MensBeam
/
HTML-Parser
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
Browse Source

Pushing forward on TreeBuilder 

• Updated mensbeam/intl dependency.
• Moved scope methods from Element to OpenElementsStack. They don't need to be used outside of the parser and don't make sense there.
• Cleaned up parse errors. Displaying what is expected or found is not helpful.
ns
Dustin Wilson 6 years ago
parent
6e7145c022
commit
0624e0be93
6 changed files with 313 additions and 221 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 7
      composer.lock
  2. 91
      lib/DOM/Element.php
  3. 101
      lib/OpenElementsStack.php
  4. 18
      lib/ParseError.php
  5. 144
      lib/Tokenizer.php
  6. 173
      lib/TreeBuilder.php

7
composer.lock
View File

@ -8,11 +8,11 @@
"packages": [
{
"name": "mensbeam/intl",
"version": "0.3.0",
"version": "0.4.0",
"source": {
"type": "git",
"url": "https://code.mensbeam.com/MensBeam/intl",
"reference": "61993bb900ebd6150c8b762c4b0158f0f4a5fc78"
"reference": "58328b7524b6889889ef0a60ab9e622b3d071a4a"
},
"require": {
"php": "^7.0"
@ -40,6 +40,7 @@
],
"description": "A set of dependency-free basic internationalization tools",
"keywords": [
"WHATWG",
"charset",
"encoding",
"internationalization",
@ -48,7 +49,7 @@
"utf-8",
"utf8"
],
"time": "2018-08-29T21:37:44+00:00"
"time": "2018-09-15T23:52:16+00:00"
}
],
"packages-dev": [],

91
lib/DOM/Element.php
View File

@ -135,95 +135,4 @@ class Element extends \DOMElement {
return $s;
}
public function isInListItemScope(): bool {
$name = $this->name;
$ns = $this->namespaceURI;
# The stack of open elements is said to have a particular element in list item
# scope when it has that element in the specific scope consisting of the
# following element types:
#
# All the element types listed above for the has an element in scope
# algorithm.
# ol in the HTML namespace
# ul in the HTML namespace
return ($this->isInScope() || ($ns === '' && ($name === 'ol' || $name === 'ul'))) ? true : false;
}
public function isInButtonScope(): bool {
$name = $this->name;
$ns = $this->namespaceURI;
# The stack of open elements is said to have a particular element in button
# scope when it has that element in the specific scope consisting of the
# following element types:
#
# All the element types listed above for the has an element in scope
# algorithm.
# button in the HTML namespace
return ($this->isInScope() || ($ns === '' && $name === 'button')) ? true : false;
}
public function isInTableScope(): bool {
$name = $this->name;
# The stack of open elements is said to have a particular element in table scope
# when it has that element in the specific scope consisting of the following
# element types:
#
# html in the HTML namespace
# table in the HTML namespace
# template in the HTML namespace
return ($this->namespaceURI === '' && ($name === 'html' || $name === 'table' || $name === 'template')) ? true : false;
}
public function isInSelectScope(): bool {
$name = $this->name;
$ns = $this->namespaceURI;
# The stack of open elements is said to have a particular element in select
# scope when it has that element in the specific scope consisting of all element
# types except the following:
#
# optgroup in the HTML namespace
# option in the HTML namespace
return ($this->namespaceURI === '' && ($name === 'optgroup' || $name === 'option')) ? false : true;
}
protected function isInScope(): bool {
$name = $this->name;
$ns = $this->namespaceURI;
# The stack of open elements is said to have a particular element in scope when
# it has that element in the specific scope consisting of the following element
# types:
#
# applet
# caption
# html
# table
# td
# th
# marquee
# object
# template
# MathML mi
# MathML mo
# MathML mn
# MathML ms
# MathML mtext
# MathML annotation-xml
# SVG foreignObject
# SVG desc
# SVG title
return (($ns === '' && ($name === 'applet' || $name === 'caption' || $name === 'html' || $name === 'table' || $name === 'td' || $name === 'th' || $name === 'marquee' || $name === 'object' || $name === 'template')) ||
($ns === Parser::MATHML_NAMESPACE && ($name === 'mi' || $name === 'mo' || $name === 'mn' || $name === 'ms' || $name === 'mtext' || $name === 'annotation-xml')) ||
($ns === Parser::SVG_NAMESPACE && ($name === 'foreignObject' || $name === 'desc' || $name === 'title'))) ? true : false;
}
}

101
lib/OpenElementsStack.php
View File

@ -84,19 +84,19 @@ class OpenElementsStack extends Stack {
protected function hasElementInScope(string $elementName, int $type): bool {
switch ($type) {
case 0: $func = 'isInListScope';
case 0: $func = 'isElementInListScope';
break;
case 1: $func = 'isInButtonScope';
case 1: $func = 'isElementInButtonScope';
break;
case 2: $func = 'isInTableScope';
case 2: $func = 'isElementInTableScope';
break;
case 3: $func = 'isInSelectScope';
case 3: $func = 'isElementInSelectScope';
break;
default: return false;
}
foreach (array_reverse($this->_storage) as $key => $value) {
if ($value->$func()) {
if ($this->$func($value)) {
return true;
}
}
@ -104,6 +104,97 @@ class OpenElementsStack extends Stack {
return false;
}
protected function isElementInListItemScope(Element $element): bool {
$name = $element->name;
$ns = $element->namespaceURI;
# The stack of open elements is said to have a particular element in list item
# scope when it has that element in the specific scope consisting of the
# following element types:
#
# All the element types listed above for the has an element in scope
# algorithm.
# ol in the HTML namespace
# ul in the HTML namespace
return ($this->isElementInScope($element) || ($ns === '' && ($name === 'ol' || $name === 'ul'))) ? true : false;
}
protected function isElementInButtonScope(Element $element): bool {
$name = $element->name;
$ns = $element->namespaceURI;
# The stack of open elements is said to have a particular element in button
# scope when it has that element in the specific scope consisting of the
# following element types:
#
# All the element types listed above for the has an element in scope
# algorithm.
# button in the HTML namespace
return ($this->isElementInScope($element) || ($ns === '' && $name === 'button')) ? true : false;
}
protected function isElementInTableScope(Element $element): bool {
$name = $element->name;
# The stack of open elements is said to have a particular element in table scope
# when it has that element in the specific scope consisting of the following
# element types:
#
# html in the HTML namespace
# table in the HTML namespace
# template in the HTML namespace
return ($element->namespaceURI === '' && ($name === 'html' || $name === 'table' || $name === 'template')) ? true : false;
}
protected function isElementInSelectScope(Element $element): bool {
$name = $element->name;
$ns = $element->namespaceURI;
# The stack of open elements is said to have a particular element in select
# scope when it has that element in the specific scope consisting of all element
# types except the following:
#
# optgroup in the HTML namespace
# option in the HTML namespace
return ($element->namespaceURI === '' && ($name === 'optgroup' || $name === 'option')) ? false : true;
}
protected function isElementInScope(Element $element): bool {
$name = $element->name;
$ns = $element->namespaceURI;
# The stack of open elements is said to have a particular element in scope when
# it has that element in the specific scope consisting of the following element
# types:
#
# applet
# caption
# html
# table
# td
# th
# marquee
# object
# template
# MathML mi
# MathML mo
# MathML mn
# MathML ms
# MathML mtext
# MathML annotation-xml
# SVG foreignObject
# SVG desc
# SVG title
return (($ns === '' && ($name === 'applet' || $name === 'caption' || $name === 'html' || $name === 'table' || $name === 'td' || $name === 'th' || $name === 'marquee' || $name === 'object' || $name === 'template')) ||
($ns === Parser::MATHML_NAMESPACE && ($name === 'mi' || $name === 'mo' || $name === 'mn' || $name === 'ms' || $name === 'mtext' || $name === 'annotation-xml')) ||
($ns === Parser::SVG_NAMESPACE && ($name === 'foreignObject' || $name === 'desc' || $name === 'title'))) ? true : false;
}
public function __get($property) {
$value = parent::__get($property);
if (!is_null($value)) {

18
lib/ParseError.php
View File

@ -21,18 +21,18 @@ class ParseError {
const INVALID_NAMED_ENTITY = 14;
const INVALID_CODEPOINT = 15;
protected static $messages = ['Tag name expected; found %s',
'Unexpected end-of-file; %s expected',
'Unexpected "%s" character; %s expected',
protected static $messages = ['Tag name expected',
'Unexpected end-of-file',
'Unexpected "%s" character',
'%s attribute already exists; discarding',
'Unexpected end-of-tag; %s expected',
'Unexpected %s start tag; %s expected',
'Unexpected %s end tag; %s expected',
'Unexpected DOCTYPE; %s expected',
'Unexpected end-of-tag',
'Unexpected %s start tag',
'Unexpected %s end tag',
'Unexpected DOCTYPE',
'Invalid DOCTYPE',
'Invalid Control or Non-character; removing',
'Unexpected xmlns attribute value; %s expected',
'Unexpected "%s" character in entity; %s expected',
'Unexpected xmlns attribute value',
'Unexpected "%s" character in entity',
'"%s" is an invalid numeric entity',
'"%s" is an invalid name for an entity',
'"%s" is an invalid character codepoint'];

144
lib/Tokenizer.php
View File

@ -431,7 +431,7 @@ class Tokenizer {
if ($char !== '') {
ParseError::trigger(ParseError::TAG_NAME_EXPECTED, $char);
} else {
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'tag name');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
}
$this->state = self::BOGUS_COMMENT_STATE;
@ -445,7 +445,7 @@ class Tokenizer {
if ($char !== '') {
ParseError::trigger(ParseError::TAG_NAME_EXPECTED, $char);
} else {
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'tag name');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
}
$this->state = self::DATA_STATE;
@ -491,7 +491,7 @@ class Tokenizer {
# Parse error. Switch to the data state. Emit a U+003C LESS-THAN SIGN character
# token and a U+002F SOLIDUS character token. Reconsume the EOF character.
// Making errors more expressive.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'tag name');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$this->data->unconsume();
return new CharacterToken('</');
@ -547,7 +547,7 @@ class Tokenizer {
if ($char !== '') {
ParseError::trigger(ParseError::TAG_NAME_EXPECTED, $char);
} else {
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'tag name');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
}
$this->state = self::DATA_STATE;
@ -1072,7 +1072,7 @@ class Tokenizer {
elseif ($char === '') {
# Switch to the data state. Parse error. Reconsume the EOF character.
$this->state = self::DATA_STATE;
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'script data');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->data->unconsume();
}
# Anything else
@ -1107,7 +1107,7 @@ class Tokenizer {
elseif ($char === '') {
# Switch to the data state. Parse error. Reconsume the EOF character.
$this->state = self::DATA_STATE;
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'script data');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->data->unconsume();
}
# Anything else
@ -1147,7 +1147,7 @@ class Tokenizer {
elseif ($char === '') {
# Switch to the data state. Parse error. Reconsume the EOF character.
$this->state = self::DATA_STATE;
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'script data');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->data->unconsume();
}
# Anything else
@ -1356,7 +1356,7 @@ class Tokenizer {
# EOF
elseif ($char === '') {
# Parse error. Switch to the data state. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'script data');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$this->data->unconsume();
}
@ -1489,7 +1489,7 @@ class Tokenizer {
# EOF
elseif ($char === '') {
# Parse error. Switch to the data state. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'attribute name');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$this->data->unconsume();
}
@ -1507,7 +1507,7 @@ class Tokenizer {
# attribute name state.
if ($char === '"' || $char === "'" || $char === '<' || $char === '=') {
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char, 'attribute name');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char);
}
// Need to add the current attribute to the token, if necessary.
@ -1573,7 +1573,7 @@ class Tokenizer {
# Append the current input character to the current attribute's name.
if ($char === '"' || $char === "'" || $char === '<' || $char === '=') {
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char, 'attribute name');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char);
}
// OPTIMIZATION: Will just check for alpha characters and strtolower the
@ -1648,7 +1648,7 @@ class Tokenizer {
# EOF
elseif ($char === '') {
# Parse error. Switch to the data state. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'attribute name, attribute value, or tag end');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$this->data->unconsume();
}
@ -1666,7 +1666,7 @@ class Tokenizer {
# attribute name state.
if ($char === '"' || $char === "'" || $char === '<' || $char === '=') {
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char, 'attribute name, attribute value, or tag end');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char);
}
// Need to add the current attribute to the token, if necessary.
@ -1714,7 +1714,7 @@ class Tokenizer {
# ">" (U+003E)
elseif ($char === '>') {
# Parse error. Switch to the data state. Emit the current tag token.
ParseError::trigger(ParseError::UNEXPECTED_END_OF_TAG, 'attribute value');
ParseError::trigger(ParseError::UNEXPECTED_END_OF_TAG);
$this->state = self::DATA_STATE;
// Need to add the current attribute to the token, if necessary.
@ -1728,7 +1728,7 @@ class Tokenizer {
# EOF
elseif ($char === '') {
# Parse error. Switch to the data state. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'attribute value');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$this->data->unconsume();
}
@ -1744,7 +1744,7 @@ class Tokenizer {
# the attribute value (unquoted) state.
if ($char === '<' || $char === '=' || $char === '`') {
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char, 'attribute value');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char);
}
$attribute->value .= $char;
@ -1783,7 +1783,7 @@ class Tokenizer {
# EOF
elseif ($char === '') {
# Parse error. Switch to the data state. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'attribute value');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$this->data->unconsume();
}
@ -1828,7 +1828,7 @@ class Tokenizer {
# EOF
elseif ($char === '') {
# Parse error. Switch to the data state. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'attribute value');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$this->data->unconsume();
}
@ -1892,7 +1892,7 @@ class Tokenizer {
}
# Parse error. Switch to the data state. Reconsume the EOF character.
elseif ($char === '') {
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'attribute value');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$this->data->unconsume();
}
@ -1909,7 +1909,7 @@ class Tokenizer {
# Append the current input character to the current attribute's value.
if ($char === '"' || $char === "'" || $char === '<' || $char === '=' || $char === '`') {
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char, 'attribute value');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char);
}
// OPTIMIZATION: Consume all characters that aren't listed above to prevent having
@ -1954,14 +1954,14 @@ class Tokenizer {
# EOF
elseif ($char === '') {
# Parse error. Switch to the data state. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'attribute name or tag end');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$this->data->unconsume();
}
# Anything else
else {
# Parse error. Switch to the before attribute name state. Reconsume the character.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char, 'attribute name or tag end');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char);
$this->state = self::BEFORE_ATTRIBUTE_NAME_STATE;
$this->data->unconsume();
}
@ -1992,14 +1992,14 @@ class Tokenizer {
# EOF
elseif ($char === '') {
# Parse error. Switch to the data state. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'tag end');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$this->data->unconsume();
}
# Anything else
else {
# Parse error. Switch to the before attribute name state. Reconsume the character.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char, 'tag end');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char);
$this->state = self::BEFORE_ATTRIBUTE_NAME_STATE;
$this->data->unconsume();
}
@ -2067,9 +2067,9 @@ class Tokenizer {
else {
$char = $this->data->consume();
if ($char !== '') {
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char, 'markup declaration');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char);
} else {
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'markup declaration');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
}
$this->state = self::BOGUS_COMMENT_STATE;
@ -2092,7 +2092,7 @@ class Tokenizer {
# ">" (U+003E)
elseif ($char === '>') {
# Parse error. Switch to the data state. Emit the comment token.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>', 'comment');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>');
$this->state = self::DATA_STATE;
return $token;
}
@ -2100,7 +2100,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Emit the comment token. Reconsume the EOF
# character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'comment');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$this->data->unconsume();
return $token;
@ -2129,7 +2129,7 @@ class Tokenizer {
# ">" (U+003E)
elseif ($char === '>') {
# Parse error. Switch to the data state. Emit the comment token.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>', 'comment');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>');
$this->state = self::DATA_STATE;
return $token;
}
@ -2137,7 +2137,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Emit the comment token. Reconsume the EOF
# character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'comment');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$this->data->unconsume();
return $token;
@ -2167,7 +2167,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Emit the comment token. Reconsume the EOF
# character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'comment');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$this->data->unconsume();
return $token;
@ -2198,7 +2198,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Emit the comment token. Reconsume the EOF
# character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'comment');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$this->data->unconsume();
return $token;
@ -2228,7 +2228,7 @@ class Tokenizer {
# "!" (U+0021)
elseif ($char === '!') {
# Parse error. Switch to the comment end bang state.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '!', 'comment end');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '!');
$this->state = self::COMMENT_END_BANG_STATE;
}
# "-" (U+002D)
@ -2239,7 +2239,7 @@ class Tokenizer {
// here every single time.
$char .= $this->data->consumeWhile('-');
for ($i = 0; $i < strlen($char); $i++) {
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '-', 'comment end');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '-');
}
$token->data .= $char;
@ -2248,7 +2248,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Emit the comment token. Reconsume the EOF
# character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'comment end');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$this->data->unconsume();
return $token;
@ -2257,7 +2257,7 @@ class Tokenizer {
else {
# Parse error. Append two "-" (U+002D) characters and the current input character
# to the comment token's data. Switch to the comment state.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char, 'comment end');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char);
$token->data .= '--'.$char;
$this->state = self::COMMENT_STATE;
}
@ -2287,7 +2287,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Emit the comment token. Reconsume the EOF
# character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'comment end');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$this->data->unconsume();
return $token;
@ -2324,7 +2324,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Create a new DOCTYPE token. Set its
# force-quirks flag to on. Emit the token. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'DOCTYPE');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$token = new DOCTYPEToken();
$token->forceQuirks = true;
@ -2334,7 +2334,7 @@ class Tokenizer {
# Anything else
else {
# Parse error. Switch to the before DOCTYPE name state. Reconsume the character.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char, 'DOCTYPE');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char);
$this->state = self::DOCTYPE_NAME_STATE;
$this->data->unconsume();
}
@ -2366,7 +2366,7 @@ class Tokenizer {
elseif ($char === '>') {
# Parse error. Create a new DOCTYPE token. Set its force-quirks flag to on. Switch
# to the data state. Emit the token.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>', 'DOCTYPE');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>');
$token = new DOCTYPEToken();
$token->forceQuirks = true;
$this->state = self::DATA_STATE;
@ -2376,7 +2376,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Create a new DOCTYPE token. Set its
# force-quirks flag to on. Emit the token. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'DOCTYPE');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$token = new DOCTYPEToken();
$token->forceQuirks = true;
@ -2428,7 +2428,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Set the DOCTYPE token's force-quirks flag
# to on. Emit that DOCTYPE token. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'DOCTYPE');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$token->forceQuirks = true;
$this->data->unconsume();
@ -2469,7 +2469,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Set the DOCTYPE token's force-quirks flag
# to on. Emit that DOCTYPE token. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'DOCTYPE name');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$token->forceQuirks = true;
$this->data->unconsume();
@ -2496,7 +2496,7 @@ class Tokenizer {
else {
// Need to unconsume what was consumed earlier.
$this->data->unconsume(5);
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char[0], 'DOCTYPE name');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char[0]);
$token->forceQuirks = true;
$this->state = self::BOGUS_DOCTYPE_STATE;
}
@ -2522,7 +2522,7 @@ class Tokenizer {
elseif ($char === '"') {
# Parse error. Set the DOCTYPE token's public identifier to the empty string (not
# missing), then switch to the DOCTYPE public identifier (double-quoted) state.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '"', 'DOCTYPE public keyword');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '"');
$token->public = '';
$this->state = self::DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED_STATE;
}
@ -2530,7 +2530,7 @@ class Tokenizer {
elseif ($char === "'") {
# Parse error. Set the DOCTYPE token's public identifier to the empty string (not
# missing), then switch to the DOCTYPE public identifier (single-quoted) state.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, "'", 'DOCTYPE public keyword');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, "'");
$token->public = '';
$this->state = self::DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED_STATE;
}
@ -2538,7 +2538,7 @@ class Tokenizer {
elseif ($char === '>') {
# Parse error. Set the DOCTYPE token's force-quirks flag to on. Switch to the data
# state. Emit that DOCTYPE token.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>', 'DOCTYPE public keyword');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>');
$token->forceQuirks = true;
$this->state = self::DATA_STATE;
return $token;
@ -2547,7 +2547,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Set the DOCTYPE token's force-quirks flag
# to on. Emit that DOCTYPE token. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'DOCTYPE public keyword');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$token->forceQuirks = true;
$this->data->unconsume();
@ -2557,7 +2557,7 @@ class Tokenizer {
else {
# Parse error. Set the DOCTYPE token's force-quirks flag to on. Switch to the
# bogus DOCTYPE state.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char, 'DOCTYPE public keyword');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char);
$token->forceQuirks = true;
$this->state = self::BOGUS_DOCTYPE_STATE;
}
@ -2595,7 +2595,7 @@ class Tokenizer {
elseif ($char === '>') {
# Parse error. Set the DOCTYPE token's force-quirks flag to on. Switch to the data
# state. Emit that DOCTYPE token.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>', 'DOCTYPE public identifier');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>');
$token->forceQuirks = true;
$this->state = self::DATA_STATE;
return $token;
@ -2604,7 +2604,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Set the DOCTYPE token's force-quirks flag
# to on. Emit that DOCTYPE token. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'DOCTYPE public identifier');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$token->forceQuirks = true;
$this->data->unconsume();
@ -2614,7 +2614,7 @@ class Tokenizer {
else {
# Parse error. Set the DOCTYPE token's force-quirks flag to on. Switch to the
# bogus DOCTYPE state.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char, 'DOCTYPE public identifier');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char);
$token->forceQuirks = true;
$this->state = self::BOGUS_DOCTYPE_STATE;
}
@ -2636,7 +2636,7 @@ class Tokenizer {
elseif ($char === '>') {
# Parse error. Set the DOCTYPE token's force-quirks flag to on. Switch to the data
# state. Emit that DOCTYPE token.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>', 'DOCTYPE public identifier');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>');
$token->forceQuirks = true;
$this->state = self::DATA_STATE;
return $token;
@ -2645,7 +2645,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Set the DOCTYPE token's force-quirks flag
# to on. Emit that DOCTYPE token. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'DOCTYPE public identifier');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$token->forceQuirks = true;
$this->data->unconsume();
@ -2677,7 +2677,7 @@ class Tokenizer {
elseif ($char === '>') {
# Parse error. Set the DOCTYPE token's force-quirks flag to on. Switch to the data
# state. Emit that DOCTYPE token.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>', 'DOCTYPE public identifier');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>');
$this->state = self::DATA_STATE;
return $token;
}
@ -2685,7 +2685,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Set the DOCTYPE token's force-quirks flag
# to on. Emit that DOCTYPE token. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'DOCTYPE public identifier');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$token->forceQuirks = true;
$this->data->unconsume();
@ -2740,7 +2740,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Set the DOCTYPE token's force-quirks flag
# to on. Emit that DOCTYPE token. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'DOCTYPE public identifier');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$token->forceQuirks = true;
$this->data->unconsume();
@ -2750,7 +2750,7 @@ class Tokenizer {
else {
# Parse error. Set the DOCTYPE token's force-quirks flag to on. Switch to the
# bogus DOCTYPE state.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char, 'DOCTYPE public identifier');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char);
$token->forceQuirks = true;
$this->state = self::BOGUS_DOCTYPE_STATE;
}
@ -2829,7 +2829,7 @@ class Tokenizer {
elseif ($char === '"') {
# Parse error. Set the DOCTYPE token's system identifier to the empty string (not
# missing), then switch to the DOCTYPE system identifier (double-quoted) state.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '"', 'DOCTYPE system keyword');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '"');
$token->system = '';
$this->state = self::DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED_STATE;
}
@ -2837,7 +2837,7 @@ class Tokenizer {
elseif ($char === "'") {
# Parse error. Set the DOCTYPE token's system identifier to the empty string (not
# missing), then switch to the DOCTYPE system identifier (single-quoted) state.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, "'", 'DOCTYPE system keyword');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, "'");
$token->system = '';
$this->state = self::DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED_STATE;
}
@ -2845,7 +2845,7 @@ class Tokenizer {
elseif ($char === '>') {
# Parse error. Set the DOCTYPE token's force-quirks flag to on. Switch to the data
# state. Emit that DOCTYPE token.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>', 'DOCTYPE system keyword');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>');
$token->forceQuirks = true;
$this->state = self::DATA_STATE;
return $token;
@ -2854,7 +2854,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Set the DOCTYPE token's force-quirks flag
# to on. Emit that DOCTYPE token. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'DOCTYPE system keyword');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$token->forceQuirks = true;
$this->data->unconsume();
@ -2864,7 +2864,7 @@ class Tokenizer {
else {
# Parse error. Set the DOCTYPE token's force-quirks flag to on. Switch to the
# bogus DOCTYPE state.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char, 'DOCTYPE system keyword');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char);
$token->forceQuirks = true;
$this->state = self::BOGUS_DOCTYPE_STATE;
}
@ -2902,7 +2902,7 @@ class Tokenizer {
elseif ($char === '>') {
# Parse error. Set the DOCTYPE token's force-quirks flag to on. Switch to the data
# state. Emit that DOCTYPE token.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>', 'DOCTYPE system identifier');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>');
$token->forceQuirks = true;
$this->state = self::DATA_STATE;
return $token;
@ -2911,7 +2911,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Set the DOCTYPE token's force-quirks flag
# to on. Emit that DOCTYPE token. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'DOCTYPE system identifier');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$token->forceQuirks = true;
$this->data->unconsume();
@ -2921,7 +2921,7 @@ class Tokenizer {
else {
# Parse error. Set the DOCTYPE token's force-quirks flag to on. Switch to the
# bogus DOCTYPE state.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char, 'DOCTYPE system identifier');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char);
$token->forceQuirks = true;
$this->state = self::BOGUS_DOCTYPE_STATE;
}
@ -2943,7 +2943,7 @@ class Tokenizer {
elseif ($char === '>') {
# Parse error. Set the DOCTYPE token's force-quirks flag to on. Switch to the data
# state. Emit that DOCTYPE token.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>', 'DOCTYPE system identifier');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>');
$this->state = self::DATA_STATE;
return $token;
}
@ -2951,7 +2951,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Set the DOCTYPE token's force-quirks flag
# to on. Emit that DOCTYPE token. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'DOCTYPE system identifier');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$token->forceQuirks = true;
$this->data->unconsume();
@ -2983,7 +2983,7 @@ class Tokenizer {
elseif ($char === '>') {
# Parse error. Set the DOCTYPE token's force-quirks flag to on. Switch to the data
# state. Emit that DOCTYPE token.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>', 'DOCTYPE system identifier');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, '>');
$this->state = self::DATA_STATE;
return $token;
}
@ -2991,7 +2991,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Set the DOCTYPE token's force-quirks flag
# to on. Emit that DOCTYPE token. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'DOCTYPE system identifier');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$token->forceQuirks = true;
$this->data->unconsume();
@ -3046,7 +3046,7 @@ class Tokenizer {
elseif ($char === '') {
# Parse error. Switch to the data state. Set the DOCTYPE token's force-quirks flag
# to on. Emit that DOCTYPE token. Reconsume the EOF character.
ParseError::trigger(ParseError::UNEXPECTED_EOF, 'DOCTYPE system identifier');
ParseError::trigger(ParseError::UNEXPECTED_EOF);
$this->state = self::DATA_STATE;
$token->forceQuirks = true;
$this->data->unconsume();
@ -3056,7 +3056,7 @@ class Tokenizer {
else {
# Parse error. Set the DOCTYPE token's force-quirks flag to on. Switch to the
# bogus DOCTYPE state.
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char, 'DOCTYPE system identifier');
ParseError::trigger(ParseError::UNEXPECTED_CHARACTER, $char);
$token->forceQuirks = true;
$this->state = self::BOGUS_DOCTYPE_STATE;
}

173
lib/TreeBuilder.php
View File

@ -385,16 +385,15 @@ class TreeBuilder {
// DEVIATION: There is no iframe srcdoc document because there are no nested
// browsing contexts in this implementation.
switch (get_class($token)) {
case 'StartTagToken': $errorType = ParseError::UNEXPECTED_START_TAG;
case 'StartTagToken': ParseError::trigger(ParseError::UNEXPECTED_START_TAG, $token->name);
break;
case 'EndTagToken': $errorType = ParseError::UNEXPECTED_END_TAG;
case 'EndTagToken': ParseError::trigger(ParseError::UNEXPECTED_END_TAG, $token->name);
break;
case 'EOFToken': $errorType = ParseError::UNEXPECTED_EOF;
case 'EOFToken': ParseError::trigger(ParseError::UNEXPECTED_EOF);
break;
default: throw new Exception(Exception::UNKNOWN_ERROR);
}
ParseError::trigger($errorType, 'doctype');
$this->quirksMode = self::QUIRKS_MODE_ON;
# In any case, switch the insertion mode to "before html", then reprocess the
@ -409,7 +408,7 @@ class TreeBuilder {
case self::BEFORE_HTML_MODE:
# A DOCTYPE token
if ($token instanceof DOCTYPEToken) {
ParseError::trigger(ParseError::UNEXPECTED_DOCTYPE, 'html start tag, comment');
ParseError::trigger(ParseError::UNEXPECTED_DOCTYPE);
}
# A comment token
elseif ($token instanceof CommentToken) {
@ -436,7 +435,7 @@ class TreeBuilder {
# Any other end tag
elseif ($token instanceof EndTagToken && $token->name !== 'head' && $token->name !== 'body' && $token->name !== 'html' && $token->name !== 'br') {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, $token->name, 'head, body, html, br end tag');
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, $token->name);
}
# An end tag whose tag name is one of: "head", "body", "html", "br"
# Anything else
@ -475,7 +474,7 @@ class TreeBuilder {
# A DOCTYPE token
elseif ($token instanceof DOCTYPEToken) {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_DOCTYPE, 'head tag');
ParseError::trigger(ParseError::UNEXPECTED_DOCTYPE);
}
elseif ($token instanceof StartTagToken) {
# A start tag whose tag name is "html"
@ -498,7 +497,7 @@ class TreeBuilder {
# Any other end tag
elseif ($token instanceof EndTagToken && $token->name !== 'head' && $token->name !== 'body' && $token->name !== 'html' && $token->name === 'br') {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, $token->name, 'head, body, html, br end tag');
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, $token->name);
}
# An end tag whose tag name is one of: "head", "body", "html", "br"
# Anything else
@ -535,7 +534,7 @@ class TreeBuilder {
# A DOCTYPE token
elseif ($token instanceof DOCTYPEToken) {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_DOCTYPE, 'head data');
ParseError::trigger(ParseError::UNEXPECTED_DOCTYPE);
}
elseif ($token instanceof StartTagToken) {
# A start tag whose tag name is "html"
@ -648,7 +647,7 @@ class TreeBuilder {
# A start tag whose tag name is "head"
elseif ($token->name === 'head') {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, 'head', 'base, basefont, bgsound, link, meta, title, noframes, style, noscript, script, template start tag');
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, 'head');
}
# Anything else
else {
@ -691,7 +690,7 @@ class TreeBuilder {
# If there is no template element on the stack of open elements, then this is a
# parse error; ignore the token.
if ($this->stack->search('template') === -1) {
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, 'template', (string)$this->stack.' end tag');
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, 'template');
}
# Otherwise, run these steps:
else {
@ -700,7 +699,7 @@ class TreeBuilder {
# 2. If the current node is not a template element, then this is a parse error.
if ($this->stack->currentNodeName !== 'template') {
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, 'template', (string)$this->stack.' end tag');
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, 'template');
}
# 3. Pop elements from the stack of open elements until a template element has been popped from the stack.
@ -721,7 +720,7 @@ class TreeBuilder {
# Any other end tag
else {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, $token->name, (string)$this->stack.' end tag');
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, $token->name);
}
}
# Anything else
@ -742,7 +741,7 @@ class TreeBuilder {
# DOCTYPE token
if ($token instanceof DOCTYPEToken) {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_DOCTYPE, 'head data');
ParseError::trigger(ParseError::UNEXPECTED_DOCTYPE);
}
elseif ($token instanceof StartTagToken) {
# A start tag whose tag name is "html"
@ -761,14 +760,14 @@ class TreeBuilder {
# A start tag whose tag name is one of: "head", "noscript"
elseif ($token->name === 'head' || $token->name === 'noscript') {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, $token->name, 'basefont, bgsound, link, meta, noframes, style start tag');
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, $token->name);
}
# Anything else
else {
# Act as described in the "anything else" entry below.
#
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, $token->name, 'basefont, bgsound, link, meta, noframes, style start tag');
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, $token->name);
# Pop the current node (which will be a noscript element) from the stack of open
# elements; the new current node will be a head element.
$this->stack->pop();
@ -793,7 +792,7 @@ class TreeBuilder {
# Act as described in the "anything else" entry below.
#
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, 'br', (string)$this->stack.' end tag');
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, 'br');
# Pop the current node (which will be a noscript element) from the stack of open
# elements; the new current node will be a head element.
$this->stack->pop();
@ -806,7 +805,7 @@ class TreeBuilder {
# Any other end tag
else {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, 'br', (string)$this->stack.' end tag');
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, 'br');
}
}
# A character token that is one of U+0009 CHARACTER TABULATION, U+000A LINE FEED
@ -823,7 +822,7 @@ class TreeBuilder {
# Anything else
else {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, 'br', (string)$this->stack.' end tag');
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, 'br');
# Pop the current node (which will be a noscript element) from the stack of open
# elements; the new current node will be a head element.
$this->stack->pop();
@ -853,7 +852,7 @@ class TreeBuilder {
# A DOCTYPE token
elseif ($token instanceof DOCTYPEToken) {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_DOCTYPE, 'body, frameset start tag');
ParseError::trigger(ParseError::UNEXPECTED_DOCTYPE);
}
elseif ($token instanceof StartTagToken) {
# A start tag whose tag name is "html"
@ -882,7 +881,7 @@ class TreeBuilder {
# "meta", "noframes", "script", "style", "template", "title"
elseif ($token->name === 'base' || $token->name === 'basefont' || $token->name === 'bgsound' || $token->name === 'link' || $token->name === 'meta' || $token->name === 'noframes' || $token->name === 'script' || $token->name === 'style' || $token->name === 'template' || $token->name === 'title') {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, $token->name, 'body, frameset start tag');
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, $token->name);
# Push the node pointed to by the head element pointer onto the stack of open elements.
$this->stack[] = $this->headElement;
# Process the token using the rules for the "in head" insertion mode.
@ -898,7 +897,7 @@ class TreeBuilder {
# A start tag whose tag name is "head"
elseif ($token->name === 'head') {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, 'head', 'body, frameset start tag');
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, 'head');
}
# Any other start tag
else {
@ -935,7 +934,7 @@ class TreeBuilder {
# Any other end tag
else {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, 'head', 'body, frameset end tag');
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, 'head');
}
}
# Anything else
@ -980,13 +979,13 @@ class TreeBuilder {
# A DOCTYPE token
elseif ($token instanceof DOCTYPEToken) {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_DOCTYPE, 'body content');
ParseError::trigger(ParseError::UNEXPECTED_DOCTYPE);
}
elseif ($token instanceof StartTagToken) {
# A start tag whose tag name is "html"
if ($token->name === 'html') {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, 'html', 'body content');
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, 'html');
# If there is a template element on the stack of open elements, then ignore the
# token.
if ($this->stack->search('template') === -1) {
@ -1011,7 +1010,7 @@ class TreeBuilder {
# A start tag whose tag name is "body"
elseif ($token->name === 'body') {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, 'body', 'body content');
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, 'body');
# If the second element on the stack of open elements is not a body element, if
# the stack of open elements has only one node on it, or if there is a template
# element on the stack of open elements, then ignore the token. (fragment case)
@ -1033,7 +1032,7 @@ class TreeBuilder {
# A start tag whose tag name is "frameset"
elseif ($token->name === 'frameset') {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, 'frameset', 'body content');
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, 'frameset');
# If the stack of open elements has only one node on it, or if the second
# element on the stack of open elements is not a body element, then ignore the
@ -1087,7 +1086,7 @@ class TreeBuilder {
$currentNodeName = $this->stack->currentNodeName;
$currentNodeNamespace = $this->stack->currentNodeNamespace;
if ($currentNodeNamespace === '' && ($currentNodeName === 'h1' || $currentNodeName === 'h2' || $currentNodeName === 'h3' || $currentNodeName === 'h4' || $currentNodeName === 'h5' || $currentNodeName === 'h6')) {
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, $token->name, $currentNodeName . ' content or end tag');
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, $token->name);
$this->stack->pop();
}
@ -1112,20 +1111,95 @@ class TreeBuilder {
# token and move on to the next one. (Newlines at the start of pre blocks are
# ignored as an authoring convenience.)
$nextToken = $this->tokenizer->createToken();
if ($token instanceof CharacterToken) {
if ($nextToken instanceof CharacterToken) {
// Character tokens in this implementation can have more than one character in
// them.
if (strlen($token->data) === 1 && $token->data === "\n") {
if (strlen($nextToken->data) === 1 && $nextToken->data === "\n") {
return true;
} elseif (strpos($token->data, "\n") === 0) {
$token->data = substr($token->data, 1);
} elseif (strpos($nextToken->data, "\n") === 0) {
$nextToken->data = substr($nextToken->data, 1);
}
}
// Process the next token
// Process the next token
$token = $nextToken;
continue 2;
}
# A start tag whose tag name is "form"
elseif ($token->name === 'form') {
# If the form element pointer is not null, and there is no template element on
# the stack of open elements, then this is a parse error; ignore the token.
$templateInStack = ($this->stack->search('template') !== -1);
if (!is_null($this->formElement) && !$templateInStack) {
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, $token->name);
}
# Otherwise:
else {
# If the stack of open elements has a p element in button scope, then close a p
# element.
if ($this->stack->hasElementInButtonScope('p')) {
$this->closePElement();
}
# Insert an HTML element for the token, and, if there is no template element on
# the stack of open elements, set the form element pointer to point to the
# element created.
$form = $this->insertStartTagToken($token);
if ($templateInStack) {
$this->formElement = $form;
}
}
}
# A start tag whose tag name is "li"
elseif ($token->name === 'li') {
# 1. Set the frameset-ok flag to "not ok".
$this->framesetOk = false;
# 2. Initialize node to be the current node (the bottommost node of the stack).
# 3. Loop: If node is an li element, then run these substeps:
for ($i = $this->stack->length - 1; $i >= 0; $i--) {
$node = $this->stack[$i];
$nodeName = $node->nodeName;
if ($nodeName === 'li') {
# 1. Generate implied end tags, except for li elements.
$this->stack->generateImpliedEndTags('li');
# 2. If the current node is not an li element, then this is a parse error.
$currentNodeName = $this->stack->currentNodeName;
if ($currentNodeName !== 'li') {
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, $currentNodeName);
}
# 3. Pop elements from the stack of open elements until an li element has been
# popped from the stack.
do {
$poppedNodeName = $this->stack->pop()->nodeName;
} while ($poppedNodeName !== 'li');
# 4. Jump to the step labeled Done below.
break;
}
# 4. If node is in the special category, but is not an address, div, or p
# element, then jump to the step labeled Done below.
elseif ($nodeName !== 'address' && $nodeName !== 'div' && $nodeName !== 'p' && $this->isElementSpecial($node)) {
break;
}
# 5. Otherwise, set node to the previous entry in the stack of open elements and
# return to the step labeled Loop.
// The loop handles that.
}
# 6. Done: If the stack of open elements has a p element in button scope, then
# close a p element.
if ($this->stack->hasElementInButtonScope('p')) {
$this->closePElement();
}
# 7. Finally, insert an HTML element for the token.
$this->insertStartTagToken($token);
}
}
elseif ($token instanceof EndTagToken) {
# An end tag whose tag name is "template"
@ -1140,7 +1214,7 @@ class TreeBuilder {
# If the stack of open elements does not have a body element in scope, this is a
# parse error; ignore the token.
if ($this->stack->search('body') === -1) {
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, 'body', (string)$this->stack.' end tag');
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, 'body');
}
# Otherwise, if there is a node in the stack of open elements that is not either
# a dd element, a dt element, an li element, an optgroup element, an option
@ -1157,7 +1231,7 @@ class TreeBuilder {
return false;
}) !== -1) {
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, 'body', (string)$this->stack.' end tag');
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, 'body');
break;
}
@ -1195,7 +1269,7 @@ class TreeBuilder {
return false;
}) !== -1) {
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, 'body', (string)$this->stack.' end tag');
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, 'body');
break;
}
@ -1246,7 +1320,7 @@ class TreeBuilder {
# A DOCTYPE token
elseif ($token instanceof DOCTYPEToken) {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_DOCTYPE, 'Character, Comment, Start Tag, or End Tag');
ParseError::trigger(ParseError::UNEXPECTED_DOCTYPE);
}
elseif ($token instanceof StartTagToken) {
# A start tag whose tag name is one of: "b", "big", "blockquote", "body", "br",
@ -1263,7 +1337,7 @@ class TreeBuilder {
)
) {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, $token->name, 'Non-HTML start tag');
ParseError::trigger(ParseError::UNEXPECTED_START_TAG, $token->name);
# If the parser was originally created for the HTML fragment parsing algorithm,
# then act as described in the "any other start tag" entry below. (fragment
@ -1586,7 +1660,7 @@ class TreeBuilder {
# 2. If node is not an element with the same tag name as the token, then this is
# a parse error.
if ($nodeName !== $token->name) {
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, $token->name, "$nodeName end tag");
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, $token->name);
}
# 3. Loop: If node's tag name, converted to ASCII lowercase, is the same as the
# tag name of the token, pop elements from the stack of open elements until node
@ -1783,7 +1857,7 @@ class TreeBuilder {
}
}
public static function insertStartTagToken(StartTagToken $token, \DOMNode $intendedParent = null, string $namespace = null) {
public static function insertStartTagToken(StartTagToken $token, \DOMNode $intendedParent = null, string $namespace = null): Element {
if (!is_null($namespace)) {
$namespace = $token->namespace;
}
@ -2094,7 +2168,7 @@ class TreeBuilder {
# 2. If the current node is not a p element, then this is a parse error.
$currentNodeName = $this->stack->currentNodeName;
if ($currentNodeName !== 'p') {
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, $currentNodeName, (string)$this->stack . ' end tag');
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, $currentNodeName);
}
# 3. Pop elements from the stack of open elements until a p element has been
# popped from the stack.
@ -2102,4 +2176,21 @@ class TreeBuilder {
$poppedNodeName = $this->stack->pop()->nodeName;
} while ($poppedNodeName !== 'p');
}
protected function isElementSpecial(Element $element): bool {
$name = $element->nodeName;
$ns = $element->namespaceURI;
# The following elements have varying levels of special parsing rules: HTML’s
# address, applet, area, article, aside, base, basefont, bgsound, blockquote,
# body, br, button, caption, center, col, colgroup, dd, details, dir, div, dl,
# dt, embed, fieldset, figcaption, figure, footer, form, frame, frameset, h1,
# h2, h3, h4, h5, h6, head, header, hr, html, iframe, img, input, li, link,
# listing, main, marquee, meta, nav, noembed, noframes, noscript, object, ol, p,
# param, plaintext, pre, script, section, select, source, style, summary, table,
# tbody, td, template, textarea, tfoot, th, thead, title, tr, track, ul, wbr,
# xmp; MathML mi, MathML mo, MathML mn, MathML ms, MathML mtext, and MathML
# annotation-xml; and SVG foreignObject, SVG desc, and SVG title.
return (($ns === '' && ($name === 'address' || $name === 'applet' || $name === 'area' || $name === 'article' || $name === 'aside' || $name === 'base' || $name === 'basefont' || $name === 'bgsound' || $name === 'blockquote' || $name === 'body' || $name === 'br' || $name === 'button' || $name === 'caption' || $name === 'center' || $name === 'col' || $name === 'colgroup' || $name === 'dd' || $name === 'details' || $name === 'dir' || $name === 'div' || $name === 'dl' || $name === 'dt' || $name === 'embed' || $name === 'fieldset' || $name === 'figcaption' || $name === 'figure' || $name === 'footer' || $name === 'form' || $name === 'frame' || $name === 'frameset' || $name === 'h1' || $name === 'h2' || $name === 'h3' || $name === 'h4' || $name === 'h5' || $name === 'h6' || $name === 'head' || $name === 'header' || $name === 'hr' || $name === 'html' || $name === 'iframe' || $name === 'img' || $name === 'input' || $name === 'li' || $name === 'link' || $name === 'listing' || $name === 'main' || $name === 'marquee' || $name === 'meta' || $name === 'nav' || $name === 'noembed' || $name === 'noframes' || $name === 'noscript' || $name === 'object' || $name === 'ol' || $name === 'p' || $name === 'param' || $name === 'plaintext' || $name === 'pre' || $name === 'script' || $name === 'section' || $name === 'select' || $name === 'source' || $name === 'style' || $name === 'summary' || $name === 'table' || $name === 'tbody' || $name === 'td' || $name === 'template' || $name === 'textarea' || $name === 'tfoot' || $name === 'th' || $name === 'thead' || $name === 'title' || $name === 'tr' || $name === 'track' || $name === 'ul' || $name === 'wbr' || $name === 'xmp')) || ($ns === Parser::MATHML_NAMESPACE && ($name === 'mi' || $name === 'mo' || $name === 'mn' || $name === 'ms' || $name === 'mtext' || $name === 'annotation-xml')) || ($ns === Parser::SVG_NAMESPACE && ($name === 'foreignObject' || $name === 'desc' || $name === 'title'));
}
}
Write Preview
Loading…
Cancel
Save