MensBeam/HTML-Parser
3
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

Started HTML content tree building

Browse source 
• Removed html5.php; shouldn't have been there to begin with.
• Fixed bug where when feeding ParseError::trigger the wrong number of parameters it wouldn't have the correct exception to throw.
This commit is contained in:
Dustin Wilson 2018-07-26 16:30:29 -05:00
parent de7cc7cbfa
commit 1fc65f85bd
5 changed files with 406 additions and 109 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
.gitignore vendored
View file

@ -1,3 +1,6 @@
# html5-parser specific
test.php
# General
*.DS_Store
.AppleDouble

8
html5.php
View file

@ -1,8 +0,0 @@
#!/usr/bin/env php
<?php
namespace dW\HTML5;
require_once 'vendor/autoload.php';
Parser::$debug = true;
var_export(Parser::parse('<!DOCTYPE HtMl'));

2
lib/ParseError.php
View file

@ -61,7 +61,7 @@ class ParseError {
$count = substr_count($message, '%s');
// If the number of replacements don't match the arguments then oops.
if (count($args) !== $count) {
throw new Exception(static::INCORRECT_PARAMETERS_FOR_MESSAGE, $count);
throw new Exception(Exception::INCORRECT_PARAMETERS_FOR_MESSAGE, $count);
}
if ($count > 0) {

492
lib/Parser.php
View file

@ -18,6 +18,9 @@ class Parser {
// with forms in the face of dramatically bad markup, for historical reasons. It is
// ignored inside template elements
public $formElement;
// Flag for determining whether to use the foster parenting (badly nested table
// elements) algorithm.
public $fosterParenting = false;
// Flag that shows whether the content that's being parsed is a fragment or not
public $fragmentCase = false;
// Flag used to determine whether elements are okay to be used in framesets or not
@ -172,6 +175,12 @@ class Parser {
static::$self = new $c;
}
// Create the document if it doesn't already exist. Will be overwritten if there is a DOCTYPE.
if (is_null(static::$self->DOM)) {
$imp = new \DOMImplementation;
static::$self->DOM = $imp->createDocument();
}
// Process the input stream.
static::$self->data = new DataStream(($file === true) ? '' : $data, ($file === true) ? $data : 'STDIN');
@ -180,8 +189,7 @@ class Parser {
setlocale(LC_CTYPE, 'en_US.UTF8');
static::$self->tokenize();
//return static::$self->fixDOM();
return static::$self->DOM;
return static::$self->fixDOM();
}
public static function parseFragment(string $data, \DOMDocument $dom = null, \DOMElement $context = null, bool $file = false): \DOMDocument {
@ -199,7 +207,7 @@ class Parser {
if (!is_null($dom)) {
static::$self->DOM = $dom;
} else {
$imp = new DOMImplementation;
$imp = new \DOMImplementation;
static::$self->DOM = $imp->createDocument();
}
@ -234,16 +242,17 @@ class Parser {
}
// DEVIATION: Since this implementation uses a DOMDocumentFragment for insertion
// there is no need to create an html element for inserting stuff into. If the
// context element is a template element, push "in template" onto the stack of
// template insertion modes so that it is the new current template insertion
// mode.
// there is no need to create an html element for inserting stuff into.
# If the context element is a template element, push "in template" onto the
# stack of template insertion modes so that it is the new current template
# insertion mode.
// FIX ME: I am not sure this is needed without scripting.
if ($name === 'template') {
static::$self->templateInsertionModeStack[] = static::IN_TEMPLATE_MODE;
}
# Reset the parser's insertion mode appropriately.
// DEVIATION: The insertion mode will be always 'in body', not 'before head' if
// there isn't a context. There isn't a need to reconstruct a valid HTML
// document when using a DOMDocumentFragment.
@ -3243,70 +3252,354 @@ class Parser {
}
protected function emitToken(Token $token) {
$adjustedCurrentNode = $this->stack->adjustedCurrentNode;
$adjustedCurrentNodeName = $this->stack->adjustedCurrentNodeName;
$adjustedCurrentNodeNamespace = $this->stack->adjustedCurrentNodeNamespace;
// Loop used for reprocessing.
while (true) {
$adjustedCurrentNode = $this->stack->adjustedCurrentNode;
$adjustedCurrentNodeName = $this->stack->adjustedCurrentNodeName;
$adjustedCurrentNodeNamespace = $this->stack->adjustedCurrentNodeNamespace;
# 8.2.5 Tree construction
#
# As each token is emitted from the tokenizer, the user agent must follow the
# appropriate steps from the following list, known as the tree construction dispatcher:
#
# If the stack of open elements is empty
if ($this->stack->length === 0 ||
# If the adjusted current node is an element in the HTML namespace
$adjustedCurrentNodeNamespace === static::HTML_NAMESPACE || (
# If the adjusted current node is a MathML text integration point and the token is a
# start tag whose tag name is neither "mglyph" nor "malignmark"
# If the adjusted current node is a MathML text integration point and the token is a
# character token
DOM::isMathMLTextIntegrationPoint($adjustedCurrentNode) && ((
$token instanceof StartTagToken && (
$token->name !== 'mglyph' && $token->name !== 'malignmark'
) ||
$token instanceof CharacterToken
# 8.2.5 Tree construction
#
# As each token is emitted from the tokenizer, the user agent must follow the
# appropriate steps from the following list, known as the tree construction dispatcher:
#
# If the stack of open elements is empty
if ($this->stack->length === 0 ||
# If the adjusted current node is an element in the HTML namespace
$adjustedCurrentNodeNamespace === static::HTML_NAMESPACE || (
# If the adjusted current node is a MathML text integration point and the token is a
# start tag whose tag name is neither "mglyph" nor "malignmark"
# If the adjusted current node is a MathML text integration point and the token is a
# character token
DOM::isMathMLTextIntegrationPoint($adjustedCurrentNode) && ((
$token instanceof StartTagToken && (
$token->name !== 'mglyph' && $token->name !== 'malignmark'
) ||
$token instanceof CharacterToken
)
)
)
) || (
# If the adjusted current node is an annotation-xml element in the MathML namespace and
# the token is a start tag whose tag name is "svg"
$adjustedCurrentNodeNamespace === static::MATHML_NAMESPACE &&
$adjustedCurrentNodeName === 'annotation-xml' &&
$token instanceof StartTagToken &&
$token->name === 'svg'
) || (
# If the adjusted current node is an HTML integration point and the token is a start tag
# If the adjusted current node is an HTML integration point and the token is a character
# token
DOM::isHTMLIntegrationPoint($adjustedCurrentNode) && (
$token instanceof StartTagToken || $token instanceof CharacterToken
)
) ||
# If the token is an end-of-file token
$token instanceof EOFToken) {
# Process the token according to the rules given in the section corresponding to
# the current insertion mode in HTML content.
$this->parseTokenInHTMLContent($token);
}
# Otherwise
else {
# Process the token according to the rules given in the section for parsing tokens in foreign content.
$this->parseTokenInForeignContent($token);
}
) || (
# If the adjusted current node is an annotation-xml element in the MathML namespace and
# the token is a start tag whose tag name is "svg"
$adjustedCurrentNodeNamespace === static::MATHML_NAMESPACE &&
$adjustedCurrentNodeName === 'annotation-xml' &&
$token instanceof StartTagToken &&
$token->name === 'svg'
) || (
# If the adjusted current node is an HTML integration point and the token is a start tag
# If the adjusted current node is an HTML integration point and the token is a character
# token
DOM::isHTMLIntegrationPoint($adjustedCurrentNode) && (
$token instanceof StartTagToken || $token instanceof CharacterToken
)
) ||
# If the token is an end-of-file token
$token instanceof EOFToken) {
# Process the token according to the rules given in the section corresponding to
# the current insertion mode in HTML content.
// Returns false when needing to reprocess.
if ($this->parseTokenInHTMLContent($token) === false) {
continue;
}
}
# Otherwise
else {
# Process the token according to the rules given in the section for parsing
# tokens in foreign content.
// Returns false when needing to reprocess.
if ($this->parseTokenInForeignContent($token) === false) {
continue;
}
}
# TEMPORARY
var_export($token);
echo "\n\n";
# TEMPORARY
var_export($token);
echo "\n\n";
if ($token instanceof StartTagToken && !$token->selfClosing) {
$this->stack[] = $token;
} elseif ($token instanceof EndTagToken) {
$this->stack->pop();
break;
}
}
protected function parseTokenInHTMLContent(Token $token, int $insertionMode = null) {
$insertionMode = (is_null($insertionMode)) ? $this->insertionMode : $insertionMode;
// Loop used when processing the token under different rules; always breaks.
while (true) {
# 8.2.5.4. The rules for parsing tokens in HTML content
switch ($insertionMode) {
# 8.2.5.4.1. The "initial" insertion mode
case static::INITIAL_MODE:
# A character token that is one of U+0009 CHARACTER TABULATION, U+000A LINE FEED
# (LF), U+000C FORM FEED (FF), U+000D CARRIAGE RETURN (CR), or U+0020 SPACE
// OPTIMIZATION: Will check for multiple space characters at once as character
// tokens can contain more than one character.
if ($token instanceof CharacterToken && (strspn($token->data, "\t\n\x0c\x0d ") !== strlen($token->data))) {
# Ignore the token.
return;
}
# A comment token
elseif ($token instanceof CommentToken) {
# Insert a comment as the last child of the Document object.
// DEVIATION: PHP's DOM cannot have comments before the DOCTYPE, so just going
// to ignore them instead.
//$this->insertCommentToken($token, $this->$DOM);
return;
}
# A DOCTYPE token
elseif ($token instanceof DOCTYPEToken) {
# If the DOCTYPE token’s name is not a case-sensitive match for the string
# "html", or the token’s public identifier is not missing, or the token’s system
# identifier is neither missing nor a case-sensitive match for the string
# "about:legacy-compat", then there is a parse error.
if ($token->name !== 'html' || !is_null($token->public) || (!is_null($token->system) && $token->system !== 'about:legacy-compat')) {
ParseError::trigger(ParseError::INVALID_DOCTYPE, $this->data);
}
# Append a DocumentType node to the Document node, with the name attribute set
# to the name given in the DOCTYPE token, or the empty string if the name was
# missing; the publicId attribute set to the public identifier given in the
# DOCTYPE token, or the empty string if the public identifier was missing; the
# systemId attribute set to the system identifier given in the DOCTYPE token, or
# the empty string if the system identifier was missing; and the other
# attributes specific to DocumentType objects set to null and empty lists as
# appropriate. Associate the DocumentType node with the Document object so that
# it is returned as the value of the doctype attribute of the Document object.
// PHP's DOM cannot just append a DOCTYPE node to the document, so a document is
// created with the specified DOCTYPE instead.
$imp = new \DOMImplementation();
// DEVIATION: PHP's DOMImplementation::createDocumentType() method cannot accept
// an empty name, so if it is missing it is replaced with 'html' instead.
$this->DOM = $imp->createDocument('', '', $imp->createDocumentType((!is_null($token->name)) ? $token->name : 'html', $token->public, $token->system));
$public = strtolower((string)$token->public);
# Then, if the document is not an iframe srcdoc document, and the DOCTYPE token
# matches one of the conditions in the following list, then set the Document to
# quirks mode:
// DEVIATION: This implementation does not render, so there is no nested
// browsing contexts to consider.
if ($token->forceQuirks === true || $token->name !== 'html' ||
$public === '-//w3o//dtd w3 html strict 3.0//en//' ||
$public === '-/w3c/dtd html 4.0 transitional/en' ||
$public === 'html' ||
strtolower($token->system) === 'http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd' ||
strpos($public, '+//silmaril//dtd html pro v0r11 19970101//') === 0 ||
strpos($public, '-//as//dtd html 3.0 aswedit + extensions//') === 0 ||
strpos($public, '+//silmaril//dtd html pro v0r11 19970101//') === 0 ||
strpos($public, '-//as//dtd html 3.0 aswedit + extensions//') === 0 ||
strpos($public, '-//advasoft ltd//dtd html 3.0 aswedit + extensions//') === 0 ||
strpos($public, '-//ietf//dtd html 2.0 level 1//') === 0 ||
strpos($public, '-//ietf//dtd html 2.0 level 2//') === 0 ||
strpos($public, '-//ietf//dtd html 2.0 strict level 1//') === 0 ||
strpos($public, '-//ietf//dtd html 2.0 strict level 2//') === 0 ||
strpos($public, '-//ietf//dtd html 2.0 strict//') === 0 ||
strpos($public, '-//ietf//dtd html 2.0//') === 0 ||
strpos($public, '-//ietf//dtd html 2.1e//') === 0 ||
strpos($public, '-//ietf//dtd html 3.0//') === 0 ||
strpos($public, '-//ietf//dtd html 3.2 final//') === 0 ||
strpos($public, '-//ietf//dtd html 3.2//') === 0 ||
strpos($public, '-//ietf//dtd html 3//') === 0 ||
strpos($public, '-//ietf//dtd html level 0//') === 0 ||
strpos($public, '-//ietf//dtd html level 1//') === 0 ||
strpos($public, '-//ietf//dtd html level 2//') === 0 ||
strpos($public, '-//ietf//dtd html level 3//') === 0 ||
strpos($public, '-//ietf//dtd html strict level 0//') === 0 ||
strpos($public, '-//ietf//dtd html strict level 1//') === 0 ||
strpos($public, '-//ietf//dtd html strict level 2//') === 0 ||
strpos($public, '-//ietf//dtd html strict level 3//') === 0 ||
strpos($public, '-//ietf//dtd html strict//') === 0 ||
strpos($public, '-//ietf//dtd html//') === 0 ||
strpos($public, '-//metrius//dtd metrius presentational//') === 0 ||
strpos($public, '-//microsoft//dtd internet explorer 2.0 html strict//') === 0 ||
strpos($public, '-//microsoft//dtd internet explorer 2.0 html//') === 0 ||
strpos($public, '-//microsoft//dtd internet explorer 2.0 tables//') === 0 ||
strpos($public, '-//microsoft//dtd internet explorer 3.0 html strict//') === 0 ||
strpos($public, '-//microsoft//dtd internet explorer 3.0 html//') === 0 ||
strpos($public, '-//microsoft//dtd internet explorer 3.0 tables//') === 0 ||
strpos($public, '-//netscape comm. corp.//dtd html//') === 0 ||
strpos($public, '-//netscape comm. corp.//dtd strict html//') === 0 ||
strpos($public, '-//o\'reilly and associates//dtd html 2.0//') === 0 ||
strpos($public, '-//o\'reilly and associates//dtd html extended 1.0//') === 0 ||
strpos($public, '-//o\'reilly and associates//dtd html extended relaxed 1.0//') === 0 ||
strpos($public, '-//sq//dtd html 2.0 hotmetal + extensions//') === 0 ||
strpos($public, '-//softquad software//dtd hotmetal pro 6.0::19990601::extensions to html 4.0//') === 0 ||
strpos($public, '-//softquad//dtd hotmetal pro 4.0::19971010::extensions to html 4.0//') === 0 ||
strpos($public, '-//spyglass//dtd html 2.0 extended//') === 0 ||
strpos($public, '-//sun microsystems corp.//dtd hotjava html//') === 0 ||
strpos($public, '-//sun microsystems corp.//dtd hotjava strict html//') === 0 ||
strpos($public, '-//w3c//dtd html 3 1995-03-24//') === 0 ||
strpos($public, '-//w3c//dtd html 3.2 draft//') === 0 ||
strpos($public, '-//w3c//dtd html 3.2 final//') === 0 ||
strpos($public, '-//w3c//dtd html 3.2//') === 0 ||
strpos($public, '-//w3c//dtd html 3.2s draft//') === 0 ||
strpos($public, '-//w3c//dtd html 4.0 frameset//') === 0 ||
strpos($public, '-//w3c//dtd html 4.0 transitional//') === 0 ||
strpos($public, '-//w3c//dtd html experimental 19960712//') === 0 ||
strpos($public, '-//w3c//dtd html experimental 970421//') === 0 ||
strpos($public, '-//w3c//dtd w3 html//') === 0 ||
strpos($public, '-//w3o//dtd w3 html 3.0//') === 0 ||
strpos($public, '-//webtechs//dtd mozilla html 2.0//') === 0 ||
strpos($public, '-//webtechs//dtd mozilla html//') === 0 ||
(is_null($token->system) &&
(strpos($public, '-//w3c//dtd html 4.01 frameset//') === 0 ||
strpos($public, '-//w3c//dtd html 4.01 transitional//') === 0))) {
$this->quirksMode = true;
}
# Otherwise, if the document is not an iframe srcdoc document, and the DOCTYPE
# token matches one of the conditions in the following list, then set the
# Document to limited-quirks mode:
// DEVIATION: There is no iframe srcdoc document because there are no nested
// browsing contexts in this implementation.
else {
if (strpos($public, '-//w3c//dtd xhtml 1.0 frameset//') === 0 ||
strpos($public, '-//w3c//dtd xhtml 1.0 transitional//') === 0 ||
(!is_null($token->system) &&
(strpos($public, '-//w3c//dtd html 4.01 frameset//') === 0 ||
strpos($public, '-//w3c//dtd html 4.01 transitional//') === 0))) {
$this->quirksMode = 'limited';
}
}
# The system identifier and public identifier strings must be compared to the
# values given in the lists above in an ASCII case-insensitive manner. A system
# identifier whose value is the empty string is not considered missing for the
# purposes of the conditions above.
# Then, switch the insertion mode to "before html".
$this->insertionMode = static::BEFORE_HTML_MODE;
}
# Anything else
else {
# If the document is not an iframe srcdoc document, then this is a parse error;
# set the Document to quirks mode.
// DEVIATION: There is no iframe srcdoc document because there are no nested
// browsing contexts in this implementation.
$this->quirksMode = true;
# In any case, switch the insertion mode to "before html", then reprocess the
# token.
$this->insertionMode = static::BEFORE_HTML_MODE;
return false;
}
break;
# 8.2.5.4.2. The "before html" insertion mode
case static::BEFORE_HTML_MODE:
# A DOCTYPE token
if ($token instanceof DOCTYPEToken) {
ParseError::trigger(ParseError::UNEXPECTED_DOCTYPE, $this->data, '');
}
# A comment token
elseif ($token instanceof CommentToken) {
# Insert a comment as the last child of the Document object.
$this->insertCommentToken($token, $this->$DOM);
}
# A character token that is one of U+0009 CHARACTER TABULATION, U+000A LINE FEED
# (LF), U+000C FORM FEED (FF), U+000D CARRIAGE RETURN (CR), or U+0020 SPACE
// OPTIMIZATION: Will check for multiple space characters at once as character
// tokens can contain more than one character.
elseif ($token instanceof CharacterToken && (strspn($token->data, "\t\n\x0c\x0d ") !== strlen($token->data))) {
# Ignore the token.
return;
}
# A start tag whose tag name is "html"
elseif ($token instanceof StartTagToken && $token->name === 'html') {
# Create an element for the token in the HTML namespace, with the Document as
# the intended parent. Append it to the Document object. Put this element in the
# stack of open elements.
$element = $this->createElement($token);
$this->DOM->appendChild($element);
$this->stack[] = $element;
# Switch the insertion mode to "before head".
$this->insertionMode = static::BEFORE_HEAD_MODE;
}
# Any other end tag
elseif ($token instanceof EndTagToken && $token->name !== 'head' && $token->name !== 'body' && $token->name !== 'html' && $token->name !== 'br') {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, $this->data, $token->name, 'head, body, html, or br tag');
}
# An end tag whose tag name is one of: "head", "body", "html", "br"
# Anything else
else {
# Create an html element whose node document is the Document object. Append it
# to the Document object. Put this element in the stack of open elements.
$element = $this->DOM->createElement('html');
$this->DOM->appendChild($element);
$this->stack[] = $element;
# Switch the insertion mode to "before head", then reprocess the token.
$this->insertionMode = static::BEFORE_HEAD_MODE;
return false;
}
# The document element can end up being removed from the Document object, e.g.,
# by scripts; nothing in particular happens in such cases, content continues
# being appended to the nodes as described in the next section.
// Good to know. There's no scripting in this implementation, though.
break;
# 8.2.5.4.3. The "before head" insertion mode
case static::BEFORE_HEAD_MODE:
# A character token that is one of U+0009 CHARACTER TABULATION, U+000A LINE FEED
# (LF), U+000C FORM FEED (FF), U+000D CARRIAGE RETURN (CR), or U+0020 SPACE
if ($token instanceof CharacterToken && (strspn($token->data, "\t\n\x0c\x0d ") !== strlen($token->data))) {
# Ignore the token.
return;
}
# A comment token
elseif ($token instanceof CommentToken) {
$this->insertCommentToken($token);
}
# A DOCTYPE token
elseif ($token instanceof DOCTYPEToken) {
ParseError::trigger(ParseError::UNEXPECTED_DOCTYPE, $this->data, '');
}
elseif ($token instanceof StartTagToken) {
# A start tag whose tag name is "html"
if ($token->name === 'html') {
# Process the token using the rules for the "in body" insertion mode.
$insertionMode = static::IN_BODY_MODE;
continue 2;
}
# A start tag whose tag name is "head"
elseif ($token->name === 'head') {
# Insert an HTML element for the token.
$element = $this->createElement($token);
$this->insertElement($element);
# Set the head element pointer to the newly created head element.
$this->headElement = $element;
# Switch the insertion mode to "in head".
$this->insertionMode = static::IN_HEAD_MODE;
}
}
# Any other end tag
elseif ($token instanceof EndTagToken && $token->name !== 'head' && $token->name !== 'body' && $token->name !== 'html' && $token->name === 'br') {
# Parse error.
ParseError::trigger(ParseError::UNEXPECTED_END_TAG, $this->data, $token->name, 'head, body, html, or br tag');
}
# An end tag whose tag name is one of: "head", "body", "html", "br"
# Anything else
else {
# Insert an HTML element for a "head" start tag token with no attributes.
$element = $this->createElement(new StartTagToken('head'));
$this->insertElement($element);
# Set the head element pointer to the newly created head element.
$this->headElement = $element;
# Switch the insertion mode to "in head".
$this->insertionMode = static::IN_HEAD_MODE;
# Reprocess the current token.
return false;
}
break;
}
break;
}
}
protected function parseTokenInForeignContent(Token $token) {
@ -3330,12 +3623,12 @@ class Parser {
}
# Insert the token's character.
$this->insertTextNode($token);
$this->insertCharacterToken($token);
}
# A comment token
elseif ($token instanceof CommentToken) {
# Insert a comment.
$this->insertCommentNode($token);
$this->insertCommentToken($token);
}
# A DOCTYPE token
elseif ($token instanceof DOCTYPEToken) {
@ -3383,7 +3676,7 @@ class Parser {
);
# Then, reprocess the token.
$this->emitToken($token);
return false;
}
# Any other start tag
else {
@ -3644,7 +3937,7 @@ class Parser {
# Insert a foreign element for the token, in the same namespace as the adjusted
# current node.
$this->createAndInsertElement($token, $adjustedCurrentNode->namespaceURI);
$this->createAndInsertElement($token, null, $adjustedCurrentNode->namespaceURI);
# If the token has its self-closing flag set, then run the appropriate steps
# from the following list:
@ -3667,7 +3960,6 @@ class Parser {
// aren't processed differently.
# Any other end tag
// ¡STOPPED HERE!
elseif ($token instanceof EndTagToken) {
# Run these steps:
#
@ -3710,7 +4002,7 @@ class Parser {
}
}
protected function appropriatePlaceForInsertingNode(Token $token, \DOMElement $overrideTarget = null) {
protected function appropriatePlaceForInsertingNode(\DOMNode $overrideTarget = null) {
$insertBefore = false;
# 8.2.5.1. Creating and inserting nodes
@ -3799,7 +4091,7 @@ class Parser {
];
}
protected function insertTextNode(CharacterToken $token) {
protected function insertCharacterToken(CharacterToken $token) {
# 1. Let data be the characters passed to the algorithm, or, if no characters
# were explicitly specified, the character of the character token being
# processed.
@ -3807,7 +4099,7 @@ class Parser {
# 2. Let the adjusted insertion location be the appropriate place for inserting
# a node.
$location = $this->appropriatePlaceForInsertingNode($token);
$location = $this->appropriatePlaceForInsertingNode();
$adjustedInsertionLocation = $location['node'];
$insertBefore = $location['insert before'];
@ -3838,7 +4130,7 @@ class Parser {
}
}
protected function insertCommentNode(CommentToken $token, DOMNode $position = null) {
protected function insertCommentToken(CommentToken $token, \DOMNode $position = null) {
# When the steps below require the user agent to insert a comment while
# processing a comment token, optionally with an explicitly insertion position
# position, the user agent must run the following steps:
@ -3853,7 +4145,7 @@ class Parser {
$adjustedInsertionLocation = $position;
$insertBefore = false;
} else {
$location = $this->appropriatePlaceForInsertingNode($token);
$location = $this->appropriatePlaceForInsertingNode();
$adjustedInsertionLocation = $location['node'];
$insertBefore = $location['insert before'];
}
@ -3871,12 +4163,7 @@ class Parser {
}
}
protected function createAndInsertElement(StartTagToken $token, string $namespace = null) {
$location = $this->appropriatePlaceForInsertingNode($token);
$adjustedInsertionLocation = $location['node'];
$insertBefore = $location['insert before'];
$intendedParent = ($insertBefore === false) ? $adjustedInsertionLocation : $adjustedInsertionLocation->parentNode;
protected function createElement(StartTagToken $token, string $namespace = null) {
if (!is_null($namespace)) {
$token->namespace = $namespace;
}
@ -3886,22 +4173,25 @@ class Parser {
# run the following steps:
# 1. Let document be intended parent’s node document.
$document = $intendedParent['location']->ownerDocument;
// DEVIATION: Unnecessary because there aren't any nested contexts to consider.
// The document will always be $this->DOM.
# 2. Let local name be the tag name of the token.
$localName = $token->name;
// Nope. Don't need it because when creating elements with
// DOMElement::createElementNS the prefix and local name are combined.
// DEVIATION: Steps three through six are unnecessary because there is no scripting in this implementation.
// DEVIATION: Steps three through six are unnecessary because there is no
// scripting in this implementation.
# 7. Let element be the result of creating an element given document, local
# name, given namespace, null, and is. If will execute script is true, set the
# synchronous custom elements flag; otherwise, leave it unset.
// DEVIATION: There is no point to setting the synchronous custom elements flag; there is no scripting in this implementation.
// DEVIATION: There is no point to looking up a custom element definition; there is no scripting in this implementation.
if ($token->namespace === static::HTML_NAMESPACE) {
$element = $document->createElement($token->name);
// DEVIATION: There is no point to setting the synchronous custom elements flag
// and custom element definition; there is no scripting in this implementation.
if ($namespace === static::HTML_NAMESPACE) {
$element = $this->DOM->createElement($token->name);
} else {
$element = $document->createElementNS($token->namespace, $token->name);
$element = $this->DOM->createElementNS($namespace, $token->name);
}
# 8. Append each attribute in the given token to element.
@ -3914,7 +4204,9 @@ class Parser {
}
# 9. If will execute script is true, then:
# - 1. Let queue be the result of popping the current element queue from the custom element reactions stack. (This will be the same element queue as was pushed above.)
# - 1. Let queue be the result of popping the current element queue from the
# custom element reactions stack. (This will be the same element queue as was
# pushed above.)
# - 2. Invoke custom element reactions in queue.
# - 3. Decrement document’s throw-on-dynamic-markup-insertion counter.
// DEVIATION: These steps are unnecessary because there is no scripting in this
@ -3925,12 +4217,12 @@ class Parser {
# Similarly, if element has an xmlns:xlink attribute in the XMLNS namespace
# whose value is not the XLink namespace, that is a parse error.
$xmlns = $element->getAttributeNS(static::XMLNS_NAMESPACE, 'xmlns');
if ($xmlns !== false && $xmlns !== $element->namespaceURI) {
if ($xmlns !== '' && $xmlns !== $element->namespaceURI) {
ParseError::trigger(ParseError::INVALID_XMLNS_ATTRIBUTE_VALUE, $this->data, $element->namespaceURI);
}
$xlink = $element->getAttributeNS(static::XMLNS_NAMESPACE, 'xlink');
if ($xlink !== false && $xlink !== static::XLINK_NAMESPACE) {
if ($xlink !== '' && $xlink !== static::XLINK_NAMESPACE) {
ParseError::trigger(ParseError::INVALID_XMLNS_ATTRIBUTE_VALUE, $this->data, static::XLINK_NAMESPACE);
}
@ -3949,8 +4241,10 @@ class Parser {
// DEVIATION: Unnecessary because there is no scripting in this implementation.
# 13. Return element.
// Don't need to return anything because going straight into insertion.
return $element;
}
protected function insertElement(\DOMElement $element, \DOMNode $intendedParent = null) {
# When the steps below require the user agent to insert an HTML element for a
# token, the user agent must insert a foreign element for the token, in the HTML
# namespace.
@ -3963,11 +4257,14 @@ class Parser {
# 1. Let the adjusted insertion location be the appropriate place for inserting
# a node.
// Already have that.
$location = $this->appropriatePlaceForInsertingNode($intendedParent);
$adjustedInsertionLocation = $location['node'];
$insertBefore = $location['insert before'];
# 2. Let element be the result of creating an element for the token in the given
# namespace, with the intended parent being the element in which the adjusted
# insertion location finds itself.
// Element is supplied.
// Have that, too.
# 3. If it is possible to insert element at the adjusted insertion location,
@ -3988,12 +4285,17 @@ class Parser {
# 4. Push element onto the stack of open elements so that it is the new current node.
// OPTIMIZATION: Going to check if it is self-closing before pushing it onto the
// stack of open elements.
if ($token->selfClosing !== true) {
// stack of open elements as per the spec it's just removed later on anyway if
// indeed self-closing.
//if ($token->selfClosing !== true) {
$this->stack[] = $element;
}
//}
# Return element.
return $element;
}
function createAndInsertElement(StartTagToken $token, \DOMNode $intendedParent = null, string $namespace = null) {
return $this->insertElement($this->createElement($token, $namespace), $intendedParent);
}
}

10
lib/Token.php
View file

@ -27,11 +27,11 @@ class DOCTYPEToken extends Token {
public $public;
public $system;
public function __construct($name = null, $public = null, $system = null) {
$this->name = (string)$name;
public function __construct(string $name = null, string $public = '', string $system = '') {
$this->name = $name;
$this->public = (string)$public;
$this->system = (string)$system;
$this->public = $public;
$this->system = $system;
}
}
@ -46,7 +46,7 @@ class CommentToken extends DataToken {
class StartTagToken extends TagToken {
public $namespace;
public $selfClosing;
public $attributes;
public $attributes = [];
public function __construct($name, bool $selfClosing = false, string $namespace = Parser::HTML_NAMESPACE) {
$this->selfClosing = $selfClosing;