WP_HTML_Processor::step_before_html(): bool

Source

/**
 * Escapes decoded text for HTML serialization.
 *
 * Use for:
 * - Attribute values.
 * - Text in ordinary (data-state) elements and in the RCDATA elements
 *   (TITLE and TEXTAREA).
 * - Text in foreign content (elements not in the HTML namespace).
 *
 * Do not use for text in the RAWTEXT elements (STYLE, XMP, IFRAME,
 * NOEMBED, NOFRAMES), HTML SCRIPT elements, or PLAINTEXT elements,
 * whose contents serialize without escaping.
 *
 * @since 7.1.0
 * @ignore
 *
 * @param string $text Decoded text to escape.
 * @return string Escaped text.
 */
private static function escape_text_for_serialization( string $text ): string {
	$text = htmlspecialchars( $text, ENT_QUOTES | ENT_SUBSTITUTE | ENT_HTML5, 'UTF-8' );

	$text = str_replace( "\r", '
', $text );

	return str_replace( "\x00", "\u{FFFD}", $text );
}

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

	switch ( $op ) {
		/*
		 * > A character token that is one of U+0009 CHARACTER TABULATION,
		 * > U+000A LINE FEED (LF), U+000C FORM FEED (FF),
		 * > U+000D CARRIAGE RETURN (CR), or U+0020 SPACE
		 *
		 * Parse error: ignore the token.
		 */
		case '#text':
			if ( parent::TEXT_IS_WHITESPACE === $this->text_node_classification ) {
				return $this->step();
			}
			goto initial_anything_else;
			break;

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

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

View all references View on Trac View on GitHub