| 8 |
## doc.write (''); |
## doc.write (''); |
| 9 |
## alert (doc.compatMode); |
## alert (doc.compatMode); |
| 10 |
|
|
| 11 |
## TODO: Control charcters and noncharacters are not allowed (HTML5 revision 1263) |
require IO::Handle; |
| 12 |
## TODO: 1252 parse error (revision 1264) |
|
| 13 |
## TODO: 8859-11 = 874 (revision 1271) |
my $HTML_NS = q<http://www.w3.org/1999/xhtml>; |
| 14 |
|
my $MML_NS = q<http://www.w3.org/1998/Math/MathML>; |
| 15 |
my $permitted_slash_tag_name = { |
my $SVG_NS = q<http://www.w3.org/2000/svg>; |
| 16 |
base => 1, |
my $XLINK_NS = q<http://www.w3.org/1999/xlink>; |
| 17 |
link => 1, |
my $XML_NS = q<http://www.w3.org/XML/1998/namespace>; |
| 18 |
meta => 1, |
my $XMLNS_NS = q<http://www.w3.org/2000/xmlns/>; |
| 19 |
hr => 1, |
|
| 20 |
br => 1, |
sub A_EL () { 0b1 } |
| 21 |
img => 1, |
sub ADDRESS_EL () { 0b10 } |
| 22 |
embed => 1, |
sub BODY_EL () { 0b100 } |
| 23 |
param => 1, |
sub BUTTON_EL () { 0b1000 } |
| 24 |
area => 1, |
sub CAPTION_EL () { 0b10000 } |
| 25 |
col => 1, |
sub DD_EL () { 0b100000 } |
| 26 |
input => 1, |
sub DIV_EL () { 0b1000000 } |
| 27 |
|
sub DT_EL () { 0b10000000 } |
| 28 |
|
sub FORM_EL () { 0b100000000 } |
| 29 |
|
sub FORMATTING_EL () { 0b1000000000 } |
| 30 |
|
sub FRAMESET_EL () { 0b10000000000 } |
| 31 |
|
sub HEADING_EL () { 0b100000000000 } |
| 32 |
|
sub HTML_EL () { 0b1000000000000 } |
| 33 |
|
sub LI_EL () { 0b10000000000000 } |
| 34 |
|
sub NOBR_EL () { 0b100000000000000 } |
| 35 |
|
sub OPTION_EL () { 0b1000000000000000 } |
| 36 |
|
sub OPTGROUP_EL () { 0b10000000000000000 } |
| 37 |
|
sub P_EL () { 0b100000000000000000 } |
| 38 |
|
sub SELECT_EL () { 0b1000000000000000000 } |
| 39 |
|
sub TABLE_EL () { 0b10000000000000000000 } |
| 40 |
|
sub TABLE_CELL_EL () { 0b100000000000000000000 } |
| 41 |
|
sub TABLE_ROW_EL () { 0b1000000000000000000000 } |
| 42 |
|
sub TABLE_ROW_GROUP_EL () { 0b10000000000000000000000 } |
| 43 |
|
sub MISC_SCOPING_EL () { 0b100000000000000000000000 } |
| 44 |
|
sub MISC_SPECIAL_EL () { 0b1000000000000000000000000 } |
| 45 |
|
sub FOREIGN_EL () { 0b10000000000000000000000000 } |
| 46 |
|
sub FOREIGN_FLOW_CONTENT_EL () { 0b100000000000000000000000000 } |
| 47 |
|
sub MML_AXML_EL () { 0b1000000000000000000000000000 } |
| 48 |
|
sub RUBY_EL () { 0b10000000000000000000000000000 } |
| 49 |
|
sub RUBY_COMPONENT_EL () { 0b100000000000000000000000000000 } |
| 50 |
|
|
| 51 |
|
sub TABLE_ROWS_EL () { |
| 52 |
|
TABLE_EL | |
| 53 |
|
TABLE_ROW_EL | |
| 54 |
|
TABLE_ROW_GROUP_EL |
| 55 |
|
} |
| 56 |
|
|
| 57 |
|
## NOTE: Used in "generate implied end tags" algorithm. |
| 58 |
|
## NOTE: There is a code where a modified version of END_TAG_OPTIONAL_EL |
| 59 |
|
## is used in "generate implied end tags" implementation (search for the |
| 60 |
|
## function mae). |
| 61 |
|
sub END_TAG_OPTIONAL_EL () { |
| 62 |
|
DD_EL | |
| 63 |
|
DT_EL | |
| 64 |
|
LI_EL | |
| 65 |
|
P_EL | |
| 66 |
|
RUBY_COMPONENT_EL |
| 67 |
|
} |
| 68 |
|
|
| 69 |
|
## NOTE: Used in </body> and EOF algorithms. |
| 70 |
|
sub ALL_END_TAG_OPTIONAL_EL () { |
| 71 |
|
DD_EL | |
| 72 |
|
DT_EL | |
| 73 |
|
LI_EL | |
| 74 |
|
P_EL | |
| 75 |
|
|
| 76 |
|
BODY_EL | |
| 77 |
|
HTML_EL | |
| 78 |
|
TABLE_CELL_EL | |
| 79 |
|
TABLE_ROW_EL | |
| 80 |
|
TABLE_ROW_GROUP_EL |
| 81 |
|
} |
| 82 |
|
|
| 83 |
|
sub SCOPING_EL () { |
| 84 |
|
BUTTON_EL | |
| 85 |
|
CAPTION_EL | |
| 86 |
|
HTML_EL | |
| 87 |
|
TABLE_EL | |
| 88 |
|
TABLE_CELL_EL | |
| 89 |
|
MISC_SCOPING_EL |
| 90 |
|
} |
| 91 |
|
|
| 92 |
|
sub TABLE_SCOPING_EL () { |
| 93 |
|
HTML_EL | |
| 94 |
|
TABLE_EL |
| 95 |
|
} |
| 96 |
|
|
| 97 |
|
sub TABLE_ROWS_SCOPING_EL () { |
| 98 |
|
HTML_EL | |
| 99 |
|
TABLE_ROW_GROUP_EL |
| 100 |
|
} |
| 101 |
|
|
| 102 |
|
sub TABLE_ROW_SCOPING_EL () { |
| 103 |
|
HTML_EL | |
| 104 |
|
TABLE_ROW_EL |
| 105 |
|
} |
| 106 |
|
|
| 107 |
|
sub SPECIAL_EL () { |
| 108 |
|
ADDRESS_EL | |
| 109 |
|
BODY_EL | |
| 110 |
|
DIV_EL | |
| 111 |
|
|
| 112 |
|
DD_EL | |
| 113 |
|
DT_EL | |
| 114 |
|
LI_EL | |
| 115 |
|
P_EL | |
| 116 |
|
|
| 117 |
|
FORM_EL | |
| 118 |
|
FRAMESET_EL | |
| 119 |
|
HEADING_EL | |
| 120 |
|
OPTION_EL | |
| 121 |
|
OPTGROUP_EL | |
| 122 |
|
SELECT_EL | |
| 123 |
|
TABLE_ROW_EL | |
| 124 |
|
TABLE_ROW_GROUP_EL | |
| 125 |
|
MISC_SPECIAL_EL |
| 126 |
|
} |
| 127 |
|
|
| 128 |
|
my $el_category = { |
| 129 |
|
a => A_EL | FORMATTING_EL, |
| 130 |
|
address => ADDRESS_EL, |
| 131 |
|
applet => MISC_SCOPING_EL, |
| 132 |
|
area => MISC_SPECIAL_EL, |
| 133 |
|
b => FORMATTING_EL, |
| 134 |
|
base => MISC_SPECIAL_EL, |
| 135 |
|
basefont => MISC_SPECIAL_EL, |
| 136 |
|
bgsound => MISC_SPECIAL_EL, |
| 137 |
|
big => FORMATTING_EL, |
| 138 |
|
blockquote => MISC_SPECIAL_EL, |
| 139 |
|
body => BODY_EL, |
| 140 |
|
br => MISC_SPECIAL_EL, |
| 141 |
|
button => BUTTON_EL, |
| 142 |
|
caption => CAPTION_EL, |
| 143 |
|
center => MISC_SPECIAL_EL, |
| 144 |
|
col => MISC_SPECIAL_EL, |
| 145 |
|
colgroup => MISC_SPECIAL_EL, |
| 146 |
|
dd => DD_EL, |
| 147 |
|
dir => MISC_SPECIAL_EL, |
| 148 |
|
div => DIV_EL, |
| 149 |
|
dl => MISC_SPECIAL_EL, |
| 150 |
|
dt => DT_EL, |
| 151 |
|
em => FORMATTING_EL, |
| 152 |
|
embed => MISC_SPECIAL_EL, |
| 153 |
|
fieldset => MISC_SPECIAL_EL, |
| 154 |
|
font => FORMATTING_EL, |
| 155 |
|
form => FORM_EL, |
| 156 |
|
frame => MISC_SPECIAL_EL, |
| 157 |
|
frameset => FRAMESET_EL, |
| 158 |
|
h1 => HEADING_EL, |
| 159 |
|
h2 => HEADING_EL, |
| 160 |
|
h3 => HEADING_EL, |
| 161 |
|
h4 => HEADING_EL, |
| 162 |
|
h5 => HEADING_EL, |
| 163 |
|
h6 => HEADING_EL, |
| 164 |
|
head => MISC_SPECIAL_EL, |
| 165 |
|
hr => MISC_SPECIAL_EL, |
| 166 |
|
html => HTML_EL, |
| 167 |
|
i => FORMATTING_EL, |
| 168 |
|
iframe => MISC_SPECIAL_EL, |
| 169 |
|
img => MISC_SPECIAL_EL, |
| 170 |
|
input => MISC_SPECIAL_EL, |
| 171 |
|
isindex => MISC_SPECIAL_EL, |
| 172 |
|
li => LI_EL, |
| 173 |
|
link => MISC_SPECIAL_EL, |
| 174 |
|
listing => MISC_SPECIAL_EL, |
| 175 |
|
marquee => MISC_SCOPING_EL, |
| 176 |
|
menu => MISC_SPECIAL_EL, |
| 177 |
|
meta => MISC_SPECIAL_EL, |
| 178 |
|
nobr => NOBR_EL | FORMATTING_EL, |
| 179 |
|
noembed => MISC_SPECIAL_EL, |
| 180 |
|
noframes => MISC_SPECIAL_EL, |
| 181 |
|
noscript => MISC_SPECIAL_EL, |
| 182 |
|
object => MISC_SCOPING_EL, |
| 183 |
|
ol => MISC_SPECIAL_EL, |
| 184 |
|
optgroup => OPTGROUP_EL, |
| 185 |
|
option => OPTION_EL, |
| 186 |
|
p => P_EL, |
| 187 |
|
param => MISC_SPECIAL_EL, |
| 188 |
|
plaintext => MISC_SPECIAL_EL, |
| 189 |
|
pre => MISC_SPECIAL_EL, |
| 190 |
|
rp => RUBY_COMPONENT_EL, |
| 191 |
|
rt => RUBY_COMPONENT_EL, |
| 192 |
|
ruby => RUBY_EL, |
| 193 |
|
s => FORMATTING_EL, |
| 194 |
|
script => MISC_SPECIAL_EL, |
| 195 |
|
select => SELECT_EL, |
| 196 |
|
small => FORMATTING_EL, |
| 197 |
|
spacer => MISC_SPECIAL_EL, |
| 198 |
|
strike => FORMATTING_EL, |
| 199 |
|
strong => FORMATTING_EL, |
| 200 |
|
style => MISC_SPECIAL_EL, |
| 201 |
|
table => TABLE_EL, |
| 202 |
|
tbody => TABLE_ROW_GROUP_EL, |
| 203 |
|
td => TABLE_CELL_EL, |
| 204 |
|
textarea => MISC_SPECIAL_EL, |
| 205 |
|
tfoot => TABLE_ROW_GROUP_EL, |
| 206 |
|
th => TABLE_CELL_EL, |
| 207 |
|
thead => TABLE_ROW_GROUP_EL, |
| 208 |
|
title => MISC_SPECIAL_EL, |
| 209 |
|
tr => TABLE_ROW_EL, |
| 210 |
|
tt => FORMATTING_EL, |
| 211 |
|
u => FORMATTING_EL, |
| 212 |
|
ul => MISC_SPECIAL_EL, |
| 213 |
|
wbr => MISC_SPECIAL_EL, |
| 214 |
|
}; |
| 215 |
|
|
| 216 |
|
my $el_category_f = { |
| 217 |
|
$MML_NS => { |
| 218 |
|
'annotation-xml' => MML_AXML_EL, |
| 219 |
|
mi => FOREIGN_FLOW_CONTENT_EL, |
| 220 |
|
mo => FOREIGN_FLOW_CONTENT_EL, |
| 221 |
|
mn => FOREIGN_FLOW_CONTENT_EL, |
| 222 |
|
ms => FOREIGN_FLOW_CONTENT_EL, |
| 223 |
|
mtext => FOREIGN_FLOW_CONTENT_EL, |
| 224 |
|
}, |
| 225 |
|
$SVG_NS => { |
| 226 |
|
foreignObject => FOREIGN_FLOW_CONTENT_EL, |
| 227 |
|
desc => FOREIGN_FLOW_CONTENT_EL, |
| 228 |
|
title => FOREIGN_FLOW_CONTENT_EL, |
| 229 |
|
}, |
| 230 |
|
## NOTE: In addition, FOREIGN_EL is set to non-HTML elements. |
| 231 |
|
}; |
| 232 |
|
|
| 233 |
|
my $svg_attr_name = { |
| 234 |
|
attributename => 'attributeName', |
| 235 |
|
attributetype => 'attributeType', |
| 236 |
|
basefrequency => 'baseFrequency', |
| 237 |
|
baseprofile => 'baseProfile', |
| 238 |
|
calcmode => 'calcMode', |
| 239 |
|
clippathunits => 'clipPathUnits', |
| 240 |
|
contentscripttype => 'contentScriptType', |
| 241 |
|
contentstyletype => 'contentStyleType', |
| 242 |
|
diffuseconstant => 'diffuseConstant', |
| 243 |
|
edgemode => 'edgeMode', |
| 244 |
|
externalresourcesrequired => 'externalResourcesRequired', |
| 245 |
|
filterres => 'filterRes', |
| 246 |
|
filterunits => 'filterUnits', |
| 247 |
|
glyphref => 'glyphRef', |
| 248 |
|
gradienttransform => 'gradientTransform', |
| 249 |
|
gradientunits => 'gradientUnits', |
| 250 |
|
kernelmatrix => 'kernelMatrix', |
| 251 |
|
kernelunitlength => 'kernelUnitLength', |
| 252 |
|
keypoints => 'keyPoints', |
| 253 |
|
keysplines => 'keySplines', |
| 254 |
|
keytimes => 'keyTimes', |
| 255 |
|
lengthadjust => 'lengthAdjust', |
| 256 |
|
limitingconeangle => 'limitingConeAngle', |
| 257 |
|
markerheight => 'markerHeight', |
| 258 |
|
markerunits => 'markerUnits', |
| 259 |
|
markerwidth => 'markerWidth', |
| 260 |
|
maskcontentunits => 'maskContentUnits', |
| 261 |
|
maskunits => 'maskUnits', |
| 262 |
|
numoctaves => 'numOctaves', |
| 263 |
|
pathlength => 'pathLength', |
| 264 |
|
patterncontentunits => 'patternContentUnits', |
| 265 |
|
patterntransform => 'patternTransform', |
| 266 |
|
patternunits => 'patternUnits', |
| 267 |
|
pointsatx => 'pointsAtX', |
| 268 |
|
pointsaty => 'pointsAtY', |
| 269 |
|
pointsatz => 'pointsAtZ', |
| 270 |
|
preservealpha => 'preserveAlpha', |
| 271 |
|
preserveaspectratio => 'preserveAspectRatio', |
| 272 |
|
primitiveunits => 'primitiveUnits', |
| 273 |
|
refx => 'refX', |
| 274 |
|
refy => 'refY', |
| 275 |
|
repeatcount => 'repeatCount', |
| 276 |
|
repeatdur => 'repeatDur', |
| 277 |
|
requiredextensions => 'requiredExtensions', |
| 278 |
|
requiredfeatures => 'requiredFeatures', |
| 279 |
|
specularconstant => 'specularConstant', |
| 280 |
|
specularexponent => 'specularExponent', |
| 281 |
|
spreadmethod => 'spreadMethod', |
| 282 |
|
startoffset => 'startOffset', |
| 283 |
|
stddeviation => 'stdDeviation', |
| 284 |
|
stitchtiles => 'stitchTiles', |
| 285 |
|
surfacescale => 'surfaceScale', |
| 286 |
|
systemlanguage => 'systemLanguage', |
| 287 |
|
tablevalues => 'tableValues', |
| 288 |
|
targetx => 'targetX', |
| 289 |
|
targety => 'targetY', |
| 290 |
|
textlength => 'textLength', |
| 291 |
|
viewbox => 'viewBox', |
| 292 |
|
viewtarget => 'viewTarget', |
| 293 |
|
xchannelselector => 'xChannelSelector', |
| 294 |
|
ychannelselector => 'yChannelSelector', |
| 295 |
|
zoomandpan => 'zoomAndPan', |
| 296 |
}; |
}; |
| 297 |
|
|
| 298 |
|
my $foreign_attr_xname = { |
| 299 |
|
'xlink:actuate' => [$XLINK_NS, ['xlink', 'actuate']], |
| 300 |
|
'xlink:arcrole' => [$XLINK_NS, ['xlink', 'arcrole']], |
| 301 |
|
'xlink:href' => [$XLINK_NS, ['xlink', 'href']], |
| 302 |
|
'xlink:role' => [$XLINK_NS, ['xlink', 'role']], |
| 303 |
|
'xlink:show' => [$XLINK_NS, ['xlink', 'show']], |
| 304 |
|
'xlink:title' => [$XLINK_NS, ['xlink', 'title']], |
| 305 |
|
'xlink:type' => [$XLINK_NS, ['xlink', 'type']], |
| 306 |
|
'xml:base' => [$XML_NS, ['xml', 'base']], |
| 307 |
|
'xml:lang' => [$XML_NS, ['xml', 'lang']], |
| 308 |
|
'xml:space' => [$XML_NS, ['xml', 'space']], |
| 309 |
|
'xmlns' => [$XMLNS_NS, [undef, 'xmlns']], |
| 310 |
|
'xmlns:xlink' => [$XMLNS_NS, ['xmlns', 'xlink']], |
| 311 |
|
}; |
| 312 |
|
|
| 313 |
|
## ISSUE: xmlns:xlink="non-xlink-ns" is not an error. |
| 314 |
|
|
| 315 |
my $c1_entity_char = { |
my $c1_entity_char = { |
| 316 |
0x80 => 0x20AC, |
0x80 => 0x20AC, |
| 317 |
0x81 => 0xFFFD, |
0x81 => 0xFFFD, |
| 347 |
0x9F => 0x0178, |
0x9F => 0x0178, |
| 348 |
}; # $c1_entity_char |
}; # $c1_entity_char |
| 349 |
|
|
|
my $special_category = { |
|
|
address => 1, area => 1, base => 1, basefont => 1, bgsound => 1, |
|
|
blockquote => 1, body => 1, br => 1, center => 1, col => 1, colgroup => 1, |
|
|
dd => 1, dir => 1, div => 1, dl => 1, dt => 1, embed => 1, fieldset => 1, |
|
|
form => 1, frame => 1, frameset => 1, h1 => 1, h2 => 1, h3 => 1, |
|
|
h4 => 1, h5 => 1, h6 => 1, head => 1, hr => 1, iframe => 1, image => 1, |
|
|
img => 1, input => 1, isindex => 1, li => 1, link => 1, listing => 1, |
|
|
menu => 1, meta => 1, noembed => 1, noframes => 1, noscript => 1, |
|
|
ol => 1, optgroup => 1, option => 1, p => 1, param => 1, plaintext => 1, |
|
|
pre => 1, script => 1, select => 1, spacer => 1, style => 1, tbody => 1, |
|
|
textarea => 1, tfoot => 1, thead => 1, title => 1, tr => 1, ul => 1, wbr => 1, |
|
|
}; |
|
|
my $scoping_category = { |
|
|
applet => 1, button => 1, caption => 1, html => 1, marquee => 1, object => 1, |
|
|
table => 1, td => 1, th => 1, |
|
|
}; |
|
|
my $formatting_category = { |
|
|
a => 1, b => 1, big => 1, em => 1, font => 1, i => 1, nobr => 1, |
|
|
s => 1, small => 1, strile => 1, strong => 1, tt => 1, u => 1, |
|
|
}; |
|
|
# $phrasing_category: all other elements |
|
|
|
|
| 350 |
sub parse_byte_string ($$$$;$) { |
sub parse_byte_string ($$$$;$) { |
| 351 |
|
my $self = shift; |
| 352 |
|
my $charset_name = shift; |
| 353 |
|
open my $input, '<', ref $_[0] ? $_[0] : \($_[0]); |
| 354 |
|
return $self->parse_byte_stream ($charset_name, $input, @_[1..$#_]); |
| 355 |
|
} # parse_byte_string |
| 356 |
|
|
| 357 |
|
sub parse_byte_stream ($$$$;$$) { |
| 358 |
|
# my ($self, $charset_name, $byte_stream, $doc, $onerror, $get_wrapper) = @_; |
| 359 |
my $self = ref $_[0] ? shift : shift->new; |
my $self = ref $_[0] ? shift : shift->new; |
| 360 |
my $charset = shift; |
my $charset_name = shift; |
| 361 |
my $bytes_s = ref $_[0] ? $_[0] : \($_[0]); |
my $byte_stream = $_[0]; |
|
my $s; |
|
|
|
|
|
if (defined $charset) { |
|
|
require Encode; ## TODO: decode(utf8) don't delete BOM |
|
|
$s = \ (Encode::decode ($charset, $$bytes_s)); |
|
|
$self->{input_encoding} = lc $charset; ## TODO: normalize name |
|
|
$self->{confident} = 1; |
|
|
} else { |
|
|
## TODO: Implement HTML5 detection algorithm |
|
|
require Whatpm::Charset::UniversalCharDet; |
|
|
$charset = Whatpm::Charset::UniversalCharDet->detect_byte_string |
|
|
(substr ($$bytes_s, 0, 1024)); |
|
|
$charset ||= 'windows-1252'; |
|
|
$s = \ (Encode::decode ($charset, $$bytes_s)); |
|
|
$self->{input_encoding} = $charset; |
|
|
$self->{confident} = 0; |
|
|
} |
|
| 362 |
|
|
| 363 |
$self->{change_encoding} = sub { |
my $onerror = $_[2] || sub { |
| 364 |
my $self = shift; |
my (%opt) = @_; |
| 365 |
my $charset = lc shift; |
warn "Parse error ($opt{type})\n"; |
| 366 |
## TODO: if $charset is supported |
}; |
| 367 |
## TODO: normalize charset name |
$self->{parse_error} = $onerror; # updated later by parse_char_string |
| 368 |
|
|
| 369 |
## "Change the encoding" algorithm: |
my $get_wrapper = $_[3] || sub ($) { |
| 370 |
|
return $_[0]; # $_[0] = byte stream handle, returned = arg to char handle |
| 371 |
## Step 1 |
}; |
| 372 |
if ($charset eq 'utf-16') { ## ISSUE: UTF-16BE -> UTF-8? UTF-16LE -> UTF-8? |
|
| 373 |
$charset = 'utf-8'; |
## HTML5 encoding sniffing algorithm |
| 374 |
|
require Message::Charset::Info; |
| 375 |
|
my $charset; |
| 376 |
|
my $buffer; |
| 377 |
|
my ($char_stream, $e_status); |
| 378 |
|
|
| 379 |
|
SNIFFING: { |
| 380 |
|
## NOTE: By setting |allow_fallback| option true when the |
| 381 |
|
## |get_decode_handle| method is invoked, we ignore what the HTML5 |
| 382 |
|
## spec requires, i.e. unsupported encoding should be ignored. |
| 383 |
|
## TODO: We should not do this unless the parser is invoked |
| 384 |
|
## in the conformance checking mode, in which this behavior |
| 385 |
|
## would be useful. |
| 386 |
|
|
| 387 |
|
## Step 1 |
| 388 |
|
if (defined $charset_name) { |
| 389 |
|
$charset = Message::Charset::Info->get_by_html_name ($charset_name); |
| 390 |
|
## TODO: Is this ok? Transfer protocol's parameter should be |
| 391 |
|
## interpreted in its semantics? |
| 392 |
|
|
| 393 |
|
## ISSUE: Unsupported encoding is not ignored according to the spec. |
| 394 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 395 |
|
($byte_stream, allow_error_reporting => 1, |
| 396 |
|
allow_fallback => 1); |
| 397 |
|
if ($char_stream) { |
| 398 |
|
$self->{confident} = 1; |
| 399 |
|
last SNIFFING; |
| 400 |
|
} else { |
| 401 |
|
## TODO: unsupported error |
| 402 |
|
} |
| 403 |
} |
} |
| 404 |
|
|
| 405 |
## Step 2 |
## Step 2 |
| 406 |
if (defined $self->{input_encoding} and |
my $byte_buffer = ''; |
| 407 |
$self->{input_encoding} eq $charset) { |
for (1..1024) { |
| 408 |
|
my $char = $byte_stream->getc; |
| 409 |
|
last unless defined $char; |
| 410 |
|
$byte_buffer .= $char; |
| 411 |
|
} ## TODO: timeout |
| 412 |
|
|
| 413 |
|
## Step 3 |
| 414 |
|
if ($byte_buffer =~ /^\xFE\xFF/) { |
| 415 |
|
$charset = Message::Charset::Info->get_by_html_name ('utf-16be'); |
| 416 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 417 |
|
($byte_stream, allow_error_reporting => 1, |
| 418 |
|
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 419 |
$self->{confident} = 1; |
$self->{confident} = 1; |
| 420 |
return; |
last SNIFFING; |
| 421 |
|
} elsif ($byte_buffer =~ /^\xFF\xFE/) { |
| 422 |
|
$charset = Message::Charset::Info->get_by_html_name ('utf-16le'); |
| 423 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 424 |
|
($byte_stream, allow_error_reporting => 1, |
| 425 |
|
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 426 |
|
$self->{confident} = 1; |
| 427 |
|
last SNIFFING; |
| 428 |
|
} elsif ($byte_buffer =~ /^\xEF\xBB\xBF/) { |
| 429 |
|
$charset = Message::Charset::Info->get_by_html_name ('utf-8'); |
| 430 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 431 |
|
($byte_stream, allow_error_reporting => 1, |
| 432 |
|
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 433 |
|
$self->{confident} = 1; |
| 434 |
|
last SNIFFING; |
| 435 |
} |
} |
| 436 |
|
|
| 437 |
!!!parse-error (type => 'charset label detected:'.$self->{input_encoding}. |
## Step 4 |
| 438 |
':'.$charset, level => 'w'); |
## TODO: <meta charset> |
| 439 |
|
|
| 440 |
## Step 3 |
## Step 5 |
| 441 |
# if (can) { |
## TODO: from history |
|
## change the encoding on the fly. |
|
|
#$self->{confident} = 1; |
|
|
#return; |
|
|
# } |
|
| 442 |
|
|
| 443 |
## Step 4 |
## Step 6 |
| 444 |
throw Whatpm::HTML::RestartParser (charset => $charset); |
require Whatpm::Charset::UniversalCharDet; |
| 445 |
|
$charset_name = Whatpm::Charset::UniversalCharDet->detect_byte_string |
| 446 |
|
($byte_buffer); |
| 447 |
|
if (defined $charset_name) { |
| 448 |
|
$charset = Message::Charset::Info->get_by_html_name ($charset_name); |
| 449 |
|
|
| 450 |
|
## ISSUE: Unsupported encoding is not ignored according to the spec. |
| 451 |
|
require Whatpm::Charset::DecodeHandle; |
| 452 |
|
$buffer = Whatpm::Charset::DecodeHandle::ByteBuffer->new |
| 453 |
|
($byte_stream); |
| 454 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 455 |
|
($buffer, allow_error_reporting => 1, |
| 456 |
|
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 457 |
|
if ($char_stream) { |
| 458 |
|
$buffer->{buffer} = $byte_buffer; |
| 459 |
|
!!!parse-error (type => 'sniffing:chardet', |
| 460 |
|
text => $charset_name, |
| 461 |
|
level => $self->{level}->{info}, |
| 462 |
|
layer => 'encode', |
| 463 |
|
line => 1, column => 1); |
| 464 |
|
$self->{confident} = 0; |
| 465 |
|
last SNIFFING; |
| 466 |
|
} |
| 467 |
|
} |
| 468 |
|
|
| 469 |
|
## Step 7: default |
| 470 |
|
## TODO: Make this configurable. |
| 471 |
|
$charset = Message::Charset::Info->get_by_html_name ('windows-1252'); |
| 472 |
|
## NOTE: We choose |windows-1252| here, since |utf-8| should be |
| 473 |
|
## detectable in the step 6. |
| 474 |
|
require Whatpm::Charset::DecodeHandle; |
| 475 |
|
$buffer = Whatpm::Charset::DecodeHandle::ByteBuffer->new |
| 476 |
|
($byte_stream); |
| 477 |
|
($char_stream, $e_status) |
| 478 |
|
= $charset->get_decode_handle ($buffer, |
| 479 |
|
allow_error_reporting => 1, |
| 480 |
|
allow_fallback => 1, |
| 481 |
|
byte_buffer => \$byte_buffer); |
| 482 |
|
$buffer->{buffer} = $byte_buffer; |
| 483 |
|
!!!parse-error (type => 'sniffing:default', |
| 484 |
|
text => 'windows-1252', |
| 485 |
|
level => $self->{level}->{info}, |
| 486 |
|
line => 1, column => 1, |
| 487 |
|
layer => 'encode'); |
| 488 |
|
$self->{confident} = 0; |
| 489 |
|
} # SNIFFING |
| 490 |
|
|
| 491 |
|
if ($e_status & Message::Charset::Info::FALLBACK_ENCODING_IMPL ()) { |
| 492 |
|
$self->{input_encoding} = $charset->get_iana_name; ## TODO: Should we set actual charset decoder's encoding name? |
| 493 |
|
!!!parse-error (type => 'chardecode:fallback', |
| 494 |
|
#text => $self->{input_encoding}, |
| 495 |
|
level => $self->{level}->{uncertain}, |
| 496 |
|
line => 1, column => 1, |
| 497 |
|
layer => 'encode'); |
| 498 |
|
} elsif (not ($e_status & |
| 499 |
|
Message::Charset::Info::ERROR_REPORTING_ENCODING_IMPL())) { |
| 500 |
|
$self->{input_encoding} = $charset->get_iana_name; |
| 501 |
|
!!!parse-error (type => 'chardecode:no error', |
| 502 |
|
text => $self->{input_encoding}, |
| 503 |
|
level => $self->{level}->{uncertain}, |
| 504 |
|
line => 1, column => 1, |
| 505 |
|
layer => 'encode'); |
| 506 |
|
} else { |
| 507 |
|
$self->{input_encoding} = $charset->get_iana_name; |
| 508 |
|
} |
| 509 |
|
|
| 510 |
|
$self->{change_encoding} = sub { |
| 511 |
|
my $self = shift; |
| 512 |
|
$charset_name = shift; |
| 513 |
|
my $token = shift; |
| 514 |
|
|
| 515 |
|
$charset = Message::Charset::Info->get_by_html_name ($charset_name); |
| 516 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 517 |
|
($byte_stream, allow_error_reporting => 1, allow_fallback => 1, |
| 518 |
|
byte_buffer => \ $buffer->{buffer}); |
| 519 |
|
|
| 520 |
|
if ($char_stream) { # if supported |
| 521 |
|
## "Change the encoding" algorithm: |
| 522 |
|
|
| 523 |
|
## Step 1 |
| 524 |
|
if ($charset->{category} & |
| 525 |
|
Message::Charset::Info::CHARSET_CATEGORY_UTF16 ()) { |
| 526 |
|
$charset = Message::Charset::Info->get_by_html_name ('utf-8'); |
| 527 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 528 |
|
($byte_stream, |
| 529 |
|
byte_buffer => \ $buffer->{buffer}); |
| 530 |
|
} |
| 531 |
|
$charset_name = $charset->get_iana_name; |
| 532 |
|
|
| 533 |
|
## Step 2 |
| 534 |
|
if (defined $self->{input_encoding} and |
| 535 |
|
$self->{input_encoding} eq $charset_name) { |
| 536 |
|
!!!parse-error (type => 'charset label:matching', |
| 537 |
|
text => $charset_name, |
| 538 |
|
level => $self->{level}->{info}); |
| 539 |
|
$self->{confident} = 1; |
| 540 |
|
return; |
| 541 |
|
} |
| 542 |
|
|
| 543 |
|
!!!parse-error (type => 'charset label detected', |
| 544 |
|
text => $self->{input_encoding}, |
| 545 |
|
value => $charset_name, |
| 546 |
|
level => $self->{level}->{warn}, |
| 547 |
|
token => $token); |
| 548 |
|
|
| 549 |
|
## Step 3 |
| 550 |
|
# if (can) { |
| 551 |
|
## change the encoding on the fly. |
| 552 |
|
#$self->{confident} = 1; |
| 553 |
|
#return; |
| 554 |
|
# } |
| 555 |
|
|
| 556 |
|
## Step 4 |
| 557 |
|
throw Whatpm::HTML::RestartParser (); |
| 558 |
|
} |
| 559 |
}; # $self->{change_encoding} |
}; # $self->{change_encoding} |
| 560 |
|
|
| 561 |
|
my $char_onerror = sub { |
| 562 |
|
my (undef, $type, %opt) = @_; |
| 563 |
|
!!!parse-error (layer => 'encode', |
| 564 |
|
%opt, type => $type, |
| 565 |
|
line => $self->{line}, column => $self->{column} + 1); |
| 566 |
|
if ($opt{octets}) { |
| 567 |
|
${$opt{octets}} = "\x{FFFD}"; # relacement character |
| 568 |
|
} |
| 569 |
|
}; |
| 570 |
|
|
| 571 |
|
my $wrapped_char_stream = $get_wrapper->($char_stream); |
| 572 |
|
$wrapped_char_stream->onerror ($char_onerror); |
| 573 |
|
|
| 574 |
my @args = @_; shift @args; # $s |
my @args = @_; shift @args; # $s |
| 575 |
my $return; |
my $return; |
| 576 |
try { |
try { |
| 577 |
$return = $self->parse_char_string ($s, @args); |
$return = $self->parse_char_stream ($wrapped_char_stream, @args); |
| 578 |
} catch Whatpm::HTML::RestartParser with { |
} catch Whatpm::HTML::RestartParser with { |
| 579 |
my $charset = shift->{charset}; |
## NOTE: Invoked after {change_encoding}. |
| 580 |
$s = \ (Encode::decode ($charset, $$bytes_s)); |
|
| 581 |
$self->{input_encoding} = $charset; ## TODO: normalize |
if ($e_status & Message::Charset::Info::FALLBACK_ENCODING_IMPL ()) { |
| 582 |
|
$self->{input_encoding} = $charset->get_iana_name; ## TODO: Should we set actual charset decoder's encoding name? |
| 583 |
|
!!!parse-error (type => 'chardecode:fallback', |
| 584 |
|
level => $self->{level}->{uncertain}, |
| 585 |
|
#text => $self->{input_encoding}, |
| 586 |
|
line => 1, column => 1, |
| 587 |
|
layer => 'encode'); |
| 588 |
|
} elsif (not ($e_status & |
| 589 |
|
Message::Charset::Info::ERROR_REPORTING_ENCODING_IMPL())) { |
| 590 |
|
$self->{input_encoding} = $charset->get_iana_name; |
| 591 |
|
!!!parse-error (type => 'chardecode:no error', |
| 592 |
|
text => $self->{input_encoding}, |
| 593 |
|
level => $self->{level}->{uncertain}, |
| 594 |
|
line => 1, column => 1, |
| 595 |
|
layer => 'encode'); |
| 596 |
|
} else { |
| 597 |
|
$self->{input_encoding} = $charset->get_iana_name; |
| 598 |
|
} |
| 599 |
$self->{confident} = 1; |
$self->{confident} = 1; |
| 600 |
$return = $self->parse_char_string ($s, @args); |
|
| 601 |
|
$wrapped_char_stream = $get_wrapper->($char_stream); |
| 602 |
|
$wrapped_char_stream->onerror ($char_onerror); |
| 603 |
|
|
| 604 |
|
$return = $self->parse_char_stream ($wrapped_char_stream, @args); |
| 605 |
}; |
}; |
| 606 |
return $return; |
return $return; |
| 607 |
} # parse_byte_string |
} # parse_byte_stream |
| 608 |
|
|
| 609 |
## NOTE: HTML5 spec says that the encoding layer MUST NOT strip BOM |
## NOTE: HTML5 spec says that the encoding layer MUST NOT strip BOM |
| 610 |
## and the HTML layer MUST ignore it. However, we does strip BOM in |
## and the HTML layer MUST ignore it. However, we does strip BOM in |
| 615 |
## such as |parse_byte_string| in this module, must ensure that it does |
## such as |parse_byte_string| in this module, must ensure that it does |
| 616 |
## strip the BOM and never strip any ZWNBSP. |
## strip the BOM and never strip any ZWNBSP. |
| 617 |
|
|
| 618 |
*parse_char_string = \&parse_string; |
sub parse_char_string ($$$;$$) { |
| 619 |
|
#my ($self, $s, $doc, $onerror, $get_wrapper) = @_; |
| 620 |
|
my $self = shift; |
| 621 |
|
require utf8; |
| 622 |
|
my $s = ref $_[0] ? $_[0] : \($_[0]); |
| 623 |
|
open my $input, '<' . (utf8::is_utf8 ($$s) ? ':utf8' : ''), $s; |
| 624 |
|
if ($_[3]) { |
| 625 |
|
$input = $_[3]->($input); |
| 626 |
|
} |
| 627 |
|
return $self->parse_char_stream ($input, @_[1..$#_]); |
| 628 |
|
} # parse_char_string |
| 629 |
|
*parse_string = \&parse_char_string; ## NOTE: Alias for backward compatibility. |
| 630 |
|
|
| 631 |
sub parse_string ($$$;$) { |
sub parse_char_stream ($$$;$) { |
| 632 |
my $self = ref $_[0] ? shift : shift->new; |
my $self = ref $_[0] ? shift : shift->new; |
| 633 |
my $s = ref $_[0] ? $_[0] : \($_[0]); |
my $input = $_[0]; |
| 634 |
$self->{document} = $_[1]; |
$self->{document} = $_[1]; |
| 635 |
@{$self->{document}->child_nodes} = (); |
@{$self->{document}->child_nodes} = (); |
| 636 |
|
|
| 641 |
if defined $self->{input_encoding}; |
if defined $self->{input_encoding}; |
| 642 |
|
|
| 643 |
my $i = 0; |
my $i = 0; |
| 644 |
my $line = 1; |
$self->{line_prev} = $self->{line} = 1; |
| 645 |
my $column = 0; |
$self->{column_prev} = $self->{column} = 0; |
| 646 |
$self->{set_next_char} = sub { |
$self->{set_next_char} = sub { |
| 647 |
my $self = shift; |
my $self = shift; |
| 648 |
|
|
| 649 |
pop @{$self->{prev_char}}; |
pop @{$self->{prev_char}}; |
| 650 |
unshift @{$self->{prev_char}}, $self->{next_char}; |
unshift @{$self->{prev_char}}, $self->{next_char}; |
| 651 |
|
|
| 652 |
$self->{next_char} = -1 and return if $i >= length $$s; |
my $char; |
| 653 |
$self->{next_char} = ord substr $$s, $i++, 1; |
if (defined $self->{next_next_char}) { |
| 654 |
$column++; |
$char = $self->{next_next_char}; |
| 655 |
|
delete $self->{next_next_char}; |
| 656 |
|
} else { |
| 657 |
|
$char = $input->getc; |
| 658 |
|
} |
| 659 |
|
$self->{next_char} = -1 and return unless defined $char; |
| 660 |
|
$self->{next_char} = ord $char; |
| 661 |
|
|
| 662 |
|
($self->{line_prev}, $self->{column_prev}) |
| 663 |
|
= ($self->{line}, $self->{column}); |
| 664 |
|
$self->{column}++; |
| 665 |
|
|
| 666 |
if ($self->{next_char} == 0x000A) { # LF |
if ($self->{next_char} == 0x000A) { # LF |
| 667 |
$line++; |
!!!cp ('j1'); |
| 668 |
$column = 0; |
$self->{line}++; |
| 669 |
|
$self->{column} = 0; |
| 670 |
} elsif ($self->{next_char} == 0x000D) { # CR |
} elsif ($self->{next_char} == 0x000D) { # CR |
| 671 |
$i++ if substr ($$s, $i, 1) eq "\x0A"; |
!!!cp ('j2'); |
| 672 |
|
## TODO: support for abort/streaming |
| 673 |
|
my $next = $input->getc; |
| 674 |
|
if (defined $next and $next ne "\x0A") { |
| 675 |
|
$self->{next_next_char} = $next; |
| 676 |
|
} |
| 677 |
$self->{next_char} = 0x000A; # LF # MUST |
$self->{next_char} = 0x000A; # LF # MUST |
| 678 |
$line++; |
$self->{line}++; |
| 679 |
$column = 0; |
$self->{column} = 0; |
| 680 |
} elsif ($self->{next_char} > 0x10FFFF) { |
} elsif ($self->{next_char} > 0x10FFFF) { |
| 681 |
|
!!!cp ('j3'); |
| 682 |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
| 683 |
} elsif ($self->{next_char} == 0x0000) { # NULL |
} elsif ($self->{next_char} == 0x0000) { # NULL |
| 684 |
|
!!!cp ('j4'); |
| 685 |
!!!parse-error (type => 'NULL'); |
!!!parse-error (type => 'NULL'); |
| 686 |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
| 687 |
|
} elsif ($self->{next_char} <= 0x0008 or |
| 688 |
|
(0x000E <= $self->{next_char} and $self->{next_char} <= 0x001F) or |
| 689 |
|
(0x007F <= $self->{next_char} and $self->{next_char} <= 0x009F) or |
| 690 |
|
(0xD800 <= $self->{next_char} and $self->{next_char} <= 0xDFFF) or |
| 691 |
|
(0xFDD0 <= $self->{next_char} and $self->{next_char} <= 0xFDDF) or |
| 692 |
|
{ |
| 693 |
|
0xFFFE => 1, 0xFFFF => 1, 0x1FFFE => 1, 0x1FFFF => 1, |
| 694 |
|
0x2FFFE => 1, 0x2FFFF => 1, 0x3FFFE => 1, 0x3FFFF => 1, |
| 695 |
|
0x4FFFE => 1, 0x4FFFF => 1, 0x5FFFE => 1, 0x5FFFF => 1, |
| 696 |
|
0x6FFFE => 1, 0x6FFFF => 1, 0x7FFFE => 1, 0x7FFFF => 1, |
| 697 |
|
0x8FFFE => 1, 0x8FFFF => 1, 0x9FFFE => 1, 0x9FFFF => 1, |
| 698 |
|
0xAFFFE => 1, 0xAFFFF => 1, 0xBFFFE => 1, 0xBFFFF => 1, |
| 699 |
|
0xCFFFE => 1, 0xCFFFF => 1, 0xDFFFE => 1, 0xDFFFF => 1, |
| 700 |
|
0xEFFFE => 1, 0xEFFFF => 1, 0xFFFFE => 1, 0xFFFFF => 1, |
| 701 |
|
0x10FFFE => 1, 0x10FFFF => 1, |
| 702 |
|
}->{$self->{next_char}}) { |
| 703 |
|
!!!cp ('j5'); |
| 704 |
|
if ($self->{next_char} < 0x10000) { |
| 705 |
|
!!!parse-error (type => 'control char', |
| 706 |
|
text => (sprintf 'U+%04X', $self->{next_char})); |
| 707 |
|
} else { |
| 708 |
|
!!!parse-error (type => 'control char', |
| 709 |
|
text => (sprintf 'U-%08X', $self->{next_char})); |
| 710 |
|
} |
| 711 |
} |
} |
| 712 |
}; |
}; |
| 713 |
$self->{prev_char} = [-1, -1, -1]; |
$self->{prev_char} = [-1, -1, -1]; |
| 715 |
|
|
| 716 |
my $onerror = $_[2] || sub { |
my $onerror = $_[2] || sub { |
| 717 |
my (%opt) = @_; |
my (%opt) = @_; |
| 718 |
warn "Parse error ($opt{type}) at line $opt{line} column $opt{column}\n"; |
my $line = $opt{token} ? $opt{token}->{line} : $opt{line}; |
| 719 |
|
my $column = $opt{token} ? $opt{token}->{column} : $opt{column}; |
| 720 |
|
warn "Parse error ($opt{type}) at line $line column $column\n"; |
| 721 |
}; |
}; |
| 722 |
$self->{parse_error} = sub { |
$self->{parse_error} = sub { |
| 723 |
$onerror->(@_, line => $line, column => $column); |
$onerror->(line => $self->{line}, column => $self->{column}, @_); |
| 724 |
}; |
}; |
| 725 |
|
|
| 726 |
$self->_initialize_tokenizer; |
$self->_initialize_tokenizer; |
| 728 |
$self->_construct_tree; |
$self->_construct_tree; |
| 729 |
$self->_terminate_tree_constructor; |
$self->_terminate_tree_constructor; |
| 730 |
|
|
| 731 |
|
delete $self->{parse_error}; # remove loop |
| 732 |
|
|
| 733 |
return $self->{document}; |
return $self->{document}; |
| 734 |
} # parse_string |
} # parse_char_stream |
| 735 |
|
|
| 736 |
sub new ($) { |
sub new ($) { |
| 737 |
my $class = shift; |
my $class = shift; |
| 738 |
my $self = bless {}, $class; |
my $self = bless { |
| 739 |
|
level => {must => 'm', |
| 740 |
|
should => 's', |
| 741 |
|
warn => 'w', |
| 742 |
|
info => 'i', |
| 743 |
|
uncertain => 'u'}, |
| 744 |
|
}, $class; |
| 745 |
$self->{set_next_char} = sub { |
$self->{set_next_char} = sub { |
| 746 |
$self->{next_char} = -1; |
$self->{next_char} = -1; |
| 747 |
}; |
}; |
| 770 |
sub PCDATA_CONTENT_MODEL () { CM_ENTITY | CM_FULL_MARKUP } |
sub PCDATA_CONTENT_MODEL () { CM_ENTITY | CM_FULL_MARKUP } |
| 771 |
|
|
| 772 |
sub DATA_STATE () { 0 } |
sub DATA_STATE () { 0 } |
| 773 |
sub ENTITY_DATA_STATE () { 1 } |
#sub ENTITY_DATA_STATE () { 1 } |
| 774 |
sub TAG_OPEN_STATE () { 2 } |
sub TAG_OPEN_STATE () { 2 } |
| 775 |
sub CLOSE_TAG_OPEN_STATE () { 3 } |
sub CLOSE_TAG_OPEN_STATE () { 3 } |
| 776 |
sub TAG_NAME_STATE () { 4 } |
sub TAG_NAME_STATE () { 4 } |
| 781 |
sub ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE () { 9 } |
sub ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE () { 9 } |
| 782 |
sub ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE () { 10 } |
sub ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE () { 10 } |
| 783 |
sub ATTRIBUTE_VALUE_UNQUOTED_STATE () { 11 } |
sub ATTRIBUTE_VALUE_UNQUOTED_STATE () { 11 } |
| 784 |
sub ENTITY_IN_ATTRIBUTE_VALUE_STATE () { 12 } |
#sub ENTITY_IN_ATTRIBUTE_VALUE_STATE () { 12 } |
| 785 |
sub MARKUP_DECLARATION_OPEN_STATE () { 13 } |
sub MARKUP_DECLARATION_OPEN_STATE () { 13 } |
| 786 |
sub COMMENT_START_STATE () { 14 } |
sub COMMENT_START_STATE () { 14 } |
| 787 |
sub COMMENT_START_DASH_STATE () { 15 } |
sub COMMENT_START_DASH_STATE () { 15 } |
| 803 |
sub AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE () { 31 } |
sub AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE () { 31 } |
| 804 |
sub BOGUS_DOCTYPE_STATE () { 32 } |
sub BOGUS_DOCTYPE_STATE () { 32 } |
| 805 |
sub AFTER_ATTRIBUTE_VALUE_QUOTED_STATE () { 33 } |
sub AFTER_ATTRIBUTE_VALUE_QUOTED_STATE () { 33 } |
| 806 |
|
sub SELF_CLOSING_START_TAG_STATE () { 34 } |
| 807 |
|
sub CDATA_SECTION_STATE () { 35 } |
| 808 |
|
sub MD_HYPHEN_STATE () { 36 } # "markup declaration open state" in the spec |
| 809 |
|
sub MD_DOCTYPE_STATE () { 37 } # "markup declaration open state" in the spec |
| 810 |
|
sub MD_CDATA_STATE () { 38 } # "markup declaration open state" in the spec |
| 811 |
|
sub CDATA_PCDATA_CLOSE_TAG_STATE () { 39 } # "close tag open state" in the spec |
| 812 |
|
sub CDATA_SECTION_MSE1_STATE () { 40 } # "CDATA section state" in the spec |
| 813 |
|
sub CDATA_SECTION_MSE2_STATE () { 41 } # "CDATA section state" in the spec |
| 814 |
|
sub PUBLIC_STATE () { 42 } # "after DOCTYPE name state" in the spec |
| 815 |
|
sub SYSTEM_STATE () { 43 } # "after DOCTYPE name state" in the spec |
| 816 |
|
## NOTE: "Entity data state", "entity in attribute value state", and |
| 817 |
|
## "consume a character reference" algorithm are jointly implemented |
| 818 |
|
## using the following six states: |
| 819 |
|
sub ENTITY_STATE () { 44 } |
| 820 |
|
sub ENTITY_HASH_STATE () { 45 } |
| 821 |
|
sub NCR_NUM_STATE () { 46 } |
| 822 |
|
sub HEXREF_X_STATE () { 47 } |
| 823 |
|
sub HEXREF_HEX_STATE () { 48 } |
| 824 |
|
sub ENTITY_NAME_STATE () { 49 } |
| 825 |
|
|
| 826 |
sub DOCTYPE_TOKEN () { 1 } |
sub DOCTYPE_TOKEN () { 1 } |
| 827 |
sub COMMENT_TOKEN () { 2 } |
sub COMMENT_TOKEN () { 2 } |
| 839 |
sub BODY_AFTER_IMS () { 0b100000000 } |
sub BODY_AFTER_IMS () { 0b100000000 } |
| 840 |
sub FRAME_IMS () { 0b1000000000 } |
sub FRAME_IMS () { 0b1000000000 } |
| 841 |
sub SELECT_IMS () { 0b10000000000 } |
sub SELECT_IMS () { 0b10000000000 } |
| 842 |
|
sub IN_FOREIGN_CONTENT_IM () { 0b100000000000 } |
| 843 |
|
## NOTE: "in foreign content" insertion mode is special; it is combined |
| 844 |
|
## with the secondary insertion mode. In this parser, they are stored |
| 845 |
|
## together in the bit-or'ed form. |
| 846 |
|
|
| 847 |
## NOTE: "initial" and "before html" insertion modes have no constants. |
## NOTE: "initial" and "before html" insertion modes have no constants. |
| 848 |
|
|
| 874 |
sub _initialize_tokenizer ($) { |
sub _initialize_tokenizer ($) { |
| 875 |
my $self = shift; |
my $self = shift; |
| 876 |
$self->{state} = DATA_STATE; # MUST |
$self->{state} = DATA_STATE; # MUST |
| 877 |
|
#$self->{state_keyword}; # initialized when used |
| 878 |
|
#$self->{entity__value}; # initialized when used |
| 879 |
|
#$self->{entity__match}; # initialized when used |
| 880 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # be |
$self->{content_model} = PCDATA_CONTENT_MODEL; # be |
| 881 |
undef $self->{current_token}; # start tag, end tag, comment, or DOCTYPE |
undef $self->{current_token}; |
| 882 |
undef $self->{current_attribute}; |
undef $self->{current_attribute}; |
| 883 |
undef $self->{last_emitted_start_tag_name}; |
undef $self->{last_emitted_start_tag_name}; |
| 884 |
undef $self->{last_attribute_value_state}; |
#$self->{prev_state}; # initialized when used |
| 885 |
$self->{char} = []; |
delete $self->{self_closing}; |
| 886 |
# $self->{next_char} |
# $self->{next_char} |
| 887 |
!!!next-input-character; |
!!!next-input-character; |
| 888 |
$self->{token} = []; |
$self->{token} = []; |
| 902 |
## ->{value} |
## ->{value} |
| 903 |
## ->{has_reference} == 1 or 0 |
## ->{has_reference} == 1 or 0 |
| 904 |
## ->{data} (COMMENT_TOKEN, CHARACTER_TOKEN) |
## ->{data} (COMMENT_TOKEN, CHARACTER_TOKEN) |
| 905 |
|
## NOTE: The "self-closing flag" is hold as |$self->{self_closing}|. |
| 906 |
|
## |->{self_closing}| is used to save the value of |$self->{self_closing}| |
| 907 |
|
## while the token is pushed back to the stack. |
| 908 |
|
|
| 909 |
## Emitted token MUST immediately be handled by the tree construction state. |
## Emitted token MUST immediately be handled by the tree construction state. |
| 910 |
|
|
| 914 |
## has completed loading. If one has, then it MUST be executed |
## has completed loading. If one has, then it MUST be executed |
| 915 |
## and removed from the list. |
## and removed from the list. |
| 916 |
|
|
| 917 |
## NOTE: HTML5 "Writing HTML documents" section, applied to |
## TODO: Polytheistic slash SHOULD NOT be used. (Applied only to atheists.) |
| 918 |
## documents and not to user agents and conformance checkers, |
## (This requirement was dropped from HTML5 spec, unfortunately.) |
|
## contains some requirements that are not detected by the |
|
|
## parsing algorithm: |
|
|
## - Some requirements on character encoding declarations. ## TODO |
|
|
## - "Elements MUST NOT contain content that their content model disallows." |
|
|
## ... Some are parse error, some are not (will be reported by c.c.). |
|
|
## - Polytheistic slash SHOULD NOT be used. (Applied only to atheists.) ## TODO |
|
|
## - Text (in elements, attributes, and comments) SHOULD NOT contain |
|
|
## control characters other than space characters. ## TODO: (what is control character? C0, C1 and DEL? Unicode control character?) |
|
|
|
|
|
## TODO: HTML5 poses authors two SHOULD-level requirements that cannot |
|
|
## be detected by the HTML5 parsing algorithm: |
|
|
## - Text, |
|
| 919 |
|
|
| 920 |
sub _get_next_token ($) { |
sub _get_next_token ($) { |
| 921 |
my $self = shift; |
my $self = shift; |
| 922 |
|
|
| 923 |
|
if ($self->{self_closing}) { |
| 924 |
|
!!!parse-error (type => 'nestc', token => $self->{current_token}); |
| 925 |
|
## NOTE: The |self_closing| flag is only set by start tag token. |
| 926 |
|
## In addition, when a start tag token is emitted, it is always set to |
| 927 |
|
## |current_token|. |
| 928 |
|
delete $self->{self_closing}; |
| 929 |
|
} |
| 930 |
|
|
| 931 |
if (@{$self->{token}}) { |
if (@{$self->{token}}) { |
| 932 |
|
$self->{self_closing} = $self->{token}->[0]->{self_closing}; |
| 933 |
return shift @{$self->{token}}; |
return shift @{$self->{token}}; |
| 934 |
} |
} |
| 935 |
|
|
| 939 |
if ($self->{content_model} & CM_ENTITY and # PCDATA | RCDATA |
if ($self->{content_model} & CM_ENTITY and # PCDATA | RCDATA |
| 940 |
not $self->{escape}) { |
not $self->{escape}) { |
| 941 |
!!!cp (1); |
!!!cp (1); |
| 942 |
$self->{state} = ENTITY_DATA_STATE; |
## NOTE: In the spec, the tokenizer is switched to the |
| 943 |
|
## "entity data state". In this implementation, the tokenizer |
| 944 |
|
## is switched to the |ENTITY_STATE|, which is an implementation |
| 945 |
|
## of the "consume a character reference" algorithm. |
| 946 |
|
$self->{entity_additional} = -1; |
| 947 |
|
$self->{prev_state} = DATA_STATE; |
| 948 |
|
$self->{state} = ENTITY_STATE; |
| 949 |
!!!next-input-character; |
!!!next-input-character; |
| 950 |
redo A; |
redo A; |
| 951 |
} else { |
} else { |
| 998 |
# |
# |
| 999 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 1000 |
!!!cp (11); |
!!!cp (11); |
| 1001 |
!!!emit ({type => END_OF_FILE_TOKEN}); |
!!!emit ({type => END_OF_FILE_TOKEN, |
| 1002 |
|
line => $self->{line}, column => $self->{column}}); |
| 1003 |
last A; ## TODO: ok? |
last A; ## TODO: ok? |
| 1004 |
} else { |
} else { |
| 1005 |
!!!cp (12); |
!!!cp (12); |
| 1006 |
} |
} |
| 1007 |
# Anything else |
# Anything else |
| 1008 |
my $token = {type => CHARACTER_TOKEN, |
my $token = {type => CHARACTER_TOKEN, |
| 1009 |
data => chr $self->{next_char}}; |
data => chr $self->{next_char}, |
| 1010 |
|
line => $self->{line}, column => $self->{column}, |
| 1011 |
|
}; |
| 1012 |
## Stay in the data state |
## Stay in the data state |
| 1013 |
!!!next-input-character; |
!!!next-input-character; |
| 1014 |
|
|
| 1015 |
!!!emit ($token); |
!!!emit ($token); |
| 1016 |
|
|
| 1017 |
redo A; |
redo A; |
|
} elsif ($self->{state} == ENTITY_DATA_STATE) { |
|
|
## (cannot happen in CDATA state) |
|
|
|
|
|
my $token = $self->_tokenize_attempt_to_consume_an_entity (0, -1); |
|
|
|
|
|
$self->{state} = DATA_STATE; |
|
|
# next-input-character is already done |
|
|
|
|
|
unless (defined $token) { |
|
|
!!!cp (13); |
|
|
!!!emit ({type => CHARACTER_TOKEN, data => '&'}); |
|
|
} else { |
|
|
!!!cp (14); |
|
|
!!!emit ($token); |
|
|
} |
|
|
|
|
|
redo A; |
|
| 1018 |
} elsif ($self->{state} == TAG_OPEN_STATE) { |
} elsif ($self->{state} == TAG_OPEN_STATE) { |
| 1019 |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
| 1020 |
if ($self->{next_char} == 0x002F) { # / |
if ($self->{next_char} == 0x002F) { # / |
| 1027 |
## reconsume |
## reconsume |
| 1028 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1029 |
|
|
| 1030 |
!!!emit ({type => CHARACTER_TOKEN, data => '<'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '<', |
| 1031 |
|
line => $self->{line_prev}, |
| 1032 |
|
column => $self->{column_prev}, |
| 1033 |
|
}); |
| 1034 |
|
|
| 1035 |
redo A; |
redo A; |
| 1036 |
} |
} |
| 1050 |
!!!cp (19); |
!!!cp (19); |
| 1051 |
$self->{current_token} |
$self->{current_token} |
| 1052 |
= {type => START_TAG_TOKEN, |
= {type => START_TAG_TOKEN, |
| 1053 |
tag_name => chr ($self->{next_char} + 0x0020)}; |
tag_name => chr ($self->{next_char} + 0x0020), |
| 1054 |
|
line => $self->{line_prev}, |
| 1055 |
|
column => $self->{column_prev}}; |
| 1056 |
$self->{state} = TAG_NAME_STATE; |
$self->{state} = TAG_NAME_STATE; |
| 1057 |
!!!next-input-character; |
!!!next-input-character; |
| 1058 |
redo A; |
redo A; |
| 1060 |
$self->{next_char} <= 0x007A) { # a..z |
$self->{next_char} <= 0x007A) { # a..z |
| 1061 |
!!!cp (20); |
!!!cp (20); |
| 1062 |
$self->{current_token} = {type => START_TAG_TOKEN, |
$self->{current_token} = {type => START_TAG_TOKEN, |
| 1063 |
tag_name => chr ($self->{next_char})}; |
tag_name => chr ($self->{next_char}), |
| 1064 |
|
line => $self->{line_prev}, |
| 1065 |
|
column => $self->{column_prev}}; |
| 1066 |
$self->{state} = TAG_NAME_STATE; |
$self->{state} = TAG_NAME_STATE; |
| 1067 |
!!!next-input-character; |
!!!next-input-character; |
| 1068 |
redo A; |
redo A; |
| 1069 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1070 |
!!!cp (21); |
!!!cp (21); |
| 1071 |
!!!parse-error (type => 'empty start tag'); |
!!!parse-error (type => 'empty start tag', |
| 1072 |
|
line => $self->{line_prev}, |
| 1073 |
|
column => $self->{column_prev}); |
| 1074 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1075 |
!!!next-input-character; |
!!!next-input-character; |
| 1076 |
|
|
| 1077 |
!!!emit ({type => CHARACTER_TOKEN, data => '<>'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '<>', |
| 1078 |
|
line => $self->{line_prev}, |
| 1079 |
|
column => $self->{column_prev}, |
| 1080 |
|
}); |
| 1081 |
|
|
| 1082 |
redo A; |
redo A; |
| 1083 |
} elsif ($self->{next_char} == 0x003F) { # ? |
} elsif ($self->{next_char} == 0x003F) { # ? |
| 1084 |
!!!cp (22); |
!!!cp (22); |
| 1085 |
!!!parse-error (type => 'pio'); |
!!!parse-error (type => 'pio', |
| 1086 |
|
line => $self->{line_prev}, |
| 1087 |
|
column => $self->{column_prev}); |
| 1088 |
$self->{state} = BOGUS_COMMENT_STATE; |
$self->{state} = BOGUS_COMMENT_STATE; |
| 1089 |
|
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
| 1090 |
|
line => $self->{line_prev}, |
| 1091 |
|
column => $self->{column_prev}, |
| 1092 |
|
}; |
| 1093 |
## $self->{next_char} is intentionally left as is |
## $self->{next_char} is intentionally left as is |
| 1094 |
redo A; |
redo A; |
| 1095 |
} else { |
} else { |
| 1096 |
!!!cp (23); |
!!!cp (23); |
| 1097 |
!!!parse-error (type => 'bare stago'); |
!!!parse-error (type => 'bare stago', |
| 1098 |
|
line => $self->{line_prev}, |
| 1099 |
|
column => $self->{column_prev}); |
| 1100 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1101 |
## reconsume |
## reconsume |
| 1102 |
|
|
| 1103 |
!!!emit ({type => CHARACTER_TOKEN, data => '<'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '<', |
| 1104 |
|
line => $self->{line_prev}, |
| 1105 |
|
column => $self->{column_prev}, |
| 1106 |
|
}); |
| 1107 |
|
|
| 1108 |
redo A; |
redo A; |
| 1109 |
} |
} |
| 1111 |
die "$0: $self->{content_model} in tag open"; |
die "$0: $self->{content_model} in tag open"; |
| 1112 |
} |
} |
| 1113 |
} elsif ($self->{state} == CLOSE_TAG_OPEN_STATE) { |
} elsif ($self->{state} == CLOSE_TAG_OPEN_STATE) { |
| 1114 |
|
## NOTE: The "close tag open state" in the spec is implemented as |
| 1115 |
|
## |CLOSE_TAG_OPEN_STATE| and |CDATA_PCDATA_CLOSE_TAG_STATE|. |
| 1116 |
|
|
| 1117 |
|
my ($l, $c) = ($self->{line_prev}, $self->{column_prev} - 1); # "<"of"</" |
| 1118 |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
| 1119 |
if (defined $self->{last_emitted_start_tag_name}) { |
if (defined $self->{last_emitted_start_tag_name}) { |
| 1120 |
## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564> |
$self->{state} = CDATA_PCDATA_CLOSE_TAG_STATE; |
| 1121 |
my @next_char; |
$self->{state_keyword} = ''; |
| 1122 |
TAGNAME: for (my $i = 0; $i < length $self->{last_emitted_start_tag_name}; $i++) { |
## Reconsume. |
| 1123 |
push @next_char, $self->{next_char}; |
redo A; |
|
my $c = ord substr ($self->{last_emitted_start_tag_name}, $i, 1); |
|
|
my $C = 0x0061 <= $c && $c <= 0x007A ? $c - 0x0020 : $c; |
|
|
if ($self->{next_char} == $c or $self->{next_char} == $C) { |
|
|
!!!cp (24); |
|
|
!!!next-input-character; |
|
|
next TAGNAME; |
|
|
} else { |
|
|
!!!cp (25); |
|
|
$self->{next_char} = shift @next_char; # reconsume |
|
|
!!!back-next-input-character (@next_char); |
|
|
$self->{state} = DATA_STATE; |
|
|
|
|
|
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
|
|
|
|
|
redo A; |
|
|
} |
|
|
} |
|
|
push @next_char, $self->{next_char}; |
|
|
|
|
|
unless ($self->{next_char} == 0x0009 or # HT |
|
|
$self->{next_char} == 0x000A or # LF |
|
|
$self->{next_char} == 0x000B or # VT |
|
|
$self->{next_char} == 0x000C or # FF |
|
|
$self->{next_char} == 0x0020 or # SP |
|
|
$self->{next_char} == 0x003E or # > |
|
|
$self->{next_char} == 0x002F or # / |
|
|
$self->{next_char} == -1) { |
|
|
!!!cp (26); |
|
|
$self->{next_char} = shift @next_char; # reconsume |
|
|
!!!back-next-input-character (@next_char); |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (27); |
|
|
$self->{next_char} = shift @next_char; |
|
|
!!!back-next-input-character (@next_char); |
|
|
# and consume... |
|
|
} |
|
| 1124 |
} else { |
} else { |
| 1125 |
## No start tag token has ever been emitted |
## No start tag token has ever been emitted |
| 1126 |
|
## NOTE: See <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564>. |
| 1127 |
!!!cp (28); |
!!!cp (28); |
|
# next-input-character is already done |
|
| 1128 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1129 |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
## Reconsume. |
| 1130 |
|
!!!emit ({type => CHARACTER_TOKEN, data => '</', |
| 1131 |
|
line => $l, column => $c, |
| 1132 |
|
}); |
| 1133 |
redo A; |
redo A; |
| 1134 |
} |
} |
| 1135 |
} |
} |
| 1136 |
|
|
| 1137 |
if (0x0041 <= $self->{next_char} and |
if (0x0041 <= $self->{next_char} and |
| 1138 |
$self->{next_char} <= 0x005A) { # A..Z |
$self->{next_char} <= 0x005A) { # A..Z |
| 1139 |
!!!cp (29); |
!!!cp (29); |
| 1140 |
$self->{current_token} = {type => END_TAG_TOKEN, |
$self->{current_token} |
| 1141 |
tag_name => chr ($self->{next_char} + 0x0020)}; |
= {type => END_TAG_TOKEN, |
| 1142 |
|
tag_name => chr ($self->{next_char} + 0x0020), |
| 1143 |
|
line => $l, column => $c}; |
| 1144 |
$self->{state} = TAG_NAME_STATE; |
$self->{state} = TAG_NAME_STATE; |
| 1145 |
!!!next-input-character; |
!!!next-input-character; |
| 1146 |
redo A; |
redo A; |
| 1148 |
$self->{next_char} <= 0x007A) { # a..z |
$self->{next_char} <= 0x007A) { # a..z |
| 1149 |
!!!cp (30); |
!!!cp (30); |
| 1150 |
$self->{current_token} = {type => END_TAG_TOKEN, |
$self->{current_token} = {type => END_TAG_TOKEN, |
| 1151 |
tag_name => chr ($self->{next_char})}; |
tag_name => chr ($self->{next_char}), |
| 1152 |
|
line => $l, column => $c}; |
| 1153 |
$self->{state} = TAG_NAME_STATE; |
$self->{state} = TAG_NAME_STATE; |
| 1154 |
!!!next-input-character; |
!!!next-input-character; |
| 1155 |
redo A; |
redo A; |
| 1156 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1157 |
!!!cp (31); |
!!!cp (31); |
| 1158 |
!!!parse-error (type => 'empty end tag'); |
!!!parse-error (type => 'empty end tag', |
| 1159 |
|
line => $self->{line_prev}, ## "<" in "</>" |
| 1160 |
|
column => $self->{column_prev} - 1); |
| 1161 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1162 |
!!!next-input-character; |
!!!next-input-character; |
| 1163 |
redo A; |
redo A; |
| 1167 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 1168 |
# reconsume |
# reconsume |
| 1169 |
|
|
| 1170 |
!!!emit ({type => CHARACTER_TOKEN, data => '</'}); |
!!!emit ({type => CHARACTER_TOKEN, data => '</', |
| 1171 |
|
line => $l, column => $c, |
| 1172 |
|
}); |
| 1173 |
|
|
| 1174 |
redo A; |
redo A; |
| 1175 |
} else { |
} else { |
| 1176 |
!!!cp (33); |
!!!cp (33); |
| 1177 |
!!!parse-error (type => 'bogus end tag'); |
!!!parse-error (type => 'bogus end tag'); |
| 1178 |
$self->{state} = BOGUS_COMMENT_STATE; |
$self->{state} = BOGUS_COMMENT_STATE; |
| 1179 |
## $self->{next_char} is intentionally left as is |
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
| 1180 |
redo A; |
line => $self->{line_prev}, # "<" of "</" |
| 1181 |
|
column => $self->{column_prev} - 1, |
| 1182 |
|
}; |
| 1183 |
|
## NOTE: $self->{next_char} is intentionally left as is. |
| 1184 |
|
## Although the "anything else" case of the spec not explicitly |
| 1185 |
|
## states that the next input character is to be reconsumed, |
| 1186 |
|
## it will be included to the |data| of the comment token |
| 1187 |
|
## generated from the bogus end tag, as defined in the |
| 1188 |
|
## "bogus comment state" entry. |
| 1189 |
|
redo A; |
| 1190 |
|
} |
| 1191 |
|
} elsif ($self->{state} == CDATA_PCDATA_CLOSE_TAG_STATE) { |
| 1192 |
|
my $ch = substr $self->{last_emitted_start_tag_name}, length $self->{state_keyword}, 1; |
| 1193 |
|
if (length $ch) { |
| 1194 |
|
my $CH = $ch; |
| 1195 |
|
$ch =~ tr/a-z/A-Z/; |
| 1196 |
|
my $nch = chr $self->{next_char}; |
| 1197 |
|
if ($nch eq $ch or $nch eq $CH) { |
| 1198 |
|
!!!cp (24); |
| 1199 |
|
## Stay in the state. |
| 1200 |
|
$self->{state_keyword} .= $nch; |
| 1201 |
|
!!!next-input-character; |
| 1202 |
|
redo A; |
| 1203 |
|
} else { |
| 1204 |
|
!!!cp (25); |
| 1205 |
|
$self->{state} = DATA_STATE; |
| 1206 |
|
## Reconsume. |
| 1207 |
|
!!!emit ({type => CHARACTER_TOKEN, |
| 1208 |
|
data => '</' . $self->{state_keyword}, |
| 1209 |
|
line => $self->{line_prev}, |
| 1210 |
|
column => $self->{column_prev} - 1 - length $self->{state_keyword}, |
| 1211 |
|
}); |
| 1212 |
|
redo A; |
| 1213 |
|
} |
| 1214 |
|
} else { # after "<{tag-name}" |
| 1215 |
|
unless ({ |
| 1216 |
|
0x0009 => 1, # HT |
| 1217 |
|
0x000A => 1, # LF |
| 1218 |
|
0x000B => 1, # VT |
| 1219 |
|
0x000C => 1, # FF |
| 1220 |
|
0x0020 => 1, # SP |
| 1221 |
|
0x003E => 1, # > |
| 1222 |
|
0x002F => 1, # / |
| 1223 |
|
-1 => 1, # EOF |
| 1224 |
|
}->{$self->{next_char}}) { |
| 1225 |
|
!!!cp (26); |
| 1226 |
|
## Reconsume. |
| 1227 |
|
$self->{state} = DATA_STATE; |
| 1228 |
|
!!!emit ({type => CHARACTER_TOKEN, |
| 1229 |
|
data => '</' . $self->{state_keyword}, |
| 1230 |
|
line => $self->{line_prev}, |
| 1231 |
|
column => $self->{column_prev} - 1 - length $self->{state_keyword}, |
| 1232 |
|
}); |
| 1233 |
|
redo A; |
| 1234 |
|
} else { |
| 1235 |
|
!!!cp (27); |
| 1236 |
|
$self->{current_token} |
| 1237 |
|
= {type => END_TAG_TOKEN, |
| 1238 |
|
tag_name => $self->{last_emitted_start_tag_name}, |
| 1239 |
|
line => $self->{line_prev}, |
| 1240 |
|
column => $self->{column_prev} - 1 - length $self->{state_keyword}}; |
| 1241 |
|
$self->{state} = TAG_NAME_STATE; |
| 1242 |
|
## Reconsume. |
| 1243 |
|
redo A; |
| 1244 |
|
} |
| 1245 |
} |
} |
| 1246 |
} elsif ($self->{state} == TAG_NAME_STATE) { |
} elsif ($self->{state} == TAG_NAME_STATE) { |
| 1247 |
if ($self->{next_char} == 0x0009 or # HT |
if ($self->{next_char} == 0x0009 or # HT |
| 1256 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1257 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1258 |
!!!cp (35); |
!!!cp (35); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1259 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1260 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1261 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1287 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 1288 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1289 |
!!!cp (39); |
!!!cp (39); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1290 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1291 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1292 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1307 |
|
|
| 1308 |
redo A; |
redo A; |
| 1309 |
} elsif ($self->{next_char} == 0x002F) { # / |
} elsif ($self->{next_char} == 0x002F) { # / |
| 1310 |
|
!!!cp (42); |
| 1311 |
|
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
| 1312 |
!!!next-input-character; |
!!!next-input-character; |
|
if ($self->{next_char} == 0x003E and # > |
|
|
$self->{current_token}->{type} == START_TAG_TOKEN and |
|
|
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
|
|
# permitted slash |
|
|
!!!cp (42); |
|
|
# |
|
|
} else { |
|
|
!!!cp (43); |
|
|
!!!parse-error (type => 'nestc'); |
|
|
} |
|
|
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
|
|
# next-input-character is already done |
|
| 1313 |
redo A; |
redo A; |
| 1314 |
} else { |
} else { |
| 1315 |
!!!cp (44); |
!!!cp (44); |
| 1332 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1333 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1334 |
!!!cp (46); |
!!!cp (46); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1335 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1336 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1337 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1353 |
} elsif (0x0041 <= $self->{next_char} and |
} elsif (0x0041 <= $self->{next_char} and |
| 1354 |
$self->{next_char} <= 0x005A) { # A..Z |
$self->{next_char} <= 0x005A) { # A..Z |
| 1355 |
!!!cp (49); |
!!!cp (49); |
| 1356 |
$self->{current_attribute} = {name => chr ($self->{next_char} + 0x0020), |
$self->{current_attribute} |
| 1357 |
value => ''}; |
= {name => chr ($self->{next_char} + 0x0020), |
| 1358 |
|
value => '', |
| 1359 |
|
line => $self->{line}, column => $self->{column}}; |
| 1360 |
$self->{state} = ATTRIBUTE_NAME_STATE; |
$self->{state} = ATTRIBUTE_NAME_STATE; |
| 1361 |
!!!next-input-character; |
!!!next-input-character; |
| 1362 |
redo A; |
redo A; |
| 1363 |
} elsif ($self->{next_char} == 0x002F) { # / |
} elsif ($self->{next_char} == 0x002F) { # / |
| 1364 |
|
!!!cp (50); |
| 1365 |
|
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
| 1366 |
!!!next-input-character; |
!!!next-input-character; |
|
if ($self->{next_char} == 0x003E and # > |
|
|
$self->{current_token}->{type} == START_TAG_TOKEN and |
|
|
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
|
|
# permitted slash |
|
|
!!!cp (50); |
|
|
# |
|
|
} else { |
|
|
!!!cp (51); |
|
|
!!!parse-error (type => 'nestc'); |
|
|
} |
|
|
## Stay in the state |
|
|
# next-input-character is already done |
|
| 1367 |
redo A; |
redo A; |
| 1368 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 1369 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 1370 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1371 |
!!!cp (52); |
!!!cp (52); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1372 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1373 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1374 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1398 |
} else { |
} else { |
| 1399 |
!!!cp (56); |
!!!cp (56); |
| 1400 |
} |
} |
| 1401 |
$self->{current_attribute} = {name => chr ($self->{next_char}), |
$self->{current_attribute} |
| 1402 |
value => ''}; |
= {name => chr ($self->{next_char}), |
| 1403 |
|
value => '', |
| 1404 |
|
line => $self->{line}, column => $self->{column}}; |
| 1405 |
$self->{state} = ATTRIBUTE_NAME_STATE; |
$self->{state} = ATTRIBUTE_NAME_STATE; |
| 1406 |
!!!next-input-character; |
!!!next-input-character; |
| 1407 |
redo A; |
redo A; |
| 1411 |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
| 1412 |
->{$self->{current_attribute}->{name}}) { # MUST |
->{$self->{current_attribute}->{name}}) { # MUST |
| 1413 |
!!!cp (57); |
!!!cp (57); |
| 1414 |
!!!parse-error (type => 'duplicate attribute:'.$self->{current_attribute}->{name}); |
!!!parse-error (type => 'duplicate attribute', text => $self->{current_attribute}->{name}, line => $self->{current_attribute}->{line}, column => $self->{current_attribute}->{column}); |
| 1415 |
## Discard $self->{current_attribute} # MUST |
## Discard $self->{current_attribute} # MUST |
| 1416 |
} else { |
} else { |
| 1417 |
!!!cp (58); |
!!!cp (58); |
| 1440 |
$before_leave->(); |
$before_leave->(); |
| 1441 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1442 |
!!!cp (61); |
!!!cp (61); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1443 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1444 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1445 |
!!!cp (62); |
!!!cp (62); |
| 1464 |
!!!next-input-character; |
!!!next-input-character; |
| 1465 |
redo A; |
redo A; |
| 1466 |
} elsif ($self->{next_char} == 0x002F) { # / |
} elsif ($self->{next_char} == 0x002F) { # / |
| 1467 |
|
!!!cp (64); |
| 1468 |
$before_leave->(); |
$before_leave->(); |
| 1469 |
|
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
| 1470 |
!!!next-input-character; |
!!!next-input-character; |
|
if ($self->{next_char} == 0x003E and # > |
|
|
$self->{current_token}->{type} == START_TAG_TOKEN and |
|
|
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
|
|
# permitted slash |
|
|
!!!cp (64); |
|
|
# |
|
|
} else { |
|
|
!!!cp (65); |
|
|
!!!parse-error (type => 'nestc'); |
|
|
} |
|
|
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
|
|
# next-input-character is already done |
|
| 1471 |
redo A; |
redo A; |
| 1472 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 1473 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 1474 |
$before_leave->(); |
$before_leave->(); |
| 1475 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1476 |
!!!cp (66); |
!!!cp (66); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1477 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1478 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1479 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1524 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1525 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1526 |
!!!cp (73); |
!!!cp (73); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1527 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1528 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1529 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1546 |
} elsif (0x0041 <= $self->{next_char} and |
} elsif (0x0041 <= $self->{next_char} and |
| 1547 |
$self->{next_char} <= 0x005A) { # A..Z |
$self->{next_char} <= 0x005A) { # A..Z |
| 1548 |
!!!cp (76); |
!!!cp (76); |
| 1549 |
$self->{current_attribute} = {name => chr ($self->{next_char} + 0x0020), |
$self->{current_attribute} |
| 1550 |
value => ''}; |
= {name => chr ($self->{next_char} + 0x0020), |
| 1551 |
|
value => '', |
| 1552 |
|
line => $self->{line}, column => $self->{column}}; |
| 1553 |
$self->{state} = ATTRIBUTE_NAME_STATE; |
$self->{state} = ATTRIBUTE_NAME_STATE; |
| 1554 |
!!!next-input-character; |
!!!next-input-character; |
| 1555 |
redo A; |
redo A; |
| 1556 |
} elsif ($self->{next_char} == 0x002F) { # / |
} elsif ($self->{next_char} == 0x002F) { # / |
| 1557 |
|
!!!cp (77); |
| 1558 |
|
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
| 1559 |
!!!next-input-character; |
!!!next-input-character; |
|
if ($self->{next_char} == 0x003E and # > |
|
|
$self->{current_token}->{type} == START_TAG_TOKEN and |
|
|
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
|
|
# permitted slash |
|
|
!!!cp (77); |
|
|
# |
|
|
} else { |
|
|
!!!cp (78); |
|
|
!!!parse-error (type => 'nestc'); |
|
|
## TODO: Different error type for <aa / bb> than <aa/> |
|
|
} |
|
|
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
|
|
# next-input-character is already done |
|
| 1560 |
redo A; |
redo A; |
| 1561 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 1562 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 1563 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1564 |
!!!cp (79); |
!!!cp (79); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1565 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1566 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1567 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1582 |
|
|
| 1583 |
redo A; |
redo A; |
| 1584 |
} else { |
} else { |
| 1585 |
!!!cp (82); |
if ($self->{next_char} == 0x0022 or # " |
| 1586 |
$self->{current_attribute} = {name => chr ($self->{next_char}), |
$self->{next_char} == 0x0027) { # ' |
| 1587 |
value => ''}; |
!!!cp (78); |
| 1588 |
|
!!!parse-error (type => 'bad attribute name'); |
| 1589 |
|
} else { |
| 1590 |
|
!!!cp (82); |
| 1591 |
|
} |
| 1592 |
|
$self->{current_attribute} |
| 1593 |
|
= {name => chr ($self->{next_char}), |
| 1594 |
|
value => '', |
| 1595 |
|
line => $self->{line}, column => $self->{column}}; |
| 1596 |
$self->{state} = ATTRIBUTE_NAME_STATE; |
$self->{state} = ATTRIBUTE_NAME_STATE; |
| 1597 |
!!!next-input-character; |
!!!next-input-character; |
| 1598 |
redo A; |
redo A; |
| 1623 |
!!!next-input-character; |
!!!next-input-character; |
| 1624 |
redo A; |
redo A; |
| 1625 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1626 |
|
!!!parse-error (type => 'empty unquoted attribute value'); |
| 1627 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1628 |
!!!cp (87); |
!!!cp (87); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1629 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1630 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1631 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1649 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 1650 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1651 |
!!!cp (90); |
!!!cp (90); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1652 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1653 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1654 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1688 |
redo A; |
redo A; |
| 1689 |
} elsif ($self->{next_char} == 0x0026) { # & |
} elsif ($self->{next_char} == 0x0026) { # & |
| 1690 |
!!!cp (96); |
!!!cp (96); |
| 1691 |
$self->{last_attribute_value_state} = $self->{state}; |
## NOTE: In the spec, the tokenizer is switched to the |
| 1692 |
$self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE; |
## "entity in attribute value state". In this implementation, the |
| 1693 |
|
## tokenizer is switched to the |ENTITY_STATE|, which is an |
| 1694 |
|
## implementation of the "consume a character reference" algorithm. |
| 1695 |
|
$self->{prev_state} = $self->{state}; |
| 1696 |
|
$self->{entity_additional} = 0x0022; # " |
| 1697 |
|
$self->{state} = ENTITY_STATE; |
| 1698 |
!!!next-input-character; |
!!!next-input-character; |
| 1699 |
redo A; |
redo A; |
| 1700 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 1701 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
| 1702 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1703 |
!!!cp (97); |
!!!cp (97); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1704 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1705 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1706 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1735 |
redo A; |
redo A; |
| 1736 |
} elsif ($self->{next_char} == 0x0026) { # & |
} elsif ($self->{next_char} == 0x0026) { # & |
| 1737 |
!!!cp (102); |
!!!cp (102); |
| 1738 |
$self->{last_attribute_value_state} = $self->{state}; |
## NOTE: In the spec, the tokenizer is switched to the |
| 1739 |
$self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE; |
## "entity in attribute value state". In this implementation, the |
| 1740 |
|
## tokenizer is switched to the |ENTITY_STATE|, which is an |
| 1741 |
|
## implementation of the "consume a character reference" algorithm. |
| 1742 |
|
$self->{entity_additional} = 0x0027; # ' |
| 1743 |
|
$self->{prev_state} = $self->{state}; |
| 1744 |
|
$self->{state} = ENTITY_STATE; |
| 1745 |
!!!next-input-character; |
!!!next-input-character; |
| 1746 |
redo A; |
redo A; |
| 1747 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 1748 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
| 1749 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1750 |
!!!cp (103); |
!!!cp (103); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1751 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1752 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1753 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1786 |
redo A; |
redo A; |
| 1787 |
} elsif ($self->{next_char} == 0x0026) { # & |
} elsif ($self->{next_char} == 0x0026) { # & |
| 1788 |
!!!cp (108); |
!!!cp (108); |
| 1789 |
$self->{last_attribute_value_state} = $self->{state}; |
## NOTE: In the spec, the tokenizer is switched to the |
| 1790 |
$self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE; |
## "entity in attribute value state". In this implementation, the |
| 1791 |
|
## tokenizer is switched to the |ENTITY_STATE|, which is an |
| 1792 |
|
## implementation of the "consume a character reference" algorithm. |
| 1793 |
|
$self->{entity_additional} = -1; |
| 1794 |
|
$self->{prev_state} = $self->{state}; |
| 1795 |
|
$self->{state} = ENTITY_STATE; |
| 1796 |
!!!next-input-character; |
!!!next-input-character; |
| 1797 |
redo A; |
redo A; |
| 1798 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1799 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1800 |
!!!cp (109); |
!!!cp (109); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1801 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1802 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1803 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1821 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 1822 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1823 |
!!!cp (112); |
!!!cp (112); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1824 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1825 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1826 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1856 |
!!!next-input-character; |
!!!next-input-character; |
| 1857 |
redo A; |
redo A; |
| 1858 |
} |
} |
|
} elsif ($self->{state} == ENTITY_IN_ATTRIBUTE_VALUE_STATE) { |
|
|
my $token = $self->_tokenize_attempt_to_consume_an_entity |
|
|
(1, |
|
|
$self->{last_attribute_value_state} |
|
|
== ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE ? 0x0022 : # " |
|
|
$self->{last_attribute_value_state} |
|
|
== ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE ? 0x0027 : # ' |
|
|
-1); |
|
|
|
|
|
unless (defined $token) { |
|
|
!!!cp (117); |
|
|
$self->{current_attribute}->{value} .= '&'; |
|
|
} else { |
|
|
!!!cp (118); |
|
|
$self->{current_attribute}->{value} .= $token->{data}; |
|
|
$self->{current_attribute}->{has_reference} = $token->{has_reference}; |
|
|
## ISSUE: spec says "append the returned character token to the current attribute's value" |
|
|
} |
|
|
|
|
|
$self->{state} = $self->{last_attribute_value_state}; |
|
|
# next-input-character is already done |
|
|
redo A; |
|
| 1859 |
} elsif ($self->{state} == AFTER_ATTRIBUTE_VALUE_QUOTED_STATE) { |
} elsif ($self->{state} == AFTER_ATTRIBUTE_VALUE_QUOTED_STATE) { |
| 1860 |
if ($self->{next_char} == 0x0009 or # HT |
if ($self->{next_char} == 0x0009 or # HT |
| 1861 |
$self->{next_char} == 0x000A or # LF |
$self->{next_char} == 0x000A or # LF |
| 1869 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 1870 |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1871 |
!!!cp (119); |
!!!cp (119); |
|
$self->{current_token}->{first_start_tag} |
|
|
= not defined $self->{last_emitted_start_tag_name}; |
|
| 1872 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1873 |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1874 |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1889 |
|
|
| 1890 |
redo A; |
redo A; |
| 1891 |
} elsif ($self->{next_char} == 0x002F) { # / |
} elsif ($self->{next_char} == 0x002F) { # / |
| 1892 |
|
!!!cp (122); |
| 1893 |
|
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
| 1894 |
!!!next-input-character; |
!!!next-input-character; |
| 1895 |
if ($self->{next_char} == 0x003E and # > |
redo A; |
| 1896 |
$self->{current_token}->{type} == START_TAG_TOKEN and |
} elsif ($self->{next_char} == -1) { |
| 1897 |
$permitted_slash_tag_name->{$self->{current_token}->{tag_name}}) { |
!!!parse-error (type => 'unclosed tag'); |
| 1898 |
# permitted slash |
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1899 |
!!!cp (122); |
!!!cp (122.3); |
| 1900 |
# |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1901 |
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1902 |
|
if ($self->{current_token}->{attributes}) { |
| 1903 |
|
!!!cp (122.1); |
| 1904 |
|
!!!parse-error (type => 'end tag attribute'); |
| 1905 |
|
} else { |
| 1906 |
|
## NOTE: This state should never be reached. |
| 1907 |
|
!!!cp (122.2); |
| 1908 |
|
} |
| 1909 |
} else { |
} else { |
| 1910 |
!!!cp (123); |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
|
!!!parse-error (type => 'nestc'); |
|
| 1911 |
} |
} |
| 1912 |
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
$self->{state} = DATA_STATE; |
| 1913 |
# next-input-character is already done |
## Reconsume. |
| 1914 |
|
!!!emit ($self->{current_token}); # start tag or end tag |
| 1915 |
redo A; |
redo A; |
| 1916 |
} else { |
} else { |
| 1917 |
!!!cp (124); |
!!!cp ('124.1'); |
| 1918 |
!!!parse-error (type => 'no space between attributes'); |
!!!parse-error (type => 'no space between attributes'); |
| 1919 |
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
| 1920 |
## reconsume |
## reconsume |
| 1921 |
redo A; |
redo A; |
| 1922 |
} |
} |
| 1923 |
} elsif ($self->{state} == BOGUS_COMMENT_STATE) { |
} elsif ($self->{state} == SELF_CLOSING_START_TAG_STATE) { |
| 1924 |
## (only happen if PCDATA state) |
if ($self->{next_char} == 0x003E) { # > |
| 1925 |
|
if ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1926 |
my $token = {type => COMMENT_TOKEN, data => ''}; |
!!!cp ('124.2'); |
| 1927 |
|
!!!parse-error (type => 'nestc', token => $self->{current_token}); |
| 1928 |
BC: { |
## TODO: Different type than slash in start tag |
| 1929 |
if ($self->{next_char} == 0x003E) { # > |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 1930 |
!!!cp (124); |
if ($self->{current_token}->{attributes}) { |
| 1931 |
$self->{state} = DATA_STATE; |
!!!cp ('124.4'); |
| 1932 |
!!!next-input-character; |
!!!parse-error (type => 'end tag attribute'); |
| 1933 |
|
} else { |
| 1934 |
!!!emit ($token); |
!!!cp ('124.5'); |
| 1935 |
|
} |
| 1936 |
|
## TODO: Test |<title></title/>| |
| 1937 |
|
} else { |
| 1938 |
|
!!!cp ('124.3'); |
| 1939 |
|
$self->{self_closing} = 1; |
| 1940 |
|
} |
| 1941 |
|
|
| 1942 |
redo A; |
$self->{state} = DATA_STATE; |
| 1943 |
} elsif ($self->{next_char} == -1) { |
!!!next-input-character; |
|
!!!cp (125); |
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
| 1944 |
|
|
| 1945 |
!!!emit ($token); |
!!!emit ($self->{current_token}); # start tag or end tag |
| 1946 |
|
|
| 1947 |
redo A; |
redo A; |
| 1948 |
|
} elsif ($self->{next_char} == -1) { |
| 1949 |
|
!!!parse-error (type => 'unclosed tag'); |
| 1950 |
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
| 1951 |
|
!!!cp (124.7); |
| 1952 |
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 1953 |
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
| 1954 |
|
if ($self->{current_token}->{attributes}) { |
| 1955 |
|
!!!cp (124.5); |
| 1956 |
|
!!!parse-error (type => 'end tag attribute'); |
| 1957 |
|
} else { |
| 1958 |
|
## NOTE: This state should never be reached. |
| 1959 |
|
!!!cp (124.6); |
| 1960 |
|
} |
| 1961 |
} else { |
} else { |
| 1962 |
!!!cp (126); |
die "$0: $self->{current_token}->{type}: Unknown token type"; |
|
$token->{data} .= chr ($self->{next_char}); |
|
|
!!!next-input-character; |
|
|
redo BC; |
|
| 1963 |
} |
} |
| 1964 |
} # BC |
$self->{state} = DATA_STATE; |
| 1965 |
|
## Reconsume. |
| 1966 |
|
!!!emit ($self->{current_token}); # start tag or end tag |
| 1967 |
|
redo A; |
| 1968 |
|
} else { |
| 1969 |
|
!!!cp ('124.4'); |
| 1970 |
|
!!!parse-error (type => 'nestc'); |
| 1971 |
|
## TODO: This error type is wrong. |
| 1972 |
|
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
| 1973 |
|
## Reconsume. |
| 1974 |
|
redo A; |
| 1975 |
|
} |
| 1976 |
|
} elsif ($self->{state} == BOGUS_COMMENT_STATE) { |
| 1977 |
|
## (only happen if PCDATA state) |
| 1978 |
|
|
| 1979 |
die "$0: _get_next_token: unexpected case [BC]"; |
## NOTE: Unlike spec's "bogus comment state", this implementation |
| 1980 |
|
## consumes characters one-by-one basis. |
| 1981 |
|
|
| 1982 |
|
if ($self->{next_char} == 0x003E) { # > |
| 1983 |
|
!!!cp (124); |
| 1984 |
|
$self->{state} = DATA_STATE; |
| 1985 |
|
!!!next-input-character; |
| 1986 |
|
|
| 1987 |
|
!!!emit ($self->{current_token}); # comment |
| 1988 |
|
redo A; |
| 1989 |
|
} elsif ($self->{next_char} == -1) { |
| 1990 |
|
!!!cp (125); |
| 1991 |
|
$self->{state} = DATA_STATE; |
| 1992 |
|
## reconsume |
| 1993 |
|
|
| 1994 |
|
!!!emit ($self->{current_token}); # comment |
| 1995 |
|
redo A; |
| 1996 |
|
} else { |
| 1997 |
|
!!!cp (126); |
| 1998 |
|
$self->{current_token}->{data} .= chr ($self->{next_char}); # comment |
| 1999 |
|
## Stay in the state. |
| 2000 |
|
!!!next-input-character; |
| 2001 |
|
redo A; |
| 2002 |
|
} |
| 2003 |
} elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) { |
} elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) { |
| 2004 |
## (only happen if PCDATA state) |
## (only happen if PCDATA state) |
|
|
|
|
my @next_char; |
|
|
push @next_char, $self->{next_char}; |
|
| 2005 |
|
|
| 2006 |
if ($self->{next_char} == 0x002D) { # - |
if ($self->{next_char} == 0x002D) { # - |
| 2007 |
|
!!!cp (133); |
| 2008 |
|
$self->{state} = MD_HYPHEN_STATE; |
| 2009 |
!!!next-input-character; |
!!!next-input-character; |
| 2010 |
push @next_char, $self->{next_char}; |
redo A; |
|
if ($self->{next_char} == 0x002D) { # - |
|
|
!!!cp (127); |
|
|
$self->{current_token} = {type => COMMENT_TOKEN, data => ''}; |
|
|
$self->{state} = COMMENT_START_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (128); |
|
|
} |
|
| 2011 |
} elsif ($self->{next_char} == 0x0044 or # D |
} elsif ($self->{next_char} == 0x0044 or # D |
| 2012 |
$self->{next_char} == 0x0064) { # d |
$self->{next_char} == 0x0064) { # d |
| 2013 |
|
## ASCII case-insensitive. |
| 2014 |
|
!!!cp (130); |
| 2015 |
|
$self->{state} = MD_DOCTYPE_STATE; |
| 2016 |
|
$self->{state_keyword} = chr $self->{next_char}; |
| 2017 |
!!!next-input-character; |
!!!next-input-character; |
| 2018 |
push @next_char, $self->{next_char}; |
redo A; |
| 2019 |
if ($self->{next_char} == 0x004F or # O |
} elsif ($self->{insertion_mode} & IN_FOREIGN_CONTENT_IM and |
| 2020 |
$self->{next_char} == 0x006F) { # o |
$self->{open_elements}->[-1]->[1] & FOREIGN_EL and |
| 2021 |
!!!next-input-character; |
$self->{next_char} == 0x005B) { # [ |
| 2022 |
push @next_char, $self->{next_char}; |
!!!cp (135.4); |
| 2023 |
if ($self->{next_char} == 0x0043 or # C |
$self->{state} = MD_CDATA_STATE; |
| 2024 |
$self->{next_char} == 0x0063) { # c |
$self->{state_keyword} = '['; |
| 2025 |
!!!next-input-character; |
!!!next-input-character; |
| 2026 |
push @next_char, $self->{next_char}; |
redo A; |
|
if ($self->{next_char} == 0x0054 or # T |
|
|
$self->{next_char} == 0x0074) { # t |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x0059 or # Y |
|
|
$self->{next_char} == 0x0079) { # y |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x0050 or # P |
|
|
$self->{next_char} == 0x0070) { # p |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x0045 or # E |
|
|
$self->{next_char} == 0x0065) { # e |
|
|
!!!cp (129); |
|
|
## TODO: What a stupid code this is! |
|
|
$self->{state} = DOCTYPE_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (130); |
|
|
} |
|
|
} else { |
|
|
!!!cp (131); |
|
|
} |
|
|
} else { |
|
|
!!!cp (132); |
|
|
} |
|
|
} else { |
|
|
!!!cp (133); |
|
|
} |
|
|
} else { |
|
|
!!!cp (134); |
|
|
} |
|
|
} else { |
|
|
!!!cp (135); |
|
|
} |
|
| 2027 |
} else { |
} else { |
| 2028 |
!!!cp (136); |
!!!cp (136); |
| 2029 |
} |
} |
| 2030 |
|
|
| 2031 |
!!!parse-error (type => 'bogus comment'); |
!!!parse-error (type => 'bogus comment', |
| 2032 |
$self->{next_char} = shift @next_char; |
line => $self->{line_prev}, |
| 2033 |
!!!back-next-input-character (@next_char); |
column => $self->{column_prev} - 1); |
| 2034 |
|
## Reconsume. |
| 2035 |
$self->{state} = BOGUS_COMMENT_STATE; |
$self->{state} = BOGUS_COMMENT_STATE; |
| 2036 |
|
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
| 2037 |
|
line => $self->{line_prev}, |
| 2038 |
|
column => $self->{column_prev} - 1, |
| 2039 |
|
}; |
| 2040 |
redo A; |
redo A; |
| 2041 |
|
} elsif ($self->{state} == MD_HYPHEN_STATE) { |
| 2042 |
## ISSUE: typos in spec: chacacters, is is a parse error |
if ($self->{next_char} == 0x002D) { # - |
| 2043 |
## 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? |
!!!cp (127); |
| 2044 |
|
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
| 2045 |
|
line => $self->{line_prev}, |
| 2046 |
|
column => $self->{column_prev} - 2, |
| 2047 |
|
}; |
| 2048 |
|
$self->{state} = COMMENT_START_STATE; |
| 2049 |
|
!!!next-input-character; |
| 2050 |
|
redo A; |
| 2051 |
|
} else { |
| 2052 |
|
!!!cp (128); |
| 2053 |
|
!!!parse-error (type => 'bogus comment', |
| 2054 |
|
line => $self->{line_prev}, |
| 2055 |
|
column => $self->{column_prev} - 2); |
| 2056 |
|
$self->{state} = BOGUS_COMMENT_STATE; |
| 2057 |
|
## Reconsume. |
| 2058 |
|
$self->{current_token} = {type => COMMENT_TOKEN, |
| 2059 |
|
data => '-', |
| 2060 |
|
line => $self->{line_prev}, |
| 2061 |
|
column => $self->{column_prev} - 2, |
| 2062 |
|
}; |
| 2063 |
|
redo A; |
| 2064 |
|
} |
| 2065 |
|
} elsif ($self->{state} == MD_DOCTYPE_STATE) { |
| 2066 |
|
## ASCII case-insensitive. |
| 2067 |
|
if ($self->{next_char} == [ |
| 2068 |
|
undef, |
| 2069 |
|
0x004F, # O |
| 2070 |
|
0x0043, # C |
| 2071 |
|
0x0054, # T |
| 2072 |
|
0x0059, # Y |
| 2073 |
|
0x0050, # P |
| 2074 |
|
]->[length $self->{state_keyword}] or |
| 2075 |
|
$self->{next_char} == [ |
| 2076 |
|
undef, |
| 2077 |
|
0x006F, # o |
| 2078 |
|
0x0063, # c |
| 2079 |
|
0x0074, # t |
| 2080 |
|
0x0079, # y |
| 2081 |
|
0x0070, # p |
| 2082 |
|
]->[length $self->{state_keyword}]) { |
| 2083 |
|
!!!cp (131); |
| 2084 |
|
## Stay in the state. |
| 2085 |
|
$self->{state_keyword} .= chr $self->{next_char}; |
| 2086 |
|
!!!next-input-character; |
| 2087 |
|
redo A; |
| 2088 |
|
} elsif ((length $self->{state_keyword}) == 6 and |
| 2089 |
|
($self->{next_char} == 0x0045 or # E |
| 2090 |
|
$self->{next_char} == 0x0065)) { # e |
| 2091 |
|
!!!cp (129); |
| 2092 |
|
$self->{state} = DOCTYPE_STATE; |
| 2093 |
|
$self->{current_token} = {type => DOCTYPE_TOKEN, |
| 2094 |
|
quirks => 1, |
| 2095 |
|
line => $self->{line_prev}, |
| 2096 |
|
column => $self->{column_prev} - 7, |
| 2097 |
|
}; |
| 2098 |
|
!!!next-input-character; |
| 2099 |
|
redo A; |
| 2100 |
|
} else { |
| 2101 |
|
!!!cp (132); |
| 2102 |
|
!!!parse-error (type => 'bogus comment', |
| 2103 |
|
line => $self->{line_prev}, |
| 2104 |
|
column => $self->{column_prev} - 1 - length $self->{state_keyword}); |
| 2105 |
|
$self->{state} = BOGUS_COMMENT_STATE; |
| 2106 |
|
## Reconsume. |
| 2107 |
|
$self->{current_token} = {type => COMMENT_TOKEN, |
| 2108 |
|
data => $self->{state_keyword}, |
| 2109 |
|
line => $self->{line_prev}, |
| 2110 |
|
column => $self->{column_prev} - 1 - length $self->{state_keyword}, |
| 2111 |
|
}; |
| 2112 |
|
redo A; |
| 2113 |
|
} |
| 2114 |
|
} elsif ($self->{state} == MD_CDATA_STATE) { |
| 2115 |
|
if ($self->{next_char} == { |
| 2116 |
|
'[' => 0x0043, # C |
| 2117 |
|
'[C' => 0x0044, # D |
| 2118 |
|
'[CD' => 0x0041, # A |
| 2119 |
|
'[CDA' => 0x0054, # T |
| 2120 |
|
'[CDAT' => 0x0041, # A |
| 2121 |
|
}->{$self->{state_keyword}}) { |
| 2122 |
|
!!!cp (135.1); |
| 2123 |
|
## Stay in the state. |
| 2124 |
|
$self->{state_keyword} .= chr $self->{next_char}; |
| 2125 |
|
!!!next-input-character; |
| 2126 |
|
redo A; |
| 2127 |
|
} elsif ($self->{state_keyword} eq '[CDATA' and |
| 2128 |
|
$self->{next_char} == 0x005B) { # [ |
| 2129 |
|
!!!cp (135.2); |
| 2130 |
|
$self->{current_token} = {type => CHARACTER_TOKEN, |
| 2131 |
|
data => '', |
| 2132 |
|
line => $self->{line_prev}, |
| 2133 |
|
column => $self->{column_prev} - 7}; |
| 2134 |
|
$self->{state} = CDATA_SECTION_STATE; |
| 2135 |
|
!!!next-input-character; |
| 2136 |
|
redo A; |
| 2137 |
|
} else { |
| 2138 |
|
!!!cp (135.3); |
| 2139 |
|
!!!parse-error (type => 'bogus comment', |
| 2140 |
|
line => $self->{line_prev}, |
| 2141 |
|
column => $self->{column_prev} - 1 - length $self->{state_keyword}); |
| 2142 |
|
$self->{state} = BOGUS_COMMENT_STATE; |
| 2143 |
|
## Reconsume. |
| 2144 |
|
$self->{current_token} = {type => COMMENT_TOKEN, |
| 2145 |
|
data => $self->{state_keyword}, |
| 2146 |
|
line => $self->{line_prev}, |
| 2147 |
|
column => $self->{column_prev} - 1 - length $self->{state_keyword}, |
| 2148 |
|
}; |
| 2149 |
|
redo A; |
| 2150 |
|
} |
| 2151 |
} elsif ($self->{state} == COMMENT_START_STATE) { |
} elsif ($self->{state} == COMMENT_START_STATE) { |
| 2152 |
if ($self->{next_char} == 0x002D) { # - |
if ($self->{next_char} == 0x002D) { # - |
| 2153 |
!!!cp (137); |
!!!cp (137); |
| 2267 |
redo A; |
redo A; |
| 2268 |
} elsif ($self->{next_char} == 0x002D) { # - |
} elsif ($self->{next_char} == 0x002D) { # - |
| 2269 |
!!!cp (152); |
!!!cp (152); |
| 2270 |
!!!parse-error (type => 'dash in comment'); |
!!!parse-error (type => 'dash in comment', |
| 2271 |
|
line => $self->{line_prev}, |
| 2272 |
|
column => $self->{column_prev}); |
| 2273 |
$self->{current_token}->{data} .= '-'; # comment |
$self->{current_token}->{data} .= '-'; # comment |
| 2274 |
## Stay in the state |
## Stay in the state |
| 2275 |
!!!next-input-character; |
!!!next-input-character; |
| 2285 |
redo A; |
redo A; |
| 2286 |
} else { |
} else { |
| 2287 |
!!!cp (154); |
!!!cp (154); |
| 2288 |
!!!parse-error (type => 'dash in comment'); |
!!!parse-error (type => 'dash in comment', |
| 2289 |
|
line => $self->{line_prev}, |
| 2290 |
|
column => $self->{column_prev}); |
| 2291 |
$self->{current_token}->{data} .= '--' . chr ($self->{next_char}); # comment |
$self->{current_token}->{data} .= '--' . chr ($self->{next_char}); # comment |
| 2292 |
$self->{state} = COMMENT_STATE; |
$self->{state} = COMMENT_STATE; |
| 2293 |
!!!next-input-character; |
!!!next-input-character; |
| 2326 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 2327 |
!!!next-input-character; |
!!!next-input-character; |
| 2328 |
|
|
| 2329 |
!!!emit ({type => DOCTYPE_TOKEN, quirks => 1}); |
!!!emit ($self->{current_token}); # DOCTYPE (quirks) |
| 2330 |
|
|
| 2331 |
redo A; |
redo A; |
| 2332 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 2335 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 2336 |
## reconsume |
## reconsume |
| 2337 |
|
|
| 2338 |
!!!emit ({type => DOCTYPE_TOKEN, quirks => 1}); |
!!!emit ($self->{current_token}); # DOCTYPE (quirks) |
| 2339 |
|
|
| 2340 |
redo A; |
redo A; |
| 2341 |
} else { |
} else { |
| 2342 |
!!!cp (160); |
!!!cp (160); |
| 2343 |
$self->{current_token} |
$self->{current_token}->{name} = chr $self->{next_char}; |
| 2344 |
= {type => DOCTYPE_TOKEN, |
delete $self->{current_token}->{quirks}; |
|
name => chr ($self->{next_char}), |
|
|
#quirks => 0, |
|
|
}; |
|
| 2345 |
## ISSUE: "Set the token's name name to the" in the spec |
## ISSUE: "Set the token's name name to the" in the spec |
| 2346 |
$self->{state} = DOCTYPE_NAME_STATE; |
$self->{state} = DOCTYPE_NAME_STATE; |
| 2347 |
!!!next-input-character; |
!!!next-input-character; |
| 2414 |
redo A; |
redo A; |
| 2415 |
} elsif ($self->{next_char} == 0x0050 or # P |
} elsif ($self->{next_char} == 0x0050 or # P |
| 2416 |
$self->{next_char} == 0x0070) { # p |
$self->{next_char} == 0x0070) { # p |
| 2417 |
|
$self->{state} = PUBLIC_STATE; |
| 2418 |
|
$self->{state_keyword} = chr $self->{next_char}; |
| 2419 |
!!!next-input-character; |
!!!next-input-character; |
| 2420 |
if ($self->{next_char} == 0x0055 or # U |
redo A; |
|
$self->{next_char} == 0x0075) { # u |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x0042 or # B |
|
|
$self->{next_char} == 0x0062) { # b |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x004C or # L |
|
|
$self->{next_char} == 0x006C) { # l |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x0049 or # I |
|
|
$self->{next_char} == 0x0069) { # i |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x0043 or # C |
|
|
$self->{next_char} == 0x0063) { # c |
|
|
!!!cp (168); |
|
|
$self->{state} = BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (169); |
|
|
} |
|
|
} else { |
|
|
!!!cp (170); |
|
|
} |
|
|
} else { |
|
|
!!!cp (171); |
|
|
} |
|
|
} else { |
|
|
!!!cp (172); |
|
|
} |
|
|
} else { |
|
|
!!!cp (173); |
|
|
} |
|
|
|
|
|
# |
|
| 2421 |
} elsif ($self->{next_char} == 0x0053 or # S |
} elsif ($self->{next_char} == 0x0053 or # S |
| 2422 |
$self->{next_char} == 0x0073) { # s |
$self->{next_char} == 0x0073) { # s |
| 2423 |
|
$self->{state} = SYSTEM_STATE; |
| 2424 |
|
$self->{state_keyword} = chr $self->{next_char}; |
| 2425 |
!!!next-input-character; |
!!!next-input-character; |
| 2426 |
if ($self->{next_char} == 0x0059 or # Y |
redo A; |
|
$self->{next_char} == 0x0079) { # y |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x0053 or # S |
|
|
$self->{next_char} == 0x0073) { # s |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x0054 or # T |
|
|
$self->{next_char} == 0x0074) { # t |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x0045 or # E |
|
|
$self->{next_char} == 0x0065) { # e |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x004D or # M |
|
|
$self->{next_char} == 0x006D) { # m |
|
|
!!!cp (174); |
|
|
$self->{state} = BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (175); |
|
|
} |
|
|
} else { |
|
|
!!!cp (176); |
|
|
} |
|
|
} else { |
|
|
!!!cp (177); |
|
|
} |
|
|
} else { |
|
|
!!!cp (178); |
|
|
} |
|
|
} else { |
|
|
!!!cp (179); |
|
|
} |
|
|
|
|
|
# |
|
| 2427 |
} else { |
} else { |
| 2428 |
!!!cp (180); |
!!!cp (180); |
| 2429 |
|
!!!parse-error (type => 'string after DOCTYPE name'); |
| 2430 |
|
$self->{current_token}->{quirks} = 1; |
| 2431 |
|
|
| 2432 |
|
$self->{state} = BOGUS_DOCTYPE_STATE; |
| 2433 |
!!!next-input-character; |
!!!next-input-character; |
| 2434 |
# |
redo A; |
| 2435 |
} |
} |
| 2436 |
|
} elsif ($self->{state} == PUBLIC_STATE) { |
| 2437 |
|
## ASCII case-insensitive |
| 2438 |
|
if ($self->{next_char} == [ |
| 2439 |
|
undef, |
| 2440 |
|
0x0055, # U |
| 2441 |
|
0x0042, # B |
| 2442 |
|
0x004C, # L |
| 2443 |
|
0x0049, # I |
| 2444 |
|
]->[length $self->{state_keyword}] or |
| 2445 |
|
$self->{next_char} == [ |
| 2446 |
|
undef, |
| 2447 |
|
0x0075, # u |
| 2448 |
|
0x0062, # b |
| 2449 |
|
0x006C, # l |
| 2450 |
|
0x0069, # i |
| 2451 |
|
]->[length $self->{state_keyword}]) { |
| 2452 |
|
!!!cp (175); |
| 2453 |
|
## Stay in the state. |
| 2454 |
|
$self->{state_keyword} .= chr $self->{next_char}; |
| 2455 |
|
!!!next-input-character; |
| 2456 |
|
redo A; |
| 2457 |
|
} elsif ((length $self->{state_keyword}) == 5 and |
| 2458 |
|
($self->{next_char} == 0x0043 or # C |
| 2459 |
|
$self->{next_char} == 0x0063)) { # c |
| 2460 |
|
!!!cp (168); |
| 2461 |
|
$self->{state} = BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE; |
| 2462 |
|
!!!next-input-character; |
| 2463 |
|
redo A; |
| 2464 |
|
} else { |
| 2465 |
|
!!!cp (169); |
| 2466 |
|
!!!parse-error (type => 'string after DOCTYPE name', |
| 2467 |
|
line => $self->{line_prev}, |
| 2468 |
|
column => $self->{column_prev} + 1 - length $self->{state_keyword}); |
| 2469 |
|
$self->{current_token}->{quirks} = 1; |
| 2470 |
|
|
| 2471 |
!!!parse-error (type => 'string after DOCTYPE name'); |
$self->{state} = BOGUS_DOCTYPE_STATE; |
| 2472 |
$self->{current_token}->{quirks} = 1; |
## Reconsume. |
| 2473 |
|
redo A; |
| 2474 |
|
} |
| 2475 |
|
} elsif ($self->{state} == SYSTEM_STATE) { |
| 2476 |
|
## ASCII case-insensitive |
| 2477 |
|
if ($self->{next_char} == [ |
| 2478 |
|
undef, |
| 2479 |
|
0x0059, # Y |
| 2480 |
|
0x0053, # S |
| 2481 |
|
0x0054, # T |
| 2482 |
|
0x0045, # E |
| 2483 |
|
]->[length $self->{state_keyword}] or |
| 2484 |
|
$self->{next_char} == [ |
| 2485 |
|
undef, |
| 2486 |
|
0x0079, # y |
| 2487 |
|
0x0073, # s |
| 2488 |
|
0x0074, # t |
| 2489 |
|
0x0065, # e |
| 2490 |
|
]->[length $self->{state_keyword}]) { |
| 2491 |
|
!!!cp (170); |
| 2492 |
|
## Stay in the state. |
| 2493 |
|
$self->{state_keyword} .= chr $self->{next_char}; |
| 2494 |
|
!!!next-input-character; |
| 2495 |
|
redo A; |
| 2496 |
|
} elsif ((length $self->{state_keyword}) == 5 and |
| 2497 |
|
($self->{next_char} == 0x004D or # M |
| 2498 |
|
$self->{next_char} == 0x006D)) { # m |
| 2499 |
|
!!!cp (171); |
| 2500 |
|
$self->{state} = BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE; |
| 2501 |
|
!!!next-input-character; |
| 2502 |
|
redo A; |
| 2503 |
|
} else { |
| 2504 |
|
!!!cp (172); |
| 2505 |
|
!!!parse-error (type => 'string after DOCTYPE name', |
| 2506 |
|
line => $self->{line_prev}, |
| 2507 |
|
column => $self->{column_prev} + 1 - length $self->{state_keyword}); |
| 2508 |
|
$self->{current_token}->{quirks} = 1; |
| 2509 |
|
|
| 2510 |
$self->{state} = BOGUS_DOCTYPE_STATE; |
$self->{state} = BOGUS_DOCTYPE_STATE; |
| 2511 |
# next-input-character is already done |
## Reconsume. |
| 2512 |
redo A; |
redo A; |
| 2513 |
|
} |
| 2514 |
} elsif ($self->{state} == BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE) { |
} elsif ($self->{state} == BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE) { |
| 2515 |
if ({ |
if ({ |
| 2516 |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
| 2743 |
redo A; |
redo A; |
| 2744 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 2745 |
!!!cp (208); |
!!!cp (208); |
| 2746 |
!!!parse-error (type => 'unclosed PUBLIC literal'); |
!!!parse-error (type => 'unclosed SYSTEM literal'); |
| 2747 |
|
|
| 2748 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 2749 |
!!!next-input-character; |
!!!next-input-character; |
| 2779 |
redo A; |
redo A; |
| 2780 |
} elsif ($self->{next_char} == 0x003E) { # > |
} elsif ($self->{next_char} == 0x003E) { # > |
| 2781 |
!!!cp (212); |
!!!cp (212); |
| 2782 |
!!!parse-error (type => 'unclosed PUBLIC literal'); |
!!!parse-error (type => 'unclosed SYSTEM literal'); |
| 2783 |
|
|
| 2784 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 2785 |
!!!next-input-character; |
!!!next-input-character; |
| 2827 |
} elsif ($self->{next_char} == -1) { |
} elsif ($self->{next_char} == -1) { |
| 2828 |
!!!cp (217); |
!!!cp (217); |
| 2829 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
|
|
|
| 2830 |
$self->{state} = DATA_STATE; |
$self->{state} = DATA_STATE; |
| 2831 |
## reconsume |
## reconsume |
| 2832 |
|
|
| 2867 |
!!!next-input-character; |
!!!next-input-character; |
| 2868 |
redo A; |
redo A; |
| 2869 |
} |
} |
| 2870 |
} else { |
} elsif ($self->{state} == CDATA_SECTION_STATE) { |
| 2871 |
die "$0: $self->{state}: Unknown state"; |
## NOTE: "CDATA section state" in the state is jointly implemented |
| 2872 |
} |
## by three states, |CDATA_SECTION_STATE|, |CDATA_SECTION_MSE1_STATE|, |
| 2873 |
} # A |
## and |CDATA_SECTION_MSE2_STATE|. |
| 2874 |
|
|
| 2875 |
die "$0: _get_next_token: unexpected case"; |
if ($self->{next_char} == 0x005D) { # ] |
| 2876 |
} # _get_next_token |
!!!cp (221.1); |
| 2877 |
|
$self->{state} = CDATA_SECTION_MSE1_STATE; |
| 2878 |
sub _tokenize_attempt_to_consume_an_entity ($$$) { |
!!!next-input-character; |
| 2879 |
my ($self, $in_attr, $additional) = @_; |
redo A; |
| 2880 |
|
} elsif ($self->{next_char} == -1) { |
| 2881 |
|
$self->{state} = DATA_STATE; |
| 2882 |
|
!!!next-input-character; |
| 2883 |
|
if (length $self->{current_token}->{data}) { # character |
| 2884 |
|
!!!cp (221.2); |
| 2885 |
|
!!!emit ($self->{current_token}); # character |
| 2886 |
|
} else { |
| 2887 |
|
!!!cp (221.3); |
| 2888 |
|
## No token to emit. $self->{current_token} is discarded. |
| 2889 |
|
} |
| 2890 |
|
redo A; |
| 2891 |
|
} else { |
| 2892 |
|
!!!cp (221.4); |
| 2893 |
|
$self->{current_token}->{data} .= chr $self->{next_char}; |
| 2894 |
|
## Stay in the state. |
| 2895 |
|
!!!next-input-character; |
| 2896 |
|
redo A; |
| 2897 |
|
} |
| 2898 |
|
|
| 2899 |
if ({ |
## ISSUE: "text tokens" in spec. |
| 2900 |
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, # HT, LF, VT, FF, |
} elsif ($self->{state} == CDATA_SECTION_MSE1_STATE) { |
| 2901 |
0x0020 => 1, 0x003C => 1, 0x0026 => 1, -1 => 1, # SP, <, & # 0x000D # CR |
if ($self->{next_char} == 0x005D) { # ] |
| 2902 |
$additional => 1, |
!!!cp (221.5); |
| 2903 |
}->{$self->{next_char}}) { |
$self->{state} = CDATA_SECTION_MSE2_STATE; |
| 2904 |
!!!cp (1001); |
!!!next-input-character; |
| 2905 |
## Don't consume |
redo A; |
| 2906 |
## No error |
} else { |
| 2907 |
return undef; |
!!!cp (221.6); |
| 2908 |
} elsif ($self->{next_char} == 0x0023) { # # |
$self->{current_token}->{data} .= ']'; |
| 2909 |
!!!next-input-character; |
$self->{state} = CDATA_SECTION_STATE; |
| 2910 |
if ($self->{next_char} == 0x0078 or # x |
## Reconsume. |
| 2911 |
$self->{next_char} == 0x0058) { # X |
redo A; |
| 2912 |
my $code; |
} |
| 2913 |
X: { |
} elsif ($self->{state} == CDATA_SECTION_MSE2_STATE) { |
| 2914 |
my $x_char = $self->{next_char}; |
if ($self->{next_char} == 0x003E) { # > |
| 2915 |
!!!next-input-character; |
$self->{state} = DATA_STATE; |
| 2916 |
if (0x0030 <= $self->{next_char} and |
!!!next-input-character; |
| 2917 |
$self->{next_char} <= 0x0039) { # 0..9 |
if (length $self->{current_token}->{data}) { # character |
| 2918 |
!!!cp (1002); |
!!!cp (221.7); |
| 2919 |
$code ||= 0; |
!!!emit ($self->{current_token}); # character |
|
$code *= 0x10; |
|
|
$code += $self->{next_char} - 0x0030; |
|
|
redo X; |
|
|
} elsif (0x0061 <= $self->{next_char} and |
|
|
$self->{next_char} <= 0x0066) { # a..f |
|
|
!!!cp (1003); |
|
|
$code ||= 0; |
|
|
$code *= 0x10; |
|
|
$code += $self->{next_char} - 0x0060 + 9; |
|
|
redo X; |
|
|
} elsif (0x0041 <= $self->{next_char} and |
|
|
$self->{next_char} <= 0x0046) { # A..F |
|
|
!!!cp (1004); |
|
|
$code ||= 0; |
|
|
$code *= 0x10; |
|
|
$code += $self->{next_char} - 0x0040 + 9; |
|
|
redo X; |
|
|
} elsif (not defined $code) { # no hexadecimal digit |
|
|
!!!cp (1005); |
|
|
!!!parse-error (type => 'bare hcro'); |
|
|
!!!back-next-input-character ($x_char, $self->{next_char}); |
|
|
$self->{next_char} = 0x0023; # # |
|
|
return undef; |
|
|
} elsif ($self->{next_char} == 0x003B) { # ; |
|
|
!!!cp (1006); |
|
|
!!!next-input-character; |
|
| 2920 |
} else { |
} else { |
| 2921 |
!!!cp (1007); |
!!!cp (221.8); |
| 2922 |
!!!parse-error (type => 'no refc'); |
## No token to emit. $self->{current_token} is discarded. |
| 2923 |
} |
} |
| 2924 |
|
redo A; |
| 2925 |
|
} elsif ($self->{next_char} == 0x005D) { # ] |
| 2926 |
|
!!!cp (221.9); # character |
| 2927 |
|
$self->{current_token}->{data} .= ']'; ## Add first "]" of "]]]". |
| 2928 |
|
## Stay in the state. |
| 2929 |
|
!!!next-input-character; |
| 2930 |
|
redo A; |
| 2931 |
|
} else { |
| 2932 |
|
!!!cp (221.11); |
| 2933 |
|
$self->{current_token}->{data} .= ']]'; # character |
| 2934 |
|
$self->{state} = CDATA_SECTION_STATE; |
| 2935 |
|
## Reconsume. |
| 2936 |
|
redo A; |
| 2937 |
|
} |
| 2938 |
|
} elsif ($self->{state} == ENTITY_STATE) { |
| 2939 |
|
if ({ |
| 2940 |
|
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, # HT, LF, VT, FF, |
| 2941 |
|
0x0020 => 1, 0x003C => 1, 0x0026 => 1, -1 => 1, # SP, <, & |
| 2942 |
|
$self->{entity_additional} => 1, |
| 2943 |
|
}->{$self->{next_char}}) { |
| 2944 |
|
!!!cp (1001); |
| 2945 |
|
## Don't consume |
| 2946 |
|
## No error |
| 2947 |
|
## Return nothing. |
| 2948 |
|
# |
| 2949 |
|
} elsif ($self->{next_char} == 0x0023) { # # |
| 2950 |
|
!!!cp (999); |
| 2951 |
|
$self->{state} = ENTITY_HASH_STATE; |
| 2952 |
|
$self->{state_keyword} = '#'; |
| 2953 |
|
!!!next-input-character; |
| 2954 |
|
redo A; |
| 2955 |
|
} elsif ((0x0041 <= $self->{next_char} and |
| 2956 |
|
$self->{next_char} <= 0x005A) or # A..Z |
| 2957 |
|
(0x0061 <= $self->{next_char} and |
| 2958 |
|
$self->{next_char} <= 0x007A)) { # a..z |
| 2959 |
|
!!!cp (998); |
| 2960 |
|
require Whatpm::_NamedEntityList; |
| 2961 |
|
$self->{state} = ENTITY_NAME_STATE; |
| 2962 |
|
$self->{state_keyword} = chr $self->{next_char}; |
| 2963 |
|
$self->{entity__value} = $self->{state_keyword}; |
| 2964 |
|
$self->{entity__match} = 0; |
| 2965 |
|
!!!next-input-character; |
| 2966 |
|
redo A; |
| 2967 |
|
} else { |
| 2968 |
|
!!!cp (1027); |
| 2969 |
|
!!!parse-error (type => 'bare ero'); |
| 2970 |
|
## Return nothing. |
| 2971 |
|
# |
| 2972 |
|
} |
| 2973 |
|
|
| 2974 |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
## NOTE: No character is consumed by the "consume a character |
| 2975 |
!!!cp (1008); |
## reference" algorithm. In other word, there is an "&" character |
| 2976 |
!!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code); |
## that does not introduce a character reference, which would be |
| 2977 |
$code = 0xFFFD; |
## appended to the parent element or the attribute value in later |
| 2978 |
} elsif ($code > 0x10FFFF) { |
## process of the tokenizer. |
| 2979 |
!!!cp (1009); |
|
| 2980 |
!!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code); |
if ($self->{prev_state} == DATA_STATE) { |
| 2981 |
$code = 0xFFFD; |
!!!cp (997); |
| 2982 |
} elsif ($code == 0x000D) { |
$self->{state} = $self->{prev_state}; |
| 2983 |
!!!cp (1010); |
## Reconsume. |
| 2984 |
!!!parse-error (type => 'CR character reference'); |
!!!emit ({type => CHARACTER_TOKEN, data => '&', |
| 2985 |
$code = 0x000A; |
line => $self->{line_prev}, |
| 2986 |
} elsif (0x80 <= $code and $code <= 0x9F) { |
column => $self->{column_prev}, |
| 2987 |
!!!cp (1011); |
}); |
| 2988 |
!!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code); |
redo A; |
| 2989 |
$code = $c1_entity_char->{$code}; |
} else { |
| 2990 |
} |
!!!cp (996); |
| 2991 |
|
$self->{current_attribute}->{value} .= '&'; |
| 2992 |
return {type => CHARACTER_TOKEN, data => chr $code, |
$self->{state} = $self->{prev_state}; |
| 2993 |
has_reference => 1}; |
## Reconsume. |
| 2994 |
} # X |
redo A; |
| 2995 |
} elsif (0x0030 <= $self->{next_char} and |
} |
| 2996 |
$self->{next_char} <= 0x0039) { # 0..9 |
} elsif ($self->{state} == ENTITY_HASH_STATE) { |
| 2997 |
my $code = $self->{next_char} - 0x0030; |
if ($self->{next_char} == 0x0078 or # x |
| 2998 |
!!!next-input-character; |
$self->{next_char} == 0x0058) { # X |
| 2999 |
|
!!!cp (995); |
| 3000 |
while (0x0030 <= $self->{next_char} and |
$self->{state} = HEXREF_X_STATE; |
| 3001 |
$self->{next_char} <= 0x0039) { # 0..9 |
$self->{state_keyword} .= chr $self->{next_char}; |
| 3002 |
|
!!!next-input-character; |
| 3003 |
|
redo A; |
| 3004 |
|
} elsif (0x0030 <= $self->{next_char} and |
| 3005 |
|
$self->{next_char} <= 0x0039) { # 0..9 |
| 3006 |
|
!!!cp (994); |
| 3007 |
|
$self->{state} = NCR_NUM_STATE; |
| 3008 |
|
$self->{state_keyword} = $self->{next_char} - 0x0030; |
| 3009 |
|
!!!next-input-character; |
| 3010 |
|
redo A; |
| 3011 |
|
} else { |
| 3012 |
|
!!!parse-error (type => 'bare nero', |
| 3013 |
|
line => $self->{line_prev}, |
| 3014 |
|
column => $self->{column_prev} - 1); |
| 3015 |
|
|
| 3016 |
|
## NOTE: According to the spec algorithm, nothing is returned, |
| 3017 |
|
## and then "&#" is appended to the parent element or the attribute |
| 3018 |
|
## value in the later processing. |
| 3019 |
|
|
| 3020 |
|
if ($self->{prev_state} == DATA_STATE) { |
| 3021 |
|
!!!cp (1019); |
| 3022 |
|
$self->{state} = $self->{prev_state}; |
| 3023 |
|
## Reconsume. |
| 3024 |
|
!!!emit ({type => CHARACTER_TOKEN, |
| 3025 |
|
data => '&#', |
| 3026 |
|
line => $self->{line_prev}, |
| 3027 |
|
column => $self->{column_prev} - 1, |
| 3028 |
|
}); |
| 3029 |
|
redo A; |
| 3030 |
|
} else { |
| 3031 |
|
!!!cp (993); |
| 3032 |
|
$self->{current_attribute}->{value} .= '&#'; |
| 3033 |
|
$self->{state} = $self->{prev_state}; |
| 3034 |
|
## Reconsume. |
| 3035 |
|
redo A; |
| 3036 |
|
} |
| 3037 |
|
} |
| 3038 |
|
} elsif ($self->{state} == NCR_NUM_STATE) { |
| 3039 |
|
if (0x0030 <= $self->{next_char} and |
| 3040 |
|
$self->{next_char} <= 0x0039) { # 0..9 |
| 3041 |
!!!cp (1012); |
!!!cp (1012); |
| 3042 |
$code *= 10; |
$self->{state_keyword} *= 10; |
| 3043 |
$code += $self->{next_char} - 0x0030; |
$self->{state_keyword} += $self->{next_char} - 0x0030; |
| 3044 |
|
|
| 3045 |
|
## Stay in the state. |
| 3046 |
!!!next-input-character; |
!!!next-input-character; |
| 3047 |
} |
redo A; |
| 3048 |
|
} elsif ($self->{next_char} == 0x003B) { # ; |
|
if ($self->{next_char} == 0x003B) { # ; |
|
| 3049 |
!!!cp (1013); |
!!!cp (1013); |
| 3050 |
!!!next-input-character; |
!!!next-input-character; |
| 3051 |
|
# |
| 3052 |
} else { |
} else { |
| 3053 |
!!!cp (1014); |
!!!cp (1014); |
| 3054 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'no refc'); |
| 3055 |
|
## Reconsume. |
| 3056 |
|
# |
| 3057 |
} |
} |
| 3058 |
|
|
| 3059 |
|
my $code = $self->{state_keyword}; |
| 3060 |
|
my $l = $self->{line_prev}; |
| 3061 |
|
my $c = $self->{column_prev}; |
| 3062 |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 3063 |
!!!cp (1015); |
!!!cp (1015); |
| 3064 |
!!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code); |
!!!parse-error (type => 'invalid character reference', |
| 3065 |
|
text => (sprintf 'U+%04X', $code), |
| 3066 |
|
line => $l, column => $c); |
| 3067 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 3068 |
} elsif ($code > 0x10FFFF) { |
} elsif ($code > 0x10FFFF) { |
| 3069 |
!!!cp (1016); |
!!!cp (1016); |
| 3070 |
!!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code); |
!!!parse-error (type => 'invalid character reference', |
| 3071 |
|
text => (sprintf 'U-%08X', $code), |
| 3072 |
|
line => $l, column => $c); |
| 3073 |
$code = 0xFFFD; |
$code = 0xFFFD; |
| 3074 |
} elsif ($code == 0x000D) { |
} elsif ($code == 0x000D) { |
| 3075 |
!!!cp (1017); |
!!!cp (1017); |
| 3076 |
!!!parse-error (type => 'CR character reference'); |
!!!parse-error (type => 'CR character reference', |
| 3077 |
|
line => $l, column => $c); |
| 3078 |
$code = 0x000A; |
$code = 0x000A; |
| 3079 |
} elsif (0x80 <= $code and $code <= 0x9F) { |
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 3080 |
!!!cp (1018); |
!!!cp (1018); |
| 3081 |
!!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code); |
!!!parse-error (type => 'C1 character reference', |
| 3082 |
|
text => (sprintf 'U+%04X', $code), |
| 3083 |
|
line => $l, column => $c); |
| 3084 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 3085 |
} |
} |
| 3086 |
|
|
| 3087 |
return {type => CHARACTER_TOKEN, data => chr $code, has_reference => 1}; |
if ($self->{prev_state} == DATA_STATE) { |
| 3088 |
} else { |
!!!cp (992); |
| 3089 |
!!!cp (1019); |
$self->{state} = $self->{prev_state}; |
| 3090 |
!!!parse-error (type => 'bare nero'); |
## Reconsume. |
| 3091 |
!!!back-next-input-character ($self->{next_char}); |
!!!emit ({type => CHARACTER_TOKEN, data => chr $code, |
| 3092 |
$self->{next_char} = 0x0023; # # |
line => $l, column => $c, |
| 3093 |
return undef; |
}); |
| 3094 |
} |
redo A; |
| 3095 |
} elsif ((0x0041 <= $self->{next_char} and |
} else { |
| 3096 |
$self->{next_char} <= 0x005A) or |
!!!cp (991); |
| 3097 |
(0x0061 <= $self->{next_char} and |
$self->{current_attribute}->{value} .= chr $code; |
| 3098 |
$self->{next_char} <= 0x007A)) { |
$self->{current_attribute}->{has_reference} = 1; |
| 3099 |
my $entity_name = chr $self->{next_char}; |
$self->{state} = $self->{prev_state}; |
| 3100 |
!!!next-input-character; |
## Reconsume. |
| 3101 |
|
redo A; |
| 3102 |
my $value = $entity_name; |
} |
| 3103 |
my $match = 0; |
} elsif ($self->{state} == HEXREF_X_STATE) { |
| 3104 |
require Whatpm::_NamedEntityList; |
if ((0x0030 <= $self->{next_char} and $self->{next_char} <= 0x0039) or |
| 3105 |
our $EntityChar; |
(0x0041 <= $self->{next_char} and $self->{next_char} <= 0x0046) or |
| 3106 |
|
(0x0061 <= $self->{next_char} and $self->{next_char} <= 0x0066)) { |
| 3107 |
while (length $entity_name < 10 and |
# 0..9, A..F, a..f |
| 3108 |
## NOTE: Some number greater than the maximum length of entity name |
!!!cp (990); |
| 3109 |
((0x0041 <= $self->{next_char} and # a |
$self->{state} = HEXREF_HEX_STATE; |
| 3110 |
$self->{next_char} <= 0x005A) or # x |
$self->{state_keyword} = 0; |
| 3111 |
(0x0061 <= $self->{next_char} and # a |
## Reconsume. |
| 3112 |
$self->{next_char} <= 0x007A) or # z |
redo A; |
| 3113 |
(0x0030 <= $self->{next_char} and # 0 |
} else { |
| 3114 |
$self->{next_char} <= 0x0039) or # 9 |
!!!parse-error (type => 'bare hcro', |
| 3115 |
$self->{next_char} == 0x003B)) { # ; |
line => $self->{line_prev}, |
| 3116 |
$entity_name .= chr $self->{next_char}; |
column => $self->{column_prev} - 2); |
| 3117 |
if (defined $EntityChar->{$entity_name}) { |
|
| 3118 |
if ($self->{next_char} == 0x003B) { # ; |
## NOTE: According to the spec algorithm, nothing is returned, |
| 3119 |
!!!cp (1020); |
## and then "&#" followed by "X" or "x" is appended to the parent |
| 3120 |
$value = $EntityChar->{$entity_name}; |
## element or the attribute value in the later processing. |
| 3121 |
$match = 1; |
|
| 3122 |
!!!next-input-character; |
if ($self->{prev_state} == DATA_STATE) { |
| 3123 |
last; |
!!!cp (1005); |
| 3124 |
|
$self->{state} = $self->{prev_state}; |
| 3125 |
|
## Reconsume. |
| 3126 |
|
!!!emit ({type => CHARACTER_TOKEN, |
| 3127 |
|
data => '&' . $self->{state_keyword}, |
| 3128 |
|
line => $self->{line_prev}, |
| 3129 |
|
column => $self->{column_prev} - length $self->{state_keyword}, |
| 3130 |
|
}); |
| 3131 |
|
redo A; |
| 3132 |
} else { |
} else { |
| 3133 |
!!!cp (1021); |
!!!cp (989); |
| 3134 |
$value = $EntityChar->{$entity_name}; |
$self->{current_attribute}->{value} .= '&' . $self->{state_keyword}; |
| 3135 |
$match = -1; |
$self->{state} = $self->{prev_state}; |
| 3136 |
!!!next-input-character; |
## Reconsume. |
| 3137 |
|
redo A; |
| 3138 |
} |
} |
| 3139 |
} else { |
} |
| 3140 |
!!!cp (1022); |
} elsif ($self->{state} == HEXREF_HEX_STATE) { |
| 3141 |
$value .= chr $self->{next_char}; |
if (0x0030 <= $self->{next_char} and $self->{next_char} <= 0x0039) { |
| 3142 |
$match *= 2; |
# 0..9 |
| 3143 |
|
!!!cp (1002); |
| 3144 |
|
$self->{state_keyword} *= 0x10; |
| 3145 |
|
$self->{state_keyword} += $self->{next_char} - 0x0030; |
| 3146 |
|
## Stay in the state. |
| 3147 |
|
!!!next-input-character; |
| 3148 |
|
redo A; |
| 3149 |
|
} elsif (0x0061 <= $self->{next_char} and |
| 3150 |
|
$self->{next_char} <= 0x0066) { # a..f |
| 3151 |
|
!!!cp (1003); |
| 3152 |
|
$self->{state_keyword} *= 0x10; |
| 3153 |
|
$self->{state_keyword} += $self->{next_char} - 0x0060 + 9; |
| 3154 |
|
## Stay in the state. |
| 3155 |
!!!next-input-character; |
!!!next-input-character; |
| 3156 |
|
redo A; |
| 3157 |
|
} elsif (0x0041 <= $self->{next_char} and |
| 3158 |
|
$self->{next_char} <= 0x0046) { # A..F |
| 3159 |
|
!!!cp (1004); |
| 3160 |
|
$self->{state_keyword} *= 0x10; |
| 3161 |
|
$self->{state_keyword} += $self->{next_char} - 0x0040 + 9; |
| 3162 |
|
## Stay in the state. |
| 3163 |
|
!!!next-input-character; |
| 3164 |
|
redo A; |
| 3165 |
|
} elsif ($self->{next_char} == 0x003B) { # ; |
| 3166 |
|
!!!cp (1006); |
| 3167 |
|
!!!next-input-character; |
| 3168 |
|
# |
| 3169 |
|
} else { |
| 3170 |
|
!!!cp (1007); |
| 3171 |
|
!!!parse-error (type => 'no refc', |
| 3172 |
|
line => $self->{line}, |
| 3173 |
|
column => $self->{column}); |
| 3174 |
|
## Reconsume. |
| 3175 |
|
# |
| 3176 |
} |
} |
| 3177 |
} |
|
| 3178 |
|
my $code = $self->{state_keyword}; |
| 3179 |
if ($match > 0) { |
my $l = $self->{line_prev}; |
| 3180 |
!!!cp (1023); |
my $c = $self->{column_prev}; |
| 3181 |
return {type => CHARACTER_TOKEN, data => $value, has_reference => 1}; |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 3182 |
} elsif ($match < 0) { |
!!!cp (1008); |
| 3183 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'invalid character reference', |
| 3184 |
if ($in_attr and $match < -1) { |
text => (sprintf 'U+%04X', $code), |
| 3185 |
!!!cp (1024); |
line => $l, column => $c); |
| 3186 |
return {type => CHARACTER_TOKEN, data => '&'.$entity_name}; |
$code = 0xFFFD; |
| 3187 |
|
} elsif ($code > 0x10FFFF) { |
| 3188 |
|
!!!cp (1009); |
| 3189 |
|
!!!parse-error (type => 'invalid character reference', |
| 3190 |
|
text => (sprintf 'U-%08X', $code), |
| 3191 |
|
line => $l, column => $c); |
| 3192 |
|
$code = 0xFFFD; |
| 3193 |
|
} elsif ($code == 0x000D) { |
| 3194 |
|
!!!cp (1010); |
| 3195 |
|
!!!parse-error (type => 'CR character reference', line => $l, column => $c); |
| 3196 |
|
$code = 0x000A; |
| 3197 |
|
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 3198 |
|
!!!cp (1011); |
| 3199 |
|
!!!parse-error (type => 'C1 character reference', text => (sprintf 'U+%04X', $code), line => $l, column => $c); |
| 3200 |
|
$code = $c1_entity_char->{$code}; |
| 3201 |
|
} |
| 3202 |
|
|
| 3203 |
|
if ($self->{prev_state} == DATA_STATE) { |
| 3204 |
|
!!!cp (988); |
| 3205 |
|
$self->{state} = $self->{prev_state}; |
| 3206 |
|
## Reconsume. |
| 3207 |
|
!!!emit ({type => CHARACTER_TOKEN, data => chr $code, |
| 3208 |
|
line => $l, column => $c, |
| 3209 |
|
}); |
| 3210 |
|
redo A; |
| 3211 |
|
} else { |
| 3212 |
|
!!!cp (987); |
| 3213 |
|
$self->{current_attribute}->{value} .= chr $code; |
| 3214 |
|
$self->{current_attribute}->{has_reference} = 1; |
| 3215 |
|
$self->{state} = $self->{prev_state}; |
| 3216 |
|
## Reconsume. |
| 3217 |
|
redo A; |
| 3218 |
|
} |
| 3219 |
|
} elsif ($self->{state} == ENTITY_NAME_STATE) { |
| 3220 |
|
if (length $self->{state_keyword} < 30 and |
| 3221 |
|
## NOTE: Some number greater than the maximum length of entity name |
| 3222 |
|
((0x0041 <= $self->{next_char} and # a |
| 3223 |
|
$self->{next_char} <= 0x005A) or # x |
| 3224 |
|
(0x0061 <= $self->{next_char} and # a |
| 3225 |
|
$self->{next_char} <= 0x007A) or # z |
| 3226 |
|
(0x0030 <= $self->{next_char} and # 0 |
| 3227 |
|
$self->{next_char} <= 0x0039) or # 9 |
| 3228 |
|
$self->{next_char} == 0x003B)) { # ; |
| 3229 |
|
our $EntityChar; |
| 3230 |
|
$self->{state_keyword} .= chr $self->{next_char}; |
| 3231 |
|
if (defined $EntityChar->{$self->{state_keyword}}) { |
| 3232 |
|
if ($self->{next_char} == 0x003B) { # ; |
| 3233 |
|
!!!cp (1020); |
| 3234 |
|
$self->{entity__value} = $EntityChar->{$self->{state_keyword}}; |
| 3235 |
|
$self->{entity__match} = 1; |
| 3236 |
|
!!!next-input-character; |
| 3237 |
|
# |
| 3238 |
|
} else { |
| 3239 |
|
!!!cp (1021); |
| 3240 |
|
$self->{entity__value} = $EntityChar->{$self->{state_keyword}}; |
| 3241 |
|
$self->{entity__match} = -1; |
| 3242 |
|
## Stay in the state. |
| 3243 |
|
!!!next-input-character; |
| 3244 |
|
redo A; |
| 3245 |
|
} |
| 3246 |
|
} else { |
| 3247 |
|
!!!cp (1022); |
| 3248 |
|
$self->{entity__value} .= chr $self->{next_char}; |
| 3249 |
|
$self->{entity__match} *= 2; |
| 3250 |
|
## Stay in the state. |
| 3251 |
|
!!!next-input-character; |
| 3252 |
|
redo A; |
| 3253 |
|
} |
| 3254 |
|
} |
| 3255 |
|
|
| 3256 |
|
my $data; |
| 3257 |
|
my $has_ref; |
| 3258 |
|
if ($self->{entity__match} > 0) { |
| 3259 |
|
!!!cp (1023); |
| 3260 |
|
$data = $self->{entity__value}; |
| 3261 |
|
$has_ref = 1; |
| 3262 |
|
# |
| 3263 |
|
} elsif ($self->{entity__match} < 0) { |
| 3264 |
|
!!!parse-error (type => 'no refc'); |
| 3265 |
|
if ($self->{prev_state} != DATA_STATE and # in attribute |
| 3266 |
|
$self->{entity__match} < -1) { |
| 3267 |
|
!!!cp (1024); |
| 3268 |
|
$data = '&' . $self->{state_keyword}; |
| 3269 |
|
# |
| 3270 |
|
} else { |
| 3271 |
|
!!!cp (1025); |
| 3272 |
|
$data = $self->{entity__value}; |
| 3273 |
|
$has_ref = 1; |
| 3274 |
|
# |
| 3275 |
|
} |
| 3276 |
} else { |
} else { |
| 3277 |
!!!cp (1025); |
!!!cp (1026); |
| 3278 |
return {type => CHARACTER_TOKEN, data => $value, has_reference => 1}; |
!!!parse-error (type => 'bare ero', |
| 3279 |
|
line => $self->{line_prev}, |
| 3280 |
|
column => $self->{column_prev}); |
| 3281 |
|
$data = '&' . $self->{state_keyword}; |
| 3282 |
|
# |
| 3283 |
|
} |
| 3284 |
|
|
| 3285 |
|
## NOTE: In these cases, when a character reference is found, |
| 3286 |
|
## it is consumed and a character token is returned, or, otherwise, |
| 3287 |
|
## nothing is consumed and returned, according to the spec algorithm. |
| 3288 |
|
## In this implementation, anything that has been examined by the |
| 3289 |
|
## tokenizer is appended to the parent element or the attribute value |
| 3290 |
|
## as string, either literal string when no character reference or |
| 3291 |
|
## entity-replaced string otherwise, in this stage, since any characters |
| 3292 |
|
## that would not be consumed are appended in the data state or in an |
| 3293 |
|
## appropriate attribute value state anyway. |
| 3294 |
|
|
| 3295 |
|
if ($self->{prev_state} == DATA_STATE) { |
| 3296 |
|
!!!cp (986); |
| 3297 |
|
$self->{state} = $self->{prev_state}; |
| 3298 |
|
## Reconsume. |
| 3299 |
|
!!!emit ({type => CHARACTER_TOKEN, |
| 3300 |
|
data => $data, |
| 3301 |
|
line => $self->{line_prev}, |
| 3302 |
|
column => $self->{column_prev} + 1 - length $self->{state_keyword}, |
| 3303 |
|
}); |
| 3304 |
|
redo A; |
| 3305 |
|
} else { |
| 3306 |
|
!!!cp (985); |
| 3307 |
|
$self->{current_attribute}->{value} .= $data; |
| 3308 |
|
$self->{current_attribute}->{has_reference} = 1 if $has_ref; |
| 3309 |
|
$self->{state} = $self->{prev_state}; |
| 3310 |
|
## Reconsume. |
| 3311 |
|
redo A; |
| 3312 |
} |
} |
| 3313 |
} else { |
} else { |
| 3314 |
!!!cp (1026); |
die "$0: $self->{state}: Unknown state"; |
|
!!!parse-error (type => 'bare ero'); |
|
|
## NOTE: "No characters are consumed" in the spec. |
|
|
return {type => CHARACTER_TOKEN, data => '&'.$value}; |
|
| 3315 |
} |
} |
| 3316 |
} else { |
} # A |
| 3317 |
!!!cp (1027); |
|
| 3318 |
## no characters are consumed |
die "$0: _get_next_token: unexpected case"; |
| 3319 |
!!!parse-error (type => 'bare ero'); |
} # _get_next_token |
|
return undef; |
|
|
} |
|
|
} # _tokenize_attempt_to_consume_an_entity |
|
| 3320 |
|
|
| 3321 |
sub _initialize_tree_constructor ($) { |
sub _initialize_tree_constructor ($) { |
| 3322 |
my $self = shift; |
my $self = shift; |
| 3325 |
## TODO: Turn mutation events off # MUST |
## TODO: Turn mutation events off # MUST |
| 3326 |
## TODO: Turn loose Document option (manakai extension) on |
## TODO: Turn loose Document option (manakai extension) on |
| 3327 |
$self->{document}->manakai_is_html (1); # MUST |
$self->{document}->manakai_is_html (1); # MUST |
| 3328 |
|
$self->{document}->set_user_data (manakai_source_line => 1); |
| 3329 |
|
$self->{document}->set_user_data (manakai_source_column => 1); |
| 3330 |
} # _initialize_tree_constructor |
} # _initialize_tree_constructor |
| 3331 |
|
|
| 3332 |
sub _terminate_tree_constructor ($) { |
sub _terminate_tree_constructor ($) { |
| 3381 |
## language. |
## language. |
| 3382 |
my $doctype_name = $token->{name}; |
my $doctype_name = $token->{name}; |
| 3383 |
$doctype_name = '' unless defined $doctype_name; |
$doctype_name = '' unless defined $doctype_name; |
| 3384 |
$doctype_name =~ tr/a-z/A-Z/; |
$doctype_name =~ tr/a-z/A-Z/; # ASCII case-insensitive |
| 3385 |
if (not defined $token->{name} or # <!DOCTYPE> |
if (not defined $token->{name} or # <!DOCTYPE> |
|
defined $token->{public_identifier} or |
|
| 3386 |
defined $token->{system_identifier}) { |
defined $token->{system_identifier}) { |
| 3387 |
!!!cp ('t1'); |
!!!cp ('t1'); |
| 3388 |
!!!parse-error (type => 'not HTML5'); |
!!!parse-error (type => 'not HTML5', token => $token); |
| 3389 |
} elsif ($doctype_name ne 'HTML') { |
} elsif ($doctype_name ne 'HTML') { |
| 3390 |
!!!cp ('t2'); |
!!!cp ('t2'); |
| 3391 |
## ISSUE: ASCII case-insensitive? (in fact it does not matter) |
!!!parse-error (type => 'not HTML5', token => $token); |
| 3392 |
!!!parse-error (type => 'not HTML5'); |
} elsif (defined $token->{public_identifier}) { |
| 3393 |
|
if ($token->{public_identifier} eq 'XSLT-compat') { |
| 3394 |
|
!!!cp ('t1.2'); |
| 3395 |
|
!!!parse-error (type => 'XSLT-compat', token => $token, |
| 3396 |
|
level => $self->{level}->{should}); |
| 3397 |
|
} else { |
| 3398 |
|
!!!parse-error (type => 'not HTML5', token => $token); |
| 3399 |
|
} |
| 3400 |
} else { |
} else { |
| 3401 |
!!!cp ('t3'); |
!!!cp ('t3'); |
| 3402 |
|
# |
| 3403 |
} |
} |
| 3404 |
|
|
| 3405 |
my $doctype = $self->{document}->create_document_type_definition |
my $doctype = $self->{document}->create_document_type_definition |
| 3406 |
($token->{name}); ## ISSUE: If name is missing (e.g. <!DOCTYPE>)? |
($token->{name}); ## ISSUE: If name is missing (e.g. <!DOCTYPE>)? |
| 3407 |
|
## NOTE: Default value for both |public_id| and |system_id| attributes |
| 3408 |
|
## are empty strings, so that we don't set any value in missing cases. |
| 3409 |
$doctype->public_id ($token->{public_identifier}) |
$doctype->public_id ($token->{public_identifier}) |
| 3410 |
if defined $token->{public_identifier}; |
if defined $token->{public_identifier}; |
| 3411 |
$doctype->system_id ($token->{system_identifier}) |
$doctype->system_id ($token->{system_identifier}) |
| 3420 |
} elsif (defined $token->{public_identifier}) { |
} elsif (defined $token->{public_identifier}) { |
| 3421 |
my $pubid = $token->{public_identifier}; |
my $pubid = $token->{public_identifier}; |
| 3422 |
$pubid =~ tr/a-z/A-z/; |
$pubid =~ tr/a-z/A-z/; |
| 3423 |
if ({ |
my $prefix = [ |
| 3424 |
"+//SILMARIL//DTD HTML PRO V0R11 19970101//EN" => 1, |
"+//SILMARIL//DTD HTML PRO V0R11 19970101//", |
| 3425 |
"-//ADVASOFT LTD//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1, |
"-//ADVASOFT LTD//DTD HTML 3.0 ASWEDIT + EXTENSIONS//", |
| 3426 |
"-//AS//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1, |
"-//AS//DTD HTML 3.0 ASWEDIT + EXTENSIONS//", |
| 3427 |
"-//IETF//DTD HTML 2.0 LEVEL 1//EN" => 1, |
"-//IETF//DTD HTML 2.0 LEVEL 1//", |
| 3428 |
"-//IETF//DTD HTML 2.0 LEVEL 2//EN" => 1, |
"-//IETF//DTD HTML 2.0 LEVEL 2//", |
| 3429 |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 1//EN" => 1, |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 1//", |
| 3430 |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 2//EN" => 1, |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 2//", |
| 3431 |
"-//IETF//DTD HTML 2.0 STRICT//EN" => 1, |
"-//IETF//DTD HTML 2.0 STRICT//", |
| 3432 |
"-//IETF//DTD HTML 2.0//EN" => 1, |
"-//IETF//DTD HTML 2.0//", |
| 3433 |
"-//IETF//DTD HTML 2.1E//EN" => 1, |
"-//IETF//DTD HTML 2.1E//", |
| 3434 |
"-//IETF//DTD HTML 3.0//EN" => 1, |
"-//IETF//DTD HTML 3.0//", |
| 3435 |
"-//IETF//DTD HTML 3.0//EN//" => 1, |
"-//IETF//DTD HTML 3.2 FINAL//", |
| 3436 |
"-//IETF//DTD HTML 3.2 FINAL//EN" => 1, |
"-//IETF//DTD HTML 3.2//", |
| 3437 |
"-//IETF//DTD HTML 3.2//EN" => 1, |
"-//IETF//DTD HTML 3//", |
| 3438 |
"-//IETF//DTD HTML 3//EN" => 1, |
"-//IETF//DTD HTML LEVEL 0//", |
| 3439 |
"-//IETF//DTD HTML LEVEL 0//EN" => 1, |
"-//IETF//DTD HTML LEVEL 1//", |
| 3440 |
"-//IETF//DTD HTML LEVEL 0//EN//2.0" => 1, |
"-//IETF//DTD HTML LEVEL 2//", |
| 3441 |
"-//IETF//DTD HTML LEVEL 1//EN" => 1, |
"-//IETF//DTD HTML LEVEL 3//", |
| 3442 |
"-//IETF//DTD HTML LEVEL 1//EN//2.0" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 0//", |
| 3443 |
"-//IETF//DTD HTML LEVEL 2//EN" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 1//", |
| 3444 |
"-//IETF//DTD HTML LEVEL 2//EN//2.0" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 2//", |
| 3445 |
"-//IETF//DTD HTML LEVEL 3//EN" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 3//", |
| 3446 |
"-//IETF//DTD HTML LEVEL 3//EN//3.0" => 1, |
"-//IETF//DTD HTML STRICT//", |
| 3447 |
"-//IETF//DTD HTML STRICT LEVEL 0//EN" => 1, |
"-//IETF//DTD HTML//", |
| 3448 |
"-//IETF//DTD HTML STRICT LEVEL 0//EN//2.0" => 1, |
"-//METRIUS//DTD METRIUS PRESENTATIONAL//", |
| 3449 |
"-//IETF//DTD HTML STRICT LEVEL 1//EN" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML STRICT//", |
| 3450 |
"-//IETF//DTD HTML STRICT LEVEL 1//EN//2.0" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML//", |
| 3451 |
"-//IETF//DTD HTML STRICT LEVEL 2//EN" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 TABLES//", |
| 3452 |
"-//IETF//DTD HTML STRICT LEVEL 2//EN//2.0" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML STRICT//", |
| 3453 |
"-//IETF//DTD HTML STRICT LEVEL 3//EN" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML//", |
| 3454 |
"-//IETF//DTD HTML STRICT LEVEL 3//EN//3.0" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 TABLES//", |
| 3455 |
"-//IETF//DTD HTML STRICT//EN" => 1, |
"-//NETSCAPE COMM. CORP.//DTD HTML//", |
| 3456 |
"-//IETF//DTD HTML STRICT//EN//2.0" => 1, |
"-//NETSCAPE COMM. CORP.//DTD STRICT HTML//", |
| 3457 |
"-//IETF//DTD HTML STRICT//EN//3.0" => 1, |
"-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//", |
| 3458 |
"-//IETF//DTD HTML//EN" => 1, |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//", |
| 3459 |
"-//IETF//DTD HTML//EN//2.0" => 1, |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED RELAXED 1.0//", |
| 3460 |
"-//IETF//DTD HTML//EN//3.0" => 1, |
"-//SOFTQUAD SOFTWARE//DTD HOTMETAL PRO 6.0::19990601::EXTENSIONS TO HTML 4.0//", |
| 3461 |
"-//METRIUS//DTD METRIUS PRESENTATIONAL//EN" => 1, |
"-//SOFTQUAD//DTD HOTMETAL PRO 4.0::19971010::EXTENSIONS TO HTML 4.0//", |
| 3462 |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML STRICT//EN" => 1, |
"-//SPYGLASS//DTD HTML 2.0 EXTENDED//", |
| 3463 |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML//EN" => 1, |
"-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//", |
| 3464 |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 TABLES//EN" => 1, |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//", |
| 3465 |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML STRICT//EN" => 1, |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA STRICT HTML//", |
| 3466 |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML//EN" => 1, |
"-//W3C//DTD HTML 3 1995-03-24//", |
| 3467 |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 TABLES//EN" => 1, |
"-//W3C//DTD HTML 3.2 DRAFT//", |
| 3468 |
"-//NETSCAPE COMM. CORP.//DTD HTML//EN" => 1, |
"-//W3C//DTD HTML 3.2 FINAL//", |
| 3469 |
"-//NETSCAPE COMM. CORP.//DTD STRICT HTML//EN" => 1, |
"-//W3C//DTD HTML 3.2//", |
| 3470 |
"-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//EN" => 1, |
"-//W3C//DTD HTML 3.2S DRAFT//", |
| 3471 |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//EN" => 1, |
"-//W3C//DTD HTML 4.0 FRAMESET//", |
| 3472 |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED RELAXED 1.0//EN" => 1, |
"-//W3C//DTD HTML 4.0 TRANSITIONAL//", |
| 3473 |
"-//SOFTQUAD SOFTWARE//DTD HOTMETAL PRO 6.0::19990601::EXTENSIONS TO HTML 4.0//EN" => 1, |
"-//W3C//DTD HTML EXPERIMETNAL 19960712//", |
| 3474 |
"-//SOFTQUAD//DTD HOTMETAL PRO 4.0::19971010::EXTENSIONS TO HTML 4.0//EN" => 1, |
"-//W3C//DTD HTML EXPERIMENTAL 970421//", |
| 3475 |
"-//SPYGLASS//DTD HTML 2.0 EXTENDED//EN" => 1, |
"-//W3C//DTD W3 HTML//", |
| 3476 |
"-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//EN" => 1, |
"-//W3O//DTD W3 HTML 3.0//", |
| 3477 |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//EN" => 1, |
"-//WEBTECHS//DTD MOZILLA HTML 2.0//", |
| 3478 |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA STRICT HTML//EN" => 1, |
"-//WEBTECHS//DTD MOZILLA HTML//", |
| 3479 |
"-//W3C//DTD HTML 3 1995-03-24//EN" => 1, |
]; # $prefix |
| 3480 |
"-//W3C//DTD HTML 3.2 DRAFT//EN" => 1, |
my $match; |
| 3481 |
"-//W3C//DTD HTML 3.2 FINAL//EN" => 1, |
for (@$prefix) { |
| 3482 |
"-//W3C//DTD HTML 3.2//EN" => 1, |
if (substr ($prefix, 0, length $_) eq $_) { |
| 3483 |
"-//W3C//DTD HTML 3.2S DRAFT//EN" => 1, |
$match = 1; |
| 3484 |
"-//W3C//DTD HTML 4.0 FRAMESET//EN" => 1, |
last; |
| 3485 |
"-//W3C//DTD HTML 4.0 TRANSITIONAL//EN" => 1, |
} |
| 3486 |
"-//W3C//DTD HTML EXPERIMETNAL 19960712//EN" => 1, |
} |
| 3487 |
"-//W3C//DTD HTML EXPERIMENTAL 970421//EN" => 1, |
if ($match or |
| 3488 |
"-//W3C//DTD W3 HTML//EN" => 1, |
$pubid eq "-//W3O//DTD W3 HTML STRICT 3.0//EN//" or |
| 3489 |
"-//W3O//DTD W3 HTML 3.0//EN" => 1, |
$pubid eq "-/W3C/DTD HTML 4.0 TRANSITIONAL/EN" or |
| 3490 |
"-//W3O//DTD W3 HTML 3.0//EN//" => 1, |
$pubid eq "HTML") { |
|
"-//W3O//DTD W3 HTML STRICT 3.0//EN//" => 1, |
|
|
"-//WEBTECHS//DTD MOZILLA HTML 2.0//EN" => 1, |
|
|
"-//WEBTECHS//DTD MOZILLA HTML//EN" => 1, |
|
|
"-/W3C/DTD HTML 4.0 TRANSITIONAL/EN" => 1, |
|
|
"HTML" => 1, |
|
|
}->{$pubid}) { |
|
| 3491 |
!!!cp ('t5'); |
!!!cp ('t5'); |
| 3492 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 3493 |
} elsif ($pubid eq "-//W3C//DTD HTML 4.01 FRAMESET//EN" or |
} elsif ($pubid =~ m[^-//W3C//DTD HTML 4.01 FRAMESET//] or |
| 3494 |
$pubid eq "-//W3C//DTD HTML 4.01 TRANSITIONAL//EN") { |
$pubid =~ m[^-//W3C//DTD HTML 4.01 TRANSITIONAL//]) { |
| 3495 |
if (defined $token->{system_identifier}) { |
if (defined $token->{system_identifier}) { |
| 3496 |
!!!cp ('t6'); |
!!!cp ('t6'); |
| 3497 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 3499 |
!!!cp ('t7'); |
!!!cp ('t7'); |
| 3500 |
$self->{document}->manakai_compat_mode ('limited quirks'); |
$self->{document}->manakai_compat_mode ('limited quirks'); |
| 3501 |
} |
} |
| 3502 |
} elsif ($pubid eq "-//W3C//DTD XHTML 1.0 FRAMESET//EN" or |
} elsif ($pubid =~ m[^-//W3C//DTD XHTML 1.0 FRAMESET//] or |
| 3503 |
$pubid eq "-//W3C//DTD XHTML 1.0 TRANSITIONAL//EN") { |
$pubid =~ m[^-//W3C//DTD XHTML 1.0 TRANSITIONAL//]) { |
| 3504 |
!!!cp ('t8'); |
!!!cp ('t8'); |
| 3505 |
$self->{document}->manakai_compat_mode ('limited quirks'); |
$self->{document}->manakai_compat_mode ('limited quirks'); |
| 3506 |
} else { |
} else { |
| 3513 |
my $sysid = $token->{system_identifier}; |
my $sysid = $token->{system_identifier}; |
| 3514 |
$sysid =~ tr/A-Z/a-z/; |
$sysid =~ tr/A-Z/a-z/; |
| 3515 |
if ($sysid eq "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd") { |
if ($sysid eq "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd") { |
| 3516 |
## TODO: Check the spec: PUBLIC "(limited quirks)" "(quirks)" |
## NOTE: Ensure that |PUBLIC "(limited quirks)" "(quirks)"| is |
| 3517 |
|
## marked as quirks. |
| 3518 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 3519 |
!!!cp ('t11'); |
!!!cp ('t11'); |
| 3520 |
} else { |
} else { |
| 3533 |
END_OF_FILE_TOKEN, 1, |
END_OF_FILE_TOKEN, 1, |
| 3534 |
}->{$token->{type}}) { |
}->{$token->{type}}) { |
| 3535 |
!!!cp ('t14'); |
!!!cp ('t14'); |
| 3536 |
!!!parse-error (type => 'no DOCTYPE'); |
!!!parse-error (type => 'no DOCTYPE', token => $token); |
| 3537 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 3538 |
## Go to the "before html" insertion mode. |
## Go to the "before html" insertion mode. |
| 3539 |
## reprocess |
## reprocess |
| 3540 |
|
!!!ack-later; |
| 3541 |
return; |
return; |
| 3542 |
} elsif ($token->{type} == CHARACTER_TOKEN) { |
} elsif ($token->{type} == CHARACTER_TOKEN) { |
| 3543 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
| 3555 |
!!!cp ('t17'); |
!!!cp ('t17'); |
| 3556 |
} |
} |
| 3557 |
|
|
| 3558 |
!!!parse-error (type => 'no DOCTYPE'); |
!!!parse-error (type => 'no DOCTYPE', token => $token); |
| 3559 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 3560 |
## Go to the "before html" insertion mode. |
## Go to the "before html" insertion mode. |
| 3561 |
## reprocess |
## reprocess |
| 3584 |
B: { |
B: { |
| 3585 |
if ($token->{type} == DOCTYPE_TOKEN) { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 3586 |
!!!cp ('t19'); |
!!!cp ('t19'); |
| 3587 |
!!!parse-error (type => 'in html:#DOCTYPE'); |
!!!parse-error (type => 'in html:#DOCTYPE', token => $token); |
| 3588 |
## Ignore the token |
## Ignore the token |
| 3589 |
## Stay in the insertion mode. |
## Stay in the insertion mode. |
| 3590 |
!!!next-token; |
!!!next-token; |
| 3618 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 3619 |
if ($token->{tag_name} eq 'html') { |
if ($token->{tag_name} eq 'html') { |
| 3620 |
my $root_element; |
my $root_element; |
| 3621 |
!!!create-element ($root_element, $token->{tag_name}, $token->{attributes}); |
!!!create-element ($root_element, $HTML_NS, $token->{tag_name}, $token->{attributes}, $token); |
| 3622 |
$self->{document}->append_child ($root_element); |
$self->{document}->append_child ($root_element); |
| 3623 |
push @{$self->{open_elements}}, [$root_element, 'html']; |
push @{$self->{open_elements}}, |
| 3624 |
|
[$root_element, $el_category->{html}]; |
| 3625 |
|
|
| 3626 |
if ($token->{attributes}->{manifest}) { |
if ($token->{attributes}->{manifest}) { |
| 3627 |
!!!cp ('t24'); |
!!!cp ('t24'); |
| 3628 |
$self->{application_cache_selection} |
$self->{application_cache_selection} |
| 3629 |
->($token->{attributes}->{manifest}->{value}); |
->($token->{attributes}->{manifest}->{value}); |
| 3630 |
## ISSUE: No relative reference resolution? |
## ISSUE: Spec is unclear on relative references. |
| 3631 |
|
## According to Hixie (#whatwg 2008-03-19), it should be |
| 3632 |
|
## resolved against the base URI of the document in HTML |
| 3633 |
|
## or xml:base of the element in XHTML. |
| 3634 |
} else { |
} else { |
| 3635 |
!!!cp ('t25'); |
!!!cp ('t25'); |
| 3636 |
$self->{application_cache_selection}->(undef); |
$self->{application_cache_selection}->(undef); |
| 3637 |
} |
} |
| 3638 |
|
|
| 3639 |
|
!!!nack ('t25c'); |
| 3640 |
|
|
| 3641 |
!!!next-token; |
!!!next-token; |
| 3642 |
return; ## Go to the "before head" insertion mode. |
return; ## Go to the "before head" insertion mode. |
| 3643 |
} else { |
} else { |
| 3654 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 3655 |
} |
} |
| 3656 |
|
|
| 3657 |
my $root_element; !!!create-element ($root_element, 'html'); |
my $root_element; |
| 3658 |
|
!!!create-element ($root_element, $HTML_NS, 'html',, $token); |
| 3659 |
$self->{document}->append_child ($root_element); |
$self->{document}->append_child ($root_element); |
| 3660 |
push @{$self->{open_elements}}, [$root_element, 'html']; |
push @{$self->{open_elements}}, [$root_element, $el_category->{html}]; |
| 3661 |
|
|
| 3662 |
$self->{application_cache_selection}->(undef); |
$self->{application_cache_selection}->(undef); |
| 3663 |
|
|
| 3664 |
## NOTE: Reprocess the token. |
## NOTE: Reprocess the token. |
| 3665 |
|
!!!ack-later; |
| 3666 |
return; ## Go to the "before head" insertion mode. |
return; ## Go to the "before head" insertion mode. |
| 3667 |
|
|
| 3668 |
## ISSUE: There is an issue in the spec |
## ISSUE: There is an issue in the spec |
| 3686 |
if ($self->{open_elements}->[0]->[0] eq $node->[0]) { |
if ($self->{open_elements}->[0]->[0] eq $node->[0]) { |
| 3687 |
$last = 1; |
$last = 1; |
| 3688 |
if (defined $self->{inner_html_node}) { |
if (defined $self->{inner_html_node}) { |
| 3689 |
if ($self->{inner_html_node}->[1] eq 'td' or |
!!!cp ('t28'); |
| 3690 |
$self->{inner_html_node}->[1] eq 'th') { |
$node = $self->{inner_html_node}; |
| 3691 |
!!!cp ('t27'); |
} else { |
| 3692 |
# |
die "_reset_insertion_mode: t27"; |
|
} else { |
|
|
!!!cp ('t28'); |
|
|
$node = $self->{inner_html_node}; |
|
|
} |
|
| 3693 |
} |
} |
| 3694 |
} |
} |
| 3695 |
|
|
| 3696 |
## Step 4..13 |
## Step 4..14 |
| 3697 |
my $new_mode = { |
my $new_mode; |
| 3698 |
|
if ($node->[1] & FOREIGN_EL) { |
| 3699 |
|
!!!cp ('t28.1'); |
| 3700 |
|
## NOTE: Strictly spaking, the line below only applies to MathML and |
| 3701 |
|
## SVG elements. Currently the HTML syntax supports only MathML and |
| 3702 |
|
## SVG elements as foreigners. |
| 3703 |
|
$new_mode = IN_BODY_IM | IN_FOREIGN_CONTENT_IM; |
| 3704 |
|
} elsif ($node->[1] & TABLE_CELL_EL) { |
| 3705 |
|
if ($last) { |
| 3706 |
|
!!!cp ('t28.2'); |
| 3707 |
|
# |
| 3708 |
|
} else { |
| 3709 |
|
!!!cp ('t28.3'); |
| 3710 |
|
$new_mode = IN_CELL_IM; |
| 3711 |
|
} |
| 3712 |
|
} else { |
| 3713 |
|
!!!cp ('t28.4'); |
| 3714 |
|
$new_mode = { |
| 3715 |
select => IN_SELECT_IM, |
select => IN_SELECT_IM, |
| 3716 |
## NOTE: |option| and |optgroup| do not set |
## NOTE: |option| and |optgroup| do not set |
| 3717 |
## insertion mode to "in select" by themselves. |
## insertion mode to "in select" by themselves. |
|
td => IN_CELL_IM, |
|
|
th => IN_CELL_IM, |
|
| 3718 |
tr => IN_ROW_IM, |
tr => IN_ROW_IM, |
| 3719 |
tbody => IN_TABLE_BODY_IM, |
tbody => IN_TABLE_BODY_IM, |
| 3720 |
thead => IN_TABLE_BODY_IM, |
thead => IN_TABLE_BODY_IM, |
| 3725 |
head => IN_BODY_IM, # not in head! |
head => IN_BODY_IM, # not in head! |
| 3726 |
body => IN_BODY_IM, |
body => IN_BODY_IM, |
| 3727 |
frameset => IN_FRAMESET_IM, |
frameset => IN_FRAMESET_IM, |
| 3728 |
}->{$node->[1]}; |
}->{$node->[0]->manakai_local_name}; |
| 3729 |
|
} |
| 3730 |
$self->{insertion_mode} = $new_mode and return if defined $new_mode; |
$self->{insertion_mode} = $new_mode and return if defined $new_mode; |
| 3731 |
|
|
| 3732 |
## Step 14 |
## Step 15 |
| 3733 |
if ($node->[1] eq 'html') { |
if ($node->[1] & HTML_EL) { |
| 3734 |
unless (defined $self->{head_element}) { |
unless (defined $self->{head_element}) { |
| 3735 |
!!!cp ('t29'); |
!!!cp ('t29'); |
| 3736 |
$self->{insertion_mode} = BEFORE_HEAD_IM; |
$self->{insertion_mode} = BEFORE_HEAD_IM; |
| 3744 |
!!!cp ('t31'); |
!!!cp ('t31'); |
| 3745 |
} |
} |
| 3746 |
|
|
| 3747 |
## Step 15 |
## Step 16 |
| 3748 |
$self->{insertion_mode} = IN_BODY_IM and return if $last; |
$self->{insertion_mode} = IN_BODY_IM and return if $last; |
| 3749 |
|
|
| 3750 |
## Step 16 |
## Step 17 |
| 3751 |
$i--; |
$i--; |
| 3752 |
$node = $self->{open_elements}->[$i]; |
$node = $self->{open_elements}->[$i]; |
| 3753 |
|
|
| 3754 |
## Step 17 |
## Step 18 |
| 3755 |
redo S3; |
redo S3; |
| 3756 |
} # S3 |
} # S3 |
| 3757 |
|
|
| 3863 |
## Step 1 |
## Step 1 |
| 3864 |
my $start_tag_name = $token->{tag_name}; |
my $start_tag_name = $token->{tag_name}; |
| 3865 |
my $el; |
my $el; |
| 3866 |
!!!create-element ($el, $start_tag_name, $token->{attributes}); |
!!!create-element ($el, $HTML_NS, $start_tag_name, $token->{attributes}, $token); |
| 3867 |
|
|
| 3868 |
## Step 2 |
## Step 2 |
| 3869 |
$insert->($el); |
$insert->($el); |
| 3874 |
|
|
| 3875 |
## Step 4 |
## Step 4 |
| 3876 |
my $text = ''; |
my $text = ''; |
| 3877 |
|
!!!nack ('t40.1'); |
| 3878 |
!!!next-token; |
!!!next-token; |
| 3879 |
while ($token->{type} == CHARACTER_TOKEN) { # or until stop tokenizing |
while ($token->{type} == CHARACTER_TOKEN) { # or until stop tokenizing |
| 3880 |
!!!cp ('t40'); |
!!!cp ('t40'); |
| 3901 |
## NOTE: An end-of-file token. |
## NOTE: An end-of-file token. |
| 3902 |
if ($content_model_flag == CDATA_CONTENT_MODEL) { |
if ($content_model_flag == CDATA_CONTENT_MODEL) { |
| 3903 |
!!!cp ('t43'); |
!!!cp ('t43'); |
| 3904 |
!!!parse-error (type => 'in CDATA:#'.$token->{type}); |
!!!parse-error (type => 'in CDATA:#eof', token => $token); |
| 3905 |
} elsif ($content_model_flag == RCDATA_CONTENT_MODEL) { |
} elsif ($content_model_flag == RCDATA_CONTENT_MODEL) { |
| 3906 |
!!!cp ('t44'); |
!!!cp ('t44'); |
| 3907 |
!!!parse-error (type => 'in RCDATA:#'.$token->{type}); |
!!!parse-error (type => 'in RCDATA:#eof', token => $token); |
| 3908 |
} else { |
} else { |
| 3909 |
die "$0: $content_model_flag in parse_rcdata"; |
die "$0: $content_model_flag in parse_rcdata"; |
| 3910 |
} |
} |
| 3914 |
|
|
| 3915 |
my $script_start_tag = sub () { |
my $script_start_tag = sub () { |
| 3916 |
my $script_el; |
my $script_el; |
| 3917 |
!!!create-element ($script_el, 'script', $token->{attributes}); |
!!!create-element ($script_el, $HTML_NS, 'script', $token->{attributes}, $token); |
| 3918 |
## TODO: mark as "parser-inserted" |
## TODO: mark as "parser-inserted" |
| 3919 |
|
|
| 3920 |
$self->{content_model} = CDATA_CONTENT_MODEL; |
$self->{content_model} = CDATA_CONTENT_MODEL; |
| 3921 |
delete $self->{escape}; # MUST |
delete $self->{escape}; # MUST |
| 3922 |
|
|
| 3923 |
my $text = ''; |
my $text = ''; |
| 3924 |
|
!!!nack ('t45.1'); |
| 3925 |
!!!next-token; |
!!!next-token; |
| 3926 |
while ($token->{type} == CHARACTER_TOKEN) { |
while ($token->{type} == CHARACTER_TOKEN) { |
| 3927 |
!!!cp ('t45'); |
!!!cp ('t45'); |
| 3941 |
## Ignore the token |
## Ignore the token |
| 3942 |
} else { |
} else { |
| 3943 |
!!!cp ('t48'); |
!!!cp ('t48'); |
| 3944 |
!!!parse-error (type => 'in CDATA:#'.$token->{type}); |
!!!parse-error (type => 'in CDATA:#eof', token => $token); |
| 3945 |
## ISSUE: And ignore? |
## ISSUE: And ignore? |
| 3946 |
## TODO: mark as "already executed" |
## TODO: mark as "already executed" |
| 3947 |
} |
} |
| 3969 |
my $open_tables = [[$self->{open_elements}->[0]->[0]]]; |
my $open_tables = [[$self->{open_elements}->[0]->[0]]]; |
| 3970 |
|
|
| 3971 |
my $formatting_end_tag = sub { |
my $formatting_end_tag = sub { |
| 3972 |
my $tag_name = shift; |
my $end_tag_token = shift; |
| 3973 |
|
my $tag_name = $end_tag_token->{tag_name}; |
| 3974 |
|
|
| 3975 |
## NOTE: The adoption agency algorithm (AAA). |
## NOTE: The adoption agency algorithm (AAA). |
| 3976 |
|
|
| 3979 |
my $formatting_element; |
my $formatting_element; |
| 3980 |
my $formatting_element_i_in_active; |
my $formatting_element_i_in_active; |
| 3981 |
AFE: for (reverse 0..$#$active_formatting_elements) { |
AFE: for (reverse 0..$#$active_formatting_elements) { |
| 3982 |
if ($active_formatting_elements->[$_]->[1] eq $tag_name) { |
if ($active_formatting_elements->[$_]->[0] eq '#marker') { |
| 3983 |
|
!!!cp ('t52'); |
| 3984 |
|
last AFE; |
| 3985 |
|
} elsif ($active_formatting_elements->[$_]->[0]->manakai_local_name |
| 3986 |
|
eq $tag_name) { |
| 3987 |
!!!cp ('t51'); |
!!!cp ('t51'); |
| 3988 |
$formatting_element = $active_formatting_elements->[$_]; |
$formatting_element = $active_formatting_elements->[$_]; |
| 3989 |
$formatting_element_i_in_active = $_; |
$formatting_element_i_in_active = $_; |
| 3990 |
last AFE; |
last AFE; |
|
} elsif ($active_formatting_elements->[$_]->[0] eq '#marker') { |
|
|
!!!cp ('t52'); |
|
|
last AFE; |
|
| 3991 |
} |
} |
| 3992 |
} # AFE |
} # AFE |
| 3993 |
unless (defined $formatting_element) { |
unless (defined $formatting_element) { |
| 3994 |
!!!cp ('t53'); |
!!!cp ('t53'); |
| 3995 |
!!!parse-error (type => 'unmatched end tag:'.$tag_name); |
!!!parse-error (type => 'unmatched end tag', text => $tag_name, token => $end_tag_token); |
| 3996 |
## Ignore the token |
## Ignore the token |
| 3997 |
!!!next-token; |
!!!next-token; |
| 3998 |
return; |
return; |
| 4009 |
last INSCOPE; |
last INSCOPE; |
| 4010 |
} else { # in open elements but not in scope |
} else { # in open elements but not in scope |
| 4011 |
!!!cp ('t55'); |
!!!cp ('t55'); |
| 4012 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 4013 |
|
text => $token->{tag_name}, |
| 4014 |
|
token => $end_tag_token); |
| 4015 |
## Ignore the token |
## Ignore the token |
| 4016 |
!!!next-token; |
!!!next-token; |
| 4017 |
return; |
return; |
| 4018 |
} |
} |
| 4019 |
} elsif ({ |
} elsif ($node->[1] & SCOPING_EL) { |
|
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
| 4020 |
!!!cp ('t56'); |
!!!cp ('t56'); |
| 4021 |
$in_scope = 0; |
$in_scope = 0; |
| 4022 |
} |
} |
| 4023 |
} # INSCOPE |
} # INSCOPE |
| 4024 |
unless (defined $formatting_element_i_in_open) { |
unless (defined $formatting_element_i_in_open) { |
| 4025 |
!!!cp ('t57'); |
!!!cp ('t57'); |
| 4026 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 4027 |
|
text => $token->{tag_name}, |
| 4028 |
|
token => $end_tag_token); |
| 4029 |
pop @$active_formatting_elements; # $formatting_element |
pop @$active_formatting_elements; # $formatting_element |
| 4030 |
!!!next-token; ## TODO: ok? |
!!!next-token; ## TODO: ok? |
| 4031 |
return; |
return; |
| 4032 |
} |
} |
| 4033 |
if (not $self->{open_elements}->[-1]->[0] eq $formatting_element->[0]) { |
if (not $self->{open_elements}->[-1]->[0] eq $formatting_element->[0]) { |
| 4034 |
!!!cp ('t58'); |
!!!cp ('t58'); |
| 4035 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed', |
| 4036 |
|
text => $self->{open_elements}->[-1]->[0] |
| 4037 |
|
->manakai_local_name, |
| 4038 |
|
token => $end_tag_token); |
| 4039 |
} |
} |
| 4040 |
|
|
| 4041 |
## Step 2 |
## Step 2 |
| 4043 |
my $furthest_block_i_in_open; |
my $furthest_block_i_in_open; |
| 4044 |
OE: for (reverse 0..$#{$self->{open_elements}}) { |
OE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4045 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 4046 |
if (not $formatting_category->{$node->[1]} and |
if (not ($node->[1] & FORMATTING_EL) and |
| 4047 |
#not $phrasing_category->{$node->[1]} and |
#not $phrasing_category->{$node->[1]} and |
| 4048 |
($special_category->{$node->[1]} or |
($node->[1] & SPECIAL_EL or |
| 4049 |
$scoping_category->{$node->[1]})) { ## Scoping is redundant, maybe |
$node->[1] & SCOPING_EL)) { ## Scoping is redundant, maybe |
| 4050 |
!!!cp ('t59'); |
!!!cp ('t59'); |
| 4051 |
$furthest_block = $node; |
$furthest_block = $node; |
| 4052 |
$furthest_block_i_in_open = $_; |
$furthest_block_i_in_open = $_; |
| 4132 |
} # S7 |
} # S7 |
| 4133 |
|
|
| 4134 |
## Step 8 |
## Step 8 |
| 4135 |
if ({ |
if ($common_ancestor_node->[1] & TABLE_ROWS_EL) { |
|
table => 1, tbody => 1, tfoot => 1, thead => 1, tr => 1, |
|
|
}->{$common_ancestor_node->[1]}) { |
|
| 4136 |
my $foster_parent_element; |
my $foster_parent_element; |
| 4137 |
my $next_sibling; |
my $next_sibling; |
| 4138 |
OE: for (reverse 0..$#{$self->{open_elements}}) { |
OE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4139 |
if ($self->{open_elements}->[$_]->[1] eq 'table') { |
if ($self->{open_elements}->[$_]->[1] & TABLE_EL) { |
| 4140 |
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
| 4141 |
if (defined $parent and $parent->node_type == 1) { |
if (defined $parent and $parent->node_type == 1) { |
| 4142 |
!!!cp ('t65.1'); |
!!!cp ('t65.1'); |
| 4209 |
|
|
| 4210 |
my $insert_to_foster = sub { |
my $insert_to_foster = sub { |
| 4211 |
my $child = shift; |
my $child = shift; |
| 4212 |
if ({ |
if ($self->{open_elements}->[-1]->[1] & TABLE_ROWS_EL) { |
|
table => 1, tbody => 1, tfoot => 1, thead => 1, tr => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 4213 |
# MUST |
# MUST |
| 4214 |
my $foster_parent_element; |
my $foster_parent_element; |
| 4215 |
my $next_sibling; |
my $next_sibling; |
| 4216 |
OE: for (reverse 0..$#{$self->{open_elements}}) { |
OE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4217 |
if ($self->{open_elements}->[$_]->[1] eq 'table') { |
if ($self->{open_elements}->[$_]->[1] & TABLE_EL) { |
| 4218 |
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
| 4219 |
if (defined $parent and $parent->node_type == 1) { |
if (defined $parent and $parent->node_type == 1) { |
| 4220 |
!!!cp ('t70'); |
!!!cp ('t70'); |
| 4239 |
} |
} |
| 4240 |
}; # $insert_to_foster |
}; # $insert_to_foster |
| 4241 |
|
|
| 4242 |
B: { |
B: while (1) { |
| 4243 |
if ($token->{type} == DOCTYPE_TOKEN) { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 4244 |
!!!cp ('t73'); |
!!!cp ('t73'); |
| 4245 |
!!!parse-error (type => 'DOCTYPE in the middle'); |
!!!parse-error (type => 'in html:#DOCTYPE', token => $token); |
| 4246 |
## Ignore the token |
## Ignore the token |
| 4247 |
## Stay in the phase |
## Stay in the phase |
| 4248 |
!!!next-token; |
!!!next-token; |
| 4249 |
redo B; |
next B; |
| 4250 |
} elsif ($token->{type} == START_TAG_TOKEN and |
} elsif ($token->{type} == START_TAG_TOKEN and |
| 4251 |
$token->{tag_name} eq 'html') { |
$token->{tag_name} eq 'html') { |
| 4252 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 4253 |
!!!cp ('t79'); |
!!!cp ('t79'); |
| 4254 |
!!!parse-error (type => 'after html:html'); |
!!!parse-error (type => 'after html', text => 'html', token => $token); |
| 4255 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 4256 |
} elsif ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 4257 |
!!!cp ('t80'); |
!!!cp ('t80'); |
| 4258 |
!!!parse-error (type => 'after html:html'); |
!!!parse-error (type => 'after html', text => 'html', token => $token); |
| 4259 |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 4260 |
} else { |
} else { |
| 4261 |
!!!cp ('t81'); |
!!!cp ('t81'); |
| 4262 |
} |
} |
| 4263 |
|
|
| 4264 |
!!!cp ('t82'); |
!!!cp ('t82'); |
| 4265 |
!!!parse-error (type => 'not first start tag'); |
!!!parse-error (type => 'not first start tag', token => $token); |
| 4266 |
my $top_el = $self->{open_elements}->[0]->[0]; |
my $top_el = $self->{open_elements}->[0]->[0]; |
| 4267 |
for my $attr_name (keys %{$token->{attributes}}) { |
for my $attr_name (keys %{$token->{attributes}}) { |
| 4268 |
unless ($top_el->has_attribute_ns (undef, $attr_name)) { |
unless ($top_el->has_attribute_ns (undef, $attr_name)) { |
| 4272 |
$token->{attributes}->{$attr_name}->{value}); |
$token->{attributes}->{$attr_name}->{value}); |
| 4273 |
} |
} |
| 4274 |
} |
} |
| 4275 |
|
!!!nack ('t84.1'); |
| 4276 |
!!!next-token; |
!!!next-token; |
| 4277 |
redo B; |
next B; |
| 4278 |
} elsif ($token->{type} == COMMENT_TOKEN) { |
} elsif ($token->{type} == COMMENT_TOKEN) { |
| 4279 |
my $comment = $self->{document}->create_comment ($token->{data}); |
my $comment = $self->{document}->create_comment ($token->{data}); |
| 4280 |
if ($self->{insertion_mode} & AFTER_HTML_IMS) { |
if ($self->{insertion_mode} & AFTER_HTML_IMS) { |
| 4288 |
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
| 4289 |
} |
} |
| 4290 |
!!!next-token; |
!!!next-token; |
| 4291 |
redo B; |
next B; |
| 4292 |
} elsif ($self->{insertion_mode} & HEAD_IMS) { |
} elsif ($self->{insertion_mode} & IN_FOREIGN_CONTENT_IM) { |
| 4293 |
|
if ($token->{type} == CHARACTER_TOKEN) { |
| 4294 |
|
!!!cp ('t87.1'); |
| 4295 |
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
| 4296 |
|
!!!next-token; |
| 4297 |
|
next B; |
| 4298 |
|
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 4299 |
|
if ((not {mglyph => 1, malignmark => 1}->{$token->{tag_name}} and |
| 4300 |
|
$self->{open_elements}->[-1]->[1] & FOREIGN_FLOW_CONTENT_EL) or |
| 4301 |
|
not ($self->{open_elements}->[-1]->[1] & FOREIGN_EL) or |
| 4302 |
|
($token->{tag_name} eq 'svg' and |
| 4303 |
|
$self->{open_elements}->[-1]->[1] & MML_AXML_EL)) { |
| 4304 |
|
## NOTE: "using the rules for secondary insertion mode"then"continue" |
| 4305 |
|
!!!cp ('t87.2'); |
| 4306 |
|
# |
| 4307 |
|
} elsif ({ |
| 4308 |
|
b => 1, big => 1, blockquote => 1, body => 1, br => 1, |
| 4309 |
|
center => 1, code => 1, dd => 1, div => 1, dl => 1, dt => 1, |
| 4310 |
|
em => 1, embed => 1, font => 1, h1 => 1, h2 => 1, h3 => 1, |
| 4311 |
|
h4 => 1, h5 => 1, h6 => 1, head => 1, hr => 1, i => 1, |
| 4312 |
|
img => 1, li => 1, listing => 1, menu => 1, meta => 1, |
| 4313 |
|
nobr => 1, ol => 1, p => 1, pre => 1, ruby => 1, s => 1, |
| 4314 |
|
small => 1, span => 1, strong => 1, strike => 1, sub => 1, |
| 4315 |
|
sup => 1, table => 1, tt => 1, u => 1, ul => 1, var => 1, |
| 4316 |
|
}->{$token->{tag_name}}) { |
| 4317 |
|
!!!cp ('t87.2'); |
| 4318 |
|
!!!parse-error (type => 'not closed', |
| 4319 |
|
text => $self->{open_elements}->[-1]->[0] |
| 4320 |
|
->manakai_local_name, |
| 4321 |
|
token => $token); |
| 4322 |
|
|
| 4323 |
|
pop @{$self->{open_elements}} |
| 4324 |
|
while $self->{open_elements}->[-1]->[1] & FOREIGN_EL; |
| 4325 |
|
|
| 4326 |
|
$self->{insertion_mode} &= ~ IN_FOREIGN_CONTENT_IM; |
| 4327 |
|
## Reprocess. |
| 4328 |
|
next B; |
| 4329 |
|
} else { |
| 4330 |
|
my $nsuri = $self->{open_elements}->[-1]->[0]->namespace_uri; |
| 4331 |
|
my $tag_name = $token->{tag_name}; |
| 4332 |
|
if ($nsuri eq $SVG_NS) { |
| 4333 |
|
$tag_name = { |
| 4334 |
|
altglyph => 'altGlyph', |
| 4335 |
|
altglyphdef => 'altGlyphDef', |
| 4336 |
|
altglyphitem => 'altGlyphItem', |
| 4337 |
|
animatecolor => 'animateColor', |
| 4338 |
|
animatemotion => 'animateMotion', |
| 4339 |
|
animatetransform => 'animateTransform', |
| 4340 |
|
clippath => 'clipPath', |
| 4341 |
|
feblend => 'feBlend', |
| 4342 |
|
fecolormatrix => 'feColorMatrix', |
| 4343 |
|
fecomponenttransfer => 'feComponentTransfer', |
| 4344 |
|
fecomposite => 'feComposite', |
| 4345 |
|
feconvolvematrix => 'feConvolveMatrix', |
| 4346 |
|
fediffuselighting => 'feDiffuseLighting', |
| 4347 |
|
fedisplacementmap => 'feDisplacementMap', |
| 4348 |
|
fedistantlight => 'feDistantLight', |
| 4349 |
|
feflood => 'feFlood', |
| 4350 |
|
fefunca => 'feFuncA', |
| 4351 |
|
fefuncb => 'feFuncB', |
| 4352 |
|
fefuncg => 'feFuncG', |
| 4353 |
|
fefuncr => 'feFuncR', |
| 4354 |
|
fegaussianblur => 'feGaussianBlur', |
| 4355 |
|
feimage => 'feImage', |
| 4356 |
|
femerge => 'feMerge', |
| 4357 |
|
femergenode => 'feMergeNode', |
| 4358 |
|
femorphology => 'feMorphology', |
| 4359 |
|
feoffset => 'feOffset', |
| 4360 |
|
fepointlight => 'fePointLight', |
| 4361 |
|
fespecularlighting => 'feSpecularLighting', |
| 4362 |
|
fespotlight => 'feSpotLight', |
| 4363 |
|
fetile => 'feTile', |
| 4364 |
|
feturbulence => 'feTurbulence', |
| 4365 |
|
foreignobject => 'foreignObject', |
| 4366 |
|
glyphref => 'glyphRef', |
| 4367 |
|
lineargradient => 'linearGradient', |
| 4368 |
|
radialgradient => 'radialGradient', |
| 4369 |
|
#solidcolor => 'solidColor', ## NOTE: Commented in spec (SVG1.2) |
| 4370 |
|
textpath => 'textPath', |
| 4371 |
|
}->{$tag_name} || $tag_name; |
| 4372 |
|
} |
| 4373 |
|
|
| 4374 |
|
## "adjust SVG attributes" (SVG only) - done in insert-element-f |
| 4375 |
|
|
| 4376 |
|
## "adjust foreign attributes" - done in insert-element-f |
| 4377 |
|
|
| 4378 |
|
!!!insert-element-f ($nsuri, $tag_name, $token->{attributes}, $token); |
| 4379 |
|
|
| 4380 |
|
if ($self->{self_closing}) { |
| 4381 |
|
pop @{$self->{open_elements}}; |
| 4382 |
|
!!!ack ('t87.3'); |
| 4383 |
|
} else { |
| 4384 |
|
!!!cp ('t87.4'); |
| 4385 |
|
} |
| 4386 |
|
|
| 4387 |
|
!!!next-token; |
| 4388 |
|
next B; |
| 4389 |
|
} |
| 4390 |
|
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 4391 |
|
## NOTE: "using the rules for secondary insertion mode" then "continue" |
| 4392 |
|
!!!cp ('t87.5'); |
| 4393 |
|
# |
| 4394 |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 4395 |
|
!!!cp ('t87.6'); |
| 4396 |
|
!!!parse-error (type => 'not closed', |
| 4397 |
|
text => $self->{open_elements}->[-1]->[0] |
| 4398 |
|
->manakai_local_name, |
| 4399 |
|
token => $token); |
| 4400 |
|
|
| 4401 |
|
pop @{$self->{open_elements}} |
| 4402 |
|
while $self->{open_elements}->[-1]->[1] & FOREIGN_EL; |
| 4403 |
|
|
| 4404 |
|
$self->{insertion_mode} &= ~ IN_FOREIGN_CONTENT_IM; |
| 4405 |
|
## Reprocess. |
| 4406 |
|
next B; |
| 4407 |
|
} else { |
| 4408 |
|
die "$0: $token->{type}: Unknown token type"; |
| 4409 |
|
} |
| 4410 |
|
} |
| 4411 |
|
|
| 4412 |
|
if ($self->{insertion_mode} & HEAD_IMS) { |
| 4413 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 4414 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 4415 |
unless ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
unless ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4419 |
!!!cp ('t88.1'); |
!!!cp ('t88.1'); |
| 4420 |
## Ignore the token. |
## Ignore the token. |
| 4421 |
!!!next-token; |
!!!next-token; |
| 4422 |
redo B; |
next B; |
| 4423 |
} |
} |
| 4424 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 4425 |
!!!cp ('t88'); |
!!!cp ('t88'); |
| 4426 |
!!!next-token; |
!!!next-token; |
| 4427 |
redo B; |
next B; |
| 4428 |
} |
} |
| 4429 |
} |
} |
| 4430 |
|
|
| 4431 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4432 |
!!!cp ('t89'); |
!!!cp ('t89'); |
| 4433 |
## As if <head> |
## As if <head> |
| 4434 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
| 4435 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 4436 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, |
| 4437 |
|
[$self->{head_element}, $el_category->{head}]; |
| 4438 |
|
|
| 4439 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4440 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4444 |
!!!cp ('t90'); |
!!!cp ('t90'); |
| 4445 |
## As if </noscript> |
## As if </noscript> |
| 4446 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4447 |
!!!parse-error (type => 'in noscript:#character'); |
!!!parse-error (type => 'in noscript:#text', token => $token); |
| 4448 |
|
|
| 4449 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4450 |
## As if </head> |
## As if </head> |
| 4460 |
!!!cp ('t92'); |
!!!cp ('t92'); |
| 4461 |
} |
} |
| 4462 |
|
|
| 4463 |
## "after head" insertion mode |
## "after head" insertion mode |
| 4464 |
## As if <body> |
## As if <body> |
| 4465 |
!!!insert-element ('body'); |
!!!insert-element ('body',, $token); |
| 4466 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 4467 |
## reprocess |
## reprocess |
| 4468 |
redo B; |
next B; |
| 4469 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 4470 |
if ($token->{tag_name} eq 'head') { |
if ($token->{tag_name} eq 'head') { |
| 4471 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4472 |
!!!cp ('t93'); |
!!!cp ('t93'); |
| 4473 |
!!!create-element ($self->{head_element}, $token->{tag_name}, $token->{attributes}); |
!!!create-element ($self->{head_element}, $HTML_NS, $token->{tag_name}, $token->{attributes}, $token); |
| 4474 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child |
| 4475 |
push @{$self->{open_elements}}, [$self->{head_element}, $token->{tag_name}]; |
($self->{head_element}); |
| 4476 |
$self->{insertion_mode} = IN_HEAD_IM; |
push @{$self->{open_elements}}, |
| 4477 |
!!!next-token; |
[$self->{head_element}, $el_category->{head}]; |
| 4478 |
redo B; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4479 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
!!!nack ('t93.1'); |
| 4480 |
!!!cp ('t94'); |
!!!next-token; |
| 4481 |
# |
next B; |
| 4482 |
} else { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4483 |
!!!cp ('t95'); |
!!!cp ('t93.2'); |
| 4484 |
!!!parse-error (type => 'in head:head'); # or in head noscript |
!!!parse-error (type => 'after head', text => 'head', |
| 4485 |
## Ignore the token |
token => $token); |
| 4486 |
!!!next-token; |
## Ignore the token |
| 4487 |
redo B; |
!!!nack ('t93.3'); |
| 4488 |
} |
!!!next-token; |
| 4489 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
next B; |
| 4490 |
!!!cp ('t96'); |
} else { |
| 4491 |
## As if <head> |
!!!cp ('t95'); |
| 4492 |
!!!create-element ($self->{head_element}, 'head'); |
!!!parse-error (type => 'in head:head', |
| 4493 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
token => $token); # or in head noscript |
| 4494 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
## Ignore the token |
| 4495 |
|
!!!nack ('t95.1'); |
| 4496 |
|
!!!next-token; |
| 4497 |
|
next B; |
| 4498 |
|
} |
| 4499 |
|
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4500 |
|
!!!cp ('t96'); |
| 4501 |
|
## As if <head> |
| 4502 |
|
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
| 4503 |
|
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 4504 |
|
push @{$self->{open_elements}}, |
| 4505 |
|
[$self->{head_element}, $el_category->{head}]; |
| 4506 |
|
|
| 4507 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4508 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4509 |
} else { |
} else { |
| 4510 |
!!!cp ('t97'); |
!!!cp ('t97'); |
| 4511 |
} |
} |
| 4512 |
|
|
| 4513 |
if ($token->{tag_name} eq 'base') { |
if ($token->{tag_name} eq 'base') { |
| 4514 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4515 |
!!!cp ('t98'); |
!!!cp ('t98'); |
| 4516 |
## As if </noscript> |
## As if </noscript> |
| 4517 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4518 |
!!!parse-error (type => 'in noscript:base'); |
!!!parse-error (type => 'in noscript', text => 'base', |
| 4519 |
|
token => $token); |
| 4520 |
|
|
| 4521 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4522 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4527 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4528 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4529 |
!!!cp ('t100'); |
!!!cp ('t100'); |
| 4530 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head', |
| 4531 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
text => $token->{tag_name}, token => $token); |
| 4532 |
|
push @{$self->{open_elements}}, |
| 4533 |
|
[$self->{head_element}, $el_category->{head}]; |
| 4534 |
} else { |
} else { |
| 4535 |
!!!cp ('t101'); |
!!!cp ('t101'); |
| 4536 |
} |
} |
| 4537 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 4538 |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 4539 |
pop @{$self->{open_elements}} # <head> |
pop @{$self->{open_elements}} # <head> |
| 4540 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 4541 |
|
!!!nack ('t101.1'); |
| 4542 |
!!!next-token; |
!!!next-token; |
| 4543 |
redo B; |
next B; |
| 4544 |
} elsif ($token->{tag_name} eq 'link') { |
} elsif ($token->{tag_name} eq 'link') { |
| 4545 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4546 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4547 |
!!!cp ('t102'); |
!!!cp ('t102'); |
| 4548 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head', |
| 4549 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
text => $token->{tag_name}, token => $token); |
| 4550 |
|
push @{$self->{open_elements}}, |
| 4551 |
|
[$self->{head_element}, $el_category->{head}]; |
| 4552 |
} else { |
} else { |
| 4553 |
!!!cp ('t103'); |
!!!cp ('t103'); |
| 4554 |
} |
} |
| 4555 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 4556 |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 4557 |
pop @{$self->{open_elements}} # <head> |
pop @{$self->{open_elements}} # <head> |
| 4558 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 4559 |
|
!!!ack ('t103.1'); |
| 4560 |
!!!next-token; |
!!!next-token; |
| 4561 |
redo B; |
next B; |
| 4562 |
} elsif ($token->{tag_name} eq 'meta') { |
} elsif ($token->{tag_name} eq 'meta') { |
| 4563 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4564 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4565 |
!!!cp ('t104'); |
!!!cp ('t104'); |
| 4566 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head', |
| 4567 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
text => $token->{tag_name}, token => $token); |
| 4568 |
|
push @{$self->{open_elements}}, |
| 4569 |
|
[$self->{head_element}, $el_category->{head}]; |
| 4570 |
} else { |
} else { |
| 4571 |
!!!cp ('t105'); |
!!!cp ('t105'); |
| 4572 |
} |
} |
| 4573 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 4574 |
my $meta_el = pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
my $meta_el = pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 4575 |
|
|
| 4576 |
unless ($self->{confident}) { |
unless ($self->{confident}) { |
| 4577 |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
if ($token->{attributes}->{charset}) { |
| 4578 |
!!!cp ('t106'); |
!!!cp ('t106'); |
| 4579 |
|
## NOTE: Whether the encoding is supported or not is handled |
| 4580 |
|
## in the {change_encoding} callback. |
| 4581 |
$self->{change_encoding} |
$self->{change_encoding} |
| 4582 |
->($self, $token->{attributes}->{charset}->{value}); |
->($self, $token->{attributes}->{charset}->{value}, |
| 4583 |
|
$token); |
| 4584 |
|
|
| 4585 |
$meta_el->[0]->get_attribute_node_ns (undef, 'charset') |
$meta_el->[0]->get_attribute_node_ns (undef, 'charset') |
| 4586 |
->set_user_data (manakai_has_reference => |
->set_user_data (manakai_has_reference => |
| 4587 |
$token->{attributes}->{charset} |
$token->{attributes}->{charset} |
| 4588 |
->{has_reference}); |
->{has_reference}); |
| 4589 |
} elsif ($token->{attributes}->{content}) { |
} elsif ($token->{attributes}->{content}) { |
|
## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition. |
|
| 4590 |
if ($token->{attributes}->{content}->{value} |
if ($token->{attributes}->{content}->{value} |
| 4591 |
=~ /\A[^;]*;[\x09-\x0D\x20]*[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
=~ /[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
| 4592 |
[\x09-\x0D\x20]*= |
[\x09-\x0D\x20]*= |
| 4593 |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
| 4594 |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20\x3B]*))/x) { |
| 4595 |
!!!cp ('t107'); |
!!!cp ('t107'); |
| 4596 |
|
## NOTE: Whether the encoding is supported or not is handled |
| 4597 |
|
## in the {change_encoding} callback. |
| 4598 |
$self->{change_encoding} |
$self->{change_encoding} |
| 4599 |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3); |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3, |
| 4600 |
|
$token); |
| 4601 |
$meta_el->[0]->get_attribute_node_ns (undef, 'content') |
$meta_el->[0]->get_attribute_node_ns (undef, 'content') |
| 4602 |
->set_user_data (manakai_has_reference => |
->set_user_data (manakai_has_reference => |
| 4603 |
$token->{attributes}->{content} |
$token->{attributes}->{content} |
| 4625 |
|
|
| 4626 |
pop @{$self->{open_elements}} # <head> |
pop @{$self->{open_elements}} # <head> |
| 4627 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 4628 |
|
!!!ack ('t110.1'); |
| 4629 |
!!!next-token; |
!!!next-token; |
| 4630 |
redo B; |
next B; |
| 4631 |
} elsif ($token->{tag_name} eq 'title') { |
} elsif ($token->{tag_name} eq 'title') { |
| 4632 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4633 |
!!!cp ('t111'); |
!!!cp ('t111'); |
| 4634 |
## As if </noscript> |
## As if </noscript> |
| 4635 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4636 |
!!!parse-error (type => 'in noscript:title'); |
!!!parse-error (type => 'in noscript', text => 'title', |
| 4637 |
|
token => $token); |
| 4638 |
|
|
| 4639 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4640 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4641 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4642 |
!!!cp ('t112'); |
!!!cp ('t112'); |
| 4643 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head', |
| 4644 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
text => $token->{tag_name}, token => $token); |
| 4645 |
|
push @{$self->{open_elements}}, |
| 4646 |
|
[$self->{head_element}, $el_category->{head}]; |
| 4647 |
} else { |
} else { |
| 4648 |
!!!cp ('t113'); |
!!!cp ('t113'); |
| 4649 |
} |
} |
| 4654 |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
| 4655 |
pop @{$self->{open_elements}} # <head> |
pop @{$self->{open_elements}} # <head> |
| 4656 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 4657 |
redo B; |
next B; |
| 4658 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($token->{tag_name} eq 'style' or |
| 4659 |
|
$token->{tag_name} eq 'noframes') { |
| 4660 |
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
| 4661 |
## insertion mode IN_HEAD_IM) |
## insertion mode IN_HEAD_IM) |
| 4662 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 4663 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4664 |
!!!cp ('t114'); |
!!!cp ('t114'); |
| 4665 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head', |
| 4666 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
text => $token->{tag_name}, token => $token); |
| 4667 |
|
push @{$self->{open_elements}}, |
| 4668 |
|
[$self->{head_element}, $el_category->{head}]; |
| 4669 |
} else { |
} else { |
| 4670 |
!!!cp ('t115'); |
!!!cp ('t115'); |
| 4671 |
} |
} |
| 4672 |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 4673 |
pop @{$self->{open_elements}} # <head> |
pop @{$self->{open_elements}} # <head> |
| 4674 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 4675 |
redo B; |
next B; |
| 4676 |
} elsif ($token->{tag_name} eq 'noscript') { |
} elsif ($token->{tag_name} eq 'noscript') { |
| 4677 |
if ($self->{insertion_mode} == IN_HEAD_IM) { |
if ($self->{insertion_mode} == IN_HEAD_IM) { |
| 4678 |
!!!cp ('t116'); |
!!!cp ('t116'); |
| 4679 |
## NOTE: and scripting is disalbed |
## NOTE: and scripting is disalbed |
| 4680 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 4681 |
$self->{insertion_mode} = IN_HEAD_NOSCRIPT_IM; |
$self->{insertion_mode} = IN_HEAD_NOSCRIPT_IM; |
| 4682 |
|
!!!nack ('t116.1'); |
| 4683 |
!!!next-token; |
!!!next-token; |
| 4684 |
redo B; |
next B; |
| 4685 |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4686 |
!!!cp ('t117'); |
!!!cp ('t117'); |
| 4687 |
!!!parse-error (type => 'in noscript:noscript'); |
!!!parse-error (type => 'in noscript', text => 'noscript', |
| 4688 |
|
token => $token); |
| 4689 |
## Ignore the token |
## Ignore the token |
| 4690 |
|
!!!nack ('t117.1'); |
| 4691 |
!!!next-token; |
!!!next-token; |
| 4692 |
redo B; |
next B; |
| 4693 |
} else { |
} else { |
| 4694 |
!!!cp ('t118'); |
!!!cp ('t118'); |
| 4695 |
# |
# |
| 4699 |
!!!cp ('t119'); |
!!!cp ('t119'); |
| 4700 |
## As if </noscript> |
## As if </noscript> |
| 4701 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4702 |
!!!parse-error (type => 'in noscript:script'); |
!!!parse-error (type => 'in noscript', text => 'script', |
| 4703 |
|
token => $token); |
| 4704 |
|
|
| 4705 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4706 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4707 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4708 |
!!!cp ('t120'); |
!!!cp ('t120'); |
| 4709 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
!!!parse-error (type => 'after head', |
| 4710 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
text => $token->{tag_name}, token => $token); |
| 4711 |
|
push @{$self->{open_elements}}, |
| 4712 |
|
[$self->{head_element}, $el_category->{head}]; |
| 4713 |
} else { |
} else { |
| 4714 |
!!!cp ('t121'); |
!!!cp ('t121'); |
| 4715 |
} |
} |
| 4718 |
$script_start_tag->(); |
$script_start_tag->(); |
| 4719 |
pop @{$self->{open_elements}} # <head> |
pop @{$self->{open_elements}} # <head> |
| 4720 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 4721 |
redo B; |
next B; |
| 4722 |
} elsif ($token->{tag_name} eq 'body' or |
} elsif ($token->{tag_name} eq 'body' or |
| 4723 |
$token->{tag_name} eq 'frameset') { |
$token->{tag_name} eq 'frameset') { |
| 4724 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4725 |
!!!cp ('t122'); |
!!!cp ('t122'); |
| 4726 |
## As if </noscript> |
## As if </noscript> |
| 4727 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4728 |
!!!parse-error (type => 'in noscript:'.$token->{tag_name}); |
!!!parse-error (type => 'in noscript', |
| 4729 |
|
text => $token->{tag_name}, token => $token); |
| 4730 |
|
|
| 4731 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4732 |
## As if </head> |
## As if </head> |
| 4743 |
} |
} |
| 4744 |
|
|
| 4745 |
## "after head" insertion mode |
## "after head" insertion mode |
| 4746 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 4747 |
if ($token->{tag_name} eq 'body') { |
if ($token->{tag_name} eq 'body') { |
| 4748 |
!!!cp ('t126'); |
!!!cp ('t126'); |
| 4749 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 4753 |
} else { |
} else { |
| 4754 |
die "$0: tag name: $self->{tag_name}"; |
die "$0: tag name: $self->{tag_name}"; |
| 4755 |
} |
} |
| 4756 |
|
!!!nack ('t127.1'); |
| 4757 |
!!!next-token; |
!!!next-token; |
| 4758 |
redo B; |
next B; |
| 4759 |
} else { |
} else { |
| 4760 |
!!!cp ('t128'); |
!!!cp ('t128'); |
| 4761 |
# |
# |
| 4765 |
!!!cp ('t129'); |
!!!cp ('t129'); |
| 4766 |
## As if </noscript> |
## As if </noscript> |
| 4767 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4768 |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}); |
!!!parse-error (type => 'in noscript:/', |
| 4769 |
|
text => $token->{tag_name}, token => $token); |
| 4770 |
|
|
| 4771 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4772 |
## As if </head> |
## As if </head> |
| 4785 |
|
|
| 4786 |
## "after head" insertion mode |
## "after head" insertion mode |
| 4787 |
## As if <body> |
## As if <body> |
| 4788 |
!!!insert-element ('body'); |
!!!insert-element ('body',, $token); |
| 4789 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 4790 |
## reprocess |
## reprocess |
| 4791 |
redo B; |
!!!ack-later; |
| 4792 |
|
next B; |
| 4793 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 4794 |
if ($token->{tag_name} eq 'head') { |
if ($token->{tag_name} eq 'head') { |
| 4795 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4796 |
!!!cp ('t132'); |
!!!cp ('t132'); |
| 4797 |
## As if <head> |
## As if <head> |
| 4798 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
| 4799 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 4800 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
push @{$self->{open_elements}}, |
| 4801 |
|
[$self->{head_element}, $el_category->{head}]; |
| 4802 |
|
|
| 4803 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4804 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4805 |
$self->{insertion_mode} = AFTER_HEAD_IM; |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4806 |
!!!next-token; |
!!!next-token; |
| 4807 |
redo B; |
next B; |
| 4808 |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4809 |
!!!cp ('t133'); |
!!!cp ('t133'); |
| 4810 |
## As if </noscript> |
## As if </noscript> |
| 4811 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4812 |
!!!parse-error (type => 'in noscript:/head'); |
!!!parse-error (type => 'in noscript:/', |
| 4813 |
|
text => 'head', token => $token); |
| 4814 |
|
|
| 4815 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4816 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4817 |
$self->{insertion_mode} = AFTER_HEAD_IM; |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4818 |
!!!next-token; |
!!!next-token; |
| 4819 |
redo B; |
next B; |
| 4820 |
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 4821 |
!!!cp ('t134'); |
!!!cp ('t134'); |
| 4822 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4823 |
$self->{insertion_mode} = AFTER_HEAD_IM; |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4824 |
!!!next-token; |
!!!next-token; |
| 4825 |
redo B; |
next B; |
| 4826 |
|
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4827 |
|
!!!cp ('t134.1'); |
| 4828 |
|
!!!parse-error (type => 'unmatched end tag', text => 'head', |
| 4829 |
|
token => $token); |
| 4830 |
|
## Ignore the token |
| 4831 |
|
!!!next-token; |
| 4832 |
|
next B; |
| 4833 |
} else { |
} else { |
| 4834 |
!!!cp ('t135'); |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
|
# |
|
| 4835 |
} |
} |
| 4836 |
} elsif ($token->{tag_name} eq 'noscript') { |
} elsif ($token->{tag_name} eq 'noscript') { |
| 4837 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4839 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4840 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4841 |
!!!next-token; |
!!!next-token; |
| 4842 |
redo B; |
next B; |
| 4843 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM or |
| 4844 |
|
$self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4845 |
!!!cp ('t137'); |
!!!cp ('t137'); |
| 4846 |
!!!parse-error (type => 'unmatched end tag:noscript'); |
!!!parse-error (type => 'unmatched end tag', |
| 4847 |
|
text => 'noscript', token => $token); |
| 4848 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 4849 |
!!!next-token; |
!!!next-token; |
| 4850 |
redo B; |
next B; |
| 4851 |
} else { |
} else { |
| 4852 |
!!!cp ('t138'); |
!!!cp ('t138'); |
| 4853 |
# |
# |
| 4855 |
} elsif ({ |
} elsif ({ |
| 4856 |
body => 1, html => 1, |
body => 1, html => 1, |
| 4857 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 4858 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM or |
| 4859 |
!!!cp ('t139'); |
$self->{insertion_mode} == IN_HEAD_IM or |
| 4860 |
## As if <head> |
$self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
|
!!!create-element ($self->{head_element}, 'head'); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
|
|
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
|
|
|
|
|
$self->{insertion_mode} = IN_HEAD_IM; |
|
|
## Reprocess in the "in head" insertion mode... |
|
|
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
|
| 4861 |
!!!cp ('t140'); |
!!!cp ('t140'); |
| 4862 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 4863 |
|
text => $token->{tag_name}, token => $token); |
| 4864 |
## Ignore the token |
## Ignore the token |
| 4865 |
!!!next-token; |
!!!next-token; |
| 4866 |
redo B; |
next B; |
| 4867 |
|
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4868 |
|
!!!cp ('t140.1'); |
| 4869 |
|
!!!parse-error (type => 'unmatched end tag', |
| 4870 |
|
text => $token->{tag_name}, token => $token); |
| 4871 |
|
## Ignore the token |
| 4872 |
|
!!!next-token; |
| 4873 |
|
next B; |
| 4874 |
} else { |
} else { |
| 4875 |
!!!cp ('t141'); |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
| 4876 |
} |
} |
| 4877 |
|
} elsif ($token->{tag_name} eq 'p') { |
| 4878 |
# |
!!!cp ('t142'); |
| 4879 |
} elsif ({ |
!!!parse-error (type => 'unmatched end tag', |
| 4880 |
p => 1, br => 1, |
text => $token->{tag_name}, token => $token); |
| 4881 |
}->{$token->{tag_name}}) { |
## Ignore the token |
| 4882 |
|
!!!next-token; |
| 4883 |
|
next B; |
| 4884 |
|
} elsif ($token->{tag_name} eq 'br') { |
| 4885 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4886 |
!!!cp ('t142'); |
!!!cp ('t142.2'); |
| 4887 |
## As if <head> |
## (before head) as if <head>, (in head) as if </head> |
| 4888 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
| 4889 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 4890 |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4891 |
|
|
| 4892 |
|
## Reprocess in the "after head" insertion mode... |
| 4893 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 4894 |
|
!!!cp ('t143.2'); |
| 4895 |
|
## As if </head> |
| 4896 |
|
pop @{$self->{open_elements}}; |
| 4897 |
|
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4898 |
|
|
| 4899 |
|
## Reprocess in the "after head" insertion mode... |
| 4900 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4901 |
|
!!!cp ('t143.3'); |
| 4902 |
|
## ISSUE: Two parse errors for <head><noscript></br> |
| 4903 |
|
!!!parse-error (type => 'unmatched end tag', |
| 4904 |
|
text => 'br', token => $token); |
| 4905 |
|
## As if </noscript> |
| 4906 |
|
pop @{$self->{open_elements}}; |
| 4907 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 4908 |
|
|
| 4909 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4910 |
} else { |
## As if </head> |
| 4911 |
!!!cp ('t143'); |
pop @{$self->{open_elements}}; |
| 4912 |
} |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 4913 |
|
|
| 4914 |
# |
## Reprocess in the "after head" insertion mode... |
| 4915 |
} else { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 4916 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
!!!cp ('t143.4'); |
|
!!!cp ('t144'); |
|
| 4917 |
# |
# |
| 4918 |
} else { |
} else { |
| 4919 |
!!!cp ('t145'); |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
| 4920 |
} |
} |
| 4921 |
|
|
| 4922 |
|
## ISSUE: does not agree with IE7 - it doesn't ignore </br>. |
| 4923 |
|
!!!parse-error (type => 'unmatched end tag', |
| 4924 |
|
text => 'br', token => $token); |
| 4925 |
|
## Ignore the token |
| 4926 |
|
!!!next-token; |
| 4927 |
|
next B; |
| 4928 |
|
} else { |
| 4929 |
|
!!!cp ('t145'); |
| 4930 |
|
!!!parse-error (type => 'unmatched end tag', |
| 4931 |
|
text => $token->{tag_name}, token => $token); |
| 4932 |
|
## Ignore the token |
| 4933 |
|
!!!next-token; |
| 4934 |
|
next B; |
| 4935 |
} |
} |
| 4936 |
|
|
| 4937 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 4938 |
!!!cp ('t146'); |
!!!cp ('t146'); |
| 4939 |
## As if </noscript> |
## As if </noscript> |
| 4940 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4941 |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}); |
!!!parse-error (type => 'in noscript:/', |
| 4942 |
|
text => $token->{tag_name}, token => $token); |
| 4943 |
|
|
| 4944 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 4945 |
## As if </head> |
## As if </head> |
| 4955 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4956 |
## ISSUE: This case cannot be reached? |
## ISSUE: This case cannot be reached? |
| 4957 |
!!!cp ('t148'); |
!!!cp ('t148'); |
| 4958 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 4959 |
|
text => $token->{tag_name}, token => $token); |
| 4960 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 4961 |
!!!next-token; |
!!!next-token; |
| 4962 |
redo B; |
next B; |
| 4963 |
} else { |
} else { |
| 4964 |
!!!cp ('t149'); |
!!!cp ('t149'); |
| 4965 |
} |
} |
| 4966 |
|
|
| 4967 |
## "after head" insertion mode |
## "after head" insertion mode |
| 4968 |
## As if <body> |
## As if <body> |
| 4969 |
!!!insert-element ('body'); |
!!!insert-element ('body',, $token); |
| 4970 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 4971 |
## reprocess |
## reprocess |
| 4972 |
redo B; |
next B; |
| 4973 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 4974 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 4975 |
!!!cp ('t149.1'); |
!!!cp ('t149.1'); |
| 4976 |
|
|
| 4977 |
## NOTE: As if <head> |
## NOTE: As if <head> |
| 4978 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
| 4979 |
$self->{open_elements}->[-1]->[0]->append_child |
$self->{open_elements}->[-1]->[0]->append_child |
| 4980 |
($self->{head_element}); |
($self->{head_element}); |
| 4981 |
#push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
#push @{$self->{open_elements}}, |
| 4982 |
|
# [$self->{head_element}, $el_category->{head}]; |
| 4983 |
#$self->{insertion_mode} = IN_HEAD_IM; |
#$self->{insertion_mode} = IN_HEAD_IM; |
| 4984 |
## NOTE: Reprocess. |
## NOTE: Reprocess. |
| 4985 |
|
|
| 5001 |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 5002 |
!!!cp ('t149.3'); |
!!!cp ('t149.3'); |
| 5003 |
|
|
| 5004 |
!!!parse-error (type => 'in noscript:#eof'); |
!!!parse-error (type => 'in noscript:#eof', token => $token); |
| 5005 |
|
|
| 5006 |
## As if </noscript> |
## As if </noscript> |
| 5007 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5020 |
} |
} |
| 5021 |
|
|
| 5022 |
## NOTE: As if <body> |
## NOTE: As if <body> |
| 5023 |
!!!insert-element ('body'); |
!!!insert-element ('body',, $token); |
| 5024 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 5025 |
## NOTE: Reprocess. |
## NOTE: Reprocess. |
| 5026 |
redo B; |
next B; |
| 5027 |
} else { |
} else { |
| 5028 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 5029 |
} |
} |
| 5038 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
| 5039 |
|
|
| 5040 |
!!!next-token; |
!!!next-token; |
| 5041 |
redo B; |
next B; |
| 5042 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 5043 |
if ({ |
if ({ |
| 5044 |
caption => 1, col => 1, colgroup => 1, tbody => 1, |
caption => 1, col => 1, colgroup => 1, tbody => 1, |
| 5046 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5047 |
if ($self->{insertion_mode} == IN_CELL_IM) { |
if ($self->{insertion_mode} == IN_CELL_IM) { |
| 5048 |
## have an element in table scope |
## have an element in table scope |
| 5049 |
my $tn; |
for (reverse 0..$#{$self->{open_elements}}) { |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
| 5050 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5051 |
if ($node->[1] eq 'td' or $node->[1] eq 'th') { |
if ($node->[1] & TABLE_CELL_EL) { |
| 5052 |
!!!cp ('t151'); |
!!!cp ('t151'); |
| 5053 |
$tn = $node->[1]; |
|
| 5054 |
last INSCOPE; |
## Close the cell |
| 5055 |
} elsif ({ |
!!!back-token; # <x> |
| 5056 |
table => 1, html => 1, |
$token = {type => END_TAG_TOKEN, |
| 5057 |
}->{$node->[1]}) { |
tag_name => $node->[0]->manakai_local_name, |
| 5058 |
|
line => $token->{line}, |
| 5059 |
|
column => $token->{column}}; |
| 5060 |
|
next B; |
| 5061 |
|
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
| 5062 |
!!!cp ('t152'); |
!!!cp ('t152'); |
| 5063 |
last INSCOPE; |
## ISSUE: This case can never be reached, maybe. |
| 5064 |
|
last; |
| 5065 |
} |
} |
| 5066 |
} # INSCOPE |
} |
| 5067 |
unless (defined $tn) { |
|
| 5068 |
!!!cp ('t153'); |
!!!cp ('t153'); |
| 5069 |
## TODO: This error type is wrong. |
!!!parse-error (type => 'start tag not allowed', |
| 5070 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
text => $token->{tag_name}, token => $token); |
| 5071 |
## Ignore the token |
## Ignore the token |
| 5072 |
!!!next-token; |
!!!nack ('t153.1'); |
| 5073 |
redo B; |
!!!next-token; |
| 5074 |
} |
next B; |
|
|
|
|
!!!cp ('t154'); |
|
|
## Close the cell |
|
|
!!!back-token; # <?> |
|
|
$token = {type => END_TAG_TOKEN, tag_name => $tn}; |
|
|
redo B; |
|
| 5075 |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 5076 |
!!!parse-error (type => 'not closed:caption'); |
!!!parse-error (type => 'not closed', text => 'caption', |
| 5077 |
|
token => $token); |
| 5078 |
|
|
| 5079 |
## As if </caption> |
## NOTE: As if </caption>. |
| 5080 |
## have a table element in table scope |
## have a table element in table scope |
| 5081 |
my $i; |
my $i; |
| 5082 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: { |
| 5083 |
my $node = $self->{open_elements}->[$_]; |
for (reverse 0..$#{$self->{open_elements}}) { |
| 5084 |
if ($node->[1] eq 'caption') { |
my $node = $self->{open_elements}->[$_]; |
| 5085 |
!!!cp ('t155'); |
if ($node->[1] & CAPTION_EL) { |
| 5086 |
$i = $_; |
!!!cp ('t155'); |
| 5087 |
last INSCOPE; |
$i = $_; |
| 5088 |
} elsif ({ |
last INSCOPE; |
| 5089 |
table => 1, html => 1, |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
| 5090 |
}->{$node->[1]}) { |
!!!cp ('t156'); |
| 5091 |
!!!cp ('t156'); |
last; |
| 5092 |
last INSCOPE; |
} |
| 5093 |
} |
} |
| 5094 |
|
|
| 5095 |
|
!!!cp ('t157'); |
| 5096 |
|
!!!parse-error (type => 'start tag not allowed', |
| 5097 |
|
text => $token->{tag_name}, token => $token); |
| 5098 |
|
## Ignore the token |
| 5099 |
|
!!!nack ('t157.1'); |
| 5100 |
|
!!!next-token; |
| 5101 |
|
next B; |
| 5102 |
} # INSCOPE |
} # INSCOPE |
|
unless (defined $i) { |
|
|
!!!cp ('t157'); |
|
|
## TODO: this type is wrong. |
|
|
!!!parse-error (type => 'unmatched end tag:caption'); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
| 5103 |
|
|
| 5104 |
## generate implied end tags |
## generate implied end tags |
| 5105 |
while ({ |
while ($self->{open_elements}->[-1]->[1] |
| 5106 |
dd => 1, dt => 1, li => 1, p => 1, |
& END_TAG_OPTIONAL_EL) { |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 5107 |
!!!cp ('t158'); |
!!!cp ('t158'); |
| 5108 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5109 |
} |
} |
| 5110 |
|
|
| 5111 |
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
| 5112 |
!!!cp ('t159'); |
!!!cp ('t159'); |
| 5113 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed', |
| 5114 |
|
text => $self->{open_elements}->[-1]->[0] |
| 5115 |
|
->manakai_local_name, |
| 5116 |
|
token => $token); |
| 5117 |
} else { |
} else { |
| 5118 |
!!!cp ('t160'); |
!!!cp ('t160'); |
| 5119 |
} |
} |
| 5125 |
$self->{insertion_mode} = IN_TABLE_IM; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 5126 |
|
|
| 5127 |
## reprocess |
## reprocess |
| 5128 |
redo B; |
!!!ack-later; |
| 5129 |
|
next B; |
| 5130 |
} else { |
} else { |
| 5131 |
!!!cp ('t161'); |
!!!cp ('t161'); |
| 5132 |
# |
# |
| 5142 |
my $i; |
my $i; |
| 5143 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5144 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5145 |
if ($node->[1] eq $token->{tag_name}) { |
if ($node->[0]->manakai_local_name eq $token->{tag_name}) { |
| 5146 |
!!!cp ('t163'); |
!!!cp ('t163'); |
| 5147 |
$i = $_; |
$i = $_; |
| 5148 |
last INSCOPE; |
last INSCOPE; |
| 5149 |
} elsif ({ |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
| 5150 |
!!!cp ('t164'); |
!!!cp ('t164'); |
| 5151 |
last INSCOPE; |
last INSCOPE; |
| 5152 |
} |
} |
| 5153 |
} # INSCOPE |
} # INSCOPE |
| 5154 |
unless (defined $i) { |
unless (defined $i) { |
| 5155 |
!!!cp ('t165'); |
!!!cp ('t165'); |
| 5156 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 5157 |
|
text => $token->{tag_name}, |
| 5158 |
|
token => $token); |
| 5159 |
## Ignore the token |
## Ignore the token |
| 5160 |
!!!next-token; |
!!!next-token; |
| 5161 |
redo B; |
next B; |
| 5162 |
} |
} |
| 5163 |
|
|
| 5164 |
## generate implied end tags |
## generate implied end tags |
| 5165 |
while ({ |
while ($self->{open_elements}->[-1]->[1] |
| 5166 |
dd => 1, dt => 1, li => 1, p => 1, |
& END_TAG_OPTIONAL_EL) { |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 5167 |
!!!cp ('t166'); |
!!!cp ('t166'); |
| 5168 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5169 |
} |
} |
| 5170 |
|
|
| 5171 |
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
if ($self->{open_elements}->[-1]->[0]->manakai_local_name |
| 5172 |
|
ne $token->{tag_name}) { |
| 5173 |
!!!cp ('t167'); |
!!!cp ('t167'); |
| 5174 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed', |
| 5175 |
|
text => $self->{open_elements}->[-1]->[0] |
| 5176 |
|
->manakai_local_name, |
| 5177 |
|
token => $token); |
| 5178 |
} else { |
} else { |
| 5179 |
!!!cp ('t168'); |
!!!cp ('t168'); |
| 5180 |
} |
} |
| 5186 |
$self->{insertion_mode} = IN_ROW_IM; |
$self->{insertion_mode} = IN_ROW_IM; |
| 5187 |
|
|
| 5188 |
!!!next-token; |
!!!next-token; |
| 5189 |
redo B; |
next B; |
| 5190 |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 5191 |
!!!cp ('t169'); |
!!!cp ('t169'); |
| 5192 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 5193 |
|
text => $token->{tag_name}, token => $token); |
| 5194 |
## Ignore the token |
## Ignore the token |
| 5195 |
!!!next-token; |
!!!next-token; |
| 5196 |
redo B; |
next B; |
| 5197 |
} else { |
} else { |
| 5198 |
!!!cp ('t170'); |
!!!cp ('t170'); |
| 5199 |
# |
# |
| 5202 |
if ($self->{insertion_mode} == IN_CAPTION_IM) { |
if ($self->{insertion_mode} == IN_CAPTION_IM) { |
| 5203 |
## have a table element in table scope |
## have a table element in table scope |
| 5204 |
my $i; |
my $i; |
| 5205 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: { |
| 5206 |
my $node = $self->{open_elements}->[$_]; |
for (reverse 0..$#{$self->{open_elements}}) { |
| 5207 |
if ($node->[1] eq $token->{tag_name}) { |
my $node = $self->{open_elements}->[$_]; |
| 5208 |
!!!cp ('t171'); |
if ($node->[1] & CAPTION_EL) { |
| 5209 |
$i = $_; |
!!!cp ('t171'); |
| 5210 |
last INSCOPE; |
$i = $_; |
| 5211 |
} elsif ({ |
last INSCOPE; |
| 5212 |
table => 1, html => 1, |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
| 5213 |
}->{$node->[1]}) { |
!!!cp ('t172'); |
| 5214 |
!!!cp ('t172'); |
last; |
| 5215 |
last INSCOPE; |
} |
| 5216 |
} |
} |
| 5217 |
|
|
| 5218 |
|
!!!cp ('t173'); |
| 5219 |
|
!!!parse-error (type => 'unmatched end tag', |
| 5220 |
|
text => $token->{tag_name}, token => $token); |
| 5221 |
|
## Ignore the token |
| 5222 |
|
!!!next-token; |
| 5223 |
|
next B; |
| 5224 |
} # INSCOPE |
} # INSCOPE |
|
unless (defined $i) { |
|
|
!!!cp ('t173'); |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
| 5225 |
|
|
| 5226 |
## generate implied end tags |
## generate implied end tags |
| 5227 |
while ({ |
while ($self->{open_elements}->[-1]->[1] |
| 5228 |
dd => 1, dt => 1, li => 1, p => 1, |
& END_TAG_OPTIONAL_EL) { |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 5229 |
!!!cp ('t174'); |
!!!cp ('t174'); |
| 5230 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5231 |
} |
} |
| 5232 |
|
|
| 5233 |
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
| 5234 |
!!!cp ('t175'); |
!!!cp ('t175'); |
| 5235 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed', |
| 5236 |
|
text => $self->{open_elements}->[-1]->[0] |
| 5237 |
|
->manakai_local_name, |
| 5238 |
|
token => $token); |
| 5239 |
} else { |
} else { |
| 5240 |
!!!cp ('t176'); |
!!!cp ('t176'); |
| 5241 |
} |
} |
| 5247 |
$self->{insertion_mode} = IN_TABLE_IM; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 5248 |
|
|
| 5249 |
!!!next-token; |
!!!next-token; |
| 5250 |
redo B; |
next B; |
| 5251 |
} elsif ($self->{insertion_mode} == IN_CELL_IM) { |
} elsif ($self->{insertion_mode} == IN_CELL_IM) { |
| 5252 |
!!!cp ('t177'); |
!!!cp ('t177'); |
| 5253 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 5254 |
|
text => $token->{tag_name}, token => $token); |
| 5255 |
## Ignore the token |
## Ignore the token |
| 5256 |
!!!next-token; |
!!!next-token; |
| 5257 |
redo B; |
next B; |
| 5258 |
} else { |
} else { |
| 5259 |
!!!cp ('t178'); |
!!!cp ('t178'); |
| 5260 |
# |
# |
| 5267 |
## have an element in table scope |
## have an element in table scope |
| 5268 |
my $i; |
my $i; |
| 5269 |
my $tn; |
my $tn; |
| 5270 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: { |
| 5271 |
my $node = $self->{open_elements}->[$_]; |
for (reverse 0..$#{$self->{open_elements}}) { |
| 5272 |
if ($node->[1] eq $token->{tag_name}) { |
my $node = $self->{open_elements}->[$_]; |
| 5273 |
!!!cp ('t179'); |
if ($node->[0]->manakai_local_name eq $token->{tag_name}) { |
| 5274 |
$i = $_; |
!!!cp ('t179'); |
| 5275 |
last INSCOPE; |
$i = $_; |
| 5276 |
} elsif ($node->[1] eq 'td' or $node->[1] eq 'th') { |
|
| 5277 |
!!!cp ('t180'); |
## Close the cell |
| 5278 |
$tn = $node->[1]; |
!!!back-token; # </x> |
| 5279 |
## NOTE: There is exactly one |td| or |th| element |
$token = {type => END_TAG_TOKEN, tag_name => $tn, |
| 5280 |
## in scope in the stack of open elements by definition. |
line => $token->{line}, |
| 5281 |
} elsif ({ |
column => $token->{column}}; |
| 5282 |
table => 1, html => 1, |
next B; |
| 5283 |
}->{$node->[1]}) { |
} elsif ($node->[1] & TABLE_CELL_EL) { |
| 5284 |
!!!cp ('t181'); |
!!!cp ('t180'); |
| 5285 |
last INSCOPE; |
$tn = $node->[0]->manakai_local_name; |
| 5286 |
|
## NOTE: There is exactly one |td| or |th| element |
| 5287 |
|
## in scope in the stack of open elements by definition. |
| 5288 |
|
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
| 5289 |
|
## ISSUE: Can this be reached? |
| 5290 |
|
!!!cp ('t181'); |
| 5291 |
|
last; |
| 5292 |
|
} |
| 5293 |
} |
} |
| 5294 |
} # INSCOPE |
|
|
unless (defined $i) { |
|
| 5295 |
!!!cp ('t182'); |
!!!cp ('t182'); |
| 5296 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 5297 |
|
text => $token->{tag_name}, token => $token); |
| 5298 |
## Ignore the token |
## Ignore the token |
| 5299 |
!!!next-token; |
!!!next-token; |
| 5300 |
redo B; |
next B; |
| 5301 |
} else { |
} # INSCOPE |
|
!!!cp ('t183'); |
|
|
} |
|
|
|
|
|
## Close the cell |
|
|
!!!back-token; # </?> |
|
|
$token = {type => END_TAG_TOKEN, tag_name => $tn}; |
|
|
redo B; |
|
| 5302 |
} elsif ($token->{tag_name} eq 'table' and |
} elsif ($token->{tag_name} eq 'table' and |
| 5303 |
$self->{insertion_mode} == IN_CAPTION_IM) { |
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 5304 |
!!!parse-error (type => 'not closed:caption'); |
!!!parse-error (type => 'not closed', text => 'caption', |
| 5305 |
|
token => $token); |
| 5306 |
|
|
| 5307 |
## As if </caption> |
## As if </caption> |
| 5308 |
## have a table element in table scope |
## have a table element in table scope |
| 5309 |
my $i; |
my $i; |
| 5310 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5311 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5312 |
if ($node->[1] eq 'caption') { |
if ($node->[1] & CAPTION_EL) { |
| 5313 |
!!!cp ('t184'); |
!!!cp ('t184'); |
| 5314 |
$i = $_; |
$i = $_; |
| 5315 |
last INSCOPE; |
last INSCOPE; |
| 5316 |
} elsif ({ |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
| 5317 |
!!!cp ('t185'); |
!!!cp ('t185'); |
| 5318 |
last INSCOPE; |
last INSCOPE; |
| 5319 |
} |
} |
| 5320 |
} # INSCOPE |
} # INSCOPE |
| 5321 |
unless (defined $i) { |
unless (defined $i) { |
| 5322 |
!!!cp ('t186'); |
!!!cp ('t186'); |
| 5323 |
!!!parse-error (type => 'unmatched end tag:caption'); |
!!!parse-error (type => 'unmatched end tag', |
| 5324 |
|
text => 'caption', token => $token); |
| 5325 |
## Ignore the token |
## Ignore the token |
| 5326 |
!!!next-token; |
!!!next-token; |
| 5327 |
redo B; |
next B; |
| 5328 |
} |
} |
| 5329 |
|
|
| 5330 |
## generate implied end tags |
## generate implied end tags |
| 5331 |
while ({ |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
|
dd => 1, dt => 1, li => 1, p => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 5332 |
!!!cp ('t187'); |
!!!cp ('t187'); |
| 5333 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5334 |
} |
} |
| 5335 |
|
|
| 5336 |
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
| 5337 |
!!!cp ('t188'); |
!!!cp ('t188'); |
| 5338 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed', |
| 5339 |
|
text => $self->{open_elements}->[-1]->[0] |
| 5340 |
|
->manakai_local_name, |
| 5341 |
|
token => $token); |
| 5342 |
} else { |
} else { |
| 5343 |
!!!cp ('t189'); |
!!!cp ('t189'); |
| 5344 |
} |
} |
| 5350 |
$self->{insertion_mode} = IN_TABLE_IM; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 5351 |
|
|
| 5352 |
## reprocess |
## reprocess |
| 5353 |
redo B; |
next B; |
| 5354 |
} elsif ({ |
} elsif ({ |
| 5355 |
body => 1, col => 1, colgroup => 1, html => 1, |
body => 1, col => 1, colgroup => 1, html => 1, |
| 5356 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5357 |
if ($self->{insertion_mode} & BODY_TABLE_IMS) { |
if ($self->{insertion_mode} & BODY_TABLE_IMS) { |
| 5358 |
!!!cp ('t190'); |
!!!cp ('t190'); |
| 5359 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 5360 |
|
text => $token->{tag_name}, token => $token); |
| 5361 |
## Ignore the token |
## Ignore the token |
| 5362 |
!!!next-token; |
!!!next-token; |
| 5363 |
redo B; |
next B; |
| 5364 |
} else { |
} else { |
| 5365 |
!!!cp ('t191'); |
!!!cp ('t191'); |
| 5366 |
# |
# |
| 5371 |
}->{$token->{tag_name}} and |
}->{$token->{tag_name}} and |
| 5372 |
$self->{insertion_mode} == IN_CAPTION_IM) { |
$self->{insertion_mode} == IN_CAPTION_IM) { |
| 5373 |
!!!cp ('t192'); |
!!!cp ('t192'); |
| 5374 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 5375 |
|
text => $token->{tag_name}, token => $token); |
| 5376 |
## Ignore the token |
## Ignore the token |
| 5377 |
!!!next-token; |
!!!next-token; |
| 5378 |
redo B; |
next B; |
| 5379 |
} else { |
} else { |
| 5380 |
!!!cp ('t193'); |
!!!cp ('t193'); |
| 5381 |
# |
# |
| 5382 |
} |
} |
| 5383 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 5384 |
for my $entry (@{$self->{open_elements}}) { |
for my $entry (@{$self->{open_elements}}) { |
| 5385 |
if (not { |
unless ($entry->[1] & ALL_END_TAG_OPTIONAL_EL) { |
|
dd => 1, dt => 1, li => 1, p => 1, tbody => 1, td => 1, tfoot => 1, |
|
|
th => 1, thead => 1, tr => 1, body => 1, html => 1, |
|
|
}->{$entry->[1]}) { |
|
| 5386 |
!!!cp ('t75'); |
!!!cp ('t75'); |
| 5387 |
!!!parse-error (type => 'in body:#eof'); |
!!!parse-error (type => 'in body:#eof', token => $token); |
| 5388 |
last; |
last; |
| 5389 |
} |
} |
| 5390 |
} |
} |
| 5406 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 5407 |
!!!cp ('t194'); |
!!!cp ('t194'); |
| 5408 |
!!!next-token; |
!!!next-token; |
| 5409 |
redo B; |
next B; |
| 5410 |
} else { |
} else { |
| 5411 |
!!!cp ('t195'); |
!!!cp ('t195'); |
| 5412 |
} |
} |
| 5413 |
} |
} |
| 5414 |
|
|
| 5415 |
!!!parse-error (type => 'in table:#character'); |
!!!parse-error (type => 'in table:#text', token => $token); |
| 5416 |
|
|
| 5417 |
## As if in body, but insert into foster parent element |
## As if in body, but insert into foster parent element |
| 5418 |
## ISSUE: Spec says that "whenever a node would be inserted |
## ISSUE: Spec says that "whenever a node would be inserted |
| 5420 |
## result in a new Text node. |
## result in a new Text node. |
| 5421 |
$reconstruct_active_formatting_elements->($insert_to_foster); |
$reconstruct_active_formatting_elements->($insert_to_foster); |
| 5422 |
|
|
| 5423 |
if ({ |
if ($self->{open_elements}->[-1]->[1] & TABLE_ROWS_EL) { |
|
table => 1, tbody => 1, tfoot => 1, |
|
|
thead => 1, tr => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 5424 |
# MUST |
# MUST |
| 5425 |
my $foster_parent_element; |
my $foster_parent_element; |
| 5426 |
my $next_sibling; |
my $next_sibling; |
| 5427 |
my $prev_sibling; |
my $prev_sibling; |
| 5428 |
OE: for (reverse 0..$#{$self->{open_elements}}) { |
OE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5429 |
if ($self->{open_elements}->[$_]->[1] eq 'table') { |
if ($self->{open_elements}->[$_]->[1] & TABLE_EL) { |
| 5430 |
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
| 5431 |
if (defined $parent and $parent->node_type == 1) { |
if (defined $parent and $parent->node_type == 1) { |
| 5432 |
!!!cp ('t196'); |
!!!cp ('t196'); |
| 5461 |
} |
} |
| 5462 |
|
|
| 5463 |
!!!next-token; |
!!!next-token; |
| 5464 |
redo B; |
next B; |
| 5465 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 5466 |
if ({ |
if ({ |
| 5467 |
tr => ($self->{insertion_mode} != IN_ROW_IM), |
tr => ($self->{insertion_mode} != IN_ROW_IM), |
| 5468 |
th => 1, td => 1, |
th => 1, td => 1, |
| 5469 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5470 |
if ($self->{insertion_mode} == IN_TABLE_IM) { |
if ($self->{insertion_mode} == IN_TABLE_IM) { |
| 5471 |
## Clear back to table context |
## Clear back to table context |
| 5472 |
while ($self->{open_elements}->[-1]->[1] ne 'table' and |
while (not ($self->{open_elements}->[-1]->[1] |
| 5473 |
$self->{open_elements}->[-1]->[1] ne 'html') { |
& TABLE_SCOPING_EL)) { |
| 5474 |
!!!cp ('t201'); |
!!!cp ('t201'); |
| 5475 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5476 |
} |
} |
| 5477 |
|
|
| 5478 |
!!!insert-element ('tbody'); |
!!!insert-element ('tbody',, $token); |
| 5479 |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 5480 |
## reprocess in the "in table body" insertion mode... |
## reprocess in the "in table body" insertion mode... |
| 5481 |
} |
} |
| 5482 |
|
|
| 5483 |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
| 5484 |
unless ($token->{tag_name} eq 'tr') { |
unless ($token->{tag_name} eq 'tr') { |
| 5485 |
!!!cp ('t202'); |
!!!cp ('t202'); |
| 5486 |
!!!parse-error (type => 'missing start tag:tr'); |
!!!parse-error (type => 'missing start tag:tr', token => $token); |
| 5487 |
} |
} |
| 5488 |
|
|
| 5489 |
## Clear back to table body context |
## Clear back to table body context |
| 5490 |
while (not { |
while (not ($self->{open_elements}->[-1]->[1] |
| 5491 |
tbody => 1, tfoot => 1, thead => 1, html => 1, |
& TABLE_ROWS_SCOPING_EL)) { |
| 5492 |
}->{$self->{open_elements}->[-1]->[1]}) { |
!!!cp ('t203'); |
| 5493 |
!!!cp ('t203'); |
## ISSUE: Can this case be reached? |
| 5494 |
## ISSUE: Can this case be reached? |
pop @{$self->{open_elements}}; |
| 5495 |
pop @{$self->{open_elements}}; |
} |
|
} |
|
| 5496 |
|
|
| 5497 |
$self->{insertion_mode} = IN_ROW_IM; |
$self->{insertion_mode} = IN_ROW_IM; |
| 5498 |
if ($token->{tag_name} eq 'tr') { |
if ($token->{tag_name} eq 'tr') { |
| 5499 |
!!!cp ('t204'); |
!!!cp ('t204'); |
| 5500 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5501 |
|
!!!nack ('t204'); |
| 5502 |
!!!next-token; |
!!!next-token; |
| 5503 |
redo B; |
next B; |
| 5504 |
} else { |
} else { |
| 5505 |
!!!cp ('t205'); |
!!!cp ('t205'); |
| 5506 |
!!!insert-element ('tr'); |
!!!insert-element ('tr',, $token); |
| 5507 |
## reprocess in the "in row" insertion mode |
## reprocess in the "in row" insertion mode |
| 5508 |
} |
} |
| 5509 |
} else { |
} else { |
| 5511 |
} |
} |
| 5512 |
|
|
| 5513 |
## Clear back to table row context |
## Clear back to table row context |
| 5514 |
while (not { |
while (not ($self->{open_elements}->[-1]->[1] |
| 5515 |
tr => 1, html => 1, |
& TABLE_ROW_SCOPING_EL)) { |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 5516 |
!!!cp ('t207'); |
!!!cp ('t207'); |
| 5517 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5518 |
} |
} |
| 5519 |
|
|
| 5520 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5521 |
$self->{insertion_mode} = IN_CELL_IM; |
$self->{insertion_mode} = IN_CELL_IM; |
| 5522 |
|
|
| 5523 |
push @$active_formatting_elements, ['#marker', '']; |
push @$active_formatting_elements, ['#marker', '']; |
| 5524 |
|
|
| 5525 |
|
!!!nack ('t207.1'); |
| 5526 |
!!!next-token; |
!!!next-token; |
| 5527 |
redo B; |
next B; |
| 5528 |
} elsif ({ |
} elsif ({ |
| 5529 |
caption => 1, col => 1, colgroup => 1, |
caption => 1, col => 1, colgroup => 1, |
| 5530 |
tbody => 1, tfoot => 1, thead => 1, |
tbody => 1, tfoot => 1, thead => 1, |
| 5536 |
my $i; |
my $i; |
| 5537 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5538 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5539 |
if ($node->[1] eq 'tr') { |
if ($node->[1] & TABLE_ROW_EL) { |
| 5540 |
!!!cp ('t208'); |
!!!cp ('t208'); |
| 5541 |
$i = $_; |
$i = $_; |
| 5542 |
last INSCOPE; |
last INSCOPE; |
| 5543 |
} elsif ({ |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
|
html => 1, |
|
|
|
|
|
## NOTE: This element does not appear here, maybe. |
|
|
table => 1, |
|
|
}->{$node->[1]}) { |
|
| 5544 |
!!!cp ('t209'); |
!!!cp ('t209'); |
| 5545 |
last INSCOPE; |
last INSCOPE; |
| 5546 |
} |
} |
| 5547 |
} # INSCOPE |
} # INSCOPE |
| 5548 |
unless (defined $i) { |
unless (defined $i) { |
| 5549 |
!!!cp ('t210'); |
!!!cp ('t210'); |
| 5550 |
## TODO: This type is wrong. |
## TODO: This type is wrong. |
| 5551 |
!!!parse-error (type => 'unmacthed end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmacthed end tag', |
| 5552 |
|
text => $token->{tag_name}, token => $token); |
| 5553 |
## Ignore the token |
## Ignore the token |
| 5554 |
|
!!!nack ('t210.1'); |
| 5555 |
!!!next-token; |
!!!next-token; |
| 5556 |
redo B; |
next B; |
| 5557 |
} |
} |
| 5558 |
|
|
| 5559 |
## Clear back to table row context |
## Clear back to table row context |
| 5560 |
while (not { |
while (not ($self->{open_elements}->[-1]->[1] |
| 5561 |
tr => 1, html => 1, |
& TABLE_ROW_SCOPING_EL)) { |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 5562 |
!!!cp ('t211'); |
!!!cp ('t211'); |
| 5563 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
| 5564 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5569 |
if ($token->{tag_name} eq 'tr') { |
if ($token->{tag_name} eq 'tr') { |
| 5570 |
!!!cp ('t212'); |
!!!cp ('t212'); |
| 5571 |
## reprocess |
## reprocess |
| 5572 |
redo B; |
!!!ack-later; |
| 5573 |
|
next B; |
| 5574 |
} else { |
} else { |
| 5575 |
!!!cp ('t213'); |
!!!cp ('t213'); |
| 5576 |
## reprocess in the "in table body" insertion mode... |
## reprocess in the "in table body" insertion mode... |
| 5582 |
my $i; |
my $i; |
| 5583 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5584 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5585 |
if ({ |
if ($node->[1] & TABLE_ROW_GROUP_EL) { |
|
tbody => 1, thead => 1, tfoot => 1, |
|
|
}->{$node->[1]}) { |
|
| 5586 |
!!!cp ('t214'); |
!!!cp ('t214'); |
| 5587 |
$i = $_; |
$i = $_; |
| 5588 |
last INSCOPE; |
last INSCOPE; |
| 5589 |
} elsif ({ |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
| 5590 |
!!!cp ('t215'); |
!!!cp ('t215'); |
| 5591 |
last INSCOPE; |
last INSCOPE; |
| 5592 |
} |
} |
| 5593 |
} # INSCOPE |
} # INSCOPE |
| 5594 |
unless (defined $i) { |
unless (defined $i) { |
| 5595 |
!!!cp ('t216'); |
!!!cp ('t216'); |
| 5596 |
## TODO: This erorr type ios wrong. |
## TODO: This erorr type is wrong. |
| 5597 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 5598 |
|
text => $token->{tag_name}, token => $token); |
| 5599 |
## Ignore the token |
## Ignore the token |
| 5600 |
|
!!!nack ('t216.1'); |
| 5601 |
!!!next-token; |
!!!next-token; |
| 5602 |
redo B; |
next B; |
| 5603 |
} |
} |
| 5604 |
|
|
| 5605 |
## Clear back to table body context |
## Clear back to table body context |
| 5606 |
while (not { |
while (not ($self->{open_elements}->[-1]->[1] |
| 5607 |
tbody => 1, tfoot => 1, thead => 1, html => 1, |
& TABLE_ROWS_SCOPING_EL)) { |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 5608 |
!!!cp ('t217'); |
!!!cp ('t217'); |
| 5609 |
## ISSUE: Can this state be reached? |
## ISSUE: Can this state be reached? |
| 5610 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5626 |
|
|
| 5627 |
if ($token->{tag_name} eq 'col') { |
if ($token->{tag_name} eq 'col') { |
| 5628 |
## Clear back to table context |
## Clear back to table context |
| 5629 |
while ($self->{open_elements}->[-1]->[1] ne 'table' and |
while (not ($self->{open_elements}->[-1]->[1] |
| 5630 |
$self->{open_elements}->[-1]->[1] ne 'html') { |
& TABLE_SCOPING_EL)) { |
| 5631 |
!!!cp ('t219'); |
!!!cp ('t219'); |
| 5632 |
## ISSUE: Can this state be reached? |
## ISSUE: Can this state be reached? |
| 5633 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5634 |
} |
} |
| 5635 |
|
|
| 5636 |
!!!insert-element ('colgroup'); |
!!!insert-element ('colgroup',, $token); |
| 5637 |
$self->{insertion_mode} = IN_COLUMN_GROUP_IM; |
$self->{insertion_mode} = IN_COLUMN_GROUP_IM; |
| 5638 |
## reprocess |
## reprocess |
| 5639 |
redo B; |
!!!ack-later; |
| 5640 |
|
next B; |
| 5641 |
} elsif ({ |
} elsif ({ |
| 5642 |
caption => 1, |
caption => 1, |
| 5643 |
colgroup => 1, |
colgroup => 1, |
| 5644 |
tbody => 1, tfoot => 1, thead => 1, |
tbody => 1, tfoot => 1, thead => 1, |
| 5645 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5646 |
## Clear back to table context |
## Clear back to table context |
| 5647 |
while ($self->{open_elements}->[-1]->[1] ne 'table' and |
while (not ($self->{open_elements}->[-1]->[1] |
| 5648 |
$self->{open_elements}->[-1]->[1] ne 'html') { |
& TABLE_SCOPING_EL)) { |
| 5649 |
!!!cp ('t220'); |
!!!cp ('t220'); |
| 5650 |
## ISSUE: Can this state be reached? |
## ISSUE: Can this state be reached? |
| 5651 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5654 |
push @$active_formatting_elements, ['#marker', ''] |
push @$active_formatting_elements, ['#marker', ''] |
| 5655 |
if $token->{tag_name} eq 'caption'; |
if $token->{tag_name} eq 'caption'; |
| 5656 |
|
|
| 5657 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5658 |
$self->{insertion_mode} = { |
$self->{insertion_mode} = { |
| 5659 |
caption => IN_CAPTION_IM, |
caption => IN_CAPTION_IM, |
| 5660 |
colgroup => IN_COLUMN_GROUP_IM, |
colgroup => IN_COLUMN_GROUP_IM, |
| 5663 |
thead => IN_TABLE_BODY_IM, |
thead => IN_TABLE_BODY_IM, |
| 5664 |
}->{$token->{tag_name}}; |
}->{$token->{tag_name}}; |
| 5665 |
!!!next-token; |
!!!next-token; |
| 5666 |
redo B; |
!!!nack ('t220.1'); |
| 5667 |
|
next B; |
| 5668 |
} else { |
} else { |
| 5669 |
die "$0: in table: <>: $token->{tag_name}"; |
die "$0: in table: <>: $token->{tag_name}"; |
| 5670 |
} |
} |
| 5671 |
} elsif ($token->{tag_name} eq 'table') { |
} elsif ($token->{tag_name} eq 'table') { |
| 5672 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed', |
| 5673 |
|
text => $self->{open_elements}->[-1]->[0] |
| 5674 |
|
->manakai_local_name, |
| 5675 |
|
token => $token); |
| 5676 |
|
|
| 5677 |
## As if </table> |
## As if </table> |
| 5678 |
## have a table element in table scope |
## have a table element in table scope |
| 5679 |
my $i; |
my $i; |
| 5680 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5681 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5682 |
if ($node->[1] eq 'table') { |
if ($node->[1] & TABLE_EL) { |
| 5683 |
!!!cp ('t221'); |
!!!cp ('t221'); |
| 5684 |
$i = $_; |
$i = $_; |
| 5685 |
last INSCOPE; |
last INSCOPE; |
| 5686 |
} elsif ({ |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
|
#table => 1, |
|
|
html => 1, |
|
|
}->{$node->[1]}) { |
|
| 5687 |
!!!cp ('t222'); |
!!!cp ('t222'); |
| 5688 |
last INSCOPE; |
last INSCOPE; |
| 5689 |
} |
} |
| 5691 |
unless (defined $i) { |
unless (defined $i) { |
| 5692 |
!!!cp ('t223'); |
!!!cp ('t223'); |
| 5693 |
## TODO: The following is wrong, maybe. |
## TODO: The following is wrong, maybe. |
| 5694 |
!!!parse-error (type => 'unmatched end tag:table'); |
!!!parse-error (type => 'unmatched end tag', text => 'table', |
| 5695 |
|
token => $token); |
| 5696 |
## Ignore tokens </table><table> |
## Ignore tokens </table><table> |
| 5697 |
|
!!!nack ('t223.1'); |
| 5698 |
!!!next-token; |
!!!next-token; |
| 5699 |
redo B; |
next B; |
| 5700 |
} |
} |
| 5701 |
|
|
| 5702 |
## TODO: Followings are removed from the latest spec. |
## TODO: Followings are removed from the latest spec. |
| 5703 |
## generate implied end tags |
## generate implied end tags |
| 5704 |
while ({ |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
|
dd => 1, dt => 1, li => 1, p => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 5705 |
!!!cp ('t224'); |
!!!cp ('t224'); |
| 5706 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5707 |
} |
} |
| 5708 |
|
|
| 5709 |
if ($self->{open_elements}->[-1]->[1] ne 'table') { |
unless ($self->{open_elements}->[-1]->[1] & TABLE_EL) { |
| 5710 |
!!!cp ('t225'); |
!!!cp ('t225'); |
| 5711 |
## ISSUE: Can this case be reached? |
## NOTE: |<table><tr><table>| |
| 5712 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed', |
| 5713 |
|
text => $self->{open_elements}->[-1]->[0] |
| 5714 |
|
->manakai_local_name, |
| 5715 |
|
token => $token); |
| 5716 |
} else { |
} else { |
| 5717 |
!!!cp ('t226'); |
!!!cp ('t226'); |
| 5718 |
} |
} |
| 5722 |
|
|
| 5723 |
$self->_reset_insertion_mode; |
$self->_reset_insertion_mode; |
| 5724 |
|
|
| 5725 |
## reprocess |
## reprocess |
| 5726 |
redo B; |
!!!ack-later; |
| 5727 |
|
next B; |
| 5728 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($token->{tag_name} eq 'style') { |
| 5729 |
if (not $open_tables->[-1]->[1]) { # tainted |
if (not $open_tables->[-1]->[1]) { # tainted |
| 5730 |
!!!cp ('t227.8'); |
!!!cp ('t227.8'); |
| 5731 |
## NOTE: This is a "as if in head" code clone. |
## NOTE: This is a "as if in head" code clone. |
| 5732 |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 5733 |
redo B; |
next B; |
| 5734 |
} else { |
} else { |
| 5735 |
!!!cp ('t227.7'); |
!!!cp ('t227.7'); |
| 5736 |
# |
# |
| 5740 |
!!!cp ('t227.6'); |
!!!cp ('t227.6'); |
| 5741 |
## NOTE: This is a "as if in head" code clone. |
## NOTE: This is a "as if in head" code clone. |
| 5742 |
$script_start_tag->(); |
$script_start_tag->(); |
| 5743 |
redo B; |
next B; |
| 5744 |
} else { |
} else { |
| 5745 |
!!!cp ('t227.5'); |
!!!cp ('t227.5'); |
| 5746 |
# |
# |
| 5751 |
my $type = lc $token->{attributes}->{type}->{value}; |
my $type = lc $token->{attributes}->{type}->{value}; |
| 5752 |
if ($type eq 'hidden') { |
if ($type eq 'hidden') { |
| 5753 |
!!!cp ('t227.3'); |
!!!cp ('t227.3'); |
| 5754 |
!!!parse-error (type => 'in table:'.$token->{tag_name}); |
!!!parse-error (type => 'in table', |
| 5755 |
|
text => $token->{tag_name}, token => $token); |
| 5756 |
|
|
| 5757 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 5758 |
|
|
| 5759 |
## TODO: form element pointer |
## TODO: form element pointer |
| 5760 |
|
|
| 5761 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5762 |
|
|
| 5763 |
!!!next-token; |
!!!next-token; |
| 5764 |
redo B; |
!!!ack ('t227.2.1'); |
| 5765 |
|
next B; |
| 5766 |
} else { |
} else { |
| 5767 |
!!!cp ('t227.2'); |
!!!cp ('t227.2'); |
| 5768 |
# |
# |
| 5780 |
# |
# |
| 5781 |
} |
} |
| 5782 |
|
|
| 5783 |
!!!parse-error (type => 'in table:'.$token->{tag_name}); |
!!!parse-error (type => 'in table', text => $token->{tag_name}, |
| 5784 |
|
token => $token); |
| 5785 |
|
|
| 5786 |
$insert = $insert_to_foster; |
$insert = $insert_to_foster; |
| 5787 |
# |
# |
| 5792 |
my $i; |
my $i; |
| 5793 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5794 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5795 |
if ($node->[1] eq $token->{tag_name}) { |
if ($node->[1] & TABLE_ROW_EL) { |
| 5796 |
!!!cp ('t228'); |
!!!cp ('t228'); |
| 5797 |
$i = $_; |
$i = $_; |
| 5798 |
last INSCOPE; |
last INSCOPE; |
| 5799 |
} elsif ({ |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
| 5800 |
!!!cp ('t229'); |
!!!cp ('t229'); |
| 5801 |
last INSCOPE; |
last INSCOPE; |
| 5802 |
} |
} |
| 5803 |
} # INSCOPE |
} # INSCOPE |
| 5804 |
unless (defined $i) { |
unless (defined $i) { |
| 5805 |
!!!cp ('t230'); |
!!!cp ('t230'); |
| 5806 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 5807 |
|
text => $token->{tag_name}, token => $token); |
| 5808 |
## Ignore the token |
## Ignore the token |
| 5809 |
|
!!!nack ('t230.1'); |
| 5810 |
!!!next-token; |
!!!next-token; |
| 5811 |
redo B; |
next B; |
| 5812 |
} else { |
} else { |
| 5813 |
!!!cp ('t232'); |
!!!cp ('t232'); |
| 5814 |
} |
} |
| 5815 |
|
|
| 5816 |
## Clear back to table row context |
## Clear back to table row context |
| 5817 |
while (not { |
while (not ($self->{open_elements}->[-1]->[1] |
| 5818 |
tr => 1, html => 1, |
& TABLE_ROW_SCOPING_EL)) { |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 5819 |
!!!cp ('t231'); |
!!!cp ('t231'); |
| 5820 |
## ISSUE: Can this state be reached? |
## ISSUE: Can this state be reached? |
| 5821 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5824 |
pop @{$self->{open_elements}}; # tr |
pop @{$self->{open_elements}}; # tr |
| 5825 |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 5826 |
!!!next-token; |
!!!next-token; |
| 5827 |
redo B; |
!!!nack ('t231.1'); |
| 5828 |
|
next B; |
| 5829 |
} elsif ($token->{tag_name} eq 'table') { |
} elsif ($token->{tag_name} eq 'table') { |
| 5830 |
if ($self->{insertion_mode} == IN_ROW_IM) { |
if ($self->{insertion_mode} == IN_ROW_IM) { |
| 5831 |
## As if </tr> |
## As if </tr> |
| 5833 |
my $i; |
my $i; |
| 5834 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5835 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5836 |
if ($node->[1] eq 'tr') { |
if ($node->[1] & TABLE_ROW_EL) { |
| 5837 |
!!!cp ('t233'); |
!!!cp ('t233'); |
| 5838 |
$i = $_; |
$i = $_; |
| 5839 |
last INSCOPE; |
last INSCOPE; |
| 5840 |
} elsif ({ |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
| 5841 |
!!!cp ('t234'); |
!!!cp ('t234'); |
| 5842 |
last INSCOPE; |
last INSCOPE; |
| 5843 |
} |
} |
| 5845 |
unless (defined $i) { |
unless (defined $i) { |
| 5846 |
!!!cp ('t235'); |
!!!cp ('t235'); |
| 5847 |
## TODO: The following is wrong. |
## TODO: The following is wrong. |
| 5848 |
!!!parse-error (type => 'unmatched end tag:'.$token->{type}); |
!!!parse-error (type => 'unmatched end tag', |
| 5849 |
|
text => $token->{type}, token => $token); |
| 5850 |
## Ignore the token |
## Ignore the token |
| 5851 |
|
!!!nack ('t236.1'); |
| 5852 |
!!!next-token; |
!!!next-token; |
| 5853 |
redo B; |
next B; |
| 5854 |
} |
} |
| 5855 |
|
|
| 5856 |
## Clear back to table row context |
## Clear back to table row context |
| 5857 |
while (not { |
while (not ($self->{open_elements}->[-1]->[1] |
| 5858 |
tr => 1, html => 1, |
& TABLE_ROW_SCOPING_EL)) { |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 5859 |
!!!cp ('t236'); |
!!!cp ('t236'); |
| 5860 |
## ISSUE: Can this state be reached? |
## ISSUE: Can this state be reached? |
| 5861 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5871 |
my $i; |
my $i; |
| 5872 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5873 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5874 |
if ({ |
if ($node->[1] & TABLE_ROW_GROUP_EL) { |
|
tbody => 1, thead => 1, tfoot => 1, |
|
|
}->{$node->[1]}) { |
|
| 5875 |
!!!cp ('t237'); |
!!!cp ('t237'); |
| 5876 |
$i = $_; |
$i = $_; |
| 5877 |
last INSCOPE; |
last INSCOPE; |
| 5878 |
} elsif ({ |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
| 5879 |
!!!cp ('t238'); |
!!!cp ('t238'); |
| 5880 |
last INSCOPE; |
last INSCOPE; |
| 5881 |
} |
} |
| 5882 |
} # INSCOPE |
} # INSCOPE |
| 5883 |
unless (defined $i) { |
unless (defined $i) { |
| 5884 |
!!!cp ('t239'); |
!!!cp ('t239'); |
| 5885 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 5886 |
|
text => $token->{tag_name}, token => $token); |
| 5887 |
## Ignore the token |
## Ignore the token |
| 5888 |
|
!!!nack ('t239.1'); |
| 5889 |
!!!next-token; |
!!!next-token; |
| 5890 |
redo B; |
next B; |
| 5891 |
} |
} |
| 5892 |
|
|
| 5893 |
## Clear back to table body context |
## Clear back to table body context |
| 5894 |
while (not { |
while (not ($self->{open_elements}->[-1]->[1] |
| 5895 |
tbody => 1, tfoot => 1, thead => 1, html => 1, |
& TABLE_ROWS_SCOPING_EL)) { |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 5896 |
!!!cp ('t240'); |
!!!cp ('t240'); |
| 5897 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5898 |
} |
} |
| 5918 |
my $i; |
my $i; |
| 5919 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5920 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5921 |
if ($node->[1] eq $token->{tag_name}) { |
if ($node->[1] & TABLE_EL) { |
| 5922 |
!!!cp ('t241'); |
!!!cp ('t241'); |
| 5923 |
$i = $_; |
$i = $_; |
| 5924 |
last INSCOPE; |
last INSCOPE; |
| 5925 |
} elsif ({ |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
| 5926 |
!!!cp ('t242'); |
!!!cp ('t242'); |
| 5927 |
last INSCOPE; |
last INSCOPE; |
| 5928 |
} |
} |
| 5929 |
} # INSCOPE |
} # INSCOPE |
| 5930 |
unless (defined $i) { |
unless (defined $i) { |
| 5931 |
!!!cp ('t243'); |
!!!cp ('t243'); |
| 5932 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 5933 |
|
text => $token->{tag_name}, token => $token); |
| 5934 |
## Ignore the token |
## Ignore the token |
| 5935 |
|
!!!nack ('t243.1'); |
| 5936 |
!!!next-token; |
!!!next-token; |
| 5937 |
redo B; |
next B; |
| 5938 |
} |
} |
| 5939 |
|
|
| 5940 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 5943 |
$self->_reset_insertion_mode; |
$self->_reset_insertion_mode; |
| 5944 |
|
|
| 5945 |
!!!next-token; |
!!!next-token; |
| 5946 |
redo B; |
next B; |
| 5947 |
} elsif ({ |
} elsif ({ |
| 5948 |
tbody => 1, tfoot => 1, thead => 1, |
tbody => 1, tfoot => 1, thead => 1, |
| 5949 |
}->{$token->{tag_name}} and |
}->{$token->{tag_name}} and |
| 5953 |
my $i; |
my $i; |
| 5954 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5955 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5956 |
if ($node->[1] eq $token->{tag_name}) { |
if ($node->[0]->manakai_local_name eq $token->{tag_name}) { |
| 5957 |
!!!cp ('t247'); |
!!!cp ('t247'); |
| 5958 |
$i = $_; |
$i = $_; |
| 5959 |
last INSCOPE; |
last INSCOPE; |
| 5960 |
} elsif ({ |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
| 5961 |
!!!cp ('t248'); |
!!!cp ('t248'); |
| 5962 |
last INSCOPE; |
last INSCOPE; |
| 5963 |
} |
} |
| 5964 |
} # INSCOPE |
} # INSCOPE |
| 5965 |
unless (defined $i) { |
unless (defined $i) { |
| 5966 |
!!!cp ('t249'); |
!!!cp ('t249'); |
| 5967 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 5968 |
|
text => $token->{tag_name}, token => $token); |
| 5969 |
## Ignore the token |
## Ignore the token |
| 5970 |
|
!!!nack ('t249.1'); |
| 5971 |
!!!next-token; |
!!!next-token; |
| 5972 |
redo B; |
next B; |
| 5973 |
} |
} |
| 5974 |
|
|
| 5975 |
## As if </tr> |
## As if </tr> |
| 5977 |
my $i; |
my $i; |
| 5978 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5979 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5980 |
if ($node->[1] eq 'tr') { |
if ($node->[1] & TABLE_ROW_EL) { |
| 5981 |
!!!cp ('t250'); |
!!!cp ('t250'); |
| 5982 |
$i = $_; |
$i = $_; |
| 5983 |
last INSCOPE; |
last INSCOPE; |
| 5984 |
} elsif ({ |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
| 5985 |
!!!cp ('t251'); |
!!!cp ('t251'); |
| 5986 |
last INSCOPE; |
last INSCOPE; |
| 5987 |
} |
} |
| 5988 |
} # INSCOPE |
} # INSCOPE |
| 5989 |
unless (defined $i) { |
unless (defined $i) { |
| 5990 |
!!!cp ('t252'); |
!!!cp ('t252'); |
| 5991 |
!!!parse-error (type => 'unmatched end tag:tr'); |
!!!parse-error (type => 'unmatched end tag', |
| 5992 |
|
text => 'tr', token => $token); |
| 5993 |
## Ignore the token |
## Ignore the token |
| 5994 |
|
!!!nack ('t252.1'); |
| 5995 |
!!!next-token; |
!!!next-token; |
| 5996 |
redo B; |
next B; |
| 5997 |
} |
} |
| 5998 |
|
|
| 5999 |
## Clear back to table row context |
## Clear back to table row context |
| 6000 |
while (not { |
while (not ($self->{open_elements}->[-1]->[1] |
| 6001 |
tr => 1, html => 1, |
& TABLE_ROW_SCOPING_EL)) { |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 6002 |
!!!cp ('t253'); |
!!!cp ('t253'); |
| 6003 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
| 6004 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 6013 |
my $i; |
my $i; |
| 6014 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 6015 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 6016 |
if ($node->[1] eq $token->{tag_name}) { |
if ($node->[0]->manakai_local_name eq $token->{tag_name}) { |
| 6017 |
!!!cp ('t254'); |
!!!cp ('t254'); |
| 6018 |
$i = $_; |
$i = $_; |
| 6019 |
last INSCOPE; |
last INSCOPE; |
| 6020 |
} elsif ({ |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
| 6021 |
!!!cp ('t255'); |
!!!cp ('t255'); |
| 6022 |
last INSCOPE; |
last INSCOPE; |
| 6023 |
} |
} |
| 6024 |
} # INSCOPE |
} # INSCOPE |
| 6025 |
unless (defined $i) { |
unless (defined $i) { |
| 6026 |
!!!cp ('t256'); |
!!!cp ('t256'); |
| 6027 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 6028 |
|
text => $token->{tag_name}, token => $token); |
| 6029 |
## Ignore the token |
## Ignore the token |
| 6030 |
|
!!!nack ('t256.1'); |
| 6031 |
!!!next-token; |
!!!next-token; |
| 6032 |
redo B; |
next B; |
| 6033 |
} |
} |
| 6034 |
|
|
| 6035 |
## Clear back to table body context |
## Clear back to table body context |
| 6036 |
while (not { |
while (not ($self->{open_elements}->[-1]->[1] |
| 6037 |
tbody => 1, tfoot => 1, thead => 1, html => 1, |
& TABLE_ROWS_SCOPING_EL)) { |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 6038 |
!!!cp ('t257'); |
!!!cp ('t257'); |
| 6039 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
| 6040 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 6042 |
|
|
| 6043 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 6044 |
$self->{insertion_mode} = IN_TABLE_IM; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 6045 |
|
!!!nack ('t257.1'); |
| 6046 |
!!!next-token; |
!!!next-token; |
| 6047 |
redo B; |
next B; |
| 6048 |
} elsif ({ |
} elsif ({ |
| 6049 |
body => 1, caption => 1, col => 1, colgroup => 1, |
body => 1, caption => 1, col => 1, colgroup => 1, |
| 6050 |
html => 1, td => 1, th => 1, |
html => 1, td => 1, th => 1, |
| 6051 |
tr => 1, # $self->{insertion_mode} == IN_ROW_IM |
tr => 1, # $self->{insertion_mode} == IN_ROW_IM |
| 6052 |
tbody => 1, tfoot => 1, thead => 1, # $self->{insertion_mode} == IN_TABLE_IM |
tbody => 1, tfoot => 1, thead => 1, # $self->{insertion_mode} == IN_TABLE_IM |
| 6053 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6054 |
!!!cp ('t258'); |
!!!cp ('t258'); |
| 6055 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 6056 |
## Ignore the token |
text => $token->{tag_name}, token => $token); |
| 6057 |
!!!next-token; |
## Ignore the token |
| 6058 |
redo B; |
!!!nack ('t258.1'); |
| 6059 |
|
!!!next-token; |
| 6060 |
|
next B; |
| 6061 |
} else { |
} else { |
| 6062 |
!!!cp ('t259'); |
!!!cp ('t259'); |
| 6063 |
!!!parse-error (type => 'in table:/'.$token->{tag_name}); |
!!!parse-error (type => 'in table:/', |
| 6064 |
|
text => $token->{tag_name}, token => $token); |
| 6065 |
|
|
| 6066 |
$insert = $insert_to_foster; |
$insert = $insert_to_foster; |
| 6067 |
# |
# |
| 6068 |
} |
} |
| 6069 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 6070 |
unless ($self->{open_elements}->[-1]->[1] eq 'html' and |
unless ($self->{open_elements}->[-1]->[1] & HTML_EL and |
| 6071 |
@{$self->{open_elements}} == 1) { # redundant, maybe |
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 6072 |
!!!parse-error (type => 'in body:#eof'); |
!!!parse-error (type => 'in body:#eof', token => $token); |
| 6073 |
!!!cp ('t259.1'); |
!!!cp ('t259.1'); |
| 6074 |
# |
# |
| 6075 |
} else { |
} else { |
| 6089 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 6090 |
!!!cp ('t260'); |
!!!cp ('t260'); |
| 6091 |
!!!next-token; |
!!!next-token; |
| 6092 |
redo B; |
next B; |
| 6093 |
} |
} |
| 6094 |
} |
} |
| 6095 |
|
|
| 6098 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 6099 |
if ($token->{tag_name} eq 'col') { |
if ($token->{tag_name} eq 'col') { |
| 6100 |
!!!cp ('t262'); |
!!!cp ('t262'); |
| 6101 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 6102 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 6103 |
|
!!!ack ('t262.1'); |
| 6104 |
!!!next-token; |
!!!next-token; |
| 6105 |
redo B; |
next B; |
| 6106 |
} else { |
} else { |
| 6107 |
!!!cp ('t263'); |
!!!cp ('t263'); |
| 6108 |
# |
# |
| 6109 |
} |
} |
| 6110 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 6111 |
if ($token->{tag_name} eq 'colgroup') { |
if ($token->{tag_name} eq 'colgroup') { |
| 6112 |
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
| 6113 |
!!!cp ('t264'); |
!!!cp ('t264'); |
| 6114 |
!!!parse-error (type => 'unmatched end tag:colgroup'); |
!!!parse-error (type => 'unmatched end tag', |
| 6115 |
|
text => 'colgroup', token => $token); |
| 6116 |
## Ignore the token |
## Ignore the token |
| 6117 |
!!!next-token; |
!!!next-token; |
| 6118 |
redo B; |
next B; |
| 6119 |
} else { |
} else { |
| 6120 |
!!!cp ('t265'); |
!!!cp ('t265'); |
| 6121 |
pop @{$self->{open_elements}}; # colgroup |
pop @{$self->{open_elements}}; # colgroup |
| 6122 |
$self->{insertion_mode} = IN_TABLE_IM; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 6123 |
!!!next-token; |
!!!next-token; |
| 6124 |
redo B; |
next B; |
| 6125 |
} |
} |
| 6126 |
} elsif ($token->{tag_name} eq 'col') { |
} elsif ($token->{tag_name} eq 'col') { |
| 6127 |
!!!cp ('t266'); |
!!!cp ('t266'); |
| 6128 |
!!!parse-error (type => 'unmatched end tag:col'); |
!!!parse-error (type => 'unmatched end tag', |
| 6129 |
|
text => 'col', token => $token); |
| 6130 |
## Ignore the token |
## Ignore the token |
| 6131 |
!!!next-token; |
!!!next-token; |
| 6132 |
redo B; |
next B; |
| 6133 |
} else { |
} else { |
| 6134 |
!!!cp ('t267'); |
!!!cp ('t267'); |
| 6135 |
# |
# |
| 6136 |
} |
} |
| 6137 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 6138 |
if ($self->{open_elements}->[-1]->[1] eq 'html' or |
if ($self->{open_elements}->[-1]->[1] & HTML_EL and |
| 6139 |
@{$self->{open_elements}} == 1) { # redundant, maybe |
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 6140 |
!!!cp ('t270.2'); |
!!!cp ('t270.2'); |
| 6141 |
## Stop parsing. |
## Stop parsing. |
| 6146 |
pop @{$self->{open_elements}}; # colgroup |
pop @{$self->{open_elements}}; # colgroup |
| 6147 |
$self->{insertion_mode} = IN_TABLE_IM; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 6148 |
## Reprocess. |
## Reprocess. |
| 6149 |
redo B; |
next B; |
| 6150 |
} |
} |
| 6151 |
} else { |
} else { |
| 6152 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 6153 |
} |
} |
| 6154 |
|
|
| 6155 |
## As if </colgroup> |
## As if </colgroup> |
| 6156 |
if ($self->{open_elements}->[-1]->[1] eq 'html') { |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
| 6157 |
!!!cp ('t269'); |
!!!cp ('t269'); |
| 6158 |
## TODO: Wrong error type? |
## TODO: Wrong error type? |
| 6159 |
!!!parse-error (type => 'unmatched end tag:colgroup'); |
!!!parse-error (type => 'unmatched end tag', |
| 6160 |
|
text => 'colgroup', token => $token); |
| 6161 |
## Ignore the token |
## Ignore the token |
| 6162 |
|
!!!nack ('t269.1'); |
| 6163 |
!!!next-token; |
!!!next-token; |
| 6164 |
redo B; |
next B; |
| 6165 |
} else { |
} else { |
| 6166 |
!!!cp ('t270'); |
!!!cp ('t270'); |
| 6167 |
pop @{$self->{open_elements}}; # colgroup |
pop @{$self->{open_elements}}; # colgroup |
| 6168 |
$self->{insertion_mode} = IN_TABLE_IM; |
$self->{insertion_mode} = IN_TABLE_IM; |
| 6169 |
|
!!!ack-later; |
| 6170 |
## reprocess |
## reprocess |
| 6171 |
redo B; |
next B; |
| 6172 |
} |
} |
| 6173 |
} elsif ($self->{insertion_mode} & SELECT_IMS) { |
} elsif ($self->{insertion_mode} & SELECT_IMS) { |
| 6174 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 6175 |
!!!cp ('t271'); |
!!!cp ('t271'); |
| 6176 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
| 6177 |
!!!next-token; |
!!!next-token; |
| 6178 |
redo B; |
next B; |
| 6179 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 6180 |
if ($token->{tag_name} eq 'option') { |
if ($token->{tag_name} eq 'option') { |
| 6181 |
if ($self->{open_elements}->[-1]->[1] eq 'option') { |
if ($self->{open_elements}->[-1]->[1] & OPTION_EL) { |
| 6182 |
!!!cp ('t272'); |
!!!cp ('t272'); |
| 6183 |
## As if </option> |
## As if </option> |
| 6184 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 6185 |
} else { |
} else { |
| 6186 |
!!!cp ('t273'); |
!!!cp ('t273'); |
| 6187 |
} |
} |
| 6188 |
|
|
| 6189 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 6190 |
!!!next-token; |
!!!nack ('t273.1'); |
| 6191 |
redo B; |
!!!next-token; |
| 6192 |
} elsif ($token->{tag_name} eq 'optgroup') { |
next B; |
| 6193 |
if ($self->{open_elements}->[-1]->[1] eq 'option') { |
} elsif ($token->{tag_name} eq 'optgroup') { |
| 6194 |
!!!cp ('t274'); |
if ($self->{open_elements}->[-1]->[1] & OPTION_EL) { |
| 6195 |
## As if </option> |
!!!cp ('t274'); |
| 6196 |
pop @{$self->{open_elements}}; |
## As if </option> |
| 6197 |
} else { |
pop @{$self->{open_elements}}; |
| 6198 |
!!!cp ('t275'); |
} else { |
| 6199 |
} |
!!!cp ('t275'); |
| 6200 |
|
} |
| 6201 |
|
|
| 6202 |
if ($self->{open_elements}->[-1]->[1] eq 'optgroup') { |
if ($self->{open_elements}->[-1]->[1] & OPTGROUP_EL) { |
| 6203 |
!!!cp ('t276'); |
!!!cp ('t276'); |
| 6204 |
## As if </optgroup> |
## As if </optgroup> |
| 6205 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 6206 |
} else { |
} else { |
| 6207 |
!!!cp ('t277'); |
!!!cp ('t277'); |
| 6208 |
} |
} |
| 6209 |
|
|
| 6210 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 6211 |
!!!next-token; |
!!!nack ('t277.1'); |
| 6212 |
redo B; |
!!!next-token; |
| 6213 |
} elsif ($token->{tag_name} eq 'select' or |
next B; |
| 6214 |
$token->{tag_name} eq 'input' or |
} elsif ({ |
| 6215 |
|
select => 1, input => 1, textarea => 1, |
| 6216 |
|
}->{$token->{tag_name}} or |
| 6217 |
($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
| 6218 |
{ |
{ |
| 6219 |
caption => 1, table => 1, |
caption => 1, table => 1, |
| 6221 |
tr => 1, td => 1, th => 1, |
tr => 1, td => 1, th => 1, |
| 6222 |
}->{$token->{tag_name}})) { |
}->{$token->{tag_name}})) { |
| 6223 |
## TODO: The type below is not good - <select> is replaced by </select> |
## TODO: The type below is not good - <select> is replaced by </select> |
| 6224 |
!!!parse-error (type => 'not closed:select'); |
!!!parse-error (type => 'not closed', text => 'select', |
| 6225 |
|
token => $token); |
| 6226 |
## NOTE: As if the token were </select> (<select> case) or |
## NOTE: As if the token were </select> (<select> case) or |
| 6227 |
## as if there were </select> (otherwise). |
## as if there were </select> (otherwise). |
| 6228 |
## have an element in table scope |
## have an element in table scope |
| 6229 |
my $i; |
my $i; |
| 6230 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 6231 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 6232 |
if ($node->[1] eq 'select') { |
if ($node->[1] & SELECT_EL) { |
| 6233 |
!!!cp ('t278'); |
!!!cp ('t278'); |
| 6234 |
$i = $_; |
$i = $_; |
| 6235 |
last INSCOPE; |
last INSCOPE; |
| 6236 |
} elsif ({ |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
| 6237 |
table => 1, html => 1, |
!!!cp ('t279'); |
| 6238 |
}->{$node->[1]}) { |
last INSCOPE; |
| 6239 |
!!!cp ('t279'); |
} |
| 6240 |
last INSCOPE; |
} # INSCOPE |
| 6241 |
} |
unless (defined $i) { |
| 6242 |
} # INSCOPE |
!!!cp ('t280'); |
| 6243 |
unless (defined $i) { |
!!!parse-error (type => 'unmatched end tag', |
| 6244 |
!!!cp ('t280'); |
text => 'select', token => $token); |
| 6245 |
!!!parse-error (type => 'unmatched end tag:select'); |
## Ignore the token |
| 6246 |
## Ignore the token |
!!!nack ('t280.1'); |
| 6247 |
!!!next-token; |
!!!next-token; |
| 6248 |
redo B; |
next B; |
| 6249 |
} |
} |
| 6250 |
|
|
| 6251 |
!!!cp ('t281'); |
!!!cp ('t281'); |
| 6252 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 6253 |
|
|
| 6254 |
$self->_reset_insertion_mode; |
$self->_reset_insertion_mode; |
| 6255 |
|
|
| 6256 |
if ($token->{tag_name} eq 'select') { |
if ($token->{tag_name} eq 'select') { |
| 6257 |
!!!cp ('t281.2'); |
!!!nack ('t281.2'); |
| 6258 |
!!!next-token; |
!!!next-token; |
| 6259 |
redo B; |
next B; |
| 6260 |
} else { |
} else { |
| 6261 |
!!!cp ('t281.1'); |
!!!cp ('t281.1'); |
| 6262 |
|
!!!ack-later; |
| 6263 |
## Reprocess the token. |
## Reprocess the token. |
| 6264 |
redo B; |
next B; |
| 6265 |
} |
} |
| 6266 |
} else { |
} else { |
| 6267 |
!!!cp ('t282'); |
!!!cp ('t282'); |
| 6268 |
!!!parse-error (type => 'in select:'.$token->{tag_name}); |
!!!parse-error (type => 'in select', |
| 6269 |
|
text => $token->{tag_name}, token => $token); |
| 6270 |
## Ignore the token |
## Ignore the token |
| 6271 |
|
!!!nack ('t282.1'); |
| 6272 |
!!!next-token; |
!!!next-token; |
| 6273 |
redo B; |
next B; |
| 6274 |
} |
} |
| 6275 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 6276 |
if ($token->{tag_name} eq 'optgroup') { |
if ($token->{tag_name} eq 'optgroup') { |
| 6277 |
if ($self->{open_elements}->[-1]->[1] eq 'option' and |
if ($self->{open_elements}->[-1]->[1] & OPTION_EL and |
| 6278 |
$self->{open_elements}->[-2]->[1] eq 'optgroup') { |
$self->{open_elements}->[-2]->[1] & OPTGROUP_EL) { |
| 6279 |
!!!cp ('t283'); |
!!!cp ('t283'); |
| 6280 |
## As if </option> |
## As if </option> |
| 6281 |
splice @{$self->{open_elements}}, -2; |
splice @{$self->{open_elements}}, -2; |
| 6282 |
} elsif ($self->{open_elements}->[-1]->[1] eq 'optgroup') { |
} elsif ($self->{open_elements}->[-1]->[1] & OPTGROUP_EL) { |
| 6283 |
!!!cp ('t284'); |
!!!cp ('t284'); |
| 6284 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 6285 |
} else { |
} else { |
| 6286 |
!!!cp ('t285'); |
!!!cp ('t285'); |
| 6287 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 6288 |
## Ignore the token |
text => $token->{tag_name}, token => $token); |
| 6289 |
} |
## Ignore the token |
| 6290 |
!!!next-token; |
} |
| 6291 |
redo B; |
!!!nack ('t285.1'); |
| 6292 |
} elsif ($token->{tag_name} eq 'option') { |
!!!next-token; |
| 6293 |
if ($self->{open_elements}->[-1]->[1] eq 'option') { |
next B; |
| 6294 |
!!!cp ('t286'); |
} elsif ($token->{tag_name} eq 'option') { |
| 6295 |
pop @{$self->{open_elements}}; |
if ($self->{open_elements}->[-1]->[1] & OPTION_EL) { |
| 6296 |
} else { |
!!!cp ('t286'); |
| 6297 |
!!!cp ('t287'); |
pop @{$self->{open_elements}}; |
| 6298 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
} else { |
| 6299 |
## Ignore the token |
!!!cp ('t287'); |
| 6300 |
} |
!!!parse-error (type => 'unmatched end tag', |
| 6301 |
!!!next-token; |
text => $token->{tag_name}, token => $token); |
| 6302 |
redo B; |
## Ignore the token |
| 6303 |
} elsif ($token->{tag_name} eq 'select') { |
} |
| 6304 |
## have an element in table scope |
!!!nack ('t287.1'); |
| 6305 |
my $i; |
!!!next-token; |
| 6306 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
next B; |
| 6307 |
my $node = $self->{open_elements}->[$_]; |
} elsif ($token->{tag_name} eq 'select') { |
| 6308 |
if ($node->[1] eq $token->{tag_name}) { |
## have an element in table scope |
| 6309 |
!!!cp ('t288'); |
my $i; |
| 6310 |
$i = $_; |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 6311 |
last INSCOPE; |
my $node = $self->{open_elements}->[$_]; |
| 6312 |
} elsif ({ |
if ($node->[1] & SELECT_EL) { |
| 6313 |
table => 1, html => 1, |
!!!cp ('t288'); |
| 6314 |
}->{$node->[1]}) { |
$i = $_; |
| 6315 |
!!!cp ('t289'); |
last INSCOPE; |
| 6316 |
last INSCOPE; |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
| 6317 |
} |
!!!cp ('t289'); |
| 6318 |
} # INSCOPE |
last INSCOPE; |
| 6319 |
unless (defined $i) { |
} |
| 6320 |
!!!cp ('t290'); |
} # INSCOPE |
| 6321 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
unless (defined $i) { |
| 6322 |
## Ignore the token |
!!!cp ('t290'); |
| 6323 |
!!!next-token; |
!!!parse-error (type => 'unmatched end tag', |
| 6324 |
redo B; |
text => $token->{tag_name}, token => $token); |
| 6325 |
} |
## Ignore the token |
| 6326 |
|
!!!nack ('t290.1'); |
| 6327 |
|
!!!next-token; |
| 6328 |
|
next B; |
| 6329 |
|
} |
| 6330 |
|
|
| 6331 |
!!!cp ('t291'); |
!!!cp ('t291'); |
| 6332 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 6333 |
|
|
| 6334 |
$self->_reset_insertion_mode; |
$self->_reset_insertion_mode; |
| 6335 |
|
|
| 6336 |
!!!next-token; |
!!!nack ('t291.1'); |
| 6337 |
redo B; |
!!!next-token; |
| 6338 |
|
next B; |
| 6339 |
} elsif ($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
} elsif ($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
| 6340 |
{ |
{ |
| 6341 |
caption => 1, table => 1, tbody => 1, |
caption => 1, table => 1, tbody => 1, |
| 6342 |
tfoot => 1, thead => 1, tr => 1, td => 1, th => 1, |
tfoot => 1, thead => 1, tr => 1, td => 1, th => 1, |
| 6343 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6344 |
## TODO: The following is wrong? |
## TODO: The following is wrong? |
| 6345 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 6346 |
|
text => $token->{tag_name}, token => $token); |
| 6347 |
|
|
| 6348 |
## have an element in table scope |
## have an element in table scope |
| 6349 |
my $i; |
my $i; |
| 6350 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 6351 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 6352 |
if ($node->[1] eq $token->{tag_name}) { |
if ($node->[0]->manakai_local_name eq $token->{tag_name}) { |
| 6353 |
!!!cp ('t292'); |
!!!cp ('t292'); |
| 6354 |
$i = $_; |
$i = $_; |
| 6355 |
last INSCOPE; |
last INSCOPE; |
| 6356 |
} elsif ({ |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
| 6357 |
table => 1, html => 1, |
!!!cp ('t293'); |
| 6358 |
}->{$node->[1]}) { |
last INSCOPE; |
| 6359 |
!!!cp ('t293'); |
} |
| 6360 |
last INSCOPE; |
} # INSCOPE |
| 6361 |
} |
unless (defined $i) { |
| 6362 |
} # INSCOPE |
!!!cp ('t294'); |
| 6363 |
unless (defined $i) { |
## Ignore the token |
| 6364 |
!!!cp ('t294'); |
!!!nack ('t294.1'); |
| 6365 |
## Ignore the token |
!!!next-token; |
| 6366 |
!!!next-token; |
next B; |
| 6367 |
redo B; |
} |
|
} |
|
| 6368 |
|
|
| 6369 |
## As if </select> |
## As if </select> |
| 6370 |
## have an element in table scope |
## have an element in table scope |
| 6371 |
undef $i; |
undef $i; |
| 6372 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 6373 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 6374 |
if ($node->[1] eq 'select') { |
if ($node->[1] & SELECT_EL) { |
| 6375 |
!!!cp ('t295'); |
!!!cp ('t295'); |
| 6376 |
$i = $_; |
$i = $_; |
| 6377 |
last INSCOPE; |
last INSCOPE; |
| 6378 |
} elsif ({ |
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
| 6379 |
## ISSUE: Can this state be reached? |
## ISSUE: Can this state be reached? |
| 6380 |
!!!cp ('t296'); |
!!!cp ('t296'); |
| 6381 |
last INSCOPE; |
last INSCOPE; |
| 6382 |
} |
} |
| 6383 |
} # INSCOPE |
} # INSCOPE |
| 6384 |
unless (defined $i) { |
unless (defined $i) { |
| 6385 |
!!!cp ('t297'); |
!!!cp ('t297'); |
| 6386 |
## TODO: The following error type is correct? |
## TODO: The following error type is correct? |
| 6387 |
!!!parse-error (type => 'unmatched end tag:select'); |
!!!parse-error (type => 'unmatched end tag', |
| 6388 |
## Ignore the </select> token |
text => 'select', token => $token); |
| 6389 |
!!!next-token; ## TODO: ok? |
## Ignore the </select> token |
| 6390 |
redo B; |
!!!nack ('t297.1'); |
| 6391 |
} |
!!!next-token; ## TODO: ok? |
| 6392 |
|
next B; |
| 6393 |
|
} |
| 6394 |
|
|
| 6395 |
!!!cp ('t298'); |
!!!cp ('t298'); |
| 6396 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 6397 |
|
|
| 6398 |
$self->_reset_insertion_mode; |
$self->_reset_insertion_mode; |
| 6399 |
|
|
| 6400 |
## reprocess |
!!!ack-later; |
| 6401 |
redo B; |
## reprocess |
| 6402 |
|
next B; |
| 6403 |
} else { |
} else { |
| 6404 |
!!!cp ('t299'); |
!!!cp ('t299'); |
| 6405 |
!!!parse-error (type => 'in select:/'.$token->{tag_name}); |
!!!parse-error (type => 'in select:/', |
| 6406 |
|
text => $token->{tag_name}, token => $token); |
| 6407 |
## Ignore the token |
## Ignore the token |
| 6408 |
|
!!!nack ('t299.3'); |
| 6409 |
!!!next-token; |
!!!next-token; |
| 6410 |
redo B; |
next B; |
| 6411 |
} |
} |
| 6412 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 6413 |
unless ($self->{open_elements}->[-1]->[1] eq 'html' and |
unless ($self->{open_elements}->[-1]->[1] & HTML_EL and |
| 6414 |
@{$self->{open_elements}} == 1) { # redundant, maybe |
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 6415 |
!!!cp ('t299.1'); |
!!!cp ('t299.1'); |
| 6416 |
!!!parse-error (type => 'in body:#eof'); |
!!!parse-error (type => 'in body:#eof', token => $token); |
| 6417 |
} else { |
} else { |
| 6418 |
!!!cp ('t299.2'); |
!!!cp ('t299.2'); |
| 6419 |
} |
} |
| 6435 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 6436 |
!!!cp ('t300'); |
!!!cp ('t300'); |
| 6437 |
!!!next-token; |
!!!next-token; |
| 6438 |
redo B; |
next B; |
| 6439 |
} |
} |
| 6440 |
} |
} |
| 6441 |
|
|
| 6442 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 6443 |
!!!cp ('t301'); |
!!!cp ('t301'); |
| 6444 |
!!!parse-error (type => 'after html:#character'); |
!!!parse-error (type => 'after html:#text', token => $token); |
| 6445 |
|
|
| 6446 |
## Reprocess in the "after body" insertion mode. |
## Reprocess in the "after body" insertion mode. |
| 6447 |
} else { |
} else { |
| 6449 |
} |
} |
| 6450 |
|
|
| 6451 |
## "after body" insertion mode |
## "after body" insertion mode |
| 6452 |
!!!parse-error (type => 'after body:#character'); |
!!!parse-error (type => 'after body:#text', token => $token); |
| 6453 |
|
|
| 6454 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 6455 |
## reprocess |
## reprocess |
| 6456 |
redo B; |
next B; |
| 6457 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 6458 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 6459 |
!!!cp ('t303'); |
!!!cp ('t303'); |
| 6460 |
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
!!!parse-error (type => 'after html', |
| 6461 |
|
text => $token->{tag_name}, token => $token); |
| 6462 |
|
|
| 6463 |
## Reprocess in the "after body" insertion mode. |
## Reprocess in the "after body" insertion mode. |
| 6464 |
} else { |
} else { |
| 6466 |
} |
} |
| 6467 |
|
|
| 6468 |
## "after body" insertion mode |
## "after body" insertion mode |
| 6469 |
!!!parse-error (type => 'after body:'.$token->{tag_name}); |
!!!parse-error (type => 'after body', |
| 6470 |
|
text => $token->{tag_name}, token => $token); |
| 6471 |
|
|
| 6472 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 6473 |
|
!!!ack-later; |
| 6474 |
## reprocess |
## reprocess |
| 6475 |
redo B; |
next B; |
| 6476 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 6477 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 6478 |
!!!cp ('t305'); |
!!!cp ('t305'); |
| 6479 |
!!!parse-error (type => 'after html:/'.$token->{tag_name}); |
!!!parse-error (type => 'after html:/', |
| 6480 |
|
text => $token->{tag_name}, token => $token); |
| 6481 |
|
|
| 6482 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 6483 |
## Reprocess in the "after body" insertion mode. |
## Reprocess in the "after body" insertion mode. |
| 6489 |
if ($token->{tag_name} eq 'html') { |
if ($token->{tag_name} eq 'html') { |
| 6490 |
if (defined $self->{inner_html_node}) { |
if (defined $self->{inner_html_node}) { |
| 6491 |
!!!cp ('t307'); |
!!!cp ('t307'); |
| 6492 |
!!!parse-error (type => 'unmatched end tag:html'); |
!!!parse-error (type => 'unmatched end tag', |
| 6493 |
|
text => 'html', token => $token); |
| 6494 |
## Ignore the token |
## Ignore the token |
| 6495 |
!!!next-token; |
!!!next-token; |
| 6496 |
redo B; |
next B; |
| 6497 |
} else { |
} else { |
| 6498 |
!!!cp ('t308'); |
!!!cp ('t308'); |
| 6499 |
$self->{insertion_mode} = AFTER_HTML_BODY_IM; |
$self->{insertion_mode} = AFTER_HTML_BODY_IM; |
| 6500 |
!!!next-token; |
!!!next-token; |
| 6501 |
redo B; |
next B; |
| 6502 |
} |
} |
| 6503 |
} else { |
} else { |
| 6504 |
!!!cp ('t309'); |
!!!cp ('t309'); |
| 6505 |
!!!parse-error (type => 'after body:/'.$token->{tag_name}); |
!!!parse-error (type => 'after body:/', |
| 6506 |
|
text => $token->{tag_name}, token => $token); |
| 6507 |
|
|
| 6508 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 6509 |
## reprocess |
## reprocess |
| 6510 |
redo B; |
next B; |
| 6511 |
} |
} |
| 6512 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 6513 |
!!!cp ('t309.2'); |
!!!cp ('t309.2'); |
| 6524 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 6525 |
!!!cp ('t310'); |
!!!cp ('t310'); |
| 6526 |
!!!next-token; |
!!!next-token; |
| 6527 |
redo B; |
next B; |
| 6528 |
} |
} |
| 6529 |
} |
} |
| 6530 |
|
|
| 6531 |
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
| 6532 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6533 |
!!!cp ('t311'); |
!!!cp ('t311'); |
| 6534 |
!!!parse-error (type => 'in frameset:#character'); |
!!!parse-error (type => 'in frameset:#text', token => $token); |
| 6535 |
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 6536 |
!!!cp ('t312'); |
!!!cp ('t312'); |
| 6537 |
!!!parse-error (type => 'after frameset:#character'); |
!!!parse-error (type => 'after frameset:#text', token => $token); |
| 6538 |
} else { # "after html frameset" |
} else { # "after after frameset" |
| 6539 |
!!!cp ('t313'); |
!!!cp ('t313'); |
| 6540 |
!!!parse-error (type => 'after html:#character'); |
!!!parse-error (type => 'after html:#text', token => $token); |
|
|
|
|
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
|
|
## Reprocess in the "after frameset" insertion mode. |
|
|
!!!parse-error (type => 'after frameset:#character'); |
|
| 6541 |
} |
} |
| 6542 |
|
|
| 6543 |
## Ignore the token. |
## Ignore the token. |
| 6548 |
!!!cp ('t315'); |
!!!cp ('t315'); |
| 6549 |
!!!next-token; |
!!!next-token; |
| 6550 |
} |
} |
| 6551 |
redo B; |
next B; |
| 6552 |
} |
} |
| 6553 |
|
|
| 6554 |
die qq[$0: Character "$token->{data}"]; |
die qq[$0: Character "$token->{data}"]; |
| 6555 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
|
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
|
|
!!!cp ('t316'); |
|
|
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
|
|
|
|
|
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
|
|
## Process in the "after frameset" insertion mode. |
|
|
} else { |
|
|
!!!cp ('t317'); |
|
|
} |
|
|
|
|
| 6556 |
if ($token->{tag_name} eq 'frameset' and |
if ($token->{tag_name} eq 'frameset' and |
| 6557 |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6558 |
!!!cp ('t318'); |
!!!cp ('t318'); |
| 6559 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 6560 |
|
!!!nack ('t318.1'); |
| 6561 |
!!!next-token; |
!!!next-token; |
| 6562 |
redo B; |
next B; |
| 6563 |
} elsif ($token->{tag_name} eq 'frame' and |
} elsif ($token->{tag_name} eq 'frame' and |
| 6564 |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6565 |
!!!cp ('t319'); |
!!!cp ('t319'); |
| 6566 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 6567 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 6568 |
|
!!!ack ('t319.1'); |
| 6569 |
!!!next-token; |
!!!next-token; |
| 6570 |
redo B; |
next B; |
| 6571 |
} elsif ($token->{tag_name} eq 'noframes') { |
} elsif ($token->{tag_name} eq 'noframes') { |
| 6572 |
!!!cp ('t320'); |
!!!cp ('t320'); |
| 6573 |
## NOTE: As if in body. |
## NOTE: As if in head. |
| 6574 |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 6575 |
redo B; |
next B; |
| 6576 |
|
|
| 6577 |
|
## NOTE: |<!DOCTYPE HTML><frameset></frameset></html><noframes></noframes>| |
| 6578 |
|
## has no parse error. |
| 6579 |
} else { |
} else { |
| 6580 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6581 |
!!!cp ('t321'); |
!!!cp ('t321'); |
| 6582 |
!!!parse-error (type => 'in frameset:'.$token->{tag_name}); |
!!!parse-error (type => 'in frameset', |
| 6583 |
} else { |
text => $token->{tag_name}, token => $token); |
| 6584 |
|
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 6585 |
!!!cp ('t322'); |
!!!cp ('t322'); |
| 6586 |
!!!parse-error (type => 'after frameset:'.$token->{tag_name}); |
!!!parse-error (type => 'after frameset', |
| 6587 |
|
text => $token->{tag_name}, token => $token); |
| 6588 |
|
} else { # "after after frameset" |
| 6589 |
|
!!!cp ('t322.2'); |
| 6590 |
|
!!!parse-error (type => 'after after frameset', |
| 6591 |
|
text => $token->{tag_name}, token => $token); |
| 6592 |
} |
} |
| 6593 |
## Ignore the token |
## Ignore the token |
| 6594 |
|
!!!nack ('t322.1'); |
| 6595 |
!!!next-token; |
!!!next-token; |
| 6596 |
redo B; |
next B; |
| 6597 |
} |
} |
| 6598 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
|
if ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
|
|
!!!cp ('t323'); |
|
|
!!!parse-error (type => 'after html:/'.$token->{tag_name}); |
|
|
|
|
|
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
|
|
## Process in the "after frameset" insertion mode. |
|
|
} else { |
|
|
!!!cp ('t324'); |
|
|
} |
|
|
|
|
| 6599 |
if ($token->{tag_name} eq 'frameset' and |
if ($token->{tag_name} eq 'frameset' and |
| 6600 |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6601 |
if ($self->{open_elements}->[-1]->[1] eq 'html' and |
if ($self->{open_elements}->[-1]->[1] & HTML_EL and |
| 6602 |
@{$self->{open_elements}} == 1) { |
@{$self->{open_elements}} == 1) { |
| 6603 |
!!!cp ('t325'); |
!!!cp ('t325'); |
| 6604 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 6605 |
|
text => $token->{tag_name}, token => $token); |
| 6606 |
## Ignore the token |
## Ignore the token |
| 6607 |
!!!next-token; |
!!!next-token; |
| 6608 |
} else { |
} else { |
| 6612 |
} |
} |
| 6613 |
|
|
| 6614 |
if (not defined $self->{inner_html_node} and |
if (not defined $self->{inner_html_node} and |
| 6615 |
$self->{open_elements}->[-1]->[1] ne 'frameset') { |
not ($self->{open_elements}->[-1]->[1] & FRAMESET_EL)) { |
| 6616 |
!!!cp ('t327'); |
!!!cp ('t327'); |
| 6617 |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 6618 |
} else { |
} else { |
| 6619 |
!!!cp ('t328'); |
!!!cp ('t328'); |
| 6620 |
} |
} |
| 6621 |
redo B; |
next B; |
| 6622 |
} elsif ($token->{tag_name} eq 'html' and |
} elsif ($token->{tag_name} eq 'html' and |
| 6623 |
$self->{insertion_mode} == AFTER_FRAMESET_IM) { |
$self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 6624 |
!!!cp ('t329'); |
!!!cp ('t329'); |
| 6625 |
$self->{insertion_mode} = AFTER_HTML_FRAMESET_IM; |
$self->{insertion_mode} = AFTER_HTML_FRAMESET_IM; |
| 6626 |
!!!next-token; |
!!!next-token; |
| 6627 |
redo B; |
next B; |
| 6628 |
} else { |
} else { |
| 6629 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 6630 |
!!!cp ('t330'); |
!!!cp ('t330'); |
| 6631 |
!!!parse-error (type => 'in frameset:/'.$token->{tag_name}); |
!!!parse-error (type => 'in frameset:/', |
| 6632 |
} else { |
text => $token->{tag_name}, token => $token); |
| 6633 |
|
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 6634 |
|
!!!cp ('t330.1'); |
| 6635 |
|
!!!parse-error (type => 'after frameset:/', |
| 6636 |
|
text => $token->{tag_name}, token => $token); |
| 6637 |
|
} else { # "after after html" |
| 6638 |
!!!cp ('t331'); |
!!!cp ('t331'); |
| 6639 |
!!!parse-error (type => 'after frameset:/'.$token->{tag_name}); |
!!!parse-error (type => 'after after frameset:/', |
| 6640 |
|
text => $token->{tag_name}, token => $token); |
| 6641 |
} |
} |
| 6642 |
## Ignore the token |
## Ignore the token |
| 6643 |
!!!next-token; |
!!!next-token; |
| 6644 |
redo B; |
next B; |
| 6645 |
} |
} |
| 6646 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 6647 |
unless ($self->{open_elements}->[-1]->[1] eq 'html' and |
unless ($self->{open_elements}->[-1]->[1] & HTML_EL and |
| 6648 |
@{$self->{open_elements}} == 1) { # redundant, maybe |
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 6649 |
!!!cp ('t331.1'); |
!!!cp ('t331.1'); |
| 6650 |
!!!parse-error (type => 'in body:#eof'); |
!!!parse-error (type => 'in body:#eof', token => $token); |
| 6651 |
} else { |
} else { |
| 6652 |
!!!cp ('t331.2'); |
!!!cp ('t331.2'); |
| 6653 |
} |
} |
| 6669 |
!!!cp ('t332'); |
!!!cp ('t332'); |
| 6670 |
## NOTE: This is an "as if in head" code clone |
## NOTE: This is an "as if in head" code clone |
| 6671 |
$script_start_tag->(); |
$script_start_tag->(); |
| 6672 |
redo B; |
next B; |
| 6673 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($token->{tag_name} eq 'style') { |
| 6674 |
!!!cp ('t333'); |
!!!cp ('t333'); |
| 6675 |
## NOTE: This is an "as if in head" code clone |
## NOTE: This is an "as if in head" code clone |
| 6676 |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 6677 |
redo B; |
next B; |
| 6678 |
} elsif ({ |
} elsif ({ |
| 6679 |
base => 1, link => 1, |
base => 1, link => 1, |
| 6680 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6681 |
!!!cp ('t334'); |
!!!cp ('t334'); |
| 6682 |
## NOTE: This is an "as if in head" code clone, only "-t" differs |
## NOTE: This is an "as if in head" code clone, only "-t" differs |
| 6683 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 6684 |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 6685 |
|
!!!ack ('t334.1'); |
| 6686 |
!!!next-token; |
!!!next-token; |
| 6687 |
redo B; |
next B; |
| 6688 |
} elsif ($token->{tag_name} eq 'meta') { |
} elsif ($token->{tag_name} eq 'meta') { |
| 6689 |
## NOTE: This is an "as if in head" code clone, only "-t" differs |
## NOTE: This is an "as if in head" code clone, only "-t" differs |
| 6690 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 6691 |
my $meta_el = pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
my $meta_el = pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 6692 |
|
|
| 6693 |
unless ($self->{confident}) { |
unless ($self->{confident}) { |
| 6694 |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
if ($token->{attributes}->{charset}) { |
| 6695 |
!!!cp ('t335'); |
!!!cp ('t335'); |
| 6696 |
|
## NOTE: Whether the encoding is supported or not is handled |
| 6697 |
|
## in the {change_encoding} callback. |
| 6698 |
$self->{change_encoding} |
$self->{change_encoding} |
| 6699 |
->($self, $token->{attributes}->{charset}->{value}); |
->($self, $token->{attributes}->{charset}->{value}, $token); |
| 6700 |
|
|
| 6701 |
$meta_el->[0]->get_attribute_node_ns (undef, 'charset') |
$meta_el->[0]->get_attribute_node_ns (undef, 'charset') |
| 6702 |
->set_user_data (manakai_has_reference => |
->set_user_data (manakai_has_reference => |
| 6703 |
$token->{attributes}->{charset} |
$token->{attributes}->{charset} |
| 6704 |
->{has_reference}); |
->{has_reference}); |
| 6705 |
} elsif ($token->{attributes}->{content}) { |
} elsif ($token->{attributes}->{content}) { |
|
## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition. |
|
| 6706 |
if ($token->{attributes}->{content}->{value} |
if ($token->{attributes}->{content}->{value} |
| 6707 |
=~ /\A[^;]*;[\x09-\x0D\x20]*[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
=~ /[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
| 6708 |
[\x09-\x0D\x20]*= |
[\x09-\x0D\x20]*= |
| 6709 |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
| 6710 |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20\x3B]*))/x) { |
| 6711 |
!!!cp ('t336'); |
!!!cp ('t336'); |
| 6712 |
|
## NOTE: Whether the encoding is supported or not is handled |
| 6713 |
|
## in the {change_encoding} callback. |
| 6714 |
$self->{change_encoding} |
$self->{change_encoding} |
| 6715 |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3); |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3, $token); |
| 6716 |
$meta_el->[0]->get_attribute_node_ns (undef, 'content') |
$meta_el->[0]->get_attribute_node_ns (undef, 'content') |
| 6717 |
->set_user_data (manakai_has_reference => |
->set_user_data (manakai_has_reference => |
| 6718 |
$token->{attributes}->{content} |
$token->{attributes}->{content} |
| 6736 |
} |
} |
| 6737 |
} |
} |
| 6738 |
|
|
| 6739 |
|
!!!ack ('t338.1'); |
| 6740 |
!!!next-token; |
!!!next-token; |
| 6741 |
redo B; |
next B; |
| 6742 |
} elsif ($token->{tag_name} eq 'title') { |
} elsif ($token->{tag_name} eq 'title') { |
| 6743 |
!!!cp ('t341'); |
!!!cp ('t341'); |
| 6744 |
## NOTE: This is an "as if in head" code clone |
## NOTE: This is an "as if in head" code clone |
| 6745 |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
| 6746 |
redo B; |
next B; |
| 6747 |
} elsif ($token->{tag_name} eq 'body') { |
} elsif ($token->{tag_name} eq 'body') { |
| 6748 |
!!!parse-error (type => 'in body:body'); |
!!!parse-error (type => 'in body', text => 'body', token => $token); |
| 6749 |
|
|
| 6750 |
if (@{$self->{open_elements}} == 1 or |
if (@{$self->{open_elements}} == 1 or |
| 6751 |
$self->{open_elements}->[1]->[1] ne 'body') { |
not ($self->{open_elements}->[1]->[1] & BODY_EL)) { |
| 6752 |
!!!cp ('t342'); |
!!!cp ('t342'); |
| 6753 |
## Ignore the token |
## Ignore the token |
| 6754 |
} else { |
} else { |
| 6762 |
} |
} |
| 6763 |
} |
} |
| 6764 |
} |
} |
| 6765 |
|
!!!nack ('t343.1'); |
| 6766 |
!!!next-token; |
!!!next-token; |
| 6767 |
redo B; |
next B; |
| 6768 |
} elsif ({ |
} elsif ({ |
| 6769 |
address => 1, blockquote => 1, center => 1, dir => 1, |
address => 1, blockquote => 1, center => 1, dir => 1, |
| 6770 |
div => 1, dl => 1, fieldset => 1, |
div => 1, dl => 1, fieldset => 1, |
| 6771 |
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
| 6772 |
menu => 1, ol => 1, p => 1, ul => 1, |
menu => 1, ol => 1, p => 1, ul => 1, |
| 6773 |
pre => 1, listing => 1, |
pre => 1, listing => 1, |
| 6774 |
|
form => 1, |
| 6775 |
|
table => 1, |
| 6776 |
|
hr => 1, |
| 6777 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 6778 |
|
if ($token->{tag_name} eq 'form' and defined $self->{form_element}) { |
| 6779 |
|
!!!cp ('t350'); |
| 6780 |
|
!!!parse-error (type => 'in form:form', token => $token); |
| 6781 |
|
## Ignore the token |
| 6782 |
|
!!!nack ('t350.1'); |
| 6783 |
|
!!!next-token; |
| 6784 |
|
next B; |
| 6785 |
|
} |
| 6786 |
|
|
| 6787 |
## has a p element in scope |
## has a p element in scope |
| 6788 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 6789 |
if ($_->[1] eq 'p') { |
if ($_->[1] & P_EL) { |
| 6790 |
!!!cp ('t344'); |
!!!cp ('t344'); |
| 6791 |
!!!back-token; |
!!!back-token; # <form> |
| 6792 |
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
| 6793 |
redo B; |
line => $token->{line}, column => $token->{column}}; |
| 6794 |
} elsif ({ |
next B; |
| 6795 |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
} elsif ($_->[1] & SCOPING_EL) { |
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
| 6796 |
!!!cp ('t345'); |
!!!cp ('t345'); |
| 6797 |
last INSCOPE; |
last INSCOPE; |
| 6798 |
} |
} |
| 6799 |
} # INSCOPE |
} # INSCOPE |
| 6800 |
|
|
| 6801 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 6802 |
if ($token->{tag_name} eq 'pre' or $token->{tag_name} eq 'listing') { |
if ($token->{tag_name} eq 'pre' or $token->{tag_name} eq 'listing') { |
| 6803 |
|
!!!nack ('t346.1'); |
| 6804 |
!!!next-token; |
!!!next-token; |
| 6805 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 6806 |
$token->{data} =~ s/^\x0A//; |
$token->{data} =~ s/^\x0A//; |
| 6813 |
} else { |
} else { |
| 6814 |
!!!cp ('t348'); |
!!!cp ('t348'); |
| 6815 |
} |
} |
| 6816 |
} else { |
} elsif ($token->{tag_name} eq 'form') { |
| 6817 |
!!!cp ('t347'); |
!!!cp ('t347.1'); |
| 6818 |
|
$self->{form_element} = $self->{open_elements}->[-1]->[0]; |
| 6819 |
|
|
| 6820 |
|
!!!nack ('t347.2'); |
| 6821 |
!!!next-token; |
!!!next-token; |
| 6822 |
} |
} elsif ($token->{tag_name} eq 'table') { |
| 6823 |
redo B; |
!!!cp ('t382'); |
| 6824 |
} elsif ($token->{tag_name} eq 'form') { |
push @{$open_tables}, [$self->{open_elements}->[-1]->[0]]; |
| 6825 |
if (defined $self->{form_element}) { |
|
| 6826 |
!!!cp ('t350'); |
$self->{insertion_mode} = IN_TABLE_IM; |
| 6827 |
!!!parse-error (type => 'in form:form'); |
|
| 6828 |
## Ignore the token |
!!!nack ('t382.1'); |
| 6829 |
|
!!!next-token; |
| 6830 |
|
} elsif ($token->{tag_name} eq 'hr') { |
| 6831 |
|
!!!cp ('t386'); |
| 6832 |
|
pop @{$self->{open_elements}}; |
| 6833 |
|
|
| 6834 |
|
!!!nack ('t386.1'); |
| 6835 |
!!!next-token; |
!!!next-token; |
|
redo B; |
|
| 6836 |
} else { |
} else { |
| 6837 |
## has a p element in scope |
!!!nack ('t347.1'); |
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
|
|
if ($_->[1] eq 'p') { |
|
|
!!!cp ('t351'); |
|
|
!!!back-token; |
|
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
|
|
redo B; |
|
|
} elsif ({ |
|
|
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
|
!!!cp ('t352'); |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
$self->{form_element} = $self->{open_elements}->[-1]->[0]; |
|
| 6838 |
!!!next-token; |
!!!next-token; |
|
redo B; |
|
| 6839 |
} |
} |
| 6840 |
} elsif ($token->{tag_name} eq 'li') { |
next B; |
| 6841 |
|
} elsif ({li => 1, dt => 1, dd => 1}->{$token->{tag_name}}) { |
| 6842 |
## has a p element in scope |
## has a p element in scope |
| 6843 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 6844 |
if ($_->[1] eq 'p') { |
if ($_->[1] & P_EL) { |
| 6845 |
!!!cp ('t353'); |
!!!cp ('t353'); |
| 6846 |
!!!back-token; |
!!!back-token; # <x> |
| 6847 |
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
| 6848 |
redo B; |
line => $token->{line}, column => $token->{column}}; |
| 6849 |
} elsif ({ |
next B; |
| 6850 |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
} elsif ($_->[1] & SCOPING_EL) { |
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
| 6851 |
!!!cp ('t354'); |
!!!cp ('t354'); |
| 6852 |
last INSCOPE; |
last INSCOPE; |
| 6853 |
} |
} |
| 6856 |
## Step 1 |
## Step 1 |
| 6857 |
my $i = -1; |
my $i = -1; |
| 6858 |
my $node = $self->{open_elements}->[$i]; |
my $node = $self->{open_elements}->[$i]; |
| 6859 |
|
my $li_or_dtdd = {li => {li => 1}, |
| 6860 |
|
dt => {dt => 1, dd => 1}, |
| 6861 |
|
dd => {dt => 1, dd => 1}}->{$token->{tag_name}}; |
| 6862 |
LI: { |
LI: { |
| 6863 |
## Step 2 |
## Step 2 |
| 6864 |
if ($node->[1] eq 'li') { |
if ($li_or_dtdd->{$node->[0]->manakai_local_name}) { |
| 6865 |
if ($i != -1) { |
if ($i != -1) { |
| 6866 |
!!!cp ('t355'); |
!!!cp ('t355'); |
| 6867 |
!!!parse-error (type => 'end tag missing:'. |
!!!parse-error (type => 'not closed', |
| 6868 |
$self->{open_elements}->[-1]->[1]); |
text => $self->{open_elements}->[-1]->[0] |
| 6869 |
|
->manakai_local_name, |
| 6870 |
|
token => $token); |
| 6871 |
} else { |
} else { |
| 6872 |
!!!cp ('t356'); |
!!!cp ('t356'); |
| 6873 |
} |
} |
| 6878 |
} |
} |
| 6879 |
|
|
| 6880 |
## Step 3 |
## Step 3 |
| 6881 |
if (not $formatting_category->{$node->[1]} and |
if (not ($node->[1] & FORMATTING_EL) and |
| 6882 |
#not $phrasing_category->{$node->[1]} and |
#not $phrasing_category->{$node->[1]} and |
| 6883 |
($special_category->{$node->[1]} or |
($node->[1] & SPECIAL_EL or |
| 6884 |
$scoping_category->{$node->[1]}) and |
$node->[1] & SCOPING_EL) and |
| 6885 |
$node->[1] ne 'address' and $node->[1] ne 'div') { |
not ($node->[1] & ADDRESS_EL) and |
| 6886 |
|
not ($node->[1] & DIV_EL)) { |
| 6887 |
!!!cp ('t358'); |
!!!cp ('t358'); |
| 6888 |
last LI; |
last LI; |
| 6889 |
} |
} |
| 6895 |
redo LI; |
redo LI; |
| 6896 |
} # LI |
} # LI |
| 6897 |
|
|
| 6898 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 6899 |
|
!!!nack ('t359.1'); |
| 6900 |
!!!next-token; |
!!!next-token; |
| 6901 |
redo B; |
next B; |
|
} elsif ($token->{tag_name} eq 'dd' or $token->{tag_name} eq 'dt') { |
|
|
## has a p element in scope |
|
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
|
|
if ($_->[1] eq 'p') { |
|
|
!!!cp ('t360'); |
|
|
!!!back-token; |
|
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
|
|
redo B; |
|
|
} elsif ({ |
|
|
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
|
!!!cp ('t361'); |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
## Step 1 |
|
|
my $i = -1; |
|
|
my $node = $self->{open_elements}->[$i]; |
|
|
LI: { |
|
|
## Step 2 |
|
|
if ($node->[1] eq 'dt' or $node->[1] eq 'dd') { |
|
|
if ($i != -1) { |
|
|
!!!cp ('t362'); |
|
|
!!!parse-error (type => 'end tag missing:'. |
|
|
$self->{open_elements}->[-1]->[1]); |
|
|
} else { |
|
|
!!!cp ('t363'); |
|
|
} |
|
|
splice @{$self->{open_elements}}, $i; |
|
|
last LI; |
|
|
} else { |
|
|
!!!cp ('t364'); |
|
|
} |
|
|
|
|
|
## Step 3 |
|
|
if (not $formatting_category->{$node->[1]} and |
|
|
#not $phrasing_category->{$node->[1]} and |
|
|
($special_category->{$node->[1]} or |
|
|
$scoping_category->{$node->[1]}) and |
|
|
$node->[1] ne 'address' and $node->[1] ne 'div') { |
|
|
!!!cp ('t365'); |
|
|
last LI; |
|
|
} |
|
|
|
|
|
!!!cp ('t366'); |
|
|
## Step 4 |
|
|
$i--; |
|
|
$node = $self->{open_elements}->[$i]; |
|
|
redo LI; |
|
|
} # LI |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 6902 |
} elsif ($token->{tag_name} eq 'plaintext') { |
} elsif ($token->{tag_name} eq 'plaintext') { |
| 6903 |
## has a p element in scope |
## has a p element in scope |
| 6904 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 6905 |
if ($_->[1] eq 'p') { |
if ($_->[1] & P_EL) { |
| 6906 |
!!!cp ('t367'); |
!!!cp ('t367'); |
| 6907 |
!!!back-token; |
!!!back-token; # <plaintext> |
| 6908 |
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
| 6909 |
redo B; |
line => $token->{line}, column => $token->{column}}; |
| 6910 |
} elsif ({ |
next B; |
| 6911 |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
} elsif ($_->[1] & SCOPING_EL) { |
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
| 6912 |
!!!cp ('t368'); |
!!!cp ('t368'); |
| 6913 |
last INSCOPE; |
last INSCOPE; |
| 6914 |
} |
} |
| 6915 |
} # INSCOPE |
} # INSCOPE |
| 6916 |
|
|
| 6917 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 6918 |
|
|
| 6919 |
$self->{content_model} = PLAINTEXT_CONTENT_MODEL; |
$self->{content_model} = PLAINTEXT_CONTENT_MODEL; |
| 6920 |
|
|
| 6921 |
|
!!!nack ('t368.1'); |
| 6922 |
!!!next-token; |
!!!next-token; |
| 6923 |
redo B; |
next B; |
| 6924 |
} elsif ($token->{tag_name} eq 'a') { |
} elsif ($token->{tag_name} eq 'a') { |
| 6925 |
AFE: for my $i (reverse 0..$#$active_formatting_elements) { |
AFE: for my $i (reverse 0..$#$active_formatting_elements) { |
| 6926 |
my $node = $active_formatting_elements->[$i]; |
my $node = $active_formatting_elements->[$i]; |
| 6927 |
if ($node->[1] eq 'a') { |
if ($node->[1] & A_EL) { |
| 6928 |
!!!cp ('t371'); |
!!!cp ('t371'); |
| 6929 |
!!!parse-error (type => 'in a:a'); |
!!!parse-error (type => 'in a:a', token => $token); |
| 6930 |
|
|
| 6931 |
!!!back-token; |
!!!back-token; # <a> |
| 6932 |
$token = {type => END_TAG_TOKEN, tag_name => 'a'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'a', |
| 6933 |
$formatting_end_tag->($token->{tag_name}); |
line => $token->{line}, column => $token->{column}}; |
| 6934 |
|
$formatting_end_tag->($token); |
| 6935 |
|
|
| 6936 |
AFE2: for (reverse 0..$#$active_formatting_elements) { |
AFE2: for (reverse 0..$#$active_formatting_elements) { |
| 6937 |
if ($active_formatting_elements->[$_]->[0] eq $node->[0]) { |
if ($active_formatting_elements->[$_]->[0] eq $node->[0]) { |
| 6956 |
|
|
| 6957 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 6958 |
|
|
| 6959 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 6960 |
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
| 6961 |
|
|
| 6962 |
|
!!!nack ('t374.1'); |
| 6963 |
!!!next-token; |
!!!next-token; |
| 6964 |
redo B; |
next B; |
|
} elsif ({ |
|
|
b => 1, big => 1, em => 1, font => 1, i => 1, |
|
|
s => 1, small => 1, strile => 1, |
|
|
strong => 1, tt => 1, u => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
!!!cp ('t375'); |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
|
|
|
|
|
!!!next-token; |
|
|
redo B; |
|
| 6965 |
} elsif ($token->{tag_name} eq 'nobr') { |
} elsif ($token->{tag_name} eq 'nobr') { |
| 6966 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 6967 |
|
|
| 6968 |
## has a |nobr| element in scope |
## has a |nobr| element in scope |
| 6969 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 6970 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 6971 |
if ($node->[1] eq 'nobr') { |
if ($node->[1] & NOBR_EL) { |
| 6972 |
!!!cp ('t376'); |
!!!cp ('t376'); |
| 6973 |
!!!parse-error (type => 'in nobr:nobr'); |
!!!parse-error (type => 'in nobr:nobr', token => $token); |
| 6974 |
!!!back-token; |
!!!back-token; # <nobr> |
| 6975 |
$token = {type => END_TAG_TOKEN, tag_name => 'nobr'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'nobr', |
| 6976 |
redo B; |
line => $token->{line}, column => $token->{column}}; |
| 6977 |
} elsif ({ |
next B; |
| 6978 |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
} elsif ($node->[1] & SCOPING_EL) { |
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
| 6979 |
!!!cp ('t377'); |
!!!cp ('t377'); |
| 6980 |
last INSCOPE; |
last INSCOPE; |
| 6981 |
} |
} |
| 6982 |
} # INSCOPE |
} # INSCOPE |
| 6983 |
|
|
| 6984 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 6985 |
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
| 6986 |
|
|
| 6987 |
|
!!!nack ('t377.1'); |
| 6988 |
!!!next-token; |
!!!next-token; |
| 6989 |
redo B; |
next B; |
| 6990 |
} elsif ($token->{tag_name} eq 'button') { |
} elsif ($token->{tag_name} eq 'button') { |
| 6991 |
## has a button element in scope |
## has a button element in scope |
| 6992 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 6993 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 6994 |
if ($node->[1] eq 'button') { |
if ($node->[1] & BUTTON_EL) { |
| 6995 |
!!!cp ('t378'); |
!!!cp ('t378'); |
| 6996 |
!!!parse-error (type => 'in button:button'); |
!!!parse-error (type => 'in button:button', token => $token); |
| 6997 |
!!!back-token; |
!!!back-token; # <button> |
| 6998 |
$token = {type => END_TAG_TOKEN, tag_name => 'button'}; |
$token = {type => END_TAG_TOKEN, tag_name => 'button', |
| 6999 |
redo B; |
line => $token->{line}, column => $token->{column}}; |
| 7000 |
} elsif ({ |
next B; |
| 7001 |
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
} elsif ($node->[1] & SCOPING_EL) { |
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
| 7002 |
!!!cp ('t379'); |
!!!cp ('t379'); |
| 7003 |
last INSCOPE; |
last INSCOPE; |
| 7004 |
} |
} |
| 7006 |
|
|
| 7007 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 7008 |
|
|
| 7009 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 7010 |
|
|
| 7011 |
## TODO: associate with $self->{form_element} if defined |
## TODO: associate with $self->{form_element} if defined |
| 7012 |
|
|
| 7013 |
push @$active_formatting_elements, ['#marker', '']; |
push @$active_formatting_elements, ['#marker', '']; |
| 7014 |
|
|
| 7015 |
|
!!!nack ('t379.1'); |
| 7016 |
!!!next-token; |
!!!next-token; |
| 7017 |
redo B; |
next B; |
|
} elsif ({ |
|
|
applet => 1, marquee => 1, object => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
!!!cp ('t380'); |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
push @$active_formatting_elements, ['#marker', '']; |
|
|
|
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'xmp') { |
|
|
!!!cp ('t381'); |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
$parse_rcdata->(CDATA_CONTENT_MODEL); |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'table') { |
|
|
## has a p element in scope |
|
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
|
|
if ($_->[1] eq 'p') { |
|
|
!!!cp ('t382'); |
|
|
!!!back-token; |
|
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
|
|
redo B; |
|
|
} elsif ({ |
|
|
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
|
!!!cp ('t383'); |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
push @{$open_tables}, [$self->{open_elements}->[-1]->[0]]; |
|
|
|
|
|
$self->{insertion_mode} = IN_TABLE_IM; |
|
|
|
|
|
!!!next-token; |
|
|
redo B; |
|
| 7018 |
} elsif ({ |
} elsif ({ |
| 7019 |
area => 1, basefont => 1, bgsound => 1, br => 1, |
xmp => 1, |
| 7020 |
embed => 1, img => 1, param => 1, spacer => 1, wbr => 1, |
iframe => 1, |
| 7021 |
image => 1, |
noembed => 1, |
| 7022 |
|
noframes => 1, ## NOTE: This is an "as if in head" code clone. |
| 7023 |
|
noscript => 0, ## TODO: 1 if scripting is enabled |
| 7024 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 7025 |
if ($token->{tag_name} eq 'image') { |
if ($token->{tag_name} eq 'xmp') { |
| 7026 |
!!!cp ('t384'); |
!!!cp ('t381'); |
| 7027 |
!!!parse-error (type => 'image'); |
$reconstruct_active_formatting_elements->($insert_to_current); |
|
$token->{tag_name} = 'img'; |
|
| 7028 |
} else { |
} else { |
| 7029 |
!!!cp ('t385'); |
!!!cp ('t399'); |
| 7030 |
} |
} |
| 7031 |
|
## NOTE: There is an "as if in body" code clone. |
| 7032 |
## NOTE: There is an "as if <br>" code clone. |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 7033 |
$reconstruct_active_formatting_elements->($insert_to_current); |
next B; |
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
pop @{$self->{open_elements}}; |
|
|
|
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'hr') { |
|
|
## has a p element in scope |
|
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
|
|
if ($_->[1] eq 'p') { |
|
|
!!!cp ('t386'); |
|
|
!!!back-token; |
|
|
$token = {type => END_TAG_TOKEN, tag_name => 'p'}; |
|
|
redo B; |
|
|
} elsif ({ |
|
|
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$_->[1]}) { |
|
|
!!!cp ('t387'); |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
pop @{$self->{open_elements}}; |
|
|
|
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'input') { |
|
|
!!!cp ('t388'); |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
## TODO: associate with $self->{form_element} if defined |
|
|
pop @{$self->{open_elements}}; |
|
|
|
|
|
!!!next-token; |
|
|
redo B; |
|
| 7034 |
} elsif ($token->{tag_name} eq 'isindex') { |
} elsif ($token->{tag_name} eq 'isindex') { |
| 7035 |
!!!parse-error (type => 'isindex'); |
!!!parse-error (type => 'isindex', token => $token); |
| 7036 |
|
|
| 7037 |
if (defined $self->{form_element}) { |
if (defined $self->{form_element}) { |
| 7038 |
!!!cp ('t389'); |
!!!cp ('t389'); |
| 7039 |
## Ignore the token |
## Ignore the token |
| 7040 |
|
!!!nack ('t389'); ## NOTE: Not acknowledged. |
| 7041 |
!!!next-token; |
!!!next-token; |
| 7042 |
redo B; |
next B; |
| 7043 |
} else { |
} else { |
| 7044 |
|
!!!ack ('t391.1'); |
| 7045 |
|
|
| 7046 |
my $at = $token->{attributes}; |
my $at = $token->{attributes}; |
| 7047 |
my $form_attrs; |
my $form_attrs; |
| 7048 |
$form_attrs->{action} = $at->{action} if $at->{action}; |
$form_attrs->{action} = $at->{action} if $at->{action}; |
| 7052 |
delete $at->{prompt}; |
delete $at->{prompt}; |
| 7053 |
my @tokens = ( |
my @tokens = ( |
| 7054 |
{type => START_TAG_TOKEN, tag_name => 'form', |
{type => START_TAG_TOKEN, tag_name => 'form', |
| 7055 |
attributes => $form_attrs}, |
attributes => $form_attrs, |
| 7056 |
{type => START_TAG_TOKEN, tag_name => 'hr'}, |
line => $token->{line}, column => $token->{column}}, |
| 7057 |
{type => START_TAG_TOKEN, tag_name => 'p'}, |
{type => START_TAG_TOKEN, tag_name => 'hr', |
| 7058 |
{type => START_TAG_TOKEN, tag_name => 'label'}, |
line => $token->{line}, column => $token->{column}}, |
| 7059 |
|
{type => START_TAG_TOKEN, tag_name => 'p', |
| 7060 |
|
line => $token->{line}, column => $token->{column}}, |
| 7061 |
|
{type => START_TAG_TOKEN, tag_name => 'label', |
| 7062 |
|
line => $token->{line}, column => $token->{column}}, |
| 7063 |
); |
); |
| 7064 |
if ($prompt_attr) { |
if ($prompt_attr) { |
| 7065 |
!!!cp ('t390'); |
!!!cp ('t390'); |
| 7066 |
push @tokens, {type => CHARACTER_TOKEN, data => $prompt_attr->{value}}; |
push @tokens, {type => CHARACTER_TOKEN, data => $prompt_attr->{value}, |
| 7067 |
|
#line => $token->{line}, column => $token->{column}, |
| 7068 |
|
}; |
| 7069 |
} else { |
} else { |
| 7070 |
!!!cp ('t391'); |
!!!cp ('t391'); |
| 7071 |
push @tokens, {type => CHARACTER_TOKEN, |
push @tokens, {type => CHARACTER_TOKEN, |
| 7072 |
data => 'This is a searchable index. Insert your search keywords here: '}; # SHOULD |
data => 'This is a searchable index. Insert your search keywords here: ', |
| 7073 |
|
#line => $token->{line}, column => $token->{column}, |
| 7074 |
|
}; # SHOULD |
| 7075 |
## TODO: make this configurable |
## TODO: make this configurable |
| 7076 |
} |
} |
| 7077 |
push @tokens, |
push @tokens, |
| 7078 |
{type => START_TAG_TOKEN, tag_name => 'input', attributes => $at}, |
{type => START_TAG_TOKEN, tag_name => 'input', attributes => $at, |
| 7079 |
|
line => $token->{line}, column => $token->{column}}, |
| 7080 |
#{type => CHARACTER_TOKEN, data => ''}, # SHOULD |
#{type => CHARACTER_TOKEN, data => ''}, # SHOULD |
| 7081 |
{type => END_TAG_TOKEN, tag_name => 'label'}, |
{type => END_TAG_TOKEN, tag_name => 'label', |
| 7082 |
{type => END_TAG_TOKEN, tag_name => 'p'}, |
line => $token->{line}, column => $token->{column}}, |
| 7083 |
{type => START_TAG_TOKEN, tag_name => 'hr'}, |
{type => END_TAG_TOKEN, tag_name => 'p', |
| 7084 |
{type => END_TAG_TOKEN, tag_name => 'form'}; |
line => $token->{line}, column => $token->{column}}, |
| 7085 |
$token = shift @tokens; |
{type => START_TAG_TOKEN, tag_name => 'hr', |
| 7086 |
|
line => $token->{line}, column => $token->{column}}, |
| 7087 |
|
{type => END_TAG_TOKEN, tag_name => 'form', |
| 7088 |
|
line => $token->{line}, column => $token->{column}}; |
| 7089 |
!!!back-token (@tokens); |
!!!back-token (@tokens); |
| 7090 |
redo B; |
!!!next-token; |
| 7091 |
|
next B; |
| 7092 |
} |
} |
| 7093 |
} elsif ($token->{tag_name} eq 'textarea') { |
} elsif ($token->{tag_name} eq 'textarea') { |
| 7094 |
my $tag_name = $token->{tag_name}; |
my $tag_name = $token->{tag_name}; |
| 7095 |
my $el; |
my $el; |
| 7096 |
!!!create-element ($el, $token->{tag_name}, $token->{attributes}); |
!!!create-element ($el, $HTML_NS, $token->{tag_name}, $token->{attributes}, $token); |
| 7097 |
|
|
| 7098 |
## TODO: $self->{form_element} if defined |
## TODO: $self->{form_element} if defined |
| 7099 |
$self->{content_model} = RCDATA_CONTENT_MODEL; |
$self->{content_model} = RCDATA_CONTENT_MODEL; |
| 7102 |
$insert->($el); |
$insert->($el); |
| 7103 |
|
|
| 7104 |
my $text = ''; |
my $text = ''; |
| 7105 |
|
!!!nack ('t392.1'); |
| 7106 |
!!!next-token; |
!!!next-token; |
| 7107 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 7108 |
$token->{data} =~ s/^\x0A//; |
$token->{data} =~ s/^\x0A//; |
| 7133 |
## Ignore the token |
## Ignore the token |
| 7134 |
} else { |
} else { |
| 7135 |
!!!cp ('t398'); |
!!!cp ('t398'); |
| 7136 |
!!!parse-error (type => 'in RCDATA:#'.$token->{type}); |
!!!parse-error (type => 'in RCDATA:#eof', token => $token); |
| 7137 |
} |
} |
| 7138 |
!!!next-token; |
!!!next-token; |
| 7139 |
|
next B; |
| 7140 |
|
} elsif ($token->{tag_name} eq 'rt' or |
| 7141 |
|
$token->{tag_name} eq 'rp') { |
| 7142 |
|
## has a |ruby| element in scope |
| 7143 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 7144 |
|
my $node = $self->{open_elements}->[$_]; |
| 7145 |
|
if ($node->[1] & RUBY_EL) { |
| 7146 |
|
!!!cp ('t398.1'); |
| 7147 |
|
## generate implied end tags |
| 7148 |
|
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 7149 |
|
!!!cp ('t398.2'); |
| 7150 |
|
pop @{$self->{open_elements}}; |
| 7151 |
|
} |
| 7152 |
|
unless ($self->{open_elements}->[-1]->[1] & RUBY_EL) { |
| 7153 |
|
!!!cp ('t398.3'); |
| 7154 |
|
!!!parse-error (type => 'not closed', |
| 7155 |
|
text => $self->{open_elements}->[-1]->[0] |
| 7156 |
|
->manakai_local_name, |
| 7157 |
|
token => $token); |
| 7158 |
|
pop @{$self->{open_elements}} |
| 7159 |
|
while not $self->{open_elements}->[-1]->[1] & RUBY_EL; |
| 7160 |
|
} |
| 7161 |
|
last INSCOPE; |
| 7162 |
|
} elsif ($node->[1] & SCOPING_EL) { |
| 7163 |
|
!!!cp ('t398.4'); |
| 7164 |
|
last INSCOPE; |
| 7165 |
|
} |
| 7166 |
|
} # INSCOPE |
| 7167 |
|
|
| 7168 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 7169 |
|
|
| 7170 |
|
!!!nack ('t398.5'); |
| 7171 |
|
!!!next-token; |
| 7172 |
redo B; |
redo B; |
| 7173 |
} elsif ({ |
} elsif ($token->{tag_name} eq 'math' or |
| 7174 |
iframe => 1, |
$token->{tag_name} eq 'svg') { |
|
noembed => 1, |
|
|
noframes => 1, |
|
|
noscript => 0, ## TODO: 1 if scripting is enabled |
|
|
}->{$token->{tag_name}}) { |
|
|
!!!cp ('t399'); |
|
|
## NOTE: There is an "as if in body" code clone. |
|
|
$parse_rcdata->(CDATA_CONTENT_MODEL); |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'select') { |
|
|
!!!cp ('t400'); |
|
| 7175 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
| 7176 |
|
|
| 7177 |
## TODO: associate with $self->{form_element} if defined |
## "Adjust MathML attributes" ('math' only) - done in insert-element-f |
| 7178 |
|
|
| 7179 |
|
## "adjust SVG attributes" ('svg' only) - done in insert-element-f |
| 7180 |
|
|
| 7181 |
|
## "adjust foreign attributes" - done in insert-element-f |
| 7182 |
|
|
| 7183 |
if ($self->{insertion_mode} & TABLE_IMS or |
!!!insert-element-f ($token->{tag_name} eq 'math' ? $MML_NS : $SVG_NS, $token->{tag_name}, $token->{attributes}, $token); |
| 7184 |
$self->{insertion_mode} & BODY_TABLE_IMS or |
|
| 7185 |
$self->{insertion_mode} == IN_COLUMN_GROUP_IM) { |
if ($self->{self_closing}) { |
| 7186 |
!!!cp ('t400.1'); |
pop @{$self->{open_elements}}; |
| 7187 |
$self->{insertion_mode} = IN_SELECT_IN_TABLE_IM; |
!!!ack ('t398.1'); |
| 7188 |
} else { |
} else { |
| 7189 |
!!!cp ('t400.2'); |
!!!cp ('t398.2'); |
| 7190 |
$self->{insertion_mode} = IN_SELECT_IM; |
$self->{insertion_mode} |= IN_FOREIGN_CONTENT_IM; |
| 7191 |
|
## NOTE: |<body><math><mi><svg>| -> "in foreign content" insertion |
| 7192 |
|
## mode, "in body" (not "in foreign content") secondary insertion |
| 7193 |
|
## mode, maybe. |
| 7194 |
} |
} |
| 7195 |
|
|
| 7196 |
!!!next-token; |
!!!next-token; |
| 7197 |
redo B; |
next B; |
| 7198 |
} elsif ({ |
} elsif ({ |
| 7199 |
caption => 1, col => 1, colgroup => 1, frame => 1, |
caption => 1, col => 1, colgroup => 1, frame => 1, |
| 7200 |
frameset => 1, head => 1, option => 1, optgroup => 1, |
frameset => 1, head => 1, option => 1, optgroup => 1, |
| 7202 |
thead => 1, tr => 1, |
thead => 1, tr => 1, |
| 7203 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 7204 |
!!!cp ('t401'); |
!!!cp ('t401'); |
| 7205 |
!!!parse-error (type => 'in body:'.$token->{tag_name}); |
!!!parse-error (type => 'in body', |
| 7206 |
|
text => $token->{tag_name}, token => $token); |
| 7207 |
## Ignore the token |
## Ignore the token |
| 7208 |
|
!!!nack ('t401.1'); ## NOTE: |<col/>| or |<frame/>| here is an error. |
| 7209 |
!!!next-token; |
!!!next-token; |
| 7210 |
redo B; |
next B; |
| 7211 |
|
|
| 7212 |
## ISSUE: An issue on HTML5 new elements in the spec. |
## ISSUE: An issue on HTML5 new elements in the spec. |
| 7213 |
} else { |
} else { |
| 7214 |
!!!cp ('t402'); |
if ($token->{tag_name} eq 'image') { |
| 7215 |
|
!!!cp ('t384'); |
| 7216 |
|
!!!parse-error (type => 'image', token => $token); |
| 7217 |
|
$token->{tag_name} = 'img'; |
| 7218 |
|
} else { |
| 7219 |
|
!!!cp ('t385'); |
| 7220 |
|
} |
| 7221 |
|
|
| 7222 |
|
## NOTE: There is an "as if <br>" code clone. |
| 7223 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 7224 |
|
|
| 7225 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 7226 |
|
|
| 7227 |
|
if ({ |
| 7228 |
|
applet => 1, marquee => 1, object => 1, |
| 7229 |
|
}->{$token->{tag_name}}) { |
| 7230 |
|
!!!cp ('t380'); |
| 7231 |
|
push @$active_formatting_elements, ['#marker', '']; |
| 7232 |
|
!!!nack ('t380.1'); |
| 7233 |
|
} elsif ({ |
| 7234 |
|
b => 1, big => 1, em => 1, font => 1, i => 1, |
| 7235 |
|
s => 1, small => 1, strile => 1, |
| 7236 |
|
strong => 1, tt => 1, u => 1, |
| 7237 |
|
}->{$token->{tag_name}}) { |
| 7238 |
|
!!!cp ('t375'); |
| 7239 |
|
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
| 7240 |
|
!!!nack ('t375.1'); |
| 7241 |
|
} elsif ($token->{tag_name} eq 'input') { |
| 7242 |
|
!!!cp ('t388'); |
| 7243 |
|
## TODO: associate with $self->{form_element} if defined |
| 7244 |
|
pop @{$self->{open_elements}}; |
| 7245 |
|
!!!ack ('t388.2'); |
| 7246 |
|
} elsif ({ |
| 7247 |
|
area => 1, basefont => 1, bgsound => 1, br => 1, |
| 7248 |
|
embed => 1, img => 1, param => 1, spacer => 1, wbr => 1, |
| 7249 |
|
#image => 1, |
| 7250 |
|
}->{$token->{tag_name}}) { |
| 7251 |
|
!!!cp ('t388.1'); |
| 7252 |
|
pop @{$self->{open_elements}}; |
| 7253 |
|
!!!ack ('t388.3'); |
| 7254 |
|
} elsif ($token->{tag_name} eq 'select') { |
| 7255 |
|
## TODO: associate with $self->{form_element} if defined |
| 7256 |
|
|
| 7257 |
|
if ($self->{insertion_mode} & TABLE_IMS or |
| 7258 |
|
$self->{insertion_mode} & BODY_TABLE_IMS or |
| 7259 |
|
$self->{insertion_mode} == IN_COLUMN_GROUP_IM) { |
| 7260 |
|
!!!cp ('t400.1'); |
| 7261 |
|
$self->{insertion_mode} = IN_SELECT_IN_TABLE_IM; |
| 7262 |
|
} else { |
| 7263 |
|
!!!cp ('t400.2'); |
| 7264 |
|
$self->{insertion_mode} = IN_SELECT_IM; |
| 7265 |
|
} |
| 7266 |
|
!!!nack ('t400.3'); |
| 7267 |
|
} else { |
| 7268 |
|
!!!nack ('t402'); |
| 7269 |
|
} |
| 7270 |
|
|
| 7271 |
!!!next-token; |
!!!next-token; |
| 7272 |
redo B; |
next B; |
| 7273 |
} |
} |
| 7274 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 7275 |
if ($token->{tag_name} eq 'body') { |
if ($token->{tag_name} eq 'body') { |
| 7276 |
if (@{$self->{open_elements}} > 1 and |
## has a |body| element in scope |
| 7277 |
$self->{open_elements}->[1]->[1] eq 'body') { |
my $i; |
| 7278 |
for (@{$self->{open_elements}}) { |
INSCOPE: { |
| 7279 |
unless ({ |
for (reverse @{$self->{open_elements}}) { |
| 7280 |
dd => 1, dt => 1, li => 1, p => 1, td => 1, |
if ($_->[1] & BODY_EL) { |
| 7281 |
th => 1, tr => 1, body => 1, html => 1, |
!!!cp ('t405'); |
| 7282 |
tbody => 1, tfoot => 1, thead => 1, |
$i = $_; |
| 7283 |
}->{$_->[1]}) { |
last INSCOPE; |
| 7284 |
!!!cp ('t403'); |
} elsif ($_->[1] & SCOPING_EL) { |
| 7285 |
!!!parse-error (type => 'not closed:'.$_->[1]); |
!!!cp ('t405.1'); |
| 7286 |
} else { |
last; |
|
!!!cp ('t404'); |
|
| 7287 |
} |
} |
| 7288 |
} |
} |
| 7289 |
|
|
| 7290 |
$self->{insertion_mode} = AFTER_BODY_IM; |
!!!parse-error (type => 'start tag not allowed', |
| 7291 |
!!!next-token; |
text => $token->{tag_name}, token => $token); |
| 7292 |
redo B; |
## NOTE: Ignore the token. |
|
} else { |
|
|
!!!cp ('t405'); |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
| 7293 |
!!!next-token; |
!!!next-token; |
| 7294 |
redo B; |
next B; |
| 7295 |
|
} # INSCOPE |
| 7296 |
|
|
| 7297 |
|
for (@{$self->{open_elements}}) { |
| 7298 |
|
unless ($_->[1] & ALL_END_TAG_OPTIONAL_EL) { |
| 7299 |
|
!!!cp ('t403'); |
| 7300 |
|
!!!parse-error (type => 'not closed', |
| 7301 |
|
text => $_->[0]->manakai_local_name, |
| 7302 |
|
token => $token); |
| 7303 |
|
last; |
| 7304 |
|
} else { |
| 7305 |
|
!!!cp ('t404'); |
| 7306 |
|
} |
| 7307 |
} |
} |
| 7308 |
|
|
| 7309 |
|
$self->{insertion_mode} = AFTER_BODY_IM; |
| 7310 |
|
!!!next-token; |
| 7311 |
|
next B; |
| 7312 |
} elsif ($token->{tag_name} eq 'html') { |
} elsif ($token->{tag_name} eq 'html') { |
| 7313 |
if (@{$self->{open_elements}} > 1 and $self->{open_elements}->[1]->[1] eq 'body') { |
## TODO: Update this code. It seems that the code below is not |
| 7314 |
|
## up-to-date, though it has same effect as speced. |
| 7315 |
|
if (@{$self->{open_elements}} > 1 and |
| 7316 |
|
$self->{open_elements}->[1]->[1] & BODY_EL) { |
| 7317 |
## ISSUE: There is an issue in the spec. |
## ISSUE: There is an issue in the spec. |
| 7318 |
if ($self->{open_elements}->[-1]->[1] ne 'body') { |
unless ($self->{open_elements}->[-1]->[1] & BODY_EL) { |
| 7319 |
!!!cp ('t406'); |
!!!cp ('t406'); |
| 7320 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[1]->[1]); |
!!!parse-error (type => 'not closed', |
| 7321 |
|
text => $self->{open_elements}->[1]->[0] |
| 7322 |
|
->manakai_local_name, |
| 7323 |
|
token => $token); |
| 7324 |
} else { |
} else { |
| 7325 |
!!!cp ('t407'); |
!!!cp ('t407'); |
| 7326 |
} |
} |
| 7327 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 7328 |
## reprocess |
## reprocess |
| 7329 |
redo B; |
next B; |
| 7330 |
} else { |
} else { |
| 7331 |
!!!cp ('t408'); |
!!!cp ('t408'); |
| 7332 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 7333 |
|
text => $token->{tag_name}, token => $token); |
| 7334 |
## Ignore the token |
## Ignore the token |
| 7335 |
!!!next-token; |
!!!next-token; |
| 7336 |
redo B; |
next B; |
| 7337 |
} |
} |
| 7338 |
} elsif ({ |
} elsif ({ |
| 7339 |
address => 1, blockquote => 1, center => 1, dir => 1, |
address => 1, blockquote => 1, center => 1, dir => 1, |
| 7346 |
my $i; |
my $i; |
| 7347 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 7348 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 7349 |
if ($node->[1] eq $token->{tag_name}) { |
if ($node->[0]->manakai_local_name eq $token->{tag_name}) { |
| 7350 |
!!!cp ('t410'); |
!!!cp ('t410'); |
| 7351 |
$i = $_; |
$i = $_; |
| 7352 |
last INSCOPE; |
last INSCOPE; |
| 7353 |
} elsif ({ |
} elsif ($node->[1] & SCOPING_EL) { |
|
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
| 7354 |
!!!cp ('t411'); |
!!!cp ('t411'); |
| 7355 |
last INSCOPE; |
last INSCOPE; |
| 7356 |
} |
} |
| 7358 |
|
|
| 7359 |
unless (defined $i) { # has an element in scope |
unless (defined $i) { # has an element in scope |
| 7360 |
!!!cp ('t413'); |
!!!cp ('t413'); |
| 7361 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 7362 |
|
text => $token->{tag_name}, token => $token); |
| 7363 |
|
## NOTE: Ignore the token. |
| 7364 |
} else { |
} else { |
| 7365 |
## Step 1. generate implied end tags |
## Step 1. generate implied end tags |
| 7366 |
while ({ |
while ({ |
| 7367 |
|
## END_TAG_OPTIONAL_EL |
| 7368 |
dd => ($token->{tag_name} ne 'dd'), |
dd => ($token->{tag_name} ne 'dd'), |
| 7369 |
dt => ($token->{tag_name} ne 'dt'), |
dt => ($token->{tag_name} ne 'dt'), |
| 7370 |
li => ($token->{tag_name} ne 'li'), |
li => ($token->{tag_name} ne 'li'), |
| 7371 |
p => 1, |
p => 1, |
| 7372 |
}->{$self->{open_elements}->[-1]->[1]}) { |
rt => 1, |
| 7373 |
|
rp => 1, |
| 7374 |
|
}->{$self->{open_elements}->[-1]->[0]->manakai_local_name}) { |
| 7375 |
!!!cp ('t409'); |
!!!cp ('t409'); |
| 7376 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 7377 |
} |
} |
| 7378 |
|
|
| 7379 |
## Step 2. |
## Step 2. |
| 7380 |
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
if ($self->{open_elements}->[-1]->[0]->manakai_local_name |
| 7381 |
|
ne $token->{tag_name}) { |
| 7382 |
!!!cp ('t412'); |
!!!cp ('t412'); |
| 7383 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed', |
| 7384 |
|
text => $self->{open_elements}->[-1]->[0] |
| 7385 |
|
->manakai_local_name, |
| 7386 |
|
token => $token); |
| 7387 |
} else { |
} else { |
| 7388 |
!!!cp ('t414'); |
!!!cp ('t414'); |
| 7389 |
} |
} |
| 7398 |
}->{$token->{tag_name}}; |
}->{$token->{tag_name}}; |
| 7399 |
} |
} |
| 7400 |
!!!next-token; |
!!!next-token; |
| 7401 |
redo B; |
next B; |
| 7402 |
} elsif ($token->{tag_name} eq 'form') { |
} elsif ($token->{tag_name} eq 'form') { |
| 7403 |
undef $self->{form_element}; |
undef $self->{form_element}; |
| 7404 |
|
|
| 7406 |
my $i; |
my $i; |
| 7407 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 7408 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 7409 |
if ($node->[1] eq $token->{tag_name}) { |
if ($node->[1] & FORM_EL) { |
| 7410 |
!!!cp ('t418'); |
!!!cp ('t418'); |
| 7411 |
$i = $_; |
$i = $_; |
| 7412 |
last INSCOPE; |
last INSCOPE; |
| 7413 |
} elsif ({ |
} elsif ($node->[1] & SCOPING_EL) { |
|
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
| 7414 |
!!!cp ('t419'); |
!!!cp ('t419'); |
| 7415 |
last INSCOPE; |
last INSCOPE; |
| 7416 |
} |
} |
| 7418 |
|
|
| 7419 |
unless (defined $i) { # has an element in scope |
unless (defined $i) { # has an element in scope |
| 7420 |
!!!cp ('t421'); |
!!!cp ('t421'); |
| 7421 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 7422 |
|
text => $token->{tag_name}, token => $token); |
| 7423 |
|
## NOTE: Ignore the token. |
| 7424 |
} else { |
} else { |
| 7425 |
## Step 1. generate implied end tags |
## Step 1. generate implied end tags |
| 7426 |
while ({ |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
|
dd => 1, dt => 1, li => 1, p => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 7427 |
!!!cp ('t417'); |
!!!cp ('t417'); |
| 7428 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 7429 |
} |
} |
| 7430 |
|
|
| 7431 |
## Step 2. |
## Step 2. |
| 7432 |
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
if ($self->{open_elements}->[-1]->[0]->manakai_local_name |
| 7433 |
|
ne $token->{tag_name}) { |
| 7434 |
!!!cp ('t417.1'); |
!!!cp ('t417.1'); |
| 7435 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed', |
| 7436 |
|
text => $self->{open_elements}->[-1]->[0] |
| 7437 |
|
->manakai_local_name, |
| 7438 |
|
token => $token); |
| 7439 |
} else { |
} else { |
| 7440 |
!!!cp ('t420'); |
!!!cp ('t420'); |
| 7441 |
} |
} |
| 7445 |
} |
} |
| 7446 |
|
|
| 7447 |
!!!next-token; |
!!!next-token; |
| 7448 |
redo B; |
next B; |
| 7449 |
} elsif ({ |
} elsif ({ |
| 7450 |
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
| 7451 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 7453 |
my $i; |
my $i; |
| 7454 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 7455 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 7456 |
if ({ |
if ($node->[1] & HEADING_EL) { |
|
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
|
|
}->{$node->[1]}) { |
|
| 7457 |
!!!cp ('t423'); |
!!!cp ('t423'); |
| 7458 |
$i = $_; |
$i = $_; |
| 7459 |
last INSCOPE; |
last INSCOPE; |
| 7460 |
} elsif ({ |
} elsif ($node->[1] & SCOPING_EL) { |
|
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
| 7461 |
!!!cp ('t424'); |
!!!cp ('t424'); |
| 7462 |
last INSCOPE; |
last INSCOPE; |
| 7463 |
} |
} |
| 7465 |
|
|
| 7466 |
unless (defined $i) { # has an element in scope |
unless (defined $i) { # has an element in scope |
| 7467 |
!!!cp ('t425.1'); |
!!!cp ('t425.1'); |
| 7468 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 7469 |
|
text => $token->{tag_name}, token => $token); |
| 7470 |
|
## NOTE: Ignore the token. |
| 7471 |
} else { |
} else { |
| 7472 |
## Step 1. generate implied end tags |
## Step 1. generate implied end tags |
| 7473 |
while ({ |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
|
dd => 1, dt => 1, li => 1, p => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 7474 |
!!!cp ('t422'); |
!!!cp ('t422'); |
| 7475 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 7476 |
} |
} |
| 7477 |
|
|
| 7478 |
## Step 2. |
## Step 2. |
| 7479 |
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
if ($self->{open_elements}->[-1]->[0]->manakai_local_name |
| 7480 |
|
ne $token->{tag_name}) { |
| 7481 |
!!!cp ('t425'); |
!!!cp ('t425'); |
| 7482 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 7483 |
|
text => $token->{tag_name}, token => $token); |
| 7484 |
} else { |
} else { |
| 7485 |
!!!cp ('t426'); |
!!!cp ('t426'); |
| 7486 |
} |
} |
| 7490 |
} |
} |
| 7491 |
|
|
| 7492 |
!!!next-token; |
!!!next-token; |
| 7493 |
redo B; |
next B; |
| 7494 |
} elsif ($token->{tag_name} eq 'p') { |
} elsif ($token->{tag_name} eq 'p') { |
| 7495 |
## has an element in scope |
## has an element in scope |
| 7496 |
my $i; |
my $i; |
| 7497 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 7498 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 7499 |
if ($node->[1] eq $token->{tag_name}) { |
if ($node->[1] & P_EL) { |
| 7500 |
!!!cp ('t410.1'); |
!!!cp ('t410.1'); |
| 7501 |
$i = $_; |
$i = $_; |
| 7502 |
last INSCOPE; |
last INSCOPE; |
| 7503 |
} elsif ({ |
} elsif ($node->[1] & SCOPING_EL) { |
|
applet => 1, table => 1, caption => 1, td => 1, th => 1, |
|
|
button => 1, marquee => 1, object => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
| 7504 |
!!!cp ('t411.1'); |
!!!cp ('t411.1'); |
| 7505 |
last INSCOPE; |
last INSCOPE; |
| 7506 |
} |
} |
| 7507 |
} # INSCOPE |
} # INSCOPE |
| 7508 |
|
|
| 7509 |
if (defined $i) { |
if (defined $i) { |
| 7510 |
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
if ($self->{open_elements}->[-1]->[0]->manakai_local_name |
| 7511 |
|
ne $token->{tag_name}) { |
| 7512 |
!!!cp ('t412.1'); |
!!!cp ('t412.1'); |
| 7513 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed', |
| 7514 |
|
text => $self->{open_elements}->[-1]->[0] |
| 7515 |
|
->manakai_local_name, |
| 7516 |
|
token => $token); |
| 7517 |
} else { |
} else { |
| 7518 |
!!!cp ('t414.1'); |
!!!cp ('t414.1'); |
| 7519 |
} |
} |
| 7521 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 7522 |
} else { |
} else { |
| 7523 |
!!!cp ('t413.1'); |
!!!cp ('t413.1'); |
| 7524 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 7525 |
|
text => $token->{tag_name}, token => $token); |
| 7526 |
|
|
| 7527 |
!!!cp ('t415.1'); |
!!!cp ('t415.1'); |
| 7528 |
## As if <p>, then reprocess the current token |
## As if <p>, then reprocess the current token |
| 7529 |
my $el; |
my $el; |
| 7530 |
!!!create-element ($el, 'p'); |
!!!create-element ($el, $HTML_NS, 'p',, $token); |
| 7531 |
$insert->($el); |
$insert->($el); |
| 7532 |
## NOTE: Not inserted into |$self->{open_elements}|. |
## NOTE: Not inserted into |$self->{open_elements}|. |
| 7533 |
} |
} |
| 7534 |
|
|
| 7535 |
!!!next-token; |
!!!next-token; |
| 7536 |
redo B; |
next B; |
| 7537 |
} elsif ({ |
} elsif ({ |
| 7538 |
a => 1, |
a => 1, |
| 7539 |
b => 1, big => 1, em => 1, font => 1, i => 1, |
b => 1, big => 1, em => 1, font => 1, i => 1, |
| 7541 |
strong => 1, tt => 1, u => 1, |
strong => 1, tt => 1, u => 1, |
| 7542 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 7543 |
!!!cp ('t427'); |
!!!cp ('t427'); |
| 7544 |
$formatting_end_tag->($token->{tag_name}); |
$formatting_end_tag->($token); |
| 7545 |
redo B; |
next B; |
| 7546 |
} elsif ($token->{tag_name} eq 'br') { |
} elsif ($token->{tag_name} eq 'br') { |
| 7547 |
!!!cp ('t428'); |
!!!cp ('t428'); |
| 7548 |
!!!parse-error (type => 'unmatched end tag:br'); |
!!!parse-error (type => 'unmatched end tag', |
| 7549 |
|
text => 'br', token => $token); |
| 7550 |
|
|
| 7551 |
## As if <br> |
## As if <br> |
| 7552 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 7553 |
|
|
| 7554 |
my $el; |
my $el; |
| 7555 |
!!!create-element ($el, 'br'); |
!!!create-element ($el, $HTML_NS, 'br',, $token); |
| 7556 |
$insert->($el); |
$insert->($el); |
| 7557 |
|
|
| 7558 |
## Ignore the token. |
## Ignore the token. |
| 7559 |
!!!next-token; |
!!!next-token; |
| 7560 |
redo B; |
next B; |
| 7561 |
} elsif ({ |
} elsif ({ |
| 7562 |
caption => 1, col => 1, colgroup => 1, frame => 1, |
caption => 1, col => 1, colgroup => 1, frame => 1, |
| 7563 |
frameset => 1, head => 1, option => 1, optgroup => 1, |
frameset => 1, head => 1, option => 1, optgroup => 1, |
| 7571 |
noscript => 0, ## TODO: if scripting is enabled |
noscript => 0, ## TODO: if scripting is enabled |
| 7572 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 7573 |
!!!cp ('t429'); |
!!!cp ('t429'); |
| 7574 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 7575 |
|
text => $token->{tag_name}, token => $token); |
| 7576 |
## Ignore the token |
## Ignore the token |
| 7577 |
!!!next-token; |
!!!next-token; |
| 7578 |
redo B; |
next B; |
| 7579 |
|
|
| 7580 |
## ISSUE: Issue on HTML5 new elements in spec |
## ISSUE: Issue on HTML5 new elements in spec |
| 7581 |
|
|
| 7586 |
|
|
| 7587 |
## Step 2 |
## Step 2 |
| 7588 |
S2: { |
S2: { |
| 7589 |
if ($node->[1] eq $token->{tag_name}) { |
if ($node->[0]->manakai_local_name eq $token->{tag_name}) { |
| 7590 |
## Step 1 |
## Step 1 |
| 7591 |
## generate implied end tags |
## generate implied end tags |
| 7592 |
while ({ |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
|
dd => 1, dt => 1, li => 1, p => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
| 7593 |
!!!cp ('t430'); |
!!!cp ('t430'); |
| 7594 |
## ISSUE: Can this case be reached? |
## NOTE: |<ruby><rt></ruby>|. |
| 7595 |
|
## ISSUE: <ruby><rt></rt> will also take this code path, |
| 7596 |
|
## which seems wrong. |
| 7597 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 7598 |
|
$node_i++; |
| 7599 |
} |
} |
| 7600 |
|
|
| 7601 |
## Step 2 |
## Step 2 |
| 7602 |
if ($token->{tag_name} ne $self->{open_elements}->[-1]->[1]) { |
if ($self->{open_elements}->[-1]->[0]->manakai_local_name |
| 7603 |
|
ne $token->{tag_name}) { |
| 7604 |
!!!cp ('t431'); |
!!!cp ('t431'); |
| 7605 |
## NOTE: <x><y></x> |
## NOTE: <x><y></x> |
| 7606 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed', |
| 7607 |
|
text => $self->{open_elements}->[-1]->[0] |
| 7608 |
|
->manakai_local_name, |
| 7609 |
|
token => $token); |
| 7610 |
} else { |
} else { |
| 7611 |
!!!cp ('t432'); |
!!!cp ('t432'); |
| 7612 |
} |
} |
| 7613 |
|
|
| 7614 |
## Step 3 |
## Step 3 |
| 7615 |
splice @{$self->{open_elements}}, $node_i; |
splice @{$self->{open_elements}}, $node_i if $node_i < 0; |
| 7616 |
|
|
| 7617 |
!!!next-token; |
!!!next-token; |
| 7618 |
last S2; |
last S2; |
| 7619 |
} else { |
} else { |
| 7620 |
## Step 3 |
## Step 3 |
| 7621 |
if (not $formatting_category->{$node->[1]} and |
if (not ($node->[1] & FORMATTING_EL) and |
| 7622 |
#not $phrasing_category->{$node->[1]} and |
#not $phrasing_category->{$node->[1]} and |
| 7623 |
($special_category->{$node->[1]} or |
($node->[1] & SPECIAL_EL or |
| 7624 |
$scoping_category->{$node->[1]})) { |
$node->[1] & SCOPING_EL)) { |
| 7625 |
!!!cp ('t433'); |
!!!cp ('t433'); |
| 7626 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag', |
| 7627 |
|
text => $token->{tag_name}, token => $token); |
| 7628 |
## Ignore the token |
## Ignore the token |
| 7629 |
!!!next-token; |
!!!next-token; |
| 7630 |
last S2; |
last S2; |
| 7640 |
## Step 5; |
## Step 5; |
| 7641 |
redo S2; |
redo S2; |
| 7642 |
} # S2 |
} # S2 |
| 7643 |
redo B; |
next B; |
| 7644 |
} |
} |
| 7645 |
} |
} |
| 7646 |
redo B; |
next B; |
| 7647 |
|
} continue { # B |
| 7648 |
|
if ($self->{insertion_mode} & IN_FOREIGN_CONTENT_IM) { |
| 7649 |
|
## NOTE: The code below is executed in cases where it does not have |
| 7650 |
|
## to be, but it it is harmless even in those cases. |
| 7651 |
|
## has an element in scope |
| 7652 |
|
INSCOPE: { |
| 7653 |
|
for (reverse 0..$#{$self->{open_elements}}) { |
| 7654 |
|
my $node = $self->{open_elements}->[$_]; |
| 7655 |
|
if ($node->[1] & FOREIGN_EL) { |
| 7656 |
|
last INSCOPE; |
| 7657 |
|
} elsif ($node->[1] & SCOPING_EL) { |
| 7658 |
|
last; |
| 7659 |
|
} |
| 7660 |
|
} |
| 7661 |
|
|
| 7662 |
|
## NOTE: No foreign element in scope. |
| 7663 |
|
$self->{insertion_mode} &= ~ IN_FOREIGN_CONTENT_IM; |
| 7664 |
|
} # INSCOPE |
| 7665 |
|
} |
| 7666 |
} # B |
} # B |
| 7667 |
|
|
| 7668 |
## Stop parsing # MUST |
## Stop parsing # MUST |
| 7670 |
## TODO: script stuffs |
## TODO: script stuffs |
| 7671 |
} # _tree_construct_main |
} # _tree_construct_main |
| 7672 |
|
|
| 7673 |
sub set_inner_html ($$$) { |
sub set_inner_html ($$$;$) { |
| 7674 |
my $class = shift; |
my $class = shift; |
| 7675 |
my $node = shift; |
my $node = shift; |
| 7676 |
my $s = \$_[0]; |
my $s = \$_[0]; |
| 7677 |
my $onerror = $_[1]; |
my $onerror = $_[1]; |
| 7678 |
|
my $get_wrapper = $_[2] || sub ($) { return $_[0] }; |
| 7679 |
|
|
| 7680 |
## ISSUE: Should {confident} be true? |
## ISSUE: Should {confident} be true? |
| 7681 |
|
|
| 7694 |
} |
} |
| 7695 |
|
|
| 7696 |
## Step 3, 4, 5 # MUST |
## Step 3, 4, 5 # MUST |
| 7697 |
$class->parse_string ($$s => $node, $onerror); |
$class->parse_char_string ($$s => $node, $onerror, $get_wrapper); |
| 7698 |
} elsif ($nt == 1) { |
} elsif ($nt == 1) { |
| 7699 |
## TODO: If non-html element |
## TODO: If non-html element |
| 7700 |
|
|
| 7701 |
## NOTE: Most of this code is copied from |parse_string| |
## NOTE: Most of this code is copied from |parse_string| |
| 7702 |
|
|
| 7703 |
|
## TODO: Support for $get_wrapper |
| 7704 |
|
|
| 7705 |
## Step 1 # MUST |
## Step 1 # MUST |
| 7706 |
my $this_doc = $node->owner_document; |
my $this_doc = $node->owner_document; |
| 7707 |
my $doc = $this_doc->implementation->create_document; |
my $doc = $this_doc->implementation->create_document; |
| 7711 |
|
|
| 7712 |
## Step 8 # MUST |
## Step 8 # MUST |
| 7713 |
my $i = 0; |
my $i = 0; |
| 7714 |
my $line = 1; |
$p->{line_prev} = $p->{line} = 1; |
| 7715 |
my $column = 0; |
$p->{column_prev} = $p->{column} = 0; |
| 7716 |
$p->{set_next_char} = sub { |
$p->{set_next_char} = sub { |
| 7717 |
my $self = shift; |
my $self = shift; |
| 7718 |
|
|
| 7721 |
|
|
| 7722 |
$self->{next_char} = -1 and return if $i >= length $$s; |
$self->{next_char} = -1 and return if $i >= length $$s; |
| 7723 |
$self->{next_char} = ord substr $$s, $i++, 1; |
$self->{next_char} = ord substr $$s, $i++, 1; |
| 7724 |
$column++; |
|
| 7725 |
|
($p->{line_prev}, $p->{column_prev}) = ($p->{line}, $p->{column}); |
| 7726 |
|
$p->{column}++; |
| 7727 |
|
|
| 7728 |
if ($self->{next_char} == 0x000A) { # LF |
if ($self->{next_char} == 0x000A) { # LF |
| 7729 |
$line++; |
$p->{line}++; |
| 7730 |
$column = 0; |
$p->{column} = 0; |
| 7731 |
!!!cp ('i1'); |
!!!cp ('i1'); |
| 7732 |
} elsif ($self->{next_char} == 0x000D) { # CR |
} elsif ($self->{next_char} == 0x000D) { # CR |
| 7733 |
$i++ if substr ($$s, $i, 1) eq "\x0A"; |
$i++ if substr ($$s, $i, 1) eq "\x0A"; |
| 7734 |
$self->{next_char} = 0x000A; # LF # MUST |
$self->{next_char} = 0x000A; # LF # MUST |
| 7735 |
$line++; |
$p->{line}++; |
| 7736 |
$column = 0; |
$p->{column} = 0; |
| 7737 |
!!!cp ('i2'); |
!!!cp ('i2'); |
| 7738 |
} elsif ($self->{next_char} > 0x10FFFF) { |
} elsif ($self->{next_char} > 0x10FFFF) { |
| 7739 |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
| 7742 |
!!!cp ('i4'); |
!!!cp ('i4'); |
| 7743 |
!!!parse-error (type => 'NULL'); |
!!!parse-error (type => 'NULL'); |
| 7744 |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
| 7745 |
|
} elsif ($self->{next_char} <= 0x0008 or |
| 7746 |
|
(0x000E <= $self->{next_char} and |
| 7747 |
|
$self->{next_char} <= 0x001F) or |
| 7748 |
|
(0x007F <= $self->{next_char} and |
| 7749 |
|
$self->{next_char} <= 0x009F) or |
| 7750 |
|
(0xD800 <= $self->{next_char} and |
| 7751 |
|
$self->{next_char} <= 0xDFFF) or |
| 7752 |
|
(0xFDD0 <= $self->{next_char} and |
| 7753 |
|
$self->{next_char} <= 0xFDDF) or |
| 7754 |
|
{ |
| 7755 |
|
0xFFFE => 1, 0xFFFF => 1, 0x1FFFE => 1, 0x1FFFF => 1, |
| 7756 |
|
0x2FFFE => 1, 0x2FFFF => 1, 0x3FFFE => 1, 0x3FFFF => 1, |
| 7757 |
|
0x4FFFE => 1, 0x4FFFF => 1, 0x5FFFE => 1, 0x5FFFF => 1, |
| 7758 |
|
0x6FFFE => 1, 0x6FFFF => 1, 0x7FFFE => 1, 0x7FFFF => 1, |
| 7759 |
|
0x8FFFE => 1, 0x8FFFF => 1, 0x9FFFE => 1, 0x9FFFF => 1, |
| 7760 |
|
0xAFFFE => 1, 0xAFFFF => 1, 0xBFFFE => 1, 0xBFFFF => 1, |
| 7761 |
|
0xCFFFE => 1, 0xCFFFF => 1, 0xDFFFE => 1, 0xDFFFF => 1, |
| 7762 |
|
0xEFFFE => 1, 0xEFFFF => 1, 0xFFFFE => 1, 0xFFFFF => 1, |
| 7763 |
|
0x10FFFE => 1, 0x10FFFF => 1, |
| 7764 |
|
}->{$self->{next_char}}) { |
| 7765 |
|
!!!cp ('i4.1'); |
| 7766 |
|
if ($self->{next_char} < 0x10000) { |
| 7767 |
|
!!!parse-error (type => 'control char', |
| 7768 |
|
text => (sprintf 'U+%04X', $self->{next_char})); |
| 7769 |
|
} else { |
| 7770 |
|
!!!parse-error (type => 'control char', |
| 7771 |
|
text => (sprintf 'U-%08X', $self->{next_char})); |
| 7772 |
|
} |
| 7773 |
} |
} |
| 7774 |
}; |
}; |
| 7775 |
$p->{prev_char} = [-1, -1, -1]; |
$p->{prev_char} = [-1, -1, -1]; |
| 7777 |
|
|
| 7778 |
my $ponerror = $onerror || sub { |
my $ponerror = $onerror || sub { |
| 7779 |
my (%opt) = @_; |
my (%opt) = @_; |
| 7780 |
warn "Parse error ($opt{type}) at line $opt{line} column $opt{column}\n"; |
my $line = $opt{line}; |
| 7781 |
|
my $column = $opt{column}; |
| 7782 |
|
if (defined $opt{token} and defined $opt{token}->{line}) { |
| 7783 |
|
$line = $opt{token}->{line}; |
| 7784 |
|
$column = $opt{token}->{column}; |
| 7785 |
|
} |
| 7786 |
|
warn "Parse error ($opt{type}) at line $line column $column\n"; |
| 7787 |
}; |
}; |
| 7788 |
$p->{parse_error} = sub { |
$p->{parse_error} = sub { |
| 7789 |
$ponerror->(@_, line => $line, column => $column); |
$ponerror->(line => $p->{line}, column => $p->{column}, @_); |
| 7790 |
}; |
}; |
| 7791 |
|
|
| 7792 |
$p->_initialize_tokenizer; |
$p->_initialize_tokenizer; |
| 7810 |
unless defined $p->{content_model}; |
unless defined $p->{content_model}; |
| 7811 |
## ISSUE: What is "the name of the element"? local name? |
## ISSUE: What is "the name of the element"? local name? |
| 7812 |
|
|
| 7813 |
$p->{inner_html_node} = [$node, $node_ln]; |
$p->{inner_html_node} = [$node, $el_category->{$node_ln}]; |
| 7814 |
|
## TODO: Foreign element OK? |
| 7815 |
|
|
| 7816 |
## Step 3 |
## Step 3 |
| 7817 |
my $root = $doc->create_element_ns |
my $root = $doc->create_element_ns |
| 7821 |
$doc->append_child ($root); |
$doc->append_child ($root); |
| 7822 |
|
|
| 7823 |
## Step 5 # MUST |
## Step 5 # MUST |
| 7824 |
push @{$p->{open_elements}}, [$root, 'html']; |
push @{$p->{open_elements}}, [$root, $el_category->{html}]; |
| 7825 |
|
|
| 7826 |
undef $p->{head_element}; |
undef $p->{head_element}; |
| 7827 |
|
|
| 7867 |
## ISSUE: mutation events? |
## ISSUE: mutation events? |
| 7868 |
|
|
| 7869 |
$p->_terminate_tree_constructor; |
$p->_terminate_tree_constructor; |
| 7870 |
|
|
| 7871 |
|
delete $p->{parse_error}; # delete loop |
| 7872 |
} else { |
} else { |
| 7873 |
die "$0: |set_inner_html| is not defined for node of type $nt"; |
die "$0: |set_inner_html| is not defined for node of type $nt"; |
| 7874 |
} |
} |