@var string|null
	 */
	private $sought_tag_name;

	/**
	 * The CSS class name this processor currently scans for.
	 *
	 * @since 6.2.0
	 * @var string|null
	 */
	private $sought_class_name;

	/**
	 * The match offset this processor currently scans for.
	 *
	 * @since 6.2.0
	 * @var int|null
	 */
	private $sought_match_offset;

	/**
	 * Whether to visit tag closers, e.g. </div>, when walking an input document.
	 *
	 * @since 6.2.0
	 * @var bool
	 */
	private $stop_on_tag_closers;

	/**
	 * Specifies mode of operation of the parser at any given time.
	 *
	 * | State           | Meaning                                                              |
	 * | ----------------|----------------------------------------------------------------------|
	 * | *Ready*         | The parser is ready to run.                                          |
	 * | *Complete*      | There is nothing left to parse.                                      |
	 * | *Incomplete*    | The HTML ended in the middle of a token; nothing more can be parsed. |
	 * | *Matched tag*   | Found an HTML tag; it's possible to modify its attributes.           |
	 * | *Text node*     | Found a #text node; this is plaintext and modifiable.                |
	 * | *CDATA node*    | Found a CDATA section; this is modifiable.                           |
	 * | *Comment*       | Found a comment or bogus comment; this is modifiable.                |
	 * | *Presumptuous*  | Found an empty tag closer: `</>`.                                    |
	 * | *Funky comment* | Found a tag closer with an invalid tag name; this is modifiable.     |
	 *
	 * @since 6.5.0
	 *
	 * @see WP_HTML_Tag_Processor::STATE_READY
	 * @see WP_HTML_Tag_Processor::STATE_COMPLETE
	 * @see WP_HTML_Tag_Processor::STATE_INCOMPLETE_INPUT
	 * @see WP_HTML_Tag_Processor::STATE_MATCHED_TAG
	 * @see WP_HTML_Tag_Processor::STATE_TEXT_NODE
	 * @see WP_HTML_Tag_Processor::STATE_CDATA_NODE
	 * @see WP_HTML_Tag_Processor::STATE_COMMENT
	 * @see WP_HTML_Tag_Processor::STATE_DOCTYPE
	 * @see WP_HTML_Tag_Processor::STATE_PRESUMPTUOUS_TAG
	 * @see WP_HTML_Tag_Processor::STATE_FUNKY_COMMENT
	 *
	 * @var string
	 */
	protected $parser_state = self::STATE_READY;

	/**
	 * What kind of syntax token became an HTML comment.
	 *
	 * Since there are many ways in which HTML syntax can create an HTML comment,
	 * this indicates which of those caused it. This allows the Tag Processor to
	 * represent more from the original input document than would appear in the DOM.
	 *
	 * @since 6.5.0
	 *
	 * @var string|null
	 */
	protected $comment_type = null;

	/**
	 * How many bytes from the original HTML document have been read and parsed.
	 *
	 * This value points to the latest byte offset in the input document which
	 * has been already parsed. It is the internal cursor for the Tag Processor
	 * and updates while scanning through the HTML tokens.
	 *
	 * @since 6.2.0
	 * @var int
	 */
	private $bytes_already_parsed = 0;

	/**
	 * Byte offset in input document where current token starts.
	 *
	 * Example:
	 *
	 *     <div id="test">...
	 *     01234
	 *     - token starts at 0
	 *
	 * @since 6.5.0
	 *
	 * @var int|null
	 */
	private $token_starts_at;

	/**
	 * Byte length of current token.
	 *
	 * Example:
	 *
	 *     <div id="test">...
	 *     012345678901234
	 *     - token length is 14 - 0 = 14
	 *
	 *     a <!-- comment --> is a token.
	 *     0123456789 123456789 123456789
	 *     - token length is 17 - 2 = 15
	 *
	 * @since 6.5.0
	 *
	 * @var int|null
	 */
	private $token_length;

	/**
	 * Byte offset in input document where current tag name starts.
	 *
	 * Example:
	 *
	 *     <div id="test">...
	 *     01234
	 *      - tag name starts at 1
	 *
	 * @since 6.2.0
	 *
	 * @var int|null
	 */
	private $tag_name_starts_at;

	/**
	 * Byte length of current tag name.
	 *
	 * Example:
	 *
	 *     <div id="test">...
	 *     01234
	 *      --- tag name length is 3
	 *
	 * @since 6.2.0
	 *
	 * @var int|null
	 */
	private $tag_name_length;

	/**
	 * Byte offset into input document where current modifiable text starts.
	 *
	 * @since 6.5.0
	 *
	 * @var int
	 */
	private $text_starts_at;

	/**
	 * Byte length of modifiable text.
	 *
	 * @since 6.5.0
	 *
	 * @var string
	 */
	private $text_length;

	/**
	 * Whether the current tag is an opening tag, e.g. <div>, or a closing tag, e.g. </div>.
	 *
	 * @var bool
	 */
	private $is_closing_tag;

	/**
	 * Lazily-built index of attributes found within an HTML tag, keyed by the attribute name.
	 *
	 * Example:
	 *
	 *     // Supposing the parser is working through this content
	 *     // and stops after recognizing the `id` attribute.
	 *     // <div id="test-4" class=outline title="data:text/plain;base64=asdk3nk1j3fo8">
	 *     //                 ^ parsing will continue from this point.
	 *     $this->attributes = array(
	 *         'id' => new WP_HTML_Attribute_Token( 'id', 9, 6, 5, 11, false )
	 *     );
	 *
	 *     // When picking up parsing again, or when asking to find the
	 *     // `class` attribute we will continue and add to this array.
	 *     $this->attributes = array(
	 *         'id'    => new WP_HTML_Attribute_Token( 'id', 9, 6, 5, 11, false ),
	 *         'class' => new WP_HTML_Attribute_Token( 'class', 23, 7, 17, 13, false )
	 *     );
	 *
	 *     // Note that only the `class` attribute value is stored in the index.
	 *     // That's because it is the only value used by this class at the moment.
	 *
	 * @since 6.2.0
	 * @var WP_HTML_Attribute_Token[]
	 */
	private $attributes = array();

	/**
	 * Tracks spans of duplicate attributes on a given tag, used for removing
	 * all copies of an attribute when calling `remove_attribute()`.
	 *
	 * @since 6.3.2
	 *
	 * @var (WP_HTML_Span[])[]|null
	 */
	private $duplicate_attributes = null;

	/**
	 * Which class names to add or remove from a tag.
	 *
	 * These are tracked separately from attribute updates because they are
	 * semantically distinct, whereas this interface exists for the common
	 * case of adding and removing class names while other attributes are
	 * generally modified as with DOM `setAttribute` calls.
	 *
	 * When modifying an HTML document these will eventually be collapsed
	 * into a single `set_attribute( 'class', $changes )` call.
	 *
	 * Example:
	 *
	 *     // Add the `wp-block-group` class, remove the `wp-group` class.
	 *     $classname_updates = array(
	 *         // Indexed by a comparable class name.
	 *         'wp-block-group' => WP_HTML_Tag_Processor::ADD_CLASS,
	 *         'wp-group'       => WP_HTML_Tag_Processor::REMOVE_CLASS
	 *     );
	 *
	 * @since 6.2.0
	 * @var bool[]
	 */
	private $classname_updates = array();

	/**
	 * Tracks a semantic location in the original HTML which
	 * shifts with updates as they are applied to the document.
	 *
	 * @since 6.2.0
	 * @var WP_HTML_Span[]
	 */
	protected $bookmarks = array();

	const ADD_CLASS    = true;
	const REMOVE_CLASS = false;
	const SKIP_CLASS   = null;

	/**
	 * Lexical replacements to apply to input HTML document.
	 *
	 * "Lexical" in this class refers to the part of this class which
	 * operates on pure text _as text_ and not as HTML. There's a line
	 * between the public interface, with HTML-semantic methods like
	 * `set_attribute` and `add_class`, and an internal state that tracks
	 * text offsets in the input document.
	 *
	 * When higher-level HTML methods are called, those have to transform their
	 * operations (such as setting an attribute's value) into text diffing
	 * operations (such as replacing the sub-string from indices A to B with
	 * some given new string). These text-diffing operations are the lexical
	 * updates.
	 *
	 * As new higher-level methods are added they need to collapse their
	 * operations into these lower-level lexical updates since that's the
	 * Tag Processor's internal language of change. Any code which creates
	 * these lexical updates must ensure that they do not cross HTML syntax
	 * boundaries, however, so these should never be exposed outside of this
	 * class or any classes which intentionally expand its functionality.
	 *
	 * These are enqueued while editing the document instead of being immediately
	 * applied to avoid processing overhead, string allocations, and string
	 * copies when applying many updates to a single document.
	 *
	 * Example:
	 *
	 *     // Replace an attribute stored with a new value, indices
	 *     // sourced from the lazily-parsed HTML recognizer.
	 *     $start  = $attributes['src']->start;
	 *     $length = $attributes['src']->length;
	 *     $modifications[] = new WP_HTML_Text_Replacement( $start, $length, $new_value );
	 *
	 *     // Correspondingly, something like this will appear in this array.
	 *     $lexical_updates = array(
	 *         WP_HTML_Text_Replacement( 14, 28, 'https://my-site.my-domain/wp-content/uploads/2014/08/kittens.jpg' )
	 *     );
	 *
	 * @since 6.2.0
	 * @var WP_HTML_Text_Replacement[]
	 */
	protected $lexical_updates = array();

	/**
	 * Tracks and limits `seek()` calls to prevent accidental infinite loops.
	 *
	 * @since 6.2.0
	 * @var int
	 *
	 * @see WP_HTML_Tag_Processor::seek()
	 */
	protected $seek_count = 0;

	/**
	 * Constructor.
	 *
	 * @since 6.2.0
	 *
	 * @param string $html HTML to process.
	 */
	public function __construct( $html ) {
		$this->html = $html;
	}

	/**
	 * Finds the next tag matching the $query.
	 *
	 * @since 6.2.0
	 * @since 6.5.0 No longer processes incomplete tokens at end of document; pauses the processor at start of token.
	 *
	 * @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 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|null $tag_closers  "visit" or "skip": whether to stop on tag closers, e.g. </div>.
	 * }
	 * @return bool Whether a tag was matched.
	 */
	public function next_tag( $query = null ) {
		$this->parse_query( $query );
		$already_found = 0;

		do {
			if ( false === $this->next_token() ) {
				return false;
			}

			if ( self::STATE_MATCHED_TAG !== $this->parser_state ) {
				continue;
			}

			if ( $this->matches() ) {
				++$already_found;
			}
		} while ( $already_found < $this->sought_match_offset );

		return true;
	}

	/**
	 * Finds the next token in the HTML document.
	 *
	 * An HTML document can be viewed as a stream of tokens,
	 * where tokens are things like HTML tags, HTML comments,
	 * text nodes, etc. This method finds the next token in
	 * the HTML document and returns whether it found one.
	 *
	 * If it starts parsing a token and reaches the end of the
	 * document then it will seek to the start of the last
	 * token and pause, returning `false` to indicate that it
	 * failed to find a complete token.
	 *
	 * Possible token types, based on the HTML specification:
	 *
	 *  - an HTML tag, whether opening, closing, or void.
	 *  - a text node - the plaintext inside tags.
	 *  - an HTML comment.
	 *  - a DOCTYPE declaration.
	 *  - a processing instruction, e.g. `<?xml version="1.0" ?>`.
	 *
	 * The Tag Processor currently only supports the tag token.
	 *
	 * @since 6.5.0
	 *
	 * @return bool Whether a token was parsed.
	 */
	public function next_token() {
		return $this->base_class_next_token();
	}

	/**
	 * Internal method which finds the next token in the HTML document.
	 *
	 * This method is a protected internal function which implements the logic for
	 * finding the next token in a document. It exists so that the parser can update
	 * its state without affecting the location of the cursor in the document and
	 * without triggering subclass methods for things like `next_token()`, e.g. when
	 * applying patches before searching for the next token.
	 *
	 * @since 6.5.0
	 *
	 * @access private
	 *
	 * @return bool Whether a token was parsed.
	 */
	private function base_class_next_token() {
		$was_at = $this->bytes_already_parsed;
		$this->after_tag();

		// Don't proceed if there's nothing more to scan.
		if (
			self::STATE_COMPLETE === $this->parser_state ||
			self::STATE_INCOMPLETE_INPUT === $this->parser_state
		) {
			return false;
		}

		/*
		 * The next step in the parsing loop determines the parsing state;
		 * clear it so that state doesn't linger from the previous step.
		 */
		$this->parser_state = self::STATE_READY;

		if ( $this->bytes_already_parsed >= strlen( $this->html ) ) {
			$this->parser_state = self::STATE_COMPLETE;
			return false;
		}

		// Find the next tag if it exists.
		if ( false === $this->parse_next_tag() ) {
			if ( self::STATE_INCOMPLETE_INPUT === $this->parser_state ) {
				$this->bytes_already_parsed = $was_at;
			}

			return false;
		}

		/*
		 * For legacy reasons the rest of this function handles tags and their
		 * attributes. If the processor has reached the end of the document
		 * or if it matched any other token then it should return here to avoid
		 * attempting to process tag-specific syntax.
		 */
		if (
			self::STATE_INCOMPLETE_INPUT !== $this->parser_state &&
			self::STATE_COMPLETE !== $this->parser_state &&
			self::STATE_MATCHED_TAG !== $this->parser_state
		) {
			return true;
		}

		// Parse all of its attributes.
		while ( $this->parse_next_attribute() ) {
			continue;
		}

		// Ensure that the tag closes before the end of the document.
		if (
			self::STATE_INCOMPLETE_INPUT === $this->parser_state ||
			$this->bytes_already_parsed >= strlen( $this->html )
		) {
			// Does this appropriately clear state (parsed attributes)?
			$this->parser_state         = self::STATE_INCOMPLETE_INPUT;
			$this->bytes_already_parsed = $was_at;

			return false;
		}

		$tag_ends_at = strpos( $this->html, '>', $this->bytes_already_parsed );
		if ( false === $tag_ends_at ) {
			$this->parser_state         = self::STATE_INCOMPLETE_INPUT;
			$this->bytes_already_parsed = $was_at;

			return false;
		}
		$this->parser_state         = self::STATE_MATCHED_TAG;
		$this->bytes_already_parsed = $tag_ends_at + 1;
		$this->token_length         = $this->bytes_already_parsed - $this->token_starts_at;

		/*
		 * For non-DATA sections which might contain text that looks like HTML tags but
		 * isn't, scan with the appropriate alternative mode. Looking at the first letter
		 * of the tag name as a pre-check avoids a string allocation when it's not needed.
		 */
		$t = $this->html[ $this->tag_name_starts_at ];
		if (
			$this->is_closing_tag ||
			! (
				'i' === $t || 'I' === $t ||
				'n' === $t || 'N' === $t ||
				's' === $t || 'S' === $t ||
				't' === $t || 'T' === $t ||
				'x' === $t || 'X' === $t
			)
		) {
			return true;
		}

		$tag_name = $this->get_tag();

		/*
		 * Preserve the opening tag pointers, as these will be overwritten
		 * when finding the closing tag. They will be reset after finding
		 * the closing to tag to point to the opening of the special atomic
		 * tag sequence.
		 */
		$tag_name_starts_at   = $this->tag_name_starts_at;
		$tag_name_length      = $this->tag_name_length;
		$tag_ends_at          = $this->token_starts_at + $this->token_length;
		$attributes           = $this->attributes;
		$duplicate_attributes = $this->duplicate_attributes;

		// Find the closing tag if necessary.
		$found_closer = false;
		switch ( $tag_name ) {
			case 'SCRIPT':
				$found_closer = $this->skip_script_data();
				break;

			case 'TEXTAREA':
			case 'TITLE':
				$found_closer = $this->skip_rcdata( $tag_name );
				break;

			/*
			 * In the browser this list would include the NOSCRIPT element,
			 * but the Tag Processor is an environment with the scripting
			 * flag disabled, meaning that it needs to descend into the
			 * NOSCRIPT element to be able to properly process what will be
			 * sent to a browser.
			 *
			 * Note that this rule makes HTML5 syntax incompatible with XML,
			 * because the parsing of this token depends on client application.
			 * The NOSCRIPT element cannot be represented in the XHTML syntax.
			 */
			case 'IFRAME':
			case 'NOEMBED':
			case 'NOFRAMES':
			case 'STYLE':
			case 'XMP':
				$found_closer = $this->skip_rawtext( $tag_name );
				break;

			// No other tags should be treated in their entirety here.
			default:
				return true;
		}

		if ( ! $found_closer ) {
			$this->parser_state         = self::STATE_INCOMPLETE_INPUT;
			$this->bytes_already_parsed = $was_at;
			return false;
		}

		/*
		 * The values here look like they reference the opening tag but they reference
		 * the closing tag instead. This is why the opening tag values were stored
		 * above in a variable. It reads confusingly here, but that's because the
		 * functions that skip the contents have moved all the internal cursors past
		 * the inner content of the tag.
		 */
		$this->token_starts_at      = $was_at;
		$this->token_length         = $this->bytes_already_parsed - $this->token_starts_at;
		$this->text_starts_at       = $tag_ends_at;
		$this->text_length          = $this->tag_name_starts_at - $this->text_starts_at;
		$this->tag_name_starts_at   = $tag_name_starts_at;
		$this->tag_name_length      = $tag_name_length;
		$this->attributes           = $attributes;
		$this->duplicate_attributes = $duplicate_attributes;

		return true;
	}

	/**
	 * Whether the processor paused because the input HTML document ended
	 * in the middle of a syntax element, such as in the middle of a tag.
	 *
	 * Example:
	 *
	 *     $processor = new WP_HTML_Tag_Processor( '<input type="text" value="Th' );
	 *     false      === $processor->get_next_tag();
	 *     true       === $processor->paused_at_incomplete_token();
	 *
	 * @since 6.5.0
	 *
	 * @return bool Whether the parse paused at the start of an incomplete token.
	 */
	public function paused_at_incomplete_token() {
		return self::STATE_INCOMPLETE_INPUT === $this->parser_state;
	}

	/**
	 * Generator for a foreach loop to step through each class name for the matched tag.
	 *
	 * This generator function is designed to be used inside a "foreach" loop.
	 *
	 * Example:
	 *
	 *     $p = new WP_HTML_Tag_Processor( "<div class='free &lt;egg&lt;\tlang-en'>" );
	 *     $p->next_tag();
	 *     foreach ( $p->class_list() as $class_name ) {
	 *         echo "{$class_name} ";
	 *     }
	 *     // Outputs: "free <egg> lang-en "
	 *
	 * @since 6.4.0
	 */
	public function class_list() {
		if ( self::STATE_MATCHED_TAG !== $this->parser_state ) {
			return;
		}

		/** @var string $class contains the string value of the class attribute, with character references decoded. */
		$class = $this->get_attribute( 'class' );

		if ( ! is_string( $class ) ) {
			return;
		}

		$seen = array();

		$at = 0;
		while ( $at < strlen( $class ) ) {
			// Skip past any initial boundary characters.
			$at += strspn( $class, " \t\f\r\n", $at );
			if ( $at >= strlen( $class ) ) {
				return;
			}

			// Find the byte length until the next boundary.
			$length = strcspn( $class, " \t\f\r\n", $at );
			if ( 0 === $length ) {
				return;
			}

			/*
			 * CSS class names are case-insensitive in the ASCII range.
			 *
			 * @see https://www.w3.org/TR/CSS2/syndata.html#x1
			 */
			$name = strtolower( substr( $class, $at, $length ) );
			$at  += $length;

			/*
			 * It's expected that the number of class names for a given tag is relatively small.
			 * Given this, it is probably faster overall to scan an array for a value rather
			 * than to use the class name as a key and check if it's a key of $seen.
			 */
			if ( in_array( $name, $seen, true ) ) {
				continue;
			}

			$seen[] = $name;
			yield $name;
		}
	}


	/**
	 * Returns if a matched tag contains the given ASCII case-insensitive class name.
	 *
	 * @since 6.4.0
	 *
	 * @param string $wanted_class Look for this CSS class name, ASCII case-insensitive.
	 * @return bool|null Whether the matched tag contains the given class name, or null if not matched.
	 */
	public function has_class( $wanted_class ) {
		if ( self::STATE_MATCHED_TAG !== $this->parser_state ) {
			return null;
		}

		$wanted_class = strtolower( $wanted_class );

		foreach ( $this->class_list() as $class_name ) {
			if ( $class_name === $wanted_class ) {
				return true;
			}
		}

		return false;
	}


	/**
	 * Sets a bookmark in the HTML document.
	 *
	 * Bookmarks represent specific places or tokens in the HTML
	 * document, such as a tag opener or closer. When applying
	 * edits to a document, such as setting an attribute, the
	 * text offsets of that token may shift; the bookmark is
	 * kept updated with those shifts and remains stable unless
	 * the entire span of text in which the token sits is removed.
	 *
	 * Release bookmarks when they are no longer needed.
	 *
	 * Example:
	 *
	 *     <main><h2>Surprising fact you may not know!</h2></main>
	 *           ^  ^
	 *            \-|-- this `H2` opener bookmark tracks the token
	 *
	 *     <main class="clickbait"><h2>Surprising fact you may no…
	 *                             ^  ^
	 *                              \-|-- it shifts with edits
	 *
	 * Bookmarks provide the ability to seek to a previously-scanned
	 * place in the HTML document. This avoids the need to re-scan
	 * the entire document.
	 *
	 * Example:
	 *
	 *     <ul><li>One</li><li>Two</li><li>Three</li></ul>
	 *                                 ^^^^
	 *                                 want to note this last item
	 *
	 *     $p = new WP_HTML_Tag_Processor( $html );
	 *     $in_list = false;
	 *     while ( $p->next_tag( array( 'tag_closers' => $in_list ? 'visit' : 'skip' ) ) ) {
	 *         if ( 'UL' === $p->get_tag() ) {
	 *             if ( $p->is_tag_closer() ) {
	 *                 $in_list = false;
	 *                 $p->set_bookmark( 'resume' );
	 *                 if ( $p->seek( 'last-li' ) ) {
	 *                     $p->add_class( 'last-li' );
	 *                 }
	 *                 $p->seek( 'resume' );
	 *                 $p->release_bookmark( 'last-li' );
	 *                 $p->release_bookmark( 'resume' );
	 *             } else {
	 *                 $in_list = true;
	 *             }
	 *         }
	 *
	 *         if ( 'LI' === $p->get_tag() ) {
	 *             $p->set_bookmark( 'last-li' );
	 *         }
	 *     }
	 *
	 * Bookmarks intentionally hide the internal string offsets
	 * to which they refer. They are maintained internally as
	 * updates are applied to the HTML document and therefore
	 * retain their "position" - the location to which they
	 * originally pointed. The inability to use bookmarks with
	 * functions like `substr` is therefore intentional to guard
	 * against accidentally breaking the HTML.
	 *
	 * Because bookmarks allocate memory and require processing
	 * for every applied update, they are limited and require
	 * a name. They should not be created with programmatically-made
	 * names, such as "li_{$index}" with some loop. As a general
	 * rule they should only be created with string-literal names
	 * like "start-of-section" or "last-paragraph".
	 *
	 * Bookmarks are a powerful tool to enable complicated behavior.
	 * Consider double-checking that you need this tool if you are
	 * reaching for it, as inappropriate use could lead to broken
	 * HTML structure or unwanted processing overhead.
	 *
	 * @since 6.2.0
	 *
	 * @param string $name Identifies this particular bookmark.
	 * @return bool Whether the bookmark was successfully created.
	 */
	public function set_bookmark( $name ) {
		// It only makes sense to set a bookmark if the parser has paused on a concrete token.
		if (
			self::STATE_COMPLETE === $this->parser_state ||
			self::STATE_INCOMPLETE_INPUT === $this->parser_state
		) {
			return false;
		}

		if ( ! array_key_exists( $name, $this->bookmarks ) && count( $this->bookmarks ) >= static::MAX_BOOKMARKS ) {
			_doing_it_wrong(
				__METHOD__,
				__( 'Too many bookmarks: cannot create any more.' ),
				'6.2.0'
			);
			return false;
		}

		$this->bookmarks[ $name ] = new WP_HTML_Span( $this->token_starts_at, $this->token_length );

		return true;
	}


	/**
	 * Removes a bookmark that is no longer needed.
	 *
	 * Releasing a bookmark frees up the small
	 * performance overhead it requires.
	 *
	 * @param string $name Name of the bookmark to remove.
	 * @return bool Whether the bookmark already existed before removal.
	 */
	public function release_bookmark( $name ) {
		if ( ! array_key_exists( $name, $this->bookmarks ) ) {
			return false;
		}

		unset( $this->bookmarks[ $name ] );

		return true;
	}

	/**
	 * Skips contents of generic rawtext elements.
	 *
	 * @since 6.3.2
	 *
	 * @see https://html.spec.whatwg.org/#generic-raw-text-element-parsing-algorithm
	 *
	 * @param string $tag_name The uppercase tag name which will close the RAWTEXT region.
	 * @return bool Whether an end to the RAWTEXT region was found before the end of the document.
	 */
	private function skip_rawtext( $tag_name ) {
		/*
		 * These two functions distinguish themselves on whether character references are
		 * decoded, and since functionality to read the inner markup isn't supported, it's
		 * not necessary to implement these two functions separately.
		 */
		return $this->skip_rcdata( $tag_name );
	}

	/**
	 * Skips contents of RCDATA elements, namely title and textarea tags.
	 *
	 * @since 6.2.0
	 *
	 * @see https://html.spec.whatwg.org/multipage/parsing.html#rcdata-state
	 *
	 * @param string $tag_name The uppercase tag name which will close the RCDATA region.
	 * @return bool Whether an end to the RCDATA region was found before the end of the document.
	 */
	private function skip_rcdata( $tag_name ) {
		$html       = $this->html;
		$doc_length = strlen( $html );
		$tag_length = strlen( $tag_name );

		$at = $this->bytes_already_parsed;

		while ( false !== $at && $at < $doc_length ) {
			$at                       = strpos( $this->html, '</', $at );
			$this->tag_name_starts_at = $at;

			// Fail if there is no possible tag closer.
			if ( false === $at || ( $at + $tag_length ) >= $doc_length ) {
				return false;
			}

			$at += 2;

			/*
			 * Find a case-insensitive match to the tag name.
			 *
			 * Because tag names are limited to US-ASCII there is no
			 * need to perform any kind of Unicode normalization when
			 * comparing; any character which could be impacted by such
			 * normalization could not be part of a tag name.
			 */
			for ( $i = 0; $i < $tag_length; $i++ ) {
				$tag_char  = $tag_name[ $i ];
				$html_char = $html[ $at + $i ];

				if ( $html_char !== $tag_char && strtoupper( $html_char ) !== $tag_char ) {
					$at += $i;
					continue 2;
				}
			}

			$at                        += $tag_length;
			$this->bytes_already_parsed = $at;

			if ( $at >= strlen( $html ) ) {
				return false;
			}

			/*
			 * Ensure that the tag name terminates to avoid matching on
			 * substrings of a longer tag name. For example, the sequence
			 * "</textarearug" should not match for "</textarea" even
			 * though "textarea" is found within the text.
			 */
			$c = $html[ $at ];
			if ( ' ' !== $c && "\t" !== $c && "\r" !== $c && "\n" !== $c && '/' !== $c && '>' !== $c ) {
				continue;
			}

			while ( $this->parse_next_attribute() ) {
				continue;
			}

			$at = $this->bytes_already_parsed;
			if ( $at >= strlen( $this->html ) ) {
				return false;
			}

			if ( '>' === $html[ $at ] ) {
				$this->bytes_already_parsed = $at + 1;
				return true;
			}

			if ( $at + 1 >= strlen( $this->html ) ) {
				return false;
			}

			if ( '/' === $html[ $at ] && '>' === $html[ $at + 1 ] ) {
				$this->bytes_already_parsed = $at + 2;
				return true;
			}
		}

		return false;
	}

	/**
	 * Skips contents of script tags.
	 *
	 * @since 6.2.0
	 *
	 * @return bool Whether the script tag was closed before the end of the document.
	 */
	private function skip_script_data() {
		$state      = 'unescaped';
		$html       = $this->html;
		$doc_length = strlen( $html );
		$at         = $this->bytes_already_parsed;

		while ( false !== $at && $at < $doc_length ) {
			$at += strcspn( $html, '-<', $at );

			/*
			 * For all script states a "-->"  transitions
			 * back into the normal unescaped script mode,
			 * even if that's the current state.
			 */
			if (
				$at + 2 < $doc_length &&
				'-' === $html[ $at ] &&
				'-' === $html[ $at + 1 ] &&
				'>' === $html[ $at + 2 ]
			) {
				$at   += 3;
				$state = 'unescaped';
				continue;
			}

			// Everything of interest past here starts with "<".
			if ( $at + 1 >= $doc_length || '<' !== $html[ $at++ ] ) {
				continue;
			}

			/*
			 * Unlike with "-->", the "<!--" only transitions
			 * into the escaped mode if not already there.
			 *
			 * Inside the escaped modes it will be ignored; and
			 * should never break out of the double-escaped
			 * mode and back into the escaped mode.
			 *
			 * While this requires a mode change, it does not
			 * impact the parsing otherwise, so continue
			 * parsing after updating the state.
			 */
			if (
				$at + 2 < $doc_length &&
				'!' === $html[ $at ] &&
				'-' === $html[ $at + 1 ] &&
				'-' === $html[ $at + 2 ]
			) {
				$at   += 3;
				$state = 'unescaped' === $state ? 'escaped' : $state;
				continue;
			}

			if ( '/' === $html[ $at ] ) {
				$closer_potentially_starts_at = $at - 1;
				$is_closing                   = true;
				++$at;
			} else {
				$is_closing = false;
			}

			/*
			 * At this point the only remaining state-changes occur with the
			 * <script> and </script> tags; unless one of these appears next,
			 * proceed scanning to the next potential token in the text.
			 */
			if ( ! (
				$at + 6 < $doc_length &&
				( 's' === $html[ $at ] || 'S' === $html[ $at ] ) &&
				( 'c' === $html[ $at + 1 ] || 'C' === $html[ $at + 1 ] ) &&
				( 'r' === $html[ $at + 2 ] || 'R' === $html[ $at + 2 ] ) &&
				( 'i' === $html[ $at + 3 ] || 'I' === $html[ $at + 3 ] ) &&
				( 'p' === $html[ $at + 4 ] || 'P' === $html[ $at + 4 ] ) &&
				( 't' === $html[ $at + 5 ] || 'T' === $html[ $at + 5 ] )
			) ) {
				++$at;
				continue;
			}

			/*
			 * Ensure that the script tag terminates to avoid matching on
			 * substrings of a non-match. For example, the sequence
			 * "<script123" should not end a script region even though
			 * "<script" is found within the text.
			 */
			if ( $at + 6 >= $doc_length ) {
				continue;
			}
			$at += 6;
			$c   = $html[ $at ];
			if ( ' ' !== $c && "\t" !== $c && "\r" !== $c && "\n" !== $c && '/' !== $c && '>' !== $c ) {
				++$at;
				continue;
			}

			if ( 'escaped' === $state && ! $is_closing ) {
				$state = 'double-escaped';
				continue;
			}

			if ( 'double-escaped' === $state && $is_closing ) {
				$state = 'escaped';
				continue;
			}

			if ( $is_closing ) {
				$this->bytes_already_parsed = $closer_potentially_starts_at;
				$this->tag_name_starts_at   = $closer_potentially_starts_at;
				if ( $this->bytes_already_parsed >= $doc_length ) {
					return false;
				}

				while ( $this->parse_next_attribute() ) {
					continue;
				}

				if ( $this->bytes_already_parsed >= $doc_length ) {
					$this->parser_state = self::STATE_INCOMPLETE_INPUT;

					return false;
				}

				if ( '>' === $html[ $this->bytes_already_parsed ] ) {
					++$this->bytes_already_parsed;
					return true;
				}
			}

			++$at;
		}

		return false;
	}

	/**
	 * Parses the next tag.
	 *
	 * This will find and start parsing the next tag, including
	 * the opening `<`, the potential closer `/`, and the tag
	 * name. It does not parse the attributes or scan to the
	 * closing `>`; these are left for other methods.
	 *
	 * @since 6.2.0
	 * @since 6.2.1 Support abruptly-closed comments, invalid-tag-closer-comments, and empty elements.
	 *
	 * @return bool Whether a tag was found before the end of the document.
	 */
	private function parse_next_tag() {
		$this->after_tag();

		$html       = $this->html;
		$doc_length = strlen( $html );
		$was_at     = $this->bytes_already_parsed;
		$at         = $was_at;

		while ( false !== $at && $at < $doc_length ) {
			$at = strpos( $html, '<', $at );

			/*
			 * This does not imply an incomplete parse; it indicates that there
			 * can be nothing left in the document other than a #text node.
			 */
			if ( false === $at ) {
				$this->parser_state         = self::STATE_TEXT_NODE;
				$this->token_starts_at      = $was_at;
				$this->token_length         = strlen( $html ) - $was_at;
				$this->text_starts_at       = $was_at;
				$this->text_length          = $this->token_length;
				$this->bytes_already_parsed = strlen( $html );
				return true;
			}

			if ( $at > $was_at ) {
				/*
				 * A "<" normally starts a new HTML tag or syntax token, but in cases where the
				 * following character can't produce a valid token, the "<" is instead treated
				 * as plaintext and the parser should skip over it. This avoids a problem when
				 * following earlier practices of typing emoji with text, e.g. "<3". This
				 * should be a heart, not a tag. It's supposed to be rendered, not hidden.
				 *
				 * At this point the parser checks if this is one of those cases and if it is
				 * will continue searching for the next "<" in search of a token boundary.
				 *
				 * @see https://html.spec.whatwg.org/#tag-open-state
				 */
				if ( strlen( $html ) > $at + 1 ) {
					$next_character  = $html[ $at + 1 ];
					$at_another_node = (
						'!' === $next_character ||
						'/' === $next_character ||
						'?' === $next_character ||
						( 'A' <= $next_character && $next_character <= 'Z' ) ||
						( 'a' <= $next_character && $next_character <= 'z' )
					);
					if ( ! $at_another_node ) {
						++$at;
						continue;
					}
				}

				$this->parser_state         = self::STATE_TEXT_NODE;
				$this->token_starts_at      = $was_at;
				$this->token_length         = $at - $was_at;
				$this->text_starts_at       = $was_at;
				$this->text_length          = $this->token_length;
				$this->bytes_already_parsed = $at;
				return true;
			}

			$this->token_starts_at = $at;

			if ( $at + 1 < $doc_length && '/' === $this->html[ $at + 1 ] ) {
				$this->is_closing_tag = true;
				++$at;
			} else {
				$this->is_closing_tag = false;
			}

			/*
			 * HTML tag names must start with [a-zA-Z] otherwise they are not tags.
			 * For example, "<3" is rendered as text, not a tag opener. If at least
			 * one letter follows the "<" then _it is_ a tag, but if the following
			 * character is anything else it _is not a tag_.
			 *
			 * It's not uncommon to find non-tags starting with `<` in an HTML
			 * document, so it's good for performance to make this pre-check before
			 * continuing to attempt to parse a tag name.
			 *
			 * Reference:
			 * * https://html.spec.whatwg.org/multipage/parsing.html#data-state
			 * * https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
			 */
			$tag_name_prefix_length = strspn( $html, 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ', $at + 1 );
			if ( $tag_name_prefix_length > 0 ) {
				++$at;
				$this->parser_state         = self::STATE_MATCHED_TAG;
				$this->tag_name_starts_at   = $at;
				$this->tag_name_length      = $tag_name_prefix_length + strcspn( $html, " \t\f\r\n/>", $at + $tag_name_prefix_length );
				$this->bytes_already_parsed = $at + $this->tag_name_length;
				return true;
			}

			/*
			 * Abort if no tag is found before the end of
			 * the document. There is nothing left to parse.
			 */
			if ( $at + 1 >= $doc_length ) {
				$this->parser_state = self::STATE_INCOMPLETE_INPUT;

				return false;
			}

			/*
			 * `<!` transitions to markup declaration open state
			 * https://html.spec.whatwg.org/multipage/parsing.html#markup-declaration-open-state
			 */
			if ( ! $this->is_closing_tag && '!' === $html[ $at + 1 ] ) {
				/*
				 * `<!--` transitions to a comment state – apply further comment rules.
				 * https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
				 */
				if (
					$doc_length > $at + 3 &&
					'-' === $html[ $at + 2 ] &&
					'-' === $html[ $at + 3 ]
				) {
					$closer_at = $at + 4;
					// If it's not possible to close the comment then there is nothing more to scan.
					if ( $doc_length <= $closer_at ) {
						$this->parser_state = self::STATE_INCOMPLETE_INPUT;

						return false;
					}

					// Abruptly-closed empty comments are a sequence of dashes followed by `>`.
					$span_of_dashes = strspn( $html, '-', $closer_at );
					if ( '>' === $html[ $closer_at + $span_of_dashes ] ) {
						/*
						 * @todo When implementing `set_modifiable_text()` ensure that updates to this token
						 *       don't break the syntax for short comments, e.g. `<!--->`. Unlike other comment
						 *       and bogus comment syntax, these leave no clear insertion point for text and
						 *       they need to be modified specially in order to contain text. E.g. to store
						 *       `?` as the modifiable text, the `<!--->` needs to become `<!--?-->`, which
						 *       involves inserting an additional `-` into the token after the modifiable text.
						 */
						$this->parser_state = self::STATE_COMMENT;
						$this->comment_type = self::COMMENT_AS_ABRUPTLY_CLOSED_COMMENT;
						$this->token_length = $closer_at + $span_of_dashes + 1 - $this->token_starts_at;

						// Only provide modifiable text if the token is long enough to contain it.
						if ( $span_of_dashes >= 2 ) {
							$this->comment_type   = self::COMMENT_AS_HTML_COMMENT;
							$this->text_starts_at = $this->token_starts_at + 4;
							$this->text_length    = $span_of_dashes - 2;
						}

						$this->bytes_already_parsed = $closer_at + $span_of_dashes + 1;
						return true;
					}

					/*
					 * Comments may be closed by either a --> or an invalid --!>.
					 * The first occurrence closes the comment.
					 *
					 * See https://html.spec.whatwg.org/#parse-error-incorrectly-closed-comment
					 */
					--$closer_at; // Pre-increment inside condition below reduces risk of accidental infinite looping.
					while ( ++$closer_at < $doc_length ) {
						$closer_at = strpos( $html, '--', $closer_at );
						if ( false === $closer_at ) {
							$this->parser_state = self::STATE_INCOMPLETE_INPUT;

							return false;
						}

						if ( $closer_at + 2 < $doc_length && '>' === $html[ $closer_at + 2 ] ) {
							$this->parser_state         = self::STATE_COMMENT;
							$this->comment_type         = self::COMMENT_AS_HTML_COMMENT;
							$this->token_length         = $closer_at + 3 - $this->token_starts_at;
							$this->text_starts_at       = $this->token_starts_at + 4;
							$this->text_length          = $closer_at - $this->text_starts_at;
							$this->bytes_already_parsed = $closer_at + 3;
							return true;
						}

						if (
							$closer_at + 3 < $doc_length &&
							'!' === $html[ $closer_at + 2 ] &&
							'>' === $html[ $closer_at + 3 ]
						) {
							$this->parser_state         = self::STATE_COMMENT;
							$this->comment_type         = self::COMMENT_AS_HTML_COMMENT;
							$this->token_length         = $closer_at + 4 - $this->token_starts_at;
							$this->text_starts_at       = $this->token_starts_at + 4;
							$this->text_length          = $closer_at - $this->text_starts_at;
							$this->bytes_already_parsed = $closer_at + 4;
							return true;
						}
					}
				}

				/*
				 * `<!DOCTYPE` transitions to DOCTYPE state – skip to the nearest >
				 * These are ASCII-case-insensitive.
				 * https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
				 */
				if (
					$doc_length > $at + 8 &&
					( 'D' === $html[ $at + 2 ] || 'd' === $html[ $at + 2 ] ) &&
					( 'O' === $html[ $at + 3 ] || 'o' === $html[ $at + 3 ] ) &&
					( 'C' === $html[ $at + 4 ] || 'c' === $html[ $at + 4 ] ) &&
					( 'T' === $html[ $at + 5 ] || 't' === $html[ $at + 5 ] ) &&
					( 'Y' === $html[ $at + 6 ] || 'y' === $html[ $at + 6 ] ) &&
					( 'P' === $html[ $at + 7 ] || 'p' === $html[ $at + 7 ] ) &&
					( 'E' === $html[ $at + 8 ] || 'e' === $html[ $at + 8 ] )
				) {
					$closer_at = strpos( $html, '>', $at + 9 );
					if ( false === $closer_at ) {
						$this->parser_state = self::STATE_INCOMPLETE_INPUT;

						return false;
					}

					$this->parser_state         = self::STATE_DOCTYPE;
					$this->token_length         = $closer_at + 1 - $this->token_starts_at;
					$this->text_starts_at       = $this->token_starts_at + 9;
					$this->text_length          = $closer_at - $this->text_starts_at;
					$this->bytes_already_parsed = $closer_at + 1;
					return true;
				}

				/*
				 * Anything else here is an incorrectly-opened comment and transitions
				 * to the bogus comment state - skip to the nearest >. If no closer is
				 * found then the HTML was truncated inside the markup declaration.
				 */
				$closer_at = strpos( $html, '>', $at + 1 );
				if ( false === $closer_at ) {
					$this->parser_state = self::STATE_INCOMPLETE_INPUT;

					return false;
				}

				$this->parser_state         = self::STATE_COMMENT;
				$this->comment_type         = self::COMMENT_AS_INVALID_HTML;
				$this->token_length         = $closer_at + 1 - $this->token_starts_at;
				$this->text_starts_at       = $this->token_starts_at + 2;
				$this->text_length          = $closer_at - $this->text_starts_at;
				$this->bytes_already_parsed = $closer_at + 1;

				/*
				 * Identify nodes that would be CDATA if HTML had CDATA sections.
				 *
				 * This section must occur after identifying the bogus comment end
				 * because in an HTML parser it will span to the nearest `>`, even
				 * if there's no `]]>` as would be required in an XML document. It
				 * is therefore not possible to parse a CDATA section containing
				 * a `>` in the HTML syntax.
				 *
				 * Inside foreign elements there is a discrepancy between browsers
				 * and the specification on this.
				 *
				 * @todo Track whether the Tag Processor is inside a foreign element
				 *       and require the proper closing `]]>` in those cases.
				 */
				if (
					$this->token_length >= 10 &&
					'[' === $html[ $this->token_starts_at + 2 ] &&
					'C' === $html[ $this->token_starts_at + 3 ] &&
					'D' === $html[ $this->token_starts_at + 4 ] &&
					'A' === $html[ $this->token_starts_at + 5 ] &&
					'T' === $html[ $this->token_starts_at + 6 ] &&
					'A' === $html[ $this->token_starts_at + 7 ] &&
					'[' === $html[ $this->token_starts_at + 8 ] &&
					']' === $html[ $closer_at - 1 ] &&
					']' === $html[ $closer_at - 2 ]
				) {
					$this->parser_state    = self::STATE_COMMENT;
					$this->comment_type    = self::COMMENT_AS_CDATA_LOOKALIKE;
					$this->text_starts_at += 7;
					$this->text_length    -= 9;
				}

				return true;
			}

			/*
			 * </> is a missing end tag name, which is ignored.
			 *
			 * This was also known as the "presumptuous empty tag"
			 * in early discussions as it was proposed to close
			 * the nearest previous opening tag.
			 *
			 * See https://html.spec.whatwg.org/#parse-error-missing-end-tag-name
			 */
			if ( '>' === $html[ $at + 1 ] ) {
				// `<>` is interpreted as plaintext.
				if ( ! $this->is_closing_tag ) {
					++$at;
					continue;
				}

				$this->parser_state         = self::STATE_PRESUMPTUOUS_TAG;
				$this->token_length         = $at + 2 - $this->token_starts_at;
				$this->bytes_already_parsed = $at + 2;
				return true;
			}

			/*
			 * `<?` transitions to a bogus comment state – skip to the nearest >
			 * See https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
			 */
			if ( ! $this->is_closing_tag && '?' === $html[ $at + 1 ] ) {
				$closer_at = strpos( $html, '>', $at + 2 );
				if ( false === $closer_at ) {
					$this->parser_state = self::STATE_INCOMPLETE_INPUT;

					return false;
				}

				$this->parser_state         = self::STATE_COMMENT;
				$this->comment_type         = self::COMMENT_AS_INVALID_HTML;
				$this->token_length         = $closer_at + 1 - $this->token_starts_at;
				$this->text_starts_at       = $this->token_starts_at + 2;
				$this->text_length          = $closer_at - $this->text_starts_at;
				$this->bytes_already_parsed = $closer_at + 1;

				/*
				 * Identify a Processing Instruction node were HTML to have them.
				 *
				 * This section must occur after identifying the bogus comment end
				 * because in an HTML parser it will span to the nearest `>`, even
				 * if there's no `?>` as would be required in an XML document. It
				 * is therefore not possible to parse a Processing Instruction node
				 * containing a `>` in the HTML syntax.
				 *
				 * XML allows for more target names, but this code only identifies
				 * those with ASCII-representable target names. This means that it
				 * may identify some Processing Instruction nodes as bogus comments,
				 * but it will not misinterpret the HTML structure. By limiting the
				 * identification to these target names the Tag Processor can avoid
				 * the need to start parsing UTF-8 sequences.
				 *
				 * > NameStartChar ::= ":" | [A-Z] | "_" | [a-z] | [#xC0-#xD6] | [#xD8-#xF6] | [#xF8-#x2FF] |
				 *                     [#x370-#x37D] | [#x37F-#x1FFF] | [#x200C-#x200D] | [#x2070-#x218F] |
				 *                     [#x2C00-#x2FEF] | [#x3001-#xD7FF] | [#xF900-#xFDCF] | [#xFDF0-#xFFFD] |
				 *                     [#x10000-#xEFFFF]
				 * > NameChar      ::= NameStartChar | "-" | "." | [0-9] | #xB7 | [#x0300-#x036F] | [#x203F-#x2040]
				 *
				 * @see https://www.w3.org/TR/2006/REC-xml11-20060816/#NT-PITarget
				 */
				if ( $this->token_length >= 5 && '?' === $html[ $closer_at - 1 ] ) {
					$comment_text     = substr( $html, $this->token_starts_at + 2, $this->token_length - 4 );
					$pi_target_length = strspn( $comment_text, 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ:_' );

					if ( 0 < $pi_target_length ) {
						$pi_target_length += strspn( $comment_text, 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789:_-.', $pi_target_length );

						$this->comment_type       = self::COMMENT_AS_PI_NODE_LOOKALIKE;
						$this->tag_name_starts_at = $this->token_starts_at + 2;
						$this->tag_name_length    = $pi_target_length;
						$this->text_starts_at    += $pi_target_length;
						$this->text_length       -= $pi_target_length + 1;
					}
				}

				return true;
			}

			/*
			 * If a non-alpha starts the tag name in a tag closer it's a comment.
			 * Find the first `>`, which closes the comment.
			 *
			 * This parser classifies these particular comments as special "funky comments"
			 * which are made available for further processing.
			 *
			 * See https://html.spec.whatwg.org/#parse-error-invalid-first-character-of-tag-name
			 */
			if ( $this->is_closing_tag ) {
				// No chance of finding a closer.
				if ( $at + 3 > $doc_length ) {
					return false;
				}

				$closer_at = strpos( $html, '>', $at + 2 );
				if ( false === $closer_at ) {
					$this->parser_state = self::STATE_INCOMPLETE_INPUT;

					return false;
				}

				$this->parser_state         = self::STATE_FUNKY_COMMENT;
				$this->token_length         = $closer_at + 1 - $this->token_starts_at;
				$this->text_starts_at       = $this->token_starts_at + 2;
				$this->text_length          = $closer_at - $this->text_starts_at;
				$this->bytes_already_parsed = $closer_at + 1;
				return true;
			}

			++$at;
		}

		return false;
	}

	/**
	 * Parses the next attribute.
	 *
	 * @since 6.2.0
	 *
	 * @return bool Whether an attribute was found before the end of the document.
	 */
	private function parse_next_attribute() {
		// Skip whitespace and slashes.
		$this->bytes_already_parsed += strspn( $this->html, " \t\f\r\n/", $this->bytes_already_parsed );
		if ( $this->bytes_already_parsed >= strlen( $this->html ) ) {
			$this->parser_state = self::STATE_INCOMPLETE_INPUT;

			return false;
		}

		/*
		 * Treat the equal sign as a part of the attribute
		 * name if it is the first encountered byte.
		 *
		 * @see https://html.spec.whatwg.org/multipage/parsing.html#before-attribute-name-state
		 */
		$name_length = '=' === $this->html[ $this->bytes_already_parsed ]
			? 1 + strcspn( $this->html, "=/> \t\f\r\n", $this->bytes_already_parsed + 1 )
			: strcspn( $this->html, "=/> \t\f\r\n", $this->bytes_already_parsed );

		// No attribute, just tag closer.
		if ( 0 === $name_length || $this->bytes_already_parsed + $name_length >= strlen( $this->html ) ) {
			return false;
		}

		$attribute_start             = $this->bytes_already_parsed;
		$attribute_name              = substr( $this->html, $attribute_start, $name_length );
		$this->bytes_already_parsed += $name_length;
		if ( $this->bytes_already_parsed >= strlen( $this->html ) ) {
			$this->parser_state = self::STATE_INCOMPLETE_INPUT;

			return false;
		}

		$this->skip_whitespace();
		if ( $this->bytes_already_parsed >= strlen( $this->html ) ) {
			$this->parser_state = self::STATE_INCOMPLETE_INPUT;

			return false;
		}

		$has_value = '=' === $this->html[ $this->bytes_already_parsed ];
		if ( $has_value ) {
			++$this->bytes_already_parsed;
			$this->skip_whitespace();
			if ( $this->bytes_already_parsed >= strlen( $this->html ) ) {
				$this->parser_state = self::STATE_INCOMPLETE_INPUT;

				return false;
			}

			switch ( $this->html[ $this->bytes_already_parsed ] ) {
				case "'":
				case '"':
					$quote                      = $this->html[ $this->bytes_already_parsed ];
					$value_start                = $this->bytes_already_parsed + 1;
					$value_length               = strcspn( $this->html, $quote, $value_start );
					$attribute_end              = $value_start + $value_length + 1;
					$this->bytes_already_parsed = $attribute_end;
					break;

				default:
					$value_start                = $this->bytes_already_parsed;
					$value_length               = strcspn( $this->html, "> \t\f\r\n", $value_start );
					$attribute_end              = $value_start + $value_length;
					$this->bytes_already_parsed = $attribute_end;
			}
		} else {
			$value_start   = $this->bytes_already_parsed;
			$value_length  = 0;
			$attribute_end = $attribute_start + $name_length;
		}

		if ( $attribute_end >= strlen( $this->html ) ) {
			$this->parser_state = self::STATE_INCOMPLETE_INPUT;

			return false;
		}

		if ( $this->is_closing_tag ) {
			return true;
		}

		/*
		 * > There must never be two or more attributes on
		 * > the same start tag whose names are an ASCII
		 * > case-insensitive match for each other.
		 *     - HTML 5 spec
		 *
		 * @see https://html.spec.whatwg.org/multipage/syntax.html#attributes-2:ascii-case-insensitive
		 */
		$comparable_name = strtolower( $attribute_name );

		// If an attribute is listed many times, only use the first declaration and ignore the rest.
		if ( ! array_key_exists( $comparable_name, $this->attributes ) ) {
			$this->attributes[ $comparable_name ] = new WP_HTML_Attribute_Token(
				$attribute_name,
				$value_start,
				$value_length,
				$attribute_start,
				$attribute_end - $attribute_start,
				! $has_value
			);

			return true;
		}

		/*
		 * Track the duplicate attributes so if we remove it, all disappear together.
		 *
		 * While `$this->duplicated_attributes` could always be stored as an `array()`,
		 * which would simplify the logic here, storing a `null` and only allocating
		 * an array when encountering duplicates avoids needless allocations in the
		 * normative case of parsing tags with no duplicate attributes.
		 */
		$duplicate_span = new WP_HTML_Span( $attribute_start, $attribute_end - $attribute_start );
		if ( null === $this->duplicate_attributes ) {
			$this->duplicate_attributes = array( $comparable_name => array( $duplicate_span ) );
		} elseif ( ! array_key_exists( $comparable_name, $this->duplicate_attributes ) ) {
			$this->duplicate_attributes[ $comparable_name ] = array( $duplicate_span );
		} else {
			$this->duplicate_attributes[ $comparable_name ][] = $duplicate_span;
		}

		return true;
	}

	/**
	 * Move the internal cursor past any immediate successive whitespace.
	 *
	 * @since 6.2.0
	 */
	private function skip_whitespace() {
		$this->bytes_already_parsed += strspn( $this->html, " \t\f\r\n", $this->bytes_already_parsed );
	}

	/**
	 * Applies attribute updates and cleans up once a tag is fully parsed.
	 *
	 * @since 6.2.0
	 */
	private function after_tag() {
		/*
		 * There could be lexical updates enqueued for an attribute that
		 * also exists on the next tag. In order to avoid conflating the
		 * attributes across the two tags, lexical updates with names
		 * need to be flushed to raw lexical updates.
		 */
		$this->class_name_updates_to_attributes_updates();

		/*
		 * Purge updates if there are too many. The actual count isn't
		 * scientific, but a few values from 100 to a few thousand were
		 * tests to find a practically-useful limit.
		 *
		 * If the update queue grows too big, then the Tag Processor
		 * will spend more time iterating through them and lose the
		 * efficiency gains of deferring applying them.
		 */
		if ( 1000 < count( $this->lexical_updates ) ) {
			$this->get_updated_html();
		}

		foreach ( $this->lexical_updates as $name => $update ) {
			/*
			 * Any updates appearing after the cursor should be applied
			 * before proceeding, otherwise they may be overlooked.
			 */
			if ( $update->start >= $this->bytes_already_parsed ) {
				$this->get_updated_html();
				break;
			}

			if ( is_int( $name ) ) {
				continue;
			}

			$this->lexical_updates[] = $update;
			unset( $this->lexical_updates[ $name ] );
		}

		$this->token_starts_at      = null;
		$this->token_length         = null;
		$this->tag_name_starts_at   = null;
		$this->tag_name_length      = null;
		$this->text_starts_at       = 0;
		$this->text_length          = 0;
		$this->is_closing_tag       = null;
		$this->attributes           = array();
		$this->comment_type         = null;
		$this->duplicate_attributes = null;
	}

	/**
	 * Converts class name updates into tag attributes updates
	 * (they are accumulated in different data formats for performance).
	 *
	 * @since 6.2.0
	 *
	 * @see WP_HTML_Tag_Processor::$lexical_updates
	 * @see WP_HTML_Tag_Processor::$classname_updates
	 */
	private function class_name_updates_to_attributes_updates() {
		if ( count( $this->classname_updates ) === 0 ) {
			return;
		}

		$existing_class = $this->get_enqueued_attribute_value( 'class' );
		if ( null === $existing_class || true === $existing_class ) {
			$existing_class = '';
		}

		if ( false === $existing_class && isset( $this->attributes['class'] ) ) {
			$existing_class = substr(
				$this->html,
				$this->attributes['class']->value_starts_at,
				$this->attributes['class']->value_length
			);
		}

		if ( false === $existing_class ) {
			$existing_class = '';
		}

		/**
		 * Updated "class" attribute value.
		 *
		 * This is incrementally built while scanning through the existing class
		 * attribute, skipping removed classes on the way, and then appending
		 * added classes at the end. Only when finished processing will the
		 * value contain the final new value.

		 * @var string $class
		 */
		$class = '';

		/**
		 * Tracks the cursor position in the existing
		 * class attribute value while parsing.
		 *
		 * @var int $at
		 */
		$at = 0;

		/**
		 * Indicates if there's any need to modify the existing class attribute.
		 *
		 * If a call to `add_class()` and `remove_class()` wouldn't impact
		 * the `class` attribute value then there's no need to rebuild it.
		 * For example, when adding a class that's already present or
		 * removing one that isn't.
		 *
		 * This flag enables a performance optimization when none of the enqueued
		 * class updates would impact the `class` attribute; namely, that the
		 * processor can continue without modifying the input document, as if
		 * none of the `add_class()` or `remove_class()` calls had been made.
		 *
		 * This flag is set upon the first change that requires a string update.
		 *
		 * @var bool $modified
		 */
		$modified = false;

		// Remove unwanted classes by only copying the new ones.
		$existing_class_length = strlen( $existing_class );
		while ( $at < $existing_class_length ) {
			// Skip to the first non-whitespace character.
			$ws_at     = $at;
			$ws_length = strspn( $existing_class, " \t\f\r\n", $ws_at );
			$at       += $ws_length;

			// Capture the class name – it's everything until the next whitespace.
			$name_length = strcspn( $existing_class, " \t\f\r\n", $at );
			if ( 0 === $name_length ) {
				// If no more class names are found then that's the end.
				break;
			}

			$name = substr( $existing_class, $at, $name_length );
			$at  += $name_length;

			// If this class is marked for removal, start processing the next one.
			$remove_class = (
				isset( $this->classname_updates[ $name ] ) &&
				self::REMOVE_CLASS === $this->classname_updates[ $name ]
			);

			// If a class has already been seen then skip it; it should not be added twice.
			if ( ! $remove_class ) {
				$this->classname_updates[ $name ] = self::SKIP_CLASS;
			}

			if ( $remove_class ) {
				$modified = true;
				continue;
			}

			/*
			 * Otherwise, append it to the new "class" attribute value.
			 *
			 * There are options for handling whitespace between tags.
			 * Preserving the existing whitespace produces fewer changes
			 * to the HTML content and should clarify the before/after
			 * content when debugging the modified output.
			 *
			 * This approach contrasts normalizing the inter-class
			 * whitespace to a single space, which might appear cleaner
			 * in the output HTML but produce a noisier change.
			 */
			$class .= substr( $existing_class, $ws_at, $ws_length );
			$class .= $name;
		}

		// Add new classes by appending those which haven't already been seen.
		foreach ( $this->classname_updates as $name => $operation ) {
			if ( self::ADD_CLASS === $operation ) {
				$modified = true;

				$class .= strlen( $class ) > 0 ? ' ' : '';
				$class .= $name;
			}
		}

		$this->classname_updates = array();
		if ( ! $modified ) {
			return;
		}

		if ( strlen( $class ) > 0 ) {
			$this->set_attribute( 'class', $class );
		} else {
			$this->remove_attribute( 'class' );
		}
	}

	/**
	 * Applies attribute updates to HTML document.
	 *
	 * @since 6.2.0
	 * @since 6.2.1 Accumulates shift for internal cursor and passed pointer.
	 * @since 6.3.0 Invalidate any bookmarks whose targets are overwritten.
	 *
	 * @param int $shift_this_point Accumulate and return shift for this position.
	 * @return int How many bytes the given pointer moved in response to the updates.
	 */
	private function apply_attributes_updates( $shift_this_point ) {
		if ( ! count( $this->lexical_updates ) ) {
			return 0;
		}

		$accumulated_shift_for_given_point = 0;

		/*
		 * Attribute updates can be enqueued in any order but updates
		 * to the document must occur in lexical order; that is, each
		 * replacement must be made before all others which follow it
		 * at later string indices in the input document.
		 *
		 * Sorting avoid making out-of-order replacements which
		 * can lead to mangled output, partially-duplicated
		 * attributes, and overwritten attributes.
		 */
		usort( $this->lexical_updates, array( self::class, 'sort_start_ascending' ) );

		$bytes_already_copied = 0;
		$output_buffer        = '';
		foreach ( $this->lexical_updates as $diff ) {
			$shift = strlen( $diff->text ) - $diff->length;

			// Adjust the cursor position by however much an update affects it.
			if ( $diff->start < $this->bytes_already_parsed ) {
				$this->bytes_already_parsed += $shift;
			}

			// Accumulate shift of the given pointer within this function call.
			if ( $diff->start <= $shift_this_point ) {
				$accumulated_shift_for_given_point += $shift;
			}

			$output_buffer       .= substr( $this->html, $bytes_already_copied, $diff->start - $bytes_already_copied );
			$output_buffer       .= $diff->text;
			$bytes_already_copied = $diff->start + $diff->length;
		}

		$this->html = $output_buffer . substr( $this->html, $bytes_already_copied );

		/*
		 * Adjust bookmark locations to account for how the text
		 * replacements adjust offsets in the input document.
		 */
		foreach ( $this->bookmarks as $bookmark_name => $bookmark ) {
			$bookmark_end = $bookmark->start + $bookmark->length;

			/*
			 * Each lexical update which appears before the bookmark's endpoints
			 * might shift the offsets for those endpoints. Loop through each change
			 * and accumulate the total shift for each bookmark, then apply that
			 * shift after tallying the full delta.
			 */
			$head_delta = 0;
			$tail_delta = 0;

			foreach ( $this->lexical_updates as $diff ) {
				$diff_end = $diff->start + $diff->length;

				if ( $bookmark->start < $diff->start && $bookmark_end < $diff->start ) {
					break;
				}

				if ( $bookmark->start >= $diff->start && $bookmark_end < $diff_end ) {
					$this->release_bookmark( $bookmark_name );
					continue 2;
				}

				$delta = strlen( $diff->text ) - $diff->length;

				if ( $bookmark->start >= $diff->start ) {
					$head_delta += $delta;
				}

				if ( $bookmark_end >= $diff_end ) {
					$tail_delta += $delta;
				}
			}

			$bookmark->start  += $head_delta;
			$bookmark->length += $tail_delta - $head_delta;
		}

		$this->lexical_updates = array();

		return $accumulated_shift_for_given_point;
	}

	/**
	 * Checks whether a bookmark with the given name exists.
	 *
	 * @since 6.3.0
	 *
	 * @param string $bookmark_name Name to identify a bookmark that potentially exists.
	 * @return bool Whether that bookmark exists.
	 */
	public function has_bookmark( $bookmark_name ) {
		return array_key_exists( $bookmark_name, $this->bookmarks );
	}

	/**
	 * Move the internal cursor in the Tag Processor to a given bookmark's location.
	 *
	 * In order to prevent accidental infinite loops, there's a
	 * maximum limit on the number of times seek() can be called.
	 *
	 * @since 6.2.0
	 *
	 * @param string $bookmark_name Jump to the place in the document identified by this bookmark name.
	 * @return bool Whether the internal cursor was successfully moved to the bookmark's location.
	 */
	public function seek( $bookmark_name ) {
		if ( ! array_key_exists( $bookmark_name, $this->bookmarks ) ) {
			_doing_it_wrong(
				__METHOD__,
				__( 'Unknown bookmark name.' ),
				'6.2.0'
			);
			return false;
		}

		if ( ++$this->seek_count > static::MAX_SEEK_OPS ) {
			_doing_it_wrong(
				__METHOD__,
				__( 'Too many calls to seek() - this can lead to performance issues.' ),
				'6.2.0'
			);
			return false;
		}

		// Flush out any pending updates to the document.
		$this->get_updated_html();

		// Point this tag processor before the sought tag opener and consume it.
		$this->bytes_already_parsed = $this->bookmarks[ $bookmark_name ]->start;
		$this->parser_state         = self::STATE_READY;
		return $this->next_token();
	}

	/**
	 * Compare two WP_HTML_Text_Replacement objects.
	 *
	 * @since 6.2.0
	 *
	 * @param WP_HTML_Text_Replacement $a First attribute update.
	 * @param WP_HTML_Text_Replacement $b Second attribute update.
	 * @return int Comparison value for string order.
	 */
	private static function sort_start_ascending( $a, $b ) {
		$by_start = $a->start - $b->start;
		if ( 0 !== $by_start ) {
			return $by_start;
		}

		$by_text = isset( $a->text, $b->text ) ? strcmp( $a->text, $b->text ) : 0;
		if ( 0 !== $by_text ) {
			return $by_text;
		}

		/*
		 * This code should be unreachable, because it implies the two replacements
		 * start at the same location and contain the same text.
		 */
		return $a->length - $b->length;
	}

	/**
	 * Return the enqueued value for a given attribute, if one exists.
	 *
	 * Enqueued updates can take different data types:
	 *  - If an update is enqueued and is boolean, the return will be `true`
	 *  - If an update is otherwise enqueued, the return will be the string value of that update.
	 *  - If an attribute is enqueued to be removed, the return will be `null` to indicate that.
	 *  - If no updates are enqueued, the return will be `false` to differentiate from "removed."
	 *
	 * @since 6.2.0
	 *
	 * @param string $comparable_name The attribute name in its comparable form.
	 * @return string|boolean|null Value of enqueued update if present, otherwise false.
	 */
	private function get_enqueued_attribute_value( $comparable_name ) {
		if ( self::STATE_MATCHED_TAG !== $this->parser_state ) {
			return false;
		}

		if ( ! isset( $this->lexical_updates[ $comparable_name ] ) ) {
			return false;
		}

		$enqueued_text = $this->lexical_updates[ $comparable_name ]->text;

		// Removed attributes erase the entire span.
		if ( '' === $enqueued_text ) {
			return null;
		}

		/*
		 * Boolean attribute updates are just the attribute name without a corresponding value.
		 *
		 * This value might differ from the given comparable name in that there could be leading
		 * or trailing whitespace, and that the casing follows the name given in `set_attribute`.
		 *
		 * Example:
		 *
		 *     $p->set_attribute( 'data-TEST-id', 'update' );
		 *     'update' === $p->get_enqueued_attribute_value( 'data-test-id' );
		 *
		 * Detect this difference based on the absence of the `=`, which _must_ exist in any
		 * attribute containing a value, e.g. `<input type="text" enabled />`.
		 *                                            ¹           ²
		 *                                       1. Attribute with a string value.
		 *                                       2. Boolean attribute whose value is `true`.
		 */
		$equals_at = strpos( $enqueued_text, '=' );
		if ( false === $equals_at ) {
			return true;
		}

		/*
		 * Finally, a normal update's value will appear after the `=` and
		 * be double-quoted, as performed incidentally by `set_attribute`.
		 *
		 * e.g. `type="text"`
		 *           ¹²    ³
		 *        1. Equals is here.
		 *        2. Double-quoting starts one after the equals sign.
		 *        3. Double-quoting ends at the last character in the update.
		 */
		$enqueued_value = substr( $enqueued_text, $equals_at + 2, -1 );
		return WP_HTML_Decoder::decode_attribute( $enqueued_value );
	}

	/**
	 * Returns the value of a requested attribute from a matched tag opener if that attribute exists.
	 *
	 * Example:
	 *
	 *     $p = new WP_HTML_Tag_Processor( '<div enabled class="test" data-test-id="14">Test</div>' );
	 *     $p->next_tag( array( 'class_name' => 'test' ) ) === true;
	 *     $p->get_attribute( 'data-test-id' ) === '14';
	 *     $p->get_attribute( 'enabled' ) === true;
	 *     $p->get_attribute( 'aria-label' ) === null;
	 *
	 *     $p->next_tag() === false;
	 *     $p->get_attribute( 'class' ) === null;
	 *
	 * @since 6.2.0
	 *
	 * @param string $name Name of attribute whose value is requested.
	 * @return string|true|null Value of attribute or `null` if not available. Boolean attributes return `true`.
	 */
	public function get_attribute( $name ) {
		if ( self::STATE_MATCHED_TAG !== $this->parser_state ) {
			return null;
		}

		$comparable = strtolower( $name );

		/*
		 * For every attribute other than `class` it's possible to perform a quick check if
		 * there's an enqueued lexical update whose value takes priority over what's found in
		 * the input document.
		 *
		 * The `class` attribute is special though because of the exposed helpers `add_class`
		 * and `remove_class`. These form a builder for the `class` attribute, so an additional
		 * check for enqueued class changes is required in addition to the check for any enqueued
		 * attribute values. If any exist, those enqueued class changes must first be flushed out
		 * into an attribute value update.
		 */
		if ( 'class' === $name ) {
			$this->class_name_updates_to_attributes_updates();
		}

		// Return any enqueued attribute value updates if they exist.
		$enqueued_value = $this->get_enqueued_attribute_value( $comparable );
		if ( false !== $enqueued_value ) {
			return $enqueued_value;
		}

		if ( ! isset( $this->attributes[ $comparable ] ) ) {
			return null;
		}

		$attribute = $this->attributes[ $comparable ];

		/*
		 * This flag distinguishes an attribute with no value
		 * from an attribute with an empty string value. For
		 * unquoted attributes this could look very similar.
		 * It refers to whether an `=` follows the name.
		 *
		 * e.g. <div boolean-attribute empty-attribute=></div>
		 *           ¹                 ²
		 *        1. Attribute `boolean-attribute` is `true`.
		 *        2. Attribute `empty-attribute` is `""`.
		 */
		if ( true === $attribute->is_true ) {
			return true;
		}

		$raw_value = substr( $this->html, $attribute->value_starts_at, $attribute->value_length );

		return WP_HTML_Decoder::decode_attribute( $raw_value );
	}

	/**
	 * Gets lowercase names of all attributes matching a given prefix in the current tag.
	 *
	 * Note that matching is case-insensitive. This is in accordance with the spec:
	 *
	 * > There must never be two or more attributes on
	 * > the same start tag whose names are an ASCII
	 * > case-insensitive match for each other.
	 *     - HTML 5 spec
	 *
	 * Example:
	 *
	 *     $p = new WP_HTML_Tag_Processor( '<div data-ENABLED class="test" DATA-test-id="14">Test</div>' );
	 *     $p->next_tag( array( 'class_name' => 'test' ) ) === true;
	 *     $p->get_attribute_names_with_prefix( 'data-' ) === array( 'data-enabled', 'data-test-id' );
	 *
	 *     $p->next_tag() === false;
	 *     $p->get_attribute_names_with_prefix( 'data-' ) === null;
	 *
	 * @since 6.2.0
	 *
	 * @see https://html.spec.whatwg.org/multipage/syntax.html#attributes-2:ascii-case-insensitive
	 *
	 * @param string $prefix Prefix of requested attribute names.
	 * @return array|null List of attribute names, or `null` when no tag opener is matched.
	 */
	public function get_attribute_names_with_prefix( $prefix ) {
		if (
			self::STATE_MATCHED_TAG !== $this->parser_state ||
			$this->is_closing_tag
		) {
			return null;
		}

		$comparable = strtolower( $prefix );

		$matches = array();
		foreach ( array_keys( $this->attributes ) as $attr_name ) {
			if ( str_starts_with( $attr_name, $comparable ) ) {
				$matches[] = $attr_name;
			}
		}
		return $matches;
	}

	/**
	 * Returns the uppercase name of the matched tag.
	 *
	 * Example:
	 *
	 *     $p = new WP_HTML_Tag_Processor( '<div class="test">Test</div>' );
	 *     $p->next_tag() === true;
	 *     $p->get_tag() === 'DIV';
	 *
	 *     $p->next_tag() === false;
	 *     $p->get_tag() === null;
	 *
	 * @since 6.2.0
	 *
	 * @return string|null Name of currently matched tag in input HTML, or `null` if none found.
	 */
	public function get_tag() {
		if ( null === $this->tag_name_starts_at ) {
			return null;
		}

		$tag_name = substr( $this->html, $this->tag_name_starts_at, $this->tag_name_length );

		if ( self::STATE_MATCHED_TAG === $this->parser_state ) {
			return strtoupper( $tag_name );
		}

		if (
			self::STATE_COMMENT === $this->parser_state &&
			self::COMMENT_AS_PI_NODE_LOOKALIKE === $this->get_comment_type()
		) {
			return $tag_name;
		}

		return null;
	}

	/**
	 * Indicates if the currently matched tag contains the self-closing flag.
	 *
	 * No HTML elements ought to have the self-closing flag and for those, the self-closing
	 * flag will be ignored. For void elements this is benign because they "self close"
	 * automatically. For non-void HTML elements though problems will appear if someone
	 * intends to use a self-closing element in place of that element with an empty body.
	 * For HTML foreign elements and custom elements the self-closing flag determines if
	 * they self-close or not.
	 *
	 * This function does not determine if a tag is self-closing,
	 * but only if the self-closing flag is present in the syntax.
	 *
	 * @since 6.3.0
	 *
	 * @return bool Whether the currently matched tag contains the self-closing flag.
	 */
	public function has_self_closing_flag() {
		if ( self::STATE_MATCHED_TAG !== $this->parser_state ) {
			return false;
		}

		/*
		 * The self-closing flag is the solidus at the _end_ of the tag, not the beginning.
		 *
		 * Example:
		 *
		 *     <figure />
		 *             ^ this appears one character before the end of the closing ">".
		 */
		return '/' === $this->html[ $this->token_starts_at + $this->token_length - 2 ];
	}

	/**
	 * Indicates if the current tag token is a tag closer.
	 *
	 * Example:
	 *
	 *     $p = new WP_HTML_Tag_Processor( '<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 6.2.0
	 *
	 * @return bool Whether the current tag is a tag closer.
	 */
	public function is_tag_closer() {
		return (
			self::STATE_MATCHED_TAG === $this->parser_state &&
			$this->is_closing_tag
		);
	}

	/**
	 * Indicates the kind of matched token, if any.
	 *
	 * This differs from `get_token_name()` in that it always
	 * returns a static string indicating the type, whereas
	 * `get_token_name()` may return values derived from the
	 * token itself, such as a tag name or processing
	 * instruction tag.
	 *
	 * Possible values:
	 *  - `#tag` when matched on a tag.
	 *  - `#text` when matched on a text node.
	 *  - `#cdata-section` when matched on a CDATA node.
	 *  - `#comment` when matched on a comment.
	 *  - `#doctype` when matched on a DOCTYPE declaration.
	 *  - `#presumptuous-tag` when matched on an empty tag closer.
	 *  - `#funky-comment` when matched on a funky comment.
	 *
	 * @since 6.5.0
	 *
	 * @return string|null What kind of token is matched, or null.
	 */
	public function get_token_type() {
		switch ( $this->parser_state ) {
			case self::STATE_MATCHED_TAG:
				return '#tag';

			case self::STATE_DOCTYPE:
				return '#doctype';

			default:
				return $this->get_token_name();
		}
	}

	/**
	 * Returns the node name represented by the token.
	 *
	 * This matches the DOM API value `nodeName`. Some values
	 * are static, such as `#text` for a text node, while others
	 * are dynamically generated from the token itself.
	 *
	 * Dynamic names:
	 *  - Uppercase tag name for tag matches.
	 *  - `html` for DOCTYPE declarations.
	 *
	 * Note that if the Tag Processor is not matched on a token
	 * then this function will return `null`, either because it
	 * hasn't yet found a token or because it reached the end
	 * of the document without matching a token.
	 *
	 * @since 6.5.0
	 *
	 * @return string|null Name of the matched token.
	 */
	public function get_token_name() {
		switch ( $this->parser_state ) {
			case self::STATE_MATCHED_TAG:
				return $this->get_tag();

			case self::STATE_TEXT_NODE:
				return '#text';

			case self::STATE_CDATA_NODE:
				return '#cdata-section';

			case self::STATE_COMMENT:
				return '#comment';

			case self::STATE_DOCTYPE:
				return 'html';

			case self::STATE_PRESUMPTUOUS_TAG:
				return '#presumptuous-tag';

			case self::STATE_FUNKY_COMMENT:
				return '#funky-comment';
		}

		return null;
	}

	/**
	 * Indicates what kind of comment produced the comment node.
	 *
	 * Because there are different kinds of HTML syntax which produce
	 * comments, the Tag Processor tracks and exposes this as a type
	 * for the comment. Nominally only regular HTML comments exist as
	 * they are commonly known, but a number of unrelated syntax errors
	 * also produce comments.
	 *
	 * @see self::COMMENT_AS_ABRUPTLY_CLOSED_COMMENT
	 * @see self::COMMENT_AS_CDATA_LOOKALIKE
	 * @see self::COMMENT_AS_INVALID_HTML
	 * @see self::COMMENT_AS_HTML_COMMENT
	 * @see self::COMMENT_AS_PI_NODE_LOOKALIKE
	 *
	 * @since 6.5.0
	 *
	 * @return string|null
	 */
	public function get_comment_type() {
		if ( self::STATE_COMMENT !== $this->parser_state ) {
			return null;
		}

		return $this->comment_type;
	}

	/**
	 * Returns the modifiable text for a matched token, or an empty string.
	 *
	 * Modifiable text is text content that may be read and changed without
	 * changing the HTML structure of the document around it. This includes
	 * the contents of `#text` nodes in the HTML as well as the inner
	 * contents of HTML comments, Processing Instructions, and others, even
	 * though these nodes aren't part of a parsed DOM tree. They also contain
	 * the contents of SCRIPT and STYLE tags, of TEXTAREA tags, and of any
	 * other section in an HTML document which cannot contain HTML markup (DATA).
	 *
	 * If a token has no modifiable text then an empty string is returned to
	 * avoid needless crashing or type errors. An empty string does not mean
	 * that a token has modifiable text, and a token with modifiable text may
	 * have an empty string (e.g. a comment with no contents).
	 *
	 * @since 6.5.0
	 *
	 * @return string
	 */
	public function get_modifiable_text() {
		if ( null === $this->text_starts_at ) {
			return '';
		}

		$text = substr( $this->html, $this->text_starts_at, $this->text_length );

		// Comment data is not decoded.
		if (
			self::STATE_CDATA_NODE === $this->parser_state ||
			self::STATE_COMMENT === $this->parser_state ||
			self::STATE_DOCTYPE === $this->parser_state ||
			self::STATE_FUNKY_COMMENT === $this->parser_state
		) {
			return $text;
		}

		$tag_name = $this->get_tag();
		if (
			// Script data is not decoded.
			'SCRIPT' === $tag_name ||

			// RAWTEXT data is not decoded.
			'IFRAME' === $tag_name ||
			'NOEMBED' === $tag_name ||
			'NOFRAMES' === $tag_name ||
			'STYLE' === $tag_name ||
			'XMP' === $tag_name
		) {
			return $text;
		}

		$decoded = WP_HTML_Decoder::decode_text_node( $text );

		/*
		 * TEXTAREA skips a leading newline, but this newline may appear not only as the
		 * literal character `\n`, but also as a character reference, such as in the
		 * following markup: `<textarea>&#x0a;Content</textarea>`.
		 *
		 * For these cases it's important to first decode the text content before checking
		 * for a leading newline and removing it.
		 */
		if (
			self::STATE_MATCHED_TAG === $this->parser_state &&
			'TEXTAREA' === $tag_name &&
			strlen( $decoded ) > 0 &&
			"\n" === $decoded[0]
		) {
			return substr( $decoded, 1 );
		}

		return $decoded;
	}

	/**
	 * Updates or creates a new attribute on the currently matched tag with the passed value.
	 *
	 * For boolean attributes special handling is provided:
	 *  - When `true` is passed as the value, then only the attribute name is added to the tag.
	 *  - When `false` is passed, the attribute gets removed if it existed before.
	 *
	 * For string attributes, the value is escaped using the `esc_attr` function.
	 *
	 * @since 6.2.0
	 * @since 6.2.1 Fix: Only create a single update for multiple calls with case-variant attribute names.
	 *
	 * @param string      $name  The attribute name to target.
	 * @param string|bool $value The new attribute value.
	 * @return bool Whether an attribute value was set.
	 */
	public function set_attribute( $name, $value ) {
		if (
			self::STATE_MATCHED_TAG !== $this->parser_state ||
			$this->is_closing_tag
		) {
			return false;
		}

		/*
		 * WordPress rejects more characters than are strictly forbidden
		 * in HTML5. This is to prevent additional security risks deeper
		 * in the WordPress and plugin stack. Specifically the
		 * less-than (<) greater-than (>) and ampersand (&) aren't allowed.
		 *
		 * The use of a PCRE match enables looking for specific Unicode
		 * code points without writing a UTF-8 decoder. Whereas scanning
		 * for one-byte characters is trivial (with `strcspn`), scanning
		 * for the longer byte sequences would be more complicated. Given
		 * that this shouldn't be in the hot path for execution, it's a
		 * reasonable compromise in efficiency without introducing a
		 * noticeable impact on the overall system.
		 *
		 * @see https://html.spec.whatwg.org/#attributes-2
		 *
		 * @todo As the only regex pattern maybe we should take it out?
		 *       Are Unicode patterns available broadly in Core?
		 */
		if ( preg_match(
			'~[' .
				// Syntax-like characters.
				'"\'>&</ =' .
				// Control characters.
				'\x{00}-\x{1F}' .
				// HTML noncharacters.
				'\x{FDD0}-\x{FDEF}' .
				'\x{FFFE}\x{FFFF}\x{1FFFE}\x{1FFFF}\x{2FFFE}\x{2FFFF}\x{3FFFE}\x{3FFFF}' .
				'\x{4FFFE}\x{4FFFF}\x{5FFFE}\x{5FFFF}\x{6FFFE}\x{6FFFF}\x{7FFFE}\x{7FFFF}' .
				'\x{8FFFE}\x{8FFFF}\x{9FFFE}\x{9FFFF}\x{AFFFE}\x{AFFFF}\x{BFFFE}\x{BFFFF}' .
				'\x{CFFFE}\x{CFFFF}\x{DFFFE}\x{DFFFF}\x{EFFFE}\x{EFFFF}\x{FFFFE}\x{FFFFF}' .
				'\x{10FFFE}\x{10FFFF}' .
			']~Ssu',
			$name
		) ) {
			_doing_it_wrong(
				__METHOD__,
				__( 'Invalid attribute name.' ),
				'6.2.0'
			);

			return false;
		}

		/*
		 * > The values "true" and "false" are not allowed on boolean attributes.
		 * > To represent a false value, the attribute has to be omitted altogether.
		 *     - HTML5 spec, https://html.spec.whatwg.org/#boolean-attributes
		 */
		if ( false === $value ) {
			return $this->remove_attribute( $name );
		}

		if ( true === $value ) {
			$updated_attribute = $name;
		} else {
			$comparable_name = strtolower( $name );

			/*
			 * Escape URL attributes.
			 *
			 * @see https://html.spec.whatwg.org/#attributes-3
			 */
			$escaped_new_value = in_array( $comparable_name, wp_kses_uri_attributes() ) ? esc_url( $value ) : esc_attr( $value );

			// If the escaping functions wiped out the update, reject it and indicate it was rejected.
			if ( '' === $escaped_new_value && '' !== $value ) {
				return false;
			}

			$updated_attribute = "{$name}=\"{$escaped_new_value}\"";
		}

		/*
		 * > There must never be two or more attributes on
		 * > the same start tag whose names are an ASCII
		 * > case-insensitive match for each other.
		 *     - HTML 5 spec
		 *
		 * @see https://html.spec.whatwg.org/multipage/syntax.html#attributes-2:ascii-case-insensitive
		 */
		$comparable_name = strtolower( $name );

		if ( isset( $this->attributes[ $comparable_name ] ) ) {
			/*
			 * Update an existing attribute.
			 *
			 * Example – set attribute id to "new" in <div id="initial_id" />:
			 *
			 *     <div id="initial_id"/>
			 *          ^-------------^
			 *          start         end
			 *     replacement: `id="new"`
			 *
			 *     Result: <div id="new"/>
			 */
			$existing_attribute                        = $this->attributes[ $comparable_name ];
			$this->lexical_updates[ $comparable_name ] = new WP_HTML_Text_Replacement(
				$existing_attribute->start,
				$existing_attribute->length,
				$updated_attribute
			);
		} else {
			/*
			 * Create a new attribute at the tag's name end.
			 *
			 * Example – add attribute id="new" to <div />:
			 *
			 *     <div/>
			 *         ^
			 *         start and end
			 *     replacement: ` id="new"`
			 *
			 *     Result: <div id="new"/>
			 */
			$this->lexical_updates[ $comparable_name ] = new WP_HTML_Text_Replacement(
				$this->tag_name_starts_at + $this->tag_name_length,
				0,
				' ' . $updated_attribute
			);
		}

		/*
		 * Any calls to update the `class` attribute directly should wipe out any
		 * enqueued class changes from `add_class` and `remove_class`.
		 */
		if ( 'class' === $comparable_name && ! empty( $this->classname_updates ) ) {
			$this->classname_updates = array();
		}

		return true;
	}

	/**
	 * Remove an attribute from the currently-matched tag.
	 *
	 * @since 6.2.0
	 *
	 * @param string $name The attribute name to remove.
	 * @return bool Whether an attribute was removed.
	 */
	public function remove_attribute( $name ) {
		if (
			self::STATE_MATCHED_TAG !== $this->parser_state ||
			$this->is_closing_tag
		) {
			return false;
		}

		/*
		 * > There must never be two or more attributes on
		 * > the same start tag whose names are an ASCII
		 * > case-insensitive match for each other.
		 *     - HTML 5 spec
		 *
		 * @see https://html.spec.whatwg.org/multipage/syntax.html#attributes-2:ascii-case-insensitive
		 */
		$name = strtolower( $name );

		/*
		 * Any calls to update the `class` attribute directly should wipe out any
		 * enqueued class changes from `add_class` and `remove_class`.
		 */
		if ( 'class' === $name && count( $this->classname_updates ) !== 0 ) {
			$this->classname_updates = array();
		}

		/*
		 * If updating an attribute that didn't exist in the input
		 * document, then remove the enqueued update and move on.
		 *
		 * For example, this might occur when calling `remove_attribute()`
		 * after calling `set_attribute()` for the same attribute
		 * and when that attribute wasn't originally present.
		 */
		if ( ! isset( $this->attributes[ $name ] ) ) {
			if ( isset( $this->lexical_updates[ $name ] ) ) {
				unset( $this->lexical_updates[ $name ] );
			}
			return false;
		}

		/*
		 * Removes an existing tag attribute.
		 *
		 * Example – remove the attribute id from <div id="main"/>:
		 *    <div id="initial_id"/>
		 *         ^-------------^
		 *         start         end
		 *    replacement: ``
		 *
		 *    Result: <div />
		 */
		$this->lexical_updates[ $name ] = new WP_HTML_Text_Replacement(
			$this->attributes[ $name ]->start,
			$this->attributes[ $name ]->length,
			''
		);

		// Removes any duplicated attributes if they were also present.
		if ( null !== $this->duplicate_attributes && array_key_exists( $name, $this->duplicate_attributes ) ) {
			foreach ( $this->duplicate_attributes[ $name ] as $attribute_token ) {
				$this->lexical_updates[] = new WP_HTML_Text_Replacement(
					$attribute_token->start,
					$attribute_token->length,
					''
				);
			}
		}

		return true;
	}

	/**
	 * Adds a new class name to the currently matched tag.
	 *
	 * @since 6.2.0
	 *
	 * @param string $class_name The class name to add.
	 * @return bool Whether the class was set to be added.
	 */
	public function add_class( $class_name ) {
		if (
			self::STATE_MATCHED_TAG !== $this->parser_state ||
			$this->is_closing_tag
		) {
			return false;
		}

		$this->classname_updates[ $class_name ] = self::ADD_CLASS;

		return true;
	}

	/**
	 * Removes a class name from the currently matched tag.
	 *
	 * @since 6.2.0
	 *
	 * @param string $class_name The class name to remove.
	 * @return bool Whether the class was set to be removed.
	 */
	public function remove_class( $class_name ) {
		if (
			self::STATE_MATCHED_TAG !== $this->parser_state ||
			$this->is_closing_tag
		) {
			return false;
		}

		if ( null !== $this->tag_name_starts_at ) {
			$this->classname_updates[ $class_name ] = self::REMOVE_CLASS;
		}

		return true;
	}

	/**
	 * Returns the string representation of the HTML Tag Processor.
	 *
	 * @since 6.2.0
	 *
	 * @see WP_HTML_Tag_Processor::get_updated_html()
	 *
	 * @return string The processed HTML.
	 */
	public function __toString() {
		return $this->get_updated_html();
	}

	/**
	 * Returns the string representation of the HTML Tag Processor.
	 *
	 * @since 6.2.0
	 * @since 6.2.1 Shifts the internal cursor corresponding to the applied updates.
	 * @since 6.4.0 No longer calls subclass method `next_tag()` after updating HTML.
	 *
	 * @return string The processed HTML.
	 */
	public function get_updated_html() {
		$requires_no_updating = 0 === count( $this->classname_updates ) && 0 === count( $this->lexical_updates );

		/*
		 * When there is nothing more to update and nothing has already been
		 * updated, return the original document and avoid a string copy.
		 */
		if ( $requires_no_updating ) {
			return $this->html;
		}

		/*
		 * Keep track of the position right before the current tag. This will
		 * be necessary for reparsing the current tag after updating the HTML.
		 */
		$before_current_tag = $this->token_starts_at ?? 0;

		/*
		 * 1. Apply the enqueued edits and update all the pointers to reflect those changes.
		 */
		$this->class_name_updates_to_attributes_updates();
		$before_current_tag += $this->apply_attributes_updates( $before_current_tag );

		/*
		 * 2. Rewind to before the current tag and reparse to get updated attributes.
		 *
		 * At this point the internal cursor points to the end of the tag name.
		 * Rewind before the tag name starts so that it's as if the cursor didn't
		 * move; a call to `next_tag()` will reparse the recently-updated attributes
		 * and additional calls to modify the attributes will apply at this same
		 * location, but in order to avoid issues with subclasses that might add
		 * behaviors to `next_tag()`, the internal methods should be called here
		 * instead.
		 *
		 * It's important to note that in this specific place there will be no change
		 * because the processor was already at a tag when this was called and it's
		 * rewinding only to the beginning of this very tag before reprocessing it
		 * and its attributes.
		 *
		 * <p>Previous HTML<em>More HTML</em></p>
		 *                 ↑  │ back up by the length of the tag name plus the opening <
		 *                 └←─┘ back up by strlen("em") + 1 ==> 3
		 */
		$this->bytes_already_parsed = $before_current_tag;
		$this->base_class_next_token();

		return $this->html;
	}

	/**
	 * Parses tag query input into internal search criteria.
	 *
	 * @since 6.2.0
	 *
	 * @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 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 class name to match.
	 *     @type string      $tag_closers  "visit" or "skip": whether to stop on tag closers, e.g. </div>.
	 * }
	 */
	private function parse_query( $query ) {
		if ( null !== $query && $query === $this->last_query ) {
			return;
		}

		$this->last_query          = $query;
		$this->sought_tag_name     = null;
		$this->sought_class_name   = null;
		$this->sought_match_offset = 1;
		$this->stop_on_tag_closers = false;

		// A single string value means "find the tag of this name".
		if ( is_string( $query ) ) {
			$this->sought_tag_name = $query;
			return;
		}

		// An empty query parameter applies no restrictions on the search.
		if ( null === $query ) {
			return;
		}

		// If not using the string interface, an associative array is required.
		if ( ! is_array( $query ) ) {
			_doing_it_wrong(
				__METHOD__,
				__( 'The query argument must be an array or a tag name.' ),
				'6.2.0'
			);
			return;
		}

		if ( isset( $query['tag_name'] ) && is_string( $query['tag_name'] ) ) {
			$this->sought_tag_name = $query['tag_name'];
		}

		if ( isset( $query['class_name'] ) && is_string( $query['class_name'] ) ) {
			$this->sought_class_name = $query['class_name'];
		}

		if ( isset( $query['match_offset'] ) && is_int( $query['match_offset'] ) && 0 < $query['match_offset'] ) {
			$this->sought_match_offset = $query['match_offset'];
		}

		if ( isset( $query['tag_closers'] ) ) {
			$this->stop_on_tag_closers = 'visit' === $query['tag_closers'];
		}
	}


	/**
	 * Checks whether a given tag and its attributes match the search criteria.
	 *
	 * @since 6.2.0
	 *
	 * @return bool Whether the given tag and its attribute match the search criteria.
	 */
	private function matches() {
		if ( $this->is_closing_tag && ! $this->stop_on_tag_closers ) {
			return false;
		}

		// Does the tag name match the requested tag name in a case-insensitive manner?
		if ( null !== $this->sought_tag_name ) {
			/*
			 * String (byte) length lookup is fast. If they aren't the
			 * same length then they can't be the same string values.
			 */
			if ( strlen( $this->sought_tag_name ) !== $this->tag_name_length ) {
				return false;
			}

			/*
			 * Check each character to determine if they are the same.
			 * Defer calls to `strtoupper()` to avoid them when possible.
			 * Calling `strcasecmp()` here tested slowed than comparing each
			 * character, so unless benchmarks show otherwise, it should
			 * not be used.
			 *
			 * It's expected that most of the time that this runs, a
			 * lower-case tag name will be supplied and the input will
			 * contain lower-case tag names, thus normally bypassing
			 * the case comparison code.
			 */
			for ( $i = 0; $i < $this->tag_name_length; $i++ ) {
				$html_char = $this->html[ $this->tag_name_starts_at + $i ];
				$tag_char  = $this->sought_tag_name[ $i ];

				if ( $html_char !== $tag_char && strtoupper( $html_char ) !== $tag_char ) {
					return false;
				}
			}
		}

		if ( null !== $this->sought_class_name && ! $this->has_class( $this->sought_class_name ) ) {
			return false;
		}

		return true;
	}

	/**
	 * Parser Ready State.
	 *
	 * Indicates that the parser is ready to run and waiting for a state transition.
	 * It may not have started yet, or it may have just finished parsing a token and
	 * is ready to find the next one.
	 *
	 * @since 6.5.0
	 *
	 * @access private
	 */
	const STATE_READY = 'STATE_READY';

	/**
	 * Parser Complete State.
	 *
	 * Indicates that the parser has reached the end of the document and there is
	 * nothing left to scan. It finished parsing the last token completely.
	 *
	 * @since 6.5.0
	 *
	 * @access private
	 */
	const STATE_COMPLETE = 'STATE_COMPLETE';

	/**
	 * Parser Incomplete Input State.
	 *
	 * Indicates that the parser has reached the end of the document before finishing
	 * a token. It started parsing a token but there is a possibility that the input
	 * HTML document was truncated in the middle of a token.
	 *
	 * The parser is reset at the start of the incomplete token and has paused. There
	 * is nothing more than can be scanned unless provided a more complete document.
	 *
	 * @since 6.5.0
	 *
	 * @access private
	 */
	const STATE_INCOMPLETE_INPUT = 'STATE_INCOMPLETE_INPUT';

	/**
	 * Parser Matched Tag State.
	 *
	 * Indicates that the parser has found an HTML tag and it's possible to get
	 * the tag name and read or modify its attributes (if it's not a closing tag).
	 *
	 * @since 6.5.0
	 *
	 * @access private
	 */
	const STATE_MATCHED_TAG = 'STATE_MATCHED_TAG';

	/**
	 * Parser Text Node State.
	 *
	 * Indicates that the parser has found a text node and it's possible
	 * to read and modify that text.
	 *
	 * @since 6.5.0
	 *
	 * @access private
	 */
	const STATE_TEXT_NODE = 'STATE_TEXT_NODE';

	/**
	 * Parser CDATA Node State.
	 *
	 * Indicates that the parser has found a CDATA node and it's possible
	 * to read and modify its modifiable text. Note that in HTML there are
	 * no CDATA nodes outside of foreign content (SVG and MathML). Outside
	 * of foreign content, they are treated as HTML comments.
	 *
	 * @since 6.5.0
	 *
	 * @access private
	 */
	const STATE_CDATA_NODE = 'STATE_CDATA_NODE';

	/**
	 * Indicates that the parser has found an HTML comment and it's
	 * possible to read and modify its modifiable text.
	 *
	 * @since 6.5.0
	 *
	 * @access private
	 */
	const STATE_COMMENT = 'STATE_COMMENT';

	/**
	 * Indicates that the parser has found a DOCTYPE node and it's
	 * possible to read and modify its modifiable text.
	 *
	 * @since 6.5.0
	 *
	 * @access private
	 */
	const STATE_DOCTYPE = 'STATE_DOCTYPE';

	/**
	 * Indicates that the parser has found an empty tag closer `</>`.
	 *
	 * Note that in HTML there are no empty tag closers, and they
	 * are ignored. Nonetheless, the Tag Processor still
	 * recognizes them as they appear in the HTML stream.
	 *
	 * These were historically discussed as a "presumptuous tag
	 * closer," which would close the nearest open tag, but were
	 * dismissed in favor of explicitly-closing tags.
	 *
	 * @since 6.5.0
	 *
	 * @access private
	 */
	const STATE_PRESUMPTUOUS_TAG = 'STATE_PRESUMPTUOUS_TAG';

	/**
	 * Indicates that the parser has found a "funky comment"
	 * and it's possible to read and modify its modifiable text.
	 *
	 * Example:
	 *
	 *     </%url>
	 *     </{"wp-bit":"query/post-author"}>
	 *     </2>
	 *
	 * Funky comments are tag closers with invalid tag names. Note
	 * that in HTML these are turn into bogus comments. Nonetheless,
	 * the Tag Processor recognizes them in a stream of HTML and
	 * exposes them for inspection and modification.
	 *
	 * @since 6.5.0
	 *
	 * @access private
	 */
	const STATE_FUNKY_COMMENT = 'STATE_WP_FUNKY';

	/**
	 * Indicates that a comment was created when encountering abruptly-closed HTML comment.
	 *
	 * Example:
	 *
	 *     <!-->
	 *     <!--->
	 *
	 * @since 6.5.0
	 */
	const COMMENT_AS_ABRUPTLY_CLOSED_COMMENT = 'COMMENT_AS_ABRUPTLY_CLOSED_COMMENT';

	/**
	 * Indicates that a comment would be parsed as a CDATA node,
	 * were HTML to allow CDATA nodes outside of foreign content.
	 *
	 * Example:
	 *
	 *     <![CDATA[This is a CDATA node.]]>
	 *
	 * This is an HTML comment, but it looks like a CDATA node.
	 *
	 * @since 6.5.0
	 */
	const COMMENT_AS_CDATA_LOOKALIKE = 'COMMENT_AS_CDATA_LOOKALIKE';

	/**
	 * Indicates that a comment was created when encountering
	 * normative HTML comment syntax.
	 *
	 * Example:
	 *
	 *     <!-- this is a comment -->
	 *
	 * @since 6.5.0
	 */
	const COMMENT_AS_HTML_COMMENT = 'COMMENT_AS_HTML_COMMENT';

	/**
	 * Indicates that a comment would be parsed as a Processing
	 * Instruction node, were they to exist within HTML.
	 *
	 * Example:
	 *
	 *     <?wp __( 'Like' ) ?>
	 *
	 * This is an HTML comment, but it looks like a CDATA node.
	 *
	 * @since 6.5.0
	 */
	const COMMENT_AS_PI_NODE_LOOKALIKE = 'COMMENT_AS_PI_NODE_LOOKALIKE';

	/**
	 * Indicates that a comment was created when encountering invalid
	 * HTML input, a so-called "bogus comment."
	 *
	 * Example:
	 *
	 *     <?nothing special>
	 *     <!{nothing special}>
	 *
	 * @since 6.5.0
	 */
	const COMMENT_AS_INVALID_HTML = 'COMMENT_AS_INVALID_HTML';
}