| 3 |
our $VERSION=do{my @r=(q$Revision$=~/\d+/g);sprintf "%d."."%02d" x $#r,@r}; |
our $VERSION=do{my @r=(q$Revision$=~/\d+/g);sprintf "%d."."%02d" x $#r,@r}; |
| 4 |
use Error qw(:try); |
use Error qw(:try); |
| 5 |
|
|
| 6 |
|
use Whatpm::HTML::Tokenizer; |
| 7 |
|
|
| 8 |
|
## NOTE: This module don't check all HTML5 parse errors; character |
| 9 |
|
## encoding related parse errors are expected to be handled by relevant |
| 10 |
|
## modules. |
| 11 |
|
## Parse errors for control characters that are not allowed in HTML5 |
| 12 |
|
## documents, for surrogate code points, and for noncharacter code |
| 13 |
|
## points, as well as U+FFFD substitions for characters whose code points |
| 14 |
|
## is higher than U+10FFFF may be detected by combining the parser with |
| 15 |
|
## the checker implemented by Whatpm::Charset::UnicodeChecker (for its |
| 16 |
|
## usage example, see |t/HTML-tree.t| in the Whatpm package or the |
| 17 |
|
## WebHACC::Language::HTML module in the WebHACC package). |
| 18 |
|
|
| 19 |
## ISSUE: |
## ISSUE: |
| 20 |
## var doc = implementation.createDocument (null, null, null); |
## var doc = implementation.createDocument (null, null, null); |
| 21 |
## doc.write (''); |
## doc.write (''); |
| 22 |
## alert (doc.compatMode); |
## alert (doc.compatMode); |
| 23 |
|
|
| 24 |
## TODO: 1252 parse error (revision 1264) |
require IO::Handle; |
| 25 |
## TODO: 8859-11 = 874 (revision 1271) |
|
| 26 |
|
## Namespace URLs |
| 27 |
|
|
| 28 |
my $HTML_NS = q<http://www.w3.org/1999/xhtml>; |
my $HTML_NS = q<http://www.w3.org/1999/xhtml>; |
| 29 |
my $MML_NS = q<http://www.w3.org/1998/Math/MathML>; |
my $MML_NS = q<http://www.w3.org/1998/Math/MathML>; |
| 32 |
my $XML_NS = q<http://www.w3.org/XML/1998/namespace>; |
my $XML_NS = q<http://www.w3.org/XML/1998/namespace>; |
| 33 |
my $XMLNS_NS = q<http://www.w3.org/2000/xmlns/>; |
my $XMLNS_NS = q<http://www.w3.org/2000/xmlns/>; |
| 34 |
|
|
| 35 |
sub A_EL () { 0b1 } |
## Element categories |
|
sub ADDRESS_EL () { 0b10 } |
|
|
sub BODY_EL () { 0b100 } |
|
|
sub BUTTON_EL () { 0b1000 } |
|
|
sub CAPTION_EL () { 0b10000 } |
|
|
sub DD_EL () { 0b100000 } |
|
|
sub DIV_EL () { 0b1000000 } |
|
|
sub DT_EL () { 0b10000000 } |
|
|
sub FORM_EL () { 0b100000000 } |
|
|
sub FORMATTING_EL () { 0b1000000000 } |
|
|
sub FRAMESET_EL () { 0b10000000000 } |
|
|
sub HEADING_EL () { 0b100000000000 } |
|
|
sub HTML_EL () { 0b1000000000000 } |
|
|
sub LI_EL () { 0b10000000000000 } |
|
|
sub NOBR_EL () { 0b100000000000000 } |
|
|
sub OPTION_EL () { 0b1000000000000000 } |
|
|
sub OPTGROUP_EL () { 0b10000000000000000 } |
|
|
sub P_EL () { 0b100000000000000000 } |
|
|
sub SELECT_EL () { 0b1000000000000000000 } |
|
|
sub TABLE_EL () { 0b10000000000000000000 } |
|
|
sub TABLE_CELL_EL () { 0b100000000000000000000 } |
|
|
sub TABLE_ROW_EL () { 0b1000000000000000000000 } |
|
|
sub TABLE_ROW_GROUP_EL () { 0b10000000000000000000000 } |
|
|
sub MISC_SCOPING_EL () { 0b100000000000000000000000 } |
|
|
sub MISC_SPECIAL_EL () { 0b1000000000000000000000000 } |
|
|
sub FOREIGN_EL () { 0b10000000000000000000000000 } |
|
|
sub FOREIGN_FLOW_CONTENT_EL () { 0b100000000000000000000000000 } |
|
|
sub MML_AXML_EL () { 0b1000000000000000000000000000 } |
|
|
|
|
|
sub TABLE_ROWS_EL () { |
|
|
TABLE_EL | |
|
|
TABLE_ROW_EL | |
|
|
TABLE_ROW_GROUP_EL |
|
|
} |
|
| 36 |
|
|
| 37 |
sub END_TAG_OPTIONAL_EL () { |
## Bits 12-15 |
| 38 |
DD_EL | |
sub SPECIAL_EL () { 0b1_000000000000000 } |
| 39 |
DT_EL | |
sub SCOPING_EL () { 0b1_00000000000000 } |
| 40 |
LI_EL | |
sub FORMATTING_EL () { 0b1_0000000000000 } |
| 41 |
P_EL |
sub PHRASING_EL () { 0b1_000000000000 } |
| 42 |
} |
|
| 43 |
|
## Bits 10-11 |
| 44 |
|
#sub FOREIGN_EL () { 0b1_00000000000 } # see Whatpm::HTML::Tokenizer |
| 45 |
|
sub FOREIGN_FLOW_CONTENT_EL () { 0b1_0000000000 } |
| 46 |
|
|
| 47 |
|
## Bits 6-9 |
| 48 |
|
sub TABLE_SCOPING_EL () { 0b1_000000000 } |
| 49 |
|
sub TABLE_ROWS_SCOPING_EL () { 0b1_00000000 } |
| 50 |
|
sub TABLE_ROW_SCOPING_EL () { 0b1_0000000 } |
| 51 |
|
sub TABLE_ROWS_EL () { 0b1_000000 } |
| 52 |
|
|
| 53 |
|
## Bit 5 |
| 54 |
|
sub ADDRESS_DIV_P_EL () { 0b1_00000 } |
| 55 |
|
|
| 56 |
|
## NOTE: Used in </body> and EOF algorithms. |
| 57 |
|
## Bit 4 |
| 58 |
|
sub ALL_END_TAG_OPTIONAL_EL () { 0b1_0000 } |
| 59 |
|
|
| 60 |
|
## NOTE: Used in "generate implied end tags" algorithm. |
| 61 |
|
## NOTE: There is a code where a modified version of |
| 62 |
|
## END_TAG_OPTIONAL_EL is used in "generate implied end tags" |
| 63 |
|
## implementation (search for the algorithm name). |
| 64 |
|
## Bit 3 |
| 65 |
|
sub END_TAG_OPTIONAL_EL () { 0b1_000 } |
| 66 |
|
|
| 67 |
|
## Bits 0-2 |
| 68 |
|
|
| 69 |
|
sub MISC_SPECIAL_EL () { SPECIAL_EL | 0b000 } |
| 70 |
|
sub FORM_EL () { SPECIAL_EL | 0b001 } |
| 71 |
|
sub FRAMESET_EL () { SPECIAL_EL | 0b010 } |
| 72 |
|
sub HEADING_EL () { SPECIAL_EL | 0b011 } |
| 73 |
|
sub SELECT_EL () { SPECIAL_EL | 0b100 } |
| 74 |
|
sub SCRIPT_EL () { SPECIAL_EL | 0b101 } |
| 75 |
|
|
| 76 |
sub ALL_END_TAG_OPTIONAL_EL () { |
sub ADDRESS_DIV_EL () { SPECIAL_EL | ADDRESS_DIV_P_EL | 0b001 } |
| 77 |
|
sub BODY_EL () { SPECIAL_EL | ALL_END_TAG_OPTIONAL_EL | 0b001 } |
| 78 |
|
|
| 79 |
|
sub DTDD_EL () { |
| 80 |
|
SPECIAL_EL | |
| 81 |
END_TAG_OPTIONAL_EL | |
END_TAG_OPTIONAL_EL | |
| 82 |
BODY_EL | |
ALL_END_TAG_OPTIONAL_EL | |
| 83 |
HTML_EL | |
0b010 |
|
TABLE_CELL_EL | |
|
|
TABLE_ROW_EL | |
|
|
TABLE_ROW_GROUP_EL |
|
| 84 |
} |
} |
| 85 |
|
sub LI_EL () { |
| 86 |
sub SCOPING_EL () { |
SPECIAL_EL | |
| 87 |
BUTTON_EL | |
END_TAG_OPTIONAL_EL | |
| 88 |
CAPTION_EL | |
ALL_END_TAG_OPTIONAL_EL | |
| 89 |
HTML_EL | |
0b100 |
|
TABLE_EL | |
|
|
TABLE_CELL_EL | |
|
|
MISC_SCOPING_EL |
|
| 90 |
} |
} |
| 91 |
|
sub P_EL () { |
| 92 |
sub TABLE_SCOPING_EL () { |
SPECIAL_EL | |
| 93 |
HTML_EL | |
ADDRESS_DIV_P_EL | |
| 94 |
TABLE_EL |
END_TAG_OPTIONAL_EL | |
| 95 |
|
ALL_END_TAG_OPTIONAL_EL | |
| 96 |
|
0b001 |
| 97 |
} |
} |
| 98 |
|
|
| 99 |
sub TABLE_ROWS_SCOPING_EL () { |
sub TABLE_ROW_EL () { |
| 100 |
HTML_EL | |
SPECIAL_EL | |
| 101 |
TABLE_ROW_GROUP_EL |
TABLE_ROWS_EL | |
| 102 |
|
TABLE_ROW_SCOPING_EL | |
| 103 |
|
ALL_END_TAG_OPTIONAL_EL | |
| 104 |
|
0b001 |
| 105 |
} |
} |
| 106 |
|
sub TABLE_ROW_GROUP_EL () { |
| 107 |
sub TABLE_ROW_SCOPING_EL () { |
SPECIAL_EL | |
| 108 |
HTML_EL | |
TABLE_ROWS_EL | |
| 109 |
TABLE_ROW_EL |
TABLE_ROWS_SCOPING_EL | |
| 110 |
|
ALL_END_TAG_OPTIONAL_EL | |
| 111 |
|
0b001 |
| 112 |
} |
} |
| 113 |
|
|
| 114 |
sub SPECIAL_EL () { |
sub MISC_SCOPING_EL () { SCOPING_EL | 0b000 } |
| 115 |
ADDRESS_EL | |
sub BUTTON_EL () { SCOPING_EL | 0b001 } |
| 116 |
BODY_EL | |
sub CAPTION_EL () { SCOPING_EL | 0b010 } |
| 117 |
DIV_EL | |
sub HTML_EL () { |
| 118 |
END_TAG_OPTIONAL_EL | |
SCOPING_EL | |
| 119 |
FORM_EL | |
TABLE_SCOPING_EL | |
| 120 |
FRAMESET_EL | |
TABLE_ROWS_SCOPING_EL | |
| 121 |
HEADING_EL | |
TABLE_ROW_SCOPING_EL | |
| 122 |
OPTION_EL | |
ALL_END_TAG_OPTIONAL_EL | |
| 123 |
OPTGROUP_EL | |
0b001 |
| 124 |
SELECT_EL | |
} |
| 125 |
TABLE_ROW_EL | |
sub TABLE_EL () { |
| 126 |
TABLE_ROW_GROUP_EL | |
SCOPING_EL | |
| 127 |
MISC_SPECIAL_EL |
TABLE_ROWS_EL | |
| 128 |
|
TABLE_SCOPING_EL | |
| 129 |
|
0b001 |
| 130 |
} |
} |
| 131 |
|
sub TABLE_CELL_EL () { |
| 132 |
|
SCOPING_EL | |
| 133 |
|
TABLE_ROW_SCOPING_EL | |
| 134 |
|
ALL_END_TAG_OPTIONAL_EL | |
| 135 |
|
0b001 |
| 136 |
|
} |
| 137 |
|
|
| 138 |
|
sub MISC_FORMATTING_EL () { FORMATTING_EL | 0b000 } |
| 139 |
|
sub A_EL () { FORMATTING_EL | 0b001 } |
| 140 |
|
sub NOBR_EL () { FORMATTING_EL | 0b010 } |
| 141 |
|
|
| 142 |
|
sub RUBY_EL () { PHRASING_EL | 0b001 } |
| 143 |
|
|
| 144 |
|
## ISSUE: ALL_END_TAG_OPTIONAL_EL? |
| 145 |
|
sub OPTGROUP_EL () { PHRASING_EL | END_TAG_OPTIONAL_EL | 0b001 } |
| 146 |
|
sub OPTION_EL () { PHRASING_EL | END_TAG_OPTIONAL_EL | 0b010 } |
| 147 |
|
sub RUBY_COMPONENT_EL () { PHRASING_EL | END_TAG_OPTIONAL_EL | 0b100 } |
| 148 |
|
|
| 149 |
|
sub MML_AXML_EL () { PHRASING_EL | FOREIGN_EL | 0b001 } |
| 150 |
|
|
| 151 |
my $el_category = { |
my $el_category = { |
| 152 |
a => A_EL | FORMATTING_EL, |
a => A_EL, |
| 153 |
address => ADDRESS_EL, |
address => ADDRESS_DIV_EL, |
| 154 |
applet => MISC_SCOPING_EL, |
applet => MISC_SCOPING_EL, |
| 155 |
area => MISC_SPECIAL_EL, |
area => MISC_SPECIAL_EL, |
| 156 |
|
article => MISC_SPECIAL_EL, |
| 157 |
|
aside => MISC_SPECIAL_EL, |
| 158 |
b => FORMATTING_EL, |
b => FORMATTING_EL, |
| 159 |
base => MISC_SPECIAL_EL, |
base => MISC_SPECIAL_EL, |
| 160 |
basefont => MISC_SPECIAL_EL, |
basefont => MISC_SPECIAL_EL, |
| 168 |
center => MISC_SPECIAL_EL, |
center => MISC_SPECIAL_EL, |
| 169 |
col => MISC_SPECIAL_EL, |
col => MISC_SPECIAL_EL, |
| 170 |
colgroup => MISC_SPECIAL_EL, |
colgroup => MISC_SPECIAL_EL, |
| 171 |
dd => DD_EL, |
command => MISC_SPECIAL_EL, |
| 172 |
|
datagrid => MISC_SPECIAL_EL, |
| 173 |
|
dd => DTDD_EL, |
| 174 |
|
details => MISC_SPECIAL_EL, |
| 175 |
|
dialog => MISC_SPECIAL_EL, |
| 176 |
dir => MISC_SPECIAL_EL, |
dir => MISC_SPECIAL_EL, |
| 177 |
div => DIV_EL, |
div => ADDRESS_DIV_EL, |
| 178 |
dl => MISC_SPECIAL_EL, |
dl => MISC_SPECIAL_EL, |
| 179 |
dt => DT_EL, |
dt => DTDD_EL, |
| 180 |
em => FORMATTING_EL, |
em => FORMATTING_EL, |
| 181 |
embed => MISC_SPECIAL_EL, |
embed => MISC_SPECIAL_EL, |
| 182 |
fieldset => MISC_SPECIAL_EL, |
fieldset => MISC_SPECIAL_EL, |
| 183 |
|
figure => MISC_SPECIAL_EL, |
| 184 |
font => FORMATTING_EL, |
font => FORMATTING_EL, |
| 185 |
|
footer => MISC_SPECIAL_EL, |
| 186 |
form => FORM_EL, |
form => FORM_EL, |
| 187 |
frame => MISC_SPECIAL_EL, |
frame => MISC_SPECIAL_EL, |
| 188 |
frameset => FRAMESET_EL, |
frameset => FRAMESET_EL, |
| 193 |
h5 => HEADING_EL, |
h5 => HEADING_EL, |
| 194 |
h6 => HEADING_EL, |
h6 => HEADING_EL, |
| 195 |
head => MISC_SPECIAL_EL, |
head => MISC_SPECIAL_EL, |
| 196 |
|
header => MISC_SPECIAL_EL, |
| 197 |
hr => MISC_SPECIAL_EL, |
hr => MISC_SPECIAL_EL, |
| 198 |
html => HTML_EL, |
html => HTML_EL, |
| 199 |
i => FORMATTING_EL, |
i => FORMATTING_EL, |
| 200 |
iframe => MISC_SPECIAL_EL, |
iframe => MISC_SPECIAL_EL, |
| 201 |
img => MISC_SPECIAL_EL, |
img => MISC_SPECIAL_EL, |
| 202 |
|
#image => MISC_SPECIAL_EL, ## NOTE: Commented out in the spec. |
| 203 |
input => MISC_SPECIAL_EL, |
input => MISC_SPECIAL_EL, |
| 204 |
isindex => MISC_SPECIAL_EL, |
isindex => MISC_SPECIAL_EL, |
| 205 |
|
## XXX keygen? (Whether a void element is in Special or not does not |
| 206 |
|
## affect to the processing, however.) |
| 207 |
li => LI_EL, |
li => LI_EL, |
| 208 |
link => MISC_SPECIAL_EL, |
link => MISC_SPECIAL_EL, |
| 209 |
listing => MISC_SPECIAL_EL, |
listing => MISC_SPECIAL_EL, |
| 210 |
marquee => MISC_SCOPING_EL, |
marquee => MISC_SCOPING_EL, |
| 211 |
menu => MISC_SPECIAL_EL, |
menu => MISC_SPECIAL_EL, |
| 212 |
meta => MISC_SPECIAL_EL, |
meta => MISC_SPECIAL_EL, |
| 213 |
nobr => NOBR_EL | FORMATTING_EL, |
nav => MISC_SPECIAL_EL, |
| 214 |
|
nobr => NOBR_EL, |
| 215 |
noembed => MISC_SPECIAL_EL, |
noembed => MISC_SPECIAL_EL, |
| 216 |
noframes => MISC_SPECIAL_EL, |
noframes => MISC_SPECIAL_EL, |
| 217 |
noscript => MISC_SPECIAL_EL, |
noscript => MISC_SPECIAL_EL, |
| 223 |
param => MISC_SPECIAL_EL, |
param => MISC_SPECIAL_EL, |
| 224 |
plaintext => MISC_SPECIAL_EL, |
plaintext => MISC_SPECIAL_EL, |
| 225 |
pre => MISC_SPECIAL_EL, |
pre => MISC_SPECIAL_EL, |
| 226 |
|
rp => RUBY_COMPONENT_EL, |
| 227 |
|
rt => RUBY_COMPONENT_EL, |
| 228 |
|
ruby => RUBY_EL, |
| 229 |
s => FORMATTING_EL, |
s => FORMATTING_EL, |
| 230 |
script => MISC_SPECIAL_EL, |
script => MISC_SPECIAL_EL, |
| 231 |
select => SELECT_EL, |
select => SELECT_EL, |
| 232 |
|
section => MISC_SPECIAL_EL, |
| 233 |
small => FORMATTING_EL, |
small => FORMATTING_EL, |
| 234 |
spacer => MISC_SPECIAL_EL, |
spacer => MISC_SPECIAL_EL, |
| 235 |
strike => FORMATTING_EL, |
strike => FORMATTING_EL, |
| 253 |
my $el_category_f = { |
my $el_category_f = { |
| 254 |
$MML_NS => { |
$MML_NS => { |
| 255 |
'annotation-xml' => MML_AXML_EL, |
'annotation-xml' => MML_AXML_EL, |
| 256 |
mi => FOREIGN_FLOW_CONTENT_EL, |
mi => FOREIGN_EL | FOREIGN_FLOW_CONTENT_EL, |
| 257 |
mo => FOREIGN_FLOW_CONTENT_EL, |
mo => FOREIGN_EL | FOREIGN_FLOW_CONTENT_EL, |
| 258 |
mn => FOREIGN_FLOW_CONTENT_EL, |
mn => FOREIGN_EL | FOREIGN_FLOW_CONTENT_EL, |
| 259 |
ms => FOREIGN_FLOW_CONTENT_EL, |
ms => FOREIGN_EL | FOREIGN_FLOW_CONTENT_EL, |
| 260 |
mtext => FOREIGN_FLOW_CONTENT_EL, |
mtext => FOREIGN_EL | FOREIGN_FLOW_CONTENT_EL, |
| 261 |
}, |
}, |
| 262 |
$SVG_NS => { |
$SVG_NS => { |
| 263 |
foreignObject => FOREIGN_FLOW_CONTENT_EL, |
foreignObject => SCOPING_EL | FOREIGN_EL | FOREIGN_FLOW_CONTENT_EL, |
| 264 |
desc => FOREIGN_FLOW_CONTENT_EL, |
desc => FOREIGN_EL | FOREIGN_FLOW_CONTENT_EL, |
| 265 |
title => FOREIGN_FLOW_CONTENT_EL, |
title => FOREIGN_EL | FOREIGN_FLOW_CONTENT_EL, |
| 266 |
}, |
}, |
| 267 |
## NOTE: In addition, FOREIGN_EL is set to non-HTML elements. |
## NOTE: In addition, FOREIGN_EL is set to non-HTML elements. |
| 268 |
}; |
}; |
| 269 |
|
|
| 270 |
my $svg_attr_name = { |
my $svg_attr_name = { |
| 271 |
|
attributename => 'attributeName', |
| 272 |
attributetype => 'attributeType', |
attributetype => 'attributeType', |
| 273 |
basefrequency => 'baseFrequency', |
basefrequency => 'baseFrequency', |
| 274 |
baseprofile => 'baseProfile', |
baseprofile => 'baseProfile', |
| 279 |
diffuseconstant => 'diffuseConstant', |
diffuseconstant => 'diffuseConstant', |
| 280 |
edgemode => 'edgeMode', |
edgemode => 'edgeMode', |
| 281 |
externalresourcesrequired => 'externalResourcesRequired', |
externalresourcesrequired => 'externalResourcesRequired', |
|
fecolormatrix => 'feColorMatrix', |
|
|
fecomposite => 'feComposite', |
|
|
fegaussianblur => 'feGaussianBlur', |
|
|
femorphology => 'feMorphology', |
|
|
fetile => 'feTile', |
|
| 282 |
filterres => 'filterRes', |
filterres => 'filterRes', |
| 283 |
filterunits => 'filterUnits', |
filterunits => 'filterUnits', |
| 284 |
glyphref => 'glyphRef', |
glyphref => 'glyphRef', |
| 312 |
repeatcount => 'repeatCount', |
repeatcount => 'repeatCount', |
| 313 |
repeatdur => 'repeatDur', |
repeatdur => 'repeatDur', |
| 314 |
requiredextensions => 'requiredExtensions', |
requiredextensions => 'requiredExtensions', |
| 315 |
|
requiredfeatures => 'requiredFeatures', |
| 316 |
specularconstant => 'specularConstant', |
specularconstant => 'specularConstant', |
| 317 |
specularexponent => 'specularExponent', |
specularexponent => 'specularExponent', |
| 318 |
spreadmethod => 'spreadMethod', |
spreadmethod => 'spreadMethod', |
| 349 |
|
|
| 350 |
## ISSUE: xmlns:xlink="non-xlink-ns" is not an error. |
## ISSUE: xmlns:xlink="non-xlink-ns" is not an error. |
| 351 |
|
|
| 352 |
my $c1_entity_char = { |
## TODO: Invoke the reset algorithm when a resettable element is |
| 353 |
0x80 => 0x20AC, |
## created (cf. HTML5 revision 2259). |
|
0x81 => 0xFFFD, |
|
|
0x82 => 0x201A, |
|
|
0x83 => 0x0192, |
|
|
0x84 => 0x201E, |
|
|
0x85 => 0x2026, |
|
|
0x86 => 0x2020, |
|
|
0x87 => 0x2021, |
|
|
0x88 => 0x02C6, |
|
|
0x89 => 0x2030, |
|
|
0x8A => 0x0160, |
|
|
0x8B => 0x2039, |
|
|
0x8C => 0x0152, |
|
|
0x8D => 0xFFFD, |
|
|
0x8E => 0x017D, |
|
|
0x8F => 0xFFFD, |
|
|
0x90 => 0xFFFD, |
|
|
0x91 => 0x2018, |
|
|
0x92 => 0x2019, |
|
|
0x93 => 0x201C, |
|
|
0x94 => 0x201D, |
|
|
0x95 => 0x2022, |
|
|
0x96 => 0x2013, |
|
|
0x97 => 0x2014, |
|
|
0x98 => 0x02DC, |
|
|
0x99 => 0x2122, |
|
|
0x9A => 0x0161, |
|
|
0x9B => 0x203A, |
|
|
0x9C => 0x0153, |
|
|
0x9D => 0xFFFD, |
|
|
0x9E => 0x017E, |
|
|
0x9F => 0x0178, |
|
|
}; # $c1_entity_char |
|
| 354 |
|
|
| 355 |
sub parse_byte_string ($$$$;$) { |
sub parse_byte_string ($$$$;$) { |
| 356 |
|
my $self = shift; |
| 357 |
|
my $charset_name = shift; |
| 358 |
|
open my $input, '<', ref $_[0] ? $_[0] : \($_[0]); |
| 359 |
|
return $self->parse_byte_stream ($charset_name, $input, @_[1..$#_]); |
| 360 |
|
} # parse_byte_string |
| 361 |
|
|
| 362 |
|
sub parse_byte_stream ($$$$;$$) { |
| 363 |
|
# my ($self, $charset_name, $byte_stream, $doc, $onerror, $get_wrapper) = @_; |
| 364 |
my $self = ref $_[0] ? shift : shift->new; |
my $self = ref $_[0] ? shift : shift->new; |
| 365 |
my $charset = shift; |
my $charset_name = shift; |
| 366 |
my $bytes_s = ref $_[0] ? $_[0] : \($_[0]); |
my $byte_stream = $_[0]; |
| 367 |
my $s; |
|
| 368 |
|
my $onerror = $_[2] || sub { |
| 369 |
if (defined $charset) { |
my (%opt) = @_; |
| 370 |
require Encode; ## TODO: decode(utf8) don't delete BOM |
warn "Parse error ($opt{type})\n"; |
| 371 |
$s = \ (Encode::decode ($charset, $$bytes_s)); |
}; |
| 372 |
$self->{input_encoding} = lc $charset; ## TODO: normalize name |
$self->{parse_error} = $onerror; # updated later by parse_char_string |
| 373 |
$self->{confident} = 1; |
|
| 374 |
} else { |
my $get_wrapper = $_[3] || sub ($) { |
| 375 |
## TODO: Implement HTML5 detection algorithm |
return $_[0]; # $_[0] = byte stream handle, returned = arg to char handle |
| 376 |
|
}; |
| 377 |
|
|
| 378 |
|
## HTML5 encoding sniffing algorithm |
| 379 |
|
require Message::Charset::Info; |
| 380 |
|
my $charset; |
| 381 |
|
my $buffer; |
| 382 |
|
my ($char_stream, $e_status); |
| 383 |
|
|
| 384 |
|
SNIFFING: { |
| 385 |
|
## NOTE: By setting |allow_fallback| option true when the |
| 386 |
|
## |get_decode_handle| method is invoked, we ignore what the HTML5 |
| 387 |
|
## spec requires, i.e. unsupported encoding should be ignored. |
| 388 |
|
## TODO: We should not do this unless the parser is invoked |
| 389 |
|
## in the conformance checking mode, in which this behavior |
| 390 |
|
## would be useful. |
| 391 |
|
|
| 392 |
|
## Step 1 |
| 393 |
|
if (defined $charset_name) { |
| 394 |
|
$charset = Message::Charset::Info->get_by_html_name ($charset_name); |
| 395 |
|
## TODO: Is this ok? Transfer protocol's parameter should be |
| 396 |
|
## interpreted in its semantics? |
| 397 |
|
|
| 398 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 399 |
|
($byte_stream, allow_error_reporting => 1, |
| 400 |
|
allow_fallback => 1); |
| 401 |
|
if ($char_stream) { |
| 402 |
|
$self->{confident} = 1; |
| 403 |
|
last SNIFFING; |
| 404 |
|
} else { |
| 405 |
|
!!!parse-error (type => 'charset:not supported', |
| 406 |
|
layer => 'encode', |
| 407 |
|
line => 1, column => 1, |
| 408 |
|
value => $charset_name, |
| 409 |
|
level => $self->{level}->{uncertain}); |
| 410 |
|
} |
| 411 |
|
} |
| 412 |
|
|
| 413 |
|
## Step 2 |
| 414 |
|
my $byte_buffer = ''; |
| 415 |
|
for (1..1024) { |
| 416 |
|
my $char = $byte_stream->getc; |
| 417 |
|
last unless defined $char; |
| 418 |
|
$byte_buffer .= $char; |
| 419 |
|
} ## TODO: timeout |
| 420 |
|
|
| 421 |
|
## Step 3 |
| 422 |
|
if ($byte_buffer =~ /^\xFE\xFF/) { |
| 423 |
|
$charset = Message::Charset::Info->get_by_html_name ('utf-16be'); |
| 424 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 425 |
|
($byte_stream, allow_error_reporting => 1, |
| 426 |
|
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 427 |
|
$self->{confident} = 1; |
| 428 |
|
last SNIFFING; |
| 429 |
|
} elsif ($byte_buffer =~ /^\xFF\xFE/) { |
| 430 |
|
$charset = Message::Charset::Info->get_by_html_name ('utf-16le'); |
| 431 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 432 |
|
($byte_stream, allow_error_reporting => 1, |
| 433 |
|
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 434 |
|
$self->{confident} = 1; |
| 435 |
|
last SNIFFING; |
| 436 |
|
} elsif ($byte_buffer =~ /^\xEF\xBB\xBF/) { |
| 437 |
|
$charset = Message::Charset::Info->get_by_html_name ('utf-8'); |
| 438 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 439 |
|
($byte_stream, allow_error_reporting => 1, |
| 440 |
|
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 441 |
|
$self->{confident} = 1; |
| 442 |
|
last SNIFFING; |
| 443 |
|
} |
| 444 |
|
|
| 445 |
|
## Step 4 |
| 446 |
|
## TODO: <meta charset> |
| 447 |
|
|
| 448 |
|
## Step 5 |
| 449 |
|
## TODO: from history |
| 450 |
|
|
| 451 |
|
## Step 6 |
| 452 |
require Whatpm::Charset::UniversalCharDet; |
require Whatpm::Charset::UniversalCharDet; |
| 453 |
$charset = Whatpm::Charset::UniversalCharDet->detect_byte_string |
$charset_name = Whatpm::Charset::UniversalCharDet->detect_byte_string |
| 454 |
(substr ($$bytes_s, 0, 1024)); |
($byte_buffer); |
| 455 |
$charset ||= 'windows-1252'; |
if (defined $charset_name) { |
| 456 |
$s = \ (Encode::decode ($charset, $$bytes_s)); |
$charset = Message::Charset::Info->get_by_html_name ($charset_name); |
| 457 |
$self->{input_encoding} = $charset; |
|
| 458 |
|
require Whatpm::Charset::DecodeHandle; |
| 459 |
|
$buffer = Whatpm::Charset::DecodeHandle::ByteBuffer->new |
| 460 |
|
($byte_stream); |
| 461 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 462 |
|
($buffer, allow_error_reporting => 1, |
| 463 |
|
allow_fallback => 1, byte_buffer => \$byte_buffer); |
| 464 |
|
if ($char_stream) { |
| 465 |
|
$buffer->{buffer} = $byte_buffer; |
| 466 |
|
!!!parse-error (type => 'sniffing:chardet', |
| 467 |
|
text => $charset_name, |
| 468 |
|
level => $self->{level}->{info}, |
| 469 |
|
layer => 'encode', |
| 470 |
|
line => 1, column => 1); |
| 471 |
|
$self->{confident} = 0; |
| 472 |
|
last SNIFFING; |
| 473 |
|
} |
| 474 |
|
} |
| 475 |
|
|
| 476 |
|
## Step 7: default |
| 477 |
|
## TODO: Make this configurable. |
| 478 |
|
$charset = Message::Charset::Info->get_by_html_name ('windows-1252'); |
| 479 |
|
## NOTE: We choose |windows-1252| here, since |utf-8| should be |
| 480 |
|
## detectable in the step 6. |
| 481 |
|
require Whatpm::Charset::DecodeHandle; |
| 482 |
|
$buffer = Whatpm::Charset::DecodeHandle::ByteBuffer->new |
| 483 |
|
($byte_stream); |
| 484 |
|
($char_stream, $e_status) |
| 485 |
|
= $charset->get_decode_handle ($buffer, |
| 486 |
|
allow_error_reporting => 1, |
| 487 |
|
allow_fallback => 1, |
| 488 |
|
byte_buffer => \$byte_buffer); |
| 489 |
|
$buffer->{buffer} = $byte_buffer; |
| 490 |
|
!!!parse-error (type => 'sniffing:default', |
| 491 |
|
text => 'windows-1252', |
| 492 |
|
level => $self->{level}->{info}, |
| 493 |
|
line => 1, column => 1, |
| 494 |
|
layer => 'encode'); |
| 495 |
$self->{confident} = 0; |
$self->{confident} = 0; |
| 496 |
|
} # SNIFFING |
| 497 |
|
|
| 498 |
|
if ($e_status & Message::Charset::Info::FALLBACK_ENCODING_IMPL ()) { |
| 499 |
|
$self->{input_encoding} = $charset->get_iana_name; ## TODO: Should we set actual charset decoder's encoding name? |
| 500 |
|
!!!parse-error (type => 'chardecode:fallback', |
| 501 |
|
#text => $self->{input_encoding}, |
| 502 |
|
level => $self->{level}->{uncertain}, |
| 503 |
|
line => 1, column => 1, |
| 504 |
|
layer => 'encode'); |
| 505 |
|
} elsif (not ($e_status & |
| 506 |
|
Message::Charset::Info::ERROR_REPORTING_ENCODING_IMPL ())) { |
| 507 |
|
$self->{input_encoding} = $charset->get_iana_name; |
| 508 |
|
!!!parse-error (type => 'chardecode:no error', |
| 509 |
|
text => $self->{input_encoding}, |
| 510 |
|
level => $self->{level}->{uncertain}, |
| 511 |
|
line => 1, column => 1, |
| 512 |
|
layer => 'encode'); |
| 513 |
|
} else { |
| 514 |
|
$self->{input_encoding} = $charset->get_iana_name; |
| 515 |
} |
} |
| 516 |
|
|
| 517 |
$self->{change_encoding} = sub { |
$self->{change_encoding} = sub { |
| 518 |
my $self = shift; |
my $self = shift; |
| 519 |
my $charset = lc shift; |
$charset_name = shift; |
| 520 |
my $token = shift; |
my $token = shift; |
|
## TODO: if $charset is supported |
|
|
## TODO: normalize charset name |
|
| 521 |
|
|
| 522 |
## "Change the encoding" algorithm: |
$charset = Message::Charset::Info->get_by_html_name ($charset_name); |
| 523 |
|
($char_stream, $e_status) = $charset->get_decode_handle |
| 524 |
|
($byte_stream, allow_error_reporting => 1, allow_fallback => 1, |
| 525 |
|
byte_buffer => \ $buffer->{buffer}); |
| 526 |
|
|
| 527 |
|
if ($char_stream) { # if supported |
| 528 |
|
## "Change the encoding" algorithm: |
| 529 |
|
|
| 530 |
|
## Step 1 |
| 531 |
|
if (defined $self->{input_encoding} and |
| 532 |
|
$self->{input_encoding} eq $charset_name) { |
| 533 |
|
!!!parse-error (type => 'charset label:matching', |
| 534 |
|
text => $charset_name, |
| 535 |
|
level => $self->{level}->{info}); |
| 536 |
|
$self->{confident} = 1; |
| 537 |
|
return; |
| 538 |
|
} |
| 539 |
|
|
| 540 |
## Step 1 |
## Step 2 (HTML5 revision 3205) |
| 541 |
if ($charset eq 'utf-16') { ## ISSUE: UTF-16BE -> UTF-8? UTF-16LE -> UTF-8? |
if (defined $self->{input_encoding} and |
| 542 |
$charset = 'utf-8'; |
Message::Charset::Info->get_by_html_name ($self->{input_encoding}) |
| 543 |
} |
->{category} & Message::Charset::Info::CHARSET_CATEGORY_UTF16 ()) { |
| 544 |
|
$self->{confident} = 1; |
| 545 |
|
return; |
| 546 |
|
} |
| 547 |
|
|
| 548 |
## Step 2 |
## Step 3 |
| 549 |
if (defined $self->{input_encoding} and |
if ($charset->{category} & |
| 550 |
$self->{input_encoding} eq $charset) { |
Message::Charset::Info::CHARSET_CATEGORY_UTF16 ()) { |
| 551 |
$self->{confident} = 1; |
$charset = Message::Charset::Info->get_by_html_name ('utf-8'); |
| 552 |
return; |
($char_stream, $e_status) = $charset->get_decode_handle |
| 553 |
|
($byte_stream, |
| 554 |
|
byte_buffer => \ $buffer->{buffer}); |
| 555 |
|
} |
| 556 |
|
$charset_name = $charset->get_iana_name; |
| 557 |
|
|
| 558 |
|
!!!parse-error (type => 'charset label detected', |
| 559 |
|
text => $self->{input_encoding}, |
| 560 |
|
value => $charset_name, |
| 561 |
|
level => $self->{level}->{warn}, |
| 562 |
|
token => $token); |
| 563 |
|
|
| 564 |
|
## Step 4 |
| 565 |
|
# if (can) { |
| 566 |
|
## change the encoding on the fly. |
| 567 |
|
#$self->{confident} = 1; |
| 568 |
|
#return; |
| 569 |
|
# } |
| 570 |
|
|
| 571 |
|
## Step 5 |
| 572 |
|
throw Whatpm::HTML::RestartParser (); |
| 573 |
} |
} |
| 574 |
|
}; # $self->{change_encoding} |
| 575 |
|
|
| 576 |
!!!parse-error (type => 'charset label detected:'.$self->{input_encoding}. |
my $char_onerror = sub { |
| 577 |
':'.$charset, level => 'w', token => $token); |
my (undef, $type, %opt) = @_; |
| 578 |
|
!!!parse-error (layer => 'encode', |
| 579 |
|
line => $self->{line}, column => $self->{column} + 1, |
| 580 |
|
%opt, type => $type); |
| 581 |
|
if ($opt{octets}) { |
| 582 |
|
${$opt{octets}} = "\x{FFFD}"; # relacement character |
| 583 |
|
} |
| 584 |
|
}; |
| 585 |
|
|
| 586 |
## Step 3 |
my $wrapped_char_stream = $get_wrapper->($char_stream); |
| 587 |
# if (can) { |
$wrapped_char_stream->onerror ($char_onerror); |
|
## change the encoding on the fly. |
|
|
#$self->{confident} = 1; |
|
|
#return; |
|
|
# } |
|
| 588 |
|
|
| 589 |
## Step 4 |
my @args = ($_[1], $_[2]); # $doc, $onerror - $get_wrapper = undef; |
|
throw Whatpm::HTML::RestartParser (charset => $charset); |
|
|
}; # $self->{change_encoding} |
|
|
|
|
|
my @args = @_; shift @args; # $s |
|
| 590 |
my $return; |
my $return; |
| 591 |
try { |
try { |
| 592 |
$return = $self->parse_char_string ($s, @args); |
$return = $self->parse_char_stream ($wrapped_char_stream, @args); |
| 593 |
} catch Whatpm::HTML::RestartParser with { |
} catch Whatpm::HTML::RestartParser with { |
| 594 |
my $charset = shift->{charset}; |
## NOTE: Invoked after {change_encoding}. |
| 595 |
$s = \ (Encode::decode ($charset, $$bytes_s)); |
|
| 596 |
$self->{input_encoding} = $charset; ## TODO: normalize |
if ($e_status & Message::Charset::Info::FALLBACK_ENCODING_IMPL ()) { |
| 597 |
|
$self->{input_encoding} = $charset->get_iana_name; ## TODO: Should we set actual charset decoder's encoding name? |
| 598 |
|
!!!parse-error (type => 'chardecode:fallback', |
| 599 |
|
level => $self->{level}->{uncertain}, |
| 600 |
|
#text => $self->{input_encoding}, |
| 601 |
|
line => 1, column => 1, |
| 602 |
|
layer => 'encode'); |
| 603 |
|
} elsif (not ($e_status & |
| 604 |
|
Message::Charset::Info::ERROR_REPORTING_ENCODING_IMPL ())) { |
| 605 |
|
$self->{input_encoding} = $charset->get_iana_name; |
| 606 |
|
!!!parse-error (type => 'chardecode:no error', |
| 607 |
|
text => $self->{input_encoding}, |
| 608 |
|
level => $self->{level}->{uncertain}, |
| 609 |
|
line => 1, column => 1, |
| 610 |
|
layer => 'encode'); |
| 611 |
|
} else { |
| 612 |
|
$self->{input_encoding} = $charset->get_iana_name; |
| 613 |
|
} |
| 614 |
$self->{confident} = 1; |
$self->{confident} = 1; |
| 615 |
$return = $self->parse_char_string ($s, @args); |
|
| 616 |
|
$wrapped_char_stream = $get_wrapper->($char_stream); |
| 617 |
|
$wrapped_char_stream->onerror ($char_onerror); |
| 618 |
|
|
| 619 |
|
$return = $self->parse_char_stream ($wrapped_char_stream, @args); |
| 620 |
}; |
}; |
| 621 |
return $return; |
return $return; |
| 622 |
} # parse_byte_string |
} # parse_byte_stream |
| 623 |
|
|
| 624 |
## NOTE: HTML5 spec says that the encoding layer MUST NOT strip BOM |
## NOTE: HTML5 spec says that the encoding layer MUST NOT strip BOM |
| 625 |
## 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 |
| 630 |
## 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 |
| 631 |
## strip the BOM and never strip any ZWNBSP. |
## strip the BOM and never strip any ZWNBSP. |
| 632 |
|
|
| 633 |
*parse_char_string = \&parse_string; |
sub parse_char_string ($$$;$$) { |
| 634 |
|
#my ($self, $s, $doc, $onerror, $get_wrapper) = @_; |
| 635 |
|
my $self = shift; |
| 636 |
|
my $s = ref $_[0] ? $_[0] : \($_[0]); |
| 637 |
|
require Whatpm::Charset::DecodeHandle; |
| 638 |
|
my $input = Whatpm::Charset::DecodeHandle::CharString->new ($s); |
| 639 |
|
return $self->parse_char_stream ($input, @_[1..$#_]); |
| 640 |
|
} # parse_char_string |
| 641 |
|
*parse_string = \&parse_char_string; ## NOTE: Alias for backward compatibility. |
| 642 |
|
|
| 643 |
sub parse_string ($$$;$) { |
sub parse_char_stream ($$$;$$) { |
| 644 |
my $self = ref $_[0] ? shift : shift->new; |
my $self = ref $_[0] ? shift : shift->new; |
| 645 |
my $s = ref $_[0] ? $_[0] : \($_[0]); |
my $input = $_[0]; |
| 646 |
$self->{document} = $_[1]; |
$self->{document} = $_[1]; |
| 647 |
@{$self->{document}->child_nodes} = (); |
@{$self->{document}->child_nodes} = (); |
| 648 |
|
|
| 651 |
$self->{confident} = 1 unless exists $self->{confident}; |
$self->{confident} = 1 unless exists $self->{confident}; |
| 652 |
$self->{document}->input_encoding ($self->{input_encoding}) |
$self->{document}->input_encoding ($self->{input_encoding}) |
| 653 |
if defined $self->{input_encoding}; |
if defined $self->{input_encoding}; |
| 654 |
|
## TODO: |{input_encoding}| is needless? |
| 655 |
|
|
|
my $i = 0; |
|
| 656 |
$self->{line_prev} = $self->{line} = 1; |
$self->{line_prev} = $self->{line} = 1; |
| 657 |
$self->{column_prev} = $self->{column} = 0; |
$self->{column_prev} = -1; |
| 658 |
$self->{set_next_char} = sub { |
$self->{column} = 0; |
| 659 |
|
$self->{set_nc} = sub { |
| 660 |
my $self = shift; |
my $self = shift; |
| 661 |
|
|
| 662 |
pop @{$self->{prev_char}}; |
my $char = ''; |
| 663 |
unshift @{$self->{prev_char}}, $self->{next_char}; |
if (defined $self->{next_nc}) { |
| 664 |
|
$char = $self->{next_nc}; |
| 665 |
|
delete $self->{next_nc}; |
| 666 |
|
$self->{nc} = ord $char; |
| 667 |
|
} else { |
| 668 |
|
$self->{char_buffer} = ''; |
| 669 |
|
$self->{char_buffer_pos} = 0; |
| 670 |
|
|
| 671 |
|
my $count = $input->manakai_read_until |
| 672 |
|
($self->{char_buffer}, qr/[^\x00\x0A\x0D]/, $self->{char_buffer_pos}); |
| 673 |
|
if ($count) { |
| 674 |
|
$self->{line_prev} = $self->{line}; |
| 675 |
|
$self->{column_prev} = $self->{column}; |
| 676 |
|
$self->{column}++; |
| 677 |
|
$self->{nc} |
| 678 |
|
= ord substr ($self->{char_buffer}, $self->{char_buffer_pos}++, 1); |
| 679 |
|
return; |
| 680 |
|
} |
| 681 |
|
|
| 682 |
$self->{next_char} = -1 and return if $i >= length $$s; |
if ($input->read ($char, 1)) { |
| 683 |
$self->{next_char} = ord substr $$s, $i++, 1; |
$self->{nc} = ord $char; |
| 684 |
|
} else { |
| 685 |
|
$self->{nc} = -1; |
| 686 |
|
return; |
| 687 |
|
} |
| 688 |
|
} |
| 689 |
|
|
| 690 |
($self->{line_prev}, $self->{column_prev}) |
($self->{line_prev}, $self->{column_prev}) |
| 691 |
= ($self->{line}, $self->{column}); |
= ($self->{line}, $self->{column}); |
| 692 |
$self->{column}++; |
$self->{column}++; |
| 693 |
|
|
| 694 |
if ($self->{next_char} == 0x000A) { # LF |
if ($self->{nc} == 0x000A) { # LF |
| 695 |
!!!cp ('j1'); |
!!!cp ('j1'); |
| 696 |
$self->{line}++; |
$self->{line}++; |
| 697 |
$self->{column} = 0; |
$self->{column} = 0; |
| 698 |
} elsif ($self->{next_char} == 0x000D) { # CR |
} elsif ($self->{nc} == 0x000D) { # CR |
| 699 |
!!!cp ('j2'); |
!!!cp ('j2'); |
| 700 |
$i++ if substr ($$s, $i, 1) eq "\x0A"; |
## TODO: support for abort/streaming |
| 701 |
$self->{next_char} = 0x000A; # LF # MUST |
my $next = ''; |
| 702 |
|
if ($input->read ($next, 1) and $next ne "\x0A") { |
| 703 |
|
$self->{next_nc} = $next; |
| 704 |
|
} |
| 705 |
|
$self->{nc} = 0x000A; # LF # MUST |
| 706 |
$self->{line}++; |
$self->{line}++; |
| 707 |
$self->{column} = 0; |
$self->{column} = 0; |
| 708 |
} elsif ($self->{next_char} > 0x10FFFF) { |
} elsif ($self->{nc} == 0x0000) { # NULL |
|
!!!cp ('j3'); |
|
|
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
|
|
} elsif ($self->{next_char} == 0x0000) { # NULL |
|
| 709 |
!!!cp ('j4'); |
!!!cp ('j4'); |
| 710 |
!!!parse-error (type => 'NULL'); |
!!!parse-error (type => 'NULL'); |
| 711 |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
$self->{nc} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
|
} elsif ($self->{next_char} <= 0x0008 or |
|
|
(0x000E <= $self->{next_char} and $self->{next_char} <= 0x001F) or |
|
|
(0x007F <= $self->{next_char} and $self->{next_char} <= 0x009F) or |
|
|
(0xD800 <= $self->{next_char} and $self->{next_char} <= 0xDFFF) or |
|
|
(0xFDD0 <= $self->{next_char} and $self->{next_char} <= 0xFDDF) or |
|
|
{ |
|
|
0xFFFE => 1, 0xFFFF => 1, 0x1FFFE => 1, 0x1FFFF => 1, |
|
|
0x2FFFE => 1, 0x2FFFF => 1, 0x3FFFE => 1, 0x3FFFF => 1, |
|
|
0x4FFFE => 1, 0x4FFFF => 1, 0x5FFFE => 1, 0x5FFFF => 1, |
|
|
0x6FFFE => 1, 0x6FFFF => 1, 0x7FFFE => 1, 0x7FFFF => 1, |
|
|
0x8FFFE => 1, 0x8FFFF => 1, 0x9FFFE => 1, 0x9FFFF => 1, |
|
|
0xAFFFE => 1, 0xAFFFF => 1, 0xBFFFE => 1, 0xBFFFF => 1, |
|
|
0xCFFFE => 1, 0xCFFFF => 1, 0xDFFFE => 1, 0xDFFFF => 1, |
|
|
0xEFFFE => 1, 0xEFFFF => 1, 0xFFFFE => 1, 0xFFFFF => 1, |
|
|
0x10FFFE => 1, 0x10FFFF => 1, |
|
|
}->{$self->{next_char}}) { |
|
|
!!!cp ('j5'); |
|
|
!!!parse-error (type => 'control char', level => $self->{must_level}); |
|
|
## TODO: error type documentation |
|
| 712 |
} |
} |
| 713 |
}; |
}; |
| 714 |
$self->{prev_char} = [-1, -1, -1]; |
|
| 715 |
$self->{next_char} = -1; |
$self->{read_until} = sub { |
| 716 |
|
#my ($scalar, $specials_range, $offset) = @_; |
| 717 |
|
return 0 if defined $self->{next_nc}; |
| 718 |
|
|
| 719 |
|
my $pattern = qr/[^$_[1]\x00\x0A\x0D]/; |
| 720 |
|
my $offset = $_[2] || 0; |
| 721 |
|
|
| 722 |
|
if ($self->{char_buffer_pos} < length $self->{char_buffer}) { |
| 723 |
|
pos ($self->{char_buffer}) = $self->{char_buffer_pos}; |
| 724 |
|
if ($self->{char_buffer} =~ /\G(?>$pattern)+/) { |
| 725 |
|
substr ($_[0], $offset) |
| 726 |
|
= substr ($self->{char_buffer}, $-[0], $+[0] - $-[0]); |
| 727 |
|
my $count = $+[0] - $-[0]; |
| 728 |
|
if ($count) { |
| 729 |
|
$self->{column} += $count; |
| 730 |
|
$self->{char_buffer_pos} += $count; |
| 731 |
|
$self->{line_prev} = $self->{line}; |
| 732 |
|
$self->{column_prev} = $self->{column} - 1; |
| 733 |
|
$self->{nc} = -1; |
| 734 |
|
} |
| 735 |
|
return $count; |
| 736 |
|
} else { |
| 737 |
|
return 0; |
| 738 |
|
} |
| 739 |
|
} else { |
| 740 |
|
my $count = $input->manakai_read_until ($_[0], $pattern, $_[2]); |
| 741 |
|
if ($count) { |
| 742 |
|
$self->{column} += $count; |
| 743 |
|
$self->{line_prev} = $self->{line}; |
| 744 |
|
$self->{column_prev} = $self->{column} - 1; |
| 745 |
|
$self->{nc} = -1; |
| 746 |
|
} |
| 747 |
|
return $count; |
| 748 |
|
} |
| 749 |
|
}; # $self->{read_until} |
| 750 |
|
|
| 751 |
my $onerror = $_[2] || sub { |
my $onerror = $_[2] || sub { |
| 752 |
my (%opt) = @_; |
my (%opt) = @_; |
| 758 |
$onerror->(line => $self->{line}, column => $self->{column}, @_); |
$onerror->(line => $self->{line}, column => $self->{column}, @_); |
| 759 |
}; |
}; |
| 760 |
|
|
| 761 |
|
my $char_onerror = sub { |
| 762 |
|
my (undef, $type, %opt) = @_; |
| 763 |
|
!!!parse-error (layer => 'encode', |
| 764 |
|
line => $self->{line}, column => $self->{column} + 1, |
| 765 |
|
%opt, type => $type); |
| 766 |
|
}; # $char_onerror |
| 767 |
|
|
| 768 |
|
if ($_[3]) { |
| 769 |
|
$input = $_[3]->($input); |
| 770 |
|
$input->onerror ($char_onerror); |
| 771 |
|
} else { |
| 772 |
|
$input->onerror ($char_onerror) unless defined $input->onerror; |
| 773 |
|
} |
| 774 |
|
|
| 775 |
$self->_initialize_tokenizer; |
$self->_initialize_tokenizer; |
| 776 |
$self->_initialize_tree_constructor; |
$self->_initialize_tree_constructor; |
| 777 |
$self->_construct_tree; |
$self->_construct_tree; |
| 780 |
delete $self->{parse_error}; # remove loop |
delete $self->{parse_error}; # remove loop |
| 781 |
|
|
| 782 |
return $self->{document}; |
return $self->{document}; |
| 783 |
} # parse_string |
} # parse_char_stream |
| 784 |
|
|
| 785 |
sub new ($) { |
sub new ($) { |
| 786 |
my $class = shift; |
my $class = shift; |
| 787 |
my $self = bless {}, $class; |
my $self = bless { |
| 788 |
$self->{set_next_char} = sub { |
level => {must => 'm', |
| 789 |
$self->{next_char} = -1; |
should => 's', |
| 790 |
|
warn => 'w', |
| 791 |
|
info => 'i', |
| 792 |
|
uncertain => 'u'}, |
| 793 |
|
}, $class; |
| 794 |
|
$self->{set_nc} = sub { |
| 795 |
|
$self->{nc} = -1; |
| 796 |
}; |
}; |
| 797 |
$self->{parse_error} = sub { |
$self->{parse_error} = sub { |
| 798 |
# |
# |
| 809 |
return $self; |
return $self; |
| 810 |
} # new |
} # new |
| 811 |
|
|
| 812 |
sub CM_ENTITY () { 0b001 } # & markup in data |
## Insertion modes |
|
sub CM_LIMITED_MARKUP () { 0b010 } # < markup in data (limited) |
|
|
sub CM_FULL_MARKUP () { 0b100 } # < markup in data (any) |
|
|
|
|
|
sub PLAINTEXT_CONTENT_MODEL () { 0 } |
|
|
sub CDATA_CONTENT_MODEL () { CM_LIMITED_MARKUP } |
|
|
sub RCDATA_CONTENT_MODEL () { CM_ENTITY | CM_LIMITED_MARKUP } |
|
|
sub PCDATA_CONTENT_MODEL () { CM_ENTITY | CM_FULL_MARKUP } |
|
|
|
|
|
sub DATA_STATE () { 0 } |
|
|
sub ENTITY_DATA_STATE () { 1 } |
|
|
sub TAG_OPEN_STATE () { 2 } |
|
|
sub CLOSE_TAG_OPEN_STATE () { 3 } |
|
|
sub TAG_NAME_STATE () { 4 } |
|
|
sub BEFORE_ATTRIBUTE_NAME_STATE () { 5 } |
|
|
sub ATTRIBUTE_NAME_STATE () { 6 } |
|
|
sub AFTER_ATTRIBUTE_NAME_STATE () { 7 } |
|
|
sub BEFORE_ATTRIBUTE_VALUE_STATE () { 8 } |
|
|
sub ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE () { 9 } |
|
|
sub ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE () { 10 } |
|
|
sub ATTRIBUTE_VALUE_UNQUOTED_STATE () { 11 } |
|
|
sub ENTITY_IN_ATTRIBUTE_VALUE_STATE () { 12 } |
|
|
sub MARKUP_DECLARATION_OPEN_STATE () { 13 } |
|
|
sub COMMENT_START_STATE () { 14 } |
|
|
sub COMMENT_START_DASH_STATE () { 15 } |
|
|
sub COMMENT_STATE () { 16 } |
|
|
sub COMMENT_END_STATE () { 17 } |
|
|
sub COMMENT_END_DASH_STATE () { 18 } |
|
|
sub BOGUS_COMMENT_STATE () { 19 } |
|
|
sub DOCTYPE_STATE () { 20 } |
|
|
sub BEFORE_DOCTYPE_NAME_STATE () { 21 } |
|
|
sub DOCTYPE_NAME_STATE () { 22 } |
|
|
sub AFTER_DOCTYPE_NAME_STATE () { 23 } |
|
|
sub BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE () { 24 } |
|
|
sub DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE () { 25 } |
|
|
sub DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE () { 26 } |
|
|
sub AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE () { 27 } |
|
|
sub BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE () { 28 } |
|
|
sub DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE () { 29 } |
|
|
sub DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE () { 30 } |
|
|
sub AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE () { 31 } |
|
|
sub BOGUS_DOCTYPE_STATE () { 32 } |
|
|
sub AFTER_ATTRIBUTE_VALUE_QUOTED_STATE () { 33 } |
|
|
sub SELF_CLOSING_START_TAG_STATE () { 34 } |
|
|
sub CDATA_BLOCK_STATE () { 35 } |
|
|
|
|
|
sub DOCTYPE_TOKEN () { 1 } |
|
|
sub COMMENT_TOKEN () { 2 } |
|
|
sub START_TAG_TOKEN () { 3 } |
|
|
sub END_TAG_TOKEN () { 4 } |
|
|
sub END_OF_FILE_TOKEN () { 5 } |
|
|
sub CHARACTER_TOKEN () { 6 } |
|
| 813 |
|
|
| 814 |
sub AFTER_HTML_IMS () { 0b100 } |
sub AFTER_HTML_IMS () { 0b100 } |
| 815 |
sub HEAD_IMS () { 0b1000 } |
sub HEAD_IMS () { 0b1000 } |
| 820 |
sub BODY_AFTER_IMS () { 0b100000000 } |
sub BODY_AFTER_IMS () { 0b100000000 } |
| 821 |
sub FRAME_IMS () { 0b1000000000 } |
sub FRAME_IMS () { 0b1000000000 } |
| 822 |
sub SELECT_IMS () { 0b10000000000 } |
sub SELECT_IMS () { 0b10000000000 } |
| 823 |
sub IN_FOREIGN_CONTENT_IM () { 0b100000000000 } |
#sub IN_FOREIGN_CONTENT_IM () { 0b100000000000 } # see Whatpm::HTML::Tokenizer |
| 824 |
## NOTE: "in foreign content" insertion mode is special; it is combined |
## NOTE: "in foreign content" insertion mode is special; it is combined |
| 825 |
## with the secondary insertion mode. In this parser, they are stored |
## with the secondary insertion mode. In this parser, they are stored |
| 826 |
## together in the bit-or'ed form. |
## together in the bit-or'ed form. |
| 827 |
|
sub IN_CDATA_RCDATA_IM () { 0b1000000000000 } |
| 828 |
|
## NOTE: "in CDATA/RCDATA" insertion mode is also special; it is |
| 829 |
|
## combined with the original insertion mode. In thie parser, |
| 830 |
|
## they are stored together in the bit-or'ed form. |
| 831 |
|
|
| 832 |
|
sub IM_MASK () { 0b11111111111 } |
| 833 |
|
|
| 834 |
## NOTE: "initial" and "before html" insertion modes have no constants. |
## NOTE: "initial" and "before html" insertion modes have no constants. |
| 835 |
|
|
| 856 |
sub IN_SELECT_IN_TABLE_IM () { SELECT_IMS | 0b10 } |
sub IN_SELECT_IN_TABLE_IM () { SELECT_IMS | 0b10 } |
| 857 |
sub IN_COLUMN_GROUP_IM () { 0b10 } |
sub IN_COLUMN_GROUP_IM () { 0b10 } |
| 858 |
|
|
|
## Implementations MUST act as if state machine in the spec |
|
|
|
|
|
sub _initialize_tokenizer ($) { |
|
|
my $self = shift; |
|
|
$self->{state} = DATA_STATE; # MUST |
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; # be |
|
|
undef $self->{current_token}; # start tag, end tag, comment, or DOCTYPE |
|
|
undef $self->{current_attribute}; |
|
|
undef $self->{last_emitted_start_tag_name}; |
|
|
undef $self->{last_attribute_value_state}; |
|
|
delete $self->{self_closing}; |
|
|
$self->{char} = []; |
|
|
# $self->{next_char} |
|
|
!!!next-input-character; |
|
|
$self->{token} = []; |
|
|
# $self->{escape} |
|
|
} # _initialize_tokenizer |
|
|
|
|
|
## A token has: |
|
|
## ->{type} == DOCTYPE_TOKEN, START_TAG_TOKEN, END_TAG_TOKEN, COMMENT_TOKEN, |
|
|
## CHARACTER_TOKEN, or END_OF_FILE_TOKEN |
|
|
## ->{name} (DOCTYPE_TOKEN) |
|
|
## ->{tag_name} (START_TAG_TOKEN, END_TAG_TOKEN) |
|
|
## ->{public_identifier} (DOCTYPE_TOKEN) |
|
|
## ->{system_identifier} (DOCTYPE_TOKEN) |
|
|
## ->{quirks} == 1 or 0 (DOCTYPE_TOKEN): "force-quirks" flag |
|
|
## ->{attributes} isa HASH (START_TAG_TOKEN, END_TAG_TOKEN) |
|
|
## ->{name} |
|
|
## ->{value} |
|
|
## ->{has_reference} == 1 or 0 |
|
|
## ->{data} (COMMENT_TOKEN, CHARACTER_TOKEN) |
|
|
## NOTE: The "self-closing flag" is hold as |$self->{self_closing}|. |
|
|
## |->{self_closing}| is used to save the value of |$self->{self_closing}| |
|
|
## while the token is pushed back to the stack. |
|
|
|
|
|
## ISSUE: "When a DOCTYPE token is created, its |
|
|
## <i>self-closing flag</i> must be unset (its other state is that it |
|
|
## be set), and its attributes list must be empty.": Wrong subject? |
|
|
|
|
|
## Emitted token MUST immediately be handled by the tree construction state. |
|
|
|
|
|
## Before each step, UA MAY check to see if either one of the scripts in |
|
|
## "list of scripts that will execute as soon as possible" or the first |
|
|
## script in the "list of scripts that will execute asynchronously", |
|
|
## has completed loading. If one has, then it MUST be executed |
|
|
## and removed from the list. |
|
|
|
|
|
## NOTE: HTML5 "Writing HTML documents" section, applied to |
|
|
## documents and not to user agents and conformance checkers, |
|
|
## 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, |
|
|
|
|
|
sub _get_next_token ($) { |
|
|
my $self = shift; |
|
|
|
|
|
if ($self->{self_closing}) { |
|
|
!!!parse-error (type => 'nestc', token => $self->{current_token}); |
|
|
## NOTE: The |self_closing| flag is only set by start tag token. |
|
|
## In addition, when a start tag token is emitted, it is always set to |
|
|
## |current_token|. |
|
|
delete $self->{self_closing}; |
|
|
} |
|
|
|
|
|
if (@{$self->{token}}) { |
|
|
$self->{self_closing} = $self->{token}->[0]->{self_closing}; |
|
|
return shift @{$self->{token}}; |
|
|
} |
|
|
|
|
|
A: { |
|
|
if ($self->{state} == DATA_STATE) { |
|
|
if ($self->{next_char} == 0x0026) { # & |
|
|
if ($self->{content_model} & CM_ENTITY and # PCDATA | RCDATA |
|
|
not $self->{escape}) { |
|
|
!!!cp (1); |
|
|
$self->{state} = ENTITY_DATA_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (2); |
|
|
# |
|
|
} |
|
|
} elsif ($self->{next_char} == 0x002D) { # - |
|
|
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
|
|
unless ($self->{escape}) { |
|
|
if ($self->{prev_char}->[0] == 0x002D and # - |
|
|
$self->{prev_char}->[1] == 0x0021 and # ! |
|
|
$self->{prev_char}->[2] == 0x003C) { # < |
|
|
!!!cp (3); |
|
|
$self->{escape} = 1; |
|
|
} else { |
|
|
!!!cp (4); |
|
|
} |
|
|
} else { |
|
|
!!!cp (5); |
|
|
} |
|
|
} |
|
|
|
|
|
# |
|
|
} elsif ($self->{next_char} == 0x003C) { # < |
|
|
if ($self->{content_model} & CM_FULL_MARKUP or # PCDATA |
|
|
(($self->{content_model} & CM_LIMITED_MARKUP) and # CDATA | RCDATA |
|
|
not $self->{escape})) { |
|
|
!!!cp (6); |
|
|
$self->{state} = TAG_OPEN_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (7); |
|
|
# |
|
|
} |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
if ($self->{escape} and |
|
|
($self->{content_model} & CM_LIMITED_MARKUP)) { # RCDATA | CDATA |
|
|
if ($self->{prev_char}->[0] == 0x002D and # - |
|
|
$self->{prev_char}->[1] == 0x002D) { # - |
|
|
!!!cp (8); |
|
|
delete $self->{escape}; |
|
|
} else { |
|
|
!!!cp (9); |
|
|
} |
|
|
} else { |
|
|
!!!cp (10); |
|
|
} |
|
|
|
|
|
# |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (11); |
|
|
!!!emit ({type => END_OF_FILE_TOKEN, |
|
|
line => $self->{line}, column => $self->{column}}); |
|
|
last A; ## TODO: ok? |
|
|
} else { |
|
|
!!!cp (12); |
|
|
} |
|
|
# Anything else |
|
|
my $token = {type => CHARACTER_TOKEN, |
|
|
data => chr $self->{next_char}, |
|
|
line => $self->{line}, column => $self->{column}, |
|
|
}; |
|
|
## Stay in the data state |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ($token); |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{state} == ENTITY_DATA_STATE) { |
|
|
## (cannot happen in CDATA state) |
|
|
|
|
|
my ($l, $c) = ($self->{line_prev}, $self->{column_prev}); |
|
|
|
|
|
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 => '&', |
|
|
line => $l, column => $c, |
|
|
}); |
|
|
} else { |
|
|
!!!cp (14); |
|
|
!!!emit ($token); |
|
|
} |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{state} == TAG_OPEN_STATE) { |
|
|
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
|
|
if ($self->{next_char} == 0x002F) { # / |
|
|
!!!cp (15); |
|
|
!!!next-input-character; |
|
|
$self->{state} = CLOSE_TAG_OPEN_STATE; |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (16); |
|
|
## reconsume |
|
|
$self->{state} = DATA_STATE; |
|
|
|
|
|
!!!emit ({type => CHARACTER_TOKEN, data => '<', |
|
|
line => $self->{line_prev}, |
|
|
column => $self->{column_prev}, |
|
|
}); |
|
|
|
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{content_model} & CM_FULL_MARKUP) { # PCDATA |
|
|
if ($self->{next_char} == 0x0021) { # ! |
|
|
!!!cp (17); |
|
|
$self->{state} = MARKUP_DECLARATION_OPEN_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x002F) { # / |
|
|
!!!cp (18); |
|
|
$self->{state} = CLOSE_TAG_OPEN_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif (0x0041 <= $self->{next_char} and |
|
|
$self->{next_char} <= 0x005A) { # A..Z |
|
|
!!!cp (19); |
|
|
$self->{current_token} |
|
|
= {type => START_TAG_TOKEN, |
|
|
tag_name => chr ($self->{next_char} + 0x0020), |
|
|
line => $self->{line_prev}, |
|
|
column => $self->{column_prev}}; |
|
|
$self->{state} = TAG_NAME_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif (0x0061 <= $self->{next_char} and |
|
|
$self->{next_char} <= 0x007A) { # a..z |
|
|
!!!cp (20); |
|
|
$self->{current_token} = {type => START_TAG_TOKEN, |
|
|
tag_name => chr ($self->{next_char}), |
|
|
line => $self->{line_prev}, |
|
|
column => $self->{column_prev}}; |
|
|
$self->{state} = TAG_NAME_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
!!!cp (21); |
|
|
!!!parse-error (type => 'empty start tag', |
|
|
line => $self->{line_prev}, |
|
|
column => $self->{column_prev}); |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ({type => CHARACTER_TOKEN, data => '<>', |
|
|
line => $self->{line_prev}, |
|
|
column => $self->{column_prev}, |
|
|
}); |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003F) { # ? |
|
|
!!!cp (22); |
|
|
!!!parse-error (type => 'pio', |
|
|
line => $self->{line_prev}, |
|
|
column => $self->{column_prev}); |
|
|
$self->{state} = BOGUS_COMMENT_STATE; |
|
|
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
|
|
line => $self->{line_prev}, |
|
|
column => $self->{column_prev}, |
|
|
}; |
|
|
## $self->{next_char} is intentionally left as is |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (23); |
|
|
!!!parse-error (type => 'bare stago'); |
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
!!!emit ({type => CHARACTER_TOKEN, data => '<', |
|
|
line => $self->{line_prev}, |
|
|
column => $self->{column_prev}, |
|
|
}); |
|
|
|
|
|
redo A; |
|
|
} |
|
|
} else { |
|
|
die "$0: $self->{content_model} in tag open"; |
|
|
} |
|
|
} elsif ($self->{state} == CLOSE_TAG_OPEN_STATE) { |
|
|
my ($l, $c) = ($self->{line_prev}, $self->{column_prev} - 1); # "<"of"</" |
|
|
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
|
|
if (defined $self->{last_emitted_start_tag_name}) { |
|
|
|
|
|
## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564> |
|
|
my @next_char; |
|
|
TAGNAME: for (my $i = 0; $i < length $self->{last_emitted_start_tag_name}; $i++) { |
|
|
push @next_char, $self->{next_char}; |
|
|
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 => '</', |
|
|
line => $l, column => $c, |
|
|
}); |
|
|
|
|
|
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 => '</', |
|
|
line => $l, column => $c, |
|
|
}); |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (27); |
|
|
$self->{next_char} = shift @next_char; |
|
|
!!!back-next-input-character (@next_char); |
|
|
# and consume... |
|
|
} |
|
|
} else { |
|
|
## No start tag token has ever been emitted |
|
|
!!!cp (28); |
|
|
# next-input-character is already done |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!emit ({type => CHARACTER_TOKEN, data => '</', |
|
|
line => $l, column => $c, |
|
|
}); |
|
|
redo A; |
|
|
} |
|
|
} |
|
|
|
|
|
if (0x0041 <= $self->{next_char} and |
|
|
$self->{next_char} <= 0x005A) { # A..Z |
|
|
!!!cp (29); |
|
|
$self->{current_token} |
|
|
= {type => END_TAG_TOKEN, |
|
|
tag_name => chr ($self->{next_char} + 0x0020), |
|
|
line => $l, column => $c}; |
|
|
$self->{state} = TAG_NAME_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif (0x0061 <= $self->{next_char} and |
|
|
$self->{next_char} <= 0x007A) { # a..z |
|
|
!!!cp (30); |
|
|
$self->{current_token} = {type => END_TAG_TOKEN, |
|
|
tag_name => chr ($self->{next_char}), |
|
|
line => $l, column => $c}; |
|
|
$self->{state} = TAG_NAME_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
!!!cp (31); |
|
|
!!!parse-error (type => 'empty end tag', |
|
|
line => $self->{line_prev}, ## "<" in "</>" |
|
|
column => $self->{column_prev} - 1); |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (32); |
|
|
!!!parse-error (type => 'bare etago'); |
|
|
$self->{state} = DATA_STATE; |
|
|
# reconsume |
|
|
|
|
|
!!!emit ({type => CHARACTER_TOKEN, data => '</', |
|
|
line => $l, column => $c, |
|
|
}); |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (33); |
|
|
!!!parse-error (type => 'bogus end tag'); |
|
|
$self->{state} = BOGUS_COMMENT_STATE; |
|
|
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
|
|
line => $self->{line_prev}, # "<" of "</" |
|
|
column => $self->{column_prev} - 1, |
|
|
}; |
|
|
## $self->{next_char} is intentionally left as is |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == TAG_NAME_STATE) { |
|
|
if ($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) { # SP |
|
|
!!!cp (34); |
|
|
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
|
|
!!!cp (35); |
|
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
|
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
|
|
#if ($self->{current_token}->{attributes}) { |
|
|
# ## NOTE: This should never be reached. |
|
|
# !!! cp (36); |
|
|
# !!! parse-error (type => 'end tag attribute'); |
|
|
#} else { |
|
|
!!!cp (37); |
|
|
#} |
|
|
} else { |
|
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
|
|
} |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ($self->{current_token}); # start tag or end tag |
|
|
|
|
|
redo A; |
|
|
} elsif (0x0041 <= $self->{next_char} and |
|
|
$self->{next_char} <= 0x005A) { # A..Z |
|
|
!!!cp (38); |
|
|
$self->{current_token}->{tag_name} .= chr ($self->{next_char} + 0x0020); |
|
|
# start tag or end tag |
|
|
## Stay in this state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!parse-error (type => 'unclosed tag'); |
|
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
|
|
!!!cp (39); |
|
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
|
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
|
|
#if ($self->{current_token}->{attributes}) { |
|
|
# ## NOTE: This state should never be reached. |
|
|
# !!! cp (40); |
|
|
# !!! parse-error (type => 'end tag attribute'); |
|
|
#} else { |
|
|
!!!cp (41); |
|
|
#} |
|
|
} else { |
|
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
|
|
} |
|
|
$self->{state} = DATA_STATE; |
|
|
# reconsume |
|
|
|
|
|
!!!emit ($self->{current_token}); # start tag or end tag |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x002F) { # / |
|
|
!!!cp (42); |
|
|
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (44); |
|
|
$self->{current_token}->{tag_name} .= chr $self->{next_char}; |
|
|
# start tag or end tag |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == BEFORE_ATTRIBUTE_NAME_STATE) { |
|
|
if ($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) { # SP |
|
|
!!!cp (45); |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
|
|
!!!cp (46); |
|
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
|
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
|
|
if ($self->{current_token}->{attributes}) { |
|
|
!!!cp (47); |
|
|
!!!parse-error (type => 'end tag attribute'); |
|
|
} else { |
|
|
!!!cp (48); |
|
|
} |
|
|
} else { |
|
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
|
|
} |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ($self->{current_token}); # start tag or end tag |
|
|
|
|
|
redo A; |
|
|
} elsif (0x0041 <= $self->{next_char} and |
|
|
$self->{next_char} <= 0x005A) { # A..Z |
|
|
!!!cp (49); |
|
|
$self->{current_attribute} |
|
|
= {name => chr ($self->{next_char} + 0x0020), |
|
|
value => '', |
|
|
line => $self->{line}, column => $self->{column}}; |
|
|
$self->{state} = ATTRIBUTE_NAME_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x002F) { # / |
|
|
!!!cp (50); |
|
|
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!parse-error (type => 'unclosed tag'); |
|
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
|
|
!!!cp (52); |
|
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
|
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
|
|
if ($self->{current_token}->{attributes}) { |
|
|
!!!cp (53); |
|
|
!!!parse-error (type => 'end tag attribute'); |
|
|
} else { |
|
|
!!!cp (54); |
|
|
} |
|
|
} else { |
|
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
|
|
} |
|
|
$self->{state} = DATA_STATE; |
|
|
# reconsume |
|
|
|
|
|
!!!emit ($self->{current_token}); # start tag or end tag |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
if ({ |
|
|
0x0022 => 1, # " |
|
|
0x0027 => 1, # ' |
|
|
0x003D => 1, # = |
|
|
}->{$self->{next_char}}) { |
|
|
!!!cp (55); |
|
|
!!!parse-error (type => 'bad attribute name'); |
|
|
} else { |
|
|
!!!cp (56); |
|
|
} |
|
|
$self->{current_attribute} |
|
|
= {name => chr ($self->{next_char}), |
|
|
value => '', |
|
|
line => $self->{line}, column => $self->{column}}; |
|
|
$self->{state} = ATTRIBUTE_NAME_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == ATTRIBUTE_NAME_STATE) { |
|
|
my $before_leave = sub { |
|
|
if (exists $self->{current_token}->{attributes} # start tag or end tag |
|
|
->{$self->{current_attribute}->{name}}) { # MUST |
|
|
!!!cp (57); |
|
|
!!!parse-error (type => 'duplicate attribute:'.$self->{current_attribute}->{name}, line => $self->{current_attribute}->{line}, column => $self->{current_attribute}->{column}); |
|
|
## Discard $self->{current_attribute} # MUST |
|
|
} else { |
|
|
!!!cp (58); |
|
|
$self->{current_token}->{attributes}->{$self->{current_attribute}->{name}} |
|
|
= $self->{current_attribute}; |
|
|
} |
|
|
}; # $before_leave |
|
|
|
|
|
if ($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) { # SP |
|
|
!!!cp (59); |
|
|
$before_leave->(); |
|
|
$self->{state} = AFTER_ATTRIBUTE_NAME_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003D) { # = |
|
|
!!!cp (60); |
|
|
$before_leave->(); |
|
|
$self->{state} = BEFORE_ATTRIBUTE_VALUE_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
$before_leave->(); |
|
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
|
|
!!!cp (61); |
|
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
|
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
|
|
!!!cp (62); |
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
|
|
if ($self->{current_token}->{attributes}) { |
|
|
!!!parse-error (type => 'end tag attribute'); |
|
|
} |
|
|
} else { |
|
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
|
|
} |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ($self->{current_token}); # start tag or end tag |
|
|
|
|
|
redo A; |
|
|
} elsif (0x0041 <= $self->{next_char} and |
|
|
$self->{next_char} <= 0x005A) { # A..Z |
|
|
!!!cp (63); |
|
|
$self->{current_attribute}->{name} .= chr ($self->{next_char} + 0x0020); |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x002F) { # / |
|
|
!!!cp (64); |
|
|
$before_leave->(); |
|
|
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!parse-error (type => 'unclosed tag'); |
|
|
$before_leave->(); |
|
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
|
|
!!!cp (66); |
|
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
|
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
|
|
if ($self->{current_token}->{attributes}) { |
|
|
!!!cp (67); |
|
|
!!!parse-error (type => 'end tag attribute'); |
|
|
} else { |
|
|
## NOTE: This state should never be reached. |
|
|
!!!cp (68); |
|
|
} |
|
|
} else { |
|
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
|
|
} |
|
|
$self->{state} = DATA_STATE; |
|
|
# reconsume |
|
|
|
|
|
!!!emit ($self->{current_token}); # start tag or end tag |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
if ($self->{next_char} == 0x0022 or # " |
|
|
$self->{next_char} == 0x0027) { # ' |
|
|
!!!cp (69); |
|
|
!!!parse-error (type => 'bad attribute name'); |
|
|
} else { |
|
|
!!!cp (70); |
|
|
} |
|
|
$self->{current_attribute}->{name} .= chr ($self->{next_char}); |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == AFTER_ATTRIBUTE_NAME_STATE) { |
|
|
if ($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) { # SP |
|
|
!!!cp (71); |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003D) { # = |
|
|
!!!cp (72); |
|
|
$self->{state} = BEFORE_ATTRIBUTE_VALUE_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
|
|
!!!cp (73); |
|
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
|
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
|
|
if ($self->{current_token}->{attributes}) { |
|
|
!!!cp (74); |
|
|
!!!parse-error (type => 'end tag attribute'); |
|
|
} else { |
|
|
## NOTE: This state should never be reached. |
|
|
!!!cp (75); |
|
|
} |
|
|
} else { |
|
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
|
|
} |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ($self->{current_token}); # start tag or end tag |
|
|
|
|
|
redo A; |
|
|
} elsif (0x0041 <= $self->{next_char} and |
|
|
$self->{next_char} <= 0x005A) { # A..Z |
|
|
!!!cp (76); |
|
|
$self->{current_attribute} |
|
|
= {name => chr ($self->{next_char} + 0x0020), |
|
|
value => '', |
|
|
line => $self->{line}, column => $self->{column}}; |
|
|
$self->{state} = ATTRIBUTE_NAME_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x002F) { # / |
|
|
!!!cp (77); |
|
|
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!parse-error (type => 'unclosed tag'); |
|
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
|
|
!!!cp (79); |
|
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
|
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
|
|
if ($self->{current_token}->{attributes}) { |
|
|
!!!cp (80); |
|
|
!!!parse-error (type => 'end tag attribute'); |
|
|
} else { |
|
|
## NOTE: This state should never be reached. |
|
|
!!!cp (81); |
|
|
} |
|
|
} else { |
|
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
|
|
} |
|
|
$self->{state} = DATA_STATE; |
|
|
# reconsume |
|
|
|
|
|
!!!emit ($self->{current_token}); # start tag or end tag |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (82); |
|
|
$self->{current_attribute} |
|
|
= {name => chr ($self->{next_char}), |
|
|
value => '', |
|
|
line => $self->{line}, column => $self->{column}}; |
|
|
$self->{state} = ATTRIBUTE_NAME_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == BEFORE_ATTRIBUTE_VALUE_STATE) { |
|
|
if ($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) { # SP |
|
|
!!!cp (83); |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x0022) { # " |
|
|
!!!cp (84); |
|
|
$self->{state} = ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x0026) { # & |
|
|
!!!cp (85); |
|
|
$self->{state} = ATTRIBUTE_VALUE_UNQUOTED_STATE; |
|
|
## reconsume |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x0027) { # ' |
|
|
!!!cp (86); |
|
|
$self->{state} = ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
|
|
!!!cp (87); |
|
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
|
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
|
|
if ($self->{current_token}->{attributes}) { |
|
|
!!!cp (88); |
|
|
!!!parse-error (type => 'end tag attribute'); |
|
|
} else { |
|
|
## NOTE: This state should never be reached. |
|
|
!!!cp (89); |
|
|
} |
|
|
} else { |
|
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
|
|
} |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ($self->{current_token}); # start tag or end tag |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!parse-error (type => 'unclosed tag'); |
|
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
|
|
!!!cp (90); |
|
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
|
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
|
|
if ($self->{current_token}->{attributes}) { |
|
|
!!!cp (91); |
|
|
!!!parse-error (type => 'end tag attribute'); |
|
|
} else { |
|
|
## NOTE: This state should never be reached. |
|
|
!!!cp (92); |
|
|
} |
|
|
} else { |
|
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
|
|
} |
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
!!!emit ($self->{current_token}); # start tag or end tag |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
if ($self->{next_char} == 0x003D) { # = |
|
|
!!!cp (93); |
|
|
!!!parse-error (type => 'bad attribute value'); |
|
|
} else { |
|
|
!!!cp (94); |
|
|
} |
|
|
$self->{current_attribute}->{value} .= chr ($self->{next_char}); |
|
|
$self->{state} = ATTRIBUTE_VALUE_UNQUOTED_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == ATTRIBUTE_VALUE_DOUBLE_QUOTED_STATE) { |
|
|
if ($self->{next_char} == 0x0022) { # " |
|
|
!!!cp (95); |
|
|
$self->{state} = AFTER_ATTRIBUTE_VALUE_QUOTED_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x0026) { # & |
|
|
!!!cp (96); |
|
|
$self->{last_attribute_value_state} = $self->{state}; |
|
|
$self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!parse-error (type => 'unclosed attribute value'); |
|
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
|
|
!!!cp (97); |
|
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
|
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
|
|
if ($self->{current_token}->{attributes}) { |
|
|
!!!cp (98); |
|
|
!!!parse-error (type => 'end tag attribute'); |
|
|
} else { |
|
|
## NOTE: This state should never be reached. |
|
|
!!!cp (99); |
|
|
} |
|
|
} else { |
|
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
|
|
} |
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
!!!emit ($self->{current_token}); # start tag or end tag |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (100); |
|
|
$self->{current_attribute}->{value} .= chr ($self->{next_char}); |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == ATTRIBUTE_VALUE_SINGLE_QUOTED_STATE) { |
|
|
if ($self->{next_char} == 0x0027) { # ' |
|
|
!!!cp (101); |
|
|
$self->{state} = AFTER_ATTRIBUTE_VALUE_QUOTED_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x0026) { # & |
|
|
!!!cp (102); |
|
|
$self->{last_attribute_value_state} = $self->{state}; |
|
|
$self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!parse-error (type => 'unclosed attribute value'); |
|
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
|
|
!!!cp (103); |
|
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
|
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
|
|
if ($self->{current_token}->{attributes}) { |
|
|
!!!cp (104); |
|
|
!!!parse-error (type => 'end tag attribute'); |
|
|
} else { |
|
|
## NOTE: This state should never be reached. |
|
|
!!!cp (105); |
|
|
} |
|
|
} else { |
|
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
|
|
} |
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
!!!emit ($self->{current_token}); # start tag or end tag |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (106); |
|
|
$self->{current_attribute}->{value} .= chr ($self->{next_char}); |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == ATTRIBUTE_VALUE_UNQUOTED_STATE) { |
|
|
if ($self->{next_char} == 0x0009 or # HT |
|
|
$self->{next_char} == 0x000A or # LF |
|
|
$self->{next_char} == 0x000B or # HT |
|
|
$self->{next_char} == 0x000C or # FF |
|
|
$self->{next_char} == 0x0020) { # SP |
|
|
!!!cp (107); |
|
|
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x0026) { # & |
|
|
!!!cp (108); |
|
|
$self->{last_attribute_value_state} = $self->{state}; |
|
|
$self->{state} = ENTITY_IN_ATTRIBUTE_VALUE_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
|
|
!!!cp (109); |
|
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
|
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
|
|
if ($self->{current_token}->{attributes}) { |
|
|
!!!cp (110); |
|
|
!!!parse-error (type => 'end tag attribute'); |
|
|
} else { |
|
|
## NOTE: This state should never be reached. |
|
|
!!!cp (111); |
|
|
} |
|
|
} else { |
|
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
|
|
} |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ($self->{current_token}); # start tag or end tag |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!parse-error (type => 'unclosed tag'); |
|
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
|
|
!!!cp (112); |
|
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
|
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
|
|
if ($self->{current_token}->{attributes}) { |
|
|
!!!cp (113); |
|
|
!!!parse-error (type => 'end tag attribute'); |
|
|
} else { |
|
|
## NOTE: This state should never be reached. |
|
|
!!!cp (114); |
|
|
} |
|
|
} else { |
|
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
|
|
} |
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
!!!emit ($self->{current_token}); # start tag or end tag |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
if ({ |
|
|
0x0022 => 1, # " |
|
|
0x0027 => 1, # ' |
|
|
0x003D => 1, # = |
|
|
}->{$self->{next_char}}) { |
|
|
!!!cp (115); |
|
|
!!!parse-error (type => 'bad attribute value'); |
|
|
} else { |
|
|
!!!cp (116); |
|
|
} |
|
|
$self->{current_attribute}->{value} .= chr ($self->{next_char}); |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} 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; |
|
|
} elsif ($self->{state} == AFTER_ATTRIBUTE_VALUE_QUOTED_STATE) { |
|
|
if ($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) { # SP |
|
|
!!!cp (118); |
|
|
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
if ($self->{current_token}->{type} == START_TAG_TOKEN) { |
|
|
!!!cp (119); |
|
|
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
|
|
} elsif ($self->{current_token}->{type} == END_TAG_TOKEN) { |
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
|
|
if ($self->{current_token}->{attributes}) { |
|
|
!!!cp (120); |
|
|
!!!parse-error (type => 'end tag attribute'); |
|
|
} else { |
|
|
## NOTE: This state should never be reached. |
|
|
!!!cp (121); |
|
|
} |
|
|
} else { |
|
|
die "$0: $self->{current_token}->{type}: Unknown token type"; |
|
|
} |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ($self->{current_token}); # start tag or end tag |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x002F) { # / |
|
|
!!!cp (122); |
|
|
$self->{state} = SELF_CLOSING_START_TAG_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp ('124.1'); |
|
|
!!!parse-error (type => 'no space between attributes'); |
|
|
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
|
|
## reconsume |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == SELF_CLOSING_START_TAG_STATE) { |
|
|
if ($self->{next_char} == 0x003E) { # > |
|
|
if ($self->{current_token}->{type} == END_TAG_TOKEN) { |
|
|
!!!cp ('124.2'); |
|
|
!!!parse-error (type => 'nestc', token => $self->{current_token}); |
|
|
## TODO: Different type than slash in start tag |
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
|
|
if ($self->{current_token}->{attributes}) { |
|
|
!!!cp ('124.4'); |
|
|
!!!parse-error (type => 'end tag attribute'); |
|
|
} else { |
|
|
!!!cp ('124.5'); |
|
|
} |
|
|
## TODO: Test |<title></title/>| |
|
|
} else { |
|
|
!!!cp ('124.3'); |
|
|
$self->{self_closing} = 1; |
|
|
} |
|
|
|
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ($self->{current_token}); # start tag or end tag |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp ('124.4'); |
|
|
!!!parse-error (type => 'nestc'); |
|
|
## TODO: This error type is wrong. |
|
|
$self->{state} = BEFORE_ATTRIBUTE_NAME_STATE; |
|
|
## Reconsume. |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == BOGUS_COMMENT_STATE) { |
|
|
## (only happen if PCDATA state) |
|
|
|
|
|
## NOTE: Set by the previous state |
|
|
#my $token = {type => COMMENT_TOKEN, data => ''}; |
|
|
|
|
|
BC: { |
|
|
if ($self->{next_char} == 0x003E) { # > |
|
|
!!!cp (124); |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ($self->{current_token}); # comment |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (125); |
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
!!!emit ($self->{current_token}); # comment |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (126); |
|
|
$self->{current_token}->{data} .= chr ($self->{next_char}); # comment |
|
|
!!!next-input-character; |
|
|
redo BC; |
|
|
} |
|
|
} # BC |
|
|
|
|
|
die "$0: _get_next_token: unexpected case [BC]"; |
|
|
} elsif ($self->{state} == MARKUP_DECLARATION_OPEN_STATE) { |
|
|
## (only happen if PCDATA state) |
|
|
|
|
|
my ($l, $c) = ($self->{line_prev}, $self->{column_prev} - 1); |
|
|
|
|
|
my @next_char; |
|
|
push @next_char, $self->{next_char}; |
|
|
|
|
|
if ($self->{next_char} == 0x002D) { # - |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x002D) { # - |
|
|
!!!cp (127); |
|
|
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
|
|
line => $l, column => $c, |
|
|
}; |
|
|
$self->{state} = COMMENT_START_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (128); |
|
|
} |
|
|
} elsif ($self->{next_char} == 0x0044 or # D |
|
|
$self->{next_char} == 0x0064) { # d |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x004F or # O |
|
|
$self->{next_char} == 0x006F) { # o |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x0043 or # C |
|
|
$self->{next_char} == 0x0063) { # c |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
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; |
|
|
$self->{current_token} = {type => DOCTYPE_TOKEN, |
|
|
quirks => 1, |
|
|
line => $l, column => $c, |
|
|
}; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (130); |
|
|
} |
|
|
} else { |
|
|
!!!cp (131); |
|
|
} |
|
|
} else { |
|
|
!!!cp (132); |
|
|
} |
|
|
} else { |
|
|
!!!cp (133); |
|
|
} |
|
|
} else { |
|
|
!!!cp (134); |
|
|
} |
|
|
} else { |
|
|
!!!cp (135); |
|
|
} |
|
|
} elsif ($self->{insertion_mode} & IN_FOREIGN_CONTENT_IM and |
|
|
$self->{open_elements}->[-1]->[1] & FOREIGN_EL and |
|
|
$self->{next_char} == 0x005B) { # [ |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x0043) { # C |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x0044) { # D |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x0041) { # A |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x0054) { # T |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x0041) { # A |
|
|
!!!next-input-character; |
|
|
push @next_char, $self->{next_char}; |
|
|
if ($self->{next_char} == 0x005B) { # [ |
|
|
!!!cp (135.1); |
|
|
$self->{state} = CDATA_BLOCK_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (135.2); |
|
|
} |
|
|
} else { |
|
|
!!!cp (135.3); |
|
|
} |
|
|
} else { |
|
|
!!!cp (135.4); |
|
|
} |
|
|
} else { |
|
|
!!!cp (135.5); |
|
|
} |
|
|
} else { |
|
|
!!!cp (135.6); |
|
|
} |
|
|
} else { |
|
|
!!!cp (135.7); |
|
|
} |
|
|
} else { |
|
|
!!!cp (136); |
|
|
} |
|
|
|
|
|
!!!parse-error (type => 'bogus comment'); |
|
|
$self->{next_char} = shift @next_char; |
|
|
!!!back-next-input-character (@next_char); |
|
|
$self->{state} = BOGUS_COMMENT_STATE; |
|
|
$self->{current_token} = {type => COMMENT_TOKEN, data => '', |
|
|
line => $l, column => $c, |
|
|
}; |
|
|
redo A; |
|
|
|
|
|
## ISSUE: typos in spec: chacacters, is is a parse error |
|
|
## 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? |
|
|
} elsif ($self->{state} == COMMENT_START_STATE) { |
|
|
if ($self->{next_char} == 0x002D) { # - |
|
|
!!!cp (137); |
|
|
$self->{state} = COMMENT_START_DASH_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
!!!cp (138); |
|
|
!!!parse-error (type => 'bogus comment'); |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ($self->{current_token}); # comment |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (139); |
|
|
!!!parse-error (type => 'unclosed comment'); |
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
!!!emit ($self->{current_token}); # comment |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (140); |
|
|
$self->{current_token}->{data} # comment |
|
|
.= chr ($self->{next_char}); |
|
|
$self->{state} = COMMENT_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == COMMENT_START_DASH_STATE) { |
|
|
if ($self->{next_char} == 0x002D) { # - |
|
|
!!!cp (141); |
|
|
$self->{state} = COMMENT_END_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
!!!cp (142); |
|
|
!!!parse-error (type => 'bogus comment'); |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ($self->{current_token}); # comment |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (143); |
|
|
!!!parse-error (type => 'unclosed comment'); |
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
!!!emit ($self->{current_token}); # comment |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (144); |
|
|
$self->{current_token}->{data} # comment |
|
|
.= '-' . chr ($self->{next_char}); |
|
|
$self->{state} = COMMENT_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == COMMENT_STATE) { |
|
|
if ($self->{next_char} == 0x002D) { # - |
|
|
!!!cp (145); |
|
|
$self->{state} = COMMENT_END_DASH_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (146); |
|
|
!!!parse-error (type => 'unclosed comment'); |
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
!!!emit ($self->{current_token}); # comment |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (147); |
|
|
$self->{current_token}->{data} .= chr ($self->{next_char}); # comment |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == COMMENT_END_DASH_STATE) { |
|
|
if ($self->{next_char} == 0x002D) { # - |
|
|
!!!cp (148); |
|
|
$self->{state} = COMMENT_END_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (149); |
|
|
!!!parse-error (type => 'unclosed comment'); |
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
!!!emit ($self->{current_token}); # comment |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (150); |
|
|
$self->{current_token}->{data} .= '-' . chr ($self->{next_char}); # comment |
|
|
$self->{state} = COMMENT_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == COMMENT_END_STATE) { |
|
|
if ($self->{next_char} == 0x003E) { # > |
|
|
!!!cp (151); |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ($self->{current_token}); # comment |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x002D) { # - |
|
|
!!!cp (152); |
|
|
!!!parse-error (type => 'dash in comment', |
|
|
line => $self->{line_prev}, |
|
|
column => $self->{column_prev}); |
|
|
$self->{current_token}->{data} .= '-'; # comment |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (153); |
|
|
!!!parse-error (type => 'unclosed comment'); |
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
!!!emit ($self->{current_token}); # comment |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (154); |
|
|
!!!parse-error (type => 'dash in comment', |
|
|
line => $self->{line_prev}, |
|
|
column => $self->{column_prev}); |
|
|
$self->{current_token}->{data} .= '--' . chr ($self->{next_char}); # comment |
|
|
$self->{state} = COMMENT_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == DOCTYPE_STATE) { |
|
|
if ($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) { # SP |
|
|
!!!cp (155); |
|
|
$self->{state} = BEFORE_DOCTYPE_NAME_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (156); |
|
|
!!!parse-error (type => 'no space before DOCTYPE name'); |
|
|
$self->{state} = BEFORE_DOCTYPE_NAME_STATE; |
|
|
## reconsume |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == BEFORE_DOCTYPE_NAME_STATE) { |
|
|
if ($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) { # SP |
|
|
!!!cp (157); |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
!!!cp (158); |
|
|
!!!parse-error (type => 'no DOCTYPE name'); |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ($self->{current_token}); # DOCTYPE (quirks) |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (159); |
|
|
!!!parse-error (type => 'no DOCTYPE name'); |
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
!!!emit ($self->{current_token}); # DOCTYPE (quirks) |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (160); |
|
|
$self->{current_token}->{name} = chr $self->{next_char}; |
|
|
delete $self->{current_token}->{quirks}; |
|
|
## ISSUE: "Set the token's name name to the" in the spec |
|
|
$self->{state} = DOCTYPE_NAME_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == DOCTYPE_NAME_STATE) { |
|
|
## ISSUE: Redundant "First," in the spec. |
|
|
if ($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) { # SP |
|
|
!!!cp (161); |
|
|
$self->{state} = AFTER_DOCTYPE_NAME_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
!!!cp (162); |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (163); |
|
|
!!!parse-error (type => 'unclosed DOCTYPE'); |
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
$self->{current_token}->{quirks} = 1; |
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (164); |
|
|
$self->{current_token}->{name} |
|
|
.= chr ($self->{next_char}); # DOCTYPE |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == AFTER_DOCTYPE_NAME_STATE) { |
|
|
if ($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) { # SP |
|
|
!!!cp (165); |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
!!!cp (166); |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (167); |
|
|
!!!parse-error (type => 'unclosed DOCTYPE'); |
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
$self->{current_token}->{quirks} = 1; |
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x0050 or # P |
|
|
$self->{next_char} == 0x0070) { # p |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x0055 or # U |
|
|
$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); |
|
|
} |
|
|
|
|
|
# |
|
|
} elsif ($self->{next_char} == 0x0053 or # S |
|
|
$self->{next_char} == 0x0073) { # s |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x0059 or # Y |
|
|
$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); |
|
|
} |
|
|
|
|
|
# |
|
|
} else { |
|
|
!!!cp (180); |
|
|
!!!next-input-character; |
|
|
# |
|
|
} |
|
|
|
|
|
!!!parse-error (type => 'string after DOCTYPE name'); |
|
|
$self->{current_token}->{quirks} = 1; |
|
|
|
|
|
$self->{state} = BOGUS_DOCTYPE_STATE; |
|
|
# next-input-character is already done |
|
|
redo A; |
|
|
} elsif ($self->{state} == BEFORE_DOCTYPE_PUBLIC_IDENTIFIER_STATE) { |
|
|
if ({ |
|
|
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
|
|
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
|
|
}->{$self->{next_char}}) { |
|
|
!!!cp (181); |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} eq 0x0022) { # " |
|
|
!!!cp (182); |
|
|
$self->{current_token}->{public_identifier} = ''; # DOCTYPE |
|
|
$self->{state} = DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} eq 0x0027) { # ' |
|
|
!!!cp (183); |
|
|
$self->{current_token}->{public_identifier} = ''; # DOCTYPE |
|
|
$self->{state} = DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} eq 0x003E) { # > |
|
|
!!!cp (184); |
|
|
!!!parse-error (type => 'no PUBLIC literal'); |
|
|
|
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
$self->{current_token}->{quirks} = 1; |
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (185); |
|
|
!!!parse-error (type => 'unclosed DOCTYPE'); |
|
|
|
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
$self->{current_token}->{quirks} = 1; |
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (186); |
|
|
!!!parse-error (type => 'string after PUBLIC'); |
|
|
$self->{current_token}->{quirks} = 1; |
|
|
|
|
|
$self->{state} = BOGUS_DOCTYPE_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE) { |
|
|
if ($self->{next_char} == 0x0022) { # " |
|
|
!!!cp (187); |
|
|
$self->{state} = AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
!!!cp (188); |
|
|
!!!parse-error (type => 'unclosed PUBLIC literal'); |
|
|
|
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
$self->{current_token}->{quirks} = 1; |
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (189); |
|
|
!!!parse-error (type => 'unclosed PUBLIC literal'); |
|
|
|
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
$self->{current_token}->{quirks} = 1; |
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (190); |
|
|
$self->{current_token}->{public_identifier} # DOCTYPE |
|
|
.= chr $self->{next_char}; |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE) { |
|
|
if ($self->{next_char} == 0x0027) { # ' |
|
|
!!!cp (191); |
|
|
$self->{state} = AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
!!!cp (192); |
|
|
!!!parse-error (type => 'unclosed PUBLIC literal'); |
|
|
|
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
$self->{current_token}->{quirks} = 1; |
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (193); |
|
|
!!!parse-error (type => 'unclosed PUBLIC literal'); |
|
|
|
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
$self->{current_token}->{quirks} = 1; |
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (194); |
|
|
$self->{current_token}->{public_identifier} # DOCTYPE |
|
|
.= chr $self->{next_char}; |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == AFTER_DOCTYPE_PUBLIC_IDENTIFIER_STATE) { |
|
|
if ({ |
|
|
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
|
|
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
|
|
}->{$self->{next_char}}) { |
|
|
!!!cp (195); |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x0022) { # " |
|
|
!!!cp (196); |
|
|
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
|
|
$self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x0027) { # ' |
|
|
!!!cp (197); |
|
|
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
|
|
$self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
!!!cp (198); |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (199); |
|
|
!!!parse-error (type => 'unclosed DOCTYPE'); |
|
|
|
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
$self->{current_token}->{quirks} = 1; |
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (200); |
|
|
!!!parse-error (type => 'string after PUBLIC literal'); |
|
|
$self->{current_token}->{quirks} = 1; |
|
|
|
|
|
$self->{state} = BOGUS_DOCTYPE_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == BEFORE_DOCTYPE_SYSTEM_IDENTIFIER_STATE) { |
|
|
if ({ |
|
|
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
|
|
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
|
|
}->{$self->{next_char}}) { |
|
|
!!!cp (201); |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x0022) { # " |
|
|
!!!cp (202); |
|
|
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
|
|
$self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x0027) { # ' |
|
|
!!!cp (203); |
|
|
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
|
|
$self->{state} = DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
!!!cp (204); |
|
|
!!!parse-error (type => 'no SYSTEM literal'); |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
$self->{current_token}->{quirks} = 1; |
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (205); |
|
|
!!!parse-error (type => 'unclosed DOCTYPE'); |
|
|
|
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
$self->{current_token}->{quirks} = 1; |
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (206); |
|
|
!!!parse-error (type => 'string after SYSTEM'); |
|
|
$self->{current_token}->{quirks} = 1; |
|
|
|
|
|
$self->{state} = BOGUS_DOCTYPE_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE) { |
|
|
if ($self->{next_char} == 0x0022) { # " |
|
|
!!!cp (207); |
|
|
$self->{state} = AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
!!!cp (208); |
|
|
!!!parse-error (type => 'unclosed PUBLIC literal'); |
|
|
|
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
$self->{current_token}->{quirks} = 1; |
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (209); |
|
|
!!!parse-error (type => 'unclosed SYSTEM literal'); |
|
|
|
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
$self->{current_token}->{quirks} = 1; |
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (210); |
|
|
$self->{current_token}->{system_identifier} # DOCTYPE |
|
|
.= chr $self->{next_char}; |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE) { |
|
|
if ($self->{next_char} == 0x0027) { # ' |
|
|
!!!cp (211); |
|
|
$self->{state} = AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
!!!cp (212); |
|
|
!!!parse-error (type => 'unclosed PUBLIC literal'); |
|
|
|
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
$self->{current_token}->{quirks} = 1; |
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (213); |
|
|
!!!parse-error (type => 'unclosed SYSTEM literal'); |
|
|
|
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
$self->{current_token}->{quirks} = 1; |
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (214); |
|
|
$self->{current_token}->{system_identifier} # DOCTYPE |
|
|
.= chr $self->{next_char}; |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == AFTER_DOCTYPE_SYSTEM_IDENTIFIER_STATE) { |
|
|
if ({ |
|
|
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
|
|
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
|
|
}->{$self->{next_char}}) { |
|
|
!!!cp (215); |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} elsif ($self->{next_char} == 0x003E) { # > |
|
|
!!!cp (216); |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (217); |
|
|
!!!parse-error (type => 'unclosed DOCTYPE'); |
|
|
|
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
$self->{current_token}->{quirks} = 1; |
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (218); |
|
|
!!!parse-error (type => 'string after SYSTEM literal'); |
|
|
#$self->{current_token}->{quirks} = 1; |
|
|
|
|
|
$self->{state} = BOGUS_DOCTYPE_STATE; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == BOGUS_DOCTYPE_STATE) { |
|
|
if ($self->{next_char} == 0x003E) { # > |
|
|
!!!cp (219); |
|
|
$self->{state} = DATA_STATE; |
|
|
!!!next-input-character; |
|
|
|
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} elsif ($self->{next_char} == -1) { |
|
|
!!!cp (220); |
|
|
!!!parse-error (type => 'unclosed DOCTYPE'); |
|
|
$self->{state} = DATA_STATE; |
|
|
## reconsume |
|
|
|
|
|
!!!emit ($self->{current_token}); # DOCTYPE |
|
|
|
|
|
redo A; |
|
|
} else { |
|
|
!!!cp (221); |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
|
} |
|
|
} elsif ($self->{state} == CDATA_BLOCK_STATE) { |
|
|
my $s = ''; |
|
|
|
|
|
my ($l, $c) = ($self->{line}, $self->{column}); |
|
|
|
|
|
CS: while ($self->{next_char} != -1) { |
|
|
if ($self->{next_char} == 0x005D) { # ] |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x005D) { # ] |
|
|
!!!next-input-character; |
|
|
MDC: { |
|
|
if ($self->{next_char} == 0x003E) { # > |
|
|
!!!cp (221.1); |
|
|
!!!next-input-character; |
|
|
last CS; |
|
|
} elsif ($self->{next_char} == 0x005D) { # ] |
|
|
!!!cp (221.2); |
|
|
$s .= ']'; |
|
|
!!!next-input-character; |
|
|
redo MDC; |
|
|
} else { |
|
|
!!!cp (221.3); |
|
|
$s .= ']]'; |
|
|
# |
|
|
} |
|
|
} # MDC |
|
|
} else { |
|
|
!!!cp (221.4); |
|
|
$s .= ']'; |
|
|
# |
|
|
} |
|
|
} else { |
|
|
!!!cp (221.5); |
|
|
# |
|
|
} |
|
|
$s .= chr $self->{next_char}; |
|
|
!!!next-input-character; |
|
|
} # CS |
|
|
|
|
|
$self->{state} = DATA_STATE; |
|
|
## next-input-character done or EOF, which is reconsumed. |
|
|
|
|
|
if (length $s) { |
|
|
!!!cp (221.6); |
|
|
!!!emit ({type => CHARACTER_TOKEN, data => $s, |
|
|
line => $l, column => $c}); |
|
|
} else { |
|
|
!!!cp (221.7); |
|
|
} |
|
|
|
|
|
redo A; |
|
|
|
|
|
## ISSUE: "text tokens" in spec. |
|
|
## TODO: Streaming support |
|
|
} else { |
|
|
die "$0: $self->{state}: Unknown state"; |
|
|
} |
|
|
} # A |
|
|
|
|
|
die "$0: _get_next_token: unexpected case"; |
|
|
} # _get_next_token |
|
|
|
|
|
sub _tokenize_attempt_to_consume_an_entity ($$$) { |
|
|
my ($self, $in_attr, $additional) = @_; |
|
|
|
|
|
my ($l, $c) = ($self->{line_prev}, $self->{column_prev}); |
|
|
|
|
|
if ({ |
|
|
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, # HT, LF, VT, FF, |
|
|
0x0020 => 1, 0x003C => 1, 0x0026 => 1, -1 => 1, # SP, <, & # 0x000D # CR |
|
|
$additional => 1, |
|
|
}->{$self->{next_char}}) { |
|
|
!!!cp (1001); |
|
|
## Don't consume |
|
|
## No error |
|
|
return undef; |
|
|
} elsif ($self->{next_char} == 0x0023) { # # |
|
|
!!!next-input-character; |
|
|
if ($self->{next_char} == 0x0078 or # x |
|
|
$self->{next_char} == 0x0058) { # X |
|
|
my $code; |
|
|
X: { |
|
|
my $x_char = $self->{next_char}; |
|
|
!!!next-input-character; |
|
|
if (0x0030 <= $self->{next_char} and |
|
|
$self->{next_char} <= 0x0039) { # 0..9 |
|
|
!!!cp (1002); |
|
|
$code ||= 0; |
|
|
$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', line => $l, column => $c); |
|
|
!!!back-next-input-character ($x_char, $self->{next_char}); |
|
|
$self->{next_char} = 0x0023; # # |
|
|
return undef; |
|
|
} elsif ($self->{next_char} == 0x003B) { # ; |
|
|
!!!cp (1006); |
|
|
!!!next-input-character; |
|
|
} else { |
|
|
!!!cp (1007); |
|
|
!!!parse-error (type => 'no refc', line => $l, column => $c); |
|
|
} |
|
|
|
|
|
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
|
|
!!!cp (1008); |
|
|
!!!parse-error (type => (sprintf 'invalid character reference:U+%04X', $code), line => $l, column => $c); |
|
|
$code = 0xFFFD; |
|
|
} elsif ($code > 0x10FFFF) { |
|
|
!!!cp (1009); |
|
|
!!!parse-error (type => (sprintf 'invalid character reference:U-%08X', $code), line => $l, column => $c); |
|
|
$code = 0xFFFD; |
|
|
} elsif ($code == 0x000D) { |
|
|
!!!cp (1010); |
|
|
!!!parse-error (type => 'CR character reference', line => $l, column => $c); |
|
|
$code = 0x000A; |
|
|
} elsif (0x80 <= $code and $code <= 0x9F) { |
|
|
!!!cp (1011); |
|
|
!!!parse-error (type => (sprintf 'C1 character reference:U+%04X', $code), line => $l, column => $c); |
|
|
$code = $c1_entity_char->{$code}; |
|
|
} |
|
|
|
|
|
return {type => CHARACTER_TOKEN, data => chr $code, |
|
|
has_reference => 1, |
|
|
line => $l, column => $c, |
|
|
}; |
|
|
} # X |
|
|
} elsif (0x0030 <= $self->{next_char} and |
|
|
$self->{next_char} <= 0x0039) { # 0..9 |
|
|
my $code = $self->{next_char} - 0x0030; |
|
|
!!!next-input-character; |
|
|
|
|
|
while (0x0030 <= $self->{next_char} and |
|
|
$self->{next_char} <= 0x0039) { # 0..9 |
|
|
!!!cp (1012); |
|
|
$code *= 10; |
|
|
$code += $self->{next_char} - 0x0030; |
|
|
|
|
|
!!!next-input-character; |
|
|
} |
|
|
|
|
|
if ($self->{next_char} == 0x003B) { # ; |
|
|
!!!cp (1013); |
|
|
!!!next-input-character; |
|
|
} else { |
|
|
!!!cp (1014); |
|
|
!!!parse-error (type => 'no refc', line => $l, column => $c); |
|
|
} |
|
|
|
|
|
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
|
|
!!!cp (1015); |
|
|
!!!parse-error (type => (sprintf 'invalid character reference:U+%04X', $code), line => $l, column => $c); |
|
|
$code = 0xFFFD; |
|
|
} elsif ($code > 0x10FFFF) { |
|
|
!!!cp (1016); |
|
|
!!!parse-error (type => (sprintf 'invalid character reference:U-%08X', $code), line => $l, column => $c); |
|
|
$code = 0xFFFD; |
|
|
} elsif ($code == 0x000D) { |
|
|
!!!cp (1017); |
|
|
!!!parse-error (type => 'CR character reference', line => $l, column => $c); |
|
|
$code = 0x000A; |
|
|
} elsif (0x80 <= $code and $code <= 0x9F) { |
|
|
!!!cp (1018); |
|
|
!!!parse-error (type => (sprintf 'C1 character reference:U+%04X', $code), line => $l, column => $c); |
|
|
$code = $c1_entity_char->{$code}; |
|
|
} |
|
|
|
|
|
return {type => CHARACTER_TOKEN, data => chr $code, has_reference => 1, |
|
|
line => $l, column => $c, |
|
|
}; |
|
|
} else { |
|
|
!!!cp (1019); |
|
|
!!!parse-error (type => 'bare nero', line => $l, column => $c); |
|
|
!!!back-next-input-character ($self->{next_char}); |
|
|
$self->{next_char} = 0x0023; # # |
|
|
return undef; |
|
|
} |
|
|
} elsif ((0x0041 <= $self->{next_char} and |
|
|
$self->{next_char} <= 0x005A) or |
|
|
(0x0061 <= $self->{next_char} and |
|
|
$self->{next_char} <= 0x007A)) { |
|
|
my $entity_name = chr $self->{next_char}; |
|
|
!!!next-input-character; |
|
|
|
|
|
my $value = $entity_name; |
|
|
my $match = 0; |
|
|
require Whatpm::_NamedEntityList; |
|
|
our $EntityChar; |
|
|
|
|
|
while (length $entity_name < 30 and |
|
|
## NOTE: Some number greater than the maximum length of entity name |
|
|
((0x0041 <= $self->{next_char} and # a |
|
|
$self->{next_char} <= 0x005A) or # x |
|
|
(0x0061 <= $self->{next_char} and # a |
|
|
$self->{next_char} <= 0x007A) or # z |
|
|
(0x0030 <= $self->{next_char} and # 0 |
|
|
$self->{next_char} <= 0x0039) or # 9 |
|
|
$self->{next_char} == 0x003B)) { # ; |
|
|
$entity_name .= chr $self->{next_char}; |
|
|
if (defined $EntityChar->{$entity_name}) { |
|
|
if ($self->{next_char} == 0x003B) { # ; |
|
|
!!!cp (1020); |
|
|
$value = $EntityChar->{$entity_name}; |
|
|
$match = 1; |
|
|
!!!next-input-character; |
|
|
last; |
|
|
} else { |
|
|
!!!cp (1021); |
|
|
$value = $EntityChar->{$entity_name}; |
|
|
$match = -1; |
|
|
!!!next-input-character; |
|
|
} |
|
|
} else { |
|
|
!!!cp (1022); |
|
|
$value .= chr $self->{next_char}; |
|
|
$match *= 2; |
|
|
!!!next-input-character; |
|
|
} |
|
|
} |
|
|
|
|
|
if ($match > 0) { |
|
|
!!!cp (1023); |
|
|
return {type => CHARACTER_TOKEN, data => $value, has_reference => 1, |
|
|
line => $l, column => $c, |
|
|
}; |
|
|
} elsif ($match < 0) { |
|
|
!!!parse-error (type => 'no refc', line => $l, column => $c); |
|
|
if ($in_attr and $match < -1) { |
|
|
!!!cp (1024); |
|
|
return {type => CHARACTER_TOKEN, data => '&'.$entity_name, |
|
|
line => $l, column => $c, |
|
|
}; |
|
|
} else { |
|
|
!!!cp (1025); |
|
|
return {type => CHARACTER_TOKEN, data => $value, has_reference => 1, |
|
|
line => $l, column => $c, |
|
|
}; |
|
|
} |
|
|
} else { |
|
|
!!!cp (1026); |
|
|
!!!parse-error (type => 'bare ero', line => $l, column => $c); |
|
|
## NOTE: "No characters are consumed" in the spec. |
|
|
return {type => CHARACTER_TOKEN, data => '&'.$value, |
|
|
line => $l, column => $c, |
|
|
}; |
|
|
} |
|
|
} else { |
|
|
!!!cp (1027); |
|
|
## no characters are consumed |
|
|
!!!parse-error (type => 'bare ero', line => $l, column => $c); |
|
|
return undef; |
|
|
} |
|
|
} # _tokenize_attempt_to_consume_an_entity |
|
|
|
|
| 859 |
sub _initialize_tree_constructor ($) { |
sub _initialize_tree_constructor ($) { |
| 860 |
my $self = shift; |
my $self = shift; |
| 861 |
## NOTE: $self->{document} MUST be specified before this method is called |
## NOTE: $self->{document} MUST be specified before this method is called |
| 863 |
## TODO: Turn mutation events off # MUST |
## TODO: Turn mutation events off # MUST |
| 864 |
## TODO: Turn loose Document option (manakai extension) on |
## TODO: Turn loose Document option (manakai extension) on |
| 865 |
$self->{document}->manakai_is_html (1); # MUST |
$self->{document}->manakai_is_html (1); # MUST |
| 866 |
|
$self->{document}->set_user_data (manakai_source_line => 1); |
| 867 |
|
$self->{document}->set_user_data (manakai_source_column => 1); |
| 868 |
} # _initialize_tree_constructor |
} # _initialize_tree_constructor |
| 869 |
|
|
| 870 |
sub _terminate_tree_constructor ($) { |
sub _terminate_tree_constructor ($) { |
| 884 |
## When an interactive UA render the $self->{document} available |
## When an interactive UA render the $self->{document} available |
| 885 |
## to the user, or when it begin accepting user input, are |
## to the user, or when it begin accepting user input, are |
| 886 |
## not defined. |
## not defined. |
|
|
|
|
## Append a character: collect it and all subsequent consecutive |
|
|
## characters and insert one Text node whose data is concatenation |
|
|
## of all those characters. # MUST |
|
| 887 |
|
|
| 888 |
!!!next-token; |
!!!next-token; |
| 889 |
|
|
| 890 |
undef $self->{form_element}; |
undef $self->{form_element}; |
| 891 |
undef $self->{head_element}; |
undef $self->{head_element}; |
| 892 |
|
undef $self->{head_element_inserted}; |
| 893 |
$self->{open_elements} = []; |
$self->{open_elements} = []; |
| 894 |
undef $self->{inner_html_node}; |
undef $self->{inner_html_node}; |
| 895 |
|
undef $self->{ignore_newline}; |
| 896 |
|
|
| 897 |
## NOTE: The "initial" insertion mode. |
## NOTE: The "initial" insertion mode. |
| 898 |
$self->_tree_construction_initial; # MUST |
$self->_tree_construction_initial; # MUST |
| 912 |
|
|
| 913 |
INITIAL: { |
INITIAL: { |
| 914 |
if ($token->{type} == DOCTYPE_TOKEN) { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 915 |
## NOTE: Conformance checkers MAY, instead of reporting "not HTML5" |
## NOTE: Conformance checkers MAY, instead of reporting "not |
| 916 |
## error, switch to a conformance checking mode for another |
## HTML5" error, switch to a conformance checking mode for |
| 917 |
## language. |
## another language. (We don't support such mode switchings; it |
| 918 |
|
## is nonsense to do anything different from what browsers do.) |
| 919 |
my $doctype_name = $token->{name}; |
my $doctype_name = $token->{name}; |
| 920 |
$doctype_name = '' unless defined $doctype_name; |
$doctype_name = '' unless defined $doctype_name; |
| 921 |
$doctype_name =~ tr/a-z/A-Z/; |
my $doctype = $self->{document}->create_document_type_definition |
| 922 |
if (not defined $token->{name} or # <!DOCTYPE> |
($doctype_name); |
| 923 |
defined $token->{public_identifier} or |
|
| 924 |
defined $token->{system_identifier}) { |
$doctype_name =~ tr/A-Z/a-z/; # ASCII case-insensitive |
| 925 |
|
if ($doctype_name ne 'html') { |
| 926 |
!!!cp ('t1'); |
!!!cp ('t1'); |
| 927 |
!!!parse-error (type => 'not HTML5', token => $token); |
!!!parse-error (type => 'not HTML5', token => $token); |
| 928 |
} elsif ($doctype_name ne 'HTML') { |
} elsif (defined $token->{pubid}) { |
| 929 |
!!!cp ('t2'); |
!!!cp ('t2'); |
| 930 |
## ISSUE: ASCII case-insensitive? (in fact it does not matter) |
## XXX Obsolete permitted DOCTYPEs |
| 931 |
!!!parse-error (type => 'not HTML5', token => $token); |
!!!parse-error (type => 'not HTML5', token => $token); |
| 932 |
} else { |
} elsif (defined $token->{sysid}) { |
| 933 |
|
if ($token->{sysid} eq 'about:legacy-compat') { |
| 934 |
|
!!!cp ('t1.2'); ## <!DOCTYPE HTML SYSTEM "about:legacy-compat"> |
| 935 |
|
!!!parse-error (type => 'XSLT-compat', token => $token, |
| 936 |
|
level => $self->{level}->{should}); |
| 937 |
|
} else { |
| 938 |
|
!!!parse-error (type => 'not HTML5', token => $token); |
| 939 |
|
} |
| 940 |
|
} else { ## <!DOCTYPE HTML> |
| 941 |
!!!cp ('t3'); |
!!!cp ('t3'); |
| 942 |
|
# |
| 943 |
} |
} |
| 944 |
|
|
|
my $doctype = $self->{document}->create_document_type_definition |
|
|
($token->{name}); ## ISSUE: If name is missing (e.g. <!DOCTYPE>)? |
|
| 945 |
## NOTE: Default value for both |public_id| and |system_id| attributes |
## NOTE: Default value for both |public_id| and |system_id| attributes |
| 946 |
## are empty strings, so that we don't set any value in missing cases. |
## are empty strings, so that we don't set any value in missing cases. |
| 947 |
$doctype->public_id ($token->{public_identifier}) |
$doctype->public_id ($token->{pubid}) if defined $token->{pubid}; |
| 948 |
if defined $token->{public_identifier}; |
$doctype->system_id ($token->{sysid}) if defined $token->{sysid}; |
| 949 |
$doctype->system_id ($token->{system_identifier}) |
|
|
if defined $token->{system_identifier}; |
|
| 950 |
## NOTE: Other DocumentType attributes are null or empty lists. |
## NOTE: Other DocumentType attributes are null or empty lists. |
| 951 |
## ISSUE: internalSubset = null?? |
## In Firefox3, |internalSubset| attribute is set to the empty |
| 952 |
|
## string, while |null| is an allowed value for the attribute |
| 953 |
|
## according to DOM3 Core. |
| 954 |
$self->{document}->append_child ($doctype); |
$self->{document}->append_child ($doctype); |
| 955 |
|
|
| 956 |
if ($token->{quirks} or $doctype_name ne 'HTML') { |
if ($token->{quirks} or $doctype_name ne 'html') { |
| 957 |
!!!cp ('t4'); |
!!!cp ('t4'); |
| 958 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 959 |
} elsif (defined $token->{public_identifier}) { |
} elsif (defined $token->{pubid}) { |
| 960 |
my $pubid = $token->{public_identifier}; |
my $pubid = $token->{pubid}; |
| 961 |
$pubid =~ tr/a-z/A-z/; |
$pubid =~ tr/a-z/A-z/; |
| 962 |
if ({ |
my $prefix = [ |
| 963 |
"+//SILMARIL//DTD HTML PRO V0R11 19970101//EN" => 1, |
"+//SILMARIL//DTD HTML PRO V0R11 19970101//", |
| 964 |
"-//ADVASOFT LTD//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1, |
"-//ADVASOFT LTD//DTD HTML 3.0 ASWEDIT + EXTENSIONS//", |
| 965 |
"-//AS//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1, |
"-//AS//DTD HTML 3.0 ASWEDIT + EXTENSIONS//", |
| 966 |
"-//IETF//DTD HTML 2.0 LEVEL 1//EN" => 1, |
"-//IETF//DTD HTML 2.0 LEVEL 1//", |
| 967 |
"-//IETF//DTD HTML 2.0 LEVEL 2//EN" => 1, |
"-//IETF//DTD HTML 2.0 LEVEL 2//", |
| 968 |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 1//EN" => 1, |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 1//", |
| 969 |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 2//EN" => 1, |
"-//IETF//DTD HTML 2.0 STRICT LEVEL 2//", |
| 970 |
"-//IETF//DTD HTML 2.0 STRICT//EN" => 1, |
"-//IETF//DTD HTML 2.0 STRICT//", |
| 971 |
"-//IETF//DTD HTML 2.0//EN" => 1, |
"-//IETF//DTD HTML 2.0//", |
| 972 |
"-//IETF//DTD HTML 2.1E//EN" => 1, |
"-//IETF//DTD HTML 2.1E//", |
| 973 |
"-//IETF//DTD HTML 3.0//EN" => 1, |
"-//IETF//DTD HTML 3.0//", |
| 974 |
"-//IETF//DTD HTML 3.0//EN//" => 1, |
"-//IETF//DTD HTML 3.2 FINAL//", |
| 975 |
"-//IETF//DTD HTML 3.2 FINAL//EN" => 1, |
"-//IETF//DTD HTML 3.2//", |
| 976 |
"-//IETF//DTD HTML 3.2//EN" => 1, |
"-//IETF//DTD HTML 3//", |
| 977 |
"-//IETF//DTD HTML 3//EN" => 1, |
"-//IETF//DTD HTML LEVEL 0//", |
| 978 |
"-//IETF//DTD HTML LEVEL 0//EN" => 1, |
"-//IETF//DTD HTML LEVEL 1//", |
| 979 |
"-//IETF//DTD HTML LEVEL 0//EN//2.0" => 1, |
"-//IETF//DTD HTML LEVEL 2//", |
| 980 |
"-//IETF//DTD HTML LEVEL 1//EN" => 1, |
"-//IETF//DTD HTML LEVEL 3//", |
| 981 |
"-//IETF//DTD HTML LEVEL 1//EN//2.0" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 0//", |
| 982 |
"-//IETF//DTD HTML LEVEL 2//EN" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 1//", |
| 983 |
"-//IETF//DTD HTML LEVEL 2//EN//2.0" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 2//", |
| 984 |
"-//IETF//DTD HTML LEVEL 3//EN" => 1, |
"-//IETF//DTD HTML STRICT LEVEL 3//", |
| 985 |
"-//IETF//DTD HTML LEVEL 3//EN//3.0" => 1, |
"-//IETF//DTD HTML STRICT//", |
| 986 |
"-//IETF//DTD HTML STRICT LEVEL 0//EN" => 1, |
"-//IETF//DTD HTML//", |
| 987 |
"-//IETF//DTD HTML STRICT LEVEL 0//EN//2.0" => 1, |
"-//METRIUS//DTD METRIUS PRESENTATIONAL//", |
| 988 |
"-//IETF//DTD HTML STRICT LEVEL 1//EN" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML STRICT//", |
| 989 |
"-//IETF//DTD HTML STRICT LEVEL 1//EN//2.0" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML//", |
| 990 |
"-//IETF//DTD HTML STRICT LEVEL 2//EN" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 TABLES//", |
| 991 |
"-//IETF//DTD HTML STRICT LEVEL 2//EN//2.0" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML STRICT//", |
| 992 |
"-//IETF//DTD HTML STRICT LEVEL 3//EN" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML//", |
| 993 |
"-//IETF//DTD HTML STRICT LEVEL 3//EN//3.0" => 1, |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 TABLES//", |
| 994 |
"-//IETF//DTD HTML STRICT//EN" => 1, |
"-//NETSCAPE COMM. CORP.//DTD HTML//", |
| 995 |
"-//IETF//DTD HTML STRICT//EN//2.0" => 1, |
"-//NETSCAPE COMM. CORP.//DTD STRICT HTML//", |
| 996 |
"-//IETF//DTD HTML STRICT//EN//3.0" => 1, |
"-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//", |
| 997 |
"-//IETF//DTD HTML//EN" => 1, |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//", |
| 998 |
"-//IETF//DTD HTML//EN//2.0" => 1, |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED RELAXED 1.0//", |
| 999 |
"-//IETF//DTD HTML//EN//3.0" => 1, |
"-//SOFTQUAD SOFTWARE//DTD HOTMETAL PRO 6.0::19990601::EXTENSIONS TO HTML 4.0//", |
| 1000 |
"-//METRIUS//DTD METRIUS PRESENTATIONAL//EN" => 1, |
"-//SOFTQUAD//DTD HOTMETAL PRO 4.0::19971010::EXTENSIONS TO HTML 4.0//", |
| 1001 |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML STRICT//EN" => 1, |
"-//SPYGLASS//DTD HTML 2.0 EXTENDED//", |
| 1002 |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML//EN" => 1, |
"-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//", |
| 1003 |
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 TABLES//EN" => 1, |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//", |
| 1004 |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML STRICT//EN" => 1, |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA STRICT HTML//", |
| 1005 |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML//EN" => 1, |
"-//W3C//DTD HTML 3 1995-03-24//", |
| 1006 |
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 TABLES//EN" => 1, |
"-//W3C//DTD HTML 3.2 DRAFT//", |
| 1007 |
"-//NETSCAPE COMM. CORP.//DTD HTML//EN" => 1, |
"-//W3C//DTD HTML 3.2 FINAL//", |
| 1008 |
"-//NETSCAPE COMM. CORP.//DTD STRICT HTML//EN" => 1, |
"-//W3C//DTD HTML 3.2//", |
| 1009 |
"-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//EN" => 1, |
"-//W3C//DTD HTML 3.2S DRAFT//", |
| 1010 |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//EN" => 1, |
"-//W3C//DTD HTML 4.0 FRAMESET//", |
| 1011 |
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED RELAXED 1.0//EN" => 1, |
"-//W3C//DTD HTML 4.0 TRANSITIONAL//", |
| 1012 |
"-//SOFTQUAD SOFTWARE//DTD HOTMETAL PRO 6.0::19990601::EXTENSIONS TO HTML 4.0//EN" => 1, |
"-//W3C//DTD HTML EXPERIMETNAL 19960712//", |
| 1013 |
"-//SOFTQUAD//DTD HOTMETAL PRO 4.0::19971010::EXTENSIONS TO HTML 4.0//EN" => 1, |
"-//W3C//DTD HTML EXPERIMENTAL 970421//", |
| 1014 |
"-//SPYGLASS//DTD HTML 2.0 EXTENDED//EN" => 1, |
"-//W3C//DTD W3 HTML//", |
| 1015 |
"-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//EN" => 1, |
"-//W3O//DTD W3 HTML 3.0//", |
| 1016 |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//EN" => 1, |
"-//WEBTECHS//DTD MOZILLA HTML 2.0//", |
| 1017 |
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA STRICT HTML//EN" => 1, |
"-//WEBTECHS//DTD MOZILLA HTML//", |
| 1018 |
"-//W3C//DTD HTML 3 1995-03-24//EN" => 1, |
]; # $prefix |
| 1019 |
"-//W3C//DTD HTML 3.2 DRAFT//EN" => 1, |
my $match; |
| 1020 |
"-//W3C//DTD HTML 3.2 FINAL//EN" => 1, |
for (@$prefix) { |
| 1021 |
"-//W3C//DTD HTML 3.2//EN" => 1, |
if (substr ($prefix, 0, length $_) eq $_) { |
| 1022 |
"-//W3C//DTD HTML 3.2S DRAFT//EN" => 1, |
$match = 1; |
| 1023 |
"-//W3C//DTD HTML 4.0 FRAMESET//EN" => 1, |
last; |
| 1024 |
"-//W3C//DTD HTML 4.0 TRANSITIONAL//EN" => 1, |
} |
| 1025 |
"-//W3C//DTD HTML EXPERIMETNAL 19960712//EN" => 1, |
} |
| 1026 |
"-//W3C//DTD HTML EXPERIMENTAL 970421//EN" => 1, |
if ($match or |
| 1027 |
"-//W3C//DTD W3 HTML//EN" => 1, |
$pubid eq "-//W3O//DTD W3 HTML STRICT 3.0//EN//" or |
| 1028 |
"-//W3O//DTD W3 HTML 3.0//EN" => 1, |
$pubid eq "-/W3C/DTD HTML 4.0 TRANSITIONAL/EN" or |
| 1029 |
"-//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}) { |
|
| 1030 |
!!!cp ('t5'); |
!!!cp ('t5'); |
| 1031 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 1032 |
} elsif ($pubid eq "-//W3C//DTD HTML 4.01 FRAMESET//EN" or |
} elsif ($pubid =~ m[^-//W3C//DTD HTML 4.01 FRAMESET//] or |
| 1033 |
$pubid eq "-//W3C//DTD HTML 4.01 TRANSITIONAL//EN") { |
$pubid =~ m[^-//W3C//DTD HTML 4.01 TRANSITIONAL//]) { |
| 1034 |
if (defined $token->{system_identifier}) { |
if (defined $token->{sysid}) { |
| 1035 |
!!!cp ('t6'); |
!!!cp ('t6'); |
| 1036 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 1037 |
} else { |
} else { |
| 1038 |
!!!cp ('t7'); |
!!!cp ('t7'); |
| 1039 |
$self->{document}->manakai_compat_mode ('limited quirks'); |
$self->{document}->manakai_compat_mode ('limited quirks'); |
| 1040 |
} |
} |
| 1041 |
} elsif ($pubid eq "-//W3C//DTD XHTML 1.0 FRAMESET//EN" or |
} elsif ($pubid =~ m[^-//W3C//DTD XHTML 1.0 FRAMESET//] or |
| 1042 |
$pubid eq "-//W3C//DTD XHTML 1.0 TRANSITIONAL//EN") { |
$pubid =~ m[^-//W3C//DTD XHTML 1.0 TRANSITIONAL//]) { |
| 1043 |
!!!cp ('t8'); |
!!!cp ('t8'); |
| 1044 |
$self->{document}->manakai_compat_mode ('limited quirks'); |
$self->{document}->manakai_compat_mode ('limited quirks'); |
| 1045 |
} else { |
} else { |
| 1048 |
} else { |
} else { |
| 1049 |
!!!cp ('t10'); |
!!!cp ('t10'); |
| 1050 |
} |
} |
| 1051 |
if (defined $token->{system_identifier}) { |
if (defined $token->{sysid}) { |
| 1052 |
my $sysid = $token->{system_identifier}; |
my $sysid = $token->{sysid}; |
| 1053 |
$sysid =~ tr/A-Z/a-z/; |
$sysid =~ tr/A-Z/a-z/; |
| 1054 |
if ($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") { |
| 1055 |
## TODO: Check the spec: PUBLIC "(limited quirks)" "(quirks)" |
## NOTE: Ensure that |PUBLIC "(limited quirks)" "(quirks)"| is |
| 1056 |
|
## marked as quirks. |
| 1057 |
$self->{document}->manakai_compat_mode ('quirks'); |
$self->{document}->manakai_compat_mode ('quirks'); |
| 1058 |
!!!cp ('t11'); |
!!!cp ('t11'); |
| 1059 |
} else { |
} else { |
| 1079 |
!!!ack-later; |
!!!ack-later; |
| 1080 |
return; |
return; |
| 1081 |
} elsif ($token->{type} == CHARACTER_TOKEN) { |
} elsif ($token->{type} == CHARACTER_TOKEN) { |
| 1082 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
if ($token->{data} =~ s/^([\x09\x0A\x0C\x20]+)//) { |
| 1083 |
## Ignore the token |
## Ignore the token |
| 1084 |
|
|
| 1085 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 1136 |
!!!next-token; |
!!!next-token; |
| 1137 |
redo B; |
redo B; |
| 1138 |
} elsif ($token->{type} == CHARACTER_TOKEN) { |
} elsif ($token->{type} == CHARACTER_TOKEN) { |
| 1139 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
if ($token->{data} =~ s/^([\x09\x0A\x0C\x20]+)//) { |
| 1140 |
## Ignore the token. |
## Ignore the token. |
| 1141 |
|
|
| 1142 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 1203 |
## NOTE: Reprocess the token. |
## NOTE: Reprocess the token. |
| 1204 |
!!!ack-later; |
!!!ack-later; |
| 1205 |
return; ## Go to the "before head" insertion mode. |
return; ## Go to the "before head" insertion mode. |
|
|
|
|
## ISSUE: There is an issue in the spec |
|
| 1206 |
} # B |
} # B |
| 1207 |
|
|
| 1208 |
die "$0: _tree_construction_root_element: This should never be reached"; |
die "$0: _tree_construction_root_element: This should never be reached"; |
| 1223 |
if ($self->{open_elements}->[0]->[0] eq $node->[0]) { |
if ($self->{open_elements}->[0]->[0] eq $node->[0]) { |
| 1224 |
$last = 1; |
$last = 1; |
| 1225 |
if (defined $self->{inner_html_node}) { |
if (defined $self->{inner_html_node}) { |
| 1226 |
if ($self->{inner_html_node}->[1] & TABLE_CELL_EL) { |
!!!cp ('t28'); |
| 1227 |
!!!cp ('t27'); |
$node = $self->{inner_html_node}; |
| 1228 |
# |
} else { |
| 1229 |
} else { |
die "_reset_insertion_mode: t27"; |
|
!!!cp ('t28'); |
|
|
$node = $self->{inner_html_node}; |
|
|
} |
|
| 1230 |
} |
} |
| 1231 |
} |
} |
| 1232 |
|
|
| 1233 |
## Step 4..14 |
## Step 4..14 |
| 1234 |
my $new_mode; |
my $new_mode; |
| 1235 |
if ($node->[1] & FOREIGN_EL) { |
if ($node->[1] & FOREIGN_EL) { |
| 1236 |
## NOTE: Strictly spaking, the line below only applies to MathML and |
!!!cp ('t28.1'); |
| 1237 |
## SVG elements. Currently the HTML syntax supports only MathML and |
## NOTE: Strictly spaking, the line below only applies to MathML and |
| 1238 |
## SVG elements as foreigners. |
## SVG elements. Currently the HTML syntax supports only MathML and |
| 1239 |
$new_mode = $self->{insertion_mode} | IN_FOREIGN_CONTENT_IM; |
## SVG elements as foreigners. |
| 1240 |
## ISSUE: What is set as the secondary insertion mode? |
$new_mode = IN_BODY_IM | IN_FOREIGN_CONTENT_IM; |
| 1241 |
} else { |
} elsif ($node->[1] == TABLE_CELL_EL) { |
| 1242 |
$new_mode = { |
if ($last) { |
| 1243 |
|
!!!cp ('t28.2'); |
| 1244 |
|
# |
| 1245 |
|
} else { |
| 1246 |
|
!!!cp ('t28.3'); |
| 1247 |
|
$new_mode = IN_CELL_IM; |
| 1248 |
|
} |
| 1249 |
|
} else { |
| 1250 |
|
!!!cp ('t28.4'); |
| 1251 |
|
$new_mode = { |
| 1252 |
select => IN_SELECT_IM, |
select => IN_SELECT_IM, |
| 1253 |
## NOTE: |option| and |optgroup| do not set |
## NOTE: |option| and |optgroup| do not set |
| 1254 |
## insertion mode to "in select" by themselves. |
## insertion mode to "in select" by themselves. |
|
td => IN_CELL_IM, |
|
|
th => IN_CELL_IM, |
|
| 1255 |
tr => IN_ROW_IM, |
tr => IN_ROW_IM, |
| 1256 |
tbody => IN_TABLE_BODY_IM, |
tbody => IN_TABLE_BODY_IM, |
| 1257 |
thead => IN_TABLE_BODY_IM, |
thead => IN_TABLE_BODY_IM, |
| 1263 |
body => IN_BODY_IM, |
body => IN_BODY_IM, |
| 1264 |
frameset => IN_FRAMESET_IM, |
frameset => IN_FRAMESET_IM, |
| 1265 |
}->{$node->[0]->manakai_local_name}; |
}->{$node->[0]->manakai_local_name}; |
| 1266 |
} |
} |
| 1267 |
$self->{insertion_mode} = $new_mode and return if defined $new_mode; |
$self->{insertion_mode} = $new_mode and return if defined $new_mode; |
| 1268 |
|
|
| 1269 |
## Step 15 |
## Step 15 |
| 1270 |
if ($node->[1] & HTML_EL) { |
if ($node->[1] == HTML_EL) { |
| 1271 |
unless (defined $self->{head_element}) { |
unless (defined $self->{head_element}) { |
| 1272 |
!!!cp ('t29'); |
!!!cp ('t29'); |
| 1273 |
$self->{insertion_mode} = BEFORE_HEAD_IM; |
$self->{insertion_mode} = BEFORE_HEAD_IM; |
| 1399 |
|
|
| 1400 |
## Step 1 |
## Step 1 |
| 1401 |
my $start_tag_name = $token->{tag_name}; |
my $start_tag_name = $token->{tag_name}; |
| 1402 |
my $el; |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
|
!!!create-element ($el, $HTML_NS, $start_tag_name, $token->{attributes}, $token); |
|
| 1403 |
|
|
| 1404 |
## Step 2 |
## Step 2 |
|
$insert->($el); |
|
|
|
|
|
## Step 3 |
|
| 1405 |
$self->{content_model} = $content_model_flag; # CDATA or RCDATA |
$self->{content_model} = $content_model_flag; # CDATA or RCDATA |
| 1406 |
delete $self->{escape}; # MUST |
delete $self->{escape}; # MUST |
| 1407 |
|
|
| 1408 |
## Step 4 |
## Step 3, 4 |
| 1409 |
my $text = ''; |
$self->{insertion_mode} |= IN_CDATA_RCDATA_IM; |
|
!!!nack ('t40.1'); |
|
|
!!!next-token; |
|
|
while ($token->{type} == CHARACTER_TOKEN) { # or until stop tokenizing |
|
|
!!!cp ('t40'); |
|
|
$text .= $token->{data}; |
|
|
!!!next-token; |
|
|
} |
|
|
|
|
|
## Step 5 |
|
|
if (length $text) { |
|
|
!!!cp ('t41'); |
|
|
my $text = $self->{document}->create_text_node ($text); |
|
|
$el->append_child ($text); |
|
|
} |
|
|
|
|
|
## Step 6 |
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; |
|
| 1410 |
|
|
| 1411 |
## Step 7 |
!!!nack ('t40.1'); |
|
if ($token->{type} == END_TAG_TOKEN and |
|
|
$token->{tag_name} eq $start_tag_name) { |
|
|
!!!cp ('t42'); |
|
|
## Ignore the token |
|
|
} else { |
|
|
## NOTE: An end-of-file token. |
|
|
if ($content_model_flag == CDATA_CONTENT_MODEL) { |
|
|
!!!cp ('t43'); |
|
|
!!!parse-error (type => 'in CDATA:#'.$token->{type}, token => $token); |
|
|
} elsif ($content_model_flag == RCDATA_CONTENT_MODEL) { |
|
|
!!!cp ('t44'); |
|
|
!!!parse-error (type => 'in RCDATA:#'.$token->{type}, token => $token); |
|
|
} else { |
|
|
die "$0: $content_model_flag in parse_rcdata"; |
|
|
} |
|
|
} |
|
| 1412 |
!!!next-token; |
!!!next-token; |
| 1413 |
}; # $parse_rcdata |
}; # $parse_rcdata |
| 1414 |
|
|
| 1415 |
my $script_start_tag = sub () { |
my $script_start_tag = sub () { |
| 1416 |
|
## Step 1 |
| 1417 |
my $script_el; |
my $script_el; |
| 1418 |
!!!create-element ($script_el, $HTML_NS, 'script', $token->{attributes}, $token); |
!!!create-element ($script_el, $HTML_NS, 'script', $token->{attributes}, $token); |
| 1419 |
|
|
| 1420 |
|
## Step 2 |
| 1421 |
## TODO: mark as "parser-inserted" |
## TODO: mark as "parser-inserted" |
| 1422 |
|
|
| 1423 |
|
## Step 3 |
| 1424 |
|
## TODO: Mark as "already executed", if ... |
| 1425 |
|
|
| 1426 |
|
## Step 4 (HTML5 revision 2702) |
| 1427 |
|
$insert->($script_el); |
| 1428 |
|
push @{$self->{open_elements}}, [$script_el, $el_category->{script}]; |
| 1429 |
|
|
| 1430 |
|
## Step 5 |
| 1431 |
$self->{content_model} = CDATA_CONTENT_MODEL; |
$self->{content_model} = CDATA_CONTENT_MODEL; |
| 1432 |
delete $self->{escape}; # MUST |
delete $self->{escape}; # MUST |
|
|
|
|
my $text = ''; |
|
|
!!!nack ('t45.1'); |
|
|
!!!next-token; |
|
|
while ($token->{type} == CHARACTER_TOKEN) { |
|
|
!!!cp ('t45'); |
|
|
$text .= $token->{data}; |
|
|
!!!next-token; |
|
|
} # stop if non-character token or tokenizer stops tokenising |
|
|
if (length $text) { |
|
|
!!!cp ('t46'); |
|
|
$script_el->manakai_append_text ($text); |
|
|
} |
|
|
|
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; |
|
| 1433 |
|
|
| 1434 |
if ($token->{type} == END_TAG_TOKEN and |
## Step 6-7 |
| 1435 |
$token->{tag_name} eq 'script') { |
$self->{insertion_mode} |= IN_CDATA_RCDATA_IM; |
|
!!!cp ('t47'); |
|
|
## Ignore the token |
|
|
} else { |
|
|
!!!cp ('t48'); |
|
|
!!!parse-error (type => 'in CDATA:#'.$token->{type}, token => $token); |
|
|
## ISSUE: And ignore? |
|
|
## TODO: mark as "already executed" |
|
|
} |
|
|
|
|
|
if (defined $self->{inner_html_node}) { |
|
|
!!!cp ('t49'); |
|
|
## TODO: mark as "already executed" |
|
|
} else { |
|
|
!!!cp ('t50'); |
|
|
## TODO: $old_insertion_point = current insertion point |
|
|
## TODO: insertion point = just before the next input character |
|
| 1436 |
|
|
| 1437 |
$insert->($script_el); |
!!!nack ('t40.2'); |
|
|
|
|
## TODO: insertion point = $old_insertion_point (might be "undefined") |
|
|
|
|
|
## TODO: if there is a script that will execute as soon as the parser resume, then... |
|
|
} |
|
|
|
|
| 1438 |
!!!next-token; |
!!!next-token; |
| 1439 |
}; # $script_start_tag |
}; # $script_start_tag |
| 1440 |
|
|
| 1441 |
## NOTE: $open_tables->[-1]->[0] is the "current table" element node. |
## NOTE: $open_tables->[-1]->[0] is the "current table" element node. |
| 1442 |
## NOTE: $open_tables->[-1]->[1] is the "tainted" flag. |
## NOTE: $open_tables->[-1]->[1] is the "tainted" flag (OBSOLETE; unused). |
| 1443 |
|
## NOTE: $open_tables->[-1]->[2] is set false when non-Text node inserted. |
| 1444 |
my $open_tables = [[$self->{open_elements}->[0]->[0]]]; |
my $open_tables = [[$self->{open_elements}->[0]->[0]]]; |
| 1445 |
|
|
| 1446 |
my $formatting_end_tag = sub { |
my $formatting_end_tag = sub { |
| 1467 |
} # AFE |
} # AFE |
| 1468 |
unless (defined $formatting_element) { |
unless (defined $formatting_element) { |
| 1469 |
!!!cp ('t53'); |
!!!cp ('t53'); |
| 1470 |
!!!parse-error (type => 'unmatched end tag:'.$tag_name, token => $end_tag_token); |
!!!parse-error (type => 'unmatched end tag', text => $tag_name, token => $end_tag_token); |
| 1471 |
## Ignore the token |
## Ignore the token |
| 1472 |
!!!next-token; |
!!!next-token; |
| 1473 |
return; |
return; |
| 1484 |
last INSCOPE; |
last INSCOPE; |
| 1485 |
} else { # in open elements but not in scope |
} else { # in open elements but not in scope |
| 1486 |
!!!cp ('t55'); |
!!!cp ('t55'); |
| 1487 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, |
!!!parse-error (type => 'unmatched end tag', |
| 1488 |
|
text => $token->{tag_name}, |
| 1489 |
token => $end_tag_token); |
token => $end_tag_token); |
| 1490 |
## Ignore the token |
## Ignore the token |
| 1491 |
!!!next-token; |
!!!next-token; |
| 1498 |
} # INSCOPE |
} # INSCOPE |
| 1499 |
unless (defined $formatting_element_i_in_open) { |
unless (defined $formatting_element_i_in_open) { |
| 1500 |
!!!cp ('t57'); |
!!!cp ('t57'); |
| 1501 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, |
!!!parse-error (type => 'unmatched end tag', |
| 1502 |
|
text => $token->{tag_name}, |
| 1503 |
token => $end_tag_token); |
token => $end_tag_token); |
| 1504 |
pop @$active_formatting_elements; # $formatting_element |
pop @$active_formatting_elements; # $formatting_element |
| 1505 |
!!!next-token; ## TODO: ok? |
!!!next-token; ## TODO: ok? |
| 1508 |
if (not $self->{open_elements}->[-1]->[0] eq $formatting_element->[0]) { |
if (not $self->{open_elements}->[-1]->[0] eq $formatting_element->[0]) { |
| 1509 |
!!!cp ('t58'); |
!!!cp ('t58'); |
| 1510 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 1511 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 1512 |
->manakai_local_name, |
->manakai_local_name, |
| 1513 |
token => $end_tag_token); |
token => $end_tag_token); |
| 1514 |
} |
} |
| 1525 |
!!!cp ('t59'); |
!!!cp ('t59'); |
| 1526 |
$furthest_block = $node; |
$furthest_block = $node; |
| 1527 |
$furthest_block_i_in_open = $_; |
$furthest_block_i_in_open = $_; |
| 1528 |
|
## NOTE: The topmost (eldest) node. |
| 1529 |
} elsif ($node->[0] eq $formatting_element->[0]) { |
} elsif ($node->[0] eq $formatting_element->[0]) { |
| 1530 |
!!!cp ('t60'); |
!!!cp ('t60'); |
| 1531 |
last OE; |
last OE; |
| 1612 |
my $foster_parent_element; |
my $foster_parent_element; |
| 1613 |
my $next_sibling; |
my $next_sibling; |
| 1614 |
OE: for (reverse 0..$#{$self->{open_elements}}) { |
OE: for (reverse 0..$#{$self->{open_elements}}) { |
| 1615 |
if ($self->{open_elements}->[$_]->[1] & TABLE_EL) { |
if ($self->{open_elements}->[$_]->[1] == TABLE_EL) { |
| 1616 |
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
| 1617 |
if (defined $parent and $parent->node_type == 1) { |
if (defined $parent and $parent->node_type == 1) { |
| 1618 |
!!!cp ('t65.1'); |
!!!cp ('t65.1'); |
| 1672 |
$i = $_; |
$i = $_; |
| 1673 |
} |
} |
| 1674 |
} # OE |
} # OE |
| 1675 |
splice @{$self->{open_elements}}, $i + 1, 1, $clone; |
splice @{$self->{open_elements}}, $i + 1, 0, $clone; |
| 1676 |
|
|
| 1677 |
## Step 14 |
## Step 14 |
| 1678 |
redo FET; |
redo FET; |
| 1690 |
my $foster_parent_element; |
my $foster_parent_element; |
| 1691 |
my $next_sibling; |
my $next_sibling; |
| 1692 |
OE: for (reverse 0..$#{$self->{open_elements}}) { |
OE: for (reverse 0..$#{$self->{open_elements}}) { |
| 1693 |
if ($self->{open_elements}->[$_]->[1] & TABLE_EL) { |
if ($self->{open_elements}->[$_]->[1] == TABLE_EL) { |
| 1694 |
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
| 1695 |
if (defined $parent and $parent->node_type == 1) { |
if (defined $parent and $parent->node_type == 1) { |
| 1696 |
!!!cp ('t70'); |
!!!cp ('t70'); |
| 1715 |
} |
} |
| 1716 |
}; # $insert_to_foster |
}; # $insert_to_foster |
| 1717 |
|
|
| 1718 |
|
## NOTE: Insert a character (MUST): When a character is inserted, if |
| 1719 |
|
## the last node that was inserted by the parser is a Text node and |
| 1720 |
|
## the character has to be inserted after that node, then the |
| 1721 |
|
## character is appended to the Text node. However, if any other |
| 1722 |
|
## node is inserted by the parser, then a new Text node is created |
| 1723 |
|
## and the character is appended as that Text node. If I'm not |
| 1724 |
|
## wrong, for a parser with scripting disabled, there are only two |
| 1725 |
|
## cases where this occurs. One is the case where an element node |
| 1726 |
|
## is inserted to the |head| element. This is covered by using the |
| 1727 |
|
## |$self->{head_element_inserted}| flag. Another is the case where |
| 1728 |
|
## an element or comment is inserted into the |table| subtree while |
| 1729 |
|
## foster parenting happens. This is covered by using the [2] flag |
| 1730 |
|
## of the |$open_tables| structure. All other cases are handled |
| 1731 |
|
## simply by calling |manakai_append_text| method. |
| 1732 |
|
|
| 1733 |
|
## TODO: |<body><script>document.write("a<br>"); |
| 1734 |
|
## document.body.removeChild (document.body.lastChild); |
| 1735 |
|
## document.write ("b")</script>| |
| 1736 |
|
|
| 1737 |
B: while (1) { |
B: while (1) { |
| 1738 |
|
|
| 1739 |
|
## The "in table text" insertion mode. |
| 1740 |
|
if ($self->{insertion_mode} & TABLE_IMS and |
| 1741 |
|
not $self->{insertion_mode} & IN_FOREIGN_CONTENT_IM and |
| 1742 |
|
not $self->{insertion_mode} & IN_CDATA_RCDATA_IM) { |
| 1743 |
|
C: { |
| 1744 |
|
my $s; |
| 1745 |
|
if ($token->{type} == CHARACTER_TOKEN) { |
| 1746 |
|
!!!cp ('t194'); |
| 1747 |
|
$self->{pending_chars} ||= []; |
| 1748 |
|
push @{$self->{pending_chars}}, $token; |
| 1749 |
|
!!!next-token; |
| 1750 |
|
next B; |
| 1751 |
|
} else { |
| 1752 |
|
if ($self->{pending_chars}) { |
| 1753 |
|
$s = join '', map { $_->{data} } @{$self->{pending_chars}}; |
| 1754 |
|
delete $self->{pending_chars}; |
| 1755 |
|
if ($s =~ /[^\x09\x0A\x0C\x0D\x20]/) { |
| 1756 |
|
!!!cp ('t195'); |
| 1757 |
|
# |
| 1758 |
|
} else { |
| 1759 |
|
!!!cp ('t195.1'); |
| 1760 |
|
#$self->{open_elements}->[-1]->[0]->manakai_append_text ($s); |
| 1761 |
|
$self->{open_elements}->[-1]->[0]->append_child |
| 1762 |
|
($self->{document}->create_text_node ($s)); |
| 1763 |
|
last C; |
| 1764 |
|
} |
| 1765 |
|
} else { |
| 1766 |
|
!!!cp ('t195.2'); |
| 1767 |
|
last C; |
| 1768 |
|
} |
| 1769 |
|
} |
| 1770 |
|
|
| 1771 |
|
## Foster parenting |
| 1772 |
|
!!!parse-error (type => 'in table:#text', token => $token); |
| 1773 |
|
|
| 1774 |
|
## NOTE: As if in body, but insert into the foster parent element. |
| 1775 |
|
$reconstruct_active_formatting_elements->($insert_to_foster); |
| 1776 |
|
|
| 1777 |
|
if ($self->{open_elements}->[-1]->[1] & TABLE_ROWS_EL) { |
| 1778 |
|
# MUST |
| 1779 |
|
my $foster_parent_element; |
| 1780 |
|
my $next_sibling; |
| 1781 |
|
#my $prev_sibling; |
| 1782 |
|
OE: for (reverse 0..$#{$self->{open_elements}}) { |
| 1783 |
|
if ($self->{open_elements}->[$_]->[1] == TABLE_EL) { |
| 1784 |
|
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
| 1785 |
|
if (defined $parent and $parent->node_type == 1) { |
| 1786 |
|
$foster_parent_element = $parent; |
| 1787 |
|
!!!cp ('t196'); |
| 1788 |
|
$next_sibling = $self->{open_elements}->[$_]->[0]; |
| 1789 |
|
# $prev_sibling = $next_sibling->previous_sibling; |
| 1790 |
|
# |
| 1791 |
|
} else { |
| 1792 |
|
!!!cp ('t197'); |
| 1793 |
|
$foster_parent_element = $self->{open_elements}->[$_ - 1]->[0]; |
| 1794 |
|
# $prev_sibling = $foster_parent_element->last_child; |
| 1795 |
|
# |
| 1796 |
|
} |
| 1797 |
|
last OE; |
| 1798 |
|
} |
| 1799 |
|
} # OE |
| 1800 |
|
$foster_parent_element = $self->{open_elements}->[0]->[0] #and |
| 1801 |
|
#$prev_sibling = $foster_parent_element->last_child |
| 1802 |
|
unless defined $foster_parent_element; |
| 1803 |
|
#undef $prev_sibling unless $open_tables->[-1]->[2]; # ~node inserted |
| 1804 |
|
#if (defined $prev_sibling and |
| 1805 |
|
# $prev_sibling->node_type == 3) { |
| 1806 |
|
# !!! cp ('t198'); |
| 1807 |
|
# $prev_sibling->manakai_append_text ($s); |
| 1808 |
|
#} else { |
| 1809 |
|
!!!cp ('t199'); |
| 1810 |
|
$foster_parent_element->insert_before |
| 1811 |
|
($self->{document}->create_text_node ($s), $next_sibling); |
| 1812 |
|
#} |
| 1813 |
|
$open_tables->[-1]->[1] = 1; # tainted |
| 1814 |
|
$open_tables->[-1]->[2] = 1; # ~node inserted |
| 1815 |
|
} else { |
| 1816 |
|
## NOTE: Fragment case or in a foster parent'ed element |
| 1817 |
|
## (e.g. |<table><span>a|). In fragment case, whether the |
| 1818 |
|
## character is appended to existing node or a new node is |
| 1819 |
|
## created is irrelevant, since the foster parent'ed nodes |
| 1820 |
|
## are discarded and fragment parsing does not invoke any |
| 1821 |
|
## script. |
| 1822 |
|
!!!cp ('t200'); |
| 1823 |
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($s); |
| 1824 |
|
} |
| 1825 |
|
} # C |
| 1826 |
|
} # TABLE_IMS |
| 1827 |
|
|
| 1828 |
if ($token->{type} == DOCTYPE_TOKEN) { |
if ($token->{type} == DOCTYPE_TOKEN) { |
| 1829 |
!!!cp ('t73'); |
!!!cp ('t73'); |
| 1830 |
!!!parse-error (type => 'DOCTYPE in the middle', token => $token); |
!!!parse-error (type => 'in html:#DOCTYPE', token => $token); |
| 1831 |
## Ignore the token |
## Ignore the token |
| 1832 |
## Stay in the phase |
## Stay in the phase |
| 1833 |
!!!next-token; |
!!!next-token; |
| 1836 |
$token->{tag_name} eq 'html') { |
$token->{tag_name} eq 'html') { |
| 1837 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 1838 |
!!!cp ('t79'); |
!!!cp ('t79'); |
| 1839 |
!!!parse-error (type => 'after html:html', token => $token); |
!!!parse-error (type => 'after html', text => 'html', token => $token); |
| 1840 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 1841 |
} elsif ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HTML_FRAMESET_IM) { |
| 1842 |
!!!cp ('t80'); |
!!!cp ('t80'); |
| 1843 |
!!!parse-error (type => 'after html:html', token => $token); |
!!!parse-error (type => 'after html', text => 'html', token => $token); |
| 1844 |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 1845 |
} else { |
} else { |
| 1846 |
!!!cp ('t81'); |
!!!cp ('t81'); |
| 1871 |
} else { |
} else { |
| 1872 |
!!!cp ('t87'); |
!!!cp ('t87'); |
| 1873 |
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
| 1874 |
|
$open_tables->[-1]->[2] = 0 if @$open_tables; # ~node inserted |
| 1875 |
} |
} |
| 1876 |
!!!next-token; |
!!!next-token; |
| 1877 |
next B; |
next B; |
| 1878 |
|
} elsif ($self->{insertion_mode} & IN_CDATA_RCDATA_IM) { |
| 1879 |
|
if ($token->{type} == CHARACTER_TOKEN) { |
| 1880 |
|
$token->{data} =~ s/^\x0A// if $self->{ignore_newline}; |
| 1881 |
|
delete $self->{ignore_newline}; |
| 1882 |
|
|
| 1883 |
|
if (length $token->{data}) { |
| 1884 |
|
!!!cp ('t43'); |
| 1885 |
|
$self->{open_elements}->[-1]->[0]->manakai_append_text |
| 1886 |
|
($token->{data}); |
| 1887 |
|
} else { |
| 1888 |
|
!!!cp ('t43.1'); |
| 1889 |
|
} |
| 1890 |
|
!!!next-token; |
| 1891 |
|
next B; |
| 1892 |
|
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 1893 |
|
delete $self->{ignore_newline}; |
| 1894 |
|
|
| 1895 |
|
if ($token->{tag_name} eq 'script') { |
| 1896 |
|
!!!cp ('t50'); |
| 1897 |
|
|
| 1898 |
|
## Para 1-2 |
| 1899 |
|
my $script = pop @{$self->{open_elements}}; |
| 1900 |
|
|
| 1901 |
|
## Para 3 |
| 1902 |
|
$self->{insertion_mode} &= ~ IN_CDATA_RCDATA_IM; |
| 1903 |
|
|
| 1904 |
|
## Para 4 |
| 1905 |
|
## TODO: $old_insertion_point = $current_insertion_point; |
| 1906 |
|
## TODO: $current_insertion_point = just before $self->{nc}; |
| 1907 |
|
|
| 1908 |
|
## Para 5 |
| 1909 |
|
## TODO: Run the $script->[0]. |
| 1910 |
|
|
| 1911 |
|
## Para 6 |
| 1912 |
|
## TODO: $current_insertion_point = $old_insertion_point; |
| 1913 |
|
|
| 1914 |
|
## Para 7 |
| 1915 |
|
## TODO: if ($pending_external_script) { |
| 1916 |
|
## TODO: ... |
| 1917 |
|
## TODO: } |
| 1918 |
|
|
| 1919 |
|
!!!next-token; |
| 1920 |
|
next B; |
| 1921 |
|
} else { |
| 1922 |
|
!!!cp ('t42'); |
| 1923 |
|
|
| 1924 |
|
pop @{$self->{open_elements}}; |
| 1925 |
|
|
| 1926 |
|
$self->{insertion_mode} &= ~ IN_CDATA_RCDATA_IM; |
| 1927 |
|
!!!next-token; |
| 1928 |
|
next B; |
| 1929 |
|
} |
| 1930 |
|
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 1931 |
|
delete $self->{ignore_newline}; |
| 1932 |
|
|
| 1933 |
|
!!!cp ('t44'); |
| 1934 |
|
!!!parse-error (type => 'not closed', |
| 1935 |
|
text => $self->{open_elements}->[-1]->[0] |
| 1936 |
|
->manakai_local_name, |
| 1937 |
|
token => $token); |
| 1938 |
|
|
| 1939 |
|
#if ($self->{open_elements}->[-1]->[1] == SCRIPT_EL) { |
| 1940 |
|
# ## TODO: Mark as "already executed" |
| 1941 |
|
#} |
| 1942 |
|
|
| 1943 |
|
pop @{$self->{open_elements}}; |
| 1944 |
|
|
| 1945 |
|
$self->{insertion_mode} &= ~ IN_CDATA_RCDATA_IM; |
| 1946 |
|
## Reprocess. |
| 1947 |
|
next B; |
| 1948 |
|
} else { |
| 1949 |
|
die "$0: $token->{type}: In CDATA/RCDATA: Unknown token type"; |
| 1950 |
|
} |
| 1951 |
} elsif ($self->{insertion_mode} & IN_FOREIGN_CONTENT_IM) { |
} elsif ($self->{insertion_mode} & IN_FOREIGN_CONTENT_IM) { |
| 1952 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 1953 |
!!!cp ('t87.1'); |
!!!cp ('t87.1'); |
| 1959 |
$self->{open_elements}->[-1]->[1] & FOREIGN_FLOW_CONTENT_EL) or |
$self->{open_elements}->[-1]->[1] & FOREIGN_FLOW_CONTENT_EL) or |
| 1960 |
not ($self->{open_elements}->[-1]->[1] & FOREIGN_EL) or |
not ($self->{open_elements}->[-1]->[1] & FOREIGN_EL) or |
| 1961 |
($token->{tag_name} eq 'svg' and |
($token->{tag_name} eq 'svg' and |
| 1962 |
$self->{open_elements}->[-1]->[1] & MML_AXML_EL)) { |
$self->{open_elements}->[-1]->[1] == MML_AXML_EL)) { |
| 1963 |
## NOTE: "using the rules for secondary insertion mode"then"continue" |
## NOTE: "using the rules for secondary insertion mode"then"continue" |
| 1964 |
!!!cp ('t87.2'); |
!!!cp ('t87.2'); |
| 1965 |
# |
# |
| 1966 |
} elsif ({ |
} elsif ({ |
| 1967 |
b => 1, big => 1, blockquote => 1, body => 1, br => 1, |
b => 1, big => 1, blockquote => 1, body => 1, br => 1, |
| 1968 |
center => 1, code => 1, dd => 1, div => 1, dl => 1, em => 1, |
center => 1, code => 1, dd => 1, div => 1, dl => 1, dt => 1, |
| 1969 |
embed => 1, font => 1, h1 => 1, h2 => 1, h3 => 1, ## No h4! |
em => 1, embed => 1, h1 => 1, h2 => 1, h3 => 1, |
| 1970 |
h5 => 1, h6 => 1, head => 1, hr => 1, i => 1, img => 1, |
h4 => 1, h5 => 1, h6 => 1, head => 1, hr => 1, i => 1, |
| 1971 |
li => 1, menu => 1, meta => 1, nobr => 1, p => 1, pre => 1, |
img => 1, li => 1, listing => 1, menu => 1, meta => 1, |
| 1972 |
ruby => 1, s => 1, small => 1, span => 1, strong => 1, |
nobr => 1, ol => 1, p => 1, pre => 1, ruby => 1, s => 1, |
| 1973 |
sub => 1, sup => 1, table => 1, tt => 1, u => 1, ul => 1, |
small => 1, span => 1, strong => 1, strike => 1, sub => 1, |
| 1974 |
var => 1, |
sup => 1, table => 1, tt => 1, u => 1, ul => 1, var => 1, |
| 1975 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}} or |
| 1976 |
|
($token->{tag_name} eq 'font' and |
| 1977 |
|
($token->{attributes}->{color} or |
| 1978 |
|
$token->{attributes}->{face} or |
| 1979 |
|
$token->{attributes}->{size}))) { |
| 1980 |
!!!cp ('t87.2'); |
!!!cp ('t87.2'); |
| 1981 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 1982 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 1983 |
->manakai_local_name, |
->manakai_local_name, |
| 1984 |
token => $token); |
token => $token); |
| 1985 |
|
|
| 2052 |
} |
} |
| 2053 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 2054 |
## NOTE: "using the rules for secondary insertion mode" then "continue" |
## NOTE: "using the rules for secondary insertion mode" then "continue" |
| 2055 |
!!!cp ('t87.5'); |
if ($token->{tag_name} eq 'script') { |
| 2056 |
# |
!!!cp ('t87.41'); |
| 2057 |
|
# |
| 2058 |
|
## XXXscript: Execute script here. |
| 2059 |
|
} else { |
| 2060 |
|
!!!cp ('t87.5'); |
| 2061 |
|
# |
| 2062 |
|
} |
| 2063 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
|
## NOTE: "using the rules for secondary insertion mode" then "continue" |
|
| 2064 |
!!!cp ('t87.6'); |
!!!cp ('t87.6'); |
| 2065 |
# |
!!!parse-error (type => 'not closed', |
| 2066 |
## TODO: ... |
text => $self->{open_elements}->[-1]->[0] |
| 2067 |
|
->manakai_local_name, |
| 2068 |
|
token => $token); |
| 2069 |
|
|
| 2070 |
|
pop @{$self->{open_elements}} |
| 2071 |
|
while $self->{open_elements}->[-1]->[1] & FOREIGN_EL; |
| 2072 |
|
|
| 2073 |
|
## NOTE: |<span><svg>| ... two parse errors, |<svg>| ... a parse error. |
| 2074 |
|
|
| 2075 |
|
$self->{insertion_mode} &= ~ IN_FOREIGN_CONTENT_IM; |
| 2076 |
|
## Reprocess. |
| 2077 |
|
next B; |
| 2078 |
} else { |
} else { |
| 2079 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 2080 |
} |
} |
| 2082 |
|
|
| 2083 |
if ($self->{insertion_mode} & HEAD_IMS) { |
if ($self->{insertion_mode} & HEAD_IMS) { |
| 2084 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 2085 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0C\x20]+)//) { |
| 2086 |
unless ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
unless ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 2087 |
!!!cp ('t88.2'); |
if ($self->{head_element_inserted}) { |
| 2088 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
!!!cp ('t88.3'); |
| 2089 |
|
$self->{open_elements}->[-1]->[0]->append_child |
| 2090 |
|
($self->{document}->create_text_node ($1)); |
| 2091 |
|
delete $self->{head_element_inserted}; |
| 2092 |
|
## NOTE: |</head> <link> | |
| 2093 |
|
# |
| 2094 |
|
} else { |
| 2095 |
|
!!!cp ('t88.2'); |
| 2096 |
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 2097 |
|
## NOTE: |</head>  | |
| 2098 |
|
# |
| 2099 |
|
} |
| 2100 |
} else { |
} else { |
| 2101 |
!!!cp ('t88.1'); |
!!!cp ('t88.1'); |
| 2102 |
## Ignore the token. |
## Ignore the token. |
| 2103 |
!!!next-token; |
# |
|
next B; |
|
| 2104 |
} |
} |
| 2105 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 2106 |
!!!cp ('t88'); |
!!!cp ('t88'); |
| 2107 |
!!!next-token; |
!!!next-token; |
| 2108 |
next B; |
next B; |
| 2109 |
} |
} |
| 2110 |
|
## TODO: set $token->{column} appropriately |
| 2111 |
} |
} |
| 2112 |
|
|
| 2113 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 2126 |
!!!cp ('t90'); |
!!!cp ('t90'); |
| 2127 |
## As if </noscript> |
## As if </noscript> |
| 2128 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2129 |
!!!parse-error (type => 'in noscript:#character', token => $token); |
!!!parse-error (type => 'in noscript:#text', token => $token); |
| 2130 |
|
|
| 2131 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 2132 |
## As if </head> |
## As if </head> |
| 2162 |
!!!next-token; |
!!!next-token; |
| 2163 |
next B; |
next B; |
| 2164 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2165 |
!!!cp ('t94'); |
!!!cp ('t93.2'); |
| 2166 |
# |
!!!parse-error (type => 'after head', text => 'head', |
| 2167 |
|
token => $token); |
| 2168 |
|
## Ignore the token |
| 2169 |
|
!!!nack ('t93.3'); |
| 2170 |
|
!!!next-token; |
| 2171 |
|
next B; |
| 2172 |
} else { |
} else { |
| 2173 |
!!!cp ('t95'); |
!!!cp ('t95'); |
| 2174 |
!!!parse-error (type => 'in head:head', token => $token); # or in head noscript |
!!!parse-error (type => 'in head:head', |
| 2175 |
|
token => $token); # or in head noscript |
| 2176 |
## Ignore the token |
## Ignore the token |
| 2177 |
!!!nack ('t95.1'); |
!!!nack ('t95.1'); |
| 2178 |
!!!next-token; |
!!!next-token; |
| 2192 |
!!!cp ('t97'); |
!!!cp ('t97'); |
| 2193 |
} |
} |
| 2194 |
|
|
| 2195 |
if ($token->{tag_name} eq 'base') { |
if ($token->{tag_name} eq 'base') { |
| 2196 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2197 |
!!!cp ('t98'); |
!!!cp ('t98'); |
| 2198 |
## As if </noscript> |
## As if </noscript> |
| 2199 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2200 |
!!!parse-error (type => 'in noscript:base', token => $token); |
!!!parse-error (type => 'in noscript', text => 'base', |
| 2201 |
|
token => $token); |
| 2202 |
$self->{insertion_mode} = IN_HEAD_IM; |
|
| 2203 |
## Reprocess in the "in head" insertion mode... |
$self->{insertion_mode} = IN_HEAD_IM; |
| 2204 |
} else { |
## Reprocess in the "in head" insertion mode... |
| 2205 |
!!!cp ('t99'); |
} else { |
| 2206 |
} |
!!!cp ('t99'); |
| 2207 |
|
} |
| 2208 |
|
|
| 2209 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 2210 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2211 |
!!!cp ('t100'); |
!!!cp ('t100'); |
| 2212 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after head', |
| 2213 |
push @{$self->{open_elements}}, |
text => $token->{tag_name}, token => $token); |
| 2214 |
[$self->{head_element}, $el_category->{head}]; |
push @{$self->{open_elements}}, |
| 2215 |
} else { |
[$self->{head_element}, $el_category->{head}]; |
| 2216 |
!!!cp ('t101'); |
$self->{head_element_inserted} = 1; |
| 2217 |
} |
} else { |
| 2218 |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
!!!cp ('t101'); |
| 2219 |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
} |
| 2220 |
pop @{$self->{open_elements}} # <head> |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 2221 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
pop @{$self->{open_elements}}; |
| 2222 |
!!!nack ('t101.1'); |
pop @{$self->{open_elements}} # <head> |
| 2223 |
!!!next-token; |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 2224 |
next B; |
!!!nack ('t101.1'); |
| 2225 |
} elsif ($token->{tag_name} eq 'link') { |
!!!next-token; |
| 2226 |
## NOTE: There is a "as if in head" code clone. |
next B; |
| 2227 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
} elsif ($token->{tag_name} eq 'link') { |
| 2228 |
!!!cp ('t102'); |
## NOTE: There is a "as if in head" code clone. |
| 2229 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2230 |
push @{$self->{open_elements}}, |
!!!cp ('t102'); |
| 2231 |
[$self->{head_element}, $el_category->{head}]; |
!!!parse-error (type => 'after head', |
| 2232 |
} else { |
text => $token->{tag_name}, token => $token); |
| 2233 |
!!!cp ('t103'); |
push @{$self->{open_elements}}, |
| 2234 |
} |
[$self->{head_element}, $el_category->{head}]; |
| 2235 |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
$self->{head_element_inserted} = 1; |
| 2236 |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
} else { |
| 2237 |
pop @{$self->{open_elements}} # <head> |
!!!cp ('t103'); |
| 2238 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
} |
| 2239 |
!!!ack ('t103.1'); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 2240 |
!!!next-token; |
pop @{$self->{open_elements}}; |
| 2241 |
next B; |
pop @{$self->{open_elements}} # <head> |
| 2242 |
} elsif ($token->{tag_name} eq 'meta') { |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 2243 |
## NOTE: There is a "as if in head" code clone. |
!!!ack ('t103.1'); |
| 2244 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
!!!next-token; |
| 2245 |
!!!cp ('t104'); |
next B; |
| 2246 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
} elsif ($token->{tag_name} eq 'command') { |
| 2247 |
push @{$self->{open_elements}}, |
if ($self->{insertion_mode} == IN_HEAD_IM) { |
| 2248 |
[$self->{head_element}, $el_category->{head}]; |
## NOTE: If the insertion mode at the time of the emission |
| 2249 |
} else { |
## of the token was "before head", $self->{insertion_mode} |
| 2250 |
!!!cp ('t105'); |
## is already changed to |IN_HEAD_IM|. |
| 2251 |
} |
|
| 2252 |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
## NOTE: There is a "as if in head" code clone. |
| 2253 |
my $meta_el = pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 2254 |
|
pop @{$self->{open_elements}}; |
| 2255 |
|
pop @{$self->{open_elements}} # <head> |
| 2256 |
|
if $self->{insertion_mode} == AFTER_HEAD_IM; |
| 2257 |
|
!!!ack ('t103.2'); |
| 2258 |
|
!!!next-token; |
| 2259 |
|
next B; |
| 2260 |
|
} else { |
| 2261 |
|
## NOTE: "in head noscript" or "after head" insertion mode |
| 2262 |
|
## - in these cases, these tags are treated as same as |
| 2263 |
|
## normal in-body tags. |
| 2264 |
|
!!!cp ('t103.3'); |
| 2265 |
|
# |
| 2266 |
|
} |
| 2267 |
|
} elsif ($token->{tag_name} eq 'meta') { |
| 2268 |
|
## NOTE: There is a "as if in head" code clone. |
| 2269 |
|
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2270 |
|
!!!cp ('t104'); |
| 2271 |
|
!!!parse-error (type => 'after head', |
| 2272 |
|
text => $token->{tag_name}, token => $token); |
| 2273 |
|
push @{$self->{open_elements}}, |
| 2274 |
|
[$self->{head_element}, $el_category->{head}]; |
| 2275 |
|
$self->{head_element_inserted} = 1; |
| 2276 |
|
} else { |
| 2277 |
|
!!!cp ('t105'); |
| 2278 |
|
} |
| 2279 |
|
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 2280 |
|
my $meta_el = pop @{$self->{open_elements}}; |
| 2281 |
|
|
| 2282 |
unless ($self->{confident}) { |
unless ($self->{confident}) { |
| 2283 |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
if ($token->{attributes}->{charset}) { |
| 2284 |
!!!cp ('t106'); |
!!!cp ('t106'); |
| 2285 |
|
## NOTE: Whether the encoding is supported or not is handled |
| 2286 |
|
## in the {change_encoding} callback. |
| 2287 |
$self->{change_encoding} |
$self->{change_encoding} |
| 2288 |
->($self, $token->{attributes}->{charset}->{value}, |
->($self, $token->{attributes}->{charset}->{value}, |
| 2289 |
$token); |
$token); |
| 2293 |
$token->{attributes}->{charset} |
$token->{attributes}->{charset} |
| 2294 |
->{has_reference}); |
->{has_reference}); |
| 2295 |
} elsif ($token->{attributes}->{content}) { |
} elsif ($token->{attributes}->{content}) { |
|
## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition. |
|
| 2296 |
if ($token->{attributes}->{content}->{value} |
if ($token->{attributes}->{content}->{value} |
| 2297 |
=~ /\A[^;]*;[\x09-\x0D\x20]*[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
=~ /[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
| 2298 |
[\x09-\x0D\x20]*= |
[\x09\x0A\x0C\x0D\x20]*= |
| 2299 |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
[\x09\x0A\x0C\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
| 2300 |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
([^"'\x09\x0A\x0C\x0D\x20] |
| 2301 |
|
[^\x09\x0A\x0C\x0D\x20\x3B]*))/x) { |
| 2302 |
!!!cp ('t107'); |
!!!cp ('t107'); |
| 2303 |
|
## NOTE: Whether the encoding is supported or not is handled |
| 2304 |
|
## in the {change_encoding} callback. |
| 2305 |
$self->{change_encoding} |
$self->{change_encoding} |
| 2306 |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3, |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3, |
| 2307 |
$token); |
$token); |
| 2335 |
!!!ack ('t110.1'); |
!!!ack ('t110.1'); |
| 2336 |
!!!next-token; |
!!!next-token; |
| 2337 |
next B; |
next B; |
| 2338 |
} elsif ($token->{tag_name} eq 'title') { |
} elsif ($token->{tag_name} eq 'title') { |
| 2339 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2340 |
!!!cp ('t111'); |
!!!cp ('t111'); |
| 2341 |
## As if </noscript> |
## As if </noscript> |
| 2342 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2343 |
!!!parse-error (type => 'in noscript:title', token => $token); |
!!!parse-error (type => 'in noscript', text => 'title', |
| 2344 |
|
token => $token); |
| 2345 |
$self->{insertion_mode} = IN_HEAD_IM; |
|
| 2346 |
## Reprocess in the "in head" insertion mode... |
$self->{insertion_mode} = IN_HEAD_IM; |
| 2347 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
## Reprocess in the "in head" insertion mode... |
| 2348 |
!!!cp ('t112'); |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2349 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!cp ('t112'); |
| 2350 |
push @{$self->{open_elements}}, |
!!!parse-error (type => 'after head', |
| 2351 |
[$self->{head_element}, $el_category->{head}]; |
text => $token->{tag_name}, token => $token); |
| 2352 |
} else { |
push @{$self->{open_elements}}, |
| 2353 |
!!!cp ('t113'); |
[$self->{head_element}, $el_category->{head}]; |
| 2354 |
} |
$self->{head_element_inserted} = 1; |
| 2355 |
|
} else { |
| 2356 |
|
!!!cp ('t113'); |
| 2357 |
|
} |
| 2358 |
|
|
| 2359 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 2360 |
my $parent = defined $self->{head_element} ? $self->{head_element} |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
| 2361 |
: $self->{open_elements}->[-1]->[0]; |
|
| 2362 |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
## NOTE: At this point the stack of open elements contain |
| 2363 |
pop @{$self->{open_elements}} # <head> |
## the |head| element (index == -2) and the |script| element |
| 2364 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
## (index == -1). In the "after head" insertion mode the |
| 2365 |
next B; |
## |head| element is inserted only for the purpose of |
| 2366 |
} elsif ($token->{tag_name} eq 'style') { |
## providing the context for the |script| element, and |
| 2367 |
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
## therefore we can now and have to remove the element from |
| 2368 |
## insertion mode IN_HEAD_IM) |
## the stack. |
| 2369 |
## NOTE: There is a "as if in head" code clone. |
splice @{$self->{open_elements}}, -2, 1, () # <head> |
| 2370 |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
if ($self->{insertion_mode} & IM_MASK) == AFTER_HEAD_IM; |
| 2371 |
!!!cp ('t114'); |
next B; |
| 2372 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
} elsif ($token->{tag_name} eq 'style' or |
| 2373 |
push @{$self->{open_elements}}, |
$token->{tag_name} eq 'noframes') { |
| 2374 |
[$self->{head_element}, $el_category->{head}]; |
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
| 2375 |
} else { |
## insertion mode IN_HEAD_IM) |
| 2376 |
!!!cp ('t115'); |
## NOTE: There is a "as if in head" code clone. |
| 2377 |
} |
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2378 |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
!!!cp ('t114'); |
| 2379 |
pop @{$self->{open_elements}} # <head> |
!!!parse-error (type => 'after head', |
| 2380 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
text => $token->{tag_name}, token => $token); |
| 2381 |
next B; |
push @{$self->{open_elements}}, |
| 2382 |
} elsif ($token->{tag_name} eq 'noscript') { |
[$self->{head_element}, $el_category->{head}]; |
| 2383 |
|
$self->{head_element_inserted} = 1; |
| 2384 |
|
} else { |
| 2385 |
|
!!!cp ('t115'); |
| 2386 |
|
} |
| 2387 |
|
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 2388 |
|
## ISSUE: A spec bug [Bug 6038] |
| 2389 |
|
splice @{$self->{open_elements}}, -2, 1, () # <head> |
| 2390 |
|
if ($self->{insertion_mode} & IM_MASK) == AFTER_HEAD_IM; |
| 2391 |
|
next B; |
| 2392 |
|
} elsif ($token->{tag_name} eq 'noscript') { |
| 2393 |
if ($self->{insertion_mode} == IN_HEAD_IM) { |
if ($self->{insertion_mode} == IN_HEAD_IM) { |
| 2394 |
!!!cp ('t116'); |
!!!cp ('t116'); |
| 2395 |
## NOTE: and scripting is disalbed |
## NOTE: and scripting is disalbed |
| 2400 |
next B; |
next B; |
| 2401 |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2402 |
!!!cp ('t117'); |
!!!cp ('t117'); |
| 2403 |
!!!parse-error (type => 'in noscript:noscript', token => $token); |
!!!parse-error (type => 'in noscript', text => 'noscript', |
| 2404 |
|
token => $token); |
| 2405 |
## Ignore the token |
## Ignore the token |
| 2406 |
!!!nack ('t117.1'); |
!!!nack ('t117.1'); |
| 2407 |
!!!next-token; |
!!!next-token; |
| 2410 |
!!!cp ('t118'); |
!!!cp ('t118'); |
| 2411 |
# |
# |
| 2412 |
} |
} |
| 2413 |
} elsif ($token->{tag_name} eq 'script') { |
} elsif ($token->{tag_name} eq 'script') { |
| 2414 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2415 |
!!!cp ('t119'); |
!!!cp ('t119'); |
| 2416 |
## As if </noscript> |
## As if </noscript> |
| 2417 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2418 |
!!!parse-error (type => 'in noscript:script', token => $token); |
!!!parse-error (type => 'in noscript', text => 'script', |
| 2419 |
|
token => $token); |
| 2420 |
$self->{insertion_mode} = IN_HEAD_IM; |
|
| 2421 |
## Reprocess in the "in head" insertion mode... |
$self->{insertion_mode} = IN_HEAD_IM; |
| 2422 |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
## Reprocess in the "in head" insertion mode... |
| 2423 |
!!!cp ('t120'); |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2424 |
!!!parse-error (type => 'after head:'.$token->{tag_name}, token => $token); |
!!!cp ('t120'); |
| 2425 |
push @{$self->{open_elements}}, |
!!!parse-error (type => 'after head', |
| 2426 |
[$self->{head_element}, $el_category->{head}]; |
text => $token->{tag_name}, token => $token); |
| 2427 |
} else { |
push @{$self->{open_elements}}, |
| 2428 |
!!!cp ('t121'); |
[$self->{head_element}, $el_category->{head}]; |
| 2429 |
} |
$self->{head_element_inserted} = 1; |
| 2430 |
|
} else { |
| 2431 |
|
!!!cp ('t121'); |
| 2432 |
|
} |
| 2433 |
|
|
| 2434 |
## NOTE: There is a "as if in head" code clone. |
## NOTE: There is a "as if in head" code clone. |
| 2435 |
$script_start_tag->(); |
$script_start_tag->(); |
| 2436 |
pop @{$self->{open_elements}} # <head> |
## ISSUE: A spec bug [Bug 6038] |
| 2437 |
if $self->{insertion_mode} == AFTER_HEAD_IM; |
splice @{$self->{open_elements}}, -2, 1 # <head> |
| 2438 |
next B; |
if ($self->{insertion_mode} & IM_MASK) == AFTER_HEAD_IM; |
| 2439 |
} elsif ($token->{tag_name} eq 'body' or |
next B; |
| 2440 |
$token->{tag_name} eq 'frameset') { |
} elsif ($token->{tag_name} eq 'body' or |
| 2441 |
|
$token->{tag_name} eq 'frameset') { |
| 2442 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2443 |
!!!cp ('t122'); |
!!!cp ('t122'); |
| 2444 |
## As if </noscript> |
## As if </noscript> |
| 2445 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2446 |
!!!parse-error (type => 'in noscript:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in noscript', |
| 2447 |
|
text => $token->{tag_name}, token => $token); |
| 2448 |
|
|
| 2449 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 2450 |
## As if </head> |
## As if </head> |
| 2483 |
!!!cp ('t129'); |
!!!cp ('t129'); |
| 2484 |
## As if </noscript> |
## As if </noscript> |
| 2485 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2486 |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in noscript:/', |
| 2487 |
|
text => $token->{tag_name}, token => $token); |
| 2488 |
|
|
| 2489 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 2490 |
## As if </head> |
## As if </head> |
| 2527 |
!!!cp ('t133'); |
!!!cp ('t133'); |
| 2528 |
## As if </noscript> |
## As if </noscript> |
| 2529 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2530 |
!!!parse-error (type => 'in noscript:/head', token => $token); |
!!!parse-error (type => 'in noscript:/', |
| 2531 |
|
text => 'head', token => $token); |
| 2532 |
|
|
| 2533 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 2534 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2541 |
$self->{insertion_mode} = AFTER_HEAD_IM; |
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 2542 |
!!!next-token; |
!!!next-token; |
| 2543 |
next B; |
next B; |
| 2544 |
|
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2545 |
|
!!!cp ('t134.1'); |
| 2546 |
|
!!!parse-error (type => 'unmatched end tag', text => 'head', |
| 2547 |
|
token => $token); |
| 2548 |
|
## Ignore the token |
| 2549 |
|
!!!next-token; |
| 2550 |
|
next B; |
| 2551 |
} else { |
} else { |
| 2552 |
!!!cp ('t135'); |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
|
# |
|
| 2553 |
} |
} |
| 2554 |
} elsif ($token->{tag_name} eq 'noscript') { |
} elsif ($token->{tag_name} eq 'noscript') { |
| 2555 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2558 |
$self->{insertion_mode} = IN_HEAD_IM; |
$self->{insertion_mode} = IN_HEAD_IM; |
| 2559 |
!!!next-token; |
!!!next-token; |
| 2560 |
next B; |
next B; |
| 2561 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM or |
| 2562 |
|
$self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2563 |
!!!cp ('t137'); |
!!!cp ('t137'); |
| 2564 |
!!!parse-error (type => 'unmatched end tag:noscript', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 2565 |
|
text => 'noscript', token => $token); |
| 2566 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 2567 |
!!!next-token; |
!!!next-token; |
| 2568 |
next B; |
next B; |
| 2573 |
} elsif ({ |
} elsif ({ |
| 2574 |
body => 1, html => 1, |
body => 1, html => 1, |
| 2575 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 2576 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
## TODO: This branch is entirely redundant. |
| 2577 |
!!!cp ('t139'); |
if ($self->{insertion_mode} == BEFORE_HEAD_IM or |
| 2578 |
## As if <head> |
$self->{insertion_mode} == IN_HEAD_IM or |
| 2579 |
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
$self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
|
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
|
|
push @{$self->{open_elements}}, |
|
|
[$self->{head_element}, $el_category->{head}]; |
|
|
|
|
|
$self->{insertion_mode} = IN_HEAD_IM; |
|
|
## Reprocess in the "in head" insertion mode... |
|
|
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
|
| 2580 |
!!!cp ('t140'); |
!!!cp ('t140'); |
| 2581 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 2582 |
|
text => $token->{tag_name}, token => $token); |
| 2583 |
## Ignore the token |
## Ignore the token |
| 2584 |
!!!next-token; |
!!!next-token; |
| 2585 |
next B; |
next B; |
| 2586 |
} else { |
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2587 |
!!!cp ('t141'); |
!!!cp ('t140.1'); |
| 2588 |
} |
!!!parse-error (type => 'unmatched end tag', |
| 2589 |
|
text => $token->{tag_name}, token => $token); |
|
# |
|
|
} elsif ({ |
|
|
p => 1, br => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
|
|
!!!cp ('t142'); |
|
|
## As if <head> |
|
|
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
|
|
push @{$self->{open_elements}}, |
|
|
[$self->{head_element}, $el_category->{head}]; |
|
|
|
|
|
$self->{insertion_mode} = IN_HEAD_IM; |
|
|
## Reprocess in the "in head" insertion mode... |
|
|
} else { |
|
|
!!!cp ('t143'); |
|
|
} |
|
|
|
|
|
# |
|
|
} else { |
|
|
if ($self->{insertion_mode} == AFTER_HEAD_IM) { |
|
|
!!!cp ('t144'); |
|
|
# |
|
|
} else { |
|
|
!!!cp ('t145'); |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
|
| 2590 |
## Ignore the token |
## Ignore the token |
| 2591 |
!!!next-token; |
!!!next-token; |
| 2592 |
next B; |
next B; |
| 2593 |
|
} else { |
| 2594 |
|
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
| 2595 |
} |
} |
| 2596 |
|
} elsif ($token->{tag_name} eq 'p') { |
| 2597 |
|
!!!cp ('t142'); |
| 2598 |
|
!!!parse-error (type => 'unmatched end tag', |
| 2599 |
|
text => $token->{tag_name}, token => $token); |
| 2600 |
|
## Ignore the token |
| 2601 |
|
!!!next-token; |
| 2602 |
|
next B; |
| 2603 |
|
} elsif ($token->{tag_name} eq 'br') { |
| 2604 |
|
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 2605 |
|
!!!cp ('t142.2'); |
| 2606 |
|
## (before head) as if <head>, (in head) as if </head> |
| 2607 |
|
!!!create-element ($self->{head_element}, $HTML_NS, 'head',, $token); |
| 2608 |
|
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 2609 |
|
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 2610 |
|
|
| 2611 |
|
## Reprocess in the "after head" insertion mode... |
| 2612 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_IM) { |
| 2613 |
|
!!!cp ('t143.2'); |
| 2614 |
|
## As if </head> |
| 2615 |
|
pop @{$self->{open_elements}}; |
| 2616 |
|
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 2617 |
|
|
| 2618 |
|
## Reprocess in the "after head" insertion mode... |
| 2619 |
|
} elsif ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2620 |
|
!!!cp ('t143.3'); |
| 2621 |
|
## NOTE: Two parse errors for <head><noscript></br> |
| 2622 |
|
!!!parse-error (type => 'unmatched end tag', |
| 2623 |
|
text => 'br', token => $token); |
| 2624 |
|
## As if </noscript> |
| 2625 |
|
pop @{$self->{open_elements}}; |
| 2626 |
|
$self->{insertion_mode} = IN_HEAD_IM; |
| 2627 |
|
|
| 2628 |
|
## Reprocess in the "in head" insertion mode... |
| 2629 |
|
## As if </head> |
| 2630 |
|
pop @{$self->{open_elements}}; |
| 2631 |
|
$self->{insertion_mode} = AFTER_HEAD_IM; |
| 2632 |
|
|
| 2633 |
|
## Reprocess in the "after head" insertion mode... |
| 2634 |
|
} elsif ($self->{insertion_mode} == AFTER_HEAD_IM) { |
| 2635 |
|
!!!cp ('t143.4'); |
| 2636 |
|
# |
| 2637 |
|
} else { |
| 2638 |
|
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
| 2639 |
|
} |
| 2640 |
|
|
| 2641 |
|
# |
| 2642 |
|
} else { ## Other end tags |
| 2643 |
|
!!!cp ('t145'); |
| 2644 |
|
!!!parse-error (type => 'unmatched end tag', |
| 2645 |
|
text => $token->{tag_name}, token => $token); |
| 2646 |
|
## Ignore the token |
| 2647 |
|
!!!next-token; |
| 2648 |
|
next B; |
| 2649 |
} |
} |
| 2650 |
|
|
| 2651 |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
if ($self->{insertion_mode} == IN_HEAD_NOSCRIPT_IM) { |
| 2652 |
!!!cp ('t146'); |
!!!cp ('t146'); |
| 2653 |
## As if </noscript> |
## As if </noscript> |
| 2654 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2655 |
!!!parse-error (type => 'in noscript:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in noscript:/', |
| 2656 |
|
text => $token->{tag_name}, token => $token); |
| 2657 |
|
|
| 2658 |
## Reprocess in the "in head" insertion mode... |
## Reprocess in the "in head" insertion mode... |
| 2659 |
## As if </head> |
## As if </head> |
| 2669 |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
} elsif ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 2670 |
## ISSUE: This case cannot be reached? |
## ISSUE: This case cannot be reached? |
| 2671 |
!!!cp ('t148'); |
!!!cp ('t148'); |
| 2672 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 2673 |
|
text => $token->{tag_name}, token => $token); |
| 2674 |
## Ignore the token ## ISSUE: An issue in the spec. |
## Ignore the token ## ISSUE: An issue in the spec. |
| 2675 |
!!!next-token; |
!!!next-token; |
| 2676 |
next B; |
next B; |
| 2683 |
!!!insert-element ('body',, $token); |
!!!insert-element ('body',, $token); |
| 2684 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 2685 |
## reprocess |
## reprocess |
| 2686 |
next B; |
next B; |
| 2687 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 2688 |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
if ($self->{insertion_mode} == BEFORE_HEAD_IM) { |
| 2689 |
!!!cp ('t149.1'); |
!!!cp ('t149.1'); |
| 2741 |
} else { |
} else { |
| 2742 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 2743 |
} |
} |
|
|
|
|
## ISSUE: An issue in the spec. |
|
| 2744 |
} elsif ($self->{insertion_mode} & BODY_IMS) { |
} elsif ($self->{insertion_mode} & BODY_IMS) { |
| 2745 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 2746 |
!!!cp ('t150'); |
!!!cp ('t150'); |
| 2756 |
caption => 1, col => 1, colgroup => 1, tbody => 1, |
caption => 1, col => 1, colgroup => 1, tbody => 1, |
| 2757 |
td => 1, tfoot => 1, th => 1, thead => 1, tr => 1, |
td => 1, tfoot => 1, th => 1, thead => 1, tr => 1, |
| 2758 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 2759 |
if ($self->{insertion_mode} == IN_CELL_IM) { |
if (($self->{insertion_mode} & IM_MASK) == IN_CELL_IM) { |
| 2760 |
## have an element in table scope |
## have an element in table scope |
| 2761 |
for (reverse 0..$#{$self->{open_elements}}) { |
for (reverse 0..$#{$self->{open_elements}}) { |
| 2762 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 2763 |
if ($node->[1] & TABLE_CELL_EL) { |
if ($node->[1] == TABLE_CELL_EL) { |
| 2764 |
!!!cp ('t151'); |
!!!cp ('t151'); |
| 2765 |
|
|
| 2766 |
## Close the cell |
## Close the cell |
| 2779 |
|
|
| 2780 |
!!!cp ('t153'); |
!!!cp ('t153'); |
| 2781 |
!!!parse-error (type => 'start tag not allowed', |
!!!parse-error (type => 'start tag not allowed', |
| 2782 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 2783 |
## Ignore the token |
## Ignore the token |
| 2784 |
!!!nack ('t153.1'); |
!!!nack ('t153.1'); |
| 2785 |
!!!next-token; |
!!!next-token; |
| 2786 |
next B; |
next B; |
| 2787 |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
} elsif (($self->{insertion_mode} & IM_MASK) == IN_CAPTION_IM) { |
| 2788 |
!!!parse-error (type => 'not closed:caption', token => $token); |
!!!parse-error (type => 'not closed', text => 'caption', |
| 2789 |
|
token => $token); |
| 2790 |
|
|
| 2791 |
## NOTE: As if </caption>. |
## NOTE: As if </caption>. |
| 2792 |
## have a table element in table scope |
## have a table element in table scope |
| 2794 |
INSCOPE: { |
INSCOPE: { |
| 2795 |
for (reverse 0..$#{$self->{open_elements}}) { |
for (reverse 0..$#{$self->{open_elements}}) { |
| 2796 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 2797 |
if ($node->[1] & CAPTION_EL) { |
if ($node->[1] == CAPTION_EL) { |
| 2798 |
!!!cp ('t155'); |
!!!cp ('t155'); |
| 2799 |
$i = $_; |
$i = $_; |
| 2800 |
last INSCOPE; |
last INSCOPE; |
| 2806 |
|
|
| 2807 |
!!!cp ('t157'); |
!!!cp ('t157'); |
| 2808 |
!!!parse-error (type => 'start tag not allowed', |
!!!parse-error (type => 'start tag not allowed', |
| 2809 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 2810 |
## Ignore the token |
## Ignore the token |
| 2811 |
!!!nack ('t157.1'); |
!!!nack ('t157.1'); |
| 2812 |
!!!next-token; |
!!!next-token; |
| 2820 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2821 |
} |
} |
| 2822 |
|
|
| 2823 |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
unless ($self->{open_elements}->[-1]->[1] == CAPTION_EL) { |
| 2824 |
!!!cp ('t159'); |
!!!cp ('t159'); |
| 2825 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 2826 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 2827 |
->manakai_local_name, |
->manakai_local_name, |
| 2828 |
token => $token); |
token => $token); |
| 2829 |
} else { |
} else { |
| 2849 |
} |
} |
| 2850 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 2851 |
if ($token->{tag_name} eq 'td' or $token->{tag_name} eq 'th') { |
if ($token->{tag_name} eq 'td' or $token->{tag_name} eq 'th') { |
| 2852 |
if ($self->{insertion_mode} == IN_CELL_IM) { |
if (($self->{insertion_mode} & IM_MASK) == IN_CELL_IM) { |
| 2853 |
## have an element in table scope |
## have an element in table scope |
| 2854 |
my $i; |
my $i; |
| 2855 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 2865 |
} # INSCOPE |
} # INSCOPE |
| 2866 |
unless (defined $i) { |
unless (defined $i) { |
| 2867 |
!!!cp ('t165'); |
!!!cp ('t165'); |
| 2868 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 2869 |
|
text => $token->{tag_name}, |
| 2870 |
|
token => $token); |
| 2871 |
## Ignore the token |
## Ignore the token |
| 2872 |
!!!next-token; |
!!!next-token; |
| 2873 |
next B; |
next B; |
| 2884 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 2885 |
!!!cp ('t167'); |
!!!cp ('t167'); |
| 2886 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 2887 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 2888 |
->manakai_local_name, |
->manakai_local_name, |
| 2889 |
token => $token); |
token => $token); |
| 2890 |
} else { |
} else { |
| 2899 |
|
|
| 2900 |
!!!next-token; |
!!!next-token; |
| 2901 |
next B; |
next B; |
| 2902 |
} elsif ($self->{insertion_mode} == IN_CAPTION_IM) { |
} elsif (($self->{insertion_mode} & IM_MASK) == IN_CAPTION_IM) { |
| 2903 |
!!!cp ('t169'); |
!!!cp ('t169'); |
| 2904 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 2905 |
|
text => $token->{tag_name}, token => $token); |
| 2906 |
## Ignore the token |
## Ignore the token |
| 2907 |
!!!next-token; |
!!!next-token; |
| 2908 |
next B; |
next B; |
| 2911 |
# |
# |
| 2912 |
} |
} |
| 2913 |
} elsif ($token->{tag_name} eq 'caption') { |
} elsif ($token->{tag_name} eq 'caption') { |
| 2914 |
if ($self->{insertion_mode} == IN_CAPTION_IM) { |
if (($self->{insertion_mode} & IM_MASK) == IN_CAPTION_IM) { |
| 2915 |
## have a table element in table scope |
## have a table element in table scope |
| 2916 |
my $i; |
my $i; |
| 2917 |
INSCOPE: { |
INSCOPE: { |
| 2918 |
for (reverse 0..$#{$self->{open_elements}}) { |
for (reverse 0..$#{$self->{open_elements}}) { |
| 2919 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 2920 |
if ($node->[1] & CAPTION_EL) { |
if ($node->[1] == CAPTION_EL) { |
| 2921 |
!!!cp ('t171'); |
!!!cp ('t171'); |
| 2922 |
$i = $_; |
$i = $_; |
| 2923 |
last INSCOPE; |
last INSCOPE; |
| 2929 |
|
|
| 2930 |
!!!cp ('t173'); |
!!!cp ('t173'); |
| 2931 |
!!!parse-error (type => 'unmatched end tag', |
!!!parse-error (type => 'unmatched end tag', |
| 2932 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 2933 |
## Ignore the token |
## Ignore the token |
| 2934 |
!!!next-token; |
!!!next-token; |
| 2935 |
next B; |
next B; |
| 2942 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 2943 |
} |
} |
| 2944 |
|
|
| 2945 |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
unless ($self->{open_elements}->[-1]->[1] == CAPTION_EL) { |
| 2946 |
!!!cp ('t175'); |
!!!cp ('t175'); |
| 2947 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 2948 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 2949 |
->manakai_local_name, |
->manakai_local_name, |
| 2950 |
token => $token); |
token => $token); |
| 2951 |
} else { |
} else { |
| 2960 |
|
|
| 2961 |
!!!next-token; |
!!!next-token; |
| 2962 |
next B; |
next B; |
| 2963 |
} elsif ($self->{insertion_mode} == IN_CELL_IM) { |
} elsif (($self->{insertion_mode} & IM_MASK) == IN_CELL_IM) { |
| 2964 |
!!!cp ('t177'); |
!!!cp ('t177'); |
| 2965 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 2966 |
|
text => $token->{tag_name}, token => $token); |
| 2967 |
## Ignore the token |
## Ignore the token |
| 2968 |
!!!next-token; |
!!!next-token; |
| 2969 |
next B; |
next B; |
| 2975 |
table => 1, tbody => 1, tfoot => 1, |
table => 1, tbody => 1, tfoot => 1, |
| 2976 |
thead => 1, tr => 1, |
thead => 1, tr => 1, |
| 2977 |
}->{$token->{tag_name}} and |
}->{$token->{tag_name}} and |
| 2978 |
$self->{insertion_mode} == IN_CELL_IM) { |
($self->{insertion_mode} & IM_MASK) == IN_CELL_IM) { |
| 2979 |
## have an element in table scope |
## have an element in table scope |
| 2980 |
my $i; |
my $i; |
| 2981 |
my $tn; |
my $tn; |
| 2992 |
line => $token->{line}, |
line => $token->{line}, |
| 2993 |
column => $token->{column}}; |
column => $token->{column}}; |
| 2994 |
next B; |
next B; |
| 2995 |
} elsif ($node->[1] & TABLE_CELL_EL) { |
} elsif ($node->[1] == TABLE_CELL_EL) { |
| 2996 |
!!!cp ('t180'); |
!!!cp ('t180'); |
| 2997 |
$tn = $node->[0]->manakai_local_name; |
$tn = $node->[0]->manakai_local_name; |
| 2998 |
## NOTE: There is exactly one |td| or |th| element |
## NOTE: There is exactly one |td| or |th| element |
| 3006 |
|
|
| 3007 |
!!!cp ('t182'); |
!!!cp ('t182'); |
| 3008 |
!!!parse-error (type => 'unmatched end tag', |
!!!parse-error (type => 'unmatched end tag', |
| 3009 |
value => $token->{tag_name}, token => $token); |
text => $token->{tag_name}, token => $token); |
| 3010 |
## Ignore the token |
## Ignore the token |
| 3011 |
!!!next-token; |
!!!next-token; |
| 3012 |
next B; |
next B; |
| 3013 |
} # INSCOPE |
} # INSCOPE |
| 3014 |
} elsif ($token->{tag_name} eq 'table' and |
} elsif ($token->{tag_name} eq 'table' and |
| 3015 |
$self->{insertion_mode} == IN_CAPTION_IM) { |
($self->{insertion_mode} & IM_MASK) == IN_CAPTION_IM) { |
| 3016 |
!!!parse-error (type => 'not closed:caption', token => $token); |
!!!parse-error (type => 'not closed', text => 'caption', |
| 3017 |
|
token => $token); |
| 3018 |
|
|
| 3019 |
## As if </caption> |
## As if </caption> |
| 3020 |
## have a table element in table scope |
## have a table element in table scope |
| 3021 |
my $i; |
my $i; |
| 3022 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3023 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 3024 |
if ($node->[1] & CAPTION_EL) { |
if ($node->[1] == CAPTION_EL) { |
| 3025 |
!!!cp ('t184'); |
!!!cp ('t184'); |
| 3026 |
$i = $_; |
$i = $_; |
| 3027 |
last INSCOPE; |
last INSCOPE; |
| 3032 |
} # INSCOPE |
} # INSCOPE |
| 3033 |
unless (defined $i) { |
unless (defined $i) { |
| 3034 |
!!!cp ('t186'); |
!!!cp ('t186'); |
| 3035 |
!!!parse-error (type => 'unmatched end tag:caption', token => $token); |
## TODO: Wrong error type? |
| 3036 |
|
!!!parse-error (type => 'unmatched end tag', |
| 3037 |
|
text => 'caption', token => $token); |
| 3038 |
## Ignore the token |
## Ignore the token |
| 3039 |
!!!next-token; |
!!!next-token; |
| 3040 |
next B; |
next B; |
| 3046 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3047 |
} |
} |
| 3048 |
|
|
| 3049 |
unless ($self->{open_elements}->[-1]->[1] & CAPTION_EL) { |
unless ($self->{open_elements}->[-1]->[1] == CAPTION_EL) { |
| 3050 |
!!!cp ('t188'); |
!!!cp ('t188'); |
| 3051 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 3052 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 3053 |
->manakai_local_name, |
->manakai_local_name, |
| 3054 |
token => $token); |
token => $token); |
| 3055 |
} else { |
} else { |
| 3069 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 3070 |
if ($self->{insertion_mode} & BODY_TABLE_IMS) { |
if ($self->{insertion_mode} & BODY_TABLE_IMS) { |
| 3071 |
!!!cp ('t190'); |
!!!cp ('t190'); |
| 3072 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 3073 |
|
text => $token->{tag_name}, token => $token); |
| 3074 |
## Ignore the token |
## Ignore the token |
| 3075 |
!!!next-token; |
!!!next-token; |
| 3076 |
next B; |
next B; |
| 3078 |
!!!cp ('t191'); |
!!!cp ('t191'); |
| 3079 |
# |
# |
| 3080 |
} |
} |
| 3081 |
} elsif ({ |
} elsif ({ |
| 3082 |
tbody => 1, tfoot => 1, |
tbody => 1, tfoot => 1, |
| 3083 |
thead => 1, tr => 1, |
thead => 1, tr => 1, |
| 3084 |
}->{$token->{tag_name}} and |
}->{$token->{tag_name}} and |
| 3085 |
$self->{insertion_mode} == IN_CAPTION_IM) { |
($self->{insertion_mode} & IM_MASK) == IN_CAPTION_IM) { |
| 3086 |
!!!cp ('t192'); |
!!!cp ('t192'); |
| 3087 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 3088 |
## Ignore the token |
text => $token->{tag_name}, token => $token); |
| 3089 |
!!!next-token; |
## Ignore the token |
| 3090 |
next B; |
!!!next-token; |
| 3091 |
} else { |
next B; |
| 3092 |
!!!cp ('t193'); |
} else { |
| 3093 |
# |
!!!cp ('t193'); |
| 3094 |
} |
# |
| 3095 |
|
} |
| 3096 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 3097 |
for my $entry (@{$self->{open_elements}}) { |
for my $entry (@{$self->{open_elements}}) { |
| 3098 |
unless ($entry->[1] & ALL_END_TAG_OPTIONAL_EL) { |
unless ($entry->[1] & ALL_END_TAG_OPTIONAL_EL) { |
| 3111 |
$insert = $insert_to_current; |
$insert = $insert_to_current; |
| 3112 |
# |
# |
| 3113 |
} elsif ($self->{insertion_mode} & TABLE_IMS) { |
} elsif ($self->{insertion_mode} & TABLE_IMS) { |
| 3114 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == START_TAG_TOKEN) { |
| 3115 |
if (not $open_tables->[-1]->[1] and # tainted |
if ({ |
| 3116 |
$token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
tr => (($self->{insertion_mode} & IM_MASK) != IN_ROW_IM), |
| 3117 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
th => 1, td => 1, |
| 3118 |
|
}->{$token->{tag_name}}) { |
| 3119 |
unless (length $token->{data}) { |
if (($self->{insertion_mode} & IM_MASK) == IN_TABLE_IM) { |
| 3120 |
!!!cp ('t194'); |
## Clear back to table context |
| 3121 |
!!!next-token; |
while (not ($self->{open_elements}->[-1]->[1] |
| 3122 |
next B; |
& TABLE_SCOPING_EL)) { |
| 3123 |
} else { |
!!!cp ('t201'); |
| 3124 |
!!!cp ('t195'); |
pop @{$self->{open_elements}}; |
| 3125 |
} |
} |
|
} |
|
|
|
|
|
!!!parse-error (type => 'in table:#character', token => $token); |
|
|
|
|
|
## As if in body, but insert into foster parent element |
|
|
## ISSUE: Spec says that "whenever a node would be inserted |
|
|
## into the current node" while characters might not be |
|
|
## result in a new Text node. |
|
|
$reconstruct_active_formatting_elements->($insert_to_foster); |
|
|
|
|
|
if ($self->{open_elements}->[-1]->[1] & TABLE_ROWS_EL) { |
|
|
# MUST |
|
|
my $foster_parent_element; |
|
|
my $next_sibling; |
|
|
my $prev_sibling; |
|
|
OE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
if ($self->{open_elements}->[$_]->[1] & TABLE_EL) { |
|
|
my $parent = $self->{open_elements}->[$_]->[0]->parent_node; |
|
|
if (defined $parent and $parent->node_type == 1) { |
|
|
!!!cp ('t196'); |
|
|
$foster_parent_element = $parent; |
|
|
$next_sibling = $self->{open_elements}->[$_]->[0]; |
|
|
$prev_sibling = $next_sibling->previous_sibling; |
|
|
} else { |
|
|
!!!cp ('t197'); |
|
|
$foster_parent_element = $self->{open_elements}->[$_ - 1]->[0]; |
|
|
$prev_sibling = $foster_parent_element->last_child; |
|
|
} |
|
|
last OE; |
|
|
} |
|
|
} # OE |
|
|
$foster_parent_element = $self->{open_elements}->[0]->[0] and |
|
|
$prev_sibling = $foster_parent_element->last_child |
|
|
unless defined $foster_parent_element; |
|
|
if (defined $prev_sibling and |
|
|
$prev_sibling->node_type == 3) { |
|
|
!!!cp ('t198'); |
|
|
$prev_sibling->manakai_append_text ($token->{data}); |
|
|
} else { |
|
|
!!!cp ('t199'); |
|
|
$foster_parent_element->insert_before |
|
|
($self->{document}->create_text_node ($token->{data}), |
|
|
$next_sibling); |
|
|
} |
|
|
$open_tables->[-1]->[1] = 1; # tainted |
|
|
} else { |
|
|
!!!cp ('t200'); |
|
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
|
|
} |
|
| 3126 |
|
|
| 3127 |
!!!next-token; |
!!!insert-element ('tbody',, $token); |
| 3128 |
next B; |
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
| 3129 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
## reprocess in the "in table body" insertion mode... |
| 3130 |
if ({ |
} |
| 3131 |
tr => ($self->{insertion_mode} != IN_ROW_IM), |
|
| 3132 |
th => 1, td => 1, |
if (($self->{insertion_mode} & IM_MASK) == IN_TABLE_BODY_IM) { |
| 3133 |
}->{$token->{tag_name}}) { |
unless ($token->{tag_name} eq 'tr') { |
| 3134 |
if ($self->{insertion_mode} == IN_TABLE_IM) { |
!!!cp ('t202'); |
| 3135 |
## Clear back to table context |
!!!parse-error (type => 'missing start tag:tr', token => $token); |
| 3136 |
while (not ($self->{open_elements}->[-1]->[1] |
} |
|
& TABLE_SCOPING_EL)) { |
|
|
!!!cp ('t201'); |
|
|
pop @{$self->{open_elements}}; |
|
|
} |
|
|
|
|
|
!!!insert-element ('tbody',, $token); |
|
|
$self->{insertion_mode} = IN_TABLE_BODY_IM; |
|
|
## reprocess in the "in table body" insertion mode... |
|
|
} |
|
|
|
|
|
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
|
|
unless ($token->{tag_name} eq 'tr') { |
|
|
!!!cp ('t202'); |
|
|
!!!parse-error (type => 'missing start tag:tr', token => $token); |
|
|
} |
|
| 3137 |
|
|
| 3138 |
## Clear back to table body context |
## Clear back to table body context |
| 3139 |
while (not ($self->{open_elements}->[-1]->[1] |
while (not ($self->{open_elements}->[-1]->[1] |
| 3140 |
& TABLE_ROWS_SCOPING_EL)) { |
& TABLE_ROWS_SCOPING_EL)) { |
| 3141 |
!!!cp ('t203'); |
!!!cp ('t203'); |
| 3142 |
## ISSUE: Can this case be reached? |
## ISSUE: Can this case be reached? |
| 3143 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3144 |
} |
} |
| 3145 |
|
|
| 3146 |
$self->{insertion_mode} = IN_ROW_IM; |
$self->{insertion_mode} = IN_ROW_IM; |
| 3147 |
if ($token->{tag_name} eq 'tr') { |
if ($token->{tag_name} eq 'tr') { |
| 3148 |
!!!cp ('t204'); |
!!!cp ('t204'); |
| 3149 |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 3150 |
!!!nack ('t204'); |
$open_tables->[-1]->[2] = 0 if @$open_tables; # ~node inserted |
| 3151 |
!!!next-token; |
!!!nack ('t204'); |
| 3152 |
next B; |
!!!next-token; |
| 3153 |
} else { |
next B; |
| 3154 |
!!!cp ('t205'); |
} else { |
| 3155 |
!!!insert-element ('tr',, $token); |
!!!cp ('t205'); |
| 3156 |
## reprocess in the "in row" insertion mode |
!!!insert-element ('tr',, $token); |
| 3157 |
} |
## reprocess in the "in row" insertion mode |
| 3158 |
} else { |
} |
| 3159 |
!!!cp ('t206'); |
} else { |
| 3160 |
} |
!!!cp ('t206'); |
| 3161 |
|
} |
| 3162 |
|
|
| 3163 |
## Clear back to table row context |
## Clear back to table row context |
| 3164 |
while (not ($self->{open_elements}->[-1]->[1] |
while (not ($self->{open_elements}->[-1]->[1] |
| 3167 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3168 |
} |
} |
| 3169 |
|
|
| 3170 |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 3171 |
$self->{insertion_mode} = IN_CELL_IM; |
$open_tables->[-1]->[2] = 0 if @$open_tables; # ~node inserted |
| 3172 |
|
$self->{insertion_mode} = IN_CELL_IM; |
| 3173 |
|
|
| 3174 |
push @$active_formatting_elements, ['#marker', '']; |
push @$active_formatting_elements, ['#marker', '']; |
| 3175 |
|
|
| 3176 |
!!!nack ('t207.1'); |
!!!nack ('t207.1'); |
| 3177 |
|
!!!next-token; |
| 3178 |
|
next B; |
| 3179 |
|
} elsif ({ |
| 3180 |
|
caption => 1, col => 1, colgroup => 1, |
| 3181 |
|
tbody => 1, tfoot => 1, thead => 1, |
| 3182 |
|
tr => 1, # $self->{insertion_mode} == IN_ROW_IM |
| 3183 |
|
}->{$token->{tag_name}}) { |
| 3184 |
|
if (($self->{insertion_mode} & IM_MASK) == IN_ROW_IM) { |
| 3185 |
|
## As if </tr> |
| 3186 |
|
## have an element in table scope |
| 3187 |
|
my $i; |
| 3188 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3189 |
|
my $node = $self->{open_elements}->[$_]; |
| 3190 |
|
if ($node->[1] == TABLE_ROW_EL) { |
| 3191 |
|
!!!cp ('t208'); |
| 3192 |
|
$i = $_; |
| 3193 |
|
last INSCOPE; |
| 3194 |
|
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
| 3195 |
|
!!!cp ('t209'); |
| 3196 |
|
last INSCOPE; |
| 3197 |
|
} |
| 3198 |
|
} # INSCOPE |
| 3199 |
|
unless (defined $i) { |
| 3200 |
|
!!!cp ('t210'); |
| 3201 |
|
## TODO: This type is wrong. |
| 3202 |
|
!!!parse-error (type => 'unmacthed end tag', |
| 3203 |
|
text => $token->{tag_name}, token => $token); |
| 3204 |
|
## Ignore the token |
| 3205 |
|
!!!nack ('t210.1'); |
| 3206 |
!!!next-token; |
!!!next-token; |
| 3207 |
next B; |
next B; |
| 3208 |
} elsif ({ |
} |
|
caption => 1, col => 1, colgroup => 1, |
|
|
tbody => 1, tfoot => 1, thead => 1, |
|
|
tr => 1, # $self->{insertion_mode} == IN_ROW_IM |
|
|
}->{$token->{tag_name}}) { |
|
|
if ($self->{insertion_mode} == IN_ROW_IM) { |
|
|
## As if </tr> |
|
|
## have an element in table scope |
|
|
my $i; |
|
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
my $node = $self->{open_elements}->[$_]; |
|
|
if ($node->[1] & TABLE_ROW_EL) { |
|
|
!!!cp ('t208'); |
|
|
$i = $_; |
|
|
last INSCOPE; |
|
|
} elsif ($node->[1] & TABLE_SCOPING_EL) { |
|
|
!!!cp ('t209'); |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
unless (defined $i) { |
|
|
!!!cp ('t210'); |
|
|
## TODO: This type is wrong. |
|
|
!!!parse-error (type => 'unmacthed end tag:'.$token->{tag_name}, token => $token); |
|
|
## Ignore the token |
|
|
!!!nack ('t210.1'); |
|
|
!!!next-token; |
|
|
next B; |
|
|
} |
|
| 3209 |
|
|
| 3210 |
## Clear back to table row context |
## Clear back to table row context |
| 3211 |
while (not ($self->{open_elements}->[-1]->[1] |
while (not ($self->{open_elements}->[-1]->[1] |
| 3228 |
} |
} |
| 3229 |
} |
} |
| 3230 |
|
|
| 3231 |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
if (($self->{insertion_mode} & IM_MASK) == IN_TABLE_BODY_IM) { |
| 3232 |
## have an element in table scope |
## have an element in table scope |
| 3233 |
my $i; |
my $i; |
| 3234 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3235 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 3236 |
if ($node->[1] & TABLE_ROW_GROUP_EL) { |
if ($node->[1] == TABLE_ROW_GROUP_EL) { |
| 3237 |
!!!cp ('t214'); |
!!!cp ('t214'); |
| 3238 |
$i = $_; |
$i = $_; |
| 3239 |
last INSCOPE; |
last INSCOPE; |
| 3244 |
} # INSCOPE |
} # INSCOPE |
| 3245 |
unless (defined $i) { |
unless (defined $i) { |
| 3246 |
!!!cp ('t216'); |
!!!cp ('t216'); |
| 3247 |
## TODO: This erorr type ios wrong. |
## TODO: This erorr type is wrong. |
| 3248 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 3249 |
|
text => $token->{tag_name}, token => $token); |
| 3250 |
## Ignore the token |
## Ignore the token |
| 3251 |
!!!nack ('t216.1'); |
!!!nack ('t216.1'); |
| 3252 |
!!!next-token; |
!!!next-token; |
| 3275 |
!!!cp ('t218'); |
!!!cp ('t218'); |
| 3276 |
} |
} |
| 3277 |
|
|
| 3278 |
if ($token->{tag_name} eq 'col') { |
if ($token->{tag_name} eq 'col') { |
| 3279 |
## Clear back to table context |
## Clear back to table context |
| 3280 |
while (not ($self->{open_elements}->[-1]->[1] |
while (not ($self->{open_elements}->[-1]->[1] |
| 3281 |
& TABLE_SCOPING_EL)) { |
& TABLE_SCOPING_EL)) { |
| 3282 |
!!!cp ('t219'); |
!!!cp ('t219'); |
| 3283 |
## ISSUE: Can this state be reached? |
## ISSUE: Can this state be reached? |
| 3284 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3285 |
} |
} |
| 3286 |
|
|
| 3287 |
!!!insert-element ('colgroup',, $token); |
!!!insert-element ('colgroup',, $token); |
| 3288 |
$self->{insertion_mode} = IN_COLUMN_GROUP_IM; |
$self->{insertion_mode} = IN_COLUMN_GROUP_IM; |
| 3289 |
## reprocess |
## reprocess |
| 3290 |
!!!ack-later; |
$open_tables->[-1]->[2] = 0 if @$open_tables; # ~node inserted |
| 3291 |
next B; |
!!!ack-later; |
| 3292 |
} elsif ({ |
next B; |
| 3293 |
caption => 1, |
} elsif ({ |
| 3294 |
colgroup => 1, |
caption => 1, |
| 3295 |
tbody => 1, tfoot => 1, thead => 1, |
colgroup => 1, |
| 3296 |
}->{$token->{tag_name}}) { |
tbody => 1, tfoot => 1, thead => 1, |
| 3297 |
## Clear back to table context |
}->{$token->{tag_name}}) { |
| 3298 |
|
## Clear back to table context |
| 3299 |
while (not ($self->{open_elements}->[-1]->[1] |
while (not ($self->{open_elements}->[-1]->[1] |
| 3300 |
& TABLE_SCOPING_EL)) { |
& TABLE_SCOPING_EL)) { |
| 3301 |
!!!cp ('t220'); |
!!!cp ('t220'); |
| 3303 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3304 |
} |
} |
| 3305 |
|
|
| 3306 |
push @$active_formatting_elements, ['#marker', ''] |
push @$active_formatting_elements, ['#marker', ''] |
| 3307 |
if $token->{tag_name} eq 'caption'; |
if $token->{tag_name} eq 'caption'; |
| 3308 |
|
|
| 3309 |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 3310 |
$self->{insertion_mode} = { |
$open_tables->[-1]->[2] = 0 if @$open_tables; # ~node inserted |
| 3311 |
caption => IN_CAPTION_IM, |
$self->{insertion_mode} = { |
| 3312 |
colgroup => IN_COLUMN_GROUP_IM, |
caption => IN_CAPTION_IM, |
| 3313 |
tbody => IN_TABLE_BODY_IM, |
colgroup => IN_COLUMN_GROUP_IM, |
| 3314 |
tfoot => IN_TABLE_BODY_IM, |
tbody => IN_TABLE_BODY_IM, |
| 3315 |
thead => IN_TABLE_BODY_IM, |
tfoot => IN_TABLE_BODY_IM, |
| 3316 |
}->{$token->{tag_name}}; |
thead => IN_TABLE_BODY_IM, |
| 3317 |
!!!next-token; |
}->{$token->{tag_name}}; |
| 3318 |
!!!nack ('t220.1'); |
!!!next-token; |
| 3319 |
next B; |
!!!nack ('t220.1'); |
| 3320 |
} else { |
next B; |
| 3321 |
die "$0: in table: <>: $token->{tag_name}"; |
} else { |
| 3322 |
} |
die "$0: in table: <>: $token->{tag_name}"; |
| 3323 |
|
} |
| 3324 |
} elsif ($token->{tag_name} eq 'table') { |
} elsif ($token->{tag_name} eq 'table') { |
| 3325 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 3326 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 3327 |
->manakai_local_name, |
->manakai_local_name, |
| 3328 |
token => $token); |
token => $token); |
| 3329 |
|
|
| 3332 |
my $i; |
my $i; |
| 3333 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3334 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 3335 |
if ($node->[1] & TABLE_EL) { |
if ($node->[1] == TABLE_EL) { |
| 3336 |
!!!cp ('t221'); |
!!!cp ('t221'); |
| 3337 |
$i = $_; |
$i = $_; |
| 3338 |
last INSCOPE; |
last INSCOPE; |
| 3344 |
unless (defined $i) { |
unless (defined $i) { |
| 3345 |
!!!cp ('t223'); |
!!!cp ('t223'); |
| 3346 |
## TODO: The following is wrong, maybe. |
## TODO: The following is wrong, maybe. |
| 3347 |
!!!parse-error (type => 'unmatched end tag:table', token => $token); |
!!!parse-error (type => 'unmatched end tag', text => 'table', |
| 3348 |
|
token => $token); |
| 3349 |
## Ignore tokens </table><table> |
## Ignore tokens </table><table> |
| 3350 |
!!!nack ('t223.1'); |
!!!nack ('t223.1'); |
| 3351 |
!!!next-token; |
!!!next-token; |
| 3352 |
next B; |
next B; |
| 3353 |
} |
} |
| 3354 |
|
|
| 3355 |
## TODO: Followings are removed from the latest spec. |
## TODO: Followings are removed from the latest spec. |
| 3356 |
## generate implied end tags |
## generate implied end tags |
| 3357 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 3358 |
!!!cp ('t224'); |
!!!cp ('t224'); |
| 3359 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3360 |
} |
} |
| 3361 |
|
|
| 3362 |
unless ($self->{open_elements}->[-1]->[1] & TABLE_EL) { |
unless ($self->{open_elements}->[-1]->[1] == TABLE_EL) { |
| 3363 |
!!!cp ('t225'); |
!!!cp ('t225'); |
| 3364 |
## NOTE: |<table><tr><table>| |
## NOTE: |<table><tr><table>| |
| 3365 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 3366 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 3367 |
->manakai_local_name, |
->manakai_local_name, |
| 3368 |
token => $token); |
token => $token); |
| 3369 |
} else { |
} else { |
| 3383 |
!!!cp ('t227.8'); |
!!!cp ('t227.8'); |
| 3384 |
## NOTE: This is a "as if in head" code clone. |
## NOTE: This is a "as if in head" code clone. |
| 3385 |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 3386 |
|
$open_tables->[-1]->[2] = 0 if @$open_tables; # ~node inserted |
| 3387 |
next B; |
next B; |
| 3388 |
} else { |
} else { |
| 3389 |
!!!cp ('t227.7'); |
!!!cp ('t227.7'); |
| 3394 |
!!!cp ('t227.6'); |
!!!cp ('t227.6'); |
| 3395 |
## NOTE: This is a "as if in head" code clone. |
## NOTE: This is a "as if in head" code clone. |
| 3396 |
$script_start_tag->(); |
$script_start_tag->(); |
| 3397 |
|
$open_tables->[-1]->[2] = 0 if @$open_tables; # ~node inserted |
| 3398 |
next B; |
next B; |
| 3399 |
} else { |
} else { |
| 3400 |
!!!cp ('t227.5'); |
!!!cp ('t227.5'); |
| 3406 |
my $type = lc $token->{attributes}->{type}->{value}; |
my $type = lc $token->{attributes}->{type}->{value}; |
| 3407 |
if ($type eq 'hidden') { |
if ($type eq 'hidden') { |
| 3408 |
!!!cp ('t227.3'); |
!!!cp ('t227.3'); |
| 3409 |
!!!parse-error (type => 'in table:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in table', |
| 3410 |
|
text => $token->{tag_name}, token => $token); |
| 3411 |
|
|
| 3412 |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
!!!insert-element ($token->{tag_name}, $token->{attributes}, $token); |
| 3413 |
|
$open_tables->[-1]->[2] = 0 if @$open_tables; # ~node inserted |
| 3414 |
|
|
| 3415 |
## TODO: form element pointer |
## TODO: form element pointer |
| 3416 |
|
|
| 3436 |
# |
# |
| 3437 |
} |
} |
| 3438 |
|
|
| 3439 |
!!!parse-error (type => 'in table:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in table', text => $token->{tag_name}, |
| 3440 |
|
token => $token); |
| 3441 |
|
|
| 3442 |
$insert = $insert_to_foster; |
$insert = $insert_to_foster; |
| 3443 |
# |
# |
| 3444 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 3445 |
if ($token->{tag_name} eq 'tr' and |
if ($token->{tag_name} eq 'tr' and |
| 3446 |
$self->{insertion_mode} == IN_ROW_IM) { |
($self->{insertion_mode} & IM_MASK) == IN_ROW_IM) { |
| 3447 |
## have an element in table scope |
## have an element in table scope |
| 3448 |
my $i; |
my $i; |
| 3449 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3450 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 3451 |
if ($node->[1] & TABLE_ROW_EL) { |
if ($node->[1] == TABLE_ROW_EL) { |
| 3452 |
!!!cp ('t228'); |
!!!cp ('t228'); |
| 3453 |
$i = $_; |
$i = $_; |
| 3454 |
last INSCOPE; |
last INSCOPE; |
| 3459 |
} # INSCOPE |
} # INSCOPE |
| 3460 |
unless (defined $i) { |
unless (defined $i) { |
| 3461 |
!!!cp ('t230'); |
!!!cp ('t230'); |
| 3462 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 3463 |
|
text => $token->{tag_name}, token => $token); |
| 3464 |
## Ignore the token |
## Ignore the token |
| 3465 |
!!!nack ('t230.1'); |
!!!nack ('t230.1'); |
| 3466 |
!!!next-token; |
!!!next-token; |
| 3483 |
!!!nack ('t231.1'); |
!!!nack ('t231.1'); |
| 3484 |
next B; |
next B; |
| 3485 |
} elsif ($token->{tag_name} eq 'table') { |
} elsif ($token->{tag_name} eq 'table') { |
| 3486 |
if ($self->{insertion_mode} == IN_ROW_IM) { |
if (($self->{insertion_mode} & IM_MASK) == IN_ROW_IM) { |
| 3487 |
## As if </tr> |
## As if </tr> |
| 3488 |
## have an element in table scope |
## have an element in table scope |
| 3489 |
my $i; |
my $i; |
| 3490 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3491 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 3492 |
if ($node->[1] & TABLE_ROW_EL) { |
if ($node->[1] == TABLE_ROW_EL) { |
| 3493 |
!!!cp ('t233'); |
!!!cp ('t233'); |
| 3494 |
$i = $_; |
$i = $_; |
| 3495 |
last INSCOPE; |
last INSCOPE; |
| 3501 |
unless (defined $i) { |
unless (defined $i) { |
| 3502 |
!!!cp ('t235'); |
!!!cp ('t235'); |
| 3503 |
## TODO: The following is wrong. |
## TODO: The following is wrong. |
| 3504 |
!!!parse-error (type => 'unmatched end tag:'.$token->{type}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 3505 |
|
text => $token->{type}, token => $token); |
| 3506 |
## Ignore the token |
## Ignore the token |
| 3507 |
!!!nack ('t236.1'); |
!!!nack ('t236.1'); |
| 3508 |
!!!next-token; |
!!!next-token; |
| 3522 |
## reprocess in the "in table body" insertion mode... |
## reprocess in the "in table body" insertion mode... |
| 3523 |
} |
} |
| 3524 |
|
|
| 3525 |
if ($self->{insertion_mode} == IN_TABLE_BODY_IM) { |
if (($self->{insertion_mode} & IM_MASK) == IN_TABLE_BODY_IM) { |
| 3526 |
## have an element in table scope |
## have an element in table scope |
| 3527 |
my $i; |
my $i; |
| 3528 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3529 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 3530 |
if ($node->[1] & TABLE_ROW_GROUP_EL) { |
if ($node->[1] == TABLE_ROW_GROUP_EL) { |
| 3531 |
!!!cp ('t237'); |
!!!cp ('t237'); |
| 3532 |
$i = $_; |
$i = $_; |
| 3533 |
last INSCOPE; |
last INSCOPE; |
| 3538 |
} # INSCOPE |
} # INSCOPE |
| 3539 |
unless (defined $i) { |
unless (defined $i) { |
| 3540 |
!!!cp ('t239'); |
!!!cp ('t239'); |
| 3541 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 3542 |
|
text => $token->{tag_name}, token => $token); |
| 3543 |
## Ignore the token |
## Ignore the token |
| 3544 |
!!!nack ('t239.1'); |
!!!nack ('t239.1'); |
| 3545 |
!!!next-token; |
!!!next-token; |
| 3574 |
my $i; |
my $i; |
| 3575 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3576 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 3577 |
if ($node->[1] & TABLE_EL) { |
if ($node->[1] == TABLE_EL) { |
| 3578 |
!!!cp ('t241'); |
!!!cp ('t241'); |
| 3579 |
$i = $_; |
$i = $_; |
| 3580 |
last INSCOPE; |
last INSCOPE; |
| 3585 |
} # INSCOPE |
} # INSCOPE |
| 3586 |
unless (defined $i) { |
unless (defined $i) { |
| 3587 |
!!!cp ('t243'); |
!!!cp ('t243'); |
| 3588 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 3589 |
|
text => $token->{tag_name}, token => $token); |
| 3590 |
## Ignore the token |
## Ignore the token |
| 3591 |
!!!nack ('t243.1'); |
!!!nack ('t243.1'); |
| 3592 |
!!!next-token; |
!!!next-token; |
| 3604 |
tbody => 1, tfoot => 1, thead => 1, |
tbody => 1, tfoot => 1, thead => 1, |
| 3605 |
}->{$token->{tag_name}} and |
}->{$token->{tag_name}} and |
| 3606 |
$self->{insertion_mode} & ROW_IMS) { |
$self->{insertion_mode} & ROW_IMS) { |
| 3607 |
if ($self->{insertion_mode} == IN_ROW_IM) { |
if (($self->{insertion_mode} & IM_MASK) == IN_ROW_IM) { |
| 3608 |
## have an element in table scope |
## have an element in table scope |
| 3609 |
my $i; |
my $i; |
| 3610 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3620 |
} # INSCOPE |
} # INSCOPE |
| 3621 |
unless (defined $i) { |
unless (defined $i) { |
| 3622 |
!!!cp ('t249'); |
!!!cp ('t249'); |
| 3623 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 3624 |
|
text => $token->{tag_name}, token => $token); |
| 3625 |
## Ignore the token |
## Ignore the token |
| 3626 |
!!!nack ('t249.1'); |
!!!nack ('t249.1'); |
| 3627 |
!!!next-token; |
!!!next-token; |
| 3633 |
my $i; |
my $i; |
| 3634 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3635 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 3636 |
if ($node->[1] & TABLE_ROW_EL) { |
if ($node->[1] == TABLE_ROW_EL) { |
| 3637 |
!!!cp ('t250'); |
!!!cp ('t250'); |
| 3638 |
$i = $_; |
$i = $_; |
| 3639 |
last INSCOPE; |
last INSCOPE; |
| 3644 |
} # INSCOPE |
} # INSCOPE |
| 3645 |
unless (defined $i) { |
unless (defined $i) { |
| 3646 |
!!!cp ('t252'); |
!!!cp ('t252'); |
| 3647 |
!!!parse-error (type => 'unmatched end tag:tr', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 3648 |
|
text => 'tr', token => $token); |
| 3649 |
## Ignore the token |
## Ignore the token |
| 3650 |
!!!nack ('t252.1'); |
!!!nack ('t252.1'); |
| 3651 |
!!!next-token; |
!!!next-token; |
| 3680 |
} # INSCOPE |
} # INSCOPE |
| 3681 |
unless (defined $i) { |
unless (defined $i) { |
| 3682 |
!!!cp ('t256'); |
!!!cp ('t256'); |
| 3683 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 3684 |
|
text => $token->{tag_name}, token => $token); |
| 3685 |
## Ignore the token |
## Ignore the token |
| 3686 |
!!!nack ('t256.1'); |
!!!nack ('t256.1'); |
| 3687 |
!!!next-token; |
!!!next-token; |
| 3708 |
tbody => 1, tfoot => 1, thead => 1, # $self->{insertion_mode} == IN_TABLE_IM |
tbody => 1, tfoot => 1, thead => 1, # $self->{insertion_mode} == IN_TABLE_IM |
| 3709 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 3710 |
!!!cp ('t258'); |
!!!cp ('t258'); |
| 3711 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 3712 |
|
text => $token->{tag_name}, token => $token); |
| 3713 |
## Ignore the token |
## Ignore the token |
| 3714 |
!!!nack ('t258.1'); |
!!!nack ('t258.1'); |
| 3715 |
!!!next-token; |
!!!next-token; |
| 3716 |
next B; |
next B; |
| 3717 |
} else { |
} else { |
| 3718 |
!!!cp ('t259'); |
!!!cp ('t259'); |
| 3719 |
!!!parse-error (type => 'in table:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in table:/', |
| 3720 |
|
text => $token->{tag_name}, token => $token); |
| 3721 |
|
|
| 3722 |
$insert = $insert_to_foster; |
$insert = $insert_to_foster; |
| 3723 |
# |
# |
| 3724 |
} |
} |
| 3725 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 3726 |
unless ($self->{open_elements}->[-1]->[1] & HTML_EL and |
unless ($self->{open_elements}->[-1]->[1] == HTML_EL and |
| 3727 |
@{$self->{open_elements}} == 1) { # redundant, maybe |
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 3728 |
!!!parse-error (type => 'in body:#eof', token => $token); |
!!!parse-error (type => 'in body:#eof', token => $token); |
| 3729 |
!!!cp ('t259.1'); |
!!!cp ('t259.1'); |
| 3738 |
} else { |
} else { |
| 3739 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 3740 |
} |
} |
| 3741 |
} elsif ($self->{insertion_mode} == IN_COLUMN_GROUP_IM) { |
} elsif (($self->{insertion_mode} & IM_MASK) == IN_COLUMN_GROUP_IM) { |
| 3742 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 3743 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0C\x20]+)//) { |
| 3744 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 3745 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 3746 |
!!!cp ('t260'); |
!!!cp ('t260'); |
| 3765 |
} |
} |
| 3766 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 3767 |
if ($token->{tag_name} eq 'colgroup') { |
if ($token->{tag_name} eq 'colgroup') { |
| 3768 |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
if ($self->{open_elements}->[-1]->[1] == HTML_EL) { |
| 3769 |
!!!cp ('t264'); |
!!!cp ('t264'); |
| 3770 |
!!!parse-error (type => 'unmatched end tag:colgroup', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 3771 |
|
text => 'colgroup', token => $token); |
| 3772 |
## Ignore the token |
## Ignore the token |
| 3773 |
!!!next-token; |
!!!next-token; |
| 3774 |
next B; |
next B; |
| 3781 |
} |
} |
| 3782 |
} elsif ($token->{tag_name} eq 'col') { |
} elsif ($token->{tag_name} eq 'col') { |
| 3783 |
!!!cp ('t266'); |
!!!cp ('t266'); |
| 3784 |
!!!parse-error (type => 'unmatched end tag:col', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 3785 |
|
text => 'col', token => $token); |
| 3786 |
## Ignore the token |
## Ignore the token |
| 3787 |
!!!next-token; |
!!!next-token; |
| 3788 |
next B; |
next B; |
| 3791 |
# |
# |
| 3792 |
} |
} |
| 3793 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 3794 |
if ($self->{open_elements}->[-1]->[1] & HTML_EL and |
if ($self->{open_elements}->[-1]->[1] == HTML_EL and |
| 3795 |
@{$self->{open_elements}} == 1) { # redundant, maybe |
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 3796 |
!!!cp ('t270.2'); |
!!!cp ('t270.2'); |
| 3797 |
## Stop parsing. |
## Stop parsing. |
| 3809 |
} |
} |
| 3810 |
|
|
| 3811 |
## As if </colgroup> |
## As if </colgroup> |
| 3812 |
if ($self->{open_elements}->[-1]->[1] & HTML_EL) { |
if ($self->{open_elements}->[-1]->[1] == HTML_EL) { |
| 3813 |
!!!cp ('t269'); |
!!!cp ('t269'); |
| 3814 |
## TODO: Wrong error type? |
## TODO: Wrong error type? |
| 3815 |
!!!parse-error (type => 'unmatched end tag:colgroup', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 3816 |
|
text => 'colgroup', token => $token); |
| 3817 |
## Ignore the token |
## Ignore the token |
| 3818 |
!!!nack ('t269.1'); |
!!!nack ('t269.1'); |
| 3819 |
!!!next-token; |
!!!next-token; |
| 3834 |
next B; |
next B; |
| 3835 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 3836 |
if ($token->{tag_name} eq 'option') { |
if ($token->{tag_name} eq 'option') { |
| 3837 |
if ($self->{open_elements}->[-1]->[1] & OPTION_EL) { |
if ($self->{open_elements}->[-1]->[1] == OPTION_EL) { |
| 3838 |
!!!cp ('t272'); |
!!!cp ('t272'); |
| 3839 |
## As if </option> |
## As if </option> |
| 3840 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3847 |
!!!next-token; |
!!!next-token; |
| 3848 |
next B; |
next B; |
| 3849 |
} elsif ($token->{tag_name} eq 'optgroup') { |
} elsif ($token->{tag_name} eq 'optgroup') { |
| 3850 |
if ($self->{open_elements}->[-1]->[1] & OPTION_EL) { |
if ($self->{open_elements}->[-1]->[1] == OPTION_EL) { |
| 3851 |
!!!cp ('t274'); |
!!!cp ('t274'); |
| 3852 |
## As if </option> |
## As if </option> |
| 3853 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3855 |
!!!cp ('t275'); |
!!!cp ('t275'); |
| 3856 |
} |
} |
| 3857 |
|
|
| 3858 |
if ($self->{open_elements}->[-1]->[1] & OPTGROUP_EL) { |
if ($self->{open_elements}->[-1]->[1] == OPTGROUP_EL) { |
| 3859 |
!!!cp ('t276'); |
!!!cp ('t276'); |
| 3860 |
## As if </optgroup> |
## As if </optgroup> |
| 3861 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3867 |
!!!nack ('t277.1'); |
!!!nack ('t277.1'); |
| 3868 |
!!!next-token; |
!!!next-token; |
| 3869 |
next B; |
next B; |
| 3870 |
} elsif ($token->{tag_name} eq 'select' or |
} elsif ({ |
| 3871 |
$token->{tag_name} eq 'input' or |
select => 1, input => 1, textarea => 1, keygen => 1, |
| 3872 |
($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
}->{$token->{tag_name}} or |
| 3873 |
|
(($self->{insertion_mode} & IM_MASK) |
| 3874 |
|
== IN_SELECT_IN_TABLE_IM and |
| 3875 |
{ |
{ |
| 3876 |
caption => 1, table => 1, |
caption => 1, table => 1, |
| 3877 |
tbody => 1, tfoot => 1, thead => 1, |
tbody => 1, tfoot => 1, thead => 1, |
| 3878 |
tr => 1, td => 1, th => 1, |
tr => 1, td => 1, th => 1, |
| 3879 |
}->{$token->{tag_name}})) { |
}->{$token->{tag_name}})) { |
| 3880 |
## TODO: The type below is not good - <select> is replaced by </select> |
|
| 3881 |
!!!parse-error (type => 'not closed:select', token => $token); |
## 1. Parse error. |
| 3882 |
## NOTE: As if the token were </select> (<select> case) or |
if ($token->{tag_name} eq 'select') { |
| 3883 |
## as if there were </select> (otherwise). |
!!!parse-error (type => 'select in select', ## XXX: documentation |
| 3884 |
## have an element in table scope |
token => $token); |
| 3885 |
|
} else { |
| 3886 |
|
!!!parse-error (type => 'not closed', text => 'select', |
| 3887 |
|
token => $token); |
| 3888 |
|
} |
| 3889 |
|
|
| 3890 |
|
## 2./<select>-1. Unless "have an element in table scope" (select): |
| 3891 |
my $i; |
my $i; |
| 3892 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3893 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 3894 |
if ($node->[1] & SELECT_EL) { |
if ($node->[1] == SELECT_EL) { |
| 3895 |
!!!cp ('t278'); |
!!!cp ('t278'); |
| 3896 |
$i = $_; |
$i = $_; |
| 3897 |
last INSCOPE; |
last INSCOPE; |
| 3902 |
} # INSCOPE |
} # INSCOPE |
| 3903 |
unless (defined $i) { |
unless (defined $i) { |
| 3904 |
!!!cp ('t280'); |
!!!cp ('t280'); |
| 3905 |
!!!parse-error (type => 'unmatched end tag:select', token => $token); |
if ($token->{tag_name} eq 'select') { |
| 3906 |
## Ignore the token |
## NOTE: This error would be raised when |
| 3907 |
|
## |select.innerHTML = '<select>'| is executed; in this |
| 3908 |
|
## case two errors, "select in select" and "unmatched |
| 3909 |
|
## end tags" are reported to the user, the latter might |
| 3910 |
|
## be confusing but this is what the spec requires. |
| 3911 |
|
!!!parse-error (type => 'unmatched end tag', |
| 3912 |
|
text => 'select', |
| 3913 |
|
token => $token); |
| 3914 |
|
} |
| 3915 |
|
## Ignore the token. |
| 3916 |
!!!nack ('t280.1'); |
!!!nack ('t280.1'); |
| 3917 |
!!!next-token; |
!!!next-token; |
| 3918 |
next B; |
next B; |
| 3919 |
} |
} |
| 3920 |
|
|
| 3921 |
|
## 3. Otherwise, as if there were <select>: |
| 3922 |
|
|
| 3923 |
!!!cp ('t281'); |
!!!cp ('t281'); |
| 3924 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 3935 |
## Reprocess the token. |
## Reprocess the token. |
| 3936 |
next B; |
next B; |
| 3937 |
} |
} |
| 3938 |
|
} elsif ($token->{tag_name} eq 'script') { |
| 3939 |
|
!!!cp ('t281.3'); |
| 3940 |
|
## NOTE: This is an "as if in head" code clone |
| 3941 |
|
$script_start_tag->(); |
| 3942 |
|
next B; |
| 3943 |
} else { |
} else { |
| 3944 |
!!!cp ('t282'); |
!!!cp ('t282'); |
| 3945 |
!!!parse-error (type => 'in select:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in select', |
| 3946 |
|
text => $token->{tag_name}, token => $token); |
| 3947 |
## Ignore the token |
## Ignore the token |
| 3948 |
!!!nack ('t282.1'); |
!!!nack ('t282.1'); |
| 3949 |
!!!next-token; |
!!!next-token; |
| 3951 |
} |
} |
| 3952 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 3953 |
if ($token->{tag_name} eq 'optgroup') { |
if ($token->{tag_name} eq 'optgroup') { |
| 3954 |
if ($self->{open_elements}->[-1]->[1] & OPTION_EL and |
if ($self->{open_elements}->[-1]->[1] == OPTION_EL and |
| 3955 |
$self->{open_elements}->[-2]->[1] & OPTGROUP_EL) { |
$self->{open_elements}->[-2]->[1] == OPTGROUP_EL) { |
| 3956 |
!!!cp ('t283'); |
!!!cp ('t283'); |
| 3957 |
## As if </option> |
## As if </option> |
| 3958 |
splice @{$self->{open_elements}}, -2; |
splice @{$self->{open_elements}}, -2; |
| 3959 |
} elsif ($self->{open_elements}->[-1]->[1] & OPTGROUP_EL) { |
} elsif ($self->{open_elements}->[-1]->[1] == OPTGROUP_EL) { |
| 3960 |
!!!cp ('t284'); |
!!!cp ('t284'); |
| 3961 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3962 |
} else { |
} else { |
| 3963 |
!!!cp ('t285'); |
!!!cp ('t285'); |
| 3964 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 3965 |
|
text => $token->{tag_name}, token => $token); |
| 3966 |
## Ignore the token |
## Ignore the token |
| 3967 |
} |
} |
| 3968 |
!!!nack ('t285.1'); |
!!!nack ('t285.1'); |
| 3969 |
!!!next-token; |
!!!next-token; |
| 3970 |
next B; |
next B; |
| 3971 |
} elsif ($token->{tag_name} eq 'option') { |
} elsif ($token->{tag_name} eq 'option') { |
| 3972 |
if ($self->{open_elements}->[-1]->[1] & OPTION_EL) { |
if ($self->{open_elements}->[-1]->[1] == OPTION_EL) { |
| 3973 |
!!!cp ('t286'); |
!!!cp ('t286'); |
| 3974 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3975 |
} else { |
} else { |
| 3976 |
!!!cp ('t287'); |
!!!cp ('t287'); |
| 3977 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 3978 |
|
text => $token->{tag_name}, token => $token); |
| 3979 |
## Ignore the token |
## Ignore the token |
| 3980 |
} |
} |
| 3981 |
!!!nack ('t287.1'); |
!!!nack ('t287.1'); |
| 3986 |
my $i; |
my $i; |
| 3987 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3988 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 3989 |
if ($node->[1] & SELECT_EL) { |
if ($node->[1] == SELECT_EL) { |
| 3990 |
!!!cp ('t288'); |
!!!cp ('t288'); |
| 3991 |
$i = $_; |
$i = $_; |
| 3992 |
last INSCOPE; |
last INSCOPE; |
| 3997 |
} # INSCOPE |
} # INSCOPE |
| 3998 |
unless (defined $i) { |
unless (defined $i) { |
| 3999 |
!!!cp ('t290'); |
!!!cp ('t290'); |
| 4000 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4001 |
|
text => $token->{tag_name}, token => $token); |
| 4002 |
## Ignore the token |
## Ignore the token |
| 4003 |
!!!nack ('t290.1'); |
!!!nack ('t290.1'); |
| 4004 |
!!!next-token; |
!!!next-token; |
| 4013 |
!!!nack ('t291.1'); |
!!!nack ('t291.1'); |
| 4014 |
!!!next-token; |
!!!next-token; |
| 4015 |
next B; |
next B; |
| 4016 |
} elsif ($self->{insertion_mode} == IN_SELECT_IN_TABLE_IM and |
} elsif (($self->{insertion_mode} & IM_MASK) |
| 4017 |
|
== IN_SELECT_IN_TABLE_IM and |
| 4018 |
{ |
{ |
| 4019 |
caption => 1, table => 1, tbody => 1, |
caption => 1, table => 1, tbody => 1, |
| 4020 |
tfoot => 1, thead => 1, tr => 1, td => 1, th => 1, |
tfoot => 1, thead => 1, tr => 1, td => 1, th => 1, |
| 4021 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 4022 |
## TODO: The following is wrong? |
## TODO: The following is wrong? |
| 4023 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4024 |
|
text => $token->{tag_name}, token => $token); |
| 4025 |
|
|
| 4026 |
## have an element in table scope |
## have an element in table scope |
| 4027 |
my $i; |
my $i; |
| 4049 |
undef $i; |
undef $i; |
| 4050 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4051 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 4052 |
if ($node->[1] & SELECT_EL) { |
if ($node->[1] == SELECT_EL) { |
| 4053 |
!!!cp ('t295'); |
!!!cp ('t295'); |
| 4054 |
$i = $_; |
$i = $_; |
| 4055 |
last INSCOPE; |
last INSCOPE; |
| 4062 |
unless (defined $i) { |
unless (defined $i) { |
| 4063 |
!!!cp ('t297'); |
!!!cp ('t297'); |
| 4064 |
## TODO: The following error type is correct? |
## TODO: The following error type is correct? |
| 4065 |
!!!parse-error (type => 'unmatched end tag:select', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4066 |
|
text => 'select', token => $token); |
| 4067 |
## Ignore the </select> token |
## Ignore the </select> token |
| 4068 |
!!!nack ('t297.1'); |
!!!nack ('t297.1'); |
| 4069 |
!!!next-token; ## TODO: ok? |
!!!next-token; ## TODO: ok? |
| 4080 |
next B; |
next B; |
| 4081 |
} else { |
} else { |
| 4082 |
!!!cp ('t299'); |
!!!cp ('t299'); |
| 4083 |
!!!parse-error (type => 'in select:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in select:/', |
| 4084 |
|
text => $token->{tag_name}, token => $token); |
| 4085 |
## Ignore the token |
## Ignore the token |
| 4086 |
!!!nack ('t299.3'); |
!!!nack ('t299.3'); |
| 4087 |
!!!next-token; |
!!!next-token; |
| 4088 |
next B; |
next B; |
| 4089 |
} |
} |
| 4090 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 4091 |
unless ($self->{open_elements}->[-1]->[1] & HTML_EL and |
unless ($self->{open_elements}->[-1]->[1] == HTML_EL and |
| 4092 |
@{$self->{open_elements}} == 1) { # redundant, maybe |
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 4093 |
!!!cp ('t299.1'); |
!!!cp ('t299.1'); |
| 4094 |
!!!parse-error (type => 'in body:#eof', token => $token); |
!!!parse-error (type => 'in body:#eof', token => $token); |
| 4103 |
} |
} |
| 4104 |
} elsif ($self->{insertion_mode} & BODY_AFTER_IMS) { |
} elsif ($self->{insertion_mode} & BODY_AFTER_IMS) { |
| 4105 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 4106 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0C\x20]+)//) { |
| 4107 |
my $data = $1; |
my $data = $1; |
| 4108 |
## As if in body |
## As if in body |
| 4109 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4119 |
|
|
| 4120 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 4121 |
!!!cp ('t301'); |
!!!cp ('t301'); |
| 4122 |
!!!parse-error (type => 'after html:#character', token => $token); |
!!!parse-error (type => 'after html:#text', token => $token); |
| 4123 |
|
# |
|
## Reprocess in the "after body" insertion mode. |
|
| 4124 |
} else { |
} else { |
| 4125 |
!!!cp ('t302'); |
!!!cp ('t302'); |
| 4126 |
|
## "after body" insertion mode |
| 4127 |
|
!!!parse-error (type => 'after body:#text', token => $token); |
| 4128 |
|
# |
| 4129 |
} |
} |
|
|
|
|
## "after body" insertion mode |
|
|
!!!parse-error (type => 'after body:#character', token => $token); |
|
| 4130 |
|
|
| 4131 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 4132 |
## reprocess |
## reprocess |
| 4134 |
} elsif ($token->{type} == START_TAG_TOKEN) { |
} elsif ($token->{type} == START_TAG_TOKEN) { |
| 4135 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 4136 |
!!!cp ('t303'); |
!!!cp ('t303'); |
| 4137 |
!!!parse-error (type => 'after html:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after html', |
| 4138 |
|
text => $token->{tag_name}, token => $token); |
| 4139 |
## Reprocess in the "after body" insertion mode. |
# |
| 4140 |
} else { |
} else { |
| 4141 |
!!!cp ('t304'); |
!!!cp ('t304'); |
| 4142 |
|
## "after body" insertion mode |
| 4143 |
|
!!!parse-error (type => 'after body', |
| 4144 |
|
text => $token->{tag_name}, token => $token); |
| 4145 |
|
# |
| 4146 |
} |
} |
| 4147 |
|
|
|
## "after body" insertion mode |
|
|
!!!parse-error (type => 'after body:'.$token->{tag_name}, token => $token); |
|
|
|
|
| 4148 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 4149 |
!!!ack-later; |
!!!ack-later; |
| 4150 |
## reprocess |
## reprocess |
| 4152 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 4153 |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
if ($self->{insertion_mode} == AFTER_HTML_BODY_IM) { |
| 4154 |
!!!cp ('t305'); |
!!!cp ('t305'); |
| 4155 |
!!!parse-error (type => 'after html:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after html:/', |
| 4156 |
|
text => $token->{tag_name}, token => $token); |
| 4157 |
|
|
| 4158 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 4159 |
## Reprocess in the "after body" insertion mode. |
## Reprocess. |
| 4160 |
|
next B; |
| 4161 |
} else { |
} else { |
| 4162 |
!!!cp ('t306'); |
!!!cp ('t306'); |
| 4163 |
} |
} |
| 4166 |
if ($token->{tag_name} eq 'html') { |
if ($token->{tag_name} eq 'html') { |
| 4167 |
if (defined $self->{inner_html_node}) { |
if (defined $self->{inner_html_node}) { |
| 4168 |
!!!cp ('t307'); |
!!!cp ('t307'); |
| 4169 |
!!!parse-error (type => 'unmatched end tag:html', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4170 |
|
text => 'html', token => $token); |
| 4171 |
## Ignore the token |
## Ignore the token |
| 4172 |
!!!next-token; |
!!!next-token; |
| 4173 |
next B; |
next B; |
| 4179 |
} |
} |
| 4180 |
} else { |
} else { |
| 4181 |
!!!cp ('t309'); |
!!!cp ('t309'); |
| 4182 |
!!!parse-error (type => 'after body:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after body:/', |
| 4183 |
|
text => $token->{tag_name}, token => $token); |
| 4184 |
|
|
| 4185 |
$self->{insertion_mode} = IN_BODY_IM; |
$self->{insertion_mode} = IN_BODY_IM; |
| 4186 |
## reprocess |
## reprocess |
| 4195 |
} |
} |
| 4196 |
} elsif ($self->{insertion_mode} & FRAME_IMS) { |
} elsif ($self->{insertion_mode} & FRAME_IMS) { |
| 4197 |
if ($token->{type} == CHARACTER_TOKEN) { |
if ($token->{type} == CHARACTER_TOKEN) { |
| 4198 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0C\x20]+)//) { |
| 4199 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 4200 |
|
|
| 4201 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 4205 |
} |
} |
| 4206 |
} |
} |
| 4207 |
|
|
| 4208 |
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
if ($token->{data} =~ s/^[^\x09\x0A\x0C\x20]+//) { |
| 4209 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 4210 |
!!!cp ('t311'); |
!!!cp ('t311'); |
| 4211 |
!!!parse-error (type => 'in frameset:#character', token => $token); |
!!!parse-error (type => 'in frameset:#text', token => $token); |
| 4212 |
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 4213 |
!!!cp ('t312'); |
!!!cp ('t312'); |
| 4214 |
!!!parse-error (type => 'after frameset:#character', token => $token); |
!!!parse-error (type => 'after frameset:#text', token => $token); |
| 4215 |
} else { # "after html frameset" |
} else { # "after after frameset" |
| 4216 |
!!!cp ('t313'); |
!!!cp ('t313'); |
| 4217 |
!!!parse-error (type => 'after html:#character', token => $token); |
!!!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', token => $token); |
|
| 4218 |
} |
} |
| 4219 |
|
|
| 4220 |
## Ignore the token. |
## Ignore the token. |
| 4230 |
|
|
| 4231 |
die qq[$0: Character "$token->{data}"]; |
die qq[$0: Character "$token->{data}"]; |
| 4232 |
} 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}, token => $token); |
|
|
|
|
|
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
|
|
## Process in the "after frameset" insertion mode. |
|
|
} else { |
|
|
!!!cp ('t317'); |
|
|
} |
|
|
|
|
| 4233 |
if ($token->{tag_name} eq 'frameset' and |
if ($token->{tag_name} eq 'frameset' and |
| 4234 |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 4235 |
!!!cp ('t318'); |
!!!cp ('t318'); |
| 4247 |
next B; |
next B; |
| 4248 |
} elsif ($token->{tag_name} eq 'noframes') { |
} elsif ($token->{tag_name} eq 'noframes') { |
| 4249 |
!!!cp ('t320'); |
!!!cp ('t320'); |
| 4250 |
## NOTE: As if in body. |
## NOTE: As if in head. |
| 4251 |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 4252 |
next B; |
next B; |
| 4253 |
|
|
| 4254 |
|
## NOTE: |<!DOCTYPE HTML><frameset></frameset></html><noframes></noframes>| |
| 4255 |
|
## has no parse error. |
| 4256 |
} else { |
} else { |
| 4257 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 4258 |
!!!cp ('t321'); |
!!!cp ('t321'); |
| 4259 |
!!!parse-error (type => 'in frameset:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in frameset', |
| 4260 |
} else { |
text => $token->{tag_name}, token => $token); |
| 4261 |
|
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 4262 |
!!!cp ('t322'); |
!!!cp ('t322'); |
| 4263 |
!!!parse-error (type => 'after frameset:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after frameset', |
| 4264 |
|
text => $token->{tag_name}, token => $token); |
| 4265 |
|
} else { # "after after frameset" |
| 4266 |
|
!!!cp ('t322.2'); |
| 4267 |
|
!!!parse-error (type => 'after after frameset', |
| 4268 |
|
text => $token->{tag_name}, token => $token); |
| 4269 |
} |
} |
| 4270 |
## Ignore the token |
## Ignore the token |
| 4271 |
!!!nack ('t322.1'); |
!!!nack ('t322.1'); |
| 4273 |
next B; |
next B; |
| 4274 |
} |
} |
| 4275 |
} elsif ($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}, token => $token); |
|
|
|
|
|
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
|
|
## Process in the "after frameset" insertion mode. |
|
|
} else { |
|
|
!!!cp ('t324'); |
|
|
} |
|
|
|
|
| 4276 |
if ($token->{tag_name} eq 'frameset' and |
if ($token->{tag_name} eq 'frameset' and |
| 4277 |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
$self->{insertion_mode} == IN_FRAMESET_IM) { |
| 4278 |
if ($self->{open_elements}->[-1]->[1] & HTML_EL and |
if ($self->{open_elements}->[-1]->[1] == HTML_EL and |
| 4279 |
@{$self->{open_elements}} == 1) { |
@{$self->{open_elements}} == 1) { |
| 4280 |
!!!cp ('t325'); |
!!!cp ('t325'); |
| 4281 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 4282 |
|
text => $token->{tag_name}, token => $token); |
| 4283 |
## Ignore the token |
## Ignore the token |
| 4284 |
!!!next-token; |
!!!next-token; |
| 4285 |
} else { |
} else { |
| 4289 |
} |
} |
| 4290 |
|
|
| 4291 |
if (not defined $self->{inner_html_node} and |
if (not defined $self->{inner_html_node} and |
| 4292 |
not ($self->{open_elements}->[-1]->[1] & FRAMESET_EL)) { |
not ($self->{open_elements}->[-1]->[1] == FRAMESET_EL)) { |
| 4293 |
!!!cp ('t327'); |
!!!cp ('t327'); |
| 4294 |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
$self->{insertion_mode} = AFTER_FRAMESET_IM; |
| 4295 |
} else { |
} else { |
| 4305 |
} else { |
} else { |
| 4306 |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
if ($self->{insertion_mode} == IN_FRAMESET_IM) { |
| 4307 |
!!!cp ('t330'); |
!!!cp ('t330'); |
| 4308 |
!!!parse-error (type => 'in frameset:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in frameset:/', |
| 4309 |
} else { |
text => $token->{tag_name}, token => $token); |
| 4310 |
|
} elsif ($self->{insertion_mode} == AFTER_FRAMESET_IM) { |
| 4311 |
|
!!!cp ('t330.1'); |
| 4312 |
|
!!!parse-error (type => 'after frameset:/', |
| 4313 |
|
text => $token->{tag_name}, token => $token); |
| 4314 |
|
} else { # "after after html" |
| 4315 |
!!!cp ('t331'); |
!!!cp ('t331'); |
| 4316 |
!!!parse-error (type => 'after frameset:/'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'after after frameset:/', |
| 4317 |
|
text => $token->{tag_name}, token => $token); |
| 4318 |
} |
} |
| 4319 |
## Ignore the token |
## Ignore the token |
| 4320 |
!!!next-token; |
!!!next-token; |
| 4321 |
next B; |
next B; |
| 4322 |
} |
} |
| 4323 |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
} elsif ($token->{type} == END_OF_FILE_TOKEN) { |
| 4324 |
unless ($self->{open_elements}->[-1]->[1] & HTML_EL and |
unless ($self->{open_elements}->[-1]->[1] == HTML_EL and |
| 4325 |
@{$self->{open_elements}} == 1) { # redundant, maybe |
@{$self->{open_elements}} == 1) { # redundant, maybe |
| 4326 |
!!!cp ('t331.1'); |
!!!cp ('t331.1'); |
| 4327 |
!!!parse-error (type => 'in body:#eof', token => $token); |
!!!parse-error (type => 'in body:#eof', token => $token); |
| 4334 |
} else { |
} else { |
| 4335 |
die "$0: $token->{type}: Unknown token type"; |
die "$0: $token->{type}: Unknown token type"; |
| 4336 |
} |
} |
|
|
|
|
## ISSUE: An issue in spec here |
|
| 4337 |
} else { |
} else { |
| 4338 |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
| 4339 |
} |
} |
| 4351 |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
$parse_rcdata->(CDATA_CONTENT_MODEL); |
| 4352 |
next B; |
next B; |
| 4353 |
} elsif ({ |
} elsif ({ |
| 4354 |
base => 1, link => 1, |
base => 1, command => 1, link => 1, |
| 4355 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 4356 |
!!!cp ('t334'); |
!!!cp ('t334'); |
| 4357 |
## NOTE: This is an "as if in head" code clone, only "-t" differs |
## NOTE: This is an "as if in head" code clone, only "-t" differs |
| 4358 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 4359 |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
pop @{$self->{open_elements}}; |
| 4360 |
!!!ack ('t334.1'); |
!!!ack ('t334.1'); |
| 4361 |
!!!next-token; |
!!!next-token; |
| 4362 |
next B; |
next B; |
| 4363 |
} elsif ($token->{tag_name} eq 'meta') { |
} elsif ($token->{tag_name} eq 'meta') { |
| 4364 |
## NOTE: This is an "as if in head" code clone, only "-t" differs |
## NOTE: This is an "as if in head" code clone, only "-t" differs |
| 4365 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 4366 |
my $meta_el = pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
my $meta_el = pop @{$self->{open_elements}}; |
| 4367 |
|
|
| 4368 |
unless ($self->{confident}) { |
unless ($self->{confident}) { |
| 4369 |
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
if ($token->{attributes}->{charset}) { |
| 4370 |
!!!cp ('t335'); |
!!!cp ('t335'); |
| 4371 |
|
## NOTE: Whether the encoding is supported or not is handled |
| 4372 |
|
## in the {change_encoding} callback. |
| 4373 |
$self->{change_encoding} |
$self->{change_encoding} |
| 4374 |
->($self, $token->{attributes}->{charset}->{value}, $token); |
->($self, $token->{attributes}->{charset}->{value}, $token); |
| 4375 |
|
|
| 4378 |
$token->{attributes}->{charset} |
$token->{attributes}->{charset} |
| 4379 |
->{has_reference}); |
->{has_reference}); |
| 4380 |
} elsif ($token->{attributes}->{content}) { |
} elsif ($token->{attributes}->{content}) { |
|
## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition. |
|
| 4381 |
if ($token->{attributes}->{content}->{value} |
if ($token->{attributes}->{content}->{value} |
| 4382 |
=~ /\A[^;]*;[\x09-\x0D\x20]*[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
=~ /[Cc][Hh][Aa][Rr][Ss][Ee][Tt] |
| 4383 |
[\x09-\x0D\x20]*= |
[\x09\x0A\x0C\x0D\x20]*= |
| 4384 |
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
[\x09\x0A\x0C\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
| 4385 |
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
([^"'\x09\x0A\x0C\x0D\x20][^\x09\x0A\x0C\x0D\x20\x3B]*)) |
| 4386 |
|
/x) { |
| 4387 |
!!!cp ('t336'); |
!!!cp ('t336'); |
| 4388 |
|
## NOTE: Whether the encoding is supported or not is handled |
| 4389 |
|
## in the {change_encoding} callback. |
| 4390 |
$self->{change_encoding} |
$self->{change_encoding} |
| 4391 |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3, $token); |
->($self, defined $1 ? $1 : defined $2 ? $2 : $3, $token); |
| 4392 |
$meta_el->[0]->get_attribute_node_ns (undef, 'content') |
$meta_el->[0]->get_attribute_node_ns (undef, 'content') |
| 4421 |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
$parse_rcdata->(RCDATA_CONTENT_MODEL); |
| 4422 |
next B; |
next B; |
| 4423 |
} elsif ($token->{tag_name} eq 'body') { |
} elsif ($token->{tag_name} eq 'body') { |
| 4424 |
!!!parse-error (type => 'in body:body', token => $token); |
!!!parse-error (type => 'in body', text => 'body', token => $token); |
| 4425 |
|
|
| 4426 |
if (@{$self->{open_elements}} == 1 or |
if (@{$self->{open_elements}} == 1 or |
| 4427 |
not ($self->{open_elements}->[1]->[1] & BODY_EL)) { |
not ($self->{open_elements}->[1]->[1] == BODY_EL)) { |
| 4428 |
!!!cp ('t342'); |
!!!cp ('t342'); |
| 4429 |
## Ignore the token |
## Ignore the token |
| 4430 |
} else { |
} else { |
| 4442 |
!!!next-token; |
!!!next-token; |
| 4443 |
next B; |
next B; |
| 4444 |
} elsif ({ |
} elsif ({ |
| 4445 |
address => 1, blockquote => 1, center => 1, dir => 1, |
## NOTE: Start tags for non-phrasing flow content elements |
| 4446 |
div => 1, dl => 1, fieldset => 1, |
|
| 4447 |
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
## NOTE: The normal one |
| 4448 |
menu => 1, ol => 1, p => 1, ul => 1, |
address => 1, article => 1, aside => 1, blockquote => 1, |
| 4449 |
|
center => 1, datagrid => 1, details => 1, dialog => 1, |
| 4450 |
|
dir => 1, div => 1, dl => 1, fieldset => 1, figure => 1, |
| 4451 |
|
footer => 1, h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, |
| 4452 |
|
h6 => 1, header => 1, menu => 1, nav => 1, ol => 1, p => 1, |
| 4453 |
|
section => 1, ul => 1, |
| 4454 |
|
## NOTE: As normal, but drops leading newline |
| 4455 |
pre => 1, listing => 1, |
pre => 1, listing => 1, |
| 4456 |
|
## NOTE: As normal, but interacts with the form element pointer |
| 4457 |
form => 1, |
form => 1, |
| 4458 |
|
|
| 4459 |
table => 1, |
table => 1, |
| 4460 |
hr => 1, |
hr => 1, |
| 4461 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 4462 |
|
|
| 4463 |
|
## 1. When there is an opening |form| element: |
| 4464 |
if ($token->{tag_name} eq 'form' and defined $self->{form_element}) { |
if ($token->{tag_name} eq 'form' and defined $self->{form_element}) { |
| 4465 |
!!!cp ('t350'); |
!!!cp ('t350'); |
| 4466 |
!!!parse-error (type => 'in form:form', token => $token); |
!!!parse-error (type => 'in form:form', token => $token); |
| 4470 |
next B; |
next B; |
| 4471 |
} |
} |
| 4472 |
|
|
| 4473 |
## has a p element in scope |
## 2. Close the |p| element, if any. |
| 4474 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
if ($token->{tag_name} ne 'table' or # The Hixie Quirk |
| 4475 |
if ($_->[1] & P_EL) { |
$self->{document}->manakai_compat_mode ne 'quirks') { |
| 4476 |
!!!cp ('t344'); |
## has a p element in scope |
| 4477 |
!!!back-token; # <form> |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4478 |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
if ($_->[1] == P_EL) { |
| 4479 |
line => $token->{line}, column => $token->{column}}; |
!!!cp ('t344'); |
| 4480 |
next B; |
!!!back-token; # <form> |
| 4481 |
} elsif ($_->[1] & SCOPING_EL) { |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
| 4482 |
!!!cp ('t345'); |
line => $token->{line}, column => $token->{column}}; |
| 4483 |
last INSCOPE; |
next B; |
| 4484 |
|
} elsif ($_->[1] & SCOPING_EL) { |
| 4485 |
|
!!!cp ('t345'); |
| 4486 |
|
last INSCOPE; |
| 4487 |
|
} |
| 4488 |
|
} # INSCOPE |
| 4489 |
|
} |
| 4490 |
|
|
| 4491 |
|
## 3. Close the opening <hn> element, if any. |
| 4492 |
|
if ({h1 => 1, h2 => 1, h3 => 1, |
| 4493 |
|
h4 => 1, h5 => 1, h6 => 1}->{$token->{tag_name}}) { |
| 4494 |
|
if ($self->{open_elements}->[-1]->[1] == HEADING_EL) { |
| 4495 |
|
!!!parse-error (type => 'not closed', |
| 4496 |
|
text => $self->{open_elements}->[-1]->[0]->manakai_local_name, |
| 4497 |
|
token => $token); |
| 4498 |
|
pop @{$self->{open_elements}}; |
| 4499 |
} |
} |
| 4500 |
} # INSCOPE |
} |
| 4501 |
|
|
| 4502 |
|
## 4. Insertion. |
| 4503 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 4504 |
if ($token->{tag_name} eq 'pre' or $token->{tag_name} eq 'listing') { |
if ($token->{tag_name} eq 'pre' or $token->{tag_name} eq 'listing') { |
| 4505 |
!!!nack ('t346.1'); |
!!!nack ('t346.1'); |
| 4540 |
!!!next-token; |
!!!next-token; |
| 4541 |
} |
} |
| 4542 |
next B; |
next B; |
| 4543 |
} elsif ({li => 1, dt => 1, dd => 1}->{$token->{tag_name}}) { |
} elsif ($token->{tag_name} eq 'li') { |
| 4544 |
## has a p element in scope |
## NOTE: As normal, but imply </li> when there's another <li> ... |
| 4545 |
|
|
| 4546 |
|
## NOTE: Special, Scope (<li><foo><li> == <li><foo><li/></foo></li>):: |
| 4547 |
|
## Interpreted as <li><foo/></li><li/> (non-conforming): |
| 4548 |
|
## blockquote (O9.27), center (O), dd (Fx3, O, S3.1.2, IE7), |
| 4549 |
|
## dt (Fx, O, S, IE), dl (O), fieldset (O, S, IE), form (Fx, O, S), |
| 4550 |
|
## hn (O), pre (O), applet (O, S), button (O, S), marquee (Fx, O, S), |
| 4551 |
|
## object (Fx) |
| 4552 |
|
## Generate non-tree (non-conforming): |
| 4553 |
|
## basefont (IE7 (where basefont is non-void)), center (IE), |
| 4554 |
|
## form (IE), hn (IE) |
| 4555 |
|
## address, div, p (<li><foo><li> == <li><foo/></li><li/>):: |
| 4556 |
|
## Interpreted as <li><foo><li/></foo></li> (non-conforming): |
| 4557 |
|
## div (Fx, S) |
| 4558 |
|
|
| 4559 |
|
my $non_optional; |
| 4560 |
|
my $i = -1; |
| 4561 |
|
|
| 4562 |
|
## 1. |
| 4563 |
|
for my $node (reverse @{$self->{open_elements}}) { |
| 4564 |
|
if ($node->[1] == LI_EL) { |
| 4565 |
|
## 2. (a) As if </li> |
| 4566 |
|
{ |
| 4567 |
|
## If no </li> - not applied |
| 4568 |
|
# |
| 4569 |
|
|
| 4570 |
|
## Otherwise |
| 4571 |
|
|
| 4572 |
|
## 1. generate implied end tags, except for </li> |
| 4573 |
|
# |
| 4574 |
|
|
| 4575 |
|
## 2. If current node != "li", parse error |
| 4576 |
|
if ($non_optional) { |
| 4577 |
|
!!!parse-error (type => 'not closed', |
| 4578 |
|
text => $non_optional->[0]->manakai_local_name, |
| 4579 |
|
token => $token); |
| 4580 |
|
!!!cp ('t355'); |
| 4581 |
|
} else { |
| 4582 |
|
!!!cp ('t356'); |
| 4583 |
|
} |
| 4584 |
|
|
| 4585 |
|
## 3. Pop |
| 4586 |
|
splice @{$self->{open_elements}}, $i; |
| 4587 |
|
} |
| 4588 |
|
|
| 4589 |
|
last; ## 2. (b) goto 5. |
| 4590 |
|
} elsif ( |
| 4591 |
|
## NOTE: not "formatting" and not "phrasing" |
| 4592 |
|
($node->[1] & SPECIAL_EL or |
| 4593 |
|
$node->[1] & SCOPING_EL) and |
| 4594 |
|
## NOTE: "li", "dt", and "dd" are in |SPECIAL_EL|. |
| 4595 |
|
(not $node->[1] & ADDRESS_DIV_P_EL) |
| 4596 |
|
) { |
| 4597 |
|
## 3. |
| 4598 |
|
!!!cp ('t357'); |
| 4599 |
|
last; ## goto 5. |
| 4600 |
|
} elsif ($node->[1] & END_TAG_OPTIONAL_EL) { |
| 4601 |
|
!!!cp ('t358'); |
| 4602 |
|
# |
| 4603 |
|
} else { |
| 4604 |
|
!!!cp ('t359'); |
| 4605 |
|
$non_optional ||= $node; |
| 4606 |
|
# |
| 4607 |
|
} |
| 4608 |
|
## 4. |
| 4609 |
|
## goto 2. |
| 4610 |
|
$i--; |
| 4611 |
|
} |
| 4612 |
|
|
| 4613 |
|
## 5. (a) has a |p| element in scope |
| 4614 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4615 |
if ($_->[1] & P_EL) { |
if ($_->[1] == P_EL) { |
| 4616 |
!!!cp ('t353'); |
!!!cp ('t353'); |
| 4617 |
|
|
| 4618 |
|
## NOTE: |<p><li>|, for example. |
| 4619 |
|
|
| 4620 |
!!!back-token; # <x> |
!!!back-token; # <x> |
| 4621 |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
| 4622 |
line => $token->{line}, column => $token->{column}}; |
line => $token->{line}, column => $token->{column}}; |
| 4626 |
last INSCOPE; |
last INSCOPE; |
| 4627 |
} |
} |
| 4628 |
} # INSCOPE |
} # INSCOPE |
| 4629 |
|
|
| 4630 |
## Step 1 |
## 5. (b) insert |
| 4631 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 4632 |
|
!!!nack ('t359.1'); |
| 4633 |
|
!!!next-token; |
| 4634 |
|
next B; |
| 4635 |
|
} elsif ($token->{tag_name} eq 'dt' or |
| 4636 |
|
$token->{tag_name} eq 'dd') { |
| 4637 |
|
## NOTE: As normal, but imply </dt> or </dd> when ... |
| 4638 |
|
|
| 4639 |
|
my $non_optional; |
| 4640 |
my $i = -1; |
my $i = -1; |
| 4641 |
my $node = $self->{open_elements}->[$i]; |
|
| 4642 |
my $li_or_dtdd = {li => {li => 1}, |
## 1. |
| 4643 |
dt => {dt => 1, dd => 1}, |
for my $node (reverse @{$self->{open_elements}}) { |
| 4644 |
dd => {dt => 1, dd => 1}}->{$token->{tag_name}}; |
if ($node->[1] == DTDD_EL) { |
| 4645 |
LI: { |
## 2. (a) As if </li> |
| 4646 |
## Step 2 |
{ |
| 4647 |
if ($li_or_dtdd->{$node->[0]->manakai_local_name}) { |
## If no </li> - not applied |
| 4648 |
if ($i != -1) { |
# |
| 4649 |
!!!cp ('t355'); |
|
| 4650 |
!!!parse-error (type => 'not closed', |
## Otherwise |
| 4651 |
value => $self->{open_elements}->[-1]->[0] |
|
| 4652 |
->manakai_local_name, |
## 1. generate implied end tags, except for </dt> or </dd> |
| 4653 |
token => $token); |
# |
| 4654 |
} else { |
|
| 4655 |
!!!cp ('t356'); |
## 2. If current node != "dt"|"dd", parse error |
| 4656 |
|
if ($non_optional) { |
| 4657 |
|
!!!parse-error (type => 'not closed', |
| 4658 |
|
text => $non_optional->[0]->manakai_local_name, |
| 4659 |
|
token => $token); |
| 4660 |
|
!!!cp ('t355.1'); |
| 4661 |
|
} else { |
| 4662 |
|
!!!cp ('t356.1'); |
| 4663 |
|
} |
| 4664 |
|
|
| 4665 |
|
## 3. Pop |
| 4666 |
|
splice @{$self->{open_elements}}, $i; |
| 4667 |
} |
} |
| 4668 |
splice @{$self->{open_elements}}, $i; |
|
| 4669 |
last LI; |
last; ## 2. (b) goto 5. |
| 4670 |
|
} elsif ( |
| 4671 |
|
## NOTE: not "formatting" and not "phrasing" |
| 4672 |
|
($node->[1] & SPECIAL_EL or |
| 4673 |
|
$node->[1] & SCOPING_EL) and |
| 4674 |
|
## NOTE: "li", "dt", and "dd" are in |SPECIAL_EL|. |
| 4675 |
|
|
| 4676 |
|
(not $node->[1] & ADDRESS_DIV_P_EL) |
| 4677 |
|
) { |
| 4678 |
|
## 3. |
| 4679 |
|
!!!cp ('t357.1'); |
| 4680 |
|
last; ## goto 5. |
| 4681 |
|
} elsif ($node->[1] & END_TAG_OPTIONAL_EL) { |
| 4682 |
|
!!!cp ('t358.1'); |
| 4683 |
|
# |
| 4684 |
} else { |
} else { |
| 4685 |
!!!cp ('t357'); |
!!!cp ('t359.1'); |
| 4686 |
} |
$non_optional ||= $node; |
| 4687 |
|
# |
|
## Step 3 |
|
|
if (not ($node->[1] & FORMATTING_EL) and |
|
|
#not $phrasing_category->{$node->[1]} and |
|
|
($node->[1] & SPECIAL_EL or |
|
|
$node->[1] & SCOPING_EL) and |
|
|
not ($node->[1] & ADDRESS_EL) and |
|
|
not ($node->[1] & DIV_EL)) { |
|
|
!!!cp ('t358'); |
|
|
last LI; |
|
| 4688 |
} |
} |
| 4689 |
|
## 4. |
| 4690 |
!!!cp ('t359'); |
## goto 2. |
|
## Step 4 |
|
| 4691 |
$i--; |
$i--; |
| 4692 |
$node = $self->{open_elements}->[$i]; |
} |
| 4693 |
redo LI; |
|
| 4694 |
} # LI |
## 5. (a) has a |p| element in scope |
| 4695 |
|
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4696 |
|
if ($_->[1] == P_EL) { |
| 4697 |
|
!!!cp ('t353.1'); |
| 4698 |
|
!!!back-token; # <x> |
| 4699 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
| 4700 |
|
line => $token->{line}, column => $token->{column}}; |
| 4701 |
|
next B; |
| 4702 |
|
} elsif ($_->[1] & SCOPING_EL) { |
| 4703 |
|
!!!cp ('t354.1'); |
| 4704 |
|
last INSCOPE; |
| 4705 |
|
} |
| 4706 |
|
} # INSCOPE |
| 4707 |
|
|
| 4708 |
|
## 5. (b) insert |
| 4709 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 4710 |
!!!nack ('t359.1'); |
!!!nack ('t359.2'); |
| 4711 |
!!!next-token; |
!!!next-token; |
| 4712 |
next B; |
next B; |
| 4713 |
} elsif ($token->{tag_name} eq 'plaintext') { |
} elsif ($token->{tag_name} eq 'plaintext') { |
| 4714 |
|
## NOTE: As normal, but effectively ends parsing |
| 4715 |
|
|
| 4716 |
## has a p element in scope |
## has a p element in scope |
| 4717 |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
INSCOPE: for (reverse @{$self->{open_elements}}) { |
| 4718 |
if ($_->[1] & P_EL) { |
if ($_->[1] == P_EL) { |
| 4719 |
!!!cp ('t367'); |
!!!cp ('t367'); |
| 4720 |
!!!back-token; # <plaintext> |
!!!back-token; # <plaintext> |
| 4721 |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
$token = {type => END_TAG_TOKEN, tag_name => 'p', |
| 4737 |
} elsif ($token->{tag_name} eq 'a') { |
} elsif ($token->{tag_name} eq 'a') { |
| 4738 |
AFE: for my $i (reverse 0..$#$active_formatting_elements) { |
AFE: for my $i (reverse 0..$#$active_formatting_elements) { |
| 4739 |
my $node = $active_formatting_elements->[$i]; |
my $node = $active_formatting_elements->[$i]; |
| 4740 |
if ($node->[1] & A_EL) { |
if ($node->[1] == A_EL) { |
| 4741 |
!!!cp ('t371'); |
!!!cp ('t371'); |
| 4742 |
!!!parse-error (type => 'in a:a', token => $token); |
!!!parse-error (type => 'in a:a', token => $token); |
| 4743 |
|
|
| 4781 |
## has a |nobr| element in scope |
## has a |nobr| element in scope |
| 4782 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4783 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 4784 |
if ($node->[1] & NOBR_EL) { |
if ($node->[1] == NOBR_EL) { |
| 4785 |
!!!cp ('t376'); |
!!!cp ('t376'); |
| 4786 |
!!!parse-error (type => 'in nobr:nobr', token => $token); |
!!!parse-error (type => 'in nobr:nobr', token => $token); |
| 4787 |
!!!back-token; # <nobr> |
!!!back-token; # <nobr> |
| 4804 |
## has a button element in scope |
## has a button element in scope |
| 4805 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4806 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 4807 |
if ($node->[1] & BUTTON_EL) { |
if ($node->[1] == BUTTON_EL) { |
| 4808 |
!!!cp ('t378'); |
!!!cp ('t378'); |
| 4809 |
!!!parse-error (type => 'in button:button', token => $token); |
!!!parse-error (type => 'in button:button', token => $token); |
| 4810 |
!!!back-token; # <button> |
!!!back-token; # <button> |
| 4832 |
xmp => 1, |
xmp => 1, |
| 4833 |
iframe => 1, |
iframe => 1, |
| 4834 |
noembed => 1, |
noembed => 1, |
| 4835 |
noframes => 1, |
noframes => 1, ## NOTE: This is an "as if in head" code clone. |
| 4836 |
noscript => 0, ## TODO: 1 if scripting is enabled |
noscript => 0, ## TODO: 1 if scripting is enabled |
| 4837 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 4838 |
if ($token->{tag_name} eq 'xmp') { |
if ($token->{tag_name} eq 'xmp') { |
| 4854 |
!!!next-token; |
!!!next-token; |
| 4855 |
next B; |
next B; |
| 4856 |
} else { |
} else { |
| 4857 |
|
!!!ack ('t391.1'); |
| 4858 |
|
|
| 4859 |
my $at = $token->{attributes}; |
my $at = $token->{attributes}; |
| 4860 |
my $form_attrs; |
my $form_attrs; |
| 4861 |
$form_attrs->{action} = $at->{action} if $at->{action}; |
$form_attrs->{action} = $at->{action} if $at->{action}; |
| 4869 |
line => $token->{line}, column => $token->{column}}, |
line => $token->{line}, column => $token->{column}}, |
| 4870 |
{type => START_TAG_TOKEN, tag_name => 'hr', |
{type => START_TAG_TOKEN, tag_name => 'hr', |
| 4871 |
line => $token->{line}, column => $token->{column}}, |
line => $token->{line}, column => $token->{column}}, |
|
{type => START_TAG_TOKEN, tag_name => 'p', |
|
|
line => $token->{line}, column => $token->{column}}, |
|
| 4872 |
{type => START_TAG_TOKEN, tag_name => 'label', |
{type => START_TAG_TOKEN, tag_name => 'label', |
| 4873 |
line => $token->{line}, column => $token->{column}}, |
line => $token->{line}, column => $token->{column}}, |
| 4874 |
); |
); |
| 4891 |
#{type => CHARACTER_TOKEN, data => ''}, # SHOULD |
#{type => CHARACTER_TOKEN, data => ''}, # SHOULD |
| 4892 |
{type => END_TAG_TOKEN, tag_name => 'label', |
{type => END_TAG_TOKEN, tag_name => 'label', |
| 4893 |
line => $token->{line}, column => $token->{column}}, |
line => $token->{line}, column => $token->{column}}, |
|
{type => END_TAG_TOKEN, tag_name => 'p', |
|
|
line => $token->{line}, column => $token->{column}}, |
|
| 4894 |
{type => START_TAG_TOKEN, tag_name => 'hr', |
{type => START_TAG_TOKEN, tag_name => 'hr', |
| 4895 |
line => $token->{line}, column => $token->{column}}, |
line => $token->{line}, column => $token->{column}}, |
| 4896 |
{type => END_TAG_TOKEN, tag_name => 'form', |
{type => END_TAG_TOKEN, tag_name => 'form', |
| 4897 |
line => $token->{line}, column => $token->{column}}; |
line => $token->{line}, column => $token->{column}}; |
|
!!!nack ('t391.1'); ## NOTE: Not acknowledged. |
|
| 4898 |
!!!back-token (@tokens); |
!!!back-token (@tokens); |
| 4899 |
!!!next-token; |
!!!next-token; |
| 4900 |
next B; |
next B; |
| 4901 |
} |
} |
| 4902 |
} elsif ($token->{tag_name} eq 'textarea') { |
} elsif ($token->{tag_name} eq 'textarea') { |
| 4903 |
my $tag_name = $token->{tag_name}; |
## 1. Insert |
| 4904 |
my $el; |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
|
!!!create-element ($el, $HTML_NS, $token->{tag_name}, $token->{attributes}, $token); |
|
| 4905 |
|
|
| 4906 |
|
## Step 2 # XXX |
| 4907 |
## TODO: $self->{form_element} if defined |
## TODO: $self->{form_element} if defined |
| 4908 |
|
|
| 4909 |
|
## 2. Drop U+000A LINE FEED |
| 4910 |
|
$self->{ignore_newline} = 1; |
| 4911 |
|
|
| 4912 |
|
## 3. RCDATA |
| 4913 |
$self->{content_model} = RCDATA_CONTENT_MODEL; |
$self->{content_model} = RCDATA_CONTENT_MODEL; |
| 4914 |
delete $self->{escape}; # MUST |
delete $self->{escape}; # MUST |
| 4915 |
|
|
| 4916 |
$insert->($el); |
## 4., 6. Insertion mode |
| 4917 |
|
$self->{insertion_mode} |= IN_CDATA_RCDATA_IM; |
| 4918 |
my $text = ''; |
|
| 4919 |
|
## XXX: 5. frameset-ok flag |
| 4920 |
|
|
| 4921 |
!!!nack ('t392.1'); |
!!!nack ('t392.1'); |
| 4922 |
!!!next-token; |
!!!next-token; |
| 4923 |
if ($token->{type} == CHARACTER_TOKEN) { |
next B; |
| 4924 |
$token->{data} =~ s/^\x0A//; |
} elsif ($token->{tag_name} eq 'optgroup' or |
| 4925 |
unless (length $token->{data}) { |
$token->{tag_name} eq 'option') { |
| 4926 |
!!!cp ('t392'); |
## has an |option| element in scope |
| 4927 |
!!!next-token; |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4928 |
} else { |
my $node = $self->{open_elements}->[$_]; |
| 4929 |
!!!cp ('t393'); |
if ($node->[1] == OPTION_EL) { |
| 4930 |
|
!!!cp ('t397.1'); |
| 4931 |
|
## NOTE: As if </option> |
| 4932 |
|
!!!back-token; # <option> or <optgroup> |
| 4933 |
|
$token = {type => END_TAG_TOKEN, tag_name => 'option', |
| 4934 |
|
line => $token->{line}, column => $token->{column}}; |
| 4935 |
|
next B; |
| 4936 |
|
} elsif ($node->[1] & SCOPING_EL) { |
| 4937 |
|
!!!cp ('t397.2'); |
| 4938 |
|
last INSCOPE; |
| 4939 |
} |
} |
| 4940 |
} else { |
} # INSCOPE |
| 4941 |
!!!cp ('t394'); |
|
| 4942 |
} |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4943 |
while ($token->{type} == CHARACTER_TOKEN) { |
|
| 4944 |
!!!cp ('t395'); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 4945 |
$text .= $token->{data}; |
|
| 4946 |
!!!next-token; |
!!!nack ('t397.3'); |
|
} |
|
|
if (length $text) { |
|
|
!!!cp ('t396'); |
|
|
$el->manakai_append_text ($text); |
|
|
} |
|
|
|
|
|
$self->{content_model} = PCDATA_CONTENT_MODEL; |
|
|
|
|
|
if ($token->{type} == END_TAG_TOKEN and |
|
|
$token->{tag_name} eq $tag_name) { |
|
|
!!!cp ('t397'); |
|
|
## Ignore the token |
|
|
} else { |
|
|
!!!cp ('t398'); |
|
|
!!!parse-error (type => 'in RCDATA:#'.$token->{type}, token => $token); |
|
|
} |
|
| 4947 |
!!!next-token; |
!!!next-token; |
| 4948 |
next B; |
redo B; |
| 4949 |
|
} elsif ($token->{tag_name} eq 'rt' or |
| 4950 |
|
$token->{tag_name} eq 'rp') { |
| 4951 |
|
## has a |ruby| element in scope |
| 4952 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 4953 |
|
my $node = $self->{open_elements}->[$_]; |
| 4954 |
|
if ($node->[1] == RUBY_EL) { |
| 4955 |
|
!!!cp ('t398.1'); |
| 4956 |
|
## generate implied end tags |
| 4957 |
|
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 4958 |
|
!!!cp ('t398.2'); |
| 4959 |
|
pop @{$self->{open_elements}}; |
| 4960 |
|
} |
| 4961 |
|
unless ($self->{open_elements}->[-1]->[1] == RUBY_EL) { |
| 4962 |
|
!!!cp ('t398.3'); |
| 4963 |
|
!!!parse-error (type => 'not closed', |
| 4964 |
|
text => $self->{open_elements}->[-1]->[0] |
| 4965 |
|
->manakai_local_name, |
| 4966 |
|
token => $token); |
| 4967 |
|
pop @{$self->{open_elements}} |
| 4968 |
|
while not $self->{open_elements}->[-1]->[1] == RUBY_EL; |
| 4969 |
|
} |
| 4970 |
|
last INSCOPE; |
| 4971 |
|
} elsif ($node->[1] & SCOPING_EL) { |
| 4972 |
|
!!!cp ('t398.4'); |
| 4973 |
|
last INSCOPE; |
| 4974 |
|
} |
| 4975 |
|
} # INSCOPE |
| 4976 |
|
|
| 4977 |
|
## TODO: <non-ruby><rt> is not allowed. |
| 4978 |
|
|
| 4979 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 4980 |
|
|
| 4981 |
|
!!!nack ('t398.5'); |
| 4982 |
|
!!!next-token; |
| 4983 |
|
redo B; |
| 4984 |
} elsif ($token->{tag_name} eq 'math' or |
} elsif ($token->{tag_name} eq 'math' or |
| 4985 |
$token->{tag_name} eq 'svg') { |
$token->{tag_name} eq 'svg') { |
| 4986 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 4987 |
|
|
| 4988 |
|
## "Adjust MathML attributes" ('math' only) - done in insert-element-f |
| 4989 |
|
|
| 4990 |
## "adjust SVG attributes" ('svg' only) - done in insert-element-f |
## "adjust SVG attributes" ('svg' only) - done in insert-element-f |
| 4991 |
|
|
| 4992 |
## "adjust foreign attributes" - done in insert-element-f |
## "adjust foreign attributes" - done in insert-element-f |
| 4995 |
|
|
| 4996 |
if ($self->{self_closing}) { |
if ($self->{self_closing}) { |
| 4997 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 4998 |
!!!ack ('t398.1'); |
!!!ack ('t398.6'); |
| 4999 |
} else { |
} else { |
| 5000 |
!!!cp ('t398.2'); |
!!!cp ('t398.7'); |
| 5001 |
$self->{insertion_mode} |= IN_FOREIGN_CONTENT_IM; |
$self->{insertion_mode} |= IN_FOREIGN_CONTENT_IM; |
| 5002 |
## NOTE: |<body><math><mi><svg>| -> "in foreign content" insertion |
## NOTE: |<body><math><mi><svg>| -> "in foreign content" insertion |
| 5003 |
## mode, "in body" (not "in foreign content") secondary insertion |
## mode, "in body" (not "in foreign content") secondary insertion |
| 5008 |
next B; |
next B; |
| 5009 |
} elsif ({ |
} elsif ({ |
| 5010 |
caption => 1, col => 1, colgroup => 1, frame => 1, |
caption => 1, col => 1, colgroup => 1, frame => 1, |
| 5011 |
frameset => 1, head => 1, option => 1, optgroup => 1, |
frameset => 1, head => 1, |
| 5012 |
tbody => 1, td => 1, tfoot => 1, th => 1, |
tbody => 1, td => 1, tfoot => 1, th => 1, |
| 5013 |
thead => 1, tr => 1, |
thead => 1, tr => 1, |
| 5014 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5015 |
!!!cp ('t401'); |
!!!cp ('t401'); |
| 5016 |
!!!parse-error (type => 'in body:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'in body', |
| 5017 |
|
text => $token->{tag_name}, token => $token); |
| 5018 |
## Ignore the token |
## Ignore the token |
| 5019 |
!!!nack ('t401.1'); ## NOTE: |<col/>| or |<frame/>| here is an error. |
!!!nack ('t401.1'); ## NOTE: |<col/>| or |<frame/>| here is an error. |
| 5020 |
!!!next-token; |
!!!next-token; |
| 5021 |
next B; |
next B; |
| 5022 |
|
} elsif ($token->{tag_name} eq 'param' or |
| 5023 |
## ISSUE: An issue on HTML5 new elements in the spec. |
$token->{tag_name} eq 'source') { |
| 5024 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}, $token); |
| 5025 |
|
pop @{$self->{open_elements}}; |
| 5026 |
|
|
| 5027 |
|
!!!ack ('t398.5'); |
| 5028 |
|
!!!next-token; |
| 5029 |
|
redo B; |
| 5030 |
} else { |
} else { |
| 5031 |
if ($token->{tag_name} eq 'image') { |
if ($token->{tag_name} eq 'image') { |
| 5032 |
!!!cp ('t384'); |
!!!cp ('t384'); |
| 5049 |
!!!nack ('t380.1'); |
!!!nack ('t380.1'); |
| 5050 |
} elsif ({ |
} elsif ({ |
| 5051 |
b => 1, big => 1, em => 1, font => 1, i => 1, |
b => 1, big => 1, em => 1, font => 1, i => 1, |
| 5052 |
s => 1, small => 1, strile => 1, |
s => 1, small => 1, strike => 1, |
| 5053 |
strong => 1, tt => 1, u => 1, |
strong => 1, tt => 1, u => 1, |
| 5054 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5055 |
!!!cp ('t375'); |
!!!cp ('t375'); |
| 5062 |
!!!ack ('t388.2'); |
!!!ack ('t388.2'); |
| 5063 |
} elsif ({ |
} elsif ({ |
| 5064 |
area => 1, basefont => 1, bgsound => 1, br => 1, |
area => 1, basefont => 1, bgsound => 1, br => 1, |
| 5065 |
embed => 1, img => 1, param => 1, spacer => 1, wbr => 1, |
embed => 1, img => 1, spacer => 1, wbr => 1, |
| 5066 |
#image => 1, |
keygen => 1, |
| 5067 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5068 |
!!!cp ('t388.1'); |
!!!cp ('t388.1'); |
| 5069 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5073 |
|
|
| 5074 |
if ($self->{insertion_mode} & TABLE_IMS or |
if ($self->{insertion_mode} & TABLE_IMS or |
| 5075 |
$self->{insertion_mode} & BODY_TABLE_IMS or |
$self->{insertion_mode} & BODY_TABLE_IMS or |
| 5076 |
$self->{insertion_mode} == IN_COLUMN_GROUP_IM) { |
($self->{insertion_mode} & IM_MASK) == IN_COLUMN_GROUP_IM) { |
| 5077 |
!!!cp ('t400.1'); |
!!!cp ('t400.1'); |
| 5078 |
$self->{insertion_mode} = IN_SELECT_IN_TABLE_IM; |
$self->{insertion_mode} = IN_SELECT_IN_TABLE_IM; |
| 5079 |
} else { |
} else { |
| 5090 |
} |
} |
| 5091 |
} elsif ($token->{type} == END_TAG_TOKEN) { |
} elsif ($token->{type} == END_TAG_TOKEN) { |
| 5092 |
if ($token->{tag_name} eq 'body') { |
if ($token->{tag_name} eq 'body') { |
| 5093 |
## has a |body| element in scope |
|
| 5094 |
|
## 1. If not "have an element in scope": |
| 5095 |
|
## "has a |body| element in scope" |
| 5096 |
my $i; |
my $i; |
| 5097 |
INSCOPE: { |
INSCOPE: { |
| 5098 |
for (reverse @{$self->{open_elements}}) { |
for (reverse @{$self->{open_elements}}) { |
| 5099 |
if ($_->[1] & BODY_EL) { |
if ($_->[1] == BODY_EL) { |
| 5100 |
!!!cp ('t405'); |
!!!cp ('t405'); |
| 5101 |
$i = $_; |
$i = $_; |
| 5102 |
last INSCOPE; |
last INSCOPE; |
| 5106 |
} |
} |
| 5107 |
} |
} |
| 5108 |
|
|
| 5109 |
!!!parse-error (type => 'start tag not allowed', |
## NOTE: |<marquee></body>|, |<svg><foreignobject></body>| |
| 5110 |
value => $token->{tag_name}, token => $token); |
|
| 5111 |
|
!!!parse-error (type => 'unmatched end tag', |
| 5112 |
|
text => $token->{tag_name}, token => $token); |
| 5113 |
## NOTE: Ignore the token. |
## NOTE: Ignore the token. |
| 5114 |
!!!next-token; |
!!!next-token; |
| 5115 |
next B; |
next B; |
| 5116 |
} # INSCOPE |
} # INSCOPE |
| 5117 |
|
|
| 5118 |
|
## 2. If unclosed elements: |
| 5119 |
for (@{$self->{open_elements}}) { |
for (@{$self->{open_elements}}) { |
| 5120 |
unless ($_->[1] & ALL_END_TAG_OPTIONAL_EL) { |
unless ($_->[1] & ALL_END_TAG_OPTIONAL_EL || |
| 5121 |
|
$_->[1] == OPTGROUP_EL || |
| 5122 |
|
$_->[1] == OPTION_EL || |
| 5123 |
|
$_->[1] == RUBY_COMPONENT_EL) { |
| 5124 |
!!!cp ('t403'); |
!!!cp ('t403'); |
| 5125 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5126 |
value => $_->[0]->manakai_local_name, |
text => $_->[0]->manakai_local_name, |
| 5127 |
token => $token); |
token => $token); |
| 5128 |
last; |
last; |
| 5129 |
} else { |
} else { |
| 5131 |
} |
} |
| 5132 |
} |
} |
| 5133 |
|
|
| 5134 |
|
## 3. Switch the insertion mode. |
| 5135 |
$self->{insertion_mode} = AFTER_BODY_IM; |
$self->{insertion_mode} = AFTER_BODY_IM; |
| 5136 |
!!!next-token; |
!!!next-token; |
| 5137 |
next B; |
next B; |
| 5139 |
## TODO: Update this code. It seems that the code below is not |
## TODO: Update this code. It seems that the code below is not |
| 5140 |
## up-to-date, though it has same effect as speced. |
## up-to-date, though it has same effect as speced. |
| 5141 |
if (@{$self->{open_elements}} > 1 and |
if (@{$self->{open_elements}} > 1 and |
| 5142 |
$self->{open_elements}->[1]->[1] & BODY_EL) { |
$self->{open_elements}->[1]->[1] == BODY_EL) { |
| 5143 |
## ISSUE: There is an issue in the spec. |
unless ($self->{open_elements}->[-1]->[1] == BODY_EL) { |
|
unless ($self->{open_elements}->[-1]->[1] & BODY_EL) { |
|
| 5144 |
!!!cp ('t406'); |
!!!cp ('t406'); |
| 5145 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5146 |
value => $self->{open_elements}->[1]->[0] |
text => $self->{open_elements}->[1]->[0] |
| 5147 |
->manakai_local_name, |
->manakai_local_name, |
| 5148 |
token => $token); |
token => $token); |
| 5149 |
} else { |
} else { |
| 5154 |
next B; |
next B; |
| 5155 |
} else { |
} else { |
| 5156 |
!!!cp ('t408'); |
!!!cp ('t408'); |
| 5157 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5158 |
|
text => $token->{tag_name}, token => $token); |
| 5159 |
## Ignore the token |
## Ignore the token |
| 5160 |
!!!next-token; |
!!!next-token; |
| 5161 |
next B; |
next B; |
| 5162 |
} |
} |
| 5163 |
} elsif ({ |
} elsif ({ |
| 5164 |
address => 1, blockquote => 1, center => 1, dir => 1, |
## NOTE: End tags for non-phrasing flow content elements |
| 5165 |
div => 1, dl => 1, fieldset => 1, listing => 1, |
|
| 5166 |
menu => 1, ol => 1, pre => 1, ul => 1, |
## NOTE: The normal ones |
| 5167 |
|
address => 1, article => 1, aside => 1, blockquote => 1, |
| 5168 |
|
center => 1, datagrid => 1, details => 1, dialog => 1, |
| 5169 |
|
dir => 1, div => 1, dl => 1, fieldset => 1, figure => 1, |
| 5170 |
|
footer => 1, header => 1, listing => 1, menu => 1, nav => 1, |
| 5171 |
|
ol => 1, pre => 1, section => 1, ul => 1, |
| 5172 |
|
|
| 5173 |
|
## NOTE: As normal, but ... optional tags |
| 5174 |
dd => 1, dt => 1, li => 1, |
dd => 1, dt => 1, li => 1, |
| 5175 |
|
|
| 5176 |
applet => 1, button => 1, marquee => 1, object => 1, |
applet => 1, button => 1, marquee => 1, object => 1, |
| 5177 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5178 |
|
## NOTE: Code for <li> start tags includes "as if </li>" code. |
| 5179 |
|
## Code for <dt> or <dd> start tags includes "as if </dt> or |
| 5180 |
|
## </dd>" code. |
| 5181 |
|
|
| 5182 |
## has an element in scope |
## has an element in scope |
| 5183 |
my $i; |
my $i; |
| 5184 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5195 |
|
|
| 5196 |
unless (defined $i) { # has an element in scope |
unless (defined $i) { # has an element in scope |
| 5197 |
!!!cp ('t413'); |
!!!cp ('t413'); |
| 5198 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5199 |
|
text => $token->{tag_name}, token => $token); |
| 5200 |
|
## NOTE: Ignore the token. |
| 5201 |
} else { |
} else { |
| 5202 |
## Step 1. generate implied end tags |
## Step 1. generate implied end tags |
| 5203 |
while ({ |
while ({ |
| 5204 |
|
## END_TAG_OPTIONAL_EL |
| 5205 |
dd => ($token->{tag_name} ne 'dd'), |
dd => ($token->{tag_name} ne 'dd'), |
| 5206 |
dt => ($token->{tag_name} ne 'dt'), |
dt => ($token->{tag_name} ne 'dt'), |
| 5207 |
li => ($token->{tag_name} ne 'li'), |
li => ($token->{tag_name} ne 'li'), |
| 5208 |
|
option => 1, |
| 5209 |
|
optgroup => 1, |
| 5210 |
p => 1, |
p => 1, |
| 5211 |
|
rt => 1, |
| 5212 |
|
rp => 1, |
| 5213 |
}->{$self->{open_elements}->[-1]->[0]->manakai_local_name}) { |
}->{$self->{open_elements}->[-1]->[0]->manakai_local_name}) { |
| 5214 |
!!!cp ('t409'); |
!!!cp ('t409'); |
| 5215 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5220 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 5221 |
!!!cp ('t412'); |
!!!cp ('t412'); |
| 5222 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5223 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5224 |
->manakai_local_name, |
->manakai_local_name, |
| 5225 |
token => $token); |
token => $token); |
| 5226 |
} else { |
} else { |
| 5239 |
!!!next-token; |
!!!next-token; |
| 5240 |
next B; |
next B; |
| 5241 |
} elsif ($token->{tag_name} eq 'form') { |
} elsif ($token->{tag_name} eq 'form') { |
| 5242 |
|
## NOTE: As normal, but interacts with the form element pointer |
| 5243 |
|
|
| 5244 |
undef $self->{form_element}; |
undef $self->{form_element}; |
| 5245 |
|
|
| 5246 |
## has an element in scope |
## has an element in scope |
| 5247 |
my $i; |
my $i; |
| 5248 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5249 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5250 |
if ($node->[1] & FORM_EL) { |
if ($node->[1] == FORM_EL) { |
| 5251 |
!!!cp ('t418'); |
!!!cp ('t418'); |
| 5252 |
$i = $_; |
$i = $_; |
| 5253 |
last INSCOPE; |
last INSCOPE; |
| 5259 |
|
|
| 5260 |
unless (defined $i) { # has an element in scope |
unless (defined $i) { # has an element in scope |
| 5261 |
!!!cp ('t421'); |
!!!cp ('t421'); |
| 5262 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5263 |
|
text => $token->{tag_name}, token => $token); |
| 5264 |
|
## NOTE: Ignore the token. |
| 5265 |
} else { |
} else { |
| 5266 |
## Step 1. generate implied end tags |
## Step 1. generate implied end tags |
| 5267 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 5274 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 5275 |
!!!cp ('t417.1'); |
!!!cp ('t417.1'); |
| 5276 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5277 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5278 |
->manakai_local_name, |
->manakai_local_name, |
| 5279 |
token => $token); |
token => $token); |
| 5280 |
} else { |
} else { |
| 5288 |
!!!next-token; |
!!!next-token; |
| 5289 |
next B; |
next B; |
| 5290 |
} elsif ({ |
} elsif ({ |
| 5291 |
|
## NOTE: As normal, except acts as a closer for any ... |
| 5292 |
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
| 5293 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5294 |
## has an element in scope |
## has an element in scope |
| 5295 |
my $i; |
my $i; |
| 5296 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5297 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5298 |
if ($node->[1] & HEADING_EL) { |
if ($node->[1] == HEADING_EL) { |
| 5299 |
!!!cp ('t423'); |
!!!cp ('t423'); |
| 5300 |
$i = $_; |
$i = $_; |
| 5301 |
last INSCOPE; |
last INSCOPE; |
| 5307 |
|
|
| 5308 |
unless (defined $i) { # has an element in scope |
unless (defined $i) { # has an element in scope |
| 5309 |
!!!cp ('t425.1'); |
!!!cp ('t425.1'); |
| 5310 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5311 |
|
text => $token->{tag_name}, token => $token); |
| 5312 |
|
## NOTE: Ignore the token. |
| 5313 |
} else { |
} else { |
| 5314 |
## Step 1. generate implied end tags |
## Step 1. generate implied end tags |
| 5315 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 5321 |
if ($self->{open_elements}->[-1]->[0]->manakai_local_name |
if ($self->{open_elements}->[-1]->[0]->manakai_local_name |
| 5322 |
ne $token->{tag_name}) { |
ne $token->{tag_name}) { |
| 5323 |
!!!cp ('t425'); |
!!!cp ('t425'); |
| 5324 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5325 |
|
text => $token->{tag_name}, token => $token); |
| 5326 |
} else { |
} else { |
| 5327 |
!!!cp ('t426'); |
!!!cp ('t426'); |
| 5328 |
} |
} |
| 5334 |
!!!next-token; |
!!!next-token; |
| 5335 |
next B; |
next B; |
| 5336 |
} elsif ($token->{tag_name} eq 'p') { |
} elsif ($token->{tag_name} eq 'p') { |
| 5337 |
|
## NOTE: As normal, except </p> implies <p> and ... |
| 5338 |
|
|
| 5339 |
## has an element in scope |
## has an element in scope |
| 5340 |
|
my $non_optional; |
| 5341 |
my $i; |
my $i; |
| 5342 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 5343 |
my $node = $self->{open_elements}->[$_]; |
my $node = $self->{open_elements}->[$_]; |
| 5344 |
if ($node->[1] & P_EL) { |
if ($node->[1] == P_EL) { |
| 5345 |
!!!cp ('t410.1'); |
!!!cp ('t410.1'); |
| 5346 |
$i = $_; |
$i = $_; |
| 5347 |
last INSCOPE; |
last INSCOPE; |
| 5348 |
} elsif ($node->[1] & SCOPING_EL) { |
} elsif ($node->[1] & SCOPING_EL) { |
| 5349 |
!!!cp ('t411.1'); |
!!!cp ('t411.1'); |
| 5350 |
last INSCOPE; |
last INSCOPE; |
| 5351 |
|
} elsif ($node->[1] & END_TAG_OPTIONAL_EL) { |
| 5352 |
|
## NOTE: |END_TAG_OPTIONAL_EL| includes "p" |
| 5353 |
|
!!!cp ('t411.2'); |
| 5354 |
|
# |
| 5355 |
|
} else { |
| 5356 |
|
!!!cp ('t411.3'); |
| 5357 |
|
$non_optional ||= $node; |
| 5358 |
|
# |
| 5359 |
} |
} |
| 5360 |
} # INSCOPE |
} # INSCOPE |
| 5361 |
|
|
| 5362 |
if (defined $i) { |
if (defined $i) { |
| 5363 |
if ($self->{open_elements}->[-1]->[0]->manakai_local_name |
## 1. Generate implied end tags |
| 5364 |
ne $token->{tag_name}) { |
# |
| 5365 |
|
|
| 5366 |
|
## 2. If current node != "p", parse error |
| 5367 |
|
if ($non_optional) { |
| 5368 |
!!!cp ('t412.1'); |
!!!cp ('t412.1'); |
| 5369 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5370 |
value => $self->{open_elements}->[-1]->[0] |
text => $non_optional->[0]->manakai_local_name, |
|
->manakai_local_name, |
|
| 5371 |
token => $token); |
token => $token); |
| 5372 |
} else { |
} else { |
| 5373 |
!!!cp ('t414.1'); |
!!!cp ('t414.1'); |
| 5374 |
} |
} |
| 5375 |
|
|
| 5376 |
|
## 3. Pop |
| 5377 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 5378 |
} else { |
} else { |
| 5379 |
!!!cp ('t413.1'); |
!!!cp ('t413.1'); |
| 5380 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5381 |
|
text => $token->{tag_name}, token => $token); |
| 5382 |
|
|
| 5383 |
!!!cp ('t415.1'); |
!!!cp ('t415.1'); |
| 5384 |
## As if <p>, then reprocess the current token |
## As if <p>, then reprocess the current token |
| 5393 |
} elsif ({ |
} elsif ({ |
| 5394 |
a => 1, |
a => 1, |
| 5395 |
b => 1, big => 1, em => 1, font => 1, i => 1, |
b => 1, big => 1, em => 1, font => 1, i => 1, |
| 5396 |
nobr => 1, s => 1, small => 1, strile => 1, |
nobr => 1, s => 1, small => 1, strike => 1, |
| 5397 |
strong => 1, tt => 1, u => 1, |
strong => 1, tt => 1, u => 1, |
| 5398 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 5399 |
!!!cp ('t427'); |
!!!cp ('t427'); |
| 5401 |
next B; |
next B; |
| 5402 |
} elsif ($token->{tag_name} eq 'br') { |
} elsif ($token->{tag_name} eq 'br') { |
| 5403 |
!!!cp ('t428'); |
!!!cp ('t428'); |
| 5404 |
!!!parse-error (type => 'unmatched end tag:br', token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5405 |
|
text => 'br', token => $token); |
| 5406 |
|
|
| 5407 |
## As if <br> |
## As if <br> |
| 5408 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 5414 |
## Ignore the token. |
## Ignore the token. |
| 5415 |
!!!next-token; |
!!!next-token; |
| 5416 |
next B; |
next B; |
|
} elsif ({ |
|
|
caption => 1, col => 1, colgroup => 1, frame => 1, |
|
|
frameset => 1, head => 1, option => 1, optgroup => 1, |
|
|
tbody => 1, td => 1, tfoot => 1, th => 1, |
|
|
thead => 1, tr => 1, |
|
|
area => 1, basefont => 1, bgsound => 1, |
|
|
embed => 1, hr => 1, iframe => 1, image => 1, |
|
|
img => 1, input => 1, isindex => 1, noembed => 1, |
|
|
noframes => 1, param => 1, select => 1, spacer => 1, |
|
|
table => 1, textarea => 1, wbr => 1, |
|
|
noscript => 0, ## TODO: if scripting is enabled |
|
|
}->{$token->{tag_name}}) { |
|
|
!!!cp ('t429'); |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
next B; |
|
|
|
|
|
## ISSUE: Issue on HTML5 new elements in spec |
|
|
|
|
| 5417 |
} else { |
} else { |
| 5418 |
|
if ($token->{tag_name} eq 'sarcasm') { |
| 5419 |
|
sleep 0.001; # take a deep breath |
| 5420 |
|
} |
| 5421 |
|
|
| 5422 |
## Step 1 |
## Step 1 |
| 5423 |
my $node_i = -1; |
my $node_i = -1; |
| 5424 |
my $node = $self->{open_elements}->[$node_i]; |
my $node = $self->{open_elements}->[$node_i]; |
| 5425 |
|
|
| 5426 |
## Step 2 |
## Step 2 |
| 5427 |
S2: { |
S2: { |
| 5428 |
if ($node->[0]->manakai_local_name eq $token->{tag_name}) { |
my $node_tag_name = $node->[0]->manakai_local_name; |
| 5429 |
|
$node_tag_name =~ tr/A-Z/a-z/; # for SVG camelCase tag names |
| 5430 |
|
if ($node_tag_name eq $token->{tag_name}) { |
| 5431 |
## Step 1 |
## Step 1 |
| 5432 |
## generate implied end tags |
## generate implied end tags |
| 5433 |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
while ($self->{open_elements}->[-1]->[1] & END_TAG_OPTIONAL_EL) { |
| 5434 |
!!!cp ('t430'); |
!!!cp ('t430'); |
| 5435 |
## ISSUE: Can this case be reached? |
## NOTE: |<ruby><rt></ruby>|. |
| 5436 |
|
## ISSUE: <ruby><rt></rt> will also take this code path, |
| 5437 |
|
## which seems wrong. |
| 5438 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 5439 |
|
$node_i++; |
| 5440 |
} |
} |
| 5441 |
|
|
| 5442 |
## Step 2 |
## Step 2 |
| 5443 |
if ($self->{open_elements}->[-1]->[0]->manakai_local_name |
my $current_tag_name |
| 5444 |
ne $token->{tag_name}) { |
= $self->{open_elements}->[-1]->[0]->manakai_local_name; |
| 5445 |
|
$current_tag_name =~ tr/A-Z/a-z/; |
| 5446 |
|
if ($current_tag_name ne $token->{tag_name}) { |
| 5447 |
!!!cp ('t431'); |
!!!cp ('t431'); |
| 5448 |
## NOTE: <x><y></x> |
## NOTE: <x><y></x> |
| 5449 |
!!!parse-error (type => 'not closed', |
!!!parse-error (type => 'not closed', |
| 5450 |
value => $self->{open_elements}->[-1]->[0] |
text => $self->{open_elements}->[-1]->[0] |
| 5451 |
->manakai_local_name, |
->manakai_local_name, |
| 5452 |
token => $token); |
token => $token); |
| 5453 |
} else { |
} else { |
| 5455 |
} |
} |
| 5456 |
|
|
| 5457 |
## Step 3 |
## Step 3 |
| 5458 |
splice @{$self->{open_elements}}, $node_i; |
splice @{$self->{open_elements}}, $node_i if $node_i < 0; |
| 5459 |
|
|
| 5460 |
!!!next-token; |
!!!next-token; |
| 5461 |
last S2; |
last S2; |
| 5466 |
($node->[1] & SPECIAL_EL or |
($node->[1] & SPECIAL_EL or |
| 5467 |
$node->[1] & SCOPING_EL)) { |
$node->[1] & SCOPING_EL)) { |
| 5468 |
!!!cp ('t433'); |
!!!cp ('t433'); |
| 5469 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}, token => $token); |
!!!parse-error (type => 'unmatched end tag', |
| 5470 |
|
text => $token->{tag_name}, token => $token); |
| 5471 |
## Ignore the token |
## Ignore the token |
| 5472 |
!!!next-token; |
!!!next-token; |
| 5473 |
last S2; |
last S2; |
|
} |
|
| 5474 |
|
|
| 5475 |
|
## NOTE: |<span><dd></span>a|: In Safari 3.1.2 and Opera |
| 5476 |
|
## 9.27, "a" is a child of <dd> (conforming). In |
| 5477 |
|
## Firefox 3.0.2, "a" is a child of <body>. In WinIE 7, |
| 5478 |
|
## "a" is a child of both <body> and <dd>. |
| 5479 |
|
} |
| 5480 |
|
|
| 5481 |
!!!cp ('t434'); |
!!!cp ('t434'); |
| 5482 |
} |
} |
| 5483 |
|
|
| 5518 |
## TODO: script stuffs |
## TODO: script stuffs |
| 5519 |
} # _tree_construct_main |
} # _tree_construct_main |
| 5520 |
|
|
| 5521 |
sub set_inner_html ($$$) { |
## XXX: How this method is organized is somewhat out of date, although |
| 5522 |
|
## it still does what the current spec documents. |
| 5523 |
|
sub set_inner_html ($$$$;$) { |
| 5524 |
my $class = shift; |
my $class = shift; |
| 5525 |
my $node = shift; |
my $node = shift; # /context/ |
| 5526 |
my $s = \$_[0]; |
#my $s = \$_[0]; |
| 5527 |
my $onerror = $_[1]; |
my $onerror = $_[1]; |
| 5528 |
|
my $get_wrapper = $_[2] || sub ($) { return $_[0] }; |
| 5529 |
|
|
| 5530 |
## ISSUE: Should {confident} be true? |
## ISSUE: Should {confident} be true? |
| 5531 |
|
|
| 5532 |
my $nt = $node->node_type; |
my $nt = $node->node_type; |
| 5533 |
if ($nt == 9) { |
if ($nt == 9) { # Document (invoke the algorithm with no /context/ element) |
| 5534 |
# MUST |
# MUST |
| 5535 |
|
|
| 5536 |
## Step 1 # MUST |
## Step 1 # MUST |
| 5544 |
} |
} |
| 5545 |
|
|
| 5546 |
## Step 3, 4, 5 # MUST |
## Step 3, 4, 5 # MUST |
| 5547 |
$class->parse_string ($$s => $node, $onerror); |
$class->parse_char_string ($_[0] => $node, $onerror, $get_wrapper); |
| 5548 |
} elsif ($nt == 1) { |
} elsif ($nt == 1) { # Element (invoke the algorithm with /context/ element) |
| 5549 |
## TODO: If non-html element |
## TODO: If non-html element |
| 5550 |
|
|
| 5551 |
## NOTE: Most of this code is copied from |parse_string| |
## NOTE: Most of this code is copied from |parse_string| |
| 5552 |
|
|
| 5553 |
## Step 1 # MUST |
## TODO: Support for $get_wrapper |
| 5554 |
|
|
| 5555 |
|
## F1. Create an HTML document. |
| 5556 |
my $this_doc = $node->owner_document; |
my $this_doc = $node->owner_document; |
| 5557 |
my $doc = $this_doc->implementation->create_document; |
my $doc = $this_doc->implementation->create_document; |
| 5558 |
$doc->manakai_is_html (1); |
$doc->manakai_is_html (1); |
| 5559 |
|
|
| 5560 |
|
## F2. Propagate quirkness flag |
| 5561 |
|
my $node_doc = $node->owner_document; |
| 5562 |
|
$doc->manakai_compat_mode ($node_doc->manakai_compat_mode); |
| 5563 |
|
|
| 5564 |
|
## F3. Create an HTML parser |
| 5565 |
my $p = $class->new; |
my $p = $class->new; |
| 5566 |
$p->{document} = $doc; |
$p->{document} = $doc; |
| 5567 |
|
|
| 5569 |
my $i = 0; |
my $i = 0; |
| 5570 |
$p->{line_prev} = $p->{line} = 1; |
$p->{line_prev} = $p->{line} = 1; |
| 5571 |
$p->{column_prev} = $p->{column} = 0; |
$p->{column_prev} = $p->{column} = 0; |
| 5572 |
$p->{set_next_char} = sub { |
require Whatpm::Charset::DecodeHandle; |
| 5573 |
|
my $input = Whatpm::Charset::DecodeHandle::CharString->new (\($_[0])); |
| 5574 |
|
$input = $get_wrapper->($input); |
| 5575 |
|
$p->{set_nc} = sub { |
| 5576 |
my $self = shift; |
my $self = shift; |
| 5577 |
|
|
| 5578 |
pop @{$self->{prev_char}}; |
my $char = ''; |
| 5579 |
unshift @{$self->{prev_char}}, $self->{next_char}; |
if (defined $self->{next_nc}) { |
| 5580 |
|
$char = $self->{next_nc}; |
| 5581 |
$self->{next_char} = -1 and return if $i >= length $$s; |
delete $self->{next_nc}; |
| 5582 |
$self->{next_char} = ord substr $$s, $i++, 1; |
$self->{nc} = ord $char; |
| 5583 |
|
} else { |
| 5584 |
|
$self->{char_buffer} = ''; |
| 5585 |
|
$self->{char_buffer_pos} = 0; |
| 5586 |
|
|
| 5587 |
|
my $count = $input->manakai_read_until |
| 5588 |
|
($self->{char_buffer}, qr/[^\x00\x0A\x0D]/, |
| 5589 |
|
$self->{char_buffer_pos}); |
| 5590 |
|
if ($count) { |
| 5591 |
|
$self->{line_prev} = $self->{line}; |
| 5592 |
|
$self->{column_prev} = $self->{column}; |
| 5593 |
|
$self->{column}++; |
| 5594 |
|
$self->{nc} |
| 5595 |
|
= ord substr ($self->{char_buffer}, |
| 5596 |
|
$self->{char_buffer_pos}++, 1); |
| 5597 |
|
return; |
| 5598 |
|
} |
| 5599 |
|
|
| 5600 |
|
if ($input->read ($char, 1)) { |
| 5601 |
|
$self->{nc} = ord $char; |
| 5602 |
|
} else { |
| 5603 |
|
$self->{nc} = -1; |
| 5604 |
|
return; |
| 5605 |
|
} |
| 5606 |
|
} |
| 5607 |
|
|
| 5608 |
($p->{line_prev}, $p->{column_prev}) = ($p->{line}, $p->{column}); |
($p->{line_prev}, $p->{column_prev}) = ($p->{line}, $p->{column}); |
| 5609 |
$p->{column}++; |
$p->{column}++; |
| 5610 |
|
|
| 5611 |
if ($self->{next_char} == 0x000A) { # LF |
if ($self->{nc} == 0x000A) { # LF |
| 5612 |
$p->{line}++; |
$p->{line}++; |
| 5613 |
$p->{column} = 0; |
$p->{column} = 0; |
| 5614 |
!!!cp ('i1'); |
!!!cp ('i1'); |
| 5615 |
} elsif ($self->{next_char} == 0x000D) { # CR |
} elsif ($self->{nc} == 0x000D) { # CR |
| 5616 |
$i++ if substr ($$s, $i, 1) eq "\x0A"; |
## TODO: support for abort/streaming |
| 5617 |
$self->{next_char} = 0x000A; # LF # MUST |
my $next = ''; |
| 5618 |
|
if ($input->read ($next, 1) and $next ne "\x0A") { |
| 5619 |
|
$self->{next_nc} = $next; |
| 5620 |
|
} |
| 5621 |
|
$self->{nc} = 0x000A; # LF # MUST |
| 5622 |
$p->{line}++; |
$p->{line}++; |
| 5623 |
$p->{column} = 0; |
$p->{column} = 0; |
| 5624 |
!!!cp ('i2'); |
!!!cp ('i2'); |
| 5625 |
} elsif ($self->{next_char} > 0x10FFFF) { |
} elsif ($self->{nc} == 0x0000) { # NULL |
|
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
|
|
!!!cp ('i3'); |
|
|
} elsif ($self->{next_char} == 0x0000) { # NULL |
|
| 5626 |
!!!cp ('i4'); |
!!!cp ('i4'); |
| 5627 |
!!!parse-error (type => 'NULL'); |
!!!parse-error (type => 'NULL'); |
| 5628 |
$self->{next_char} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
$self->{nc} = 0xFFFD; # REPLACEMENT CHARACTER # MUST |
|
} elsif ($self->{next_char} <= 0x0008 or |
|
|
(0x000E <= $self->{next_char} and |
|
|
$self->{next_char} <= 0x001F) or |
|
|
(0x007F <= $self->{next_char} and |
|
|
$self->{next_char} <= 0x009F) or |
|
|
(0xD800 <= $self->{next_char} and |
|
|
$self->{next_char} <= 0xDFFF) or |
|
|
(0xFDD0 <= $self->{next_char} and |
|
|
$self->{next_char} <= 0xFDDF) or |
|
|
{ |
|
|
0xFFFE => 1, 0xFFFF => 1, 0x1FFFE => 1, 0x1FFFF => 1, |
|
|
0x2FFFE => 1, 0x2FFFF => 1, 0x3FFFE => 1, 0x3FFFF => 1, |
|
|
0x4FFFE => 1, 0x4FFFF => 1, 0x5FFFE => 1, 0x5FFFF => 1, |
|
|
0x6FFFE => 1, 0x6FFFF => 1, 0x7FFFE => 1, 0x7FFFF => 1, |
|
|
0x8FFFE => 1, 0x8FFFF => 1, 0x9FFFE => 1, 0x9FFFF => 1, |
|
|
0xAFFFE => 1, 0xAFFFF => 1, 0xBFFFE => 1, 0xBFFFF => 1, |
|
|
0xCFFFE => 1, 0xCFFFF => 1, 0xDFFFE => 1, 0xDFFFF => 1, |
|
|
0xEFFFE => 1, 0xEFFFF => 1, 0xFFFFE => 1, 0xFFFFF => 1, |
|
|
0x10FFFE => 1, 0x10FFFF => 1, |
|
|
}->{$self->{next_char}}) { |
|
|
!!!cp ('i4.1'); |
|
|
!!!parse-error (type => 'control char', level => $self->{must_level}); |
|
|
## TODO: error type documentation |
|
| 5629 |
} |
} |
| 5630 |
}; |
}; |
| 5631 |
$p->{prev_char} = [-1, -1, -1]; |
|
| 5632 |
$p->{next_char} = -1; |
$p->{read_until} = sub { |
| 5633 |
|
#my ($scalar, $specials_range, $offset) = @_; |
| 5634 |
|
return 0 if defined $p->{next_nc}; |
| 5635 |
|
|
| 5636 |
|
my $pattern = qr/[^$_[1]\x00\x0A\x0D]/; |
| 5637 |
|
my $offset = $_[2] || 0; |
| 5638 |
|
|
| 5639 |
|
if ($p->{char_buffer_pos} < length $p->{char_buffer}) { |
| 5640 |
|
pos ($p->{char_buffer}) = $p->{char_buffer_pos}; |
| 5641 |
|
if ($p->{char_buffer} =~ /\G(?>$pattern)+/) { |
| 5642 |
|
substr ($_[0], $offset) |
| 5643 |
|
= substr ($p->{char_buffer}, $-[0], $+[0] - $-[0]); |
| 5644 |
|
my $count = $+[0] - $-[0]; |
| 5645 |
|
if ($count) { |
| 5646 |
|
$p->{column} += $count; |
| 5647 |
|
$p->{char_buffer_pos} += $count; |
| 5648 |
|
$p->{line_prev} = $p->{line}; |
| 5649 |
|
$p->{column_prev} = $p->{column} - 1; |
| 5650 |
|
$p->{nc} = -1; |
| 5651 |
|
} |
| 5652 |
|
return $count; |
| 5653 |
|
} else { |
| 5654 |
|
return 0; |
| 5655 |
|
} |
| 5656 |
|
} else { |
| 5657 |
|
my $count = $input->manakai_read_until ($_[0], $pattern, $_[2]); |
| 5658 |
|
if ($count) { |
| 5659 |
|
$p->{column} += $count; |
| 5660 |
|
$p->{column_prev} += $count; |
| 5661 |
|
$p->{nc} = -1; |
| 5662 |
|
} |
| 5663 |
|
return $count; |
| 5664 |
|
} |
| 5665 |
|
}; # $p->{read_until} |
| 5666 |
|
|
| 5667 |
my $ponerror = $onerror || sub { |
my $ponerror = $onerror || sub { |
| 5668 |
my (%opt) = @_; |
my (%opt) = @_; |
| 5669 |
my $line = $opt{line}; |
my $line = $opt{line}; |
| 5678 |
$ponerror->(line => $p->{line}, column => $p->{column}, @_); |
$ponerror->(line => $p->{line}, column => $p->{column}, @_); |
| 5679 |
}; |
}; |
| 5680 |
|
|
| 5681 |
|
my $char_onerror = sub { |
| 5682 |
|
my (undef, $type, %opt) = @_; |
| 5683 |
|
$ponerror->(layer => 'encode', |
| 5684 |
|
line => $p->{line}, column => $p->{column} + 1, |
| 5685 |
|
%opt, type => $type); |
| 5686 |
|
}; # $char_onerror |
| 5687 |
|
$input->onerror ($char_onerror); |
| 5688 |
|
|
| 5689 |
$p->_initialize_tokenizer; |
$p->_initialize_tokenizer; |
| 5690 |
$p->_initialize_tree_constructor; |
$p->_initialize_tree_constructor; |
| 5691 |
|
|
| 5692 |
## Step 2 |
## F4. If /context/ is not undef... |
| 5693 |
|
|
| 5694 |
|
## F4.1. content model flag |
| 5695 |
my $node_ln = $node->manakai_local_name; |
my $node_ln = $node->manakai_local_name; |
| 5696 |
$p->{content_model} = { |
$p->{content_model} = { |
| 5697 |
title => RCDATA_CONTENT_MODEL, |
title => RCDATA_CONTENT_MODEL, |
| 5707 |
}->{$node_ln}; |
}->{$node_ln}; |
| 5708 |
$p->{content_model} = PCDATA_CONTENT_MODEL |
$p->{content_model} = PCDATA_CONTENT_MODEL |
| 5709 |
unless defined $p->{content_model}; |
unless defined $p->{content_model}; |
|
## ISSUE: What is "the name of the element"? local name? |
|
| 5710 |
|
|
| 5711 |
$p->{inner_html_node} = [$node, $el_category->{$node_ln}]; |
$p->{inner_html_node} = [$node, $el_category->{$node_ln}]; |
| 5712 |
## TODO: Foreign element OK? |
## TODO: Foreign element OK? |
| 5713 |
|
|
| 5714 |
## Step 3 |
## F4.2. Root |html| element |
| 5715 |
my $root = $doc->create_element_ns |
my $root = $doc->create_element_ns |
| 5716 |
('http://www.w3.org/1999/xhtml', [undef, 'html']); |
('http://www.w3.org/1999/xhtml', [undef, 'html']); |
| 5717 |
|
|
| 5718 |
## Step 4 # MUST |
## F4.3. |
| 5719 |
$doc->append_child ($root); |
$doc->append_child ($root); |
| 5720 |
|
|
| 5721 |
## Step 5 # MUST |
## F4.4. |
| 5722 |
push @{$p->{open_elements}}, [$root, $el_category->{html}]; |
push @{$p->{open_elements}}, [$root, $el_category->{html}]; |
| 5723 |
|
|
| 5724 |
undef $p->{head_element}; |
undef $p->{head_element}; |
| 5725 |
|
undef $p->{head_element_inserted}; |
| 5726 |
|
|
| 5727 |
## Step 6 # MUST |
## F4.5. |
| 5728 |
$p->_reset_insertion_mode; |
$p->_reset_insertion_mode; |
| 5729 |
|
|
| 5730 |
## Step 7 # MUST |
## F4.6. |
| 5731 |
my $anode = $node; |
my $anode = $node; |
| 5732 |
AN: while (defined $anode) { |
AN: while (defined $anode) { |
| 5733 |
if ($anode->node_type == 1) { |
if ($anode->node_type == 1) { |
| 5742 |
} |
} |
| 5743 |
$anode = $anode->parent_node; |
$anode = $anode->parent_node; |
| 5744 |
} # AN |
} # AN |
| 5745 |
|
|
| 5746 |
## Step 9 # MUST |
## F.6. Start the parser. |
| 5747 |
{ |
{ |
| 5748 |
my $self = $p; |
my $self = $p; |
| 5749 |
!!!next-token; |
!!!next-token; |
| 5750 |
} |
} |
| 5751 |
$p->_tree_construction_main; |
$p->_tree_construction_main; |
| 5752 |
|
|
| 5753 |
## Step 10 # MUST |
## F.7. |
| 5754 |
my @cn = @{$node->child_nodes}; |
my @cn = @{$node->child_nodes}; |
| 5755 |
for (@cn) { |
for (@cn) { |
| 5756 |
$node->remove_child ($_); |
$node->remove_child ($_); |