 1.1 | $self->{state} = 'data'; |
| 364 | |||
| 365 | if (@{$self->{char}}) { | ||
| 366 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 367 | } else { | ||
| 368 | $self->{set_next_input_character}->($self); | ||
| 369 | } | ||
| 370 | |||
| 371 | |||
| 372 | return ({type => 'character', data => '<>'}); | ||
| 373 | |||
| 374 | redo A; | ||
| 375 | } elsif ($self->{next_input_character} == 0x003F) { # ? | ||
| 376 | wakaba | 1.3 | $self->{parse_error}-> (type => 'pio'); |
| 377 | wakaba | 1.1 | $self->{state} = 'bogus comment'; |
| 378 | ## $self->{next_input_character} is intentionally left as is | ||
| 379 | redo A; | ||
| 380 | } else { | ||
| 381 | wakaba | 1.3 | $self->{parse_error}-> (type => 'bare stago'); |
| 382 | wakaba | 1.1 | $self->{state} = 'data'; |
| 383 | ## reconsume | ||
| 384 | |||
| 385 | return ({type => 'character', data => '<'}); | ||
| 386 | |||
| 387 | redo A; | ||
| 388 | } | ||
| 389 | } else { | ||
| 390 | die "$0: $self->{content_model_flag}: Unknown content model flag"; | ||
| 391 | } | ||
| 392 | } elsif ($self->{state} eq 'close tag open') { | ||
| 393 | if ($self->{content_model_flag} eq 'RCDATA' or | ||
| 394 | $self->{content_model_flag} eq 'CDATA') { | ||
| 395 | wakaba | 1.23 | if (defined $self->{last_emitted_start_tag_name}) { |
| 396 | wakaba | 1.30 | ## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564> |
| 397 | wakaba | 1.23 | my @next_char; |
| 398 | TAGNAME: for (my $i = 0; $i < length $self->{last_emitted_start_tag_name}; $i++) { | ||
| 399 | push @next_char, $self->{next_input_character}; | ||
| 400 | my $c = ord substr ($self->{last_emitted_start_tag_name}, $i, 1); | ||
| 401 | my $C = 0x0061 <= $c && $c <= 0x007A ? $c - 0x0020 : $c; | ||
| 402 | if ($self->{next_input_character} == $c or $self->{next_input_character} == $C) { | ||
| 403 | |||
| 404 | wakaba | 1.1 | if (@{$self->{char}}) { |
| 405 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 406 | } else { | ||
| 407 | $self->{set_next_input_character}->($self); | ||
| 408 | } | ||
| 409 | |||
| 410 | wakaba | 1.23 | next TAGNAME; |
| 411 | } else { | ||
| 412 | $self->{next_input_character} = shift @next_char; # reconsume | ||
| 413 | unshift @{$self->{char}}, (@next_char); | ||
| 414 | $self->{state} = 'data'; | ||
| 415 | |||
| 416 | return ({type => 'character', data => '</'}); | ||
| 417 | |||
| 418 | redo A; | ||
| 419 | } | ||
| 420 | } | ||
| 421 | push @next_char, $self->{next_input_character}; | ||
| 422 | |||
| 423 | unless ($self->{next_input_character} == 0x0009 or # HT | ||
| 424 | $self->{next_input_character} == 0x000A or # LF | ||
| 425 | $self->{next_input_character} == 0x000B or # VT | ||
| 426 | $self->{next_input_character} == 0x000C or # FF | ||
| 427 | $self->{next_input_character} == 0x0020 or # SP | ||
| 428 | $self->{next_input_character} == 0x003E or # > | ||
| 429 | $self->{next_input_character} == 0x002F or # / | ||
| 430 | $self->{next_input_character} == -1) { | ||
| 431 | wakaba | 1.1 | $self->{next_input_character} = shift @next_char; # reconsume |
| 432 | unshift @{$self->{char}}, (@next_char); | ||
| 433 | $self->{state} = 'data'; | ||
| 434 | return ({type => 'character', data => '</'}); | ||
| 435 | redo A; | ||
| 436 | wakaba | 1.23 | } else { |
| 437 | $self->{next_input_character} = shift @next_char; | ||
| 438 | unshift @{$self->{char}}, (@next_char); | ||
| 439 | # and consume... | ||
| 440 | wakaba | 1.1 | } |
| 441 | wakaba | 1.23 | } else { |
| 442 | ## No start tag token has ever been emitted | ||
| 443 | # next-input-character is already done | ||
| 444 | wakaba | 1.1 | $self->{state} = 'data'; |
| 445 | return ({type => 'character', data => '</'}); | ||
| 446 | redo A; | ||
| 447 | } | ||
| 448 | } | ||
| 449 | |||
| 450 | if (0x0041 <= $self->{next_input_character} and | ||
| 451 | $self->{next_input_character} <= 0x005A) { # A..Z | ||
| 452 | $self->{current_token} = {type => 'end tag', | ||
| 453 | tag_name => chr ($self->{next_input_character} + 0x0020)}; | ||
| 454 | $self->{state} = 'tag name'; | ||
| 455 | |||
| 456 | if (@{$self->{char}}) { | ||
| 457 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 458 | } else { | ||
| 459 | $self->{set_next_input_character}->($self); | ||
| 460 | } | ||
| 461 | |||
| 462 | redo A; | ||
| 463 | } elsif (0x0061 <= $self->{next_input_character} and | ||
| 464 | $self->{next_input_character} <= 0x007A) { # a..z | ||
| 465 | $self->{current_token} = {type => 'end tag', | ||
| 466 | tag_name => chr ($self->{next_input_character})}; | ||
| 467 | $self->{state} = 'tag name'; | ||
| 468 | |||
| 469 | if (@{$self->{char}}) { | ||
| 470 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 471 | } else { | ||
| 472 | $self->{set_next_input_character}->($self); | ||
| 473 | } | ||
| 474 | |||
| 475 | redo A; | ||
| 476 | } elsif ($self->{next_input_character} == 0x003E) { # > | ||
| 477 | wakaba | 1.3 | $self->{parse_error}-> (type => 'empty end tag'); |
| 478 | wakaba | 1.1 | $self->{state} = 'data'; |
| 479 | |||
| 480 | if (@{$self->{char}}) { | ||
| 481 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 482 | } else { | ||
| 483 | $self->{set_next_input_character}->($self); | ||
| 484 | } | ||
| 485 | |||
| 486 | redo A; | ||
| 487 | } elsif ($self->{next_input_character} == -1) { | ||
| 488 | wakaba | 1.3 | $self->{parse_error}-> (type => 'bare etago'); |
| 489 | wakaba | 1.1 | $self->{state} = 'data'; |
| 490 | # reconsume | ||
| 491 | |||
| 492 | return ({type => 'character', data => '</'}); | ||
| 493 | |||
| 494 | redo A; | ||
| 495 | } else { | ||
| 496 | wakaba | 1.3 | $self->{parse_error}-> (type => 'bogus end tag'); |
| 497 | wakaba | 1.1 | $self->{state} = 'bogus comment'; |
| 498 | ## $self->{next_input_character} is intentionally left as is | ||
| 499 | redo A; | ||
| 500 | } | ||
| 501 | } elsif ($self->{state} eq 'tag name') { | ||
| 502 | if ($self->{next_input_character} == 0x0009 or # HT | ||
| 503 | $self->{next_input_character} == 0x000A or # LF | ||
| 504 | $self->{next_input_character} == 0x000B or # VT | ||
| 505 | $self->{next_input_character} == 0x000C or # FF | ||
| 506 | $self->{next_input_character} == 0x0020) { # SP | ||
| 507 | $self->{state} = 'before attribute name'; | ||
| 508 | |||
| 509 | if (@{$self->{char}}) { | ||
| 510 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 511 | } else { | ||
| 512 | $self->{set_next_input_character}->($self); | ||
| 513 | } | ||
| 514 | |||
| 515 | redo A; | ||
| 516 | } elsif ($self->{next_input_character} == 0x003E) { # > | ||
| 517 | if ($self->{current_token}->{type} eq 'start tag') { | ||
| 518 | wakaba | 1.28 | $self->{current_token}->{first_start_tag} |
| 519 | = not defined $self->{last_emitted_start_tag_name}; | ||
| 520 | wakaba | 1.1 | $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 521 | } elsif ($self->{current_token}->{type} eq 'end tag') { | ||
| 522 | $self->{content_model_flag} = 'PCDATA'; # MUST | ||
| 523 | if ($self->{current_token}->{attributes}) { | ||
| 524 | wakaba | 1.3 | $self->{parse_error}-> (type => 'end tag attribute'); |
| 525 | wakaba | 1.1 | } |
| 526 | } else { | ||
| 527 | die "$0: $self->{current_token}->{type}: Unknown token type"; | ||
| 528 | } | ||
| 529 | $self->{state} = 'data'; | ||
| 530 | |||
| 531 | if (@{$self->{char}}) { | ||
| 532 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 533 | } else { | ||
| 534 | $self->{set_next_input_character}->($self); | ||
| 535 | } | ||
| 536 | |||
| 537 | |||
| 538 | return ($self->{current_token}); # start tag or end tag | ||
| 539 | |||
| 540 | redo A; | ||
| 541 | } elsif (0x0041 <= $self->{next_input_character} and | ||
| 542 | $self->{next_input_character} <= 0x005A) { # A..Z | ||
| 543 | $self->{current_token}->{tag_name} .= chr ($self->{next_input_character} + 0x0020); | ||
| 544 | # start tag or end tag | ||
| 545 | ## Stay in this state | ||
| 546 | |||
| 547 | if (@{$self->{char}}) { | ||
| 548 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 549 | } else { | ||
| 550 | $self->{set_next_input_character}->($self); | ||
| 551 | } | ||
| 552 | |||
| 553 | redo A; | ||
| 554 | wakaba | 1.17 | } elsif ($self->{next_input_character} == -1) { |
| 555 | wakaba | 1.3 | $self->{parse_error}-> (type => 'unclosed tag'); |
| 556 | wakaba | 1.1 | if ($self->{current_token}->{type} eq 'start tag') { |
| 557 | wakaba | 1.28 | $self->{current_token}->{first_start_tag} |
| 558 | = not defined $self->{last_emitted_start_tag_name}; | ||
| 559 | wakaba | 1.1 | $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 560 | } elsif ($self->{current_token}->{type} eq 'end tag') { | ||
| 561 | $self->{content_model_flag} = 'PCDATA'; # MUST | ||
| 562 | if ($self->{current_token}->{attributes}) { | ||
| 563 | wakaba | 1.3 | $self->{parse_error}-> (type => 'end tag attribute'); |
| 564 | wakaba | 1.1 | } |
| 565 | } else { | ||
| 566 | die "$0: $self->{current_token}->{type}: Unknown token type"; | ||
| 567 | } | ||
| 568 | $self->{state} = 'data'; | ||
| 569 | # reconsume | ||
| 570 | |||
| 571 | return ($self->{current_token}); # start tag or end tag | ||
| 572 | |||
| 573 | redo A; | ||
| 574 | } elsif ($self->{next_input_character} == 0x002F) { # / | ||
| 575 | |||
| 576 | if (@{$self->{char}}) { | ||
| 577 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 578 | } else { | ||
| 579 | $self->{set_next_input_character}->($self); | ||
| 580 | } | ||
| 581 | |||
| 582 | if ($self->{next_input_character} == 0x003E and # > | ||
| 583 | $self->{current_token}->{type} eq 'start tag' and | ||
| 584 | $permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { | ||
| 585 | # permitted slash | ||
| 586 | # | ||
| 587 | } else { | ||
| 588 | wakaba | 1.3 | $self->{parse_error}-> (type => 'nestc'); |
| 589 | wakaba | 1.1 | } |
| 590 | $self->{state} = 'before attribute name'; | ||
| 591 | # next-input-character is already done | ||
| 592 | redo A; | ||
| 593 | } else { | ||
| 594 | $self->{current_token}->{tag_name} .= chr $self->{next_input_character}; | ||
| 595 | # start tag or end tag | ||
| 596 | ## Stay in the state | ||
| 597 | |||
| 598 | if (@{$self->{char}}) { | ||
| 599 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 600 | } else { | ||
| 601 | $self->{set_next_input_character}->($self); | ||
| 602 | } | ||
| 603 | |||
| 604 | redo A; | ||
| 605 | } | ||
| 606 | } elsif ($self->{state} eq 'before attribute name') { | ||
| 607 | if ($self->{next_input_character} == 0x0009 or # HT | ||
| 608 | $self->{next_input_character} == 0x000A or # LF | ||
| 609 | $self->{next_input_character} == 0x000B or # VT | ||
| 610 | $self->{next_input_character} == 0x000C or # FF | ||
| 611 | $self->{next_input_character} == 0x0020) { # SP | ||
| 612 | ## Stay in the state | ||
| 613 | |||
| 614 | if (@{$self->{char}}) { | ||
| 615 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 616 | } else { | ||
| 617 | $self->{set_next_input_character}->($self); | ||
| 618 | } | ||
| 619 | |||
| 620 | redo A; | ||
| 621 | } elsif ($self->{next_input_character} == 0x003E) { # > | ||
| 622 | if ($self->{current_token}->{type} eq 'start tag') { | ||
| 623 | wakaba | 1.28 | $self->{current_token}->{first_start_tag} |
| 624 | = not defined $self->{last_emitted_start_tag_name}; | ||
| 625 | wakaba | 1.1 | $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 626 | } elsif ($self->{current_token}->{type} eq 'end tag') { | ||
| 627 | $self->{content_model_flag} = 'PCDATA'; # MUST | ||
| 628 | if ($self->{current_token}->{attributes}) { | ||
| 629 | wakaba | 1.3 | $self->{parse_error}-> (type => 'end tag attribute'); |
| 630 | wakaba | 1.1 | } |
| 631 | } else { | ||
| 632 | die "$0: $self->{current_token}->{type}: Unknown token type"; | ||
| 633 | } | ||
| 634 | $self->{state} = 'data'; | ||
| 635 | |||
| 636 | if (@{$self->{char}}) { | ||
| 637 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 638 | } else { | ||
| 639 | $self->{set_next_input_character}->($self); | ||
| 640 | } | ||
| 641 | |||
| 642 | |||
| 643 | return ($self->{current_token}); # start tag or end tag | ||
| 644 | |||
| 645 | redo A; | ||
| 646 | } elsif (0x0041 <= $self->{next_input_character} and | ||
| 647 | $self->{next_input_character} <= 0x005A) { # A..Z | ||
| 648 | $self->{current_attribute} = {name => chr ($self->{next_input_character} + 0x0020), | ||
| 649 | value => ''}; | ||
| 650 | $self->{state} = 'attribute name'; | ||
| 651 | |||
| 652 | if (@{$self->{char}}) { | ||
| 653 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 654 | } else { | ||
| 655 | $self->{set_next_input_character}->($self); | ||
| 656 | } | ||
| 657 | |||
| 658 | redo A; | ||
| 659 | } elsif ($self->{next_input_character} == 0x002F) { # / | ||
| 660 | |||
| 661 | if (@{$self->{char}}) { | ||
| 662 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 663 | } else { | ||
| 664 | $self->{set_next_input_character}->($self); | ||
| 665 | } | ||
| 666 | |||
| 667 | if ($self->{next_input_character} == 0x003E and # > | ||
| 668 | $self->{current_token}->{type} eq 'start tag' and | ||
| 669 | $permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { | ||
| 670 | # permitted slash | ||
| 671 | # | ||
| 672 | } else { | ||
| 673 | wakaba | 1.3 | $self->{parse_error}-> (type => 'nestc'); |
| 674 | wakaba | 1.1 | } |
| 675 | ## Stay in the state | ||
| 676 | # next-input-character is already done | ||
| 677 | redo A; | ||
| 678 | wakaba | 1.17 | } elsif ($self->{next_input_character} == -1) { |
| 679 | wakaba | 1.3 | $self->{parse_error}-> (type => 'unclosed tag'); |
| 680 | wakaba | 1.1 | if ($self->{current_token}->{type} eq 'start tag') { |
| 681 | wakaba | 1.28 | $self->{current_token}->{first_start_tag} |
| 682 | = not defined $self->{last_emitted_start_tag_name}; | ||
| 683 | wakaba | 1.1 | $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 684 | } elsif ($self->{current_token}->{type} eq 'end tag') { | ||
| 685 | $self->{content_model_flag} = 'PCDATA'; # MUST | ||
| 686 | if ($self->{current_token}->{attributes}) { | ||
| 687 | wakaba | 1.3 | $self->{parse_error}-> (type => 'end tag attribute'); |
| 688 | wakaba | 1.1 | } |
| 689 | } else { | ||
| 690 | die "$0: $self->{current_token}->{type}: Unknown token type"; | ||
| 691 | } | ||
| 692 | $self->{state} = 'data'; | ||
| 693 | # reconsume | ||
| 694 | |||
| 695 | return ($self->{current_token}); # start tag or end tag | ||
| 696 | |||
| 697 | redo A; | ||
| 698 | } else { | ||
| 699 | $self->{current_attribute} = {name => chr ($self->{next_input_character}), | ||
| 700 | value => ''}; | ||
| 701 | $self->{state} = 'attribute name'; | ||
| 702 | |||
| 703 | if (@{$self->{char}}) { | ||
| 704 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 705 | } else { | ||
| 706 | $self->{set_next_input_character}->($self); | ||
| 707 | } | ||
| 708 | |||
| 709 | redo A; | ||
| 710 | } | ||
| 711 | } elsif ($self->{state} eq 'attribute name') { | ||
| 712 | my $before_leave = sub { | ||
| 713 | if (exists $self->{current_token}->{attributes} # start tag or end tag | ||
| 714 | ->{$self->{current_attribute}->{name}}) { # MUST | ||
| 715 | wakaba | 1.3 | $self->{parse_error}-> (type => 'dupulicate attribute'); |
| 716 | wakaba | 1.1 | ## Discard $self->{current_attribute} # MUST |
| 717 | } else { | ||
| 718 | $self->{current_token}->{attributes}->{$self->{current_attribute}->{name}} | ||
| 719 | = $self->{current_attribute}; | ||
| 720 | } | ||
| 721 | }; # $before_leave | ||
| 722 | |||
| 723 | if ($self->{next_input_character} == 0x0009 or # HT | ||
| 724 | $self->{next_input_character} == 0x000A or # LF | ||
| 725 | $self->{next_input_character} == 0x000B or # VT | ||
| 726 | $self->{next_input_character} == 0x000C or # FF | ||
| 727 | $self->{next_input_character} == 0x0020) { # SP | ||
| 728 | $before_leave->(); | ||
| 729 | $self->{state} = 'after attribute name'; | ||
| 730 | |||
| 731 | if (@{$self->{char}}) { | ||
| 732 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 733 | } else { | ||
| 734 | $self->{set_next_input_character}->($self); | ||
| 735 | } | ||
| 736 | |||
| 737 | redo A; | ||
| 738 | } elsif ($self->{next_input_character} == 0x003D) { # = | ||
| 739 | $before_leave->(); | ||
| 740 | $self->{state} = 'before attribute value'; | ||
| 741 | |||
| 742 | if (@{$self->{char}}) { | ||
| 743 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 744 | } else { | ||
| 745 | $self->{set_next_input_character}->($self); | ||
| 746 | } | ||
| 747 | |||
| 748 | redo A; | ||
| 749 | } elsif ($self->{next_input_character} == 0x003E) { # > | ||
| 750 | $before_leave->(); | ||
| 751 | if ($self->{current_token}->{type} eq 'start tag') { | ||
| 752 | wakaba | 1.28 | $self->{current_token}->{first_start_tag} |
| 753 | = not defined $self->{last_emitted_start_tag_name}; | ||
| 754 | wakaba | 1.1 | $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 755 | } elsif ($self->{current_token}->{type} eq 'end tag') { | ||
| 756 | $self->{content_model_flag} = 'PCDATA'; # MUST | ||
| 757 | if ($self->{current_token}->{attributes}) { | ||
| 758 | wakaba | 1.3 | $self->{parse_error}-> (type => 'end tag attribute'); |
| 759 | wakaba | 1.1 | } |
| 760 | } else { | ||
| 761 | die "$0: $self->{current_token}->{type}: Unknown token type"; | ||
| 762 | } | ||
| 763 | $self->{state} = 'data'; | ||
| 764 | |||
| 765 | if (@{$self->{char}}) { | ||
| 766 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 767 | } else { | ||
| 768 | $self->{set_next_input_character}->($self); | ||
| 769 | } | ||
| 770 | |||
| 771 | |||
| 772 | return ($self->{current_token}); # start tag or end tag | ||
| 773 | |||
| 774 | redo A; | ||
| 775 | } elsif (0x0041 <= $self->{next_input_character} and | ||
| 776 | $self->{next_input_character} <= 0x005A) { # A..Z | ||
| 777 | $self->{current_attribute}->{name} .= chr ($self->{next_input_character} + 0x0020); | ||
| 778 | ## Stay in the state | ||
| 779 | |||
| 780 | if (@{$self->{char}}) { | ||
| 781 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 782 | } else { | ||
| 783 | $self->{set_next_input_character}->($self); | ||
| 784 | } | ||
| 785 | |||
| 786 | redo A; | ||
| 787 | } elsif ($self->{next_input_character} == 0x002F) { # / | ||
| 788 | $before_leave->(); | ||
| 789 | |||
| 790 | if (@{$self->{char}}) { | ||
| 791 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 792 | } else { | ||
| 793 | $self->{set_next_input_character}->($self); | ||
| 794 | } | ||
| 795 | |||
| 796 | if ($self->{next_input_character} == 0x003E and # > | ||
| 797 | $self->{current_token}->{type} eq 'start tag' and | ||
| 798 | $permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { | ||
| 799 | # permitted slash | ||
| 800 | # | ||
| 801 | } else { | ||
| 802 | wakaba | 1.3 | $self->{parse_error}-> (type => 'nestc'); |
| 803 | wakaba | 1.1 | } |
| 804 | $self->{state} = 'before attribute name'; | ||
| 805 | # next-input-character is already done | ||
| 806 | redo A; | ||
| 807 | wakaba | 1.17 | } elsif ($self->{next_input_character} == -1) { |
| 808 | wakaba | 1.3 | $self->{parse_error}-> (type => 'unclosed tag'); |
| 809 | wakaba | 1.1 | $before_leave->(); |
| 810 | if ($self->{current_token}->{type} eq 'start tag') { | ||
| 811 | wakaba | 1.28 | $self->{current_token}->{first_start_tag} |
| 812 | = not defined $self->{last_emitted_start_tag_name}; | ||
| 813 | wakaba | 1.1 | $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 814 | } elsif ($self->{current_token}->{type} eq 'end tag') { | ||
| 815 | $self->{content_model_flag} = 'PCDATA'; # MUST | ||
| 816 | if ($self->{current_token}->{attributes}) { | ||
| 817 | wakaba | 1.3 | $self->{parse_error}-> (type => 'end tag attribute'); |
| 818 | wakaba | 1.1 | } |
| 819 | } else { | ||
| 820 | die "$0: $self->{current_token}->{type}: Unknown token type"; | ||
| 821 | } | ||
| 822 | $self->{state} = 'data'; | ||
| 823 | # reconsume | ||
| 824 | |||
| 825 | return ($self->{current_token}); # start tag or end tag | ||
| 826 | |||
| 827 | redo A; | ||
| 828 | } else { | ||
| 829 | $self->{current_attribute}->{name} .= chr ($self->{next_input_character}); | ||
| 830 | ## Stay in the state | ||
| 831 | |||
| 832 | if (@{$self->{char}}) { | ||
| 833 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 834 | } else { | ||
| 835 | $self->{set_next_input_character}->($self); | ||
| 836 | } | ||
| 837 | |||
| 838 | redo A; | ||
| 839 | } | ||
| 840 | } elsif ($self->{state} eq 'after attribute name') { | ||
| 841 | if ($self->{next_input_character} == 0x0009 or # HT | ||
| 842 | $self->{next_input_character} == 0x000A or # LF | ||
| 843 | $self->{next_input_character} == 0x000B or # VT | ||
| 844 | $self->{next_input_character} == 0x000C or # FF | ||
| 845 | $self->{next_input_character} == 0x0020) { # SP | ||
| 846 | ## Stay in the state | ||
| 847 | |||
| 848 | if (@{$self->{char}}) { | ||
| 849 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 850 | } else { | ||
| 851 | $self->{set_next_input_character}->($self); | ||
| 852 | } | ||
| 853 | |||
| 854 | redo A; | ||
| 855 | } elsif ($self->{next_input_character} == 0x003D) { # = | ||
| 856 | $self->{state} = 'before attribute value'; | ||
| 857 | |||
| 858 | if (@{$self->{char}}) { | ||
| 859 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 860 | } else { | ||
| 861 | $self->{set_next_input_character}->($self); | ||
| 862 | } | ||
| 863 | |||
| 864 | redo A; | ||
| 865 | } elsif ($self->{next_input_character} == 0x003E) { # > | ||
| 866 | if ($self->{current_token}->{type} eq 'start tag') { | ||
| 867 | wakaba | 1.28 | $self->{current_token}->{first_start_tag} |
| 868 | = not defined $self->{last_emitted_start_tag_name}; | ||
| 869 | wakaba | 1.1 | $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 870 | } elsif ($self->{current_token}->{type} eq 'end tag') { | ||
| 871 | $self->{content_model_flag} = 'PCDATA'; # MUST | ||
| 872 | if ($self->{current_token}->{attributes}) { | ||
| 873 | wakaba | 1.3 | $self->{parse_error}-> (type => 'end tag attribute'); |
| 874 | wakaba | 1.1 | } |
| 875 | } else { | ||
| 876 | die "$0: $self->{current_token}->{type}: Unknown token type"; | ||
| 877 | } | ||
| 878 | $self->{state} = 'data'; | ||
| 879 | |||
| 880 | if (@{$self->{char}}) { | ||
| 881 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 882 | } else { | ||
| 883 | $self->{set_next_input_character}->($self); | ||
| 884 | } | ||
| 885 | |||
| 886 | |||
| 887 | return ($self->{current_token}); # start tag or end tag | ||
| 888 | |||
| 889 | redo A; | ||
| 890 | } elsif (0x0041 <= $self->{next_input_character} and | ||
| 891 | $self->{next_input_character} <= 0x005A) { # A..Z | ||
| 892 | $self->{current_attribute} = {name => chr ($self->{next_input_character} + 0x0020), | ||
| 893 | value => ''}; | ||
| 894 | $self->{state} = 'attribute name'; | ||
| 895 | |||
| 896 | if (@{$self->{char}}) { | ||
| 897 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 898 | } else { | ||
| 899 | $self->{set_next_input_character}->($self); | ||
| 900 | } | ||
| 901 | |||
| 902 | redo A; | ||
| 903 | } elsif ($self->{next_input_character} == 0x002F) { # / | ||
| 904 | |||
| 905 | if (@{$self->{char}}) { | ||
| 906 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 907 | } else { | ||
| 908 | $self->{set_next_input_character}->($self); | ||
| 909 | } | ||
| 910 | |||
| 911 | if ($self->{next_input_character} == 0x003E and # > | ||
| 912 | $self->{current_token}->{type} eq 'start tag' and | ||
| 913 | $permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { | ||
| 914 | # permitted slash | ||
| 915 | # | ||
| 916 | } else { | ||
| 917 | wakaba | 1.3 | $self->{parse_error}-> (type => 'nestc'); |
| 918 | wakaba | 1.33 | ## TODO: Different error type for <aa / bb> than <aa/> |
| 919 | wakaba | 1.1 | } |
| 920 | $self->{state} = 'before attribute name'; | ||
| 921 | # next-input-character is already done | ||
| 922 | redo A; | ||
| 923 | wakaba | 1.17 | } elsif ($self->{next_input_character} == -1) { |
| 924 | wakaba | 1.3 | $self->{parse_error}-> (type => 'unclosed tag'); |
| 925 | wakaba | 1.1 | if ($self->{current_token}->{type} eq 'start tag') { |
| 926 | wakaba | 1.28 | $self->{current_token}->{first_start_tag} |
| 927 | = not defined $self->{last_emitted_start_tag_name}; | ||
| 928 | wakaba | 1.1 | $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 929 | } elsif ($self->{current_token}->{type} eq 'end tag') { | ||
| 930 | $self->{content_model_flag} = 'PCDATA'; # MUST | ||
| 931 | if ($self->{current_token}->{attributes}) { | ||
| 932 | wakaba | 1.3 | $self->{parse_error}-> (type => 'end tag attribute'); |
| 933 | wakaba | 1.1 | } |
| 934 | } else { | ||
| 935 | die "$0: $self->{current_token}->{type}: Unknown token type"; | ||
| 936 | } | ||
| 937 | $self->{state} = 'data'; | ||
| 938 | # reconsume | ||
| 939 | |||
| 940 | return ($self->{current_token}); # start tag or end tag | ||
| 941 | |||
| 942 | redo A; | ||
| 943 | } else { | ||
| 944 | $self->{current_attribute} = {name => chr ($self->{next_input_character}), | ||
| 945 | value => ''}; | ||
| 946 | $self->{state} = 'attribute name'; | ||
| 947 | |||
| 948 | if (@{$self->{char}}) { | ||
| 949 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 950 | } else { | ||
| 951 | $self->{set_next_input_character}->($self); | ||
| 952 | } | ||
| 953 | |||
| 954 | redo A; | ||
| 955 | } | ||
| 956 | } elsif ($self->{state} eq 'before attribute value') { | ||
| 957 | if ($self->{next_input_character} == 0x0009 or # HT | ||
| 958 | $self->{next_input_character} == 0x000A or # LF | ||
| 959 | $self->{next_input_character} == 0x000B or # VT | ||
| 960 | $self->{next_input_character} == 0x000C or # FF | ||
| 961 | $self->{next_input_character} == 0x0020) { # SP | ||
| 962 | ## Stay in the state | ||
| 963 | |||
| 964 | if (@{$self->{char}}) { | ||
| 965 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 966 | } else { | ||
| 967 | $self->{set_next_input_character}->($self); | ||
| 968 | } | ||
| 969 | |||
| 970 | redo A; | ||
| 971 | } elsif ($self->{next_input_character} == 0x0022) { # " | ||
| 972 | $self->{state} = 'attribute value (double-quoted)'; | ||
| 973 | |||
| 974 | if (@{$self->{char}}) { | ||
| 975 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 976 | } else { | ||
| 977 | $self->{set_next_input_character}->($self); | ||
| 978 | } | ||
| 979 | |||
| 980 | redo A; | ||
| 981 | } elsif ($self->{next_input_character} == 0x0026) { # & | ||
| 982 | $self->{state} = 'attribute value (unquoted)'; | ||
| 983 | ## reconsume | ||
| 984 | redo A; | ||
| 985 | } elsif ($self->{next_input_character} == 0x0027) { # ' | ||
| 986 | $self->{state} = 'attribute value (single-quoted)'; | ||
| 987 | |||
| 988 | if (@{$self->{char}}) { | ||
| 989 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 990 | } else { | ||
| 991 | $self->{set_next_input_character}->($self); | ||
| 992 | } | ||
| 993 | |||
| 994 | redo A; | ||
| 995 | } elsif ($self->{next_input_character} == 0x003E) { # > | ||
| 996 | if ($self->{current_token}->{type} eq 'start tag') { | ||
| 997 | wakaba | 1.28 | $self->{current_token}->{first_start_tag} |
| 998 | = not defined $self->{last_emitted_start_tag_name}; | ||
| 999 | wakaba | 1.1 | $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1000 | } elsif ($self->{current_token}->{type} eq 'end tag') { | ||
| 1001 | $self->{content_model_flag} = 'PCDATA'; # MUST | ||
| 1002 | if ($self->{current_token}->{attributes}) { | ||
| 1003 | wakaba | 1.3 | $self->{parse_error}-> (type => 'end tag attribute'); |
| 1004 | wakaba | 1.1 | } |
| 1005 | } else { | ||
| 1006 | die "$0: $self->{current_token}->{type}: Unknown token type"; | ||
| 1007 | } | ||
| 1008 | $self->{state} = 'data'; | ||
| 1009 | |||
| 1010 | if (@{$self->{char}}) { | ||
| 1011 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1012 | } else { | ||
| 1013 | $self->{set_next_input_character}->($self); | ||
| 1014 | } | ||
| 1015 | |||
| 1016 | |||
| 1017 | return ($self->{current_token}); # start tag or end tag | ||
| 1018 | |||
| 1019 | redo A; | ||
| 1020 | wakaba | 1.17 | } elsif ($self->{next_input_character} == -1) { |
| 1021 | wakaba | 1.3 | $self->{parse_error}-> (type => 'unclosed tag'); |
| 1022 | wakaba | 1.1 | if ($self->{current_token}->{type} eq 'start tag') { |
| 1023 | wakaba | 1.28 | $self->{current_token}->{first_start_tag} |
| 1024 | = not defined $self->{last_emitted_start_tag_name}; | ||
| 1025 | wakaba | 1.1 | $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1026 | } elsif ($self->{current_token}->{type} eq 'end tag') { | ||
| 1027 | $self->{content_model_flag} = 'PCDATA'; # MUST | ||
| 1028 | if ($self->{current_token}->{attributes}) { | ||
| 1029 | wakaba | 1.3 | $self->{parse_error}-> (type => 'end tag attribute'); |
| 1030 | wakaba | 1.1 | } |
| 1031 | } else { | ||
| 1032 | die "$0: $self->{current_token}->{type}: Unknown token type"; | ||
| 1033 | } | ||
| 1034 | $self->{state} = 'data'; | ||
| 1035 | ## reconsume | ||
| 1036 | |||
| 1037 | return ($self->{current_token}); # start tag or end tag | ||
| 1038 | |||
| 1039 | redo A; | ||
| 1040 | } else { | ||
| 1041 | $self->{current_attribute}->{value} .= chr ($self->{next_input_character}); | ||
| 1042 | $self->{state} = 'attribute value (unquoted)'; | ||
| 1043 | |||
| 1044 | if (@{$self->{char}}) { | ||
| 1045 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1046 | } else { | ||
| 1047 | $self->{set_next_input_character}->($self); | ||
| 1048 | } | ||
| 1049 | |||
| 1050 | redo A; | ||
| 1051 | } | ||
| 1052 | } elsif ($self->{state} eq 'attribute value (double-quoted)') { | ||
| 1053 | if ($self->{next_input_character} == 0x0022) { # " | ||
| 1054 | $self->{state} = 'before attribute name'; | ||
| 1055 | |||
| 1056 | if (@{$self->{char}}) { | ||
| 1057 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1058 | } else { | ||
| 1059 | $self->{set_next_input_character}->($self); | ||
| 1060 | } | ||
| 1061 | |||
| 1062 | redo A; | ||
| 1063 | } elsif ($self->{next_input_character} == 0x0026) { # & | ||
| 1064 | $self->{last_attribute_value_state} = 'attribute value (double-quoted)'; | ||
| 1065 | $self->{state} = 'entity in attribute value'; | ||
| 1066 | |||
| 1067 | if (@{$self->{char}}) { | ||
| 1068 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1069 | } else { | ||
| 1070 | $self->{set_next_input_character}->($self); | ||
| 1071 | } | ||
| 1072 | |||
| 1073 | redo A; | ||
| 1074 | } elsif ($self->{next_input_character} == -1) { | ||
| 1075 | wakaba | 1.3 | $self->{parse_error}-> (type => 'unclosed attribute value'); |
| 1076 | wakaba | 1.1 | if ($self->{current_token}->{type} eq 'start tag') { |
| 1077 | wakaba | 1.28 | $self->{current_token}->{first_start_tag} |
| 1078 | = not defined $self->{last_emitted_start_tag_name}; | ||
| 1079 | wakaba | 1.1 | $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1080 | } elsif ($self->{current_token}->{type} eq 'end tag') { | ||
| 1081 | $self->{content_model_flag} = 'PCDATA'; # MUST | ||
| 1082 | if ($self->{current_token}->{attributes}) { | ||
| 1083 | wakaba | 1.3 | $self->{parse_error}-> (type => 'end tag attribute'); |
| 1084 | wakaba | 1.1 | } |
| 1085 | } else { | ||
| 1086 | die "$0: $self->{current_token}->{type}: Unknown token type"; | ||
| 1087 | } | ||
| 1088 | $self->{state} = 'data'; | ||
| 1089 | ## reconsume | ||
| 1090 | |||
| 1091 | return ($self->{current_token}); # start tag or end tag | ||
| 1092 | |||
| 1093 | redo A; | ||
| 1094 | } else { | ||
| 1095 | $self->{current_attribute}->{value} .= chr ($self->{next_input_character}); | ||
| 1096 | ## Stay in the state | ||
| 1097 | |||
| 1098 | if (@{$self->{char}}) { | ||
| 1099 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1100 | } else { | ||
| 1101 | $self->{set_next_input_character}->($self); | ||
| 1102 | } | ||
| 1103 | |||
| 1104 | redo A; | ||
| 1105 | } | ||
| 1106 | } elsif ($self->{state} eq 'attribute value (single-quoted)') { | ||
| 1107 | if ($self->{next_input_character} == 0x0027) { # ' | ||
| 1108 | $self->{state} = 'before attribute name'; | ||
| 1109 | |||
| 1110 | if (@{$self->{char}}) { | ||
| 1111 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1112 | } else { | ||
| 1113 | $self->{set_next_input_character}->($self); | ||
| 1114 | } | ||
| 1115 | |||
| 1116 | redo A; | ||
| 1117 | } elsif ($self->{next_input_character} == 0x0026) { # & | ||
| 1118 | $self->{last_attribute_value_state} = 'attribute value (single-quoted)'; | ||
| 1119 | $self->{state} = 'entity in attribute value'; | ||
| 1120 | |||
| 1121 | if (@{$self->{char}}) { | ||
| 1122 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1123 | } else { | ||
| 1124 | $self->{set_next_input_character}->($self); | ||
| 1125 | } | ||
| 1126 | |||
| 1127 | redo A; | ||
| 1128 | } elsif ($self->{next_input_character} == -1) { | ||
| 1129 | wakaba | 1.3 | $self->{parse_error}-> (type => 'unclosed attribute value'); |
| 1130 | wakaba | 1.1 | if ($self->{current_token}->{type} eq 'start tag') { |
| 1131 | wakaba | 1.28 | $self->{current_token}->{first_start_tag} |
| 1132 | = not defined $self->{last_emitted_start_tag_name}; | ||
| 1133 | wakaba | 1.1 | $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1134 | } elsif ($self->{current_token}->{type} eq 'end tag') { | ||
| 1135 | $self->{content_model_flag} = 'PCDATA'; # MUST | ||
| 1136 | if ($self->{current_token}->{attributes}) { | ||
| 1137 | wakaba | 1.3 | $self->{parse_error}-> (type => 'end tag attribute'); |
| 1138 | wakaba | 1.1 | } |
| 1139 | } else { | ||
| 1140 | die "$0: $self->{current_token}->{type}: Unknown token type"; | ||
| 1141 | } | ||
| 1142 | $self->{state} = 'data'; | ||
| 1143 | ## reconsume | ||
| 1144 | |||
| 1145 | return ($self->{current_token}); # start tag or end tag | ||
| 1146 | |||
| 1147 | redo A; | ||
| 1148 | } else { | ||
| 1149 | $self->{current_attribute}->{value} .= chr ($self->{next_input_character}); | ||
| 1150 | ## Stay in the state | ||
| 1151 | |||
| 1152 | if (@{$self->{char}}) { | ||
| 1153 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1154 | } else { | ||
| 1155 | $self->{set_next_input_character}->($self); | ||
| 1156 | } | ||
| 1157 | |||
| 1158 | redo A; | ||
| 1159 | } | ||
| 1160 | } elsif ($self->{state} eq 'attribute value (unquoted)') { | ||
| 1161 | if ($self->{next_input_character} == 0x0009 or # HT | ||
| 1162 | $self->{next_input_character} == 0x000A or # LF | ||
| 1163 | $self->{next_input_character} == 0x000B or # HT | ||
| 1164 | $self->{next_input_character} == 0x000C or # FF | ||
| 1165 | $self->{next_input_character} == 0x0020) { # SP | ||
| 1166 | $self->{state} = 'before attribute name'; | ||
| 1167 | |||
| 1168 | if (@{$self->{char}}) { | ||
| 1169 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1170 | } else { | ||
| 1171 | $self->{set_next_input_character}->($self); | ||
| 1172 | } | ||
| 1173 | |||
| 1174 | redo A; | ||
| 1175 | } elsif ($self->{next_input_character} == 0x0026) { # & | ||
| 1176 | $self->{last_attribute_value_state} = 'attribute value (unquoted)'; | ||
| 1177 | $self->{state} = 'entity in attribute value'; | ||
| 1178 | |||
| 1179 | if (@{$self->{char}}) { | ||
| 1180 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1181 | } else { | ||
| 1182 | $self->{set_next_input_character}->($self); | ||
| 1183 | } | ||
| 1184 | |||
| 1185 | redo A; | ||
| 1186 | } elsif ($self->{next_input_character} == 0x003E) { # > | ||
| 1187 | if ($self->{current_token}->{type} eq 'start tag') { | ||
| 1188 | wakaba | 1.28 | $self->{current_token}->{first_start_tag} |
| 1189 | = not defined $self->{last_emitted_start_tag_name}; | ||
| 1190 | wakaba | 1.1 | $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1191 | } elsif ($self->{current_token}->{type} eq 'end tag') { | ||
| 1192 | $self->{content_model_flag} = 'PCDATA'; # MUST | ||
| 1193 | if ($self->{current_token}->{attributes}) { | ||
| 1194 | wakaba | 1.3 | $self->{parse_error}-> (type => 'end tag attribute'); |
| 1195 | wakaba | 1.1 | } |
| 1196 | } else { | ||
| 1197 | die "$0: $self->{current_token}->{type}: Unknown token type"; | ||
| 1198 | } | ||
| 1199 | $self->{state} = 'data'; | ||
| 1200 | |||
| 1201 | if (@{$self->{char}}) { | ||
| 1202 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1203 | } else { | ||
| 1204 | $self->{set_next_input_character}->($self); | ||
| 1205 | } | ||
| 1206 | |||
| 1207 | |||
| 1208 | return ($self->{current_token}); # start tag or end tag | ||
| 1209 | |||
| 1210 | redo A; | ||
| 1211 | wakaba | 1.17 | } elsif ($self->{next_input_character} == -1) { |
| 1212 | wakaba | 1.3 | $self->{parse_error}-> (type => 'unclosed tag'); |
| 1213 | wakaba | 1.1 | if ($self->{current_token}->{type} eq 'start tag') { |
| 1214 | wakaba | 1.28 | $self->{current_token}->{first_start_tag} |
| 1215 | = not defined $self->{last_emitted_start_tag_name}; | ||
| 1216 | wakaba | 1.1 | $self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1217 | } elsif ($self->{current_token}->{type} eq 'end tag') { | ||
| 1218 | $self->{content_model_flag} = 'PCDATA'; # MUST | ||
| 1219 | if ($self->{current_token}->{attributes}) { | ||
| 1220 | wakaba | 1.3 | $self->{parse_error}-> (type => 'end tag attribute'); |
| 1221 | wakaba | 1.1 | } |
| 1222 | } else { | ||
| 1223 | die "$0: $self->{current_token}->{type}: Unknown token type"; | ||
| 1224 | } | ||
| 1225 | $self->{state} = 'data'; | ||
| 1226 | ## reconsume | ||
| 1227 | |||
| 1228 | return ($self->{current_token}); # start tag or end tag | ||
| 1229 | |||
| 1230 | redo A; | ||
| 1231 | } else { | ||
| 1232 | $self->{current_attribute}->{value} .= chr ($self->{next_input_character}); | ||
| 1233 | ## Stay in the state | ||
| 1234 | |||
| 1235 | if (@{$self->{char}}) { | ||
| 1236 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1237 | } else { | ||
| 1238 | $self->{set_next_input_character}->($self); | ||
| 1239 | } | ||
| 1240 | |||
| 1241 | redo A; | ||
| 1242 | } | ||
| 1243 | } elsif ($self->{state} eq 'entity in attribute value') { | ||
| 1244 | wakaba | 1.26 | my $token = $self->_tokenize_attempt_to_consume_an_entity (1); |
| 1245 | wakaba | 1.1 | |
| 1246 | unless (defined $token) { | ||
| 1247 | $self->{current_attribute}->{value} .= '&'; | ||
| 1248 | } else { | ||
| 1249 | $self->{current_attribute}->{value} .= $token->{data}; | ||
| 1250 | ## ISSUE: spec says "append the returned character token to the current attribute's value" | ||
| 1251 | } | ||
| 1252 | |||
| 1253 | $self->{state} = $self->{last_attribute_value_state}; | ||
| 1254 | # next-input-character is already done | ||
| 1255 | redo A; | ||
| 1256 | } elsif ($self->{state} eq 'bogus comment') { | ||
| 1257 | ## (only happen if PCDATA state) | ||
| 1258 | |||
| 1259 | my $token = {type => 'comment', data => ''}; | ||
| 1260 | |||
| 1261 | BC: { | ||
| 1262 | if ($self->{next_input_character} == 0x003E) { # > | ||
| 1263 | $self->{state} = 'data'; | ||
| 1264 | |||
| 1265 | if (@{$self->{char}}) { | ||
| 1266 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1267 | } else { | ||
| 1268 | $self->{set_next_input_character}->($self); | ||
| 1269 | } | ||
| 1270 | |||
| 1271 | |||
| 1272 | return ($token); | ||
| 1273 | |||
| 1274 | redo A; | ||
| 1275 | } elsif ($self->{next_input_character} == -1) { | ||
| 1276 | $self->{state} = 'data'; | ||
| 1277 | ## reconsume | ||
| 1278 | |||
| 1279 | return ($token); | ||
| 1280 | |||
| 1281 | redo A; | ||
| 1282 | } else { | ||
| 1283 | $token->{data} .= chr ($self->{next_input_character}); | ||
| 1284 | |||
| 1285 | if (@{$self->{char}}) { | ||
| 1286 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1287 | } else { | ||
| 1288 | $self->{set_next_input_character}->($self); | ||
| 1289 | } | ||
| 1290 | |||
| 1291 | redo BC; | ||
| 1292 | } | ||
| 1293 | } # BC | ||
| 1294 | } elsif ($self->{state} eq 'markup declaration open') { | ||
| 1295 | ## (only happen if PCDATA state) | ||
| 1296 | |||
| 1297 | my @next_char; | ||
| 1298 | push @next_char, $self->{next_input_character}; | ||
| 1299 | |||
| 1300 | if ($self->{next_input_character} == 0x002D) { # - | ||
| 1301 | |||
| 1302 | if (@{$self->{char}}) { | ||
| 1303 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1304 | } else { | ||
| 1305 | $self->{set_next_input_character}->($self); | ||
| 1306 | } | ||
| 1307 | |||
| 1308 | push @next_char, $self->{next_input_character}; | ||
| 1309 | if ($self->{next_input_character} == 0x002D) { # - | ||
| 1310 | $self->{current_token} = {type => 'comment', data => ''}; | ||
| 1311 | wakaba | 1.23 | $self->{state} = 'comment start'; |
| 1312 | wakaba | 1.1 | |
| 1313 | if (@{$self->{char}}) { | ||
| 1314 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1315 | } else { | ||
| 1316 | $self->{set_next_input_character}->($self); | ||
| 1317 | } | ||
| 1318 | |||
| 1319 | redo A; | ||
| 1320 | } | ||
| 1321 | } elsif ($self->{next_input_character} == 0x0044 or # D | ||
| 1322 | $self->{next_input_character} == 0x0064) { # d | ||
| 1323 | |||
| 1324 | if (@{$self->{char}}) { | ||
| 1325 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1326 | } else { | ||
| 1327 | $self->{set_next_input_character}->($self); | ||
| 1328 | } | ||
| 1329 | |||
| 1330 | push @next_char, $self->{next_input_character}; | ||
| 1331 | if ($self->{next_input_character} == 0x004F or # O | ||
| 1332 | $self->{next_input_character} == 0x006F) { # o | ||
| 1333 | |||
| 1334 | if (@{$self->{char}}) { | ||
| 1335 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1336 | } else { | ||
| 1337 | $self->{set_next_input_character}->($self); | ||
| 1338 | } | ||
| 1339 | |||
| 1340 | push @next_char, $self->{next_input_character}; | ||
| 1341 | if ($self->{next_input_character} == 0x0043 or # C | ||
| 1342 | $self->{next_input_character} == 0x0063) { # c | ||
| 1343 | |||
| 1344 | if (@{$self->{char}}) { | ||
| 1345 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1346 | } else { | ||
| 1347 | $self->{set_next_input_character}->($self); | ||
| 1348 | } | ||
| 1349 | |||
| 1350 | push @next_char, $self->{next_input_character}; | ||
| 1351 | if ($self->{next_input_character} == 0x0054 or # T | ||
| 1352 | $self->{next_input_character} == 0x0074) { # t | ||
| 1353 | |||
| 1354 | if (@{$self->{char}}) { | ||
| 1355 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1356 | } else { | ||
| 1357 | $self->{set_next_input_character}->($self); | ||
| 1358 | } | ||
| 1359 | |||
| 1360 | push @next_char, $self->{next_input_character}; | ||
| 1361 | if ($self->{next_input_character} == 0x0059 or # Y | ||
| 1362 | $self->{next_input_character} == 0x0079) { # y | ||
| 1363 | |||
| 1364 | if (@{$self->{char}}) { | ||
| 1365 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1366 | } else { | ||
| 1367 | $self->{set_next_input_character}->($self); | ||
| 1368 | } | ||
| 1369 | |||
| 1370 | push @next_char, $self->{next_input_character}; | ||
| 1371 | if ($self->{next_input_character} == 0x0050 or # P | ||
| 1372 | $self->{next_input_character} == 0x0070) { # p | ||
| 1373 | |||
| 1374 | if (@{$self->{char}}) { | ||
| 1375 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1376 | } else { | ||
| 1377 | $self->{set_next_input_character}->($self); | ||
| 1378 | } | ||
| 1379 | |||
| 1380 | push @next_char, $self->{next_input_character}; | ||
| 1381 | if ($self->{next_input_character} == 0x0045 or # E | ||
| 1382 | $self->{next_input_character} == 0x0065) { # e | ||
| 1383 | ## ISSUE: What a stupid code this is! | ||
| 1384 | $self->{state} = 'DOCTYPE'; | ||
| 1385 | |||
| 1386 | if (@{$self->{char}}) { | ||
| 1387 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1388 | } else { | ||
| 1389 | $self->{set_next_input_character}->($self); | ||
| 1390 | } | ||
| 1391 | |||
| 1392 | redo A; | ||
| 1393 | } | ||
| 1394 | } | ||
| 1395 | } | ||
| 1396 | } | ||
| 1397 | } | ||
| 1398 | } | ||
| 1399 | } | ||
| 1400 | |||
| 1401 | wakaba | 1.30 | $self->{parse_error}-> (type => 'bogus comment'); |
| 1402 | wakaba | 1.1 | $self->{next_input_character} = shift @next_char; |
| 1403 | unshift @{$self->{char}}, (@next_char); | ||
| 1404 | $self->{state} = 'bogus comment'; | ||
| 1405 | redo A; | ||
| 1406 | |||
| 1407 | ## ISSUE: typos in spec: chacacters, is is a parse error | ||
| 1408 | ## ISSUE: spec is somewhat unclear on "is the first character that will be in the comment"; what is "that will be in the comment" is what the algorithm defines, isn't it? | ||
| 1409 | wakaba | 1.23 | } elsif ($self->{state} eq 'comment start') { |
| 1410 | if ($self->{next_input_character} == 0x002D) { # - | ||
| 1411 | $self->{state} = 'comment start dash'; | ||
| 1412 | |||
| 1413 | if (@{$self->{char}}) { | ||
| 1414 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1415 | } else { | ||
| 1416 | $self->{set_next_input_character}->($self); | ||
| 1417 | } | ||
| 1418 | |||
| 1419 | redo A; | ||
| 1420 | } elsif ($self->{next_input_character} == 0x003E) { # > | ||
| 1421 | $self->{parse_error}-> (type => 'bogus comment'); | ||
| 1422 | $self->{state} = 'data'; | ||
| 1423 | |||
| 1424 | if (@{$self->{char}}) { | ||
| 1425 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1426 | } else { | ||
| 1427 | $self->{set_next_input_character}->($self); | ||
| 1428 | } | ||
| 1429 | |||
| 1430 | |||
| 1431 | return ($self->{current_token}); # comment | ||
| 1432 | |||
| 1433 | redo A; | ||
| 1434 | } elsif ($self->{next_input_character} == -1) { | ||
| 1435 | $self->{parse_error}-> (type => 'unclosed comment'); | ||
| 1436 | $self->{state} = 'data'; | ||
| 1437 | ## reconsume | ||
| 1438 | |||
| 1439 | return ($self->{current_token}); # comment | ||
| 1440 | |||
| 1441 | redo A; | ||
| 1442 | } else { | ||
| 1443 | $self->{current_token}->{data} # comment | ||
| 1444 | .= chr ($self->{next_input_character}); | ||
| 1445 | $self->{state} = 'comment'; | ||
| 1446 | |||
| 1447 | if (@{$self->{char}}) { | ||
| 1448 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1449 | } else { | ||
| 1450 | $self->{set_next_input_character}->($self); | ||
| 1451 | } | ||
| 1452 | |||
| 1453 | redo A; | ||
| 1454 | } | ||
| 1455 | } elsif ($self->{state} eq 'comment start dash') { | ||
| 1456 | if ($self->{next_input_character} == 0x002D) { # - | ||
| 1457 | $self->{state} = 'comment end'; | ||
| 1458 | |||
| 1459 | if (@{$self->{char}}) { | ||
| 1460 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1461 | } else { | ||
| 1462 | $self->{set_next_input_character}->($self); | ||
| 1463 | } | ||
| 1464 | |||
| 1465 | redo A; | ||
| 1466 | } elsif ($self->{next_input_character} == 0x003E) { # > | ||
| 1467 | $self->{parse_error}-> (type => 'bogus comment'); | ||
| 1468 | $self->{state} = 'data'; | ||
| 1469 | |||
| 1470 | if (@{$self->{char}}) { | ||
| 1471 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1472 | } else { | ||
| 1473 | $self->{set_next_input_character}->($self); | ||
| 1474 | } | ||
| 1475 | |||
| 1476 | |||
| 1477 | return ($self->{current_token}); # comment | ||
| 1478 | |||
| 1479 | redo A; | ||
| 1480 | } elsif ($self->{next_input_character} == -1) { | ||
| 1481 | $self->{parse_error}-> (type => 'unclosed comment'); | ||
| 1482 | $self->{state} = 'data'; | ||
| 1483 | ## reconsume | ||
| 1484 | |||
| 1485 | return ($self->{current_token}); # comment | ||
| 1486 | |||
| 1487 | redo A; | ||
| 1488 | } else { | ||
| 1489 | $self->{current_token}->{data} # comment | ||
| 1490 | wakaba | 1.33 | .= '-' . chr ($self->{next_input_character}); |
| 1491 | wakaba | 1.23 | $self->{state} = 'comment'; |
| 1492 | |||
| 1493 | if (@{$self->{char}}) { | ||
| 1494 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1495 | } else { | ||
| 1496 | $self->{set_next_input_character}->($self); | ||
| 1497 | } | ||
| 1498 | |||
| 1499 | redo A; | ||
| 1500 | } | ||
| 1501 | wakaba | 1.1 | } elsif ($self->{state} eq 'comment') { |
| 1502 | if ($self->{next_input_character} == 0x002D) { # - | ||
| 1503 | wakaba | 1.23 | $self->{state} = 'comment end dash'; |
| 1504 | wakaba | 1.1 | |
| 1505 | if (@{$self->{char}}) { | ||
| 1506 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1507 | } else { | ||
| 1508 | $self->{set_next_input_character}->($self); | ||
| 1509 | } | ||
| 1510 | |||
| 1511 | redo A; | ||
| 1512 | } elsif ($self->{next_input_character} == -1) { | ||
| 1513 | wakaba | 1.3 | $self->{parse_error}-> (type => 'unclosed comment'); |
| 1514 | wakaba | 1.1 | $self->{state} = 'data'; |
| 1515 | ## reconsume | ||
| 1516 | |||
| 1517 | return ($self->{current_token}); # comment | ||
| 1518 | |||
| 1519 | redo A; | ||
| 1520 | } else { | ||
| 1521 | $self->{current_token}->{data} .= chr ($self->{next_input_character}); # comment | ||
| 1522 | ## Stay in the state | ||
| 1523 | |||
| 1524 | if (@{$self->{char}}) { | ||
| 1525 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1526 | } else { | ||
| 1527 | $self->{set_next_input_character}->($self); | ||
| 1528 | } | ||
| 1529 | |||
| 1530 | redo A; | ||
| 1531 | } | ||
| 1532 | wakaba | 1.23 | } elsif ($self->{state} eq 'comment end dash') { |
| 1533 | wakaba | 1.1 | if ($self->{next_input_character} == 0x002D) { # - |
| 1534 | $self->{state} = 'comment end'; | ||
| 1535 | |||
| 1536 | if (@{$self->{char}}) { | ||
| 1537 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1538 | } else { | ||
| 1539 | $self->{set_next_input_character}->($self); | ||
| 1540 | } | ||
| 1541 | |||
| 1542 | redo A; | ||
| 1543 | } elsif ($self->{next_input_character} == -1) { | ||
| 1544 | wakaba | 1.3 | $self->{parse_error}-> (type => 'unclosed comment'); |
| 1545 | wakaba | 1.1 | $self->{state} = 'data'; |
| 1546 | ## reconsume | ||
| 1547 | |||
| 1548 | return ($self->{current_token}); # comment | ||
| 1549 | |||
| 1550 | redo A; | ||
| 1551 | } else { | ||
| 1552 | $self->{current_token}->{data} .= '-' . chr ($self->{next_input_character}); # comment | ||
| 1553 | $self->{state} = 'comment'; | ||
| 1554 | |||
| 1555 | if (@{$self->{char}}) { | ||
| 1556 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1557 | } else { | ||
| 1558 | $self->{set_next_input_character}->($self); | ||
| 1559 | } | ||
| 1560 | |||
| 1561 | redo A; | ||
| 1562 | } | ||
| 1563 | } elsif ($self->{state} eq 'comment end') { | ||
| 1564 | if ($self->{next_input_character} == 0x003E) { # > | ||
| 1565 | $self->{state} = 'data'; | ||
| 1566 | |||
| 1567 | if (@{$self->{char}}) { | ||
| 1568 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1569 | } else { | ||
| 1570 | $self->{set_next_input_character}->($self); | ||
| 1571 | } | ||
| 1572 | |||
| 1573 | |||
| 1574 | return ($self->{current_token}); # comment | ||
| 1575 | |||
| 1576 | redo A; | ||
| 1577 | } elsif ($self->{next_input_character} == 0x002D) { # - | ||
| 1578 | wakaba | 1.3 | $self->{parse_error}-> (type => 'dash in comment'); |
| 1579 | wakaba | 1.1 | $self->{current_token}->{data} .= '-'; # comment |
| 1580 | ## Stay in the state | ||
| 1581 | |||
| 1582 | if (@{$self->{char}}) { | ||
| 1583 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1584 | } else { | ||
| 1585 | $self->{set_next_input_character}->($self); | ||
| 1586 | } | ||
| 1587 | |||
| 1588 | redo A; | ||
| 1589 | } elsif ($self->{next_input_character} == -1) { | ||
| 1590 | wakaba | 1.3 | $self->{parse_error}-> (type => 'unclosed comment'); |
| 1591 | wakaba | 1.1 | $self->{state} = 'data'; |
| 1592 | ## reconsume | ||
| 1593 | |||
| 1594 | return ($self->{current_token}); # comment | ||
| 1595 | |||
| 1596 | redo A; | ||
| 1597 | } else { | ||
| 1598 | wakaba | 1.3 | $self->{parse_error}-> (type => 'dash in comment'); |
| 1599 | wakaba | 1.1 | $self->{current_token}->{data} .= '--' . chr ($self->{next_input_character}); # comment |
| 1600 | $self->{state} = 'comment'; | ||
| 1601 | |||
| 1602 | if (@{$self->{char}}) { | ||
| 1603 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1604 | } else { | ||
| 1605 | $self->{set_next_input_character}->($self); | ||
| 1606 | } | ||
| 1607 | |||
| 1608 | redo A; | ||
| 1609 | } | ||
| 1610 | } elsif ($self->{state} eq 'DOCTYPE') { | ||
| 1611 | if ($self->{next_input_character} == 0x0009 or # HT | ||
| 1612 | $self->{next_input_character} == 0x000A or # LF | ||
| 1613 | $self->{next_input_character} == 0x000B or # VT | ||
| 1614 | $self->{next_input_character} == 0x000C or # FF | ||
| 1615 | $self->{next_input_character} == 0x0020) { # SP | ||
| 1616 | $self->{state} = 'before DOCTYPE name'; | ||
| 1617 | |||
| 1618 | if (@{$self->{char}}) { | ||
| 1619 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1620 | } else { | ||
| 1621 | $self->{set_next_input_character}->($self); | ||
| 1622 | } | ||
| 1623 | |||
| 1624 | redo A; | ||
| 1625 | } else { | ||
| 1626 | wakaba | 1.3 | $self->{parse_error}-> (type => 'no space before DOCTYPE name'); |
| 1627 | wakaba | 1.1 | $self->{state} = 'before DOCTYPE name'; |
| 1628 | ## reconsume | ||
| 1629 | redo A; | ||
| 1630 | } | ||
| 1631 | } elsif ($self->{state} eq 'before DOCTYPE name') { | ||
| 1632 | if ($self->{next_input_character} == 0x0009 or # HT | ||
| 1633 | $self->{next_input_character} == 0x000A or # LF | ||
| 1634 | $self->{next_input_character} == 0x000B or # VT | ||
| 1635 | $self->{next_input_character} == 0x000C or # FF | ||
| 1636 | $self->{next_input_character} == 0x0020) { # SP | ||
| 1637 | ## Stay in the state | ||
| 1638 | |||
| 1639 | if (@{$self->{char}}) { | ||
| 1640 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1641 | } else { | ||
| 1642 | $self->{set_next_input_character}->($self); | ||
| 1643 | } | ||
| 1644 | |||
| 1645 | redo A; | ||
| 1646 | wakaba | 1.18 | } elsif ($self->{next_input_character} == 0x003E) { # > |
| 1647 | $self->{parse_error}-> (type => 'no DOCTYPE name'); | ||
| 1648 | $self->{state} = 'data'; | ||
| 1649 | |||
| 1650 | if (@{$self->{char}}) { | ||
| 1651 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1652 | } else { | ||
| 1653 | $self->{set_next_input_character}->($self); | ||
| 1654 | } | ||
| 1655 | |||
| 1656 | |||
| 1657 | return ({type => 'DOCTYPE'}); # incorrect | ||
| 1658 | |||
| 1659 | redo A; | ||
| 1660 | } elsif ($self->{next_input_character} == -1) { | ||
| 1661 | $self->{parse_error}-> (type => 'no DOCTYPE name'); | ||
| 1662 | $self->{state} = 'data'; | ||
| 1663 | ## reconsume | ||
| 1664 | |||
| 1665 | return ({type => 'DOCTYPE'}); # incorrect | ||
| 1666 | |||
| 1667 | redo A; | ||
| 1668 | } else { | ||
| 1669 | $self->{current_token} | ||
| 1670 | = {type => 'DOCTYPE', | ||
| 1671 | name => chr ($self->{next_input_character}), | ||
| 1672 | correct => 1}; | ||
| 1673 | wakaba | 1.4 | ## ISSUE: "Set the token's name name to the" in the spec |
| 1674 | wakaba | 1.1 | $self->{state} = 'DOCTYPE name'; |
| 1675 | |||
| 1676 | if (@{$self->{char}}) { | ||
| 1677 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1678 | } else { | ||
| 1679 | $self->{set_next_input_character}->($self); | ||
| 1680 | } | ||
| 1681 | |||
| 1682 | redo A; | ||
| 1683 | wakaba | 1.18 | } |
| 1684 | } elsif ($self->{state} eq 'DOCTYPE name') { | ||
| 1685 | ## ISSUE: Redundant "First," in the spec. | ||
| 1686 | if ($self->{next_input_character} == 0x0009 or # HT | ||
| 1687 | $self->{next_input_character} == 0x000A or # LF | ||
| 1688 | $self->{next_input_character} == 0x000B or # VT | ||
| 1689 | $self->{next_input_character} == 0x000C or # FF | ||
| 1690 | $self->{next_input_character} == 0x0020) { # SP | ||
| 1691 | $self->{state} = 'after DOCTYPE name'; | ||
| 1692 | |||
| 1693 | if (@{$self->{char}}) { | ||
| 1694 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1695 | } else { | ||
| 1696 | $self->{set_next_input_character}->($self); | ||
| 1697 | } | ||
| 1698 | |||
| 1699 | redo A; | ||
| 1700 | wakaba | 1.1 | } elsif ($self->{next_input_character} == 0x003E) { # > |
| 1701 | $self->{state} = 'data'; | ||
| 1702 | |||
| 1703 | if (@{$self->{char}}) { | ||
| 1704 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1705 | } else { | ||
| 1706 | $self->{set_next_input_character}->($self); | ||
| 1707 | } | ||
| 1708 | |||
| 1709 | |||
| 1710 | wakaba | 1.18 | return ($self->{current_token}); # DOCTYPE |
| 1711 | wakaba | 1.1 | |
| 1712 | redo A; | ||
| 1713 | wakaba | 1.18 | } elsif ($self->{next_input_character} == -1) { |
| 1714 | $self->{parse_error}-> (type => 'unclosed DOCTYPE'); | ||
| 1715 | wakaba | 1.1 | $self->{state} = 'data'; |
| 1716 | ## reconsume | ||
| 1717 | |||
| 1718 | wakaba | 1.18 | delete $self->{current_token}->{correct}; |
| 1719 | return ($self->{current_token}); # DOCTYPE | ||
| 1720 | wakaba | 1.1 | |
| 1721 | redo A; | ||
| 1722 | } else { | ||
| 1723 | wakaba | 1.18 | $self->{current_token}->{name} |
| 1724 | .= chr ($self->{next_input_character}); # DOCTYPE | ||
| 1725 | ## Stay in the state | ||
| 1726 | wakaba | 1.1 | |
| 1727 | if (@{$self->{char}}) { | ||
| 1728 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1729 | } else { | ||
| 1730 | $self->{set_next_input_character}->($self); | ||
| 1731 | } | ||
| 1732 | |||
| 1733 | redo A; | ||
| 1734 | } | ||
| 1735 | wakaba | 1.18 | } elsif ($self->{state} eq 'after DOCTYPE name') { |
| 1736 | wakaba | 1.1 | if ($self->{next_input_character} == 0x0009 or # HT |
| 1737 | $self->{next_input_character} == 0x000A or # LF | ||
| 1738 | $self->{next_input_character} == 0x000B or # VT | ||
| 1739 | $self->{next_input_character} == 0x000C or # FF | ||
| 1740 | $self->{next_input_character} == 0x0020) { # SP | ||
| 1741 | wakaba | 1.18 | ## Stay in the state |
| 1742 | wakaba | 1.1 | |
| 1743 | if (@{$self->{char}}) { | ||
| 1744 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1745 | } else { | ||
| 1746 | $self->{set_next_input_character}->($self); | ||
| 1747 | } | ||
| 1748 | |||
| 1749 | redo A; | ||
| 1750 | } elsif ($self->{next_input_character} == 0x003E) { # > | ||
| 1751 | $self->{state} = 'data'; | ||
| 1752 | |||
| 1753 | if (@{$self->{char}}) { | ||
| 1754 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1755 | } else { | ||
| 1756 | $self->{set_next_input_character}->($self); | ||
| 1757 | } | ||
| 1758 | |||
| 1759 | |||
| 1760 | return ($self->{current_token}); # DOCTYPE | ||
| 1761 | |||
| 1762 | redo A; | ||
| 1763 | wakaba | 1.18 | } elsif ($self->{next_input_character} == -1) { |
| 1764 | $self->{parse_error}-> (type => 'unclosed DOCTYPE'); | ||
| 1765 | $self->{state} = 'data'; | ||
| 1766 | ## reconsume | ||
| 1767 | |||
| 1768 | delete $self->{current_token}->{correct}; | ||
| 1769 | return ($self->{current_token}); # DOCTYPE | ||
| 1770 | |||
| 1771 | redo A; | ||
| 1772 | } elsif ($self->{next_input_character} == 0x0050 or # P | ||
| 1773 | $self->{next_input_character} == 0x0070) { # p | ||
| 1774 | |||
| 1775 | if (@{$self->{char}}) { | ||
| 1776 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1777 | } else { | ||
| 1778 | $self->{set_next_input_character}->($self); | ||
| 1779 | } | ||
| 1780 | |||
| 1781 | if ($self->{next_input_character} == 0x0055 or # U | ||
| 1782 | $self->{next_input_character} == 0x0075) { # u | ||
| 1783 | |||
| 1784 | if (@{$self->{char}}) { | ||
| 1785 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1786 | } else { | ||
| 1787 | $self->{set_next_input_character}->($self); | ||
| 1788 | } | ||
| 1789 | |||
| 1790 | if ($self->{next_input_character} == 0x0042 or # B | ||
| 1791 | $self->{next_input_character} == 0x0062) { # b | ||
| 1792 | |||
| 1793 | if (@{$self->{char}}) { | ||
| 1794 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1795 | } else { | ||
| 1796 | $self->{set_next_input_character}->($self); | ||
| 1797 | } | ||
| 1798 | |||
| 1799 | if ($self->{next_input_character} == 0x004C or # L | ||
| 1800 | $self->{next_input_character} == 0x006C) { # l | ||
| 1801 | |||
| 1802 | if (@{$self->{char}}) { | ||
| 1803 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1804 | } else { | ||
| 1805 | $self->{set_next_input_character}->($self); | ||
| 1806 | } | ||
| 1807 | |||
| 1808 | if ($self->{next_input_character} == 0x0049 or # I | ||
| 1809 | $self->{next_input_character} == 0x0069) { # i | ||
| 1810 | |||
| 1811 | if (@{$self->{char}}) { | ||
| 1812 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1813 | } else { | ||
| 1814 | $self->{set_next_input_character}->($self); | ||
| 1815 | } | ||
| 1816 | |||
| 1817 | if ($self->{next_input_character} == 0x0043 or # C | ||
| 1818 | $self->{next_input_character} == 0x0063) { # c | ||
| 1819 | $self->{state} = 'before DOCTYPE public identifier'; | ||
| 1820 | |||
| 1821 | if (@{$self->{char}}) { | ||
| 1822 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1823 | } else { | ||
| 1824 | $self->{set_next_input_character}->($self); | ||
| 1825 | } | ||
| 1826 | |||
| 1827 | redo A; | ||
| 1828 | } | ||
| 1829 | } | ||
| 1830 | } | ||
| 1831 | } | ||
| 1832 | } | ||
| 1833 | |||
| 1834 | # | ||
| 1835 | } elsif ($self->{next_input_character} == 0x0053 or # S | ||
| 1836 | $self->{next_input_character} == 0x0073) { # s | ||
| 1837 | |||
| 1838 | if (@{$self->{char}}) { | ||
| 1839 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1840 | } else { | ||
| 1841 | $self->{set_next_input_character}->($self); | ||
| 1842 | } | ||
| 1843 | |||
| 1844 | if ($self->{next_input_character} == 0x0059 or # Y | ||
| 1845 | $self->{next_input_character} == 0x0079) { # y | ||
| 1846 | |||
| 1847 | if (@{$self->{char}}) { | ||
| 1848 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1849 | } else { | ||
| 1850 | $self->{set_next_input_character}->($self); | ||
| 1851 | } | ||
| 1852 | |||
| 1853 | if ($self->{next_input_character} == 0x0053 or # S | ||
| 1854 | $self->{next_input_character} == 0x0073) { # s | ||
| 1855 | |||
| 1856 | if (@{$self->{char}}) { | ||
| 1857 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1858 | } else { | ||
| 1859 | $self->{set_next_input_character}->($self); | ||
| 1860 | } | ||
| 1861 | |||
| 1862 | if ($self->{next_input_character} == 0x0054 or # T | ||
| 1863 | $self->{next_input_character} == 0x0074) { # t | ||
| 1864 | |||
| 1865 | if (@{$self->{char}}) { | ||
| 1866 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1867 | } else { | ||
| 1868 | $self->{set_next_input_character}->($self); | ||
| 1869 | } | ||
| 1870 | |||
| 1871 | if ($self->{next_input_character} == 0x0045 or # E | ||
| 1872 | $self->{next_input_character} == 0x0065) { # e | ||
| 1873 | |||
| 1874 | if (@{$self->{char}}) { | ||
| 1875 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1876 | } else { | ||
| 1877 | $self->{set_next_input_character}->($self); | ||
| 1878 | } | ||
| 1879 | |||
| 1880 | if ($self->{next_input_character} == 0x004D or # M | ||
| 1881 | $self->{next_input_character} == 0x006D) { # m | ||
| 1882 | $self->{state} = 'before DOCTYPE system identifier'; | ||
| 1883 | |||
| 1884 | if (@{$self->{char}}) { | ||
| 1885 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1886 | } else { | ||
| 1887 | $self->{set_next_input_character}->($self); | ||
| 1888 | } | ||
| 1889 | |||
| 1890 | redo A; | ||
| 1891 | } | ||
| 1892 | } | ||
| 1893 | } | ||
| 1894 | } | ||
| 1895 | } | ||
| 1896 | |||
| 1897 | # | ||
| 1898 | } else { | ||
| 1899 | |||
| 1900 | if (@{$self->{char}}) { | ||
| 1901 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1902 | } else { | ||
| 1903 | $self->{set_next_input_character}->($self); | ||
| 1904 | } | ||
| 1905 | |||
| 1906 | # | ||
| 1907 | } | ||
| 1908 | |||
| 1909 | $self->{parse_error}-> (type => 'string after DOCTYPE name'); | ||
| 1910 | $self->{state} = 'bogus DOCTYPE'; | ||
| 1911 | # next-input-character is already done | ||
| 1912 | redo A; | ||
| 1913 | } elsif ($self->{state} eq 'before DOCTYPE public identifier') { | ||
| 1914 | if ({ | ||
| 1915 | 0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, | ||
| 1916 | #0x000D => 1, # HT, LF, VT, FF, SP, CR | ||
| 1917 | }->{$self->{next_input_character}}) { | ||
| 1918 | wakaba | 1.1 | ## Stay in the state |
| 1919 | |||
| 1920 | if (@{$self->{char}}) { | ||
| 1921 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1922 | } else { | ||
| 1923 | $self->{set_next_input_character}->($self); | ||
| 1924 | } | ||
| 1925 | |||
| 1926 | redo A; | ||
| 1927 | wakaba | 1.18 | } elsif ($self->{next_input_character} eq 0x0022) { # " |
| 1928 | $self->{current_token}->{public_identifier} = ''; # DOCTYPE | ||
| 1929 | $self->{state} = 'DOCTYPE public identifier (double-quoted)'; | ||
| 1930 | |||
| 1931 | if (@{$self->{char}}) { | ||
| 1932 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1933 | } else { | ||
| 1934 | $self->{set_next_input_character}->($self); | ||
| 1935 | } | ||
| 1936 | |||
| 1937 | redo A; | ||
| 1938 | } elsif ($self->{next_input_character} eq 0x0027) { # ' | ||
| 1939 | $self->{current_token}->{public_identifier} = ''; # DOCTYPE | ||
| 1940 | $self->{state} = 'DOCTYPE public identifier (single-quoted)'; | ||
| 1941 | |||
| 1942 | if (@{$self->{char}}) { | ||
| 1943 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1944 | } else { | ||
| 1945 | $self->{set_next_input_character}->($self); | ||
| 1946 | } | ||
| 1947 | |||
| 1948 | redo A; | ||
| 1949 | } elsif ($self->{next_input_character} eq 0x003E) { # > | ||
| 1950 | $self->{parse_error}-> (type => 'no PUBLIC literal'); | ||
| 1951 | |||
| 1952 | $self->{state} = 'data'; | ||
| 1953 | |||
| 1954 | if (@{$self->{char}}) { | ||
| 1955 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1956 | } else { | ||
| 1957 | $self->{set_next_input_character}->($self); | ||
| 1958 | } | ||
| 1959 | |||
| 1960 | |||
| 1961 | delete $self->{current_token}->{correct}; | ||
| 1962 | return ($self->{current_token}); # DOCTYPE | ||
| 1963 | |||
| 1964 | redo A; | ||
| 1965 | wakaba | 1.1 | } elsif ($self->{next_input_character} == -1) { |
| 1966 | wakaba | 1.3 | $self->{parse_error}-> (type => 'unclosed DOCTYPE'); |
| 1967 | wakaba | 1.18 | |
| 1968 | wakaba | 1.1 | $self->{state} = 'data'; |
| 1969 | ## reconsume | ||
| 1970 | |||
| 1971 | wakaba | 1.18 | delete $self->{current_token}->{correct}; |
| 1972 | return ($self->{current_token}); # DOCTYPE | ||
| 1973 | wakaba | 1.1 | |
| 1974 | redo A; | ||
| 1975 | } else { | ||
| 1976 | wakaba | 1.18 | $self->{parse_error}-> (type => 'string after PUBLIC'); |
| 1977 | $self->{state} = 'bogus DOCTYPE'; | ||
| 1978 | |||
| 1979 | if (@{$self->{char}}) { | ||
| 1980 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1981 | } else { | ||
| 1982 | $self->{set_next_input_character}->($self); | ||
| 1983 | } | ||
| 1984 | |||
| 1985 | redo A; | ||
| 1986 | } | ||
| 1987 | } elsif ($self->{state} eq 'DOCTYPE public identifier (double-quoted)') { | ||
| 1988 | if ($self->{next_input_character} == 0x0022) { # " | ||
| 1989 | $self->{state} = 'after DOCTYPE public identifier'; | ||
| 1990 | |||
| 1991 | if (@{$self->{char}}) { | ||
| 1992 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 1993 | } else { | ||
| 1994 | $self->{set_next_input_character}->($self); | ||
| 1995 | } | ||
| 1996 | |||
| 1997 | redo A; | ||
| 1998 | } elsif ($self->{next_input_character} == -1) { | ||
| 1999 | $self->{parse_error}-> (type => 'unclosed PUBLIC literal'); | ||
| 2000 | |||
| 2001 | $self->{state} = 'data'; | ||
| 2002 | ## reconsume | ||
| 2003 | |||
| 2004 | delete $self->{current_token}->{correct}; | ||
| 2005 | return ($self->{current_token}); # DOCTYPE | ||
| 2006 | |||
| 2007 | redo A; | ||
| 2008 | } else { | ||
| 2009 | $self->{current_token}->{public_identifier} # DOCTYPE | ||
| 2010 | .= chr $self->{next_input_character}; | ||
| 2011 | ## Stay in the state | ||
| 2012 | |||
| 2013 | if (@{$self->{char}}) { | ||
| 2014 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2015 | } else { | ||
| 2016 | $self->{set_next_input_character}->($self); | ||
| 2017 | } | ||
| 2018 | |||
| 2019 | redo A; | ||
| 2020 | } | ||
| 2021 | } elsif ($self->{state} eq 'DOCTYPE public identifier (single-quoted)') { | ||
| 2022 | if ($self->{next_input_character} == 0x0027) { # ' | ||
| 2023 | $self->{state} = 'after DOCTYPE public identifier'; | ||
| 2024 | |||
| 2025 | if (@{$self->{char}}) { | ||
| 2026 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2027 | } else { | ||
| 2028 | $self->{set_next_input_character}->($self); | ||
| 2029 | } | ||
| 2030 | |||
| 2031 | redo A; | ||
| 2032 | } elsif ($self->{next_input_character} == -1) { | ||
| 2033 | $self->{parse_error}-> (type => 'unclosed PUBLIC literal'); | ||
| 2034 | |||
| 2035 | $self->{state} = 'data'; | ||
| 2036 | ## reconsume | ||
| 2037 | |||
| 2038 | delete $self->{current_token}->{correct}; | ||
| 2039 | return ($self->{current_token}); # DOCTYPE | ||
| 2040 | |||
| 2041 | redo A; | ||
| 2042 | } else { | ||
| 2043 | $self->{current_token}->{public_identifier} # DOCTYPE | ||
| 2044 | .= chr $self->{next_input_character}; | ||
| 2045 | ## Stay in the state | ||
| 2046 | |||
| 2047 | if (@{$self->{char}}) { | ||
| 2048 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2049 | } else { | ||
| 2050 | $self->{set_next_input_character}->($self); | ||
| 2051 | } | ||
| 2052 | |||
| 2053 | redo A; | ||
| 2054 | } | ||
| 2055 | } elsif ($self->{state} eq 'after DOCTYPE public identifier') { | ||
| 2056 | if ({ | ||
| 2057 | 0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, | ||
| 2058 | #0x000D => 1, # HT, LF, VT, FF, SP, CR | ||
| 2059 | }->{$self->{next_input_character}}) { | ||
| 2060 | wakaba | 1.1 | ## Stay in the state |
| 2061 | |||
| 2062 | if (@{$self->{char}}) { | ||
| 2063 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2064 | } else { | ||
| 2065 | $self->{set_next_input_character}->($self); | ||
| 2066 | } | ||
| 2067 | |||
| 2068 | redo A; | ||
| 2069 | wakaba | 1.18 | } elsif ($self->{next_input_character} == 0x0022) { # " |
| 2070 | $self->{current_token}->{system_identifier} = ''; # DOCTYPE | ||
| 2071 | $self->{state} = 'DOCTYPE system identifier (double-quoted)'; | ||
| 2072 | |||
| 2073 | if (@{$self->{char}}) { | ||
| 2074 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2075 | } else { | ||
| 2076 | $self->{set_next_input_character}->($self); | ||
| 2077 | } | ||
| 2078 | |||
| 2079 | redo A; | ||
| 2080 | } elsif ($self->{next_input_character} == 0x0027) { # ' | ||
| 2081 | $self->{current_token}->{system_identifier} = ''; # DOCTYPE | ||
| 2082 | $self->{state} = 'DOCTYPE system identifier (single-quoted)'; | ||
| 2083 | |||
| 2084 | if (@{$self->{char}}) { | ||
| 2085 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2086 | } else { | ||
| 2087 | $self->{set_next_input_character}->($self); | ||
| 2088 | } | ||
| 2089 | |||
| 2090 | redo A; | ||
| 2091 | } elsif ($self->{next_input_character} == 0x003E) { # > | ||
| 2092 | $self->{state} = 'data'; | ||
| 2093 | |||
| 2094 | if (@{$self->{char}}) { | ||
| 2095 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2096 | } else { | ||
| 2097 | $self->{set_next_input_character}->($self); | ||
| 2098 | } | ||
| 2099 | |||
| 2100 | |||
| 2101 | return ($self->{current_token}); # DOCTYPE | ||
| 2102 | |||
| 2103 | redo A; | ||
| 2104 | } elsif ($self->{next_input_character} == -1) { | ||
| 2105 | $self->{parse_error}-> (type => 'unclosed DOCTYPE'); | ||
| 2106 | |||
| 2107 | $self->{state} = 'data'; | ||
| 2108 | wakaba | 1.26 | ## reconsume |
| 2109 | wakaba | 1.18 | |
| 2110 | delete $self->{current_token}->{correct}; | ||
| 2111 | return ($self->{current_token}); # DOCTYPE | ||
| 2112 | |||
| 2113 | redo A; | ||
| 2114 | } else { | ||
| 2115 | $self->{parse_error}-> (type => 'string after PUBLIC literal'); | ||
| 2116 | $self->{state} = 'bogus DOCTYPE'; | ||
| 2117 | |||
| 2118 | if (@{$self->{char}}) { | ||
| 2119 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2120 | } else { | ||
| 2121 | $self->{set_next_input_character}->($self); | ||
| 2122 | } | ||
| 2123 | |||
| 2124 | redo A; | ||
| 2125 | wakaba | 1.1 | } |
| 2126 | wakaba | 1.18 | } elsif ($self->{state} eq 'before DOCTYPE system identifier') { |
| 2127 | if ({ | ||
| 2128 | 0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, | ||
| 2129 | #0x000D => 1, # HT, LF, VT, FF, SP, CR | ||
| 2130 | }->{$self->{next_input_character}}) { | ||
| 2131 | wakaba | 1.1 | ## Stay in the state |
| 2132 | |||
| 2133 | if (@{$self->{char}}) { | ||
| 2134 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2135 | } else { | ||
| 2136 | $self->{set_next_input_character}->($self); | ||
| 2137 | } | ||
| 2138 | |||
| 2139 | redo A; | ||
| 2140 | wakaba | 1.18 | } elsif ($self->{next_input_character} == 0x0022) { # " |
| 2141 | $self->{current_token}->{system_identifier} = ''; # DOCTYPE | ||
| 2142 | $self->{state} = 'DOCTYPE system identifier (double-quoted)'; | ||
| 2143 | |||
| 2144 | if (@{$self->{char}}) { | ||
| 2145 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2146 | } else { | ||
| 2147 | $self->{set_next_input_character}->($self); | ||
| 2148 | } | ||
| 2149 | |||
| 2150 | redo A; | ||
| 2151 | } elsif ($self->{next_input_character} == 0x0027) { # ' | ||
| 2152 | $self->{current_token}->{system_identifier} = ''; # DOCTYPE | ||
| 2153 | $self->{state} = 'DOCTYPE system identifier (single-quoted)'; | ||
| 2154 | |||
| 2155 | if (@{$self->{char}}) { | ||
| 2156 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2157 | } else { | ||
| 2158 | $self->{set_next_input_character}->($self); | ||
| 2159 | } | ||
| 2160 | |||
| 2161 | redo A; | ||
| 2162 | wakaba | 1.1 | } elsif ($self->{next_input_character} == 0x003E) { # > |
| 2163 | wakaba | 1.18 | $self->{parse_error}-> (type => 'no SYSTEM literal'); |
| 2164 | wakaba | 1.1 | $self->{state} = 'data'; |
| 2165 | |||
| 2166 | if (@{$self->{char}}) { | ||
| 2167 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2168 | } else { | ||
| 2169 | $self->{set_next_input_character}->($self); | ||
| 2170 | } | ||
| 2171 | |||
| 2172 | |||
| 2173 | wakaba | 1.18 | delete $self->{current_token}->{correct}; |
| 2174 | wakaba | 1.1 | return ($self->{current_token}); # DOCTYPE |
| 2175 | |||
| 2176 | redo A; | ||
| 2177 | } elsif ($self->{next_input_character} == -1) { | ||
| 2178 | wakaba | 1.3 | $self->{parse_error}-> (type => 'unclosed DOCTYPE'); |
| 2179 | wakaba | 1.18 | |
| 2180 | $self->{state} = 'data'; | ||
| 2181 | wakaba | 1.26 | ## reconsume |
| 2182 | wakaba | 1.18 | |
| 2183 | delete $self->{current_token}->{correct}; | ||
| 2184 | return ($self->{current_token}); # DOCTYPE | ||
| 2185 | |||
| 2186 | redo A; | ||
| 2187 | } else { | ||
| 2188 | wakaba | 1.30 | $self->{parse_error}-> (type => 'string after SYSTEM'); |
| 2189 | wakaba | 1.18 | $self->{state} = 'bogus DOCTYPE'; |
| 2190 | |||
| 2191 | if (@{$self->{char}}) { | ||
| 2192 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2193 | } else { | ||
| 2194 | $self->{set_next_input_character}->($self); | ||
| 2195 | } | ||
| 2196 | |||
| 2197 | redo A; | ||
| 2198 | } | ||
| 2199 | } elsif ($self->{state} eq 'DOCTYPE system identifier (double-quoted)') { | ||
| 2200 | if ($self->{next_input_character} == 0x0022) { # " | ||
| 2201 | $self->{state} = 'after DOCTYPE system identifier'; | ||
| 2202 | |||
| 2203 | if (@{$self->{char}}) { | ||
| 2204 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2205 | } else { | ||
| 2206 | $self->{set_next_input_character}->($self); | ||
| 2207 | } | ||
| 2208 | |||
| 2209 | redo A; | ||
| 2210 | } elsif ($self->{next_input_character} == -1) { | ||
| 2211 | $self->{parse_error}-> (type => 'unclosed SYSTEM literal'); | ||
| 2212 | |||
| 2213 | wakaba | 1.1 | $self->{state} = 'data'; |
| 2214 | ## reconsume | ||
| 2215 | |||
| 2216 | wakaba | 1.18 | delete $self->{current_token}->{correct}; |
| 2217 | wakaba | 1.1 | return ($self->{current_token}); # DOCTYPE |
| 2218 | |||
| 2219 | redo A; | ||
| 2220 | } else { | ||
| 2221 | wakaba | 1.18 | $self->{current_token}->{system_identifier} # DOCTYPE |
| 2222 | .= chr $self->{next_input_character}; | ||
| 2223 | ## Stay in the state | ||
| 2224 | |||
| 2225 | if (@{$self->{char}}) { | ||
| 2226 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2227 | } else { | ||
| 2228 | $self->{set_next_input_character}->($self); | ||
| 2229 | } | ||
| 2230 | |||
| 2231 | redo A; | ||
| 2232 | } | ||
| 2233 | } elsif ($self->{state} eq 'DOCTYPE system identifier (single-quoted)') { | ||
| 2234 | if ($self->{next_input_character} == 0x0027) { # ' | ||
| 2235 | $self->{state} = 'after DOCTYPE system identifier'; | ||
| 2236 | |||
| 2237 | if (@{$self->{char}}) { | ||
| 2238 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2239 | } else { | ||
| 2240 | $self->{set_next_input_character}->($self); | ||
| 2241 | } | ||
| 2242 | |||
| 2243 | redo A; | ||
| 2244 | } elsif ($self->{next_input_character} == -1) { | ||
| 2245 | $self->{parse_error}-> (type => 'unclosed SYSTEM literal'); | ||
| 2246 | |||
| 2247 | $self->{state} = 'data'; | ||
| 2248 | ## reconsume | ||
| 2249 | |||
| 2250 | delete $self->{current_token}->{correct}; | ||
| 2251 | return ($self->{current_token}); # DOCTYPE | ||
| 2252 | |||
| 2253 | redo A; | ||
| 2254 | } else { | ||
| 2255 | $self->{current_token}->{system_identifier} # DOCTYPE | ||
| 2256 | .= chr $self->{next_input_character}; | ||
| 2257 | ## Stay in the state | ||
| 2258 | |||
| 2259 | if (@{$self->{char}}) { | ||
| 2260 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2261 | } else { | ||
| 2262 | $self->{set_next_input_character}->($self); | ||
| 2263 | } | ||
| 2264 | |||
| 2265 | redo A; | ||
| 2266 | } | ||
| 2267 | } elsif ($self->{state} eq 'after DOCTYPE system identifier') { | ||
| 2268 | if ({ | ||
| 2269 | 0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, | ||
| 2270 | #0x000D => 1, # HT, LF, VT, FF, SP, CR | ||
| 2271 | }->{$self->{next_input_character}}) { | ||
| 2272 | ## Stay in the state | ||
| 2273 | |||
| 2274 | if (@{$self->{char}}) { | ||
| 2275 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2276 | } else { | ||
| 2277 | $self->{set_next_input_character}->($self); | ||
| 2278 | } | ||
| 2279 | |||
| 2280 | redo A; | ||
| 2281 | } elsif ($self->{next_input_character} == 0x003E) { # > | ||
| 2282 | $self->{state} = 'data'; | ||
| 2283 | |||
| 2284 | if (@{$self->{char}}) { | ||
| 2285 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2286 | } else { | ||
| 2287 | $self->{set_next_input_character}->($self); | ||
| 2288 | } | ||
| 2289 | |||
| 2290 | |||
| 2291 | return ($self->{current_token}); # DOCTYPE | ||
| 2292 | |||
| 2293 | redo A; | ||
| 2294 | } elsif ($self->{next_input_character} == -1) { | ||
| 2295 | $self->{parse_error}-> (type => 'unclosed DOCTYPE'); | ||
| 2296 | |||
| 2297 | $self->{state} = 'data'; | ||
| 2298 | wakaba | 1.26 | ## reconsume |
| 2299 | wakaba | 1.18 | |
| 2300 | delete $self->{current_token}->{correct}; | ||
| 2301 | return ($self->{current_token}); # DOCTYPE | ||
| 2302 | |||
| 2303 | redo A; | ||
| 2304 | } else { | ||
| 2305 | $self->{parse_error}-> (type => 'string after SYSTEM literal'); | ||
| 2306 | wakaba | 1.1 | $self->{state} = 'bogus DOCTYPE'; |
| 2307 | |||
| 2308 | if (@{$self->{char}}) { | ||
| 2309 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2310 | } else { | ||
| 2311 | $self->{set_next_input_character}->($self); | ||
| 2312 | } | ||
| 2313 | |||
| 2314 | redo A; | ||
| 2315 | } | ||
| 2316 | } elsif ($self->{state} eq 'bogus DOCTYPE') { | ||
| 2317 | if ($self->{next_input_character} == 0x003E) { # > | ||
| 2318 | $self->{state} = 'data'; | ||
| 2319 | |||
| 2320 | if (@{$self->{char}}) { | ||
| 2321 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2322 | } else { | ||
| 2323 | $self->{set_next_input_character}->($self); | ||
| 2324 | } | ||
| 2325 | |||
| 2326 | |||
| 2327 | wakaba | 1.18 | delete $self->{current_token}->{correct}; |
| 2328 | wakaba | 1.1 | return ($self->{current_token}); # DOCTYPE |
| 2329 | |||
| 2330 | redo A; | ||
| 2331 | } elsif ($self->{next_input_character} == -1) { | ||
| 2332 | wakaba | 1.3 | $self->{parse_error}-> (type => 'unclosed DOCTYPE'); |
| 2333 | wakaba | 1.1 | $self->{state} = 'data'; |
| 2334 | ## reconsume | ||
| 2335 | |||
| 2336 | wakaba | 1.18 | delete $self->{current_token}->{correct}; |
| 2337 | wakaba | 1.1 | return ($self->{current_token}); # DOCTYPE |
| 2338 | |||
| 2339 | redo A; | ||
| 2340 | } else { | ||
| 2341 | ## Stay in the state | ||
| 2342 | |||
| 2343 | if (@{$self->{char}}) { | ||
| 2344 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2345 | } else { | ||
| 2346 | $self->{set_next_input_character}->($self); | ||
| 2347 | } | ||
| 2348 | |||
| 2349 | redo A; | ||
| 2350 | } | ||
| 2351 | } else { | ||
| 2352 | die "$0: $self->{state}: Unknown state"; | ||
| 2353 | } | ||
| 2354 | } # A | ||
| 2355 | |||
| 2356 | die "$0: _get_next_token: unexpected case"; | ||
| 2357 | } # _get_next_token | ||
| 2358 | |||
| 2359 | wakaba | 1.26 | sub _tokenize_attempt_to_consume_an_entity ($$) { |
| 2360 | my ($self, $in_attr) = @_; | ||
| 2361 | wakaba | 1.20 | |
| 2362 | if ({ | ||
| 2363 | 0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, # HT, LF, VT, FF, | ||
| 2364 | 0x0020 => 1, 0x003C => 1, 0x0026 => 1, -1 => 1, # SP, <, & # 0x000D # CR | ||
| 2365 | }->{$self->{next_input_character}}) { | ||
| 2366 | ## Don't consume | ||
| 2367 | ## No error | ||
| 2368 | return undef; | ||
| 2369 | } elsif ($self->{next_input_character} == 0x0023) { # # | ||
| 2370 | wakaba | 1.1 | |
| 2371 | if (@{$self->{char}}) { | ||
| 2372 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2373 | } else { | ||
| 2374 | $self->{set_next_input_character}->($self); | ||
| 2375 | } | ||
| 2376 | |||
| 2377 | if ($self->{next_input_character} == 0x0078 or # x | ||
| 2378 | $self->{next_input_character} == 0x0058) { # X | ||
| 2379 | wakaba | 1.26 | my $code; |
| 2380 | wakaba | 1.1 | X: { |
| 2381 | my $x_char = $self->{next_input_character}; | ||
| 2382 | |||
| 2383 | if (@{$self->{char}}) { | ||
| 2384 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2385 | } else { | ||
| 2386 | $self->{set_next_input_character}->($self); | ||
| 2387 | } | ||
| 2388 | |||
| 2389 | if (0x0030 <= $self->{next_input_character} and | ||
| 2390 | $self->{next_input_character} <= 0x0039) { # 0..9 | ||
| 2391 | wakaba | 1.26 | $code ||= 0; |
| 2392 | $code *= 0x10; | ||
| 2393 | $code += $self->{next_input_character} - 0x0030; | ||
| 2394 | wakaba | 1.1 | redo X; |
| 2395 | } elsif (0x0061 <= $self->{next_input_character} and | ||
| 2396 | $self->{next_input_character} <= 0x0066) { # a..f | ||
| 2397 | wakaba | 1.26 | $code ||= 0; |
| 2398 | $code *= 0x10; | ||
| 2399 | $code += $self->{next_input_character} - 0x0060 + 9; | ||
| 2400 | wakaba | 1.1 | redo X; |
| 2401 | } elsif (0x0041 <= $self->{next_input_character} and | ||
| 2402 | $self->{next_input_character} <= 0x0046) { # A..F | ||
| 2403 | wakaba | 1.26 | $code ||= 0; |
| 2404 | $code *= 0x10; | ||
| 2405 | $code += $self->{next_input_character} - 0x0040 + 9; | ||
| 2406 | wakaba | 1.1 | redo X; |
| 2407 | wakaba | 1.26 | } elsif (not defined $code) { # no hexadecimal digit |
| 2408 | wakaba | 1.3 | $self->{parse_error}-> (type => 'bare hcro'); |
| 2409 | wakaba | 1.1 | $self->{next_input_character} = 0x0023; # # |
| 2410 | unshift @{$self->{char}}, ($x_char); | ||
| 2411 | return undef; | ||
| 2412 | } elsif ($self->{next_input_character} == 0x003B) { # ; | ||
| 2413 | |||
| 2414 | if (@{$self->{char}}) { | ||
| 2415 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2416 | } else { | ||
| 2417 | $self->{set_next_input_character}->($self); | ||
| 2418 | } | ||
| 2419 | |||
| 2420 | } else { | ||
| 2421 | wakaba | 1.3 | $self->{parse_error}-> (type => 'no refc'); |
| 2422 | wakaba | 1.1 | } |
| 2423 | |||
| 2424 | wakaba | 1.26 | if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 2425 | $self->{parse_error}-> (type => sprintf 'invalid character reference:U+%04X', $code); | ||
| 2426 | $code = 0xFFFD; | ||
| 2427 | } elsif ($code > 0x10FFFF) { | ||
| 2428 | $self->{parse_error}-> (type => sprintf 'invalid character reference:U-%08X', $code); | ||
| 2429 | $code = 0xFFFD; | ||
| 2430 | } elsif ($code == 0x000D) { | ||
| 2431 | $self->{parse_error}-> (type => 'CR character reference'); | ||
| 2432 | $code = 0x000A; | ||
| 2433 | } elsif (0x80 <= $code and $code <= 0x9F) { | ||
| 2434 | wakaba | 1.30 | $self->{parse_error}-> (type => sprintf 'C1 character reference:U+%04X', $code); |
| 2435 | wakaba | 1.26 | $code = $c1_entity_char->{$code}; |
| 2436 | wakaba | 1.1 | } |
| 2437 | |||
| 2438 | wakaba | 1.26 | return {type => 'character', data => chr $code}; |
| 2439 | wakaba | 1.1 | } # X |
| 2440 | } elsif (0x0030 <= $self->{next_input_character} and | ||
| 2441 | $self->{next_input_character} <= 0x0039) { # 0..9 | ||
| 2442 | my $code = $self->{next_input_character} - 0x0030; | ||
| 2443 | |||
| 2444 | if (@{$self->{char}}) { | ||
| 2445 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2446 | } else { | ||
| 2447 | $self->{set_next_input_character}->($self); | ||
| 2448 | } | ||
| 2449 | |||
| 2450 | |||
| 2451 | while (0x0030 <= $self->{next_input_character} and | ||
| 2452 | $self->{next_input_character} <= 0x0039) { # 0..9 | ||
| 2453 | $code *= 10; | ||
| 2454 | $code += $self->{next_input_character} - 0x0030; | ||
| 2455 | |||
| 2456 | |||
| 2457 | if (@{$self->{char}}) { | ||
| 2458 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2459 | } else { | ||
| 2460 | $self->{set_next_input_character}->($self); | ||
| 2461 | } | ||
| 2462 | |||
| 2463 | } | ||
| 2464 | |||
| 2465 | if ($self->{next_input_character} == 0x003B) { # ; | ||
| 2466 | |||
| 2467 | if (@{$self->{char}}) { | ||
| 2468 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2469 | } else { | ||
| 2470 | $self->{set_next_input_character}->($self); | ||
| 2471 | } | ||
| 2472 | |||
| 2473 | } else { | ||
| 2474 | wakaba | 1.3 | $self->{parse_error}-> (type => 'no refc'); |
| 2475 | wakaba | 1.1 | } |
| 2476 | |||
| 2477 | wakaba | 1.26 | if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 2478 | $self->{parse_error}-> (type => sprintf 'invalid character reference:U+%04X', $code); | ||
| 2479 | $code = 0xFFFD; | ||
| 2480 | } elsif ($code > 0x10FFFF) { | ||
| 2481 | $self->{parse_error}-> (type => sprintf 'invalid character reference:U-%08X', $code); | ||
| 2482 | $code = 0xFFFD; | ||
| 2483 | } elsif ($code == 0x000D) { | ||
| 2484 | $self->{parse_error}-> (type => 'CR character reference'); | ||
| 2485 | $code = 0x000A; | ||
| 2486 | wakaba | 1.4 | } elsif (0x80 <= $code and $code <= 0x9F) { |
| 2487 | wakaba | 1.30 | $self->{parse_error}-> (type => sprintf 'C1 character reference:U+%04X', $code); |
| 2488 | wakaba | 1.4 | $code = $c1_entity_char->{$code}; |
| 2489 | wakaba | 1.1 | } |
| 2490 | |||
| 2491 | return {type => 'character', data => chr $code}; | ||
| 2492 | } else { | ||
| 2493 | wakaba | 1.3 | $self->{parse_error}-> (type => 'bare nero'); |
| 2494 | wakaba | 1.1 | unshift @{$self->{char}}, ($self->{next_input_character}); |
| 2495 | $self->{next_input_character} = 0x0023; # # | ||
| 2496 | return undef; | ||
| 2497 | } | ||
| 2498 | } elsif ((0x0041 <= $self->{next_input_character} and | ||
| 2499 | $self->{next_input_character} <= 0x005A) or | ||
| 2500 | (0x0061 <= $self->{next_input_character} and | ||
| 2501 | $self->{next_input_character} <= 0x007A)) { | ||
| 2502 | my $entity_name = chr $self->{next_input_character}; | ||
| 2503 | |||
| 2504 | if (@{$self->{char}}) { | ||
| 2505 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2506 | } else { | ||
| 2507 | $self->{set_next_input_character}->($self); | ||
| 2508 | } | ||
| 2509 | |||
| 2510 | |||
| 2511 | my $value = $entity_name; | ||
| 2512 | my $match; | ||
| 2513 | wakaba | 1.16 | require Whatpm::_NamedEntityList; |
| 2514 | our $EntityChar; | ||
| 2515 | wakaba | 1.1 | |
| 2516 | while (length $entity_name < 10 and | ||
| 2517 | ## NOTE: Some number greater than the maximum length of entity name | ||
| 2518 | wakaba | 1.16 | ((0x0041 <= $self->{next_input_character} and # a |
| 2519 | $self->{next_input_character} <= 0x005A) or # x | ||
| 2520 | (0x0061 <= $self->{next_input_character} and # a | ||
| 2521 | $self->{next_input_character} <= 0x007A) or # z | ||
| 2522 | (0x0030 <= $self->{next_input_character} and # 0 | ||
| 2523 | $self->{next_input_character} <= 0x0039) or # 9 | ||
| 2524 | $self->{next_input_character} == 0x003B)) { # ; | ||
| 2525 | wakaba | 1.1 | $entity_name .= chr $self->{next_input_character}; |
| 2526 | wakaba | 1.16 | if (defined $EntityChar->{$entity_name}) { |
| 2527 | if ($self->{next_input_character} == 0x003B) { # ; | ||
| 2528 | wakaba | 1.26 | $value = $EntityChar->{$entity_name}; |
| 2529 | wakaba | 1.16 | $match = 1; |
| 2530 | |||
| 2531 | if (@{$self->{char}}) { | ||
| 2532 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2533 | } else { | ||
| 2534 | $self->{set_next_input_character}->($self); | ||
| 2535 | } | ||
| 2536 | |||
| 2537 | last; | ||
| 2538 | wakaba | 1.26 | } elsif (not $in_attr) { |
| 2539 | $value = $EntityChar->{$entity_name}; | ||
| 2540 | $match = -1; | ||
| 2541 | wakaba | 1.16 | } else { |
| 2542 | wakaba | 1.26 | $value .= chr $self->{next_input_character}; |
| 2543 | wakaba | 1.16 | } |
| 2544 | wakaba | 1.1 | } else { |
| 2545 | $value .= chr $self->{next_input_character}; | ||
| 2546 | } | ||
| 2547 | |||
| 2548 | if (@{$self->{char}}) { | ||
| 2549 | $self->{next_input_character} = shift @{$self->{char}}; | ||
| 2550 | } else { | ||
| 2551 | $self->{set_next_input_character}->($self); | ||
| 2552 | } | ||
| 2553 | |||
| 2554 | } | ||
| 2555 | |||
| 2556 | wakaba | 1.16 | if ($match > 0) { |
| 2557 | return {type => 'character', data => $value}; | ||
| 2558 | } elsif ($match < 0) { | ||
| 2559 | wakaba | 1.30 | $self->{parse_error}-> (type => 'no refc'); |
| 2560 | wakaba | 1.1 | return {type => 'character', data => $value}; |
| 2561 | } else { | ||
| 2562 | wakaba | 1.3 | $self->{parse_error}-> (type => 'bare ero'); |
| 2563 | wakaba | 1.1 | ## NOTE: No characters are consumed in the spec. |
| 2564 | wakaba | 1.26 | return {type => 'character', data => '&'.$value}; |
| 2565 | wakaba | 1.1 | } |
| 2566 | } else { | ||
| 2567 | ## no characters are consumed | ||
| 2568 | wakaba | 1.3 | $self->{parse_error}-> (type => 'bare ero'); |
| 2569 | wakaba | 1.1 | return undef; |
| 2570 | } | ||
| 2571 | } # _tokenize_attempt_to_consume_an_entity | ||
| 2572 | |||
| 2573 | sub _initialize_tree_constructor ($) { | ||
| 2574 | my $self = shift; | ||
| 2575 | ## NOTE: $self->{document} MUST be specified before this method is called | ||
| 2576 | $self->{document}->strict_error_checking (0); | ||
| 2577 | ## TODO: Turn mutation events off # MUST | ||
| 2578 | ## TODO: Turn loose Document option (manakai extension) on | ||
| 2579 | wakaba | 1.18 | $self->{document}->manakai_is_html (1); # MUST |
| 2580 | wakaba | 1.1 | } # _initialize_tree_constructor |
| 2581 | |||
| 2582 | sub _terminate_tree_constructor ($) { | ||
| 2583 | my $self = shift; | ||
| 2584 | $self->{document}->strict_error_checking (1); | ||
| 2585 | ## TODO: Turn mutation events on | ||
| 2586 | } # _terminate_tree_constructor | ||
| 2587 | |||
| 2588 | ## ISSUE: Should append_child (for example) in script executed in tree construction stage fire mutation events? | ||
| 2589 | |||
| 2590 | wakaba | 1.3 | { # tree construction stage |
| 2591 | my $token; | ||
| 2592 | |||
| 2593 | wakaba | 1.1 | sub _construct_tree ($) { |
| 2594 | my ($self) = @_; | ||
| 2595 | |||
| 2596 | ## When an interactive UA render the $self->{document} available | ||
| 2597 | ## to the user, or when it begin accepting user input, are | ||
| 2598 | ## not defined. | ||
| 2599 | |||
| 2600 | ## Append a character: collect it and all subsequent consecutive | ||
| 2601 | ## characters and insert one Text node whose data is concatenation | ||
| 2602 | ## of all those characters. # MUST | ||
| 2603 | |||
| 2604 | $token = $self->_get_next_token; | ||
| 2605 | |||
| 2606 | wakaba | 1.3 | $self->{insertion_mode} = 'before head'; |
| 2607 | undef $self->{form_element}; | ||
| 2608 | undef $self->{head_element}; | ||
| 2609 | $self->{open_elements} = []; | ||
| 2610 | undef $self->{inner_html_node}; | ||
| 2611 | |||
| 2612 | $self->_tree_construction_initial; # MUST | ||
| 2613 | $self->_tree_construction_root_element; | ||
| 2614 | $self->_tree_construction_main; | ||
| 2615 | } # _construct_tree | ||
| 2616 | |||
| 2617 | sub _tree_construction_initial ($) { | ||
| 2618 | my $self = shift; | ||
| 2619 | wakaba | 1.18 | INITIAL: { |
| 2620 | if ($token->{type} eq 'DOCTYPE') { | ||
| 2621 | ## NOTE: Conformance checkers MAY, instead of reporting "not HTML5" | ||
| 2622 | ## error, switch to a conformance checking mode for another | ||
| 2623 | ## language. | ||
| 2624 | my $doctype_name = $token->{name}; | ||
| 2625 | $doctype_name = '' unless defined $doctype_name; | ||
| 2626 | $doctype_name =~ tr/a-z/A-Z/; | ||
| 2627 | if (not defined $token->{name} or # <!DOCTYPE> | ||
| 2628 | defined $token->{public_identifier} or | ||
| 2629 | defined $token->{system_identifier}) { | ||
| 2630 | $self->{parse_error}-> (type => 'not HTML5'); | ||
| 2631 | } elsif ($doctype_name ne 'HTML') { | ||
| 2632 | ## ISSUE: ASCII case-insensitive? (in fact it does not matter) | ||
| 2633 | $self->{parse_error}-> (type => 'not HTML5'); | ||
| 2634 | } | ||
| 2635 | |||
| 2636 | my $doctype = $self->{document}->create_document_type_definition | ||
| 2637 | ($token->{name}); ## ISSUE: If name is missing (e.g. <!DOCTYPE>)? | ||
| 2638 | $doctype->public_id ($token->{public_identifier}) | ||
| 2639 | if defined $token->{public_identifier}; | ||
| 2640 | $doctype->system_id ($token->{system_identifier}) | ||
| 2641 | if defined $token->{system_identifier}; | ||
| 2642 | ## NOTE: Other DocumentType attributes are null or empty lists. | ||
| 2643 | ## ISSUE: internalSubset = null?? | ||
| 2644 | $self->{document}->append_child ($doctype); | ||
| 2645 | |||
| 2646 | if (not $token->{correct} or $doctype_name ne 'HTML') { | ||
| 2647 | $self->{document}->manakai_compat_mode ('quirks'); | ||
| 2648 | } elsif (defined $token->{public_identifier}) { | ||
| 2649 | my $pubid = $token->{public_identifier}; | ||
| 2650 | $pubid =~ tr/a-z/A-z/; | ||
| 2651 | if ({ | ||
| 2652 | "+//SILMARIL//DTD HTML PRO V0R11 19970101//EN" => 1, | ||
| 2653 | "-//ADVASOFT LTD//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1, | ||
| 2654 | "-//AS//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1, | ||
| 2655 | "-//IETF//DTD HTML 2.0 LEVEL 1//EN" => 1, | ||
| 2656 | "-//IETF//DTD HTML 2.0 LEVEL 2//EN" => 1, | ||
| 2657 | "-//IETF//DTD HTML 2.0 STRICT LEVEL 1//EN" => 1, | ||
| 2658 | "-//IETF//DTD HTML 2.0 STRICT LEVEL 2//EN" => 1, | ||
| 2659 | "-//IETF//DTD HTML 2.0 STRICT//EN" => 1, | ||
| 2660 | "-//IETF//DTD HTML 2.0//EN" => 1, | ||
| 2661 | "-//IETF//DTD HTML 2.1E//EN" => 1, | ||
| 2662 | "-//IETF//DTD HTML 3.0//EN" => 1, | ||
| 2663 | "-//IETF//DTD HTML 3.0//EN//" => 1, | ||
| 2664 | "-//IETF//DTD HTML 3.2 FINAL//EN" => 1, | ||
| 2665 | "-//IETF//DTD HTML 3.2//EN" => 1, | ||
| 2666 | "-//IETF//DTD HTML 3//EN" => 1, | ||
| 2667 | "-//IETF//DTD HTML LEVEL 0//EN" => 1, | ||
| 2668 | "-//IETF//DTD HTML LEVEL 0//EN//2.0" => 1, | ||
| 2669 | "-//IETF//DTD HTML LEVEL 1//EN" => 1, | ||
| 2670 | "-//IETF//DTD HTML LEVEL 1//EN//2.0" => 1, | ||
| 2671 | "-//IETF//DTD HTML LEVEL 2//EN" => 1, | ||
| 2672 | "-//IETF//DTD HTML LEVEL 2//EN//2.0" => 1, | ||
| 2673 | "-//IETF//DTD HTML LEVEL 3//EN" => 1, | ||
| 2674 | "-//IETF//DTD HTML LEVEL 3//EN//3.0" => 1, | ||
| 2675 | "-//IETF//DTD HTML STRICT LEVEL 0//EN" => 1, | ||
| 2676 | "-//IETF//DTD HTML STRICT LEVEL 0//EN//2.0" => 1, | ||
| 2677 | "-//IETF//DTD HTML STRICT LEVEL 1//EN" => 1, | ||
| 2678 | "-//IETF//DTD HTML STRICT LEVEL 1//EN//2.0" => 1, | ||
| 2679 | "-//IETF//DTD HTML STRICT LEVEL 2//EN" => 1, | ||
| 2680 | "-//IETF//DTD HTML STRICT LEVEL 2//EN//2.0" => 1, | ||
| 2681 | "-//IETF//DTD HTML STRICT LEVEL 3//EN" => 1, | ||
| 2682 | "-//IETF//DTD HTML STRICT LEVEL 3//EN//3.0" => 1, | ||
| 2683 | "-//IETF//DTD HTML STRICT//EN" => 1, | ||
| 2684 | "-//IETF//DTD HTML STRICT//EN//2.0" => 1, | ||
| 2685 | "-//IETF//DTD HTML STRICT//EN//3.0" => 1, | ||
| 2686 | "-//IETF//DTD HTML//EN" => 1, | ||
| 2687 | "-//IETF//DTD HTML//EN//2.0" => 1, | ||
| 2688 | "-//IETF//DTD HTML//EN//3.0" => 1, | ||
| 2689 | "-//METRIUS//DTD METRIUS PRESENTATIONAL//EN" => 1, | ||
| 2690 | "-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML STRICT//EN" => 1, | ||
| 2691 | "-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML//EN" => 1, | ||
| 2692 | "-//MICROSOFT//DTD INTERNET EXPLORER 2.0 TABLES//EN" => 1, | ||
| 2693 | "-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML STRICT//EN" => 1, | ||
| 2694 | "-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML//EN" => 1, | ||
| 2695 | "-//MICROSOFT//DTD INTERNET EXPLORER 3.0 TABLES//EN" => 1, | ||
| 2696 | "-//NETSCAPE COMM. CORP.//DTD HTML//EN" => 1, | ||
| 2697 | "-//NETSCAPE COMM. CORP.//DTD STRICT HTML//EN" => 1, | ||
| 2698 | "-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//EN" => 1, | ||
| 2699 | "-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//EN" => 1, | ||
| 2700 | "-//SPYGLASS//DTD HTML 2.0 EXTENDED//EN" => 1, | ||
| 2701 | "-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//EN" => 1, | ||
| 2702 | "-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//EN" => 1, | ||
| 2703 | "-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA STRICT HTML//EN" => 1, | ||
| 2704 | "-//W3C//DTD HTML 3 1995-03-24//EN" => 1, | ||
| 2705 | "-//W3C//DTD HTML 3.2 DRAFT//EN" => 1, | ||
| 2706 | "-//W3C//DTD HTML 3.2 FINAL//EN" => 1, | ||
| 2707 | "-//W3C//DTD HTML 3.2//EN" => 1, | ||
| 2708 | "-//W3C//DTD HTML 3.2S DRAFT//EN" => 1, | ||
| 2709 | "-//W3C//DTD HTML 4.0 FRAMESET//EN" => 1, | ||
| 2710 | "-//W3C//DTD HTML 4.0 TRANSITIONAL//EN" => 1, | ||
| 2711 | "-//W3C//DTD HTML EXPERIMETNAL 19960712//EN" => 1, | ||
| 2712 | "-//W3C//DTD HTML EXPERIMENTAL 970421//EN" => 1, | ||
| 2713 | "-//W3C//DTD W3 HTML//EN" => 1, | ||
| 2714 | "-//W3O//DTD W3 HTML 3.0//EN" => 1, | ||
| 2715 | "-//W3O//DTD W3 HTML 3.0//EN//" => 1, | ||
| 2716 | "-//W3O//DTD W3 HTML STRICT 3.0//EN//" => 1, | ||
| 2717 | "-//WEBTECHS//DTD MOZILLA HTML 2.0//EN" => 1, | ||
| 2718 | "-//WEBTECHS//DTD MOZILLA HTML//EN" => 1, | ||
| 2719 | "-/W3C/DTD HTML 4.0 TRANSITIONAL/EN" => 1, | ||
| 2720 | "HTML" => 1, | ||
| 2721 | }->{$pubid}) { | ||
| 2722 | $self->{document}->manakai_compat_mode ('quirks'); | ||
| 2723 | } elsif ($pubid eq "-//W3C//DTD HTML 4.01 FRAMESET//EN" or | ||
| 2724 | $pubid eq "-//W3C//DTD HTML 4.01 TRANSITIONAL//EN") { | ||
| 2725 | if (defined $token->{system_identifier}) { | ||
| 2726 | $self->{document}->manakai_compat_mode ('quirks'); | ||
| 2727 | } else { | ||
| 2728 | $self->{document}->manakai_compat_mode ('limited quirks'); | ||
| 2729 | wakaba | 1.3 | } |
| 2730 | wakaba | 1.18 | } elsif ($pubid eq "-//W3C//DTD XHTML 1.0 Frameset//EN" or |
| 2731 | $pubid eq "-//W3C//DTD XHTML 1.0 Transitional//EN") { | ||
| 2732 | $self->{document}->manakai_compat_mode ('limited quirks'); | ||
| 2733 | } | ||
| 2734 | } | ||
| 2735 | if (defined $token->{system_identifier}) { | ||
| 2736 | my $sysid = $token->{system_identifier}; | ||
| 2737 | $sysid =~ tr/A-Z/a-z/; | ||
| 2738 | if ($sysid eq "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd") { | ||
| 2739 | $self->{document}->manakai_compat_mode ('quirks'); | ||
| 2740 | } | ||
| 2741 | } | ||
| 2742 | |||
| 2743 | ## Go to the root element phase. | ||
| 2744 | $token = $self->_get_next_token; | ||
| 2745 | return; | ||
| 2746 | } elsif ({ | ||
| 2747 | 'start tag' => 1, | ||
| 2748 | 'end tag' => 1, | ||
| 2749 | 'end-of-file' => 1, | ||
| 2750 | }->{$token->{type}}) { | ||
| 2751 | $self->{parse_error}-> (type => 'no DOCTYPE'); | ||
| 2752 | $self->{document}->manakai_compat_mode ('quirks'); | ||
| 2753 | ## Go to the root element phase | ||
| 2754 | ## reprocess | ||
| 2755 | return; | ||
| 2756 | } elsif ($token->{type} eq 'character') { | ||
| 2757 | if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D | ||
| 2758 | ## Ignore the token | ||
| 2759 | wakaba | 1.26 | |
| 2760 | wakaba | 1.18 | unless (length $token->{data}) { |
| 2761 | ## Stay in the phase | ||
| 2762 | $token = $self->_get_next_token; | ||
| 2763 | redo INITIAL; | ||
| 2764 | wakaba | 1.3 | } |
| 2765 | } | ||
| 2766 | wakaba | 1.18 | |
| 2767 | $self->{parse_error}-> (type => 'no DOCTYPE'); | ||
| 2768 | $self->{document}->manakai_compat_mode ('quirks'); | ||
| 2769 | ## Go to the root element phase | ||
| 2770 | ## reprocess | ||
| 2771 | return; | ||
| 2772 | } elsif ($token->{type} eq 'comment') { | ||
| 2773 | my $comment = $self->{document}->create_comment ($token->{data}); | ||
| 2774 | $self->{document}->append_child ($comment); | ||
| 2775 | |||
| 2776 | ## Stay in the phase. | ||
| 2777 | $token = $self->_get_next_token; | ||
| 2778 | redo INITIAL; | ||
| 2779 | } else { | ||
| 2780 | die "$0: $token->{type}: Unknown token"; | ||
| 2781 | } | ||
| 2782 | } # INITIAL | ||
| 2783 | wakaba | 1.3 | } # _tree_construction_initial |
| 2784 | |||
| 2785 | sub _tree_construction_root_element ($) { | ||
| 2786 | my $self = shift; | ||
| 2787 | |||
| 2788 | B: { | ||
| 2789 | if ($token->{type} eq 'DOCTYPE') { | ||
| 2790 | $self->{parse_error}-> (type => 'in html:#DOCTYPE'); | ||
| 2791 | ## Ignore the token | ||
| 2792 | ## Stay in the phase | ||
| 2793 | $token = $self->_get_next_token; | ||
| 2794 | redo B; | ||
| 2795 | } elsif ($token->{type} eq 'comment') { | ||
| 2796 | my $comment = $self->{document}->create_comment ($token->{data}); | ||
| 2797 | $self->{document}->append_child ($comment); | ||
| 2798 | ## Stay in the phase | ||
| 2799 | $token = $self->_get_next_token; | ||
| 2800 | redo B; | ||
| 2801 | } elsif ($token->{type} eq 'character') { | ||
| 2802 | wakaba | 1.26 | if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
| 2803 | ## Ignore the token. | ||
| 2804 | |||
| 2805 | wakaba | 1.3 | unless (length $token->{data}) { |
| 2806 | ## Stay in the phase | ||
| 2807 | $token = $self->_get_next_token; | ||
| 2808 | redo B; | ||
| 2809 | } | ||
| 2810 | } | ||
| 2811 | # | ||
| 2812 | } elsif ({ | ||
| 2813 | 'start tag' => 1, | ||
| 2814 | 'end tag' => 1, | ||
| 2815 | 'end-of-file' => 1, | ||
| 2816 | }->{$token->{type}}) { | ||
| 2817 | ## ISSUE: There is an issue in the spec | ||
| 2818 | # | ||
| 2819 | } else { | ||
| 2820 | die "$0: $token->{type}: Unknown token"; | ||
| 2821 | } | ||
| 2822 | my $root_element; | ||
| 2823 | $root_element = $self->{document}->create_element_ns | ||
| 2824 | (q<http://www.w3.org/1999/xhtml>, [undef, 'html']); | ||
| 2825 | |||
| 2826 | $self->{document}->append_child ($root_element); | ||
| 2827 | push @{$self->{open_elements}}, [$root_element, 'html']; | ||
| 2828 | ## reprocess | ||
| 2829 | #redo B; | ||
| 2830 | wakaba | 1.35 | return; ## Go to the main phase. |
| 2831 | wakaba | 1.3 | } # B |
| 2832 | } # _tree_construction_root_element | ||
| 2833 | |||
| 2834 | sub _reset_insertion_mode ($) { | ||
| 2835 | my $self = shift; | ||
| 2836 | |||
| 2837 | ## Step 1 | ||
| 2838 | my $last; | ||
| 2839 | |||
| 2840 | ## Step 2 | ||
| 2841 | my $i = -1; | ||
| 2842 | my $node = $self->{open_elements}->[$i]; | ||
| 2843 | |||
| 2844 | ## Step 3 | ||
| 2845 | S3: { | ||
| 2846 | wakaba | 1.29 | ## ISSUE: Oops! "If node is the first node in the stack of open |
| 2847 | ## elements, then set last to true. If the context element of the | ||
| 2848 | ## HTML fragment parsing algorithm is neither a td element nor a | ||
| 2849 | ## th element, then set node to the context element. (fragment case)": | ||
| 2850 | ## The second "if" is in the scope of the first "if"!? | ||
| 2851 | if ($self->{open_elements}->[0]->[0] eq $node->[0]) { | ||
| 2852 | $last = 1; | ||
| 2853 | if (defined $self->{inner_html_node}) { | ||
| 2854 | if ($self->{inner_html_node}->[1] eq 'td' or | ||
| 2855 | $self->{inner_html_node}->[1] eq 'th') { | ||
| 2856 | # | ||
| 2857 | } else { | ||
| 2858 | $node = $self->{inner_html_node}; | ||
| 2859 | } | ||
| 2860 | wakaba | 1.3 | } |
| 2861 | } | ||
| 2862 | |||
| 2863 | ## Step 4..13 | ||
| 2864 | my $new_mode = { | ||
| 2865 | select => 'in select', | ||
| 2866 | td => 'in cell', | ||
| 2867 | th => 'in cell', | ||
| 2868 | tr => 'in row', | ||
| 2869 | tbody => 'in table body', | ||
| 2870 | thead => 'in table head', | ||
| 2871 | tfoot => 'in table foot', | ||
| 2872 | caption => 'in caption', | ||
| 2873 | colgroup => 'in column group', | ||
| 2874 | table => 'in table', | ||
| 2875 | head => 'in body', # not in head! | ||
| 2876 | body => 'in body', | ||
| 2877 | frameset => 'in frameset', | ||
| 2878 | }->{$node->[1]}; | ||
| 2879 | $self->{insertion_mode} = $new_mode and return if defined $new_mode; | ||
| 2880 | |||
| 2881 | ## Step 14 | ||
| 2882 | if ($node->[1] eq 'html') { | ||
| 2883 | unless (defined $self->{head_element}) { | ||
| 2884 | $self->{insertion_mode} = 'before head'; | ||
| 2885 | } else { | ||
| 2886 | $self->{insertion_mode} = 'after head'; | ||
| 2887 | } | ||
| 2888 | return; | ||
| 2889 | } | ||
| 2890 | |||
| 2891 | ## Step 15 | ||
| 2892 | $self->{insertion_mode} = 'in body' and return if $last; | ||
| 2893 | |||
| 2894 | ## Step 16 | ||
| 2895 | $i--; | ||
| 2896 | $node = $self->{open_elements}->[$i]; | ||
| 2897 | |||
| 2898 | ## Step 17 | ||
| 2899 | redo S3; | ||
| 2900 | } # S3 | ||
| 2901 | } # _reset_insertion_mode | ||
| 2902 | |||
| 2903 | sub _tree_construction_main ($) { | ||
| 2904 | my $self = shift; | ||
| 2905 | |||
| 2906 | wakaba | 1.35 | my $previous_insertion_mode; |
| 2907 | wakaba | 1.1 | |
| 2908 | my $active_formatting_elements = []; | ||
| 2909 | |||
| 2910 | my $reconstruct_active_formatting_elements = sub { # MUST | ||
| 2911 | my $insert = shift; | ||
| 2912 | |||
| 2913 | ## Step 1 | ||
| 2914 | return unless @$active_formatting_elements; | ||
| 2915 | |||
| 2916 | ## Step 3 | ||
| 2917 | my $i = -1; | ||
| 2918 | my $entry = $active_formatting_elements->[$i]; | ||
| 2919 | |||
| 2920 | ## Step 2 | ||
| 2921 | return if $entry->[0] eq '#marker'; | ||
| 2922 | wakaba | 1.3 | for (@{$self->{open_elements}}) { |
| 2923 | wakaba | 1.1 | if ($entry->[0] eq $_->[0]) { |
| 2924 | return; | ||
| 2925 | } | ||
| 2926 | } | ||
| 2927 | |||
| 2928 | S4: { | ||
| 2929 | ## Step 4 | ||
| 2930 | last S4 if $active_formatting_elements->[0]->[0] eq $entry->[0]; | ||
| 2931 | |||
| 2932 | ## Step 5 | ||
| 2933 | $i--; | ||
| 2934 | $entry = $active_formatting_elements->[$i]; | ||
| 2935 | |||
| 2936 | ## Step 6 | ||
| 2937 | if ($entry->[0] eq '#marker') { | ||
| 2938 | # | ||
| 2939 | } else { | ||
| 2940 | my $in_open_elements; | ||
| 2941 | wakaba | 1.3 | OE: for (@{$self->{open_elements}}) { |
| 2942 | wakaba | 1.1 | if ($entry->[0] eq $_->[0]) { |
| 2943 | $in_open_elements = 1; | ||
| 2944 | last OE; | ||
| 2945 | } | ||
| 2946 | } | ||
| 2947 | if ($in_open_elements) { | ||
| 2948 | # | ||
| 2949 | } else { | ||
| 2950 | redo S4; | ||
| 2951 | } | ||
| 2952 | } | ||
| 2953 | |||
| 2954 | ## Step 7 | ||
| 2955 | $i++; | ||
| 2956 | $entry = $active_formatting_elements->[$i]; | ||
| 2957 | } # S4 | ||
| 2958 | |||
| 2959 | S7: { | ||
| 2960 | ## Step 8 | ||
| 2961 | my $clone = [$entry->[0]->clone_node (0), $entry->[1]]; | ||
| 2962 | |||
| 2963 | ## Step 9 | ||
| 2964 | $insert->($clone->[0]); | ||
| 2965 | wakaba | 1.3 | push @{$self->{open_elements}}, $clone; |
| 2966 | wakaba | 1.1 | |
| 2967 | ## Step 10 | ||
| 2968 | wakaba | 1.3 | $active_formatting_elements->[$i] = $self->{open_elements}->[-1]; |
| 2969 | wakaba | 1.1 | |
| 2970 | ## Step 11 | ||
| 2971 | unless ($clone->[0] eq $active_formatting_elements->[-1]->[0]) { | ||
| 2972 | ## Step 7' | ||
| 2973 | $i++; | ||
| 2974 | $entry = $active_formatting_elements->[$i]; | ||
| 2975 | |||
| 2976 | redo S7; | ||
| 2977 | } | ||
| 2978 | } # S7 | ||
| 2979 | }; # $reconstruct_active_formatting_elements | ||
| 2980 | |||
| 2981 | my $clear_up_to_marker = sub { | ||
| 2982 | for (reverse 0..$#$active_formatting_elements) { | ||
| 2983 | if ($active_formatting_elements->[$_]->[0] eq '#marker') { | ||
| 2984 | splice @$active_formatting_elements, $_; | ||
| 2985 | return; | ||
| 2986 | } | ||
| 2987 | } | ||
| 2988 | }; # $clear_up_to_marker | ||
| 2989 | |||
| 2990 | wakaba | 1.25 | my $parse_rcdata = sub ($$) { |
| 2991 | my ($content_model_flag, $insert) = @_; | ||
| 2992 | |||
| 2993 | ## Step 1 | ||
| 2994 | my $start_tag_name = $token->{tag_name}; | ||
| 2995 | my $el; | ||
| 2996 | |||
| 2997 | $el = $self->{document}->create_element_ns | ||
| 2998 | (q<http://www.w3.org/1999/xhtml>, [undef, $start_tag_name]); | ||
| 2999 | wakaba | 1.1 | |
| 3000 | wakaba | 1.6 | for my $attr_name (keys %{ $token->{attributes}}) { |
| 3001 | wakaba | 1.25 | $el->set_attribute_ns (undef, [undef, $attr_name], |
| 3002 | wakaba | 1.6 | $token->{attributes} ->{$attr_name}->{value}); |
| 3003 | } | ||
| 3004 | |||
| 3005 | wakaba | 1.25 | |
| 3006 | ## Step 2 | ||
| 3007 | $insert->($el); # /context node/->append_child ($el) | ||
| 3008 | |||
| 3009 | ## Step 3 | ||
| 3010 | $self->{content_model_flag} = $content_model_flag; # CDATA or RCDATA | ||
| 3011 | wakaba | 1.13 | delete $self->{escape}; # MUST |
| 3012 | wakaba | 1.25 | |
| 3013 | ## Step 4 | ||
| 3014 | wakaba | 1.1 | my $text = ''; |
| 3015 | $token = $self->_get_next_token; | ||
| 3016 | wakaba | 1.25 | while ($token->{type} eq 'character') { # or until stop tokenizing |
| 3017 | wakaba | 1.1 | $text .= $token->{data}; |
| 3018 | $token = $self->_get_next_token; | ||
| 3019 | wakaba | 1.25 | } |
| 3020 | |||
| 3021 | ## Step 5 | ||
| 3022 | wakaba | 1.1 | if (length $text) { |
| 3023 | wakaba | 1.25 | my $text = $self->{document}->create_text_node ($text); |
| 3024 | $el->append_child ($text); | ||
| 3025 | wakaba | 1.1 | } |
| 3026 | wakaba | 1.25 | |
| 3027 | ## Step 6 | ||
| 3028 | wakaba | 1.1 | $self->{content_model_flag} = 'PCDATA'; |
| 3029 | wakaba | 1.25 | |
| 3030 | ## Step 7 | ||
| 3031 | if ($token->{type} eq 'end tag' and $token->{tag_name} eq $start_tag_name) { | ||
| 3032 | wakaba | 1.1 | ## Ignore the token |
| 3033 | } else { | ||
| 3034 | wakaba | 1.25 | $self->{parse_error}-> (type => 'in '.$content_model_flag.':#'.$token->{type}); |
| 3035 | wakaba | 1.1 | } |
| 3036 | $token = $self->_get_next_token; | ||
| 3037 | wakaba | 1.25 | }; # $parse_rcdata |
| 3038 | wakaba | 1.1 | |
| 3039 | wakaba | 1.25 | my $script_start_tag = sub ($) { |
| 3040 | my $insert = $_[0]; | ||
| 3041 | wakaba | 1.1 | my $script_el; |
| 3042 | |||
| 3043 | $script_el = $self->{document}->create_element_ns | ||
| 3044 | (q<http://www.w3.org/1999/xhtml>, [undef, 'script']); | ||
| 3045 | |||
| 3046 | for my $attr_name (keys %{ $token->{attributes}}) { | ||
| 3047 | $script_el->set_attribute_ns (undef, [undef, $attr_name], | ||
| 3048 | $token->{attributes} ->{$attr_name}->{value}); | ||
| 3049 | } | ||
| 3050 | |||
| 3051 | ## TODO: mark as "parser-inserted" | ||
| 3052 | |||
| 3053 | $self->{content_model_flag} = 'CDATA'; | ||
| 3054 | wakaba | 1.13 | delete $self->{escape}; # MUST |
| 3055 | wakaba | 1.1 | |
| 3056 | my $text = ''; | ||
| 3057 | $token = $self->_get_next_token; | ||
| 3058 | while ($token->{type} eq 'character') { | ||
| 3059 | $text .= $token->{data}; | ||
| 3060 | $token = $self->_get_next_token; | ||
| 3061 | } # stop if non-character token or tokenizer stops tokenising | ||
| 3062 | if (length $text) { | ||
| 3063 | $script_el->manakai_append_text ($text); | ||
| 3064 | } | ||
| 3065 | |||
| 3066 | $self->{content_model_flag} = 'PCDATA'; | ||
| 3067 | |||
| 3068 | if ($token->{type} eq 'end tag' and | ||
| 3069 | $token->{tag_name} eq 'script') { | ||
| 3070 | ## Ignore the token | ||
| 3071 | } else { | ||
| 3072 | wakaba | 1.3 | $self->{parse_error}-> (type => 'in CDATA:#'.$token->{type}); |
| 3073 | wakaba | 1.1 | ## ISSUE: And ignore? |
| 3074 | ## TODO: mark as "already executed" | ||
| 3075 | } | ||
| 3076 | |||
| 3077 | wakaba | 1.3 | if (defined $self->{inner_html_node}) { |
| 3078 | ## TODO: mark as "already executed" | ||
| 3079 | } else { | ||
| 3080 | wakaba | 1.1 | ## TODO: $old_insertion_point = current insertion point |
| 3081 | ## TODO: insertion point = just before the next input character | ||
| 3082 | wakaba | 1.25 | |
| 3083 | $insert->($script_el); | ||
| 3084 | wakaba | 1.1 | |
| 3085 | ## TODO: insertion point = $old_insertion_point (might be "undefined") | ||
| 3086 | |||
| 3087 | ## TODO: if there is a script that will execute as soon as the parser resume, then... | ||
| 3088 | } | ||
| 3089 | |||
| 3090 | $token = $self->_get_next_token; | ||
| 3091 | }; # $script_start_tag | ||
| 3092 | |||
| 3093 | my $formatting_end_tag = sub { | ||
| 3094 | my $tag_name = shift; | ||
| 3095 | |||
| 3096 | FET: { | ||
| 3097 | ## Step 1 | ||
| 3098 | my $formatting_element; | ||
| 3099 | my $formatting_element_i_in_active; | ||
| 3100 | AFE: for (reverse 0..$#$active_formatting_elements) { | ||
| 3101 | if ($active_formatting_elements->[$_]->[1] eq $tag_name) { | ||
| 3102 | $formatting_element = $active_formatting_elements->[$_]; | ||
| 3103 | $formatting_element_i_in_active = $_; | ||
| 3104 | last AFE; | ||
| 3105 | } elsif ($active_formatting_elements->[$_]->[0] eq '#marker') { | ||
| 3106 | last AFE; | ||
| 3107 | } | ||
| 3108 | } # AFE | ||
| 3109 | unless (defined $formatting_element) { | ||
| 3110 | wakaba | 1.3 | $self->{parse_error}-> (type => 'unmatched end tag:'.$tag_name); |
| 3111 | wakaba | 1.1 | ## Ignore the token |
| 3112 | $token = $self->_get_next_token; | ||
| 3113 | return; | ||
| 3114 | } | ||
| 3115 | ## has an element in scope | ||
| 3116 | my $in_scope = 1; | ||
| 3117 | my $formatting_element_i_in_open; | ||
| 3118 | wakaba | 1.3 | INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3119 | my $node = $self->{open_elements}->[$_]; | ||
| 3120 | wakaba | 1.1 | if ($node->[0] eq $formatting_element->[0]) { |
| 3121 | if ($in_scope) { | ||
| 3122 | $formatting_element_i_in_open = $_; | ||
| 3123 | last INSCOPE; | ||
| 3124 | } else { # in open elements but not in scope | ||
| 3125 | wakaba | 1.4 | $self->{parse_error}-> (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3126 | wakaba | 1.1 | ## Ignore the token |
| 3127 | $token = $self->_get_next_token; | ||
| 3128 | return; | ||
| 3129 | } | ||
| 3130 | } elsif ({ | ||
| 3131 | table => 1, caption => 1, td => 1, th => 1, | ||
| 3132 | button => 1, marquee => 1, object => 1, html => 1, | ||
| 3133 | }->{$node->[1]}) { | ||
| 3134 | $in_scope = 0; | ||
| 3135 | } | ||
| 3136 | } # INSCOPE | ||
| 3137 | unless (defined $formatting_element_i_in_open) { | ||
| 3138 | wakaba | 1.4 | $self->{parse_error}-> (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3139 | wakaba | 1.1 | pop @$active_formatting_elements; # $formatting_element |
| 3140 | $token = $self->_get_next_token; ## TODO: ok? | ||
| 3141 | return; | ||
| 3142 | } | ||
| 3143 | wakaba | 1.3 | if (not $self->{open_elements}->[-1]->[0] eq $formatting_element->[0]) { |
| 3144 | wakaba | 1.4 | $self->{parse_error}-> (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3145 | wakaba | 1.1 | } |
| 3146 | |||
| 3147 | ## Step 2 | ||
| 3148 | my $furthest_block; | ||
| 3149 | my $furthest_block_i_in_open; | ||
| 3150 | wakaba | 1.3 | OE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3151 | my $node = $self->{open_elements}->[$_]; | ||
| 3152 | wakaba | 1.1 | if (not $formatting_category->{$node->[1]} and |
| 3153 | #not $phrasing_category->{$node->[1]} and | ||
| 3154 | ($special_category->{$node->[1]} or | ||
| 3155 | $scoping_category->{$node->[1]})) { | ||
| 3156 | $furthest_block = $node; | ||
| 3157 | $furthest_block_i_in_open = $_; | ||
| 3158 | } elsif ($node->[0] eq $formatting_element->[0]) { | ||
| 3159 | last OE; | ||
| 3160 | } | ||
| 3161 | } # OE | ||
| 3162 | |||
| 3163 | ## Step 3 | ||
| 3164 | unless (defined $furthest_block) { # MUST | ||
| 3165 | wakaba | 1.3 | splice @{$self->{open_elements}}, $formatting_element_i_in_open; |
| 3166 | wakaba | 1.1 | splice @$active_formatting_elements, $formatting_element_i_in_active, 1; |
| 3167 | $token = $self->_get_next_token; | ||
| 3168 | return; | ||
| 3169 | } | ||
| 3170 | |||
| 3171 | ## Step 4 | ||
| 3172 | wakaba | 1.3 | my $common_ancestor_node = $self->{open_elements}->[$formatting_element_i_in_open - 1]; |
| 3173 | wakaba | 1.1 | |
| 3174 | ## Step 5 | ||
| 3175 | my $furthest_block_parent = $furthest_block->[0]->parent_node; | ||
| 3176 | if (defined $furthest_block_parent) { | ||
| 3177 | $furthest_block_parent->remove_child ($furthest_block->[0]); | ||
| 3178 | } | ||
| 3179 | |||
| 3180 | ## Step 6 | ||
| 3181 | my $bookmark_prev_el | ||
| 3182 | = $active_formatting_elements->[$formatting_element_i_in_active - 1] | ||
| 3183 | ->[0]; | ||
| 3184 | |||
| 3185 | ## Step 7 | ||
| 3186 | my $node = $furthest_block; | ||
| 3187 | my $node_i_in_open = $furthest_block_i_in_open; | ||
| 3188 | my $last_node = $furthest_block; | ||
| 3189 | S7: { | ||
| 3190 | ## Step 1 | ||
| 3191 | $node_i_in_open--; | ||
| 3192 | wakaba | 1.3 | $node = $self->{open_elements}->[$node_i_in_open]; |
| 3193 | wakaba | 1.1 | |
| 3194 | ## Step 2 | ||
| 3195 | my $node_i_in_active; | ||
| 3196 | S7S2: { | ||
| 3197 | for (reverse 0..$#$active_formatting_elements) { | ||
| 3198 | if ($active_formatting_elements->[$_]->[0] eq $node->[0]) { | ||
| 3199 | $node_i_in_active = $_; | ||
| 3200 | last S7S2; | ||
| 3201 | } | ||
| 3202 | } | ||
| 3203 | wakaba | 1.3 | splice @{$self->{open_elements}}, $node_i_in_open, 1; |
| 3204 | wakaba | 1.1 | redo S7; |
| 3205 | } # S7S2 | ||
| 3206 | |||
| 3207 | ## Step 3 | ||
| 3208 | last S7 if $node->[0] eq $formatting_element->[0]; | ||
| 3209 | |||
| 3210 | ## Step 4 | ||
| 3211 | if ($last_node->[0] eq $furthest_block->[0]) { | ||
| 3212 | $bookmark_prev_el = $node->[0]; | ||
| 3213 | } | ||
| 3214 | |||
| 3215 | ## Step 5 | ||
| 3216 | if ($node->[0]->has_child_nodes ()) { | ||
| 3217 | my $clone = [$node->[0]->clone_node (0), $node->[1]]; | ||
| 3218 | $active_formatting_elements->[$node_i_in_active] = $clone; | ||
| 3219 | wakaba | 1.3 | $self->{open_elements}->[$node_i_in_open] = $clone; |
| 3220 | wakaba | 1.1 | $node = $clone; |
| 3221 | } | ||
| 3222 | |||
| 3223 | ## Step 6 | ||
| 3224 | $node->[0]->append_child ($last_node->[0]); | ||
| 3225 | |||
| 3226 | ## Step 7 | ||
| 3227 | $last_node = $node; | ||
| 3228 | |||
| 3229 | ## Step 8 | ||
| 3230 | redo S7; | ||
| 3231 | } # S7 | ||
| 3232 | |||
| 3233 | ## Step 8 | ||
| 3234 | $common_ancestor_node->[0]->append_child ($last_node->[0]); | ||
| 3235 | |||
| 3236 | ## Step 9 | ||
| 3237 | my $clone = [$formatting_element->[0]->clone_node (0), | ||
| 3238 | $formatting_element->[1]]; | ||
| 3239 | |||
| 3240 | ## Step 10 | ||
| 3241 | my @cn = @{$furthest_block->[0]->child_nodes}; | ||
| 3242 | $clone->[0]->append_child ($_) for @cn; | ||
| 3243 | |||
| 3244 | ## Step 11 | ||
| 3245 | $furthest_block->[0]->append_child ($clone->[0]); | ||
| 3246 | |||
| 3247 | ## Step 12 | ||
| 3248 | my $i; | ||
| 3249 | AFE: for (reverse 0..$#$active_formatting_elements) { | ||
| 3250 | if ($active_formatting_elements->[$_]->[0] eq $formatting_element->[0]) { | ||
| 3251 | splice @$active_formatting_elements, $_, 1; | ||
| 3252 | $i-- and last AFE if defined $i; | ||
| 3253 | } elsif ($active_formatting_elements->[$_]->[0] eq $bookmark_prev_el) { | ||
| 3254 | $i = $_; | ||
| 3255 | } | ||
| 3256 | } # AFE | ||
| 3257 | splice @$active_formatting_elements, $i + 1, 0, $clone; | ||
| 3258 | |||
| 3259 | ## Step 13 | ||
| 3260 | undef $i; | ||
| 3261 | wakaba | 1.3 | OE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3262 | if ($self->{open_elements}->[$_]->[0] eq $formatting_element->[0]) { | ||
| 3263 | splice @{$self->{open_elements}}, $_, 1; | ||
| 3264 | wakaba | 1.1 | $i-- and last OE if defined $i; |
| 3265 | wakaba | 1.3 | } elsif ($self->{open_elements}->[$_]->[0] eq $furthest_block->[0]) { |
| 3266 | wakaba | 1.1 | $i = $_; |
| 3267 | } | ||
| 3268 | } # OE | ||
| 3269 | wakaba | 1.3 | splice @{$self->{open_elements}}, $i + 1, 1, $clone; |
| 3270 | wakaba | 1.1 | |
| 3271 | ## Step 14 | ||
| 3272 | redo FET; | ||
| 3273 | } # FET | ||
| 3274 | }; # $formatting_end_tag | ||
| 3275 | |||
| 3276 | my $insert_to_current = sub { | ||
| 3277 | wakaba | 1.25 | $self->{open_elements}->[-1]->[0]->append_child ($_[0]); |
| 3278 | wakaba | 1.1 | }; # $insert_to_current |
| 3279 | |||
| 3280 | my $insert_to_foster = sub { | ||
| 3281 | my $child = shift; | ||
| 3282 | if ({ | ||
| 3283 | table => 1, tbody => 1, tfoot => 1, | ||
| 3284 | thead => 1, tr => 1, | ||
| 3285 | wakaba | 1.3 | }->{$self->{open_elements}->[-1]->[1]}) { |
| 3286 | wakaba | 1.1 | # MUST |
| 3287 | my $foster_parent_element; | ||
| 3288 | my $next_sibling; | ||
| 3289 | wakaba | 1.3 | OE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3290 | if ($self->{open_elements}->[$_]->[1] eq 'table') { | ||
| 3291 | my $parent = $self->{open_elements}->[$_]->[0]->parent_node; | ||
| 3292 | wakaba | 1.1 | if (defined $parent and $parent->node_type == 1) { |
| 3293 | $foster_parent_element = $parent; | ||
| 3294 | wakaba | 1.3 | $next_sibling = $self->{open_elements}->[$_]->[0]; |
| 3295 | wakaba | 1.1 | } else { |
| 3296 | $foster_parent_element | ||
| 3297 | wakaba | 1.3 | = $self->{open_elements}->[$_ - 1]->[0]; |
| 3298 | wakaba | 1.1 | } |
| 3299 | last OE; | ||
| 3300 | } | ||
| 3301 | } # OE | ||
| 3302 | wakaba | 1.3 | $foster_parent_element = $self->{open_elements}->[0]->[0] |
| 3303 | wakaba | 1.1 | unless defined $foster_parent_element; |
| 3304 | $foster_parent_element->insert_before | ||
| 3305 | ($child, $next_sibling); | ||
| 3306 | } else { | ||
| 3307 | wakaba | 1.3 | $self->{open_elements}->[-1]->[0]->append_child ($child); |
| 3308 | wakaba | 1.1 | } |
| 3309 | }; # $insert_to_foster | ||
| 3310 | |||
| 3311 | my $in_body = sub { | ||
| 3312 | my $insert = shift; | ||
| 3313 | if ($token->{type} eq 'start tag') { | ||
| 3314 | if ($token->{tag_name} eq 'script') { | ||
| 3315 | wakaba | 1.25 | ## NOTE: This is an "as if in head" code clone |
| 3316 | $script_start_tag->($insert); | ||
| 3317 | wakaba | 1.1 | return; |
| 3318 | } elsif ($token->{tag_name} eq 'style') { | ||
| 3319 | wakaba | 1.25 | ## NOTE: This is an "as if in head" code clone |
| 3320 | $parse_rcdata->('CDATA', $insert); | ||
| 3321 | wakaba | 1.1 | return; |
| 3322 | } elsif ({ | ||
| 3323 | wakaba | 1.35 | base => 1, link => 1, |
| 3324 | wakaba | 1.1 | }->{$token->{tag_name}}) { |
| 3325 | wakaba | 1.25 | ## NOTE: This is an "as if in head" code clone, only "-t" differs |
| 3326 | wakaba | 1.1 | |
| 3327 | wakaba | 1.25 | { |
| 3328 | my $el; | ||
| 3329 | |||
| 3330 | wakaba | 1.1 | $el = $self->{document}->create_element_ns |
| 3331 | (q<http://www.w3.org/1999/xhtml>, [undef, $token->{tag_name}]); | ||
| 3332 | |||
| 3333 | wakaba | 1.25 | for my $attr_name (keys %{ $token->{attributes}}) { |
| 3334 | wakaba | 1.1 | $el->set_attribute_ns (undef, [undef, $attr_name], |
| 3335 | wakaba | 1.25 | $token->{attributes} ->{$attr_name}->{value}); |
| 3336 | wakaba | 1.1 | } |
| 3337 | |||
| 3338 | wakaba | 1.25 | $insert->($el); |
| 3339 | push @{$self->{open_elements}}, [$el, $token->{tag_name}]; | ||
| 3340 | } | ||
| 3341 | |||
| 3342 | pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. | ||
| 3343 | wakaba | 1.1 | $token = $self->_get_next_token; |
| 3344 | return; | ||
| 3345 | wakaba | 1.34 | } elsif ($token->{tag_name} eq 'meta') { |
| 3346 | ## NOTE: This is an "as if in head" code clone, only "-t" differs | ||
| 3347 | |||
| 3348 | { | ||
| 3349 | my $el; | ||
| 3350 | |||
| 3351 | $el = $self->{document}->create_element_ns | ||
| 3352 | (q<http://www.w3.org/1999/xhtml>, [undef, $token->{tag_name}]); | ||
| 3353 | |||
| 3354 | for my $attr_name (keys %{ $token->{attributes}}) { | ||
| 3355 | $el->set_attribute_ns (undef, [undef, $attr_name], | ||
| 3356 | $token->{attributes} ->{$attr_name}->{value}); | ||
| 3357 | } | ||
| 3358 | |||
| 3359 | $insert->($el); | ||
| 3360 | push @{$self->{open_elements}}, [$el, $token->{tag_name}]; | ||
| 3361 | } | ||
| 3362 | |||
| 3363 | pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. | ||
| 3364 | |||
| 3365 | unless ($self->{confident}) { | ||
| 3366 | my $charset; | ||
| 3367 | if ($token->{attributes}->{charset}) { ## TODO: And if supported | ||
| 3368 | $charset = $token->{attributes}->{charset}->{value}; | ||
| 3369 | } | ||
| 3370 | if ($token->{attributes}->{'http-equiv'}) { | ||
| 3371 | wakaba | 1.35 | ## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition. |
| 3372 | wakaba | 1.34 | if ($token->{attributes}->{'http-equiv'}->{value} |
| 3373 | =~ /\A[^;]*;[\x09-\x0D\x20]*charset[\x09-\x0D\x20]*= | ||
| 3374 | [\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| | ||
| 3375 | ([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { | ||
| 3376 | $charset = defined $1 ? $1 : defined $2 ? $2 : $3; | ||
| 3377 | } ## TODO: And if supported | ||
| 3378 | } | ||
| 3379 | ## TODO: Change the encoding | ||
| 3380 | } | ||
| 3381 | |||
| 3382 | $token = $self->_get_next_token; | ||
| 3383 | return; | ||
| 3384 | wakaba | 1.1 | } elsif ($token->{tag_name} eq 'title') { |
| 3385 | wakaba | 1.3 | $self->{parse_error}-> (type => 'in body:title'); |
| 3386 | wakaba | 1.25 | ## NOTE: This is an "as if in head" code clone |
| 3387 | wakaba | 1.31 | $parse_rcdata->('RCDATA', sub { |
| 3388 | if (defined $self->{head_element}) { | ||
| 3389 | $self->{head_element}->append_child ($_[0]); | ||
| 3390 | } else { | ||
| 3391 | $insert->($_[0]); | ||
| 3392 | } | ||
| 3393 | }); | ||
| 3394 | wakaba | 1.1 | return; |
| 3395 | } elsif ($token->{tag_name} eq 'body') { | ||
| 3396 | wakaba | 1.3 | $self->{parse_error}-> (type => 'in body:body'); |
| 3397 | wakaba | 1.1 | |
| 3398 | wakaba | 1.3 | if (@{$self->{open_elements}} == 1 or |
| 3399 | $self->{open_elements}->[1]->[1] ne 'body') { | ||
| 3400 | wakaba | 1.1 | ## Ignore the token |
| 3401 | } else { | ||
| 3402 | wakaba | 1.3 | my $body_el = $self->{open_elements}->[1]->[0]; |
| 3403 | wakaba | 1.1 | for my $attr_name (keys %{$token->{attributes}}) { |
| 3404 | unless ($body_el->has_attribute_ns (undef, $attr_name)) { | ||
| 3405 | $body_el->set_attribute_ns | ||
| 3406 | (undef, [undef, $attr_name], | ||
| 3407 | $token->{attributes}->{$attr_name}->{value}); | ||
| 3408 | } | ||
| 3409 | } | ||
| 3410 | } | ||
| 3411 | $token = $self->_get_next_token; | ||
| 3412 | return; | ||
| 3413 | } elsif ({ | ||
| 3414 | address => 1, blockquote => 1, center => 1, dir => 1, | ||
| 3415 | div => 1, dl => 1, fieldset => 1, listing => 1, | ||
| 3416 | menu => 1, ol => 1, p => 1, ul => 1, | ||
| 3417 | pre => 1, | ||
| 3418 | }->{$token->{tag_name}}) { | ||
| 3419 | ## has a p element in scope | ||
| 3420 | wakaba | 1.3 | INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 3421 | wakaba | 1.1 | if ($_->[1] eq 'p') { |
| 3422 | unshift @{$self->{token}}, $token; | ||
| 3423 | $token = {type => 'end tag', tag_name => 'p'}; | ||
| 3424 | return; | ||
| 3425 | } elsif ({ | ||
| 3426 | table => 1, caption => 1, td => 1, th => 1, | ||
| 3427 | button => 1, marquee => 1, object => 1, html => 1, | ||
| 3428 | }->{$_->[1]}) { | ||
| 3429 | last INSCOPE; | ||
| 3430 | } | ||
| 3431 | } # INSCOPE | ||
| 3432 | |||
| 3433 | |||
| 3434 | { | ||
| 3435 | my $el; | ||
| 3436 | |||
| 3437 | $el = $self->{document}->create_element_ns | ||
| 3438 | (q<http://www.w3.org/1999/xhtml>, [undef, $token->{tag_name}]); | ||
| 3439 | |||
| 3440 | for my $attr_name (keys %{ $token->{attributes}}) { | ||
| 3441 | $el->set_attribute_ns (undef, [undef, $attr_name], | ||
| 3442 | $token->{attributes} ->{$attr_name}->{value}); | ||
| 3443 | } | ||
| 3444 | |||
| 3445 | $insert->($el); | ||
| 3446 | wakaba | 1.3 | push @{$self->{open_elements}}, [$el, $token->{tag_name}]; |
| 3447 | wakaba | 1.1 | } |
| 3448 | |||
| 3449 | if ($token->{tag_name} eq 'pre') { | ||
| 3450 | $token = $self->_get_next_token; | ||
| 3451 | if ($token->{type} eq 'character') { | ||
| 3452 | $token->{data} =~ s/^\x0A//; | ||
| 3453 | unless (length $token->{data}) { | ||
| 3454 | $token = $self->_get_next_token; | ||
| 3455 | } | ||
| 3456 | } | ||
| 3457 | } else { | ||
| 3458 | $token = $self->_get_next_token; | ||
| 3459 | } | ||
| 3460 | return; | ||
| 3461 | } elsif ($token->{tag_name} eq 'form') { | ||
| 3462 | wakaba | 1.3 | if (defined $self->{form_element}) { |
| 3463 | $self->{parse_error}-> (type => 'in form:form'); | ||
| 3464 | wakaba | 1.1 | ## Ignore the token |
| 3465 | wakaba | 1.7 | $token = $self->_get_next_token; |
| 3466 | return; | ||
| 3467 | wakaba | 1.1 | } else { |
| 3468 | ## has a p element in scope | ||
| 3469 | wakaba | 1.3 | INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 3470 | wakaba | 1.1 | if ($_->[1] eq 'p') { |
| 3471 | unshift @{$self->{token}}, $token; | ||
| 3472 | $token = {type => 'end tag', tag_name => 'p'}; | ||
| 3473 | return; | ||
| 3474 | } elsif ({ | ||
| 3475 | table => 1, caption => 1, td => 1, th => 1, | ||
| 3476 | button => 1, marquee => 1, object => 1, html => 1, | ||
| 3477 | }->{$_->[1]}) { | ||
| 3478 | last INSCOPE; | ||
| 3479 | } | ||
| 3480 | } # INSCOPE | ||
| 3481 | |||
| 3482 | |||
| 3483 | { | ||
| 3484 | my $el; | ||
| 3485 | |||
| 3486 | $el = $self->{document}->create_element_ns | ||
| 3487 | (q<http://www.w3.org/1999/xhtml>, [undef, $token->{tag_name}]); | ||
| 3488 | |||
| 3489 | for my $attr_name (keys %{ $token->{attributes}}) { | ||
| 3490 | $el->set_attribute_ns (undef, [undef, $attr_name], | ||
| 3491 | $token->{attributes} ->{$attr_name}->{value}); | ||
| 3492 | } | ||
| 3493 | |||
| 3494 | $insert->($el); | ||
| 3495 | wakaba | 1.3 | push @{$self->{open_elements}}, [$el, $token->{tag_name}]; |
| 3496 | wakaba | 1.1 | } |
| 3497 | |||
| 3498 | wakaba | 1.3 | $self->{form_element} = $self->{open_elements}->[-1]->[0]; |
| 3499 | wakaba | 1.1 | $token = $self->_get_next_token; |
| 3500 | return; | ||
| 3501 | } | ||
| 3502 | } elsif ($token->{tag_name} eq 'li') { | ||
| 3503 | ## has a p element in scope | ||
| 3504 | wakaba | 1.3 | INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 3505 | wakaba | 1.1 | if ($_->[1] eq 'p') { |
| 3506 | unshift @{$self->{token}}, $token; | ||
| 3507 | $token = {type => 'end tag', tag_name => 'p'}; | ||
| 3508 | return; | ||
| 3509 | } elsif ({ | ||
| 3510 | table => 1, caption => 1, td => 1, th => 1, | ||
| 3511 | button => 1, marquee => 1, object => 1, html => 1, | ||
| 3512 | }->{$_->[1]}) { | ||
| 3513 | last INSCOPE; | ||
| 3514 | } | ||
| 3515 | } # INSCOPE | ||
| 3516 | |||
| 3517 | ## Step 1 | ||
| 3518 | my $i = -1; | ||
| 3519 | wakaba | 1.3 | my $node = $self->{open_elements}->[$i]; |
| 3520 | wakaba | 1.1 | LI: { |
| 3521 | ## Step 2 | ||
| 3522 | if ($node->[1] eq 'li') { | ||
| 3523 | wakaba | 1.8 | if ($i != -1) { |
| 3524 | $self->{parse_error}-> (type => 'end tag missing:'. | ||
| 3525 | $self->{open_elements}->[-1]->[1]); | ||
| 3526 | } | ||
| 3527 | wakaba | 1.3 | splice @{$self->{open_elements}}, $i; |
| 3528 | wakaba | 1.1 | last LI; |
| 3529 | } | ||
| 3530 | |||
| 3531 | ## Step 3 | ||
| 3532 | if (not $formatting_category->{$node->[1]} and | ||
| 3533 | #not $phrasing_category->{$node->[1]} and | ||
| 3534 | ($special_category->{$node->[1]} or | ||
| 3535 | $scoping_category->{$node->[1]}) and | ||
| 3536 | $node->[1] ne 'address' and $node->[1] ne 'div') { | ||
| 3537 | last LI; | ||
| 3538 | } | ||
| 3539 | |||
| 3540 | ## Step 4 | ||
| 3541 | $i--; | ||
| 3542 | wakaba | 1.3 | $node = $self->{open_elements}->[$i]; |
| 3543 | wakaba | 1.1 | redo LI; |
| 3544 | } # LI | ||
| 3545 | |||
| 3546 | |||
| 3547 | { | ||
| 3548 | my $el; | ||
| 3549 | |||
| 3550 | $el = $self->{document}->create_element_ns | ||
| 3551 | (q<http://www.w3.org/1999/xhtml>, [undef, $token->{tag_name}]); | ||
| 3552 | |||
| 3553 | for my $attr_name (keys %{ $token->{attributes}}) { | ||
| 3554 | $el->set_attribute_ns (undef, [undef, $attr_name], | ||
| 3555 | $token->{attributes} ->{$attr_name}->{value}); | ||
| 3556 | } | ||
| 3557 | |||
| 3558 | $insert->($el); | ||
| 3559 | wakaba | 1.3 | push @{$self->{open_elements}}, [$el, $token->{tag_name}]; |
| 3560 | wakaba | 1.1 | } |
| 3561 | |||
| 3562 | $token = $self->_get_next_token; | ||
| 3563 | return; | ||
| 3564 | } elsif ($token->{tag_name} eq 'dd' or $token->{tag_name} eq 'dt') { | ||
| 3565 | ## has a p element in scope | ||
| 3566 | wakaba | 1.3 | INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 3567 | wakaba | 1.1 | if ($_->[1] eq 'p') { |
| 3568 | unshift @{$self->{token}}, $token; | ||
| 3569 | $token = {type => 'end tag', tag_name => 'p'}; | ||
| 3570 | return; | ||
| 3571 | } elsif ({ | ||
| 3572 | table => 1, caption => 1, td => 1, th => 1, | ||
| 3573 | button => 1, marquee => 1, object => 1, html => 1, | ||
| 3574 | }->{$_->[1]}) { | ||
| 3575 | last INSCOPE; | ||
| 3576 | } | ||
| 3577 | } # INSCOPE | ||
| 3578 | |||
| 3579 | ## Step 1 | ||
| 3580 | my $i = -1; | ||
| 3581 | wakaba | 1.3 | my $node = $self->{open_elements}->[$i]; |
| 3582 | wakaba | 1.1 | LI: { |
| 3583 | ## Step 2 | ||
| 3584 | if ($node->[1] eq 'dt' or $node->[1] eq 'dd') { | ||
| 3585 | wakaba | 1.8 | if ($i != -1) { |
| 3586 | $self->{parse_error}-> (type => 'end tag missing:'. | ||
| 3587 | $self->{open_elements}->[-1]->[1]); | ||
| 3588 | } | ||
| 3589 | wakaba | 1.3 | splice @{$self->{open_elements}}, $i; |
| 3590 | wakaba | 1.1 | last LI; |
| 3591 | } | ||
| 3592 | |||
| 3593 | ## Step 3 | ||
| 3594 | if (not $formatting_category->{$node->[1]} and | ||
| 3595 | #not $phrasing_category->{$node->[1]} and | ||
| 3596 | ($special_category->{$node->[1]} or | ||
| 3597 | $scoping_category->{$node->[1]}) and | ||
| 3598 | $node->[1] ne 'address' and $node->[1] ne 'div') { | ||
| 3599 | last LI; | ||
| 3600 | } | ||
| 3601 | |||
| 3602 | ## Step 4 | ||
| 3603 | $i--; | ||
| 3604 | wakaba | 1.3 | $node = $self->{open_elements}->[$i]; |
| 3605 | wakaba | 1.1 | redo LI; |
| 3606 | } # LI | ||
| 3607 | |||
| 3608 | |||
| 3609 | { | ||
| 3610 | my $el; | ||
| 3611 | |||
| 3612 | $el = $self->{document}->create_element_ns | ||
| 3613 | (q<http://www.w3.org/1999/xhtml>, [undef, $token->{tag_name}]); | ||
| 3614 | |||
| 3615 | for my $attr_name (keys %{ $token->{attributes}}) { | ||
| 3616 | $el->set_attribute_ns (undef, [undef, $attr_name], | ||
| 3617 | $token->{attributes} ->{$attr_name}->{value}); | ||
| 3618 | } | ||
| 3619 | |||
| 3620 | $insert->($el); | ||
| 3621 | wakaba | 1.3 | push @{$self->{open_elements}}, [$el, $token->{tag_name}]; |
| 3622 | wakaba | 1.1 | } |
| 3623 | |||
| 3624 | $token = $self->_get_next_token; | ||
| 3625 | return; | ||
| 3626 | } elsif ($token->{tag_name} eq 'plaintext') { | ||
| 3627 | ## has a p element in scope | ||
| 3628 | wakaba | 1.3 | INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 3629 | wakaba | 1.1 | if ($_->[1] eq 'p') { |
| 3630 | unshift @{$self->{token}}, $token; | ||
| 3631 | $token = {type => 'end tag', tag_name => 'p'}; | ||
| 3632 | return; | ||
| 3633 | } elsif ({ | ||
| 3634 | table => 1, caption => 1, td => 1, th => 1, | ||
| 3635 | button => 1, marquee => 1, object => 1, html => 1, | ||
| 3636 | }->{$_->[1]}) { | ||
| 3637 | last INSCOPE; | ||
| 3638 | } | ||
| 3639 | } # INSCOPE | ||
| 3640 | |||
| 3641 | |||
| 3642 | { | ||
| 3643 | my $el; | ||
| 3644 | |||
| 3645 | $el = $self->{document}->create_element_ns | ||
| 3646 | (q<http://www.w3.org/1999/xhtml>, [undef, $token->{tag_name}]); | ||
| 3647 | |||
| 3648 | for my $attr_name (keys %{ $token->{attributes}}) { | ||
| 3649 | $el->set_attribute_ns (undef, [undef, $attr_name], | ||
| 3650 | $token->{attributes} ->{$attr_name}->{value}); | ||
| 3651 | } | ||
| 3652 | |||
| 3653 | $insert->($el); | ||
| 3654 | wakaba | 1.3 | push @{$self->{open_elements}}, [$el, $token->{tag_name}]; |
| 3655 | wakaba | 1.1 | } |
| 3656 | |||
| 3657 | |||
| 3658 | $self->{content_model_flag} = 'PLAINTEXT'; | ||
| 3659 | |||
| 3660 | $token = $self->_get_next_token; | ||
| 3661 | return; | ||
| 3662 | } elsif ({ | ||
| 3663 | h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, | ||
| 3664 | }->{$token->{tag_name}}) { | ||
| 3665 | ## has a p element in scope | ||
| 3666 | wakaba | 1.3 | INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3667 | my $node = $self->{open_elements}->[$_]; | ||
| 3668 | wakaba | 1.1 | if ($node->[1] eq 'p') { |
| 3669 | unshift @{$self->{token}}, $token; | ||
| 3670 | $token = {type => 'end tag', tag_name => 'p'}; | ||
| 3671 | return; | ||
| 3672 | } elsif ({ | ||
| 3673 | table => 1, caption => 1, td => 1, th => 1, | ||
| 3674 | button => 1, marquee => 1, object => 1, html => 1, | ||
| 3675 | }->{$node->[1]}) { | ||
| 3676 | last INSCOPE; | ||
| 3677 | } | ||
| 3678 | } # INSCOPE | ||
| 3679 | |||
| 3680 | wakaba | 1.23 | ## NOTE: See <http://html5.org/tools/web-apps-tracker?from=925&to=926> |
| 3681 | wakaba | 1.1 | ## has an element in scope |
| 3682 | wakaba | 1.23 | #my $i; |
| 3683 | #INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { | ||
| 3684 | # my $node = $self->{open_elements}->[$_]; | ||
| 3685 | # if ({ | ||
| 3686 | # h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, | ||
| 3687 | # }->{$node->[1]}) { | ||
| 3688 | # $i = $_; | ||
| 3689 | # last INSCOPE; | ||
| 3690 | # } elsif ({ | ||
| 3691 | # table => 1, caption => 1, td => 1, th => 1, | ||
| 3692 | # button => 1, marquee => 1, object => 1, html => 1, | ||
| 3693 | # }->{$node->[1]}) { | ||
| 3694 | # last INSCOPE; | ||
| 3695 | # } | ||
| 3696 | #} # INSCOPE | ||
| 3697 | # | ||
| 3698 | #if (defined $i) { | ||
| 3699 | # !!! parse-error (type => 'in hn:hn'); | ||
| 3700 | # splice @{$self->{open_elements}}, $i; | ||
| 3701 | #} | ||
| 3702 | wakaba | 1.1 | |
| 3703 | |||
| 3704 | { | ||
| 3705 | my $el; | ||
| 3706 | |||
| 3707 | $el = $self->{document}->create_element_ns | ||
| 3708 | (q<http://www.w3.org/1999/xhtml>, [undef, $token->{tag_name}]); | ||
| 3709 | |||
| 3710 | for my $attr_name (keys %{ $token->{attributes}}) { | ||
| 3711 | $el->set_attribute_ns (undef, [undef, $attr_name], | ||
| 3712 | $token->{attributes} ->{$attr_name}->{value}); | ||
| 3713 | } | ||
| 3714 | |||
| 3715 | $insert->($el); | ||
| 3716 | wakaba | 1.3 | push @{$self->{open_elements}}, [$el, $token->{tag_name}]; |
| 3717 | wakaba | 1.1 | } |
| 3718 | |||
| 3719 | |||
| 3720 | $token = $self->_get_next_token; | ||
| 3721 | return; | ||
| 3722 | } elsif ($token->{tag_name} eq 'a') { | ||
| 3723 | AFE: for my $i (reverse 0..$#$active_formatting_elements) { | ||
| 3724 | my $node = $active_formatting_elements->[$i]; | ||
| 3725 | if ($node->[1] eq 'a') { | ||
| 3726 | wakaba | 1.3 | $self->{parse_error}-> (type => 'in a:a'); |
| 3727 | wakaba | 1.1 | |
| 3728 | unshift @{$self->{token}}, $token; | ||
| 3729 | $token = {type => 'end tag', tag_name => 'a'}; | ||
| 3730 | $formatting_end_tag->($token->{tag_name}); | ||
| 3731 | |||
| 3732 | AFE2: for (reverse 0..$#$active_formatting_elements) { | ||
| 3733 | if ($active_formatting_elements->[$_]->[0] eq $node->[0]) { | ||
| 3734 | splice @$active_formatting_elements, $_, 1; | ||
| 3735 | last AFE2; | ||
| 3736 | } | ||
| 3737 | } # AFE2 | ||
| 3738 | wakaba | 1.3 | OE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3739 | if ($self->{open_elements}->[$_]->[0] eq $node->[0]) { | ||
| 3740 | splice @{$self->{open_elements}}, $_, 1; | ||
| 3741 | wakaba | 1.1 | last OE; |
| 3742 | } | ||
| 3743 | } # OE | ||
| 3744 | last AFE; | ||
| 3745 | } elsif ($node->[0] eq '#marker') { | ||
| 3746 | last AFE; | ||
| 3747 | } | ||
| 3748 | } # AFE | ||
| 3749 | |||
| 3750 | $reconstruct_active_formatting_elements->($insert_to_current); | ||
| 3751 | |||
| 3752 | |||
| 3753 | { | ||
| 3754 | my $el; | ||
| 3755 | |||
| 3756 | $el = $self->{document}->create_element_ns | ||
| 3757 | (q<http://www.w3.org/1999/xhtml>, [undef, $token->{tag_name}]); | ||
| 3758 | |||
| 3759 | for my $attr_name (keys %{ $token->{attributes}}) { | ||
| 3760 | $el->set_attribute_ns (undef, [undef, $attr_name], | ||
| 3761 | $token->{attributes} ->{$attr_name}->{value}); | ||
| 3762 | } | ||
| 3763 | |||
| 3764 | $insert->($el); | ||
| 3765 | wakaba | 1.3 | push @{$self->{open_elements}}, [$el, $token->{tag_name}]; |
| 3766 | wakaba | 1.1 | } |
| 3767 | |||
| 3768 | wakaba | 1.3 | push @$active_formatting_elements, $self->{open_elements}->[-1]; |
| 3769 | wakaba | 1.1 | |
| 3770 | $token = $self->_get_next_token; | ||
| 3771 | return; | ||
| 3772 | } elsif ({ | ||
| 3773 | b => 1, big => 1, em => 1, font => 1, i => 1, | ||
| 3774 | wakaba | 1.19 | s => 1, small => 1, strile => 1, |
| 3775 | wakaba | 1.1 | strong => 1, tt => 1, u => 1, |
| 3776 | }->{$token->{tag_name}}) { | ||
| 3777 | $reconstruct_active_formatting_elements->($insert_to_current); | ||
| 3778 | |||
| 3779 | |||
| 3780 | { | ||
| 3781 | my $el; | ||
| 3782 | |||
| 3783 | $el = $self->{document}->create_element_ns | ||
| 3784 | (q<http://www.w3.org/1999/xhtml>, [undef, $token->{tag_name}]); | ||
| 3785 | |||
| 3786 | for my $attr_name (keys %{ $token->{attributes}}) { | ||
| 3787 | $el->set_attribute_ns (undef, [undef, $attr_name], | ||
| 3788 | $token->{attributes} ->{$attr_name}->{value}); | ||
| 3789 | } | ||
| 3790 | |||
| 3791 | $insert->($el); | ||
| 3792 | wakaba | 1.3 | push @{$self->{open_elements}}, [$el, $token->{tag_name}]; |
| 3793 | wakaba | 1.1 | } |
| 3794 | |||
| 3795 | wakaba | 1.3 | push @$active_formatting_elements, $self->{open_elements}->[-1]; |
| 3796 | wakaba | 1.1 | |
| 3797 | $token = $self->_get_next_token; | ||
| 3798 | return; | ||
| 3799 | wakaba | 1.19 | } elsif ($token->{tag_name} eq 'nobr') { |
| 3800 | $reconstruct_active_formatting_elements->($insert_to_current); | ||
| 3801 | |||
| 3802 | ## has a |nobr| element in scope | ||
| 3803 | INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { | ||
| 3804 | my $node = $self->{open_elements}->[$_]; | ||
| 3805 | if ($node->[1] eq 'nobr') { | ||
| 3806 | wakaba | 1.31 | $self->{parse_error}-> (type => 'not closed:nobr'); |
| 3807 | wakaba | 1.19 | unshift @{$self->{token}}, $token; |
| 3808 | $token = {type => 'end tag', tag_name => 'nobr'}; | ||
| 3809 | return; | ||
| 3810 | } elsif ({ | ||
| 3811 | table => 1, caption => 1, td => 1, th => 1, | ||
| 3812 | button => 1, marquee => 1, object => 1, html => 1, | ||
| 3813 | }->{$node->[1]}) { | ||
| 3814 | last INSCOPE; | ||
| 3815 | } | ||
| 3816 | } # INSCOPE | ||
| 3817 | |||
| 3818 | |||
| 3819 | { | ||
| 3820 | my $el; | ||
| 3821 | |||
| 3822 | $el = $self->{document}->create_element_ns | ||
| 3823 | (q<http://www.w3.org/1999/xhtml>, [undef, $token->{tag_name}]); | ||
| 3824 | |||
| 3825 | for my $attr_name (keys %{ $token->{attributes}}) { | ||
| 3826 | $el->set_attribute_ns (undef, [undef, $attr_name], | ||
| 3827 | $token->{attributes} ->{$attr_name}->{value}); | ||
| 3828 | } | ||
| 3829 | |||
| 3830 | $insert->($el); | ||
| 3831 | push @{$self->{open_elements}}, [$el, $token->{tag_name}]; | ||
| 3832 | } | ||
| 3833 | |||
| 3834 | push @$active_formatting_elements, $self->{open_elements}->[-1]; | ||
| 3835 | |||
| 3836 | $token = $self->_get_next_token; | ||
| 3837 | return; | ||
| 3838 | wakaba | 1.1 | } elsif ($token->{tag_name} eq 'button') { |
| 3839 | ## has a button element in scope | ||
| 3840 | wakaba | 1.3 | INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3841 | my $node = $self->{open_elements}->[$_]; | ||
| 3842 | wakaba | 1.1 | if ($node->[1] eq 'button') { |
| 3843 | wakaba | 1.3 | $self->{parse_error}-> (type => 'in button:button'); |
| 3844 | wakaba | 1.1 | unshift @{$self->{token}}, $token; |
| 3845 | $token = {type => 'end tag', tag_name => 'button'}; | ||
| 3846 | return; | ||
| 3847 | } elsif ({ | ||
| 3848 | table => 1, caption => 1, td => 1, th => 1, | ||
| 3849 | button => 1, marquee => 1, object => 1, html => 1, | ||
| 3850 | }->{$node->[1]}) { | ||
| 3851 | last INSCOPE; | ||
| 3852 | } | ||
| 3853 | } # INSCOPE | ||
| 3854 | |||
| 3855 | $reconstruct_active_formatting_elements->($insert_to_current); | ||
| 3856 | |||
| 3857 | |||
| 3858 | { | ||
| 3859 | my $el; | ||
| 3860 | |||
| 3861 | $el = $self->{document}->create_element_ns | ||
| 3862 | (q<http://www.w3.org/1999/xhtml>, [undef, $token->{tag_name}]); | ||
| 3863 | |||
| 3864 | for my $attr_name (keys %{ $token->{attributes}}) { | ||
| 3865 | $el->set_attribute_ns (undef, [undef, $attr_name], | ||
| 3866 | $token->{attributes} ->{$attr_name}->{value}); | ||
| 3867 | } | ||
| 3868 | |||
| 3869 | $insert->($el); | ||
| 3870 | wakaba | 1.3 | push @{$self->{open_elements}}, [$el, $token->{tag_name}]; |
| 3871 | wakaba | 1.1 | } |
| 3872 | |||
| 3873 | push @$active_formatting_elements, ['#marker', '']; | ||
| 3874 | |||
| 3875 | $token = $self->_get_next_token; | ||
| 3876 | return; | ||
| 3877 | } elsif ($token->{tag_name} eq 'marquee' or | ||
| 3878 | $token->{tag_name} eq 'object') { | ||
| 3879 | $reconstruct_active_formatting_elements->($insert_to_current); | ||
| 3880 | |||
| 3881 | |||
| 3882 | { | ||
| 3883 | my $el; | ||
| 3884 | |||
| 3885 | $el = $self->{document}->create_element_ns | ||
| 3886 | (q<http://www.w3.org/1999/xhtml>, [undef, $token->{tag_name}]); | ||
| 3887 | |||
| 3888 | for my $attr_name (keys %{ $token->{attributes}}) { | ||
| 3889 | $el->set_attribute_ns (undef, [undef, $attr_name], | ||
| 3890 | $token->{attributes} ->{$attr_name}->{value}); | ||
| 3891 | } | ||
| 3892 | |||
| 3893 | $insert->($el); | ||
| 3894 | wakaba | 1.3 | push @{$self->{open_elements}}, [$el, $token->{tag_name}]; |
| 3895 | wakaba | 1.1 | } |
| 3896 | |||
| 3897 | push @$active_formatting_elements, ['#marker', '']; | ||
| 3898 | |||
| 3899 | $token = $self->_get_next_token; | ||
| 3900 | return; | ||
| 3901 | } elsif ($token->{tag_name} eq 'xmp') { | ||
| 3902 | $reconstruct_active_formatting_elements->($insert_to_current); | ||
| 3903 | wakaba | 1.25 | $parse_rcdata->('CDATA', $insert); |
| 3904 | wakaba | 1.1 | return; |
| 3905 | } elsif ($token->{tag_name} eq 'table') { | ||
| 3906 | ## has a p element in scope | ||
| 3907 | wakaba | 1.3 | INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 3908 | wakaba | 1.1 | if ($_->[1] eq 'p') { |
| 3909 | unshift @{$self->{token}}, $token; | ||
| 3910 | $token = {type => 'end tag', tag_name => 'p'}; | ||
| 3911 | return; | ||
| 3912 | } elsif ({ | ||
| 3913 | table => 1, caption => 1, td => 1, th => 1, | ||
| 3914 | button => 1, marquee => 1, object => 1, html => 1, | ||
| 3915 | }->{$_->[1]}) { | ||
| 3916 | last INSCOPE; | ||
| 3917 | } | ||
| 3918 | } # INSCOPE | ||
| 3919 | |||
| 3920 | |||
| 3921 | { | ||
| 3922 | my $el; | ||
| 3923 | |||
| 3924 | $el = $self->{document}->create_element_ns | ||
| 3925 | (q<http://www.w3.org/1999/xhtml>, [undef, $token->{tag_name}]); | ||
| 3926 | |||
| 3927 | for my $attr_name (keys %{ $token->{attributes}}) { | ||
| 3928 | $el->set_attribute_ns (undef, [undef, $attr_name], | ||
| 3929 | $token->{attributes} ->{$attr_name}->{value}); | ||
| 3930 | } | ||
| 3931 | |||
| 3932 | $insert->($el); | ||
| 3933 | wakaba | 1.3 | push @{$self->{open_elements}}, [$el, $token->{tag_name}]; |
| 3934 | wakaba | 1.1 | } |
| 3935 | |||
| 3936 | |||
| 3937 | wakaba | 1.3 | $self->{insertion_mode} = 'in table'; |
| 3938 | wakaba | 1.1 | |
| 3939 | $token = $self->_get_next_token; | ||
| 3940 | return; | ||
| 3941 | } elsif ({ | ||
| 3942 | area => 1, basefont => 1, bgsound => 1, br => 1, | ||
| 3943 | embed => 1, img => 1, param => 1, spacer => 1, wbr => 1, | ||
| 3944 | image => 1, | ||
| 3945 | }->{$token->{tag_name}}) { | ||
| 3946 | if ($token->{tag_name} eq 'image') { | ||
| 3947 | wakaba | 1.3 | $self->{parse_error}-> (type => 'image'); |
| 3948 | wakaba | 1.1 | $token->{tag_name} = 'img'; |
| 3949 | } | ||
| 3950 | wakaba | 1.31 | |
| 3951 | ## NOTE: There is an "as if <br>" code clone. | ||
| 3952 | wakaba | 1.1 | $reconstruct_active_formatting_elements->($insert_to_current); |
| 3953 | |||
| 3954 | |||
| 3955 | { | ||
| 3956 | my $el; | ||
| 3957 | |||
| 3958 | $el = $self->{document}->create_element_ns | ||
| 3959 | (q<http://www.w3.org/1999/xhtml>, [undef, $token->{tag_name}]); | ||
| 3960 | |||
| 3961 | for my $attr_name (keys %{ $token->{attributes}}) { | ||
| 3962 | $el->set_attribute_ns (undef, [undef, $attr_name], | ||
| 3963 | $token->{attributes} ->{$attr_name}->{value}); | ||
| 3964 | } | ||
| 3965 | |||
| 3966 | $insert->($el); | ||
| 3967 | wakaba | 1.3 | push @{$self->{open_elements}}, [$el, $token->{tag_name}]; |
| 3968 | wakaba | 1.1 | } |
| 3969 | |||
| 3970 | wakaba | 1.3 | pop @{$self->{open_elements}}; |
| 3971 | wakaba | 1.1 | |
| 3972 | $token = $self->_get_next_token; | ||
| 3973 | return; | ||
| 3974 | } elsif ($token->{tag_name} eq 'hr') { | ||
| 3975 | ## has a p element in scope | ||
| 3976 | wakaba | 1.3 | INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 3977 | wakaba | 1.1 | if ($_->[1] eq 'p') { |
| 3978 | unshift @{$self->{token}}, $token; | ||
| 3979 | $token = {type => 'end tag', tag_name => 'p'}; | ||
| 3980 | return; | ||
| 3981 | } elsif ({ | ||
| 3982 | table => 1, caption => 1, td => 1, th => 1, | ||
| 3983 | button => 1, marquee => 1, object => 1, html => 1, | ||
| 3984 | }->{$_->[1]}) { | ||
| 3985 | last INSCOPE; | ||
| 3986 | } | ||
| 3987 | } # INSCOPE | ||
| 3988 | |||
| 3989 | |||
| 3990 | { | ||
| 3991 | my $el; | ||
| 3992 | |||
| 3993 | $el = $self->{document}->create_element_ns | ||
| 3994 | (q<http://www.w3.org/1999/xhtml>, [undef, $token->{tag_name}]); | ||
| 3995 | |||
| 3996 | for my $attr_name (keys %{ $token->{attributes}}) { | ||
| 3997 | $el->set_attribute_ns (undef, [undef, $attr_name], | ||
| 3998 | $token->{attributes} ->{$attr_name}->{value}); | ||
| 3999 | } | ||
| 4000 | |||
| 4001 | $insert->($el); | ||
| 4002 | wakaba | 1.3 | push @{$self->{open_elements}}, [$el, $token->{tag_name}]; |
| 4003 | wakaba | 1.1 | } |
| 4004 | |||
| 4005 | wakaba | 1.3 | pop @{$self->{open_elements}}; |
| 4006 | wakaba | 1.1 | |
| 4007 | $token = $self->_get_next_token; | ||
| 4008 | return; | ||
| 4009 | } elsif ($token->{tag_name} eq 'input') { | ||
| 4010 | $reconstruct_active_formatting_elements->($insert_to_current); | ||
| 4011 | |||
| 4012 | |||
| 4013 | { | ||
| 4014 | my $el; | ||
| 4015 | |||
| 4016 | $el = $self->{document}->create_element_ns | ||
| 4017 | (q<http://www.w3.org/1999/xhtml>, [undef, $token->{tag_name}]); | ||
| 4018 | |||
| 4019 | for my $attr_name (keys %{ $token->{attributes}}) { | ||
| 4020 | $el->set_attribute_ns (undef, [undef, $attr_name], | ||
| 4021 | $token->{attributes} ->{$attr_name}->{value}); | ||
| 4022 | } | ||
| 4023 | |||
| 4024 | $insert->($el); | ||
| 4025 | wakaba | 1.3 | push @{$self->{open_elements}}, [$el, $token->{tag_name}]; |
| 4026 | wakaba | 1.1 | } |
| 4027 | |||
| 4028 | wakaba | 1.3 | ## TODO: associate with $self->{form_element} if defined |
| 4029 | pop @{$self->{open_elements}}; | ||
| 4030 | wakaba | 1.1 | |
| 4031 | $token = $self->_get_next_token; | ||
| 4032 | return; | ||
| 4033 | } elsif ($token->{tag_name} eq 'isindex') { | ||
| 4034 | wakaba | 1.3 | $self->{parse_error}-> (type => 'isindex'); |
| 4035 | wakaba | 1.1 | |
| 4036 | wakaba | 1.3 | if (defined $self->{form_element}) { |
| 4037 | wakaba | 1.1 | ## Ignore the token |
| 4038 | $token = $self->_get_next_token; | ||
| 4039 | return; | ||
| 4040 | } else { | ||
| 4041 | my $at = $token->{attributes}; | ||
| 4042 | wakaba | 1.22 | my $form_attrs; |
| 4043 |