HTML API: Add select handling

src/wp-includes/html-api/class-wp-html-open-elements.php

@@ -144,6 +144,28 @@ public function current_node() {
 		return $current_node ? $current_node : null;
 	}
 
+	/**
+	 * Checks if the node at the top of the stack matches provided node name.
+	 *
+	 * @example
+	 *   // Is the current node a text node:
+	 *   $stack->current_node_is( '#text' );
+	 *
+	 *   // Is the current node a DIV element:
+	 *   $stack->current_node_is( 'DIV' );
+	 *
+	 * @since 6.7.0
+	 *
+	 * @param  string $node_name The node name to match. Provide a tag name for tags or a
+	 *                           token name for other types of tokens.
+	 * @return bool True if there are nodes on the stack and the top node has
+	 *              a matching node_name.
+	 */
+	public function current_node_is( string $node_name ): bool {
+		$current_node = end( $this->stack );
+		return $current_node && $current_node->node_name === $node_name;
+	}
+
 	/**
 	 * Returns whether an element is in a specific scope.
 	 *
@@ -269,19 +291,34 @@ public function has_element_in_table_scope( $tag_name ) {
 	/**
 	 * Returns whether a particular element is in select scope.
 	 *
-	 * @since 6.4.0
+	 * @since 6.4.0 Stub implementation (throws).
+	 * @since 6.7.0 Full implementation.
 	 *
 	 * @see https://html.spec.whatwg.org/#has-an-element-in-select-scope
 	 *
-	 * @throws WP_HTML_Unsupported_Exception Always until this function is implemented.
+	 * > The stack of open elements is said to have a particular element in select scope when it has
+	 * > that element in the specific scope consisting of all element types except the following:
+	 * > - optgroup in the HTML namespace
+	 * > - option in the HTML namespace
 	 *
 	 * @param string $tag_name Name of tag to check.
 	 * @return bool Whether given element is in scope.
 	 */
 	public function has_element_in_select_scope( $tag_name ) {
-		throw new WP_HTML_Unsupported_Exception( 'Cannot process elements depending on select scope.' );
+		foreach ( $this->walk_up() as $node ) {
+			if ( $node->node_name === $tag_name ) {
+				return true;
+			}
 
-		return false; // The linter requires this unreachable code until the function is implemented and can return.
+			if (
+				'OPTION' !== $node->node_name &&
+				'OPTGROUP' !== $node->node_name
+			) {
+				return false;
+			}
+		}
+
+		return false;
 	}
 
 	/**

src/wp-includes/html-api/class-wp-html-processor.php

@@ -101,7 +101,7 @@
  *
  *  - Containers: ADDRESS, BLOCKQUOTE, DETAILS, DIALOG, DIV, FOOTER, HEADER, MAIN, MENU, SPAN, SUMMARY.
  *  - Custom elements: All custom elements are supported. :)
- *  - Form elements: BUTTON, DATALIST, FIELDSET, INPUT, LABEL, LEGEND, METER, PROGRESS, SEARCH.
+ *  - Form elements: BUTTON, DATALIST, FIELDSET, INPUT, LABEL, LEGEND, METER, OPTGROUP, OPTION, PROGRESS, SEARCH, SELECT.
  *  - Formatting elements: B, BIG, CODE, EM, FONT, I, PRE, SMALL, STRIKE, STRONG, TT, U, WBR.
  *  - Heading elements: H1, H2, H3, H4, H5, H6, HGROUP.
  *  - Links: A.
@@ -757,6 +757,12 @@ public function step( $node_to_process = self::PROCESS_NEXT_NODE ) {
 				case WP_HTML_Processor_State::INSERTION_MODE_IN_BODY:
 					return $this->step_in_body();
 
+				case WP_HTML_Processor_State::INSERTION_MODE_IN_HEAD:
+					return $this->step_in_head();
+
+				case WP_HTML_Processor_State::INSERTION_MODE_IN_SELECT:
+					return $this->step_in_select();
+
 				default:
 					$this->last_error = self::ERROR_UNSUPPORTED;
 					throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." );
@@ -1336,6 +1342,51 @@ private function step_in_body() {
 			case '+TRACK':
 				$this->insert_html_element( $this->state->current_token );
 				return true;
+
+			/*
+			 * > A start tag whose tag name is "select"
+			 */
+			case '+SELECT':
+				$this->reconstruct_active_formatting_elements();
+				$this->insert_html_element( $this->state->current_token );
+				$this->state->frameset_ok = false;
+
+				/*
+				 * If the insertion mode is one of
+				 * - "in table"
+				 * - "in caption"
+				 * - "in table body"
+				 * - "in row"
+				 * - "in cell"
+				 * then switch the insertion mode to "in select in table"
+				 *
+				 * Otherwise, switch the insertion mode to "in select".
+				 */
+				switch ( $this->state->insertion_mode ) {
+					case WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE:
+					case WP_HTML_Processor_State::INSERTION_MODE_IN_CAPTION:
+					case WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY:
+					case WP_HTML_Processor_State::INSERTION_MODE_IN_ROW:
+					case WP_HTML_Processor_State::INSERTION_MODE_IN_CELL:
+						$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_SELECT_IN_TABLE;
+						break;
+					default:
+						$this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_SELECT;
+						break;
+				}
+				return true;
+
+			/*
+			 * > A start tag whose tag name is one of: "optgroup", "option"
+			 */
+			case '+OPTGROUP':
+			case '+OPTION':
+				if ( $this->state->stack_of_open_elements->current_node_is( 'OPTION' ) ) {
+					$this->state->stack_of_open_elements->pop();
+				}
+				$this->reconstruct_active_formatting_elements();
+				$this->insert_html_element( $this->state->current_token );
+				return true;
 		}
 
 		/*
@@ -1378,16 +1429,13 @@ private function step_in_body() {
 			case 'NOFRAMES':
 			case 'NOSCRIPT':
 			case 'OBJECT':
-			case 'OPTGROUP':
-			case 'OPTION':
 			case 'PLAINTEXT':
 			case 'RB':
 			case 'RP':
 			case 'RT':
 			case 'RTC':
 			case 'SARCASM':
 			case 'SCRIPT':
-			case 'SELECT':
 			case 'STYLE':
 			case 'SVG':
 			case 'TABLE':
@@ -1448,6 +1496,184 @@ private function step_in_body() {
 		}
 	}
 
+	/*
+	 * Parses next element in the 'in head' insertion mode.
+	 *
+	 * This internal function performs the 'in head' insertion mode
+	 * logic for the generalized WP_HTML_Processor::step() function.
+	 *
+	 * @since 6.7.0
+	 *
+	 * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
+	 *
+	 * @see https://html.spec.whatwg.org/multipage/parsing.html#parsing-main-inhead
+	 * @see WP_HTML_Processor::step
+	 *
+	 * @return bool Whether an element was found.
+	 */
+	private function step_in_head() {
+		$this->last_error = self::ERROR_UNSUPPORTED;
+		throw new WP_HTML_Unsupported_Exception( "No support for parsing in the '{$this->state->insertion_mode}' state." );
+	}
+
+	/**
+	 * Parses next element in the 'in select' insertion mode.
+	 *
+	 * This internal function performs the 'in select' insertion mode
+	 * logic for the generalized WP_HTML_Processor::step() function.
+	 *
+	 * @since 6.7.0
+	 *
+	 * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
+	 *
+	 * @see https://html.spec.whatwg.org/multipage/parsing.html#parsing-main-inselect
+	 * @see WP_HTML_Processor::step
+	 *
+	 * @return bool Whether an element was found.
+	 */
+	private function step_in_select() {
+		$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 ) {
+			/*
+			 * > Any other character token
+			 */
+			case '#text':
+				$this->insert_html_element( $this->state->current_token );
+				return true;
+
+			/*
+			 * > A comment token
+			 */
+			case '#comment':
+			case '#funky-comment':
+			case '#presumptuous-tag':
+				$this->insert_html_element( $this->state->current_token );
+				return true;
+
+			/*
+			 * > A DOCTYPE token
+			 */
+			case 'html':
+				// Parse error. Ignore the token.
+				return $this->step();
+
+			/*
+			 * > A start tag whose tag name is "html"
+			 */
+			case '+HTML':
+				return $this->step_in_body();
+
+			/*
+			 * > A start tag whose tag name is "option"
+			 */
+			case '+OPTION':
+				if ( $this->state->stack_of_open_elements->current_node_is( 'OPTION' ) ) {
+					$this->state->stack_of_open_elements->pop();
+				}
+				$this->insert_html_element( $this->state->current_token );
+				return true;
+
+			/*
+			 * > A start tag whose tag name is "optgroup"
+			 * > A start tag whose tag name is "hr"
+			 *
+			 * These rules are identical except for the treatment of the self-closing flag and
+			 * the subsequent pop of the HR void element, all of which is handled elsewhere in the processor.
+			 */
+			case '+OPTGROUP':
+			case '+HR':
+				if ( $this->state->stack_of_open_elements->current_node_is( 'OPTION' ) ) {
+					$this->state->stack_of_open_elements->pop();
+				}
+
+				if ( $this->state->stack_of_open_elements->current_node_is( 'OPTGROUP' ) ) {
+					$this->state->stack_of_open_elements->pop();
+				}
+
+				$this->insert_html_element( $this->state->current_token );
+				return true;
+
+			/*
+			 * > An end tag whose tag name is "optgroup"
+			 */
+			case '-OPTGROUP':
+				$current_node = $this->state->stack_of_open_elements->current_node();
+				if ( $current_node && 'OPTION' === $current_node->node_name ) {
+					foreach ( $this->state->stack_of_open_elements->walk_up( $current_node ) as $parent ) {
+						break;
+					}
+					if ( $parent && 'OPTGROUP' === $parent->node_name ) {
+						$this->state->stack_of_open_elements->pop();
+					}
+				}
+
+				if ( $this->state->stack_of_open_elements->current_node_is( 'OPTGROUP' ) ) {
+					$this->state->stack_of_open_elements->pop();
+					return true;
+				}
+				// Parse error: ignore the token.
+				return $this->step();
+
+			/*
+			 * > An end tag whose tag name is "option"
+			 */
+			case '-OPTION':
+				if ( $this->state->stack_of_open_elements->current_node_is( 'OPTION' ) ) {
+					$this->state->stack_of_open_elements->pop();
+					return true;
+				}
+				// Parse error: ignore the token.
+				return $this->step();
+
+			/*
+			 * > An end tag whose tag name is "select"
+			 * > A start tag whose tag name is "select"
+			 */
+			case '-SELECT':
+			case '+SELECT':
+				if ( ! $this->state->stack_of_open_elements->has_element_in_select_scope( 'SELECT' ) ) {
+					return $this->step();
+				}
+				$this->state->stack_of_open_elements->pop_until( 'SELECT' );
+				$this->state->stack_of_open_elements->pop();
+				$this->reset_insertion_mode();
+				return true;
+
+			/*
+			 * > A start tag whose tag name is one of: "input", "keygen", "textarea"
+			 */
+			case '+INPUT':
+			case '+KEYGEN':
+			case '+TEXTAREA':
+				// Parse error.
+				if ( ! $this->state->stack_of_open_elements->has_element_in_select_scope( 'SELECT' ) ) {
+					return $this->step();
+				}
+				$this->state->stack_of_open_elements->pop_until( 'SELECT' );
+				$this->reset_insertion_mode();
+				return $this->step( self::REPROCESS_CURRENT_NODE );
+
+			/*
+			 * > A start tag whose tag name is one of: "script", "template"
+			 * > An end tag whose tag name is "template"
+			 */
+			case '+SCRIPT':
+			case '+TEMPLATE':
+			case '-TEMPLATE':
+				return $this->step_in_head();
+		}
+
+		/*
+		 * > Anything else
+		 * >   Parse error: ignore the token.
+		 */
+		return $this->step();
+	}
+
 	/*
 	 * Internal helpers
 	 */
@@ -2036,6 +2262,7 @@ private function close_a_p_element() {
 	 * Closes elements that have implied end tags.
 	 *
 	 * @since 6.4.0
+	 * @since 6.7.0 Support "option" and "optgroup".
 	 *
 	 * @see https://html.spec.whatwg.org/#generate-implied-end-tags
 	 *
@@ -2046,6 +2273,8 @@ private function generate_implied_end_tags( $except_for_this_element = null ) {
 			'DD',
 			'DT',
 			'LI',
+			'OPTGROUP',
+			'OPTION',
 			'P',
 		);
 
@@ -2074,6 +2303,8 @@ private function generate_implied_end_tags_thoroughly() {
 			'DD',
 			'DT',
 			'LI',
+			'OPTGROUP',
+			'OPTION',
 			'P',
 		);
 

tests/phpunit/tests/html-api/wpHtmlProcessor.php

@@ -406,16 +406,13 @@ public static function data_unsupported_special_in_body_tags() {
 			'NOFRAMES'  => array( 'NOFRAMES' ),
 			'NOSCRIPT'  => array( 'NOSCRIPT' ),
 			'OBJECT'    => array( 'OBJECT' ),
-			'OPTGROUP'  => array( 'OPTGROUP' ),
-			'OPTION'    => array( 'OPTION' ),
 			'PLAINTEXT' => array( 'PLAINTEXT' ),
 			'RB'        => array( 'RB' ),
 			'RP'        => array( 'RP' ),
 			'RT'        => array( 'RT' ),
 			'RTC'       => array( 'RTC' ),
 			'SARCASM'   => array( 'SARCASM' ),
 			'SCRIPT'    => array( 'SCRIPT' ),
-			'SELECT'    => array( 'SELECT' ),
 			'STYLE'     => array( 'STYLE' ),
 			'SVG'       => array( 'SVG' ),
 			'TABLE'     => array( 'TABLE' ),