class WP_HTML_Processor {}

Source

 *
 * @see WP_HTML_Tag_Processor
 * @see https://html.spec.whatwg.org/
 */
class WP_HTML_Processor extends WP_HTML_Tag_Processor {
	/**
	 * The maximum number of bookmarks allowed to exist at any given time.
	 *
	 * HTML processing requires more bookmarks than basic tag processing,
	 * so this class constant from the Tag Processor is overwritten.
	 *
	 * @since 6.4.0
	 *
	 * @var int
	 */
	const MAX_BOOKMARKS = 100;

	/**
	 * Holds the working state of the parser, including the stack of
	 * open elements and the stack of active formatting elements.
	 *
	 * Initialized in the constructor.
	 *
	 * @since 6.4.0
	 *
	 * @var WP_HTML_Processor_State
	 */
	private $state;

	/**
	 * Used to create unique bookmark names.
	 *
	 * This class sets a bookmark for every tag in the HTML document that it encounters.
	 * The bookmark name is auto-generated and increments, starting with `1`. These are
	 * internal bookmarks and are automatically released when the referring WP_HTML_Token
	 * goes out of scope and is garbage-collected.
	 *
	 * @since 6.4.0
	 *
	 * @see WP_HTML_Processor::$release_internal_bookmark_on_destruct
	 *
	 * @var int
	 */
	private $bookmark_counter = 0;

	/**
	 * Stores an explanation for why something failed, if it did.
	 *
	 * @see self::get_last_error
	 *
	 * @since 6.4.0
	 *
	 * @var string|null
	 */
	private $last_error = null;

	/**
	 * Stores context for why the parser bailed on unsupported HTML, if it did.
	 *
	 * @see self::get_unsupported_exception
	 *
	 * @since 6.7.0
	 *
	 * @var WP_HTML_Unsupported_Exception|null
	 */
	private $unsupported_exception = null;

	/**
	 * Releases a bookmark when PHP garbage-collects its wrapping WP_HTML_Token instance.
	 *
	 * This function is created inside the class constructor so that it can be passed to
	 * the stack of open elements and the stack of active formatting elements without
	 * exposing it as a public method on the class.
	 *
	 * @since 6.4.0
	 *
	 * @var Closure|null
	 */
	private $release_internal_bookmark_on_destruct = null;

	/**
	 * Stores stack events which arise during parsing of the
	 * HTML document, which will then supply the "match" events.
	 *
	 * @since 6.6.0
	 *
	 * @var WP_HTML_Stack_Event[]
	 */
	private $element_queue = array();

	/**
	 * Stores the current breadcrumbs.
	 *
	 * @since 6.7.0
	 *
	 * @var string[]
	 */
	private $breadcrumbs = array();

	/**
	 * Current stack event, if set, representing a matched token.
	 *
	 * Because the parser may internally point to a place further along in a document
	 * than the nodes which have already been processed (some "virtual" nodes may have
	 * appeared while scanning the HTML document), this will point at the "current" node
	 * being processed. It comes from the front of the element queue.
	 *
	 * @since 6.6.0
	 *
	 * @var WP_HTML_Stack_Event|null
	 */
	private $current_element = null;

	/**
	 * Context node if created as a fragment parser.
	 *
	 * @var WP_HTML_Token|null
	 */
	private $context_node = null;

	/*
	 * Public Interface Functions
	 */

	/**
	 * Creates an HTML processor in the fragment parsing mode.
	 *
	 * Use this for cases where you are processing chunks of HTML that
	 * will be found within a bigger HTML document, such as rendered
	 * block output that exists within a post, `the_content` inside a
	 * rendered site layout.
	 *
	 * Fragment parsing occurs within a context, which is an HTML element
	 * that the document will eventually be placed in. It becomes important
	 * when special elements have different rules than others, such as inside
	 * a TEXTAREA or a TITLE tag where things that look like tags are text,
	 * or inside a SCRIPT tag where things that look like HTML syntax are JS.
	 *
	 * The context value should be a representation of the tag into which the
	 * HTML is found. For most cases this will be the body element. The HTML
	 * form is provided because a context element may have attributes that
	 * impact the parse, such as with a SCRIPT tag and its `type` attribute.
	 *
	 * ## Current HTML Support
	 *
	 *  - The only supported context is `<body>`, which is the default value.
	 *  - The only supported document encoding is `UTF-8`, which is the default value.
	 *
	 * @since 6.4.0
	 * @since 6.6.0 Returns `static` instead of `self` so it can create subclass instances.
	 *
	 * @param string $html     Input HTML fragment to process.
	 * @param string $context  Context element for the fragment, must be default of `<body>`.
	 * @param string $encoding Text encoding of the document; must be default of 'UTF-8'.
	 * @return static|null The created processor if successful, otherwise null.
	 */
	public static function create_fragment( $html, $context = '<body>', $encoding = 'UTF-8' ) {
		if ( '<body>' !== $context || 'UTF-8' !== $encoding ) {
			return null;
		}

		$processor                             = new static( $html, self::CONSTRUCTOR_UNLOCK_CODE );
		$processor->state->context_node        = array( 'BODY', array() );
		$processor->state->insertion_mode      = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY;
		$processor->state->encoding            = $encoding;
		$processor->state->encoding_confidence = 'certain';

		// @todo Create "fake" bookmarks for non-existent but implied nodes.
		$processor->bookmarks['root-node']    = new WP_HTML_Span( 0, 0 );
		$processor->bookmarks['context-node'] = new WP_HTML_Span( 0, 0 );

		$root_node = new WP_HTML_Token(
			'root-node',
			'HTML',
			false
		);

		$processor->state->stack_of_open_elements->push( $root_node );

		$context_node = new WP_HTML_Token(
			'context-node',
			$processor->state->context_node[0],
			false
		);

		$processor->context_node = $context_node;
		$processor->breadcrumbs  = array( 'HTML', $context_node->node_name );

		return $processor;
	}

	/**
	 * Creates an HTML processor in the full parsing mode.
	 *
	 * It's likely that a fragment parser is more appropriate, unless sending an
	 * entire HTML document from start to finish. Consider a fragment parser with
	 * a context node of `<body>`.
	 *
	 * Since UTF-8 is the only currently-accepted charset, if working with a
	 * document that isn't UTF-8, it's important to convert the document before
	 * creating the processor: pass in the converted HTML.
	 *
	 * @param string      $html                    Input HTML document to process.
	 * @param string|null $known_definite_encoding Optional. If provided, specifies the charset used
	 *                                             in the input byte stream. Currently must be UTF-8.
	 * @return static|null The created processor if successful, otherwise null.
	 */
	public static function create_full_parser( $html, $known_definite_encoding = 'UTF-8' ) {
		if ( 'UTF-8' !== $known_definite_encoding ) {
			return null;
		}

		$processor                             = new static( $html, self::CONSTRUCTOR_UNLOCK_CODE );
		$processor->state->encoding            = $known_definite_encoding;
		$processor->state->encoding_confidence = 'certain';

		return $processor;
	}

	/**
	 * Constructor.
	 *
	 * Do not use this method. Use the static creator methods instead.
	 *
	 * @access private
	 *
	 * @since 6.4.0
	 *
	 * @see WP_HTML_Processor::create_fragment()
	 *
	 * @param string      $html                                  HTML to process.
	 * @param string|null $use_the_static_create_methods_instead This constructor should not be called manually.
	 */
	public function __construct( $html, $use_the_static_create_methods_instead = null ) {
		parent::__construct( $html );

		if ( self::CONSTRUCTOR_UNLOCK_CODE !== $use_the_static_create_methods_instead ) {
			_doing_it_wrong(
				__METHOD__,
				sprintf(
					/* translators: %s: WP_HTML_Processor::create_fragment(). */
					__( 'Call %s to create an HTML Processor instead of calling the constructor directly.' ),
					'<code>WP_HTML_Processor::create_fragment()</code>'
				),
				'6.4.0'
			);
		}

		$this->state = new WP_HTML_Processor_State();

		$this->state->stack_of_open_elements->set_push_handler(
			function ( WP_HTML_Token $token ): void {
				$is_virtual            = ! isset( $this->state->current_token ) || $this->is_tag_closer();
				$same_node             = isset( $this->state->current_token ) && $token->node_name === $this->state->current_token->node_name;
				$provenance            = ( ! $same_node || $is_virtual ) ? 'virtual' : 'real';
				$this->element_queue[] = new WP_HTML_Stack_Event( $token, WP_HTML_Stack_Event::PUSH, $provenance );

				$this->change_parsing_namespace( $token->integration_node_type ? 'html' : $token->namespace );
			}
		);

		$this->state->stack_of_open_elements->set_pop_handler(
			function ( WP_HTML_Token $token ): void {
				$is_virtual            = ! isset( $this->state->current_token ) || ! $this->is_tag_closer();
				$same_node             = isset( $this->state->current_token ) && $token->node_name === $this->state->current_token->node_name;
				$provenance            = ( ! $same_node || $is_virtual ) ? 'virtual' : 'real';
				$this->element_queue[] = new WP_HTML_Stack_Event( $token, WP_HTML_Stack_Event::POP, $provenance );

				$adjusted_current_node = $this->get_adjusted_current_node();

				if ( $adjusted_current_node ) {
					$this->change_parsing_namespace( $adjusted_current_node->integration_node_type ? 'html' : $adjusted_current_node->namespace );
				} else {
					$this->change_parsing_namespace( 'html' );
				}
			}
		);

		/*
		 * Create this wrapper so that it's possible to pass
		 * a private method into WP_HTML_Token classes without
		 * exposing it to any public API.
		 */
		$this->release_internal_bookmark_on_destruct = function ( string $name ): void {
			parent::release_bookmark( $name );
		};
	}

	/**
	 * Stops the parser and terminates its execution when encountering unsupported markup.
	 *
	 * @throws WP_HTML_Unsupported_Exception Halts execution of the parser.
	 *
	 * @since 6.7.0
	 *
	 * @param string $message Explains support is missing in order to parse the current node.
	 */
	private function bail( string $message ) {
		$here  = $this->bookmarks[ $this->state->current_token->bookmark_name ];
		$token = substr( $this->html, $here->start, $here->length );

		$open_elements = array();
		foreach ( $this->state->stack_of_open_elements->stack as $item ) {
			$open_elements[] = $item->node_name;
		}

		$active_formats = array();
		foreach ( $this->state->active_formatting_elements->walk_down() as $item ) {
			$active_formats[] = $item->node_name;
		}

		$this->last_error = self::ERROR_UNSUPPORTED;

		$this->unsupported_exception = new WP_HTML_Unsupported_Exception(
			$message,
			$this->state->current_token->node_name,
			$here->start,
			$token,
			$open_elements,
			$active_formats
		);

		throw $this->unsupported_exception;
	}

	/**
	 * Returns the last error, if any.
	 *
	 * Various situations lead to parsing failure but this class will
	 * return `false` in all those cases. To determine why something
	 * failed it's possible to request the last error. This can be
	 * helpful to know to distinguish whether a given tag couldn't
	 * be found or if content in the document caused the processor
	 * to give up and abort processing.
	 *
	 * Example
	 *
	 *     $processor = WP_HTML_Processor::create_fragment( '<template><strong><button><em><p><em>' );
	 *     false === $processor->next_tag();
	 *     WP_HTML_Processor::ERROR_UNSUPPORTED === $processor->get_last_error();
	 *
	 * @since 6.4.0
	 *
	 * @see self::ERROR_UNSUPPORTED
	 * @see self::ERROR_EXCEEDED_MAX_BOOKMARKS
	 *
	 * @return string|null The last error, if one exists, otherwise null.
	 */
	public function get_last_error(): ?string {
		return $this->last_error;
	}

	/**
	 * Returns context for why the parser aborted due to unsupported HTML, if it did.
	 *
	 * This is meant for debugging purposes, not for production use.
	 *
	 * @since 6.7.0
	 *
	 * @see self::$unsupported_exception
	 *
	 * @return WP_HTML_Unsupported_Exception|null
	 */
	public function get_unsupported_exception() {
		return $this->unsupported_exception;
	}

	/**
	 * Finds the next tag matching the $query.
	 *
	 * @todo Support matching the class name and tag name.
	 *
	 * @since 6.4.0
	 * @since 6.6.0 Visits all tokens, including virtual ones.
	 *
	 * @throws Exception When unable to allocate a bookmark for the next token in the input HTML document.
	 *
	 * @param array|string|null $query {
	 *     Optional. Which tag name to find, having which class, etc. Default is to find any tag.
	 *
	 *     @type string|null $tag_name     Which tag to find, or `null` for "any tag."
	 *     @type string      $tag_closers  'visit' to pause at tag closers, 'skip' or unset to only visit openers.
	 *     @type int|null    $match_offset Find the Nth tag matching all search criteria.
	 *                                     1 for "first" tag, 3 for "third," etc.
	 *                                     Defaults to first tag.
	 *     @type string|null $class_name   Tag must contain this whole class name to match.
	 *     @type string[]    $breadcrumbs  DOM sub-path at which element is found, e.g. `array( 'FIGURE', 'IMG' )`.
	 *                                     May also contain the wildcard `*` which matches a single element, e.g. `array( 'SECTION', '*' )`.
	 * }
	 * @return bool Whether a tag was matched.
	 */
	public function next_tag( $query = null ): bool {
		$visit_closers = isset( $query['tag_closers'] ) && 'visit' === $query['tag_closers'];

		if ( null === $query ) {
			while ( $this->next_token() ) {
				if ( '#tag' !== $this->get_token_type() ) {
					continue;
				}

				if ( ! $this->is_tag_closer() || $visit_closers ) {
					return true;
				}
			}

			return false;
		}

		if ( is_string( $query ) ) {
			$query = array( 'breadcrumbs' => array( $query ) );
		}

		if ( ! is_array( $query ) ) {
			_doing_it_wrong(
				__METHOD__,
				__( 'Please pass a query array to this function.' ),
				'6.4.0'
			);
			return false;
		}

		$needs_class = ( isset( $query['class_name'] ) && is_string( $query['class_name'] ) )
			? $query['class_name']
			: null;

		if ( ! ( array_key_exists( 'breadcrumbs', $query ) && is_array( $query['breadcrumbs'] ) ) ) {
			while ( $this->next_token() ) {
				if ( '#tag' !== $this->get_token_type() ) {
					continue;
				}

				if ( isset( $query['tag_name'] ) && $query['tag_name'] !== $this->get_token_name() ) {
					continue;
				}

				if ( isset( $needs_class ) && ! $this->has_class( $needs_class ) ) {
					continue;
				}

				if ( ! $this->is_tag_closer() || $visit_closers ) {
					return true;
				}
			}

			return false;
		}

		$breadcrumbs  = $query['breadcrumbs'];
		$match_offset = isset( $query['match_offset'] ) ? (int) $query['match_offset'] : 1;

		while ( $match_offset > 0 && $this->next_token() ) {
			if ( '#tag' !== $this->get_token_type() || $this->is_tag_closer() ) {
				continue;
			}

			if ( isset( $needs_class ) && ! $this->has_class( $needs_class ) ) {
				continue;
			}

			if ( $this->matches_breadcrumbs( $breadcrumbs ) && 0 === --$match_offset ) {
				return true;
			}
		}

		return false;
	}

	/**
	 * Ensures internal accounting is maintained for HTML semantic rules while
	 * the underlying Tag Processor class is seeking to a bookmark.
	 *
	 * This doesn't currently have a way to represent non-tags and doesn't process
	 * semantic rules for text nodes. For access to the raw tokens consider using
	 * WP_HTML_Tag_Processor instead.
	 *
	 * @since 6.5.0 Added for internal support; do not use.
	 *
	 * @access private
	 *
	 * @return bool
	 */
	public function next_token(): bool {
		$this->current_element = null;

		if ( isset( $this->last_error ) ) {
			return false;
		}

		/*
		 * Prime the events if there are none.
		 *
		 * @todo In some cases, probably related to the adoption agency
		 *       algorithm, this call to step() doesn't create any new
		 *       events. Calling it again creates them. Figure out why
		 *       this is and if it's inherent or if it's a bug. Looping
		 *       until there are events or until there are no more
		 *       tokens works in the meantime and isn't obviously wrong.
		 */
		if ( empty( $this->element_queue ) && $this->step() ) {
			return $this->next_token();
		}

		// Process the next event on the queue.
		$this->current_element = array_shift( $this->element_queue );
		if ( ! isset( $this->current_element ) ) {
			// There are no tokens left, so close all remaining open elements.
			while ( $this->state->stack_of_open_elements->pop() ) {
				continue;
			}

			return empty( $this->element_queue ) ? false : $this->next_token();
		}

		$is_pop = WP_HTML_Stack_Event::POP === $this->current_element->operation;

		/*
		 * The root node only exists in the fragment parser, and closing it
		 * indicates that the parse is complete. Stop before popping it from
		 * the breadcrumbs.
		 */
		if ( 'root-node' === $this->current_element->token->bookmark_name ) {
			return $this->next_token();
		}

		// Adjust the breadcrumbs for this event.
		if ( $is_pop ) {
			array_pop( $this->breadcrumbs );
		} else {
			$this->breadcrumbs[] = $this->current_element->token->node_name;
		}

		// Avoid sending close events for elements which don't expect a closing.
		if ( $is_pop && ! $this->expects_closer( $this->current_element->token ) ) {
			return $this->next_token();
		}

		return true;
	}

	/**
	 * Indicates if the current tag token is a tag closer.
	 *
	 * Example:
	 *
	 *     $p = WP_HTML_Processor::create_fragment( '<div></div>' );
	 *     $p->next_tag( array( 'tag_name' => 'div', 'tag_closers' => 'visit' ) );
	 *     $p->is_tag_closer() === false;
	 *
	 *     $p->next_tag( array( 'tag_name' => 'div', 'tag_closers' => 'visit' ) );
	 *     $p->is_tag_closer() === true;
	 *
	 * @since 6.6.0 Subclassed for HTML Processor.
	 *
	 * @return bool Whether the current tag is a tag closer.
	 */
	public function is_tag_closer(): bool {
		return $this->is_virtual()
			? ( WP_HTML_Stack_Event::POP === $this->current_element->operation && '#tag' === $this->get_token_type() )
			: parent::is_tag_closer();
	}

	/**
	 * Indicates if the currently-matched token is virtual, created by a stack operation
	 * while processing HTML, rather than a token found in the HTML text itself.
	 *
	 * @since 6.6.0
	 *
	 * @return bool Whether the current token is virtual.
	 */
	private function is_virtual(): bool {
		return (
			isset( $this->current_element->provenance ) &&
			'virtual' === $this->current_element->provenance
		);
	}

	/**
	 * Indicates if the currently-matched tag matches the given breadcrumbs.
	 *
	 * A "*" represents a single tag wildcard, where any tag matches, but not no tags.
	 *
	 * At some point this function _may_ support a `**` syntax for matching any number
	 * of unspecified tags in the breadcrumb stack. This has been intentionally left
	 * out, however, to keep this function simple and to avoid introducing backtracking,
	 * which could open up surprising performance breakdowns.
	 *
	 * Example:
	 *
	 *     $processor = WP_HTML_Processor::create_fragment( '<div><span><figure><img></figure></span></div>' );
	 *     $processor->next_tag( 'img' );
	 *     true  === $processor->matches_breadcrumbs( array( 'figure', 'img' ) );
	 *     true  === $processor->matches_breadcrumbs( array( 'span', 'figure', 'img' ) );
	 *     false === $processor->matches_breadcrumbs( array( 'span', 'img' ) );
	 *     true  === $processor->matches_breadcrumbs( array( 'span', '*', 'img' ) );
	 *
	 * @since 6.4.0
	 *
	 * @param string[] $breadcrumbs DOM sub-path at which element is found, e.g. `array( 'FIGURE', 'IMG' )`.
	 *                              May also contain the wildcard `*` which matches a single element, e.g. `array( 'SECTION', '*' )`.
	 * @return bool Whether the currently-matched tag is found at the given nested structure.
	 */
	public function matches_breadcrumbs( $breadcrumbs ): bool {
		// Everything matches when there are zero constraints.
		if ( 0 === count( $breadcrumbs ) ) {
			return true;
		}

		// Start at the last crumb.
		$crumb = end( $breadcrumbs );

		if ( '*' !== $crumb && $this->get_tag() !== strtoupper( $crumb ) ) {
			return false;
		}

		for ( $i = count( $this->breadcrumbs ) - 1; $i >= 0; $i-- ) {
			$node  = $this->breadcrumbs[ $i ];
			$crumb = strtoupper( current( $breadcrumbs ) );

			if ( '*' !== $crumb && $node !== $crumb ) {
				return false;
			}

			if ( false === prev( $breadcrumbs ) ) {
				return true;
			}
		}

		return false;
	}

	/**
	 * Indicates if the currently-matched node expects a closing
	 * token, or if it will self-close on the next step.
	 *
	 * Most HTML elements expect a closer, such as a P element or
	 * a DIV element. Others, like an IMG element are void and don't
	 * have a closing tag. Special elements, such as SCRIPT and STYLE,
	 * are treated just like void tags. Text nodes and self-closing
	 * foreign content will also act just like a void tag, immediately
	 * closing as soon as the processor advances to the next token.
	 *
	 * @since 6.6.0
	 *
	 * @param WP_HTML_Token|null $node Optional. Node to examine, if provided.
	 *                                 Default is to examine current node.
	 * @return bool|null Whether to expect a closer for the currently-matched node,
	 *                   or `null` if not matched on any token.
	 */
	public function expects_closer( ?WP_HTML_Token $node = null ): ?bool {
		$token_name = $node->node_name ?? $this->get_token_name();

		if ( ! isset( $token_name ) ) {
			return null;
		}

		$token_namespace        = $node->namespace ?? $this->get_namespace();
		$token_has_self_closing = $node->has_self_closing_flag ?? $this->has_self_closing_flag();

		return ! (
			// Comments, text nodes, and other atomic tokens.
			'#' === $token_name[0] ||
			// Doctype declarations.
			'html' === $token_name ||
			// Void elements.
			self::is_void( $token_name ) ||
			// Special atomic elements.
			( 'html' === $token_namespace && in_array( $token_name, array( 'IFRAME', 'NOEMBED', 'NOFRAMES', 'SCRIPT', 'STYLE', 'TEXTAREA', 'TITLE', 'XMP' ), true ) ) ||
			// Self-closing elements in foreign content.
			( 'html' !== $token_namespace && $token_has_self_closing )
		);
	}

	/**
	 * Steps through the HTML document and stop at the next tag, if any.
	 *
	 * @since 6.4.0
	 *
	 * @throws Exception When unable to allocate a bookmark for the next token in the input HTML document.
	 *
	 * @see self::PROCESS_NEXT_NODE
	 * @see self::REPROCESS_CURRENT_NODE
	 *
	 * @param string $node_to_process Whether to parse the next node or reprocess the current node.
	 * @return bool Whether a tag was matched.
	 */
	public function step( $node_to_process = self::PROCESS_NEXT_NODE ): bool {
		// Refuse to proceed if there was a previous error.
		if ( null !== $this->last_error ) {
			return false;
		}

		if ( self::REPROCESS_CURRENT_NODE !== $node_to_process ) {
			/*
			 * Void elements still hop onto the stack of open elements even though
			 * there's no corresponding closing tag. This is important for managing
			 * stack-based operations such as "navigate to parent node" or checking
			 * on an element's breadcrumbs.
			 *
			 * When moving on to the next node, therefore, if the bottom-most element
			 * on the stack is a void element, it must be closed.
			 */
			$top_node = $this->state->stack_of_open_elements->current_node();
			if ( isset( $top_node ) && ! $this->expects_closer( $top_node ) ) {
				$this->state->stack_of_open_elements->pop();
			}
		}

		if ( self::PROCESS_NEXT_NODE === $node_to_process ) {
			parent::next_token();
			if ( WP_HTML_Tag_Processor::STATE_TEXT_NODE === $this->parser_state ) {
				parent::subdivide_text_appropriately();
			}
		}

		// Finish stepping when there are no more tokens in the document.
		if (
			WP_HTML_Tag_Processor::STATE_INCOMPLETE_INPUT === $this->parser_state ||
			WP_HTML_Tag_Processor::STATE_COMPLETE === $this->parser_state
		) {
			return false;
		}

		$adjusted_current_node = $this->get_adjusted_current_node();
		$is_closer             = $this->is_tag_closer();
		$is_start_tag          = WP_HTML_Tag_Processor::STATE_MATCHED_TAG === $this->parser_state && ! $is_closer;
		$token_name            = $this->get_token_name();

		if ( self::REPROCESS_CURRENT_NODE !== $node_to_process ) {
			$this->state->current_token = new WP_HTML_Token(
				$this->bookmark_token(),
				$token_name,
				$this->has_self_closing_flag(),
				$this->release_internal_bookmark_on_destruct
			);
		}

		$parse_in_current_insertion_mode = (
			0 === $this->state->stack_of_open_elements->count() ||
			'html' === $adjusted_current_node->namespace ||
			(
				'math' === $adjusted_current_node->integration_node_type &&
				(
					( $is_start_tag && ! in_array( $token_name, array( 'MGLYPH', 'MALIGNMARK' ), true ) ) ||
					'#text' === $token_name
				)
			) ||
			(
				'math' === $adjusted_current_node->namespace &&
				'ANNOTATION-XML' === $adjusted_current_node->node_name &&
				$is_start_tag && 'SVG' === $token_name
			) ||
			(
				'html' === $adjusted_current_node->integration_node_type &&
				( $is_start_tag || '#text' === $token_name )
			)
		);

		try {
			if ( ! $parse_in_current_insertion_mode ) {
				return $this->step_in_foreign_content();
			}

			switch ( $this->state->insertion_mode ) {
				case WP_HTML_Processor_State::INSERTION_MODE_INITIAL:
					return $this->step_initial();

				case WP_HTML_Processor_State::INSERTION_MODE_BEFORE_HTML:
					return $this->step_before_html();

				case WP_HTML_Processor_State::INSERTION_MODE_BEFORE_HEAD:
					return $this->step_before_head();

				case WP_HTML_Processor_State::INSERTION_MODE_IN_HEAD:
					return $this->step_in_head();

				case WP_HTML_Processor_State::INSERTION_MODE_IN_HEAD_NOSCRIPT:
					return $this->step_in_head_noscript();

				case WP_HTML_Processor_State::INSERTION_MODE_AFTER_HEAD:
					return $this->step_after_head();

				case WP_HTML_Processor_State::INSERTION_MODE_IN_BODY:
					return $this->step_in_body();

				case WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE:
					return $this->step_in_table();

				case WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_TEXT:
					return $this->step_in_table_text();

				case WP_HTML_Processor_State::INSERTION_MODE_IN_CAPTION:
					return $this->step_in_caption();

				case WP_HTML_Processor_State::INSERTION_MODE_IN_COLUMN_GROUP:
					return $this->step_in_column_group();

				case WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY:
					return $this->step_in_table_body();

				case WP_HTML_Processor_State::INSERTION_MODE_IN_ROW:
					return $this->step_in_row();

				case WP_HTML_Processor_State::INSERTION_MODE_IN_CELL:
					return $this->step_in_cell();

				case WP_HTML_Processor_State::INSERTION_MODE_IN_SELECT:
					return $this->step_in_select();

				case WP_HTML_Processor_State::INSERTION_MODE_IN_SELECT_IN_TABLE:
					return $this->step_in_select_in_table();

				case WP_HTML_Processor_State::INSERTION_MODE_IN_TEMPLATE:
					return $this->step_in_template();

				case WP_HTML_Processor_State::INSERTION_MODE_AFTER_BODY:
					return $this->step_after_body();

				case WP_HTML_Processor_State::INSERTION_MODE_IN_FRAMESET:
					return $this->step_in_frameset();

				case WP_HTML_Processor_State::INSERTION_MODE_AFTER_FRAMESET:
					return $this->step_after_frameset();

				case WP_HTML_Processor_State::INSERTION_MODE_AFTER_AFTER_BODY:
					return $this->step_after_after_body();

				case WP_HTML_Processor_State::INSERTION_MODE_AFTER_AFTER_FRAMESET:
					return $this->step_after_after_frameset();

				// This should be unreachable but PHP doesn't have total type checking on switch.
				default:
					$this->bail( "Unaware of the requested parsing mode: '{$this->state->insertion_mode}'." );
			}
		} catch ( WP_HTML_Unsupported_Exception $e ) {
			/*
			 * Exceptions are used in this class to escape deep call stacks that
			 * otherwise might involve messier calling and return conventions.
			 */
			return false;
		}
	}

	/**
	 * Computes the HTML breadcrumbs for the currently-matched node, if matched.
	 *
	 * Breadcrumbs start at the outermost parent and descend toward the matched element.
	 * They always include the entire path from the root HTML node to the matched element.
	 *
	 * @todo It could be more efficient to expose a generator-based version of this function
	 *       to avoid creating the array copy on tag iteration. If this is done, it would likely
	 *       be more useful to walk up the stack when yielding instead of starting at the top.
	 *
	 * Example
	 *
	 *     $processor = WP_HTML_Processor::create_fragment( '<p><strong><em><img></em></strong></p>' );
	 *     $processor->next_tag( 'IMG' );
	 *     $processor->get_breadcrumbs() === array( 'HTML', 'BODY', 'P', 'STRONG', 'EM', 'IMG' );
	 *
	 * @since 6.4.0
	 *
	 * @return string[]|null Array of tag names representing path to matched node, if matched, otherwise NULL.
	 */
	public function get_breadcrumbs(): ?array {
		return $this->breadcrumbs;
	}

	/**
	 * Returns the nesting depth of the current location in the document.
	 *
	 * Example:
	 *
	 *     $processor = WP_HTML_Processor::create_fragment( '<div><p></p></div>' );
	 *     // The processor starts in the BODY context, meaning it has depth from the start: HTML > BODY.
	 *     2 === $processor->get_current_depth();
	 *
	 *     // Opening the DIV element increases the depth.
	 *     $processor->next_token();
	 *     3 === $processor->get_current_depth();
	 *
	 *     // Opening the P element increases the depth.
	 *     $processor->next_token();
	 *     4 === $processor->get_current_depth();
	 *
	 *     // The P element is closed during `next_token()` so the depth is decreased to reflect that.
	 *     $processor->next_token();
	 *     3 === $processor->get_current_depth();
	 *
	 * @since 6.6.0
	 *
	 * @return int Nesting-depth of current location in the document.
	 */
	public function get_current_depth(): int {
		return count( $this->breadcrumbs );
	}

	/**
	 * Normalizes an HTML fragment by serializing it.
	 *
	 * This method assumes that the given HTML snippet is found in BODY context.
	 * For normalizing full documents or fragments found in other contexts, create
	 * a new processor using WP_HTML_Processor::create_fragment or
	 * WP_HTML_Processor::create_full_parser and call WP_HTML_Processor::serialize
	 * on the created instances.
	 *
	 * Many aspects of an input HTML fragment may be changed during normalization.
	 *
	 *  - Attribute values will be double-quoted.
	 *  - Duplicate attributes will be removed.
	 *  - Omitted tags will be added.
	 *  - Tag and attribute name casing will be lower-cased,
	 *    except for specific SVG and MathML tags or attributes.
	 *  - Text will be re-encoded, null bytes handled,
	 *    and invalid UTF-8 replaced with U+FFFD.
	 *  - Any incomplete syntax trailing at the end will be omitted,
	 *    for example, an unclosed comment opener will be removed.
	 *
	 * Example:
	 *
	 *     echo WP_HTML_Processor::normalize( '<a href=#anchor v=5 href="/" enabled>One</a another v=5><!--' );
	 *     // <a href="#anchor" v="5" enabled>One</a>
	 *
	 *     echo WP_HTML_Processor::normalize( '<div></p>fun<table><td>cell</div>' );
	 *     // <div><p></p>fun<table><tbody><tr><td>cell</td></tr></tbody></table></div>
	 *
	 *     echo WP_HTML_Processor::normalize( '<![CDATA[invalid comment]]> syntax < <> "oddities"' );
	 *     // <!--[CDATA[invalid comment]]--> syntax &lt; &lt;&gt; &quot;oddities&quot;
	 *
	 * @since 6.7.0
	 *
	 * @param string $html Input HTML to normalize.
	 *
	 * @return string|null Normalized output, or `null` if unable to normalize.
	 */
	public static function normalize( string $html ): ?string {
		return static::create_fragment( $html )->serialize();
	}

	/**
	 * Returns normalized HTML for a fragment by serializing it.
	 *
	 * This differs from WP_HTML_Processor::normalize in that it starts with
	 * a specific HTML Processor, which _must_ not have already started scanning;
	 * it must be in the initial ready state and will be in the completed state once
	 * serialization is complete.
	 *
	 * Many aspects of an input HTML fragment may be changed during normalization.
	 *
	 *  - Attribute values will be double-quoted.
	 *  - Duplicate attributes will be removed.
	 *  - Omitted tags will be added.
	 *  - Tag and attribute name casing will be lower-cased,
	 *    except for specific SVG and MathML tags or attributes.
	 *  - Text will be re-encoded, null bytes handled,
	 *    and invalid UTF-8 replaced with U+FFFD.
	 *  - Any incomplete syntax trailing at the end will be omitted,
	 *    for example, an unclosed comment opener will be removed.
	 *
	 * Example:
	 *
	 *     $processor = WP_HTML_Processor::create_fragment( '<a href=#anchor v=5 href="/" enabled>One</a another v=5><!--' );
	 *     echo $processor->serialize();
	 *     // <a href="#anchor" v="5" enabled>One</a>
	 *
	 *     $processor = WP_HTML_Processor::create_fragment( '<div></p>fun<table><td>cell</div>' );
	 *     echo $processor->serialize();
	 *     // <div><p></p>fun<table><tbody><tr><td>cell</td></tr></tbody></table></div>
	 *
	 *     $processor = WP_HTML_Processor::create_fragment( '<![CDATA[invalid comment]]> syntax < <> "oddities"' );
	 *     echo $processor->serialize();
	 *     // <!--[CDATA[invalid comment]]--> syntax &lt; &lt;&gt; &quot;oddities&quot;
	 *
	 * @since 6.7.0
	 *
	 * @return string|null Normalized HTML markup represented by processor,
	 *                     or `null` if unable to generate serialization.
	 */
	public function serialize(): ?string {
		if ( WP_HTML_Tag_Processor::STATE_READY !== $this->parser_state ) {
			wp_trigger_error(
				__METHOD__,
				'An HTML Processor which has already started processing cannot serialize its contents. Serialize immediately after creating the instance.',
				E_USER_WARNING
			);
			return null;
		}

		$html = '';
		while ( $this->next_token() ) {
			$html .= $this->serialize_token();
		}

		if ( null !== $this->get_last_error() ) {
			wp_trigger_error(
				__METHOD__,
				"Cannot serialize HTML Processor with parsing error: {$this->get_last_error()}.",
				E_USER_WARNING
			);
			return null;
		}

		return $html;
	}

	/**
	 * Serializes the currently-matched token.
	 *
	 * This method produces a fully-normative HTML string for the currently-matched token,
	 * if able. If not matched at any token or if the token doesn't correspond to any HTML
	 * it will return an empty string (for example, presumptuous end tags are ignored).
	 *
	 * @see static::serialize()
	 *
	 * @since 6.7.0
	 *
	 * @return string Serialization of token, or empty string if no serialization exists.
	 */
	protected function serialize_token(): string {
		$html       = '';
		$token_type = $this->get_token_type();

		switch ( $token_type ) {
			case '#text':
				$html .= htmlspecialchars( $this->get_modifiable_text(), ENT_QUOTES | ENT_SUBSTITUTE | ENT_HTML5, 'UTF-8' );
				break;

			// Unlike the `<>` which is interpreted as plaintext, this is ignored entirely.
			case '#presumptuous-tag':
				break;

			case '#funky-comment':
			case '#comment':
				$html .= "<!--{$this->get_full_comment_text()}-->";
				break;

			case '#cdata-section':
				$html .= "<![CDATA[{$this->get_modifiable_text()}]]>";
				break;

			case 'html':
				$html .= '<!DOCTYPE html>';
				break;
		}

		if ( '#tag' !== $token_type ) {
			return $html;
		}

		$tag_name       = str_replace( "\x00", "\u{FFFD}", $this->get_tag() );
		$in_html        = 'html' === $this->get_namespace();
		$qualified_name = $in_html ? strtolower( $tag_name ) : $this->get_qualified_tag_name();

		if ( $this->is_tag_closer() ) {
			$html .= "</{$qualified_name}>";
			return $html;
		}

		$attribute_names = $this->get_attribute_names_with_prefix( '' );
		if ( ! isset( $attribute_names ) ) {
			$html .= "<{$qualified_name}>";
			return $html;
		}

		$html .= "<{$qualified_name}";
		foreach ( $attribute_names as $attribute_name ) {
			$html .= " {$this->get_qualified_attribute_name( $attribute_name )}";
			$value = $this->get_attribute( $attribute_name );

			if ( is_string( $value ) ) {
				$html .= '="' . htmlspecialchars( $value, ENT_QUOTES | ENT_SUBSTITUTE | ENT_HTML5 ) . '"';
			}

			$html = str_replace( "\x00", "\u{FFFD}", $html );
		}

		if ( ! $in_html && $this->has_self_closing_flag() ) {
			$html .= ' /';
		}

		$html .= '>';

		// Flush out self-contained elements.
		if ( $in_html && in_array( $tag_name, array( 'IFRAME', 'NOEMBED', 'NOFRAMES', 'SCRIPT', 'STYLE', 'TEXTAREA', 'TITLE', 'XMP' ), true ) ) {
			$text = $this->get_modifiable_text();

			switch ( $tag_name ) {
				case 'IFRAME':
				case 'NOEMBED':
				case 'NOFRAMES':
					$text = '';
					break;

				case 'SCRIPT':
				case 'STYLE':
					break;

				default:
					$text = htmlspecialchars( $text, ENT_QUOTES | ENT_SUBSTITUTE | ENT_HTML5, 'UTF-8' );
			}

			$html .= "{$text}</{$qualified_name}>";
		}

		return $html;
	}

	/**
	 * Parses next element in the 'initial' insertion mode.
	 *
	 * This internal function performs the 'initial' insertion mode
	 * logic for the generalized WP_HTML_Processor::step() function.
	 *
	 * @since 6.7.0
	 *
	 * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
	 *
	 * @see https://html.spec.whatwg.org/#the-initial-insertion-mode
	 * @see WP_HTML_Processor::step
	 *
	 * @return bool Whether an element was found.
	 */
	private function step_initial(): bool {
		$token_name = $this->get_token_name();
		$token_type = $this->get_token_type();
		$op_sigil   = '#tag' === $token_type ? ( parent::is_tag_closer() ? '-' : '+' ) : '';
		$op         = "{$op_sigil}{$token_name}";

		switch ( $op ) {
			/*
			 * > 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
			 *
			 * Parse error: ignore the token.
			 */
			case '#text':
				if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) {
					return $this->step();
				}
				goto initial_anything_else;
				break;

			/*
			 * > A comment token
			 */
			case '#comment':
			case '#funky-comment':
			case '#presumptuous-tag':
				$this->insert_html_element( $this->state->current_token );
				return true;

			/*
			 * > A DOCTYPE token
			 */
			case 'html':
				$doctype = $this->get_doctype_info();
				if ( null !== $doctype && 'quirks' === $doctype->indicated_compatability_mode ) {
					$this->compat_mode = WP_HTML_Tag_Processor::QUIRKS_MODE;
				}

				/*
				 * > Then, switch the insertion mode to "before html".
				 */
				$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_BEFORE_HTML;
				$this->insert_html_element( $this->state->current_token );
				return true;
		}

		/*
		 * > Anything else
		 */
		initial_anything_else:
		$this->compat_mode           = WP_HTML_Tag_Processor::QUIRKS_MODE;
		$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_BEFORE_HTML;
		return $this->step( self::REPROCESS_CURRENT_NODE );
	}

	/**
	 * Parses next element in the 'before html' insertion mode.
	 *
	 * This internal function performs the 'before html' insertion mode
	 * logic for the generalized WP_HTML_Processor::step() function.
	 *
	 * @since 6.7.0
	 *
	 * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
	 *
	 * @see https://html.spec.whatwg.org/#the-before-html-insertion-mode
	 * @see WP_HTML_Processor::step
	 *
	 * @return bool Whether an element was found.
	 */
	private function step_before_html(): bool {
		$token_name = $this->get_token_name();
		$token_type = $this->get_token_type();
		$is_closer  = parent::is_tag_closer();
		$op_sigil   = '#tag' === $token_type ? ( $is_closer ? '-' : '+' ) : '';
		$op         = "{$op_sigil}{$token_name}";

		switch ( $op ) {
			/*
			 * > A DOCTYPE token
			 */
			case 'html':
				// Parse error: ignore the token.
				return $this->step();

			/*
			 * > A comment token
			 */
			case '#comment':
			case '#funky-comment':
			case '#presumptuous-tag':
				$this->insert_html_element( $this->state->current_token );
				return true;

			/*
			 * > 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
			 *
			 * Parse error: ignore the token.
			 */
			case '#text':
				if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) {
					return $this->step();
				}
				goto before_html_anything_else;
				break;

			/*
			 * > A start tag whose tag name is "html"
			 */
			case '+HTML':
				$this->insert_html_element( $this->state->current_token );
				$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_BEFORE_HEAD;
				return true;

			/*
			 * > An end tag whose tag name is one of: "head", "body", "html", "br"
			 *
			 * Closing BR tags are always reported by the Tag Processor as opening tags.
			 */
			case '-HEAD':
			case '-BODY':
			case '-HTML':
				/*
				 * > Act as described in the "anything else" entry below.
				 */
				goto before_html_anything_else;
				break;
		}

		/*
		 * > Any other end tag
		 */
		if ( $is_closer ) {
			// Parse error: ignore the token.
			return $this->step();
		}

		/*
		 * > Anything 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.
		 * > Switch the insertion mode to "before head", then reprocess the token.
		 */
		before_html_anything_else:
		$this->insert_virtual_node( 'HTML' );
		$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_BEFORE_HEAD;
		return $this->step( self::REPROCESS_CURRENT_NODE );
	}

	/**
	 * Parses next element in the 'before head' insertion mode.
	 *
	 * This internal function performs the 'before head' insertion mode
	 * logic for the generalized WP_HTML_Processor::step() function.
	 *
	 * @since 6.7.0 Stub implementation.
	 *
	 * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
	 *
	 * @see https://html.spec.whatwg.org/#the-before-head-insertion-mode
	 * @see WP_HTML_Processor::step
	 *
	 * @return bool Whether an element was found.
	 */
	private function step_before_head(): bool {
		$token_name = $this->get_token_name();
		$token_type = $this->get_token_type();
		$is_closer  = parent::is_tag_closer();
		$op_sigil   = '#tag' === $token_type ? ( $is_closer ? '-' : '+' ) : '';
		$op         = "{$op_sigil}{$token_name}";

		switch ( $op ) {
			/*
			 * > 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
			 *
			 * Parse error: ignore the token.
			 */
			case '#text':
				if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) {
					return $this->step();
				}
				goto before_head_anything_else;
				break;

			/*
			 * > A comment token
			 */
			case '#comment':
			case '#funky-comment':
			case '#presumptuous-tag':
				$this->insert_html_element( $this->state->current_token );
				return true;

			/*
			 * > A DOCTYPE token
			 */
			case 'html':
				// Parse error: ignore the token.
				return $this->step();

			/*
			 * > A start tag whose tag name is "html"
			 */
			case '+HTML':
				return $this->step_in_body();

			/*
			 * > A start tag whose tag name is "head"
			 */
			case '+HEAD':
				$this->insert_html_element( $this->state->current_token );
				$this->state->head_element   = $this->state->current_token;
				$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_HEAD;
				return true;

			/*
			 * > An end tag whose tag name is one of: "head", "body", "html", "br"
			 * > Act as described in the "anything else" entry below.
			 *
			 * Closing BR tags are always reported by the Tag Processor as opening tags.
			 */
			case '-HEAD':
			case '-BODY':
			case '-HTML':
				goto before_head_anything_else;
				break;
		}

		if ( $is_closer ) {
			// Parse error: ignore the token.
			return $this->step();
		}

		/*
		 * > Anything else
		 *
		 * > Insert an HTML element for a "head" start tag token with no attributes.
		 */
		before_head_anything_else:
		$this->state->head_element   = $this->insert_virtual_node( 'HEAD' );
		$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_HEAD;
		return $this->step( self::REPROCESS_CURRENT_NODE );
	}

	/**
	 * Parses next element in the 'in head' insertion mode.
	 *
	 * This internal function performs the 'in head' insertion mode
	 * logic for the generalized WP_HTML_Processor::step() function.
	 *
	 * @since 6.7.0
	 *
	 * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
	 *
	 * @see https://html.spec.whatwg.org/multipage/parsing.html#parsing-main-inhead
	 * @see WP_HTML_Processor::step
	 *
	 * @return bool Whether an element was found.
	 */
	private function step_in_head(): bool {
		$token_name = $this->get_token_name();
		$token_type = $this->get_token_type();
		$is_closer  = parent::is_tag_closer();
		$op_sigil   = '#tag' === $token_type ? ( $is_closer ? '-' : '+' ) : '';
		$op         = "{$op_sigil}{$token_name}";

		switch ( $op ) {
			case '#text':
				/*
				 * > 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 ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) {
					// Insert the character.
					$this->insert_html_element( $this->state->current_token );
					return true;
				}

				goto in_head_anything_else;
				break;

			/*
			 * > A comment token
			 */
			case '#comment':
			case '#funky-comment':
			case '#presumptuous-tag':
				$this->insert_html_element( $this->state->current_token );
				return true;

			/*
			 * > A DOCTYPE token
			 */
			case 'html':
				// Parse error: ignore the token.
				return $this->step();

			/*
			 * > A start tag whose tag name is "html"
			 */
			case '+HTML':
				return $this->step_in_body();

			/*
			 * > A start tag whose tag name is one of: "base", "basefont", "bgsound", "link"
			 */
			case '+BASE':
			case '+BASEFONT':
			case '+BGSOUND':
			case '+LINK':
				$this->insert_html_element( $this->state->current_token );
				return true;

			/*
			 * > A start tag whose tag name is "meta"
			 */
			case '+META':
				$this->insert_html_element( $this->state->current_token );

				/*
				 * > If the active speculative HTML parser is null, then:
				 * >   - If the element has a charset attribute, and getting an encoding from
				 * >     its value results in an encoding, and the confidence is currently
				 * >     tentative, then change the encoding to the resulting encoding.
				 */
				$charset = $this->get_attribute( 'charset' );
				if ( is_string( $charset ) && 'tentative' === $this->state->encoding_confidence ) {
					$this->bail( 'Cannot yet process META tags with charset to determine encoding.' );
				}

				/*
				 * >   - Otherwise, if the element has an http-equiv attribute whose value is
				 * >     an ASCII case-insensitive match for the string "Content-Type", and
				 * >     the element has a content attribute, and applying the algorithm for
				 * >     extracting a character encoding from a meta element to that attribute's
				 * >     value returns an encoding, and the confidence is currently tentative,
				 * >     then change the encoding to the extracted encoding.
				 */
				$http_equiv = $this->get_attribute( 'http-equiv' );
				$content    = $this->get_attribute( 'content' );
				if (
					is_string( $http_equiv ) &&
					is_string( $content ) &&
					0 === strcasecmp( $http_equiv, 'Content-Type' ) &&
					'tentative' === $this->state->encoding_confidence
				) {
					$this->bail( 'Cannot yet process META tags with http-equiv Content-Type to determine encoding.' );
				}

				return true;

			/*
			 * > A start tag whose tag name is "title"
			 */
			case '+TITLE':
				$this->insert_html_element( $this->state->current_token );
				return true;

			/*
			 * > A start tag whose tag name is "noscript", if the scripting flag is enabled
			 * > A start tag whose tag name is one of: "noframes", "style"
			 *
			 * The scripting flag is never enabled in this parser.
			 */
			case '+NOFRAMES':
			case '+STYLE':
				$this->insert_html_element( $this->state->current_token );
				return true;

			/*
			 * > A start tag whose tag name is "noscript", if the scripting flag is disabled
			 */
			case '+NOSCRIPT':
				$this->insert_html_element( $this->state->current_token );
				$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_HEAD_NOSCRIPT;
				return true;

			/*
			 * > A start tag whose tag name is "script"
			 *
			 * @todo Could the adjusted insertion location be anything other than the current location?
			 */
			case '+SCRIPT':
				$this->insert_html_element( $this->state->current_token );
				return true;

			/*
			 * > An end tag whose tag name is "head"
			 */
			case '-HEAD':
				$this->state->stack_of_open_elements->pop();
				$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_AFTER_HEAD;
				return true;

			/*
			 * > An end tag whose tag name is one of: "body", "html", "br"
			 *
			 * BR tags are always reported by the Tag Processor as opening tags.
			 */
			case '-BODY':
			case '-HTML':
				/*
				 * > Act as described in the "anything else" entry below.
				 */
				goto in_head_anything_else;
				break;

			/*
			 * > A start tag whose tag name is "template"
			 *
			 * @todo Could the adjusted insertion location be anything other than the current location?
			 */
			case '+TEMPLATE':
				$this->state->active_formatting_elements->insert_marker();
				$this->state->frameset_ok = false;

				$this->state->insertion_mode                      = WP_HTML_Processor_State::INSERTION_MODE_IN_TEMPLATE;
				$this->state->stack_of_template_insertion_modes[] = WP_HTML_Processor_State::INSERTION_MODE_IN_TEMPLATE;

				$this->insert_html_element( $this->state->current_token );
				return true;

			/*
			 * > An end tag whose tag name is "template"
			 */
			case '-TEMPLATE':
				if ( ! $this->state->stack_of_open_elements->contains( 'TEMPLATE' ) ) {
					// @todo Indicate a parse error once it's possible.
					return $this->step();
				}

				$this->generate_implied_end_tags_thoroughly();
				if ( ! $this->state->stack_of_open_elements->current_node_is( 'TEMPLATE' ) ) {
					// @todo Indicate a parse error once it's possible.
				}

				$this->state->stack_of_open_elements->pop_until( 'TEMPLATE' );
				$this->state->active_formatting_elements->clear_up_to_last_marker();
				array_pop( $this->state->stack_of_template_insertion_modes );
				$this->reset_insertion_mode_appropriately();
				return true;
		}

		/*
		 * > A start tag whose tag name is "head"
		 * > Any other end tag
		 */
		if ( '+HEAD' === $op || $is_closer ) {
			// Parse error: ignore the token.
			return $this->step();
		}

		/*
		 * > Anything else
		 */
		in_head_anything_else:
		$this->state->stack_of_open_elements->pop();
		$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_AFTER_HEAD;
		return $this->step( self::REPROCESS_CURRENT_NODE );
	}

	/**
	 * Parses next element in the 'in head noscript' insertion mode.
	 *
	 * This internal function performs the 'in head noscript' insertion mode
	 * logic for the generalized WP_HTML_Processor::step() function.
	 *
	 * @since 6.7.0 Stub implementation.
	 *
	 * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
	 *
	 * @see https://html.spec.whatwg.org/#parsing-main-inheadnoscript
	 * @see WP_HTML_Processor::step
	 *
	 * @return bool Whether an element was found.
	 */
	private function step_in_head_noscript(): bool {
		$token_name = $this->get_token_name();
		$token_type = $this->get_token_type();
		$is_closer  = parent::is_tag_closer();
		$op_sigil   = '#tag' === $token_type ? ( $is_closer ? '-' : '+' ) : '';
		$op         = "{$op_sigil}{$token_name}";

		switch ( $op ) {
			/*
			 * > 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
			 *
			 * Parse error: ignore the token.
			 */
			case '#text':
				if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) {
					return $this->step_in_head();
				}

				goto in_head_noscript_anything_else;
				break;

			/*
			 * > A DOCTYPE token
			 */
			case 'html':
				// Parse error: ignore the token.
				return $this->step();

			/*
			 * > A start tag whose tag name is "html"
			 */
			case '+HTML':
				return $this->step_in_body();

			/*
			 * > An end tag whose tag name is "noscript"
			 */
			case '-NOSCRIPT':
				$this->state->stack_of_open_elements->pop();
				$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_HEAD;
				return true;

			/*
			 * > A comment token
			 * >
			 * > A start tag whose tag name is one of: "basefont", "bgsound",
			 * > "link", "meta", "noframes", "style"
			 */
			case '#comment':
			case '#funky-comment':
			case '#presumptuous-tag':
			case '+BASEFONT':
			case '+BGSOUND':
			case '+LINK':
			case '+META':
			case '+NOFRAMES':
			case '+STYLE':
				return $this->step_in_head();

			/*
			 * > An end tag whose tag name is "br"
			 *
			 * This should never happen, as the Tag Processor prevents showing a BR closing tag.
			 */
		}

		/*
		 * > A start tag whose tag name is one of: "head", "noscript"
		 * > Any other end tag
		 */
		if ( '+HEAD' === $op || '+NOSCRIPT' === $op || $is_closer ) {
			// Parse error: ignore the token.
			return $this->step();
		}

		/*
		 * > Anything else
		 *
		 * Anything here is a parse error.
		 */
		in_head_noscript_anything_else:
		$this->state->stack_of_open_elements->pop();
		$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_HEAD;
		return $this->step( self::REPROCESS_CURRENT_NODE );
	}

	/**
	 * Parses next element in the 'after head' insertion mode.
	 *
	 * This internal function performs the 'after head' insertion mode
	 * logic for the generalized WP_HTML_Processor::step() function.
	 *
	 * @since 6.7.0 Stub implementation.
	 *
	 * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
	 *
	 * @see https://html.spec.whatwg.org/#the-after-head-insertion-mode
	 * @see WP_HTML_Processor::step
	 *
	 * @return bool Whether an element was found.
	 */
	private function step_after_head(): bool {
		$token_name = $this->get_token_name();
		$token_type = $this->get_token_type();
		$is_closer  = parent::is_tag_closer();
		$op_sigil   = '#tag' === $token_type ? ( $is_closer ? '-' : '+' ) : '';
		$op         = "{$op_sigil}{$token_name}";

		switch ( $op ) {
			/*
			 * > 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
			 */
			case '#text':
				if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) {
					// Insert the character.
					$this->insert_html_element( $this->state->current_token );
					return true;
				}
				goto after_head_anything_else;
				break;

			/*
			 * > A comment token
			 */
			case '#comment':
			case '#funky-comment':
			case '#presumptuous-tag':
				$this->insert_html_element( $this->state->current_token );
				return true;

			/*
			 * > A DOCTYPE token
			 */
			case 'html':
				// Parse error: ignore the token.
				return $this->step();

			/*
			 * > A start tag whose tag name is "html"
			 */
			case '+HTML':
				return $this->step_in_body();

			/*
			 * > A start tag whose tag name is "body"
			 */
			case '+BODY':
				$this->insert_html_element( $this->state->current_token );
				$this->state->frameset_ok    = false;
				$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY;
				return true;

			/*
			 * > A start tag whose tag name is "frameset"
			 */
			case '+FRAMESET':
				$this->insert_html_element( $this->state->current_token );
				$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_FRAMESET;
				return true;

			/*
			 * > A start tag whose tag name is one of: "base", "basefont", "bgsound",
			 * > "link", "meta", "noframes", "script", "style", "template", "title"
			 *
			 * Anything here is a parse error.
			 */
			case '+BASE':
			case '+BASEFONT':
			case '+BGSOUND':
			case '+LINK':
			case '+META':
			case '+NOFRAMES':
			case '+SCRIPT':
			case '+STYLE':
			case '+TEMPLATE':
			case '+TITLE':
				/*
				 * > Push the node pointed to by the head element pointer onto the stack of open elements.
				 * > Process the token using the rules for the "in head" insertion mode.
				 * > Remove the node pointed to by the head element pointer from the stack of open elements. (It might not be the current node at this point.)
				 */
				$this->bail( 'Cannot process elements after HEAD which reopen the HEAD element.' );
				/*
				 * Do not leave this break in when adding support; it's here to prevent
				 * WPCS from getting confused at the switch structure without a return,
				 * because it doesn't know that `bail()` always throws.
				 */
				break;

			/*
			 * > An end tag whose tag name is "template"
			 */
			case '-TEMPLATE':
				return $this->step_in_head();

			/*
			 * > An end tag whose tag name is one of: "body", "html", "br"
			 *
			 * Closing BR tags are always reported by the Tag Processor as opening tags.
			 */
			case '-BODY':
			case '-HTML':
				/*
				 * > Act as described in the "anything else" entry below.
				 */
				goto after_head_anything_else;
				break;
		}

		/*
		 * > A start tag whose tag name is "head"
		 * > Any other end tag
		 */
		if ( '+HEAD' === $op || $is_closer ) {
			// Parse error: ignore the token.
			return $this->step();
		}

		/*
		 * > Anything else
		 * > Insert an HTML element for a "body" start tag token with no attributes.
		 */
		after_head_anything_else:
		$this->insert_virtual_node( 'BODY' );
		$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY;
		return $this->step( self::REPROCESS_CURRENT_NODE );
	}

	/**
	 * Parses next element in the 'in body' insertion mode.
	 *
	 * This internal function performs the 'in body' insertion mode
	 * logic for the generalized WP_HTML_Processor::step() function.
	 *
	 * @since 6.4.0
	 *
	 * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
	 *
	 * @see https://html.spec.whatwg.org/#parsing-main-inbody
	 * @see WP_HTML_Processor::step
	 *
	 * @return bool Whether an element was found.
	 */
	private function step_in_body(): bool {
		$token_name = $this->get_token_name();
		$token_type = $this->get_token_type();
		$op_sigil   = '#tag' === $token_type ? ( parent::is_tag_closer() ? '-' : '+' ) : '';
		$op         = "{$op_sigil}{$token_name}";

		switch ( $op ) {
			case '#text':
				/*
				 * > A character token that is U+0000 NULL
				 *
				 * Any successive sequence of NULL bytes is ignored and won't
				 * trigger active format reconstruction. Therefore, if the text
				 * only comprises NULL bytes then the token should be ignored
				 * here, but if there are any other characters in the stream
				 * the active formats should be reconstructed.
				 */
				if ( parent::TEXT_IS_NULL_SEQUENCE === $this->text_node_classification ) {
					// Parse error: ignore the token.
					return $this->step();
				}

				$this->reconstruct_active_formatting_elements();

				/*
				 * Whitespace-only text does not affect the frameset-ok flag.
				 * It is probably inter-element whitespace, but it may also
				 * contain character references which decode only to whitespace.
				 */
				if ( parent::TEXT_IS_GENERIC === $this->text_node_classification ) {
					$this->state->frameset_ok = false;
				}

				$this->insert_html_element( $this->state->current_token );
				return true;

			case '#comment':
			case '#funky-comment':
			case '#presumptuous-tag':
				$this->insert_html_element( $this->state->current_token );
				return true;

			/*
			 * > A DOCTYPE token
			 * > Parse error. Ignore the token.
			 */
			case 'html':
				return $this->step();

			/*
			 * > A start tag whose tag name is "html"
			 */
			case '+HTML':
				if ( ! $this->state->stack_of_open_elements->contains( 'TEMPLATE' ) ) {
					/*
					 * > Otherwise, for each attribute on the token, check to see if the attribute
					 * > is already present on the top element of the stack of open elements. If
					 * > it is not, add the attribute and its corresponding value to that element.
					 *
					 * This parser does not currently support this behavior: ignore the token.
					 */
				}

				// Ignore the token.
				return $this->step();

			/*
			 * > A start tag whose tag name is one of: "base", "basefont", "bgsound", "link",
			 * > "meta", "noframes", "script", "style", "template", "title"
			 * >
			 * > An end tag whose tag name is "template"
			 */
			case '+BASE':
			case '+BASEFONT':
			case '+BGSOUND':
			case '+LINK':
			case '+META':
			case '+NOFRAMES':
			case '+SCRIPT':
			case '+STYLE':
			case '+TEMPLATE':
			case '+TITLE':
			case '-TEMPLATE':
				return $this->step_in_head();

			/*
			 * > A start tag whose tag name is "body"
			 *
			 * This tag in the IN BODY insertion mode is a parse error.
			 */
			case '+BODY':
				if (
					1 === $this->state->stack_of_open_elements->count() ||
					'BODY' !== ( $this->state->stack_of_open_elements->at( 2 )->node_name ?? null ) ||
					$this->state->stack_of_open_elements->contains( 'TEMPLATE' )
				) {
					// Ignore the token.
					return $this->step();
				}

				/*
				 * > Otherwise, set the frameset-ok flag to "not ok"; then, for each attribute
				 * > on the token, check to see if the attribute is already present on the body
				 * > element (the second element) on the stack of open elements, and if it is
				 * > not, add the attribute and its corresponding value to that element.
				 *
				 * This parser does not currently support this behavior: ignore the token.
				 */
				$this->state->frameset_ok = false;
				return $this->step();

			/*
			 * > A start tag whose tag name is "frameset"
			 *
			 * This tag in the IN BODY insertion mode is a parse error.
			 */
			case '+FRAMESET':
				if (
					1 === $this->state->stack_of_open_elements->count() ||
					'BODY' !== ( $this->state->stack_of_open_elements->at( 2 )->node_name ?? null ) ||
					false === $this->state->frameset_ok
				) {
					// Ignore the token.
					return $this->step();
				}

				/*
				 * > Otherwise, run the following steps:
				 */
				$this->bail( 'Cannot process non-ignored FRAMESET tags.' );
				break;

			/*
			 * > An end tag whose tag name is "body"
			 */
			case '-BODY':
				if ( ! $this->state->stack_of_open_elements->has_element_in_scope( 'BODY' ) ) {
					// Parse error: ignore the token.
					return $this->step();
				}

				/*
				 * > 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 element,
				 * > a p element, an rb element, an rp element, an rt element, an rtc element, a tbody
				 * > element, a td element, a tfoot element, a th element, a thread element, a tr
				 * > element, the body element, or the html element, then this is a parse error.
				 *
				 * There is nothing to do for this parse error, so don't check for it.
				 */

				$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_AFTER_BODY;
				return true;

			/*
			 * > An end tag whose tag name is "html"
			 */
			case '-HTML':
				if ( ! $this->state->stack_of_open_elements->has_element_in_scope( 'BODY' ) ) {
					// Parse error: ignore the token.
					return $this->step();
				}

				/*
				 * > 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 element,
				 * > a p element, an rb element, an rp element, an rt element, an rtc element, a tbody
				 * > element, a td element, a tfoot element, a th element, a thread element, a tr
				 * > element, the body element, or the html element, then this is a parse error.
				 *
				 * There is nothing to do for this parse error, so don't check for it.
				 */

				$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_AFTER_BODY;
				return $this->step( self::REPROCESS_CURRENT_NODE );

			/*
			 * > A start tag whose tag name is one of: "address", "article", "aside",
			 * > "blockquote", "center", "details", "dialog", "dir", "div", "dl",
			 * > "fieldset", "figcaption", "figure", "footer", "header", "hgroup",
			 * > "main", "menu", "nav", "ol", "p", "search", "section", "summary", "ul"
			 */
			case '+ADDRESS':
			case '+ARTICLE':
			case '+ASIDE':
			case '+BLOCKQUOTE':
			case '+CENTER':
			case '+DETAILS':
			case '+DIALOG':
			case '+DIR':
			case '+DIV':
			case '+DL':
			case '+FIELDSET':
			case '+FIGCAPTION':
			case '+FIGURE':
			case '+FOOTER':
			case '+HEADER':
			case '+HGROUP':
			case '+MAIN':
			case '+MENU':
			case '+NAV':
			case '+OL':
			case '+P':
			case '+SEARCH':
			case '+SECTION':
			case '+SUMMARY':
			case '+UL':
				if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
					$this->close_a_p_element();
				}

				$this->insert_html_element( $this->state->current_token );
				return true;

			/*
			 * > A start tag whose tag name is one of: "h1", "h2", "h3", "h4", "h5", "h6"
			 */
			case '+H1':
			case '+H2':
			case '+H3':
			case '+H4':
			case '+H5':
			case '+H6':
				if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
					$this->close_a_p_element();
				}

				if (
					in_array(
						$this->state->stack_of_open_elements->current_node()->node_name,
						array( 'H1', 'H2', 'H3', 'H4', 'H5', 'H6' ),
						true
					)
				) {
					// @todo Indicate a parse error once it's possible.
					$this->state->stack_of_open_elements->pop();
				}

				$this->insert_html_element( $this->state->current_token );
				return true;

			/*
			 * > A start tag whose tag name is one of: "pre", "listing"
			 */
			case '+PRE':
			case '+LISTING':
				if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
					$this->close_a_p_element();
				}

				/*
				 * > If the next token is a U+000A LINE FEED (LF) character token,
				 * > then ignore that token and move on to the next one. (Newlines
				 * > at the start of pre blocks are ignored as an authoring convenience.)
				 *
				 * This is handled in `get_modifiable_text()`.
				 */

				$this->insert_html_element( $this->state->current_token );
				$this->state->frameset_ok = false;
				return true;

			/*
			 * > A start tag whose tag name is "form"
			 */
			case '+FORM':
				$stack_contains_template = $this->state->stack_of_open_elements->contains( 'TEMPLATE' );

				if ( isset( $this->state->form_element ) && ! $stack_contains_template ) {
					// Parse error: ignore the token.
					return $this->step();
				}

				if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
					$this->close_a_p_element();
				}

				$this->insert_html_element( $this->state->current_token );
				if ( ! $stack_contains_template ) {
					$this->state->form_element = $this->state->current_token;
				}

				return true;

			/*
			 * > A start tag whose tag name is "li"
			 * > A start tag whose tag name is one of: "dd", "dt"
			 */
			case '+DD':
			case '+DT':
			case '+LI':
				$this->state->frameset_ok = false;
				$node                     = $this->state->stack_of_open_elements->current_node();
				$is_li                    = 'LI' === $token_name;

				in_body_list_loop:
				/*
				 * The logic for LI and DT/DD is the same except for one point: LI elements _only_
				 * close other LI elements, but a DT or DD element closes _any_ open DT or DD element.
				 */
				if ( $is_li ? 'LI' === $node->node_name : ( 'DD' === $node->node_name || 'DT' === $node->node_name ) ) {
					$node_name = $is_li ? 'LI' : $node->node_name;
					$this->generate_implied_end_tags( $node_name );
					if ( ! $this->state->stack_of_open_elements->current_node_is( $node_name ) ) {
						// @todo Indicate a parse error once it's possible. This error does not impact the logic here.
					}

					$this->state->stack_of_open_elements->pop_until( $node_name );
					goto in_body_list_done;
				}

				if (
					'ADDRESS' !== $node->node_name &&
					'DIV' !== $node->node_name &&
					'P' !== $node->node_name &&
					self::is_special( $node )
				) {
					/*
					 * > If node is in the special category, but is not an address, div,
					 * > or p element, then jump to the step labeled done below.
					 */
					goto in_body_list_done;
				} else {
					/*
					 * > Otherwise, set node to the previous entry in the stack of open elements
					 * > and return to the step labeled loop.
					 */
					foreach ( $this->state->stack_of_open_elements->walk_up( $node ) as $item ) {
						$node = $item;
						break;
					}
					goto in_body_list_loop;
				}

				in_body_list_done:
				if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
					$this->close_a_p_element();
				}

				$this->insert_html_element( $this->state->current_token );
				return true;

			case '+PLAINTEXT':
				if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
					$this->close_a_p_element();
				}

				/*
				 * @todo This may need to be handled in the Tag Processor and turn into
				 *       a single self-contained tag like TEXTAREA, whose modifiable text
				 *       is the rest of the input document as plaintext.
				 */
				$this->bail( 'Cannot process PLAINTEXT elements.' );
				break;

			/*
			 * > A start tag whose tag name is "button"
			 */
			case '+BUTTON':
				if ( $this->state->stack_of_open_elements->has_element_in_scope( 'BUTTON' ) ) {
					// @todo Indicate a parse error once it's possible. This error does not impact the logic here.
					$this->generate_implied_end_tags();
					$this->state->stack_of_open_elements->pop_until( 'BUTTON' );
				}

				$this->reconstruct_active_formatting_elements();
				$this->insert_html_element( $this->state->current_token );
				$this->state->frameset_ok = false;

				return true;

			/*
			 * > An end tag whose tag name is one of: "address", "article", "aside", "blockquote",
			 * > "button", "center", "details", "dialog", "dir", "div", "dl", "fieldset",
			 * > "figcaption", "figure", "footer", "header", "hgroup", "listing", "main",
			 * > "menu", "nav", "ol", "pre", "search", "section", "summary", "ul"
			 */
			case '-ADDRESS':
			case '-ARTICLE':
			case '-ASIDE':
			case '-BLOCKQUOTE':
			case '-BUTTON':
			case '-CENTER':
			case '-DETAILS':
			case '-DIALOG':
			case '-DIR':
			case '-DIV':
			case '-DL':
			case '-FIELDSET':
			case '-FIGCAPTION':
			case '-FIGURE':
			case '-FOOTER':
			case '-HEADER':
			case '-HGROUP':
			case '-LISTING':
			case '-MAIN':
			case '-MENU':
			case '-NAV':
			case '-OL':
			case '-PRE':
			case '-SEARCH':
			case '-SECTION':
			case '-SUMMARY':
			case '-UL':
				if ( ! $this->state->stack_of_open_elements->has_element_in_scope( $token_name ) ) {
					// @todo Report parse error.
					// Ignore the token.
					return $this->step();
				}

				$this->generate_implied_end_tags();
				if ( ! $this->state->stack_of_open_elements->current_node_is( $token_name ) ) {
					// @todo Record parse error: this error doesn't impact parsing.
				}
				$this->state->stack_of_open_elements->pop_until( $token_name );
				return true;

			/*
			 * > An end tag whose tag name is "form"
			 */
			case '-FORM':
				if ( ! $this->state->stack_of_open_elements->contains( 'TEMPLATE' ) ) {
					$node                      = $this->state->form_element;
					$this->state->form_element = null;

					/*
					 * > If node is null or if the stack of open elements does not have node
					 * > in scope, then this is a parse error; return and ignore the token.
					 *
					 * @todo It's necessary to check if the form token itself is in scope, not
					 *       simply whether any FORM is in scope.
					 */
					if (
						null === $node ||
						! $this->state->stack_of_open_elements->has_element_in_scope( 'FORM' )
					) {
						// Parse error: ignore the token.
						return $this->step();
					}

					$this->generate_implied_end_tags();
					if ( $node !== $this->state->stack_of_open_elements->current_node() ) {
						// @todo Indicate a parse error once it's possible. This error does not impact the logic here.
						$this->bail( 'Cannot close a FORM when other elements remain open as this would throw off the breadcrumbs for the following tokens.' );
					}

					$this->state->stack_of_open_elements->remove_node( $node );
					return true;
				} else {
					/*
					 * > If the stack of open elements does not have a form element in scope,
					 * > then this is a parse error; return and ignore the token.
					 *
					 * Note that unlike in the clause above, this is checking for any FORM in scope.
					 */
					if ( ! $this->state->stack_of_open_elements->has_element_in_scope( 'FORM' ) ) {
						// Parse error: ignore the token.
						return $this->step();
					}

					$this->generate_implied_end_tags();

					if ( ! $this->state->stack_of_open_elements->current_node_is( 'FORM' ) ) {
						// @todo Indicate a parse error once it's possible. This error does not impact the logic here.
					}

					$this->state->stack_of_open_elements->pop_until( 'FORM' );
					return true;
				}
				break;

			/*
			 * > An end tag whose tag name is "p"
			 */
			case '-P':
				if ( ! $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
					$this->insert_html_element( $this->state->current_token );
				}

				$this->close_a_p_element();
				return true;

			/*
			 * > An end tag whose tag name is "li"

View all references View on Trac View on GitHub