WP_HTML_Processor::step_in_head(): bool

Source

	 */
	before_html_anything_else:
	$this->insert_virtual_node( 'HTML' );
	$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_BEFORE_HEAD;
	return $this->step( self::REPROCESS_CURRENT_NODE );
}

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

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

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

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

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

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

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

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

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

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

			goto in_head_anything_else;
			break;

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

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

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

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

			// All following conditions depend on "tentative" encoding confidence.
			if ( 'tentative' !== $this->state->encoding_confidence ) {
				return true;
			}

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

			/*
			 * >   - Otherwise, if the element has an http-equiv attribute whose value is
			 * >     an ASCII case-insensitive match for the string "Content-Type", and
			 * >     the element has a content attribute, and applying the algorithm for

View all references View on Trac View on GitHub