1270 |
|
|
1271 |
redo A; |
redo A; |
1272 |
} else { |
} else { |
1273 |
if ($self->{nc} == 0x003D) { # = |
if ($self->{nc} == 0x003D or $self->{nc} == 0x003C) { # =, < |
1274 |
!!!cp (93); |
!!!cp (93); |
1275 |
## XML5: Not a parse error. |
## XML5: Not a parse error. |
1276 |
!!!parse-error (type => 'bad attribute value'); |
!!!parse-error (type => 'bad attribute value'); |
1316 |
$self->{state} = ENTITY_STATE; |
$self->{state} = ENTITY_STATE; |
1317 |
!!!next-input-character; |
!!!next-input-character; |
1318 |
redo A; |
redo A; |
1319 |
|
} elsif ($self->{is_xml} and |
1320 |
|
$is_space->{$self->{nc}}) { |
1321 |
|
!!!cp (97.1); |
1322 |
|
$self->{ca}->{value} .= ' '; |
1323 |
|
## Stay in the state. |
1324 |
|
!!!next-input-character; |
1325 |
|
redo A; |
1326 |
} elsif ($self->{nc} == -1) { |
} elsif ($self->{nc} == -1) { |
1327 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
1328 |
if ($self->{ct}->{type} == START_TAG_TOKEN) { |
if ($self->{ct}->{type} == START_TAG_TOKEN) { |
1370 |
} |
} |
1371 |
$self->{ca}->{value} .= chr ($self->{nc}); |
$self->{ca}->{value} .= chr ($self->{nc}); |
1372 |
$self->{read_until}->($self->{ca}->{value}, |
$self->{read_until}->($self->{ca}->{value}, |
1373 |
q["&<], |
qq["&<\x09\x0C\x20], |
1374 |
length $self->{ca}->{value}); |
length $self->{ca}->{value}); |
1375 |
|
|
1376 |
## Stay in the state |
## Stay in the state |
1407 |
$self->{state} = ENTITY_STATE; |
$self->{state} = ENTITY_STATE; |
1408 |
!!!next-input-character; |
!!!next-input-character; |
1409 |
redo A; |
redo A; |
1410 |
|
} elsif ($self->{is_xml} and |
1411 |
|
$is_space->{$self->{nc}}) { |
1412 |
|
!!!cp (103.1); |
1413 |
|
$self->{ca}->{value} .= ' '; |
1414 |
|
## Stay in the state. |
1415 |
|
!!!next-input-character; |
1416 |
|
redo A; |
1417 |
} elsif ($self->{nc} == -1) { |
} elsif ($self->{nc} == -1) { |
1418 |
!!!parse-error (type => 'unclosed attribute value'); |
!!!parse-error (type => 'unclosed attribute value'); |
1419 |
if ($self->{ct}->{type} == START_TAG_TOKEN) { |
if ($self->{ct}->{type} == START_TAG_TOKEN) { |
1461 |
} |
} |
1462 |
$self->{ca}->{value} .= chr ($self->{nc}); |
$self->{ca}->{value} .= chr ($self->{nc}); |
1463 |
$self->{read_until}->($self->{ca}->{value}, |
$self->{read_until}->($self->{ca}->{value}, |
1464 |
q['&<], |
qq['&<\x09\x0C\x20], |
1465 |
length $self->{ca}->{value}); |
length $self->{ca}->{value}); |
1466 |
|
|
1467 |
## Stay in the state |
## Stay in the state |
1573 |
0x0022 => 1, # " |
0x0022 => 1, # " |
1574 |
0x0027 => 1, # ' |
0x0027 => 1, # ' |
1575 |
0x003D => 1, # = |
0x003D => 1, # = |
1576 |
|
0x003C => 1, # < |
1577 |
}->{$self->{nc}}) { |
}->{$self->{nc}}) { |
1578 |
!!!cp (115); |
!!!cp (115); |
1579 |
## XML5: Not a parse error. |
## XML5: Not a parse error. |
1583 |
} |
} |
1584 |
$self->{ca}->{value} .= chr ($self->{nc}); |
$self->{ca}->{value} .= chr ($self->{nc}); |
1585 |
$self->{read_until}->($self->{ca}->{value}, |
$self->{read_until}->($self->{ca}->{value}, |
1586 |
q["'=& >], |
qq["'=& \x09\x0C>], |
1587 |
length $self->{ca}->{value}); |
length $self->{ca}->{value}); |
1588 |
|
|
1589 |
## Stay in the state |
## Stay in the state |
2119 |
redo A; |
redo A; |
2120 |
} else { |
} else { |
2121 |
!!!cp (154); |
!!!cp (154); |
|
## XML5: Not a parse error. |
|
|
!!!parse-error (type => 'dash in comment', |
|
|
line => $self->{line_prev}, |
|
|
column => $self->{column_prev}); |
|
2122 |
$self->{ct}->{data} .= '--' . chr ($self->{nc}); # comment |
$self->{ct}->{data} .= '--' . chr ($self->{nc}); # comment |
2123 |
$self->{state} = COMMENT_STATE; |
$self->{state} = COMMENT_STATE; |
2124 |
!!!next-input-character; |
!!!next-input-character; |
2130 |
$self->{state} = BEFORE_DOCTYPE_NAME_STATE; |
$self->{state} = BEFORE_DOCTYPE_NAME_STATE; |
2131 |
!!!next-input-character; |
!!!next-input-character; |
2132 |
redo A; |
redo A; |
2133 |
|
} elsif ($self->{nc} == -1) { |
2134 |
|
!!!cp (155.1); |
2135 |
|
!!!parse-error (type => 'unclosed DOCTYPE'); |
2136 |
|
$self->{ct}->{quirks} = 1; |
2137 |
|
|
2138 |
|
$self->{state} = DATA_STATE; |
2139 |
|
## Reconsume. |
2140 |
|
!!!emit ($self->{ct}); # DOCTYPE (quirks) |
2141 |
|
|
2142 |
|
redo A; |
2143 |
} else { |
} else { |
2144 |
!!!cp (156); |
!!!cp (156); |
2145 |
## XML5: Unless EOF, swith to the bogus comment state. |
## XML5: Swith to the bogus comment state. |
2146 |
!!!parse-error (type => 'no space before DOCTYPE name'); |
!!!parse-error (type => 'no space before DOCTYPE name'); |
2147 |
$self->{state} = BEFORE_DOCTYPE_NAME_STATE; |
$self->{state} = BEFORE_DOCTYPE_NAME_STATE; |
2148 |
## reconsume |
## reconsume |
3238 |
my $code = $self->{kwd}; |
my $code = $self->{kwd}; |
3239 |
my $l = $self->{line_prev}; |
my $l = $self->{line_prev}; |
3240 |
my $c = $self->{column_prev}; |
my $c = $self->{column_prev}; |
3241 |
if ($charref_map->{$code}) { |
if ((not $self->{is_xml} and $charref_map->{$code}) or |
3242 |
|
($self->{is_xml} and 0xD800 <= $code and $code <= 0xDFFF) or |
3243 |
|
($self->{is_xml} and $code == 0x0000)) { |
3244 |
!!!cp (1015); |
!!!cp (1015); |
3245 |
!!!parse-error (type => 'invalid character reference', |
!!!parse-error (type => 'invalid character reference', |
3246 |
text => (sprintf 'U+%04X', $code), |
text => (sprintf 'U+%04X', $code), |
3353 |
my $code = $self->{kwd}; |
my $code = $self->{kwd}; |
3354 |
my $l = $self->{line_prev}; |
my $l = $self->{line_prev}; |
3355 |
my $c = $self->{column_prev}; |
my $c = $self->{column_prev}; |
3356 |
if ($charref_map->{$code}) { |
if ((not $self->{is_xml} and $charref_map->{$code}) or |
3357 |
|
($self->{is_xml} and 0xD800 <= $code and $code <= 0xDFFF) or |
3358 |
|
($self->{is_xml} and $code == 0x0000)) { |
3359 |
!!!cp (1008); |
!!!cp (1008); |
3360 |
!!!parse-error (type => 'invalid character reference', |
!!!parse-error (type => 'invalid character reference', |
3361 |
text => (sprintf 'U+%04X', $code), |
text => (sprintf 'U+%04X', $code), |