| 2 |
use strict; |
use strict; |
| 3 |
our $VERSION=do{my @r=(q$Revision$=~/\d+/g);sprintf "%d."."%02d" x $#r,@r}; |
our $VERSION=do{my @r=(q$Revision$=~/\d+/g);sprintf "%d."."%02d" x $#r,@r}; |
| 4 |
|
|
| 5 |
## This is an early version of an HTML parser. |
## ISSUE: |
| 6 |
|
## var doc = implementation.createDocument (null, null, null); |
| 7 |
|
## doc.write (''); |
| 8 |
|
## alert (doc.compatMode); |
| 9 |
|
|
| 10 |
|
## ISSUE: HTML5 revision 967 says that the encoding layer MUST NOT |
| 11 |
|
## strip BOM and the HTML layer MUST ignore it. Whether we can do it |
| 12 |
|
## is not yet clear. |
| 13 |
|
## "{U+FEFF}..." in UTF-16BE/UTF-16LE is three or four characters? |
| 14 |
|
## "{U+FEFF}..." in GB18030? |
| 15 |
|
|
| 16 |
my $permitted_slash_tag_name = { |
my $permitted_slash_tag_name = { |
| 17 |
base => 1, |
base => 1, |
| 27 |
input => 1, |
input => 1, |
| 28 |
}; |
}; |
| 29 |
|
|
|
my $entity_char = { |
|
|
AElig => "\x{00C6}", |
|
|
Aacute => "\x{00C1}", |
|
|
Acirc => "\x{00C2}", |
|
|
Agrave => "\x{00C0}", |
|
|
Alpha => "\x{0391}", |
|
|
Aring => "\x{00C5}", |
|
|
Atilde => "\x{00C3}", |
|
|
Auml => "\x{00C4}", |
|
|
Beta => "\x{0392}", |
|
|
Ccedil => "\x{00C7}", |
|
|
Chi => "\x{03A7}", |
|
|
Dagger => "\x{2021}", |
|
|
Delta => "\x{0394}", |
|
|
ETH => "\x{00D0}", |
|
|
Eacute => "\x{00C9}", |
|
|
Ecirc => "\x{00CA}", |
|
|
Egrave => "\x{00C8}", |
|
|
Epsilon => "\x{0395}", |
|
|
Eta => "\x{0397}", |
|
|
Euml => "\x{00CB}", |
|
|
Gamma => "\x{0393}", |
|
|
Iacute => "\x{00CD}", |
|
|
Icirc => "\x{00CE}", |
|
|
Igrave => "\x{00CC}", |
|
|
Iota => "\x{0399}", |
|
|
Iuml => "\x{00CF}", |
|
|
Kappa => "\x{039A}", |
|
|
Lambda => "\x{039B}", |
|
|
Mu => "\x{039C}", |
|
|
Ntilde => "\x{00D1}", |
|
|
Nu => "\x{039D}", |
|
|
OElig => "\x{0152}", |
|
|
Oacute => "\x{00D3}", |
|
|
Ocirc => "\x{00D4}", |
|
|
Ograve => "\x{00D2}", |
|
|
Omega => "\x{03A9}", |
|
|
Omicron => "\x{039F}", |
|
|
Oslash => "\x{00D8}", |
|
|
Otilde => "\x{00D5}", |
|
|
Ouml => "\x{00D6}", |
|
|
Phi => "\x{03A6}", |
|
|
Pi => "\x{03A0}", |
|
|
Prime => "\x{2033}", |
|
|
Psi => "\x{03A8}", |
|
|
Rho => "\x{03A1}", |
|
|
Scaron => "\x{0160}", |
|
|
Sigma => "\x{03A3}", |
|
|
THORN => "\x{00DE}", |
|
|
Tau => "\x{03A4}", |
|
|
Theta => "\x{0398}", |
|
|
Uacute => "\x{00DA}", |
|
|
Ucirc => "\x{00DB}", |
|
|
Ugrave => "\x{00D9}", |
|
|
Upsilon => "\x{03A5}", |
|
|
Uuml => "\x{00DC}", |
|
|
Xi => "\x{039E}", |
|
|
Yacute => "\x{00DD}", |
|
|
Yuml => "\x{0178}", |
|
|
Zeta => "\x{0396}", |
|
|
aacute => "\x{00E1}", |
|
|
acirc => "\x{00E2}", |
|
|
acute => "\x{00B4}", |
|
|
aelig => "\x{00E6}", |
|
|
agrave => "\x{00E0}", |
|
|
alefsym => "\x{2135}", |
|
|
alpha => "\x{03B1}", |
|
|
amp => "\x{0026}", |
|
|
AMP => "\x{0026}", |
|
|
and => "\x{2227}", |
|
|
ang => "\x{2220}", |
|
|
apos => "\x{0027}", |
|
|
aring => "\x{00E5}", |
|
|
asymp => "\x{2248}", |
|
|
atilde => "\x{00E3}", |
|
|
auml => "\x{00E4}", |
|
|
bdquo => "\x{201E}", |
|
|
beta => "\x{03B2}", |
|
|
brvbar => "\x{00A6}", |
|
|
bull => "\x{2022}", |
|
|
cap => "\x{2229}", |
|
|
ccedil => "\x{00E7}", |
|
|
cedil => "\x{00B8}", |
|
|
cent => "\x{00A2}", |
|
|
chi => "\x{03C7}", |
|
|
circ => "\x{02C6}", |
|
|
clubs => "\x{2663}", |
|
|
cong => "\x{2245}", |
|
|
copy => "\x{00A9}", |
|
|
COPY => "\x{00A9}", |
|
|
crarr => "\x{21B5}", |
|
|
cup => "\x{222A}", |
|
|
curren => "\x{00A4}", |
|
|
dArr => "\x{21D3}", |
|
|
dagger => "\x{2020}", |
|
|
darr => "\x{2193}", |
|
|
deg => "\x{00B0}", |
|
|
delta => "\x{03B4}", |
|
|
diams => "\x{2666}", |
|
|
divide => "\x{00F7}", |
|
|
eacute => "\x{00E9}", |
|
|
ecirc => "\x{00EA}", |
|
|
egrave => "\x{00E8}", |
|
|
empty => "\x{2205}", |
|
|
emsp => "\x{2003}", |
|
|
ensp => "\x{2002}", |
|
|
epsilon => "\x{03B5}", |
|
|
equiv => "\x{2261}", |
|
|
eta => "\x{03B7}", |
|
|
eth => "\x{00F0}", |
|
|
euml => "\x{00EB}", |
|
|
euro => "\x{20AC}", |
|
|
exist => "\x{2203}", |
|
|
fnof => "\x{0192}", |
|
|
forall => "\x{2200}", |
|
|
frac12 => "\x{00BD}", |
|
|
frac14 => "\x{00BC}", |
|
|
frac34 => "\x{00BE}", |
|
|
frasl => "\x{2044}", |
|
|
gamma => "\x{03B3}", |
|
|
ge => "\x{2265}", |
|
|
gt => "\x{003E}", |
|
|
GT => "\x{003E}", |
|
|
hArr => "\x{21D4}", |
|
|
harr => "\x{2194}", |
|
|
hearts => "\x{2665}", |
|
|
hellip => "\x{2026}", |
|
|
iacute => "\x{00ED}", |
|
|
icirc => "\x{00EE}", |
|
|
iexcl => "\x{00A1}", |
|
|
igrave => "\x{00EC}", |
|
|
image => "\x{2111}", |
|
|
infin => "\x{221E}", |
|
|
int => "\x{222B}", |
|
|
iota => "\x{03B9}", |
|
|
iquest => "\x{00BF}", |
|
|
isin => "\x{2208}", |
|
|
iuml => "\x{00EF}", |
|
|
kappa => "\x{03BA}", |
|
|
lArr => "\x{21D0}", |
|
|
lambda => "\x{03BB}", |
|
|
lang => "\x{2329}", |
|
|
laquo => "\x{00AB}", |
|
|
larr => "\x{2190}", |
|
|
lceil => "\x{2308}", |
|
|
ldquo => "\x{201C}", |
|
|
le => "\x{2264}", |
|
|
lfloor => "\x{230A}", |
|
|
lowast => "\x{2217}", |
|
|
loz => "\x{25CA}", |
|
|
lrm => "\x{200E}", |
|
|
lsaquo => "\x{2039}", |
|
|
lsquo => "\x{2018}", |
|
|
lt => "\x{003C}", |
|
|
LT => "\x{003C}", |
|
|
macr => "\x{00AF}", |
|
|
mdash => "\x{2014}", |
|
|
micro => "\x{00B5}", |
|
|
middot => "\x{00B7}", |
|
|
minus => "\x{2212}", |
|
|
mu => "\x{03BC}", |
|
|
nabla => "\x{2207}", |
|
|
nbsp => "\x{00A0}", |
|
|
ndash => "\x{2013}", |
|
|
ne => "\x{2260}", |
|
|
ni => "\x{220B}", |
|
|
not => "\x{00AC}", |
|
|
notin => "\x{2209}", |
|
|
nsub => "\x{2284}", |
|
|
ntilde => "\x{00F1}", |
|
|
nu => "\x{03BD}", |
|
|
oacute => "\x{00F3}", |
|
|
ocirc => "\x{00F4}", |
|
|
oelig => "\x{0153}", |
|
|
ograve => "\x{00F2}", |
|
|
oline => "\x{203E}", |
|
|
omega => "\x{03C9}", |
|
|
omicron => "\x{03BF}", |
|
|
oplus => "\x{2295}", |
|
|
or => "\x{2228}", |
|
|
ordf => "\x{00AA}", |
|
|
ordm => "\x{00BA}", |
|
|
oslash => "\x{00F8}", |
|
|
otilde => "\x{00F5}", |
|
|
otimes => "\x{2297}", |
|
|
ouml => "\x{00F6}", |
|
|
para => "\x{00B6}", |
|
|
part => "\x{2202}", |
|
|
permil => "\x{2030}", |
|
|
perp => "\x{22A5}", |
|
|
phi => "\x{03C6}", |
|
|
pi => "\x{03C0}", |
|
|
piv => "\x{03D6}", |
|
|
plusmn => "\x{00B1}", |
|
|
pound => "\x{00A3}", |
|
|
prime => "\x{2032}", |
|
|
prod => "\x{220F}", |
|
|
prop => "\x{221D}", |
|
|
psi => "\x{03C8}", |
|
|
quot => "\x{0022}", |
|
|
QUOT => "\x{0022}", |
|
|
rArr => "\x{21D2}", |
|
|
radic => "\x{221A}", |
|
|
rang => "\x{232A}", |
|
|
raquo => "\x{00BB}", |
|
|
rarr => "\x{2192}", |
|
|
rceil => "\x{2309}", |
|
|
rdquo => "\x{201D}", |
|
|
real => "\x{211C}", |
|
|
reg => "\x{00AE}", |
|
|
REG => "\x{00AE}", |
|
|
rfloor => "\x{230B}", |
|
|
rho => "\x{03C1}", |
|
|
rlm => "\x{200F}", |
|
|
rsaquo => "\x{203A}", |
|
|
rsquo => "\x{2019}", |
|
|
sbquo => "\x{201A}", |
|
|
scaron => "\x{0161}", |
|
|
sdot => "\x{22C5}", |
|
|
sect => "\x{00A7}", |
|
|
shy => "\x{00AD}", |
|
|
sigma => "\x{03C3}", |
|
|
sigmaf => "\x{03C2}", |
|
|
sim => "\x{223C}", |
|
|
spades => "\x{2660}", |
|
|
sub => "\x{2282}", |
|
|
sube => "\x{2286}", |
|
|
sum => "\x{2211}", |
|
|
sup => "\x{2283}", |
|
|
sup1 => "\x{00B9}", |
|
|
sup2 => "\x{00B2}", |
|
|
sup3 => "\x{00B3}", |
|
|
supe => "\x{2287}", |
|
|
szlig => "\x{00DF}", |
|
|
tau => "\x{03C4}", |
|
|
there4 => "\x{2234}", |
|
|
theta => "\x{03B8}", |
|
|
thetasym => "\x{03D1}", |
|
|
thinsp => "\x{2009}", |
|
|
thorn => "\x{00FE}", |
|
|
tilde => "\x{02DC}", |
|
|
times => "\x{00D7}", |
|
|
trade => "\x{2122}", |
|
|
uArr => "\x{21D1}", |
|
|
uacute => "\x{00FA}", |
|
|
uarr => "\x{2191}", |
|
|
ucirc => "\x{00FB}", |
|
|
ugrave => "\x{00F9}", |
|
|
uml => "\x{00A8}", |
|
|
upsih => "\x{03D2}", |
|
|
upsilon => "\x{03C5}", |
|
|
uuml => "\x{00FC}", |
|
|
weierp => "\x{2118}", |
|
|
xi => "\x{03BE}", |
|
|
yacute => "\x{00FD}", |
|
|
yen => "\x{00A5}", |
|
|
yuml => "\x{00FF}", |
|
|
zeta => "\x{03B6}", |
|
|
zwj => "\x{200D}", |
|
|
zwnj => "\x{200C}", |
|
|
}; # $entity_char |
|
|
|
|
| 30 |
my $c1_entity_char = { |
my $c1_entity_char = { |
| 31 |
0x80 => 0x20AC, |
0x80 => 0x20AC, |
| 32 |
0x81 => 0xFFFD, |
0x81 => 0xFFFD, |
| 150 |
return $self; |
return $self; |
| 151 |
} # new |
} # new |
| 152 |
|
|
| 153 |
|
sub CM_ENTITY () { 0b001 } # & markup in data |
| 154 |
|
sub CM_LIMITED_MARKUP () { 0b010 } # < markup in data (limited) |
| 155 |
|
sub CM_FULL_MARKUP () { 0b100 } # < markup in data (any) |
| 156 |
|
|
| 157 |
|
sub PLAINTEXT_CONTENT_MODEL () { 0 } |
| 158 |
|
sub CDATA_CONTENT_MODEL () { CM_LIMITED_MARKUP } |
| 159 |
|
sub RCDATA_CONTENT_MODEL () { CM_ENTITY | CM_LIMITED_MARKUP } |
| 160 |
|
sub PCDATA_CONTENT_MODEL () { CM_ENTITY | CM_FULL_MARKUP } |
| 161 |
|
|
| 162 |
## Implementations MUST act as if state machine in the spec |
## Implementations MUST act as if state machine in the spec |
| 163 |
|
|
| 164 |
sub _initialize_tokenizer ($) { |
sub _initialize_tokenizer ($) { |
| 165 |
my $self = shift; |
my $self = shift; |
| 166 |
$self->{state} = 'data'; # MUST |
$self->{state} = 'data'; # MUST |
| 167 |
$self->{content_model_flag} = 'PCDATA'; # be |
$self->{content_model} = PCDATA_CONTENT_MODEL; # be |
| 168 |
undef $self->{current_token}; # start tag, end tag, comment, or DOCTYPE |
undef $self->{current_token}; # start tag, end tag, comment, or DOCTYPE |
| 169 |
undef $self->{current_attribute}; |
undef $self->{current_attribute}; |
| 170 |
undef $self->{last_emitted_start_tag_name}; |
undef $self->{last_emitted_start_tag_name}; |
| 173 |
# $self->{next_input_character} |
# $self->{next_input_character} |
| 174 |
!!!next-input-character; |
!!!next-input-character; |
| 175 |
$self->{token} = []; |
$self->{token} = []; |
| 176 |
|
# $self->{escape} |
| 177 |
} # _initialize_tokenizer |
} # _initialize_tokenizer |
| 178 |
|
|
| 179 |
## A token has: |
## A token has: |
| 180 |
## ->{type} eq 'DOCTYPE', 'start tag', 'end tag', 'comment', |
## ->{type} eq 'DOCTYPE', 'start tag', 'end tag', 'comment', |
| 181 |
## 'character', or 'end-of-file' |
## 'character', or 'end-of-file' |
| 182 |
## ->{name} (DOCTYPE, start tag (tagname), end tag (tagname)) |
## ->{name} (DOCTYPE, start tag (tag name), end tag (tag name)) |
| 183 |
## ISSUE: the spec need s/tagname/tag name/ |
## ->{public_identifier} (DOCTYPE) |
| 184 |
## ->{error} == 1 or 0 (DOCTYPE) |
## ->{system_identifier} (DOCTYPE) |
| 185 |
|
## ->{correct} == 1 or 0 (DOCTYPE) |
| 186 |
## ->{attributes} isa HASH (start tag, end tag) |
## ->{attributes} isa HASH (start tag, end tag) |
| 187 |
## ->{data} (comment, character) |
## ->{data} (comment, character) |
| 188 |
|
|
|
## Macros |
|
|
## Macros MUST be preceded by three EXCLAMATION MARKs. |
|
|
## emit ($token) |
|
|
## Emits the specified token. |
|
|
|
|
| 189 |
## Emitted token MUST immediately be handled by the tree construction state. |
## Emitted token MUST immediately be handled by the tree construction state. |
| 190 |
|
|
| 191 |
## Before each step, UA MAY check to see if either one of the scripts in |
## Before each step, UA MAY check to see if either one of the scripts in |
| 203 |
A: { |
A: { |
| 204 |
if ($self->{state} eq 'data') { |
if ($self->{state} eq 'data') { |
| 205 |
if ($self->{next_input_character} == 0x0026) { # & |
if ($self->{next_input_character} == 0x0026) { # & |
| 206 |
if ($self->{content_model_flag} eq 'PCDATA' or |
if ($self->{content_model} & CM_ENTITY) { # PCDATA | RCDATA |
|
$self->{content_model_flag} eq 'RCDATA') { |
|
| 207 |
$self->{state} = 'entity data'; |
$self->{state} = 'entity data'; |
| 208 |
!!!next-input-character; |
!!!next-input-character; |
| 209 |
redo A; |
redo A; |
| 211 |
# |
# |
| 212 |
} |
} |
| 213 |
} elsif ($self->{next_input_character} == 0x002D) { # - |
} elsif ($self->{next_input_character} == 0x002D) { # - |
| 214 |
if ($self->{content_model_flag} eq 'RCDATA' or |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
|
$self->{content_model_flag} eq 'CDATA') { |
|
| 215 |
unless ($self->{escape}) { |
unless ($self->{escape}) { |
| 216 |
if ($self->{prev_input_character}->[0] == 0x002D and # - |
if ($self->{prev_input_character}->[0] == 0x002D and # - |
| 217 |
$self->{prev_input_character}->[1] == 0x0021 and # ! |
$self->{prev_input_character}->[1] == 0x0021 and # ! |
| 223 |
|
|
| 224 |
# |
# |
| 225 |
} elsif ($self->{next_input_character} == 0x003C) { # < |
} elsif ($self->{next_input_character} == 0x003C) { # < |
| 226 |
if ($self->{content_model_flag} eq 'PCDATA' or |
if ($self->{content_model} & CM_FULL_MARKUP or # PCDATA |
| 227 |
(($self->{content_model_flag} eq 'CDATA' or |
(($self->{content_model} & CM_LIMITED_MARKUP) and # CDATA | RCDATA |
|
$self->{content_model_flag} eq 'RCDATA') and |
|
| 228 |
not $self->{escape})) { |
not $self->{escape})) { |
| 229 |
$self->{state} = 'tag open'; |
$self->{state} = 'tag open'; |
| 230 |
!!!next-input-character; |
!!!next-input-character; |
| 234 |
} |
} |
| 235 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 236 |
if ($self->{escape} and |
if ($self->{escape} and |
| 237 |
($self->{content_model_flag} eq 'RCDATA' or |
($self->{content_model} & CM_LIMITED_MARKUP)) { # RCDATA | CDATA |
|
$self->{content_model_flag} eq 'CDATA')) { |
|
| 238 |
if ($self->{prev_input_character}->[0] == 0x002D and # - |
if ($self->{prev_input_character}->[0] == 0x002D and # - |
| 239 |
$self->{prev_input_character}->[1] == 0x002D) { # - |
$self->{prev_input_character}->[1] == 0x002D) { # - |
| 240 |
delete $self->{escape}; |
delete $self->{escape}; |
| 258 |
} elsif ($self->{state} eq 'entity data') { |
} elsif ($self->{state} eq 'entity data') { |
| 259 |
## (cannot happen in CDATA state) |
## (cannot happen in CDATA state) |
| 260 |
|
|
| 261 |
my $token = $self->_tokenize_attempt_to_consume_an_entity; |
my $token = $self->_tokenize_attempt_to_consume_an_entity (0); |
| 262 |
|
|
| 263 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 264 |
# next-input-character is already done |
# next-input-character is already done |
| 271 |
|
|
| 272 |
redo A; |
redo A; |
| 273 |
} elsif ($self->{state} eq 'tag open') { |
} elsif ($self->{state} eq 'tag open') { |
| 274 |
if ($self->{content_model_flag} eq 'RCDATA' or |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
|
$self->{content_model_flag} eq 'CDATA') { |
|
| 275 |
if ($self->{next_input_character} == 0x002F) { # / |
if ($self->{next_input_character} == 0x002F) { # / |
| 276 |
!!!next-input-character; |
!!!next-input-character; |
| 277 |
$self->{state} = 'close tag open'; |
$self->{state} = 'close tag open'; |
| 284 |
|
|
| 285 |
redo A; |
redo A; |
| 286 |
} |
} |
| 287 |
} elsif ($self->{content_model_flag} eq 'PCDATA') { |
} elsif ($self->{content_model} & CM_FULL_MARKUP) { # PCDATA |
| 288 |
if ($self->{next_input_character} == 0x0021) { # ! |
if ($self->{next_input_character} == 0x0021) { # ! |
| 289 |
$self->{state} = 'markup declaration open'; |
$self->{state} = 'markup declaration open'; |
| 290 |
!!!next-input-character; |
!!!next-input-character; |
| 331 |
redo A; |
redo A; |
| 332 |
} |
} |
| 333 |
} else { |
} else { |
| 334 |
die "$0: $self->{content_model_flag}: Unknown content model flag"; |
die "$0: $self->{content_model} in tag open"; |
| 335 |
} |
} |
| 336 |
} elsif ($self->{state} eq 'close tag open') { |
} elsif ($self->{state} eq 'close tag open') { |
| 337 |
if ($self->{content_model_flag} eq 'RCDATA' or |
if ($self->{content_model} & CM_LIMITED_MARKUP) { # RCDATA | CDATA |
| 338 |
$self->{content_model_flag} eq 'CDATA') { |
if (defined $self->{last_emitted_start_tag_name}) { |
| 339 |
my @next_char; |
## NOTE: <http://krijnhoetmer.nl/irc-logs/whatwg/20070626#l-564> |
| 340 |
TAGNAME: for (my $i = 0; $i < length $self->{last_emitted_start_tag_name}; $i++) { |
my @next_char; |
| 341 |
|
TAGNAME: for (my $i = 0; $i < length $self->{last_emitted_start_tag_name}; $i++) { |
| 342 |
|
push @next_char, $self->{next_input_character}; |
| 343 |
|
my $c = ord substr ($self->{last_emitted_start_tag_name}, $i, 1); |
| 344 |
|
my $C = 0x0061 <= $c && $c <= 0x007A ? $c - 0x0020 : $c; |
| 345 |
|
if ($self->{next_input_character} == $c or $self->{next_input_character} == $C) { |
| 346 |
|
!!!next-input-character; |
| 347 |
|
next TAGNAME; |
| 348 |
|
} else { |
| 349 |
|
$self->{next_input_character} = shift @next_char; # reconsume |
| 350 |
|
!!!back-next-input-character (@next_char); |
| 351 |
|
$self->{state} = 'data'; |
| 352 |
|
|
| 353 |
|
!!!emit ({type => 'character', data => '</'}); |
| 354 |
|
|
| 355 |
|
redo A; |
| 356 |
|
} |
| 357 |
|
} |
| 358 |
push @next_char, $self->{next_input_character}; |
push @next_char, $self->{next_input_character}; |
| 359 |
my $c = ord substr ($self->{last_emitted_start_tag_name}, $i, 1); |
|
| 360 |
my $C = 0x0061 <= $c && $c <= 0x007A ? $c - 0x0020 : $c; |
unless ($self->{next_input_character} == 0x0009 or # HT |
| 361 |
if ($self->{next_input_character} == $c or $self->{next_input_character} == $C) { |
$self->{next_input_character} == 0x000A or # LF |
| 362 |
!!!next-input-character; |
$self->{next_input_character} == 0x000B or # VT |
| 363 |
next TAGNAME; |
$self->{next_input_character} == 0x000C or # FF |
| 364 |
} else { |
$self->{next_input_character} == 0x0020 or # SP |
| 365 |
!!!parse-error (type => 'unmatched end tag'); |
$self->{next_input_character} == 0x003E or # > |
| 366 |
|
$self->{next_input_character} == 0x002F or # / |
| 367 |
|
$self->{next_input_character} == -1) { |
| 368 |
$self->{next_input_character} = shift @next_char; # reconsume |
$self->{next_input_character} = shift @next_char; # reconsume |
| 369 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 370 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
|
|
|
| 371 |
!!!emit ({type => 'character', data => '</'}); |
!!!emit ({type => 'character', data => '</'}); |
|
|
|
| 372 |
redo A; |
redo A; |
| 373 |
|
} else { |
| 374 |
|
$self->{next_input_character} = shift @next_char; |
| 375 |
|
!!!back-next-input-character (@next_char); |
| 376 |
|
# and consume... |
| 377 |
} |
} |
| 378 |
} |
} else { |
| 379 |
push @next_char, $self->{next_input_character}; |
## No start tag token has ever been emitted |
| 380 |
|
# next-input-character is already done |
|
unless ($self->{next_input_character} == 0x0009 or # HT |
|
|
$self->{next_input_character} == 0x000A or # LF |
|
|
$self->{next_input_character} == 0x000B or # VT |
|
|
$self->{next_input_character} == 0x000C or # FF |
|
|
$self->{next_input_character} == 0x0020 or # SP |
|
|
$self->{next_input_character} == 0x003E or # > |
|
|
$self->{next_input_character} == 0x002F or # / |
|
|
$self->{next_input_character} == 0x003C or # < |
|
|
$self->{next_input_character} == -1) { |
|
|
!!!parse-error (type => 'unmatched end tag'); |
|
|
$self->{next_input_character} = shift @next_char; # reconsume |
|
|
!!!back-next-input-character (@next_char); |
|
| 381 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
|
|
|
| 382 |
!!!emit ({type => 'character', data => '</'}); |
!!!emit ({type => 'character', data => '</'}); |
|
|
|
| 383 |
redo A; |
redo A; |
|
} else { |
|
|
$self->{next_input_character} = shift @next_char; |
|
|
!!!back-next-input-character (@next_char); |
|
|
# and consume... |
|
| 384 |
} |
} |
| 385 |
} |
} |
| 386 |
|
|
| 428 |
redo A; |
redo A; |
| 429 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 430 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 431 |
|
$self->{current_token}->{first_start_tag} |
| 432 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 433 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 434 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 435 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 436 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 437 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 438 |
} |
} |
| 443 |
!!!next-input-character; |
!!!next-input-character; |
| 444 |
|
|
| 445 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 446 |
|
|
| 447 |
redo A; |
redo A; |
| 448 |
} elsif (0x0041 <= $self->{next_input_character} and |
} elsif (0x0041 <= $self->{next_input_character} and |
| 452 |
## Stay in this state |
## Stay in this state |
| 453 |
!!!next-input-character; |
!!!next-input-character; |
| 454 |
redo A; |
redo A; |
| 455 |
} elsif ($self->{next_input_character} == 0x003C or # < |
} elsif ($self->{next_input_character} == -1) { |
|
$self->{next_input_character} == -1) { |
|
| 456 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 457 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 458 |
|
$self->{current_token}->{first_start_tag} |
| 459 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 460 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 461 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 462 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 463 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 464 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 465 |
} |
} |
| 470 |
# reconsume |
# reconsume |
| 471 |
|
|
| 472 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 473 |
|
|
| 474 |
redo A; |
redo A; |
| 475 |
} elsif ($self->{next_input_character} == 0x002F) { # / |
} elsif ($self->{next_input_character} == 0x002F) { # / |
| 503 |
redo A; |
redo A; |
| 504 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 505 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 506 |
|
$self->{current_token}->{first_start_tag} |
| 507 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 508 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 509 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 510 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 511 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 512 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 513 |
} |
} |
| 518 |
!!!next-input-character; |
!!!next-input-character; |
| 519 |
|
|
| 520 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 521 |
|
|
| 522 |
redo A; |
redo A; |
| 523 |
} elsif (0x0041 <= $self->{next_input_character} and |
} elsif (0x0041 <= $self->{next_input_character} and |
| 540 |
## Stay in the state |
## Stay in the state |
| 541 |
# next-input-character is already done |
# next-input-character is already done |
| 542 |
redo A; |
redo A; |
| 543 |
} elsif ($self->{next_input_character} == 0x003C or # < |
} elsif ($self->{next_input_character} == -1) { |
|
$self->{next_input_character} == -1) { |
|
| 544 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 545 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 546 |
|
$self->{current_token}->{first_start_tag} |
| 547 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 548 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 549 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 550 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 551 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 552 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 553 |
} |
} |
| 558 |
# reconsume |
# reconsume |
| 559 |
|
|
| 560 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 561 |
|
|
| 562 |
redo A; |
redo A; |
| 563 |
} else { |
} else { |
| 571 |
my $before_leave = sub { |
my $before_leave = sub { |
| 572 |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
if (exists $self->{current_token}->{attributes} # start tag or end tag |
| 573 |
->{$self->{current_attribute}->{name}}) { # MUST |
->{$self->{current_attribute}->{name}}) { # MUST |
| 574 |
!!!parse-error (type => 'dupulicate attribute'); |
!!!parse-error (type => 'duplicate attribute:'.$self->{current_attribute}->{name}); |
| 575 |
## Discard $self->{current_attribute} # MUST |
## Discard $self->{current_attribute} # MUST |
| 576 |
} else { |
} else { |
| 577 |
$self->{current_token}->{attributes}->{$self->{current_attribute}->{name}} |
$self->{current_token}->{attributes}->{$self->{current_attribute}->{name}} |
| 596 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 597 |
$before_leave->(); |
$before_leave->(); |
| 598 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 599 |
|
$self->{current_token}->{first_start_tag} |
| 600 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 601 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 602 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 603 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 604 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 605 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 606 |
} |
} |
| 611 |
!!!next-input-character; |
!!!next-input-character; |
| 612 |
|
|
| 613 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 614 |
|
|
| 615 |
redo A; |
redo A; |
| 616 |
} elsif (0x0041 <= $self->{next_input_character} and |
} elsif (0x0041 <= $self->{next_input_character} and |
| 633 |
$self->{state} = 'before attribute name'; |
$self->{state} = 'before attribute name'; |
| 634 |
# next-input-character is already done |
# next-input-character is already done |
| 635 |
redo A; |
redo A; |
| 636 |
} elsif ($self->{next_input_character} == 0x003C or # < |
} elsif ($self->{next_input_character} == -1) { |
|
$self->{next_input_character} == -1) { |
|
| 637 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 638 |
$before_leave->(); |
$before_leave->(); |
| 639 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 640 |
|
$self->{current_token}->{first_start_tag} |
| 641 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 642 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 643 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 644 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 645 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 646 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 647 |
} |
} |
| 652 |
# reconsume |
# reconsume |
| 653 |
|
|
| 654 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 655 |
|
|
| 656 |
redo A; |
redo A; |
| 657 |
} else { |
} else { |
| 675 |
redo A; |
redo A; |
| 676 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 677 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 678 |
|
$self->{current_token}->{first_start_tag} |
| 679 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 680 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 681 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 682 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 683 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 684 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 685 |
} |
} |
| 690 |
!!!next-input-character; |
!!!next-input-character; |
| 691 |
|
|
| 692 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 693 |
|
|
| 694 |
redo A; |
redo A; |
| 695 |
} elsif (0x0041 <= $self->{next_input_character} and |
} elsif (0x0041 <= $self->{next_input_character} and |
| 708 |
# |
# |
| 709 |
} else { |
} else { |
| 710 |
!!!parse-error (type => 'nestc'); |
!!!parse-error (type => 'nestc'); |
| 711 |
|
## TODO: Different error type for <aa / bb> than <aa/> |
| 712 |
} |
} |
| 713 |
$self->{state} = 'before attribute name'; |
$self->{state} = 'before attribute name'; |
| 714 |
# next-input-character is already done |
# next-input-character is already done |
| 715 |
redo A; |
redo A; |
| 716 |
} elsif ($self->{next_input_character} == 0x003C or # < |
} elsif ($self->{next_input_character} == -1) { |
|
$self->{next_input_character} == -1) { |
|
| 717 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 718 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 719 |
|
$self->{current_token}->{first_start_tag} |
| 720 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 721 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 722 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 723 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 724 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 725 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 726 |
} |
} |
| 731 |
# reconsume |
# reconsume |
| 732 |
|
|
| 733 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 734 |
|
|
| 735 |
redo A; |
redo A; |
| 736 |
} else { |
} else { |
| 763 |
redo A; |
redo A; |
| 764 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 765 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 766 |
|
$self->{current_token}->{first_start_tag} |
| 767 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 768 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 769 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 770 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 771 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 772 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 773 |
} |
} |
| 778 |
!!!next-input-character; |
!!!next-input-character; |
| 779 |
|
|
| 780 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 781 |
|
|
| 782 |
redo A; |
redo A; |
| 783 |
} elsif ($self->{next_input_character} == 0x003C or # < |
} elsif ($self->{next_input_character} == -1) { |
|
$self->{next_input_character} == -1) { |
|
| 784 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 785 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 786 |
|
$self->{current_token}->{first_start_tag} |
| 787 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 788 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 789 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 790 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 791 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 792 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 793 |
} |
} |
| 798 |
## reconsume |
## reconsume |
| 799 |
|
|
| 800 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 801 |
|
|
| 802 |
redo A; |
redo A; |
| 803 |
} else { |
} else { |
| 819 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 820 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
| 821 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 822 |
|
$self->{current_token}->{first_start_tag} |
| 823 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 824 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 825 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 826 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 827 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 828 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 829 |
} |
} |
| 834 |
## reconsume |
## reconsume |
| 835 |
|
|
| 836 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 837 |
|
|
| 838 |
redo A; |
redo A; |
| 839 |
} else { |
} else { |
| 855 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 856 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
| 857 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 858 |
|
$self->{current_token}->{first_start_tag} |
| 859 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 860 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 861 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 862 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 863 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 864 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 865 |
} |
} |
| 870 |
## reconsume |
## reconsume |
| 871 |
|
|
| 872 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 873 |
|
|
| 874 |
redo A; |
redo A; |
| 875 |
} else { |
} else { |
| 894 |
redo A; |
redo A; |
| 895 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 896 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 897 |
|
$self->{current_token}->{first_start_tag} |
| 898 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 899 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 900 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 901 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 902 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 903 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 904 |
} |
} |
| 909 |
!!!next-input-character; |
!!!next-input-character; |
| 910 |
|
|
| 911 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 912 |
|
|
| 913 |
redo A; |
redo A; |
| 914 |
} elsif ($self->{next_input_character} == 0x003C or # < |
} elsif ($self->{next_input_character} == -1) { |
|
$self->{next_input_character} == -1) { |
|
| 915 |
!!!parse-error (type => 'unclosed tag'); |
!!!parse-error (type => 'unclosed tag'); |
| 916 |
if ($self->{current_token}->{type} eq 'start tag') { |
if ($self->{current_token}->{type} eq 'start tag') { |
| 917 |
|
$self->{current_token}->{first_start_tag} |
| 918 |
|
= not defined $self->{last_emitted_start_tag_name}; |
| 919 |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
$self->{last_emitted_start_tag_name} = $self->{current_token}->{tag_name}; |
| 920 |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
} elsif ($self->{current_token}->{type} eq 'end tag') { |
| 921 |
$self->{content_model_flag} = 'PCDATA'; # MUST |
$self->{content_model} = PCDATA_CONTENT_MODEL; # MUST |
| 922 |
if ($self->{current_token}->{attributes}) { |
if ($self->{current_token}->{attributes}) { |
| 923 |
!!!parse-error (type => 'end tag attribute'); |
!!!parse-error (type => 'end tag attribute'); |
| 924 |
} |
} |
| 929 |
## reconsume |
## reconsume |
| 930 |
|
|
| 931 |
!!!emit ($self->{current_token}); # start tag or end tag |
!!!emit ($self->{current_token}); # start tag or end tag |
|
undef $self->{current_token}; |
|
| 932 |
|
|
| 933 |
redo A; |
redo A; |
| 934 |
} else { |
} else { |
| 938 |
redo A; |
redo A; |
| 939 |
} |
} |
| 940 |
} elsif ($self->{state} eq 'entity in attribute value') { |
} elsif ($self->{state} eq 'entity in attribute value') { |
| 941 |
my $token = $self->_tokenize_attempt_to_consume_an_entity; |
my $token = $self->_tokenize_attempt_to_consume_an_entity (1); |
| 942 |
|
|
| 943 |
unless (defined $token) { |
unless (defined $token) { |
| 944 |
$self->{current_attribute}->{value} .= '&'; |
$self->{current_attribute}->{value} .= '&'; |
| 987 |
push @next_char, $self->{next_input_character}; |
push @next_char, $self->{next_input_character}; |
| 988 |
if ($self->{next_input_character} == 0x002D) { # - |
if ($self->{next_input_character} == 0x002D) { # - |
| 989 |
$self->{current_token} = {type => 'comment', data => ''}; |
$self->{current_token} = {type => 'comment', data => ''}; |
| 990 |
$self->{state} = 'comment'; |
$self->{state} = 'comment start'; |
| 991 |
!!!next-input-character; |
!!!next-input-character; |
| 992 |
redo A; |
redo A; |
| 993 |
} |
} |
| 1029 |
} |
} |
| 1030 |
} |
} |
| 1031 |
|
|
| 1032 |
!!!parse-error (type => 'bogus comment open'); |
!!!parse-error (type => 'bogus comment'); |
| 1033 |
$self->{next_input_character} = shift @next_char; |
$self->{next_input_character} = shift @next_char; |
| 1034 |
!!!back-next-input-character (@next_char); |
!!!back-next-input-character (@next_char); |
| 1035 |
$self->{state} = 'bogus comment'; |
$self->{state} = 'bogus comment'; |
| 1037 |
|
|
| 1038 |
## ISSUE: typos in spec: chacacters, is is a parse error |
## ISSUE: typos in spec: chacacters, is is a parse error |
| 1039 |
## ISSUE: spec is somewhat unclear on "is the first character that will be in the comment"; what is "that will be in the comment" is what the algorithm defines, isn't it? |
## ISSUE: spec is somewhat unclear on "is the first character that will be in the comment"; what is "that will be in the comment" is what the algorithm defines, isn't it? |
| 1040 |
|
} elsif ($self->{state} eq 'comment start') { |
| 1041 |
|
if ($self->{next_input_character} == 0x002D) { # - |
| 1042 |
|
$self->{state} = 'comment start dash'; |
| 1043 |
|
!!!next-input-character; |
| 1044 |
|
redo A; |
| 1045 |
|
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1046 |
|
!!!parse-error (type => 'bogus comment'); |
| 1047 |
|
$self->{state} = 'data'; |
| 1048 |
|
!!!next-input-character; |
| 1049 |
|
|
| 1050 |
|
!!!emit ($self->{current_token}); # comment |
| 1051 |
|
|
| 1052 |
|
redo A; |
| 1053 |
|
} elsif ($self->{next_input_character} == -1) { |
| 1054 |
|
!!!parse-error (type => 'unclosed comment'); |
| 1055 |
|
$self->{state} = 'data'; |
| 1056 |
|
## reconsume |
| 1057 |
|
|
| 1058 |
|
!!!emit ($self->{current_token}); # comment |
| 1059 |
|
|
| 1060 |
|
redo A; |
| 1061 |
|
} else { |
| 1062 |
|
$self->{current_token}->{data} # comment |
| 1063 |
|
.= chr ($self->{next_input_character}); |
| 1064 |
|
$self->{state} = 'comment'; |
| 1065 |
|
!!!next-input-character; |
| 1066 |
|
redo A; |
| 1067 |
|
} |
| 1068 |
|
} elsif ($self->{state} eq 'comment start dash') { |
| 1069 |
|
if ($self->{next_input_character} == 0x002D) { # - |
| 1070 |
|
$self->{state} = 'comment end'; |
| 1071 |
|
!!!next-input-character; |
| 1072 |
|
redo A; |
| 1073 |
|
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1074 |
|
!!!parse-error (type => 'bogus comment'); |
| 1075 |
|
$self->{state} = 'data'; |
| 1076 |
|
!!!next-input-character; |
| 1077 |
|
|
| 1078 |
|
!!!emit ($self->{current_token}); # comment |
| 1079 |
|
|
| 1080 |
|
redo A; |
| 1081 |
|
} elsif ($self->{next_input_character} == -1) { |
| 1082 |
|
!!!parse-error (type => 'unclosed comment'); |
| 1083 |
|
$self->{state} = 'data'; |
| 1084 |
|
## reconsume |
| 1085 |
|
|
| 1086 |
|
!!!emit ($self->{current_token}); # comment |
| 1087 |
|
|
| 1088 |
|
redo A; |
| 1089 |
|
} else { |
| 1090 |
|
$self->{current_token}->{data} # comment |
| 1091 |
|
.= '-' . chr ($self->{next_input_character}); |
| 1092 |
|
$self->{state} = 'comment'; |
| 1093 |
|
!!!next-input-character; |
| 1094 |
|
redo A; |
| 1095 |
|
} |
| 1096 |
} elsif ($self->{state} eq 'comment') { |
} elsif ($self->{state} eq 'comment') { |
| 1097 |
if ($self->{next_input_character} == 0x002D) { # - |
if ($self->{next_input_character} == 0x002D) { # - |
| 1098 |
$self->{state} = 'comment dash'; |
$self->{state} = 'comment end dash'; |
| 1099 |
!!!next-input-character; |
!!!next-input-character; |
| 1100 |
redo A; |
redo A; |
| 1101 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1104 |
## reconsume |
## reconsume |
| 1105 |
|
|
| 1106 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
|
undef $self->{current_token}; |
|
| 1107 |
|
|
| 1108 |
redo A; |
redo A; |
| 1109 |
} else { |
} else { |
| 1112 |
!!!next-input-character; |
!!!next-input-character; |
| 1113 |
redo A; |
redo A; |
| 1114 |
} |
} |
| 1115 |
} elsif ($self->{state} eq 'comment dash') { |
} elsif ($self->{state} eq 'comment end dash') { |
| 1116 |
if ($self->{next_input_character} == 0x002D) { # - |
if ($self->{next_input_character} == 0x002D) { # - |
| 1117 |
$self->{state} = 'comment end'; |
$self->{state} = 'comment end'; |
| 1118 |
!!!next-input-character; |
!!!next-input-character; |
| 1123 |
## reconsume |
## reconsume |
| 1124 |
|
|
| 1125 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
|
undef $self->{current_token}; |
|
| 1126 |
|
|
| 1127 |
redo A; |
redo A; |
| 1128 |
} else { |
} else { |
| 1137 |
!!!next-input-character; |
!!!next-input-character; |
| 1138 |
|
|
| 1139 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
|
undef $self->{current_token}; |
|
| 1140 |
|
|
| 1141 |
redo A; |
redo A; |
| 1142 |
} elsif ($self->{next_input_character} == 0x002D) { # - |
} elsif ($self->{next_input_character} == 0x002D) { # - |
| 1151 |
## reconsume |
## reconsume |
| 1152 |
|
|
| 1153 |
!!!emit ($self->{current_token}); # comment |
!!!emit ($self->{current_token}); # comment |
|
undef $self->{current_token}; |
|
| 1154 |
|
|
| 1155 |
redo A; |
redo A; |
| 1156 |
} else { |
} else { |
| 1184 |
## Stay in the state |
## Stay in the state |
| 1185 |
!!!next-input-character; |
!!!next-input-character; |
| 1186 |
redo A; |
redo A; |
|
} elsif (0x0061 <= $self->{next_input_character} and |
|
|
$self->{next_input_character} <= 0x007A) { # a..z |
|
|
## ISSUE: "Set the token's name name to the" in the spec |
|
|
$self->{current_token} = {type => 'DOCTYPE', |
|
|
name => chr ($self->{next_input_character} - 0x0020), |
|
|
error => 1}; |
|
|
$self->{state} = 'DOCTYPE name'; |
|
|
!!!next-input-character; |
|
|
redo A; |
|
| 1187 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1188 |
!!!parse-error (type => 'no DOCTYPE name'); |
!!!parse-error (type => 'no DOCTYPE name'); |
| 1189 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 1190 |
!!!next-input-character; |
!!!next-input-character; |
| 1191 |
|
|
| 1192 |
!!!emit ({type => 'DOCTYPE', name => '', error => 1}); |
!!!emit ({type => 'DOCTYPE'}); # incorrect |
| 1193 |
|
|
| 1194 |
redo A; |
redo A; |
| 1195 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1197 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 1198 |
## reconsume |
## reconsume |
| 1199 |
|
|
| 1200 |
!!!emit ({type => 'DOCTYPE', name => '', error => 1}); |
!!!emit ({type => 'DOCTYPE'}); # incorrect |
| 1201 |
|
|
| 1202 |
redo A; |
redo A; |
| 1203 |
} else { |
} else { |
| 1204 |
$self->{current_token} = {type => 'DOCTYPE', |
$self->{current_token} |
| 1205 |
name => chr ($self->{next_input_character}), |
= {type => 'DOCTYPE', |
| 1206 |
error => 1}; |
name => chr ($self->{next_input_character}), |
| 1207 |
|
correct => 1}; |
| 1208 |
## ISSUE: "Set the token's name name to the" in the spec |
## ISSUE: "Set the token's name name to the" in the spec |
| 1209 |
$self->{state} = 'DOCTYPE name'; |
$self->{state} = 'DOCTYPE name'; |
| 1210 |
!!!next-input-character; |
!!!next-input-character; |
| 1211 |
redo A; |
redo A; |
| 1212 |
} |
} |
| 1213 |
} elsif ($self->{state} eq 'DOCTYPE name') { |
} elsif ($self->{state} eq 'DOCTYPE name') { |
| 1214 |
|
## ISSUE: Redundant "First," in the spec. |
| 1215 |
if ($self->{next_input_character} == 0x0009 or # HT |
if ($self->{next_input_character} == 0x0009 or # HT |
| 1216 |
$self->{next_input_character} == 0x000A or # LF |
$self->{next_input_character} == 0x000A or # LF |
| 1217 |
$self->{next_input_character} == 0x000B or # VT |
$self->{next_input_character} == 0x000B or # VT |
| 1218 |
$self->{next_input_character} == 0x000C or # FF |
$self->{next_input_character} == 0x000C or # FF |
| 1219 |
$self->{next_input_character} == 0x0020) { # SP |
$self->{next_input_character} == 0x0020) { # SP |
|
$self->{current_token}->{error} = ($self->{current_token}->{name} ne 'HTML'); # DOCTYPE |
|
| 1220 |
$self->{state} = 'after DOCTYPE name'; |
$self->{state} = 'after DOCTYPE name'; |
| 1221 |
!!!next-input-character; |
!!!next-input-character; |
| 1222 |
redo A; |
redo A; |
| 1223 |
} elsif ($self->{next_input_character} == 0x003E) { # > |
} elsif ($self->{next_input_character} == 0x003E) { # > |
|
$self->{current_token}->{error} = ($self->{current_token}->{name} ne 'HTML'); # DOCTYPE |
|
| 1224 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 1225 |
!!!next-input-character; |
!!!next-input-character; |
| 1226 |
|
|
| 1227 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1228 |
|
|
| 1229 |
redo A; |
redo A; |
|
} elsif (0x0061 <= $self->{next_input_character} and |
|
|
$self->{next_input_character} <= 0x007A) { # a..z |
|
|
$self->{current_token}->{name} .= chr ($self->{next_input_character} - 0x0020); # DOCTYPE |
|
|
#$self->{current_token}->{error} = ($self->{current_token}->{name} ne 'HTML'); |
|
|
## Stay in the state |
|
|
!!!next-input-character; |
|
|
redo A; |
|
| 1230 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1231 |
!!!parse-error (type => 'unclosed DOCTYPE'); |
!!!parse-error (type => 'unclosed DOCTYPE'); |
|
$self->{current_token}->{error} = ($self->{current_token}->{name} ne 'HTML'); # DOCTYPE |
|
| 1232 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 1233 |
## reconsume |
## reconsume |
| 1234 |
|
|
| 1235 |
!!!emit ($self->{current_token}); |
delete $self->{current_token}->{correct}; |
| 1236 |
undef $self->{current_token}; |
!!!emit ($self->{current_token}); # DOCTYPE |
| 1237 |
|
|
| 1238 |
redo A; |
redo A; |
| 1239 |
} else { |
} else { |
| 1240 |
$self->{current_token}->{name} |
$self->{current_token}->{name} |
| 1241 |
.= chr ($self->{next_input_character}); # DOCTYPE |
.= chr ($self->{next_input_character}); # DOCTYPE |
|
#$self->{current_token}->{error} = ($self->{current_token}->{name} ne 'HTML'); |
|
| 1242 |
## Stay in the state |
## Stay in the state |
| 1243 |
!!!next-input-character; |
!!!next-input-character; |
| 1244 |
redo A; |
redo A; |
| 1257 |
!!!next-input-character; |
!!!next-input-character; |
| 1258 |
|
|
| 1259 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1260 |
|
|
| 1261 |
redo A; |
redo A; |
| 1262 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1264 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 1265 |
## reconsume |
## reconsume |
| 1266 |
|
|
| 1267 |
|
delete $self->{current_token}->{correct}; |
| 1268 |
|
!!!emit ($self->{current_token}); # DOCTYPE |
| 1269 |
|
|
| 1270 |
|
redo A; |
| 1271 |
|
} elsif ($self->{next_input_character} == 0x0050 or # P |
| 1272 |
|
$self->{next_input_character} == 0x0070) { # p |
| 1273 |
|
!!!next-input-character; |
| 1274 |
|
if ($self->{next_input_character} == 0x0055 or # U |
| 1275 |
|
$self->{next_input_character} == 0x0075) { # u |
| 1276 |
|
!!!next-input-character; |
| 1277 |
|
if ($self->{next_input_character} == 0x0042 or # B |
| 1278 |
|
$self->{next_input_character} == 0x0062) { # b |
| 1279 |
|
!!!next-input-character; |
| 1280 |
|
if ($self->{next_input_character} == 0x004C or # L |
| 1281 |
|
$self->{next_input_character} == 0x006C) { # l |
| 1282 |
|
!!!next-input-character; |
| 1283 |
|
if ($self->{next_input_character} == 0x0049 or # I |
| 1284 |
|
$self->{next_input_character} == 0x0069) { # i |
| 1285 |
|
!!!next-input-character; |
| 1286 |
|
if ($self->{next_input_character} == 0x0043 or # C |
| 1287 |
|
$self->{next_input_character} == 0x0063) { # c |
| 1288 |
|
$self->{state} = 'before DOCTYPE public identifier'; |
| 1289 |
|
!!!next-input-character; |
| 1290 |
|
redo A; |
| 1291 |
|
} |
| 1292 |
|
} |
| 1293 |
|
} |
| 1294 |
|
} |
| 1295 |
|
} |
| 1296 |
|
|
| 1297 |
|
# |
| 1298 |
|
} elsif ($self->{next_input_character} == 0x0053 or # S |
| 1299 |
|
$self->{next_input_character} == 0x0073) { # s |
| 1300 |
|
!!!next-input-character; |
| 1301 |
|
if ($self->{next_input_character} == 0x0059 or # Y |
| 1302 |
|
$self->{next_input_character} == 0x0079) { # y |
| 1303 |
|
!!!next-input-character; |
| 1304 |
|
if ($self->{next_input_character} == 0x0053 or # S |
| 1305 |
|
$self->{next_input_character} == 0x0073) { # s |
| 1306 |
|
!!!next-input-character; |
| 1307 |
|
if ($self->{next_input_character} == 0x0054 or # T |
| 1308 |
|
$self->{next_input_character} == 0x0074) { # t |
| 1309 |
|
!!!next-input-character; |
| 1310 |
|
if ($self->{next_input_character} == 0x0045 or # E |
| 1311 |
|
$self->{next_input_character} == 0x0065) { # e |
| 1312 |
|
!!!next-input-character; |
| 1313 |
|
if ($self->{next_input_character} == 0x004D or # M |
| 1314 |
|
$self->{next_input_character} == 0x006D) { # m |
| 1315 |
|
$self->{state} = 'before DOCTYPE system identifier'; |
| 1316 |
|
!!!next-input-character; |
| 1317 |
|
redo A; |
| 1318 |
|
} |
| 1319 |
|
} |
| 1320 |
|
} |
| 1321 |
|
} |
| 1322 |
|
} |
| 1323 |
|
|
| 1324 |
|
# |
| 1325 |
|
} else { |
| 1326 |
|
!!!next-input-character; |
| 1327 |
|
# |
| 1328 |
|
} |
| 1329 |
|
|
| 1330 |
|
!!!parse-error (type => 'string after DOCTYPE name'); |
| 1331 |
|
$self->{state} = 'bogus DOCTYPE'; |
| 1332 |
|
# next-input-character is already done |
| 1333 |
|
redo A; |
| 1334 |
|
} elsif ($self->{state} eq 'before DOCTYPE public identifier') { |
| 1335 |
|
if ({ |
| 1336 |
|
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
| 1337 |
|
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
| 1338 |
|
}->{$self->{next_input_character}}) { |
| 1339 |
|
## Stay in the state |
| 1340 |
|
!!!next-input-character; |
| 1341 |
|
redo A; |
| 1342 |
|
} elsif ($self->{next_input_character} eq 0x0022) { # " |
| 1343 |
|
$self->{current_token}->{public_identifier} = ''; # DOCTYPE |
| 1344 |
|
$self->{state} = 'DOCTYPE public identifier (double-quoted)'; |
| 1345 |
|
!!!next-input-character; |
| 1346 |
|
redo A; |
| 1347 |
|
} elsif ($self->{next_input_character} eq 0x0027) { # ' |
| 1348 |
|
$self->{current_token}->{public_identifier} = ''; # DOCTYPE |
| 1349 |
|
$self->{state} = 'DOCTYPE public identifier (single-quoted)'; |
| 1350 |
|
!!!next-input-character; |
| 1351 |
|
redo A; |
| 1352 |
|
} elsif ($self->{next_input_character} eq 0x003E) { # > |
| 1353 |
|
!!!parse-error (type => 'no PUBLIC literal'); |
| 1354 |
|
|
| 1355 |
|
$self->{state} = 'data'; |
| 1356 |
|
!!!next-input-character; |
| 1357 |
|
|
| 1358 |
|
delete $self->{current_token}->{correct}; |
| 1359 |
|
!!!emit ($self->{current_token}); # DOCTYPE |
| 1360 |
|
|
| 1361 |
|
redo A; |
| 1362 |
|
} elsif ($self->{next_input_character} == -1) { |
| 1363 |
|
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1364 |
|
|
| 1365 |
|
$self->{state} = 'data'; |
| 1366 |
|
## reconsume |
| 1367 |
|
|
| 1368 |
|
delete $self->{current_token}->{correct}; |
| 1369 |
|
!!!emit ($self->{current_token}); # DOCTYPE |
| 1370 |
|
|
| 1371 |
|
redo A; |
| 1372 |
|
} else { |
| 1373 |
|
!!!parse-error (type => 'string after PUBLIC'); |
| 1374 |
|
$self->{state} = 'bogus DOCTYPE'; |
| 1375 |
|
!!!next-input-character; |
| 1376 |
|
redo A; |
| 1377 |
|
} |
| 1378 |
|
} elsif ($self->{state} eq 'DOCTYPE public identifier (double-quoted)') { |
| 1379 |
|
if ($self->{next_input_character} == 0x0022) { # " |
| 1380 |
|
$self->{state} = 'after DOCTYPE public identifier'; |
| 1381 |
|
!!!next-input-character; |
| 1382 |
|
redo A; |
| 1383 |
|
} elsif ($self->{next_input_character} == -1) { |
| 1384 |
|
!!!parse-error (type => 'unclosed PUBLIC literal'); |
| 1385 |
|
|
| 1386 |
|
$self->{state} = 'data'; |
| 1387 |
|
## reconsume |
| 1388 |
|
|
| 1389 |
|
delete $self->{current_token}->{correct}; |
| 1390 |
|
!!!emit ($self->{current_token}); # DOCTYPE |
| 1391 |
|
|
| 1392 |
|
redo A; |
| 1393 |
|
} else { |
| 1394 |
|
$self->{current_token}->{public_identifier} # DOCTYPE |
| 1395 |
|
.= chr $self->{next_input_character}; |
| 1396 |
|
## Stay in the state |
| 1397 |
|
!!!next-input-character; |
| 1398 |
|
redo A; |
| 1399 |
|
} |
| 1400 |
|
} elsif ($self->{state} eq 'DOCTYPE public identifier (single-quoted)') { |
| 1401 |
|
if ($self->{next_input_character} == 0x0027) { # ' |
| 1402 |
|
$self->{state} = 'after DOCTYPE public identifier'; |
| 1403 |
|
!!!next-input-character; |
| 1404 |
|
redo A; |
| 1405 |
|
} elsif ($self->{next_input_character} == -1) { |
| 1406 |
|
!!!parse-error (type => 'unclosed PUBLIC literal'); |
| 1407 |
|
|
| 1408 |
|
$self->{state} = 'data'; |
| 1409 |
|
## reconsume |
| 1410 |
|
|
| 1411 |
|
delete $self->{current_token}->{correct}; |
| 1412 |
|
!!!emit ($self->{current_token}); # DOCTYPE |
| 1413 |
|
|
| 1414 |
|
redo A; |
| 1415 |
|
} else { |
| 1416 |
|
$self->{current_token}->{public_identifier} # DOCTYPE |
| 1417 |
|
.= chr $self->{next_input_character}; |
| 1418 |
|
## Stay in the state |
| 1419 |
|
!!!next-input-character; |
| 1420 |
|
redo A; |
| 1421 |
|
} |
| 1422 |
|
} elsif ($self->{state} eq 'after DOCTYPE public identifier') { |
| 1423 |
|
if ({ |
| 1424 |
|
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
| 1425 |
|
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
| 1426 |
|
}->{$self->{next_input_character}}) { |
| 1427 |
|
## Stay in the state |
| 1428 |
|
!!!next-input-character; |
| 1429 |
|
redo A; |
| 1430 |
|
} elsif ($self->{next_input_character} == 0x0022) { # " |
| 1431 |
|
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
| 1432 |
|
$self->{state} = 'DOCTYPE system identifier (double-quoted)'; |
| 1433 |
|
!!!next-input-character; |
| 1434 |
|
redo A; |
| 1435 |
|
} elsif ($self->{next_input_character} == 0x0027) { # ' |
| 1436 |
|
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
| 1437 |
|
$self->{state} = 'DOCTYPE system identifier (single-quoted)'; |
| 1438 |
|
!!!next-input-character; |
| 1439 |
|
redo A; |
| 1440 |
|
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1441 |
|
$self->{state} = 'data'; |
| 1442 |
|
!!!next-input-character; |
| 1443 |
|
|
| 1444 |
|
!!!emit ($self->{current_token}); # DOCTYPE |
| 1445 |
|
|
| 1446 |
|
redo A; |
| 1447 |
|
} elsif ($self->{next_input_character} == -1) { |
| 1448 |
|
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1449 |
|
|
| 1450 |
|
$self->{state} = 'data'; |
| 1451 |
|
## reconsume |
| 1452 |
|
|
| 1453 |
|
delete $self->{current_token}->{correct}; |
| 1454 |
|
!!!emit ($self->{current_token}); # DOCTYPE |
| 1455 |
|
|
| 1456 |
|
redo A; |
| 1457 |
|
} else { |
| 1458 |
|
!!!parse-error (type => 'string after PUBLIC literal'); |
| 1459 |
|
$self->{state} = 'bogus DOCTYPE'; |
| 1460 |
|
!!!next-input-character; |
| 1461 |
|
redo A; |
| 1462 |
|
} |
| 1463 |
|
} elsif ($self->{state} eq 'before DOCTYPE system identifier') { |
| 1464 |
|
if ({ |
| 1465 |
|
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
| 1466 |
|
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
| 1467 |
|
}->{$self->{next_input_character}}) { |
| 1468 |
|
## Stay in the state |
| 1469 |
|
!!!next-input-character; |
| 1470 |
|
redo A; |
| 1471 |
|
} elsif ($self->{next_input_character} == 0x0022) { # " |
| 1472 |
|
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
| 1473 |
|
$self->{state} = 'DOCTYPE system identifier (double-quoted)'; |
| 1474 |
|
!!!next-input-character; |
| 1475 |
|
redo A; |
| 1476 |
|
} elsif ($self->{next_input_character} == 0x0027) { # ' |
| 1477 |
|
$self->{current_token}->{system_identifier} = ''; # DOCTYPE |
| 1478 |
|
$self->{state} = 'DOCTYPE system identifier (single-quoted)'; |
| 1479 |
|
!!!next-input-character; |
| 1480 |
|
redo A; |
| 1481 |
|
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1482 |
|
!!!parse-error (type => 'no SYSTEM literal'); |
| 1483 |
|
$self->{state} = 'data'; |
| 1484 |
|
!!!next-input-character; |
| 1485 |
|
|
| 1486 |
|
delete $self->{current_token}->{correct}; |
| 1487 |
|
!!!emit ($self->{current_token}); # DOCTYPE |
| 1488 |
|
|
| 1489 |
|
redo A; |
| 1490 |
|
} elsif ($self->{next_input_character} == -1) { |
| 1491 |
|
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1492 |
|
|
| 1493 |
|
$self->{state} = 'data'; |
| 1494 |
|
## reconsume |
| 1495 |
|
|
| 1496 |
|
delete $self->{current_token}->{correct}; |
| 1497 |
|
!!!emit ($self->{current_token}); # DOCTYPE |
| 1498 |
|
|
| 1499 |
|
redo A; |
| 1500 |
|
} else { |
| 1501 |
|
!!!parse-error (type => 'string after SYSTEM'); |
| 1502 |
|
$self->{state} = 'bogus DOCTYPE'; |
| 1503 |
|
!!!next-input-character; |
| 1504 |
|
redo A; |
| 1505 |
|
} |
| 1506 |
|
} elsif ($self->{state} eq 'DOCTYPE system identifier (double-quoted)') { |
| 1507 |
|
if ($self->{next_input_character} == 0x0022) { # " |
| 1508 |
|
$self->{state} = 'after DOCTYPE system identifier'; |
| 1509 |
|
!!!next-input-character; |
| 1510 |
|
redo A; |
| 1511 |
|
} elsif ($self->{next_input_character} == -1) { |
| 1512 |
|
!!!parse-error (type => 'unclosed SYSTEM literal'); |
| 1513 |
|
|
| 1514 |
|
$self->{state} = 'data'; |
| 1515 |
|
## reconsume |
| 1516 |
|
|
| 1517 |
|
delete $self->{current_token}->{correct}; |
| 1518 |
|
!!!emit ($self->{current_token}); # DOCTYPE |
| 1519 |
|
|
| 1520 |
|
redo A; |
| 1521 |
|
} else { |
| 1522 |
|
$self->{current_token}->{system_identifier} # DOCTYPE |
| 1523 |
|
.= chr $self->{next_input_character}; |
| 1524 |
|
## Stay in the state |
| 1525 |
|
!!!next-input-character; |
| 1526 |
|
redo A; |
| 1527 |
|
} |
| 1528 |
|
} elsif ($self->{state} eq 'DOCTYPE system identifier (single-quoted)') { |
| 1529 |
|
if ($self->{next_input_character} == 0x0027) { # ' |
| 1530 |
|
$self->{state} = 'after DOCTYPE system identifier'; |
| 1531 |
|
!!!next-input-character; |
| 1532 |
|
redo A; |
| 1533 |
|
} elsif ($self->{next_input_character} == -1) { |
| 1534 |
|
!!!parse-error (type => 'unclosed SYSTEM literal'); |
| 1535 |
|
|
| 1536 |
|
$self->{state} = 'data'; |
| 1537 |
|
## reconsume |
| 1538 |
|
|
| 1539 |
|
delete $self->{current_token}->{correct}; |
| 1540 |
|
!!!emit ($self->{current_token}); # DOCTYPE |
| 1541 |
|
|
| 1542 |
|
redo A; |
| 1543 |
|
} else { |
| 1544 |
|
$self->{current_token}->{system_identifier} # DOCTYPE |
| 1545 |
|
.= chr $self->{next_input_character}; |
| 1546 |
|
## Stay in the state |
| 1547 |
|
!!!next-input-character; |
| 1548 |
|
redo A; |
| 1549 |
|
} |
| 1550 |
|
} elsif ($self->{state} eq 'after DOCTYPE system identifier') { |
| 1551 |
|
if ({ |
| 1552 |
|
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, 0x0020 => 1, |
| 1553 |
|
#0x000D => 1, # HT, LF, VT, FF, SP, CR |
| 1554 |
|
}->{$self->{next_input_character}}) { |
| 1555 |
|
## Stay in the state |
| 1556 |
|
!!!next-input-character; |
| 1557 |
|
redo A; |
| 1558 |
|
} elsif ($self->{next_input_character} == 0x003E) { # > |
| 1559 |
|
$self->{state} = 'data'; |
| 1560 |
|
!!!next-input-character; |
| 1561 |
|
|
| 1562 |
|
!!!emit ($self->{current_token}); # DOCTYPE |
| 1563 |
|
|
| 1564 |
|
redo A; |
| 1565 |
|
} elsif ($self->{next_input_character} == -1) { |
| 1566 |
|
!!!parse-error (type => 'unclosed DOCTYPE'); |
| 1567 |
|
|
| 1568 |
|
$self->{state} = 'data'; |
| 1569 |
|
## reconsume |
| 1570 |
|
|
| 1571 |
|
delete $self->{current_token}->{correct}; |
| 1572 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1573 |
|
|
| 1574 |
redo A; |
redo A; |
| 1575 |
} else { |
} else { |
| 1576 |
!!!parse-error (type => 'string after DOCTYPE name'); |
!!!parse-error (type => 'string after SYSTEM literal'); |
|
$self->{current_token}->{error} = 1; # DOCTYPE |
|
| 1577 |
$self->{state} = 'bogus DOCTYPE'; |
$self->{state} = 'bogus DOCTYPE'; |
| 1578 |
!!!next-input-character; |
!!!next-input-character; |
| 1579 |
redo A; |
redo A; |
| 1583 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 1584 |
!!!next-input-character; |
!!!next-input-character; |
| 1585 |
|
|
| 1586 |
|
delete $self->{current_token}->{correct}; |
| 1587 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1588 |
|
|
| 1589 |
redo A; |
redo A; |
| 1590 |
} elsif ($self->{next_input_character} == -1) { |
} elsif ($self->{next_input_character} == -1) { |
| 1592 |
$self->{state} = 'data'; |
$self->{state} = 'data'; |
| 1593 |
## reconsume |
## reconsume |
| 1594 |
|
|
| 1595 |
|
delete $self->{current_token}->{correct}; |
| 1596 |
!!!emit ($self->{current_token}); # DOCTYPE |
!!!emit ($self->{current_token}); # DOCTYPE |
|
undef $self->{current_token}; |
|
| 1597 |
|
|
| 1598 |
redo A; |
redo A; |
| 1599 |
} else { |
} else { |
| 1609 |
die "$0: _get_next_token: unexpected case"; |
die "$0: _get_next_token: unexpected case"; |
| 1610 |
} # _get_next_token |
} # _get_next_token |
| 1611 |
|
|
| 1612 |
sub _tokenize_attempt_to_consume_an_entity ($) { |
sub _tokenize_attempt_to_consume_an_entity ($$) { |
| 1613 |
my $self = shift; |
my ($self, $in_attr) = @_; |
| 1614 |
|
|
| 1615 |
if ($self->{next_input_character} == 0x0023) { # # |
if ({ |
| 1616 |
|
0x0009 => 1, 0x000A => 1, 0x000B => 1, 0x000C => 1, # HT, LF, VT, FF, |
| 1617 |
|
0x0020 => 1, 0x003C => 1, 0x0026 => 1, -1 => 1, # SP, <, & # 0x000D # CR |
| 1618 |
|
}->{$self->{next_input_character}}) { |
| 1619 |
|
## Don't consume |
| 1620 |
|
## No error |
| 1621 |
|
return undef; |
| 1622 |
|
} elsif ($self->{next_input_character} == 0x0023) { # # |
| 1623 |
!!!next-input-character; |
!!!next-input-character; |
| 1624 |
if ($self->{next_input_character} == 0x0078 or # x |
if ($self->{next_input_character} == 0x0078 or # x |
| 1625 |
$self->{next_input_character} == 0x0058) { # X |
$self->{next_input_character} == 0x0058) { # X |
| 1626 |
my $num; |
my $code; |
| 1627 |
X: { |
X: { |
| 1628 |
my $x_char = $self->{next_input_character}; |
my $x_char = $self->{next_input_character}; |
| 1629 |
!!!next-input-character; |
!!!next-input-character; |
| 1630 |
if (0x0030 <= $self->{next_input_character} and |
if (0x0030 <= $self->{next_input_character} and |
| 1631 |
$self->{next_input_character} <= 0x0039) { # 0..9 |
$self->{next_input_character} <= 0x0039) { # 0..9 |
| 1632 |
$num ||= 0; |
$code ||= 0; |
| 1633 |
$num *= 0x10; |
$code *= 0x10; |
| 1634 |
$num += $self->{next_input_character} - 0x0030; |
$code += $self->{next_input_character} - 0x0030; |
| 1635 |
redo X; |
redo X; |
| 1636 |
} elsif (0x0061 <= $self->{next_input_character} and |
} elsif (0x0061 <= $self->{next_input_character} and |
| 1637 |
$self->{next_input_character} <= 0x0066) { # a..f |
$self->{next_input_character} <= 0x0066) { # a..f |
| 1638 |
## ISSUE: the spec says U+0078, which is apparently incorrect |
$code ||= 0; |
| 1639 |
$num ||= 0; |
$code *= 0x10; |
| 1640 |
$num *= 0x10; |
$code += $self->{next_input_character} - 0x0060 + 9; |
|
$num += $self->{next_input_character} - 0x0060 + 9; |
|
| 1641 |
redo X; |
redo X; |
| 1642 |
} elsif (0x0041 <= $self->{next_input_character} and |
} elsif (0x0041 <= $self->{next_input_character} and |
| 1643 |
$self->{next_input_character} <= 0x0046) { # A..F |
$self->{next_input_character} <= 0x0046) { # A..F |
| 1644 |
## ISSUE: the spec says U+0058, which is apparently incorrect |
$code ||= 0; |
| 1645 |
$num ||= 0; |
$code *= 0x10; |
| 1646 |
$num *= 0x10; |
$code += $self->{next_input_character} - 0x0040 + 9; |
|
$num += $self->{next_input_character} - 0x0040 + 9; |
|
| 1647 |
redo X; |
redo X; |
| 1648 |
} elsif (not defined $num) { # no hexadecimal digit |
} elsif (not defined $code) { # no hexadecimal digit |
| 1649 |
!!!parse-error (type => 'bare hcro'); |
!!!parse-error (type => 'bare hcro'); |
| 1650 |
|
!!!back-next-input-character ($x_char, $self->{next_input_character}); |
| 1651 |
$self->{next_input_character} = 0x0023; # # |
$self->{next_input_character} = 0x0023; # # |
|
!!!back-next-input-character ($x_char); |
|
| 1652 |
return undef; |
return undef; |
| 1653 |
} elsif ($self->{next_input_character} == 0x003B) { # ; |
} elsif ($self->{next_input_character} == 0x003B) { # ; |
| 1654 |
!!!next-input-character; |
!!!next-input-character; |
| 1656 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'no refc'); |
| 1657 |
} |
} |
| 1658 |
|
|
| 1659 |
## TODO: check the definition for |a valid Unicode character|. |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 1660 |
## <http://lists.whatwg.org/pipermail/whatwg-whatwg.org/2006-December/thread.html#8189> |
!!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code); |
| 1661 |
if ($num > 1114111 or $num == 0) { |
$code = 0xFFFD; |
| 1662 |
$num = 0xFFFD; # REPLACEMENT CHARACTER |
} elsif ($code > 0x10FFFF) { |
| 1663 |
## ISSUE: Why this is not an error? |
!!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code); |
| 1664 |
} elsif (0x80 <= $num and $num <= 0x9F) { |
$code = 0xFFFD; |
| 1665 |
!!!parse-error (type => sprintf 'c1 entity:U+%04X', $num); |
} elsif ($code == 0x000D) { |
| 1666 |
$num = $c1_entity_char->{$num}; |
!!!parse-error (type => 'CR character reference'); |
| 1667 |
|
$code = 0x000A; |
| 1668 |
|
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 1669 |
|
!!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code); |
| 1670 |
|
$code = $c1_entity_char->{$code}; |
| 1671 |
} |
} |
| 1672 |
|
|
| 1673 |
return {type => 'character', data => chr $num}; |
return {type => 'character', data => chr $code}; |
| 1674 |
} # X |
} # X |
| 1675 |
} elsif (0x0030 <= $self->{next_input_character} and |
} elsif (0x0030 <= $self->{next_input_character} and |
| 1676 |
$self->{next_input_character} <= 0x0039) { # 0..9 |
$self->{next_input_character} <= 0x0039) { # 0..9 |
| 1691 |
!!!parse-error (type => 'no refc'); |
!!!parse-error (type => 'no refc'); |
| 1692 |
} |
} |
| 1693 |
|
|
| 1694 |
## TODO: check the definition for |a valid Unicode character|. |
if ($code == 0 or (0xD800 <= $code and $code <= 0xDFFF)) { |
| 1695 |
if ($code > 1114111 or $code == 0) { |
!!!parse-error (type => sprintf 'invalid character reference:U+%04X', $code); |
| 1696 |
$code = 0xFFFD; # REPLACEMENT CHARACTER |
$code = 0xFFFD; |
| 1697 |
## ISSUE: Why this is not an error? |
} elsif ($code > 0x10FFFF) { |
| 1698 |
|
!!!parse-error (type => sprintf 'invalid character reference:U-%08X', $code); |
| 1699 |
|
$code = 0xFFFD; |
| 1700 |
|
} elsif ($code == 0x000D) { |
| 1701 |
|
!!!parse-error (type => 'CR character reference'); |
| 1702 |
|
$code = 0x000A; |
| 1703 |
} elsif (0x80 <= $code and $code <= 0x9F) { |
} elsif (0x80 <= $code and $code <= 0x9F) { |
| 1704 |
!!!parse-error (type => sprintf 'c1 entity:U+%04X', $code); |
!!!parse-error (type => sprintf 'C1 character reference:U+%04X', $code); |
| 1705 |
$code = $c1_entity_char->{$code}; |
$code = $c1_entity_char->{$code}; |
| 1706 |
} |
} |
| 1707 |
|
|
| 1720 |
!!!next-input-character; |
!!!next-input-character; |
| 1721 |
|
|
| 1722 |
my $value = $entity_name; |
my $value = $entity_name; |
| 1723 |
my $match; |
my $match = 0; |
| 1724 |
|
require Whatpm::_NamedEntityList; |
| 1725 |
|
our $EntityChar; |
| 1726 |
|
|
| 1727 |
while (length $entity_name < 10 and |
while (length $entity_name < 10 and |
| 1728 |
## NOTE: Some number greater than the maximum length of entity name |
## NOTE: Some number greater than the maximum length of entity name |
| 1729 |
((0x0041 <= $self->{next_input_character} and |
((0x0041 <= $self->{next_input_character} and # a |
| 1730 |
$self->{next_input_character} <= 0x005A) or |
$self->{next_input_character} <= 0x005A) or # x |
| 1731 |
(0x0061 <= $self->{next_input_character} and |
(0x0061 <= $self->{next_input_character} and # a |
| 1732 |
$self->{next_input_character} <= 0x007A) or |
$self->{next_input_character} <= 0x007A) or # z |
| 1733 |
(0x0030 <= $self->{next_input_character} and |
(0x0030 <= $self->{next_input_character} and # 0 |
| 1734 |
$self->{next_input_character} <= 0x0039))) { |
$self->{next_input_character} <= 0x0039) or # 9 |
| 1735 |
|
$self->{next_input_character} == 0x003B)) { # ; |
| 1736 |
$entity_name .= chr $self->{next_input_character}; |
$entity_name .= chr $self->{next_input_character}; |
| 1737 |
if (defined $entity_char->{$entity_name}) { |
if (defined $EntityChar->{$entity_name}) { |
| 1738 |
$value = $entity_char->{$entity_name}; |
if ($self->{next_input_character} == 0x003B) { # ; |
| 1739 |
$match = 1; |
$value = $EntityChar->{$entity_name}; |
| 1740 |
|
$match = 1; |
| 1741 |
|
!!!next-input-character; |
| 1742 |
|
last; |
| 1743 |
|
} else { |
| 1744 |
|
$value = $EntityChar->{$entity_name}; |
| 1745 |
|
$match = -1; |
| 1746 |
|
!!!next-input-character; |
| 1747 |
|
} |
| 1748 |
} else { |
} else { |
| 1749 |
$value .= chr $self->{next_input_character}; |
$value .= chr $self->{next_input_character}; |
| 1750 |
|
$match *= 2; |
| 1751 |
|
!!!next-input-character; |
| 1752 |
} |
} |
|
!!!next-input-character; |
|
| 1753 |
} |
} |
| 1754 |
|
|
| 1755 |
if ($match) { |
if ($match > 0) { |
| 1756 |
if ($self->{next_input_character} == 0x003B) { # ; |
return {type => 'character', data => $value}; |
| 1757 |
!!!next-input-character; |
} elsif ($match < 0) { |
| 1758 |
|
!!!parse-error (type => 'no refc'); |
| 1759 |
|
if ($in_attr and $match < -1) { |
| 1760 |
|
return {type => 'character', data => '&'.$entity_name}; |
| 1761 |
} else { |
} else { |
| 1762 |
!!!parse-error (type => 'refc'); |
return {type => 'character', data => $value}; |
| 1763 |
} |
} |
|
|
|
|
return {type => 'character', data => $value}; |
|
| 1764 |
} else { |
} else { |
| 1765 |
!!!parse-error (type => 'bare ero'); |
!!!parse-error (type => 'bare ero'); |
| 1766 |
## NOTE: No characters are consumed in the spec. |
## NOTE: No characters are consumed in the spec. |
| 1767 |
!!!back-token ({type => 'character', data => $value}); |
return {type => 'character', data => '&'.$value}; |
|
return undef; |
|
| 1768 |
} |
} |
| 1769 |
} else { |
} else { |
| 1770 |
## no characters are consumed |
## no characters are consumed |
| 1779 |
$self->{document}->strict_error_checking (0); |
$self->{document}->strict_error_checking (0); |
| 1780 |
## TODO: Turn mutation events off # MUST |
## TODO: Turn mutation events off # MUST |
| 1781 |
## TODO: Turn loose Document option (manakai extension) on |
## TODO: Turn loose Document option (manakai extension) on |
| 1782 |
## TODO: Mark the Document as an HTML document # MUST |
$self->{document}->manakai_is_html (1); # MUST |
| 1783 |
} # _initialize_tree_constructor |
} # _initialize_tree_constructor |
| 1784 |
|
|
| 1785 |
sub _terminate_tree_constructor ($) { |
sub _terminate_tree_constructor ($) { |
| 1819 |
|
|
| 1820 |
sub _tree_construction_initial ($) { |
sub _tree_construction_initial ($) { |
| 1821 |
my $self = shift; |
my $self = shift; |
| 1822 |
B: { |
INITIAL: { |
| 1823 |
if ($token->{type} eq 'DOCTYPE') { |
if ($token->{type} eq 'DOCTYPE') { |
| 1824 |
if ($token->{error}) { |
## NOTE: Conformance checkers MAY, instead of reporting "not HTML5" |
| 1825 |
## ISSUE: Spec currently left this case undefined. |
## error, switch to a conformance checking mode for another |
| 1826 |
!!!parse-error (type => 'bogus DOCTYPE'); |
## language. |
| 1827 |
} |
my $doctype_name = $token->{name}; |
| 1828 |
my $doctype = $self->{document}->create_document_type_definition |
$doctype_name = '' unless defined $doctype_name; |
| 1829 |
($token->{name}); |
$doctype_name =~ tr/a-z/A-Z/; |
| 1830 |
$self->{document}->append_child ($doctype); |
if (not defined $token->{name} or # <!DOCTYPE> |
| 1831 |
#$phase = 'root element'; |
defined $token->{public_identifier} or |
| 1832 |
!!!next-token; |
defined $token->{system_identifier}) { |
| 1833 |
#redo B; |
!!!parse-error (type => 'not HTML5'); |
| 1834 |
return; |
} elsif ($doctype_name ne 'HTML') { |
| 1835 |
} elsif ({ |
## ISSUE: ASCII case-insensitive? (in fact it does not matter) |
| 1836 |
comment => 1, |
!!!parse-error (type => 'not HTML5'); |
| 1837 |
'start tag' => 1, |
} |
| 1838 |
'end tag' => 1, |
|
| 1839 |
'end-of-file' => 1, |
my $doctype = $self->{document}->create_document_type_definition |
| 1840 |
}->{$token->{type}}) { |
($token->{name}); ## ISSUE: If name is missing (e.g. <!DOCTYPE>)? |
| 1841 |
## ISSUE: Spec currently left this case undefined. |
$doctype->public_id ($token->{public_identifier}) |
| 1842 |
!!!parse-error (type => 'missing DOCTYPE'); |
if defined $token->{public_identifier}; |
| 1843 |
#$phase = 'root element'; |
$doctype->system_id ($token->{system_identifier}) |
| 1844 |
## reprocess |
if defined $token->{system_identifier}; |
| 1845 |
#redo B; |
## NOTE: Other DocumentType attributes are null or empty lists. |
| 1846 |
return; |
## ISSUE: internalSubset = null?? |
| 1847 |
} elsif ($token->{type} eq 'character') { |
$self->{document}->append_child ($doctype); |
| 1848 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
|
| 1849 |
$self->{document}->manakai_append_text ($1); |
if (not $token->{correct} or $doctype_name ne 'HTML') { |
| 1850 |
## ISSUE: DOM3 Core does not allow Document > Text |
$self->{document}->manakai_compat_mode ('quirks'); |
| 1851 |
unless (length $token->{data}) { |
} elsif (defined $token->{public_identifier}) { |
| 1852 |
## Stay in the phase |
my $pubid = $token->{public_identifier}; |
| 1853 |
!!!next-token; |
$pubid =~ tr/a-z/A-z/; |
| 1854 |
redo B; |
if ({ |
| 1855 |
|
"+//SILMARIL//DTD HTML PRO V0R11 19970101//EN" => 1, |
| 1856 |
|
"-//ADVASOFT LTD//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1, |
| 1857 |
|
"-//AS//DTD HTML 3.0 ASWEDIT + EXTENSIONS//EN" => 1, |
| 1858 |
|
"-//IETF//DTD HTML 2.0 LEVEL 1//EN" => 1, |
| 1859 |
|
"-//IETF//DTD HTML 2.0 LEVEL 2//EN" => 1, |
| 1860 |
|
"-//IETF//DTD HTML 2.0 STRICT LEVEL 1//EN" => 1, |
| 1861 |
|
"-//IETF//DTD HTML 2.0 STRICT LEVEL 2//EN" => 1, |
| 1862 |
|
"-//IETF//DTD HTML 2.0 STRICT//EN" => 1, |
| 1863 |
|
"-//IETF//DTD HTML 2.0//EN" => 1, |
| 1864 |
|
"-//IETF//DTD HTML 2.1E//EN" => 1, |
| 1865 |
|
"-//IETF//DTD HTML 3.0//EN" => 1, |
| 1866 |
|
"-//IETF//DTD HTML 3.0//EN//" => 1, |
| 1867 |
|
"-//IETF//DTD HTML 3.2 FINAL//EN" => 1, |
| 1868 |
|
"-//IETF//DTD HTML 3.2//EN" => 1, |
| 1869 |
|
"-//IETF//DTD HTML 3//EN" => 1, |
| 1870 |
|
"-//IETF//DTD HTML LEVEL 0//EN" => 1, |
| 1871 |
|
"-//IETF//DTD HTML LEVEL 0//EN//2.0" => 1, |
| 1872 |
|
"-//IETF//DTD HTML LEVEL 1//EN" => 1, |
| 1873 |
|
"-//IETF//DTD HTML LEVEL 1//EN//2.0" => 1, |
| 1874 |
|
"-//IETF//DTD HTML LEVEL 2//EN" => 1, |
| 1875 |
|
"-//IETF//DTD HTML LEVEL 2//EN//2.0" => 1, |
| 1876 |
|
"-//IETF//DTD HTML LEVEL 3//EN" => 1, |
| 1877 |
|
"-//IETF//DTD HTML LEVEL 3//EN//3.0" => 1, |
| 1878 |
|
"-//IETF//DTD HTML STRICT LEVEL 0//EN" => 1, |
| 1879 |
|
"-//IETF//DTD HTML STRICT LEVEL 0//EN//2.0" => 1, |
| 1880 |
|
"-//IETF//DTD HTML STRICT LEVEL 1//EN" => 1, |
| 1881 |
|
"-//IETF//DTD HTML STRICT LEVEL 1//EN//2.0" => 1, |
| 1882 |
|
"-//IETF//DTD HTML STRICT LEVEL 2//EN" => 1, |
| 1883 |
|
"-//IETF//DTD HTML STRICT LEVEL 2//EN//2.0" => 1, |
| 1884 |
|
"-//IETF//DTD HTML STRICT LEVEL 3//EN" => 1, |
| 1885 |
|
"-//IETF//DTD HTML STRICT LEVEL 3//EN//3.0" => 1, |
| 1886 |
|
"-//IETF//DTD HTML STRICT//EN" => 1, |
| 1887 |
|
"-//IETF//DTD HTML STRICT//EN//2.0" => 1, |
| 1888 |
|
"-//IETF//DTD HTML STRICT//EN//3.0" => 1, |
| 1889 |
|
"-//IETF//DTD HTML//EN" => 1, |
| 1890 |
|
"-//IETF//DTD HTML//EN//2.0" => 1, |
| 1891 |
|
"-//IETF//DTD HTML//EN//3.0" => 1, |
| 1892 |
|
"-//METRIUS//DTD METRIUS PRESENTATIONAL//EN" => 1, |
| 1893 |
|
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML STRICT//EN" => 1, |
| 1894 |
|
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 HTML//EN" => 1, |
| 1895 |
|
"-//MICROSOFT//DTD INTERNET EXPLORER 2.0 TABLES//EN" => 1, |
| 1896 |
|
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML STRICT//EN" => 1, |
| 1897 |
|
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 HTML//EN" => 1, |
| 1898 |
|
"-//MICROSOFT//DTD INTERNET EXPLORER 3.0 TABLES//EN" => 1, |
| 1899 |
|
"-//NETSCAPE COMM. CORP.//DTD HTML//EN" => 1, |
| 1900 |
|
"-//NETSCAPE COMM. CORP.//DTD STRICT HTML//EN" => 1, |
| 1901 |
|
"-//O'REILLY AND ASSOCIATES//DTD HTML 2.0//EN" => 1, |
| 1902 |
|
"-//O'REILLY AND ASSOCIATES//DTD HTML EXTENDED 1.0//EN" => 1, |
| 1903 |
|
"-//SPYGLASS//DTD HTML 2.0 EXTENDED//EN" => 1, |
| 1904 |
|
"-//SQ//DTD HTML 2.0 HOTMETAL + EXTENSIONS//EN" => 1, |
| 1905 |
|
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA HTML//EN" => 1, |
| 1906 |
|
"-//SUN MICROSYSTEMS CORP.//DTD HOTJAVA STRICT HTML//EN" => 1, |
| 1907 |
|
"-//W3C//DTD HTML 3 1995-03-24//EN" => 1, |
| 1908 |
|
"-//W3C//DTD HTML 3.2 DRAFT//EN" => 1, |
| 1909 |
|
"-//W3C//DTD HTML 3.2 FINAL//EN" => 1, |
| 1910 |
|
"-//W3C//DTD HTML 3.2//EN" => 1, |
| 1911 |
|
"-//W3C//DTD HTML 3.2S DRAFT//EN" => 1, |
| 1912 |
|
"-//W3C//DTD HTML 4.0 FRAMESET//EN" => 1, |
| 1913 |
|
"-//W3C//DTD HTML 4.0 TRANSITIONAL//EN" => 1, |
| 1914 |
|
"-//W3C//DTD HTML EXPERIMETNAL 19960712//EN" => 1, |
| 1915 |
|
"-//W3C//DTD HTML EXPERIMENTAL 970421//EN" => 1, |
| 1916 |
|
"-//W3C//DTD W3 HTML//EN" => 1, |
| 1917 |
|
"-//W3O//DTD W3 HTML 3.0//EN" => 1, |
| 1918 |
|
"-//W3O//DTD W3 HTML 3.0//EN//" => 1, |
| 1919 |
|
"-//W3O//DTD W3 HTML STRICT 3.0//EN//" => 1, |
| 1920 |
|
"-//WEBTECHS//DTD MOZILLA HTML 2.0//EN" => 1, |
| 1921 |
|
"-//WEBTECHS//DTD MOZILLA HTML//EN" => 1, |
| 1922 |
|
"-/W3C/DTD HTML 4.0 TRANSITIONAL/EN" => 1, |
| 1923 |
|
"HTML" => 1, |
| 1924 |
|
}->{$pubid}) { |
| 1925 |
|
$self->{document}->manakai_compat_mode ('quirks'); |
| 1926 |
|
} elsif ($pubid eq "-//W3C//DTD HTML 4.01 FRAMESET//EN" or |
| 1927 |
|
$pubid eq "-//W3C//DTD HTML 4.01 TRANSITIONAL//EN") { |
| 1928 |
|
if (defined $token->{system_identifier}) { |
| 1929 |
|
$self->{document}->manakai_compat_mode ('quirks'); |
| 1930 |
|
} else { |
| 1931 |
|
$self->{document}->manakai_compat_mode ('limited quirks'); |
| 1932 |
} |
} |
| 1933 |
|
} elsif ($pubid eq "-//W3C//DTD XHTML 1.0 Frameset//EN" or |
| 1934 |
|
$pubid eq "-//W3C//DTD XHTML 1.0 Transitional//EN") { |
| 1935 |
|
$self->{document}->manakai_compat_mode ('limited quirks'); |
| 1936 |
|
} |
| 1937 |
|
} |
| 1938 |
|
if (defined $token->{system_identifier}) { |
| 1939 |
|
my $sysid = $token->{system_identifier}; |
| 1940 |
|
$sysid =~ tr/A-Z/a-z/; |
| 1941 |
|
if ($sysid eq "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd") { |
| 1942 |
|
$self->{document}->manakai_compat_mode ('quirks'); |
| 1943 |
} |
} |
|
## ISSUE: Spec currently left this case undefined. |
|
|
!!!parse-error (type => 'missing DOCTYPE'); |
|
|
#$phase = 'root element'; |
|
|
## reprocess |
|
|
#redo B; |
|
|
return; |
|
|
} else { |
|
|
die "$0: $token->{type}: Unknown token"; |
|
| 1944 |
} |
} |
| 1945 |
} # B |
|
| 1946 |
|
## Go to the root element phase. |
| 1947 |
|
!!!next-token; |
| 1948 |
|
return; |
| 1949 |
|
} elsif ({ |
| 1950 |
|
'start tag' => 1, |
| 1951 |
|
'end tag' => 1, |
| 1952 |
|
'end-of-file' => 1, |
| 1953 |
|
}->{$token->{type}}) { |
| 1954 |
|
!!!parse-error (type => 'no DOCTYPE'); |
| 1955 |
|
$self->{document}->manakai_compat_mode ('quirks'); |
| 1956 |
|
## Go to the root element phase |
| 1957 |
|
## reprocess |
| 1958 |
|
return; |
| 1959 |
|
} elsif ($token->{type} eq 'character') { |
| 1960 |
|
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
| 1961 |
|
## Ignore the token |
| 1962 |
|
|
| 1963 |
|
unless (length $token->{data}) { |
| 1964 |
|
## Stay in the phase |
| 1965 |
|
!!!next-token; |
| 1966 |
|
redo INITIAL; |
| 1967 |
|
} |
| 1968 |
|
} |
| 1969 |
|
|
| 1970 |
|
!!!parse-error (type => 'no DOCTYPE'); |
| 1971 |
|
$self->{document}->manakai_compat_mode ('quirks'); |
| 1972 |
|
## Go to the root element phase |
| 1973 |
|
## reprocess |
| 1974 |
|
return; |
| 1975 |
|
} elsif ($token->{type} eq 'comment') { |
| 1976 |
|
my $comment = $self->{document}->create_comment ($token->{data}); |
| 1977 |
|
$self->{document}->append_child ($comment); |
| 1978 |
|
|
| 1979 |
|
## Stay in the phase. |
| 1980 |
|
!!!next-token; |
| 1981 |
|
redo INITIAL; |
| 1982 |
|
} else { |
| 1983 |
|
die "$0: $token->{type}: Unknown token"; |
| 1984 |
|
} |
| 1985 |
|
} # INITIAL |
| 1986 |
} # _tree_construction_initial |
} # _tree_construction_initial |
| 1987 |
|
|
| 1988 |
sub _tree_construction_root_element ($) { |
sub _tree_construction_root_element ($) { |
| 2002 |
!!!next-token; |
!!!next-token; |
| 2003 |
redo B; |
redo B; |
| 2004 |
} elsif ($token->{type} eq 'character') { |
} elsif ($token->{type} eq 'character') { |
| 2005 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { # \x0D |
| 2006 |
$self->{document}->manakai_append_text ($1); |
## Ignore the token. |
| 2007 |
## ISSUE: DOM3 Core does not allow Document > Text |
|
| 2008 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 2009 |
## Stay in the phase |
## Stay in the phase |
| 2010 |
!!!next-token; |
!!!next-token; |
| 2025 |
my $root_element; !!!create-element ($root_element, 'html'); |
my $root_element; !!!create-element ($root_element, 'html'); |
| 2026 |
$self->{document}->append_child ($root_element); |
$self->{document}->append_child ($root_element); |
| 2027 |
push @{$self->{open_elements}}, [$root_element, 'html']; |
push @{$self->{open_elements}}, [$root_element, 'html']; |
|
#$phase = 'main'; |
|
| 2028 |
## reprocess |
## reprocess |
| 2029 |
#redo B; |
#redo B; |
| 2030 |
return; |
return; ## Go to the main phase. |
| 2031 |
} # B |
} # B |
| 2032 |
} # _tree_construction_root_element |
} # _tree_construction_root_element |
| 2033 |
|
|
| 2043 |
|
|
| 2044 |
## Step 3 |
## Step 3 |
| 2045 |
S3: { |
S3: { |
| 2046 |
$last = 1 if $self->{open_elements}->[0]->[0] eq $node->[0]; |
## ISSUE: Oops! "If node is the first node in the stack of open |
| 2047 |
if (defined $self->{inner_html_node}) { |
## elements, then set last to true. If the context element of the |
| 2048 |
if ($self->{inner_html_node}->[1] eq 'td' or |
## HTML fragment parsing algorithm is neither a td element nor a |
| 2049 |
$self->{inner_html_node}->[1] eq 'th') { |
## th element, then set node to the context element. (fragment case)": |
| 2050 |
# |
## The second "if" is in the scope of the first "if"!? |
| 2051 |
} else { |
if ($self->{open_elements}->[0]->[0] eq $node->[0]) { |
| 2052 |
$node = $self->{inner_html_node}; |
$last = 1; |
| 2053 |
|
if (defined $self->{inner_html_node}) { |
| 2054 |
|
if ($self->{inner_html_node}->[1] eq 'td' or |
| 2055 |
|
$self->{inner_html_node}->[1] eq 'th') { |
| 2056 |
|
# |
| 2057 |
|
} else { |
| 2058 |
|
$node = $self->{inner_html_node}; |
| 2059 |
|
} |
| 2060 |
} |
} |
| 2061 |
} |
} |
| 2062 |
|
|
| 2103 |
sub _tree_construction_main ($) { |
sub _tree_construction_main ($) { |
| 2104 |
my $self = shift; |
my $self = shift; |
| 2105 |
|
|
| 2106 |
my $phase = 'main'; |
my $previous_insertion_mode; |
| 2107 |
|
|
| 2108 |
my $active_formatting_elements = []; |
my $active_formatting_elements = []; |
| 2109 |
|
|
| 2187 |
} |
} |
| 2188 |
}; # $clear_up_to_marker |
}; # $clear_up_to_marker |
| 2189 |
|
|
| 2190 |
my $style_start_tag = sub { |
my $parse_rcdata = sub ($$) { |
| 2191 |
my $style_el; !!!create-element ($style_el, 'style', $token->{attributes}); |
my ($content_model_flag, $insert) = @_; |
| 2192 |
## $self->{insertion_mode} eq 'in head' and ... (always true) |
|
| 2193 |
(($self->{insertion_mode} eq 'in head' and defined $self->{head_element}) |
## Step 1 |
| 2194 |
? $self->{head_element} : $self->{open_elements}->[-1]->[0]) |
my $start_tag_name = $token->{tag_name}; |
| 2195 |
->append_child ($style_el); |
my $el; |
| 2196 |
$self->{content_model_flag} = 'CDATA'; |
!!!create-element ($el, $start_tag_name, $token->{attributes}); |
| 2197 |
|
|
| 2198 |
|
## Step 2 |
| 2199 |
|
$insert->($el); # /context node/->append_child ($el) |
| 2200 |
|
|
| 2201 |
|
## Step 3 |
| 2202 |
|
$self->{content_model} = $content_model_flag; # CDATA or RCDATA |
| 2203 |
delete $self->{escape}; # MUST |
delete $self->{escape}; # MUST |
| 2204 |
|
|
| 2205 |
|
## Step 4 |
| 2206 |
my $text = ''; |
my $text = ''; |
| 2207 |
!!!next-token; |
!!!next-token; |
| 2208 |
while ($token->{type} eq 'character') { |
while ($token->{type} eq 'character') { # or until stop tokenizing |
| 2209 |
$text .= $token->{data}; |
$text .= $token->{data}; |
| 2210 |
!!!next-token; |
!!!next-token; |
| 2211 |
} # stop if non-character token or tokenizer stops tokenising |
} |
| 2212 |
|
|
| 2213 |
|
## Step 5 |
| 2214 |
if (length $text) { |
if (length $text) { |
| 2215 |
$style_el->manakai_append_text ($text); |
my $text = $self->{document}->create_text_node ($text); |
| 2216 |
|
$el->append_child ($text); |
| 2217 |
} |
} |
| 2218 |
|
|
| 2219 |
$self->{content_model_flag} = 'PCDATA'; |
## Step 6 |
| 2220 |
|
$self->{content_model} = PCDATA_CONTENT_MODEL; |
| 2221 |
if ($token->{type} eq 'end tag' and $token->{tag_name} eq 'style') { |
|
| 2222 |
|
## Step 7 |
| 2223 |
|
if ($token->{type} eq 'end tag' and $token->{tag_name} eq $start_tag_name) { |
| 2224 |
## Ignore the token |
## Ignore the token |
| 2225 |
} else { |
} elsif ($content_model_flag == CDATA_CONTENT_MODEL) { |
| 2226 |
!!!parse-error (type => 'in CDATA:#'.$token->{type}); |
!!!parse-error (type => 'in CDATA:#'.$token->{type}); |
| 2227 |
## ISSUE: And ignore? |
} elsif ($content_model_flag == RCDATA_CONTENT_MODEL) { |
| 2228 |
|
!!!parse-error (type => 'in RCDATA:#'.$token->{type}); |
| 2229 |
|
} else { |
| 2230 |
|
die "$0: $content_model_flag in parse_rcdata"; |
| 2231 |
} |
} |
| 2232 |
!!!next-token; |
!!!next-token; |
| 2233 |
}; # $style_start_tag |
}; # $parse_rcdata |
| 2234 |
|
|
| 2235 |
my $script_start_tag = sub { |
my $script_start_tag = sub ($) { |
| 2236 |
|
my $insert = $_[0]; |
| 2237 |
my $script_el; |
my $script_el; |
| 2238 |
!!!create-element ($script_el, 'script', $token->{attributes}); |
!!!create-element ($script_el, 'script', $token->{attributes}); |
| 2239 |
## TODO: mark as "parser-inserted" |
## TODO: mark as "parser-inserted" |
| 2240 |
|
|
| 2241 |
$self->{content_model_flag} = 'CDATA'; |
$self->{content_model} = CDATA_CONTENT_MODEL; |
| 2242 |
delete $self->{escape}; # MUST |
delete $self->{escape}; # MUST |
| 2243 |
|
|
| 2244 |
my $text = ''; |
my $text = ''; |
| 2251 |
$script_el->manakai_append_text ($text); |
$script_el->manakai_append_text ($text); |
| 2252 |
} |
} |
| 2253 |
|
|
| 2254 |
$self->{content_model_flag} = 'PCDATA'; |
$self->{content_model} = PCDATA_CONTENT_MODEL; |
| 2255 |
|
|
| 2256 |
if ($token->{type} eq 'end tag' and |
if ($token->{type} eq 'end tag' and |
| 2257 |
$token->{tag_name} eq 'script') { |
$token->{tag_name} eq 'script') { |
| 2267 |
} else { |
} else { |
| 2268 |
## TODO: $old_insertion_point = current insertion point |
## TODO: $old_insertion_point = current insertion point |
| 2269 |
## TODO: insertion point = just before the next input character |
## TODO: insertion point = just before the next input character |
| 2270 |
|
|
| 2271 |
(($self->{insertion_mode} eq 'in head' and defined $self->{head_element}) |
$insert->($script_el); |
|
? $self->{head_element} : $self->{open_elements}->[-1]->[0])->append_child ($script_el); |
|
| 2272 |
|
|
| 2273 |
## TODO: insertion point = $old_insertion_point (might be "undefined") |
## TODO: insertion point = $old_insertion_point (might be "undefined") |
| 2274 |
|
|
| 2462 |
}; # $formatting_end_tag |
}; # $formatting_end_tag |
| 2463 |
|
|
| 2464 |
my $insert_to_current = sub { |
my $insert_to_current = sub { |
| 2465 |
$self->{open_elements}->[-1]->[0]->append_child (shift); |
$self->{open_elements}->[-1]->[0]->append_child ($_[0]); |
| 2466 |
}; # $insert_to_current |
}; # $insert_to_current |
| 2467 |
|
|
| 2468 |
my $insert_to_foster = sub { |
my $insert_to_foster = sub { |
| 2500 |
my $insert = shift; |
my $insert = shift; |
| 2501 |
if ($token->{type} eq 'start tag') { |
if ($token->{type} eq 'start tag') { |
| 2502 |
if ($token->{tag_name} eq 'script') { |
if ($token->{tag_name} eq 'script') { |
| 2503 |
$script_start_tag->(); |
## NOTE: This is an "as if in head" code clone |
| 2504 |
|
$script_start_tag->($insert); |
| 2505 |
return; |
return; |
| 2506 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($token->{tag_name} eq 'style') { |
| 2507 |
$style_start_tag->(); |
## NOTE: This is an "as if in head" code clone |
| 2508 |
|
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert); |
| 2509 |
return; |
return; |
| 2510 |
} elsif ({ |
} elsif ({ |
| 2511 |
base => 1, link => 1, meta => 1, |
base => 1, link => 1, |
| 2512 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 2513 |
!!!parse-error (type => 'in body:'.$token->{tag_name}); |
## NOTE: This is an "as if in head" code clone, only "-t" differs |
| 2514 |
## NOTE: This is an "as if in head" code clone |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 2515 |
my $el; |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 2516 |
!!!create-element ($el, $token->{tag_name}, $token->{attributes}); |
!!!next-token; |
| 2517 |
if (defined $self->{head_element}) { |
return; |
| 2518 |
$self->{head_element}->append_child ($el); |
} elsif ($token->{tag_name} eq 'meta') { |
| 2519 |
} else { |
## NOTE: This is an "as if in head" code clone, only "-t" differs |
| 2520 |
$insert->($el); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 2521 |
|
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 2522 |
|
|
| 2523 |
|
unless ($self->{confident}) { |
| 2524 |
|
my $charset; |
| 2525 |
|
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
| 2526 |
|
$charset = $token->{attributes}->{charset}->{value}; |
| 2527 |
|
} |
| 2528 |
|
if ($token->{attributes}->{'http-equiv'}) { |
| 2529 |
|
## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition. |
| 2530 |
|
if ($token->{attributes}->{'http-equiv'}->{value} |
| 2531 |
|
=~ /\A[^;]*;[\x09-\x0D\x20]*charset[\x09-\x0D\x20]*= |
| 2532 |
|
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
| 2533 |
|
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
| 2534 |
|
$charset = defined $1 ? $1 : defined $2 ? $2 : $3; |
| 2535 |
|
} ## TODO: And if supported |
| 2536 |
|
} |
| 2537 |
|
## TODO: Change the encoding |
| 2538 |
} |
} |
| 2539 |
|
|
| 2540 |
!!!next-token; |
!!!next-token; |
| 2541 |
return; |
return; |
| 2542 |
} elsif ($token->{tag_name} eq 'title') { |
} elsif ($token->{tag_name} eq 'title') { |
| 2543 |
!!!parse-error (type => 'in body:title'); |
!!!parse-error (type => 'in body:title'); |
| 2544 |
## NOTE: There is an "as if in head" code clone |
## NOTE: This is an "as if in head" code clone |
| 2545 |
my $title_el; |
$parse_rcdata->(RCDATA_CONTENT_MODEL, sub { |
| 2546 |
!!!create-element ($title_el, 'title', $token->{attributes}); |
if (defined $self->{head_element}) { |
| 2547 |
(defined $self->{head_element} ? $self->{head_element} : $self->{open_elements}->[-1]->[0]) |
$self->{head_element}->append_child ($_[0]); |
| 2548 |
->append_child ($title_el); |
} else { |
| 2549 |
$self->{content_model_flag} = 'RCDATA'; |
$insert->($_[0]); |
| 2550 |
delete $self->{escape}; # MUST |
} |
| 2551 |
|
}); |
|
my $text = ''; |
|
|
!!!next-token; |
|
|
while ($token->{type} eq 'character') { |
|
|
$text .= $token->{data}; |
|
|
!!!next-token; |
|
|
} |
|
|
if (length $text) { |
|
|
$title_el->manakai_append_text ($text); |
|
|
} |
|
|
|
|
|
$self->{content_model_flag} = 'PCDATA'; |
|
|
|
|
|
if ($token->{type} eq 'end tag' and |
|
|
$token->{tag_name} eq 'title') { |
|
|
## Ignore the token |
|
|
} else { |
|
|
!!!parse-error (type => 'in RCDATA:#'.$token->{type}); |
|
|
## ISSUE: And ignore? |
|
|
} |
|
|
!!!next-token; |
|
| 2552 |
return; |
return; |
| 2553 |
} elsif ($token->{tag_name} eq 'body') { |
} elsif ($token->{tag_name} eq 'body') { |
| 2554 |
!!!parse-error (type => 'in body:body'); |
!!!parse-error (type => 'in body:body'); |
| 2651 |
if ($i != -1) { |
if ($i != -1) { |
| 2652 |
!!!parse-error (type => 'end tag missing:'. |
!!!parse-error (type => 'end tag missing:'. |
| 2653 |
$self->{open_elements}->[-1]->[1]); |
$self->{open_elements}->[-1]->[1]); |
|
## TODO: test |
|
| 2654 |
} |
} |
| 2655 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 2656 |
last LI; |
last LI; |
| 2698 |
if ($i != -1) { |
if ($i != -1) { |
| 2699 |
!!!parse-error (type => 'end tag missing:'. |
!!!parse-error (type => 'end tag missing:'. |
| 2700 |
$self->{open_elements}->[-1]->[1]); |
$self->{open_elements}->[-1]->[1]); |
|
## TODO: test |
|
| 2701 |
} |
} |
| 2702 |
splice @{$self->{open_elements}}, $i; |
splice @{$self->{open_elements}}, $i; |
| 2703 |
last LI; |
last LI; |
| 2738 |
|
|
| 2739 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 2740 |
|
|
| 2741 |
$self->{content_model_flag} = 'PLAINTEXT'; |
$self->{content_model} = PLAINTEXT_CONTENT_MODEL; |
| 2742 |
|
|
| 2743 |
!!!next-token; |
!!!next-token; |
| 2744 |
return; |
return; |
| 2760 |
} |
} |
| 2761 |
} # INSCOPE |
} # INSCOPE |
| 2762 |
|
|
| 2763 |
|
## NOTE: See <http://html5.org/tools/web-apps-tracker?from=925&to=926> |
| 2764 |
## has an element in scope |
## has an element in scope |
| 2765 |
my $i; |
#my $i; |
| 2766 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
#INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 2767 |
my $node = $self->{open_elements}->[$_]; |
# my $node = $self->{open_elements}->[$_]; |
| 2768 |
if ({ |
# if ({ |
| 2769 |
h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
# h1 => 1, h2 => 1, h3 => 1, h4 => 1, h5 => 1, h6 => 1, |
| 2770 |
}->{$node->[1]}) { |
# }->{$node->[1]}) { |
| 2771 |
$i = $_; |
# $i = $_; |
| 2772 |
last INSCOPE; |
# last INSCOPE; |
| 2773 |
} elsif ({ |
# } elsif ({ |
| 2774 |
table => 1, caption => 1, td => 1, th => 1, |
# table => 1, caption => 1, td => 1, th => 1, |
| 2775 |
button => 1, marquee => 1, object => 1, html => 1, |
# button => 1, marquee => 1, object => 1, html => 1, |
| 2776 |
}->{$node->[1]}) { |
# }->{$node->[1]}) { |
| 2777 |
last INSCOPE; |
# last INSCOPE; |
| 2778 |
} |
# } |
| 2779 |
} # INSCOPE |
#} # INSCOPE |
| 2780 |
|
# |
| 2781 |
if (defined $i) { |
#if (defined $i) { |
| 2782 |
!!!parse-error (type => 'in hn:hn'); |
# !!! parse-error (type => 'in hn:hn'); |
| 2783 |
splice @{$self->{open_elements}}, $i; |
# splice @{$self->{open_elements}}, $i; |
| 2784 |
} |
#} |
| 2785 |
|
|
| 2786 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 2787 |
|
|
| 2824 |
return; |
return; |
| 2825 |
} elsif ({ |
} elsif ({ |
| 2826 |
b => 1, big => 1, em => 1, font => 1, i => 1, |
b => 1, big => 1, em => 1, font => 1, i => 1, |
| 2827 |
nobr => 1, s => 1, small => 1, strile => 1, |
s => 1, small => 1, strile => 1, |
| 2828 |
strong => 1, tt => 1, u => 1, |
strong => 1, tt => 1, u => 1, |
| 2829 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 2830 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 2834 |
|
|
| 2835 |
!!!next-token; |
!!!next-token; |
| 2836 |
return; |
return; |
| 2837 |
|
} elsif ($token->{tag_name} eq 'nobr') { |
| 2838 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 2839 |
|
|
| 2840 |
|
## has a |nobr| element in scope |
| 2841 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 2842 |
|
my $node = $self->{open_elements}->[$_]; |
| 2843 |
|
if ($node->[1] eq 'nobr') { |
| 2844 |
|
!!!parse-error (type => 'not closed:nobr'); |
| 2845 |
|
!!!back-token; |
| 2846 |
|
$token = {type => 'end tag', tag_name => 'nobr'}; |
| 2847 |
|
return; |
| 2848 |
|
} elsif ({ |
| 2849 |
|
table => 1, caption => 1, td => 1, th => 1, |
| 2850 |
|
button => 1, marquee => 1, object => 1, html => 1, |
| 2851 |
|
}->{$node->[1]}) { |
| 2852 |
|
last INSCOPE; |
| 2853 |
|
} |
| 2854 |
|
} # INSCOPE |
| 2855 |
|
|
| 2856 |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 2857 |
|
push @$active_formatting_elements, $self->{open_elements}->[-1]; |
| 2858 |
|
|
| 2859 |
|
!!!next-token; |
| 2860 |
|
return; |
| 2861 |
} elsif ($token->{tag_name} eq 'button') { |
} elsif ($token->{tag_name} eq 'button') { |
| 2862 |
## has a button element in scope |
## has a button element in scope |
| 2863 |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 2893 |
return; |
return; |
| 2894 |
} elsif ($token->{tag_name} eq 'xmp') { |
} elsif ($token->{tag_name} eq 'xmp') { |
| 2895 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 2896 |
|
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert); |
|
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
|
|
|
|
|
$self->{content_model_flag} = 'CDATA'; |
|
|
delete $self->{escape}; # MUST |
|
|
|
|
|
!!!next-token; |
|
| 2897 |
return; |
return; |
| 2898 |
} elsif ($token->{tag_name} eq 'table') { |
} elsif ($token->{tag_name} eq 'table') { |
| 2899 |
## has a p element in scope |
## has a p element in scope |
| 2925 |
!!!parse-error (type => 'image'); |
!!!parse-error (type => 'image'); |
| 2926 |
$token->{tag_name} = 'img'; |
$token->{tag_name} = 'img'; |
| 2927 |
} |
} |
| 2928 |
|
|
| 2929 |
|
## NOTE: There is an "as if <br>" code clone. |
| 2930 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 2931 |
|
|
| 2932 |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
!!!insert-element-t ($token->{tag_name}, $token->{attributes}); |
| 2972 |
return; |
return; |
| 2973 |
} else { |
} else { |
| 2974 |
my $at = $token->{attributes}; |
my $at = $token->{attributes}; |
| 2975 |
|
my $form_attrs; |
| 2976 |
|
$form_attrs->{action} = $at->{action} if $at->{action}; |
| 2977 |
|
my $prompt_attr = $at->{prompt}; |
| 2978 |
$at->{name} = {name => 'name', value => 'isindex'}; |
$at->{name} = {name => 'name', value => 'isindex'}; |
| 2979 |
|
delete $at->{action}; |
| 2980 |
|
delete $at->{prompt}; |
| 2981 |
my @tokens = ( |
my @tokens = ( |
| 2982 |
{type => 'start tag', tag_name => 'form'}, |
{type => 'start tag', tag_name => 'form', |
| 2983 |
|
attributes => $form_attrs}, |
| 2984 |
{type => 'start tag', tag_name => 'hr'}, |
{type => 'start tag', tag_name => 'hr'}, |
| 2985 |
{type => 'start tag', tag_name => 'p'}, |
{type => 'start tag', tag_name => 'p'}, |
| 2986 |
{type => 'start tag', tag_name => 'label'}, |
{type => 'start tag', tag_name => 'label'}, |
| 2987 |
{type => 'character', |
); |
| 2988 |
data => 'This is a searchable index. Insert your search keywords here: '}, # SHOULD |
if ($prompt_attr) { |
| 2989 |
## TODO: make this configurable |
push @tokens, {type => 'character', data => $prompt_attr->{value}}; |
| 2990 |
|
} else { |
| 2991 |
|
push @tokens, {type => 'character', |
| 2992 |
|
data => 'This is a searchable index. Insert your search keywords here: '}; # SHOULD |
| 2993 |
|
## TODO: make this configurable |
| 2994 |
|
} |
| 2995 |
|
push @tokens, |
| 2996 |
{type => 'start tag', tag_name => 'input', attributes => $at}, |
{type => 'start tag', tag_name => 'input', attributes => $at}, |
| 2997 |
#{type => 'character', data => ''}, # SHOULD |
#{type => 'character', data => ''}, # SHOULD |
| 2998 |
{type => 'end tag', tag_name => 'label'}, |
{type => 'end tag', tag_name => 'label'}, |
| 2999 |
{type => 'end tag', tag_name => 'p'}, |
{type => 'end tag', tag_name => 'p'}, |
| 3000 |
{type => 'start tag', tag_name => 'hr'}, |
{type => 'start tag', tag_name => 'hr'}, |
| 3001 |
{type => 'end tag', tag_name => 'form'}, |
{type => 'end tag', tag_name => 'form'}; |
|
); |
|
| 3002 |
$token = shift @tokens; |
$token = shift @tokens; |
| 3003 |
!!!back-token (@tokens); |
!!!back-token (@tokens); |
| 3004 |
return; |
return; |
| 3005 |
} |
} |
| 3006 |
} elsif ({ |
} elsif ($token->{tag_name} eq 'textarea') { |
|
textarea => 1, |
|
|
iframe => 1, |
|
|
noembed => 1, |
|
|
noframes => 1, |
|
|
noscript => 0, ## TODO: 1 if scripting is enabled |
|
|
}->{$token->{tag_name}}) { |
|
| 3007 |
my $tag_name = $token->{tag_name}; |
my $tag_name = $token->{tag_name}; |
| 3008 |
my $el; |
my $el; |
| 3009 |
!!!create-element ($el, $token->{tag_name}, $token->{attributes}); |
!!!create-element ($el, $token->{tag_name}, $token->{attributes}); |
| 3010 |
|
|
| 3011 |
if ($token->{tag_name} eq 'textarea') { |
## TODO: $self->{form_element} if defined |
| 3012 |
## TODO: $self->{form_element} if defined |
$self->{content_model} = RCDATA_CONTENT_MODEL; |
|
$self->{content_model_flag} = 'RCDATA'; |
|
|
} else { |
|
|
$self->{content_model_flag} = 'CDATA'; |
|
|
} |
|
| 3013 |
delete $self->{escape}; # MUST |
delete $self->{escape}; # MUST |
| 3014 |
|
|
| 3015 |
$insert->($el); |
$insert->($el); |
| 3016 |
|
|
| 3017 |
my $text = ''; |
my $text = ''; |
| 3018 |
if ($token->{tag_name} eq 'textarea') { |
!!!next-token; |
| 3019 |
!!!next-token; |
if ($token->{type} eq 'character') { |
| 3020 |
if ($token->{type} eq 'character') { |
$token->{data} =~ s/^\x0A//; |
| 3021 |
$token->{data} =~ s/^\x0A//; |
unless (length $token->{data}) { |
| 3022 |
unless (length $token->{data}) { |
!!!next-token; |
|
!!!next-token; |
|
|
} |
|
| 3023 |
} |
} |
|
} else { |
|
|
!!!next-token; |
|
| 3024 |
} |
} |
| 3025 |
while ($token->{type} eq 'character') { |
while ($token->{type} eq 'character') { |
| 3026 |
$text .= $token->{data}; |
$text .= $token->{data}; |
| 3030 |
$el->manakai_append_text ($text); |
$el->manakai_append_text ($text); |
| 3031 |
} |
} |
| 3032 |
|
|
| 3033 |
$self->{content_model_flag} = 'PCDATA'; |
$self->{content_model} = PCDATA_CONTENT_MODEL; |
| 3034 |
|
|
| 3035 |
if ($token->{type} eq 'end tag' and |
if ($token->{type} eq 'end tag' and |
| 3036 |
$token->{tag_name} eq $tag_name) { |
$token->{tag_name} eq $tag_name) { |
| 3037 |
## Ignore the token |
## Ignore the token |
| 3038 |
} else { |
} else { |
| 3039 |
if ($token->{tag_name} eq 'textarea') { |
!!!parse-error (type => 'in RCDATA:#'.$token->{type}); |
|
!!!parse-error (type => 'in RCDATA:#'.$token->{type}); |
|
|
} else { |
|
|
!!!parse-error (type => 'in CDATA:#'.$token->{type}); |
|
|
} |
|
|
## ISSUE: And ignore? |
|
| 3040 |
} |
} |
| 3041 |
!!!next-token; |
!!!next-token; |
| 3042 |
return; |
return; |
| 3043 |
|
} elsif ({ |
| 3044 |
|
iframe => 1, |
| 3045 |
|
noembed => 1, |
| 3046 |
|
noframes => 1, |
| 3047 |
|
noscript => 0, ## TODO: 1 if scripting is enabled |
| 3048 |
|
}->{$token->{tag_name}}) { |
| 3049 |
|
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert); |
| 3050 |
|
return; |
| 3051 |
} elsif ($token->{tag_name} eq 'select') { |
} elsif ($token->{tag_name} eq 'select') { |
| 3052 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 3053 |
|
|
| 3078 |
} |
} |
| 3079 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} eq 'end tag') { |
| 3080 |
if ($token->{tag_name} eq 'body') { |
if ($token->{tag_name} eq 'body') { |
| 3081 |
if (@{$self->{open_elements}} > 1 and $self->{open_elements}->[1]->[1] eq 'body') { |
if (@{$self->{open_elements}} > 1 and |
| 3082 |
## ISSUE: There is an issue in the spec. |
$self->{open_elements}->[1]->[1] eq 'body') { |
| 3083 |
if ($self->{open_elements}->[-1]->[1] ne 'body') { |
for (@{$self->{open_elements}}) { |
| 3084 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
unless ({ |
| 3085 |
|
dd => 1, dt => 1, li => 1, p => 1, td => 1, |
| 3086 |
|
th => 1, tr => 1, body => 1, html => 1, |
| 3087 |
|
tbody => 1, tfoot => 1, thead => 1, |
| 3088 |
|
}->{$_->[1]}) { |
| 3089 |
|
!!!parse-error (type => 'not closed:'.$_->[1]); |
| 3090 |
|
} |
| 3091 |
} |
} |
| 3092 |
|
|
| 3093 |
$self->{insertion_mode} = 'after body'; |
$self->{insertion_mode} = 'after body'; |
| 3094 |
!!!next-token; |
!!!next-token; |
| 3095 |
return; |
return; |
| 3134 |
li => ($token->{tag_name} ne 'li'), |
li => ($token->{tag_name} ne 'li'), |
| 3135 |
p => ($token->{tag_name} ne 'p'), |
p => ($token->{tag_name} ne 'p'), |
| 3136 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3137 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3138 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3139 |
!!!back-token; |
!!!back-token; |
| 3140 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 3152 |
} # INSCOPE |
} # INSCOPE |
| 3153 |
|
|
| 3154 |
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
if ($self->{open_elements}->[-1]->[1] ne $token->{tag_name}) { |
| 3155 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
if (defined $i) { |
| 3156 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3157 |
|
} else { |
| 3158 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3159 |
|
} |
| 3160 |
} |
} |
| 3161 |
|
|
| 3162 |
splice @{$self->{open_elements}}, $i if defined $i; |
if (defined $i) { |
| 3163 |
|
splice @{$self->{open_elements}}, $i; |
| 3164 |
|
} elsif ($token->{tag_name} eq 'p') { |
| 3165 |
|
## As if <p>, then reprocess the current token |
| 3166 |
|
my $el; |
| 3167 |
|
!!!create-element ($el, 'p'); |
| 3168 |
|
$insert->($el); |
| 3169 |
|
} |
| 3170 |
$clear_up_to_marker->() |
$clear_up_to_marker->() |
| 3171 |
if { |
if { |
| 3172 |
button => 1, marquee => 1, object => 1, |
button => 1, marquee => 1, object => 1, |
| 3182 |
if ({ |
if ({ |
| 3183 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3184 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3185 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3186 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3187 |
!!!back-token; |
!!!back-token; |
| 3188 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 3221 |
if ({ |
if ({ |
| 3222 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3223 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3224 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3225 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3226 |
!!!back-token; |
!!!back-token; |
| 3227 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 3252 |
strong => 1, tt => 1, u => 1, |
strong => 1, tt => 1, u => 1, |
| 3253 |
}->{$token->{tag_name}}) { |
}->{$token->{tag_name}}) { |
| 3254 |
$formatting_end_tag->($token->{tag_name}); |
$formatting_end_tag->($token->{tag_name}); |
| 3255 |
## TODO: <http://html5.org/tools/web-apps-tracker?from=883&to=884> |
return; |
| 3256 |
|
} elsif ($token->{tag_name} eq 'br') { |
| 3257 |
|
!!!parse-error (type => 'unmatched end tag:br'); |
| 3258 |
|
|
| 3259 |
|
## As if <br> |
| 3260 |
|
$reconstruct_active_formatting_elements->($insert_to_current); |
| 3261 |
|
|
| 3262 |
|
my $el; |
| 3263 |
|
!!!create-element ($el, 'br'); |
| 3264 |
|
$insert->($el); |
| 3265 |
|
|
| 3266 |
|
## Ignore the token. |
| 3267 |
|
!!!next-token; |
| 3268 |
return; |
return; |
| 3269 |
} elsif ({ |
} elsif ({ |
| 3270 |
caption => 1, col => 1, colgroup => 1, frame => 1, |
caption => 1, col => 1, colgroup => 1, frame => 1, |
| 3271 |
frameset => 1, head => 1, option => 1, optgroup => 1, |
frameset => 1, head => 1, option => 1, optgroup => 1, |
| 3272 |
tbody => 1, td => 1, tfoot => 1, th => 1, |
tbody => 1, td => 1, tfoot => 1, th => 1, |
| 3273 |
thead => 1, tr => 1, |
thead => 1, tr => 1, |
| 3274 |
area => 1, basefont => 1, bgsound => 1, br => 1, |
area => 1, basefont => 1, bgsound => 1, |
| 3275 |
embed => 1, hr => 1, iframe => 1, image => 1, |
embed => 1, hr => 1, iframe => 1, image => 1, |
| 3276 |
img => 1, input => 1, isindex => 1, noembed => 1, |
img => 1, input => 1, isindex => 1, noembed => 1, |
| 3277 |
noframes => 1, param => 1, select => 1, spacer => 1, |
noframes => 1, param => 1, select => 1, spacer => 1, |
| 3298 |
if ({ |
if ({ |
| 3299 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3300 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3301 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3302 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3303 |
!!!back-token; |
!!!back-token; |
| 3304 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 3322 |
#not $phrasing_category->{$node->[1]} and |
#not $phrasing_category->{$node->[1]} and |
| 3323 |
($special_category->{$node->[1]} or |
($special_category->{$node->[1]} or |
| 3324 |
$scoping_category->{$node->[1]})) { |
$scoping_category->{$node->[1]})) { |
| 3325 |
!!!parse-error (type => 'not closed:'.$node->[1]); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3326 |
## Ignore the token |
## Ignore the token |
| 3327 |
!!!next-token; |
!!!next-token; |
| 3328 |
last S2; |
last S2; |
| 3342 |
}; # $in_body |
}; # $in_body |
| 3343 |
|
|
| 3344 |
B: { |
B: { |
| 3345 |
if ($phase eq 'main') { |
if ($token->{type} eq 'DOCTYPE') { |
| 3346 |
if ($token->{type} eq 'DOCTYPE') { |
!!!parse-error (type => 'DOCTYPE in the middle'); |
| 3347 |
!!!parse-error (type => 'in html:#DOCTYPE'); |
## Ignore the token |
| 3348 |
## Ignore the token |
## Stay in the phase |
| 3349 |
## Stay in the phase |
!!!next-token; |
| 3350 |
!!!next-token; |
redo B; |
| 3351 |
redo B; |
} elsif ($token->{type} eq 'end-of-file') { |
| 3352 |
} elsif ($token->{type} eq 'start tag' and |
if ($token->{insertion_mode} ne 'trailing end') { |
|
$token->{tag_name} eq 'html') { |
|
|
## TODO: unless it is the first start tag token, parse-error |
|
|
my $top_el = $self->{open_elements}->[0]->[0]; |
|
|
for my $attr_name (keys %{$token->{attributes}}) { |
|
|
unless ($top_el->has_attribute_ns (undef, $attr_name)) { |
|
|
$top_el->set_attribute_ns |
|
|
(undef, [undef, $attr_name], |
|
|
$token->{attributes}->{$attr_name}->{value}); |
|
|
} |
|
|
} |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{type} eq 'end-of-file') { |
|
| 3353 |
## Generate implied end tags |
## Generate implied end tags |
| 3354 |
if ({ |
if ({ |
| 3355 |
dd => 1, dt => 1, li => 1, p => 1, td => 1, th => 1, tr => 1, |
dd => 1, dt => 1, li => 1, p => 1, td => 1, th => 1, tr => 1, |
| 3356 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3357 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3358 |
!!!back-token; |
!!!back-token; |
| 3359 |
$token = {type => 'end tag', tag_name => $self->{open_elements}->[-1]->[1]}; |
$token = {type => 'end tag', tag_name => $self->{open_elements}->[-1]->[1]}; |
| 3369 |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3370 |
} |
} |
| 3371 |
|
|
|
## Stop parsing |
|
|
last B; |
|
|
|
|
| 3372 |
## ISSUE: There is an issue in the spec. |
## ISSUE: There is an issue in the spec. |
| 3373 |
|
} |
| 3374 |
|
|
| 3375 |
|
## Stop parsing |
| 3376 |
|
last B; |
| 3377 |
|
} elsif ($token->{type} eq 'start tag' and |
| 3378 |
|
$token->{tag_name} eq 'html') { |
| 3379 |
|
if ($self->{insertion_mode} eq 'trailing end') { |
| 3380 |
|
## Turn into the main phase |
| 3381 |
|
!!!parse-error (type => 'after html:html'); |
| 3382 |
|
$self->{insertion_mode} = $previous_insertion_mode; |
| 3383 |
|
} |
| 3384 |
|
|
| 3385 |
|
## ISSUE: "aa<html>" is not a parse error. |
| 3386 |
|
## ISSUE: "<html>" in fragment is not a parse error. |
| 3387 |
|
unless ($token->{first_start_tag}) { |
| 3388 |
|
!!!parse-error (type => 'not first start tag'); |
| 3389 |
|
} |
| 3390 |
|
my $top_el = $self->{open_elements}->[0]->[0]; |
| 3391 |
|
for my $attr_name (keys %{$token->{attributes}}) { |
| 3392 |
|
unless ($top_el->has_attribute_ns (undef, $attr_name)) { |
| 3393 |
|
$top_el->set_attribute_ns |
| 3394 |
|
(undef, [undef, $attr_name], |
| 3395 |
|
$token->{attributes}->{$attr_name}->{value}); |
| 3396 |
|
} |
| 3397 |
|
} |
| 3398 |
|
!!!next-token; |
| 3399 |
|
redo B; |
| 3400 |
|
} elsif ($token->{type} eq 'comment') { |
| 3401 |
|
my $comment = $self->{document}->create_comment ($token->{data}); |
| 3402 |
|
if ($self->{insertion_mode} eq 'trailing end') { |
| 3403 |
|
$self->{document}->append_child ($comment); |
| 3404 |
|
} elsif ($self->{insertion_mode} eq 'after body') { |
| 3405 |
|
$self->{open_elements}->[0]->[0]->append_child ($comment); |
| 3406 |
} else { |
} else { |
| 3407 |
if ($self->{insertion_mode} eq 'before head') { |
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
| 3408 |
|
} |
| 3409 |
|
!!!next-token; |
| 3410 |
|
redo B; |
| 3411 |
|
} elsif ($self->{insertion_mode} eq 'before head') { |
| 3412 |
if ($token->{type} eq 'character') { |
if ($token->{type} eq 'character') { |
| 3413 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 3414 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 3424 |
$self->{insertion_mode} = 'in head'; |
$self->{insertion_mode} = 'in head'; |
| 3425 |
## reprocess |
## reprocess |
| 3426 |
redo B; |
redo B; |
|
} elsif ($token->{type} eq 'comment') { |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 3427 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 3428 |
my $attr = $token->{tag_name} eq 'head' ? $token->{attributes} : {}; |
my $attr = $token->{tag_name} eq 'head' ? $token->{attributes} : {}; |
| 3429 |
!!!create-element ($self->{head_element}, 'head', $attr); |
!!!create-element ($self->{head_element}, 'head', $attr); |
| 3442 |
} |
} |
| 3443 |
redo B; |
redo B; |
| 3444 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} eq 'end tag') { |
| 3445 |
if ($token->{tag_name} eq 'html') { |
if ({ |
| 3446 |
|
head => 1, body => 1, html => 1, |
| 3447 |
|
p => 1, br => 1, |
| 3448 |
|
}->{$token->{tag_name}}) { |
| 3449 |
## As if <head> |
## As if <head> |
| 3450 |
!!!create-element ($self->{head_element}, 'head'); |
!!!create-element ($self->{head_element}, 'head'); |
| 3451 |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
$self->{open_elements}->[-1]->[0]->append_child ($self->{head_element}); |
| 3455 |
redo B; |
redo B; |
| 3456 |
} else { |
} else { |
| 3457 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3458 |
## Ignore the token |
## Ignore the token ## ISSUE: An issue in the spec. |
| 3459 |
!!!next-token; |
!!!next-token; |
| 3460 |
redo B; |
redo B; |
| 3461 |
} |
} |
| 3462 |
} else { |
} else { |
| 3463 |
die "$0: $token->{type}: Unknown type"; |
die "$0: $token->{type}: Unknown type"; |
| 3464 |
} |
} |
| 3465 |
} elsif ($self->{insertion_mode} eq 'in head') { |
} elsif ($self->{insertion_mode} eq 'in head' or |
| 3466 |
|
$self->{insertion_mode} eq 'in head noscript' or |
| 3467 |
|
$self->{insertion_mode} eq 'after head') { |
| 3468 |
if ($token->{type} eq 'character') { |
if ($token->{type} eq 'character') { |
| 3469 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 3470 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 3475 |
} |
} |
| 3476 |
|
|
| 3477 |
# |
# |
|
} elsif ($token->{type} eq 'comment') { |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 3478 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 3479 |
if ($token->{tag_name} eq 'title') { |
if ({base => ($self->{insertion_mode} eq 'in head' or |
| 3480 |
## NOTE: There is an "as if in head" code clone |
$self->{insertion_mode} eq 'after head'), |
| 3481 |
my $title_el; |
link => 1}->{$token->{tag_name}}) { |
| 3482 |
!!!create-element ($title_el, 'title', $token->{attributes}); |
## NOTE: There is a "as if in head" code clone. |
| 3483 |
(defined $self->{head_element} ? $self->{head_element} : $self->{open_elements}->[-1]->[0]) |
if ($self->{insertion_mode} eq 'after head') { |
| 3484 |
->append_child ($title_el); |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 3485 |
$self->{content_model_flag} = 'RCDATA'; |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3486 |
delete $self->{escape}; # MUST |
} |
| 3487 |
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 3488 |
my $text = ''; |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 3489 |
|
pop @{$self->{open_elements}} |
| 3490 |
|
if $self->{insertion_mode} eq 'after head'; |
| 3491 |
!!!next-token; |
!!!next-token; |
| 3492 |
while ($token->{type} eq 'character') { |
redo B; |
| 3493 |
$text .= $token->{data}; |
} elsif ($token->{tag_name} eq 'meta') { |
| 3494 |
!!!next-token; |
## NOTE: There is a "as if in head" code clone. |
| 3495 |
|
if ($self->{insertion_mode} eq 'after head') { |
| 3496 |
|
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 3497 |
|
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3498 |
} |
} |
| 3499 |
if (length $text) { |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 3500 |
$title_el->manakai_append_text ($text); |
pop @{$self->{open_elements}}; ## ISSUE: This step is missing in the spec. |
| 3501 |
|
|
| 3502 |
|
unless ($self->{confident}) { |
| 3503 |
|
my $charset; |
| 3504 |
|
if ($token->{attributes}->{charset}) { ## TODO: And if supported |
| 3505 |
|
$charset = $token->{attributes}->{charset}->{value}; |
| 3506 |
|
} |
| 3507 |
|
if ($token->{attributes}->{'http-equiv'}) { |
| 3508 |
|
## ISSUE: Algorithm name in the spec was incorrect so that not linked to the definition. |
| 3509 |
|
if ($token->{attributes}->{'http-equiv'}->{value} |
| 3510 |
|
=~ /\A[^;]*;[\x09-\x0D\x20]*charset[\x09-\x0D\x20]*= |
| 3511 |
|
[\x09-\x0D\x20]*(?>"([^"]*)"|'([^']*)'| |
| 3512 |
|
([^"'\x09-\x0D\x20][^\x09-\x0D\x20]*))/x) { |
| 3513 |
|
$charset = defined $1 ? $1 : defined $2 ? $2 : $3; |
| 3514 |
|
} ## TODO: And if supported |
| 3515 |
|
} |
| 3516 |
|
## TODO: Change the encoding |
| 3517 |
} |
} |
| 3518 |
|
|
| 3519 |
$self->{content_model_flag} = 'PCDATA'; |
## TODO: Extracting |charset| from |meta|. |
| 3520 |
|
pop @{$self->{open_elements}} |
| 3521 |
if ($token->{type} eq 'end tag' and |
if $self->{insertion_mode} eq 'after head'; |
| 3522 |
$token->{tag_name} eq 'title') { |
!!!next-token; |
| 3523 |
|
redo B; |
| 3524 |
|
} elsif ($token->{tag_name} eq 'title' and |
| 3525 |
|
$self->{insertion_mode} eq 'in head') { |
| 3526 |
|
## NOTE: There is a "as if in head" code clone. |
| 3527 |
|
if ($self->{insertion_mode} eq 'after head') { |
| 3528 |
|
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 3529 |
|
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3530 |
|
} |
| 3531 |
|
my $parent = defined $self->{head_element} ? $self->{head_element} |
| 3532 |
|
: $self->{open_elements}->[-1]->[0]; |
| 3533 |
|
$parse_rcdata->(RCDATA_CONTENT_MODEL, |
| 3534 |
|
sub { $parent->append_child ($_[0]) }); |
| 3535 |
|
pop @{$self->{open_elements}} |
| 3536 |
|
if $self->{insertion_mode} eq 'after head'; |
| 3537 |
|
redo B; |
| 3538 |
|
} elsif ($token->{tag_name} eq 'style') { |
| 3539 |
|
## NOTE: Or (scripting is enabled and tag_name eq 'noscript' and |
| 3540 |
|
## insertion mode 'in head') |
| 3541 |
|
## NOTE: There is a "as if in head" code clone. |
| 3542 |
|
if ($self->{insertion_mode} eq 'after head') { |
| 3543 |
|
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 3544 |
|
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3545 |
|
} |
| 3546 |
|
$parse_rcdata->(CDATA_CONTENT_MODEL, $insert_to_current); |
| 3547 |
|
pop @{$self->{open_elements}} |
| 3548 |
|
if $self->{insertion_mode} eq 'after head'; |
| 3549 |
|
redo B; |
| 3550 |
|
} elsif ($token->{tag_name} eq 'noscript') { |
| 3551 |
|
if ($self->{insertion_mode} eq 'in head') { |
| 3552 |
|
## NOTE: and scripting is disalbed |
| 3553 |
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 3554 |
|
$self->{insertion_mode} = 'in head noscript'; |
| 3555 |
|
!!!next-token; |
| 3556 |
|
redo B; |
| 3557 |
|
} elsif ($self->{insertion_mode} eq 'in head noscript') { |
| 3558 |
|
!!!parse-error (type => 'in noscript:noscript'); |
| 3559 |
## Ignore the token |
## Ignore the token |
| 3560 |
|
!!!next-token; |
| 3561 |
|
redo B; |
| 3562 |
} else { |
} else { |
| 3563 |
!!!parse-error (type => 'in RCDATA:#'.$token->{type}); |
# |
|
## ISSUE: And ignore? |
|
| 3564 |
} |
} |
| 3565 |
|
} elsif ($token->{tag_name} eq 'head' and |
| 3566 |
|
$self->{insertion_mode} ne 'after head') { |
| 3567 |
|
!!!parse-error (type => 'in head:head'); # or in head noscript |
| 3568 |
|
## Ignore the token |
| 3569 |
!!!next-token; |
!!!next-token; |
| 3570 |
redo B; |
redo B; |
| 3571 |
} elsif ($token->{tag_name} eq 'style') { |
} elsif ($self->{insertion_mode} ne 'in head noscript' and |
| 3572 |
$style_start_tag->(); |
$token->{tag_name} eq 'script') { |
| 3573 |
redo B; |
if ($self->{insertion_mode} eq 'after head') { |
| 3574 |
} elsif ($token->{tag_name} eq 'script') { |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
| 3575 |
$script_start_tag->(); |
push @{$self->{open_elements}}, [$self->{head_element}, 'head']; |
| 3576 |
|
} |
| 3577 |
|
## NOTE: There is a "as if in head" code clone. |
| 3578 |
|
$script_start_tag->($insert_to_current); |
| 3579 |
|
pop @{$self->{open_elements}} |
| 3580 |
|
if $self->{insertion_mode} eq 'after head'; |
| 3581 |
redo B; |
redo B; |
| 3582 |
} elsif ({base => 1, link => 1, meta => 1}->{$token->{tag_name}}) { |
} elsif ($self->{insertion_mode} eq 'after head' and |
| 3583 |
## NOTE: There are "as if in head" code clones |
$token->{tag_name} eq 'body') { |
| 3584 |
my $el; |
!!!insert-element ('body', $token->{attributes}); |
| 3585 |
!!!create-element ($el, $token->{tag_name}, $token->{attributes}); |
$self->{insertion_mode} = 'in body'; |
|
(defined $self->{head_element} ? $self->{head_element} : $self->{open_elements}->[-1]->[0]) |
|
|
->append_child ($el); |
|
|
|
|
| 3586 |
!!!next-token; |
!!!next-token; |
| 3587 |
redo B; |
redo B; |
| 3588 |
} elsif ($token->{tag_name} eq 'head') { |
} elsif ($self->{insertion_mode} eq 'after head' and |
| 3589 |
!!!parse-error (type => 'in head:head'); |
$token->{tag_name} eq 'frameset') { |
| 3590 |
## Ignore the token |
!!!insert-element ('frameset', $token->{attributes}); |
| 3591 |
|
$self->{insertion_mode} = 'in frameset'; |
| 3592 |
!!!next-token; |
!!!next-token; |
| 3593 |
redo B; |
redo B; |
| 3594 |
} else { |
} else { |
| 3595 |
# |
# |
| 3596 |
} |
} |
| 3597 |
} elsif ($token->{type} eq 'end tag') { |
} elsif ($token->{type} eq 'end tag') { |
| 3598 |
if ($token->{tag_name} eq 'head') { |
if ($self->{insertion_mode} eq 'in head' and |
| 3599 |
if ($self->{open_elements}->[-1]->[1] eq 'head') { |
$token->{tag_name} eq 'head') { |
| 3600 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
|
} else { |
|
|
!!!parse-error (type => 'unmatched end tag:head'); |
|
|
} |
|
| 3601 |
$self->{insertion_mode} = 'after head'; |
$self->{insertion_mode} = 'after head'; |
| 3602 |
!!!next-token; |
!!!next-token; |
| 3603 |
redo B; |
redo B; |
| 3604 |
} elsif ($token->{tag_name} eq 'html') { |
} elsif ($self->{insertion_mode} eq 'in head noscript' and |
| 3605 |
|
$token->{tag_name} eq 'noscript') { |
| 3606 |
|
pop @{$self->{open_elements}}; |
| 3607 |
|
$self->{insertion_mode} = 'in head'; |
| 3608 |
|
!!!next-token; |
| 3609 |
|
redo B; |
| 3610 |
|
} elsif ($self->{insertion_mode} eq 'in head' and |
| 3611 |
|
{ |
| 3612 |
|
body => 1, html => 1, |
| 3613 |
|
p => 1, br => 1, |
| 3614 |
|
}->{$token->{tag_name}}) { |
| 3615 |
# |
# |
| 3616 |
} else { |
} elsif ($self->{insertion_mode} eq 'in head noscript' and |
| 3617 |
|
{ |
| 3618 |
|
p => 1, br => 1, |
| 3619 |
|
}->{$token->{tag_name}}) { |
| 3620 |
|
# |
| 3621 |
|
} elsif ($self->{insertion_mode} ne 'after head') { |
| 3622 |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3623 |
## Ignore the token |
## Ignore the token |
| 3624 |
!!!next-token; |
!!!next-token; |
| 3625 |
redo B; |
redo B; |
| 3626 |
|
} else { |
| 3627 |
|
# |
| 3628 |
} |
} |
| 3629 |
} else { |
} else { |
| 3630 |
# |
# |
| 3631 |
} |
} |
| 3632 |
|
|
| 3633 |
if ($self->{open_elements}->[-1]->[1] eq 'head') { |
## As if </head> or </noscript> or <body> |
| 3634 |
## As if </head> |
if ($self->{insertion_mode} eq 'in head') { |
| 3635 |
|
pop @{$self->{open_elements}}; |
| 3636 |
|
$self->{insertion_mode} = 'after head'; |
| 3637 |
|
} elsif ($self->{insertion_mode} eq 'in head noscript') { |
| 3638 |
pop @{$self->{open_elements}}; |
pop @{$self->{open_elements}}; |
| 3639 |
|
!!!parse-error (type => 'in noscript:'.(defined $token->{tag_name} ? ($token->{type} eq 'end tag' ? '/' : '') . $token->{tag_name} : '#' . $token->{type})); |
| 3640 |
|
$self->{insertion_mode} = 'in head'; |
| 3641 |
|
} else { # 'after head' |
| 3642 |
|
!!!insert-element ('body'); |
| 3643 |
|
$self->{insertion_mode} = 'in body'; |
| 3644 |
} |
} |
|
$self->{insertion_mode} = 'after head'; |
|
| 3645 |
## reprocess |
## reprocess |
| 3646 |
redo B; |
redo B; |
| 3647 |
|
|
| 3648 |
## ISSUE: An issue in the spec. |
## ISSUE: An issue in the spec. |
| 3649 |
} elsif ($self->{insertion_mode} eq 'after head') { |
} elsif ($self->{insertion_mode} eq 'in body' or |
| 3650 |
|
$self->{insertion_mode} eq 'in caption') { |
| 3651 |
if ($token->{type} eq 'character') { |
if ($token->{type} eq 'character') { |
| 3652 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
## NOTE: There is a code clone of "character in body". |
| 3653 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
$reconstruct_active_formatting_elements->($insert_to_current); |
|
unless (length $token->{data}) { |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
|
} |
|
| 3654 |
|
|
| 3655 |
# |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
| 3656 |
} elsif ($token->{type} eq 'comment') { |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
| 3657 |
!!!next-token; |
!!!next-token; |
| 3658 |
redo B; |
redo B; |
| 3659 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 3660 |
if ($token->{tag_name} eq 'body') { |
if ({ |
| 3661 |
!!!insert-element ('body', $token->{attributes}); |
caption => 1, col => 1, colgroup => 1, tbody => 1, |
| 3662 |
$self->{insertion_mode} = 'in body'; |
td => 1, tfoot => 1, th => 1, thead => 1, tr => 1, |
| 3663 |
!!!next-token; |
}->{$token->{tag_name}} and |
| 3664 |
|
$self->{insertion_mode} eq 'in caption') { |
| 3665 |
|
!!!parse-error (type => 'not closed:caption'); |
| 3666 |
|
|
| 3667 |
|
## As if </caption> |
| 3668 |
|
## have a table element in table scope |
| 3669 |
|
my $i; |
| 3670 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3671 |
|
my $node = $self->{open_elements}->[$_]; |
| 3672 |
|
if ($node->[1] eq 'caption') { |
| 3673 |
|
$i = $_; |
| 3674 |
|
last INSCOPE; |
| 3675 |
|
} elsif ({ |
| 3676 |
|
table => 1, html => 1, |
| 3677 |
|
}->{$node->[1]}) { |
| 3678 |
|
last INSCOPE; |
| 3679 |
|
} |
| 3680 |
|
} # INSCOPE |
| 3681 |
|
unless (defined $i) { |
| 3682 |
|
!!!parse-error (type => 'unmatched end tag:caption'); |
| 3683 |
|
## Ignore the token |
| 3684 |
|
!!!next-token; |
| 3685 |
|
redo B; |
| 3686 |
|
} |
| 3687 |
|
|
| 3688 |
|
## generate implied end tags |
| 3689 |
|
if ({ |
| 3690 |
|
dd => 1, dt => 1, li => 1, p => 1, |
| 3691 |
|
td => 1, th => 1, tr => 1, |
| 3692 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3693 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3694 |
|
!!!back-token; # <?> |
| 3695 |
|
$token = {type => 'end tag', tag_name => 'caption'}; |
| 3696 |
|
!!!back-token; |
| 3697 |
|
$token = {type => 'end tag', |
| 3698 |
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3699 |
|
redo B; |
| 3700 |
|
} |
| 3701 |
|
|
| 3702 |
|
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
| 3703 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3704 |
|
} |
| 3705 |
|
|
| 3706 |
|
splice @{$self->{open_elements}}, $i; |
| 3707 |
|
|
| 3708 |
|
$clear_up_to_marker->(); |
| 3709 |
|
|
| 3710 |
|
$self->{insertion_mode} = 'in table'; |
| 3711 |
|
|
| 3712 |
|
## reprocess |
| 3713 |
redo B; |
redo B; |
| 3714 |
} elsif ($token->{tag_name} eq 'frameset') { |
} else { |
| 3715 |
!!!insert-element ('frameset', $token->{attributes}); |
# |
| 3716 |
$self->{insertion_mode} = 'in frameset'; |
} |
| 3717 |
|
} elsif ($token->{type} eq 'end tag') { |
| 3718 |
|
if ($token->{tag_name} eq 'caption' and |
| 3719 |
|
$self->{insertion_mode} eq 'in caption') { |
| 3720 |
|
## have a table element in table scope |
| 3721 |
|
my $i; |
| 3722 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3723 |
|
my $node = $self->{open_elements}->[$_]; |
| 3724 |
|
if ($node->[1] eq $token->{tag_name}) { |
| 3725 |
|
$i = $_; |
| 3726 |
|
last INSCOPE; |
| 3727 |
|
} elsif ({ |
| 3728 |
|
table => 1, html => 1, |
| 3729 |
|
}->{$node->[1]}) { |
| 3730 |
|
last INSCOPE; |
| 3731 |
|
} |
| 3732 |
|
} # INSCOPE |
| 3733 |
|
unless (defined $i) { |
| 3734 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3735 |
|
## Ignore the token |
| 3736 |
|
!!!next-token; |
| 3737 |
|
redo B; |
| 3738 |
|
} |
| 3739 |
|
|
| 3740 |
|
## generate implied end tags |
| 3741 |
|
if ({ |
| 3742 |
|
dd => 1, dt => 1, li => 1, p => 1, |
| 3743 |
|
td => 1, th => 1, tr => 1, |
| 3744 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3745 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3746 |
|
!!!back-token; |
| 3747 |
|
$token = {type => 'end tag', |
| 3748 |
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3749 |
|
redo B; |
| 3750 |
|
} |
| 3751 |
|
|
| 3752 |
|
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
| 3753 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3754 |
|
} |
| 3755 |
|
|
| 3756 |
|
splice @{$self->{open_elements}}, $i; |
| 3757 |
|
|
| 3758 |
|
$clear_up_to_marker->(); |
| 3759 |
|
|
| 3760 |
|
$self->{insertion_mode} = 'in table'; |
| 3761 |
|
|
| 3762 |
!!!next-token; |
!!!next-token; |
| 3763 |
redo B; |
redo B; |
| 3764 |
} elsif ({ |
} elsif ($token->{tag_name} eq 'table' and |
| 3765 |
base => 1, link => 1, meta => 1, |
$self->{insertion_mode} eq 'in caption') { |
| 3766 |
script => 1, style => 1, title => 1, |
!!!parse-error (type => 'not closed:caption'); |
| 3767 |
}->{$token->{tag_name}}) { |
|
| 3768 |
!!!parse-error (type => 'after head:'.$token->{tag_name}); |
## As if </caption> |
| 3769 |
$self->{insertion_mode} = 'in head'; |
## have a table element in table scope |
| 3770 |
|
my $i; |
| 3771 |
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
| 3772 |
|
my $node = $self->{open_elements}->[$_]; |
| 3773 |
|
if ($node->[1] eq 'caption') { |
| 3774 |
|
$i = $_; |
| 3775 |
|
last INSCOPE; |
| 3776 |
|
} elsif ({ |
| 3777 |
|
table => 1, html => 1, |
| 3778 |
|
}->{$node->[1]}) { |
| 3779 |
|
last INSCOPE; |
| 3780 |
|
} |
| 3781 |
|
} # INSCOPE |
| 3782 |
|
unless (defined $i) { |
| 3783 |
|
!!!parse-error (type => 'unmatched end tag:caption'); |
| 3784 |
|
## Ignore the token |
| 3785 |
|
!!!next-token; |
| 3786 |
|
redo B; |
| 3787 |
|
} |
| 3788 |
|
|
| 3789 |
|
## generate implied end tags |
| 3790 |
|
if ({ |
| 3791 |
|
dd => 1, dt => 1, li => 1, p => 1, |
| 3792 |
|
td => 1, th => 1, tr => 1, |
| 3793 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3794 |
|
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3795 |
|
!!!back-token; # </table> |
| 3796 |
|
$token = {type => 'end tag', tag_name => 'caption'}; |
| 3797 |
|
!!!back-token; |
| 3798 |
|
$token = {type => 'end tag', |
| 3799 |
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
| 3800 |
|
redo B; |
| 3801 |
|
} |
| 3802 |
|
|
| 3803 |
|
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
| 3804 |
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
| 3805 |
|
} |
| 3806 |
|
|
| 3807 |
|
splice @{$self->{open_elements}}, $i; |
| 3808 |
|
|
| 3809 |
|
$clear_up_to_marker->(); |
| 3810 |
|
|
| 3811 |
|
$self->{insertion_mode} = 'in table'; |
| 3812 |
|
|
| 3813 |
## reprocess |
## reprocess |
| 3814 |
redo B; |
redo B; |
| 3815 |
|
} elsif ({ |
| 3816 |
|
body => 1, col => 1, colgroup => 1, |
| 3817 |
|
html => 1, tbody => 1, td => 1, tfoot => 1, |
| 3818 |
|
th => 1, thead => 1, tr => 1, |
| 3819 |
|
}->{$token->{tag_name}} and |
| 3820 |
|
$self->{insertion_mode} eq 'in caption') { |
| 3821 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 3822 |
|
## Ignore the token |
| 3823 |
|
!!!next-token; |
| 3824 |
|
redo B; |
| 3825 |
} else { |
} else { |
| 3826 |
# |
# |
| 3827 |
} |
} |
| 3828 |
} else { |
} else { |
| 3829 |
# |
# |
| 3830 |
} |
} |
|
|
|
|
## As if <body> |
|
|
!!!insert-element ('body'); |
|
|
$self->{insertion_mode} = 'in body'; |
|
|
## reprocess |
|
|
redo B; |
|
|
} elsif ($self->{insertion_mode} eq 'in body') { |
|
|
if ($token->{type} eq 'character') { |
|
|
## NOTE: There is a code clone of "character in body". |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
|
| 3831 |
|
|
| 3832 |
!!!next-token; |
$in_body->($insert_to_current); |
| 3833 |
redo B; |
redo B; |
|
} elsif ($token->{type} eq 'comment') { |
|
|
## NOTE: There is a code clone of "comment in body". |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} else { |
|
|
$in_body->($insert_to_current); |
|
|
redo B; |
|
|
} |
|
| 3834 |
} elsif ($self->{insertion_mode} eq 'in table') { |
} elsif ($self->{insertion_mode} eq 'in table') { |
| 3835 |
if ($token->{type} eq 'character') { |
if ($token->{type} eq 'character') { |
| 3836 |
## NOTE: There are "character in table" code clones. |
## NOTE: There are "character in table" code clones. |
| 3890 |
|
|
| 3891 |
!!!next-token; |
!!!next-token; |
| 3892 |
redo B; |
redo B; |
|
} elsif ($token->{type} eq 'comment') { |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 3893 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 3894 |
if ({ |
if ({ |
| 3895 |
caption => 1, |
caption => 1, |
| 3961 |
if ({ |
if ({ |
| 3962 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 3963 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 3964 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 3965 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 3966 |
!!!back-token; # <table> |
!!!back-token; # <table> |
| 3967 |
$token = {type => 'end tag', tag_name => 'table'}; |
$token = {type => 'end tag', tag_name => 'table'}; |
| 4010 |
if ({ |
if ({ |
| 4011 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 4012 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 4013 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 4014 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4015 |
!!!back-token; |
!!!back-token; |
| 4016 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 4047 |
!!!parse-error (type => 'in table:'.$token->{tag_name}); |
!!!parse-error (type => 'in table:'.$token->{tag_name}); |
| 4048 |
$in_body->($insert_to_foster); |
$in_body->($insert_to_foster); |
| 4049 |
redo B; |
redo B; |
|
} elsif ($self->{insertion_mode} eq 'in caption') { |
|
|
if ($token->{type} eq 'character') { |
|
|
## NOTE: This is a code clone of "character in body". |
|
|
$reconstruct_active_formatting_elements->($insert_to_current); |
|
|
|
|
|
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
|
|
|
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{type} eq 'comment') { |
|
|
## NOTE: This is a code clone of "comment in body". |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{type} eq 'start tag') { |
|
|
if ({ |
|
|
caption => 1, col => 1, colgroup => 1, tbody => 1, |
|
|
td => 1, tfoot => 1, th => 1, thead => 1, tr => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
!!!parse-error (type => 'not closed:caption'); |
|
|
|
|
|
## As if </caption> |
|
|
## have a table element in table scope |
|
|
my $i; |
|
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
my $node = $self->{open_elements}->[$_]; |
|
|
if ($node->[1] eq 'caption') { |
|
|
$i = $_; |
|
|
last INSCOPE; |
|
|
} elsif ({ |
|
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
unless (defined $i) { |
|
|
!!!parse-error (type => 'unmatched end tag:caption'); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
|
|
|
|
## generate implied end tags |
|
|
if ({ |
|
|
dd => 1, dt => 1, li => 1, p => 1, |
|
|
td => 1, th => 1, tr => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!back-token; # <?> |
|
|
$token = {type => 'end tag', tag_name => 'caption'}; |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
|
} |
|
|
|
|
|
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
|
} |
|
|
|
|
|
splice @{$self->{open_elements}}, $i; |
|
|
|
|
|
$clear_up_to_marker->(); |
|
|
|
|
|
$self->{insertion_mode} = 'in table'; |
|
|
|
|
|
## reprocess |
|
|
redo B; |
|
|
} else { |
|
|
# |
|
|
} |
|
|
} elsif ($token->{type} eq 'end tag') { |
|
|
if ($token->{tag_name} eq 'caption') { |
|
|
## have a table element in table scope |
|
|
my $i; |
|
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
my $node = $self->{open_elements}->[$_]; |
|
|
if ($node->[1] eq $token->{tag_name}) { |
|
|
$i = $_; |
|
|
last INSCOPE; |
|
|
} elsif ({ |
|
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
unless (defined $i) { |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
|
|
|
|
## generate implied end tags |
|
|
if ({ |
|
|
dd => 1, dt => 1, li => 1, p => 1, |
|
|
td => 1, th => 1, tr => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
|
} |
|
|
|
|
|
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
|
} |
|
|
|
|
|
splice @{$self->{open_elements}}, $i; |
|
|
|
|
|
$clear_up_to_marker->(); |
|
|
|
|
|
$self->{insertion_mode} = 'in table'; |
|
|
|
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'table') { |
|
|
!!!parse-error (type => 'not closed:caption'); |
|
|
|
|
|
## As if </caption> |
|
|
## have a table element in table scope |
|
|
my $i; |
|
|
INSCOPE: for (reverse 0..$#{$self->{open_elements}}) { |
|
|
my $node = $self->{open_elements}->[$_]; |
|
|
if ($node->[1] eq 'caption') { |
|
|
$i = $_; |
|
|
last INSCOPE; |
|
|
} elsif ({ |
|
|
table => 1, html => 1, |
|
|
}->{$node->[1]}) { |
|
|
last INSCOPE; |
|
|
} |
|
|
} # INSCOPE |
|
|
unless (defined $i) { |
|
|
!!!parse-error (type => 'unmatched end tag:caption'); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
|
|
|
|
## generate implied end tags |
|
|
if ({ |
|
|
dd => 1, dt => 1, li => 1, p => 1, |
|
|
td => 1, th => 1, tr => 1, |
|
|
}->{$self->{open_elements}->[-1]->[1]}) { |
|
|
!!!back-token; # </table> |
|
|
$token = {type => 'end tag', tag_name => 'caption'}; |
|
|
!!!back-token; |
|
|
$token = {type => 'end tag', |
|
|
tag_name => $self->{open_elements}->[-1]->[1]}; # MUST |
|
|
redo B; |
|
|
} |
|
|
|
|
|
if ($self->{open_elements}->[-1]->[1] ne 'caption') { |
|
|
!!!parse-error (type => 'not closed:'.$self->{open_elements}->[-1]->[1]); |
|
|
} |
|
|
|
|
|
splice @{$self->{open_elements}}, $i; |
|
|
|
|
|
$clear_up_to_marker->(); |
|
|
|
|
|
$self->{insertion_mode} = 'in table'; |
|
|
|
|
|
## reprocess |
|
|
redo B; |
|
|
} elsif ({ |
|
|
body => 1, col => 1, colgroup => 1, |
|
|
html => 1, tbody => 1, td => 1, tfoot => 1, |
|
|
th => 1, thead => 1, tr => 1, |
|
|
}->{$token->{tag_name}}) { |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
redo B; |
|
|
} else { |
|
|
# |
|
|
} |
|
|
} else { |
|
|
# |
|
|
} |
|
|
|
|
|
$in_body->($insert_to_current); |
|
|
redo B; |
|
| 4050 |
} elsif ($self->{insertion_mode} eq 'in column group') { |
} elsif ($self->{insertion_mode} eq 'in column group') { |
| 4051 |
if ($token->{type} eq 'character') { |
if ($token->{type} eq 'character') { |
| 4052 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 4058 |
} |
} |
| 4059 |
|
|
| 4060 |
# |
# |
|
} elsif ($token->{type} eq 'comment') { |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 4061 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 4062 |
if ($token->{tag_name} eq 'col') { |
if ($token->{tag_name} eq 'col') { |
| 4063 |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 4163 |
|
|
| 4164 |
!!!next-token; |
!!!next-token; |
| 4165 |
redo B; |
redo B; |
|
} elsif ($token->{type} eq 'comment') { |
|
|
## Copied from 'in table' |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 4166 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 4167 |
if ({ |
if ({ |
| 4168 |
tr => 1, |
tr => 1, |
| 4263 |
if ({ |
if ({ |
| 4264 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 4265 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 4266 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 4267 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4268 |
!!!back-token; # <table> |
!!!back-token; # <table> |
| 4269 |
$token = {type => 'end tag', tag_name => 'table'}; |
$token = {type => 'end tag', tag_name => 'table'}; |
| 4442 |
|
|
| 4443 |
!!!next-token; |
!!!next-token; |
| 4444 |
redo B; |
redo B; |
|
} elsif ($token->{type} eq 'comment') { |
|
|
## Copied from 'in table' |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 4445 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 4446 |
if ($token->{tag_name} eq 'th' or |
if ($token->{tag_name} eq 'th' or |
| 4447 |
$token->{tag_name} eq 'td') { |
$token->{tag_name} eq 'td') { |
| 4526 |
if ({ |
if ({ |
| 4527 |
dd => 1, dt => 1, li => 1, p => 1, |
dd => 1, dt => 1, li => 1, p => 1, |
| 4528 |
td => 1, th => 1, tr => 1, |
td => 1, th => 1, tr => 1, |
| 4529 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 4530 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4531 |
!!!back-token; # <table> |
!!!back-token; # <table> |
| 4532 |
$token = {type => 'end tag', tag_name => 'table'}; |
$token = {type => 'end tag', tag_name => 'table'}; |
| 4701 |
|
|
| 4702 |
!!!next-token; |
!!!next-token; |
| 4703 |
redo B; |
redo B; |
|
} elsif ($token->{type} eq 'comment') { |
|
|
## NOTE: This is a code clone of "comment in body". |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 4704 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 4705 |
if ({ |
if ({ |
| 4706 |
caption => 1, col => 1, colgroup => 1, |
caption => 1, col => 1, colgroup => 1, |
| 4762 |
td => ($token->{tag_name} eq 'th'), |
td => ($token->{tag_name} eq 'th'), |
| 4763 |
th => ($token->{tag_name} eq 'td'), |
th => ($token->{tag_name} eq 'td'), |
| 4764 |
tr => 1, |
tr => 1, |
| 4765 |
|
tbody => 1, tfoot=> 1, thead => 1, |
| 4766 |
}->{$self->{open_elements}->[-1]->[1]}) { |
}->{$self->{open_elements}->[-1]->[1]}) { |
| 4767 |
!!!back-token; |
!!!back-token; |
| 4768 |
$token = {type => 'end tag', |
$token = {type => 'end tag', |
| 4837 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
| 4838 |
!!!next-token; |
!!!next-token; |
| 4839 |
redo B; |
redo B; |
|
} elsif ($token->{type} eq 'comment') { |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 4840 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 4841 |
if ($token->{tag_name} eq 'option') { |
if ($token->{tag_name} eq 'option') { |
| 4842 |
if ($self->{open_elements}->[-1]->[1] eq 'option') { |
if ($self->{open_elements}->[-1]->[1] eq 'option') { |
| 5009 |
} elsif ($self->{insertion_mode} eq 'after body') { |
} elsif ($self->{insertion_mode} eq 'after body') { |
| 5010 |
if ($token->{type} eq 'character') { |
if ($token->{type} eq 'character') { |
| 5011 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 5012 |
|
my $data = $1; |
| 5013 |
## As if in body |
## As if in body |
| 5014 |
$reconstruct_active_formatting_elements->($insert_to_current); |
$reconstruct_active_formatting_elements->($insert_to_current); |
| 5015 |
|
|
| 5016 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 5017 |
|
|
| 5018 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 5019 |
!!!next-token; |
!!!next-token; |
| 5022 |
} |
} |
| 5023 |
|
|
| 5024 |
# |
# |
| 5025 |
!!!parse-error (type => 'after body:#'.$token->{type}); |
!!!parse-error (type => 'after body:#character'); |
|
} elsif ($token->{type} eq 'comment') { |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[0]->[0]->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
| 5026 |
} elsif ($token->{type} eq 'start tag') { |
} elsif ($token->{type} eq 'start tag') { |
| 5027 |
!!!parse-error (type => 'after body:'.$token->{tag_name}); |
!!!parse-error (type => 'after body:'.$token->{tag_name}); |
| 5028 |
# |
# |
| 5034 |
!!!next-token; |
!!!next-token; |
| 5035 |
redo B; |
redo B; |
| 5036 |
} else { |
} else { |
| 5037 |
$phase = 'trailing end'; |
$previous_insertion_mode = $self->{insertion_mode}; |
| 5038 |
|
$self->{insertion_mode} = 'trailing end'; |
| 5039 |
!!!next-token; |
!!!next-token; |
| 5040 |
redo B; |
redo B; |
| 5041 |
} |
} |
| 5043 |
!!!parse-error (type => 'after body:/'.$token->{tag_name}); |
!!!parse-error (type => 'after body:/'.$token->{tag_name}); |
| 5044 |
} |
} |
| 5045 |
} else { |
} else { |
| 5046 |
!!!parse-error (type => 'after body:#'.$token->{type}); |
die "$0: $token->{type}: Unknown token type"; |
| 5047 |
} |
} |
| 5048 |
|
|
| 5049 |
$self->{insertion_mode} = 'in body'; |
$self->{insertion_mode} = 'in body'; |
| 5050 |
## reprocess |
## reprocess |
| 5051 |
redo B; |
redo B; |
| 5052 |
} elsif ($self->{insertion_mode} eq 'in frameset') { |
} elsif ($self->{insertion_mode} eq 'in frameset') { |
| 5053 |
if ($token->{type} eq 'character') { |
if ($token->{type} eq 'character') { |
| 5054 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 5055 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
|
|
|
|
unless (length $token->{data}) { |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} |
|
|
} |
|
| 5056 |
|
|
| 5057 |
# |
unless (length $token->{data}) { |
|
} elsif ($token->{type} eq 'comment') { |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
|
| 5058 |
!!!next-token; |
!!!next-token; |
| 5059 |
redo B; |
redo B; |
|
} elsif ($token->{type} eq 'start tag') { |
|
|
if ($token->{tag_name} eq 'frameset') { |
|
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'frame') { |
|
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
|
|
pop @{$self->{open_elements}}; |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{tag_name} eq 'noframes') { |
|
|
$in_body->($insert_to_current); |
|
|
redo B; |
|
|
} else { |
|
|
# |
|
|
} |
|
|
} elsif ($token->{type} eq 'end tag') { |
|
|
if ($token->{tag_name} eq 'frameset') { |
|
|
if ($self->{open_elements}->[-1]->[1] eq 'html' and |
|
|
@{$self->{open_elements}} == 1) { |
|
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
} else { |
|
|
pop @{$self->{open_elements}}; |
|
|
!!!next-token; |
|
|
} |
|
|
|
|
|
## if not inner_html and |
|
|
if ($self->{open_elements}->[-1]->[1] ne 'frameset') { |
|
|
$self->{insertion_mode} = 'after frameset'; |
|
|
} |
|
|
redo B; |
|
|
} else { |
|
|
# |
|
|
} |
|
|
} else { |
|
|
# |
|
| 5060 |
} |
} |
| 5061 |
|
} |
| 5062 |
if (defined $token->{tag_name}) { |
|
| 5063 |
!!!parse-error (type => 'in frameset:'.$token->{tag_name}); |
!!!parse-error (type => 'in frameset:#character'); |
| 5064 |
|
## Ignore the token |
| 5065 |
|
!!!next-token; |
| 5066 |
|
redo B; |
| 5067 |
|
} elsif ($token->{type} eq 'start tag') { |
| 5068 |
|
if ($token->{tag_name} eq 'frameset') { |
| 5069 |
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 5070 |
|
!!!next-token; |
| 5071 |
|
redo B; |
| 5072 |
|
} elsif ($token->{tag_name} eq 'frame') { |
| 5073 |
|
!!!insert-element ($token->{tag_name}, $token->{attributes}); |
| 5074 |
|
pop @{$self->{open_elements}}; |
| 5075 |
|
!!!next-token; |
| 5076 |
|
redo B; |
| 5077 |
|
} elsif ($token->{tag_name} eq 'noframes') { |
| 5078 |
|
$in_body->($insert_to_current); |
| 5079 |
|
redo B; |
| 5080 |
|
} else { |
| 5081 |
|
!!!parse-error (type => 'in frameset:'.$token->{tag_name}); |
| 5082 |
|
## Ignore the token |
| 5083 |
|
!!!next-token; |
| 5084 |
|
redo B; |
| 5085 |
|
} |
| 5086 |
|
} elsif ($token->{type} eq 'end tag') { |
| 5087 |
|
if ($token->{tag_name} eq 'frameset') { |
| 5088 |
|
if ($self->{open_elements}->[-1]->[1] eq 'html' and |
| 5089 |
|
@{$self->{open_elements}} == 1) { |
| 5090 |
|
!!!parse-error (type => 'unmatched end tag:'.$token->{tag_name}); |
| 5091 |
|
## Ignore the token |
| 5092 |
|
!!!next-token; |
| 5093 |
} else { |
} else { |
| 5094 |
!!!parse-error (type => 'in frameset:#'.$token->{type}); |
pop @{$self->{open_elements}}; |
| 5095 |
|
!!!next-token; |
| 5096 |
|
} |
| 5097 |
|
|
| 5098 |
|
if (not defined $self->{inner_html_node} and |
| 5099 |
|
$self->{open_elements}->[-1]->[1] ne 'frameset') { |
| 5100 |
|
$self->{insertion_mode} = 'after frameset'; |
| 5101 |
} |
} |
| 5102 |
|
redo B; |
| 5103 |
|
} else { |
| 5104 |
|
!!!parse-error (type => 'in frameset:/'.$token->{tag_name}); |
| 5105 |
## Ignore the token |
## Ignore the token |
| 5106 |
!!!next-token; |
!!!next-token; |
| 5107 |
redo B; |
redo B; |
| 5108 |
} elsif ($self->{insertion_mode} eq 'after frameset') { |
} |
| 5109 |
if ($token->{type} eq 'character') { |
} else { |
| 5110 |
|
die "$0: $token->{type}: Unknown token type"; |
| 5111 |
|
} |
| 5112 |
|
} elsif ($self->{insertion_mode} eq 'after frameset') { |
| 5113 |
|
if ($token->{type} eq 'character') { |
| 5114 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 5115 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($token->{data}); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($1); |
| 5116 |
|
|
| 5117 |
unless (length $token->{data}) { |
unless (length $token->{data}) { |
| 5118 |
!!!next-token; |
!!!next-token; |
| 5120 |
} |
} |
| 5121 |
} |
} |
| 5122 |
|
|
| 5123 |
# |
if ($token->{data} =~ s/^[^\x09\x0A\x0B\x0C\x20]+//) { |
| 5124 |
} elsif ($token->{type} eq 'comment') { |
!!!parse-error (type => 'after frameset:#character'); |
| 5125 |
my $comment = $self->{document}->create_comment ($token->{data}); |
|
| 5126 |
$self->{open_elements}->[-1]->[0]->append_child ($comment); |
## Ignore the token. |
| 5127 |
!!!next-token; |
if (length $token->{data}) { |
| 5128 |
redo B; |
## reprocess the rest of characters |
| 5129 |
} elsif ($token->{type} eq 'start tag') { |
} else { |
| 5130 |
if ($token->{tag_name} eq 'noframes') { |
!!!next-token; |
| 5131 |
$in_body->($insert_to_current); |
} |
|
redo B; |
|
|
} else { |
|
|
# |
|
|
} |
|
|
} elsif ($token->{type} eq 'end tag') { |
|
|
if ($token->{tag_name} eq 'html') { |
|
|
$phase = 'trailing end'; |
|
|
!!!next-token; |
|
| 5132 |
redo B; |
redo B; |
|
} else { |
|
|
# |
|
| 5133 |
} |
} |
| 5134 |
} else { |
|
| 5135 |
# |
die qq[$0: Character "$token->{data}"]; |
| 5136 |
} |
} elsif ($token->{type} eq 'start tag') { |
| 5137 |
|
if ($token->{tag_name} eq 'noframes') { |
| 5138 |
if (defined $token->{tag_name}) { |
$in_body->($insert_to_current); |
| 5139 |
!!!parse-error (type => 'after frameset:'.$token->{tag_name}); |
redo B; |
| 5140 |
} else { |
} else { |
| 5141 |
!!!parse-error (type => 'after frameset:#'.$token->{type}); |
!!!parse-error (type => 'after frameset:'.$token->{tag_name}); |
|
} |
|
| 5142 |
## Ignore the token |
## Ignore the token |
| 5143 |
!!!next-token; |
!!!next-token; |
| 5144 |
redo B; |
redo B; |
| 5145 |
|
} |
| 5146 |
## ISSUE: An issue in spec there |
} elsif ($token->{type} eq 'end tag') { |
| 5147 |
|
if ($token->{tag_name} eq 'html') { |
| 5148 |
|
$previous_insertion_mode = $self->{insertion_mode}; |
| 5149 |
|
$self->{insertion_mode} = 'trailing end'; |
| 5150 |
|
!!!next-token; |
| 5151 |
|
redo B; |
| 5152 |
} else { |
} else { |
| 5153 |
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
!!!parse-error (type => 'after frameset:/'.$token->{tag_name}); |
| 5154 |
|
## Ignore the token |
| 5155 |
|
!!!next-token; |
| 5156 |
|
redo B; |
| 5157 |
} |
} |
| 5158 |
|
} else { |
| 5159 |
|
die "$0: $token->{type}: Unknown token type"; |
| 5160 |
} |
} |
| 5161 |
} elsif ($phase eq 'trailing end') { |
|
| 5162 |
|
## ISSUE: An issue in spec here |
| 5163 |
|
} elsif ($self->{insertion_mode} eq 'trailing end') { |
| 5164 |
## states in the main stage is preserved yet # MUST |
## states in the main stage is preserved yet # MUST |
| 5165 |
|
|
| 5166 |
if ($token->{type} eq 'DOCTYPE') { |
if ($token->{type} eq 'character') { |
|
!!!parse-error (type => 'after html:#DOCTYPE'); |
|
|
## Ignore the token |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{type} eq 'comment') { |
|
|
my $comment = $self->{document}->create_comment ($token->{data}); |
|
|
$self->{document}->append_child ($comment); |
|
|
!!!next-token; |
|
|
redo B; |
|
|
} elsif ($token->{type} eq 'character') { |
|
| 5167 |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
if ($token->{data} =~ s/^([\x09\x0A\x0B\x0C\x20]+)//) { |
| 5168 |
my $data = $1; |
my $data = $1; |
| 5169 |
## As if in the main phase. |
## As if in the main phase. |
| 5170 |
## NOTE: The insertion mode in the main phase |
## NOTE: The insertion mode in the main phase |
| 5171 |
## just before the phase has been changed to the trailing |
## just before the phase has been changed to the trailing |
| 5172 |
## end phase is either "after body" or "after frameset". |
## end phase is either "after body" or "after frameset". |
| 5173 |
$reconstruct_active_formatting_elements->($insert_to_current) |
$reconstruct_active_formatting_elements->($insert_to_current); |
|
if $phase eq 'main'; |
|
| 5174 |
|
|
| 5175 |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($data); |
$self->{open_elements}->[-1]->[0]->manakai_append_text ($data); |
| 5176 |
|
|
| 5181 |
} |
} |
| 5182 |
|
|
| 5183 |
!!!parse-error (type => 'after html:#character'); |
!!!parse-error (type => 'after html:#character'); |
| 5184 |
$phase = 'main'; |
$self->{insertion_mode} = $previous_insertion_mode; |
| 5185 |
## reprocess |
## reprocess |
| 5186 |
redo B; |
redo B; |
| 5187 |
} elsif ($token->{type} eq 'start tag' or |
} elsif ($token->{type} eq 'start tag') { |
|
$token->{type} eq 'end tag') { |
|
| 5188 |
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
!!!parse-error (type => 'after html:'.$token->{tag_name}); |
| 5189 |
$phase = 'main'; |
$self->{insertion_mode} = $previous_insertion_mode; |
| 5190 |
|
## reprocess |
| 5191 |
|
redo B; |
| 5192 |
|
} elsif ($token->{type} eq 'end tag') { |
| 5193 |
|
!!!parse-error (type => 'after html:/'.$token->{tag_name}); |
| 5194 |
|
$self->{insertion_mode} = $previous_insertion_mode; |
| 5195 |
## reprocess |
## reprocess |
| 5196 |
redo B; |
redo B; |
|
} elsif ($token->{type} eq 'end-of-file') { |
|
|
## Stop parsing |
|
|
last B; |
|
| 5197 |
} else { |
} else { |
| 5198 |
die "$0: $token->{type}: Unknown token"; |
die "$0: $token->{type}: Unknown token"; |
| 5199 |
} |
} |
| 5200 |
|
} else { |
| 5201 |
|
die "$0: $self->{insertion_mode}: Unknown insertion mode"; |
| 5202 |
} |
} |
| 5203 |
} # B |
} # B |
| 5204 |
|
|
| 5237 |
## Step 1 # MUST |
## Step 1 # MUST |
| 5238 |
my $this_doc = $node->owner_document; |
my $this_doc = $node->owner_document; |
| 5239 |
my $doc = $this_doc->implementation->create_document; |
my $doc = $this_doc->implementation->create_document; |
| 5240 |
## TODO: Mark as HTML document |
$doc->manakai_is_html (1); |
| 5241 |
my $p = $class->new; |
my $p = $class->new; |
| 5242 |
$p->{document} = $doc; |
$p->{document} = $doc; |
| 5243 |
|
|
| 5286 |
|
|
| 5287 |
## Step 2 |
## Step 2 |
| 5288 |
my $node_ln = $node->local_name; |
my $node_ln = $node->local_name; |
| 5289 |
$p->{content_model_flag} = { |
$p->{content_model} = { |
| 5290 |
title => 'RCDATA', |
title => RCDATA_CONTENT_MODEL, |
| 5291 |
textarea => 'RCDATA', |
textarea => RCDATA_CONTENT_MODEL, |
| 5292 |
style => 'CDATA', |
style => CDATA_CONTENT_MODEL, |
| 5293 |
script => 'CDATA', |
script => CDATA_CONTENT_MODEL, |
| 5294 |
xmp => 'CDATA', |
xmp => CDATA_CONTENT_MODEL, |
| 5295 |
iframe => 'CDATA', |
iframe => CDATA_CONTENT_MODEL, |
| 5296 |
noembed => 'CDATA', |
noembed => CDATA_CONTENT_MODEL, |
| 5297 |
noframes => 'CDATA', |
noframes => CDATA_CONTENT_MODEL, |
| 5298 |
noscript => 'CDATA', |
noscript => CDATA_CONTENT_MODEL, |
| 5299 |
plaintext => 'PLAINTEXT', |
plaintext => PLAINTEXT_CONTENT_MODEL, |
| 5300 |
}->{$node_ln} || 'PCDATA'; |
}->{$node_ln}; |
| 5301 |
## ISSUE: What is "the name of the element"? local name? |
$p->{content_model} = PCDATA_CONTENT_MODEL |
| 5302 |
|
unless defined $p->{content_model}; |
| 5303 |
|
## ISSUE: What is "the name of the element"? local name? |
| 5304 |
|
|
| 5305 |
$p->{inner_html_node} = [$node, $node_ln]; |
$p->{inner_html_node} = [$node, $node_ln]; |
| 5306 |
|
|
| 5400 |
|
|
| 5401 |
my $nt = $child->node_type; |
my $nt = $child->node_type; |
| 5402 |
if ($nt == 1) { # Element |
if ($nt == 1) { # Element |
| 5403 |
my $tag_name = lc $child->tag_name; ## ISSUE: Definition of "lowercase" |
my $tag_name = $child->tag_name; ## TODO: manakai_tag_name |
| 5404 |
$s .= '<' . $tag_name; |
$s .= '<' . $tag_name; |
| 5405 |
|
## NOTE: Non-HTML case: |
| 5406 |
## ISSUE: Non-html elements |
## <http://permalink.gmane.org/gmane.org.w3c.whatwg.discuss/11191> |
| 5407 |
|
|
| 5408 |
my @attrs = @{$child->attributes}; # sort order MUST be stable |
my @attrs = @{$child->attributes}; # sort order MUST be stable |
| 5409 |
for my $attr (@attrs) { # order is implementation dependent |
for my $attr (@attrs) { # order is implementation dependent |
| 5410 |
my $attr_name = lc $attr->name; ## ISSUE: Definition of "lowercase" |
my $attr_name = $attr->name; ## TODO: manakai_name |
| 5411 |
$s .= ' ' . $attr_name . '="'; |
$s .= ' ' . $attr_name . '="'; |
| 5412 |
my $attr_value = $attr->value; |
my $attr_value = $attr->value; |
| 5413 |
## escape |
## escape |
| 5426 |
spacer => 1, wbr => 1, |
spacer => 1, wbr => 1, |
| 5427 |
}->{$tag_name}; |
}->{$tag_name}; |
| 5428 |
|
|
| 5429 |
|
$s .= "\x0A" if $tag_name eq 'pre' or $tag_name eq 'textarea'; |
| 5430 |
|
|
| 5431 |
if (not $in_cdata and { |
if (not $in_cdata and { |
| 5432 |
style => 1, script => 1, xmp => 1, iframe => 1, |
style => 1, script => 1, xmp => 1, iframe => 1, |
| 5433 |
noembed => 1, noframes => 1, noscript => 1, |
noembed => 1, noframes => 1, noscript => 1, |
| 5434 |
|
plaintext => 1, |
| 5435 |
}->{$tag_name}) { |
}->{$tag_name}) { |
| 5436 |
unshift @node, 'cdata-out'; |
unshift @node, 'cdata-out'; |
| 5437 |
$in_cdata = 1; |
$in_cdata = 1; |